From: Mingming Cao mmc@linux.vnet.ibm.com

[ Upstream commit 9f13457377907fa253aef560e1a37e1ca4197f9b ]

At the time of do_rest, ibmvnic tries to re-initalize the tx_pools and rx_pools to avoid re-allocating the long term buffer. However there is a window inside do_reset that the tx_pools and rx_pools were freed before re-initialized making it possible to deference null pointers.

This patch fix this issue by always check the tx_pool and rx_pool are not NULL after ibmvnic_login. If so, re-allocating the pools. This will avoid getting into calling reset_tx/rx_pools with NULL adapter tx_pools/rx_pools pointer. Also add null pointer check in reset_tx_pools and reset_rx_pools to safe handle NULL pointer case.

Signed-off-by: Mingming Cao mmc@linux.vnet.ibm.com Signed-off-by: Dany Madden drt@linux.ibm.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/ibm/ibmvnic.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 5afb3c9c52d20..d3a774331afc7 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -479,6 +479,9 @@ static int reset_rx_pools(struct ibmvnic_adapter *adapter) int i, j, rc; u64 *size_array;

+ if (!adapter->rx_pool) + return -1; + size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size));

@@ -649,6 +652,9 @@ static int reset_tx_pools(struct ibmvnic_adapter *adapter) int tx_scrqs; int i, rc;

+ if (!adapter->tx_pool) + return -1; + tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); for (i = 0; i < tx_scrqs; i++) { rc = reset_one_tx_pool(adapter, &adapter->tso_pool[i]); @@ -2011,7 +2017,10 @@ static int do_reset(struct ibmvnic_adapter *adapter, adapter->req_rx_add_entries_per_subcrq != old_num_rx_slots || adapter->req_tx_entries_per_subcrq != - old_num_tx_slots) { + old_num_tx_slots || + !adapter->rx_pool || + !adapter->tso_pool || + !adapter->tx_pool) { release_rx_pools(adapter); release_tx_pools(adapter); release_napi(adapter); @@ -2024,10 +2033,14 @@ static int do_reset(struct ibmvnic_adapter *adapter, } else { rc = reset_tx_pools(adapter); if (rc) + netdev_dbg(adapter->netdev, "reset tx pools failed (%d)\n", + rc); goto out;

rc = reset_rx_pools(adapter); if (rc) + netdev_dbg(adapter->netdev, "reset rx pools failed (%d)\n", + rc); goto out; } ibmvnic_disable_irqs(adapter);

From: Cong Wang xiyou.wangcong@gmail.com

[ Upstream commit cc8e58f8325cdf14b9516b61c384cdfd02a4f408 ]

The following deadlock scenario is triggered by syzbot:

Thread A: Thread B: tcf_idr_check_alloc() ... populate_metalist() rtnl_unlock() rtnl_lock() ... request_module() tcf_idr_check_alloc() rtnl_lock()

At this point, thread A is waiting for thread B to release RTNL lock, while thread B is waiting for thread A to commit the IDR change with tcf_idr_insert() later.

Break this deadlock situation by preloading ife modules earlier, before tcf_idr_check_alloc(), this is fine because we only need to load modules we need potentially.

Reported-and-tested-by: syzbot+80e32b5d1f9923f8ace6@syzkaller.appspotmail.com Fixes: 0190c1d452a9 ("net: sched: atomically check-allocate action") Cc: Jamal Hadi Salim jhs@mojatatu.com Cc: Vlad Buslov vladbu@mellanox.com Cc: Jiri Pirko jiri@resnulli.us Signed-off-by: Cong Wang xiyou.wangcong@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/act_ife.c | 44 ++++++++++++++++++++++++++++++++++---------- 1 file changed, 34 insertions(+), 10 deletions(-)

--- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -436,6 +436,25 @@ static void tcf_ife_cleanup(struct tc_ac kfree_rcu(p, rcu); }

+static int load_metalist(struct nlattr **tb, bool rtnl_held) +{ + int i; + + for (i = 1; i < max_metacnt; i++) { + if (tb[i]) { + void *val = nla_data(tb[i]); + int len = nla_len(tb[i]); + int rc; + + rc = load_metaops_and_vet(i, val, len, rtnl_held); + if (rc != 0) + return rc; + } + } + + return 0; +} + static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, bool exists, bool rtnl_held) { @@ -449,10 +468,6 @@ static int populate_metalist(struct tcf_ val = nla_data(tb[i]); len = nla_len(tb[i]);

- rc = load_metaops_and_vet(i, val, len, rtnl_held); - if (rc != 0) - return rc; - rc = add_metainfo(ife, i, val, len, exists); if (rc) return rc; @@ -509,6 +524,21 @@ static int tcf_ife_init(struct net *net, if (!p) return -ENOMEM;

+ if (tb[TCA_IFE_METALST]) { + err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, + tb[TCA_IFE_METALST], NULL, + NULL); + if (err) { + kfree(p); + return err; + } + err = load_metalist(tb2, rtnl_held); + if (err) { + kfree(p); + return err; + } + } + index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) { @@ -570,15 +600,9 @@ static int tcf_ife_init(struct net *net, }

if (tb[TCA_IFE_METALST]) { - err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, - tb[TCA_IFE_METALST], NULL, - NULL); - if (err) - goto metadata_parse_err; err = populate_metalist(ife, tb2, exists, rtnl_held); if (err) goto metadata_parse_err; - } else { /* if no passed metadata allow list or passed allow-all * then here we process by adding as many supported metadatum

From: Vasundhara Volam vasundhara-v.volam@broadcom.com

[ Upstream commit b16939b59cc00231a75d224fd058d22c9d064976 ]

bnxt_fw_reset_task() which runs from a workqueue can race with bnxt_remove_one(). For example, if firmware reset and VF FLR are happening at about the same time.

bnxt_remove_one() already cancels the workqueue and waits for it to finish, but we need to do this earlier before the devlink reporters are destroyed. This will guarantee that the devlink reporters will always be valid when bnxt_fw_reset_task() is still running.

Fixes: b148bb238c02 ("bnxt_en: Fix possible crash in bnxt_fw_reset_task().") Reviewed-by: Edwin Peer edwin.peer@broadcom.com Signed-off-by: Vasundhara Volam vasundhara-v.volam@broadcom.com Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11498,6 +11498,10 @@ static void bnxt_remove_one(struct pci_d if (BNXT_PF(bp)) bnxt_sriov_disable(bp);

+ clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); + bnxt_cancel_sp_work(bp); + bp->sp_event = 0; + bnxt_dl_fw_reporters_destroy(bp, true); if (BNXT_PF(bp)) devlink_port_type_clear(&bp->dl_port); @@ -11505,9 +11509,6 @@ static void bnxt_remove_one(struct pci_d unregister_netdev(dev); bnxt_dl_unregister(bp); bnxt_shutdown_tc(bp); - clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); - bnxt_cancel_sp_work(bp); - bp->sp_event = 0;

bnxt_clear_int_mode(bp); bnxt_hwrm_func_drv_unrgtr(bp);

From: Ganji Aravind ganji.aravind@chelsio.com

[ Upstream commit 94cc242a067a869c29800aa789d38b7676136e50 ]

Pass the correct offset to clear the stale filter hit bytes counter. Otherwise, the counter starts incrementing from the stale information, instead of 0.

Fixes: 12b276fbf6e0 ("cxgb4: add support to create hash filters") Signed-off-by: Ganji Aravind ganji.aravind@chelsio.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -1906,13 +1906,16 @@ out: static int configure_filter_tcb(struct adapter *adap, unsigned int tid, struct filter_entry *f) { - if (f->fs.hitcnts) + if (f->fs.hitcnts) { set_tcb_field(adap, f, tid, TCB_TIMESTAMP_W, - TCB_TIMESTAMP_V(TCB_TIMESTAMP_M) | + TCB_TIMESTAMP_V(TCB_TIMESTAMP_M), + TCB_TIMESTAMP_V(0ULL), + 1); + set_tcb_field(adap, f, tid, TCB_RTT_TS_RECENT_AGE_W, TCB_RTT_TS_RECENT_AGE_V(TCB_RTT_TS_RECENT_AGE_M), - TCB_TIMESTAMP_V(0ULL) | TCB_RTT_TS_RECENT_AGE_V(0ULL), 1); + }

if (f->fs.newdmac) set_tcb_tflag(adap, f, tid, TF_CCTRL_ECE_S, 1,

From: Dan Carpenter dan.carpenter@oracle.com

[ Upstream commit 66d42ed8b25b64eb63111a2b8582c5afc8bf1105 ]

There are a couple bugs here: 1) If opt[1] is zero then this results in a forever loop. If the value is less than 2 then it is invalid. 2) It assumes that "len" is more than sizeof(valid_accm) or 6 which can result in memory corruption.

In the case of LCP_OPTION_ACCM, then we should check "opt[1]" instead of "len" because, if "opt[1]" is less than sizeof(valid_accm) then "nak_len" gets out of sync and it can lead to memory corruption in the next iterations through the loop. In case of LCP_OPTION_MAGIC, the only valid value for opt[1] is 6, but the code is trying to log invalid data so we should only discard the data when "len" is less than 6 because that leads to a read overflow.

Reported-by: ChenNan Of Chaitin Security Research Lab whutchennan@gmail.com Fixes: e022c2f07ae5 ("WAN: new synchronous PPP implementation for generic HDLC.") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Reviewed-by: Eric Dumazet edumazet@google.com Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wan/hdlc_ppp.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-)

--- a/drivers/net/wan/hdlc_ppp.c +++ b/drivers/net/wan/hdlc_ppp.c @@ -383,11 +383,8 @@ static void ppp_cp_parse_cr(struct net_d }

for (opt = data; len; len -= opt[1], opt += opt[1]) { - if (len < 2 || len < opt[1]) { - dev->stats.rx_errors++; - kfree(out); - return; /* bad packet, drop silently */ - } + if (len < 2 || opt[1] < 2 || len < opt[1]) + goto err_out;

if (pid == PID_LCP) switch (opt[0]) { @@ -395,6 +392,8 @@ static void ppp_cp_parse_cr(struct net_d continue; /* MRU always OK and > 1500 bytes? */

case LCP_OPTION_ACCM: /* async control character map */ + if (opt[1] < sizeof(valid_accm)) + goto err_out; if (!memcmp(opt, valid_accm, sizeof(valid_accm))) continue; @@ -406,6 +405,8 @@ static void ppp_cp_parse_cr(struct net_d } break; case LCP_OPTION_MAGIC: + if (len < 6) + goto err_out; if (opt[1] != 6 || (!opt[2] && !opt[3] && !opt[4] && !opt[5])) break; /* reject invalid magic number */ @@ -424,6 +425,11 @@ static void ppp_cp_parse_cr(struct net_d ppp_cp_event(dev, pid, RCR_GOOD, CP_CONF_ACK, id, req_len, data);

kfree(out); + return; + +err_out: + dev->stats.rx_errors++; + kfree(out); }

static int ppp_rx(struct sk_buff *skb)

From: Wei Wang weiwan@google.com

[ Upstream commit ba9e04a7ddf4f22a10e05bf9403db6b97743c7bf ]

Currently, in tcp_v4_reqsk_send_ack() and tcp_v4_send_reset(), we echo the TOS value of the received packets in the response. However, we do not want to echo the lower 2 ECN bits in accordance with RFC 3168 6.1.5 robustness principles.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")

Signed-off-by: Wei Wang weiwan@google.com Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/ip_output.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -74,6 +74,7 @@ #include <net/icmp.h> #include <net/checksum.h> #include <net/inetpeer.h> +#include <net/inet_ecn.h> #include <net/lwtunnel.h> #include <linux/bpf-cgroup.h> #include <linux/igmp.h> @@ -1697,7 +1698,7 @@ void ip_send_unicast_reply(struct sock * if (IS_ERR(rt)) return;

- inet_sk(sk)->tos = arg->tos; + inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK;

sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if;

From: David Ahern dsahern@kernel.org

[ Upstream commit 2fbc6e89b2f1403189e624cabaf73e189c5e50c6 ]

Kfir reported that pmtu exceptions are not created properly for deployments where multipath routes use the same device.

After some digging I see 2 compounding problems: 1. ip_route_output_key_hash_rcu is updating the flowi4_oif *after* the route lookup. This is the second use case where this has been a problem (the first is related to use of vti devices with VRF). I can not find any reason for the oif to be changed after the lookup; the code goes back to the start of git. It does not seem logical so remove it.

2. fib_lookups for exceptions do not call fib_select_path to handle multipath route selection based on the hash.

The end result is that the fib_lookup used to add the exception always creates it based using the first leg of the route.

An example topology showing the problem:

| host1 +------+ | eth0 | .209 +------+ | +------+ switch | br0 | +------+ | +---------+---------+ | host2 | host3 +------+ +------+ | eth0 | .250 | eth0 | 192.168.252.252 +------+ +------+

+-----+ +-----+ | vti | .2 | vti | 192.168.247.3 +-----+ +-----+ \ / ================================= tunnels 192.168.247.1/24

for h in host1 host2 host3; do ip netns add ${h} ip -netns ${h} link set lo up ip netns exec ${h} sysctl -wq net.ipv4.ip_forward=1 done

ip netns add switch ip -netns switch li set lo up ip -netns switch link add br0 type bridge stp 0 ip -netns switch link set br0 up

for n in 1 2 3; do ip -netns switch link add eth-sw type veth peer name eth-h${n} ip -netns switch li set eth-h${n} master br0 up ip -netns switch li set eth-sw netns host${n} name eth0 done

ip -netns host1 addr add 192.168.252.209/24 dev eth0 ip -netns host1 link set dev eth0 up ip -netns host1 route add 192.168.247.0/24 \ nexthop via 192.168.252.250 dev eth0 nexthop via 192.168.252.252 dev eth0

ip -netns host2 addr add 192.168.252.250/24 dev eth0 ip -netns host2 link set dev eth0 up

ip -netns host2 addr add 192.168.252.252/24 dev eth0 ip -netns host3 link set dev eth0 up

ip netns add tunnel ip -netns tunnel li set lo up ip -netns tunnel li add br0 type bridge ip -netns tunnel li set br0 up for n in $(seq 11 20); do ip -netns tunnel addr add dev br0 192.168.247.${n}/24 done

for n in 2 3 do ip -netns tunnel link add vti${n} type veth peer name eth${n} ip -netns tunnel link set eth${n} mtu 1360 master br0 up ip -netns tunnel link set vti${n} netns host${n} mtu 1360 up ip -netns host${n} addr add dev vti${n} 192.168.247.${n}/24 done ip -netns tunnel ro add default nexthop via 192.168.247.2 nexthop via 192.168.247.3

ip netns exec host1 ping -M do -s 1400 -c3 -I 192.168.252.209 192.168.247.11 ip netns exec host1 ping -M do -s 1400 -c3 -I 192.168.252.209 192.168.247.15 ip -netns host1 ro ls cache

Before this patch the cache always shows exceptions against the first leg in the multipath route; 192.168.252.250 per this example. Since the hash has an initial random seed, you may need to vary the final octet more than what is listed. In my tests, using addresses between 11 and 19 usually found 1 that used both legs.

With this patch, the cache will have exceptions for both legs.

Fixes: 4895c771c7f0 ("ipv4: Add FIB nexthop exceptions") Reported-by: Kfir Itzhak mastertheknife@gmail.com Signed-off-by: David Ahern dsahern@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/route.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-)

--- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -786,8 +786,10 @@ static void __ip_do_redirect(struct rtab neigh_event_send(n, NULL); } else { if (fib_lookup(net, fl4, &res, 0) == 0) { - struct fib_nh_common *nhc = FIB_RES_NHC(res); + struct fib_nh_common *nhc;

+ fib_select_path(net, &res, fl4, skb); + nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, new_gw, 0, false, jiffies + ip_rt_gc_timeout); @@ -1013,6 +1015,7 @@ out: kfree_skb(skb); static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; + struct net *net = dev_net(dst->dev); u32 old_mtu = ipv4_mtu(dst); struct fib_result res; bool lock = false; @@ -1033,9 +1036,11 @@ static void __ip_rt_update_pmtu(struct r return;

rcu_read_lock(); - if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) { - struct fib_nh_common *nhc = FIB_RES_NHC(res); + if (fib_lookup(net, fl4, &res, 0) == 0) { + struct fib_nh_common *nhc;

+ fib_select_path(net, &res, fl4, NULL); + nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + ip_rt_mtu_expires); } @@ -2663,8 +2668,6 @@ struct rtable *ip_route_output_key_hash_ fib_select_path(net, res, fl4, skb);

dev_out = FIB_RES_DEV(*res); - fl4->flowi4_oif = dev_out->ifindex; -

make_route: rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags);

From: Vladimir Oltean vladimir.oltean@nxp.com

[ Upstream commit 99f62a746066fa436aa15d4606a538569540db08 ]

When calling the RCU brother of br_vlan_get_pvid(), lockdep warns:

============================= WARNING: suspicious RCU usage 5.9.0-rc3-01631-g13c17acb8e38-dirty #814 Not tainted ----------------------------- net/bridge/br_private.h:1054 suspicious rcu_dereference_protected() usage!

Call trace: lockdep_rcu_suspicious+0xd4/0xf8 __br_vlan_get_pvid+0xc0/0x100 br_vlan_get_pvid_rcu+0x78/0x108

The warning is because br_vlan_get_pvid_rcu() calls nbp_vlan_group() which calls rtnl_dereference() instead of rcu_dereference(). In turn, rtnl_dereference() calls rcu_dereference_protected() which assumes operation under an RCU write-side critical section, which obviously is not the case here. So, when the incorrect primitive is used to access the RCU-protected VLAN group pointer, READ_ONCE() is not used, which may cause various unexpected problems.

I'm sad to say that br_vlan_get_pvid() and br_vlan_get_pvid_rcu() cannot share the same implementation. So fix the bug by splitting the 2 functions, and making br_vlan_get_pvid_rcu() retrieve the VLAN groups under proper locking annotations.

Fixes: 7582f5b70f9a ("bridge: add br_vlan_get_pvid_rcu()") Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bridge/br_vlan.c | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-)

--- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1288,11 +1288,13 @@ void br_vlan_get_stats(const struct net_ } }

-static int __br_vlan_get_pvid(const struct net_device *dev, - struct net_bridge_port *p, u16 *p_pvid) +int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) { struct net_bridge_vlan_group *vg; + struct net_bridge_port *p;

+ ASSERT_RTNL(); + p = br_port_get_check_rtnl(dev); if (p) vg = nbp_vlan_group(p); else if (netif_is_bridge_master(dev)) @@ -1303,18 +1305,23 @@ static int __br_vlan_get_pvid(const stru *p_pvid = br_get_pvid(vg); return 0; } - -int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) -{ - ASSERT_RTNL(); - - return __br_vlan_get_pvid(dev, br_port_get_check_rtnl(dev), p_pvid); -} EXPORT_SYMBOL_GPL(br_vlan_get_pvid);

int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid) { - return __br_vlan_get_pvid(dev, br_port_get_check_rcu(dev), p_pvid); + struct net_bridge_vlan_group *vg; + struct net_bridge_port *p; + + p = br_port_get_check_rcu(dev); + if (p) + vg = nbp_vlan_group_rcu(p); + else if (netif_is_bridge_master(dev)) + vg = br_vlan_group_rcu(netdev_priv(dev)); + else + return -EINVAL; + + *p_pvid = br_get_pvid(vg); + return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu);

From: Linus Walleij linus.walleij@linaro.org

[ Upstream commit 4ddcaf1ebb5e4e99240f29d531ee69d4244fe416 ]

When removing a port from a VLAN we are just erasing the member config for the VLAN, which is wrong: other ports can be using it.

Just mask off the port and only zero out the rest of the member config once ports using of the VLAN are removed from it.

Reported-by: Florian Fainelli f.fainelli@gmail.com Fixes: d8652956cf37 ("net: dsa: realtek-smi: Add Realtek SMI driver") Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/dsa/rtl8366.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-)

--- a/drivers/net/dsa/rtl8366.c +++ b/drivers/net/dsa/rtl8366.c @@ -452,13 +452,19 @@ int rtl8366_vlan_del(struct dsa_switch * return ret;

if (vid == vlanmc.vid) { - /* clear VLAN member configurations */ - vlanmc.vid = 0; - vlanmc.priority = 0; - vlanmc.member = 0; - vlanmc.untag = 0; - vlanmc.fid = 0; - + /* Remove this port from the VLAN */ + vlanmc.member &= ~BIT(port); + vlanmc.untag &= ~BIT(port); + /* + * If no ports are members of this VLAN + * anymore then clear the whole member + * config so it can be reused. + */ + if (!vlanmc.member && vlanmc.untag) { + vlanmc.vid = 0; + vlanmc.priority = 0; + vlanmc.fid = 0; + } ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); if (ret) { dev_err(smi->dev,

From: Necip Fazil Yildiran fazilyildiran@gmail.com

[ Upstream commit db7cd91a4be15e1485d6b58c6afc8761c59c4efb ]

When IPV6_SEG6_HMAC is enabled and CRYPTO is disabled, it results in the following Kbuild warning:

WARNING: unmet direct dependencies detected for CRYPTO_HMAC Depends on [n]: CRYPTO [=n] Selected by [y]: - IPV6_SEG6_HMAC [=y] && NET [=y] && INET [=y] && IPV6 [=y]

WARNING: unmet direct dependencies detected for CRYPTO_SHA1 Depends on [n]: CRYPTO [=n] Selected by [y]: - IPV6_SEG6_HMAC [=y] && NET [=y] && INET [=y] && IPV6 [=y]

WARNING: unmet direct dependencies detected for CRYPTO_SHA256 Depends on [n]: CRYPTO [=n] Selected by [y]: - IPV6_SEG6_HMAC [=y] && NET [=y] && INET [=y] && IPV6 [=y]

The reason is that IPV6_SEG6_HMAC selects CRYPTO_HMAC, CRYPTO_SHA1, and CRYPTO_SHA256 without depending on or selecting CRYPTO while those configs are subordinate to CRYPTO.

Honor the kconfig menu hierarchy to remove kconfig dependency warnings.

Fixes: bf355b8d2c30 ("ipv6: sr: add core files for SR HMAC support") Signed-off-by: Necip Fazil Yildiran fazilyildiran@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/Kconfig | 1 + 1 file changed, 1 insertion(+)

--- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -303,6 +303,7 @@ config IPV6_SEG6_LWTUNNEL config IPV6_SEG6_HMAC bool "IPv6: Segment Routing HMAC support" depends on IPV6 + select CRYPTO select CRYPTO_HMAC select CRYPTO_SHA1 select CRYPTO_SHA256

From: Yoshihiro Shimoda yoshihiro.shimoda.uh@renesas.com

[ Upstream commit 7d3ba9360c6dac7c077fbd6631e08f32ea2bcd53 ]

Since the micrel phy driver calls phy_init_hw() as a workaround, the commit 9886a4dbd2aa ("net: phy: call phy_disable_interrupts() in phy_init_hw()") disables the interrupt unexpectedly. So, call phy_disable_interrupts() in phy_attach_direct() instead. Otherwise, the phy cannot link up after the ethernet cable was disconnected.

Note that other drivers (like at803x.c) also calls phy_init_hw(). So, perhaps, the driver caused a similar issue too.

Fixes: 9886a4dbd2aa ("net: phy: call phy_disable_interrupts() in phy_init_hw()") Signed-off-by: Yoshihiro Shimoda yoshihiro.shimoda.uh@renesas.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/phy/phy_device.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1092,10 +1092,6 @@ int phy_init_hw(struct phy_device *phyde if (ret < 0) return ret;

- ret = phy_disable_interrupts(phydev); - if (ret) - return ret; - if (phydev->drv->config_init) ret = phydev->drv->config_init(phydev);

@@ -1372,6 +1368,10 @@ int phy_attach_direct(struct net_device if (err) goto error;

+ err = phy_disable_interrupts(phydev); + if (err) + return err; + phy_resume(phydev); phy_led_triggers_register(phydev);

From: Yunsheng Lin linyunsheng@huawei.com

[ Upstream commit 2fb541c862c987d02dfdf28f1545016deecfa0d5 ]

Currently there is concurrent reset and enqueue operation for the same lockless qdisc when there is no lock to synchronize the q->enqueue() in __dev_xmit_skb() with the qdisc reset operation in qdisc_deactivate() called by dev_deactivate_queue(), which may cause out-of-bounds access for priv->ring[] in hns3 driver if user has requested a smaller queue num when __dev_xmit_skb() still enqueue a skb with a larger queue_mapping after the corresponding qdisc is reset, and call hns3_nic_net_xmit() with that skb later.

Reused the existing synchronize_net() in dev_deactivate_many() to make sure skb with larger queue_mapping enqueued to old qdisc(which is saved in dev_queue->qdisc_sleeping) will always be reset when dev_reset_queue() is called.

Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking") Signed-off-by: Yunsheng Lin linyunsheng@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/sch_generic.c | 48 +++++++++++++++++++++++++++++++++--------------- 1 file changed, 33 insertions(+), 15 deletions(-)

--- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1131,24 +1131,10 @@ EXPORT_SYMBOL(dev_activate);

static void qdisc_deactivate(struct Qdisc *qdisc) { - bool nolock = qdisc->flags & TCQ_F_NOLOCK; - if (qdisc->flags & TCQ_F_BUILTIN) return; - if (test_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state)) - return; - - if (nolock) - spin_lock_bh(&qdisc->seqlock); - spin_lock_bh(qdisc_lock(qdisc));

set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state); - - qdisc_reset(qdisc); - - spin_unlock_bh(qdisc_lock(qdisc)); - if (nolock) - spin_unlock_bh(&qdisc->seqlock); }

static void dev_deactivate_queue(struct net_device *dev, @@ -1165,6 +1151,30 @@ static void dev_deactivate_queue(struct } }

+static void dev_reset_queue(struct net_device *dev, + struct netdev_queue *dev_queue, + void *_unused) +{ + struct Qdisc *qdisc; + bool nolock; + + qdisc = dev_queue->qdisc_sleeping; + if (!qdisc) + return; + + nolock = qdisc->flags & TCQ_F_NOLOCK; + + if (nolock) + spin_lock_bh(&qdisc->seqlock); + spin_lock_bh(qdisc_lock(qdisc)); + + qdisc_reset(qdisc); + + spin_unlock_bh(qdisc_lock(qdisc)); + if (nolock) + spin_unlock_bh(&qdisc->seqlock); +} + static bool some_qdisc_is_busy(struct net_device *dev) { unsigned int i; @@ -1213,12 +1223,20 @@ void dev_deactivate_many(struct list_hea dev_watchdog_down(dev); }

- /* Wait for outstanding qdisc-less dev_queue_xmit calls. + /* Wait for outstanding qdisc-less dev_queue_xmit calls or + * outstanding qdisc enqueuing calls. * This is avoided if all devices are in dismantle phase : * Caller will call synchronize_net() for us */ synchronize_net();

+ list_for_each_entry(dev, head, close_list) { + netdev_for_each_tx_queue(dev, dev_reset_queue, NULL); + + if (dev_ingress_queue(dev)) + dev_reset_queue(dev, dev_ingress_queue(dev), NULL); + } + /* Wait for outstanding qdisc_run calls. */ list_for_each_entry(dev, head, close_list) { while (some_qdisc_is_busy(dev)) {

From: Jakub Kicinski kuba@kernel.org

[ Upstream commit 5f6857e808a8bd078296575b417c4b9d160b9779 ]

struct ethtool_fecparam carries bitmasks not bit numbers. We want to return 1 (NONE), not 0.

Fixes: 0d0870938337 ("nfp: implement ethtool FEC mode settings") Signed-off-by: Jakub Kicinski kuba@kernel.org Reviewed-by: Simon Horman simon.horman@netronome.com Reviewed-by: Jesse Brandeburg jesse.brandeburg@intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -829,8 +829,8 @@ nfp_port_get_fecparam(struct net_device struct nfp_eth_table_port *eth_port; struct nfp_port *port;

- param->active_fec = ETHTOOL_FEC_NONE_BIT; - param->fec = ETHTOOL_FEC_NONE_BIT; + param->active_fec = ETHTOOL_FEC_NONE; + param->fec = ETHTOOL_FEC_NONE;

port = nfp_port_from_netdev(netdev); eth_port = nfp_port_get_eth_port(port);

From: Peilin Ye yepeilin.cs@gmail.com

[ Upstream commit bb3a420d47ab00d7e1e5083286cab15235a96680 ]

tipc_group_add_to_tree() returns silently if `key` matches `nkey` of an existing node, causing tipc_group_create_member() to leak memory. Let tipc_group_add_to_tree() return an error in such a case, so that tipc_group_create_member() can handle it properly.

Fixes: 75da2163dbb6 ("tipc: introduce communication groups") Reported-and-tested-by: syzbot+f95d90c454864b3b5bc9@syzkaller.appspotmail.com Cc: Hillf Danton hdanton@sina.com Link: https://syzkaller.appspot.com/bug?id=048390604fe1b60df34150265479202f10e13af... Signed-off-by: Peilin Ye yepeilin.cs@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/tipc/group.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-)

--- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -273,8 +273,8 @@ static struct tipc_member *tipc_group_fi return NULL; }

-static void tipc_group_add_to_tree(struct tipc_group *grp, - struct tipc_member *m) +static int tipc_group_add_to_tree(struct tipc_group *grp, + struct tipc_member *m) { u64 nkey, key = (u64)m->node << 32 | m->port; struct rb_node **n, *parent = NULL; @@ -291,10 +291,11 @@ static void tipc_group_add_to_tree(struc else if (key > nkey) n = &(*n)->rb_right; else - return; + return -EEXIST; } rb_link_node(&m->tree_node, parent, n); rb_insert_color(&m->tree_node, &grp->members); + return 0; }

static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, @@ -302,6 +303,7 @@ static struct tipc_member *tipc_group_cr u32 instance, int state) { struct tipc_member *m; + int ret;

m = kzalloc(sizeof(*m), GFP_ATOMIC); if (!m) @@ -314,8 +316,12 @@ static struct tipc_member *tipc_group_cr m->port = port; m->instance = instance; m->bc_acked = grp->bc_snd_nxt - 1; + ret = tipc_group_add_to_tree(grp, m); + if (ret < 0) { + kfree(m); + return NULL; + } grp->member_cnt++; - tipc_group_add_to_tree(grp, m); tipc_nlist_add(&grp->dests, m->node); m->state = state; return m;

From: Xin Long lucien.xin@gmail.com

[ Upstream commit ff48b6222e65ebdba5a403ef1deba6214e749193 ]

In tipc_buf_append() it may change skb's frag_list, and it causes problems when this skb is cloned. skb_unclone() doesn't really make this skb's flag_list available to change.

Shuang Li has reported an use-after-free issue because of this when creating quite a few macvlan dev over the same dev, where the broadcast packets will be cloned and go up to the stack:

[ ] BUG: KASAN: use-after-free in pskb_expand_head+0x86d/0xea0 [ ] Call Trace: [ ] dump_stack+0x7c/0xb0 [ ] print_address_description.constprop.7+0x1a/0x220 [ ] kasan_report.cold.10+0x37/0x7c [ ] check_memory_region+0x183/0x1e0 [ ] pskb_expand_head+0x86d/0xea0 [ ] process_backlog+0x1df/0x660 [ ] net_rx_action+0x3b4/0xc90 [ ] [ ] Allocated by task 1786: [ ] kmem_cache_alloc+0xbf/0x220 [ ] skb_clone+0x10a/0x300 [ ] macvlan_broadcast+0x2f6/0x590 [macvlan] [ ] macvlan_process_broadcast+0x37c/0x516 [macvlan] [ ] process_one_work+0x66a/0x1060 [ ] worker_thread+0x87/0xb10 [ ] [ ] Freed by task 3253: [ ] kmem_cache_free+0x82/0x2a0 [ ] skb_release_data+0x2c3/0x6e0 [ ] kfree_skb+0x78/0x1d0 [ ] tipc_recvmsg+0x3be/0xa40 [tipc]

So fix it by using skb_unshare() instead, which would create a new skb for the cloned frag and it'll be safe to change its frag_list. The similar things were also done in sctp_make_reassembled_event(), which is using skb_copy().

Reported-by: Shuang Li shuali@redhat.com Fixes: 37e22164a8a3 ("tipc: rename and move message reassembly function") Signed-off-by: Xin Long lucien.xin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/tipc/msg.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -150,7 +150,8 @@ int tipc_buf_append(struct sk_buff **hea if (fragid == FIRST_FRAGMENT) { if (unlikely(head)) goto err; - if (unlikely(skb_unclone(frag, GFP_ATOMIC))) + frag = skb_unshare(frag, GFP_ATOMIC); + if (unlikely(!frag)) goto err; head = *headbuf = frag; *buf = NULL;

From: Tariq Toukan tariqt@mellanox.com

[ Upstream commit 8f0bcd19b1da3f264223abea985b9462e85a3718 ]

The set of TLS TX global SW counters in mlx5e_tls_sw_stats_desc is updated from all rings by using atomic ops. This set of stats is used only in the FPGA TLS use case, not in the Connect-X TLS one, where regular per-ring counters are used.

Do not expose them in the Connect-X use case, as this would cause counter duplication. For example, tx_tls_drop_no_sync_data would appear twice in the ethtool stats.

Fixes: d2ead1f360e8 ("net/mlx5e: Add kTLS TX HW offload support") Signed-off-by: Tariq Toukan tariqt@mellanox.com Reviewed-by: Moshe Shemesh moshe@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c | 12 +++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c @@ -35,7 +35,6 @@ #include <net/sock.h>

#include "en.h" -#include "accel/tls.h" #include "fpga/sdk.h" #include "en_accel/tls.h"

@@ -51,9 +50,14 @@ static const struct counter_desc mlx5e_t

#define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc)

+static bool is_tls_atomic_stats(struct mlx5e_priv *priv) +{ + return priv->tls && !mlx5_accel_is_ktls_device(priv->mdev); +} + int mlx5e_tls_get_count(struct mlx5e_priv *priv) { - if (!priv->tls) + if (!is_tls_atomic_stats(priv)) return 0;

return NUM_TLS_SW_COUNTERS; @@ -63,7 +67,7 @@ int mlx5e_tls_get_strings(struct mlx5e_p { unsigned int i, idx = 0;

- if (!priv->tls) + if (!is_tls_atomic_stats(priv)) return 0;

for (i = 0; i < NUM_TLS_SW_COUNTERS; i++) @@ -77,7 +81,7 @@ int mlx5e_tls_get_stats(struct mlx5e_pri { int i, idx = 0;

- if (!priv->tls) + if (!is_tls_atomic_stats(priv)) return 0;

for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)

From: Edwin Peer edwin.peer@broadcom.com

[ Upstream commit d69753fa1ecb3218b56b022722f7a5822735b876 ]

Returning "unknown" as a temperature value violates the hwmon interface rules. Appropriate error codes should be returned via device_attribute show instead. These will ultimately be propagated to the user via the file system interface.

In addition to the corrected error handling, it is an even better idea to not present the sensor in sysfs at all if it is known that the read will definitely fail. Given that temp1_input is currently the only sensor reported, ensure no hwmon registration if TEMP_MONITOR_QUERY is not supported or if it will fail due to access permissions. Something smarter may be needed if and when other sensors are added.

Fixes: 12cce90b934b ("bnxt_en: fix HWRM error when querying VF temperature") Signed-off-by: Edwin Peer edwin.peer@broadcom.com Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-)

--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -8993,18 +8993,16 @@ static ssize_t bnxt_show_temp(struct dev struct hwrm_temp_monitor_query_output *resp; struct bnxt *bp = dev_get_drvdata(dev); u32 len = 0; + int rc;

resp = bp->hwrm_cmd_resp_addr; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1); mutex_lock(&bp->hwrm_cmd_lock); - if (!_hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT)) + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (!rc) len = sprintf(buf, "%u\n", resp->temp * 1000); /* display millidegree */ mutex_unlock(&bp->hwrm_cmd_lock); - - if (len) - return len; - - return sprintf(buf, "unknown\n"); + return rc ?: len; } static SENSOR_DEVICE_ATTR(temp1_input, 0444, bnxt_show_temp, NULL, 0);

@@ -9024,7 +9022,16 @@ static void bnxt_hwmon_close(struct bnxt

static void bnxt_hwmon_open(struct bnxt *bp) { + struct hwrm_temp_monitor_query_input req = {0}; struct pci_dev *pdev = bp->pdev; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1); + rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc == -EACCES || rc == -EOPNOTSUPP) { + bnxt_hwmon_close(bp); + return; + }

if (bp->hwmon_dev) return;

From: Hauke Mehrtens hauke@hauke-m.de

[ Upstream commit dea36631e6f186d4b853af67a4aef2e35cfa8bb7 ]

The call to netif_wake_queue() when the TX descriptors were freed was missing. When there are no TX buffers available the TX queue will be stopped, but it was not started again when they are available again, this is fixed in this patch.

Fixes: fe1a56420cf2 ("net: lantiq: Add Lantiq / Intel VRX200 Ethernet driver") Signed-off-by: Hauke Mehrtens hauke@hauke-m.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/lantiq_xrx200.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -268,6 +268,9 @@ static int xrx200_tx_housekeeping(struct net_dev->stats.tx_bytes += bytes; netdev_completed_queue(ch->priv->net_dev, pkts, bytes);

+ if (netif_queue_stopped(net_dev)) + netif_wake_queue(net_dev); + if (pkts < budget) { napi_complete(&ch->napi); ltq_dma_enable_irq(&ch->dma);

From: Hauke Mehrtens hauke@hauke-m.de

[ Upstream commit c582a7fea9dad4d309437d1a7e22e6d2cb380e2e ]

Use napi_complete_done() and activate the interrupts when this function returns true. This way the generic NAPI code can take care of activating the interrupts.

Signed-off-by: Hauke Mehrtens hauke@hauke-m.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/lantiq_xrx200.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -230,8 +230,8 @@ static int xrx200_poll_rx(struct napi_st }

if (rx < budget) { - napi_complete(&ch->napi); - ltq_dma_enable_irq(&ch->dma); + if (napi_complete_done(&ch->napi, rx)) + ltq_dma_enable_irq(&ch->dma); }

return rx; @@ -272,8 +272,8 @@ static int xrx200_tx_housekeeping(struct netif_wake_queue(net_dev);

if (pkts < budget) { - napi_complete(&ch->napi); - ltq_dma_enable_irq(&ch->dma); + if (napi_complete_done(&ch->napi, pkts)) + ltq_dma_enable_irq(&ch->dma); }

return pkts;

From: Florian Fainelli f.fainelli@gmail.com

[ Upstream commit c2b727df7caa33876e7066bde090f40001b6d643 ]

If we have unbound the PHY driver prior to calling phy_detach() (often via phy_disconnect()) then we can cause a NULL pointer de-reference accessing the driver owner member. The steps to reproduce are:

echo unimac-mdio-0:01 > /sys/class/net/eth0/phydev/driver/unbind ip link set eth0 down

Fixes: cafe8df8b9bc ("net: phy: Fix lack of reference count on PHY driver") Signed-off-by: Florian Fainelli f.fainelli@gmail.com Reviewed-by: Andrew Lunn andrew@lunn.ch Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/phy/phy_device.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1631,7 +1631,8 @@ void phy_detach(struct phy_device *phyde

phy_led_triggers_unregister(phydev);

- module_put(phydev->mdio.dev.driver->owner); + if (phydev->mdio.dev.driver) + module_put(phydev->mdio.dev.driver->owner);

/* If the device had no specific driver before (i.e. - it * was using the generic driver), we unbind the device

From: Eric Dumazet edumazet@google.com

[ Upstream commit 3ca1a42a52ca4b4f02061683851692ad65fefac8 ]

If skb_put_padto() returns an error, skb has been freed. Better not touch it anymore, as reported by syzbot [1]

Note to qrtr maintainers : this suggests qrtr_sendmsg() should adjust sock_alloc_send_skb() second parameter to account for the potential added alignment to avoid reallocation.

[1]

BUG: KASAN: use-after-free in __skb_insert include/linux/skbuff.h:1907 [inline] BUG: KASAN: use-after-free in __skb_queue_before include/linux/skbuff.h:2016 [inline] BUG: KASAN: use-after-free in __skb_queue_tail include/linux/skbuff.h:2049 [inline] BUG: KASAN: use-after-free in skb_queue_tail+0x6b/0x120 net/core/skbuff.c:3146 Write of size 8 at addr ffff88804d8ab3c0 by task syz-executor.4/4316

CPU: 1 PID: 4316 Comm: syz-executor.4 Not tainted 5.9.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1d6/0x29e lib/dump_stack.c:118 print_address_description+0x66/0x620 mm/kasan/report.c:383 __kasan_report mm/kasan/report.c:513 [inline] kasan_report+0x132/0x1d0 mm/kasan/report.c:530 __skb_insert include/linux/skbuff.h:1907 [inline] __skb_queue_before include/linux/skbuff.h:2016 [inline] __skb_queue_tail include/linux/skbuff.h:2049 [inline] skb_queue_tail+0x6b/0x120 net/core/skbuff.c:3146 qrtr_tun_send+0x1a/0x40 net/qrtr/tun.c:23 qrtr_node_enqueue+0x44f/0xc00 net/qrtr/qrtr.c:364 qrtr_bcast_enqueue+0xbe/0x140 net/qrtr/qrtr.c:861 qrtr_sendmsg+0x680/0x9c0 net/qrtr/qrtr.c:960 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] sock_write_iter+0x317/0x470 net/socket.c:998 call_write_iter include/linux/fs.h:1882 [inline] new_sync_write fs/read_write.c:503 [inline] vfs_write+0xa96/0xd10 fs/read_write.c:578 ksys_write+0x11b/0x220 fs/read_write.c:631 do_syscall_64+0x31/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x45d5b9 Code: 5d b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 2b b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f84b5b81c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000038b40 RCX: 000000000045d5b9 RDX: 0000000000000055 RSI: 0000000020001240 RDI: 0000000000000003 RBP: 00007f84b5b81ca0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000000f R13: 00007ffcbbf86daf R14: 00007f84b5b829c0 R15: 000000000118cf4c

Allocated by task 4316: kasan_save_stack mm/kasan/common.c:48 [inline] kasan_set_track mm/kasan/common.c:56 [inline] __kasan_kmalloc+0x100/0x130 mm/kasan/common.c:461 slab_post_alloc_hook+0x3e/0x290 mm/slab.h:518 slab_alloc mm/slab.c:3312 [inline] kmem_cache_alloc+0x1c1/0x2d0 mm/slab.c:3482 skb_clone+0x1b2/0x370 net/core/skbuff.c:1449 qrtr_bcast_enqueue+0x6d/0x140 net/qrtr/qrtr.c:857 qrtr_sendmsg+0x680/0x9c0 net/qrtr/qrtr.c:960 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] sock_write_iter+0x317/0x470 net/socket.c:998 call_write_iter include/linux/fs.h:1882 [inline] new_sync_write fs/read_write.c:503 [inline] vfs_write+0xa96/0xd10 fs/read_write.c:578 ksys_write+0x11b/0x220 fs/read_write.c:631 do_syscall_64+0x31/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Freed by task 4316: kasan_save_stack mm/kasan/common.c:48 [inline] kasan_set_track+0x3d/0x70 mm/kasan/common.c:56 kasan_set_free_info+0x17/0x30 mm/kasan/generic.c:355 __kasan_slab_free+0xdd/0x110 mm/kasan/common.c:422 __cache_free mm/slab.c:3418 [inline] kmem_cache_free+0x82/0xf0 mm/slab.c:3693 __skb_pad+0x3f5/0x5a0 net/core/skbuff.c:1823 __skb_put_padto include/linux/skbuff.h:3233 [inline] skb_put_padto include/linux/skbuff.h:3252 [inline] qrtr_node_enqueue+0x62f/0xc00 net/qrtr/qrtr.c:360 qrtr_bcast_enqueue+0xbe/0x140 net/qrtr/qrtr.c:861 qrtr_sendmsg+0x680/0x9c0 net/qrtr/qrtr.c:960 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] sock_write_iter+0x317/0x470 net/socket.c:998 call_write_iter include/linux/fs.h:1882 [inline] new_sync_write fs/read_write.c:503 [inline] vfs_write+0xa96/0xd10 fs/read_write.c:578 ksys_write+0x11b/0x220 fs/read_write.c:631 do_syscall_64+0x31/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9

The buggy address belongs to the object at ffff88804d8ab3c0 which belongs to the cache skbuff_head_cache of size 224 The buggy address is located 0 bytes inside of 224-byte region [ffff88804d8ab3c0, ffff88804d8ab4a0) The buggy address belongs to the page: page:00000000ea8cccfb refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88804d8abb40 pfn:0x4d8ab flags: 0xfffe0000000200(slab) raw: 00fffe0000000200 ffffea0002237ec8 ffffea00029b3388 ffff88821bb66800 raw: ffff88804d8abb40 ffff88804d8ab000 000000010000000b 0000000000000000 page dumped because: kasan: bad access detected

Fixes: ce57785bf91b ("net: qrtr: fix len of skb_put_padto in qrtr_node_enqueue") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Cc: Carl Huang cjhuang@codeaurora.org Cc: Wen Gong wgong@codeaurora.org Cc: Bjorn Andersson bjorn.andersson@linaro.org Cc: Manivannan Sadhasivam manivannan.sadhasivam@linaro.org Acked-by: Manivannan Sadhasivam manivannan.sadhasivam@linaro.org Reviewed-by: Bjorn Andersson bjorn.andersson@linaro.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/qrtr/qrtr.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-)

--- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -332,8 +332,7 @@ static int qrtr_node_enqueue(struct qrtr { struct qrtr_hdr_v1 *hdr; size_t len = skb->len; - int rc = -ENODEV; - int confirm_rx; + int rc, confirm_rx;

confirm_rx = qrtr_tx_wait(node, to->sq_node, to->sq_port, type); if (confirm_rx < 0) { @@ -357,15 +356,17 @@ static int qrtr_node_enqueue(struct qrtr hdr->size = cpu_to_le32(len); hdr->confirm_rx = !!confirm_rx;

- skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr)); - - mutex_lock(&node->ep_lock); - if (node->ep) - rc = node->ep->xmit(node->ep, skb); - else - kfree_skb(skb); - mutex_unlock(&node->ep_lock); + rc = skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr));

+ if (!rc) { + mutex_lock(&node->ep_lock); + rc = -ENODEV; + if (node->ep) + rc = node->ep->xmit(node->ep, skb); + else + kfree_skb(skb); + mutex_unlock(&node->ep_lock); + } /* Need to ensure that a subsequent message carries the otherwise lost * confirm_rx flag if we dropped this one */ if (rc && confirm_rx)

From: Grygorii Strashko grygorii.strashko@ti.com

[ Upstream commit 5760d9acbe9514eec68eb70821d6fa5764f57042 ]

Add missed suspend/resume callbacks to properly restore networking after suspend/resume cycle.

Fixes: ed3525eda4c4 ("net: ethernet: ti: introduce cpsw switchdev based driver part 1 - dual-emac") Signed-off-by: Grygorii Strashko grygorii.strashko@ti.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/ti/cpsw_new.c | 53 +++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+)

--- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -17,6 +17,7 @@ #include <linux/phy.h> #include <linux/phy/phy.h> #include <linux/delay.h> +#include <linux/pinctrl/consumer.h> #include <linux/pm_runtime.h> #include <linux/gpio/consumer.h> #include <linux/of.h> @@ -2070,9 +2071,61 @@ static int cpsw_remove(struct platform_d return 0; }

+static int __maybe_unused cpsw_suspend(struct device *dev) +{ + struct cpsw_common *cpsw = dev_get_drvdata(dev); + int i; + + rtnl_lock(); + + for (i = 0; i < cpsw->data.slaves; i++) { + struct net_device *ndev = cpsw->slaves[i].ndev; + + if (!(ndev && netif_running(ndev))) + continue; + + cpsw_ndo_stop(ndev); + } + + rtnl_unlock(); + + /* Select sleep pin state */ + pinctrl_pm_select_sleep_state(dev); + + return 0; +} + +static int __maybe_unused cpsw_resume(struct device *dev) +{ + struct cpsw_common *cpsw = dev_get_drvdata(dev); + int i; + + /* Select default pin state */ + pinctrl_pm_select_default_state(dev); + + /* shut up ASSERT_RTNL() warning in netif_set_real_num_tx/rx_queues */ + rtnl_lock(); + + for (i = 0; i < cpsw->data.slaves; i++) { + struct net_device *ndev = cpsw->slaves[i].ndev; + + if (!(ndev && netif_running(ndev))) + continue; + + cpsw_ndo_open(ndev); + } + + rtnl_unlock(); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(cpsw_pm_ops, cpsw_suspend, cpsw_resume); + static struct platform_driver cpsw_driver = { .driver = { .name = "cpsw-switch", + .pm = &cpsw_pm_ops, .of_match_table = cpsw_of_mtable, }, .probe = cpsw_probe,

From: "Jason A. Donenfeld" Jason@zx2c4.com

[ Upstream commit 6147f7b1e90ff09bd52afc8b9206a7fcd133daf7 ]

Eric's suggested fix for the previous commit's mentioned race condition was to simply take the table->lock in wg_index_hashtable_replace(). The table->lock of the hash table is supposed to protect the bucket heads, not the entires, but actually, since all the mutator functions are already taking it, it makes sense to take it too for the test to hlist_unhashed, as a defense in depth measure, so that it no longer races with deletions, regardless of what other locks are protecting individual entries. This is sensible from a performance perspective because, as Eric pointed out, the case of being unhashed is already the unlikely case, so this won't add common contention. And comparing instructions, this basically doesn't make much of a difference other than pushing and popping %r13, used by the new `bool ret`. More generally, I like the idea of locking consistency across table mutator functions, and this might let me rest slightly easier at night.

Suggested-by: Eric Dumazet edumazet@google.com Link: https://lore.kernel.org/wireguard/20200908145911.4090480-1-edumazet@google.c... Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireguard/peerlookup.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)

--- a/drivers/net/wireguard/peerlookup.c +++ b/drivers/net/wireguard/peerlookup.c @@ -167,9 +167,13 @@ bool wg_index_hashtable_replace(struct i struct index_hashtable_entry *old, struct index_hashtable_entry *new) { - if (unlikely(hlist_unhashed(&old->index_hash))) - return false; + bool ret; + spin_lock_bh(&table->lock); + ret = !hlist_unhashed(&old->index_hash); + if (unlikely(!ret)) + goto out; + new->index = old->index; hlist_replace_rcu(&old->index_hash, &new->index_hash);

@@ -180,8 +184,9 @@ bool wg_index_hashtable_replace(struct i * simply gets dropped, which isn't terrible. */ INIT_HLIST_NODE(&old->index_hash); +out: spin_unlock_bh(&table->lock); - return true; + return ret; }

void wg_index_hashtable_remove(struct index_hashtable *table,

From: Jianbo Liu jianbol@mellanox.com

[ Upstream commit 12a240a41427d37b5e70570700704e84c827452f ]

When deleting vxlan flow rule under multipath, tun_info in parse_attr is not freed when the rule is not ready.

Fixes: ef06c9ee8933 ("net/mlx5e: Allow one failure when offloading tc encap rules under multipath") Signed-off-by: Jianbo Liu jianbol@mellanox.com Reviewed-by: Roi Dayan roid@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1399,11 +1399,8 @@ static void mlx5e_tc_del_fdb_flow(struct

mlx5e_put_flow_tunnel_id(flow);

- if (flow_flag_test(flow, NOT_READY)) { + if (flow_flag_test(flow, NOT_READY)) remove_unready_flow(flow); - kvfree(attr->parse_attr); - return; - }

if (mlx5e_is_offloaded_flow(flow)) { if (flow_flag_test(flow, SLOW))

From: Dexuan Cui decui@microsoft.com

[ Upstream commit 19162fd4063a3211843b997a454b505edb81d5ce ]

mlx5_suspend()/resume() keep the network interface, so during hibernation netvsc_unregister_vf() and netvsc_register_vf() are not called, and hence netvsc_resume() should call netvsc_vf_changed() to switch the data path back to the VF after hibernation. Note: after we close and re-open the vmbus channel of the netvsc NIC in netvsc_suspend() and netvsc_resume(), the data path is implicitly switched to the netvsc NIC. Similarly, netvsc_suspend() should not call netvsc_unregister_vf(), otherwise the VF can no longer be used after hibernation.

For mlx4, since the VF network interafce is explicitly destroyed and re-created during hibernation (see mlx4_suspend()/resume()), hv_netvsc already explicitly switches the data path from and to the VF automatically via netvsc_register_vf() and netvsc_unregister_vf(), so mlx4 doesn't need this fix. Note: mlx4 can still work with the fix because in netvsc_suspend()/resume() ndev_ctx->vf_netdev is NULL for mlx4.

Fixes: 0efeea5fb153 ("hv_netvsc: Add the support of hibernation") Signed-off-by: Dexuan Cui decui@microsoft.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/hyperv/netvsc_drv.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-)

--- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2544,8 +2544,8 @@ static int netvsc_remove(struct hv_devic static int netvsc_suspend(struct hv_device *dev) { struct net_device_context *ndev_ctx; - struct net_device *vf_netdev, *net; struct netvsc_device *nvdev; + struct net_device *net; int ret;

net = hv_get_drvdata(dev); @@ -2561,10 +2561,6 @@ static int netvsc_suspend(struct hv_devi goto out; }

- vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev); - if (vf_netdev) - netvsc_unregister_vf(vf_netdev); - /* Save the current config info */ ndev_ctx->saved_netvsc_dev_info = netvsc_devinfo_get(nvdev);

@@ -2580,6 +2576,7 @@ static int netvsc_resume(struct hv_devic struct net_device *net = hv_get_drvdata(dev); struct net_device_context *net_device_ctx; struct netvsc_device_info *device_info; + struct net_device *vf_netdev; int ret;

rtnl_lock(); @@ -2592,6 +2589,15 @@ static int netvsc_resume(struct hv_devic netvsc_devinfo_put(device_info); net_device_ctx->saved_netvsc_dev_info = NULL;

+ /* A NIC driver (e.g. mlx5) may keep the VF network interface across + * hibernation, but here the data path is implicitly switched to the + * netvsc NIC since the vmbus channel is closed and re-opened, so + * netvsc_vf_changed() must be used to switch the data path to the VF. + */ + vf_netdev = rtnl_dereference(net_device_ctx->vf_netdev); + if (vf_netdev && netvsc_vf_changed(vf_netdev) != NOTIFY_OK) + ret = -EINVAL; + rtnl_unlock();

return ret;

From: Matthias Schiffer matthias.schiffer@ew.tq-group.com

[ Upstream commit fd944dc24336922656a48f4608bfb41abdcdc4aa ]

The KSZ9477 and KSZ8795 use the port_cnt field differently: For the KSZ9477, it includes the CPU port(s), while for the KSZ8795, it doesn't.

It would be a good cleanup to make the handling of both drivers match, but as a first step, fix the recently broken assignment of num_ports in the KSZ8795 driver (which completely broke probing, as the CPU port index was always failing the num_ports check).

Fixes: af199a1a9cb0 ("net: dsa: microchip: set the correct number of ports") Signed-off-by: Matthias Schiffer matthias.schiffer@ew.tq-group.com Reviewed-by: Codrin Ciubotariu codrin.ciubotariu@microchip.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/dsa/microchip/ksz8795.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -1269,7 +1269,7 @@ static int ksz8795_switch_init(struct ks }

/* set the real number of ports */ - dev->ds->num_ports = dev->port_cnt; + dev->ds->num_ports = dev->port_cnt + 1;

return 0; }

From: Taehee Yoo ap420073@gmail.com

[ Upstream commit e1f469cd5866499ac40bfdca87411e1c525a10c7 ]

This reverts commit 8d7e5dee972f1cde2ba96c621f1541fa36e7d4f4.

To protect netns id, the nsid_lock is used when netns id is being allocated and removed by peernet2id_alloc() and unhash_nsid(). The nsid_lock can be used in BH context but only spin_lock() is used in this code. Using spin_lock() instead of spin_lock_bh() can result in a deadlock in the following scenario reported by the lockdep. In order to avoid a deadlock, the spin_lock_bh() should be used instead of spin_lock() to acquire nsid_lock.

Test commands: ip netns del nst ip netns add nst ip link add veth1 type veth peer name veth2 ip link set veth1 netns nst ip netns exec nst ip link add name br1 type bridge vlan_filtering 1 ip netns exec nst ip link set dev br1 up ip netns exec nst ip link set dev veth1 master br1 ip netns exec nst ip link set dev veth1 up ip netns exec nst ip link add macvlan0 link br1 up type macvlan

Splat looks like: [ 33.615860][ T607] WARNING: SOFTIRQ-safe -> SOFTIRQ-unsafe lock order detected [ 33.617194][ T607] 5.9.0-rc1+ #665 Not tainted [ ... ] [ 33.670615][ T607] Chain exists of: [ 33.670615][ T607] &mc->mca_lock --> &bridge_netdev_addr_lock_key --> &net->nsid_lock [ 33.670615][ T607] [ 33.673118][ T607] Possible interrupt unsafe locking scenario: [ 33.673118][ T607] [ 33.674599][ T607] CPU0 CPU1 [ 33.675557][ T607] ---- ---- [ 33.676516][ T607] lock(&net->nsid_lock); [ 33.677306][ T607] local_irq_disable(); [ 33.678517][ T607] lock(&mc->mca_lock); [ 33.679725][ T607] lock(&bridge_netdev_addr_lock_key); [ 33.681166][ T607] <Interrupt> [ 33.681791][ T607] lock(&mc->mca_lock); [ 33.682579][ T607] [ 33.682579][ T607] *** DEADLOCK *** [ ... ] [ 33.922046][ T607] stack backtrace: [ 33.922999][ T607] CPU: 3 PID: 607 Comm: ip Not tainted 5.9.0-rc1+ #665 [ 33.924099][ T607] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 [ 33.925714][ T607] Call Trace: [ 33.926238][ T607] dump_stack+0x78/0xab [ 33.926905][ T607] check_irq_usage+0x70b/0x720 [ 33.927708][ T607] ? iterate_chain_key+0x60/0x60 [ 33.928507][ T607] ? check_path+0x22/0x40 [ 33.929201][ T607] ? check_noncircular+0xcf/0x180 [ 33.930024][ T607] ? __lock_acquire+0x1952/0x1f20 [ 33.930860][ T607] __lock_acquire+0x1952/0x1f20 [ 33.931667][ T607] lock_acquire+0xaf/0x3a0 [ 33.932366][ T607] ? peernet2id_alloc+0x3a/0x170 [ 33.933147][ T607] ? br_port_fill_attrs+0x54c/0x6b0 [bridge] [ 33.934140][ T607] ? br_port_fill_attrs+0x5de/0x6b0 [bridge] [ 33.935113][ T607] ? kvm_sched_clock_read+0x14/0x30 [ 33.935974][ T607] _raw_spin_lock+0x30/0x70 [ 33.936728][ T607] ? peernet2id_alloc+0x3a/0x170 [ 33.937523][ T607] peernet2id_alloc+0x3a/0x170 [ 33.938313][ T607] rtnl_fill_ifinfo+0xb5e/0x1400 [ 33.939091][ T607] rtmsg_ifinfo_build_skb+0x8a/0xf0 [ 33.939953][ T607] rtmsg_ifinfo_event.part.39+0x17/0x50 [ 33.940863][ T607] rtmsg_ifinfo+0x1f/0x30 [ 33.941571][ T607] __dev_notify_flags+0xa5/0xf0 [ 33.942376][ T607] ? __irq_work_queue_local+0x49/0x50 [ 33.943249][ T607] ? irq_work_queue+0x1d/0x30 [ 33.943993][ T607] ? __dev_set_promiscuity+0x7b/0x1a0 [ 33.944878][ T607] __dev_set_promiscuity+0x7b/0x1a0 [ 33.945758][ T607] dev_set_promiscuity+0x1e/0x50 [ 33.946582][ T607] br_port_set_promisc+0x1f/0x40 [bridge] [ 33.947487][ T607] br_manage_promisc+0x8b/0xe0 [bridge] [ 33.948388][ T607] __dev_set_promiscuity+0x123/0x1a0 [ 33.949244][ T607] __dev_set_rx_mode+0x68/0x90 [ 33.950021][ T607] dev_uc_add+0x50/0x60 [ 33.950720][ T607] macvlan_open+0x18e/0x1f0 [macvlan] [ 33.951601][ T607] __dev_open+0xd6/0x170 [ 33.952269][ T607] __dev_change_flags+0x181/0x1d0 [ 33.953056][ T607] rtnl_configure_link+0x2f/0xa0 [ 33.953884][ T607] __rtnl_newlink+0x6b9/0x8e0 [ 33.954665][ T607] ? __lock_acquire+0x95d/0x1f20 [ 33.955450][ T607] ? lock_acquire+0xaf/0x3a0 [ 33.956193][ T607] ? is_bpf_text_address+0x5/0xe0 [ 33.956999][ T607] rtnl_newlink+0x47/0x70

Acked-by: Guillaume Nault gnault@redhat.com Fixes: 8d7e5dee972f ("netns: don't disable BHs when locking "nsid_lock"") Reported-by: syzbot+3f960c64a104eaa2c813@syzkaller.appspotmail.com Signed-off-by: Taehee Yoo ap420073@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/net_namespace.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-)

--- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -251,10 +251,10 @@ int peernet2id_alloc(struct net *net, st if (refcount_read(&net->count) == 0) return NETNSA_NSID_NOT_ASSIGNED;

- spin_lock(&net->nsid_lock); + spin_lock_bh(&net->nsid_lock); id = __peernet2id(net, peer); if (id >= 0) { - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); return id; }

@@ -264,12 +264,12 @@ int peernet2id_alloc(struct net *net, st * just been idr_remove()'d from there in cleanup_net(). */ if (!maybe_get_net(peer)) { - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); return NETNSA_NSID_NOT_ASSIGNED; }

id = alloc_netid(net, peer, -1); - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock);

put_net(peer); if (id < 0) @@ -534,20 +534,20 @@ static void unhash_nsid(struct net *net, for_each_net(tmp) { int id;

- spin_lock(&tmp->nsid_lock); + spin_lock_bh(&tmp->nsid_lock); id = __peernet2id(tmp, net); if (id >= 0) idr_remove(&tmp->netns_ids, id); - spin_unlock(&tmp->nsid_lock); + spin_unlock_bh(&tmp->nsid_lock); if (id >= 0) rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL, GFP_KERNEL); if (tmp == last) break; } - spin_lock(&net->nsid_lock); + spin_lock_bh(&net->nsid_lock); idr_destroy(&net->netns_ids); - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); }

static LLIST_HEAD(cleanup_list); @@ -760,9 +760,9 @@ static int rtnl_net_newid(struct sk_buff return PTR_ERR(peer); }

- spin_lock(&net->nsid_lock); + spin_lock_bh(&net->nsid_lock); if (__peernet2id(net, peer) >= 0) { - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); err = -EEXIST; NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, @@ -771,7 +771,7 @@ static int rtnl_net_newid(struct sk_buff }

err = alloc_netid(net, peer, nsid); - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); if (err >= 0) { rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid, nlh, GFP_KERNEL);

From: Maxim Mikityanskiy maximmi@mellanox.com

[ Upstream commit 9c25a22dfb00270372224721fed646965420323a ]

As described in the previous commit, napi_synchronize doesn't quite fit the purpose when we just need to wait until the currently running NAPI quits. Its implementation waits until NAPI is not running by polling and waiting for 1ms in between. In cases where we need to deactivate one queue (e.g., recovery flows) or where we deactivate them one-by-one (deactivate channel flow), we may get stuck in napi_synchronize forever if other queues keep NAPI active, causing a soft lockup. Depending on kernel configuration (CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC), it may result in a kernel panic.

To fix the issue, use synchronize_rcu to wait for NAPI to quit, and wrap the whole NAPI in rcu_read_lock.

Fixes: acc6c5953af1 ("net/mlx5e: Split open/close channels to stages") Signed-off-by: Maxim Mikityanskiy maximmi@mellanox.com Reviewed-by: Tariq Toukan tariqt@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c | 14 ++------------ drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c | 3 +-- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 12 ++++-------- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 12 ++---------- drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c | 17 +++++++++++++---- 5 files changed, 22 insertions(+), 36 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -31,7 +31,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_m { struct xdp_buff *xdp = wi->umr.dma_info[page_idx].xsk; u32 cqe_bcnt32 = cqe_bcnt; - bool consumed;

/* Check packet size. Note LRO doesn't use linear SKB */ if (unlikely(cqe_bcnt > rq->hw_mtu)) { @@ -51,10 +50,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_m xsk_buff_dma_sync_for_cpu(xdp); prefetch(xdp->data);

- rcu_read_lock(); - consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp); - rcu_read_unlock(); - /* Possible flows: * - XDP_REDIRECT to XSKMAP: * The page is owned by the userspace from now. @@ -70,7 +65,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_m * allocated first from the Reuse Ring, so it has enough space. */

- if (likely(consumed)) { + if (likely(mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp))) { if (likely(__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))) __set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */ return NULL; /* page/packet was consumed by XDP */ @@ -88,7 +83,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_l u32 cqe_bcnt) { struct xdp_buff *xdp = wi->di->xsk; - bool consumed;

/* wi->offset is not used in this function, because xdp->data and the * DMA address point directly to the necessary place. Furthermore, the @@ -107,11 +101,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_l return NULL; }

- rcu_read_lock(); - consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp); - rcu_read_unlock(); - - if (likely(consumed)) + if (likely(mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp))) return NULL; /* page/packet was consumed by XDP */

/* XDP_PASS: copy the data from the UMEM to a new SKB. The frame reuse --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -143,8 +143,7 @@ err_free_cparam: void mlx5e_close_xsk(struct mlx5e_channel *c) { clear_bit(MLX5E_CHANNEL_STATE_XSK, c->state); - napi_synchronize(&c->napi); - synchronize_rcu(); /* Sync with the XSK wakeup. */ + synchronize_rcu(); /* Sync with the XSK wakeup and with NAPI. */

mlx5e_close_rq(&c->xskrq); mlx5e_close_cq(&c->xskrq.cq); --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -911,7 +911,7 @@ void mlx5e_activate_rq(struct mlx5e_rq * void mlx5e_deactivate_rq(struct mlx5e_rq *rq) { clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); - napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */ + synchronize_rcu(); /* Sync with NAPI to prevent mlx5e_post_rx_wqes. */ }

void mlx5e_close_rq(struct mlx5e_rq *rq) @@ -1356,12 +1356,10 @@ void mlx5e_tx_disable_queue(struct netde

static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) { - struct mlx5e_channel *c = sq->channel; struct mlx5_wq_cyc *wq = &sq->wq;

clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); - /* prevent netif_tx_wake_queue */ - napi_synchronize(&c->napi); + synchronize_rcu(); /* Sync with NAPI to prevent netif_tx_wake_queue. */

mlx5e_tx_disable_queue(sq->txq);

@@ -1436,10 +1434,8 @@ void mlx5e_activate_icosq(struct mlx5e_i

void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq) { - struct mlx5e_channel *c = icosq->channel; - clear_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state); - napi_synchronize(&c->napi); + synchronize_rcu(); /* Sync with NAPI. */ }

void mlx5e_close_icosq(struct mlx5e_icosq *sq) @@ -1517,7 +1513,7 @@ void mlx5e_close_xdpsq(struct mlx5e_xdps struct mlx5e_channel *c = sq->channel;

clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); - napi_synchronize(&c->napi); + synchronize_rcu(); /* Sync with NAPI. */

mlx5e_destroy_sq(c->mdev, sq->sqn); mlx5e_free_xdpsq_descs(sq); --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1072,7 +1072,6 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_r struct xdp_buff xdp; struct sk_buff *skb; void *va, *data; - bool consumed; u32 frag_size;

va = page_address(di->page) + wi->offset; @@ -1084,11 +1083,8 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_r prefetchw(va); /* xdp_frame data area */ prefetch(data);

- rcu_read_lock(); mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt, &xdp); - consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt, &xdp); - rcu_read_unlock(); - if (consumed) + if (mlx5e_xdp_handle(rq, di, &cqe_bcnt, &xdp)) return NULL; /* page/packet was consumed by XDP */

rx_headroom = xdp.data - xdp.data_hard_start; @@ -1369,7 +1365,6 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct m struct sk_buff *skb; void *va, *data; u32 frag_size; - bool consumed;

/* Check packet size. Note LRO doesn't use linear SKB */ if (unlikely(cqe_bcnt > rq->hw_mtu)) { @@ -1386,11 +1381,8 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct m prefetchw(va); /* xdp_frame data area */ prefetch(data);

- rcu_read_lock(); mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt32, &xdp); - consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt32, &xdp); - rcu_read_unlock(); - if (consumed) { + if (mlx5e_xdp_handle(rq, di, &cqe_bcnt32, &xdp)) { if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) __set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */ return NULL; /* page/packet was consumed by XDP */ --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -121,13 +121,17 @@ int mlx5e_napi_poll(struct napi_struct * struct mlx5e_xdpsq *xsksq = &c->xsksq; struct mlx5e_rq *xskrq = &c->xskrq; struct mlx5e_rq *rq = &c->rq; - bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state); bool aff_change = false; bool busy_xsk = false; bool busy = false; int work_done = 0; + bool xsk_open; int i;

+ rcu_read_lock(); + + xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state); + ch_stats->poll++;

for (i = 0; i < c->num_tc; i++) @@ -167,8 +171,10 @@ int mlx5e_napi_poll(struct napi_struct * busy |= busy_xsk;

if (busy) { - if (likely(mlx5e_channel_no_affinity_change(c))) - return budget; + if (likely(mlx5e_channel_no_affinity_change(c))) { + work_done = budget; + goto out; + } ch_stats->aff_change++; aff_change = true; if (budget && work_done == budget) @@ -176,7 +182,7 @@ int mlx5e_napi_poll(struct napi_struct * }

if (unlikely(!napi_complete_done(napi, work_done))) - return work_done; + goto out;

ch_stats->arm++;

@@ -203,6 +209,9 @@ int mlx5e_napi_poll(struct napi_struct * ch_stats->force_irq++; }

+out: + rcu_read_unlock(); + return work_done; }