From 0e63208915a8d7590d0a6218dadb2a6a00ac705a Mon Sep 17 00:00:00 2001 From: Erik Hugne Date: Mon, 4 Mar 2019 23:26:10 +0100 Subject: [PATCH 01/72] tipc: fix RDM/DGRAM connect() regression Fix regression bug introduced in commit 365ad353c256 ("tipc: reduce risk of user starvation during link congestion") Only signal -EDESTADDRREQ for RDM/DGRAM if we don't have a cached sockaddr. Fixes: 365ad353c256 ("tipc: reduce risk of user starvation during link congestion") Signed-off-by: Erik Hugne Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index e482b342bfa8..3274ef625dba 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1333,7 +1333,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (unlikely(!dest)) { dest = &tsk->peer; - if (!syn || dest->family != AF_TIPC) + if (!syn && dest->family != AF_TIPC) return -EDESTADDRREQ; } From 4177c5d94264b57f426ef5c45a788808d1a1e536 Mon Sep 17 00:00:00 2001 From: wenxu Date: Tue, 5 Mar 2019 08:29:28 +0800 Subject: [PATCH 02/72] net/sched: act_tunnel_key: Fix double free dst_cache dst_cache_destroy will be called in dst_release dst_release-->dst_destroy_rcu-->dst_destroy-->metadata_dst_free -->dst_cache_destroy It should not call dst_cache_destroy before dst_release Fixes: 41411e2fd6b8 ("net/sched: act_tunnel_key: Add dst_cache support") Signed-off-by: wenxu Signed-off-by: David S. Miller --- net/sched/act_tunnel_key.c | 22 ++++++---------------- 1 file changed, 6 insertions(+), 16 deletions(-) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 3beb4717d3b7..7c6591b991d5 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -201,14 +201,9 @@ static void tunnel_key_release_params(struct tcf_tunnel_key_params *p) { if (!p) return; - if (p->tcft_action == TCA_TUNNEL_KEY_ACT_SET) { -#ifdef CONFIG_DST_CACHE - struct ip_tunnel_info *info = &p->tcft_enc_metadata->u.tun_info; - - dst_cache_destroy(&info->dst_cache); -#endif + if (p->tcft_action == TCA_TUNNEL_KEY_ACT_SET) dst_release(&p->tcft_enc_metadata->dst); - } + kfree_rcu(p, rcu); } @@ -338,7 +333,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, &metadata->u.tun_info, opts_len, extack); if (ret < 0) - goto release_dst_cache; + goto release_tun_meta; } metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; @@ -354,14 +349,14 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, &act_tunnel_key_ops, bind, true); if (ret) { NL_SET_ERR_MSG(extack, "Cannot create TC IDR"); - goto release_dst_cache; + goto release_tun_meta; } ret = ACT_P_CREATED; } else if (!ovr) { NL_SET_ERR_MSG(extack, "TC IDR already exists"); ret = -EEXIST; - goto release_dst_cache; + goto release_tun_meta; } t = to_tunnel_key(*a); @@ -371,7 +366,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters"); ret = -ENOMEM; exists = true; - goto release_dst_cache; + goto release_tun_meta; } params_new->tcft_action = parm->t_action; params_new->tcft_enc_metadata = metadata; @@ -388,12 +383,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, return ret; -release_dst_cache: -#ifdef CONFIG_DST_CACHE - if (metadata) - dst_cache_destroy(&metadata->u.tun_info.dst_cache); release_tun_meta: -#endif if (metadata) dst_release(&metadata->dst); From f4772dee101c7ac66e395d07b3140d457901fa18 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 6 Mar 2019 11:12:34 +0300 Subject: [PATCH 03/72] net: hns3: Fix a logical vs bitwise typo There were a couple logical ORs accidentally mixed in with the bitwise ORs. Fixes: e8149933b1fa ("net: hns3: remove hnae3_get_bit in data path") Signed-off-by: Dan Carpenter Reviewed-by: Yunsheng Lin Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 3cb43b1f1c2e..1e4efc47c7a5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2321,8 +2321,8 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb, if (!(bd_base_info & BIT(HNS3_RXD_L3L4P_B))) return; - if (unlikely(l234info & (BIT(HNS3_RXD_L3E_B) | BIT(HNS3_RXD_L4E_B) || - BIT(HNS3_RXD_OL3E_B) || + if (unlikely(l234info & (BIT(HNS3_RXD_L3E_B) | BIT(HNS3_RXD_L4E_B) | + BIT(HNS3_RXD_OL3E_B) | BIT(HNS3_RXD_OL4E_B)))) { u64_stats_update_begin(&ring->syncp); ring->stats.l3l4_csum_err++; From 22c74764aa2943ecdf9f07c900d8a9c8ba6c9265 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 6 Mar 2019 10:42:53 +0100 Subject: [PATCH 04/72] ipv4/route: fail early when inet dev is missing If a non local multicast packet reaches ip_route_input_rcu() while the ingress device IPv4 private data (in_dev) is NULL, we end up doing a NULL pointer dereference in IN_DEV_MFORWARD(). Since the later call to ip_route_input_mc() is going to fail if !in_dev, we can fail early in such scenario and avoid the dangerous code path. v1 -> v2: - clarified the commit message, no code changes Reported-by: Tianhao Zhao Fixes: e58e41596811 ("net: Enable support for VRF with ipv4 multicast") Signed-off-by: Paolo Abeni Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/route.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 738ff0a1a048..8ca3642f0d9b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2149,12 +2149,13 @@ int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, int our = 0; int err = -EINVAL; - if (in_dev) - our = ip_check_mc_rcu(in_dev, daddr, saddr, - ip_hdr(skb)->protocol); + if (!in_dev) + return err; + our = ip_check_mc_rcu(in_dev, daddr, saddr, + ip_hdr(skb)->protocol); /* check l3 master if no match yet */ - if ((!in_dev || !our) && netif_is_l3_slave(dev)) { + if (!our && netif_is_l3_slave(dev)) { struct in_device *l3_in_dev; l3_in_dev = __in_dev_get_rcu(skb->dev); From f4b3ec4e6aa1a2ca437905a519ae08e8cf6af754 Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Wed, 6 Mar 2019 10:25:42 +0000 Subject: [PATCH 05/72] iptunnel: NULL pointer deref for ip_md_tunnel_xmit Naresh Kamboju noted the following oops during execution of selftest tools/testing/selftests/bpf/test_tunnel.sh on x86_64: [ 274.120445] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 [ 274.128285] #PF error: [INSTR] [ 274.131351] PGD 8000000414a0e067 P4D 8000000414a0e067 PUD 3b6334067 PMD 0 [ 274.138241] Oops: 0010 [#1] SMP PTI [ 274.141734] CPU: 1 PID: 11464 Comm: ping Not tainted 5.0.0-rc4-next-20190129 #1 [ 274.149046] Hardware name: Supermicro SYS-5019S-ML/X11SSH-F, BIOS 2.0b 07/27/2017 [ 274.156526] RIP: 0010: (null) [ 274.160280] Code: Bad RIP value. [ 274.163509] RSP: 0018:ffffbc9681f83540 EFLAGS: 00010286 [ 274.168726] RAX: 0000000000000000 RBX: ffffdc967fa80a18 RCX: 0000000000000000 [ 274.175851] RDX: ffff9db2ee08b540 RSI: 000000000000000e RDI: ffffdc967fa809a0 [ 274.182974] RBP: ffffbc9681f83580 R08: ffff9db2c4d62690 R09: 000000000000000c [ 274.190098] R10: 0000000000000000 R11: ffff9db2ee08b540 R12: ffff9db31ce7c000 [ 274.197222] R13: 0000000000000001 R14: 000000000000000c R15: ffff9db3179cf400 [ 274.204346] FS: 00007ff4ae7c5740(0000) GS:ffff9db31fa80000(0000) knlGS:0000000000000000 [ 274.212424] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 274.218162] CR2: ffffffffffffffd6 CR3: 00000004574da004 CR4: 00000000003606e0 [ 274.225292] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 274.232416] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 274.239541] Call Trace: [ 274.241988] ? tnl_update_pmtu+0x296/0x3b0 [ 274.246085] ip_md_tunnel_xmit+0x1bc/0x520 [ 274.250176] gre_fb_xmit+0x330/0x390 [ 274.253754] gre_tap_xmit+0x128/0x180 [ 274.257414] dev_hard_start_xmit+0xb7/0x300 [ 274.261598] sch_direct_xmit+0xf6/0x290 [ 274.265430] __qdisc_run+0x15d/0x5e0 [ 274.269007] __dev_queue_xmit+0x2c5/0xc00 [ 274.273011] ? dev_queue_xmit+0x10/0x20 [ 274.276842] ? eth_header+0x2b/0xc0 [ 274.280326] dev_queue_xmit+0x10/0x20 [ 274.283984] ? dev_queue_xmit+0x10/0x20 [ 274.287813] arp_xmit+0x1a/0xf0 [ 274.290952] arp_send_dst.part.19+0x46/0x60 [ 274.295138] arp_solicit+0x177/0x6b0 [ 274.298708] ? mod_timer+0x18e/0x440 [ 274.302281] neigh_probe+0x57/0x70 [ 274.305684] __neigh_event_send+0x197/0x2d0 [ 274.309862] neigh_resolve_output+0x18c/0x210 [ 274.314212] ip_finish_output2+0x257/0x690 [ 274.318304] ip_finish_output+0x219/0x340 [ 274.322314] ? ip_finish_output+0x219/0x340 [ 274.326493] ip_output+0x76/0x240 [ 274.329805] ? ip_fragment.constprop.53+0x80/0x80 [ 274.334510] ip_local_out+0x3f/0x70 [ 274.337992] ip_send_skb+0x19/0x40 [ 274.341391] ip_push_pending_frames+0x33/0x40 [ 274.345740] raw_sendmsg+0xc15/0x11d0 [ 274.349403] ? __might_fault+0x85/0x90 [ 274.353151] ? _copy_from_user+0x6b/0xa0 [ 274.357070] ? rw_copy_check_uvector+0x54/0x130 [ 274.361604] inet_sendmsg+0x42/0x1c0 [ 274.365179] ? inet_sendmsg+0x42/0x1c0 [ 274.368937] sock_sendmsg+0x3e/0x50 [ 274.372460] ___sys_sendmsg+0x26f/0x2d0 [ 274.376293] ? lock_acquire+0x95/0x190 [ 274.380043] ? __handle_mm_fault+0x7ce/0xb70 [ 274.384307] ? lock_acquire+0x95/0x190 [ 274.388053] ? __audit_syscall_entry+0xdd/0x130 [ 274.392586] ? ktime_get_coarse_real_ts64+0x64/0xc0 [ 274.397461] ? __audit_syscall_entry+0xdd/0x130 [ 274.401989] ? trace_hardirqs_on+0x4c/0x100 [ 274.406173] __sys_sendmsg+0x63/0xa0 [ 274.409744] ? __sys_sendmsg+0x63/0xa0 [ 274.413488] __x64_sys_sendmsg+0x1f/0x30 [ 274.417405] do_syscall_64+0x55/0x190 [ 274.421064] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 274.426113] RIP: 0033:0x7ff4ae0e6e87 [ 274.429686] Code: 64 89 02 48 c7 c0 ff ff ff ff eb b9 0f 1f 80 00 00 00 00 8b 05 ca d9 2b 00 48 63 d2 48 63 ff 85 c0 75 10 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 53 48 89 f3 48 83 ec 10 48 89 7c 24 08 [ 274.448422] RSP: 002b:00007ffcd9b76db8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 274.455978] RAX: ffffffffffffffda RBX: 0000000000000040 RCX: 00007ff4ae0e6e87 [ 274.463104] RDX: 0000000000000000 RSI: 00000000006092e0 RDI: 0000000000000003 [ 274.470228] RBP: 0000000000000000 R08: 00007ffcd9bc40a0 R09: 00007ffcd9bc4080 [ 274.477349] R10: 000000000000060a R11: 0000000000000246 R12: 0000000000000003 [ 274.484475] R13: 0000000000000016 R14: 00007ffcd9b77fa0 R15: 00007ffcd9b78da4 [ 274.491602] Modules linked in: cls_bpf sch_ingress iptable_filter ip_tables algif_hash af_alg x86_pkg_temp_thermal fuse [last unloaded: test_bpf] [ 274.504634] CR2: 0000000000000000 [ 274.507976] ---[ end trace 196d18386545eae1 ]--- [ 274.512588] RIP: 0010: (null) [ 274.516334] Code: Bad RIP value. [ 274.519557] RSP: 0018:ffffbc9681f83540 EFLAGS: 00010286 [ 274.524775] RAX: 0000000000000000 RBX: ffffdc967fa80a18 RCX: 0000000000000000 [ 274.531921] RDX: ffff9db2ee08b540 RSI: 000000000000000e RDI: ffffdc967fa809a0 [ 274.539082] RBP: ffffbc9681f83580 R08: ffff9db2c4d62690 R09: 000000000000000c [ 274.546205] R10: 0000000000000000 R11: ffff9db2ee08b540 R12: ffff9db31ce7c000 [ 274.553329] R13: 0000000000000001 R14: 000000000000000c R15: ffff9db3179cf400 [ 274.560456] FS: 00007ff4ae7c5740(0000) GS:ffff9db31fa80000(0000) knlGS:0000000000000000 [ 274.568541] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 274.574277] CR2: ffffffffffffffd6 CR3: 00000004574da004 CR4: 00000000003606e0 [ 274.581403] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 274.588535] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 274.595658] Kernel panic - not syncing: Fatal exception in interrupt [ 274.602046] Kernel Offset: 0x14400000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 274.612827] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]--- [ 274.620387] ------------[ cut here ]------------ I'm also seeing the same failure on x86_64, and it reproduces consistently. >From poking around it looks like the skb's dst entry is being used to calculate the mtu in: mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; ...but because that dst_entry has an "ops" value set to md_dst_ops, the various ops (including mtu) are not set: crash> struct sk_buff._skb_refdst ffff928f87447700 -x _skb_refdst = 0xffffcd6fbf5ea590 crash> struct dst_entry.ops 0xffffcd6fbf5ea590 ops = 0xffffffffa0193800 crash> struct dst_ops.mtu 0xffffffffa0193800 mtu = 0x0 crash> I confirmed that the dst entry also has dst->input set to dst_md_discard, so it looks like it's an entry that's been initialized via __metadata_dst_init alright. I think the fix here is to use skb_valid_dst(skb) - it checks for DST_METADATA also, and with that fix in place, the problem - which was previously 100% reproducible - disappears. The below patch resolves the panic and all bpf tunnel tests pass without incident. Fixes: c8b34e680a09 ("ip_tunnel: Add tnl_update_pmtu in ip_md_tunnel_xmit") Reported-by: Naresh Kamboju Signed-off-by: Alan Maguire Acked-by: Alexei Starovoitov Tested-by: Anders Roxell Reported-by: Nicolas Dichtel Tested-by: Nicolas Dichtel Acked-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/ipv4/ip_tunnel.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 2756fb725bf0..a5d8cad18ead 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -515,9 +515,10 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, mtu = dst_mtu(&rt->dst) - dev->hard_header_len - sizeof(struct iphdr) - tunnel_hlen; else - mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; + mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; - skb_dst_update_pmtu(skb, mtu); + if (skb_valid_dst(skb)) + skb_dst_update_pmtu(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { if (!skb_is_gso(skb) && @@ -530,9 +531,11 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, } #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { - struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb); + struct rt6_info *rt6; __be32 daddr; + rt6 = skb_valid_dst(skb) ? (struct rt6_info *)skb_dst(skb) : + NULL; daddr = md ? dst : tunnel->parms.iph.daddr; if (rt6 && mtu < dst_mtu(skb_dst(skb)) && From 27da0d2ef998e222a876c0cec72aa7829a626266 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 6 Mar 2019 11:52:36 +0100 Subject: [PATCH 06/72] appletalk: Fix compile regression A bugfix just broke compilation of appletalk when CONFIG_SYSCTL is disabled: In file included from net/appletalk/ddp.c:65: net/appletalk/ddp.c: In function 'atalk_init': include/linux/atalk.h:164:34: error: expected expression before 'do' #define atalk_register_sysctl() do { } while(0) ^~ net/appletalk/ddp.c:1934:7: note: in expansion of macro 'atalk_register_sysctl' rc = atalk_register_sysctl(); This is easier to avoid by using conventional inline functions as stubs rather than macros. The header already has inline functions for other purposes, so I'm changing over all the macros for consistency. Fixes: 6377f787aeb9 ("appletalk: Fix use-after-free in atalk_proc_exit") Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- include/linux/atalk.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/include/linux/atalk.h b/include/linux/atalk.h index 5a90f28d5ff2..d5cfc0b15b76 100644 --- a/include/linux/atalk.h +++ b/include/linux/atalk.h @@ -161,16 +161,26 @@ extern int sysctl_aarp_resolve_time; extern int atalk_register_sysctl(void); extern void atalk_unregister_sysctl(void); #else -#define atalk_register_sysctl() do { } while(0) -#define atalk_unregister_sysctl() do { } while(0) +static inline int atalk_register_sysctl(void) +{ + return 0; +} +static inline void atalk_unregister_sysctl(void) +{ +} #endif #ifdef CONFIG_PROC_FS extern int atalk_proc_init(void); extern void atalk_proc_exit(void); #else -#define atalk_proc_init() ({ 0; }) -#define atalk_proc_exit() do { } while(0) +static inline int atalk_proc_init(void) +{ + return 0; +} +static inline void atalk_proc_exit(void) +{ +} #endif /* CONFIG_PROC_FS */ #endif /* __LINUX_ATALK_H__ */ From 7b8376237618e4ddbf71277c8da6b2e0c57f0f70 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 6 Mar 2019 11:52:37 +0100 Subject: [PATCH 07/72] appletalk: Add atalk.h header files to MAINTAINERS file Add the path names here so that git-send-email can pick up the netdev@vger.kernel.org Cc line automatically for a patch that only touches the headers. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index fbbb96236d98..f470eb4aeb21 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1034,6 +1034,8 @@ L: netdev@vger.kernel.org S: Odd fixes F: drivers/net/appletalk/ F: net/appletalk/ +F: include/linux/atalk.h +F: include/uapi/linux/atalk.h APPLIED MICRO (APM) X-GENE DEVICE TREE SUPPORT M: Duc Dang From a10674bf2406afc2554f9c7d31b2dc65d6a27fd9 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Wed, 6 Mar 2019 14:10:22 +0300 Subject: [PATCH 08/72] tcp: detecting the misuse of .sendpage for Slab objects sendpage was not designed for processing of the Slab pages, in some situations it can trigger BUG_ON on receiving side. Signed-off-by: Vasily Averin Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ad07dd71063d..dbb08140cdc9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -943,6 +943,10 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, ssize_t copied; long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); + if (IS_ENABLED(CONFIG_DEBUG_VM) && + WARN_ONCE(PageSlab(page), "page must not be a Slab one")) + return -EINVAL; + /* Wait for a connection to finish. One exception is TCP Fast Open * (passive side) where data is allowed to be sent before a connection * is fully established. From ecb3dea400d3beaf611ce76ac7a51d4230492cf2 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Wed, 6 Mar 2019 16:22:12 +0200 Subject: [PATCH 09/72] net: sched: flower: insert new filter to idr after setting its mask When adding new filter to flower classifier, fl_change() inserts it to handle_idr before initializing filter extensions and assigning it a mask. Normally this ordering doesn't matter because all flower classifier ops callbacks assume rtnl lock protection. However, when filter has an action that doesn't have its kernel module loaded, rtnl lock is released before call to request_module(). During this time the filter can be accessed bu concurrent task before its initialization is completed, which can lead to a crash. Example case of NULL pointer dereference in concurrent dump: Task 1 Task 2 tc_new_tfilter() fl_change() idr_alloc_u32(fnew) fl_set_parms() tcf_exts_validate() tcf_action_init() tcf_action_init_1() rtnl_unlock() request_module() ... rtnl_lock() tc_dump_tfilter() tcf_chain_dump() fl_walk() idr_get_next_ul() tcf_node_dump() tcf_fill_node() fl_dump() mask = &f->mask->key; <- NULL ptr rtnl_lock() Extension initialization and mask assignment don't depend on fnew->handle that is allocated by idr_alloc_u32(). Move idr allocation code after action creation and mask assignment in fl_change() to prevent concurrent access to not fully initialized filter when rtnl lock is released to load action module. Fixes: 01683a146999 ("net: sched: refactor flower walk to iterate over idr") Signed-off-by: Vlad Buslov Reviewed-by: Roi Dayan Signed-off-by: David S. Miller --- net/sched/cls_flower.c | 49 +++++++++++++++++++++--------------------- 1 file changed, 25 insertions(+), 24 deletions(-) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 27300a3e76c7..c04247b403ed 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1348,6 +1348,24 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout; + if (tb[TCA_FLOWER_FLAGS]) { + fnew->flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]); + + if (!tc_flags_valid(fnew->flags)) { + err = -EINVAL; + goto errout; + } + } + + err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], ovr, + tp->chain->tmplt_priv, extack); + if (err) + goto errout; + + err = fl_check_assign_mask(head, fnew, fold, mask); + if (err) + goto errout; + if (!handle) { handle = 1; err = idr_alloc_u32(&head->handle_idr, fnew, &handle, @@ -1358,36 +1376,18 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, handle, GFP_KERNEL); } if (err) - goto errout; + goto errout_mask; fnew->handle = handle; - if (tb[TCA_FLOWER_FLAGS]) { - fnew->flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]); - - if (!tc_flags_valid(fnew->flags)) { - err = -EINVAL; - goto errout_idr; - } - } - - err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], ovr, - tp->chain->tmplt_priv, extack); - if (err) - goto errout_idr; - - err = fl_check_assign_mask(head, fnew, fold, mask); - if (err) - goto errout_idr; - if (!fold && __fl_lookup(fnew->mask, &fnew->mkey)) { err = -EEXIST; - goto errout_mask; + goto errout_idr; } err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node, fnew->mask->filter_ht_params); if (err) - goto errout_mask; + goto errout_idr; if (!tc_skip_hw(fnew->flags)) { err = fl_hw_replace_filter(tp, fnew, extack); @@ -1426,12 +1426,13 @@ errout_mask_ht: rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node, fnew->mask->filter_ht_params); -errout_mask: - fl_mask_put(head, fnew->mask, false); - errout_idr: if (!fold) idr_remove(&head->handle_idr, fnew->handle); + +errout_mask: + fl_mask_put(head, fnew->mask, false); + errout: tcf_exts_destroy(&fnew->exts); kfree(fnew); From 6caabe7f197d3466d238f70915d65301f1716626 Mon Sep 17 00:00:00 2001 From: Mao Wenan Date: Wed, 6 Mar 2019 22:45:01 +0800 Subject: [PATCH 10/72] net: hsr: fix memory leak in hsr_dev_finalize() If hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER) failed to add port, it directly returns res and forgets to free the node that allocated in hsr_create_self_node(), and forgets to delete the node->mac_list linked in hsr->self_node_db. BUG: memory leak unreferenced object 0xffff8881cfa0c780 (size 64): comm "syz-executor.0", pid 2077, jiffies 4294717969 (age 2415.377s) hex dump (first 32 bytes): e0 c7 a0 cf 81 88 ff ff 00 02 00 00 00 00 ad de ................ 00 e6 49 cd 81 88 ff ff c0 9b 87 d0 81 88 ff ff ..I............. backtrace: [<00000000e2ff5070>] hsr_dev_finalize+0x736/0x960 [hsr] [<000000003ed2e597>] hsr_newlink+0x2b2/0x3e0 [hsr] [<000000003fa8c6b6>] __rtnl_newlink+0xf1f/0x1600 net/core/rtnetlink.c:3182 [<000000001247a7ad>] rtnl_newlink+0x66/0x90 net/core/rtnetlink.c:3240 [<00000000e7d1b61d>] rtnetlink_rcv_msg+0x54e/0xb90 net/core/rtnetlink.c:5130 [<000000005556bd3a>] netlink_rcv_skb+0x129/0x340 net/netlink/af_netlink.c:2477 [<00000000741d5ee6>] netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline] [<00000000741d5ee6>] netlink_unicast+0x49a/0x650 net/netlink/af_netlink.c:1336 [<000000009d56f9b7>] netlink_sendmsg+0x88b/0xdf0 net/netlink/af_netlink.c:1917 [<0000000046b35c59>] sock_sendmsg_nosec net/socket.c:621 [inline] [<0000000046b35c59>] sock_sendmsg+0xc3/0x100 net/socket.c:631 [<00000000d208adc9>] __sys_sendto+0x33e/0x560 net/socket.c:1786 [<00000000b582837a>] __do_sys_sendto net/socket.c:1798 [inline] [<00000000b582837a>] __se_sys_sendto net/socket.c:1794 [inline] [<00000000b582837a>] __x64_sys_sendto+0xdd/0x1b0 net/socket.c:1794 [<00000000c866801d>] do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290 [<00000000fea382d9>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<00000000e01dacb3>] 0xffffffffffffffff Fixes: c5a759117210 ("net/hsr: Use list_head (and rcu) instead of array for slave devices.") Reported-by: Hulk Robot Signed-off-by: Mao Wenan Signed-off-by: David S. Miller --- net/hsr/hsr_device.c | 4 +++- net/hsr/hsr_framereg.c | 12 ++++++++++++ net/hsr/hsr_framereg.h | 1 + 3 files changed, 16 insertions(+), 1 deletion(-) diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index b8cd43c9ed5b..c4676bacb8db 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -486,7 +486,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER); if (res) - return res; + goto err_add_port; res = register_netdevice(hsr_dev); if (res) @@ -506,6 +506,8 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], fail: hsr_for_each_port(hsr, port) hsr_del_port(port); +err_add_port: + hsr_del_node(&hsr->self_node_db); return res; } diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 286ceb41ac0c..9af16cb68f76 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -124,6 +124,18 @@ int hsr_create_self_node(struct list_head *self_node_db, return 0; } +void hsr_del_node(struct list_head *self_node_db) +{ + struct hsr_node *node; + + rcu_read_lock(); + node = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list); + rcu_read_unlock(); + if (node) { + list_del_rcu(&node->mac_list); + kfree(node); + } +} /* Allocate an hsr_node and add it to node_db. 'addr' is the node's AddressA; * seq_out is used to initialize filtering of outgoing duplicate frames diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index 370b45998121..531fd3dfcac1 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -16,6 +16,7 @@ struct hsr_node; +void hsr_del_node(struct list_head *self_node_db); struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[], u16 seq_out); struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, From 6466e715651f9f358e60c5ea4880e4731325827f Mon Sep 17 00:00:00 2001 From: Soheil Hassas Yeganeh Date: Wed, 6 Mar 2019 13:01:36 -0500 Subject: [PATCH 11/72] tcp: do not report TCP_CM_INQ of 0 for closed connections Returning 0 as inq to userspace indicates there is no more data to read, and the application needs to wait for EPOLLIN. For a connection that has received FIN from the remote peer, however, the application must continue reading until getting EOF (return value of 0 from tcp_recvmsg) or an error, if edge-triggered epoll (EPOLLET) is being used. Otherwise, the application will never receive a new EPOLLIN, since there is no epoll edge after the FIN. Return 1 when there is no data left on the queue but the connection has received FIN, so that the applications continue reading. Fixes: b75eba76d3d72 (tcp: send in-queue bytes in cmsg upon read) Signed-off-by: Soheil Hassas Yeganeh Acked-by: Neal Cardwell Signed-off-by: Eric Dumazet Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index dbb08140cdc9..6baa6dc1b13b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1937,6 +1937,11 @@ static int tcp_inq_hint(struct sock *sk) inq = tp->rcv_nxt - tp->copied_seq; release_sock(sk); } + /* After receiving a FIN, tell the user-space to continue reading + * by returning a non-zero inq. + */ + if (inq == 0 && sock_flag(sk, SOCK_DONE)) + inq = 1; return inq; } From 78c3aff834f7939d1a2570e366e33f2a880d4d9e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 4 Mar 2019 21:34:12 +0100 Subject: [PATCH 12/72] bpf: fix sysctl.c warning When CONFIG_BPF_SYSCALL or CONFIG_SYSCTL is disabled, we get a warning about an unused function: kernel/sysctl.c:3331:12: error: 'proc_dointvec_minmax_bpf_stats' defined but not used [-Werror=unused-function] static int proc_dointvec_minmax_bpf_stats(struct ctl_table *table, int write, The CONFIG_BPF_SYSCALL check was already handled, but the SYSCTL check is needed on top. Fixes: 492ecee892c2 ("bpf: enable program stats") Signed-off-by: Arnd Bergmann Reviewed-by: Kees Cook Reviewed-by: Christian Brauner Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- kernel/sysctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 7578e21a711b..2322b12cb4cf 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -3274,7 +3274,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, #endif /* CONFIG_PROC_SYSCTL */ -#ifdef CONFIG_BPF_SYSCALL +#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_SYSCTL) static int proc_dointvec_minmax_bpf_stats(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) From 4c3024debf62de4c6ac6d3cb4c0063be21d4f652 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 6 Mar 2019 14:35:15 -0500 Subject: [PATCH 13/72] bpf: only test gso type on gso packets BPF can adjust gso only for tcp bytestreams. Fail on other gso types. But only on gso packets. It does not touch this field if !gso_size. Fixes: b90efd225874 ("bpf: only adjust gso_size on bytestream protocols") Signed-off-by: Willem de Bruijn Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann --- include/linux/skbuff.h | 4 ++-- net/core/filter.c | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 27beb549ffbe..f32f32407dc4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4232,10 +4232,10 @@ static inline bool skb_is_gso_sctp(const struct sk_buff *skb) return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP; } +/* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_tcp(const struct sk_buff *skb) { - return skb_is_gso(skb) && - skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6); + return skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6); } static inline void skb_gso_reset(struct sk_buff *skb) diff --git a/net/core/filter.c b/net/core/filter.c index 5ceba98069d4..f274620945ff 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2804,7 +2804,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - if (!skb_is_gso_tcp(skb)) + if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_cow(skb, len_diff); @@ -2845,7 +2845,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - if (!skb_is_gso_tcp(skb)) + if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_unclone(skb, GFP_ATOMIC); @@ -2970,7 +2970,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; - if (!skb_is_gso_tcp(skb)) + if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_cow(skb, len_diff); @@ -2999,7 +2999,7 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; - if (!skb_is_gso_tcp(skb)) + if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_unclone(skb, GFP_ATOMIC); From 5b4f21b2a5c4f41de3e49eef66d2fa566f23971a Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 5 Mar 2019 17:31:13 +0000 Subject: [PATCH 14/72] bpf: hbm: fix spelling mistake "deault" -> "default" There are a couple of typos, fix these. Signed-off-by: Colin Ian King Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- samples/bpf/hbm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c index 8408ccb7409f..a79828ab273f 100644 --- a/samples/bpf/hbm.c +++ b/samples/bpf/hbm.c @@ -18,7 +18,7 @@ * Default is /hbm1 * -r Rate limit in Mbps * -s Get HBM stats (marked, dropped, etc.) - * -t