From: Greg Kroah-Hartman Date: Tue, 21 Nov 2017 12:40:23 +0000 (+0100) Subject: 4.9-stable patches X-Git-Tag: v3.18.84~25 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=5511c0313e9bdef1c32bac4a21c83ef8ec0b05fe;p=thirdparty%2Fkernel%2Fstable-queue.git 4.9-stable patches added patches: af_netlink-ensure-that-nlmsg_done-never-fails-in-dumps.patch bonding-discard-lowest-hash-bit-for-802.3ad-layer3-4.patch fealnx-fix-building-error-on-mips.patch net-cdc_ether-fix-divide-by-0-on-bad-descriptors.patch net-qmi_wwan-fix-divide-by-0-on-bad-descriptors.patch net-sctp-always-set-scope_id-in-sctp_inet6_skb_msgname.patch net-usb-asix-fill-null-ptr-deref-in-asix_suspend.patch net-vrf-correct-fra_l3mdev-encode-type.patch netfilter-ipvs-clear-ipvs_property-flag-when-skb-net-namespace-changed.patch qmi_wwan-add-missing-skb_reset_mac_header-call.patch sctp-do-not-peel-off-an-assoc-from-one-netns-to-another-one.patch tcp-do-not-mangle-skb-cb-in-tcp_make_synack.patch tcp_nv-fix-division-by-zero-in-tcpnv_acked.patch vlan-fix-a-use-after-free-in-vlan_device_event.patch --- diff --git a/queue-4.9/af_netlink-ensure-that-nlmsg_done-never-fails-in-dumps.patch b/queue-4.9/af_netlink-ensure-that-nlmsg_done-never-fails-in-dumps.patch new file mode 100644 index 00000000000..f4c992934f2 --- /dev/null +++ b/queue-4.9/af_netlink-ensure-that-nlmsg_done-never-fails-in-dumps.patch @@ -0,0 +1,114 @@ +From foo@baz Tue Nov 21 13:08:13 CET 2017 +From: "Jason A. Donenfeld" +Date: Thu, 9 Nov 2017 13:04:44 +0900 +Subject: af_netlink: ensure that NLMSG_DONE never fails in dumps + +From: "Jason A. Donenfeld" + + +[ Upstream commit 0642840b8bb008528dbdf929cec9f65ac4231ad0 ] + +The way people generally use netlink_dump is that they fill in the skb +as much as possible, breaking when nla_put returns an error. Then, they +get called again and start filling out the next skb, and again, and so +forth. The mechanism at work here is the ability for the iterative +dumping function to detect when the skb is filled up and not fill it +past the brim, waiting for a fresh skb for the rest of the data. + +However, if the attributes are small and nicely packed, it is possible +that a dump callback function successfully fills in attributes until the +skb is of size 4080 (libmnl's default page-sized receive buffer size). +The dump function completes, satisfied, and then, if it happens to be +that this is actually the last skb, and no further ones are to be sent, +then netlink_dump will add on the NLMSG_DONE part: + + nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI); + +It is very important that netlink_dump does this, of course. However, in +this example, that call to nlmsg_put_answer will fail, because the +previous filling by the dump function did not leave it enough room. And +how could it possibly have done so? All of the nla_put variety of +functions simply check to see if the skb has enough tailroom, +independent of the context it is in. + +In order to keep the important assumptions of all netlink dump users, it +is therefore important to give them an skb that has this end part of the +tail already reserved, so that the call to nlmsg_put_answer does not +fail. Otherwise, library authors are forced to find some bizarre sized +receive buffer that has a large modulo relative to the common sizes of +messages received, which is ugly and buggy. + +This patch thus saves the NLMSG_DONE for an additional message, for the +case that things are dangerously close to the brim. This requires +keeping track of the errno from ->dump() across calls. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/netlink/af_netlink.c | 17 +++++++++++------ + net/netlink/af_netlink.h | 1 + + 2 files changed, 12 insertions(+), 6 deletions(-) + +--- a/net/netlink/af_netlink.c ++++ b/net/netlink/af_netlink.c +@@ -2077,7 +2077,7 @@ static int netlink_dump(struct sock *sk) + struct sk_buff *skb = NULL; + struct nlmsghdr *nlh; + struct module *module; +- int len, err = -ENOBUFS; ++ int err = -ENOBUFS; + int alloc_min_size; + int alloc_size; + +@@ -2124,9 +2124,11 @@ static int netlink_dump(struct sock *sk) + skb_reserve(skb, skb_tailroom(skb) - alloc_size); + netlink_skb_set_owner_r(skb, sk); + +- len = cb->dump(skb, cb); ++ if (nlk->dump_done_errno > 0) ++ nlk->dump_done_errno = cb->dump(skb, cb); + +- if (len > 0) { ++ if (nlk->dump_done_errno > 0 || ++ skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) { + mutex_unlock(nlk->cb_mutex); + + if (sk_filter(sk, skb)) +@@ -2136,13 +2138,15 @@ static int netlink_dump(struct sock *sk) + return 0; + } + +- nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI); +- if (!nlh) ++ nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, ++ sizeof(nlk->dump_done_errno), NLM_F_MULTI); ++ if (WARN_ON(!nlh)) + goto errout_skb; + + nl_dump_check_consistent(cb, nlh); + +- memcpy(nlmsg_data(nlh), &len, sizeof(len)); ++ memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, ++ sizeof(nlk->dump_done_errno)); + + if (sk_filter(sk, skb)) + kfree_skb(skb); +@@ -2214,6 +2218,7 @@ int __netlink_dump_start(struct sock *ss + } + + nlk->cb_running = true; ++ nlk->dump_done_errno = INT_MAX; + + mutex_unlock(nlk->cb_mutex); + +--- a/net/netlink/af_netlink.h ++++ b/net/netlink/af_netlink.h +@@ -24,6 +24,7 @@ struct netlink_sock { + wait_queue_head_t wait; + bool bound; + bool cb_running; ++ int dump_done_errno; + struct netlink_callback cb; + struct mutex *cb_mutex; + struct mutex cb_def_mutex; diff --git a/queue-4.9/bonding-discard-lowest-hash-bit-for-802.3ad-layer3-4.patch b/queue-4.9/bonding-discard-lowest-hash-bit-for-802.3ad-layer3-4.patch new file mode 100644 index 00000000000..cfd6bb3d8a5 --- /dev/null +++ b/queue-4.9/bonding-discard-lowest-hash-bit-for-802.3ad-layer3-4.patch @@ -0,0 +1,45 @@ +From foo@baz Tue Nov 21 13:08:13 CET 2017 +From: Hangbin Liu +Date: Mon, 6 Nov 2017 09:01:57 +0800 +Subject: bonding: discard lowest hash bit for 802.3ad layer3+4 + +From: Hangbin Liu + + +[ Upstream commit b5f862180d7011d9575d0499fa37f0f25b423b12 ] + +After commit 07f4c90062f8 ("tcp/dccp: try to not exhaust ip_local_port_range +in connect()"), we will try to use even ports for connect(). Then if an +application (seen clearly with iperf) opens multiple streams to the same +destination IP and port, each stream will be given an even source port. + +So the bonding driver's simple xmit_hash_policy based on layer3+4 addressing +will always hash all these streams to the same interface. And the total +throughput will limited to a single slave. + +Change the tcp code will impact the whole tcp behavior, only for bonding +usage. Paolo Abeni suggested fix this by changing the bonding code only, +which should be more reasonable, and less impact. + +Fix this by discarding the lowest hash bit because it contains little entropy. +After the fix we can re-balance between slaves. + +Signed-off-by: Paolo Abeni +Signed-off-by: Hangbin Liu +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/bonding/bond_main.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/net/bonding/bond_main.c ++++ b/drivers/net/bonding/bond_main.c +@@ -3217,7 +3217,7 @@ u32 bond_xmit_hash(struct bonding *bond, + hash ^= (hash >> 16); + hash ^= (hash >> 8); + +- return hash; ++ return hash >> 1; + } + + /*-------------------------- Device entry points ----------------------------*/ diff --git a/queue-4.9/fealnx-fix-building-error-on-mips.patch b/queue-4.9/fealnx-fix-building-error-on-mips.patch new file mode 100644 index 00000000000..fbd27655abf --- /dev/null +++ b/queue-4.9/fealnx-fix-building-error-on-mips.patch @@ -0,0 +1,43 @@ +From foo@baz Tue Nov 21 13:08:13 CET 2017 +From: Huacai Chen +Date: Thu, 16 Nov 2017 11:07:15 +0800 +Subject: fealnx: Fix building error on MIPS + +From: Huacai Chen + + +[ Upstream commit cc54c1d32e6a4bb3f116721abf900513173e4d02 ] + +This patch try to fix the building error on MIPS. The reason is MIPS +has already defined the LONG macro, which conflicts with the LONG enum +in drivers/net/ethernet/fealnx.c. + +Signed-off-by: Huacai Chen +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/fealnx.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +--- a/drivers/net/ethernet/fealnx.c ++++ b/drivers/net/ethernet/fealnx.c +@@ -257,8 +257,8 @@ enum rx_desc_status_bits { + RXFSD = 0x00000800, /* first descriptor */ + RXLSD = 0x00000400, /* last descriptor */ + ErrorSummary = 0x80, /* error summary */ +- RUNT = 0x40, /* runt packet received */ +- LONG = 0x20, /* long packet received */ ++ RUNTPKT = 0x40, /* runt packet received */ ++ LONGPKT = 0x20, /* long packet received */ + FAE = 0x10, /* frame align error */ + CRC = 0x08, /* crc error */ + RXER = 0x04, /* receive error */ +@@ -1633,7 +1633,7 @@ static int netdev_rx(struct net_device * + dev->name, rx_status); + + dev->stats.rx_errors++; /* end of a packet. */ +- if (rx_status & (LONG | RUNT)) ++ if (rx_status & (LONGPKT | RUNTPKT)) + dev->stats.rx_length_errors++; + if (rx_status & RXER) + dev->stats.rx_frame_errors++; diff --git a/queue-4.9/net-cdc_ether-fix-divide-by-0-on-bad-descriptors.patch b/queue-4.9/net-cdc_ether-fix-divide-by-0-on-bad-descriptors.patch new file mode 100644 index 00000000000..eb6585de1a2 --- /dev/null +++ b/queue-4.9/net-cdc_ether-fix-divide-by-0-on-bad-descriptors.patch @@ -0,0 +1,33 @@ +From foo@baz Tue Nov 21 13:08:13 CET 2017 +From: Bjørn Mork +Date: Mon, 6 Nov 2017 15:37:22 +0100 +Subject: net: cdc_ether: fix divide by 0 on bad descriptors + +From: Bjørn Mork + + +[ Upstream commit 2cb80187ba065d7decad7c6614e35e07aec8a974 ] + +Setting dev->hard_mtu to 0 will cause a divide error in +usbnet_probe. Protect against devices with bogus CDC Ethernet +functional descriptors by ignoring a zero wMaxSegmentSize. + +Signed-off-by: Bjørn Mork +Acked-by: Oliver Neukum +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/usb/cdc_ether.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/net/usb/cdc_ether.c ++++ b/drivers/net/usb/cdc_ether.c +@@ -221,7 +221,7 @@ skip: + goto bad_desc; + } + +- if (header.usb_cdc_ether_desc) { ++ if (header.usb_cdc_ether_desc && info->ether->wMaxSegmentSize) { + dev->hard_mtu = le16_to_cpu(info->ether->wMaxSegmentSize); + /* because of Zaurus, we may be ignoring the host + * side link address we were given. diff --git a/queue-4.9/net-qmi_wwan-fix-divide-by-0-on-bad-descriptors.patch b/queue-4.9/net-qmi_wwan-fix-divide-by-0-on-bad-descriptors.patch new file mode 100644 index 00000000000..f7147858596 --- /dev/null +++ b/queue-4.9/net-qmi_wwan-fix-divide-by-0-on-bad-descriptors.patch @@ -0,0 +1,59 @@ +From foo@baz Tue Nov 21 13:08:13 CET 2017 +From: Bjørn Mork +Date: Mon, 6 Nov 2017 15:32:18 +0100 +Subject: net: qmi_wwan: fix divide by 0 on bad descriptors + +From: Bjørn Mork + + +[ Upstream commit 7fd078337201cf7468f53c3d9ef81ff78cb6df3b ] + +A CDC Ethernet functional descriptor with wMaxSegmentSize = 0 will +cause a divide error in usbnet_probe: + +divide error: 0000 [#1] PREEMPT SMP KASAN +Modules linked in: +CPU: 0 PID: 24 Comm: kworker/0:1 Not tainted 4.14.0-rc8-44453-g1fdc1a82c34f #56 +Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 +Workqueue: usb_hub_wq hub_event +task: ffff88006bef5c00 task.stack: ffff88006bf60000 +RIP: 0010:usbnet_update_max_qlen+0x24d/0x390 drivers/net/usb/usbnet.c:355 +RSP: 0018:ffff88006bf67508 EFLAGS: 00010246 +RAX: 00000000000163c8 RBX: ffff8800621fce40 RCX: ffff8800621fcf34 +RDX: 0000000000000000 RSI: ffffffff837ecb7a RDI: ffff8800621fcf34 +RBP: ffff88006bf67520 R08: ffff88006bef5c00 R09: ffffed000c43f881 +R10: ffffed000c43f880 R11: ffff8800621fc406 R12: 0000000000000003 +R13: ffffffff85c71de0 R14: 0000000000000000 R15: 0000000000000000 +FS: 0000000000000000(0000) GS:ffff88006ca00000(0000) knlGS:0000000000000000 +CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +CR2: 00007ffe9c0d6dac CR3: 00000000614f4000 CR4: 00000000000006f0 +Call Trace: + usbnet_probe+0x18b5/0x2790 drivers/net/usb/usbnet.c:1783 + qmi_wwan_probe+0x133/0x220 drivers/net/usb/qmi_wwan.c:1338 + usb_probe_interface+0x324/0x940 drivers/usb/core/driver.c:361 + really_probe drivers/base/dd.c:413 + driver_probe_device+0x522/0x740 drivers/base/dd.c:557 + +Fix by simply ignoring the bogus descriptor, as it is optional +for QMI devices anyway. + +Fixes: 423ce8caab7e ("net: usb: qmi_wwan: New driver for Huawei QMI based WWAN devices") +Reported-by: Andrey Konovalov +Signed-off-by: Bjørn Mork +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/usb/qmi_wwan.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/net/usb/qmi_wwan.c ++++ b/drivers/net/usb/qmi_wwan.c +@@ -386,7 +386,7 @@ static int qmi_wwan_bind(struct usbnet * + } + + /* errors aren't fatal - we can live with the dynamic address */ +- if (cdc_ether) { ++ if (cdc_ether && cdc_ether->wMaxSegmentSize) { + dev->hard_mtu = le16_to_cpu(cdc_ether->wMaxSegmentSize); + usbnet_get_ethernet_addr(dev, cdc_ether->iMACAddress); + } diff --git a/queue-4.9/net-sctp-always-set-scope_id-in-sctp_inet6_skb_msgname.patch b/queue-4.9/net-sctp-always-set-scope_id-in-sctp_inet6_skb_msgname.patch new file mode 100644 index 00000000000..786d131c0d4 --- /dev/null +++ b/queue-4.9/net-sctp-always-set-scope_id-in-sctp_inet6_skb_msgname.patch @@ -0,0 +1,57 @@ +From foo@baz Tue Nov 21 13:08:13 CET 2017 +From: "Eric W. Biederman" +Date: Wed, 15 Nov 2017 22:17:48 -0600 +Subject: net/sctp: Always set scope_id in sctp_inet6_skb_msgname + +From: "Eric W. Biederman" + + +[ Upstream commit 7c8a61d9ee1df0fb4747879fa67a99614eb62fec ] + +Alexandar Potapenko while testing the kernel with KMSAN and syzkaller +discovered that in some configurations sctp would leak 4 bytes of +kernel stack. + +Working with his reproducer I discovered that those 4 bytes that +are leaked is the scope id of an ipv6 address returned by recvmsg. + +With a little code inspection and a shrewd guess I discovered that +sctp_inet6_skb_msgname only initializes the scope_id field for link +local ipv6 addresses to the interface index the link local address +pertains to instead of initializing the scope_id field for all ipv6 +addresses. + +That is almost reasonable as scope_id's are meaniningful only for link +local addresses. Set the scope_id in all other cases to 0 which is +not a valid interface index to make it clear there is nothing useful +in the scope_id field. + +There should be no danger of breaking userspace as the stack leak +guaranteed that previously meaningless random data was being returned. + +Fixes: 372f525b495c ("SCTP: Resync with LKSCTP tree.") +History-tree: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git +Reported-by: Alexander Potapenko +Tested-by: Alexander Potapenko +Signed-off-by: "Eric W. Biederman" +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/sctp/ipv6.c | 5 +++-- + 1 file changed, 3 insertions(+), 2 deletions(-) + +--- a/net/sctp/ipv6.c ++++ b/net/sctp/ipv6.c +@@ -806,9 +806,10 @@ static void sctp_inet6_skb_msgname(struc + addr->v6.sin6_flowinfo = 0; + addr->v6.sin6_port = sh->source; + addr->v6.sin6_addr = ipv6_hdr(skb)->saddr; +- if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) { ++ if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) + addr->v6.sin6_scope_id = sctp_v6_skb_iif(skb); +- } ++ else ++ addr->v6.sin6_scope_id = 0; + } + + *addr_len = sctp_v6_addr_to_user(sctp_sk(skb->sk), addr); diff --git a/queue-4.9/net-usb-asix-fill-null-ptr-deref-in-asix_suspend.patch b/queue-4.9/net-usb-asix-fill-null-ptr-deref-in-asix_suspend.patch new file mode 100644 index 00000000000..788029664d3 --- /dev/null +++ b/queue-4.9/net-usb-asix-fill-null-ptr-deref-in-asix_suspend.patch @@ -0,0 +1,86 @@ +From foo@baz Tue Nov 21 13:08:13 CET 2017 +From: Andrey Konovalov +Date: Mon, 6 Nov 2017 13:26:46 +0100 +Subject: net: usb: asix: fill null-ptr-deref in asix_suspend + +From: Andrey Konovalov + + +[ Upstream commit 8f5624629105589bcc23d0e51cc01bd8103d09a5 ] + +When asix_suspend() is called dev->driver_priv might not have been +assigned a value, so we need to check that it's not NULL. + +Similar issue is present in asix_resume(), this patch fixes it as well. + +Found by syzkaller. + +kasan: CONFIG_KASAN_INLINE enabled +kasan: GPF could be caused by NULL-ptr deref or user memory access +general protection fault: 0000 [#1] PREEMPT SMP KASAN +Modules linked in: +CPU: 0 PID: 24 Comm: kworker/0:1 Not tainted 4.14.0-rc4-43422-geccacdd69a8c #400 +Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 +Workqueue: usb_hub_wq hub_event +task: ffff88006bb36300 task.stack: ffff88006bba8000 +RIP: 0010:asix_suspend+0x76/0xc0 drivers/net/usb/asix_devices.c:629 +RSP: 0018:ffff88006bbae718 EFLAGS: 00010202 +RAX: dffffc0000000000 RBX: ffff880061ba3b80 RCX: 1ffff1000c34d644 +RDX: 0000000000000001 RSI: 0000000000000402 RDI: 0000000000000008 +RBP: ffff88006bbae738 R08: 1ffff1000d775cad R09: 0000000000000000 +R10: 0000000000000000 R11: 0000000000000000 R12: ffff8800630a8b40 +R13: 0000000000000000 R14: 0000000000000402 R15: ffff880061ba3b80 +FS: 0000000000000000(0000) GS:ffff88006c600000(0000) knlGS:0000000000000000 +CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +CR2: 00007ff33cf89000 CR3: 0000000061c0a000 CR4: 00000000000006f0 +Call Trace: + usb_suspend_interface drivers/usb/core/driver.c:1209 + usb_suspend_both+0x27f/0x7e0 drivers/usb/core/driver.c:1314 + usb_runtime_suspend+0x41/0x120 drivers/usb/core/driver.c:1852 + __rpm_callback+0x339/0xb60 drivers/base/power/runtime.c:334 + rpm_callback+0x106/0x220 drivers/base/power/runtime.c:461 + rpm_suspend+0x465/0x1980 drivers/base/power/runtime.c:596 + __pm_runtime_suspend+0x11e/0x230 drivers/base/power/runtime.c:1009 + pm_runtime_put_sync_autosuspend ./include/linux/pm_runtime.h:251 + usb_new_device+0xa37/0x1020 drivers/usb/core/hub.c:2487 + hub_port_connect drivers/usb/core/hub.c:4903 + hub_port_connect_change drivers/usb/core/hub.c:5009 + port_event drivers/usb/core/hub.c:5115 + hub_event+0x194d/0x3740 drivers/usb/core/hub.c:5195 + process_one_work+0xc7f/0x1db0 kernel/workqueue.c:2119 + worker_thread+0x221/0x1850 kernel/workqueue.c:2253 + kthread+0x3a1/0x470 kernel/kthread.c:231 + ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:431 +Code: 8d 7c 24 20 48 89 fa 48 c1 ea 03 80 3c 02 00 75 5b 48 b8 00 00 +00 00 00 fc ff df 4d 8b 6c 24 20 49 8d 7d 08 48 89 fa 48 c1 ea 03 <80> +3c 02 00 75 34 4d 8b 6d 08 4d 85 ed 74 0b e8 26 2b 51 fd 4c +RIP: asix_suspend+0x76/0xc0 RSP: ffff88006bbae718 +---[ end trace dfc4f5649284342c ]--- + +Signed-off-by: Andrey Konovalov +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/usb/asix_devices.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/drivers/net/usb/asix_devices.c ++++ b/drivers/net/usb/asix_devices.c +@@ -624,7 +624,7 @@ static int asix_suspend(struct usb_inter + struct usbnet *dev = usb_get_intfdata(intf); + struct asix_common_private *priv = dev->driver_priv; + +- if (priv->suspend) ++ if (priv && priv->suspend) + priv->suspend(dev); + + return usbnet_suspend(intf, message); +@@ -676,7 +676,7 @@ static int asix_resume(struct usb_interf + struct usbnet *dev = usb_get_intfdata(intf); + struct asix_common_private *priv = dev->driver_priv; + +- if (priv->resume) ++ if (priv && priv->resume) + priv->resume(dev); + + return usbnet_resume(intf); diff --git a/queue-4.9/net-vrf-correct-fra_l3mdev-encode-type.patch b/queue-4.9/net-vrf-correct-fra_l3mdev-encode-type.patch new file mode 100644 index 00000000000..13ba12f5d1b --- /dev/null +++ b/queue-4.9/net-vrf-correct-fra_l3mdev-encode-type.patch @@ -0,0 +1,34 @@ +From foo@baz Tue Nov 21 13:08:13 CET 2017 +From: Jeff Barnhill <0xeffeff@gmail.com> +Date: Wed, 1 Nov 2017 14:58:09 +0000 +Subject: net: vrf: correct FRA_L3MDEV encode type + +From: Jeff Barnhill <0xeffeff@gmail.com> + + +[ Upstream commit 18129a24983906eaf2a2d448ce4b83e27091ebe2 ] + +FRA_L3MDEV is defined as U8, but is being added as a U32 attribute. On +big endian architecture, this results in the l3mdev entry not being +added to the FIB rules. + +Fixes: 1aa6c4f6b8cd8 ("net: vrf: Add l3mdev rules on first device create") +Signed-off-by: Jeff Barnhill <0xeffeff@gmail.com> +Acked-by: David Ahern +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/vrf.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/net/vrf.c ++++ b/drivers/net/vrf.c +@@ -1129,7 +1129,7 @@ static int vrf_fib_rule(const struct net + frh->family = family; + frh->action = FR_ACT_TO_TBL; + +- if (nla_put_u32(skb, FRA_L3MDEV, 1)) ++ if (nla_put_u8(skb, FRA_L3MDEV, 1)) + goto nla_put_failure; + + if (nla_put_u32(skb, FRA_PRIORITY, FIB_RULE_PREF)) diff --git a/queue-4.9/netfilter-ipvs-clear-ipvs_property-flag-when-skb-net-namespace-changed.patch b/queue-4.9/netfilter-ipvs-clear-ipvs_property-flag-when-skb-net-namespace-changed.patch new file mode 100644 index 00000000000..2d5b244f7cc --- /dev/null +++ b/queue-4.9/netfilter-ipvs-clear-ipvs_property-flag-when-skb-net-namespace-changed.patch @@ -0,0 +1,53 @@ +From foo@baz Tue Nov 21 13:08:13 CET 2017 +From: Ye Yin +Date: Thu, 26 Oct 2017 16:57:05 +0800 +Subject: netfilter/ipvs: clear ipvs_property flag when SKB net namespace changed + +From: Ye Yin + + +[ Upstream commit 2b5ec1a5f9738ee7bf8f5ec0526e75e00362c48f ] + +When run ipvs in two different network namespace at the same host, and one +ipvs transport network traffic to the other network namespace ipvs. +'ipvs_property' flag will make the second ipvs take no effect. So we should +clear 'ipvs_property' when SKB network namespace changed. + +Fixes: 621e84d6f373 ("dev: introduce skb_scrub_packet()") +Signed-off-by: Ye Yin +Signed-off-by: Wei Zhou +Signed-off-by: Julian Anastasov +Signed-off-by: Simon Horman +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + include/linux/skbuff.h | 7 +++++++ + net/core/skbuff.c | 1 + + 2 files changed, 8 insertions(+) + +--- a/include/linux/skbuff.h ++++ b/include/linux/skbuff.h +@@ -3584,6 +3584,13 @@ static inline void nf_reset_trace(struct + #endif + } + ++static inline void ipvs_reset(struct sk_buff *skb) ++{ ++#if IS_ENABLED(CONFIG_IP_VS) ++ skb->ipvs_property = 0; ++#endif ++} ++ + /* Note: This doesn't put any conntrack and bridge info in dst. */ + static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, + bool copy) +--- a/net/core/skbuff.c ++++ b/net/core/skbuff.c +@@ -4375,6 +4375,7 @@ void skb_scrub_packet(struct sk_buff *sk + if (!xnet) + return; + ++ ipvs_reset(skb); + skb_orphan(skb); + skb->mark = 0; + } diff --git a/queue-4.9/qmi_wwan-add-missing-skb_reset_mac_header-call.patch b/queue-4.9/qmi_wwan-add-missing-skb_reset_mac_header-call.patch new file mode 100644 index 00000000000..be4c0c0d4f0 --- /dev/null +++ b/queue-4.9/qmi_wwan-add-missing-skb_reset_mac_header-call.patch @@ -0,0 +1,79 @@ +From foo@baz Tue Nov 21 13:08:13 CET 2017 +From: Kristian Evensen +Date: Tue, 7 Nov 2017 13:47:56 +0100 +Subject: qmi_wwan: Add missing skb_reset_mac_header-call + +From: Kristian Evensen + + +[ Upstream commit 0de0add10e587effa880c741c9413c874f16be91 ] + +When we receive a packet on a QMI device in raw IP mode, we should call +skb_reset_mac_header() to ensure that skb->mac_header contains a valid +offset in the packet. While it shouldn't really matter, the packets have +no MAC header and the interface is configured as-such, it seems certain +parts of the network stack expects a "good" value in skb->mac_header. + +Without the skb_reset_mac_header() call added in this patch, for example +shaping traffic (using tc) triggers the following oops on the first +received packet: + +[ 303.642957] skbuff: skb_under_panic: text:8f137918 len:177 put:67 head:8e4b0f00 data:8e4b0eff tail:0x8e4b0fb0 end:0x8e4b1520 dev:wwan0 +[ 303.655045] Kernel bug detected[#1]: +[ 303.658622] CPU: 1 PID: 1002 Comm: logd Not tainted 4.9.58 #0 +[ 303.664339] task: 8fdf05e0 task.stack: 8f15c000 +[ 303.668844] $ 0 : 00000000 00000001 0000007a 00000000 +[ 303.674062] $ 4 : 8149a2fc 8149a2fc 8149ce20 00000000 +[ 303.679284] $ 8 : 00000030 3878303a 31623465 20303235 +[ 303.684510] $12 : ded731e3 2626a277 00000000 03bd0000 +[ 303.689747] $16 : 8ef62b40 00000043 8f137918 804db5fc +[ 303.694978] $20 : 00000001 00000004 8fc13800 00000003 +[ 303.700215] $24 : 00000001 8024ab10 +[ 303.705442] $28 : 8f15c000 8fc19cf0 00000043 802cc920 +[ 303.710664] Hi : 00000000 +[ 303.713533] Lo : 74e58000 +[ 303.716436] epc : 802cc920 skb_panic+0x58/0x5c +[ 303.721046] ra : 802cc920 skb_panic+0x58/0x5c +[ 303.725639] Status: 11007c03 KERNEL EXL IE +[ 303.729823] Cause : 50800024 (ExcCode 09) +[ 303.733817] PrId : 0001992f (MIPS 1004Kc) +[ 303.737892] Modules linked in: rt2800pci rt2800mmio rt2800lib qcserial ppp_async option usb_wwan rt2x00pci rt2x00mmio rt2x00lib rndis_host qmi_wwan ppp_generic nf_nat_pptp nf_conntrack_pptp nf_conntrack_ipv6 mt76x2i +Process logd (pid: 1002, threadinfo=8f15c000, task=8fdf05e0, tls=77b3eee4) +[ 303.962509] Stack : 00000000 80408990 8f137918 000000b1 00000043 8e4b0f00 8e4b0eff 8e4b0fb0 +[ 303.970871] 8e4b1520 8fec1800 00000043 802cd2a4 6e000045 00000043 00000000 8ef62000 +[ 303.979219] 8eef5d00 8ef62b40 8fea7300 8f137918 00000000 00000000 0002bb01 793e5664 +[ 303.987568] 8ef08884 00000001 8fea7300 00000002 8fc19e80 8eef5d00 00000006 00000003 +[ 303.995934] 00000000 8030ba90 00000003 77ab3fd0 8149dc80 8004d1bc 8f15c000 8f383700 +[ 304.004324] ... +[ 304.006767] Call Trace: +[ 304.009241] [<802cc920>] skb_panic+0x58/0x5c +[ 304.013504] [<802cd2a4>] skb_push+0x78/0x90 +[ 304.017783] [<8f137918>] 0x8f137918 +[ 304.021269] Code: 00602825 0c02a3b4 24842888 <000c000d> 8c870060 8c8200a0 0007382b 00070336 8c88005c +[ 304.031034] +[ 304.032805] ---[ end trace b778c482b3f0bda9 ]--- +[ 304.041384] Kernel panic - not syncing: Fatal exception in interrupt +[ 304.051975] Rebooting in 3 seconds.. + +While the oops is for a 4.9-kernel, I was able to trigger the same oops with +net-next as of yesterday. + +Fixes: 32f7adf633b9 ("net: qmi_wwan: support "raw IP" mode") +Signed-off-by: Kristian Evensen +Acked-by: Bjørn Mork +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/usb/qmi_wwan.c | 1 + + 1 file changed, 1 insertion(+) + +--- a/drivers/net/usb/qmi_wwan.c ++++ b/drivers/net/usb/qmi_wwan.c +@@ -205,6 +205,7 @@ static int qmi_wwan_rx_fixup(struct usbn + return 1; + } + if (rawip) { ++ skb_reset_mac_header(skb); + skb->dev = dev->net; /* normally set by eth_type_trans */ + skb->protocol = proto; + return 1; diff --git a/queue-4.9/sctp-do-not-peel-off-an-assoc-from-one-netns-to-another-one.patch b/queue-4.9/sctp-do-not-peel-off-an-assoc-from-one-netns-to-another-one.patch new file mode 100644 index 00000000000..836a4176c1e --- /dev/null +++ b/queue-4.9/sctp-do-not-peel-off-an-assoc-from-one-netns-to-another-one.patch @@ -0,0 +1,63 @@ +From foo@baz Tue Nov 21 13:08:13 CET 2017 +From: Xin Long +Date: Tue, 17 Oct 2017 23:26:10 +0800 +Subject: sctp: do not peel off an assoc from one netns to another one + +From: Xin Long + + +[ Upstream commit df80cd9b28b9ebaa284a41df611dbf3a2d05ca74 ] + +Now when peeling off an association to the sock in another netns, all +transports in this assoc are not to be rehashed and keep use the old +key in hashtable. + +As a transport uses sk->net as the hash key to insert into hashtable, +it would miss removing these transports from hashtable due to the new +netns when closing the sock and all transports are being freeed, then +later an use-after-free issue could be caused when looking up an asoc +and dereferencing those transports. + +This is a very old issue since very beginning, ChunYu found it with +syzkaller fuzz testing with this series: + + socket$inet6_sctp() + bind$inet6() + sendto$inet6() + unshare(0x40000000) + getsockopt$inet_sctp6_SCTP_GET_ASSOC_ID_LIST() + getsockopt$inet_sctp6_SCTP_SOCKOPT_PEELOFF() + +This patch is to block this call when peeling one assoc off from one +netns to another one, so that the netns of all transport would not +go out-sync with the key in hashtable. + +Note that this patch didn't fix it by rehashing transports, as it's +difficult to handle the situation when the tuple is already in use +in the new netns. Besides, no one would like to peel off one assoc +to another netns, considering ipaddrs, ifaces, etc. are usually +different. + +Reported-by: ChunYu Wang +Signed-off-by: Xin Long +Acked-by: Marcelo Ricardo Leitner +Acked-by: Neil Horman +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/sctp/socket.c | 4 ++++ + 1 file changed, 4 insertions(+) + +--- a/net/sctp/socket.c ++++ b/net/sctp/socket.c +@@ -4764,6 +4764,10 @@ int sctp_do_peeloff(struct sock *sk, sct + struct socket *sock; + int err = 0; + ++ /* Do not peel off from one netns to another one. */ ++ if (!net_eq(current->nsproxy->net_ns, sock_net(sk))) ++ return -EINVAL; ++ + if (!asoc) + return -EINVAL; + diff --git a/queue-4.9/tcp-do-not-mangle-skb-cb-in-tcp_make_synack.patch b/queue-4.9/tcp-do-not-mangle-skb-cb-in-tcp_make_synack.patch new file mode 100644 index 00000000000..dc14b9a55c3 --- /dev/null +++ b/queue-4.9/tcp-do-not-mangle-skb-cb-in-tcp_make_synack.patch @@ -0,0 +1,53 @@ +From foo@baz Tue Nov 21 13:08:13 CET 2017 +From: Eric Dumazet +Date: Thu, 2 Nov 2017 12:30:25 -0700 +Subject: tcp: do not mangle skb->cb[] in tcp_make_synack() + +From: Eric Dumazet + + +[ Upstream commit 3b11775033dc87c3d161996c54507b15ba26414a ] + +Christoph Paasch sent a patch to address the following issue : + +tcp_make_synack() is leaving some TCP private info in skb->cb[], +then send the packet by other means than tcp_transmit_skb() + +tcp_transmit_skb() makes sure to clear skb->cb[] to not confuse +IPv4/IPV6 stacks, but we have no such cleanup for SYNACK. + +tcp_make_synack() should not use tcp_init_nondata_skb() : + +tcp_init_nondata_skb() really should be limited to skbs put in write/rtx +queues (the ones that are only sent via tcp_transmit_skb()) + +This patch fixes the issue and should even save few cpu cycles ;) + +Fixes: 971f10eca186 ("tcp: better TCP_SKB_CB layout to reduce cache line misses") +Signed-off-by: Eric Dumazet +Reported-by: Christoph Paasch +Reviewed-by: Christoph Paasch +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/tcp_output.c | 9 ++------- + 1 file changed, 2 insertions(+), 7 deletions(-) + +--- a/net/ipv4/tcp_output.c ++++ b/net/ipv4/tcp_output.c +@@ -3110,13 +3110,8 @@ struct sk_buff *tcp_make_synack(const st + tcp_ecn_make_synack(req, th); + th->source = htons(ireq->ir_num); + th->dest = ireq->ir_rmt_port; +- /* Setting of flags are superfluous here for callers (and ECE is +- * not even correctly set) +- */ +- tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn, +- TCPHDR_SYN | TCPHDR_ACK); +- +- th->seq = htonl(TCP_SKB_CB(skb)->seq); ++ skb->ip_summed = CHECKSUM_PARTIAL; ++ th->seq = htonl(tcp_rsk(req)->snt_isn); + /* XXX data is queued and acked as is. No buffer/window check */ + th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt); + diff --git a/queue-4.9/tcp_nv-fix-division-by-zero-in-tcpnv_acked.patch b/queue-4.9/tcp_nv-fix-division-by-zero-in-tcpnv_acked.patch new file mode 100644 index 00000000000..5cd928014e1 --- /dev/null +++ b/queue-4.9/tcp_nv-fix-division-by-zero-in-tcpnv_acked.patch @@ -0,0 +1,32 @@ +From foo@baz Tue Nov 21 13:08:13 CET 2017 +From: Konstantin Khlebnikov +Date: Wed, 1 Nov 2017 16:32:15 +0300 +Subject: tcp_nv: fix division by zero in tcpnv_acked() + +From: Konstantin Khlebnikov + + +[ Upstream commit 4eebff27ca4182bbf5f039dd60d79e2d7c0a707e ] + +Average RTT could become zero. This happened in real life at least twice. +This patch treats zero as 1us. + +Signed-off-by: Konstantin Khlebnikov +Acked-by: Lawrence Brakmo +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/tcp_nv.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/net/ipv4/tcp_nv.c ++++ b/net/ipv4/tcp_nv.c +@@ -263,7 +263,7 @@ static void tcpnv_acked(struct sock *sk, + + /* rate in 100's bits per second */ + rate64 = ((u64)sample->in_flight) * 8000000; +- rate = (u32)div64_u64(rate64, (u64)(avg_rtt * 100)); ++ rate = (u32)div64_u64(rate64, (u64)(avg_rtt ?: 1) * 100); + + /* Remember the maximum rate seen during this RTT + * Note: It may be more than one RTT. This function should be diff --git a/queue-4.9/vlan-fix-a-use-after-free-in-vlan_device_event.patch b/queue-4.9/vlan-fix-a-use-after-free-in-vlan_device_event.patch new file mode 100644 index 00000000000..82a5bc35035 --- /dev/null +++ b/queue-4.9/vlan-fix-a-use-after-free-in-vlan_device_event.patch @@ -0,0 +1,68 @@ +From foo@baz Tue Nov 21 13:08:13 CET 2017 +From: Cong Wang +Date: Thu, 9 Nov 2017 16:43:13 -0800 +Subject: vlan: fix a use-after-free in vlan_device_event() + +From: Cong Wang + + +[ Upstream commit 052d41c01b3a2e3371d66de569717353af489d63 ] + +After refcnt reaches zero, vlan_vid_del() could free +dev->vlan_info via RCU: + + RCU_INIT_POINTER(dev->vlan_info, NULL); + call_rcu(&vlan_info->rcu, vlan_info_rcu_free); + +However, the pointer 'grp' still points to that memory +since it is set before vlan_vid_del(): + + vlan_info = rtnl_dereference(dev->vlan_info); + if (!vlan_info) + goto out; + grp = &vlan_info->grp; + +Depends on when that RCU callback is scheduled, we could +trigger a use-after-free in vlan_group_for_each_dev() +right following this vlan_vid_del(). + +Fix it by moving vlan_vid_del() before setting grp. This +is also symmetric to the vlan_vid_add() we call in +vlan_device_event(). + +Reported-by: Fengguang Wu +Fixes: efc73f4bbc23 ("net: Fix memory leak - vlan_info struct") +Cc: Alexander Duyck +Cc: Linus Torvalds +Cc: Girish Moodalbail +Signed-off-by: Cong Wang +Reviewed-by: Girish Moodalbail +Tested-by: Fengguang Wu +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/8021q/vlan.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +--- a/net/8021q/vlan.c ++++ b/net/8021q/vlan.c +@@ -376,6 +376,9 @@ static int vlan_device_event(struct noti + dev->name); + vlan_vid_add(dev, htons(ETH_P_8021Q), 0); + } ++ if (event == NETDEV_DOWN && ++ (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) ++ vlan_vid_del(dev, htons(ETH_P_8021Q), 0); + + vlan_info = rtnl_dereference(dev->vlan_info); + if (!vlan_info) +@@ -423,9 +426,6 @@ static int vlan_device_event(struct noti + struct net_device *tmp; + LIST_HEAD(close_list); + +- if (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER) +- vlan_vid_del(dev, htons(ETH_P_8021Q), 0); +- + /* Put all VLANs for this dev in the down state too. */ + vlan_group_for_each_dev(grp, i, vlandev) { + flgs = vlandev->flags;