From 6194114324139dc16f3251c67ed853bd6d4ae056 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 24 Sep 2018 21:58:59 +0200 Subject: net: core: add member wol_enabled to struct net_device Add flag wol_enabled to struct net_device indicating whether Wake-on-LAN is enabled. As first user phy_suspend() will use it to decide whether PHY can be suspended or not. Fixes: f1e911d5d0df ("r8169: add basic phylib support") Fixes: e8cfd9d6c772 ("net: phy: call state machine synchronously in phy_stop") Signed-off-by: Heiner Kallweit Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/core/ethtool.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 234a0ec2e932..0762aaf8e964 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1483,6 +1483,7 @@ static int ethtool_get_wol(struct net_device *dev, char __user *useraddr) static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) { struct ethtool_wolinfo wol; + int ret; if (!dev->ethtool_ops->set_wol) return -EOPNOTSUPP; @@ -1490,7 +1491,13 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) if (copy_from_user(&wol, useraddr, sizeof(wol))) return -EFAULT; - return dev->ethtool_ops->set_wol(dev, &wol); + ret = dev->ethtool_ops->set_wol(dev, &wol); + if (ret) + return ret; + + dev->wol_enabled = !!wol.wolopts; + + return 0; } static int ethtool_get_eee(struct net_device *dev, char __user *useraddr) -- cgit v1.2.3 From c24498c6827b71f80fecc9fb1b70a792053d41a9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 27 Sep 2018 09:31:51 -0700 Subject: netpoll: do not test NAPI_STATE_SCHED in poll_one_napi() Since we do no longer require NAPI drivers to provide an ndo_poll_controller(), napi_schedule() has not been done before poll_one_napi() invocation. So testing NAPI_STATE_SCHED is likely to cause early returns. While we are at it, remove outdated comment. Note to future bisections : This change might surface prior bugs in drivers. See commit 73f21c653f93 ("bnxt_en: Fix TX timeout during netpoll.") for one occurrence. Fixes: ac3d9dd034e5 ("netpoll: make ndo_poll_controller() optional") Signed-off-by: Eric Dumazet Tested-by: Song Liu Cc: Michael Chan Signed-off-by: David S. Miller --- net/core/netpoll.c | 20 +------------------- 1 file changed, 1 insertion(+), 19 deletions(-) (limited to 'net/core') diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 3219a2932463..3ae899805f8b 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -135,27 +135,9 @@ static void queue_process(struct work_struct *work) } } -/* - * Check whether delayed processing was scheduled for our NIC. If so, - * we attempt to grab the poll lock and use ->poll() to pump the card. - * If this fails, either we've recursed in ->poll() or it's already - * running on another CPU. - * - * Note: we don't mask interrupts with this lock because we're using - * trylock here and interrupts are already disabled in the softirq - * case. Further, we test the poll_owner to avoid recursion on UP - * systems where the lock doesn't exist. - */ static void poll_one_napi(struct napi_struct *napi) { - int work = 0; - - /* net_rx_action's ->poll() invocations and our's are - * synchronized by this test which is only made while - * holding the napi->poll_lock. - */ - if (!test_bit(NAPI_STATE_SCHED, &napi->state)) - return; + int work; /* If we set this bit but see that it has already been set, * that indicates that napi has been disabled and we need -- cgit v1.2.3 From 893626d6a353d1356528f94e081246ecf233d77a Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 28 Sep 2018 12:28:41 -0700 Subject: rtnetlink: Fail dump if target netnsid is invalid Link dumps can return results from a target namespace. If the namespace id is invalid, then the dump request should fail if get_target_net fails rather than continuing with a dump of the current namespace. Fixes: 79e1ad148c844 ("rtnetlink: use netnsid to query interface") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 63ce2283a456..7f37fe9c65a5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1898,10 +1898,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (tb[IFLA_IF_NETNSID]) { netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); tgt_net = get_target_net(skb->sk, netnsid); - if (IS_ERR(tgt_net)) { - tgt_net = net; - netnsid = -1; - } + if (IS_ERR(tgt_net)) + return PTR_ERR(tgt_net); } if (tb[IFLA_EXT_MASK]) -- cgit v1.2.3 From 6fe9487892b32cb1c8b8b0d552ed7222a527fe30 Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Fri, 28 Sep 2018 16:26:08 -0400 Subject: bond: take rcu lock in netpoll_send_skb_on_dev The bonding driver lacks the rcu lock when it calls down into netdev_lower_get_next_private_rcu from bond_poll_controller, which results in a trace like: WARNING: CPU: 2 PID: 179 at net/core/dev.c:6567 netdev_lower_get_next_private_rcu+0x34/0x40 CPU: 2 PID: 179 Comm: kworker/u16:15 Not tainted 4.19.0-rc5-backup+ #1 Workqueue: bond0 bond_mii_monitor RIP: 0010:netdev_lower_get_next_private_rcu+0x34/0x40 Code: 48 89 fb e8 fe 29 63 ff 85 c0 74 1e 48 8b 45 00 48 81 c3 c0 00 00 00 48 8b 00 48 39 d8 74 0f 48 89 45 00 48 8b 40 f8 5b 5d c3 <0f> 0b eb de 31 c0 eb f5 0f 1f 40 00 0f 1f 44 00 00 48 8> RSP: 0018:ffffc9000087fa68 EFLAGS: 00010046 RAX: 0000000000000000 RBX: ffff880429614560 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 00000000ffffffff RDI: ffffffffa184ada0 RBP: ffffc9000087fa80 R08: 0000000000000001 R09: 0000000000000000 R10: ffffc9000087f9f0 R11: ffff880429798040 R12: ffff8804289d5980 R13: ffffffffa1511f60 R14: 00000000000000c8 R15: 00000000ffffffff FS: 0000000000000000(0000) GS:ffff88042f880000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f4b78fce180 CR3: 000000018180f006 CR4: 00000000001606e0 Call Trace: bond_poll_controller+0x52/0x170 netpoll_poll_dev+0x79/0x290 netpoll_send_skb_on_dev+0x158/0x2c0 netpoll_send_udp+0x2d5/0x430 write_ext_msg+0x1e0/0x210 console_unlock+0x3c4/0x630 vprintk_emit+0xfa/0x2f0 printk+0x52/0x6e ? __netdev_printk+0x12b/0x220 netdev_info+0x64/0x80 ? bond_3ad_set_carrier+0xe9/0x180 bond_select_active_slave+0x1fc/0x310 bond_mii_monitor+0x709/0x9b0 process_one_work+0x221/0x5e0 worker_thread+0x4f/0x3b0 kthread+0x100/0x140 ? process_one_work+0x5e0/0x5e0 ? kthread_delayed_work_timer_fn+0x90/0x90 ret_from_fork+0x24/0x30 We're also doing rcu dereferences a layer up in netpoll_send_skb_on_dev before we call down into netpoll_poll_dev, so just take the lock there. Suggested-by: Cong Wang Signed-off-by: Dave Jones Signed-off-by: David S. Miller --- net/core/netpoll.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/core') diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 3ae899805f8b..de1d1ba92f2d 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -312,6 +312,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, /* It is up to the caller to keep npinfo alive. */ struct netpoll_info *npinfo; + rcu_read_lock_bh(); lockdep_assert_irqs_disabled(); npinfo = rcu_dereference_bh(np->dev->npinfo); @@ -356,6 +357,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, skb_queue_tail(&npinfo->txq, skb); schedule_delayed_work(&npinfo->tx_work,0); } + rcu_read_unlock_bh(); } EXPORT_SYMBOL(netpoll_send_skb_on_dev); -- cgit v1.2.3 From 0e1d6eca5113858ed2caea61a5adc03c595f6096 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 2 Oct 2018 15:47:35 -0700 Subject: rtnl: limit IFLA_NUM_TX_QUEUES and IFLA_NUM_RX_QUEUES to 4096 We have an impressive number of syzkaller bugs that are linked to the fact that syzbot was able to create a networking device with millions of TX (or RX) queues. Let's limit the number of RX/TX queues to 4096, this really should cover all known cases. A separate patch will add various cond_resched() in the loops handling sysfs entries at device creation and dismantle. Tested: lpaa6:~# ip link add gre-4097 numtxqueues 4097 numrxqueues 4097 type ip6gretap RTNETLINK answers: Invalid argument lpaa6:~# time ip link add gre-4096 numtxqueues 4096 numrxqueues 4096 type ip6gretap real 0m0.180s user 0m0.000s sys 0m0.107s Fixes: 76ff5cc91935 ("rtnl: allow to specify number of rx and tx queues on device creation") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 7f37fe9c65a5..448703312fed 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2835,6 +2835,12 @@ struct net_device *rtnl_create_link(struct net *net, else if (ops->get_num_rx_queues) num_rx_queues = ops->get_num_rx_queues(); + if (num_tx_queues < 1 || num_tx_queues > 4096) + return ERR_PTR(-EINVAL); + + if (num_rx_queues < 1 || num_rx_queues > 4096) + return ERR_PTR(-EINVAL); + dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type, ops->setup, num_tx_queues, num_rx_queues); if (!dev) -- cgit v1.2.3 From bd961c9bc66497f0c63f4ba1d02900bb85078366 Mon Sep 17 00:00:00 2001 From: Mauricio Faria de Oliveira Date: Mon, 1 Oct 2018 22:46:40 -0300 Subject: rtnetlink: fix rtnl_fdb_dump() for ndmsg header Currently, rtnl_fdb_dump() assumes the family header is 'struct ifinfomsg', which is not always true -- 'struct ndmsg' is used by iproute2 ('ip neigh'). The problem is, the function bails out early if nlmsg_parse() fails, which does occur for iproute2 usage of 'struct ndmsg' because the payload length is shorter than the family header alone (as 'struct ifinfomsg' is assumed). This breaks backward compatibility with userspace -- nothing is sent back. Some examples with iproute2 and netlink library for go [1]: 1) $ bridge fdb show 33:33:00:00:00:01 dev ens3 self permanent 01:00:5e:00:00:01 dev ens3 self permanent 33:33:ff:15:98:30 dev ens3 self permanent This one works, as it uses 'struct ifinfomsg'. fdb_show() @ iproute2/bridge/fdb.c """ .n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), ... if (rtnl_dump_request(&rth, RTM_GETNEIGH, [...] """ 2) $ ip --family bridge neigh RTNETLINK answers: Invalid argument Dump terminated This one fails, as it uses 'struct ndmsg'. do_show_or_flush() @ iproute2/ip/ipneigh.c """ .n.nlmsg_type = RTM_GETNEIGH, .n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ndmsg)), """ 3) $ ./neighlist < no output > This one fails, as it uses 'struct ndmsg'-based. neighList() @ netlink/neigh_linux.go """ req := h.newNetlinkRequest(unix.RTM_GETNEIGH, [...] msg := Ndmsg{ """ The actual breakage was introduced by commit 0ff50e83b512 ("net: rtnetlink: bail out from rtnl_fdb_dump() on parse error"), because nlmsg_parse() fails if the payload length (with the _actual_ family header) is less than the family header length alone (which is assumed, in parameter 'hdrlen'). This is true in the examples above with struct ndmsg, with size and payload length shorter than struct ifinfomsg. However, that commit just intends to fix something under the assumption the family header is indeed an 'struct ifinfomsg' - by preventing access to the payload as such (via 'ifm' pointer) if the payload length is not sufficient to actually contain it. The assumption was introduced by commit 5e6d24358799 ("bridge: netlink dump interface at par with brctl"), to support iproute2's 'bridge fdb' command (not 'ip neigh') which indeed uses 'struct ifinfomsg', thus is not broken. So, in order to unbreak the 'struct ndmsg' family headers and still allow 'struct ifinfomsg' to continue to work, check for the known message sizes used with 'struct ndmsg' in iproute2 (with zero or one attribute which is not used in this function anyway) then do not parse the data as ifinfomsg. Same examples with this patch applied (or revert/before the original fix): $ bridge fdb show 33:33:00:00:00:01 dev ens3 self permanent 01:00:5e:00:00:01 dev ens3 self permanent 33:33:ff:15:98:30 dev ens3 self permanent $ ip --family bridge neigh dev ens3 lladdr 33:33:00:00:00:01 PERMANENT dev ens3 lladdr 01:00:5e:00:00:01 PERMANENT dev ens3 lladdr 33:33:ff:15:98:30 PERMANENT $ ./neighlist netlink.Neigh{LinkIndex:2, Family:7, State:128, Type:0, Flags:2, IP:net.IP(nil), HardwareAddr:net.HardwareAddr{0x33, 0x33, 0x0, 0x0, 0x0, 0x1}, LLIPAddr:net.IP(nil), Vlan:0, VNI:0} netlink.Neigh{LinkIndex:2, Family:7, State:128, Type:0, Flags:2, IP:net.IP(nil), HardwareAddr:net.HardwareAddr{0x1, 0x0, 0x5e, 0x0, 0x0, 0x1}, LLIPAddr:net.IP(nil), Vlan:0, VNI:0} netlink.Neigh{LinkIndex:2, Family:7, State:128, Type:0, Flags:2, IP:net.IP(nil), HardwareAddr:net.HardwareAddr{0x33, 0x33, 0xff, 0x15, 0x98, 0x30}, LLIPAddr:net.IP(nil), Vlan:0, VNI:0} Tested on mainline (v4.19-rc6) and net-next (3bd09b05b068). References: [1] netlink library for go (test-case) https://github.com/vishvananda/netlink $ cat ~/go/src/neighlist/main.go package main import ("fmt"; "syscall"; "github.com/vishvananda/netlink") func main() { neighs, _ := netlink.NeighList(0, syscall.AF_BRIDGE) for _, neigh := range neighs { fmt.Printf("%#v\n", neigh) } } $ export GOPATH=~/go $ go get github.com/vishvananda/netlink $ go build neighlist $ ~/go/src/neighlist/neighlist Thanks to David Ahern for suggestions to improve this patch. Fixes: 0ff50e83b512 ("net: rtnetlink: bail out from rtnl_fdb_dump() on parse error") Fixes: 5e6d24358799 ("bridge: netlink dump interface at par with brctl") Reported-by: Aidan Obley Signed-off-by: Mauricio Faria de Oliveira Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 29 ++++++++++++++++++++--------- 1 file changed, 20 insertions(+), 9 deletions(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 448703312fed..37c7936124e6 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3748,16 +3748,27 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) int err = 0; int fidx = 0; - err = nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, - IFLA_MAX, ifla_policy, NULL); - if (err < 0) { - return -EINVAL; - } else if (err == 0) { - if (tb[IFLA_MASTER]) - br_idx = nla_get_u32(tb[IFLA_MASTER]); - } + /* A hack to preserve kernel<->userspace interface. + * Before Linux v4.12 this code accepted ndmsg since iproute2 v3.3.0. + * However, ndmsg is shorter than ifinfomsg thus nlmsg_parse() bails. + * So, check for ndmsg with an optional u32 attribute (not used here). + * Fortunately these sizes don't conflict with the size of ifinfomsg + * with an optional attribute. + */ + if (nlmsg_len(cb->nlh) != sizeof(struct ndmsg) && + (nlmsg_len(cb->nlh) != sizeof(struct ndmsg) + + nla_attr_size(sizeof(u32)))) { + err = nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, + IFLA_MAX, ifla_policy, NULL); + if (err < 0) { + return -EINVAL; + } else if (err == 0) { + if (tb[IFLA_MASTER]) + br_idx = nla_get_u32(tb[IFLA_MASTER]); + } - brport_idx = ifm->ifi_index; + brport_idx = ifm->ifi_index; + } if (br_idx) { br_dev = __dev_get_by_index(net, br_idx); -- cgit v1.2.3 From f355cfcdb251e22b9dfb78c0eef4005a9d902a35 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 10 Oct 2018 16:09:25 +0300 Subject: devlink: Fix param set handling for string type In case devlink param type is string, it needs to copy the string value it got from the input to devlink_param_value. Fixes: e3b7ca18ad7b ("devlink: Add param set command") Signed-off-by: Moshe Shemesh Signed-off-by: David S. Miller --- include/net/devlink.h | 2 +- net/core/devlink.c | 11 ++++++++--- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'net/core') diff --git a/include/net/devlink.h b/include/net/devlink.h index b9b89d6604d4..b0e17c025fdc 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -311,7 +311,7 @@ union devlink_param_value { u8 vu8; u16 vu16; u32 vu32; - const char *vstr; + char vstr[DEVLINK_PARAM_MAX_STRING_VALUE]; bool vbool; }; diff --git a/net/core/devlink.c b/net/core/devlink.c index 8c0ed225e280..d808af7a5c52 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2995,6 +2995,8 @@ devlink_param_value_get_from_info(const struct devlink_param *param, struct genl_info *info, union devlink_param_value *value) { + int len; + if (param->type != DEVLINK_PARAM_TYPE_BOOL && !info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) return -EINVAL; @@ -3010,10 +3012,13 @@ devlink_param_value_get_from_info(const struct devlink_param *param, value->vu32 = nla_get_u32(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); break; case DEVLINK_PARAM_TYPE_STRING: - if (nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) > - DEVLINK_PARAM_MAX_STRING_VALUE) + len = strnlen(nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]), + nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])); + if (len == nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) || + len >= DEVLINK_PARAM_MAX_STRING_VALUE) return -EINVAL; - value->vstr = nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); + strcpy(value->vstr, + nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])); break; case DEVLINK_PARAM_TYPE_BOOL: value->vbool = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA] ? -- cgit v1.2.3 From 1276534c988ba752fa01bf090412a877ee783829 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 10 Oct 2018 16:09:26 +0300 Subject: devlink: Fix param cmode driverinit for string type Driverinit configuration mode value is held by devlink to enable the driver fetch the value after reload command. In case the param type is string devlink should copy the value from driver string buffer to devlink string buffer on devlink_param_driverinit_value_set() and vice-versa on devlink_param_driverinit_value_get(). Fixes: ec01aeb1803e ("devlink: Add support for get/set driverinit value") Signed-off-by: Moshe Shemesh Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/devlink.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'net/core') diff --git a/net/core/devlink.c b/net/core/devlink.c index d808af7a5c52..1a0de1677197 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3105,7 +3105,10 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, return -EOPNOTSUPP; if (cmode == DEVLINK_PARAM_CMODE_DRIVERINIT) { - param_item->driverinit_value = value; + if (param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(param_item->driverinit_value.vstr, value.vstr); + else + param_item->driverinit_value = value; param_item->driverinit_value_valid = true; } else { if (!param->set) @@ -4545,7 +4548,10 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, DEVLINK_PARAM_CMODE_DRIVERINIT)) return -EOPNOTSUPP; - *init_val = param_item->driverinit_value; + if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(init_val->vstr, param_item->driverinit_value.vstr); + else + *init_val = param_item->driverinit_value; return 0; } @@ -4576,7 +4582,10 @@ int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, DEVLINK_PARAM_CMODE_DRIVERINIT)) return -EOPNOTSUPP; - param_item->driverinit_value = init_val; + if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(param_item->driverinit_value.vstr, init_val.vstr); + else + param_item->driverinit_value = init_val; param_item->driverinit_value_valid = true; devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); -- cgit v1.2.3 From bde74ad10eb55aaa472c37b107934e6b8563c25e Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 10 Oct 2018 16:09:27 +0300 Subject: devlink: Add helper function for safely copy string param Devlink string param buffer is allocated at the size of DEVLINK_PARAM_MAX_STRING_VALUE. Add helper function which makes sure this size is not exceeded. Renamed DEVLINK_PARAM_MAX_STRING_VALUE to __DEVLINK_PARAM_MAX_STRING_VALUE to emphasize that it should be used by devlink only. The driver should use the helper function instead to verify it doesn't exceed the allowed length. Signed-off-by: Moshe Shemesh Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 12 ++++++++++-- net/core/devlink.c | 19 ++++++++++++++++++- 2 files changed, 28 insertions(+), 3 deletions(-) (limited to 'net/core') diff --git a/include/net/devlink.h b/include/net/devlink.h index b0e17c025fdc..99efc156a309 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -298,7 +298,7 @@ struct devlink_resource { #define DEVLINK_RESOURCE_ID_PARENT_TOP 0 -#define DEVLINK_PARAM_MAX_STRING_VALUE 32 +#define __DEVLINK_PARAM_MAX_STRING_VALUE 32 enum devlink_param_type { DEVLINK_PARAM_TYPE_U8, DEVLINK_PARAM_TYPE_U16, @@ -311,7 +311,7 @@ union devlink_param_value { u8 vu8; u16 vu16; u32 vu32; - char vstr[DEVLINK_PARAM_MAX_STRING_VALUE]; + char vstr[__DEVLINK_PARAM_MAX_STRING_VALUE]; bool vbool; }; @@ -553,6 +553,8 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, union devlink_param_value init_val); void devlink_param_value_changed(struct devlink *devlink, u32 param_id); +void devlink_param_value_str_fill(union devlink_param_value *dst_val, + const char *src); struct devlink_region *devlink_region_create(struct devlink *devlink, const char *region_name, u32 region_max_snapshots, @@ -789,6 +791,12 @@ devlink_param_value_changed(struct devlink *devlink, u32 param_id) { } +static inline void +devlink_param_value_str_fill(union devlink_param_value *dst_val, + const char *src) +{ +} + static inline struct devlink_region * devlink_region_create(struct devlink *devlink, const char *region_name, diff --git a/net/core/devlink.c b/net/core/devlink.c index 1a0de1677197..6bc42933be4a 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3015,7 +3015,7 @@ devlink_param_value_get_from_info(const struct devlink_param *param, len = strnlen(nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]), nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])); if (len == nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) || - len >= DEVLINK_PARAM_MAX_STRING_VALUE) + len >= __DEVLINK_PARAM_MAX_STRING_VALUE) return -EINVAL; strcpy(value->vstr, nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])); @@ -4617,6 +4617,23 @@ void devlink_param_value_changed(struct devlink *devlink, u32 param_id) } EXPORT_SYMBOL_GPL(devlink_param_value_changed); +/** + * devlink_param_value_str_fill - Safely fill-up the string preventing + * from overflow of the preallocated buffer + * + * @dst_val: destination devlink_param_value + * @src: source buffer + */ +void devlink_param_value_str_fill(union devlink_param_value *dst_val, + const char *src) +{ + size_t len; + + len = strlcpy(dst_val->vstr, src, __DEVLINK_PARAM_MAX_STRING_VALUE); + WARN_ON(len >= __DEVLINK_PARAM_MAX_STRING_VALUE); +} +EXPORT_SYMBOL_GPL(devlink_param_value_str_fill); + /** * devlink_region_create - create a new address region * -- cgit v1.2.3 From 52b5d6f5dcf0e5201392f7d417148ccb537dbf6f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 10 Oct 2018 06:59:35 -0700 Subject: net: make skb_partial_csum_set() more robust against overflows syzbot managed to crash in skb_checksum_help() [1] : BUG_ON(offset + sizeof(__sum16) > skb_headlen(skb)); Root cause is the following check in skb_partial_csum_set() if (unlikely(start > skb_headlen(skb)) || unlikely((int)start + off > skb_headlen(skb) - 2)) return false; If skb_headlen(skb) is 1, then (skb_headlen(skb) - 2) becomes 0xffffffff and the check fails to detect that ((int)start + off) is off the limit, since the compare is unsigned. When we fix that, then the first condition (start > skb_headlen(skb)) becomes obsolete. Then we should also check that (skb_headroom(skb) + start) wont overflow 16bit field. [1] kernel BUG at net/core/dev.c:2880! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 1 PID: 7330 Comm: syz-executor4 Not tainted 4.19.0-rc6+ #253 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:skb_checksum_help+0x9e3/0xbb0 net/core/dev.c:2880 Code: 85 00 ff ff ff 48 c1 e8 03 42 80 3c 28 00 0f 84 09 fb ff ff 48 8b bd 00 ff ff ff e8 97 a8 b9 fb e9 f8 fa ff ff e8 2d 09 76 fb <0f> 0b 48 8b bd 28 ff ff ff e8 1f a8 b9 fb e9 b1 f6 ff ff 48 89 cf RSP: 0018:ffff8801d83a6f60 EFLAGS: 00010293 RAX: ffff8801b9834380 RBX: ffff8801b9f8d8c0 RCX: ffffffff8608c6d7 RDX: 0000000000000000 RSI: ffffffff8608cc63 RDI: 0000000000000006 RBP: ffff8801d83a7068 R08: ffff8801b9834380 R09: 0000000000000000 R10: ffff8801d83a76d8 R11: 0000000000000000 R12: 0000000000000001 R13: 0000000000010001 R14: 000000000000ffff R15: 00000000000000a8 FS: 00007f1a66db5700(0000) GS:ffff8801daf00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f7d77f091b0 CR3: 00000001ba252000 CR4: 00000000001406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: skb_csum_hwoffload_help+0x8f/0xe0 net/core/dev.c:3269 validate_xmit_skb+0xa2a/0xf30 net/core/dev.c:3312 __dev_queue_xmit+0xc2f/0x3950 net/core/dev.c:3797 dev_queue_xmit+0x17/0x20 net/core/dev.c:3838 packet_snd net/packet/af_packet.c:2928 [inline] packet_sendmsg+0x422d/0x64c0 net/packet/af_packet.c:2953 Fixes: 5ff8dda3035d ("net: Ensure partial checksum offset is inside the skb head") Signed-off-by: Eric Dumazet Cc: Herbert Xu Reported-by: syzbot Signed-off-by: David S. Miller --- net/core/skbuff.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'net/core') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b2c807f67aba..428094b577fc 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4452,14 +4452,16 @@ EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); */ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) { - if (unlikely(start > skb_headlen(skb)) || - unlikely((int)start + off > skb_headlen(skb) - 2)) { - net_warn_ratelimited("bad partial csum: csum=%u/%u len=%u\n", - start, off, skb_headlen(skb)); + u32 csum_end = (u32)start + (u32)off + sizeof(__sum16); + u32 csum_start = skb_headroom(skb) + (u32)start; + + if (unlikely(csum_start > U16_MAX || csum_end > skb_headlen(skb))) { + net_warn_ratelimited("bad partial csum: csum=%u/%u headroom=%u headlen=%u\n", + start, off, skb_headroom(skb), skb_headlen(skb)); return false; } skb->ip_summed = CHECKSUM_PARTIAL; - skb->csum_start = skb_headroom(skb) + start; + skb->csum_start = csum_start; skb->csum_offset = off; skb_set_transport_header(skb, start); return true; -- cgit v1.2.3 From af7d6cce53694a88d6a1bb60c9a239a6a5144459 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 9 Oct 2018 17:48:14 +0200 Subject: net: ipv4: update fnhe_pmtu when first hop's MTU changes Since commit 5aad1de5ea2c ("ipv4: use separate genid for next hop exceptions"), exceptions get deprecated separately from cached routes. In particular, administrative changes don't clear PMTU anymore. As Stefano described in commit e9fa1495d738 ("ipv6: Reflect MTU changes on PMTU of exceptions for MTU-less routes"), the PMTU discovered before the local MTU change can become stale: - if the local MTU is now lower than the PMTU, that PMTU is now incorrect - if the local MTU was the lowest value in the path, and is increased, we might discover a higher PMTU Similarly to what commit e9fa1495d738 did for IPv6, update PMTU in those cases. If the exception was locked, the discovered PMTU was smaller than the minimal accepted PMTU. In that case, if the new local MTU is smaller than the current PMTU, let PMTU discovery figure out if locking of the exception is still needed. To do this, we need to know the old link MTU in the NETDEV_CHANGEMTU notifier. By the time the notifier is called, dev->mtu has been changed. This patch adds the old MTU as additional information in the notifier structure, and a new call_netdevice_notifiers_u32() function. Fixes: 5aad1de5ea2c ("ipv4: use separate genid for next hop exceptions") Signed-off-by: Sabrina Dubroca Reviewed-by: Stefano Brivio Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++++ include/net/ip_fib.h | 1 + net/core/dev.c | 28 ++++++++++++++++++++++++-- net/ipv4/fib_frontend.c | 12 ++++++++---- net/ipv4/fib_semantics.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 92 insertions(+), 6 deletions(-) (limited to 'net/core') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c7861e4b402c..d837dad24b4c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2458,6 +2458,13 @@ struct netdev_notifier_info { struct netlink_ext_ack *extack; }; +struct netdev_notifier_info_ext { + struct netdev_notifier_info info; /* must be first */ + union { + u32 mtu; + } ext; +}; + struct netdev_notifier_change_info { struct netdev_notifier_info info; /* must be first */ unsigned int flags_changed; diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 69c91d1934c1..c9b7b136939d 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -394,6 +394,7 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev); int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force); int fib_sync_down_addr(struct net_device *dev, __be32 local); int fib_sync_up(struct net_device *dev, unsigned int nh_flags); +void fib_sync_mtu(struct net_device *dev, u32 orig_mtu); #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, diff --git a/net/core/dev.c b/net/core/dev.c index 82114e1111e6..93243479085f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1752,6 +1752,28 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev) } EXPORT_SYMBOL(call_netdevice_notifiers); +/** + * call_netdevice_notifiers_mtu - call all network notifier blocks + * @val: value passed unmodified to notifier function + * @dev: net_device pointer passed unmodified to notifier function + * @arg: additional u32 argument passed to the notifier function + * + * Call all network notifier blocks. Parameters and return value + * are as for raw_notifier_call_chain(). + */ +static int call_netdevice_notifiers_mtu(unsigned long val, + struct net_device *dev, u32 arg) +{ + struct netdev_notifier_info_ext info = { + .info.dev = dev, + .ext.mtu = arg, + }; + + BUILD_BUG_ON(offsetof(struct netdev_notifier_info_ext, info) != 0); + + return call_netdevice_notifiers_info(val, &info.info); +} + #ifdef CONFIG_NET_INGRESS static DEFINE_STATIC_KEY_FALSE(ingress_needed_key); @@ -7574,14 +7596,16 @@ int dev_set_mtu_ext(struct net_device *dev, int new_mtu, err = __dev_set_mtu(dev, new_mtu); if (!err) { - err = call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + err = call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, + orig_mtu); err = notifier_to_errno(err); if (err) { /* setting mtu back and notifying everyone again, * so that they have a chance to revert changes. */ __dev_set_mtu(dev, orig_mtu); - call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, + new_mtu); } } return err; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 2998b0e47d4b..0113993e9b2c 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1243,7 +1243,8 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct netdev_notifier_changeupper_info *info; + struct netdev_notifier_changeupper_info *upper_info = ptr; + struct netdev_notifier_info_ext *info_ext = ptr; struct in_device *in_dev; struct net *net = dev_net(dev); unsigned int flags; @@ -1278,16 +1279,19 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo fib_sync_up(dev, RTNH_F_LINKDOWN); else fib_sync_down_dev(dev, event, false); - /* fall through */ + rt_cache_flush(net); + break; case NETDEV_CHANGEMTU: + fib_sync_mtu(dev, info_ext->ext.mtu); rt_cache_flush(net); break; case NETDEV_CHANGEUPPER: - info = ptr; + upper_info = ptr; /* flush all routes if dev is linked to or unlinked from * an L3 master device (e.g., VRF) */ - if (info->upper_dev && netif_is_l3_master(info->upper_dev)) + if (upper_info->upper_dev && + netif_is_l3_master(upper_info->upper_dev)) fib_disable_ip(dev, NETDEV_DOWN, true); break; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f3c89ccf14c5..446204ca7406 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1470,6 +1470,56 @@ static int call_fib_nh_notifiers(struct fib_nh *fib_nh, return NOTIFY_DONE; } +/* Update the PMTU of exceptions when: + * - the new MTU of the first hop becomes smaller than the PMTU + * - the old MTU was the same as the PMTU, and it limited discovery of + * larger MTUs on the path. With that limit raised, we can now + * discover larger MTUs + * A special case is locked exceptions, for which the PMTU is smaller + * than the minimal accepted PMTU: + * - if the new MTU is greater than the PMTU, don't make any change + * - otherwise, unlock and set PMTU + */ +static void nh_update_mtu(struct fib_nh *nh, u32 new, u32 orig) +{ + struct fnhe_hash_bucket *bucket; + int i; + + bucket = rcu_dereference_protected(nh->nh_exceptions, 1); + if (!bucket) + return; + + for (i = 0; i < FNHE_HASH_SIZE; i++) { + struct fib_nh_exception *fnhe; + + for (fnhe = rcu_dereference_protected(bucket[i].chain, 1); + fnhe; + fnhe = rcu_dereference_protected(fnhe->fnhe_next, 1)) { + if (fnhe->fnhe_mtu_locked) { + if (new <= fnhe->fnhe_pmtu) { + fnhe->fnhe_pmtu = new; + fnhe->fnhe_mtu_locked = false; + } + } else if (new < fnhe->fnhe_pmtu || + orig == fnhe->fnhe_pmtu) { + fnhe->fnhe_pmtu = new; + } + } + } +} + +void fib_sync_mtu(struct net_device *dev, u32 orig_mtu) +{ + unsigned int hash = fib_devindex_hashfn(dev->ifindex); + struct hlist_head *head = &fib_info_devhash[hash]; + struct fib_nh *nh; + + hlist_for_each_entry(nh, head, nh_hash) { + if (nh->nh_dev == dev) + nh_update_mtu(nh, dev->mtu, orig_mtu); + } +} + /* Event force Flags Description * NETDEV_CHANGE 0 LINKDOWN Carrier OFF, not for scope host * NETDEV_DOWN 0 LINKDOWN|DEAD Link down, not for scope host -- cgit v1.2.3