From 68fda450a7df51cff9e5a4d4a4d9d0d5f2589153 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 12 Jan 2018 18:59:52 -0800 Subject: bpf: fix 32-bit divide by zero due to some JITs doing if (src_reg == 0) check in 64-bit mode for div/mod operations mask upper 32-bits of src register before doing the check Fixes: 622582786c9e ("net: filter: x86: internal BPF JIT") Fixes: 7a12b5031c6b ("sparc64: Add eBPF JIT.") Reported-by: syzbot+48340bb518e88849e2e3@syzkaller.appspotmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- net/core/filter.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/core/filter.c b/net/core/filter.c index d339ef170df6..1c0eb436671f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -458,6 +458,10 @@ do_pass: convert_bpf_extensions(fp, &insn)) break; + if (fp->code == (BPF_ALU | BPF_DIV | BPF_X) || + fp->code == (BPF_ALU | BPF_MOD | BPF_X)) + *insn++ = BPF_MOV32_REG(BPF_REG_X, BPF_REG_X); + *insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k); break; -- cgit v1.2.3 From d91c3e17f75f218022140dee18cf515292184a8f Mon Sep 17 00:00:00 2001 From: Ilya Lesokhin Date: Tue, 16 Jan 2018 15:31:52 +0200 Subject: net/tls: Only attach to sockets in ESTABLISHED state Calling accept on a TCP socket with a TLS ulp attached results in two sockets that share the same ulp context. The ulp context is freed while a socket is destroyed, so after one of the sockets is released, the second second will trigger a use after free when it tries to access the ulp context attached to it. We restrict the TLS ulp to sockets in ESTABLISHED state to prevent the scenario above. Fixes: 3c4d7559159b ("tls: kernel TLS support") Reported-by: syzbot+904e7cd6c5c741609228@syzkaller.appspotmail.com Signed-off-by: Ilya Lesokhin Signed-off-by: David S. Miller --- net/tls/tls_main.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'net') diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index e07ee3ae0023..7b7a70e22d90 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -454,6 +454,15 @@ static int tls_init(struct sock *sk) struct tls_context *ctx; int rc = 0; + /* The TLS ulp is currently supported only for TCP sockets + * in ESTABLISHED state. + * Supporting sockets in LISTEN state will require us + * to modify the accept implementation to clone rather then + * share the ulp context. + */ + if (sk->sk_state != TCP_ESTABLISHED) + return -ENOTSUPP; + /* allocate tls context */ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) { -- cgit v1.2.3 From cf6d43ef66f416282121f436ce1bee9a25199d52 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 16 Jan 2018 16:04:26 +0100 Subject: tls: fix sw_ctx leak During setsockopt(SOL_TCP, TLS_TX), if initialization of the software context fails in tls_set_sw_offload(), we leak sw_ctx. We also don't reassign ctx->priv_ctx to NULL, so we can't even do another attempt to set it up on the same socket, as it will fail with -EEXIST. Fixes: 3c4d7559159b ('tls: kernel TLS support') Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller --- net/tls/tls_sw.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 9773571b6a34..61f394d369bf 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -681,18 +681,17 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx) } default: rc = -EINVAL; - goto out; + goto free_priv; } ctx->prepend_size = TLS_HEADER_SIZE + nonce_size; ctx->tag_size = tag_size; ctx->overhead_size = ctx->prepend_size + ctx->tag_size; ctx->iv_size = iv_size; - ctx->iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE, - GFP_KERNEL); + ctx->iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE, GFP_KERNEL); if (!ctx->iv) { rc = -ENOMEM; - goto out; + goto free_priv; } memcpy(ctx->iv, gcm_128_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); memcpy(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size); @@ -740,7 +739,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx) rc = crypto_aead_setauthsize(sw_ctx->aead_send, ctx->tag_size); if (!rc) - goto out; + return 0; free_aead: crypto_free_aead(sw_ctx->aead_send); @@ -751,6 +750,9 @@ free_rec_seq: free_iv: kfree(ctx->iv); ctx->iv = NULL; +free_priv: + kfree(ctx->priv_ctx); + ctx->priv_ctx = NULL; out: return rc; } -- cgit v1.2.3 From 877d17c79b66466942a836403773276e34fe3614 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 16 Jan 2018 16:04:27 +0100 Subject: tls: return -EBUSY if crypto_info is already set do_tls_setsockopt_tx returns 0 without doing anything when crypto_info is already set. Silent failure is confusing for users. Fixes: 3c4d7559159b ("tls: kernel TLS support") Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller --- net/tls/tls_main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 7b7a70e22d90..8e9cbfd21423 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -367,8 +367,10 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval, crypto_info = &ctx->crypto_send; /* Currently we don't support set crypto info more than one time */ - if (TLS_CRYPTO_INFO_READY(crypto_info)) + if (TLS_CRYPTO_INFO_READY(crypto_info)) { + rc = -EBUSY; goto out; + } rc = copy_from_user(crypto_info, optval, sizeof(*crypto_info)); if (rc) { -- cgit v1.2.3 From 6db959c82eb039a151d95a0f8b7dea643657327a Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 16 Jan 2018 16:04:28 +0100 Subject: tls: reset crypto_info when do_tls_setsockopt_tx fails The current code copies directly from userspace to ctx->crypto_send, but doesn't always reinitialize it to 0 on failure. This causes any subsequent attempt to use this setsockopt to fail because of the TLS_CRYPTO_INFO_READY check, eventhough crypto_info is not actually ready. This should result in a correctly set up socket after the 3rd call, but currently it does not: size_t s = sizeof(struct tls12_crypto_info_aes_gcm_128); struct tls12_crypto_info_aes_gcm_128 crypto_good = { .info.version = TLS_1_2_VERSION, .info.cipher_type = TLS_CIPHER_AES_GCM_128, }; struct tls12_crypto_info_aes_gcm_128 crypto_bad_type = crypto_good; crypto_bad_type.info.cipher_type = 42; setsockopt(sock, SOL_TLS, TLS_TX, &crypto_bad_type, s); setsockopt(sock, SOL_TLS, TLS_TX, &crypto_good, s - 1); setsockopt(sock, SOL_TLS, TLS_TX, &crypto_good, s); Fixes: 3c4d7559159b ("tls: kernel TLS support") Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller --- net/tls/tls_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 8e9cbfd21423..736719c8314e 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -388,7 +388,7 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval, case TLS_CIPHER_AES_GCM_128: { if (optlen != sizeof(struct tls12_crypto_info_aes_gcm_128)) { rc = -EINVAL; - goto out; + goto err_crypto_info; } rc = copy_from_user(crypto_info + 1, optval + sizeof(*crypto_info), optlen - sizeof(*crypto_info)); @@ -400,7 +400,7 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval, } default: rc = -EINVAL; - goto out; + goto err_crypto_info; } /* currently SW is default, we will have ethtool in future */ -- cgit v1.2.3 From ad9294dbc227cbc8e173b3b963e7dd9af5314f77 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 17 Jan 2018 22:36:49 +0100 Subject: bpf: fix cls_bpf on filter replace Running the following sequence is currently broken: # tc qdisc add dev foo clsact # tc filter replace dev foo ingress prio 1 handle 1 bpf da obj bar.o # tc filter replace dev foo ingress prio 1 handle 1 bpf da obj bar.o RTNETLINK answers: Invalid argument The normal expectation on kernel side is that the second command succeeds replacing the existing program. However, what happens is in cls_bpf_change(), we bail out with err in the second run in cls_bpf_offload(). The EINVAL comes directly in cls_bpf_offload() when comparing prog vs oldprog's gen_flags. In case of above replace the new prog's gen_flags are 0, but the old ones are 8, which means TCA_CLS_FLAGS_NOT_IN_HW is set (e.g. drivers not having cls_bpf offload). Fix 102740bd9436 ("cls_bpf: fix offload assumptions after callback conversion") in the following way: gen_flags from user space passed down via netlink cannot include status flags like TCA_CLS_FLAGS_IN_HW or TCA_CLS_FLAGS_NOT_IN_HW as opposed to oldprog that we previously loaded. Therefore, it doesn't make any sense to include them in the gen_flags comparison with the new prog before we even attempt to offload. Thus, lets fix this before 4.15 goes out. Fixes: 102740bd9436 ("cls_bpf: fix offload assumptions after callback conversion") Signed-off-by: Daniel Borkmann Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- net/sched/cls_bpf.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 8d78e7f4ecc3..a62586e2dbdb 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -183,10 +183,17 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, return 0; } +static u32 cls_bpf_flags(u32 flags) +{ + return flags & CLS_BPF_SUPPORTED_GEN_FLAGS; +} + static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, struct cls_bpf_prog *oldprog) { - if (prog && oldprog && prog->gen_flags != oldprog->gen_flags) + if (prog && oldprog && + cls_bpf_flags(prog->gen_flags) != + cls_bpf_flags(oldprog->gen_flags)) return -EINVAL; if (prog && tc_skip_hw(prog->gen_flags)) -- cgit v1.2.3 From 8cb68751c115d176ec851ca56ecfbb411568c9e8 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Tue, 16 Jan 2018 19:30:14 +0100 Subject: can: af_can: can_rcv(): replace WARN_ONCE by pr_warn_once If an invalid CAN frame is received, from a driver or from a tun interface, a Kernel warning is generated. This patch replaces the WARN_ONCE by a simple pr_warn_once, so that a kernel, bootet with panic_on_warn, does not panic. A printk seems to be more appropriate here. Reported-by: syzbot+4386709c0c1284dca827@syzkaller.appspotmail.com Suggested-by: Dmitry Vyukov Acked-by: Oliver Hartkopp Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- net/can/af_can.c | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-) (limited to 'net') diff --git a/net/can/af_can.c b/net/can/af_can.c index 003b2d6d655f..ae835382e678 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -721,20 +721,16 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - if (WARN_ONCE(dev->type != ARPHRD_CAN || - skb->len != CAN_MTU || - cfd->len > CAN_MAX_DLEN, - "PF_CAN: dropped non conform CAN skbuf: " - "dev type %d, len %d, datalen %d\n", - dev->type, skb->len, cfd->len)) - goto drop; + if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU || + cfd->len > CAN_MAX_DLEN)) { + pr_warn_once("PF_CAN: dropped non conform CAN skbuf: dev type %d, len %d, datalen %d\n", + dev->type, skb->len, cfd->len); + kfree_skb(skb); + return NET_RX_DROP; + } can_receive(skb, dev); return NET_RX_SUCCESS; - -drop: - kfree_skb(skb); - return NET_RX_DROP; } static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, -- cgit v1.2.3 From d4689846881d160a4d12a514e991a740bcb5d65a Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Tue, 16 Jan 2018 19:30:14 +0100 Subject: can: af_can: canfd_rcv(): replace WARN_ONCE by pr_warn_once If an invalid CANFD frame is received, from a driver or from a tun interface, a Kernel warning is generated. This patch replaces the WARN_ONCE by a simple pr_warn_once, so that a kernel, bootet with panic_on_warn, does not panic. A printk seems to be more appropriate here. Reported-by: syzbot+e3b775f40babeff6e68b@syzkaller.appspotmail.com Suggested-by: Dmitry Vyukov Acked-by: Oliver Hartkopp Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- net/can/af_can.c | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-) (limited to 'net') diff --git a/net/can/af_can.c b/net/can/af_can.c index ae835382e678..4d7f988a3130 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -738,20 +738,16 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - if (WARN_ONCE(dev->type != ARPHRD_CAN || - skb->len != CANFD_MTU || - cfd->len > CANFD_MAX_DLEN, - "PF_CAN: dropped non conform CAN FD skbuf: " - "dev type %d, len %d, datalen %d\n", - dev->type, skb->len, cfd->len)) - goto drop; + if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU || + cfd->len > CANFD_MAX_DLEN)) { + pr_warn_once("PF_CAN: dropped non conform CAN FD skbuf: dev type %d, len %d, datalen %d\n", + dev->type, skb->len, cfd->len); + kfree_skb(skb); + return NET_RX_DROP; + } can_receive(skb, dev); return NET_RX_SUCCESS; - -drop: - kfree_skb(skb); - return NET_RX_DROP; } /* -- cgit v1.2.3 From cd443f1e91ca600a092e780e8250cd6a2954b763 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 18 Jan 2018 14:48:03 +0800 Subject: netlink: reset extack earlier in netlink_rcv_skb Move up the extack reset/initialization in netlink_rcv_skb, so that those 'goto ack' will not skip it. Otherwise, later on netlink_ack may use the uninitialized extack and cause kernel crash. Fixes: cbbdf8433a5f ("netlink: extack needs to be reset each time through loop") Reported-by: syzbot+03bee3680a37466775e7@syzkaller.appspotmail.com Signed-off-by: Xin Long Acked-by: David Ahern Signed-off-by: David S. Miller --- net/netlink/af_netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 47ef2d8683d6..84a4e4c3be4b 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2391,6 +2391,7 @@ int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, while (skb->len >= nlmsg_total_size(0)) { int msglen; + memset(&extack, 0, sizeof(extack)); nlh = nlmsg_hdr(skb); err = 0; @@ -2405,7 +2406,6 @@ int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, if (nlh->nlmsg_type < NLMSG_MIN_TYPE) goto ack; - memset(&extack, 0, sizeof(extack)); err = cb(skb, nlh, &extack); if (err == -EINTR) goto skip; -- cgit v1.2.3 From 5762d7d3eda25c03cc2d9d45227be3f5ab6bec9e Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 16 Jan 2018 23:20:22 +0100 Subject: cfg80211: fix station info handling bugs Fix two places where the structure isn't initialized to zero, and thus can't be filled properly by the driver. Fixes: 4a4b8169501b ("cfg80211: Accept multiple RSSI thresholds for CQM") Fixes: 9930380f0bd8 ("cfg80211: implement IWRATE") Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- net/wireless/nl80211.c | 2 +- net/wireless/wext-compat.c | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ed87a97fcb0b..542a4fc0a8d7 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -9809,7 +9809,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, */ if (!wdev->cqm_config->last_rssi_event_value && wdev->current_bss && rdev->ops->get_station) { - struct station_info sinfo; + struct station_info sinfo = {}; u8 *mac_addr; mac_addr = wdev->current_bss->pub.bssid; diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 7ca04a7de85a..05186a47878f 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -1254,8 +1254,7 @@ static int cfg80211_wext_giwrate(struct net_device *dev, { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - /* we are under RTNL - globally locked - so can use a static struct */ - static struct station_info sinfo; + struct station_info sinfo = {}; u8 addr[ETH_ALEN]; int err; -- cgit v1.2.3 From d0c081b49137cd3200f2023c0875723be66e7ce5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 17 Jan 2018 14:21:13 -0800 Subject: flow_dissector: properly cap thoff field syzbot reported yet another crash [1] that is caused by insufficient validation of DODGY packets. Two bugs are happening here to trigger the crash. 1) Flow dissection leaves with incorrect thoff field. 2) skb_probe_transport_header() sets transport header to this invalid thoff, even if pointing after skb valid data. 3) qdisc_pkt_len_init() reads out-of-bound data because it trusts tcp_hdrlen(skb) Possible fixes : - Full flow dissector validation before injecting bad DODGY packets in the stack. This approach was attempted here : https://patchwork.ozlabs.org/patch/ 861874/ - Have more robust functions in the core. This might be needed anyway for stable versions. This patch fixes the flow dissection issue. [1] CPU: 1 PID: 3144 Comm: syzkaller271204 Not tainted 4.15.0-rc4-mm1+ #49 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:53 print_address_description+0x73/0x250 mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:355 [inline] kasan_report+0x23b/0x360 mm/kasan/report.c:413 __asan_report_load2_noabort+0x14/0x20 mm/kasan/report.c:432 __tcp_hdrlen include/linux/tcp.h:35 [inline] tcp_hdrlen include/linux/tcp.h:40 [inline] qdisc_pkt_len_init net/core/dev.c:3160 [inline] __dev_queue_xmit+0x20d3/0x2200 net/core/dev.c:3465 dev_queue_xmit+0x17/0x20 net/core/dev.c:3554 packet_snd net/packet/af_packet.c:2943 [inline] packet_sendmsg+0x3ad5/0x60a0 net/packet/af_packet.c:2968 sock_sendmsg_nosec net/socket.c:628 [inline] sock_sendmsg+0xca/0x110 net/socket.c:638 sock_write_iter+0x31a/0x5d0 net/socket.c:907 call_write_iter include/linux/fs.h:1776 [inline] new_sync_write fs/read_write.c:469 [inline] __vfs_write+0x684/0x970 fs/read_write.c:482 vfs_write+0x189/0x510 fs/read_write.c:544 SYSC_write fs/read_write.c:589 [inline] SyS_write+0xef/0x220 fs/read_write.c:581 entry_SYSCALL_64_fastpath+0x1f/0x96 Fixes: 34fad54c2537 ("net: __skb_flow_dissect() must cap its return value") Fixes: a6e544b0a88b ("flow_dissector: Jump to exit code in __skb_flow_dissect") Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Reported-by: syzbot Acked-by: Jason Wang Signed-off-by: David S. Miller --- net/core/flow_dissector.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net') diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 15ce30063765..544bddf08e13 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -976,8 +976,8 @@ ip_proto_again: out_good: ret = true; - key_control->thoff = (u16)nhoff; out: + key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen); key_basic->n_proto = proto; key_basic->ip_proto = ip_proto; @@ -985,7 +985,6 @@ out: out_bad: ret = false; - key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen); goto out; } EXPORT_SYMBOL(__skb_flow_dissect); -- cgit v1.2.3 From 128bb975dc3c25d00de04e503e2fe0a780d04459 Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Thu, 18 Jan 2018 20:51:12 +0300 Subject: ip6_gre: init dev->mtu and dev->hard_header_len correctly Commit b05229f44228 ("gre6: Cleanup GREv6 transmit path, call common GRE functions") moved dev->mtu initialization from ip6gre_tunnel_setup() to ip6gre_tunnel_init(), as a result, the previously set values, before ndo_init(), are reset in the following cases: * rtnl_create_link() can update dev->mtu from IFLA_MTU parameter. * ip6gre_tnl_link_config() is invoked before ndo_init() in netlink and ioctl setup, so ndo_init() can reset MTU adjustments with the lower device MTU as well, dev->mtu and dev->hard_header_len. Not applicable for ip6gretap because it has one more call to ip6gre_tnl_link_config(tunnel, 1) in ip6gre_tap_init(). Fix the first case by updating dev->mtu with 'tb[IFLA_MTU]' parameter if a user sets it manually on a device creation, and fix the second one by moving ip6gre_tnl_link_config() call after register_netdevice(). Fixes: b05229f44228 ("gre6: Cleanup GREv6 transmit path, call common GRE functions") Fixes: db2ec95d1ba4 ("ip6_gre: Fix MTU setting") Signed-off-by: Alexey Kodanev Signed-off-by: David S. Miller --- net/ipv6/ip6_gre.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'net') diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 772695960890..873549228ccb 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -337,11 +337,12 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net, nt->dev = dev; nt->net = dev_net(dev); - ip6gre_tnl_link_config(nt, 1); if (register_netdevice(dev) < 0) goto failed_free; + ip6gre_tnl_link_config(nt, 1); + /* Can use a lockless transmit, unless we generate output sequences */ if (!(nt->parms.o_flags & TUNNEL_SEQ)) dev->features |= NETIF_F_LLTX; @@ -1303,7 +1304,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[], static int ip6gre_tap_init(struct net_device *dev) { - struct ip6_tnl *tunnel; int ret; ret = ip6gre_tunnel_init_common(dev); @@ -1312,10 +1312,6 @@ static int ip6gre_tap_init(struct net_device *dev) dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; - tunnel = netdev_priv(dev); - - ip6gre_tnl_link_config(tunnel, 1); - return 0; } @@ -1408,12 +1404,16 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev, nt->dev = dev; nt->net = dev_net(dev); - ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]); err = register_netdevice(dev); if (err) goto out; + ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]); + + if (tb[IFLA_MTU]) + ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); + dev_hold(dev); ip6gre_tunnel_link(ign, nt); -- cgit v1.2.3 From 591ff9ea51cec683e4cb378a3469228ba1d69010 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Thu, 18 Jan 2018 10:40:03 -0800 Subject: ipv6: don't let tb6_root node share routes with other node After commit 4512c43eac7e, if we add a route to the subtree of tb6_root which does not have any route attached to it yet, the current code will let tb6_root and the node in the subtree share the same route. This could cause problem cause tb6_root has RTN_INFO flag marked and the tree repair and clean up code will not work properly. This commit makes sure tb6_root->leaf points back to null_entry instead of sharing route with other node. It fixes the following syzkaller reported issue: BUG: KASAN: use-after-free in ipv6_prefix_equal include/net/ipv6.h:540 [inline] BUG: KASAN: use-after-free in fib6_add_1+0x165f/0x1790 net/ipv6/ip6_fib.c:618 Read of size 8 at addr ffff8801bc043498 by task syz-executor5/19819 CPU: 1 PID: 19819 Comm: syz-executor5 Not tainted 4.15.0-rc7+ #186 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:53 print_address_description+0x73/0x250 mm/kasan/report.c:252 kasan_report_error mm/kasan/report.c:351 [inline] kasan_report+0x25b/0x340 mm/kasan/report.c:409 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:430 ipv6_prefix_equal include/net/ipv6.h:540 [inline] fib6_add_1+0x165f/0x1790 net/ipv6/ip6_fib.c:618 fib6_add+0x5fa/0x1540 net/ipv6/ip6_fib.c:1214 __ip6_ins_rt+0x6c/0x90 net/ipv6/route.c:1003 ip6_route_add+0x141/0x190 net/ipv6/route.c:2790 ipv6_route_ioctl+0x4db/0x6b0 net/ipv6/route.c:3299 inet6_ioctl+0xef/0x1e0 net/ipv6/af_inet6.c:520 sock_do_ioctl+0x65/0xb0 net/socket.c:958 sock_ioctl+0x2c2/0x440 net/socket.c:1055 vfs_ioctl fs/ioctl.c:46 [inline] do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:686 SYSC_ioctl fs/ioctl.c:701 [inline] SyS_ioctl+0x8f/0xc0 fs/ioctl.c:692 entry_SYSCALL_64_fastpath+0x23/0x9a RIP: 0033:0x452ac9 RSP: 002b:00007fd42b321c58 EFLAGS: 00000212 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 000000000071bea0 RCX: 0000000000452ac9 RDX: 0000000020fd7000 RSI: 000000000000890b RDI: 0000000000000013 RBP: 000000000000049e R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000212 R12: 00000000006f4f70 R13: 00000000ffffffff R14: 00007fd42b3226d4 R15: 0000000000000000 Fixes: 4512c43eac7e ("ipv6: remove null_entry before adding default route") Signed-off-by: Wei Wang Acked-by: Eric Dumazet Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- net/ipv6/ip6_fib.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 9dcc3924a975..217683d40f12 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1226,8 +1226,14 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, } if (!rcu_access_pointer(fn->leaf)) { - atomic_inc(&rt->rt6i_ref); - rcu_assign_pointer(fn->leaf, rt); + if (fn->fn_flags & RTN_TL_ROOT) { + /* put back null_entry for root node */ + rcu_assign_pointer(fn->leaf, + info->nl_net->ipv6.ip6_null_entry); + } else { + atomic_inc(&rt->rt6i_ref); + rcu_assign_pointer(fn->leaf, rt); + } } fn = sn; } -- cgit v1.2.3