OpenCloudOS-Kernel/drivers/net/veth.c

1419 lines
31 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* drivers/net/veth.c
*
* Copyright (C) 2007 OpenVZ http://openvz.org, SWsoft Inc
*
* Author: Pavel Emelianov <xemul@openvz.org>
* Ethtool interface from: Eric W. Biederman <ebiederm@xmission.com>
*
*/
#include <linux/netdevice.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/ethtool.h>
#include <linux/etherdevice.h>
#include <linux/u64_stats_sync.h>
#include <net/rtnetlink.h>
#include <net/dst.h>
#include <net/xfrm.h>
#include <net/xdp.h>
#include <linux/veth.h>
#include <linux/module.h>
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/ptr_ring.h>
#include <linux/bpf_trace.h>
#include <linux/net_tstamp.h>
#define DRV_NAME "veth"
#define DRV_VERSION "1.0"
#define VETH_XDP_FLAG BIT(0)
#define VETH_RING_SIZE 256
#define VETH_XDP_HEADROOM (XDP_PACKET_HEADROOM + NET_IP_ALIGN)
#define VETH_XDP_TX_BULK_SIZE 16
struct veth_stats {
u64 rx_drops;
/* xdp */
u64 xdp_packets;
u64 xdp_bytes;
u64 xdp_redirect;
u64 xdp_drops;
u64 xdp_tx;
};
struct veth_rq_stats {
struct veth_stats vs;
struct u64_stats_sync syncp;
};
struct veth_rq {
struct napi_struct xdp_napi;
struct net_device *dev;
struct bpf_prog __rcu *xdp_prog;
struct xdp_mem_info xdp_mem;
struct veth_rq_stats stats;
bool rx_notify_masked;
struct ptr_ring xdp_ring;
struct xdp_rxq_info xdp_rxq;
};
struct veth_priv {
struct net_device __rcu *peer;
atomic64_t dropped;
struct bpf_prog *_xdp_prog;
struct veth_rq *rq;
unsigned int requested_headroom;
};
struct veth_xdp_tx_bq {
struct xdp_frame *q[VETH_XDP_TX_BULK_SIZE];
unsigned int count;
};
/*
* ethtool interface
*/
struct veth_q_stat_desc {
char desc[ETH_GSTRING_LEN];
size_t offset;
};
#define VETH_RQ_STAT(m) offsetof(struct veth_stats, m)
static const struct veth_q_stat_desc veth_rq_stats_desc[] = {
{ "xdp_packets", VETH_RQ_STAT(xdp_packets) },
{ "xdp_bytes", VETH_RQ_STAT(xdp_bytes) },
{ "xdp_drops", VETH_RQ_STAT(xdp_drops) },
};
#define VETH_RQ_STATS_LEN ARRAY_SIZE(veth_rq_stats_desc)
static struct {
const char string[ETH_GSTRING_LEN];
} ethtool_stats_keys[] = {
{ "peer_ifindex" },
};
static int veth_get_link_ksettings(struct net_device *dev,
struct ethtool_link_ksettings *cmd)
{
cmd->base.speed = SPEED_10000;
cmd->base.duplex = DUPLEX_FULL;
cmd->base.port = PORT_TP;
cmd->base.autoneg = AUTONEG_DISABLE;
return 0;
}
static void veth_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
strlcpy(info->version, DRV_VERSION, sizeof(info->version));
}
static void veth_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
{
char *p = (char *)buf;
int i, j;
switch(stringset) {
case ETH_SS_STATS:
memcpy(p, &ethtool_stats_keys, sizeof(ethtool_stats_keys));
p += sizeof(ethtool_stats_keys);
for (i = 0; i < dev->real_num_rx_queues; i++) {
for (j = 0; j < VETH_RQ_STATS_LEN; j++) {
snprintf(p, ETH_GSTRING_LEN,
"rx_queue_%u_%.11s",
i, veth_rq_stats_desc[j].desc);
p += ETH_GSTRING_LEN;
}
}
break;
}
}
static int veth_get_sset_count(struct net_device *dev, int sset)
{
switch (sset) {
case ETH_SS_STATS:
return ARRAY_SIZE(ethtool_stats_keys) +
VETH_RQ_STATS_LEN * dev->real_num_rx_queues;
default:
return -EOPNOTSUPP;
}
}
static void veth_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
veth: avoid a NULL deref in veth_stats_one commit 2681128f0ced8a (veth: extend device features) added a NULL deref in veth_stats_one(), as veth_get_stats64() was not testing if the peer device was setup or not. At init time, we call dev_get_stats() before veth pair is fully setup. [ 178.854758] [<ffffffffa00f5677>] veth_get_stats64+0x47/0x70 [veth] [ 178.861013] [<ffffffff814f0a2d>] dev_get_stats+0x6d/0x130 [ 178.866486] [<ffffffff81504efc>] rtnl_fill_ifinfo+0x47c/0x930 [ 178.872299] [<ffffffff81505b93>] rtmsg_ifinfo+0x83/0x100 [ 178.877678] [<ffffffff81505cc6>] rtnl_configure_link+0x76/0xa0 [ 178.883580] [<ffffffffa00f52fa>] veth_newlink+0x16a/0x350 [veth] [ 178.889654] [<ffffffff815061cc>] rtnl_newlink+0x4dc/0x5e0 [ 178.895128] [<ffffffff81505e1e>] ? rtnl_newlink+0x12e/0x5e0 [ 178.900769] [<ffffffff8150587d>] rtnetlink_rcv_msg+0x11d/0x310 [ 178.906669] [<ffffffff81505760>] ? __rtnl_unlock+0x20/0x20 [ 178.912225] [<ffffffff81521f89>] netlink_rcv_skb+0xa9/0xd0 [ 178.917779] [<ffffffff81502d55>] rtnetlink_rcv+0x25/0x40 [ 178.923159] [<ffffffff815218d1>] netlink_unicast+0x1b1/0x230 [ 178.928887] [<ffffffff81521c4e>] netlink_sendmsg+0x2fe/0x3b0 [ 178.934615] [<ffffffff814dbe22>] sock_sendmsg+0xd2/0xf0 So we must check if peer was setup in veth_get_stats64() As pointed out by Ben Hutchings, priv->peer is missing proper synchronization. Adding RCU protection is a safe and well documented way to make sure we don't access about to be freed or already freed data. Reported-by: Tom Parkin <tparkin@katalix.com> Signed-off-by: Eric Dumazet <edumazet@google.com> CC: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 23:42:40 +08:00
struct veth_priv *priv = netdev_priv(dev);
struct net_device *peer = rtnl_dereference(priv->peer);
int i, j, idx;
veth: avoid a NULL deref in veth_stats_one commit 2681128f0ced8a (veth: extend device features) added a NULL deref in veth_stats_one(), as veth_get_stats64() was not testing if the peer device was setup or not. At init time, we call dev_get_stats() before veth pair is fully setup. [ 178.854758] [<ffffffffa00f5677>] veth_get_stats64+0x47/0x70 [veth] [ 178.861013] [<ffffffff814f0a2d>] dev_get_stats+0x6d/0x130 [ 178.866486] [<ffffffff81504efc>] rtnl_fill_ifinfo+0x47c/0x930 [ 178.872299] [<ffffffff81505b93>] rtmsg_ifinfo+0x83/0x100 [ 178.877678] [<ffffffff81505cc6>] rtnl_configure_link+0x76/0xa0 [ 178.883580] [<ffffffffa00f52fa>] veth_newlink+0x16a/0x350 [veth] [ 178.889654] [<ffffffff815061cc>] rtnl_newlink+0x4dc/0x5e0 [ 178.895128] [<ffffffff81505e1e>] ? rtnl_newlink+0x12e/0x5e0 [ 178.900769] [<ffffffff8150587d>] rtnetlink_rcv_msg+0x11d/0x310 [ 178.906669] [<ffffffff81505760>] ? __rtnl_unlock+0x20/0x20 [ 178.912225] [<ffffffff81521f89>] netlink_rcv_skb+0xa9/0xd0 [ 178.917779] [<ffffffff81502d55>] rtnetlink_rcv+0x25/0x40 [ 178.923159] [<ffffffff815218d1>] netlink_unicast+0x1b1/0x230 [ 178.928887] [<ffffffff81521c4e>] netlink_sendmsg+0x2fe/0x3b0 [ 178.934615] [<ffffffff814dbe22>] sock_sendmsg+0xd2/0xf0 So we must check if peer was setup in veth_get_stats64() As pointed out by Ben Hutchings, priv->peer is missing proper synchronization. Adding RCU protection is a safe and well documented way to make sure we don't access about to be freed or already freed data. Reported-by: Tom Parkin <tparkin@katalix.com> Signed-off-by: Eric Dumazet <edumazet@google.com> CC: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 23:42:40 +08:00
data[0] = peer ? peer->ifindex : 0;
idx = 1;
for (i = 0; i < dev->real_num_rx_queues; i++) {
const struct veth_rq_stats *rq_stats = &priv->rq[i].stats;
const void *stats_base = (void *)&rq_stats->vs;
unsigned int start;
size_t offset;
do {
start = u64_stats_fetch_begin_irq(&rq_stats->syncp);
for (j = 0; j < VETH_RQ_STATS_LEN; j++) {
offset = veth_rq_stats_desc[j].offset;
data[idx + j] = *(u64 *)(stats_base + offset);
}
} while (u64_stats_fetch_retry_irq(&rq_stats->syncp, start));
idx += VETH_RQ_STATS_LEN;
}
}
static const struct ethtool_ops veth_ethtool_ops = {
.get_drvinfo = veth_get_drvinfo,
.get_link = ethtool_op_get_link,
.get_strings = veth_get_strings,
.get_sset_count = veth_get_sset_count,
.get_ethtool_stats = veth_get_ethtool_stats,
.get_link_ksettings = veth_get_link_ksettings,
.get_ts_info = ethtool_op_get_ts_info,
};
/* general routines */
static bool veth_is_xdp_frame(void *ptr)
{
return (unsigned long)ptr & VETH_XDP_FLAG;
}
static void *veth_ptr_to_xdp(void *ptr)
{
return (void *)((unsigned long)ptr & ~VETH_XDP_FLAG);
}
static void *veth_xdp_to_ptr(void *ptr)
{
return (void *)((unsigned long)ptr | VETH_XDP_FLAG);
}
static void veth_ptr_free(void *ptr)
{
if (veth_is_xdp_frame(ptr))
xdp_return_frame(veth_ptr_to_xdp(ptr));
else
kfree_skb(ptr);
}
static void __veth_xdp_flush(struct veth_rq *rq)
{
/* Write ptr_ring before reading rx_notify_masked */
smp_mb();
if (!rq->rx_notify_masked) {
rq->rx_notify_masked = true;
napi_schedule(&rq->xdp_napi);
}
}
static int veth_xdp_rx(struct veth_rq *rq, struct sk_buff *skb)
{
if (unlikely(ptr_ring_produce(&rq->xdp_ring, skb))) {
dev_kfree_skb_any(skb);
return NET_RX_DROP;
}
return NET_RX_SUCCESS;
}
static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb,
struct veth_rq *rq, bool xdp)
{
return __dev_forward_skb(dev, skb) ?: xdp ?
veth_xdp_rx(rq, skb) :
netif_rx(skb);
}
static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
struct veth_rq *rq = NULL;
veth: avoid a NULL deref in veth_stats_one commit 2681128f0ced8a (veth: extend device features) added a NULL deref in veth_stats_one(), as veth_get_stats64() was not testing if the peer device was setup or not. At init time, we call dev_get_stats() before veth pair is fully setup. [ 178.854758] [<ffffffffa00f5677>] veth_get_stats64+0x47/0x70 [veth] [ 178.861013] [<ffffffff814f0a2d>] dev_get_stats+0x6d/0x130 [ 178.866486] [<ffffffff81504efc>] rtnl_fill_ifinfo+0x47c/0x930 [ 178.872299] [<ffffffff81505b93>] rtmsg_ifinfo+0x83/0x100 [ 178.877678] [<ffffffff81505cc6>] rtnl_configure_link+0x76/0xa0 [ 178.883580] [<ffffffffa00f52fa>] veth_newlink+0x16a/0x350 [veth] [ 178.889654] [<ffffffff815061cc>] rtnl_newlink+0x4dc/0x5e0 [ 178.895128] [<ffffffff81505e1e>] ? rtnl_newlink+0x12e/0x5e0 [ 178.900769] [<ffffffff8150587d>] rtnetlink_rcv_msg+0x11d/0x310 [ 178.906669] [<ffffffff81505760>] ? __rtnl_unlock+0x20/0x20 [ 178.912225] [<ffffffff81521f89>] netlink_rcv_skb+0xa9/0xd0 [ 178.917779] [<ffffffff81502d55>] rtnetlink_rcv+0x25/0x40 [ 178.923159] [<ffffffff815218d1>] netlink_unicast+0x1b1/0x230 [ 178.928887] [<ffffffff81521c4e>] netlink_sendmsg+0x2fe/0x3b0 [ 178.934615] [<ffffffff814dbe22>] sock_sendmsg+0xd2/0xf0 So we must check if peer was setup in veth_get_stats64() As pointed out by Ben Hutchings, priv->peer is missing proper synchronization. Adding RCU protection is a safe and well documented way to make sure we don't access about to be freed or already freed data. Reported-by: Tom Parkin <tparkin@katalix.com> Signed-off-by: Eric Dumazet <edumazet@google.com> CC: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 23:42:40 +08:00
struct net_device *rcv;
int length = skb->len;
bool rcv_xdp = false;
int rxq;
veth: avoid a NULL deref in veth_stats_one commit 2681128f0ced8a (veth: extend device features) added a NULL deref in veth_stats_one(), as veth_get_stats64() was not testing if the peer device was setup or not. At init time, we call dev_get_stats() before veth pair is fully setup. [ 178.854758] [<ffffffffa00f5677>] veth_get_stats64+0x47/0x70 [veth] [ 178.861013] [<ffffffff814f0a2d>] dev_get_stats+0x6d/0x130 [ 178.866486] [<ffffffff81504efc>] rtnl_fill_ifinfo+0x47c/0x930 [ 178.872299] [<ffffffff81505b93>] rtmsg_ifinfo+0x83/0x100 [ 178.877678] [<ffffffff81505cc6>] rtnl_configure_link+0x76/0xa0 [ 178.883580] [<ffffffffa00f52fa>] veth_newlink+0x16a/0x350 [veth] [ 178.889654] [<ffffffff815061cc>] rtnl_newlink+0x4dc/0x5e0 [ 178.895128] [<ffffffff81505e1e>] ? rtnl_newlink+0x12e/0x5e0 [ 178.900769] [<ffffffff8150587d>] rtnetlink_rcv_msg+0x11d/0x310 [ 178.906669] [<ffffffff81505760>] ? __rtnl_unlock+0x20/0x20 [ 178.912225] [<ffffffff81521f89>] netlink_rcv_skb+0xa9/0xd0 [ 178.917779] [<ffffffff81502d55>] rtnetlink_rcv+0x25/0x40 [ 178.923159] [<ffffffff815218d1>] netlink_unicast+0x1b1/0x230 [ 178.928887] [<ffffffff81521c4e>] netlink_sendmsg+0x2fe/0x3b0 [ 178.934615] [<ffffffff814dbe22>] sock_sendmsg+0xd2/0xf0 So we must check if peer was setup in veth_get_stats64() As pointed out by Ben Hutchings, priv->peer is missing proper synchronization. Adding RCU protection is a safe and well documented way to make sure we don't access about to be freed or already freed data. Reported-by: Tom Parkin <tparkin@katalix.com> Signed-off-by: Eric Dumazet <edumazet@google.com> CC: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 23:42:40 +08:00
rcu_read_lock();
rcv = rcu_dereference(priv->peer);
if (unlikely(!rcv)) {
kfree_skb(skb);
goto drop;
}
rcv_priv = netdev_priv(rcv);
rxq = skb_get_queue_mapping(skb);
if (rxq < rcv->real_num_rx_queues) {
rq = &rcv_priv->rq[rxq];
rcv_xdp = rcu_access_pointer(rq->xdp_prog);
if (rcv_xdp)
skb_record_rx_queue(skb, rxq);
}
skb_tx_timestamp(skb);
if (likely(veth_forward_skb(rcv, skb, rq, rcv_xdp) == NET_RX_SUCCESS)) {
if (!rcv_xdp)
dev_lstats_add(dev, length);
} else {
veth: avoid a NULL deref in veth_stats_one commit 2681128f0ced8a (veth: extend device features) added a NULL deref in veth_stats_one(), as veth_get_stats64() was not testing if the peer device was setup or not. At init time, we call dev_get_stats() before veth pair is fully setup. [ 178.854758] [<ffffffffa00f5677>] veth_get_stats64+0x47/0x70 [veth] [ 178.861013] [<ffffffff814f0a2d>] dev_get_stats+0x6d/0x130 [ 178.866486] [<ffffffff81504efc>] rtnl_fill_ifinfo+0x47c/0x930 [ 178.872299] [<ffffffff81505b93>] rtmsg_ifinfo+0x83/0x100 [ 178.877678] [<ffffffff81505cc6>] rtnl_configure_link+0x76/0xa0 [ 178.883580] [<ffffffffa00f52fa>] veth_newlink+0x16a/0x350 [veth] [ 178.889654] [<ffffffff815061cc>] rtnl_newlink+0x4dc/0x5e0 [ 178.895128] [<ffffffff81505e1e>] ? rtnl_newlink+0x12e/0x5e0 [ 178.900769] [<ffffffff8150587d>] rtnetlink_rcv_msg+0x11d/0x310 [ 178.906669] [<ffffffff81505760>] ? __rtnl_unlock+0x20/0x20 [ 178.912225] [<ffffffff81521f89>] netlink_rcv_skb+0xa9/0xd0 [ 178.917779] [<ffffffff81502d55>] rtnetlink_rcv+0x25/0x40 [ 178.923159] [<ffffffff815218d1>] netlink_unicast+0x1b1/0x230 [ 178.928887] [<ffffffff81521c4e>] netlink_sendmsg+0x2fe/0x3b0 [ 178.934615] [<ffffffff814dbe22>] sock_sendmsg+0xd2/0xf0 So we must check if peer was setup in veth_get_stats64() As pointed out by Ben Hutchings, priv->peer is missing proper synchronization. Adding RCU protection is a safe and well documented way to make sure we don't access about to be freed or already freed data. Reported-by: Tom Parkin <tparkin@katalix.com> Signed-off-by: Eric Dumazet <edumazet@google.com> CC: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 23:42:40 +08:00
drop:
atomic64_inc(&priv->dropped);
}
if (rcv_xdp)
__veth_xdp_flush(rq);
veth: avoid a NULL deref in veth_stats_one commit 2681128f0ced8a (veth: extend device features) added a NULL deref in veth_stats_one(), as veth_get_stats64() was not testing if the peer device was setup or not. At init time, we call dev_get_stats() before veth pair is fully setup. [ 178.854758] [<ffffffffa00f5677>] veth_get_stats64+0x47/0x70 [veth] [ 178.861013] [<ffffffff814f0a2d>] dev_get_stats+0x6d/0x130 [ 178.866486] [<ffffffff81504efc>] rtnl_fill_ifinfo+0x47c/0x930 [ 178.872299] [<ffffffff81505b93>] rtmsg_ifinfo+0x83/0x100 [ 178.877678] [<ffffffff81505cc6>] rtnl_configure_link+0x76/0xa0 [ 178.883580] [<ffffffffa00f52fa>] veth_newlink+0x16a/0x350 [veth] [ 178.889654] [<ffffffff815061cc>] rtnl_newlink+0x4dc/0x5e0 [ 178.895128] [<ffffffff81505e1e>] ? rtnl_newlink+0x12e/0x5e0 [ 178.900769] [<ffffffff8150587d>] rtnetlink_rcv_msg+0x11d/0x310 [ 178.906669] [<ffffffff81505760>] ? __rtnl_unlock+0x20/0x20 [ 178.912225] [<ffffffff81521f89>] netlink_rcv_skb+0xa9/0xd0 [ 178.917779] [<ffffffff81502d55>] rtnetlink_rcv+0x25/0x40 [ 178.923159] [<ffffffff815218d1>] netlink_unicast+0x1b1/0x230 [ 178.928887] [<ffffffff81521c4e>] netlink_sendmsg+0x2fe/0x3b0 [ 178.934615] [<ffffffff814dbe22>] sock_sendmsg+0xd2/0xf0 So we must check if peer was setup in veth_get_stats64() As pointed out by Ben Hutchings, priv->peer is missing proper synchronization. Adding RCU protection is a safe and well documented way to make sure we don't access about to be freed or already freed data. Reported-by: Tom Parkin <tparkin@katalix.com> Signed-off-by: Eric Dumazet <edumazet@google.com> CC: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 23:42:40 +08:00
rcu_read_unlock();
return NETDEV_TX_OK;
}
static u64 veth_stats_tx(struct net_device *dev, u64 *packets, u64 *bytes)
{
struct veth_priv *priv = netdev_priv(dev);
dev_lstats_read(dev, packets, bytes);
return atomic64_read(&priv->dropped);
}
static void veth_stats_rx(struct veth_stats *result, struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
int i;
result->xdp_packets = 0;
result->xdp_bytes = 0;
result->xdp_drops = 0;
for (i = 0; i < dev->num_rx_queues; i++) {
struct veth_rq_stats *stats = &priv->rq[i].stats;
u64 packets, bytes, drops;
unsigned int start;
do {
start = u64_stats_fetch_begin_irq(&stats->syncp);
packets = stats->vs.xdp_packets;
bytes = stats->vs.xdp_bytes;
drops = stats->vs.xdp_drops;
} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
result->xdp_packets += packets;
result->xdp_bytes += bytes;
result->xdp_drops += drops;
}
}
static void veth_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *tot)
{
struct veth_priv *priv = netdev_priv(dev);
veth: avoid a NULL deref in veth_stats_one commit 2681128f0ced8a (veth: extend device features) added a NULL deref in veth_stats_one(), as veth_get_stats64() was not testing if the peer device was setup or not. At init time, we call dev_get_stats() before veth pair is fully setup. [ 178.854758] [<ffffffffa00f5677>] veth_get_stats64+0x47/0x70 [veth] [ 178.861013] [<ffffffff814f0a2d>] dev_get_stats+0x6d/0x130 [ 178.866486] [<ffffffff81504efc>] rtnl_fill_ifinfo+0x47c/0x930 [ 178.872299] [<ffffffff81505b93>] rtmsg_ifinfo+0x83/0x100 [ 178.877678] [<ffffffff81505cc6>] rtnl_configure_link+0x76/0xa0 [ 178.883580] [<ffffffffa00f52fa>] veth_newlink+0x16a/0x350 [veth] [ 178.889654] [<ffffffff815061cc>] rtnl_newlink+0x4dc/0x5e0 [ 178.895128] [<ffffffff81505e1e>] ? rtnl_newlink+0x12e/0x5e0 [ 178.900769] [<ffffffff8150587d>] rtnetlink_rcv_msg+0x11d/0x310 [ 178.906669] [<ffffffff81505760>] ? __rtnl_unlock+0x20/0x20 [ 178.912225] [<ffffffff81521f89>] netlink_rcv_skb+0xa9/0xd0 [ 178.917779] [<ffffffff81502d55>] rtnetlink_rcv+0x25/0x40 [ 178.923159] [<ffffffff815218d1>] netlink_unicast+0x1b1/0x230 [ 178.928887] [<ffffffff81521c4e>] netlink_sendmsg+0x2fe/0x3b0 [ 178.934615] [<ffffffff814dbe22>] sock_sendmsg+0xd2/0xf0 So we must check if peer was setup in veth_get_stats64() As pointed out by Ben Hutchings, priv->peer is missing proper synchronization. Adding RCU protection is a safe and well documented way to make sure we don't access about to be freed or already freed data. Reported-by: Tom Parkin <tparkin@katalix.com> Signed-off-by: Eric Dumazet <edumazet@google.com> CC: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 23:42:40 +08:00
struct net_device *peer;
struct veth_stats rx;
u64 packets, bytes;
tot->tx_dropped = veth_stats_tx(dev, &packets, &bytes);
tot->tx_bytes = bytes;
tot->tx_packets = packets;
veth_stats_rx(&rx, dev);
tot->rx_dropped = rx.xdp_drops;
tot->rx_bytes = rx.xdp_bytes;
tot->rx_packets = rx.xdp_packets;
veth: avoid a NULL deref in veth_stats_one commit 2681128f0ced8a (veth: extend device features) added a NULL deref in veth_stats_one(), as veth_get_stats64() was not testing if the peer device was setup or not. At init time, we call dev_get_stats() before veth pair is fully setup. [ 178.854758] [<ffffffffa00f5677>] veth_get_stats64+0x47/0x70 [veth] [ 178.861013] [<ffffffff814f0a2d>] dev_get_stats+0x6d/0x130 [ 178.866486] [<ffffffff81504efc>] rtnl_fill_ifinfo+0x47c/0x930 [ 178.872299] [<ffffffff81505b93>] rtmsg_ifinfo+0x83/0x100 [ 178.877678] [<ffffffff81505cc6>] rtnl_configure_link+0x76/0xa0 [ 178.883580] [<ffffffffa00f52fa>] veth_newlink+0x16a/0x350 [veth] [ 178.889654] [<ffffffff815061cc>] rtnl_newlink+0x4dc/0x5e0 [ 178.895128] [<ffffffff81505e1e>] ? rtnl_newlink+0x12e/0x5e0 [ 178.900769] [<ffffffff8150587d>] rtnetlink_rcv_msg+0x11d/0x310 [ 178.906669] [<ffffffff81505760>] ? __rtnl_unlock+0x20/0x20 [ 178.912225] [<ffffffff81521f89>] netlink_rcv_skb+0xa9/0xd0 [ 178.917779] [<ffffffff81502d55>] rtnetlink_rcv+0x25/0x40 [ 178.923159] [<ffffffff815218d1>] netlink_unicast+0x1b1/0x230 [ 178.928887] [<ffffffff81521c4e>] netlink_sendmsg+0x2fe/0x3b0 [ 178.934615] [<ffffffff814dbe22>] sock_sendmsg+0xd2/0xf0 So we must check if peer was setup in veth_get_stats64() As pointed out by Ben Hutchings, priv->peer is missing proper synchronization. Adding RCU protection is a safe and well documented way to make sure we don't access about to be freed or already freed data. Reported-by: Tom Parkin <tparkin@katalix.com> Signed-off-by: Eric Dumazet <edumazet@google.com> CC: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 23:42:40 +08:00
rcu_read_lock();
peer = rcu_dereference(priv->peer);
if (peer) {
veth_stats_tx(peer, &packets, &bytes);
tot->rx_bytes += bytes;
tot->rx_packets += packets;
veth_stats_rx(&rx, peer);
tot->tx_bytes += rx.xdp_bytes;
tot->tx_packets += rx.xdp_packets;
veth: avoid a NULL deref in veth_stats_one commit 2681128f0ced8a (veth: extend device features) added a NULL deref in veth_stats_one(), as veth_get_stats64() was not testing if the peer device was setup or not. At init time, we call dev_get_stats() before veth pair is fully setup. [ 178.854758] [<ffffffffa00f5677>] veth_get_stats64+0x47/0x70 [veth] [ 178.861013] [<ffffffff814f0a2d>] dev_get_stats+0x6d/0x130 [ 178.866486] [<ffffffff81504efc>] rtnl_fill_ifinfo+0x47c/0x930 [ 178.872299] [<ffffffff81505b93>] rtmsg_ifinfo+0x83/0x100 [ 178.877678] [<ffffffff81505cc6>] rtnl_configure_link+0x76/0xa0 [ 178.883580] [<ffffffffa00f52fa>] veth_newlink+0x16a/0x350 [veth] [ 178.889654] [<ffffffff815061cc>] rtnl_newlink+0x4dc/0x5e0 [ 178.895128] [<ffffffff81505e1e>] ? rtnl_newlink+0x12e/0x5e0 [ 178.900769] [<ffffffff8150587d>] rtnetlink_rcv_msg+0x11d/0x310 [ 178.906669] [<ffffffff81505760>] ? __rtnl_unlock+0x20/0x20 [ 178.912225] [<ffffffff81521f89>] netlink_rcv_skb+0xa9/0xd0 [ 178.917779] [<ffffffff81502d55>] rtnetlink_rcv+0x25/0x40 [ 178.923159] [<ffffffff815218d1>] netlink_unicast+0x1b1/0x230 [ 178.928887] [<ffffffff81521c4e>] netlink_sendmsg+0x2fe/0x3b0 [ 178.934615] [<ffffffff814dbe22>] sock_sendmsg+0xd2/0xf0 So we must check if peer was setup in veth_get_stats64() As pointed out by Ben Hutchings, priv->peer is missing proper synchronization. Adding RCU protection is a safe and well documented way to make sure we don't access about to be freed or already freed data. Reported-by: Tom Parkin <tparkin@katalix.com> Signed-off-by: Eric Dumazet <edumazet@google.com> CC: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 23:42:40 +08:00
}
rcu_read_unlock();
}
/* fake multicast ability */
static void veth_set_multicast_list(struct net_device *dev)
{
}
static struct sk_buff *veth_build_skb(void *head, int headroom, int len,
int buflen)
{
struct sk_buff *skb;
if (!buflen) {
buflen = SKB_DATA_ALIGN(headroom + len) +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
}
skb = build_skb(head, buflen);
if (!skb)
return NULL;
skb_reserve(skb, headroom);
skb_put(skb, len);
return skb;
}
static int veth_select_rxq(struct net_device *dev)
{
return smp_processor_id() % dev->real_num_rx_queues;
}
static int veth_xdp_xmit(struct net_device *dev, int n,
struct xdp_frame **frames, u32 flags)
{
struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
struct net_device *rcv;
int i, ret, drops = n;
unsigned int max_len;
struct veth_rq *rq;
bpf, xdp: Remove no longer required rcu_read_{un}lock() Now that we depend on rcu_call() and synchronize_rcu() to also wait for preempt_disabled region to complete the rcu read critical section in __dev_map_flush() is no longer required. Except in a few special cases in drivers that need it for other reasons. These originally ensured the map reference was safe while a map was also being free'd. And additionally that bpf program updates via ndo_bpf did not happen while flush updates were in flight. But flush by new rules can only be called from preempt-disabled NAPI context. The synchronize_rcu from the map free path and the rcu_call from the delete path will ensure the reference there is safe. So lets remove the rcu_read_lock and rcu_read_unlock pair to avoid any confusion around how this is being protected. If the rcu_read_lock was required it would mean errors in the above logic and the original patch would also be wrong. Now that we have done above we put the rcu_read_lock in the driver code where it is needed in a driver dependent way. I think this helps readability of the code so we know where and why we are taking read locks. Most drivers will not need rcu_read_locks here and further XDP drivers already have rcu_read_locks in their code paths for reading xdp programs on RX side so this makes it symmetric where we don't have half of rcu critical sections define in driver and the other half in devmap. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/1580084042-11598-4-git-send-email-john.fastabend@gmail.com
2020-01-27 08:14:02 +08:00
rcu_read_lock();
if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) {
ret = -EINVAL;
goto drop;
}
rcv = rcu_dereference(priv->peer);
if (unlikely(!rcv)) {
ret = -ENXIO;
goto drop;
}
rcv_priv = netdev_priv(rcv);
rq = &rcv_priv->rq[veth_select_rxq(rcv)];
/* Non-NULL xdp_prog ensures that xdp_ring is initialized on receive
* side. This means an XDP program is loaded on the peer and the peer
* device is up.
*/
if (!rcu_access_pointer(rq->xdp_prog)) {
ret = -ENXIO;
goto drop;
}
drops = 0;
max_len = rcv->mtu + rcv->hard_header_len + VLAN_HLEN;
spin_lock(&rq->xdp_ring.producer_lock);
for (i = 0; i < n; i++) {
struct xdp_frame *frame = frames[i];
void *ptr = veth_xdp_to_ptr(frame);
if (unlikely(frame->len > max_len ||
__ptr_ring_produce(&rq->xdp_ring, ptr))) {
xdp_return_frame_rx_napi(frame);
drops++;
}
}
spin_unlock(&rq->xdp_ring.producer_lock);
if (flags & XDP_XMIT_FLUSH)
__veth_xdp_flush(rq);
bpf, xdp: Remove no longer required rcu_read_{un}lock() Now that we depend on rcu_call() and synchronize_rcu() to also wait for preempt_disabled region to complete the rcu read critical section in __dev_map_flush() is no longer required. Except in a few special cases in drivers that need it for other reasons. These originally ensured the map reference was safe while a map was also being free'd. And additionally that bpf program updates via ndo_bpf did not happen while flush updates were in flight. But flush by new rules can only be called from preempt-disabled NAPI context. The synchronize_rcu from the map free path and the rcu_call from the delete path will ensure the reference there is safe. So lets remove the rcu_read_lock and rcu_read_unlock pair to avoid any confusion around how this is being protected. If the rcu_read_lock was required it would mean errors in the above logic and the original patch would also be wrong. Now that we have done above we put the rcu_read_lock in the driver code where it is needed in a driver dependent way. I think this helps readability of the code so we know where and why we are taking read locks. Most drivers will not need rcu_read_locks here and further XDP drivers already have rcu_read_locks in their code paths for reading xdp programs on RX side so this makes it symmetric where we don't have half of rcu critical sections define in driver and the other half in devmap. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/1580084042-11598-4-git-send-email-john.fastabend@gmail.com
2020-01-27 08:14:02 +08:00
if (likely(!drops)) {
rcu_read_unlock();
return n;
bpf, xdp: Remove no longer required rcu_read_{un}lock() Now that we depend on rcu_call() and synchronize_rcu() to also wait for preempt_disabled region to complete the rcu read critical section in __dev_map_flush() is no longer required. Except in a few special cases in drivers that need it for other reasons. These originally ensured the map reference was safe while a map was also being free'd. And additionally that bpf program updates via ndo_bpf did not happen while flush updates were in flight. But flush by new rules can only be called from preempt-disabled NAPI context. The synchronize_rcu from the map free path and the rcu_call from the delete path will ensure the reference there is safe. So lets remove the rcu_read_lock and rcu_read_unlock pair to avoid any confusion around how this is being protected. If the rcu_read_lock was required it would mean errors in the above logic and the original patch would also be wrong. Now that we have done above we put the rcu_read_lock in the driver code where it is needed in a driver dependent way. I think this helps readability of the code so we know where and why we are taking read locks. Most drivers will not need rcu_read_locks here and further XDP drivers already have rcu_read_locks in their code paths for reading xdp programs on RX side so this makes it symmetric where we don't have half of rcu critical sections define in driver and the other half in devmap. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/1580084042-11598-4-git-send-email-john.fastabend@gmail.com
2020-01-27 08:14:02 +08:00
}
ret = n - drops;
drop:
bpf, xdp: Remove no longer required rcu_read_{un}lock() Now that we depend on rcu_call() and synchronize_rcu() to also wait for preempt_disabled region to complete the rcu read critical section in __dev_map_flush() is no longer required. Except in a few special cases in drivers that need it for other reasons. These originally ensured the map reference was safe while a map was also being free'd. And additionally that bpf program updates via ndo_bpf did not happen while flush updates were in flight. But flush by new rules can only be called from preempt-disabled NAPI context. The synchronize_rcu from the map free path and the rcu_call from the delete path will ensure the reference there is safe. So lets remove the rcu_read_lock and rcu_read_unlock pair to avoid any confusion around how this is being protected. If the rcu_read_lock was required it would mean errors in the above logic and the original patch would also be wrong. Now that we have done above we put the rcu_read_lock in the driver code where it is needed in a driver dependent way. I think this helps readability of the code so we know where and why we are taking read locks. Most drivers will not need rcu_read_locks here and further XDP drivers already have rcu_read_locks in their code paths for reading xdp programs on RX side so this makes it symmetric where we don't have half of rcu critical sections define in driver and the other half in devmap. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/1580084042-11598-4-git-send-email-john.fastabend@gmail.com
2020-01-27 08:14:02 +08:00
rcu_read_unlock();
atomic64_add(drops, &priv->dropped);
return ret;
}
static void veth_xdp_flush_bq(struct net_device *dev, struct veth_xdp_tx_bq *bq)
{
int sent, i, err = 0;
sent = veth_xdp_xmit(dev, bq->count, bq->q, 0);
if (sent < 0) {
err = sent;
sent = 0;
for (i = 0; i < bq->count; i++)
xdp_return_frame(bq->q[i]);
}
trace_xdp_bulk_tx(dev, sent, bq->count - sent, err);
bq->count = 0;
}
static void veth_xdp_flush(struct net_device *dev, struct veth_xdp_tx_bq *bq)
{
struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
struct net_device *rcv;
struct veth_rq *rq;
rcu_read_lock();
veth_xdp_flush_bq(dev, bq);
rcv = rcu_dereference(priv->peer);
if (unlikely(!rcv))
goto out;
rcv_priv = netdev_priv(rcv);
rq = &rcv_priv->rq[veth_select_rxq(rcv)];
/* xdp_ring is initialized on receive side? */
if (unlikely(!rcu_access_pointer(rq->xdp_prog)))
goto out;
__veth_xdp_flush(rq);
out:
rcu_read_unlock();
}
static int veth_xdp_tx(struct net_device *dev, struct xdp_buff *xdp,
struct veth_xdp_tx_bq *bq)
{
struct xdp_frame *frame = convert_to_xdp_frame(xdp);
if (unlikely(!frame))
return -EOVERFLOW;
if (unlikely(bq->count == VETH_XDP_TX_BULK_SIZE))
veth_xdp_flush_bq(dev, bq);
bq->q[bq->count++] = frame;
return 0;
}
static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
struct xdp_frame *frame,
struct veth_xdp_tx_bq *bq,
struct veth_stats *stats)
{
void *hard_start = frame->data - frame->headroom;
void *head = hard_start - sizeof(struct xdp_frame);
int len = frame->len, delta = 0;
struct xdp_frame orig_frame;
struct bpf_prog *xdp_prog;
unsigned int headroom;
struct sk_buff *skb;
rcu_read_lock();
xdp_prog = rcu_dereference(rq->xdp_prog);
if (likely(xdp_prog)) {
struct xdp_buff xdp;
u32 act;
xdp.data_hard_start = hard_start;
xdp.data = frame->data;
xdp.data_end = frame->data + frame->len;
xdp.data_meta = frame->data - frame->metasize;
xdp.rxq = &rq->xdp_rxq;
act = bpf_prog_run_xdp(xdp_prog, &xdp);
switch (act) {
case XDP_PASS:
delta = frame->data - xdp.data;
len = xdp.data_end - xdp.data;
break;
case XDP_TX:
orig_frame = *frame;
xdp.data_hard_start = head;
xdp.rxq->mem = frame->mem;
if (unlikely(veth_xdp_tx(rq->dev, &xdp, bq) < 0)) {
trace_xdp_exception(rq->dev, xdp_prog, act);
frame = &orig_frame;
stats->rx_drops++;
goto err_xdp;
}
stats->xdp_tx++;
rcu_read_unlock();
goto xdp_xmit;
case XDP_REDIRECT:
orig_frame = *frame;
xdp.data_hard_start = head;
xdp.rxq->mem = frame->mem;
if (xdp_do_redirect(rq->dev, &xdp, xdp_prog)) {
frame = &orig_frame;
stats->rx_drops++;
goto err_xdp;
}
stats->xdp_redirect++;
rcu_read_unlock();
goto xdp_xmit;
default:
bpf_warn_invalid_xdp_action(act);
/* fall through */
case XDP_ABORTED:
trace_xdp_exception(rq->dev, xdp_prog, act);
/* fall through */
case XDP_DROP:
stats->xdp_drops++;
goto err_xdp;
}
}
rcu_read_unlock();
headroom = sizeof(struct xdp_frame) + frame->headroom - delta;
skb = veth_build_skb(head, headroom, len, 0);
if (!skb) {
xdp_return_frame(frame);
stats->rx_drops++;
goto err;
}
xdp_release_frame(frame);
xdp_scrub_frame(frame);
skb->protocol = eth_type_trans(skb, rq->dev);
err:
return skb;
err_xdp:
rcu_read_unlock();
xdp_return_frame(frame);
xdp_xmit:
return NULL;
}
static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq,
struct sk_buff *skb,
struct veth_xdp_tx_bq *bq,
struct veth_stats *stats)
{
u32 pktlen, headroom, act, metalen;
void *orig_data, *orig_data_end;
struct bpf_prog *xdp_prog;
int mac_len, delta, off;
struct xdp_buff xdp;
veth: Orphan skb before GRO GRO expects skbs not to be owned by sockets, but when XDP is enabled veth passed skbs owned by sockets. It caused corrupted sk_wmem_alloc. Paolo Abeni reported the following splat: [ 362.098904] refcount_t overflow at skb_set_owner_w+0x5e/0xa0 in iperf3[1644], uid/euid: 0/0 [ 362.108239] WARNING: CPU: 0 PID: 1644 at kernel/panic.c:648 refcount_error_report+0xa0/0xa4 [ 362.117547] Modules linked in: tcp_diag inet_diag veth intel_rapl sb_edac x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel intel_cstate intel_uncore intel_rapl_perf ipmi_ssif iTCO_wdt sg ipmi_si iTCO_vendor_support ipmi_devintf mxm_wmi ipmi_msghandler pcspkr dcdbas mei_me wmi mei lpc_ich acpi_power_meter pcc_cpufreq xfs libcrc32c sd_mod mgag200 drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ixgbe igb ttm ahci mdio libahci ptp crc32c_intel drm pps_core libata i2c_algo_bit dca dm_mirror dm_region_hash dm_log dm_mod [ 362.176622] CPU: 0 PID: 1644 Comm: iperf3 Not tainted 4.19.0-rc2.vanilla+ #2025 [ 362.184777] Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.1.7 06/16/2016 [ 362.193124] RIP: 0010:refcount_error_report+0xa0/0xa4 [ 362.198758] Code: 08 00 00 48 8b 95 80 00 00 00 49 8d 8c 24 80 0a 00 00 41 89 c1 44 89 2c 24 48 89 de 48 c7 c7 18 4d e7 9d 31 c0 e8 30 fa ff ff <0f> 0b eb 88 0f 1f 44 00 00 55 48 89 e5 41 56 41 55 41 54 49 89 fc [ 362.219711] RSP: 0018:ffff9ee6ff603c20 EFLAGS: 00010282 [ 362.225538] RAX: 0000000000000000 RBX: ffffffff9de83e10 RCX: 0000000000000000 [ 362.233497] RDX: 0000000000000001 RSI: ffff9ee6ff6167d8 RDI: ffff9ee6ff6167d8 [ 362.241457] RBP: ffff9ee6ff603d78 R08: 0000000000000490 R09: 0000000000000004 [ 362.249416] R10: 0000000000000000 R11: ffff9ee6ff603990 R12: ffff9ee664b94500 [ 362.257377] R13: 0000000000000000 R14: 0000000000000004 R15: ffffffff9de615f9 [ 362.265337] FS: 00007f1d22d28740(0000) GS:ffff9ee6ff600000(0000) knlGS:0000000000000000 [ 362.274363] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 362.280773] CR2: 00007f1d222f35d0 CR3: 0000001fddfec003 CR4: 00000000001606f0 [ 362.288733] Call Trace: [ 362.291459] <IRQ> [ 362.293702] ex_handler_refcount+0x4e/0x80 [ 362.298269] fixup_exception+0x35/0x40 [ 362.302451] do_trap+0x109/0x150 [ 362.306048] do_error_trap+0xd5/0x130 [ 362.315766] invalid_op+0x14/0x20 [ 362.319460] RIP: 0010:skb_set_owner_w+0x5e/0xa0 [ 362.324512] Code: ef ff ff 74 49 48 c7 43 60 20 7b 4a 9d 8b 85 f4 01 00 00 85 c0 75 16 8b 83 e0 00 00 00 f0 01 85 44 01 00 00 0f 88 d8 23 16 00 <5b> 5d c3 80 8b 91 00 00 00 01 8b 85 f4 01 00 00 89 83 a4 00 00 00 [ 362.345465] RSP: 0018:ffff9ee6ff603e20 EFLAGS: 00010a86 [ 362.351291] RAX: 0000000000001100 RBX: ffff9ee65deec700 RCX: ffff9ee65e829244 [ 362.359250] RDX: 0000000000000100 RSI: ffff9ee65e829100 RDI: ffff9ee65deec700 [ 362.367210] RBP: ffff9ee65e829100 R08: 000000000002a380 R09: 0000000000000000 [ 362.375169] R10: 0000000000000002 R11: fffff1a4bf77bb00 R12: ffffc0754661d000 [ 362.383130] R13: ffff9ee65deec200 R14: ffff9ee65f597000 R15: 00000000000000aa [ 362.391092] veth_xdp_rcv+0x4e4/0x890 [veth] [ 362.399357] veth_poll+0x4d/0x17a [veth] [ 362.403731] net_rx_action+0x2af/0x3f0 [ 362.407912] __do_softirq+0xdd/0x29e [ 362.411897] do_softirq_own_stack+0x2a/0x40 [ 362.416561] </IRQ> [ 362.418899] do_softirq+0x4b/0x70 [ 362.422594] __local_bh_enable_ip+0x50/0x60 [ 362.427258] ip_finish_output2+0x16a/0x390 [ 362.431824] ip_output+0x71/0xe0 [ 362.440670] __tcp_transmit_skb+0x583/0xab0 [ 362.445333] tcp_write_xmit+0x247/0xfb0 [ 362.449609] __tcp_push_pending_frames+0x2d/0xd0 [ 362.454760] tcp_sendmsg_locked+0x857/0xd30 [ 362.459424] tcp_sendmsg+0x27/0x40 [ 362.463216] sock_sendmsg+0x36/0x50 [ 362.467104] sock_write_iter+0x87/0x100 [ 362.471382] __vfs_write+0x112/0x1a0 [ 362.475369] vfs_write+0xad/0x1a0 [ 362.479062] ksys_write+0x52/0xc0 [ 362.482759] do_syscall_64+0x5b/0x180 [ 362.486841] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 362.492473] RIP: 0033:0x7f1d22293238 [ 362.496458] Code: 89 02 48 c7 c0 ff ff ff ff eb b3 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 c5 54 2d 00 8b 00 85 c0 75 17 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 41 54 49 89 d4 55 [ 362.517409] RSP: 002b:00007ffebaef8008 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 362.525855] RAX: ffffffffffffffda RBX: 0000000000002800 RCX: 00007f1d22293238 [ 362.533816] RDX: 0000000000002800 RSI: 00007f1d22d36000 RDI: 0000000000000005 [ 362.541775] RBP: 00007f1d22d36000 R08: 00000002db777a30 R09: 0000562b70712b20 [ 362.549734] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000005 [ 362.557693] R13: 0000000000002800 R14: 00007ffebaef8060 R15: 0000562b70712260 In order to avoid this, orphan the skb before entering GRO. Fixes: 948d4f214fde ("veth: Add driver XDP") Reported-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Tested-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-14 12:33:44 +08:00
skb_orphan(skb);
rcu_read_lock();
xdp_prog = rcu_dereference(rq->xdp_prog);
if (unlikely(!xdp_prog)) {
rcu_read_unlock();
goto out;
}
mac_len = skb->data - skb_mac_header(skb);
pktlen = skb->len + mac_len;
headroom = skb_headroom(skb) - mac_len;
if (skb_shared(skb) || skb_head_is_locked(skb) ||
skb_is_nonlinear(skb) || headroom < XDP_PACKET_HEADROOM) {
struct sk_buff *nskb;
int size, head_off;
void *head, *start;
struct page *page;
size = SKB_DATA_ALIGN(VETH_XDP_HEADROOM + pktlen) +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
if (size > PAGE_SIZE)
goto drop;
page = alloc_page(GFP_ATOMIC | __GFP_NOWARN);
if (!page)
goto drop;
head = page_address(page);
start = head + VETH_XDP_HEADROOM;
if (skb_copy_bits(skb, -mac_len, start, pktlen)) {
page_frag_free(head);
goto drop;
}
nskb = veth_build_skb(head,
VETH_XDP_HEADROOM + mac_len, skb->len,
PAGE_SIZE);
if (!nskb) {
page_frag_free(head);
goto drop;
}
skb_copy_header(nskb, skb);
head_off = skb_headroom(nskb) - skb_headroom(skb);
skb_headers_offset_update(nskb, head_off);
consume_skb(skb);
skb = nskb;
}
xdp.data_hard_start = skb->head;
xdp.data = skb_mac_header(skb);
xdp.data_end = xdp.data + pktlen;
xdp.data_meta = xdp.data;
xdp.rxq = &rq->xdp_rxq;
orig_data = xdp.data;
orig_data_end = xdp.data_end;
act = bpf_prog_run_xdp(xdp_prog, &xdp);
switch (act) {
case XDP_PASS:
break;
case XDP_TX:
get_page(virt_to_page(xdp.data));
consume_skb(skb);
xdp.rxq->mem = rq->xdp_mem;
if (unlikely(veth_xdp_tx(rq->dev, &xdp, bq) < 0)) {
trace_xdp_exception(rq->dev, xdp_prog, act);
stats->rx_drops++;
goto err_xdp;
}
stats->xdp_tx++;
rcu_read_unlock();
goto xdp_xmit;
case XDP_REDIRECT:
get_page(virt_to_page(xdp.data));
consume_skb(skb);
xdp.rxq->mem = rq->xdp_mem;
if (xdp_do_redirect(rq->dev, &xdp, xdp_prog)) {
stats->rx_drops++;
goto err_xdp;
}
stats->xdp_redirect++;
rcu_read_unlock();
goto xdp_xmit;
default:
bpf_warn_invalid_xdp_action(act);
/* fall through */
case XDP_ABORTED:
trace_xdp_exception(rq->dev, xdp_prog, act);
/* fall through */
case XDP_DROP:
stats->xdp_drops++;
goto xdp_drop;
}
rcu_read_unlock();
delta = orig_data - xdp.data;
off = mac_len + delta;
if (off > 0)
__skb_push(skb, off);
else if (off < 0)
__skb_pull(skb, -off);
skb->mac_header -= delta;
off = xdp.data_end - orig_data_end;
if (off != 0)
__skb_put(skb, off);
skb->protocol = eth_type_trans(skb, rq->dev);
metalen = xdp.data - xdp.data_meta;
if (metalen)
skb_metadata_set(skb, metalen);
out:
return skb;
drop:
stats->rx_drops++;
xdp_drop:
rcu_read_unlock();
kfree_skb(skb);
return NULL;
err_xdp:
rcu_read_unlock();
page_frag_free(xdp.data);
xdp_xmit:
return NULL;
}
static int veth_xdp_rcv(struct veth_rq *rq, int budget,
struct veth_xdp_tx_bq *bq,
struct veth_stats *stats)
{
int i, done = 0;
for (i = 0; i < budget; i++) {
void *ptr = __ptr_ring_consume(&rq->xdp_ring);
struct sk_buff *skb;
if (!ptr)
break;
if (veth_is_xdp_frame(ptr)) {
struct xdp_frame *frame = veth_ptr_to_xdp(ptr);
stats->xdp_bytes += frame->len;
skb = veth_xdp_rcv_one(rq, frame, bq, stats);
} else {
skb = ptr;
stats->xdp_bytes += skb->len;
skb = veth_xdp_rcv_skb(rq, skb, bq, stats);
}
if (skb)
napi_gro_receive(&rq->xdp_napi, skb);
done++;
}
u64_stats_update_begin(&rq->stats.syncp);
rq->stats.vs.xdp_bytes += stats->xdp_bytes;
rq->stats.vs.xdp_drops += stats->xdp_drops + stats->rx_drops;
rq->stats.vs.xdp_packets += done;
u64_stats_update_end(&rq->stats.syncp);
return done;
}
static int veth_poll(struct napi_struct *napi, int budget)
{
struct veth_rq *rq =
container_of(napi, struct veth_rq, xdp_napi);
struct veth_stats stats = {};
struct veth_xdp_tx_bq bq;
int done;
bq.count = 0;
xdp_set_return_frame_no_direct();
done = veth_xdp_rcv(rq, budget, &bq, &stats);
if (done < budget && napi_complete_done(napi, done)) {
/* Write rx_notify_masked before reading ptr_ring */
smp_store_mb(rq->rx_notify_masked, false);
if (unlikely(!__ptr_ring_empty(&rq->xdp_ring))) {
rq->rx_notify_masked = true;
napi_schedule(&rq->xdp_napi);
}
}
if (stats.xdp_tx > 0)
veth_xdp_flush(rq->dev, &bq);
if (stats.xdp_redirect > 0)
xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths Since the bulk queue used by XDP_REDIRECT now lives in struct net_device, we can re-use the bulking for the non-map version of the bpf_redirect() helper. This is a simple matter of having xdp_do_redirect_slow() queue the frame on the bulk queue instead of sending it out with __bpf_tx_xdp(). Unfortunately we can't make the bpf_redirect() helper return an error if the ifindex doesn't exit (as bpf_redirect_map() does), because we don't have a reference to the network namespace of the ingress device at the time the helper is called. So we have to leave it as-is and keep the device lookup in xdp_do_redirect_slow(). Since this leaves less reason to have the non-map redirect code in a separate function, so we get rid of the xdp_do_redirect_slow() function entirely. This does lose us the tracepoint disambiguation, but fortunately the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint entry structures. This means both can contain a map index, so we can just amend the tracepoint definitions so we always emit the xdp_redirect(_err) tracepoints, but with the map ID only populated if a map is present. This means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep the definitions around in case someone is still listening for them. With this change, the performance of the xdp_redirect sample program goes from 5Mpps to 8.4Mpps (a 68% increase). Since the flush functions are no longer map-specific, rename the flush() functions to drop _map from their names. One of the renamed functions is the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To keep from having to update all drivers, use a #define to keep the old name working, and only update the virtual drivers in this patch. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768505.1458396.17518057312953572912.stgit@toke.dk
2020-01-16 23:14:45 +08:00
xdp_do_flush();
xdp_clear_return_frame_no_direct();
return done;
}
static int veth_napi_add(struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
int err, i;
for (i = 0; i < dev->real_num_rx_queues; i++) {
struct veth_rq *rq = &priv->rq[i];
err = ptr_ring_init(&rq->xdp_ring, VETH_RING_SIZE, GFP_KERNEL);
if (err)
goto err_xdp_ring;
}
for (i = 0; i < dev->real_num_rx_queues; i++) {
struct veth_rq *rq = &priv->rq[i];
netif_napi_add(dev, &rq->xdp_napi, veth_poll, NAPI_POLL_WEIGHT);
napi_enable(&rq->xdp_napi);
}
return 0;
err_xdp_ring:
for (i--; i >= 0; i--)
ptr_ring_cleanup(&priv->rq[i].xdp_ring, veth_ptr_free);
return err;
}
static void veth_napi_del(struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
int i;
for (i = 0; i < dev->real_num_rx_queues; i++) {
struct veth_rq *rq = &priv->rq[i];
napi_disable(&rq->xdp_napi);
napi_hash_del(&rq->xdp_napi);
}
synchronize_net();
for (i = 0; i < dev->real_num_rx_queues; i++) {
struct veth_rq *rq = &priv->rq[i];
netif_napi_del(&rq->xdp_napi);
rq->rx_notify_masked = false;
ptr_ring_cleanup(&rq->xdp_ring, veth_ptr_free);
}
}
static int veth_enable_xdp(struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
int err, i;
if (!xdp_rxq_info_is_reg(&priv->rq[0].xdp_rxq)) {
for (i = 0; i < dev->real_num_rx_queues; i++) {
struct veth_rq *rq = &priv->rq[i];
err = xdp_rxq_info_reg(&rq->xdp_rxq, dev, i);
if (err < 0)
goto err_rxq_reg;
err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
MEM_TYPE_PAGE_SHARED,
NULL);
if (err < 0)
goto err_reg_mem;
/* Save original mem info as it can be overwritten */
rq->xdp_mem = rq->xdp_rxq.mem;
}
err = veth_napi_add(dev);
if (err)
goto err_rxq_reg;
}
for (i = 0; i < dev->real_num_rx_queues; i++)
rcu_assign_pointer(priv->rq[i].xdp_prog, priv->_xdp_prog);
return 0;
err_reg_mem:
xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq);
err_rxq_reg:
for (i--; i >= 0; i--)
xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq);
return err;
}
static void veth_disable_xdp(struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
int i;
for (i = 0; i < dev->real_num_rx_queues; i++)
rcu_assign_pointer(priv->rq[i].xdp_prog, NULL);
veth_napi_del(dev);
for (i = 0; i < dev->real_num_rx_queues; i++) {
struct veth_rq *rq = &priv->rq[i];
rq->xdp_rxq.mem = rq->xdp_mem;
xdp_rxq_info_unreg(&rq->xdp_rxq);
}
}
static int veth_open(struct net_device *dev)
{
veth: avoid a NULL deref in veth_stats_one commit 2681128f0ced8a (veth: extend device features) added a NULL deref in veth_stats_one(), as veth_get_stats64() was not testing if the peer device was setup or not. At init time, we call dev_get_stats() before veth pair is fully setup. [ 178.854758] [<ffffffffa00f5677>] veth_get_stats64+0x47/0x70 [veth] [ 178.861013] [<ffffffff814f0a2d>] dev_get_stats+0x6d/0x130 [ 178.866486] [<ffffffff81504efc>] rtnl_fill_ifinfo+0x47c/0x930 [ 178.872299] [<ffffffff81505b93>] rtmsg_ifinfo+0x83/0x100 [ 178.877678] [<ffffffff81505cc6>] rtnl_configure_link+0x76/0xa0 [ 178.883580] [<ffffffffa00f52fa>] veth_newlink+0x16a/0x350 [veth] [ 178.889654] [<ffffffff815061cc>] rtnl_newlink+0x4dc/0x5e0 [ 178.895128] [<ffffffff81505e1e>] ? rtnl_newlink+0x12e/0x5e0 [ 178.900769] [<ffffffff8150587d>] rtnetlink_rcv_msg+0x11d/0x310 [ 178.906669] [<ffffffff81505760>] ? __rtnl_unlock+0x20/0x20 [ 178.912225] [<ffffffff81521f89>] netlink_rcv_skb+0xa9/0xd0 [ 178.917779] [<ffffffff81502d55>] rtnetlink_rcv+0x25/0x40 [ 178.923159] [<ffffffff815218d1>] netlink_unicast+0x1b1/0x230 [ 178.928887] [<ffffffff81521c4e>] netlink_sendmsg+0x2fe/0x3b0 [ 178.934615] [<ffffffff814dbe22>] sock_sendmsg+0xd2/0xf0 So we must check if peer was setup in veth_get_stats64() As pointed out by Ben Hutchings, priv->peer is missing proper synchronization. Adding RCU protection is a safe and well documented way to make sure we don't access about to be freed or already freed data. Reported-by: Tom Parkin <tparkin@katalix.com> Signed-off-by: Eric Dumazet <edumazet@google.com> CC: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 23:42:40 +08:00
struct veth_priv *priv = netdev_priv(dev);
struct net_device *peer = rtnl_dereference(priv->peer);
int err;
veth: avoid a NULL deref in veth_stats_one commit 2681128f0ced8a (veth: extend device features) added a NULL deref in veth_stats_one(), as veth_get_stats64() was not testing if the peer device was setup or not. At init time, we call dev_get_stats() before veth pair is fully setup. [ 178.854758] [<ffffffffa00f5677>] veth_get_stats64+0x47/0x70 [veth] [ 178.861013] [<ffffffff814f0a2d>] dev_get_stats+0x6d/0x130 [ 178.866486] [<ffffffff81504efc>] rtnl_fill_ifinfo+0x47c/0x930 [ 178.872299] [<ffffffff81505b93>] rtmsg_ifinfo+0x83/0x100 [ 178.877678] [<ffffffff81505cc6>] rtnl_configure_link+0x76/0xa0 [ 178.883580] [<ffffffffa00f52fa>] veth_newlink+0x16a/0x350 [veth] [ 178.889654] [<ffffffff815061cc>] rtnl_newlink+0x4dc/0x5e0 [ 178.895128] [<ffffffff81505e1e>] ? rtnl_newlink+0x12e/0x5e0 [ 178.900769] [<ffffffff8150587d>] rtnetlink_rcv_msg+0x11d/0x310 [ 178.906669] [<ffffffff81505760>] ? __rtnl_unlock+0x20/0x20 [ 178.912225] [<ffffffff81521f89>] netlink_rcv_skb+0xa9/0xd0 [ 178.917779] [<ffffffff81502d55>] rtnetlink_rcv+0x25/0x40 [ 178.923159] [<ffffffff815218d1>] netlink_unicast+0x1b1/0x230 [ 178.928887] [<ffffffff81521c4e>] netlink_sendmsg+0x2fe/0x3b0 [ 178.934615] [<ffffffff814dbe22>] sock_sendmsg+0xd2/0xf0 So we must check if peer was setup in veth_get_stats64() As pointed out by Ben Hutchings, priv->peer is missing proper synchronization. Adding RCU protection is a safe and well documented way to make sure we don't access about to be freed or already freed data. Reported-by: Tom Parkin <tparkin@katalix.com> Signed-off-by: Eric Dumazet <edumazet@google.com> CC: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 23:42:40 +08:00
if (!peer)
return -ENOTCONN;
if (priv->_xdp_prog) {
err = veth_enable_xdp(dev);
if (err)
return err;
}
veth: avoid a NULL deref in veth_stats_one commit 2681128f0ced8a (veth: extend device features) added a NULL deref in veth_stats_one(), as veth_get_stats64() was not testing if the peer device was setup or not. At init time, we call dev_get_stats() before veth pair is fully setup. [ 178.854758] [<ffffffffa00f5677>] veth_get_stats64+0x47/0x70 [veth] [ 178.861013] [<ffffffff814f0a2d>] dev_get_stats+0x6d/0x130 [ 178.866486] [<ffffffff81504efc>] rtnl_fill_ifinfo+0x47c/0x930 [ 178.872299] [<ffffffff81505b93>] rtmsg_ifinfo+0x83/0x100 [ 178.877678] [<ffffffff81505cc6>] rtnl_configure_link+0x76/0xa0 [ 178.883580] [<ffffffffa00f52fa>] veth_newlink+0x16a/0x350 [veth] [ 178.889654] [<ffffffff815061cc>] rtnl_newlink+0x4dc/0x5e0 [ 178.895128] [<ffffffff81505e1e>] ? rtnl_newlink+0x12e/0x5e0 [ 178.900769] [<ffffffff8150587d>] rtnetlink_rcv_msg+0x11d/0x310 [ 178.906669] [<ffffffff81505760>] ? __rtnl_unlock+0x20/0x20 [ 178.912225] [<ffffffff81521f89>] netlink_rcv_skb+0xa9/0xd0 [ 178.917779] [<ffffffff81502d55>] rtnetlink_rcv+0x25/0x40 [ 178.923159] [<ffffffff815218d1>] netlink_unicast+0x1b1/0x230 [ 178.928887] [<ffffffff81521c4e>] netlink_sendmsg+0x2fe/0x3b0 [ 178.934615] [<ffffffff814dbe22>] sock_sendmsg+0xd2/0xf0 So we must check if peer was setup in veth_get_stats64() As pointed out by Ben Hutchings, priv->peer is missing proper synchronization. Adding RCU protection is a safe and well documented way to make sure we don't access about to be freed or already freed data. Reported-by: Tom Parkin <tparkin@katalix.com> Signed-off-by: Eric Dumazet <edumazet@google.com> CC: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 23:42:40 +08:00
if (peer->flags & IFF_UP) {
netif_carrier_on(dev);
veth: avoid a NULL deref in veth_stats_one commit 2681128f0ced8a (veth: extend device features) added a NULL deref in veth_stats_one(), as veth_get_stats64() was not testing if the peer device was setup or not. At init time, we call dev_get_stats() before veth pair is fully setup. [ 178.854758] [<ffffffffa00f5677>] veth_get_stats64+0x47/0x70 [veth] [ 178.861013] [<ffffffff814f0a2d>] dev_get_stats+0x6d/0x130 [ 178.866486] [<ffffffff81504efc>] rtnl_fill_ifinfo+0x47c/0x930 [ 178.872299] [<ffffffff81505b93>] rtmsg_ifinfo+0x83/0x100 [ 178.877678] [<ffffffff81505cc6>] rtnl_configure_link+0x76/0xa0 [ 178.883580] [<ffffffffa00f52fa>] veth_newlink+0x16a/0x350 [veth] [ 178.889654] [<ffffffff815061cc>] rtnl_newlink+0x4dc/0x5e0 [ 178.895128] [<ffffffff81505e1e>] ? rtnl_newlink+0x12e/0x5e0 [ 178.900769] [<ffffffff8150587d>] rtnetlink_rcv_msg+0x11d/0x310 [ 178.906669] [<ffffffff81505760>] ? __rtnl_unlock+0x20/0x20 [ 178.912225] [<ffffffff81521f89>] netlink_rcv_skb+0xa9/0xd0 [ 178.917779] [<ffffffff81502d55>] rtnetlink_rcv+0x25/0x40 [ 178.923159] [<ffffffff815218d1>] netlink_unicast+0x1b1/0x230 [ 178.928887] [<ffffffff81521c4e>] netlink_sendmsg+0x2fe/0x3b0 [ 178.934615] [<ffffffff814dbe22>] sock_sendmsg+0xd2/0xf0 So we must check if peer was setup in veth_get_stats64() As pointed out by Ben Hutchings, priv->peer is missing proper synchronization. Adding RCU protection is a safe and well documented way to make sure we don't access about to be freed or already freed data. Reported-by: Tom Parkin <tparkin@katalix.com> Signed-off-by: Eric Dumazet <edumazet@google.com> CC: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 23:42:40 +08:00
netif_carrier_on(peer);
}
return 0;
}
static int veth_close(struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
struct net_device *peer = rtnl_dereference(priv->peer);
netif_carrier_off(dev);
if (peer)
netif_carrier_off(peer);
if (priv->_xdp_prog)
veth_disable_xdp(dev);
return 0;
}
net: use core MTU range checking in core net infra geneve: - Merge __geneve_change_mtu back into geneve_change_mtu, set max_mtu - This one isn't quite as straight-forward as others, could use some closer inspection and testing macvlan: - set min/max_mtu tun: - set min/max_mtu, remove tun_net_change_mtu vxlan: - Merge __vxlan_change_mtu back into vxlan_change_mtu - Set max_mtu to IP_MAX_MTU and retain dynamic MTU range checks in change_mtu function - This one is also not as straight-forward and could use closer inspection and testing from vxlan folks bridge: - set max_mtu of IP_MAX_MTU and retain dynamic MTU range checks in change_mtu function openvswitch: - set min/max_mtu, remove internal_dev_change_mtu - note: max_mtu wasn't checked previously, it's been set to 65535, which is the largest possible size supported sch_teql: - set min/max_mtu (note: max_mtu previously unchecked, used max of 65535) macsec: - min_mtu = 0, max_mtu = 65535 macvlan: - min_mtu = 0, max_mtu = 65535 ntb_netdev: - min_mtu = 0, max_mtu = 65535 veth: - min_mtu = 68, max_mtu = 65535 8021q: - min_mtu = 0, max_mtu = 65535 CC: netdev@vger.kernel.org CC: Nicolas Dichtel <nicolas.dichtel@6wind.com> CC: Hannes Frederic Sowa <hannes@stressinduktion.org> CC: Tom Herbert <tom@herbertland.com> CC: Daniel Borkmann <daniel@iogearbox.net> CC: Alexander Duyck <alexander.h.duyck@intel.com> CC: Paolo Abeni <pabeni@redhat.com> CC: Jiri Benc <jbenc@redhat.com> CC: WANG Cong <xiyou.wangcong@gmail.com> CC: Roopa Prabhu <roopa@cumulusnetworks.com> CC: Pravin B Shelar <pshelar@ovn.org> CC: Sabrina Dubroca <sd@queasysnail.net> CC: Patrick McHardy <kaber@trash.net> CC: Stephen Hemminger <stephen@networkplumber.org> CC: Pravin Shelar <pshelar@nicira.com> CC: Maxim Krasnyansky <maxk@qti.qualcomm.com> Signed-off-by: Jarod Wilson <jarod@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-21 01:55:20 +08:00
static int is_valid_veth_mtu(int mtu)
{
net: use core MTU range checking in core net infra geneve: - Merge __geneve_change_mtu back into geneve_change_mtu, set max_mtu - This one isn't quite as straight-forward as others, could use some closer inspection and testing macvlan: - set min/max_mtu tun: - set min/max_mtu, remove tun_net_change_mtu vxlan: - Merge __vxlan_change_mtu back into vxlan_change_mtu - Set max_mtu to IP_MAX_MTU and retain dynamic MTU range checks in change_mtu function - This one is also not as straight-forward and could use closer inspection and testing from vxlan folks bridge: - set max_mtu of IP_MAX_MTU and retain dynamic MTU range checks in change_mtu function openvswitch: - set min/max_mtu, remove internal_dev_change_mtu - note: max_mtu wasn't checked previously, it's been set to 65535, which is the largest possible size supported sch_teql: - set min/max_mtu (note: max_mtu previously unchecked, used max of 65535) macsec: - min_mtu = 0, max_mtu = 65535 macvlan: - min_mtu = 0, max_mtu = 65535 ntb_netdev: - min_mtu = 0, max_mtu = 65535 veth: - min_mtu = 68, max_mtu = 65535 8021q: - min_mtu = 0, max_mtu = 65535 CC: netdev@vger.kernel.org CC: Nicolas Dichtel <nicolas.dichtel@6wind.com> CC: Hannes Frederic Sowa <hannes@stressinduktion.org> CC: Tom Herbert <tom@herbertland.com> CC: Daniel Borkmann <daniel@iogearbox.net> CC: Alexander Duyck <alexander.h.duyck@intel.com> CC: Paolo Abeni <pabeni@redhat.com> CC: Jiri Benc <jbenc@redhat.com> CC: WANG Cong <xiyou.wangcong@gmail.com> CC: Roopa Prabhu <roopa@cumulusnetworks.com> CC: Pravin B Shelar <pshelar@ovn.org> CC: Sabrina Dubroca <sd@queasysnail.net> CC: Patrick McHardy <kaber@trash.net> CC: Stephen Hemminger <stephen@networkplumber.org> CC: Pravin Shelar <pshelar@nicira.com> CC: Maxim Krasnyansky <maxk@qti.qualcomm.com> Signed-off-by: Jarod Wilson <jarod@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-21 01:55:20 +08:00
return mtu >= ETH_MIN_MTU && mtu <= ETH_MAX_MTU;
}
veth: Free queues on link delete David Ahern reported memory leak in veth. ======================================================================= $ cat /sys/kernel/debug/kmemleak unreferenced object 0xffff8800354d5c00 (size 1024): comm "ip", pid 836, jiffies 4294722952 (age 25.904s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] kmemleak_alloc+0x70/0x94 [<(____ptrval____)>] slab_post_alloc_hook+0x42/0x52 [<(____ptrval____)>] __kmalloc+0x101/0x142 [<(____ptrval____)>] kmalloc_array.constprop.20+0x1e/0x26 [veth] [<(____ptrval____)>] veth_newlink+0x147/0x3ac [veth] ... unreferenced object 0xffff88002e009c00 (size 1024): comm "ip", pid 836, jiffies 4294722958 (age 25.898s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] kmemleak_alloc+0x70/0x94 [<(____ptrval____)>] slab_post_alloc_hook+0x42/0x52 [<(____ptrval____)>] __kmalloc+0x101/0x142 [<(____ptrval____)>] kmalloc_array.constprop.20+0x1e/0x26 [veth] [<(____ptrval____)>] veth_newlink+0x219/0x3ac [veth] ======================================================================= veth_rq allocated in veth_newlink() was not freed on dellink. We need to free up them after veth_close() so that any packets will not reference the queues afterwards. Thus free them in veth_dev_free() in the same way as freeing stats structure (vstats). Also move queues allocation to veth_dev_init() to be in line with stats allocation. Fixes: 638264dc90227 ("veth: Support per queue XDP ring") Reported-by: David Ahern <dsahern@gmail.com> Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-15 16:07:29 +08:00
static int veth_alloc_queues(struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
int i;
priv->rq = kcalloc(dev->num_rx_queues, sizeof(*priv->rq), GFP_KERNEL);
if (!priv->rq)
return -ENOMEM;
for (i = 0; i < dev->num_rx_queues; i++) {
veth: Free queues on link delete David Ahern reported memory leak in veth. ======================================================================= $ cat /sys/kernel/debug/kmemleak unreferenced object 0xffff8800354d5c00 (size 1024): comm "ip", pid 836, jiffies 4294722952 (age 25.904s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] kmemleak_alloc+0x70/0x94 [<(____ptrval____)>] slab_post_alloc_hook+0x42/0x52 [<(____ptrval____)>] __kmalloc+0x101/0x142 [<(____ptrval____)>] kmalloc_array.constprop.20+0x1e/0x26 [veth] [<(____ptrval____)>] veth_newlink+0x147/0x3ac [veth] ... unreferenced object 0xffff88002e009c00 (size 1024): comm "ip", pid 836, jiffies 4294722958 (age 25.898s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] kmemleak_alloc+0x70/0x94 [<(____ptrval____)>] slab_post_alloc_hook+0x42/0x52 [<(____ptrval____)>] __kmalloc+0x101/0x142 [<(____ptrval____)>] kmalloc_array.constprop.20+0x1e/0x26 [veth] [<(____ptrval____)>] veth_newlink+0x219/0x3ac [veth] ======================================================================= veth_rq allocated in veth_newlink() was not freed on dellink. We need to free up them after veth_close() so that any packets will not reference the queues afterwards. Thus free them in veth_dev_free() in the same way as freeing stats structure (vstats). Also move queues allocation to veth_dev_init() to be in line with stats allocation. Fixes: 638264dc90227 ("veth: Support per queue XDP ring") Reported-by: David Ahern <dsahern@gmail.com> Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-15 16:07:29 +08:00
priv->rq[i].dev = dev;
u64_stats_init(&priv->rq[i].stats.syncp);
}
veth: Free queues on link delete David Ahern reported memory leak in veth. ======================================================================= $ cat /sys/kernel/debug/kmemleak unreferenced object 0xffff8800354d5c00 (size 1024): comm "ip", pid 836, jiffies 4294722952 (age 25.904s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] kmemleak_alloc+0x70/0x94 [<(____ptrval____)>] slab_post_alloc_hook+0x42/0x52 [<(____ptrval____)>] __kmalloc+0x101/0x142 [<(____ptrval____)>] kmalloc_array.constprop.20+0x1e/0x26 [veth] [<(____ptrval____)>] veth_newlink+0x147/0x3ac [veth] ... unreferenced object 0xffff88002e009c00 (size 1024): comm "ip", pid 836, jiffies 4294722958 (age 25.898s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] kmemleak_alloc+0x70/0x94 [<(____ptrval____)>] slab_post_alloc_hook+0x42/0x52 [<(____ptrval____)>] __kmalloc+0x101/0x142 [<(____ptrval____)>] kmalloc_array.constprop.20+0x1e/0x26 [veth] [<(____ptrval____)>] veth_newlink+0x219/0x3ac [veth] ======================================================================= veth_rq allocated in veth_newlink() was not freed on dellink. We need to free up them after veth_close() so that any packets will not reference the queues afterwards. Thus free them in veth_dev_free() in the same way as freeing stats structure (vstats). Also move queues allocation to veth_dev_init() to be in line with stats allocation. Fixes: 638264dc90227 ("veth: Support per queue XDP ring") Reported-by: David Ahern <dsahern@gmail.com> Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-15 16:07:29 +08:00
return 0;
}
static void veth_free_queues(struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
kfree(priv->rq);
}
static int veth_dev_init(struct net_device *dev)
{
veth: Free queues on link delete David Ahern reported memory leak in veth. ======================================================================= $ cat /sys/kernel/debug/kmemleak unreferenced object 0xffff8800354d5c00 (size 1024): comm "ip", pid 836, jiffies 4294722952 (age 25.904s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] kmemleak_alloc+0x70/0x94 [<(____ptrval____)>] slab_post_alloc_hook+0x42/0x52 [<(____ptrval____)>] __kmalloc+0x101/0x142 [<(____ptrval____)>] kmalloc_array.constprop.20+0x1e/0x26 [veth] [<(____ptrval____)>] veth_newlink+0x147/0x3ac [veth] ... unreferenced object 0xffff88002e009c00 (size 1024): comm "ip", pid 836, jiffies 4294722958 (age 25.898s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] kmemleak_alloc+0x70/0x94 [<(____ptrval____)>] slab_post_alloc_hook+0x42/0x52 [<(____ptrval____)>] __kmalloc+0x101/0x142 [<(____ptrval____)>] kmalloc_array.constprop.20+0x1e/0x26 [veth] [<(____ptrval____)>] veth_newlink+0x219/0x3ac [veth] ======================================================================= veth_rq allocated in veth_newlink() was not freed on dellink. We need to free up them after veth_close() so that any packets will not reference the queues afterwards. Thus free them in veth_dev_free() in the same way as freeing stats structure (vstats). Also move queues allocation to veth_dev_init() to be in line with stats allocation. Fixes: 638264dc90227 ("veth: Support per queue XDP ring") Reported-by: David Ahern <dsahern@gmail.com> Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-15 16:07:29 +08:00
int err;
dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
if (!dev->lstats)
return -ENOMEM;
veth: Free queues on link delete David Ahern reported memory leak in veth. ======================================================================= $ cat /sys/kernel/debug/kmemleak unreferenced object 0xffff8800354d5c00 (size 1024): comm "ip", pid 836, jiffies 4294722952 (age 25.904s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] kmemleak_alloc+0x70/0x94 [<(____ptrval____)>] slab_post_alloc_hook+0x42/0x52 [<(____ptrval____)>] __kmalloc+0x101/0x142 [<(____ptrval____)>] kmalloc_array.constprop.20+0x1e/0x26 [veth] [<(____ptrval____)>] veth_newlink+0x147/0x3ac [veth] ... unreferenced object 0xffff88002e009c00 (size 1024): comm "ip", pid 836, jiffies 4294722958 (age 25.898s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] kmemleak_alloc+0x70/0x94 [<(____ptrval____)>] slab_post_alloc_hook+0x42/0x52 [<(____ptrval____)>] __kmalloc+0x101/0x142 [<(____ptrval____)>] kmalloc_array.constprop.20+0x1e/0x26 [veth] [<(____ptrval____)>] veth_newlink+0x219/0x3ac [veth] ======================================================================= veth_rq allocated in veth_newlink() was not freed on dellink. We need to free up them after veth_close() so that any packets will not reference the queues afterwards. Thus free them in veth_dev_free() in the same way as freeing stats structure (vstats). Also move queues allocation to veth_dev_init() to be in line with stats allocation. Fixes: 638264dc90227 ("veth: Support per queue XDP ring") Reported-by: David Ahern <dsahern@gmail.com> Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-15 16:07:29 +08:00
err = veth_alloc_queues(dev);
if (err) {
free_percpu(dev->lstats);
veth: Free queues on link delete David Ahern reported memory leak in veth. ======================================================================= $ cat /sys/kernel/debug/kmemleak unreferenced object 0xffff8800354d5c00 (size 1024): comm "ip", pid 836, jiffies 4294722952 (age 25.904s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] kmemleak_alloc+0x70/0x94 [<(____ptrval____)>] slab_post_alloc_hook+0x42/0x52 [<(____ptrval____)>] __kmalloc+0x101/0x142 [<(____ptrval____)>] kmalloc_array.constprop.20+0x1e/0x26 [veth] [<(____ptrval____)>] veth_newlink+0x147/0x3ac [veth] ... unreferenced object 0xffff88002e009c00 (size 1024): comm "ip", pid 836, jiffies 4294722958 (age 25.898s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] kmemleak_alloc+0x70/0x94 [<(____ptrval____)>] slab_post_alloc_hook+0x42/0x52 [<(____ptrval____)>] __kmalloc+0x101/0x142 [<(____ptrval____)>] kmalloc_array.constprop.20+0x1e/0x26 [veth] [<(____ptrval____)>] veth_newlink+0x219/0x3ac [veth] ======================================================================= veth_rq allocated in veth_newlink() was not freed on dellink. We need to free up them after veth_close() so that any packets will not reference the queues afterwards. Thus free them in veth_dev_free() in the same way as freeing stats structure (vstats). Also move queues allocation to veth_dev_init() to be in line with stats allocation. Fixes: 638264dc90227 ("veth: Support per queue XDP ring") Reported-by: David Ahern <dsahern@gmail.com> Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-15 16:07:29 +08:00
return err;
}
return 0;
}
static void veth_dev_free(struct net_device *dev)
{
veth: Free queues on link delete David Ahern reported memory leak in veth. ======================================================================= $ cat /sys/kernel/debug/kmemleak unreferenced object 0xffff8800354d5c00 (size 1024): comm "ip", pid 836, jiffies 4294722952 (age 25.904s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] kmemleak_alloc+0x70/0x94 [<(____ptrval____)>] slab_post_alloc_hook+0x42/0x52 [<(____ptrval____)>] __kmalloc+0x101/0x142 [<(____ptrval____)>] kmalloc_array.constprop.20+0x1e/0x26 [veth] [<(____ptrval____)>] veth_newlink+0x147/0x3ac [veth] ... unreferenced object 0xffff88002e009c00 (size 1024): comm "ip", pid 836, jiffies 4294722958 (age 25.898s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] kmemleak_alloc+0x70/0x94 [<(____ptrval____)>] slab_post_alloc_hook+0x42/0x52 [<(____ptrval____)>] __kmalloc+0x101/0x142 [<(____ptrval____)>] kmalloc_array.constprop.20+0x1e/0x26 [veth] [<(____ptrval____)>] veth_newlink+0x219/0x3ac [veth] ======================================================================= veth_rq allocated in veth_newlink() was not freed on dellink. We need to free up them after veth_close() so that any packets will not reference the queues afterwards. Thus free them in veth_dev_free() in the same way as freeing stats structure (vstats). Also move queues allocation to veth_dev_init() to be in line with stats allocation. Fixes: 638264dc90227 ("veth: Support per queue XDP ring") Reported-by: David Ahern <dsahern@gmail.com> Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-15 16:07:29 +08:00
veth_free_queues(dev);
free_percpu(dev->lstats);
}
#ifdef CONFIG_NET_POLL_CONTROLLER
static void veth_poll_controller(struct net_device *dev)
{
/* veth only receives frames when its peer sends one
* Since it has nothing to do with disabling irqs, we are guaranteed
* never to have pending data when we poll for it so
* there is nothing to do here.
*
* We need this though so netpoll recognizes us as an interface that
* supports polling, which enables bridge devices in virt setups to
* still use netconsole
*/
}
#endif /* CONFIG_NET_POLL_CONTROLLER */
static int veth_get_iflink(const struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
struct net_device *peer;
int iflink;
rcu_read_lock();
peer = rcu_dereference(priv->peer);
iflink = peer ? peer->ifindex : 0;
rcu_read_unlock();
return iflink;
}
static netdev_features_t veth_fix_features(struct net_device *dev,
netdev_features_t features)
{
struct veth_priv *priv = netdev_priv(dev);
struct net_device *peer;
peer = rtnl_dereference(priv->peer);
if (peer) {
struct veth_priv *peer_priv = netdev_priv(peer);
if (peer_priv->_xdp_prog)
features &= ~NETIF_F_GSO_SOFTWARE;
}
return features;
}
static void veth_set_rx_headroom(struct net_device *dev, int new_hr)
{
struct veth_priv *peer_priv, *priv = netdev_priv(dev);
struct net_device *peer;
if (new_hr < 0)
new_hr = 0;
rcu_read_lock();
peer = rcu_dereference(priv->peer);
if (unlikely(!peer))
goto out;
peer_priv = netdev_priv(peer);
priv->requested_headroom = new_hr;
new_hr = max(priv->requested_headroom, peer_priv->requested_headroom);
dev->needed_headroom = new_hr;
peer->needed_headroom = new_hr;
out:
rcu_read_unlock();
}
static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
struct netlink_ext_ack *extack)
{
struct veth_priv *priv = netdev_priv(dev);
struct bpf_prog *old_prog;
struct net_device *peer;
unsigned int max_mtu;
int err;
old_prog = priv->_xdp_prog;
priv->_xdp_prog = prog;
peer = rtnl_dereference(priv->peer);
if (prog) {
if (!peer) {
NL_SET_ERR_MSG_MOD(extack, "Cannot set XDP when peer is detached");
err = -ENOTCONN;
goto err;
}
max_mtu = PAGE_SIZE - VETH_XDP_HEADROOM -
peer->hard_header_len -
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
if (peer->mtu > max_mtu) {
NL_SET_ERR_MSG_MOD(extack, "Peer MTU is too large to set XDP");
err = -ERANGE;
goto err;
}
if (dev->real_num_rx_queues < peer->real_num_tx_queues) {
NL_SET_ERR_MSG_MOD(extack, "XDP expects number of rx queues not less than peer tx queues");
err = -ENOSPC;
goto err;
}
if (dev->flags & IFF_UP) {
err = veth_enable_xdp(dev);
if (err) {
NL_SET_ERR_MSG_MOD(extack, "Setup for XDP failed");
goto err;
}
}
if (!old_prog) {
peer->hw_features &= ~NETIF_F_GSO_SOFTWARE;
peer->max_mtu = max_mtu;
}
}
if (old_prog) {
if (!prog) {
if (dev->flags & IFF_UP)
veth_disable_xdp(dev);
if (peer) {
peer->hw_features |= NETIF_F_GSO_SOFTWARE;
peer->max_mtu = ETH_MAX_MTU;
}
}
bpf_prog_put(old_prog);
}
if ((!!old_prog ^ !!prog) && peer)
netdev_update_features(peer);
return 0;
err:
priv->_xdp_prog = old_prog;
return err;
}
static u32 veth_xdp_query(struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
const struct bpf_prog *xdp_prog;
xdp_prog = priv->_xdp_prog;
if (xdp_prog)
return xdp_prog->aux->id;
return 0;
}
static int veth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
{
switch (xdp->command) {
case XDP_SETUP_PROG:
return veth_xdp_set(dev, xdp->prog, xdp->extack);
case XDP_QUERY_PROG:
xdp->prog_id = veth_xdp_query(dev);
return 0;
default:
return -EINVAL;
}
}
static const struct net_device_ops veth_netdev_ops = {
.ndo_init = veth_dev_init,
.ndo_open = veth_open,
.ndo_stop = veth_close,
.ndo_start_xmit = veth_xmit,
.ndo_get_stats64 = veth_get_stats64,
.ndo_set_rx_mode = veth_set_multicast_list,
.ndo_set_mac_address = eth_mac_addr,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = veth_poll_controller,
#endif
.ndo_get_iflink = veth_get_iflink,
.ndo_fix_features = veth_fix_features,
.ndo_features_check = passthru_features_check,
.ndo_set_rx_headroom = veth_set_rx_headroom,
.ndo_bpf = veth_xdp,
.ndo_xdp_xmit = veth_xdp_xmit,
};
#define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \
NETIF_F_RXCSUM | NETIF_F_SCTP_CRC | NETIF_F_HIGHDMA | \
NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL | \
NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | \
NETIF_F_HW_VLAN_STAG_TX | NETIF_F_HW_VLAN_STAG_RX )
static void veth_setup(struct net_device *dev)
{
ether_setup(dev);
dev->priv_flags &= ~IFF_TX_SKB_SHARING;
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
dev->priv_flags |= IFF_NO_QUEUE;
dev->priv_flags |= IFF_PHONY_HEADROOM;
dev->netdev_ops = &veth_netdev_ops;
dev->ethtool_ops = &veth_ethtool_ops;
dev->features |= NETIF_F_LLTX;
dev->features |= VETH_FEATURES;
dev->vlan_features = dev->features &
~(NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX |
NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_HW_VLAN_STAG_RX);
net: Fix inconsistent teardown and release of private netdev state. Network devices can allocate reasources and private memory using netdev_ops->ndo_init(). However, the release of these resources can occur in one of two different places. Either netdev_ops->ndo_uninit() or netdev->destructor(). The decision of which operation frees the resources depends upon whether it is necessary for all netdev refs to be released before it is safe to perform the freeing. netdev_ops->ndo_uninit() presumably can occur right after the NETDEV_UNREGISTER notifier completes and the unicast and multicast address lists are flushed. netdev->destructor(), on the other hand, does not run until the netdev references all go away. Further complicating the situation is that netdev->destructor() almost universally does also a free_netdev(). This creates a problem for the logic in register_netdevice(). Because all callers of register_netdevice() manage the freeing of the netdev, and invoke free_netdev(dev) if register_netdevice() fails. If netdev_ops->ndo_init() succeeds, but something else fails inside of register_netdevice(), it does call ndo_ops->ndo_uninit(). But it is not able to invoke netdev->destructor(). This is because netdev->destructor() will do a free_netdev() and then the caller of register_netdevice() will do the same. However, this means that the resources that would normally be released by netdev->destructor() will not be. Over the years drivers have added local hacks to deal with this, by invoking their destructor parts by hand when register_netdevice() fails. Many drivers do not try to deal with this, and instead we have leaks. Let's close this hole by formalizing the distinction between what private things need to be freed up by netdev->destructor() and whether the driver needs unregister_netdevice() to perform the free_netdev(). netdev->priv_destructor() performs all actions to free up the private resources that used to be freed by netdev->destructor(), except for free_netdev(). netdev->needs_free_netdev is a boolean that indicates whether free_netdev() should be done at the end of unregister_netdevice(). Now, register_netdevice() can sanely release all resources after ndo_ops->ndo_init() succeeds, by invoking both ndo_ops->ndo_uninit() and netdev->priv_destructor(). And at the end of unregister_netdevice(), we invoke netdev->priv_destructor() and optionally call free_netdev(). Signed-off-by: David S. Miller <davem@davemloft.net>
2017-05-09 00:52:56 +08:00
dev->needs_free_netdev = true;
dev->priv_destructor = veth_dev_free;
net: use core MTU range checking in core net infra geneve: - Merge __geneve_change_mtu back into geneve_change_mtu, set max_mtu - This one isn't quite as straight-forward as others, could use some closer inspection and testing macvlan: - set min/max_mtu tun: - set min/max_mtu, remove tun_net_change_mtu vxlan: - Merge __vxlan_change_mtu back into vxlan_change_mtu - Set max_mtu to IP_MAX_MTU and retain dynamic MTU range checks in change_mtu function - This one is also not as straight-forward and could use closer inspection and testing from vxlan folks bridge: - set max_mtu of IP_MAX_MTU and retain dynamic MTU range checks in change_mtu function openvswitch: - set min/max_mtu, remove internal_dev_change_mtu - note: max_mtu wasn't checked previously, it's been set to 65535, which is the largest possible size supported sch_teql: - set min/max_mtu (note: max_mtu previously unchecked, used max of 65535) macsec: - min_mtu = 0, max_mtu = 65535 macvlan: - min_mtu = 0, max_mtu = 65535 ntb_netdev: - min_mtu = 0, max_mtu = 65535 veth: - min_mtu = 68, max_mtu = 65535 8021q: - min_mtu = 0, max_mtu = 65535 CC: netdev@vger.kernel.org CC: Nicolas Dichtel <nicolas.dichtel@6wind.com> CC: Hannes Frederic Sowa <hannes@stressinduktion.org> CC: Tom Herbert <tom@herbertland.com> CC: Daniel Borkmann <daniel@iogearbox.net> CC: Alexander Duyck <alexander.h.duyck@intel.com> CC: Paolo Abeni <pabeni@redhat.com> CC: Jiri Benc <jbenc@redhat.com> CC: WANG Cong <xiyou.wangcong@gmail.com> CC: Roopa Prabhu <roopa@cumulusnetworks.com> CC: Pravin B Shelar <pshelar@ovn.org> CC: Sabrina Dubroca <sd@queasysnail.net> CC: Patrick McHardy <kaber@trash.net> CC: Stephen Hemminger <stephen@networkplumber.org> CC: Pravin Shelar <pshelar@nicira.com> CC: Maxim Krasnyansky <maxk@qti.qualcomm.com> Signed-off-by: Jarod Wilson <jarod@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-21 01:55:20 +08:00
dev->max_mtu = ETH_MAX_MTU;
dev->hw_features = VETH_FEATURES;
dev->hw_enc_features = VETH_FEATURES;
dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE;
}
/*
* netlink interface
*/
static int veth_validate(struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
if (tb[IFLA_ADDRESS]) {
if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
return -EINVAL;
if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
return -EADDRNOTAVAIL;
}
if (tb[IFLA_MTU]) {
if (!is_valid_veth_mtu(nla_get_u32(tb[IFLA_MTU])))
return -EINVAL;
}
return 0;
}
static struct rtnl_link_ops veth_link_ops;
static int veth_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
veth: Free queues on link delete David Ahern reported memory leak in veth. ======================================================================= $ cat /sys/kernel/debug/kmemleak unreferenced object 0xffff8800354d5c00 (size 1024): comm "ip", pid 836, jiffies 4294722952 (age 25.904s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] kmemleak_alloc+0x70/0x94 [<(____ptrval____)>] slab_post_alloc_hook+0x42/0x52 [<(____ptrval____)>] __kmalloc+0x101/0x142 [<(____ptrval____)>] kmalloc_array.constprop.20+0x1e/0x26 [veth] [<(____ptrval____)>] veth_newlink+0x147/0x3ac [veth] ... unreferenced object 0xffff88002e009c00 (size 1024): comm "ip", pid 836, jiffies 4294722958 (age 25.898s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] kmemleak_alloc+0x70/0x94 [<(____ptrval____)>] slab_post_alloc_hook+0x42/0x52 [<(____ptrval____)>] __kmalloc+0x101/0x142 [<(____ptrval____)>] kmalloc_array.constprop.20+0x1e/0x26 [veth] [<(____ptrval____)>] veth_newlink+0x219/0x3ac [veth] ======================================================================= veth_rq allocated in veth_newlink() was not freed on dellink. We need to free up them after veth_close() so that any packets will not reference the queues afterwards. Thus free them in veth_dev_free() in the same way as freeing stats structure (vstats). Also move queues allocation to veth_dev_init() to be in line with stats allocation. Fixes: 638264dc90227 ("veth: Support per queue XDP ring") Reported-by: David Ahern <dsahern@gmail.com> Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-15 16:07:29 +08:00
int err;
struct net_device *peer;
struct veth_priv *priv;
char ifname[IFNAMSIZ];
struct nlattr *peer_tb[IFLA_MAX + 1], **tbp;
unsigned char name_assign_type;
rtnetlink: support specifying device flags on device creation commit e8469ed959c373c2ff9e6f488aa5a14971aebe1f Author: Patrick McHardy <kaber@trash.net> Date: Tue Feb 23 20:41:30 2010 +0100 Support specifying the initial device flags when creating a device though rtnl_link. Devices allocated by rtnl_create_link() are marked as INITIALIZING in order to surpress netlink registration notifications. To complete setup, rtnl_configure_link() must be called, which performs the device flag changes and invokes the deferred notifiers if everything went well. Two examples: # add macvlan to eth0 # $ ip link add link eth0 up allmulticast on type macvlan [LINK]11: macvlan0@eth0: <BROADCAST,MULTICAST,ALLMULTI,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN link/ether 26:f8:84:02:f9:2a brd ff:ff:ff:ff:ff:ff [ROUTE]ff00::/8 dev macvlan0 table local metric 256 mtu 1500 advmss 1440 hoplimit 0 [ROUTE]fe80::/64 dev macvlan0 proto kernel metric 256 mtu 1500 advmss 1440 hoplimit 0 [LINK]11: macvlan0@eth0: <BROADCAST,MULTICAST,ALLMULTI,UP,LOWER_UP> mtu 1500 link/ether 26:f8:84:02:f9:2a [ADDR]11: macvlan0 inet6 fe80::24f8:84ff:fe02:f92a/64 scope link valid_lft forever preferred_lft forever [ROUTE]local fe80::24f8:84ff:fe02:f92a via :: dev lo table local proto none metric 0 mtu 16436 advmss 16376 hoplimit 0 [ROUTE]default via fe80::215:e9ff:fef0:10f8 dev macvlan0 proto kernel metric 1024 mtu 1500 advmss 1440 hoplimit 0 [NEIGH]fe80::215:e9ff:fef0:10f8 dev macvlan0 lladdr 00:15:e9:f0:10:f8 router STALE [ROUTE]2001:6f8:974::/64 dev macvlan0 proto kernel metric 256 expires 0sec mtu 1500 advmss 1440 hoplimit 0 [PREFIX]prefix 2001:6f8:974::/64 dev macvlan0 onlink autoconf valid 14400 preferred 131084 [ADDR]11: macvlan0 inet6 2001:6f8:974:0:24f8:84ff:fe02:f92a/64 scope global dynamic valid_lft 86399sec preferred_lft 14399sec # add VLAN to eth1, eth1 is down # $ ip link add link eth1 up type vlan id 1000 RTNETLINK answers: Network is down <no events> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-26 14:34:54 +08:00
struct ifinfomsg *ifmp;
struct net *net;
/*
* create and register peer first
*/
if (data != NULL && data[VETH_INFO_PEER] != NULL) {
struct nlattr *nla_peer;
nla_peer = data[VETH_INFO_PEER];
rtnetlink: support specifying device flags on device creation commit e8469ed959c373c2ff9e6f488aa5a14971aebe1f Author: Patrick McHardy <kaber@trash.net> Date: Tue Feb 23 20:41:30 2010 +0100 Support specifying the initial device flags when creating a device though rtnl_link. Devices allocated by rtnl_create_link() are marked as INITIALIZING in order to surpress netlink registration notifications. To complete setup, rtnl_configure_link() must be called, which performs the device flag changes and invokes the deferred notifiers if everything went well. Two examples: # add macvlan to eth0 # $ ip link add link eth0 up allmulticast on type macvlan [LINK]11: macvlan0@eth0: <BROADCAST,MULTICAST,ALLMULTI,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN link/ether 26:f8:84:02:f9:2a brd ff:ff:ff:ff:ff:ff [ROUTE]ff00::/8 dev macvlan0 table local metric 256 mtu 1500 advmss 1440 hoplimit 0 [ROUTE]fe80::/64 dev macvlan0 proto kernel metric 256 mtu 1500 advmss 1440 hoplimit 0 [LINK]11: macvlan0@eth0: <BROADCAST,MULTICAST,ALLMULTI,UP,LOWER_UP> mtu 1500 link/ether 26:f8:84:02:f9:2a [ADDR]11: macvlan0 inet6 fe80::24f8:84ff:fe02:f92a/64 scope link valid_lft forever preferred_lft forever [ROUTE]local fe80::24f8:84ff:fe02:f92a via :: dev lo table local proto none metric 0 mtu 16436 advmss 16376 hoplimit 0 [ROUTE]default via fe80::215:e9ff:fef0:10f8 dev macvlan0 proto kernel metric 1024 mtu 1500 advmss 1440 hoplimit 0 [NEIGH]fe80::215:e9ff:fef0:10f8 dev macvlan0 lladdr 00:15:e9:f0:10:f8 router STALE [ROUTE]2001:6f8:974::/64 dev macvlan0 proto kernel metric 256 expires 0sec mtu 1500 advmss 1440 hoplimit 0 [PREFIX]prefix 2001:6f8:974::/64 dev macvlan0 onlink autoconf valid 14400 preferred 131084 [ADDR]11: macvlan0 inet6 2001:6f8:974:0:24f8:84ff:fe02:f92a/64 scope global dynamic valid_lft 86399sec preferred_lft 14399sec # add VLAN to eth1, eth1 is down # $ ip link add link eth1 up type vlan id 1000 RTNETLINK answers: Network is down <no events> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-26 14:34:54 +08:00
ifmp = nla_data(nla_peer);
err = rtnl_nla_parse_ifla(peer_tb,
nla_data(nla_peer) + sizeof(struct ifinfomsg),
nla_len(nla_peer) - sizeof(struct ifinfomsg),
NULL);
if (err < 0)
return err;
err = veth_validate(peer_tb, NULL, extack);
if (err < 0)
return err;
tbp = peer_tb;
rtnetlink: support specifying device flags on device creation commit e8469ed959c373c2ff9e6f488aa5a14971aebe1f Author: Patrick McHardy <kaber@trash.net> Date: Tue Feb 23 20:41:30 2010 +0100 Support specifying the initial device flags when creating a device though rtnl_link. Devices allocated by rtnl_create_link() are marked as INITIALIZING in order to surpress netlink registration notifications. To complete setup, rtnl_configure_link() must be called, which performs the device flag changes and invokes the deferred notifiers if everything went well. Two examples: # add macvlan to eth0 # $ ip link add link eth0 up allmulticast on type macvlan [LINK]11: macvlan0@eth0: <BROADCAST,MULTICAST,ALLMULTI,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN link/ether 26:f8:84:02:f9:2a brd ff:ff:ff:ff:ff:ff [ROUTE]ff00::/8 dev macvlan0 table local metric 256 mtu 1500 advmss 1440 hoplimit 0 [ROUTE]fe80::/64 dev macvlan0 proto kernel metric 256 mtu 1500 advmss 1440 hoplimit 0 [LINK]11: macvlan0@eth0: <BROADCAST,MULTICAST,ALLMULTI,UP,LOWER_UP> mtu 1500 link/ether 26:f8:84:02:f9:2a [ADDR]11: macvlan0 inet6 fe80::24f8:84ff:fe02:f92a/64 scope link valid_lft forever preferred_lft forever [ROUTE]local fe80::24f8:84ff:fe02:f92a via :: dev lo table local proto none metric 0 mtu 16436 advmss 16376 hoplimit 0 [ROUTE]default via fe80::215:e9ff:fef0:10f8 dev macvlan0 proto kernel metric 1024 mtu 1500 advmss 1440 hoplimit 0 [NEIGH]fe80::215:e9ff:fef0:10f8 dev macvlan0 lladdr 00:15:e9:f0:10:f8 router STALE [ROUTE]2001:6f8:974::/64 dev macvlan0 proto kernel metric 256 expires 0sec mtu 1500 advmss 1440 hoplimit 0 [PREFIX]prefix 2001:6f8:974::/64 dev macvlan0 onlink autoconf valid 14400 preferred 131084 [ADDR]11: macvlan0 inet6 2001:6f8:974:0:24f8:84ff:fe02:f92a/64 scope global dynamic valid_lft 86399sec preferred_lft 14399sec # add VLAN to eth1, eth1 is down # $ ip link add link eth1 up type vlan id 1000 RTNETLINK answers: Network is down <no events> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-26 14:34:54 +08:00
} else {
ifmp = NULL;
tbp = tb;
rtnetlink: support specifying device flags on device creation commit e8469ed959c373c2ff9e6f488aa5a14971aebe1f Author: Patrick McHardy <kaber@trash.net> Date: Tue Feb 23 20:41:30 2010 +0100 Support specifying the initial device flags when creating a device though rtnl_link. Devices allocated by rtnl_create_link() are marked as INITIALIZING in order to surpress netlink registration notifications. To complete setup, rtnl_configure_link() must be called, which performs the device flag changes and invokes the deferred notifiers if everything went well. Two examples: # add macvlan to eth0 # $ ip link add link eth0 up allmulticast on type macvlan [LINK]11: macvlan0@eth0: <BROADCAST,MULTICAST,ALLMULTI,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN link/ether 26:f8:84:02:f9:2a brd ff:ff:ff:ff:ff:ff [ROUTE]ff00::/8 dev macvlan0 table local metric 256 mtu 1500 advmss 1440 hoplimit 0 [ROUTE]fe80::/64 dev macvlan0 proto kernel metric 256 mtu 1500 advmss 1440 hoplimit 0 [LINK]11: macvlan0@eth0: <BROADCAST,MULTICAST,ALLMULTI,UP,LOWER_UP> mtu 1500 link/ether 26:f8:84:02:f9:2a [ADDR]11: macvlan0 inet6 fe80::24f8:84ff:fe02:f92a/64 scope link valid_lft forever preferred_lft forever [ROUTE]local fe80::24f8:84ff:fe02:f92a via :: dev lo table local proto none metric 0 mtu 16436 advmss 16376 hoplimit 0 [ROUTE]default via fe80::215:e9ff:fef0:10f8 dev macvlan0 proto kernel metric 1024 mtu 1500 advmss 1440 hoplimit 0 [NEIGH]fe80::215:e9ff:fef0:10f8 dev macvlan0 lladdr 00:15:e9:f0:10:f8 router STALE [ROUTE]2001:6f8:974::/64 dev macvlan0 proto kernel metric 256 expires 0sec mtu 1500 advmss 1440 hoplimit 0 [PREFIX]prefix 2001:6f8:974::/64 dev macvlan0 onlink autoconf valid 14400 preferred 131084 [ADDR]11: macvlan0 inet6 2001:6f8:974:0:24f8:84ff:fe02:f92a/64 scope global dynamic valid_lft 86399sec preferred_lft 14399sec # add VLAN to eth1, eth1 is down # $ ip link add link eth1 up type vlan id 1000 RTNETLINK answers: Network is down <no events> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-26 14:34:54 +08:00
}
if (ifmp && tbp[IFLA_IFNAME]) {
nla_strlcpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
name_assign_type = NET_NAME_USER;
} else {
snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d");
name_assign_type = NET_NAME_ENUM;
}
net = rtnl_link_get_net(src_net, tbp);
if (IS_ERR(net))
return PTR_ERR(net);
peer = rtnl_create_link(net, ifname, name_assign_type,
&veth_link_ops, tbp, extack);
if (IS_ERR(peer)) {
put_net(net);
return PTR_ERR(peer);
}
if (!ifmp || !tbp[IFLA_ADDRESS])
eth_hw_addr_random(peer);
if (ifmp && (dev->ifindex != 0))
peer->ifindex = ifmp->ifi_index;
peer->gso_max_size = dev->gso_max_size;
peer->gso_max_segs = dev->gso_max_segs;
err = register_netdevice(peer);
put_net(net);
net = NULL;
if (err < 0)
goto err_register_peer;
netif_carrier_off(peer);
rtnetlink: support specifying device flags on device creation commit e8469ed959c373c2ff9e6f488aa5a14971aebe1f Author: Patrick McHardy <kaber@trash.net> Date: Tue Feb 23 20:41:30 2010 +0100 Support specifying the initial device flags when creating a device though rtnl_link. Devices allocated by rtnl_create_link() are marked as INITIALIZING in order to surpress netlink registration notifications. To complete setup, rtnl_configure_link() must be called, which performs the device flag changes and invokes the deferred notifiers if everything went well. Two examples: # add macvlan to eth0 # $ ip link add link eth0 up allmulticast on type macvlan [LINK]11: macvlan0@eth0: <BROADCAST,MULTICAST,ALLMULTI,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN link/ether 26:f8:84:02:f9:2a brd ff:ff:ff:ff:ff:ff [ROUTE]ff00::/8 dev macvlan0 table local metric 256 mtu 1500 advmss 1440 hoplimit 0 [ROUTE]fe80::/64 dev macvlan0 proto kernel metric 256 mtu 1500 advmss 1440 hoplimit 0 [LINK]11: macvlan0@eth0: <BROADCAST,MULTICAST,ALLMULTI,UP,LOWER_UP> mtu 1500 link/ether 26:f8:84:02:f9:2a [ADDR]11: macvlan0 inet6 fe80::24f8:84ff:fe02:f92a/64 scope link valid_lft forever preferred_lft forever [ROUTE]local fe80::24f8:84ff:fe02:f92a via :: dev lo table local proto none metric 0 mtu 16436 advmss 16376 hoplimit 0 [ROUTE]default via fe80::215:e9ff:fef0:10f8 dev macvlan0 proto kernel metric 1024 mtu 1500 advmss 1440 hoplimit 0 [NEIGH]fe80::215:e9ff:fef0:10f8 dev macvlan0 lladdr 00:15:e9:f0:10:f8 router STALE [ROUTE]2001:6f8:974::/64 dev macvlan0 proto kernel metric 256 expires 0sec mtu 1500 advmss 1440 hoplimit 0 [PREFIX]prefix 2001:6f8:974::/64 dev macvlan0 onlink autoconf valid 14400 preferred 131084 [ADDR]11: macvlan0 inet6 2001:6f8:974:0:24f8:84ff:fe02:f92a/64 scope global dynamic valid_lft 86399sec preferred_lft 14399sec # add VLAN to eth1, eth1 is down # $ ip link add link eth1 up type vlan id 1000 RTNETLINK answers: Network is down <no events> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-26 14:34:54 +08:00
err = rtnl_configure_link(peer, ifmp);
if (err < 0)
goto err_configure_peer;
/*
* register dev last
*
* note, that since we've registered new device the dev's name
* should be re-allocated
*/
if (tb[IFLA_ADDRESS] == NULL)
eth_hw_addr_random(dev);
if (tb[IFLA_IFNAME])
nla_strlcpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
else
snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d");
err = register_netdevice(dev);
if (err < 0)
goto err_register_dev;
netif_carrier_off(dev);
/*
* tie the deviced together
*/
priv = netdev_priv(dev);
veth: avoid a NULL deref in veth_stats_one commit 2681128f0ced8a (veth: extend device features) added a NULL deref in veth_stats_one(), as veth_get_stats64() was not testing if the peer device was setup or not. At init time, we call dev_get_stats() before veth pair is fully setup. [ 178.854758] [<ffffffffa00f5677>] veth_get_stats64+0x47/0x70 [veth] [ 178.861013] [<ffffffff814f0a2d>] dev_get_stats+0x6d/0x130 [ 178.866486] [<ffffffff81504efc>] rtnl_fill_ifinfo+0x47c/0x930 [ 178.872299] [<ffffffff81505b93>] rtmsg_ifinfo+0x83/0x100 [ 178.877678] [<ffffffff81505cc6>] rtnl_configure_link+0x76/0xa0 [ 178.883580] [<ffffffffa00f52fa>] veth_newlink+0x16a/0x350 [veth] [ 178.889654] [<ffffffff815061cc>] rtnl_newlink+0x4dc/0x5e0 [ 178.895128] [<ffffffff81505e1e>] ? rtnl_newlink+0x12e/0x5e0 [ 178.900769] [<ffffffff8150587d>] rtnetlink_rcv_msg+0x11d/0x310 [ 178.906669] [<ffffffff81505760>] ? __rtnl_unlock+0x20/0x20 [ 178.912225] [<ffffffff81521f89>] netlink_rcv_skb+0xa9/0xd0 [ 178.917779] [<ffffffff81502d55>] rtnetlink_rcv+0x25/0x40 [ 178.923159] [<ffffffff815218d1>] netlink_unicast+0x1b1/0x230 [ 178.928887] [<ffffffff81521c4e>] netlink_sendmsg+0x2fe/0x3b0 [ 178.934615] [<ffffffff814dbe22>] sock_sendmsg+0xd2/0xf0 So we must check if peer was setup in veth_get_stats64() As pointed out by Ben Hutchings, priv->peer is missing proper synchronization. Adding RCU protection is a safe and well documented way to make sure we don't access about to be freed or already freed data. Reported-by: Tom Parkin <tparkin@katalix.com> Signed-off-by: Eric Dumazet <edumazet@google.com> CC: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 23:42:40 +08:00
rcu_assign_pointer(priv->peer, peer);
priv = netdev_priv(peer);
veth: avoid a NULL deref in veth_stats_one commit 2681128f0ced8a (veth: extend device features) added a NULL deref in veth_stats_one(), as veth_get_stats64() was not testing if the peer device was setup or not. At init time, we call dev_get_stats() before veth pair is fully setup. [ 178.854758] [<ffffffffa00f5677>] veth_get_stats64+0x47/0x70 [veth] [ 178.861013] [<ffffffff814f0a2d>] dev_get_stats+0x6d/0x130 [ 178.866486] [<ffffffff81504efc>] rtnl_fill_ifinfo+0x47c/0x930 [ 178.872299] [<ffffffff81505b93>] rtmsg_ifinfo+0x83/0x100 [ 178.877678] [<ffffffff81505cc6>] rtnl_configure_link+0x76/0xa0 [ 178.883580] [<ffffffffa00f52fa>] veth_newlink+0x16a/0x350 [veth] [ 178.889654] [<ffffffff815061cc>] rtnl_newlink+0x4dc/0x5e0 [ 178.895128] [<ffffffff81505e1e>] ? rtnl_newlink+0x12e/0x5e0 [ 178.900769] [<ffffffff8150587d>] rtnetlink_rcv_msg+0x11d/0x310 [ 178.906669] [<ffffffff81505760>] ? __rtnl_unlock+0x20/0x20 [ 178.912225] [<ffffffff81521f89>] netlink_rcv_skb+0xa9/0xd0 [ 178.917779] [<ffffffff81502d55>] rtnetlink_rcv+0x25/0x40 [ 178.923159] [<ffffffff815218d1>] netlink_unicast+0x1b1/0x230 [ 178.928887] [<ffffffff81521c4e>] netlink_sendmsg+0x2fe/0x3b0 [ 178.934615] [<ffffffff814dbe22>] sock_sendmsg+0xd2/0xf0 So we must check if peer was setup in veth_get_stats64() As pointed out by Ben Hutchings, priv->peer is missing proper synchronization. Adding RCU protection is a safe and well documented way to make sure we don't access about to be freed or already freed data. Reported-by: Tom Parkin <tparkin@katalix.com> Signed-off-by: Eric Dumazet <edumazet@google.com> CC: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 23:42:40 +08:00
rcu_assign_pointer(priv->peer, dev);
return 0;
err_register_dev:
/* nothing to do */
rtnetlink: support specifying device flags on device creation commit e8469ed959c373c2ff9e6f488aa5a14971aebe1f Author: Patrick McHardy <kaber@trash.net> Date: Tue Feb 23 20:41:30 2010 +0100 Support specifying the initial device flags when creating a device though rtnl_link. Devices allocated by rtnl_create_link() are marked as INITIALIZING in order to surpress netlink registration notifications. To complete setup, rtnl_configure_link() must be called, which performs the device flag changes and invokes the deferred notifiers if everything went well. Two examples: # add macvlan to eth0 # $ ip link add link eth0 up allmulticast on type macvlan [LINK]11: macvlan0@eth0: <BROADCAST,MULTICAST,ALLMULTI,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN link/ether 26:f8:84:02:f9:2a brd ff:ff:ff:ff:ff:ff [ROUTE]ff00::/8 dev macvlan0 table local metric 256 mtu 1500 advmss 1440 hoplimit 0 [ROUTE]fe80::/64 dev macvlan0 proto kernel metric 256 mtu 1500 advmss 1440 hoplimit 0 [LINK]11: macvlan0@eth0: <BROADCAST,MULTICAST,ALLMULTI,UP,LOWER_UP> mtu 1500 link/ether 26:f8:84:02:f9:2a [ADDR]11: macvlan0 inet6 fe80::24f8:84ff:fe02:f92a/64 scope link valid_lft forever preferred_lft forever [ROUTE]local fe80::24f8:84ff:fe02:f92a via :: dev lo table local proto none metric 0 mtu 16436 advmss 16376 hoplimit 0 [ROUTE]default via fe80::215:e9ff:fef0:10f8 dev macvlan0 proto kernel metric 1024 mtu 1500 advmss 1440 hoplimit 0 [NEIGH]fe80::215:e9ff:fef0:10f8 dev macvlan0 lladdr 00:15:e9:f0:10:f8 router STALE [ROUTE]2001:6f8:974::/64 dev macvlan0 proto kernel metric 256 expires 0sec mtu 1500 advmss 1440 hoplimit 0 [PREFIX]prefix 2001:6f8:974::/64 dev macvlan0 onlink autoconf valid 14400 preferred 131084 [ADDR]11: macvlan0 inet6 2001:6f8:974:0:24f8:84ff:fe02:f92a/64 scope global dynamic valid_lft 86399sec preferred_lft 14399sec # add VLAN to eth1, eth1 is down # $ ip link add link eth1 up type vlan id 1000 RTNETLINK answers: Network is down <no events> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-26 14:34:54 +08:00
err_configure_peer:
unregister_netdevice(peer);
return err;
err_register_peer:
free_netdev(peer);
return err;
}
static void veth_dellink(struct net_device *dev, struct list_head *head)
{
struct veth_priv *priv;
struct net_device *peer;
priv = netdev_priv(dev);
veth: avoid a NULL deref in veth_stats_one commit 2681128f0ced8a (veth: extend device features) added a NULL deref in veth_stats_one(), as veth_get_stats64() was not testing if the peer device was setup or not. At init time, we call dev_get_stats() before veth pair is fully setup. [ 178.854758] [<ffffffffa00f5677>] veth_get_stats64+0x47/0x70 [veth] [ 178.861013] [<ffffffff814f0a2d>] dev_get_stats+0x6d/0x130 [ 178.866486] [<ffffffff81504efc>] rtnl_fill_ifinfo+0x47c/0x930 [ 178.872299] [<ffffffff81505b93>] rtmsg_ifinfo+0x83/0x100 [ 178.877678] [<ffffffff81505cc6>] rtnl_configure_link+0x76/0xa0 [ 178.883580] [<ffffffffa00f52fa>] veth_newlink+0x16a/0x350 [veth] [ 178.889654] [<ffffffff815061cc>] rtnl_newlink+0x4dc/0x5e0 [ 178.895128] [<ffffffff81505e1e>] ? rtnl_newlink+0x12e/0x5e0 [ 178.900769] [<ffffffff8150587d>] rtnetlink_rcv_msg+0x11d/0x310 [ 178.906669] [<ffffffff81505760>] ? __rtnl_unlock+0x20/0x20 [ 178.912225] [<ffffffff81521f89>] netlink_rcv_skb+0xa9/0xd0 [ 178.917779] [<ffffffff81502d55>] rtnetlink_rcv+0x25/0x40 [ 178.923159] [<ffffffff815218d1>] netlink_unicast+0x1b1/0x230 [ 178.928887] [<ffffffff81521c4e>] netlink_sendmsg+0x2fe/0x3b0 [ 178.934615] [<ffffffff814dbe22>] sock_sendmsg+0xd2/0xf0 So we must check if peer was setup in veth_get_stats64() As pointed out by Ben Hutchings, priv->peer is missing proper synchronization. Adding RCU protection is a safe and well documented way to make sure we don't access about to be freed or already freed data. Reported-by: Tom Parkin <tparkin@katalix.com> Signed-off-by: Eric Dumazet <edumazet@google.com> CC: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 23:42:40 +08:00
peer = rtnl_dereference(priv->peer);
/* Note : dellink() is called from default_device_exit_batch(),
* before a rcu_synchronize() point. The devices are guaranteed
* not being freed before one RCU grace period.
*/
RCU_INIT_POINTER(priv->peer, NULL);
unregister_netdevice_queue(dev, head);
if (peer) {
priv = netdev_priv(peer);
RCU_INIT_POINTER(priv->peer, NULL);
unregister_netdevice_queue(peer, head);
}
}
static const struct nla_policy veth_policy[VETH_INFO_MAX + 1] = {
[VETH_INFO_PEER] = { .len = sizeof(struct ifinfomsg) },
};
static struct net *veth_get_link_net(const struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
struct net_device *peer = rtnl_dereference(priv->peer);
return peer ? dev_net(peer) : dev_net(dev);
}
static struct rtnl_link_ops veth_link_ops = {
.kind = DRV_NAME,
.priv_size = sizeof(struct veth_priv),
.setup = veth_setup,
.validate = veth_validate,
.newlink = veth_newlink,
.dellink = veth_dellink,
.policy = veth_policy,
.maxtype = VETH_INFO_MAX,
.get_link_net = veth_get_link_net,
};
/*
* init/fini
*/
static __init int veth_init(void)
{
return rtnl_link_register(&veth_link_ops);
}
static __exit void veth_exit(void)
{
rtnl_link_unregister(&veth_link_ops);
}
module_init(veth_init);
module_exit(veth_exit);
MODULE_DESCRIPTION("Virtual Ethernet Tunnel");
MODULE_LICENSE("GPL v2");
MODULE_ALIAS_RTNL_LINK(DRV_NAME);