From eeb0d56fab4cd7848cf2be6704fa48900dbc1381 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 14 Dec 2016 16:47:43 +0100 Subject: mac80211: implement multicast forwarding on fast-RX path In AP (or VLAN) mode, when unicast 802.11 packets are received, they might actually be multicast after conversion. In this case the fast-RX path didn't handle them properly to send them back to the wireless medium. Implement that by copying the SKB and sending it back out. The possible alternative would be to just punt the packet back to the regular (slow) RX path, but since we have almost all of the required code here already it's not so complicated to add here. Punting it back would also mean acquiring the spinlock, which would be bad for the stated purpose of the fast-RX path, to enable well-performing parallel RX. Cc: stable@vger.kernel.org Signed-off-by: Johannes Berg --- net/mac80211/rx.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 3e289a64ed43..c037c5bb6167 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3942,21 +3942,31 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, u64_stats_update_end(&stats->syncp); if (fast_rx->internal_forward) { - struct sta_info *dsta = sta_info_get(rx->sdata, skb->data); + struct sk_buff *xmit_skb = NULL; + bool multicast = is_multicast_ether_addr(skb->data); - if (dsta) { + if (multicast) { + xmit_skb = skb_copy(skb, GFP_ATOMIC); + } else if (sta_info_get(rx->sdata, skb->data)) { + xmit_skb = skb; + skb = NULL; + } + + if (xmit_skb) { /* * Send to wireless media and increase priority by 256 * to keep the received priority instead of * reclassifying the frame (see cfg80211_classify8021d). */ - skb->priority += 256; - skb->protocol = htons(ETH_P_802_3); - skb_reset_network_header(skb); - skb_reset_mac_header(skb); - dev_queue_xmit(skb); - return true; + xmit_skb->priority += 256; + xmit_skb->protocol = htons(ETH_P_802_3); + skb_reset_network_header(xmit_skb); + skb_reset_mac_header(xmit_skb); + dev_queue_xmit(xmit_skb); } + + if (!skb) + return true; } /* deliver to local stack */ -- cgit v1.2.3 From c38c39bf7cc04d688291f382469e84ec2a8548a4 Mon Sep 17 00:00:00 2001 From: Cedric Izoard Date: Wed, 11 Jan 2017 14:39:07 +0000 Subject: mac80211: Fix headroom allocation when forwarding mesh pkt This patch fix issue introduced by my previous commit that tried to ensure enough headroom was present, and instead broke it. When forwarding mesh pkt, mac80211 may also add security header, and it must therefore be taken into account in the needed headroom. Fixes: d8da0b5d64d5 ("mac80211: Ensure enough headroom when forwarding mesh pkt") Signed-off-by: Cedric Izoard Signed-off-by: Johannes Berg --- net/mac80211/rx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index c037c5bb6167..c87e61358b77 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2472,7 +2472,8 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) if (!ifmsh->mshcfg.dot11MeshForwarding) goto out; - fwd_skb = skb_copy_expand(skb, local->tx_headroom, 0, GFP_ATOMIC); + fwd_skb = skb_copy_expand(skb, local->tx_headroom + + sdata->encrypt_headroom, 0, GFP_ATOMIC); if (!fwd_skb) { net_info_ratelimited("%s: failed to clone mesh frame\n", sdata->name); -- cgit v1.2.3 From d7f842442f766db3f39fc5d166ddcc24bf817056 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Tue, 25 Oct 2016 10:32:16 +0300 Subject: mac80211: fix the TID on NDPs sent as EOSP carrier In the commit below, I forgot to translate the mac80211's AC to QoS IE order. Moreover, the condition in the if was wrong. Fix both issues. This bug would hit only with clients that didn't set all the ACs as delivery enabled. Fixes: f438ceb81d4 ("mac80211: uapsd_queues is in QoS IE order") Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- net/mac80211/sta_info.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index b6cfcf038c11..50c309094c37 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1501,8 +1501,8 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, /* This will evaluate to 1, 3, 5 or 7. */ for (ac = IEEE80211_AC_VO; ac < IEEE80211_NUM_ACS; ac++) - if (ignored_acs & BIT(ac)) - continue; + if (!(ignored_acs & ieee80211_ac_to_qos_mask[ac])) + break; tid = 7 - 2 * ac; ieee80211_send_null_response(sta, tid, reason, true, false); -- cgit v1.2.3 From 06f7c88c107fb469f4f1344142e80df5175c6836 Mon Sep 17 00:00:00 2001 From: Beni Lev Date: Tue, 19 Jul 2016 19:28:56 +0300 Subject: cfg80211: consider VHT opmode on station update Currently, this attribute is only fetched on station addition, but not on station change. Since this info is only present in the assoc request, with full station state support in the driver it cannot be present when the station is added. Thus, add support for changing the VHT opmode on station update if done before (or while) the station is marked as associated. After this, ignore it, since it used to be ignored. Signed-off-by: Beni Lev Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 4 +++- net/wireless/nl80211.c | 15 +++++++++++++++ 2 files changed, 18 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 6b76e3b0c18e..bea982af9cfb 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1772,7 +1772,9 @@ enum nl80211_commands { * * @NL80211_ATTR_OPMODE_NOTIF: Operating mode field from Operating Mode * Notification Element based on association request when used with - * %NL80211_CMD_NEW_STATION; u8 attribute. + * %NL80211_CMD_NEW_STATION or %NL80211_CMD_SET_STATION (only when + * %NL80211_FEATURE_FULL_AP_CLIENT_STATE is supported, or with TDLS); + * u8 attribute. * * @NL80211_ATTR_VENDOR_ID: The vendor ID, either a 24-bit OUI or, if * %NL80211_VENDOR_ID_IS_LINUX is set, a special Linux ID (not used yet) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ef5eff93a8b8..5c1b267e22be 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4615,6 +4615,15 @@ int cfg80211_check_station_change(struct wiphy *wiphy, break; } + /* + * Older kernel versions ignored this attribute entirely, so don't + * reject attempts to update it but mark it as unused instead so the + * driver won't look at the data. + */ + if (statype != CFG80211_STA_AP_CLIENT_UNASSOC && + statype != CFG80211_STA_TDLS_PEER_SETUP) + params->opmode_notif_used = false; + return 0; } EXPORT_SYMBOL(cfg80211_check_station_change); @@ -4854,6 +4863,12 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) params.local_pm = pm; } + if (info->attrs[NL80211_ATTR_OPMODE_NOTIF]) { + params.opmode_notif_used = true; + params.opmode_notif = + nla_get_u8(info->attrs[NL80211_ATTR_OPMODE_NOTIF]); + } + /* Include parameters for TDLS peer (will check later) */ err = nl80211_set_station_tdls(info, ¶ms); if (err) -- cgit v1.2.3 From 96aa2e7cf126773b16c6c19b7474a8a38d3c707e Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 7 Oct 2016 12:23:49 +0200 Subject: mac80211: calculate min channel width correctly In the current minimum chandef code there's an issue in that the recalculation can happen after rate control is initialized for a station that has a wider bandwidth than the current chanctx, and then rate control can immediately start using those higher rates which could cause problems. Observe that first of all that this problem is because we don't take non-associated and non-uploaded stations into account. The restriction to non-associated is quite pointless and is one of the causes for the problem described above, since the rate init will happen before the station is set to associated; no frames could actually be sent until associated, but the rate table can already contain higher rates and that might cause problems. Also, rejecting non-uploaded stations is wrong, since the rate control can select higher rates for those as well. Secondly, it's then necessary to recalculate the minimal config before initializing rate control, so that when rate control is initialized, the higher rates are already available. This can be done easily by adding the necessary function call in rate init. Change-Id: Ib9bc02d34797078db55459d196993f39dcd43070 Signed-off-by: Johannes Berg --- net/mac80211/chan.c | 3 --- net/mac80211/rate.c | 2 ++ 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index e75cbf6ecc26..a0d901d8992e 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -231,9 +231,6 @@ ieee80211_get_max_required_bw(struct ieee80211_sub_if_data *sdata) !(sta->sdata->bss && sta->sdata->bss == sdata->bss)) continue; - if (!sta->uploaded || !test_sta_flag(sta, WLAN_STA_ASSOC)) - continue; - max_bw = max(max_bw, ieee80211_get_sta_bw(&sta->sta)); } rcu_read_unlock(); diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 206698bc93f4..9e2641d45587 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -40,6 +40,8 @@ void rate_control_rate_init(struct sta_info *sta) ieee80211_sta_set_rx_nss(sta); + ieee80211_recalc_min_chandef(sta->sdata); + if (!ref) return; -- cgit v1.2.3 From d2941df8fbd9708035d66d889ada4d3d160170ce Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 20 Oct 2016 08:52:50 +0200 Subject: mac80211: recalculate min channel width on VHT opmode changes When an associated station changes its VHT operating mode this can/will affect the bandwidth it's using, and consequently we must recalculate the minimum bandwidth we need to use. Failure to do so can lead to one of two scenarios: 1) we use a too high bandwidth, this is benign 2) we use a too narrow bandwidth, causing rate control and actual PHY configuration to be out of sync, which can in turn cause problems/crashes Signed-off-by: Johannes Berg --- net/mac80211/iface.c | 21 +++++++++++++++++++++ net/mac80211/rx.c | 9 +-------- net/mac80211/vht.c | 4 +++- 3 files changed, 25 insertions(+), 9 deletions(-) diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 41497b670e2b..d37ae7dc114b 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -6,6 +6,7 @@ * Copyright (c) 2006 Jiri Benc * Copyright 2008, Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright (c) 2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1295,6 +1296,26 @@ static void ieee80211_iface_work(struct work_struct *work) } else if (ieee80211_is_action(mgmt->frame_control) && mgmt->u.action.category == WLAN_CATEGORY_VHT) { switch (mgmt->u.action.u.vht_group_notif.action_code) { + case WLAN_VHT_ACTION_OPMODE_NOTIF: { + struct ieee80211_rx_status *status; + enum nl80211_band band; + u8 opmode; + + status = IEEE80211_SKB_RXCB(skb); + band = status->band; + opmode = mgmt->u.action.u.vht_opmode_notif.operating_mode; + + mutex_lock(&local->sta_mtx); + sta = sta_info_get_bss(sdata, mgmt->sa); + + if (sta) + ieee80211_vht_handle_opmode(sdata, sta, + opmode, + band); + + mutex_unlock(&local->sta_mtx); + break; + } case WLAN_VHT_ACTION_GROUPID_MGMT: ieee80211_process_mu_groups(sdata, mgmt); break; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index c87e61358b77..3090dd4342f6 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2881,17 +2881,10 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) switch (mgmt->u.action.u.vht_opmode_notif.action_code) { case WLAN_VHT_ACTION_OPMODE_NOTIF: { - u8 opmode; - /* verify opmode is present */ if (len < IEEE80211_MIN_ACTION_SIZE + 2) goto invalid; - - opmode = mgmt->u.action.u.vht_opmode_notif.operating_mode; - - ieee80211_vht_handle_opmode(rx->sdata, rx->sta, - opmode, status->band); - goto handled; + goto queue; } case WLAN_VHT_ACTION_GROUPID_MGMT: { if (len < IEEE80211_MIN_ACTION_SIZE + 25) diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 6832bf6ab69f..43e45bb660bc 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -527,8 +527,10 @@ void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, u32 changed = __ieee80211_vht_handle_opmode(sdata, sta, opmode, band); - if (changed > 0) + if (changed > 0) { + ieee80211_recalc_min_chandef(sdata); rate_control_rate_update(local, sband, sta, changed); + } } void ieee80211_get_vht_mask_from_cap(__le16 vht_cap, -- cgit v1.2.3 From 19c0f40d4fca3a47b8f784a627f0467f0138ccc8 Mon Sep 17 00:00:00 2001 From: hayeswang Date: Wed, 11 Jan 2017 16:25:34 +0800 Subject: r8152: fix the sw rx checksum is unavailable Fix the hw rx checksum is always enabled, and the user couldn't switch it to sw rx checksum. Note that the RTL_VER_01 only support sw rx checksum only. Besides, the hw rx checksum for RTL_VER_02 is disabled after commit b9a321b48af4 ("r8152: Fix broken RX checksums."). Re-enable it. Signed-off-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index be418563cb18..f3b48ad90865 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1730,7 +1730,7 @@ static u8 r8152_rx_csum(struct r8152 *tp, struct rx_desc *rx_desc) u8 checksum = CHECKSUM_NONE; u32 opts2, opts3; - if (tp->version == RTL_VER_01 || tp->version == RTL_VER_02) + if (!(tp->netdev->features & NETIF_F_RXCSUM)) goto return_result; opts2 = le32_to_cpu(rx_desc->opts2); @@ -4356,6 +4356,11 @@ static int rtl8152_probe(struct usb_interface *intf, NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | NETIF_F_IPV6_CSUM | NETIF_F_TSO6; + if (tp->version == RTL_VER_01) { + netdev->features &= ~NETIF_F_RXCSUM; + netdev->hw_features &= ~NETIF_F_RXCSUM; + } + netdev->ethtool_ops = &ops; netif_set_gso_max_size(netdev, RTL_LIMITED_TSO_SIZE); -- cgit v1.2.3 From 4ecb1d83f6abe8d49163427f4d431ebe98f8bd5f Mon Sep 17 00:00:00 2001 From: Martynas Pumputis Date: Wed, 11 Jan 2017 15:18:53 +0000 Subject: vxlan: Set ports in flow key when doing route lookups Otherwise, a xfrm policy with sport/dport being set cannot be matched. Signed-off-by: Martynas Pumputis Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index bb70dd5723b5..ca7196c40060 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1798,7 +1798,7 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, struct net_device *dev, struct vxlan_sock *sock4, struct sk_buff *skb, int oif, u8 tos, - __be32 daddr, __be32 *saddr, + __be32 daddr, __be32 *saddr, __be16 dport, __be16 sport, struct dst_cache *dst_cache, const struct ip_tunnel_info *info) { @@ -1824,6 +1824,8 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, struct net_device fl4.flowi4_proto = IPPROTO_UDP; fl4.daddr = daddr; fl4.saddr = *saddr; + fl4.fl4_dport = dport; + fl4.fl4_sport = sport; rt = ip_route_output_key(vxlan->net, &fl4); if (likely(!IS_ERR(rt))) { @@ -1851,6 +1853,7 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, __be32 label, const struct in6_addr *daddr, struct in6_addr *saddr, + __be16 dport, __be16 sport, struct dst_cache *dst_cache, const struct ip_tunnel_info *info) { @@ -1877,6 +1880,8 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tos), label); fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = IPPROTO_UDP; + fl6.fl6_dport = dport; + fl6.fl6_sport = sport; err = ipv6_stub->ipv6_dst_lookup(vxlan->net, sock6->sock->sk, @@ -2068,6 +2073,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, rdst ? rdst->remote_ifindex : 0, tos, dst->sin.sin_addr.s_addr, &src->sin.sin_addr.s_addr, + dst_port, src_port, dst_cache, info); if (IS_ERR(rt)) { err = PTR_ERR(rt); @@ -2104,6 +2110,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, rdst ? rdst->remote_ifindex : 0, tos, label, &dst->sin6.sin6_addr, &src->sin6.sin6_addr, + dst_port, src_port, dst_cache, info); if (IS_ERR(ndst)) { err = PTR_ERR(ndst); @@ -2430,7 +2437,7 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) rt = vxlan_get_route(vxlan, dev, sock4, skb, 0, info->key.tos, info->key.u.ipv4.dst, - &info->key.u.ipv4.src, NULL, info); + &info->key.u.ipv4.src, dport, sport, NULL, info); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); @@ -2441,7 +2448,7 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) ndst = vxlan6_get_route(vxlan, dev, sock6, skb, 0, info->key.tos, info->key.label, &info->key.u.ipv6.dst, - &info->key.u.ipv6.src, NULL, info); + &info->key.u.ipv6.src, dport, sport, NULL, info); if (IS_ERR(ndst)) return PTR_ERR(ndst); dst_release(ndst); -- cgit v1.2.3 From 0719e72ccb801829a3d735d187ca8417f0930459 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 11 Jan 2017 09:16:32 -0800 Subject: netvsc: add rcu_read locking to netvsc callback The receive callback (in tasklet context) is using RCU to get reference to associated VF network device but this is not safe. RCU read lock needs to be held. Found by running with full lockdep debugging enabled. Fixes: f207c10d9823 ("hv_netvsc: use RCU to protect vf_netdev") Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/hyperv/netvsc_drv.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index c9414c054852..fcab8019dda0 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -659,6 +659,7 @@ int netvsc_recv_callback(struct hv_device *device_obj, * policy filters on the host). Deliver these via the VF * interface in the guest. */ + rcu_read_lock(); vf_netdev = rcu_dereference(net_device_ctx->vf_netdev); if (vf_netdev && (vf_netdev->flags & IFF_UP)) net = vf_netdev; @@ -667,6 +668,7 @@ int netvsc_recv_callback(struct hv_device *device_obj, skb = netvsc_alloc_recv_skb(net, packet, csum_info, *data, vlan_tci); if (unlikely(!skb)) { ++net->stats.rx_dropped; + rcu_read_unlock(); return NVSP_STAT_FAIL; } @@ -696,6 +698,7 @@ int netvsc_recv_callback(struct hv_device *device_obj, * TODO - use NAPI? */ netif_rx(skb); + rcu_read_unlock(); return 0; } -- cgit v1.2.3 From 36bf38d158d3482119b3e159c0619b3c1539b508 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Thu, 12 Jan 2017 09:10:37 +0100 Subject: mlxsw: spectrum: Fix memory leak at skb reallocation During transmission the skb is checked for headroom in order to add vendor specific header. In case the skb needs to be re-allocated, skb_realloc_headroom() is called to make a private copy of the original, but doesn't release it. Current code assumes that the original skb is released during reallocation and only releases it at the error path which causes a memory leak. Fix this by adding the original skb release to the main path. Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC") Signed-off-by: Arkadi Sharshevsky Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index d768c7b6c6d6..003093abb170 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -684,6 +684,7 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb, dev_kfree_skb_any(skb_orig); return NETDEV_TX_OK; } + dev_consume_skb_any(skb_orig); } if (eth_skb_pad(skb)) { -- cgit v1.2.3 From 400fc0106dd8c27ed84781c929c1a184785b9c79 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Thu, 12 Jan 2017 09:10:38 +0100 Subject: mlxsw: switchx2: Fix memory leak at skb reallocation During transmission the skb is checked for headroom in order to add vendor specific header. In case the skb needs to be re-allocated, skb_realloc_headroom() is called to make a private copy of the original, but doesn't release it. Current code assumes that the original skb is released during reallocation and only releases it at the error path which causes a memory leak. Fix this by adding the original skb release to the main path. Fixes: d003462a50de ("mlxsw: Simplify mlxsw_sx_port_xmit function") Signed-off-by: Arkadi Sharshevsky Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/switchx2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index 150ccf5192a9..2e88115e8735 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -345,6 +345,7 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb, dev_kfree_skb_any(skb_orig); return NETDEV_TX_OK; } + dev_consume_skb_any(skb_orig); } mlxsw_sx_txhdr_construct(skb, &tx_info); /* TX header is consumed by HW on the way so we shouldn't count its -- cgit v1.2.3 From 28e46a0f2e03ab4ed0e23cace1ea89a68c8c115b Mon Sep 17 00:00:00 2001 From: Elad Raz Date: Thu, 12 Jan 2017 09:10:39 +0100 Subject: mlxsw: pci: Fix EQE structure definition The event_data starts from address 0x00-0x0C and not from 0x08-0x014. This leads to duplication with other fields in the Event Queue Element such as sub-type, cqn and owner. Fixes: eda6500a987a0 ("mlxsw: Add PCI bus implementation") Signed-off-by: Elad Raz Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/pci_hw.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index d147ddd97997..0af3338bfcb4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -209,21 +209,21 @@ MLXSW_ITEM32(pci, eqe, owner, 0x0C, 0, 1); /* pci_eqe_cmd_token * Command completion event - token */ -MLXSW_ITEM32(pci, eqe, cmd_token, 0x08, 16, 16); +MLXSW_ITEM32(pci, eqe, cmd_token, 0x00, 16, 16); /* pci_eqe_cmd_status * Command completion event - status */ -MLXSW_ITEM32(pci, eqe, cmd_status, 0x08, 0, 8); +MLXSW_ITEM32(pci, eqe, cmd_status, 0x00, 0, 8); /* pci_eqe_cmd_out_param_h * Command completion event - output parameter - higher part */ -MLXSW_ITEM32(pci, eqe, cmd_out_param_h, 0x0C, 0, 32); +MLXSW_ITEM32(pci, eqe, cmd_out_param_h, 0x04, 0, 32); /* pci_eqe_cmd_out_param_l * Command completion event - output parameter - lower part */ -MLXSW_ITEM32(pci, eqe, cmd_out_param_l, 0x10, 0, 32); +MLXSW_ITEM32(pci, eqe, cmd_out_param_l, 0x08, 0, 32); #endif -- cgit v1.2.3 From 18a3ed59d09cf81a6447aadf6931bf0c9ffec5e0 Mon Sep 17 00:00:00 2001 From: Kazuya Mizuguchi Date: Thu, 12 Jan 2017 13:21:06 +0100 Subject: ravb: Remove Rx overflow log messages Remove Rx overflow log messages as in an environment where logging results in network traffic logging may cause further overflows. Fixes: c156633f1353 ("Renesas Ethernet AVB driver proper") Signed-off-by: Kazuya Mizuguchi [simon: reworked changelog] Signed-off-by: Simon Horman Acked-by: Sergei Shtylyov Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/ravb_main.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 92d7692c840d..5e5ad978eab9 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -926,14 +926,10 @@ static int ravb_poll(struct napi_struct *napi, int budget) /* Receive error message handling */ priv->rx_over_errors = priv->stats[RAVB_BE].rx_over_errors; priv->rx_over_errors += priv->stats[RAVB_NC].rx_over_errors; - if (priv->rx_over_errors != ndev->stats.rx_over_errors) { + if (priv->rx_over_errors != ndev->stats.rx_over_errors) ndev->stats.rx_over_errors = priv->rx_over_errors; - netif_err(priv, rx_err, ndev, "Receive Descriptor Empty\n"); - } - if (priv->rx_fifo_errors != ndev->stats.rx_fifo_errors) { + if (priv->rx_fifo_errors != ndev->stats.rx_fifo_errors) ndev->stats.rx_fifo_errors = priv->rx_fifo_errors; - netif_err(priv, rx_err, ndev, "Receive FIFO Overflow\n"); - } out: return budget - quota; } -- cgit v1.2.3 From ea7a80858f57d8878b1499ea0f1b8a635cc48de7 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 11 Jan 2017 14:29:54 -0800 Subject: net: lwtunnel: Handle lwtunnel_fill_encap failure Handle failure in lwtunnel_fill_encap adding attributes to skb. Fixes: 571e722676fe ("ipv4: support for fib route lwtunnel encap attributes") Fixes: 19e42e451506 ("ipv6: support for fib route lwtunnel encap attributes") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/fib_semantics.c | 11 +++++++---- net/ipv6/route.c | 3 ++- 2 files changed, 9 insertions(+), 5 deletions(-) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index eba1546b5031..9a375b908d01 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1279,8 +1279,9 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid)) goto nla_put_failure; #endif - if (fi->fib_nh->nh_lwtstate) - lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate); + if (fi->fib_nh->nh_lwtstate && + lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate) < 0) + goto nla_put_failure; } #ifdef CONFIG_IP_ROUTE_MULTIPATH if (fi->fib_nhs > 1) { @@ -1316,8 +1317,10 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) goto nla_put_failure; #endif - if (nh->nh_lwtstate) - lwtunnel_fill_encap(skb, nh->nh_lwtstate); + if (nh->nh_lwtstate && + lwtunnel_fill_encap(skb, nh->nh_lwtstate) < 0) + goto nla_put_failure; + /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh; } endfor_nexthops(fi); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index ce5aaf448c54..4f6b067c8753 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3317,7 +3317,8 @@ static int rt6_fill_node(struct net *net, if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags))) goto nla_put_failure; - lwtunnel_fill_encap(skb, rt->dst.lwtstate); + if (lwtunnel_fill_encap(skb, rt->dst.lwtstate) < 0) + goto nla_put_failure; nlmsg_end(skb, nlh); return 0; -- cgit v1.2.3 From 994c5483e7f6dbf9fea622ba2031b9d868feb4b9 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Wed, 11 Jan 2017 16:45:51 -0600 Subject: net: qcom/emac: grab a reference to the phydev on ACPI systems Commit 6ffe1c4cd0a7 ("net: qcom/emac: fix of_node and phydev leaks") fixed the problem with reference leaks on phydev, but the fix is device-tree specific. When the driver unloads, the reference is dropped only on DT systems. Instead, it's cleaner if up grab an reference on ACPI systems. When the driver unloads, we can drop the reference without having to check whether we're on a DT system. Signed-off-by: Timur Tabi Reviewed-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/emac/emac-phy.c | 7 +++++++ drivers/net/ethernet/qualcomm/emac/emac.c | 6 ++---- 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/emac/emac-phy.c b/drivers/net/ethernet/qualcomm/emac/emac-phy.c index 99a14df28b96..2851b4c56570 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-phy.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-phy.c @@ -201,6 +201,13 @@ int emac_phy_config(struct platform_device *pdev, struct emac_adapter *adpt) else adpt->phydev = mdiobus_get_phy(mii_bus, phy_addr); + /* of_phy_find_device() claims a reference to the phydev, + * so we do that here manually as well. When the driver + * later unloads, it can unilaterally drop the reference + * without worrying about ACPI vs DT. + */ + if (adpt->phydev) + get_device(&adpt->phydev->mdio.dev); } else { struct device_node *phy_np; diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 422289c232bc..f46d300bd585 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -719,8 +719,7 @@ static int emac_probe(struct platform_device *pdev) err_undo_napi: netif_napi_del(&adpt->rx_q.napi); err_undo_mdiobus: - if (!has_acpi_companion(&pdev->dev)) - put_device(&adpt->phydev->mdio.dev); + put_device(&adpt->phydev->mdio.dev); mdiobus_unregister(adpt->mii_bus); err_undo_clocks: emac_clks_teardown(adpt); @@ -740,8 +739,7 @@ static int emac_remove(struct platform_device *pdev) emac_clks_teardown(adpt); - if (!has_acpi_companion(&pdev->dev)) - put_device(&adpt->phydev->mdio.dev); + put_device(&adpt->phydev->mdio.dev); mdiobus_unregister(adpt->mii_bus); free_netdev(netdev); -- cgit v1.2.3 From 8a430ed50bb1b19ca14a46661f3b1b35f2fb5c39 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 11 Jan 2017 15:42:17 -0800 Subject: net: ipv4: fix table id in getroute response rtm_table is an 8-bit field while table ids are allowed up to u32. Commit 709772e6e065 ("net: Fix routing tables with id > 255 for legacy software") added the preference to set rtm_table in dumps to RT_TABLE_COMPAT if the table id is > 255. The table id returned on get route requests should do the same. Fixes: c36ba6603a11 ("net: Allow user to get table id from route lookup") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 0fcac8e7a2b2..709ffe67d1de 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2472,7 +2472,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, r->rtm_dst_len = 32; r->rtm_src_len = 0; r->rtm_tos = fl4->flowi4_tos; - r->rtm_table = table_id; + r->rtm_table = table_id < 256 ? table_id : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table_id)) goto nla_put_failure; r->rtm_type = rt->rt_type; -- cgit v1.2.3 From 05a974efa4bdf6e2a150e3f27dc6fcf0a9ad5655 Mon Sep 17 00:00:00 2001 From: Stefan Schmidt Date: Thu, 15 Dec 2016 18:40:14 +0100 Subject: ieee802154: atusb: do not use the stack for buffers to make them DMA able From 4.9 we should really avoid using the stack here as this will not be DMA able on various platforms. This changes the buffers already being present in time of 4.9 being released. This should go into stable as well. Reported-by: Dan Carpenter Cc: stable@vger.kernel.org Signed-off-by: Stefan Schmidt Signed-off-by: Marcel Holtmann --- drivers/net/ieee802154/atusb.c | 31 +++++++++++++++++++++++++++---- 1 file changed, 27 insertions(+), 4 deletions(-) diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c index 1253f864737a..fa3e8c34b26c 100644 --- a/drivers/net/ieee802154/atusb.c +++ b/drivers/net/ieee802154/atusb.c @@ -117,13 +117,26 @@ static int atusb_read_reg(struct atusb *atusb, uint8_t reg) { struct usb_device *usb_dev = atusb->usb_dev; int ret; + uint8_t *buffer; uint8_t value; + buffer = kmalloc(1, GFP_KERNEL); + if (!buffer) + return -ENOMEM; + dev_dbg(&usb_dev->dev, "atusb: reg = 0x%x\n", reg); ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0), ATUSB_REG_READ, ATUSB_REQ_FROM_DEV, - 0, reg, &value, 1, 1000); - return ret >= 0 ? value : ret; + 0, reg, buffer, 1, 1000); + + if (ret >= 0) { + value = buffer[0]; + kfree(buffer); + return value; + } else { + kfree(buffer); + return ret; + } } static int atusb_write_subreg(struct atusb *atusb, uint8_t reg, uint8_t mask, @@ -608,9 +621,13 @@ static const struct ieee802154_ops atusb_ops = { static int atusb_get_and_show_revision(struct atusb *atusb) { struct usb_device *usb_dev = atusb->usb_dev; - unsigned char buffer[3]; + unsigned char *buffer; int ret; + buffer = kmalloc(3, GFP_KERNEL); + if (!buffer) + return -ENOMEM; + /* Get a couple of the ATMega Firmware values */ ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0), ATUSB_ID, ATUSB_REQ_FROM_DEV, 0, 0, @@ -631,15 +648,20 @@ static int atusb_get_and_show_revision(struct atusb *atusb) dev_info(&usb_dev->dev, "Please update to version 0.2 or newer"); } + kfree(buffer); return ret; } static int atusb_get_and_show_build(struct atusb *atusb) { struct usb_device *usb_dev = atusb->usb_dev; - char build[ATUSB_BUILD_SIZE + 1]; + char *build; int ret; + build = kmalloc(ATUSB_BUILD_SIZE + 1, GFP_KERNEL); + if (!build) + return -ENOMEM; + ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0), ATUSB_BUILD, ATUSB_REQ_FROM_DEV, 0, 0, build, ATUSB_BUILD_SIZE, 1000); @@ -648,6 +670,7 @@ static int atusb_get_and_show_build(struct atusb *atusb) dev_info(&usb_dev->dev, "Firmware: build %s\n", build); } + kfree(build); return ret; } -- cgit v1.2.3 From 2fd2b550a5ed13b1d6640ff77630fc369636a544 Mon Sep 17 00:00:00 2001 From: Stefan Schmidt Date: Thu, 15 Dec 2016 18:40:15 +0100 Subject: ieee802154: atusb: make sure we set a randaom extended address if fetching fails In the unlikely case were the firmware is new enough but the actual USB command still fails make sure we set a random address and return. Signed-off-by: Stefan Schmidt Signed-off-by: Marcel Holtmann --- drivers/net/ieee802154/atusb.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c index fa3e8c34b26c..67790f88908d 100644 --- a/drivers/net/ieee802154/atusb.c +++ b/drivers/net/ieee802154/atusb.c @@ -737,8 +737,11 @@ static int atusb_set_extended_addr(struct atusb *atusb) ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0), ATUSB_EUI64_READ, ATUSB_REQ_FROM_DEV, 0, 0, buffer, IEEE802154_EXTENDED_ADDR_LEN, 1000); - if (ret < 0) - dev_err(&usb_dev->dev, "failed to fetch extended address\n"); + if (ret < 0) { + dev_err(&usb_dev->dev, "failed to fetch extended address, random address set\n"); + ieee802154_random_extended_addr(&atusb->hw->phy->perm_extended_addr); + return ret; + } memcpy(&extended_addr, buffer, IEEE802154_EXTENDED_ADDR_LEN); /* Check if read address is not empty and the unicast bit is set correctly */ -- cgit v1.2.3 From 5eb35a6ccea61648a55713c076ab65423eea1ac0 Mon Sep 17 00:00:00 2001 From: Stefan Schmidt Date: Thu, 15 Dec 2016 18:40:16 +0100 Subject: ieee802154: atusb: do not use the stack for address fetching to make it DMA able From 4.9 we should really avoid using the stack here as this will not be DMA able on various platforms. This changes a buffer that was introduced in the 4.10 merge window. Fixes: 6cc33eba232c ("ieee802154: atusb: try to read permanent extended address from device") Reported-by: Dan Carpenter Signed-off-by: Stefan Schmidt Signed-off-by: Marcel Holtmann --- drivers/net/ieee802154/atusb.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c index 67790f88908d..63cb67917a07 100644 --- a/drivers/net/ieee802154/atusb.c +++ b/drivers/net/ieee802154/atusb.c @@ -721,7 +721,7 @@ fail: static int atusb_set_extended_addr(struct atusb *atusb) { struct usb_device *usb_dev = atusb->usb_dev; - unsigned char buffer[IEEE802154_EXTENDED_ADDR_LEN]; + unsigned char *buffer; __le64 extended_addr; u64 addr; int ret; @@ -733,6 +733,10 @@ static int atusb_set_extended_addr(struct atusb *atusb) return 0; } + buffer = kmalloc(IEEE802154_EXTENDED_ADDR_LEN, GFP_KERNEL); + if (!buffer) + return -ENOMEM; + /* Firmware is new enough so we fetch the address from EEPROM */ ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0), ATUSB_EUI64_READ, ATUSB_REQ_FROM_DEV, 0, 0, @@ -740,6 +744,7 @@ static int atusb_set_extended_addr(struct atusb *atusb) if (ret < 0) { dev_err(&usb_dev->dev, "failed to fetch extended address, random address set\n"); ieee802154_random_extended_addr(&atusb->hw->phy->perm_extended_addr); + kfree(buffer); return ret; } @@ -755,6 +760,7 @@ static int atusb_set_extended_addr(struct atusb *atusb) &addr); } + kfree(buffer); return ret; } -- cgit v1.2.3 From f301606934b240fb54d8edf3618a0483e36046fc Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Sun, 18 Dec 2016 15:25:33 -0800 Subject: at86rf230: Allow slow GPIO pins for "rstn" Driver code never touches "rstn" signal in atomic context, so there's no need to implicitly put such restriction on it by using gpio_set_value to manipulate it. Replace gpio_set_value to gpio_set_value_cansleep to fix that. As a an example of where such restriction might be inconvenient, consider a hardware design where "rstn" is connected to a pin of I2C/SPI GPIO expander chip. Cc: Chris Healy Signed-off-by: Andrey Smirnov Signed-off-by: Stefan Schmidt Signed-off-by: Marcel Holtmann --- drivers/net/ieee802154/at86rf230.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c index 46d53a6c8cf8..76ba7ecfe142 100644 --- a/drivers/net/ieee802154/at86rf230.c +++ b/drivers/net/ieee802154/at86rf230.c @@ -1715,9 +1715,9 @@ static int at86rf230_probe(struct spi_device *spi) /* Reset */ if (gpio_is_valid(rstn)) { udelay(1); - gpio_set_value(rstn, 0); + gpio_set_value_cansleep(rstn, 0); udelay(1); - gpio_set_value(rstn, 1); + gpio_set_value_cansleep(rstn, 1); usleep_range(120, 240); } -- cgit v1.2.3 From 8e38b7d4d71479b23b77f01cf0e5071610b8f357 Mon Sep 17 00:00:00 2001 From: Stefan Schmidt Date: Mon, 2 Jan 2017 16:58:13 +0100 Subject: ieee802154: atusb: fix driver to work with older firmware versions After the addition of the frame_retries callback we could run into cases where a ATUSB device with an older firmware version would now longer be able to bring the interface up. We keep this functionality disabled now if the minimum firmware version for this feature is not available. Fixes: 5d82288b93db3bc ("ieee802154: atusb: implement .set_frame_retries ops callback") Reported-by: Alexander Aring Acked-by: Alexander Aring Signed-off-by: Stefan Schmidt Signed-off-by: Marcel Holtmann --- drivers/net/ieee802154/atusb.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c index 63cb67917a07..ef688518ad77 100644 --- a/drivers/net/ieee802154/atusb.c +++ b/drivers/net/ieee802154/atusb.c @@ -562,13 +562,6 @@ static int atusb_set_frame_retries(struct ieee802154_hw *hw, s8 retries) { struct atusb *atusb = hw->priv; - struct device *dev = &atusb->usb_dev->dev; - - if (atusb->fw_ver_maj == 0 && atusb->fw_ver_min < 3) { - dev_info(dev, "Automatic frame retransmission is only available from " - "firmware version 0.3. Please update if you want this feature."); - return -EINVAL; - } return atusb_write_subreg(atusb, SR_MAX_FRAME_RETRIES, retries); } @@ -802,8 +795,7 @@ static int atusb_probe(struct usb_interface *interface, hw->parent = &usb_dev->dev; hw->flags = IEEE802154_HW_TX_OMIT_CKSUM | IEEE802154_HW_AFILT | - IEEE802154_HW_PROMISCUOUS | IEEE802154_HW_CSMA_PARAMS | - IEEE802154_HW_FRAME_RETRIES; + IEEE802154_HW_PROMISCUOUS | IEEE802154_HW_CSMA_PARAMS; hw->phy->flags = WPAN_PHY_FLAG_TXPOWER | WPAN_PHY_FLAG_CCA_ED_LEVEL | WPAN_PHY_FLAG_CCA_MODE; @@ -832,6 +824,9 @@ static int atusb_probe(struct usb_interface *interface, atusb_get_and_show_build(atusb); atusb_set_extended_addr(atusb); + if (atusb->fw_ver_maj >= 0 && atusb->fw_ver_min >= 3) + hw->flags |= IEEE802154_HW_FRAME_RETRIES; + ret = atusb_get_and_clear_error(atusb); if (ret) { dev_err(&atusb->usb_dev->dev, -- cgit v1.2.3 From 7aa4865506a26c607e00bd9794a85785b55ebca7 Mon Sep 17 00:00:00 2001 From: Vadim Lomovtsev Date: Thu, 12 Jan 2017 07:28:06 -0800 Subject: net: thunderx: acpi: fix LMAC initialization While probing BGX we requesting appropriate QLM for it's configuration and get LMAC count by that request. Then, while reading configured MAC values from SSDT table we need to save them in proper mapping: BGX[i]->lmac[j].mac = to later provide for initialization stuff. In order to fill such mapping properly we need to add lmac index to be used while acpi initialization since at this moment bgx->lmac_count already contains actual value. Signed-off-by: Vadim Lomovtsev Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/thunder_bgx.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 9211c750e064..2f85b64f01fa 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -47,8 +47,9 @@ struct lmac { struct bgx { u8 bgx_id; struct lmac lmac[MAX_LMAC_PER_BGX]; - int lmac_count; + u8 lmac_count; u8 max_lmac; + u8 acpi_lmac_idx; void __iomem *reg_base; struct pci_dev *pdev; bool is_dlm; @@ -1143,13 +1144,13 @@ static acpi_status bgx_acpi_register_phy(acpi_handle handle, if (acpi_bus_get_device(handle, &adev)) goto out; - acpi_get_mac_address(dev, adev, bgx->lmac[bgx->lmac_count].mac); + acpi_get_mac_address(dev, adev, bgx->lmac[bgx->acpi_lmac_idx].mac); - SET_NETDEV_DEV(&bgx->lmac[bgx->lmac_count].netdev, dev); + SET_NETDEV_DEV(&bgx->lmac[bgx->acpi_lmac_idx].netdev, dev); - bgx->lmac[bgx->lmac_count].lmacid = bgx->lmac_count; + bgx->lmac[bgx->acpi_lmac_idx].lmacid = bgx->acpi_lmac_idx; + bgx->acpi_lmac_idx++; /* move to next LMAC */ out: - bgx->lmac_count++; return AE_OK; } -- cgit v1.2.3 From 43071d8fb3b7f589d72663c496a6880fb097533c Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 13 Jan 2017 11:28:25 +0100 Subject: mac80211: initialize SMPS field in HT capabilities ibss and mesh modes copy the ht capabilites from the band without overriding the SMPS state. Unfortunately the default value 0 for the SMPS field means static SMPS instead of disabled. This results in HT ibss and mesh setups using only single-stream rates, even though SMPS is not supposed to be active. Initialize SMPS to disabled for all bands on ieee80211_hw_register to ensure that the value is sane where it is not overriden with the real SMPS state. Reported-by: Elektra Wagenrad Signed-off-by: Felix Fietkau [move VHT TODO comment to a better place] Signed-off-by: Johannes Berg --- net/mac80211/main.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 1822c77f2b1c..56fb47953b72 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -913,12 +913,17 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) supp_ht = supp_ht || sband->ht_cap.ht_supported; supp_vht = supp_vht || sband->vht_cap.vht_supported; - if (sband->ht_cap.ht_supported) - local->rx_chains = - max(ieee80211_mcs_to_chains(&sband->ht_cap.mcs), - local->rx_chains); + if (!sband->ht_cap.ht_supported) + continue; /* TODO: consider VHT for RX chains, hopefully it's the same */ + local->rx_chains = + max(ieee80211_mcs_to_chains(&sband->ht_cap.mcs), + local->rx_chains); + + /* no need to mask, SM_PS_DISABLED has all bits set */ + sband->ht_cap.cap |= WLAN_HT_CAP_SM_PS_DISABLED << + IEEE80211_HT_CAP_SM_PS_SHIFT; } /* if low-level driver supports AP, we also support VLAN */ -- cgit v1.2.3 From dbef53621116474bb883f76f0ba6b7640bc42332 Mon Sep 17 00:00:00 2001 From: Michal Kazior Date: Fri, 13 Jan 2017 13:32:51 +0100 Subject: mac80211: prevent skb/txq mismatch Station structure is considered as not uploaded (to driver) until drv_sta_state() finishes. This call is however done after the structure is attached to mac80211 internal lists and hashes. This means mac80211 can lookup (and use) station structure before it is uploaded to a driver. If this happens (structure exists, but sta->uploaded is false) fast_tx path can still be taken. Deep in the fastpath call the sta->uploaded is checked against to derive "pubsta" argument for ieee80211_get_txq(). If sta->uploaded is false (and sta is actually non-NULL) ieee80211_get_txq() effectively downgraded to vif->txq. At first glance this may look innocent but coerces mac80211 into a state that is almost guaranteed (codel may drop offending skb) to crash because a station-oriented skb gets queued up on vif-oriented txq. The ieee80211_tx_dequeue() ends up looking at info->control.flags and tries to use txq->sta which in the fail case is NULL. It's probably pointless to pretend one can downgrade skb from sta-txq to vif-txq. Since downgrading unicast traffic to vif->txq must not be done there's no txq to put a frame on if sta->uploaded is false. Therefore the code is made to fall back to regular tx() op path if the described condition is hit. Only drivers using wake_tx_queue were affected. Example crash dump before fix: Unable to handle kernel paging request at virtual address ffffe26c PC is at ieee80211_tx_dequeue+0x204/0x690 [mac80211] [] (ieee80211_tx_dequeue [mac80211]) from [] (ath10k_mac_tx_push_txq+0x54/0x1c0 [ath10k_core]) [] (ath10k_mac_tx_push_txq [ath10k_core]) from [] (ath10k_htt_txrx_compl_task+0xd78/0x11d0 [ath10k_core]) [] (ath10k_htt_txrx_compl_task [ath10k_core]) [] (ath10k_pci_napi_poll+0x54/0xe8 [ath10k_pci]) [] (ath10k_pci_napi_poll [ath10k_pci]) from [] (net_rx_action+0xac/0x160) Reported-by: Mohammed Shafi Shajakhan Signed-off-by: Michal Kazior Signed-off-by: Johannes Berg --- net/mac80211/tx.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 0d8b716e509e..797e847cbc49 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1243,7 +1243,7 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local, struct ieee80211_vif *vif, - struct ieee80211_sta *pubsta, + struct sta_info *sta, struct sk_buff *skb) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; @@ -1257,10 +1257,13 @@ static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local, if (!ieee80211_is_data(hdr->frame_control)) return NULL; - if (pubsta) { + if (sta) { u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; - txq = pubsta->txq[tid]; + if (!sta->uploaded) + return NULL; + + txq = sta->sta.txq[tid]; } else if (vif) { txq = vif->txq; } @@ -1503,23 +1506,17 @@ static bool ieee80211_queue_skb(struct ieee80211_local *local, struct fq *fq = &local->fq; struct ieee80211_vif *vif; struct txq_info *txqi; - struct ieee80211_sta *pubsta; if (!local->ops->wake_tx_queue || sdata->vif.type == NL80211_IFTYPE_MONITOR) return false; - if (sta && sta->uploaded) - pubsta = &sta->sta; - else - pubsta = NULL; - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) sdata = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); vif = &sdata->vif; - txqi = ieee80211_get_txq(local, vif, pubsta, skb); + txqi = ieee80211_get_txq(local, vif, sta, skb); if (!txqi) return false; -- cgit v1.2.3 From 148d3d021cf9724fcf189ce4e525a094bbf5ce89 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 12 Jan 2017 12:09:09 -0800 Subject: net: systemport: Decouple flow control from __bcm_sysport_tx_reclaim The __bcm_sysport_tx_reclaim() function is used to reclaim transmit resources in different places within the driver. Most of them should not affect the state of the transit flow control. Introduce bcm_sysport_tx_clean() which cleans the ring, but does not re-enable flow control towards the networking stack, and make bcm_sysport_tx_reclaim() do the actual transmit queue flow control. Fixes: 80105befdb4b ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcmsysport.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 7e8cf213fd81..744ed6ddaf37 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -710,11 +710,8 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv, unsigned int c_index, last_c_index, last_tx_cn, num_tx_cbs; unsigned int pkts_compl = 0, bytes_compl = 0; struct bcm_sysport_cb *cb; - struct netdev_queue *txq; u32 hw_ind; - txq = netdev_get_tx_queue(ndev, ring->index); - /* Compute how many descriptors have been processed since last call */ hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index)); c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK; @@ -745,9 +742,6 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv, ring->c_index = c_index; - if (netif_tx_queue_stopped(txq) && pkts_compl) - netif_tx_wake_queue(txq); - netif_dbg(priv, tx_done, ndev, "ring=%d c_index=%d pkts_compl=%d, bytes_compl=%d\n", ring->index, ring->c_index, pkts_compl, bytes_compl); @@ -759,16 +753,33 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv, static unsigned int bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv, struct bcm_sysport_tx_ring *ring) { + struct netdev_queue *txq; unsigned int released; unsigned long flags; + txq = netdev_get_tx_queue(priv->netdev, ring->index); + spin_lock_irqsave(&ring->lock, flags); released = __bcm_sysport_tx_reclaim(priv, ring); + if (released) + netif_tx_wake_queue(txq); + spin_unlock_irqrestore(&ring->lock, flags); return released; } +/* Locked version of the per-ring TX reclaim, but does not wake the queue */ +static void bcm_sysport_tx_clean(struct bcm_sysport_priv *priv, + struct bcm_sysport_tx_ring *ring) +{ + unsigned long flags; + + spin_lock_irqsave(&ring->lock, flags); + __bcm_sysport_tx_reclaim(priv, ring); + spin_unlock_irqrestore(&ring->lock, flags); +} + static int bcm_sysport_tx_poll(struct napi_struct *napi, int budget) { struct bcm_sysport_tx_ring *ring = @@ -1252,7 +1263,7 @@ static void bcm_sysport_fini_tx_ring(struct bcm_sysport_priv *priv, napi_disable(&ring->napi); netif_napi_del(&ring->napi); - bcm_sysport_tx_reclaim(priv, ring); + bcm_sysport_tx_clean(priv, ring); kfree(ring->cbs); ring->cbs = NULL; -- cgit v1.2.3 From fa79581ea66ca43d56ef065346ac5be767fcb418 Mon Sep 17 00:00:00 2001 From: David Lebrun Date: Thu, 12 Jan 2017 21:30:01 +0100 Subject: ipv6: sr: fix several BUGs when preemption is enabled When CONFIG_PREEMPT=y, CONFIG_IPV6=m and CONFIG_SEG6_HMAC=y, seg6_hmac_init() is called during the initialization of the ipv6 module. This causes a subsequent call to smp_processor_id() with preemption enabled, resulting in the following trace. [ 20.451460] BUG: using smp_processor_id() in preemptible [00000000] code: systemd/1 [ 20.452556] caller is debug_smp_processor_id+0x17/0x19 [ 20.453304] CPU: 0 PID: 1 Comm: systemd Not tainted 4.9.0-rc5-00973-g46738b1 #1 [ 20.454406] ffffc9000062fc18 ffffffff813607b2 0000000000000000 ffffffff81a7f782 [ 20.455528] ffffc9000062fc48 ffffffff813778dc 0000000000000000 00000000001dcf98 [ 20.456539] ffffffffa003bd08 ffffffff81af93e0 ffffc9000062fc58 ffffffff81377905 [ 20.456539] Call Trace: [ 20.456539] [] dump_stack+0x63/0x7f [ 20.456539] [] check_preemption_disabled+0xd1/0xe3 [ 20.456539] [] debug_smp_processor_id+0x17/0x19 [ 20.460260] [] seg6_hmac_init+0xfa/0x192 [ipv6] [ 20.460260] [] seg6_init+0x39/0x6f [ipv6] [ 20.460260] [] inet6_init+0x21a/0x321 [ipv6] [ 20.460260] [] ? 0xffffffffa0061000 [ 20.460260] [] do_one_initcall+0x8b/0x115 [ 20.460260] [] do_init_module+0x53/0x1c4 [ 20.460260] [] load_module+0x1153/0x14ec [ 20.460260] [] SYSC_finit_module+0x8c/0xb9 [ 20.460260] [] ? SYSC_finit_module+0x8c/0xb9 [ 20.460260] [] SyS_finit_module+0x9/0xb [ 20.460260] [] do_syscall_64+0x62/0x75 [ 20.460260] [] entry_SYSCALL64_slow_path+0x25/0x25 Moreover, dst_cache_* functions also call smp_processor_id(), generating a similar trace. This patch uses raw_cpu_ptr() in seg6_hmac_init() rather than this_cpu_ptr() and disable preemption when using dst_cache_* functions. Signed-off-by: David Lebrun Signed-off-by: David S. Miller --- net/ipv6/seg6_hmac.c | 2 +- net/ipv6/seg6_iptunnel.c | 4 ++++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index ef1c8a46e7ac..03a064803626 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -400,7 +400,7 @@ static int seg6_hmac_init_algo(void) *p_tfm = tfm; } - p_tfm = this_cpu_ptr(algo->tfms); + p_tfm = raw_cpu_ptr(algo->tfms); tfm = *p_tfm; shsize = sizeof(*shash) + crypto_shash_descsize(tfm); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index bbfca22c34ae..1d60cb132835 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -265,7 +265,9 @@ int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb) slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); #ifdef CONFIG_DST_CACHE + preempt_disable(); dst = dst_cache_get(&slwt->cache); + preempt_enable(); #endif if (unlikely(!dst)) { @@ -286,7 +288,9 @@ int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb) } #ifdef CONFIG_DST_CACHE + preempt_disable(); dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr); + preempt_enable(); #endif } -- cgit v1.2.3 From 003c941057eaa868ca6fedd29a274c863167230d Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Thu, 12 Jan 2017 14:24:58 -0800 Subject: tcp: fix tcp_fastopen unaligned access complaints on sparc Fix up a data alignment issue on sparc by swapping the order of the cookie byte array field with the length field in struct tcp_fastopen_cookie, and making it a proper union to clean up the typecasting. This addresses log complaints like these: log_unaligned: 113 callbacks suppressed Kernel unaligned access at TPC[976490] tcp_try_fastopen+0x2d0/0x360 Kernel unaligned access at TPC[9764ac] tcp_try_fastopen+0x2ec/0x360 Kernel unaligned access at TPC[9764c8] tcp_try_fastopen+0x308/0x360 Kernel unaligned access at TPC[9764e4] tcp_try_fastopen+0x324/0x360 Kernel unaligned access at TPC[976490] tcp_try_fastopen+0x2d0/0x360 Cc: Eric Dumazet Signed-off-by: Shannon Nelson Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 7 ++++++- net/ipv4/tcp_fastopen.c | 2 +- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/include/linux/tcp.h b/include/linux/tcp.h index fc5848dad7a4..c93f4b3a59cb 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -62,8 +62,13 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb) /* TCP Fast Open Cookie as stored in memory */ struct tcp_fastopen_cookie { + union { + u8 val[TCP_FASTOPEN_COOKIE_MAX]; +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr addr; +#endif + }; s8 len; - u8 val[TCP_FASTOPEN_COOKIE_MAX]; bool exp; /* In RFC6994 experimental option format */ }; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 4e777a3243f9..f51919535ca7 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -113,7 +113,7 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req, struct tcp_fastopen_cookie tmp; if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) { - struct in6_addr *buf = (struct in6_addr *) tmp.val; + struct in6_addr *buf = &tmp.addr; int i; for (i = 0; i < 4; i++) -- cgit v1.2.3 From 75f01a4c9cc291ff5cb28ca1216adb163b7a20ee Mon Sep 17 00:00:00 2001 From: Lance Richardson Date: Thu, 12 Jan 2017 19:33:18 -0500 Subject: openvswitch: maintain correct checksum state in conntrack actions When executing conntrack actions on skbuffs with checksum mode CHECKSUM_COMPLETE, the checksum must be updated to account for header pushes and pulls. Otherwise we get "hw csum failure" logs similar to this (ICMP packet received on geneve tunnel via ixgbe NIC): [ 405.740065] genev_sys_6081: hw csum failure [ 405.740106] CPU: 3 PID: 0 Comm: swapper/3 Tainted: G I 4.10.0-rc3+ #1 [ 405.740108] Call Trace: [ 405.740110] [ 405.740113] dump_stack+0x63/0x87 [ 405.740116] netdev_rx_csum_fault+0x3a/0x40 [ 405.740118] __skb_checksum_complete+0xcf/0xe0 [ 405.740120] nf_ip_checksum+0xc8/0xf0 [ 405.740124] icmp_error+0x1de/0x351 [nf_conntrack_ipv4] [ 405.740132] nf_conntrack_in+0xe1/0x550 [nf_conntrack] [ 405.740137] ? find_bucket.isra.2+0x62/0x70 [openvswitch] [ 405.740143] __ovs_ct_lookup+0x95/0x980 [openvswitch] [ 405.740145] ? netif_rx_internal+0x44/0x110 [ 405.740149] ovs_ct_execute+0x147/0x4b0 [openvswitch] [ 405.740153] do_execute_actions+0x22e/0xa70 [openvswitch] [ 405.740157] ovs_execute_actions+0x40/0x120 [openvswitch] [ 405.740161] ovs_dp_process_packet+0x84/0x120 [openvswitch] [ 405.740166] ovs_vport_receive+0x73/0xd0 [openvswitch] [ 405.740168] ? udp_rcv+0x1a/0x20 [ 405.740170] ? ip_local_deliver_finish+0x93/0x1e0 [ 405.740172] ? ip_local_deliver+0x6f/0xe0 [ 405.740174] ? ip_rcv_finish+0x3a0/0x3a0 [ 405.740176] ? ip_rcv_finish+0xdb/0x3a0 [ 405.740177] ? ip_rcv+0x2a7/0x400 [ 405.740180] ? __netif_receive_skb_core+0x970/0xa00 [ 405.740185] netdev_frame_hook+0xd3/0x160 [openvswitch] [ 405.740187] __netif_receive_skb_core+0x1dc/0xa00 [ 405.740194] ? ixgbe_clean_rx_irq+0x46d/0xa20 [ixgbe] [ 405.740197] __netif_receive_skb+0x18/0x60 [ 405.740199] netif_receive_skb_internal+0x40/0xb0 [ 405.740201] napi_gro_receive+0xcd/0x120 [ 405.740204] gro_cell_poll+0x57/0x80 [geneve] [ 405.740206] net_rx_action+0x260/0x3c0 [ 405.740209] __do_softirq+0xc9/0x28c [ 405.740211] irq_exit+0xd9/0xf0 [ 405.740213] do_IRQ+0x51/0xd0 [ 405.740215] common_interrupt+0x93/0x93 Fixes: 7f8a436eaa2c ("openvswitch: Add conntrack action") Signed-off-by: Lance Richardson Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/openvswitch/conntrack.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 6b78bab27755..54253ea5976e 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -514,7 +514,7 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, int hooknum, nh_off, err = NF_ACCEPT; nh_off = skb_network_offset(skb); - skb_pull(skb, nh_off); + skb_pull_rcsum(skb, nh_off); /* See HOOK2MANIP(). */ if (maniptype == NF_NAT_MANIP_SRC) @@ -579,6 +579,7 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, err = nf_nat_packet(ct, ctinfo, hooknum, skb); push: skb_push(skb, nh_off); + skb_postpush_rcsum(skb, skb->data, nh_off); return err; } @@ -886,7 +887,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, /* The conntrack module expects to be working at L3. */ nh_ofs = skb_network_offset(skb); - skb_pull(skb, nh_ofs); + skb_pull_rcsum(skb, nh_ofs); if (key->ip.frag != OVS_FRAG_TYPE_NONE) { err = handle_fragments(net, key, info->zone.id, skb); @@ -900,6 +901,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, err = ovs_ct_lookup(net, key, info, skb); skb_push(skb, nh_ofs); + skb_postpush_rcsum(skb, skb->data, nh_ofs); if (err) kfree_skb(skb); return err; -- cgit v1.2.3 From 8cf699ec849f4ca1413cea01289bd7d37dbcc626 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 Jan 2017 08:39:24 -0800 Subject: mlx4: do not call napi_schedule() without care Disable BH around the call to napi_schedule() to avoid following warning [ 52.095499] NOHZ: local_softirq_pending 08 [ 52.421291] NOHZ: local_softirq_pending 08 [ 52.608313] NOHZ: local_softirq_pending 08 Fixes: 8d59de8f7bb3 ("net/mlx4_en: Process all completions in RX rings after port goes up") Signed-off-by: Eric Dumazet Cc: Erez Shitrit Cc: Eugenia Emantayev Cc: Tariq Toukan Acked-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 4910d9af1933..761f8b12399c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1748,8 +1748,11 @@ int mlx4_en_start_port(struct net_device *dev) /* Process all completions if exist to prevent * the queues freezing if they are full */ - for (i = 0; i < priv->rx_ring_num; i++) + for (i = 0; i < priv->rx_ring_num; i++) { + local_bh_disable(); napi_schedule(&priv->rx_cq[i]->napi); + local_bh_enable(); + } netif_tx_start_all_queues(dev); netif_device_attach(dev); -- cgit v1.2.3 From 8ec3e8a192ba6f13be4522ee81227c792c86fb1a Mon Sep 17 00:00:00 2001 From: Masaru Nagai Date: Mon, 16 Jan 2017 11:45:21 +0100 Subject: ravb: do not use zero-length alignment DMA descriptor Due to alignment requirements of the hardware transmissions are split into two DMA descriptors, a small padding descriptor of 0 - 3 bytes in length followed by a descriptor for rest of the packet. In the case of IP packets the first descriptor will never be zero due to the way that the stack aligns buffers for IP packets. However, for non-IP packets it may be zero. In that case it has been reported that timeouts occur, presumably because transmission stops at the first zero-length DMA descriptor and thus the packet is not transmitted. However, in my environment a BUG is triggered as follows: [ 20.381417] ------------[ cut here ]------------ [ 20.386054] kernel BUG at lib/swiotlb.c:495! [ 20.390324] Internal error: Oops - BUG: 0 [#1] PREEMPT SMP [ 20.395805] Modules linked in: [ 20.398862] CPU: 0 PID: 2089 Comm: mz Not tainted 4.10.0-rc3-00001-gf13ad2db193f #162 [ 20.406689] Hardware name: Renesas Salvator-X board based on r8a7796 (DT) [ 20.413474] task: ffff80063b1f1900 task.stack: ffff80063a71c000 [ 20.419404] PC is at swiotlb_tbl_map_single+0x178/0x2ec [ 20.424625] LR is at map_single+0x4c/0x98 [ 20.428629] pc : [] lr : [] pstate: 800001c5 [ 20.436019] sp : ffff80063a71f9b0 [ 20.439327] x29: ffff80063a71f9b0 x28: ffff80063a20d500 [ 20.444636] x27: ffff000008ed5000 x26: 0000000000000000 [ 20.449944] x25: 000000067abe2adc x24: 0000000000000000 [ 20.455252] x23: 0000000000200000 x22: 0000000000000001 [ 20.460559] x21: 0000000000175ffe x20: ffff80063b2a0010 [ 20.465866] x19: 0000000000000000 x18: 0000ffffcae6fb20 [ 20.471173] x17: 0000ffffa09ba018 x16: ffff0000087c8b70 [ 20.476480] x15: 0000ffffa084f588 x14: 0000ffffa09cfa14 [ 20.481787] x13: 0000ffffcae87ff0 x12: 000000000063abe2 [ 20.487098] x11: ffff000008096360 x10: ffff80063abe2adc [ 20.492407] x9 : 0000000000000000 x8 : 0000000000000000 [ 20.497718] x7 : 0000000000000000 x6 : ffff000008ed50d0 [ 20.503028] x5 : 0000000000000000 x4 : 0000000000000001 [ 20.508338] x3 : 0000000000000000 x2 : 000000067abe2adc [ 20.513648] x1 : 00000000bafff000 x0 : 0000000000000000 [ 20.518958] [ 20.520446] Process mz (pid: 2089, stack limit = 0xffff80063a71c000) [ 20.526798] Stack: (0xffff80063a71f9b0 to 0xffff80063a720000) [ 20.532543] f9a0: ffff80063a71fa30 ffff00000839c680 [ 20.540374] f9c0: ffff80063b2a0010 ffff80063b2a0010 0000000000000001 0000000000000000 [ 20.548204] f9e0: 000000000000006e ffff80063b23c000 ffff80063b23c000 0000000000000000 [ 20.556034] fa00: ffff80063b23c000 ffff80063a20d500 000000013b1f1900 0000000000000000 [ 20.563864] fa20: ffff80063ffd18e0 ffff80063b2a0010 ffff80063a71fa60 ffff00000839cd10 [ 20.571694] fa40: ffff80063b2a0010 0000000000000000 ffff80063ffd18e0 000000067abe2adc [ 20.579524] fa60: ffff80063a71fa90 ffff000008096380 ffff80063b2a0010 0000000000000000 [ 20.587353] fa80: 0000000000000000 0000000000000001 ffff80063a71fac0 ffff00000864f770 [ 20.595184] faa0: ffff80063b23caf0 0000000000000000 0000000000000000 0000000000000140 [ 20.603014] fac0: ffff80063a71fb60 ffff0000087e6498 ffff80063a20d500 ffff80063b23c000 [ 20.610843] fae0: 0000000000000000 ffff000008daeaf0 0000000000000000 ffff000008daeb00 [ 20.618673] fb00: ffff80063a71fc0c ffff000008da7000 ffff80063b23c090 ffff80063a44f000 [ 20.626503] fb20: 0000000000000000 ffff000008daeb00 ffff80063a71fc0c ffff000008da7000 [ 20.634333] fb40: ffff80063b23c090 0000000000000000 ffff800600000037 ffff0000087e63d8 [ 20.642163] fb60: ffff80063a71fbc0 ffff000008807510 ffff80063a692400 ffff80063a20d500 [ 20.649993] fb80: ffff80063a44f000 ffff80063b23c000 ffff80063a69249c 0000000000000000 [ 20.657823] fba0: 0000000000000000 ffff80063a087800 ffff80063b23c000 ffff80063a20d500 [ 20.665653] fbc0: ffff80063a71fc10 ffff0000087e67dc ffff80063a20d500 ffff80063a692400 [ 20.673483] fbe0: ffff80063b23c000 0000000000000000 ffff80063a44f000 ffff80063a69249c [ 20.681312] fc00: ffff80063a5f1a10 000000103a087800 ffff80063a71fc70 ffff0000087e6b24 [ 20.689142] fc20: ffff80063a5f1a80 ffff80063a71fde8 000000000000000f 00000000000005ea [ 20.696972] fc40: ffff80063a5f1a10 0000000000000000 000000000000000f ffff00000887fbd0 [ 20.704802] fc60: fffffff43a5f1a80 0000000000000000 ffff80063a71fc80 ffff000008880240 [ 20.712632] fc80: ffff80063a71fd90 ffff0000087c7a34 ffff80063afc7180 0000000000000000 [ 20.720462] fca0: 0000ffffcae6fe18 0000000000000014 0000000060000000 0000000000000015 [ 20.728292] fcc0: 0000000000000123 00000000000000ce ffff0000088d2000 ffff80063b1f1900 [ 20.736122] fce0: 0000000000008933 ffff000008e7cb80 ffff80063a71fd80 ffff0000087c50a4 [ 20.743951] fd00: 0000000000008933 ffff000008e7cb80 ffff000008e7cb80 000000100000000e [ 20.751781] fd20: ffff80063a71fe4c 0000ffff00000300 0000000000000123 0000000000000000 [ 20.759611] fd40: 0000000000000000 ffff80063b1f0000 000000000000000e 0000000000000300 [ 20.767441] fd60: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [ 20.775271] fd80: 0000000000000000 0000000000000000 ffff80063a71fda0 ffff0000087c8c20 [ 20.783100] fda0: 0000000000000000 ffff000008082f30 0000000000000000 0000800637260000 [ 20.790930] fdc0: ffffffffffffffff 0000ffffa0903078 0000000000000000 000000001ea87232 [ 20.798760] fde0: 000000000000000f ffff80063a71fe40 ffff800600000014 ffff000000000001 [ 20.806590] fe00: 0000000000000000 0000000000000000 ffff80063a71fde8 0000000000000000 [ 20.814420] fe20: 0000000000000000 0000000000000000 0000000000000000 0000000000000001 [ 20.822249] fe40: 0000000203000011 0000000000000000 0000000000000000 ffff80063a68aa00 [ 20.830079] fe60: ffff80063a68aa00 0000000000000003 0000000000008933 ffff0000081f1b9c [ 20.837909] fe80: 0000000000000000 ffff000008082f30 0000000000000000 0000800637260000 [ 20.845739] fea0: ffffffffffffffff 0000ffffa07ca81c 0000000060000000 0000000000000015 [ 20.853569] fec0: 0000000000000003 000000001ea87232 000000000000000f 0000000000000000 [ 20.861399] fee0: 0000ffffcae6fe18 0000000000000014 0000000000000300 0000000000000000 [ 20.869228] ff00: 00000000000000ce 0000000000000000 00000000ffffffff 0000000000000000 [ 20.877059] ff20: 0000000000000002 0000ffffcae87ff0 0000ffffa09cfa14 0000ffffa084f588 [ 20.884888] ff40: 0000000000000000 0000ffffa09ba018 0000ffffcae6fb20 000000001ea87010 [ 20.892718] ff60: 0000ffffa09b9000 0000ffffcae6fe30 0000ffffcae6fe18 000000000000000f [ 20.900548] ff80: 0000000000000003 000000001ea87232 0000000000000000 0000000000000000 [ 20.908378] ffa0: 0000000000000000 0000ffffcae6fdc0 0000ffffa09a7824 0000ffffcae6fdc0 [ 20.916208] ffc0: 0000ffffa0903078 0000000060000000 0000000000000003 00000000000000ce [ 20.924038] ffe0: 0000000000000000 0000000000000000 ffffffffffffffff ffffffffffffffff [ 20.931867] Call trace: [ 20.934312] Exception stack(0xffff80063a71f7e0 to 0xffff80063a71f910) [ 20.940750] f7e0: 0000000000000000 0001000000000000 ffff80063a71f9b0 ffff00000839c4c0 [ 20.948580] f800: ffff80063a71f840 ffff00000888a6e4 ffff80063a24c418 ffff80063a24c448 [ 20.956410] f820: 0000000000000000 ffff00000811cd54 ffff80063a71f860 ffff80063a24c458 [ 20.964240] f840: ffff80063a71f870 ffff00000888b258 ffff80063a24c418 0000000000000001 [ 20.972070] f860: ffff80063a71f910 ffff80063a7b7028 ffff80063a71f890 ffff0000088825e4 [ 20.979899] f880: 0000000000000000 00000000bafff000 000000067abe2adc 0000000000000000 [ 20.987729] f8a0: 0000000000000001 0000000000000000 ffff000008ed50d0 0000000000000000 [ 20.995560] f8c0: 0000000000000000 0000000000000000 ffff80063abe2adc ffff000008096360 [ 21.003390] f8e0: 000000000063abe2 0000ffffcae87ff0 0000ffffa09cfa14 0000ffffa084f588 [ 21.011219] f900: ffff0000087c8b70 0000ffffa09ba018 [ 21.016097] [] swiotlb_tbl_map_single+0x178/0x2ec [ 21.022362] [] map_single+0x4c/0x98 [ 21.027411] [] swiotlb_map_page+0xa4/0x138 [ 21.033072] [] __swiotlb_map_page+0x20/0x7c [ 21.038821] [] ravb_start_xmit+0x174/0x668 [ 21.044484] [] dev_hard_start_xmit+0x8c/0x120 [ 21.050407] [] sch_direct_xmit+0x108/0x1a0 [ 21.056064] [] __dev_queue_xmit+0x194/0x4cc [ 21.061807] [] dev_queue_xmit+0x10/0x18 [ 21.067214] [] packet_sendmsg+0xf40/0x1220 [ 21.072873] [] sock_sendmsg+0x18/0x2c [ 21.078097] [] SyS_sendto+0xb0/0xf0 [ 21.083150] [] el0_svc_naked+0x24/0x28 [ 21.088462] Code: d34bfef7 2a1803f3 1a9f86d6 35fff878 (d4210000) [ 21.094611] ---[ end trace 5bc544ad491f3814 ]--- [ 21.099234] Kernel panic - not syncing: Fatal exception in interrupt [ 21.105587] Kernel Offset: disabled [ 21.109073] Memory Limit: none [ 21.112126] ---[ end Kernel panic - not syncing: Fatal exception in interrupt Fixes: 2f45d1902acf ("ravb: minimize TX data copying") Signed-off-by: Masaru Nagai Acked-by: Sergei Shtylyov Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/ravb_main.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 5e5ad978eab9..89ac1e3f6175 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1504,6 +1504,19 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) buffer = PTR_ALIGN(priv->tx_align[q], DPTR_ALIGN) + entry / NUM_TX_DESC * DPTR_ALIGN; len = PTR_ALIGN(skb->data, DPTR_ALIGN) - skb->data; + /* Zero length DMA descriptors are problematic as they seem to + * terminate DMA transfers. Avoid them by simply using a length of + * DPTR_ALIGN (4) when skb data is aligned to DPTR_ALIGN. + * + * As skb is guaranteed to have at least ETH_ZLEN (60) bytes of + * data by the call to skb_put_padto() above this is safe with + * respect to both the length of the first DMA descriptor (len) + * overflowing the available data and the length of the second DMA + * descriptor (skb->len - len) being negative. + */ + if (len == 0) + len = DPTR_ALIGN; + memcpy(buffer, skb->data, len); dma_addr = dma_map_single(ndev->dev.parent, buffer, len, DMA_TO_DEVICE); if (dma_mapping_error(ndev->dev.parent, dma_addr)) -- cgit v1.2.3 From d43e6fb4ac4abfe4ef7c102833ed02330ad701e0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 16 Jan 2017 14:20:54 +0100 Subject: cpmac: remove hopeless #warning The #warning was present 10 years ago when the driver first got merged. As the platform is rather obsolete by now, it seems very unlikely that the warning will cause anyone to fix the code properly. kernelci.org reports the warning for every build in the meantime, so I think it's better to just turn it into a code comment to reduce noise. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/cpmac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c index 77c88fcf2b86..9b8a30bf939b 100644 --- a/drivers/net/ethernet/ti/cpmac.c +++ b/drivers/net/ethernet/ti/cpmac.c @@ -1210,7 +1210,7 @@ int cpmac_init(void) goto fail_alloc; } -#warning FIXME: unhardcode gpio&reset bits + /* FIXME: unhardcode gpio&reset bits */ ar7_gpio_disable(26); ar7_gpio_disable(27); ar7_device_reset(AR7_RESET_BIT_CPMAC_LO); -- cgit v1.2.3 From fe68d8bfe59c561664aa87d827aa4b320eb08895 Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Fri, 13 Jan 2017 22:38:27 +0100 Subject: be2net: fix status check in be_cmd_pmac_add() Return value from be_mcc_notify_wait() contains a base completion status together with an additional status. The base_status() macro need to be used to access base status. Fixes: e3a7ae2 be2net: Changing MAC Address of a VF was broken Cc: Sathya Perla Cc: Ajit Khaparde Cc: Sriharsha Basavapatna Cc: Somnath Kotur Signed-off-by: Ivan Vecera Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_cmds.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 0e74529a4209..30e855004c57 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -1118,7 +1118,7 @@ int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr, err: mutex_unlock(&adapter->mcc_lock); - if (status == MCC_STATUS_UNAUTHORIZED_REQUEST) + if (base_status(status) == MCC_STATUS_UNAUTHORIZED_REQUEST) status = -EPERM; return status; -- cgit v1.2.3 From 6d928ae590c8d58cfd5cca997d54394de139cbb7 Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Fri, 13 Jan 2017 22:38:28 +0100 Subject: be2net: don't delete MAC on close on unprivileged BE3 VFs BE3 VFs without FILTMGMT privilege are not allowed to modify its MAC, VLAN table and UC/MC lists. So don't try to delete MAC on such VFs. Cc: Sathya Perla Cc: Ajit Khaparde Cc: Sriharsha Basavapatna Cc: Somnath Kotur Signed-off-by: Ivan Vecera Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_main.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index ec010ced6c99..d606e20fe69e 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -3609,7 +3609,11 @@ static void be_rx_qs_destroy(struct be_adapter *adapter) static void be_disable_if_filters(struct be_adapter *adapter) { - be_dev_mac_del(adapter, adapter->pmac_id[0]); + /* Don't delete MAC on BE3 VFs without FILTMGMT privilege */ + if (!BEx_chip(adapter) || !be_virtfn(adapter) || + check_privilege(adapter, BE_PRIV_FILTMGMT)) + be_dev_mac_del(adapter, adapter->pmac_id[0]); + be_clear_uc_list(adapter); be_clear_mc_list(adapter); -- cgit v1.2.3 From 34393529163af7163ef8459808e3cf2af7db7f16 Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Fri, 13 Jan 2017 22:38:29 +0100 Subject: be2net: fix MAC addr setting on privileged BE3 VFs During interface opening MAC address stored in netdev->dev_addr is programmed in the HW with exception of BE3 VFs where the initial MAC is programmed by parent PF. This is OK when MAC address is not changed when an interfaces is down. In this case the requested MAC is stored to netdev->dev_addr and later is stored into HW during opening. But this is not done for all BE3 VFs so the NIC HW does not know anything about this change and all traffic is filtered. This is the case of bonding if fail_over_mac == 0 where the MACs of the slaves are changed while they are down. The be2net behavior is too restrictive because if a BE3 VF has the FILTMGMT privilege then it is able to modify its MAC without any restriction. To solve the described problem the driver should take care about these privileged BE3 VFs so the MAC is programmed during opening. And by contrast unpriviled BE3 VFs should not be allowed to change its MAC in any case. Cc: Sathya Perla Cc: Ajit Khaparde Cc: Sriharsha Basavapatna Cc: Somnath Kotur Signed-off-by: Ivan Vecera Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_main.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index d606e20fe69e..1a7f8ad7b9c6 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -318,6 +318,13 @@ static int be_mac_addr_set(struct net_device *netdev, void *p) if (ether_addr_equal(addr->sa_data, adapter->dev_mac)) return 0; + /* BE3 VFs without FILTMGMT privilege are not allowed to set its MAC + * address + */ + if (BEx_chip(adapter) && be_virtfn(adapter) && + !check_privilege(adapter, BE_PRIV_FILTMGMT)) + return -EPERM; + /* if device is not running, copy MAC to netdev->dev_addr */ if (!netif_running(netdev)) goto done; @@ -3766,8 +3773,9 @@ static int be_enable_if_filters(struct be_adapter *adapter) if (status) return status; - /* For BE3 VFs, the PF programs the initial MAC address */ - if (!(BEx_chip(adapter) && be_virtfn(adapter))) { + /* Don't add MAC on BE3 VFs without FILTMGMT privilege */ + if (!BEx_chip(adapter) || !be_virtfn(adapter) || + check_privilege(adapter, BE_PRIV_FILTMGMT)) { status = be_dev_mac_add(adapter, adapter->netdev->dev_addr); if (status) return status; -- cgit v1.2.3 From 1666d49e1d416fcc2cce708242a52fe3317ea8ba Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Thu, 12 Jan 2017 21:19:37 +0800 Subject: mld: do not remove mld souce list info when set link down This is an IPv6 version of commit 24803f38a5c0 ("igmp: do not remove igmp souce list..."). In mld_del_delrec(), we will restore back all source filter info instead of flush them. Move mld_clear_delrec() from ipv6_mc_down() to ipv6_mc_destroy_dev() since we should not remove source list info when set link down. Remove igmp6_group_dropped() in ipv6_mc_destroy_dev() since we have called it in ipv6_mc_down(). Also clear all source info after igmp6_group_dropped() instead of in it because ipv6_mc_down() will call igmp6_group_dropped(). Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- net/ipv6/mcast.c | 51 ++++++++++++++++++++++++++++++--------------------- 1 file changed, 30 insertions(+), 21 deletions(-) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 14a3903f1c82..7139fffd61b6 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -81,7 +81,7 @@ static void mld_gq_timer_expire(unsigned long data); static void mld_ifc_timer_expire(unsigned long data); static void mld_ifc_event(struct inet6_dev *idev); static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *pmc); -static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *addr); +static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *pmc); static void mld_clear_delrec(struct inet6_dev *idev); static bool mld_in_v1_mode(const struct inet6_dev *idev); static int sf_setstate(struct ifmcaddr6 *pmc); @@ -692,9 +692,9 @@ static void igmp6_group_dropped(struct ifmcaddr6 *mc) dev_mc_del(dev, buf); } - if (mc->mca_flags & MAF_NOREPORT) - goto done; spin_unlock_bh(&mc->mca_lock); + if (mc->mca_flags & MAF_NOREPORT) + return; if (!mc->idev->dead) igmp6_leave_group(mc); @@ -702,8 +702,6 @@ static void igmp6_group_dropped(struct ifmcaddr6 *mc) spin_lock_bh(&mc->mca_lock); if (del_timer(&mc->mca_timer)) atomic_dec(&mc->mca_refcnt); -done: - ip6_mc_clear_src(mc); spin_unlock_bh(&mc->mca_lock); } @@ -748,10 +746,11 @@ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) spin_unlock_bh(&idev->mc_lock); } -static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *pmca) +static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) { struct ifmcaddr6 *pmc, *pmc_prev; - struct ip6_sf_list *psf, *psf_next; + struct ip6_sf_list *psf; + struct in6_addr *pmca = &im->mca_addr; spin_lock_bh(&idev->mc_lock); pmc_prev = NULL; @@ -768,14 +767,20 @@ static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *pmca) } spin_unlock_bh(&idev->mc_lock); + spin_lock_bh(&im->mca_lock); if (pmc) { - for (psf = pmc->mca_tomb; psf; psf = psf_next) { - psf_next = psf->sf_next; - kfree(psf); + im->idev = pmc->idev; + im->mca_crcount = idev->mc_qrv; + im->mca_sfmode = pmc->mca_sfmode; + if (pmc->mca_sfmode == MCAST_INCLUDE) { + im->mca_tomb = pmc->mca_tomb; + im->mca_sources = pmc->mca_sources; + for (psf = im->mca_sources; psf; psf = psf->sf_next) + psf->sf_crcount = im->mca_crcount; } in6_dev_put(pmc->idev); - kfree(pmc); } + spin_unlock_bh(&im->mca_lock); } static void mld_clear_delrec(struct inet6_dev *idev) @@ -904,7 +909,7 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) mca_get(mc); write_unlock_bh(&idev->lock); - mld_del_delrec(idev, &mc->mca_addr); + mld_del_delrec(idev, mc); igmp6_group_added(mc); ma_put(mc); return 0; @@ -927,6 +932,7 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) write_unlock_bh(&idev->lock); igmp6_group_dropped(ma); + ip6_mc_clear_src(ma); ma_put(ma); return 0; @@ -2501,15 +2507,17 @@ void ipv6_mc_down(struct inet6_dev *idev) /* Withdraw multicast list */ read_lock_bh(&idev->lock); - mld_ifc_stop_timer(idev); - mld_gq_stop_timer(idev); - mld_dad_stop_timer(idev); for (i = idev->mc_list; i; i = i->next) igmp6_group_dropped(i); - read_unlock_bh(&idev->lock); - mld_clear_delrec(idev); + /* Should stop timer after group drop. or we will + * start timer again in mld_ifc_event() + */ + mld_ifc_stop_timer(idev); + mld_gq_stop_timer(idev); + mld_dad_stop_timer(idev); + read_unlock_bh(&idev->lock); } static void ipv6_mc_reset(struct inet6_dev *idev) @@ -2531,8 +2539,10 @@ void ipv6_mc_up(struct inet6_dev *idev) read_lock_bh(&idev->lock); ipv6_mc_reset(idev); - for (i = idev->mc_list; i; i = i->next) + for (i = idev->mc_list; i; i = i->next) { + mld_del_delrec(idev, i); igmp6_group_added(i); + } read_unlock_bh(&idev->lock); } @@ -2565,6 +2575,7 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev) /* Deactivate timers */ ipv6_mc_down(idev); + mld_clear_delrec(idev); /* Delete all-nodes address. */ /* We cannot call ipv6_dev_mc_dec() directly, our caller in @@ -2579,11 +2590,9 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev) write_lock_bh(&idev->lock); while ((i = idev->mc_list) != NULL) { idev->mc_list = i->next; - write_unlock_bh(&idev->lock); - igmp6_group_dropped(i); + write_unlock_bh(&idev->lock); ma_put(i); - write_lock_bh(&idev->lock); } write_unlock_bh(&idev->lock); -- cgit v1.2.3 From 02ca0423fd65a0a9c4d70da0dbb8f4b8503f08c7 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Fri, 13 Jan 2017 10:12:20 +0100 Subject: ip6_tunnel: Account for tunnel header in tunnel MTU With ip6gre we have a tunnel header which also makes the tunnel MTU smaller. We need to reserve room for it. Previously we were using up space reserved for the Tunnel Encapsulation Limit option header (RFC 2473). Also, after commit b05229f44228 ("gre6: Cleanup GREv6 transmit path, call common GRE functions") our contract with the caller has changed. Now we check if the packet length exceeds the tunnel MTU after the tunnel header has been pushed, unlike before. This is reflected in the check where we look at the packet length minus the size of the tunnel header, which is already accounted for in tunnel MTU. Fixes: b05229f44228 ("gre6: Cleanup GREv6 transmit path, call common GRE functions") Signed-off-by: Jakub Sitnicki Signed-off-by: David S. Miller --- net/ipv6/ip6_tunnel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 36d292180942..753d6d0860fb 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1108,7 +1108,7 @@ route_lookup: t->parms.name); goto tx_err_dst_release; } - mtu = dst_mtu(dst) - psh_hlen; + mtu = dst_mtu(dst) - psh_hlen - t->tun_hlen; if (encap_limit >= 0) { max_headroom += 8; mtu -= 8; @@ -1117,7 +1117,7 @@ route_lookup: mtu = IPV6_MIN_MTU; if (skb_dst(skb) && !t->parms.collect_md) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); - if (skb->len > mtu && !skb_is_gso(skb)) { + if (skb->len - t->tun_hlen > mtu && !skb_is_gso(skb)) { *pmtu = mtu; err = -EMSGSIZE; goto tx_err_dst_release; -- cgit v1.2.3 From 34c55cf2fc75f8bf6ba87df321038c064cf2d426 Mon Sep 17 00:00:00 2001 From: "Karicheri, Muralidharan" Date: Fri, 13 Jan 2017 09:32:34 -0500 Subject: net: phy: dp83867: allow RGMII_TXID/RGMII_RXID interface types Currently dp83867 driver returns error if phy interface type PHY_INTERFACE_MODE_RGMII_RXID is used to set the rx only internal delay. Similarly issue happens for PHY_INTERFACE_MODE_RGMII_TXID. Fix this by checking also the interface type if a particular delay value is missing in the phy dt bindings. Also update the DT document accordingly. Signed-off-by: Murali Karicheri Signed-off-by: Sekhar Nori Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/ti,dp83867.txt | 6 ++++-- drivers/net/phy/dp83867.c | 8 ++++++-- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/net/ti,dp83867.txt b/Documentation/devicetree/bindings/net/ti,dp83867.txt index 85bf945b898f..afe9630a5e7d 100644 --- a/Documentation/devicetree/bindings/net/ti,dp83867.txt +++ b/Documentation/devicetree/bindings/net/ti,dp83867.txt @@ -3,9 +3,11 @@ Required properties: - reg - The ID number for the phy, usually a small integer - ti,rx-internal-delay - RGMII Receive Clock Delay - see dt-bindings/net/ti-dp83867.h - for applicable values + for applicable values. Required only if interface type is + PHY_INTERFACE_MODE_RGMII_ID or PHY_INTERFACE_MODE_RGMII_RXID - ti,tx-internal-delay - RGMII Transmit Clock Delay - see dt-bindings/net/ti-dp83867.h - for applicable values + for applicable values. Required only if interface type is + PHY_INTERFACE_MODE_RGMII_ID or PHY_INTERFACE_MODE_RGMII_TXID - ti,fifo-depth - Transmitt FIFO depth- see dt-bindings/net/ti-dp83867.h for applicable values diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index e84ae084e259..ca1b462bf7b2 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -132,12 +132,16 @@ static int dp83867_of_init(struct phy_device *phydev) ret = of_property_read_u32(of_node, "ti,rx-internal-delay", &dp83867->rx_id_delay); - if (ret) + if (ret && + (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID || + phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID)) return ret; ret = of_property_read_u32(of_node, "ti,tx-internal-delay", &dp83867->tx_id_delay); - if (ret) + if (ret && + (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID || + phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)) return ret; return of_property_read_u32(of_node, "ti,fifo-depth", -- cgit v1.2.3 From 57d5f64d83ab5b5a5118b1597386dd76eaf4340d Mon Sep 17 00:00:00 2001 From: Parthasarathy Bhuvaragan Date: Fri, 13 Jan 2017 15:46:25 +0100 Subject: tipc: allocate user memory with GFP_KERNEL flag Until now, we allocate memory always with GFP_ATOMIC flag. When the system is under memory pressure and a user tries to send, the send fails due to low memory. However, the user application can wait for free memory if we allocate it using GFP_KERNEL flag. In this commit, we use allocate memory with GFP_KERNEL for all user allocation. Reported-by: Rune Torgersen Acked-by: Jon Maloy Signed-off-by: Parthasarathy Bhuvaragan Signed-off-by: David S. Miller --- net/tipc/discover.c | 4 ++-- net/tipc/link.c | 2 +- net/tipc/msg.c | 16 ++++++++-------- net/tipc/msg.h | 2 +- net/tipc/name_distr.c | 2 +- 5 files changed, 13 insertions(+), 13 deletions(-) diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 6b109a808d4c..02462d67d191 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -169,7 +169,7 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, /* Send response, if necessary */ if (respond && (mtyp == DSC_REQ_MSG)) { - rskb = tipc_buf_acquire(MAX_H_SIZE); + rskb = tipc_buf_acquire(MAX_H_SIZE, GFP_ATOMIC); if (!rskb) return; tipc_disc_init_msg(net, rskb, DSC_RESP_MSG, bearer); @@ -278,7 +278,7 @@ int tipc_disc_create(struct net *net, struct tipc_bearer *b, req = kmalloc(sizeof(*req), GFP_ATOMIC); if (!req) return -ENOMEM; - req->buf = tipc_buf_acquire(MAX_H_SIZE); + req->buf = tipc_buf_acquire(MAX_H_SIZE, GFP_ATOMIC); if (!req->buf) { kfree(req); return -ENOMEM; diff --git a/net/tipc/link.c b/net/tipc/link.c index bda89bf9f4ff..4e8647aef01c 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1395,7 +1395,7 @@ tnl: msg_set_seqno(hdr, seqno++); pktlen = msg_size(hdr); msg_set_size(&tnlhdr, pktlen + INT_H_SIZE); - tnlskb = tipc_buf_acquire(pktlen + INT_H_SIZE); + tnlskb = tipc_buf_acquire(pktlen + INT_H_SIZE, GFP_ATOMIC); if (!tnlskb) { pr_warn("%sunable to send packet\n", link_co_err); return; diff --git a/net/tipc/msg.c b/net/tipc/msg.c index a22be502f1bd..ab02d0742476 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -58,12 +58,12 @@ static unsigned int align(unsigned int i) * NOTE: Headroom is reserved to allow prepending of a data link header. * There may also be unrequested tailroom present at the buffer's end. */ -struct sk_buff *tipc_buf_acquire(u32 size) +struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp) { struct sk_buff *skb; unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u; - skb = alloc_skb_fclone(buf_size, GFP_ATOMIC); + skb = alloc_skb_fclone(buf_size, gfp); if (skb) { skb_reserve(skb, BUF_HEADROOM); skb_put(skb, size); @@ -95,7 +95,7 @@ struct sk_buff *tipc_msg_create(uint user, uint type, struct tipc_msg *msg; struct sk_buff *buf; - buf = tipc_buf_acquire(hdr_sz + data_sz); + buf = tipc_buf_acquire(hdr_sz + data_sz, GFP_ATOMIC); if (unlikely(!buf)) return NULL; @@ -261,7 +261,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, /* No fragmentation needed? */ if (likely(msz <= pktmax)) { - skb = tipc_buf_acquire(msz); + skb = tipc_buf_acquire(msz, GFP_KERNEL); if (unlikely(!skb)) return -ENOMEM; skb_orphan(skb); @@ -282,7 +282,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, msg_set_importance(&pkthdr, msg_importance(mhdr)); /* Prepare first fragment */ - skb = tipc_buf_acquire(pktmax); + skb = tipc_buf_acquire(pktmax, GFP_KERNEL); if (!skb) return -ENOMEM; skb_orphan(skb); @@ -313,7 +313,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, pktsz = drem + INT_H_SIZE; else pktsz = pktmax; - skb = tipc_buf_acquire(pktsz); + skb = tipc_buf_acquire(pktsz, GFP_KERNEL); if (!skb) { rc = -ENOMEM; goto error; @@ -448,7 +448,7 @@ bool tipc_msg_make_bundle(struct sk_buff **skb, struct tipc_msg *msg, if (msz > (max / 2)) return false; - _skb = tipc_buf_acquire(max); + _skb = tipc_buf_acquire(max, GFP_ATOMIC); if (!_skb) return false; @@ -496,7 +496,7 @@ bool tipc_msg_reverse(u32 own_node, struct sk_buff **skb, int err) /* Never return SHORT header; expand by replacing buffer if necessary */ if (msg_short(hdr)) { - *skb = tipc_buf_acquire(BASIC_H_SIZE + dlen); + *skb = tipc_buf_acquire(BASIC_H_SIZE + dlen, GFP_ATOMIC); if (!*skb) goto exit; memcpy((*skb)->data + BASIC_H_SIZE, msg_data(hdr), dlen); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 8d408612ffa4..2c3dc38abf9c 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -820,7 +820,7 @@ static inline bool msg_is_reset(struct tipc_msg *hdr) return (msg_user(hdr) == LINK_PROTOCOL) && (msg_type(hdr) == RESET_MSG); } -struct sk_buff *tipc_buf_acquire(u32 size); +struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp); bool tipc_msg_validate(struct sk_buff *skb); bool tipc_msg_reverse(u32 own_addr, struct sk_buff **skb, int err); void tipc_msg_init(u32 own_addr, struct tipc_msg *m, u32 user, u32 type, diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index c1cfd92de17a..23f8899e0f8c 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -69,7 +69,7 @@ static struct sk_buff *named_prepare_buf(struct net *net, u32 type, u32 size, u32 dest) { struct tipc_net *tn = net_generic(net, tipc_net_id); - struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE + size); + struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE + size, GFP_ATOMIC); struct tipc_msg *msg; if (buf != NULL) { -- cgit v1.2.3 From f1f7714ea51c56b7163fb1a5acf39c6a204dd758 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 13 Jan 2017 23:38:15 +0100 Subject: bpf: rework prog_digest into prog_tag Commit 7bd509e311f4 ("bpf: add prog_digest and expose it via fdinfo/netlink") was recently discussed, partially due to admittedly suboptimal name of "prog_digest" in combination with sha1 hash usage, thus inevitably and rightfully concerns about its security in terms of collision resistance were raised with regards to use-cases. The intended use cases are for debugging resp. introspection only for providing a stable "tag" over the instruction sequence that both kernel and user space can calculate independently. It's not usable at all for making a security relevant decision. So collisions where two different instruction sequences generate the same tag can happen, but ideally at a rather low rate. The "tag" will be dumped in hex and is short enough to introspect in tracepoints or kallsyms output along with other data such as stack trace, etc. Thus, this patch performs a rename into prog_tag and truncates the tag to a short output (64 bits) to make it obvious it's not collision-free. Should in future a hash or facility be needed with a security relevant focus, then we can think about requirements, constraints, etc that would fit to that situation. For now, rework the exposed parts for the current use cases as long as nothing has been released yet. Tested on x86_64 and s390x. Fixes: 7bd509e311f4 ("bpf: add prog_digest and expose it via fdinfo/netlink") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Cc: Andy Lutomirski Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 +- include/linux/filter.h | 6 ++++-- include/uapi/linux/pkt_cls.h | 2 +- include/uapi/linux/tc_act/tc_bpf.h | 2 +- kernel/bpf/core.c | 14 ++++++++------ kernel/bpf/syscall.c | 8 ++++---- kernel/bpf/verifier.c | 2 +- net/sched/act_bpf.c | 5 ++--- net/sched/cls_bpf.c | 4 ++-- 9 files changed, 24 insertions(+), 21 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f74ae68086dc..05cf951df3fe 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -216,7 +216,7 @@ u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5); u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); -int bpf_prog_calc_digest(struct bpf_prog *fp); +int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); diff --git a/include/linux/filter.h b/include/linux/filter.h index a0934e6c9bab..e4eb2546339a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -57,6 +57,8 @@ struct bpf_prog_aux; /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 +#define BPF_TAG_SIZE 8 + /* Helper macros for filter block array initializers. */ /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ @@ -408,7 +410,7 @@ struct bpf_prog { kmemcheck_bitfield_end(meta); enum bpf_prog_type type; /* Type of BPF program */ u32 len; /* Number of filter blocks */ - u32 digest[SHA_DIGEST_WORDS]; /* Program digest */ + u8 tag[BPF_TAG_SIZE]; struct bpf_prog_aux *aux; /* Auxiliary fields */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ unsigned int (*bpf_func)(const void *ctx, @@ -519,7 +521,7 @@ static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) return prog->len * sizeof(struct bpf_insn); } -static inline u32 bpf_prog_digest_scratch_size(const struct bpf_prog *prog) +static inline u32 bpf_prog_tag_scratch_size(const struct bpf_prog *prog) { return round_up(bpf_prog_insn_size(prog) + sizeof(__be64) + 1, SHA_MESSAGE_BYTES); diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index cb4bcdc58543..a4dcd88ec271 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -397,7 +397,7 @@ enum { TCA_BPF_NAME, TCA_BPF_FLAGS, TCA_BPF_FLAGS_GEN, - TCA_BPF_DIGEST, + TCA_BPF_TAG, __TCA_BPF_MAX, }; diff --git a/include/uapi/linux/tc_act/tc_bpf.h b/include/uapi/linux/tc_act/tc_bpf.h index a6b88a6f7f71..975b50dc8d1d 100644 --- a/include/uapi/linux/tc_act/tc_bpf.h +++ b/include/uapi/linux/tc_act/tc_bpf.h @@ -27,7 +27,7 @@ enum { TCA_ACT_BPF_FD, TCA_ACT_BPF_NAME, TCA_ACT_BPF_PAD, - TCA_ACT_BPF_DIGEST, + TCA_ACT_BPF_TAG, __TCA_ACT_BPF_MAX, }; #define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 1eb4f1303756..503d4211988a 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -146,10 +146,11 @@ void __bpf_prog_free(struct bpf_prog *fp) vfree(fp); } -int bpf_prog_calc_digest(struct bpf_prog *fp) +int bpf_prog_calc_tag(struct bpf_prog *fp) { const u32 bits_offset = SHA_MESSAGE_BYTES - sizeof(__be64); - u32 raw_size = bpf_prog_digest_scratch_size(fp); + u32 raw_size = bpf_prog_tag_scratch_size(fp); + u32 digest[SHA_DIGEST_WORDS]; u32 ws[SHA_WORKSPACE_WORDS]; u32 i, bsize, psize, blocks; struct bpf_insn *dst; @@ -162,7 +163,7 @@ int bpf_prog_calc_digest(struct bpf_prog *fp) if (!raw) return -ENOMEM; - sha_init(fp->digest); + sha_init(digest); memset(ws, 0, sizeof(ws)); /* We need to take out the map fd for the digest calculation @@ -204,13 +205,14 @@ int bpf_prog_calc_digest(struct bpf_prog *fp) *bits = cpu_to_be64((psize - 1) << 3); while (blocks--) { - sha_transform(fp->digest, todo, ws); + sha_transform(digest, todo, ws); todo += SHA_MESSAGE_BYTES; } - result = (__force __be32 *)fp->digest; + result = (__force __be32 *)digest; for (i = 0; i < SHA_DIGEST_WORDS; i++) - result[i] = cpu_to_be32(fp->digest[i]); + result[i] = cpu_to_be32(digest[i]); + memcpy(fp->tag, result, sizeof(fp->tag)); vfree(raw); return 0; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e89acea22ecf..1d6b29e4e2c3 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -688,17 +688,17 @@ static int bpf_prog_release(struct inode *inode, struct file *filp) static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_prog *prog = filp->private_data; - char prog_digest[sizeof(prog->digest) * 2 + 1] = { }; + char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; - bin2hex(prog_digest, prog->digest, sizeof(prog->digest)); + bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, "prog_type:\t%u\n" "prog_jited:\t%u\n" - "prog_digest:\t%s\n" + "prog_tag:\t%s\n" "memlock:\t%llu\n", prog->type, prog->jited, - prog_digest, + prog_tag, prog->pages * 1ULL << PAGE_SHIFT); } #endif diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 83ed2f8f6f22..cdc43b899f28 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2936,7 +2936,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) int insn_cnt = env->prog->len; int i, j, err; - err = bpf_prog_calc_digest(env->prog); + err = bpf_prog_calc_tag(env->prog); if (err) return err; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 1c60317f0121..520baa41cba3 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -123,12 +123,11 @@ static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog, nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name)) return -EMSGSIZE; - nla = nla_reserve(skb, TCA_ACT_BPF_DIGEST, - sizeof(prog->filter->digest)); + nla = nla_reserve(skb, TCA_ACT_BPF_TAG, sizeof(prog->filter->tag)); if (nla == NULL) return -EMSGSIZE; - memcpy(nla_data(nla), prog->filter->digest, nla_len(nla)); + memcpy(nla_data(nla), prog->filter->tag, nla_len(nla)); return 0; } diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index adc776048d1a..d9c97018317d 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -555,11 +555,11 @@ static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog, nla_put_string(skb, TCA_BPF_NAME, prog->bpf_name)) return -EMSGSIZE; - nla = nla_reserve(skb, TCA_BPF_DIGEST, sizeof(prog->filter->digest)); + nla = nla_reserve(skb, TCA_BPF_TAG, sizeof(prog->filter->tag)); if (nla == NULL) return -EMSGSIZE; - memcpy(nla_data(nla), prog->filter->digest, nla_len(nla)); + memcpy(nla_data(nla), prog->filter->tag, nla_len(nla)); return 0; } -- cgit v1.2.3 From 8a367e74c0120ef68c8c70d5a025648c96626dff Mon Sep 17 00:00:00 2001 From: Basil Gunn Date: Sat, 14 Jan 2017 12:18:55 -0800 Subject: ax25: Fix segfault after sock connection timeout The ax.25 socket connection timed out & the sock struct has been previously taken down ie. sock struct is now a NULL pointer. Checking the sock_flag causes the segfault. Check if the socket struct pointer is NULL before checking sock_flag. This segfault is seen in timed out netrom connections. Please submit to -stable. Signed-off-by: Basil Gunn Signed-off-by: David S. Miller --- net/ax25/ax25_subr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c index 4855d18a8511..038b109b2be7 100644 --- a/net/ax25/ax25_subr.c +++ b/net/ax25/ax25_subr.c @@ -264,7 +264,7 @@ void ax25_disconnect(ax25_cb *ax25, int reason) { ax25_clear_queues(ax25); - if (!sock_flag(ax25->sk, SOCK_DESTROY)) + if (!ax25->sk || !sock_flag(ax25->sk, SOCK_DESTROY)) ax25_stop_heartbeat(ax25); ax25_stop_t1timer(ax25); ax25_stop_t2timer(ax25); -- cgit v1.2.3 From abeffce90c7f6ce74de9794ad0977a168edf8ef6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sun, 15 Jan 2017 19:50:46 +0200 Subject: net/mlx5e: Fix a -Wmaybe-uninitialized warning As found by Olof's build bot, we gain a harmless warning about a potential uninitialized variable reference in mlx5: drivers/net/ethernet/mellanox/mlx5/core/en_tc.c: In function 'parse_tc_fdb_actions': drivers/net/ethernet/mellanox/mlx5/core/en_tc.c:769:13: warning: 'out_dev' may be used uninitialized in this function [-Wmaybe-uninitialized] drivers/net/ethernet/mellanox/mlx5/core/en_tc.c:811:21: note: 'out_dev' was declared here This was introduced through the addition of an 'IS_ERR/PTR_ERR' pair that gcc is unfortunately unable to completely figure out. The problem being gcc cannot tell that if(IS_ERR()) in mlx5e_route_lookup_ipv4() is equivalent to checking if(err) later, so it assumes that 'out_dev' is used after the 'return PTR_ERR(rt)'. The PTR_ERR_OR_ZERO() case by comparison is fairly easy to detect by gcc, so it can't get that wrong, so it no longer warns. Hadar Hen Zion already attempted to fix the warning earlier by adding fake initializations, but that ended up not fully addressing all warnings, so I'm reverting it now that it is no longer needed. Link: http://arm-soc.lixom.net/buildlogs/mainline/v4.10-rc3-98-gcff3b2c/ Fixes: a42485eb0ee4 ("net/mlx5e: TC ipv4 tunnel encap offload error flow fixes") Fixes: a757d108dc1a ("net/mlx5e: Fix kbuild warnings for uninitialized parameters") Signed-off-by: Arnd Bergmann Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 118cea5e5489..46bef6a26a8c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -668,9 +668,12 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, int ttl; #if IS_ENABLED(CONFIG_INET) + int ret; + rt = ip_route_output_key(dev_net(mirred_dev), fl4); - if (IS_ERR(rt)) - return PTR_ERR(rt); + ret = PTR_ERR_OR_ZERO(rt); + if (ret) + return ret; #else return -EOPNOTSUPP; #endif @@ -741,8 +744,8 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, struct flowi4 fl4 = {}; char *encap_header; int encap_size; - __be32 saddr = 0; - int ttl = 0; + __be32 saddr; + int ttl; int err; encap_header = kzalloc(max_encap_size, GFP_KERNEL); -- cgit v1.2.3 From b618ab4561d40664492cf9f9507f19a1c8272970 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 15 Jan 2017 19:19:00 +0100 Subject: net: stmmac: don't use netdev_[dbg, info, ..] before net_device is registered Don't use netdev_info and friends before the net_device is registered. This avoids ugly messages like "meson8b-dwmac c9410000.ethernet (unnamed net_device) (uninitialized): Enable RX Mitigation via HW Watchdog Timer" Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index a276a32d57f2..e3f6389e1b01 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3326,9 +3326,9 @@ int stmmac_dvr_probe(struct device *device, (priv->plat->maxmtu >= ndev->min_mtu)) ndev->max_mtu = priv->plat->maxmtu; else if (priv->plat->maxmtu < ndev->min_mtu) - netdev_warn(priv->dev, - "%s: warning: maxmtu having invalid value (%d)\n", - __func__, priv->plat->maxmtu); + dev_warn(priv->device, + "%s: warning: maxmtu having invalid value (%d)\n", + __func__, priv->plat->maxmtu); if (flow_ctrl) priv->flow_ctrl = FLOW_AUTO; /* RX/TX pause on */ @@ -3340,7 +3340,8 @@ int stmmac_dvr_probe(struct device *device, */ if ((priv->synopsys_id >= DWMAC_CORE_3_50) && (!priv->plat->riwt_off)) { priv->use_riwt = 1; - netdev_info(priv->dev, "Enable RX Mitigation via HW Watchdog Timer\n"); + dev_info(priv->device, + "Enable RX Mitigation via HW Watchdog Timer\n"); } netif_napi_add(ndev, &priv->napi, stmmac_poll, 64); @@ -3366,17 +3367,17 @@ int stmmac_dvr_probe(struct device *device, /* MDIO bus Registration */ ret = stmmac_mdio_register(ndev); if (ret < 0) { - netdev_err(priv->dev, - "%s: MDIO bus (id: %d) registration failed", - __func__, priv->plat->bus_id); + dev_err(priv->device, + "%s: MDIO bus (id: %d) registration failed", + __func__, priv->plat->bus_id); goto error_mdio_register; } } ret = register_netdev(ndev); if (ret) { - netdev_err(priv->dev, "%s: ERROR %i registering the device\n", - __func__, ret); + dev_err(priv->device, "%s: ERROR %i registering the device\n", + __func__, ret); goto error_netdev_register; } -- cgit v1.2.3 From 291c566a28910614ce42d0ffe82196eddd6346f4 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Mon, 16 Jan 2017 18:31:37 +0200 Subject: net/mlx4_core: Fix racy CQ (Completion Queue) free In function mlx4_cq_completion() and mlx4_cq_event(), the radix_tree_lookup requires a rcu_read_lock. This is mandatory: if another core frees the CQ, it could run the radix_tree_node_rcu_free() call_rcu() callback while its being used by the radix tree lookup function. Additionally, in function mlx4_cq_event(), since we are adding the rcu lock around the radix-tree lookup, we no longer need to take the spinlock. Also, the synchronize_irq() call for the async event eliminates the need for incrementing the cq reference count in mlx4_cq_event(). Other changes: 1. In function mlx4_cq_free(), replace spin_lock_irq with spin_lock: we no longer take this spinlock in the interrupt context. The spinlock here, therefore, simply protects against different threads simultaneously invoking mlx4_cq_free() for different cq's. 2. In function mlx4_cq_free(), we move the radix tree delete to before the synchronize_irq() calls. This guarantees that we will not access this cq during any subsequent interrupts, and therefore can safely free the CQ after the synchronize_irq calls. The rcu_read_lock in the interrupt handlers only needs to protect against corrupting the radix tree; the interrupt handlers may access the cq outside the rcu_read_lock due to the synchronize_irq calls which protect against premature freeing of the cq. 3. In function mlx4_cq_event(), we change the mlx_warn message to mlx4_dbg. 4. We leave the cq reference count mechanism in place, because it is still needed for the cq completion tasklet mechanism. Fixes: 6d90aa5cf17b ("net/mlx4_core: Make sure there are no pending async events when freeing CQ") Fixes: 225c7b1feef1 ("IB/mlx4: Add a driver Mellanox ConnectX InfiniBand adapters") Signed-off-by: Jack Morgenstein Signed-off-by: Matan Barak Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/cq.c | 38 +++++++++++++++++---------------- 1 file changed, 20 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c index a849da92f857..6b8635378f1f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/cq.c @@ -101,13 +101,19 @@ void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn) { struct mlx4_cq *cq; + rcu_read_lock(); cq = radix_tree_lookup(&mlx4_priv(dev)->cq_table.tree, cqn & (dev->caps.num_cqs - 1)); + rcu_read_unlock(); + if (!cq) { mlx4_dbg(dev, "Completion event for bogus CQ %08x\n", cqn); return; } + /* Acessing the CQ outside of rcu_read_lock is safe, because + * the CQ is freed only after interrupt handling is completed. + */ ++cq->arm_sn; cq->comp(cq); @@ -118,23 +124,19 @@ void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type) struct mlx4_cq_table *cq_table = &mlx4_priv(dev)->cq_table; struct mlx4_cq *cq; - spin_lock(&cq_table->lock); - + rcu_read_lock(); cq = radix_tree_lookup(&cq_table->tree, cqn & (dev->caps.num_cqs - 1)); - if (cq) - atomic_inc(&cq->refcount); - - spin_unlock(&cq_table->lock); + rcu_read_unlock(); if (!cq) { - mlx4_warn(dev, "Async event for bogus CQ %08x\n", cqn); + mlx4_dbg(dev, "Async event for bogus CQ %08x\n", cqn); return; } + /* Acessing the CQ outside of rcu_read_lock is safe, because + * the CQ is freed only after interrupt handling is completed. + */ cq->event(cq, event_type); - - if (atomic_dec_and_test(&cq->refcount)) - complete(&cq->free); } static int mlx4_SW2HW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox, @@ -301,9 +303,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, if (err) return err; - spin_lock_irq(&cq_table->lock); + spin_lock(&cq_table->lock); err = radix_tree_insert(&cq_table->tree, cq->cqn, cq); - spin_unlock_irq(&cq_table->lock); + spin_unlock(&cq_table->lock); if (err) goto err_icm; @@ -349,9 +351,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, return 0; err_radix: - spin_lock_irq(&cq_table->lock); + spin_lock(&cq_table->lock); radix_tree_delete(&cq_table->tree, cq->cqn); - spin_unlock_irq(&cq_table->lock); + spin_unlock(&cq_table->lock); err_icm: mlx4_cq_free_icm(dev, cq->cqn); @@ -370,15 +372,15 @@ void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq) if (err) mlx4_warn(dev, "HW2SW_CQ failed (%d) for CQN %06x\n", err, cq->cqn); + spin_lock(&cq_table->lock); + radix_tree_delete(&cq_table->tree, cq->cqn); + spin_unlock(&cq_table->lock); + synchronize_irq(priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq); if (priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq != priv->eq_table.eq[MLX4_EQ_ASYNC].irq) synchronize_irq(priv->eq_table.eq[MLX4_EQ_ASYNC].irq); - spin_lock_irq(&cq_table->lock); - radix_tree_delete(&cq_table->tree, cq->cqn); - spin_unlock_irq(&cq_table->lock); - if (atomic_dec_and_test(&cq->refcount)) complete(&cq->free); wait_for_completion(&cq->free); -- cgit v1.2.3 From 7c3945bc2073554bb2ecf983e073dee686679c53 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Mon, 16 Jan 2017 18:31:38 +0200 Subject: net/mlx4_core: Fix when to save some qp context flags for dynamic VST to VGT transitions Save the qp context flags byte containing the flag disabling vlan stripping in the RESET to INIT qp transition, rather than in the INIT to RTR transition. Per the firmware spec, the flags in this byte are active in the RESET to INIT transition. As a result of saving the flags in the incorrect qp transition, when switching dynamically from VGT to VST and back to VGT, the vlan remained stripped (as is required for VST) and did not return to not-stripped (as is required for VGT). Fixes: f0f829bf42cd ("net/mlx4_core: Add immediate activate for VGT->VST->VGT") Signed-off-by: Jack Morgenstein Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 56185a0b827d..1822382212ee 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2980,6 +2980,9 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, put_res(dev, slave, srqn, RES_SRQ); qp->srq = srq; } + + /* Save param3 for dynamic changes from VST back to VGT */ + qp->param3 = qpc->param3; put_res(dev, slave, rcqn, RES_CQ); put_res(dev, slave, mtt_base, RES_MTT); res_end_move(dev, slave, RES_QP, qpn); @@ -3772,7 +3775,6 @@ int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave, int qpn = vhcr->in_modifier & 0x7fffff; struct res_qp *qp; u8 orig_sched_queue; - __be32 orig_param3 = qpc->param3; u8 orig_vlan_control = qpc->pri_path.vlan_control; u8 orig_fvl_rx = qpc->pri_path.fvl_rx; u8 orig_pri_path_fl = qpc->pri_path.fl; @@ -3814,7 +3816,6 @@ out: */ if (!err) { qp->sched_queue = orig_sched_queue; - qp->param3 = orig_param3; qp->vlan_control = orig_vlan_control; qp->fvl_rx = orig_fvl_rx; qp->pri_path_fl = orig_pri_path_fl; -- cgit v1.2.3 From 9577b174cd0323d287c994ef0891db71666d0765 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Mon, 16 Jan 2017 18:31:39 +0200 Subject: net/mlx4_core: Eliminate warning messages for SRQ_LIMIT under SRIOV When running SRIOV, warnings for SRQ LIMIT events flood the Hypervisor's message log when (correct, normally operating) apps use SRQ LIMIT events as a trigger to post WQEs to SRQs. Add more information to the existing debug printout for SRQ_LIMIT, and output the warning messages only for the SRQ CATAS ERROR event. Fixes: acba2420f9d2 ("mlx4_core: Add wrapper functions and comm channel and slave event support to EQs") Fixes: e0debf9cb50d ("mlx4_core: Reduce warning message for SRQ_LIMIT event to debug level") Signed-off-by: Jack Morgenstein Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/eq.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index cd3638e6fe25..0509996957d9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -554,8 +554,9 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) break; case MLX4_EVENT_TYPE_SRQ_LIMIT: - mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT\n", - __func__); + mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT. srq_no=0x%x, eq 0x%x\n", + __func__, be32_to_cpu(eqe->event.srq.srqn), + eq->eqn); case MLX4_EVENT_TYPE_SRQ_CATAS_ERROR: if (mlx4_is_master(dev)) { /* forward only to slave owning the SRQ */ @@ -570,15 +571,19 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) eq->eqn, eq->cons_index, ret); break; } - mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n", - __func__, slave, - be32_to_cpu(eqe->event.srq.srqn), - eqe->type, eqe->subtype); + if (eqe->type == + MLX4_EVENT_TYPE_SRQ_CATAS_ERROR) + mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n", + __func__, slave, + be32_to_cpu(eqe->event.srq.srqn), + eqe->type, eqe->subtype); if (!ret && slave != dev->caps.function) { - mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n", - __func__, eqe->type, - eqe->subtype, slave); + if (eqe->type == + MLX4_EVENT_TYPE_SRQ_CATAS_ERROR) + mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n", + __func__, eqe->type, + eqe->subtype, slave); mlx4_slave_event(dev, slave, eqe); break; } -- cgit v1.2.3 From 0faa9cb5b3836a979864a6357e01d2046884ad52 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sun, 15 Jan 2017 10:14:06 -0500 Subject: net sched actions: fix refcnt when GETing of action after bind Demonstrating the issue: .. add a drop action $sudo $TC actions add action drop index 10 .. retrieve it $ sudo $TC -s actions get action gact index 10 action order 1: gact action drop random type none pass val 0 index 10 ref 2 bind 0 installed 29 sec used 29 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 ... bug 1 above: reference is two. Reference is actually 1 but we forget to subtract 1. ... do a GET again and we see the same issue try a few times and nothing changes ~$ sudo $TC -s actions get action gact index 10 action order 1: gact action drop random type none pass val 0 index 10 ref 2 bind 0 installed 31 sec used 31 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 ... lets try to bind the action to a filter.. $ sudo $TC qdisc add dev lo ingress $ sudo $TC filter add dev lo parent ffff: protocol ip prio 1 \ u32 match ip dst 127.0.0.1/32 flowid 1:1 action gact index 10 ... and now a few GETs: $ sudo $TC -s actions get action gact index 10 action order 1: gact action drop random type none pass val 0 index 10 ref 3 bind 1 installed 204 sec used 204 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 $ sudo $TC -s actions get action gact index 10 action order 1: gact action drop random type none pass val 0 index 10 ref 4 bind 1 installed 206 sec used 206 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 $ sudo $TC -s actions get action gact index 10 action order 1: gact action drop random type none pass val 0 index 10 ref 5 bind 1 installed 235 sec used 235 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 .... as can be observed the reference count keeps going up. After the fix $ sudo $TC actions add action drop index 10 $ sudo $TC -s actions get action gact index 10 action order 1: gact action drop random type none pass val 0 index 10 ref 1 bind 0 installed 4 sec used 4 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 $ sudo $TC -s actions get action gact index 10 action order 1: gact action drop random type none pass val 0 index 10 ref 1 bind 0 installed 6 sec used 6 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 $ sudo $TC qdisc add dev lo ingress $ sudo $TC filter add dev lo parent ffff: protocol ip prio 1 \ u32 match ip dst 127.0.0.1/32 flowid 1:1 action gact index 10 $ sudo $TC -s actions get action gact index 10 action order 1: gact action drop random type none pass val 0 index 10 ref 2 bind 1 installed 32 sec used 32 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 $ sudo $TC -s actions get action gact index 10 action order 1: gact action drop random type none pass val 0 index 10 ref 2 bind 1 installed 33 sec used 33 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Fixes: aecc5cefc389 ("net sched actions: fix GETing actions") Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/sched/act_api.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 2095c83ce773..e10456ef6f7a 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -900,8 +900,6 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, goto err; } act->order = i; - if (event == RTM_GETACTION) - act->tcfa_refcnt++; list_add_tail(&act->list, &actions); } @@ -914,7 +912,8 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, return ret; } err: - tcf_action_destroy(&actions, 0); + if (event != RTM_GETACTION) + tcf_action_destroy(&actions, 0); return ret; } -- cgit v1.2.3