mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-25 15:55:40 +07:00
fda85ce912
In the time between rxe_send has finished and skb destructor
called, the QP's ref count might be 0, leading to a possible
QP destruction. This will lead to a kernel panic when the destructor
dereferences the QP.
The operation of incrementing QP ref count at rxe_send and decrementing
from skb destructor will prevent this crash.
BUG: unable to handle kernel NULL pointer dereference at 000000000000072c
IP: [<ffffffffa05df765>] rxe_skb_tx_dtor+0x15/0x50 [rdma_rxe]
PGD 0 [16240.211178]
Oops: 0002 [#1] SMP
CPU: 3 PID: 0 Comm: swapper/3 Tainted: G OE 4.9.0-mlnx #1
Hardware name: Red Hat KVM, BIOS Bochs 01/01/2011
task: ffff88042d6b1480 task.stack: ffffc90001904000
RIP: 0010:[<ffffffffa05df765>] [<ffffffffa05df765>] rxe_skb_tx_dtor+0x15/0x50 [rdma_rxe]
RSP: 0018:ffff88043fcc3df0 EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff880429684700 RCX: ffff88042d248200
RDX: 00000000ffffffff RSI: 00000000fffffe01 RDI: ffff880429684700
RBP: ffff88043fcc3e00 R08: ffff88043fcda240 R09: 00000000ff2d1de6
R10: 0000000000000000 R11: 00000000f49cf6fe R12: ffff880429684700
R13: ffffffff81893f96 R14: ffffffff817d66f0 R15: ffff880427f74200
FS: 0000000000000000(0000) GS:ffff88043fcc0000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000000000072c CR3: 000000041d3df000 CR4: 00000000000006e0
Stack:
ffffffff817b29cf ffff880429684700 ffff88043fcc3e18 ffffffff817b42c2
ffff880429684700 ffff88043fcc3e40 ffffffff817b4332 ffff880429684700
ffff880427f74238 ffff880427f74228 ffff88043fcc3e58 ffffffff81893f96
Call Trace:
<IRQ> [16240.336345] [<ffffffff817b29cf>] ? skb_release_head_state+0x4f/0xb0
[<ffffffff817b42c2>] skb_release_all+0x12/0x30
[<ffffffff817b4332>] kfree_skb+0x32/0x90
[<ffffffff81893f96>] ndisc_error_report+0x36/0x40
[<ffffffff817d4de1>] neigh_invalidate+0x81/0xf0
[<ffffffff817d68f7>] neigh_timer_handler+0x207/0x2b0
[<ffffffff81109295>] call_timer_fn+0x35/0x120
[<ffffffff81109db7>] run_timer_softirq+0x1d7/0x460
[<ffffffff8106155e>] ? kvm_sched_clock_read+0x1e/0x30
[<ffffffff810366b9>] ? sched_clock+0x9/0x10
[<ffffffff810cfed2>] ? sched_clock_cpu+0x72/0xa0
[<ffffffff818dd537>] __do_softirq+0xd7/0x289
[<ffffffff810a6c95>] irq_exit+0xb5/0xc0
[<ffffffff818dd372>] smp_apic_timer_interrupt+0x42/0x50
[<ffffffff818dc682>] apic_timer_interrupt+0x82/0x90
<EOI> [16240.395776] [<ffffffff818da156>] ? native_safe_halt+0x6/0x10
[<ffffffff818d9e6e>] default_idle+0x1e/0xd0
[<ffffffff8103797f>] arch_cpu_idle+0xf/0x20
[<ffffffff818da2c5>] default_idle_call+0x35/0x40
[<ffffffff810e3eb5>] cpu_startup_entry+0x185/0x210
[<ffffffff81050433>] start_secondary+0x103/0x130
RIP [<ffffffffa05df765>] rxe_skb_tx_dtor+0x15/0x50 [rdma_rxe]
Fixes: 8700e3e7c4
("Soft RoCE driver")
Signed-off-by: Yonatan Cohen <yonatanc@mellanox.com>
Reviewed-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Doug Ledford <dledford@redhat.com>
723 lines
16 KiB
C
723 lines
16 KiB
C
/*
|
|
* Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved.
|
|
* Copyright (c) 2015 System Fabric Works, Inc. All rights reserved.
|
|
*
|
|
* This software is available to you under a choice of one of two
|
|
* licenses. You may choose to be licensed under the terms of the GNU
|
|
* General Public License (GPL) Version 2, available from the file
|
|
* COPYING in the main directory of this source tree, or the
|
|
* OpenIB.org BSD license below:
|
|
*
|
|
* Redistribution and use in source and binary forms, with or
|
|
* without modification, are permitted provided that the following
|
|
* conditions are met:
|
|
*
|
|
* - Redistributions of source code must retain the above
|
|
* copyright notice, this list of conditions and the following
|
|
* disclaimer.
|
|
*
|
|
* - Redistributions in binary form must reproduce the above
|
|
* copyright notice, this list of conditions and the following
|
|
* disclaimer in the documentation and/or other materials
|
|
* provided with the distribution.
|
|
*
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
|
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
|
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
|
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
|
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
|
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
|
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
* SOFTWARE.
|
|
*/
|
|
|
|
#include <linux/skbuff.h>
|
|
#include <linux/if_arp.h>
|
|
#include <linux/netdevice.h>
|
|
#include <linux/if.h>
|
|
#include <linux/if_vlan.h>
|
|
#include <net/udp_tunnel.h>
|
|
#include <net/sch_generic.h>
|
|
#include <linux/netfilter.h>
|
|
#include <rdma/ib_addr.h>
|
|
|
|
#include "rxe.h"
|
|
#include "rxe_net.h"
|
|
#include "rxe_loc.h"
|
|
|
|
static LIST_HEAD(rxe_dev_list);
|
|
static DEFINE_SPINLOCK(dev_list_lock); /* spinlock for device list */
|
|
|
|
struct rxe_dev *net_to_rxe(struct net_device *ndev)
|
|
{
|
|
struct rxe_dev *rxe;
|
|
struct rxe_dev *found = NULL;
|
|
|
|
spin_lock_bh(&dev_list_lock);
|
|
list_for_each_entry(rxe, &rxe_dev_list, list) {
|
|
if (rxe->ndev == ndev) {
|
|
found = rxe;
|
|
break;
|
|
}
|
|
}
|
|
spin_unlock_bh(&dev_list_lock);
|
|
|
|
return found;
|
|
}
|
|
|
|
struct rxe_dev *get_rxe_by_name(const char *name)
|
|
{
|
|
struct rxe_dev *rxe;
|
|
struct rxe_dev *found = NULL;
|
|
|
|
spin_lock_bh(&dev_list_lock);
|
|
list_for_each_entry(rxe, &rxe_dev_list, list) {
|
|
if (!strcmp(name, rxe->ib_dev.name)) {
|
|
found = rxe;
|
|
break;
|
|
}
|
|
}
|
|
spin_unlock_bh(&dev_list_lock);
|
|
return found;
|
|
}
|
|
|
|
|
|
struct rxe_recv_sockets recv_sockets;
|
|
|
|
struct device *rxe_dma_device(struct rxe_dev *rxe)
|
|
{
|
|
struct net_device *ndev;
|
|
|
|
ndev = rxe->ndev;
|
|
|
|
if (is_vlan_dev(ndev))
|
|
ndev = vlan_dev_real_dev(ndev);
|
|
|
|
return ndev->dev.parent;
|
|
}
|
|
|
|
int rxe_mcast_add(struct rxe_dev *rxe, union ib_gid *mgid)
|
|
{
|
|
int err;
|
|
unsigned char ll_addr[ETH_ALEN];
|
|
|
|
ipv6_eth_mc_map((struct in6_addr *)mgid->raw, ll_addr);
|
|
err = dev_mc_add(rxe->ndev, ll_addr);
|
|
|
|
return err;
|
|
}
|
|
|
|
int rxe_mcast_delete(struct rxe_dev *rxe, union ib_gid *mgid)
|
|
{
|
|
int err;
|
|
unsigned char ll_addr[ETH_ALEN];
|
|
|
|
ipv6_eth_mc_map((struct in6_addr *)mgid->raw, ll_addr);
|
|
err = dev_mc_del(rxe->ndev, ll_addr);
|
|
|
|
return err;
|
|
}
|
|
|
|
static struct dst_entry *rxe_find_route4(struct net_device *ndev,
|
|
struct in_addr *saddr,
|
|
struct in_addr *daddr)
|
|
{
|
|
struct rtable *rt;
|
|
struct flowi4 fl = { { 0 } };
|
|
|
|
memset(&fl, 0, sizeof(fl));
|
|
fl.flowi4_oif = ndev->ifindex;
|
|
memcpy(&fl.saddr, saddr, sizeof(*saddr));
|
|
memcpy(&fl.daddr, daddr, sizeof(*daddr));
|
|
fl.flowi4_proto = IPPROTO_UDP;
|
|
|
|
rt = ip_route_output_key(&init_net, &fl);
|
|
if (IS_ERR(rt)) {
|
|
pr_err_ratelimited("no route to %pI4\n", &daddr->s_addr);
|
|
return NULL;
|
|
}
|
|
|
|
return &rt->dst;
|
|
}
|
|
|
|
#if IS_ENABLED(CONFIG_IPV6)
|
|
static struct dst_entry *rxe_find_route6(struct net_device *ndev,
|
|
struct in6_addr *saddr,
|
|
struct in6_addr *daddr)
|
|
{
|
|
struct dst_entry *ndst;
|
|
struct flowi6 fl6 = { { 0 } };
|
|
|
|
memset(&fl6, 0, sizeof(fl6));
|
|
fl6.flowi6_oif = ndev->ifindex;
|
|
memcpy(&fl6.saddr, saddr, sizeof(*saddr));
|
|
memcpy(&fl6.daddr, daddr, sizeof(*daddr));
|
|
fl6.flowi6_proto = IPPROTO_UDP;
|
|
|
|
if (unlikely(ipv6_stub->ipv6_dst_lookup(sock_net(recv_sockets.sk6->sk),
|
|
recv_sockets.sk6->sk, &ndst, &fl6))) {
|
|
pr_err_ratelimited("no route to %pI6\n", daddr);
|
|
goto put;
|
|
}
|
|
|
|
if (unlikely(ndst->error)) {
|
|
pr_err("no route to %pI6\n", daddr);
|
|
goto put;
|
|
}
|
|
|
|
return ndst;
|
|
put:
|
|
dst_release(ndst);
|
|
return NULL;
|
|
}
|
|
|
|
#else
|
|
|
|
static struct dst_entry *rxe_find_route6(struct net_device *ndev,
|
|
struct in6_addr *saddr,
|
|
struct in6_addr *daddr)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
#endif
|
|
|
|
static struct dst_entry *rxe_find_route(struct rxe_dev *rxe,
|
|
struct rxe_qp *qp,
|
|
struct rxe_av *av)
|
|
{
|
|
struct dst_entry *dst = NULL;
|
|
|
|
if (qp_type(qp) == IB_QPT_RC)
|
|
dst = sk_dst_get(qp->sk->sk);
|
|
|
|
if (!dst || !(dst->obsolete && dst->ops->check(dst, 0))) {
|
|
if (dst)
|
|
dst_release(dst);
|
|
|
|
if (av->network_type == RDMA_NETWORK_IPV4) {
|
|
struct in_addr *saddr;
|
|
struct in_addr *daddr;
|
|
|
|
saddr = &av->sgid_addr._sockaddr_in.sin_addr;
|
|
daddr = &av->dgid_addr._sockaddr_in.sin_addr;
|
|
dst = rxe_find_route4(rxe->ndev, saddr, daddr);
|
|
} else if (av->network_type == RDMA_NETWORK_IPV6) {
|
|
struct in6_addr *saddr6;
|
|
struct in6_addr *daddr6;
|
|
|
|
saddr6 = &av->sgid_addr._sockaddr_in6.sin6_addr;
|
|
daddr6 = &av->dgid_addr._sockaddr_in6.sin6_addr;
|
|
dst = rxe_find_route6(rxe->ndev, saddr6, daddr6);
|
|
}
|
|
}
|
|
|
|
return dst;
|
|
}
|
|
|
|
static int rxe_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
struct udphdr *udph;
|
|
struct net_device *ndev = skb->dev;
|
|
struct rxe_dev *rxe = net_to_rxe(ndev);
|
|
struct rxe_pkt_info *pkt = SKB_TO_PKT(skb);
|
|
|
|
if (!rxe)
|
|
goto drop;
|
|
|
|
if (skb_linearize(skb)) {
|
|
pr_err("skb_linearize failed\n");
|
|
goto drop;
|
|
}
|
|
|
|
udph = udp_hdr(skb);
|
|
pkt->rxe = rxe;
|
|
pkt->port_num = 1;
|
|
pkt->hdr = (u8 *)(udph + 1);
|
|
pkt->mask = RXE_GRH_MASK;
|
|
pkt->paylen = be16_to_cpu(udph->len) - sizeof(*udph);
|
|
|
|
return rxe_rcv(skb);
|
|
drop:
|
|
kfree_skb(skb);
|
|
return 0;
|
|
}
|
|
|
|
static struct socket *rxe_setup_udp_tunnel(struct net *net, __be16 port,
|
|
bool ipv6)
|
|
{
|
|
int err;
|
|
struct socket *sock;
|
|
struct udp_port_cfg udp_cfg = { };
|
|
struct udp_tunnel_sock_cfg tnl_cfg = { };
|
|
|
|
if (ipv6) {
|
|
udp_cfg.family = AF_INET6;
|
|
udp_cfg.ipv6_v6only = 1;
|
|
} else {
|
|
udp_cfg.family = AF_INET;
|
|
}
|
|
|
|
udp_cfg.local_udp_port = port;
|
|
|
|
/* Create UDP socket */
|
|
err = udp_sock_create(net, &udp_cfg, &sock);
|
|
if (err < 0) {
|
|
pr_err("failed to create udp socket. err = %d\n", err);
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
tnl_cfg.encap_type = 1;
|
|
tnl_cfg.encap_rcv = rxe_udp_encap_recv;
|
|
|
|
/* Setup UDP tunnel */
|
|
setup_udp_tunnel_sock(net, sock, &tnl_cfg);
|
|
|
|
return sock;
|
|
}
|
|
|
|
void rxe_release_udp_tunnel(struct socket *sk)
|
|
{
|
|
if (sk)
|
|
udp_tunnel_sock_release(sk);
|
|
}
|
|
|
|
static void prepare_udp_hdr(struct sk_buff *skb, __be16 src_port,
|
|
__be16 dst_port)
|
|
{
|
|
struct udphdr *udph;
|
|
|
|
__skb_push(skb, sizeof(*udph));
|
|
skb_reset_transport_header(skb);
|
|
udph = udp_hdr(skb);
|
|
|
|
udph->dest = dst_port;
|
|
udph->source = src_port;
|
|
udph->len = htons(skb->len);
|
|
udph->check = 0;
|
|
}
|
|
|
|
static void prepare_ipv4_hdr(struct dst_entry *dst, struct sk_buff *skb,
|
|
__be32 saddr, __be32 daddr, __u8 proto,
|
|
__u8 tos, __u8 ttl, __be16 df, bool xnet)
|
|
{
|
|
struct iphdr *iph;
|
|
|
|
skb_scrub_packet(skb, xnet);
|
|
|
|
skb_clear_hash(skb);
|
|
skb_dst_set(skb, dst_clone(dst));
|
|
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
|
|
|
|
skb_push(skb, sizeof(struct iphdr));
|
|
skb_reset_network_header(skb);
|
|
|
|
iph = ip_hdr(skb);
|
|
|
|
iph->version = IPVERSION;
|
|
iph->ihl = sizeof(struct iphdr) >> 2;
|
|
iph->frag_off = df;
|
|
iph->protocol = proto;
|
|
iph->tos = tos;
|
|
iph->daddr = daddr;
|
|
iph->saddr = saddr;
|
|
iph->ttl = ttl;
|
|
__ip_select_ident(dev_net(dst->dev), iph,
|
|
skb_shinfo(skb)->gso_segs ?: 1);
|
|
iph->tot_len = htons(skb->len);
|
|
ip_send_check(iph);
|
|
}
|
|
|
|
static void prepare_ipv6_hdr(struct dst_entry *dst, struct sk_buff *skb,
|
|
struct in6_addr *saddr, struct in6_addr *daddr,
|
|
__u8 proto, __u8 prio, __u8 ttl)
|
|
{
|
|
struct ipv6hdr *ip6h;
|
|
|
|
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
|
|
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED
|
|
| IPSKB_REROUTED);
|
|
skb_dst_set(skb, dst);
|
|
|
|
__skb_push(skb, sizeof(*ip6h));
|
|
skb_reset_network_header(skb);
|
|
ip6h = ipv6_hdr(skb);
|
|
ip6_flow_hdr(ip6h, prio, htonl(0));
|
|
ip6h->payload_len = htons(skb->len);
|
|
ip6h->nexthdr = proto;
|
|
ip6h->hop_limit = ttl;
|
|
ip6h->daddr = *daddr;
|
|
ip6h->saddr = *saddr;
|
|
ip6h->payload_len = htons(skb->len - sizeof(*ip6h));
|
|
}
|
|
|
|
static int prepare4(struct rxe_dev *rxe, struct rxe_pkt_info *pkt,
|
|
struct sk_buff *skb, struct rxe_av *av)
|
|
{
|
|
struct rxe_qp *qp = pkt->qp;
|
|
struct dst_entry *dst;
|
|
bool xnet = false;
|
|
__be16 df = htons(IP_DF);
|
|
struct in_addr *saddr = &av->sgid_addr._sockaddr_in.sin_addr;
|
|
struct in_addr *daddr = &av->dgid_addr._sockaddr_in.sin_addr;
|
|
|
|
dst = rxe_find_route(rxe, qp, av);
|
|
if (!dst) {
|
|
pr_err("Host not reachable\n");
|
|
return -EHOSTUNREACH;
|
|
}
|
|
|
|
if (!memcmp(saddr, daddr, sizeof(*daddr)))
|
|
pkt->mask |= RXE_LOOPBACK_MASK;
|
|
|
|
prepare_udp_hdr(skb, htons(RXE_ROCE_V2_SPORT),
|
|
htons(ROCE_V2_UDP_DPORT));
|
|
|
|
prepare_ipv4_hdr(dst, skb, saddr->s_addr, daddr->s_addr, IPPROTO_UDP,
|
|
av->grh.traffic_class, av->grh.hop_limit, df, xnet);
|
|
|
|
if (qp_type(qp) == IB_QPT_RC)
|
|
sk_dst_set(qp->sk->sk, dst);
|
|
else
|
|
dst_release(dst);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int prepare6(struct rxe_dev *rxe, struct rxe_pkt_info *pkt,
|
|
struct sk_buff *skb, struct rxe_av *av)
|
|
{
|
|
struct rxe_qp *qp = pkt->qp;
|
|
struct dst_entry *dst = NULL;
|
|
struct in6_addr *saddr = &av->sgid_addr._sockaddr_in6.sin6_addr;
|
|
struct in6_addr *daddr = &av->dgid_addr._sockaddr_in6.sin6_addr;
|
|
|
|
dst = rxe_find_route(rxe, qp, av);
|
|
if (!dst) {
|
|
pr_err("Host not reachable\n");
|
|
return -EHOSTUNREACH;
|
|
}
|
|
|
|
if (!memcmp(saddr, daddr, sizeof(*daddr)))
|
|
pkt->mask |= RXE_LOOPBACK_MASK;
|
|
|
|
prepare_udp_hdr(skb, htons(RXE_ROCE_V2_SPORT),
|
|
htons(ROCE_V2_UDP_DPORT));
|
|
|
|
prepare_ipv6_hdr(dst, skb, saddr, daddr, IPPROTO_UDP,
|
|
av->grh.traffic_class,
|
|
av->grh.hop_limit);
|
|
|
|
if (qp_type(qp) == IB_QPT_RC)
|
|
sk_dst_set(qp->sk->sk, dst);
|
|
else
|
|
dst_release(dst);
|
|
|
|
return 0;
|
|
}
|
|
|
|
int rxe_prepare(struct rxe_dev *rxe, struct rxe_pkt_info *pkt,
|
|
struct sk_buff *skb, u32 *crc)
|
|
{
|
|
int err = 0;
|
|
struct rxe_av *av = rxe_get_av(pkt);
|
|
|
|
if (av->network_type == RDMA_NETWORK_IPV4)
|
|
err = prepare4(rxe, pkt, skb, av);
|
|
else if (av->network_type == RDMA_NETWORK_IPV6)
|
|
err = prepare6(rxe, pkt, skb, av);
|
|
|
|
*crc = rxe_icrc_hdr(pkt, skb);
|
|
|
|
return err;
|
|
}
|
|
|
|
static void rxe_skb_tx_dtor(struct sk_buff *skb)
|
|
{
|
|
struct sock *sk = skb->sk;
|
|
struct rxe_qp *qp = sk->sk_user_data;
|
|
int skb_out = atomic_dec_return(&qp->skb_out);
|
|
|
|
if (unlikely(qp->need_req_skb &&
|
|
skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW))
|
|
rxe_run_task(&qp->req.task, 1);
|
|
|
|
rxe_drop_ref(qp);
|
|
}
|
|
|
|
int rxe_send(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, struct sk_buff *skb)
|
|
{
|
|
struct sk_buff *nskb;
|
|
struct rxe_av *av;
|
|
int err;
|
|
|
|
av = rxe_get_av(pkt);
|
|
|
|
nskb = skb_clone(skb, GFP_ATOMIC);
|
|
if (!nskb)
|
|
return -ENOMEM;
|
|
|
|
nskb->destructor = rxe_skb_tx_dtor;
|
|
nskb->sk = pkt->qp->sk->sk;
|
|
|
|
if (av->network_type == RDMA_NETWORK_IPV4) {
|
|
err = ip_local_out(dev_net(skb_dst(skb)->dev), nskb->sk, nskb);
|
|
} else if (av->network_type == RDMA_NETWORK_IPV6) {
|
|
err = ip6_local_out(dev_net(skb_dst(skb)->dev), nskb->sk, nskb);
|
|
} else {
|
|
pr_err("Unknown layer 3 protocol: %d\n", av->network_type);
|
|
kfree_skb(nskb);
|
|
return -EINVAL;
|
|
}
|
|
|
|
if (unlikely(net_xmit_eval(err))) {
|
|
pr_debug("error sending packet: %d\n", err);
|
|
return -EAGAIN;
|
|
}
|
|
|
|
rxe_add_ref(pkt->qp);
|
|
atomic_inc(&pkt->qp->skb_out);
|
|
kfree_skb(skb);
|
|
|
|
return 0;
|
|
}
|
|
|
|
int rxe_loopback(struct sk_buff *skb)
|
|
{
|
|
return rxe_rcv(skb);
|
|
}
|
|
|
|
static inline int addr_same(struct rxe_dev *rxe, struct rxe_av *av)
|
|
{
|
|
return rxe->port.port_guid == av->grh.dgid.global.interface_id;
|
|
}
|
|
|
|
struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av,
|
|
int paylen, struct rxe_pkt_info *pkt)
|
|
{
|
|
unsigned int hdr_len;
|
|
struct sk_buff *skb;
|
|
|
|
if (av->network_type == RDMA_NETWORK_IPV4)
|
|
hdr_len = ETH_HLEN + sizeof(struct udphdr) +
|
|
sizeof(struct iphdr);
|
|
else
|
|
hdr_len = ETH_HLEN + sizeof(struct udphdr) +
|
|
sizeof(struct ipv6hdr);
|
|
|
|
skb = alloc_skb(paylen + hdr_len + LL_RESERVED_SPACE(rxe->ndev),
|
|
GFP_ATOMIC);
|
|
if (unlikely(!skb))
|
|
return NULL;
|
|
|
|
skb_reserve(skb, hdr_len + LL_RESERVED_SPACE(rxe->ndev));
|
|
|
|
skb->dev = rxe->ndev;
|
|
if (av->network_type == RDMA_NETWORK_IPV4)
|
|
skb->protocol = htons(ETH_P_IP);
|
|
else
|
|
skb->protocol = htons(ETH_P_IPV6);
|
|
|
|
pkt->rxe = rxe;
|
|
pkt->port_num = 1;
|
|
pkt->hdr = skb_put(skb, paylen);
|
|
pkt->mask |= RXE_GRH_MASK;
|
|
|
|
memset(pkt->hdr, 0, paylen);
|
|
|
|
return skb;
|
|
}
|
|
|
|
/*
|
|
* this is required by rxe_cfg to match rxe devices in
|
|
* /sys/class/infiniband up with their underlying ethernet devices
|
|
*/
|
|
const char *rxe_parent_name(struct rxe_dev *rxe, unsigned int port_num)
|
|
{
|
|
return rxe->ndev->name;
|
|
}
|
|
|
|
enum rdma_link_layer rxe_link_layer(struct rxe_dev *rxe, unsigned int port_num)
|
|
{
|
|
return IB_LINK_LAYER_ETHERNET;
|
|
}
|
|
|
|
struct rxe_dev *rxe_net_add(struct net_device *ndev)
|
|
{
|
|
int err;
|
|
struct rxe_dev *rxe = NULL;
|
|
|
|
rxe = (struct rxe_dev *)ib_alloc_device(sizeof(*rxe));
|
|
if (!rxe)
|
|
return NULL;
|
|
|
|
rxe->ndev = ndev;
|
|
|
|
err = rxe_add(rxe, ndev->mtu);
|
|
if (err) {
|
|
ib_dealloc_device(&rxe->ib_dev);
|
|
return NULL;
|
|
}
|
|
|
|
spin_lock_bh(&dev_list_lock);
|
|
list_add_tail(&rxe->list, &rxe_dev_list);
|
|
spin_unlock_bh(&dev_list_lock);
|
|
return rxe;
|
|
}
|
|
|
|
void rxe_remove_all(void)
|
|
{
|
|
spin_lock_bh(&dev_list_lock);
|
|
while (!list_empty(&rxe_dev_list)) {
|
|
struct rxe_dev *rxe =
|
|
list_first_entry(&rxe_dev_list, struct rxe_dev, list);
|
|
|
|
list_del(&rxe->list);
|
|
spin_unlock_bh(&dev_list_lock);
|
|
rxe_remove(rxe);
|
|
spin_lock_bh(&dev_list_lock);
|
|
}
|
|
spin_unlock_bh(&dev_list_lock);
|
|
}
|
|
EXPORT_SYMBOL(rxe_remove_all);
|
|
|
|
static void rxe_port_event(struct rxe_dev *rxe,
|
|
enum ib_event_type event)
|
|
{
|
|
struct ib_event ev;
|
|
|
|
ev.device = &rxe->ib_dev;
|
|
ev.element.port_num = 1;
|
|
ev.event = event;
|
|
|
|
ib_dispatch_event(&ev);
|
|
}
|
|
|
|
/* Caller must hold net_info_lock */
|
|
void rxe_port_up(struct rxe_dev *rxe)
|
|
{
|
|
struct rxe_port *port;
|
|
|
|
port = &rxe->port;
|
|
port->attr.state = IB_PORT_ACTIVE;
|
|
port->attr.phys_state = IB_PHYS_STATE_LINK_UP;
|
|
|
|
rxe_port_event(rxe, IB_EVENT_PORT_ACTIVE);
|
|
pr_info("set %s active\n", rxe->ib_dev.name);
|
|
}
|
|
|
|
/* Caller must hold net_info_lock */
|
|
void rxe_port_down(struct rxe_dev *rxe)
|
|
{
|
|
struct rxe_port *port;
|
|
|
|
port = &rxe->port;
|
|
port->attr.state = IB_PORT_DOWN;
|
|
port->attr.phys_state = IB_PHYS_STATE_LINK_DOWN;
|
|
|
|
rxe_port_event(rxe, IB_EVENT_PORT_ERR);
|
|
pr_info("set %s down\n", rxe->ib_dev.name);
|
|
}
|
|
|
|
static int rxe_notify(struct notifier_block *not_blk,
|
|
unsigned long event,
|
|
void *arg)
|
|
{
|
|
struct net_device *ndev = netdev_notifier_info_to_dev(arg);
|
|
struct rxe_dev *rxe = net_to_rxe(ndev);
|
|
|
|
if (!rxe)
|
|
goto out;
|
|
|
|
switch (event) {
|
|
case NETDEV_UNREGISTER:
|
|
list_del(&rxe->list);
|
|
rxe_remove(rxe);
|
|
break;
|
|
case NETDEV_UP:
|
|
rxe_port_up(rxe);
|
|
break;
|
|
case NETDEV_DOWN:
|
|
rxe_port_down(rxe);
|
|
break;
|
|
case NETDEV_CHANGEMTU:
|
|
pr_info("%s changed mtu to %d\n", ndev->name, ndev->mtu);
|
|
rxe_set_mtu(rxe, ndev->mtu);
|
|
break;
|
|
case NETDEV_REBOOT:
|
|
case NETDEV_CHANGE:
|
|
case NETDEV_GOING_DOWN:
|
|
case NETDEV_CHANGEADDR:
|
|
case NETDEV_CHANGENAME:
|
|
case NETDEV_FEAT_CHANGE:
|
|
default:
|
|
pr_info("ignoring netdev event = %ld for %s\n",
|
|
event, ndev->name);
|
|
break;
|
|
}
|
|
out:
|
|
return NOTIFY_OK;
|
|
}
|
|
|
|
struct notifier_block rxe_net_notifier = {
|
|
.notifier_call = rxe_notify,
|
|
};
|
|
|
|
static int rxe_net_ipv4_init(void)
|
|
{
|
|
recv_sockets.sk4 = rxe_setup_udp_tunnel(&init_net,
|
|
htons(ROCE_V2_UDP_DPORT), false);
|
|
if (IS_ERR(recv_sockets.sk4)) {
|
|
recv_sockets.sk4 = NULL;
|
|
pr_err("Failed to create IPv4 UDP tunnel\n");
|
|
return -1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int rxe_net_ipv6_init(void)
|
|
{
|
|
#if IS_ENABLED(CONFIG_IPV6)
|
|
|
|
recv_sockets.sk6 = rxe_setup_udp_tunnel(&init_net,
|
|
htons(ROCE_V2_UDP_DPORT), true);
|
|
if (IS_ERR(recv_sockets.sk6)) {
|
|
recv_sockets.sk6 = NULL;
|
|
pr_err("Failed to create IPv6 UDP tunnel\n");
|
|
return -1;
|
|
}
|
|
#endif
|
|
return 0;
|
|
}
|
|
|
|
void rxe_net_exit(void)
|
|
{
|
|
rxe_release_udp_tunnel(recv_sockets.sk6);
|
|
rxe_release_udp_tunnel(recv_sockets.sk4);
|
|
unregister_netdevice_notifier(&rxe_net_notifier);
|
|
}
|
|
|
|
int rxe_net_init(void)
|
|
{
|
|
int err;
|
|
|
|
recv_sockets.sk6 = NULL;
|
|
|
|
err = rxe_net_ipv4_init();
|
|
if (err)
|
|
return err;
|
|
err = rxe_net_ipv6_init();
|
|
if (err)
|
|
goto err_out;
|
|
err = register_netdevice_notifier(&rxe_net_notifier);
|
|
if (err) {
|
|
pr_err("Failed to register netdev notifier\n");
|
|
goto err_out;
|
|
}
|
|
return 0;
|
|
err_out:
|
|
rxe_net_exit();
|
|
return err;
|
|
}
|