From 4564b187c16327045d87596e8980c65ba7b84c50 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 11 Dec 2017 12:33:47 +0100 Subject: nl80211: fix nl80211_send_iface() error paths Evidently I introduced a locking bug in my change here, the nla_put_failure sometimes needs to unlock. Fix it. Fixes: 44905265bc15 ("nl80211: don't expose wdev->ssid for most interfaces") Signed-off-by: Johannes Berg --- net/wireless/nl80211.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b1ac23c..213d0c4 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2610,7 +2610,7 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag case NL80211_IFTYPE_AP: if (wdev->ssid_len && nla_put(msg, NL80211_ATTR_SSID, wdev->ssid_len, wdev->ssid)) - goto nla_put_failure; + goto nla_put_failure_locked; break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: @@ -2623,7 +2623,7 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag if (!ssid_ie) break; if (nla_put(msg, NL80211_ATTR_SSID, ssid_ie[1], ssid_ie + 2)) - goto nla_put_failure; + goto nla_put_failure_locked; break; } default: @@ -2635,6 +2635,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag genlmsg_end(msg, hdr); return 0; + nla_put_failure_locked: + wdev_unlock(wdev); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; -- cgit v1.1 From 2d17d8d79e77ff3f1b35b87522fc72fa562260ff Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 14 Dec 2017 17:17:56 -0800 Subject: xdp: linearize skb in netif_receive_generic_xdp() In netif_receive_generic_xdp(), it is necessary to linearize all nonlinear skb. However, in current implementation, skb with troom <= 0 are not linearized. This patch fixes this by calling skb_linearize() for all nonlinear skb. Fixes: de8f3a83b0a0 ("bpf: add meta pointer for direct access") Signed-off-by: Song Liu Acked-by: Martin KaFai Lau Cc: Daniel Borkmann Cc: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/dev.c b/net/core/dev.c index f47e96b..01ee854 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3904,7 +3904,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, troom > 0 ? troom + 128 : 0, GFP_ATOMIC)) goto do_drop; - if (troom > 0 && __skb_linearize(skb)) + if (skb_linearize(skb)) goto do_drop; } -- cgit v1.1 From 588753f1eb18978512b1c9b85fddb457d46f9033 Mon Sep 17 00:00:00 2001 From: Brendan McGrath Date: Wed, 13 Dec 2017 22:14:57 +1100 Subject: ipv6: icmp6: Allow icmp messages to be looped back One example of when an ICMPv6 packet is required to be looped back is when a host acts as both a Multicast Listener and a Multicast Router. A Multicast Router will listen on address ff02::16 for MLDv2 messages. Currently, MLDv2 messages originating from a Multicast Listener running on the same host as the Multicast Router are not being delivered to the Multicast Router. This is due to dst.input being assigned the default value of dst_discard. This results in the packet being looped back but discarded before being delivered to the Multicast Router. This patch sets dst.input to ip6_input to ensure a looped back packet is delivered to the Multicast Router. Signed-off-by: Brendan McGrath Signed-off-by: David S. Miller --- net/ipv6/route.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7a8d150..2bc91c3 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2336,6 +2336,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, } rt->dst.flags |= DST_HOST; + rt->dst.input = ip6_input; rt->dst.output = ip6_output; rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; -- cgit v1.1 From 234833991e14681f61cbfd93e65a5c976089cf11 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Mon, 18 Dec 2017 17:34:16 +0100 Subject: tipc: fix lost member events bug Group messages are not supposed to be returned to sender when the destination socket disappears. This is done correctly for regular traffic messages, by setting the 'dest_droppable' bit in the header. But we forget to do that in group protocol messages. This has the effect that such messages may sometimes bounce back to the sender, be perceived as a legitimate peer message, and wreak general havoc for the rest of the session. In particular, we have seen that a member in state LEAVING may go back to state RECLAIMED or REMITTED, hence causing suppression of an otherwise expected 'member down' event to the user. We fix this by setting the 'dest_droppable' bit even in group protocol messages. Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/group.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/tipc/group.c b/net/tipc/group.c index 95fec2c..efb5714 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -648,6 +648,7 @@ static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, } else if (mtyp == GRP_REMIT_MSG) { msg_set_grp_remitted(hdr, m->window); } + msg_set_dest_droppable(hdr, true); __skb_queue_tail(xmitq, skb); } -- cgit v1.1 From 3f42f5fe31c8715a34064bfd7b788488d1ea2f7c Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Mon, 18 Dec 2017 18:13:34 +0100 Subject: tipc: remove leaving group member from all lists A group member going into state LEAVING should never go back to any other state before it is finally deleted. However, this might happen if the socket needs to send out a RECLAIM message during this interval. Since we forget to remove the leaving member from the group's 'active' or 'pending' list, the member might be selected for reclaiming, change state to RECLAIMING, and get stuck in this state instead of being deleted. This might lead to suppression of the expected 'member down' event to the receiver. We fix this by removing the member from all lists, except the RB tree, at the moment it goes into state LEAVING. Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/group.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/tipc/group.c b/net/tipc/group.c index efb5714..b96ec42 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -699,6 +699,9 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, if (!m) return; m->bc_syncpt = msg_grp_bc_syncpt(hdr); + list_del_init(&m->list); + list_del_init(&m->congested); + *usr_wakeup = true; /* Wait until WITHDRAW event is received */ if (m->state != MBR_LEAVING) { @@ -710,8 +713,6 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, ehdr = buf_msg(m->event_msg); msg_set_grp_bc_seqno(ehdr, m->bc_syncpt); __skb_queue_tail(inputq, m->event_msg); - *usr_wakeup = true; - list_del_init(&m->congested); return; case GRP_ADV_MSG: if (!m) @@ -863,6 +864,7 @@ void tipc_group_member_evt(struct tipc_group *grp, msg_set_grp_bc_seqno(hdr, m->bc_rcv_nxt); __skb_queue_tail(inputq, skb); } + list_del_init(&m->list); list_del_init(&m->congested); } *sk_rcvbuf = tipc_group_rcvbuf_limit(grp); -- cgit v1.1 From 5c468674d17056148da06218d4da5d04baf22eac Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 18 Dec 2017 14:07:25 +0800 Subject: sctp: fix the issue that a __u16 variable may overflow in sctp_ulpq_renege Now when reneging events in sctp_ulpq_renege(), the variable freed could be increased by a __u16 value twice while freed is of __u16 type. It means freed may overflow at the second addition. This patch is to fix it by using __u32 type for 'freed', while at it, also to remove 'if (chunk)' check, as all renege commands are generated in sctp_eat_data and it can't be NULL. Reported-by: Marcelo Ricardo Leitner Signed-off-by: Xin Long Acked-by: Neil Horman Signed-off-by: David S. Miller --- net/sctp/ulpqueue.c | 24 ++++++++---------------- 1 file changed, 8 insertions(+), 16 deletions(-) (limited to 'net') diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index a71be33..e36ec5d 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -1084,29 +1084,21 @@ void sctp_ulpq_partial_delivery(struct sctp_ulpq *ulpq, void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, gfp_t gfp) { - struct sctp_association *asoc; - __u16 needed, freed; - - asoc = ulpq->asoc; + struct sctp_association *asoc = ulpq->asoc; + __u32 freed = 0; + __u16 needed; - if (chunk) { - needed = ntohs(chunk->chunk_hdr->length); - needed -= sizeof(struct sctp_data_chunk); - } else - needed = SCTP_DEFAULT_MAXWINDOW; - - freed = 0; + needed = ntohs(chunk->chunk_hdr->length) - + sizeof(struct sctp_data_chunk); if (skb_queue_empty(&asoc->base.sk->sk_receive_queue)) { freed = sctp_ulpq_renege_order(ulpq, needed); - if (freed < needed) { + if (freed < needed) freed += sctp_ulpq_renege_frags(ulpq, needed - freed); - } } /* If able to free enough room, accept this chunk. */ - if (chunk && (freed >= needed)) { - int retval; - retval = sctp_ulpq_tail_data(ulpq, chunk, gfp); + if (freed >= needed) { + int retval = sctp_ulpq_tail_data(ulpq, chunk, gfp); /* * Enter partial delivery if chunk has not been * delivered; otherwise, drain the reassembly queue. -- cgit v1.1 From d196975905b2bb227dc54547c03b3d9d0013805c Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 18 Dec 2017 14:13:17 +0800 Subject: sctp: add SCTP_CID_RECONF conversion in sctp_cname Whenever a new type of chunk is added, the corresp conversion in sctp_cname should be added. Otherwise, in some places, pr_debug will print it as "unknown chunk". Fixes: cc16f00f6529 ("sctp: add support for generating stream reconf ssn reset request chunk") Signed-off-by: Xin Long Acked-by: Marcelo R. Leitner Acked-by: Neil Horman Signed-off-by: David S. Miller --- net/sctp/debug.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net') diff --git a/net/sctp/debug.c b/net/sctp/debug.c index 3f619fd..291c97b 100644 --- a/net/sctp/debug.c +++ b/net/sctp/debug.c @@ -78,6 +78,9 @@ const char *sctp_cname(const union sctp_subtype cid) case SCTP_CID_AUTH: return "AUTH"; + case SCTP_CID_RECONF: + return "RECONF"; + default: break; } -- cgit v1.1 From 84aeb437ab98a2bce3d4b2111c79723aedfceb33 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Mon, 18 Dec 2017 17:35:09 +0200 Subject: net: bridge: fix early call to br_stp_change_bridge_id and plug newlink leaks The early call to br_stp_change_bridge_id in bridge's newlink can cause a memory leak if an error occurs during the newlink because the fdb entries are not cleaned up if a different lladdr was specified, also another minor issue is that it generates fdb notifications with ifindex = 0. Another unrelated memory leak is the bridge sysfs entries which get added on NETDEV_REGISTER event, but are not cleaned up in the newlink error path. To remove this special case the call to br_stp_change_bridge_id is done after netdev register and we cleanup the bridge on changelink error via br_dev_delete to plug all leaks. This patch makes netlink bridge destruction on newlink error the same as dellink and ioctl del which is necessary since at that point we have a fully initialized bridge device. To reproduce the issue: $ ip l add br0 address 00:11:22:33:44:55 type bridge group_fwd_mask 1 RTNETLINK answers: Invalid argument $ rmmod bridge [ 1822.142525] ============================================================================= [ 1822.143640] BUG bridge_fdb_cache (Tainted: G O ): Objects remaining in bridge_fdb_cache on __kmem_cache_shutdown() [ 1822.144821] ----------------------------------------------------------------------------- [ 1822.145990] Disabling lock debugging due to kernel taint [ 1822.146732] INFO: Slab 0x0000000092a844b2 objects=32 used=2 fp=0x00000000fef011b0 flags=0x1ffff8000000100 [ 1822.147700] CPU: 2 PID: 13584 Comm: rmmod Tainted: G B O 4.15.0-rc2+ #87 [ 1822.148578] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014 [ 1822.150008] Call Trace: [ 1822.150510] dump_stack+0x78/0xa9 [ 1822.151156] slab_err+0xb1/0xd3 [ 1822.151834] ? __kmalloc+0x1bb/0x1ce [ 1822.152546] __kmem_cache_shutdown+0x151/0x28b [ 1822.153395] shutdown_cache+0x13/0x144 [ 1822.154126] kmem_cache_destroy+0x1c0/0x1fb [ 1822.154669] SyS_delete_module+0x194/0x244 [ 1822.155199] ? trace_hardirqs_on_thunk+0x1a/0x1c [ 1822.155773] entry_SYSCALL_64_fastpath+0x23/0x9a [ 1822.156343] RIP: 0033:0x7f929bd38b17 [ 1822.156859] RSP: 002b:00007ffd160e9a98 EFLAGS: 00000202 ORIG_RAX: 00000000000000b0 [ 1822.157728] RAX: ffffffffffffffda RBX: 00005578316ba090 RCX: 00007f929bd38b17 [ 1822.158422] RDX: 00007f929bd9ec60 RSI: 0000000000000800 RDI: 00005578316ba0f0 [ 1822.159114] RBP: 0000000000000003 R08: 00007f929bff5f20 R09: 00007ffd160e8a11 [ 1822.159808] R10: 00007ffd160e9860 R11: 0000000000000202 R12: 00007ffd160e8a80 [ 1822.160513] R13: 0000000000000000 R14: 0000000000000000 R15: 00005578316ba090 [ 1822.161278] INFO: Object 0x000000007645de29 @offset=0 [ 1822.161666] INFO: Object 0x00000000d5df2ab5 @offset=128 Fixes: 30313a3d5794 ("bridge: Handle IFLA_ADDRESS correctly when creating bridge device") Fixes: 5b8d5429daa0 ("bridge: netlink: register netdevice before executing changelink") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/bridge/br_netlink.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index d0ef0a8..015f465c 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1262,19 +1262,20 @@ static int br_dev_newlink(struct net *src_net, struct net_device *dev, struct net_bridge *br = netdev_priv(dev); int err; + err = register_netdevice(dev); + if (err) + return err; + if (tb[IFLA_ADDRESS]) { spin_lock_bh(&br->lock); br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); spin_unlock_bh(&br->lock); } - err = register_netdevice(dev); - if (err) - return err; - err = br_changelink(dev, tb, data, extack); if (err) - unregister_netdevice(dev); + br_dev_delete(dev, NULL); + return err; } -- cgit v1.1 From 5d32407396b0433f9b738fcfcb9599bcba7379ae Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 14 Dec 2017 14:33:38 +0100 Subject: cfg80211: always rewrite generated files from scratch Currently the certs C code generation appends to the generated files, which is most likely a leftover from commit 715a12334764 ("wireless: don't write C files on failures"). This causes duplicate code in the generated files if the certificates have their timestamps modified between builds and thereby trigger the generation rules. Fixes: 715a12334764 ("wireless: don't write C files on failures") Signed-off-by: Thierry Reding Signed-off-by: Johannes Berg --- net/wireless/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/wireless/Makefile b/net/wireless/Makefile index d7d6cb00..b662be3 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -43,7 +43,7 @@ $(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.x509) echo "$$allf"; \ echo '};'; \ echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);'; \ - ) >> $@) + ) > $@) $(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%) \ $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%)/*.x509) @@ -66,4 +66,4 @@ $(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%) \ echo "$$allf"; \ echo '};'; \ echo 'unsigned int extra_regdb_certs_len = sizeof(extra_regdb_certs);'; \ - ) >> $@) + ) > $@) -- cgit v1.1 From 04a7279ff12fc47b657f70731d401c0064f5838a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 19 Dec 2017 09:26:17 +0100 Subject: cfg80211: ship certificates as hex files Not only does this remove the need for the hexdump code in most normal kernel builds (still there for the extra directory), but it also removes the need to ship binary files, which apparently is somewhat problematic, as Randy reported. While at it, also add the generated files to clean-files. Reported-by: Randy Dunlap Signed-off-by: Johannes Berg --- net/wireless/Makefile | 29 ++++--------- net/wireless/certs/sforshee.hex | 86 +++++++++++++++++++++++++++++++++++++++ net/wireless/certs/sforshee.x509 | Bin 680 -> 0 bytes 3 files changed, 95 insertions(+), 20 deletions(-) create mode 100644 net/wireless/certs/sforshee.hex delete mode 100644 net/wireless/certs/sforshee.x509 (limited to 'net') diff --git a/net/wireless/Makefile b/net/wireless/Makefile index b662be3..1d84f91 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -23,27 +23,14 @@ ifneq ($(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR),) cfg80211-y += extra-certs.o endif -$(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.x509) +$(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.hex) @$(kecho) " GEN $@" - @(set -e; \ - allf=""; \ - for f in $^ ; do \ - # similar to hexdump -v -e '1/1 "0x%.2x," "\n"' \ - thisf=$$(od -An -v -tx1 < $$f | \ - sed -e 's/ /\n/g' | \ - sed -e 's/^[0-9a-f]\+$$/\0/;t;d' | \ - sed -e 's/^/0x/;s/$$/,/'); \ - # file should not be empty - maybe command substitution failed? \ - test ! -z "$$thisf";\ - allf=$$allf$$thisf;\ - done; \ - ( \ - echo '#include "reg.h"'; \ - echo 'const u8 shipped_regdb_certs[] = {'; \ - echo "$$allf"; \ - echo '};'; \ - echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);'; \ - ) > $@) + @(echo '#include "reg.h"'; \ + echo 'const u8 shipped_regdb_certs[] = {'; \ + cat $^ ; \ + echo '};'; \ + echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);'; \ + ) > $@ $(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%) \ $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%)/*.x509) @@ -67,3 +54,5 @@ $(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%) \ echo '};'; \ echo 'unsigned int extra_regdb_certs_len = sizeof(extra_regdb_certs);'; \ ) > $@) + +clean-files += shipped-certs.c extra-certs.c diff --git a/net/wireless/certs/sforshee.hex b/net/wireless/certs/sforshee.hex new file mode 100644 index 0000000..14ea666 --- /dev/null +++ b/net/wireless/certs/sforshee.hex @@ -0,0 +1,86 @@ +/* Seth Forshee's regdb certificate */ +0x30, 0x82, 0x02, 0xa4, 0x30, 0x82, 0x01, 0x8c, +0x02, 0x09, 0x00, 0xb2, 0x8d, 0xdf, 0x47, 0xae, +0xf9, 0xce, 0xa7, 0x30, 0x0d, 0x06, 0x09, 0x2a, +0x86, 0x48, 0x86, 0xf7, 0x0d, 0x01, 0x01, 0x0b, +0x05, 0x00, 0x30, 0x13, 0x31, 0x11, 0x30, 0x0f, +0x06, 0x03, 0x55, 0x04, 0x03, 0x0c, 0x08, 0x73, +0x66, 0x6f, 0x72, 0x73, 0x68, 0x65, 0x65, 0x30, +0x20, 0x17, 0x0d, 0x31, 0x37, 0x31, 0x30, 0x30, +0x36, 0x31, 0x39, 0x34, 0x30, 0x33, 0x35, 0x5a, +0x18, 0x0f, 0x32, 0x31, 0x31, 0x37, 0x30, 0x39, +0x31, 0x32, 0x31, 0x39, 0x34, 0x30, 0x33, 0x35, +0x5a, 0x30, 0x13, 0x31, 0x11, 0x30, 0x0f, 0x06, +0x03, 0x55, 0x04, 0x03, 0x0c, 0x08, 0x73, 0x66, +0x6f, 0x72, 0x73, 0x68, 0x65, 0x65, 0x30, 0x82, +0x01, 0x22, 0x30, 0x0d, 0x06, 0x09, 0x2a, 0x86, +0x48, 0x86, 0xf7, 0x0d, 0x01, 0x01, 0x01, 0x05, +0x00, 0x03, 0x82, 0x01, 0x0f, 0x00, 0x30, 0x82, +0x01, 0x0a, 0x02, 0x82, 0x01, 0x01, 0x00, 0xb5, +0x40, 0xe3, 0x9c, 0x28, 0x84, 0x39, 0x03, 0xf2, +0x39, 0xd7, 0x66, 0x2c, 0x41, 0x38, 0x15, 0xac, +0x7e, 0xa5, 0x83, 0x71, 0x25, 0x7e, 0x90, 0x7c, +0x68, 0xdd, 0x6f, 0x3f, 0xd9, 0xd7, 0x59, 0x38, +0x9f, 0x7c, 0x6a, 0x52, 0xc2, 0x03, 0x2a, 0x2d, +0x7e, 0x66, 0xf4, 0x1e, 0xb3, 0x12, 0x70, 0x20, +0x5b, 0xd4, 0x97, 0x32, 0x3d, 0x71, 0x8b, 0x3b, +0x1b, 0x08, 0x17, 0x14, 0x6b, 0x61, 0xc4, 0x57, +0x8b, 0x96, 0x16, 0x1c, 0xfd, 0x24, 0xd5, 0x0b, +0x09, 0xf9, 0x68, 0x11, 0x84, 0xfb, 0xca, 0x51, +0x0c, 0xd1, 0x45, 0x19, 0xda, 0x10, 0x44, 0x8a, +0xd9, 0xfe, 0x76, 0xa9, 0xfd, 0x60, 0x2d, 0x18, +0x0b, 0x28, 0x95, 0xb2, 0x2d, 0xea, 0x88, 0x98, +0xb8, 0xd1, 0x56, 0x21, 0xf0, 0x53, 0x1f, 0xf1, +0x02, 0x6f, 0xe9, 0x46, 0x9b, 0x93, 0x5f, 0x28, +0x90, 0x0f, 0xac, 0x36, 0xfa, 0x68, 0x23, 0x71, +0x57, 0x56, 0xf6, 0xcc, 0xd3, 0xdf, 0x7d, 0x2a, +0xd9, 0x1b, 0x73, 0x45, 0xeb, 0xba, 0x27, 0x85, +0xef, 0x7a, 0x7f, 0xa5, 0xcb, 0x80, 0xc7, 0x30, +0x36, 0xd2, 0x53, 0xee, 0xec, 0xac, 0x1e, 0xe7, +0x31, 0xf1, 0x36, 0xa2, 0x9c, 0x63, 0xc6, 0x65, +0x5b, 0x7f, 0x25, 0x75, 0x68, 0xa1, 0xea, 0xd3, +0x7e, 0x00, 0x5c, 0x9a, 0x5e, 0xd8, 0x20, 0x18, +0x32, 0x77, 0x07, 0x29, 0x12, 0x66, 0x1e, 0x36, +0x73, 0xe7, 0x97, 0x04, 0x41, 0x37, 0xb1, 0xb1, +0x72, 0x2b, 0xf4, 0xa1, 0x29, 0x20, 0x7c, 0x96, +0x79, 0x0b, 0x2b, 0xd0, 0xd8, 0xde, 0xc8, 0x6c, +0x3f, 0x93, 0xfb, 0xc5, 0xee, 0x78, 0x52, 0x11, +0x15, 0x1b, 0x7a, 0xf6, 0xe2, 0x68, 0x99, 0xe7, +0xfb, 0x46, 0x16, 0x84, 0xe3, 0xc7, 0xa1, 0xe6, +0xe0, 0xd2, 0x46, 0xd5, 0xe1, 0xc4, 0x5f, 0xa0, +0x66, 0xf4, 0xda, 0xc4, 0xff, 0x95, 0x1d, 0x02, +0x03, 0x01, 0x00, 0x01, 0x30, 0x0d, 0x06, 0x09, +0x2a, 0x86, 0x48, 0x86, 0xf7, 0x0d, 0x01, 0x01, +0x0b, 0x05, 0x00, 0x03, 0x82, 0x01, 0x01, 0x00, +0x87, 0x03, 0xda, 0xf2, 0x82, 0xc2, 0xdd, 0xaf, +0x7c, 0x44, 0x2f, 0x86, 0xd3, 0x5f, 0x4c, 0x93, +0x48, 0xb9, 0xfe, 0x07, 0x17, 0xbb, 0x21, 0xf7, +0x25, 0x23, 0x4e, 0xaa, 0x22, 0x0c, 0x16, 0xb9, +0x73, 0xae, 0x9d, 0x46, 0x7c, 0x75, 0xd9, 0xc3, +0x49, 0x57, 0x47, 0xbf, 0x33, 0xb7, 0x97, 0xec, +0xf5, 0x40, 0x75, 0xc0, 0x46, 0x22, 0xf0, 0xa0, +0x5d, 0x9c, 0x79, 0x13, 0xa1, 0xff, 0xb8, 0xa3, +0x2f, 0x7b, 0x8e, 0x06, 0x3f, 0xc8, 0xb6, 0xe4, +0x6a, 0x28, 0xf2, 0x34, 0x5c, 0x23, 0x3f, 0x32, +0xc0, 0xe6, 0xad, 0x0f, 0xac, 0xcf, 0x55, 0x74, +0x47, 0x73, 0xd3, 0x01, 0x85, 0xb7, 0x0b, 0x22, +0x56, 0x24, 0x7d, 0x9f, 0x09, 0xa9, 0x0e, 0x86, +0x9e, 0x37, 0x5b, 0x9c, 0x6d, 0x02, 0xd9, 0x8c, +0xc8, 0x50, 0x6a, 0xe2, 0x59, 0xf3, 0x16, 0x06, +0xea, 0xb2, 0x42, 0xb5, 0x58, 0xfe, 0xba, 0xd1, +0x81, 0x57, 0x1a, 0xef, 0xb2, 0x38, 0x88, 0x58, +0xf6, 0xaa, 0xc4, 0x2e, 0x8b, 0x5a, 0x27, 0xe4, +0xa5, 0xe8, 0xa4, 0xca, 0x67, 0x5c, 0xac, 0x72, +0x67, 0xc3, 0x6f, 0x13, 0xc3, 0x2d, 0x35, 0x79, +0xd7, 0x8a, 0xe7, 0xf5, 0xd4, 0x21, 0x30, 0x4a, +0xd5, 0xf6, 0xa3, 0xd9, 0x79, 0x56, 0xf2, 0x0f, +0x10, 0xf7, 0x7d, 0xd0, 0x51, 0x93, 0x2f, 0x47, +0xf8, 0x7d, 0x4b, 0x0a, 0x84, 0x55, 0x12, 0x0a, +0x7d, 0x4e, 0x3b, 0x1f, 0x2b, 0x2f, 0xfc, 0x28, +0xb3, 0x69, 0x34, 0xe1, 0x80, 0x80, 0xbb, 0xe2, +0xaf, 0xb9, 0xd6, 0x30, 0xf1, 0x1d, 0x54, 0x87, +0x23, 0x99, 0x9f, 0x51, 0x03, 0x4c, 0x45, 0x7d, +0x02, 0x65, 0x73, 0xab, 0xfd, 0xcf, 0x94, 0xcc, +0x0d, 0x3a, 0x60, 0xfd, 0x3c, 0x14, 0x2f, 0x16, +0x33, 0xa9, 0x21, 0x1f, 0xcb, 0x50, 0xb1, 0x8f, +0x03, 0xee, 0xa0, 0x66, 0xa9, 0x16, 0x79, 0x14, diff --git a/net/wireless/certs/sforshee.x509 b/net/wireless/certs/sforshee.x509 deleted file mode 100644 index c6f8f9d..0000000 Binary files a/net/wireless/certs/sforshee.x509 and /dev/null differ -- cgit v1.1 From cfddd4c33c254954927942599d299b3865743146 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 18 Dec 2017 14:24:35 +0800 Subject: ip_gre: remove the incorrect mtu limit for ipgre tap ipgre tap driver calls ether_setup(), after commit 61e84623ace3 ("net: centralize net_device min/max MTU checking"), the range of mtu is [min_mtu, max_mtu], which is [68, 1500] by default. It causes the dev mtu of the ipgre tap device to not be greater than 1500, this limit value is not correct for ipgre tap device. Besides, it's .change_mtu already does the right check. So this patch is just to set max_mtu as 0, and leave the check to it's .change_mtu. Fixes: 61e84623ace3 ("net: centralize net_device min/max MTU checking") Reported-by: Jianlin Shi Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 9c17356..45ffd3d 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1310,6 +1310,7 @@ static const struct net_device_ops erspan_netdev_ops = { static void ipgre_tap_setup(struct net_device *dev) { ether_setup(dev); + dev->max_mtu = 0; dev->netdev_ops = &gre_tap_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; -- cgit v1.1 From 2c52129a7d74d017320804c6928de770815c5f4a Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 18 Dec 2017 14:25:09 +0800 Subject: ip6_gre: remove the incorrect mtu limit for ipgre tap The same fix as the patch "ip_gre: remove the incorrect mtu limit for ipgre tap" is also needed for ip6_gre. Fixes: 61e84623ace3 ("net: centralize net_device min/max MTU checking") Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/ipv6/ip6_gre.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 4cfd8e0..416c891 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1308,6 +1308,7 @@ static void ip6gre_tap_setup(struct net_device *dev) ether_setup(dev); + dev->max_mtu = 0; dev->netdev_ops = &ip6gre_tap_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; -- cgit v1.1 From c9fefa08190fc879fb2e681035d7774e0a8c5170 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 18 Dec 2017 14:26:21 +0800 Subject: ip6_tunnel: get the min mtu properly in ip6_tnl_xmit Now it's using IPV6_MIN_MTU as the min mtu in ip6_tnl_xmit, but IPV6_MIN_MTU actually only works when the inner packet is ipv6. With IPV6_MIN_MTU for ipv4 packets, the new pmtu for inner dst couldn't be set less than 1280. It would cause tx_err and the packet to be dropped when the outer dst pmtu is close to 1280. Jianlin found it by running ipv4 traffic with the topo: (client) gre6 <---> eth1 (route) eth2 <---> gre6 (server) After changing eth2 mtu to 1300, the performance became very low, or the connection was even broken. The issue also affects ip4ip6 and ip6ip6 tunnels. So if the inner packet is ipv4, 576 should be considered as the min mtu. Note that for ip4ip6 and ip6ip6 tunnels, the inner packet can only be ipv4 or ipv6, but for gre6 tunnel, it may also be ARP. This patch using 576 as the min mtu for non-ipv6 packet works for all those cases. Reported-by: Jianlin Shi Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/ipv6/ip6_tunnel.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index db84f52..931c38f 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1123,8 +1123,13 @@ route_lookup: max_headroom += 8; mtu -= 8; } - if (mtu < IPV6_MIN_MTU) - mtu = IPV6_MIN_MTU; + if (skb->protocol == htons(ETH_P_IPV6)) { + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + } else if (mtu < 576) { + mtu = 576; + } + if (skb_dst(skb) && !t->parms.collect_md) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) { -- cgit v1.1 From 3db096011722fd8717e57687ae94b6917a11c9cc Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Mon, 18 Dec 2017 20:03:05 +0100 Subject: tipc: fix list sorting bug in function tipc_group_update_member() When, during a join operation, or during message transmission, a group member needs to be added to the group's 'congested' list, we sort it into the list in ascending order, according to its current advertised window size. However, we miss the case when the member is already on that list. This will have the result that the member, after the window size has been decremented, might be at the wrong position in that list. This again may have the effect that we during broadcast and multicast transmissions miss the fact that a destination is not yet ready for reception, and we end up sending anyway. From this point on, the behavior during the remaining session is unpredictable, e.g., with underflowing window sizes. We now correct this bug by unconditionally removing the member from the list before (re-)sorting it in. Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/group.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net') diff --git a/net/tipc/group.c b/net/tipc/group.c index b96ec42..bbc004e 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -351,8 +351,7 @@ void tipc_group_update_member(struct tipc_member *m, int len) if (m->window >= ADV_IDLE) return; - if (!list_empty(&m->congested)) - return; + list_del_init(&m->congested); /* Sort member into congested members' list */ list_for_each_entry_safe(_m, tmp, &grp->congested, congested) { -- cgit v1.1 From d03a45572efa068fa64db211d6d45222660e76c5 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Tue, 19 Dec 2017 15:17:13 +0100 Subject: ipv4: fib: Fix metrics match when deleting a route The recently added fib_metrics_match() causes a regression for routes with both RTAX_FEATURES and RTAX_CC_ALGO if the latter has TCP_CONG_NEEDS_ECN flag set: | # ip link add d0 type dummy | # ip link set d0 up | # ip route add 172.29.29.0/24 dev d0 features ecn congctl dctcp | # ip route del 172.29.29.0/24 dev d0 features ecn congctl dctcp | RTNETLINK answers: No such process During route insertion, fib_convert_metrics() detects that the given CC algo requires ECN and hence sets DST_FEATURE_ECN_CA bit in RTAX_FEATURES. During route deletion though, fib_metrics_match() compares stored RTAX_FEATURES value with that from userspace (which obviously has no knowledge about DST_FEATURE_ECN_CA) and fails. Fixes: 5f9ae3d9e7e4a ("ipv4: do metrics match when looking up and deleting a route") Signed-off-by: Phil Sutter Signed-off-by: David S. Miller --- net/ipv4/fib_semantics.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f04d944..c586597 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -698,7 +698,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi) nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { int type = nla_type(nla); - u32 val; + u32 fi_val, val; if (!type) continue; @@ -715,7 +715,11 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi) val = nla_get_u32(nla); } - if (fi->fib_metrics->metrics[type - 1] != val) + fi_val = fi->fib_metrics->metrics[type - 1]; + if (type == RTAX_FEATURES) + fi_val &= ~DST_FEATURE_ECN_CA; + + if (fi_val != val) return false; } -- cgit v1.1 From 21b5944350052d2583e82dd59b19a9ba94a007f0 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 19 Dec 2017 11:27:56 -0600 Subject: net: Fix double free and memory corruption in get_net_ns_by_id() (I can trivially verify that that idr_remove in cleanup_net happens after the network namespace count has dropped to zero --EWB) Function get_net_ns_by_id() does not check for net::count after it has found a peer in netns_ids idr. It may dereference a peer, after its count has already been finaly decremented. This leads to double free and memory corruption: put_net(peer) rtnl_lock() atomic_dec_and_test(&peer->count) [count=0] ... __put_net(peer) get_net_ns_by_id(net, id) spin_lock(&cleanup_list_lock) list_add(&net->cleanup_list, &cleanup_list) spin_unlock(&cleanup_list_lock) queue_work() peer = idr_find(&net->netns_ids, id) | get_net(peer) [count=1] | ... | (use after final put) v ... cleanup_net() ... spin_lock(&cleanup_list_lock) ... list_replace_init(&cleanup_list, ..) ... spin_unlock(&cleanup_list_lock) ... ... ... ... put_net(peer) ... atomic_dec_and_test(&peer->count) [count=0] ... spin_lock(&cleanup_list_lock) ... list_add(&net->cleanup_list, &cleanup_list) ... spin_unlock(&cleanup_list_lock) ... queue_work() ... rtnl_unlock() rtnl_lock() ... for_each_net(tmp) { ... id = __peernet2id(tmp, peer) ... spin_lock_irq(&tmp->nsid_lock) ... idr_remove(&tmp->netns_ids, id) ... ... ... net_drop_ns() ... net_free(peer) ... } ... | v cleanup_net() ... (Second free of peer) Also, put_net() on the right cpu may reorder with left's cpu list_replace_init(&cleanup_list, ..), and then cleanup_list will be corrupted. Since cleanup_net() is executed in worker thread, while put_net(peer) can happen everywhere, there should be enough time for concurrent get_net_ns_by_id() to pick the peer up, and the race does not seem to be unlikely. The patch fixes the problem in standard way. (Also, there is possible problem in peernet2id_alloc(), which requires check for net::count under nsid_lock and maybe_get_net(peer), but in current stable kernel it's used under rtnl_lock() and it has to be safe. Openswitch begun to use peernet2id_alloc(), and possibly it should be fixed too. While this is not in stable kernel yet, so I'll send a separate message to netdev@ later). Cc: Nicolas Dichtel Signed-off-by: Kirill Tkhai Fixes: 0c7aecd4bde4 "netns: add rtnl cmd to add and get peer netns ids" Reviewed-by: Andrey Ryabinin Reviewed-by: "Eric W. Biederman" Signed-off-by: Eric W. Biederman Reviewed-by: Eric Dumazet Acked-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/core/net_namespace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index b797832..60a71be 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -267,7 +267,7 @@ struct net *get_net_ns_by_id(struct net *net, int id) spin_lock_bh(&net->nsid_lock); peer = idr_find(&net->netns_ids, id); if (peer) - get_net(peer); + peer = maybe_get_net(peer); spin_unlock_bh(&net->nsid_lock); rcu_read_unlock(); -- cgit v1.1 From 102740bd9436a3a6ba129af3a48271d794009fa5 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 19 Dec 2017 13:32:13 -0800 Subject: cls_bpf: fix offload assumptions after callback conversion cls_bpf used to take care of tracking what offload state a filter is in, i.e. it would track if offload request succeeded or not. This information would then be used to issue correct requests to the driver, e.g. requests for statistics only on offloaded filters, removing only filters which were offloaded, using add instead of replace if previous filter was not added etc. This tracking of offload state no longer functions with the new callback infrastructure. There could be multiple entities trying to offload the same filter. Throw out all the tracking and corresponding commands and simply pass to the drivers both old and new bpf program. Drivers will have to deal with offload state tracking by themselves. Fixes: 3f7889c4c79b ("net: sched: cls_bpf: call block callbacks for offload") Signed-off-by: Jakub Kicinski Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- net/sched/cls_bpf.c | 93 ++++++++++++++++++++++------------------------------- 1 file changed, 38 insertions(+), 55 deletions(-) (limited to 'net') diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 6fe798c..8d78e7f 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -42,7 +42,6 @@ struct cls_bpf_prog { struct list_head link; struct tcf_result res; bool exts_integrated; - bool offloaded; u32 gen_flags; struct tcf_exts exts; u32 handle; @@ -148,33 +147,37 @@ static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog) } static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, - enum tc_clsbpf_command cmd) + struct cls_bpf_prog *oldprog) { - bool addorrep = cmd == TC_CLSBPF_ADD || cmd == TC_CLSBPF_REPLACE; struct tcf_block *block = tp->chain->block; - bool skip_sw = tc_skip_sw(prog->gen_flags); struct tc_cls_bpf_offload cls_bpf = {}; + struct cls_bpf_prog *obj; + bool skip_sw; int err; + skip_sw = prog && tc_skip_sw(prog->gen_flags); + obj = prog ?: oldprog; + tc_cls_common_offload_init(&cls_bpf.common, tp); - cls_bpf.command = cmd; - cls_bpf.exts = &prog->exts; - cls_bpf.prog = prog->filter; - cls_bpf.name = prog->bpf_name; - cls_bpf.exts_integrated = prog->exts_integrated; - cls_bpf.gen_flags = prog->gen_flags; + cls_bpf.command = TC_CLSBPF_OFFLOAD; + cls_bpf.exts = &obj->exts; + cls_bpf.prog = prog ? prog->filter : NULL; + cls_bpf.oldprog = oldprog ? oldprog->filter : NULL; + cls_bpf.name = obj->bpf_name; + cls_bpf.exts_integrated = obj->exts_integrated; + cls_bpf.gen_flags = obj->gen_flags; err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSBPF, &cls_bpf, skip_sw); - if (addorrep) { + if (prog) { if (err < 0) { - cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_DESTROY); + cls_bpf_offload_cmd(tp, oldprog, prog); return err; } else if (err > 0) { prog->gen_flags |= TCA_CLS_FLAGS_IN_HW; } } - if (addorrep && skip_sw && !(prog->gen_flags & TCA_CLS_FLAGS_IN_HW)) + if (prog && skip_sw && !(prog->gen_flags & TCA_CLS_FLAGS_IN_HW)) return -EINVAL; return 0; @@ -183,38 +186,17 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, struct cls_bpf_prog *oldprog) { - struct cls_bpf_prog *obj = prog; - enum tc_clsbpf_command cmd; - bool skip_sw; - int ret; - - skip_sw = tc_skip_sw(prog->gen_flags) || - (oldprog && tc_skip_sw(oldprog->gen_flags)); - - if (oldprog && oldprog->offloaded) { - if (!tc_skip_hw(prog->gen_flags)) { - cmd = TC_CLSBPF_REPLACE; - } else if (!tc_skip_sw(prog->gen_flags)) { - obj = oldprog; - cmd = TC_CLSBPF_DESTROY; - } else { - return -EINVAL; - } - } else { - if (tc_skip_hw(prog->gen_flags)) - return skip_sw ? -EINVAL : 0; - cmd = TC_CLSBPF_ADD; - } - - ret = cls_bpf_offload_cmd(tp, obj, cmd); - if (ret) - return ret; + if (prog && oldprog && prog->gen_flags != oldprog->gen_flags) + return -EINVAL; - obj->offloaded = true; - if (oldprog) - oldprog->offloaded = false; + if (prog && tc_skip_hw(prog->gen_flags)) + prog = NULL; + if (oldprog && tc_skip_hw(oldprog->gen_flags)) + oldprog = NULL; + if (!prog && !oldprog) + return 0; - return 0; + return cls_bpf_offload_cmd(tp, prog, oldprog); } static void cls_bpf_stop_offload(struct tcf_proto *tp, @@ -222,25 +204,26 @@ static void cls_bpf_stop_offload(struct tcf_proto *tp, { int err; - if (!prog->offloaded) - return; - - err = cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_DESTROY); - if (err) { + err = cls_bpf_offload_cmd(tp, NULL, prog); + if (err) pr_err("Stopping hardware offload failed: %d\n", err); - return; - } - - prog->offloaded = false; } static void cls_bpf_offload_update_stats(struct tcf_proto *tp, struct cls_bpf_prog *prog) { - if (!prog->offloaded) - return; + struct tcf_block *block = tp->chain->block; + struct tc_cls_bpf_offload cls_bpf = {}; + + tc_cls_common_offload_init(&cls_bpf.common, tp); + cls_bpf.command = TC_CLSBPF_STATS; + cls_bpf.exts = &prog->exts; + cls_bpf.prog = prog->filter; + cls_bpf.name = prog->bpf_name; + cls_bpf.exts_integrated = prog->exts_integrated; + cls_bpf.gen_flags = prog->gen_flags; - cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_STATS); + tc_setup_cb_call(block, NULL, TC_SETUP_CLSBPF, &cls_bpf, false); } static int cls_bpf_init(struct tcf_proto *tp) -- cgit v1.1 From bb25c3855a12cc58e33cd7ee9b69943790fe35f7 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Wed, 20 Dec 2017 11:03:15 +0100 Subject: tipc: remove joining group member from congested list When we receive a JOIN message from a peer member, the message may contain an advertised window value ADV_IDLE that permits removing the member in question from the tipc_group::congested list. However, since the removal has been made conditional on that the advertised window is *not* ADV_IDLE, we miss this case. This has the effect that a sender sometimes may enter a state of permanent, false, broadcast congestion. We fix this by unconditinally removing the member from the congested list before calling tipc_member_update(), which might potentially sort it into the list again. Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/group.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/tipc/group.c b/net/tipc/group.c index bbc004e..7ebbdeb 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -689,10 +689,8 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, msg_set_grp_bc_seqno(ehdr, m->bc_syncpt); __skb_queue_tail(inputq, m->event_msg); } - if (m->window < ADV_IDLE) - tipc_group_update_member(m, 0); - else - list_del_init(&m->congested); + list_del_init(&m->congested); + tipc_group_update_member(m, 0); return; case GRP_LEAVE_MSG: if (!m) -- cgit v1.1 From b4681c2829e24943aadd1a7bb3a30d41d0a20050 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 20 Dec 2017 19:34:19 +0200 Subject: ipv4: Fix use-after-free when flushing FIB tables Since commit 0ddcf43d5d4a ("ipv4: FIB Local/MAIN table collapse") the local table uses the same trie allocated for the main table when custom rules are not in use. When a net namespace is dismantled, the main table is flushed and freed (via an RCU callback) before the local table. In case the callback is invoked before the local table is iterated, a use-after-free can occur. Fix this by iterating over the FIB tables in reverse order, so that the main table is always freed after the local table. v3: Reworded comment according to Alex's suggestion. v2: Add a comment to make the fix more explicit per Dave's and Alex's feedback. Fixes: 0ddcf43d5d4a ("ipv4: FIB Local/MAIN table collapse") Signed-off-by: Ido Schimmel Reported-by: Fengguang Wu Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- net/ipv4/fib_frontend.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index f52d27a..08259d0 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1298,14 +1298,19 @@ err_table_hash_alloc: static void ip_fib_net_exit(struct net *net) { - unsigned int i; + int i; rtnl_lock(); #ifdef CONFIG_IP_MULTIPLE_TABLES RCU_INIT_POINTER(net->ipv4.fib_main, NULL); RCU_INIT_POINTER(net->ipv4.fib_default, NULL); #endif - for (i = 0; i < FIB_TABLE_HASHSZ; i++) { + /* Destroy the tables in reverse order to guarantee that the + * local table, ID 255, is destroyed before the main table, ID + * 254. This is necessary as the local table may contain + * references to data contained in the main table. + */ + for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) { struct hlist_head *head = &net->ipv4.fib_table_hash[i]; struct hlist_node *tmp; struct fib_table *tb; -- cgit v1.1 From 58acfd714e6b02e8617448b431c2b64a2f1f0792 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 20 Dec 2017 12:28:25 +0200 Subject: ipv6: Honor specified parameters in fibmatch lookup Currently, parameters such as oif and source address are not taken into account during fibmatch lookup. Example (IPv4 for reference) before patch: $ ip -4 route show 192.0.2.0/24 dev dummy0 proto kernel scope link src 192.0.2.1 198.51.100.0/24 dev dummy1 proto kernel scope link src 198.51.100.1 $ ip -6 route show 2001:db8:1::/64 dev dummy0 proto kernel metric 256 pref medium 2001:db8:2::/64 dev dummy1 proto kernel metric 256 pref medium fe80::/64 dev dummy0 proto kernel metric 256 pref medium fe80::/64 dev dummy1 proto kernel metric 256 pref medium $ ip -4 route get fibmatch 192.0.2.2 oif dummy0 192.0.2.0/24 dev dummy0 proto kernel scope link src 192.0.2.1 $ ip -4 route get fibmatch 192.0.2.2 oif dummy1 RTNETLINK answers: No route to host $ ip -6 route get fibmatch 2001:db8:1::2 oif dummy0 2001:db8:1::/64 dev dummy0 proto kernel metric 256 pref medium $ ip -6 route get fibmatch 2001:db8:1::2 oif dummy1 2001:db8:1::/64 dev dummy0 proto kernel metric 256 pref medium After: $ ip -6 route get fibmatch 2001:db8:1::2 oif dummy0 2001:db8:1::/64 dev dummy0 proto kernel metric 256 pref medium $ ip -6 route get fibmatch 2001:db8:1::2 oif dummy1 RTNETLINK answers: Network is unreachable The problem stems from the fact that the necessary route lookup flags are not set based on these parameters. Instead of duplicating the same logic for fibmatch, we can simply resolve the original route from its copy and dump it instead. Fixes: 18c3a61c4264 ("net: ipv6: RTM_GETROUTE: return matched fib result when requested") Signed-off-by: Ido Schimmel Acked-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/route.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2bc91c3..0458b76 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4298,19 +4298,13 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (!ipv6_addr_any(&fl6.saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; - if (!fibmatch) - dst = ip6_route_input_lookup(net, dev, &fl6, flags); - else - dst = ip6_route_lookup(net, &fl6, 0); + dst = ip6_route_input_lookup(net, dev, &fl6, flags); rcu_read_unlock(); } else { fl6.flowi6_oif = oif; - if (!fibmatch) - dst = ip6_route_output(net, NULL, &fl6); - else - dst = ip6_route_lookup(net, &fl6, 0); + dst = ip6_route_output(net, NULL, &fl6); } @@ -4327,6 +4321,15 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, goto errout; } + if (fibmatch && rt->dst.from) { + struct rt6_info *ort = container_of(rt->dst.from, + struct rt6_info, dst); + + dst_hold(&ort->dst); + ip6_rt_put(rt); + rt = ort; + } + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { ip6_rt_put(rt); -- cgit v1.1 From c48e74736fccf25fb32bb015426359e1c2016e3b Mon Sep 17 00:00:00 2001 From: Eric Garver Date: Wed, 20 Dec 2017 15:09:22 -0500 Subject: openvswitch: Fix pop_vlan action for double tagged frames skb_vlan_pop() expects skb->protocol to be a valid TPID for double tagged frames. So set skb->protocol to the TPID and let skb_vlan_pop() shift the true ethertype into position for us. Fixes: 5108bbaddc37 ("openvswitch: add processing of L3 packets") Signed-off-by: Eric Garver Reviewed-by: Jiri Benc Signed-off-by: David S. Miller --- net/openvswitch/flow.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index dbe2379..f039064 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -579,6 +579,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) return -EINVAL; skb_reset_network_header(skb); + key->eth.type = skb->protocol; } else { eth = eth_hdr(skb); ether_addr_copy(key->eth.src, eth->h_source); @@ -592,15 +593,23 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) if (unlikely(parse_vlan(skb, key))) return -ENOMEM; - skb->protocol = parse_ethertype(skb); - if (unlikely(skb->protocol == htons(0))) + key->eth.type = parse_ethertype(skb); + if (unlikely(key->eth.type == htons(0))) return -ENOMEM; + /* Multiple tagged packets need to retain TPID to satisfy + * skb_vlan_pop(), which will later shift the ethertype into + * skb->protocol. + */ + if (key->eth.cvlan.tci & htons(VLAN_TAG_PRESENT)) + skb->protocol = key->eth.cvlan.tpid; + else + skb->protocol = key->eth.type; + skb_reset_network_header(skb); __skb_push(skb, skb->data - skb_mac_header(skb)); } skb_reset_mac_len(skb); - key->eth.type = skb->protocol; /* Network layer. */ if (key->eth.type == htons(ETH_P_IP)) { -- cgit v1.1 From 513674b5a2c9c7a67501506419da5c3c77ac6f08 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 20 Dec 2017 12:10:21 -0800 Subject: net: reevalulate autoflowlabel setting after sysctl setting sysctl.ip6.auto_flowlabels is default 1. In our hosts, we set it to 2. If sockopt doesn't set autoflowlabel, outcome packets from the hosts are supposed to not include flowlabel. This is true for normal packet, but not for reset packet. The reason is ipv6_pinfo.autoflowlabel is set in sock creation. Later if we change sysctl.ip6.auto_flowlabels, the ipv6_pinfo.autoflowlabel isn't changed, so the sock will keep the old behavior in terms of auto flowlabel. Reset packet is suffering from this problem, because reset packet is sent from a special control socket, which is created at boot time. Since sysctl.ipv6.auto_flowlabels is 1 by default, the control socket will always have its ipv6_pinfo.autoflowlabel set, even after user set sysctl.ipv6.auto_flowlabels to 1, so reset packset will always have flowlabel. Normal sock created before sysctl setting suffers from the same issue. We can't even turn off autoflowlabel unless we kill all socks in the hosts. To fix this, if IPV6_AUTOFLOWLABEL sockopt is used, we use the autoflowlabel setting from user, otherwise we always call ip6_default_np_autolabel() which has the new settings of sysctl. Note, this changes behavior a little bit. Before commit 42240901f7c4 (ipv6: Implement different admin modes for automatic flow labels), the autoflowlabel behavior of a sock isn't sticky, eg, if sysctl changes, existing connection will change autoflowlabel behavior. After that commit, autoflowlabel behavior is sticky in the whole life of the sock. With this patch, the behavior isn't sticky again. Cc: Martin KaFai Lau Cc: Eric Dumazet Cc: Tom Herbert Signed-off-by: Shaohua Li Signed-off-by: David S. Miller --- net/ipv6/af_inet6.c | 1 - net/ipv6/ip6_output.c | 12 ++++++++++-- net/ipv6/ipv6_sockglue.c | 1 + 3 files changed, 11 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index c26f712..c9441ca 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -210,7 +210,6 @@ lookup_protocol: np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; np->mc_loop = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; - np->autoflowlabel = ip6_default_np_autolabel(net); np->repflow = net->ipv6.sysctl.flowlabel_reflect; sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 5110a41..f7dd51c 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -166,6 +166,14 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } +static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np) +{ + if (!np->autoflowlabel_set) + return ip6_default_np_autolabel(net); + else + return np->autoflowlabel; +} + /* * xmit an sk_buff (used by TCP, SCTP and DCCP) * Note : socket lock is not held for SYNACK packets, but might be modified @@ -230,7 +238,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, hlimit = ip6_dst_hoplimit(dst); ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, - np->autoflowlabel, fl6)); + ip6_autoflowlabel(net, np), fl6)); hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; @@ -1626,7 +1634,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, ip6_flow_hdr(hdr, v6_cork->tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, - np->autoflowlabel, fl6)); + ip6_autoflowlabel(net, np), fl6)); hdr->hop_limit = v6_cork->hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index b9404fe..2d4680e 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -886,6 +886,7 @@ pref_skip_coa: break; case IPV6_AUTOFLOWLABEL: np->autoflowlabel = valbool; + np->autoflowlabel_set = 1; retv = 0; break; case IPV6_RECVFRAGSIZE: -- cgit v1.1 From 268b790679422a89e9ab0685d9f291edae780c98 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 20 Dec 2017 17:37:49 -0500 Subject: skbuff: orphan frags before zerocopy clone Call skb_zerocopy_clone after skb_orphan_frags, to avoid duplicate calls to skb_uarg(skb)->callback for the same data. skb_zerocopy_clone associates skb_shinfo(skb)->uarg from frag_skb with each segment. This is only safe for uargs that do refcounting, which is those that pass skb_orphan_frags without dropping their shared frags. For others, skb_orphan_frags drops the user frags and sets the uarg to NULL, after which sock_zerocopy_clone has no effect. Qemu hangs were reported due to duplicate vhost_net_zerocopy_callback calls for the same data causing the vhost_net_ubuf_ref_>refcount to drop below zero. Link: http://lkml.kernel.org/r/ Fixes: 1f8b977ab32d ("sock: enable MSG_ZEROCOPY") Reported-by: Andreas Hartmann Reported-by: David Hill Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- net/core/skbuff.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a592ca0..edf40ac 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3654,8 +3654,6 @@ normal: skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags & SKBTX_SHARED_FRAG; - if (skb_zerocopy_clone(nskb, head_skb, GFP_ATOMIC)) - goto err; while (pos < offset + len) { if (i >= nfrags) { @@ -3681,6 +3679,8 @@ normal: if (unlikely(skb_orphan_frags(frag_skb, GFP_ATOMIC))) goto err; + if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC)) + goto err; *nskb_frag = *frag; __skb_frag_ref(nskb_frag); -- cgit v1.1 From b90ddd568792bcb0054eaf0f61785c8f80c3bd1c Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 20 Dec 2017 17:37:50 -0500 Subject: skbuff: skb_copy_ubufs must release uarg even without user frags skb_copy_ubufs creates a private copy of frags[] to release its hold on user frags, then calls uarg->callback to notify the owner. Call uarg->callback even when no frags exist. This edge case can happen when zerocopy_sg_from_iter finds enough room in skb_headlen to copy all the data. Fixes: 3ece782693c4 ("sock: skb_copy_ubufs support for compound pages") Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- net/core/skbuff.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index edf40ac..a3cb0be 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1178,7 +1178,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) u32 d_off; if (!num_frags) - return 0; + goto release; if (skb_shared(skb) || skb_unclone(skb, gfp_mask)) return -EINVAL; @@ -1238,6 +1238,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) __skb_fill_page_desc(skb, new_frags - 1, head, 0, d_off); skb_shinfo(skb)->nr_frags = new_frags; +release: skb_zcopy_clear(skb, false); return 0; } -- cgit v1.1