From: Greg Kroah-Hartman Date: Fri, 27 Jul 2018 07:32:57 +0000 (+0200) Subject: 4.9-stable patches X-Git-Tag: v3.18.117~11 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=b884e5d421a1f00a977ad33929742ab5a83c277c;p=thirdparty%2Fkernel%2Fstable-queue.git 4.9-stable patches added patches: ip-hash-fragments-consistently.patch ip-in-cmsg-ip-v6-_origdstaddr-call-pskb_may_pull.patch multicast-do-not-restore-deleted-record-source-filter-mode-to-new-one.patch net-mlx4_core-save-the-qpn-from-the-input-modifier-in-rst2init-wrapper.patch net-mlx5-adjust-clock-overflow-work-period.patch net-mlx5e-don-t-allow-arfs-for-encapsulated-packets.patch net-mlx5e-fix-quota-counting-in-arfs-expire-flow.patch net-phy-consider-phy_ignore_interrupt-in-phy_start_aneg_priv.patch net-skb_segment-should-not-return-null.patch rtnetlink-add-rtnl_link_state-check-in-rtnl_configure_link.patch tcp-avoid-collapses-in-tcp_prune_queue-if-possible.patch tcp-call-tcp_drop-from-tcp_data_queue_ofo.patch tcp-detect-malicious-patterns-in-tcp_collapse_ofo_queue.patch tcp-do-not-cancel-delay-ack-on-dctcp-special-ack.patch tcp-do-not-delay-ack-in-dctcp-upon-ce-status-change.patch tcp-fix-dctcp-delayed-ack-schedule.patch tcp-free-batches-of-packets-in-tcp_prune_ofo_queue.patch tcp-helpers-to-send-special-dctcp-ack.patch --- diff --git a/queue-4.9/ip-hash-fragments-consistently.patch b/queue-4.9/ip-hash-fragments-consistently.patch new file mode 100644 index 00000000000..428ca00ea1b --- /dev/null +++ b/queue-4.9/ip-hash-fragments-consistently.patch @@ -0,0 +1,73 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Paolo Abeni +Date: Mon, 23 Jul 2018 16:50:48 +0200 +Subject: ip: hash fragments consistently + +From: Paolo Abeni + +[ Upstream commit 3dd1c9a1270736029ffca670e9bd0265f4120600 ] + +The skb hash for locally generated ip[v6] fragments belonging +to the same datagram can vary in several circumstances: +* for connected UDP[v6] sockets, the first fragment get its hash + via set_owner_w()/skb_set_hash_from_sk() +* for unconnected IPv6 UDPv6 sockets, the first fragment can get + its hash via ip6_make_flowlabel()/skb_get_hash_flowi6(), if + auto_flowlabel is enabled + +For the following frags the hash is usually computed via +skb_get_hash(). +The above can cause OoO for unconnected IPv6 UDPv6 socket: in that +scenario the egress tx queue can be selected on a per packet basis +via the skb hash. +It may also fool flow-oriented schedulers to place fragments belonging +to the same datagram in different flows. + +Fix the issue by copying the skb hash from the head frag into +the others at fragmentation time. + +Before this commit: +perf probe -a "dev_queue_xmit skb skb->hash skb->l4_hash:b1@0/8 skb->sw_hash:b1@1/8" +netperf -H $IPV4 -t UDP_STREAM -l 5 -- -m 2000 -n & +perf record -e probe:dev_queue_xmit -e probe:skb_set_owner_w -a sleep 0.1 +perf script +probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=3713014309 l4_hash=1 sw_hash=0 +probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=0 l4_hash=0 sw_hash=0 + +After this commit: +probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=2171763177 l4_hash=1 sw_hash=0 +probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=2171763177 l4_hash=1 sw_hash=0 + +Fixes: b73c3d0e4f0e ("net: Save TX flow hash in sock and set in skbuf on xmit") +Fixes: 67800f9b1f4e ("ipv6: Call skb_get_hash_flowi6 to get skb->hash in ip6_make_flowlabel") +Signed-off-by: Paolo Abeni +Reviewed-by: Eric Dumazet +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/ip_output.c | 2 ++ + net/ipv6/ip6_output.c | 2 ++ + 2 files changed, 4 insertions(+) + +--- a/net/ipv4/ip_output.c ++++ b/net/ipv4/ip_output.c +@@ -497,6 +497,8 @@ static void ip_copy_metadata(struct sk_b + to->dev = from->dev; + to->mark = from->mark; + ++ skb_copy_hash(to, from); ++ + /* Copy the flags to each fragment. */ + IPCB(to)->flags = IPCB(from)->flags; + +--- a/net/ipv6/ip6_output.c ++++ b/net/ipv6/ip6_output.c +@@ -576,6 +576,8 @@ static void ip6_copy_metadata(struct sk_ + to->dev = from->dev; + to->mark = from->mark; + ++ skb_copy_hash(to, from); ++ + #ifdef CONFIG_NET_SCHED + to->tc_index = from->tc_index; + #endif diff --git a/queue-4.9/ip-in-cmsg-ip-v6-_origdstaddr-call-pskb_may_pull.patch b/queue-4.9/ip-in-cmsg-ip-v6-_origdstaddr-call-pskb_may_pull.patch new file mode 100644 index 00000000000..7952e35f0e0 --- /dev/null +++ b/queue-4.9/ip-in-cmsg-ip-v6-_origdstaddr-call-pskb_may_pull.patch @@ -0,0 +1,93 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Willem de Bruijn +Date: Mon, 23 Jul 2018 19:36:48 -0400 +Subject: ip: in cmsg IP(V6)_ORIGDSTADDR call pskb_may_pull + +From: Willem de Bruijn + +[ Upstream commit 2efd4fca703a6707cad16ab486eaab8fc7f0fd49 ] + +Syzbot reported a read beyond the end of the skb head when returning +IPV6_ORIGDSTADDR: + + BUG: KMSAN: kernel-infoleak in put_cmsg+0x5ef/0x860 net/core/scm.c:242 + CPU: 0 PID: 4501 Comm: syz-executor128 Not tainted 4.17.0+ #9 + Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS + Google 01/01/2011 + Call Trace: + __dump_stack lib/dump_stack.c:77 [inline] + dump_stack+0x185/0x1d0 lib/dump_stack.c:113 + kmsan_report+0x188/0x2a0 mm/kmsan/kmsan.c:1125 + kmsan_internal_check_memory+0x138/0x1f0 mm/kmsan/kmsan.c:1219 + kmsan_copy_to_user+0x7a/0x160 mm/kmsan/kmsan.c:1261 + copy_to_user include/linux/uaccess.h:184 [inline] + put_cmsg+0x5ef/0x860 net/core/scm.c:242 + ip6_datagram_recv_specific_ctl+0x1cf3/0x1eb0 net/ipv6/datagram.c:719 + ip6_datagram_recv_ctl+0x41c/0x450 net/ipv6/datagram.c:733 + rawv6_recvmsg+0x10fb/0x1460 net/ipv6/raw.c:521 + [..] + +This logic and its ipv4 counterpart read the destination port from +the packet at skb_transport_offset(skb) + 4. + +With MSG_MORE and a local SOCK_RAW sender, syzbot was able to cook a +packet that stores headers exactly up to skb_transport_offset(skb) in +the head and the remainder in a frag. + +Call pskb_may_pull before accessing the pointer to ensure that it lies +in skb head. + +Link: http://lkml.kernel.org/r/CAF=yD-LEJwZj5a1-bAAj2Oy_hKmGygV6rsJ_WOrAYnv-fnayiQ@mail.gmail.com +Reported-by: syzbot+9adb4b567003cac781f0@syzkaller.appspotmail.com +Signed-off-by: Willem de Bruijn +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/ip_sockglue.c | 7 +++++-- + net/ipv6/datagram.c | 7 +++++-- + 2 files changed, 10 insertions(+), 4 deletions(-) + +--- a/net/ipv4/ip_sockglue.c ++++ b/net/ipv4/ip_sockglue.c +@@ -135,15 +135,18 @@ static void ip_cmsg_recv_dstaddr(struct + { + struct sockaddr_in sin; + const struct iphdr *iph = ip_hdr(skb); +- __be16 *ports = (__be16 *)skb_transport_header(skb); ++ __be16 *ports; ++ int end; + +- if (skb_transport_offset(skb) + 4 > (int)skb->len) ++ end = skb_transport_offset(skb) + 4; ++ if (end > 0 && !pskb_may_pull(skb, end)) + return; + + /* All current transport protocols have the port numbers in the + * first four bytes of the transport header and this function is + * written with this assumption in mind. + */ ++ ports = (__be16 *)skb_transport_header(skb); + + sin.sin_family = AF_INET; + sin.sin_addr.s_addr = iph->daddr; +--- a/net/ipv6/datagram.c ++++ b/net/ipv6/datagram.c +@@ -694,13 +694,16 @@ void ip6_datagram_recv_specific_ctl(stru + } + if (np->rxopt.bits.rxorigdstaddr) { + struct sockaddr_in6 sin6; +- __be16 *ports = (__be16 *) skb_transport_header(skb); ++ __be16 *ports; ++ int end; + +- if (skb_transport_offset(skb) + 4 <= (int)skb->len) { ++ end = skb_transport_offset(skb) + 4; ++ if (end <= 0 || pskb_may_pull(skb, end)) { + /* All current transport protocols have the port numbers in the + * first four bytes of the transport header and this function is + * written with this assumption in mind. + */ ++ ports = (__be16 *)skb_transport_header(skb); + + sin6.sin6_family = AF_INET6; + sin6.sin6_addr = ipv6_hdr(skb)->daddr; diff --git a/queue-4.9/multicast-do-not-restore-deleted-record-source-filter-mode-to-new-one.patch b/queue-4.9/multicast-do-not-restore-deleted-record-source-filter-mode-to-new-one.patch new file mode 100644 index 00000000000..4c14a2042d4 --- /dev/null +++ b/queue-4.9/multicast-do-not-restore-deleted-record-source-filter-mode-to-new-one.patch @@ -0,0 +1,56 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Hangbin Liu +Date: Fri, 20 Jul 2018 14:04:27 +0800 +Subject: multicast: do not restore deleted record source filter mode to new one + +From: Hangbin Liu + +There are two scenarios that we will restore deleted records. The first is +when device down and up(or unmap/remap). In this scenario the new filter +mode is same with previous one. Because we get it from in_dev->mc_list and +we do not touch it during device down and up. + +The other scenario is when a new socket join a group which was just delete +and not finish sending status reports. In this scenario, we should use the +current filter mode instead of restore old one. Here are 4 cases in total. + +old_socket new_socket before_fix after_fix + IN(A) IN(A) ALLOW(A) ALLOW(A) + IN(A) EX( ) TO_IN( ) TO_EX( ) + EX( ) IN(A) TO_EX( ) ALLOW(A) + EX( ) EX( ) TO_EX( ) TO_EX( ) + +Fixes: 24803f38a5c0b (igmp: do not remove igmp souce list info when set link down) +Fixes: 1666d49e1d416 (mld: do not remove mld souce list info when set link down) +Signed-off-by: Hangbin Liu +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/igmp.c | 3 +-- + net/ipv6/mcast.c | 3 +-- + 2 files changed, 2 insertions(+), 4 deletions(-) + +--- a/net/ipv4/igmp.c ++++ b/net/ipv4/igmp.c +@@ -1193,8 +1193,7 @@ static void igmpv3_del_delrec(struct in_ + if (pmc) { + im->interface = pmc->interface; + im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; +- im->sfmode = pmc->sfmode; +- if (pmc->sfmode == MCAST_INCLUDE) { ++ if (im->sfmode == MCAST_INCLUDE) { + im->tomb = pmc->tomb; + im->sources = pmc->sources; + for (psf = im->sources; psf; psf = psf->sf_next) +--- a/net/ipv6/mcast.c ++++ b/net/ipv6/mcast.c +@@ -771,8 +771,7 @@ static void mld_del_delrec(struct inet6_ + if (pmc) { + im->idev = pmc->idev; + im->mca_crcount = idev->mc_qrv; +- im->mca_sfmode = pmc->mca_sfmode; +- if (pmc->mca_sfmode == MCAST_INCLUDE) { ++ if (im->mca_sfmode == MCAST_INCLUDE) { + im->mca_tomb = pmc->mca_tomb; + im->mca_sources = pmc->mca_sources; + for (psf = im->mca_sources; psf; psf = psf->sf_next) diff --git a/queue-4.9/net-mlx4_core-save-the-qpn-from-the-input-modifier-in-rst2init-wrapper.patch b/queue-4.9/net-mlx4_core-save-the-qpn-from-the-input-modifier-in-rst2init-wrapper.patch new file mode 100644 index 00000000000..5f04aeb17b3 --- /dev/null +++ b/queue-4.9/net-mlx4_core-save-the-qpn-from-the-input-modifier-in-rst2init-wrapper.patch @@ -0,0 +1,40 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Jack Morgenstein +Date: Tue, 24 Jul 2018 14:27:55 +0300 +Subject: net/mlx4_core: Save the qpn from the input modifier in RST2INIT wrapper + +From: Jack Morgenstein + +[ Upstream commit 958c696f5a7274d9447a458ad7aa70719b29a50a ] + +Function mlx4_RST2INIT_QP_wrapper saved the qp number passed in the qp +context, rather than the one passed in the input modifier. + +However, the qp number in the qp context is not defined as a +required parameter by the FW. Therefore, drivers may choose to not +specify the qp number in the qp context for the reset-to-init transition. + +Thus, we must save the qp number passed in the command input modifier -- +which is always present. (This saved qp number is used as the input +modifier for command 2RST_QP when a slave's qp's are destroyed). + +Fixes: c82e9aa0a8bc ("mlx4_core: resource tracking for HCA resources used by guests") +Signed-off-by: Jack Morgenstein +Signed-off-by: Tariq Toukan +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c ++++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +@@ -2916,7 +2916,7 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4 + u32 srqn = qp_get_srqn(qpc) & 0xffffff; + int use_srq = (qp_get_srqn(qpc) >> 24) & 1; + struct res_srq *srq; +- int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff; ++ int local_qpn = vhcr->in_modifier & 0xffffff; + + err = adjust_qp_sched_queue(dev, slave, qpc, inbox); + if (err) diff --git a/queue-4.9/net-mlx5-adjust-clock-overflow-work-period.patch b/queue-4.9/net-mlx5-adjust-clock-overflow-work-period.patch new file mode 100644 index 00000000000..4d933199655 --- /dev/null +++ b/queue-4.9/net-mlx5-adjust-clock-overflow-work-period.patch @@ -0,0 +1,70 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Ariel Levkovich +Date: Mon, 25 Jun 2018 19:12:02 +0300 +Subject: net/mlx5: Adjust clock overflow work period + +From: Ariel Levkovich + +[ Upstream commit 33180bee86a8940a84950edca46315cd9dd6deb5 ] + +When driver converts HW timestamp to wall clock time it subtracts +the last saved cycle counter from the HW timestamp and converts the +difference to nanoseconds. +The conversion is done by multiplying the cycles difference with the +clock multiplier value as a first step and therefore the cycles +difference should be small enough so that the multiplication product +doesn't exceed 64bit. + +The overflow handling routine is in charge of updating the last saved +cycle counter in driver and it is called periodically using kernel +delayed workqueue. + +The delay period for this work is calculated using the max HW cycle +counter value (a 41 bit mask) as a base which doesn't take the 64bit +limit into account so the delay period may be incorrect and too +long to prevent a large difference between the HW counter and the last +saved counter in SW. + +This change adjusts the work period for the HW clock overflow work by +taking the minimum between the previous value and the quotient of max +u64 value and the clock multiplier value. + +Fixes: ef9814deafd0 ("net/mlx5e: Add HW timestamping (TS) support") +Signed-off-by: Ariel Levkovich +Reviewed-by: Eran Ben Elisha +Signed-off-by: Saeed Mahameed +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/mellanox/mlx5/core/en_clock.c | 12 ++++++++++-- + 1 file changed, 10 insertions(+), 2 deletions(-) + +--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c ++++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c +@@ -233,6 +233,7 @@ static void mlx5e_timestamp_init_config( + void mlx5e_timestamp_init(struct mlx5e_priv *priv) + { + struct mlx5e_tstamp *tstamp = &priv->tstamp; ++ u64 overflow_cycles; + u64 ns; + u64 frac = 0; + u32 dev_freq; +@@ -257,10 +258,17 @@ void mlx5e_timestamp_init(struct mlx5e_p + + /* Calculate period in seconds to call the overflow watchdog - to make + * sure counter is checked at least once every wrap around. ++ * The period is calculated as the minimum between max HW cycles count ++ * (The clock source mask) and max amount of cycles that can be ++ * multiplied by clock multiplier where the result doesn't exceed ++ * 64bits. + */ +- ns = cyclecounter_cyc2ns(&tstamp->cycles, tstamp->cycles.mask, ++ overflow_cycles = div64_u64(~0ULL >> 1, tstamp->cycles.mult); ++ overflow_cycles = min(overflow_cycles, tstamp->cycles.mask >> 1); ++ ++ ns = cyclecounter_cyc2ns(&tstamp->cycles, overflow_cycles, + frac, &frac); +- do_div(ns, NSEC_PER_SEC / 2 / HZ); ++ do_div(ns, NSEC_PER_SEC / HZ); + tstamp->overflow_period = ns; + + INIT_DELAYED_WORK(&tstamp->overflow_work, mlx5e_timestamp_overflow); diff --git a/queue-4.9/net-mlx5e-don-t-allow-arfs-for-encapsulated-packets.patch b/queue-4.9/net-mlx5e-don-t-allow-arfs-for-encapsulated-packets.patch new file mode 100644 index 00000000000..ce43486ae9e --- /dev/null +++ b/queue-4.9/net-mlx5e-don-t-allow-arfs-for-encapsulated-packets.patch @@ -0,0 +1,33 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Eran Ben Elisha +Date: Sun, 8 Jul 2018 14:52:12 +0300 +Subject: net/mlx5e: Don't allow aRFS for encapsulated packets + +From: Eran Ben Elisha + +[ Upstream commit d2e1c57bcf9a07cbb67f30ecf238f298799bce1c ] + +Driver is yet to support aRFS for encapsulated packets, return early +error in such case. + +Fixes: 18c908e477dc ("net/mlx5e: Add accelerated RFS support") +Signed-off-by: Eran Ben Elisha +Reviewed-by: Tariq Toukan +Signed-off-by: Saeed Mahameed +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c | 3 +++ + 1 file changed, 3 insertions(+) + +--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c ++++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +@@ -715,6 +715,9 @@ int mlx5e_rx_flow_steer(struct net_devic + skb->protocol != htons(ETH_P_IPV6)) + return -EPROTONOSUPPORT; + ++ if (skb->encapsulation) ++ return -EPROTONOSUPPORT; ++ + arfs_t = arfs_get_table(arfs, arfs_get_ip_proto(skb), skb->protocol); + if (!arfs_t) + return -EPROTONOSUPPORT; diff --git a/queue-4.9/net-mlx5e-fix-quota-counting-in-arfs-expire-flow.patch b/queue-4.9/net-mlx5e-fix-quota-counting-in-arfs-expire-flow.patch new file mode 100644 index 00000000000..d6836ca6f30 --- /dev/null +++ b/queue-4.9/net-mlx5e-fix-quota-counting-in-arfs-expire-flow.patch @@ -0,0 +1,41 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Eran Ben Elisha +Date: Sun, 8 Jul 2018 13:08:55 +0300 +Subject: net/mlx5e: Fix quota counting in aRFS expire flow + +From: Eran Ben Elisha + +[ Upstream commit 2630bae8018823c3b88788b69fb9f16ea3b4a11e ] + +Quota should follow the amount of rules which do expire, and not the +number of rules that were examined, fixed that. + +Fixes: 18c908e477dc ("net/mlx5e: Add accelerated RFS support") +Signed-off-by: Eran Ben Elisha +Reviewed-by: Maor Gottlieb +Reviewed-by: Tariq Toukan +Signed-off-by: Saeed Mahameed +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c ++++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +@@ -383,14 +383,14 @@ static void arfs_may_expire_flow(struct + HLIST_HEAD(del_list); + spin_lock_bh(&priv->fs.arfs.arfs_lock); + mlx5e_for_each_arfs_rule(arfs_rule, htmp, priv->fs.arfs.arfs_tables, i, j) { +- if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA) +- break; + if (!work_pending(&arfs_rule->arfs_work) && + rps_may_expire_flow(priv->netdev, + arfs_rule->rxq, arfs_rule->flow_id, + arfs_rule->filter_id)) { + hlist_del_init(&arfs_rule->hlist); + hlist_add_head(&arfs_rule->hlist, &del_list); ++ if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA) ++ break; + } + } + spin_unlock_bh(&priv->fs.arfs.arfs_lock); diff --git a/queue-4.9/net-phy-consider-phy_ignore_interrupt-in-phy_start_aneg_priv.patch b/queue-4.9/net-phy-consider-phy_ignore_interrupt-in-phy_start_aneg_priv.patch new file mode 100644 index 00000000000..f573569b33e --- /dev/null +++ b/queue-4.9/net-phy-consider-phy_ignore_interrupt-in-phy_start_aneg_priv.patch @@ -0,0 +1,32 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Heiner Kallweit +Date: Thu, 19 Jul 2018 08:15:16 +0200 +Subject: net: phy: consider PHY_IGNORE_INTERRUPT in phy_start_aneg_priv + +From: Heiner Kallweit + +[ Upstream commit 215d08a85b9acf5e1fe9dbf50f1774cde333efef ] + +The situation described in the comment can occur also with +PHY_IGNORE_INTERRUPT, therefore change the condition to include it. + +Fixes: f555f34fdc58 ("net: phy: fix auto-negotiation stall due to unavailable interrupt") +Signed-off-by: Heiner Kallweit +Reviewed-by: Andrew Lunn +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/phy/phy.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/net/phy/phy.c ++++ b/drivers/net/phy/phy.c +@@ -598,7 +598,7 @@ static int phy_start_aneg_priv(struct ph + * negotiation may already be done and aneg interrupt may not be + * generated. + */ +- if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) { ++ if (phydev->irq != PHY_POLL && phydev->state == PHY_AN) { + err = phy_aneg_done(phydev); + if (err > 0) { + trigger = true; diff --git a/queue-4.9/net-skb_segment-should-not-return-null.patch b/queue-4.9/net-skb_segment-should-not-return-null.patch new file mode 100644 index 00000000000..e104bbd5c79 --- /dev/null +++ b/queue-4.9/net-skb_segment-should-not-return-null.patch @@ -0,0 +1,139 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Eric Dumazet +Date: Thu, 19 Jul 2018 16:04:38 -0700 +Subject: net: skb_segment() should not return NULL + +From: Eric Dumazet + +[ Upstream commit ff907a11a0d68a749ce1a321f4505c03bf72190c ] + +syzbot caught a NULL deref [1], caused by skb_segment() + +skb_segment() has many "goto err;" that assume the @err variable +contains -ENOMEM. + +A successful call to __skb_linearize() should not clear @err, +otherwise a subsequent memory allocation error could return NULL. + +While we are at it, we might use -EINVAL instead of -ENOMEM when +MAX_SKB_FRAGS limit is reached. + +[1] +kasan: CONFIG_KASAN_INLINE enabled +kasan: GPF could be caused by NULL-ptr deref or user memory access +general protection fault: 0000 [#1] SMP KASAN +CPU: 0 PID: 13285 Comm: syz-executor3 Not tainted 4.18.0-rc4+ #146 +Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 +RIP: 0010:tcp_gso_segment+0x3dc/0x1780 net/ipv4/tcp_offload.c:106 +Code: f0 ff ff 0f 87 1c fd ff ff e8 00 88 0b fb 48 8b 75 d0 48 b9 00 00 00 00 00 fc ff df 48 8d be 90 00 00 00 48 89 f8 48 c1 e8 03 <0f> b6 14 08 48 8d 86 94 00 00 00 48 89 c6 83 e0 07 48 c1 ee 03 0f +RSP: 0018:ffff88019b7fd060 EFLAGS: 00010206 +RAX: 0000000000000012 RBX: 0000000000000020 RCX: dffffc0000000000 +RDX: 0000000000040000 RSI: 0000000000000000 RDI: 0000000000000090 +RBP: ffff88019b7fd0f0 R08: ffff88019510e0c0 R09: ffffed003b5c46d6 +R10: ffffed003b5c46d6 R11: ffff8801dae236b3 R12: 0000000000000001 +R13: ffff8801d6c581f4 R14: 0000000000000000 R15: ffff8801d6c58128 +FS: 00007fcae64d6700(0000) GS:ffff8801dae00000(0000) knlGS:0000000000000000 +CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +CR2: 00000000004e8664 CR3: 00000001b669b000 CR4: 00000000001406f0 +DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 +DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 +Call Trace: + tcp4_gso_segment+0x1c3/0x440 net/ipv4/tcp_offload.c:54 + inet_gso_segment+0x64e/0x12d0 net/ipv4/af_inet.c:1342 + inet_gso_segment+0x64e/0x12d0 net/ipv4/af_inet.c:1342 + skb_mac_gso_segment+0x3b5/0x740 net/core/dev.c:2792 + __skb_gso_segment+0x3c3/0x880 net/core/dev.c:2865 + skb_gso_segment include/linux/netdevice.h:4099 [inline] + validate_xmit_skb+0x640/0xf30 net/core/dev.c:3104 + __dev_queue_xmit+0xc14/0x3910 net/core/dev.c:3561 + dev_queue_xmit+0x17/0x20 net/core/dev.c:3602 + neigh_hh_output include/net/neighbour.h:473 [inline] + neigh_output include/net/neighbour.h:481 [inline] + ip_finish_output2+0x1063/0x1860 net/ipv4/ip_output.c:229 + ip_finish_output+0x841/0xfa0 net/ipv4/ip_output.c:317 + NF_HOOK_COND include/linux/netfilter.h:276 [inline] + ip_output+0x223/0x880 net/ipv4/ip_output.c:405 + dst_output include/net/dst.h:444 [inline] + ip_local_out+0xc5/0x1b0 net/ipv4/ip_output.c:124 + iptunnel_xmit+0x567/0x850 net/ipv4/ip_tunnel_core.c:91 + ip_tunnel_xmit+0x1598/0x3af1 net/ipv4/ip_tunnel.c:778 + ipip_tunnel_xmit+0x264/0x2c0 net/ipv4/ipip.c:308 + __netdev_start_xmit include/linux/netdevice.h:4148 [inline] + netdev_start_xmit include/linux/netdevice.h:4157 [inline] + xmit_one net/core/dev.c:3034 [inline] + dev_hard_start_xmit+0x26c/0xc30 net/core/dev.c:3050 + __dev_queue_xmit+0x29ef/0x3910 net/core/dev.c:3569 + dev_queue_xmit+0x17/0x20 net/core/dev.c:3602 + neigh_direct_output+0x15/0x20 net/core/neighbour.c:1403 + neigh_output include/net/neighbour.h:483 [inline] + ip_finish_output2+0xa67/0x1860 net/ipv4/ip_output.c:229 + ip_finish_output+0x841/0xfa0 net/ipv4/ip_output.c:317 + NF_HOOK_COND include/linux/netfilter.h:276 [inline] + ip_output+0x223/0x880 net/ipv4/ip_output.c:405 + dst_output include/net/dst.h:444 [inline] + ip_local_out+0xc5/0x1b0 net/ipv4/ip_output.c:124 + ip_queue_xmit+0x9df/0x1f80 net/ipv4/ip_output.c:504 + tcp_transmit_skb+0x1bf9/0x3f10 net/ipv4/tcp_output.c:1168 + tcp_write_xmit+0x1641/0x5c20 net/ipv4/tcp_output.c:2363 + __tcp_push_pending_frames+0xb2/0x290 net/ipv4/tcp_output.c:2536 + tcp_push+0x638/0x8c0 net/ipv4/tcp.c:735 + tcp_sendmsg_locked+0x2ec5/0x3f00 net/ipv4/tcp.c:1410 + tcp_sendmsg+0x2f/0x50 net/ipv4/tcp.c:1447 + inet_sendmsg+0x1a1/0x690 net/ipv4/af_inet.c:798 + sock_sendmsg_nosec net/socket.c:641 [inline] + sock_sendmsg+0xd5/0x120 net/socket.c:651 + __sys_sendto+0x3d7/0x670 net/socket.c:1797 + __do_sys_sendto net/socket.c:1809 [inline] + __se_sys_sendto net/socket.c:1805 [inline] + __x64_sys_sendto+0xe1/0x1a0 net/socket.c:1805 + do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 + entry_SYSCALL_64_after_hwframe+0x49/0xbe +RIP: 0033:0x455ab9 +Code: 1d ba fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb b9 fb ff c3 66 2e 0f 1f 84 00 00 00 00 +RSP: 002b:00007fcae64d5c68 EFLAGS: 00000246 ORIG_RAX: 000000000000002c +RAX: ffffffffffffffda RBX: 00007fcae64d66d4 RCX: 0000000000455ab9 +RDX: 0000000000000001 RSI: 0000000020000200 RDI: 0000000000000013 +RBP: 000000000072bea0 R08: 0000000000000000 R09: 0000000000000000 +R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000014 +R13: 00000000004c1145 R14: 00000000004d1818 R15: 0000000000000006 +Modules linked in: +Dumping ftrace buffer: + (ftrace buffer empty) + +Fixes: ddff00d42043 ("net: Move skb_has_shared_frag check out of GRE code and into segmentation") +Signed-off-by: Eric Dumazet +Cc: Alexander Duyck +Reported-by: syzbot +Acked-by: Alexander Duyck +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/core/skbuff.c | 10 +++++----- + 1 file changed, 5 insertions(+), 5 deletions(-) + +--- a/net/core/skbuff.c ++++ b/net/core/skbuff.c +@@ -3253,6 +3253,7 @@ normal: + net_warn_ratelimited( + "skb_segment: too many frags: %u %u\n", + pos, mss); ++ err = -EINVAL; + goto err; + } + +@@ -3289,11 +3290,10 @@ skip_fraglist: + + perform_csum_check: + if (!csum) { +- if (skb_has_shared_frag(nskb)) { +- err = __skb_linearize(nskb); +- if (err) +- goto err; +- } ++ if (skb_has_shared_frag(nskb) && ++ __skb_linearize(nskb)) ++ goto err; ++ + if (!nskb->remcsum_offload) + nskb->ip_summed = CHECKSUM_NONE; + SKB_GSO_CB(nskb)->csum = diff --git a/queue-4.9/rtnetlink-add-rtnl_link_state-check-in-rtnl_configure_link.patch b/queue-4.9/rtnetlink-add-rtnl_link_state-check-in-rtnl_configure_link.patch new file mode 100644 index 00000000000..9178e38ab2e --- /dev/null +++ b/queue-4.9/rtnetlink-add-rtnl_link_state-check-in-rtnl_configure_link.patch @@ -0,0 +1,65 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Roopa Prabhu +Date: Fri, 20 Jul 2018 13:21:01 -0700 +Subject: rtnetlink: add rtnl_link_state check in rtnl_configure_link + +From: Roopa Prabhu + +[ Upstream commit 5025f7f7d506fba9b39e7fe8ca10f6f34cb9bc2d ] + +rtnl_configure_link sets dev->rtnl_link_state to +RTNL_LINK_INITIALIZED and unconditionally calls +__dev_notify_flags to notify user-space of dev flags. + +current call sequence for rtnl_configure_link +rtnetlink_newlink + rtnl_link_ops->newlink + rtnl_configure_link (unconditionally notifies userspace of + default and new dev flags) + +If a newlink handler wants to call rtnl_configure_link +early, we will end up with duplicate notifications to +user-space. + +This patch fixes rtnl_configure_link to check rtnl_link_state +and call __dev_notify_flags with gchanges = 0 if already +RTNL_LINK_INITIALIZED. + +Later in the series, this patch will help the following sequence +where a driver implementing newlink can call rtnl_configure_link +to initialize the link early. + +makes the following call sequence work: +rtnetlink_newlink + rtnl_link_ops->newlink (vxlan) -> rtnl_configure_link (initializes + link and notifies + user-space of default + dev flags) + rtnl_configure_link (updates dev flags if requested by user ifm + and notifies user-space of new dev flags) + +Signed-off-by: Roopa Prabhu +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/core/rtnetlink.c | 9 ++++++--- + 1 file changed, 6 insertions(+), 3 deletions(-) + +--- a/net/core/rtnetlink.c ++++ b/net/core/rtnetlink.c +@@ -2339,9 +2339,12 @@ int rtnl_configure_link(struct net_devic + return err; + } + +- dev->rtnl_link_state = RTNL_LINK_INITIALIZED; +- +- __dev_notify_flags(dev, old_flags, ~0U); ++ if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) { ++ __dev_notify_flags(dev, old_flags, 0U); ++ } else { ++ dev->rtnl_link_state = RTNL_LINK_INITIALIZED; ++ __dev_notify_flags(dev, old_flags, ~0U); ++ } + return 0; + } + EXPORT_SYMBOL(rtnl_configure_link); diff --git a/queue-4.9/series b/queue-4.9/series index faf5d517d99..566d3280879 100644 --- a/queue-4.9/series +++ b/queue-4.9/series @@ -1,2 +1,20 @@ mips-ath79-fix-register-address-in-ath79_ddr_wb_flush.patch mips-fix-off-by-one-in-pci_resource_to_user.patch +ip-hash-fragments-consistently.patch +ip-in-cmsg-ip-v6-_origdstaddr-call-pskb_may_pull.patch +net-mlx4_core-save-the-qpn-from-the-input-modifier-in-rst2init-wrapper.patch +net-skb_segment-should-not-return-null.patch +net-mlx5-adjust-clock-overflow-work-period.patch +net-mlx5e-don-t-allow-arfs-for-encapsulated-packets.patch +net-mlx5e-fix-quota-counting-in-arfs-expire-flow.patch +multicast-do-not-restore-deleted-record-source-filter-mode-to-new-one.patch +net-phy-consider-phy_ignore_interrupt-in-phy_start_aneg_priv.patch +rtnetlink-add-rtnl_link_state-check-in-rtnl_configure_link.patch +tcp-fix-dctcp-delayed-ack-schedule.patch +tcp-helpers-to-send-special-dctcp-ack.patch +tcp-do-not-cancel-delay-ack-on-dctcp-special-ack.patch +tcp-do-not-delay-ack-in-dctcp-upon-ce-status-change.patch +tcp-free-batches-of-packets-in-tcp_prune_ofo_queue.patch +tcp-avoid-collapses-in-tcp_prune_queue-if-possible.patch +tcp-detect-malicious-patterns-in-tcp_collapse_ofo_queue.patch +tcp-call-tcp_drop-from-tcp_data_queue_ofo.patch diff --git a/queue-4.9/tcp-avoid-collapses-in-tcp_prune_queue-if-possible.patch b/queue-4.9/tcp-avoid-collapses-in-tcp_prune_queue-if-possible.patch new file mode 100644 index 00000000000..127906a5179 --- /dev/null +++ b/queue-4.9/tcp-avoid-collapses-in-tcp_prune_queue-if-possible.patch @@ -0,0 +1,46 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Eric Dumazet +Date: Mon, 23 Jul 2018 09:28:18 -0700 +Subject: tcp: avoid collapses in tcp_prune_queue() if possible + +From: Eric Dumazet + +[ Upstream commit f4a3313d8e2ca9fd8d8f45e40a2903ba782607e7 ] + +Right after a TCP flow is created, receiving tiny out of order +packets allways hit the condition : + +if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) + tcp_clamp_window(sk); + +tcp_clamp_window() increases sk_rcvbuf to match sk_rmem_alloc +(guarded by tcp_rmem[2]) + +Calling tcp_collapse_ofo_queue() in this case is not useful, +and offers a O(N^2) surface attack to malicious peers. + +Better not attempt anything before full queue capacity is reached, +forcing attacker to spend lots of resource and allow us to more +easily detect the abuse. + +Signed-off-by: Eric Dumazet +Acked-by: Soheil Hassas Yeganeh +Acked-by: Yuchung Cheng +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/tcp_input.c | 3 +++ + 1 file changed, 3 insertions(+) + +--- a/net/ipv4/tcp_input.c ++++ b/net/ipv4/tcp_input.c +@@ -5027,6 +5027,9 @@ static int tcp_prune_queue(struct sock * + else if (tcp_under_memory_pressure(sk)) + tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); + ++ if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) ++ return 0; ++ + tcp_collapse_ofo_queue(sk); + if (!skb_queue_empty(&sk->sk_receive_queue)) + tcp_collapse(sk, &sk->sk_receive_queue, NULL, diff --git a/queue-4.9/tcp-call-tcp_drop-from-tcp_data_queue_ofo.patch b/queue-4.9/tcp-call-tcp_drop-from-tcp_data_queue_ofo.patch new file mode 100644 index 00000000000..96774be57fe --- /dev/null +++ b/queue-4.9/tcp-call-tcp_drop-from-tcp_data_queue_ofo.patch @@ -0,0 +1,42 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Eric Dumazet +Date: Mon, 23 Jul 2018 09:28:20 -0700 +Subject: tcp: call tcp_drop() from tcp_data_queue_ofo() + +From: Eric Dumazet + +[ Upstream commit 8541b21e781a22dce52a74fef0b9bed00404a1cd ] + +In order to be able to give better diagnostics and detect +malicious traffic, we need to have better sk->sk_drops tracking. + +Fixes: 9f5afeae5152 ("tcp: use an RB tree for ooo receive queue") +Signed-off-by: Eric Dumazet +Acked-by: Soheil Hassas Yeganeh +Acked-by: Yuchung Cheng +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/tcp_input.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/net/ipv4/tcp_input.c ++++ b/net/ipv4/tcp_input.c +@@ -4517,7 +4517,7 @@ coalesce_done: + /* All the bits are present. Drop. */ + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPOFOMERGE); +- __kfree_skb(skb); ++ tcp_drop(sk, skb); + skb = NULL; + tcp_dsack_set(sk, seq, end_seq); + goto add_sack; +@@ -4536,7 +4536,7 @@ coalesce_done: + TCP_SKB_CB(skb1)->end_seq); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPOFOMERGE); +- __kfree_skb(skb1); ++ tcp_drop(sk, skb1); + goto merge_right; + } + } else if (tcp_try_coalesce(sk, skb1, skb, &fragstolen)) { diff --git a/queue-4.9/tcp-detect-malicious-patterns-in-tcp_collapse_ofo_queue.patch b/queue-4.9/tcp-detect-malicious-patterns-in-tcp_collapse_ofo_queue.patch new file mode 100644 index 00000000000..63567238316 --- /dev/null +++ b/queue-4.9/tcp-detect-malicious-patterns-in-tcp_collapse_ofo_queue.patch @@ -0,0 +1,72 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Eric Dumazet +Date: Mon, 23 Jul 2018 09:28:19 -0700 +Subject: tcp: detect malicious patterns in tcp_collapse_ofo_queue() + +From: Eric Dumazet + +[ Upstream commit 3d4bf93ac12003f9b8e1e2de37fe27983deebdcf ] + +In case an attacker feeds tiny packets completely out of order, +tcp_collapse_ofo_queue() might scan the whole rb-tree, performing +expensive copies, but not changing socket memory usage at all. + +1) Do not attempt to collapse tiny skbs. +2) Add logic to exit early when too many tiny skbs are detected. + +We prefer not doing aggressive collapsing (which copies packets) +for pathological flows, and revert to tcp_prune_ofo_queue() which +will be less expensive. + +In the future, we might add the possibility of terminating flows +that are proven to be malicious. + +Signed-off-by: Eric Dumazet +Acked-by: Soheil Hassas Yeganeh +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/tcp_input.c | 15 +++++++++++++-- + 1 file changed, 13 insertions(+), 2 deletions(-) + +--- a/net/ipv4/tcp_input.c ++++ b/net/ipv4/tcp_input.c +@@ -4918,6 +4918,7 @@ end: + static void tcp_collapse_ofo_queue(struct sock *sk) + { + struct tcp_sock *tp = tcp_sk(sk); ++ u32 range_truesize, sum_tiny = 0; + struct sk_buff *skb, *head; + struct rb_node *p; + u32 start, end; +@@ -4936,6 +4937,7 @@ new_range: + } + start = TCP_SKB_CB(skb)->seq; + end = TCP_SKB_CB(skb)->end_seq; ++ range_truesize = skb->truesize; + + for (head = skb;;) { + skb = tcp_skb_next(skb, NULL); +@@ -4946,11 +4948,20 @@ new_range: + if (!skb || + after(TCP_SKB_CB(skb)->seq, end) || + before(TCP_SKB_CB(skb)->end_seq, start)) { +- tcp_collapse(sk, NULL, &tp->out_of_order_queue, +- head, skb, start, end); ++ /* Do not attempt collapsing tiny skbs */ ++ if (range_truesize != head->truesize || ++ end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) { ++ tcp_collapse(sk, NULL, &tp->out_of_order_queue, ++ head, skb, start, end); ++ } else { ++ sum_tiny += range_truesize; ++ if (sum_tiny > sk->sk_rcvbuf >> 3) ++ return; ++ } + goto new_range; + } + ++ range_truesize += skb->truesize; + if (unlikely(before(TCP_SKB_CB(skb)->seq, start))) + start = TCP_SKB_CB(skb)->seq; + if (after(TCP_SKB_CB(skb)->end_seq, end)) diff --git a/queue-4.9/tcp-do-not-cancel-delay-ack-on-dctcp-special-ack.patch b/queue-4.9/tcp-do-not-cancel-delay-ack-on-dctcp-special-ack.patch new file mode 100644 index 00000000000..24412ab524d --- /dev/null +++ b/queue-4.9/tcp-do-not-cancel-delay-ack-on-dctcp-special-ack.patch @@ -0,0 +1,138 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Yuchung Cheng +Date: Wed, 18 Jul 2018 13:56:35 -0700 +Subject: tcp: do not cancel delay-AcK on DCTCP special ACK + +From: Yuchung Cheng + +[ Upstream commit 27cde44a259c380a3c09066fc4b42de7dde9b1ad ] + +Currently when a DCTCP receiver delays an ACK and receive a +data packet with a different CE mark from the previous one's, it +sends two immediate ACKs acking previous and latest sequences +respectly (for ECN accounting). + +Previously sending the first ACK may mark off the delayed ACK timer +(tcp_event_ack_sent). This may subsequently prevent sending the +second ACK to acknowledge the latest sequence (tcp_ack_snd_check). +The culprit is that tcp_send_ack() assumes it always acknowleges +the latest sequence, which is not true for the first special ACK. + +The fix is to not make the assumption in tcp_send_ack and check the +actual ack sequence before cancelling the delayed ACK. Further it's +safer to pass the ack sequence number as a local variable into +tcp_send_ack routine, instead of intercepting tp->rcv_nxt to avoid +future bugs like this. + +Reported-by: Neal Cardwell +Signed-off-by: Yuchung Cheng +Acked-by: Neal Cardwell +Signed-off-by: Eric Dumazet +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + include/net/tcp.h | 1 + + net/ipv4/tcp_dctcp.c | 34 ++++------------------------------ + net/ipv4/tcp_output.c | 11 ++++++++--- + 3 files changed, 13 insertions(+), 33 deletions(-) + +--- a/include/net/tcp.h ++++ b/include/net/tcp.h +@@ -553,6 +553,7 @@ void tcp_send_fin(struct sock *sk); + void tcp_send_active_reset(struct sock *sk, gfp_t priority); + int tcp_send_synack(struct sock *); + void tcp_push_one(struct sock *, unsigned int mss_now); ++void __tcp_send_ack(struct sock *sk, u32 rcv_nxt); + void tcp_send_ack(struct sock *sk); + void tcp_send_delayed_ack(struct sock *sk); + void tcp_send_loss_probe(struct sock *sk); +--- a/net/ipv4/tcp_dctcp.c ++++ b/net/ipv4/tcp_dctcp.c +@@ -135,21 +135,8 @@ static void dctcp_ce_state_0_to_1(struct + * ACK has not sent yet. + */ + if (!ca->ce_state && +- inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { +- u32 tmp_rcv_nxt; +- +- /* Save current rcv_nxt. */ +- tmp_rcv_nxt = tp->rcv_nxt; +- +- /* Generate previous ack with CE=0. */ +- tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; +- tp->rcv_nxt = ca->prior_rcv_nxt; +- +- tcp_send_ack(sk); +- +- /* Recover current rcv_nxt. */ +- tp->rcv_nxt = tmp_rcv_nxt; +- } ++ inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) ++ __tcp_send_ack(sk, ca->prior_rcv_nxt); + + ca->prior_rcv_nxt = tp->rcv_nxt; + ca->ce_state = 1; +@@ -166,21 +153,8 @@ static void dctcp_ce_state_1_to_0(struct + * ACK has not sent yet. + */ + if (ca->ce_state && +- inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { +- u32 tmp_rcv_nxt; +- +- /* Save current rcv_nxt. */ +- tmp_rcv_nxt = tp->rcv_nxt; +- +- /* Generate previous ack with CE=1. */ +- tp->ecn_flags |= TCP_ECN_DEMAND_CWR; +- tp->rcv_nxt = ca->prior_rcv_nxt; +- +- tcp_send_ack(sk); +- +- /* Recover current rcv_nxt. */ +- tp->rcv_nxt = tmp_rcv_nxt; +- } ++ inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) ++ __tcp_send_ack(sk, ca->prior_rcv_nxt); + + ca->prior_rcv_nxt = tp->rcv_nxt; + ca->ce_state = 0; +--- a/net/ipv4/tcp_output.c ++++ b/net/ipv4/tcp_output.c +@@ -174,8 +174,13 @@ static void tcp_event_data_sent(struct t + } + + /* Account for an ACK we sent. */ +-static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) ++static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, ++ u32 rcv_nxt) + { ++ struct tcp_sock *tp = tcp_sk(sk); ++ ++ if (unlikely(rcv_nxt != tp->rcv_nxt)) ++ return; /* Special ACK sent by DCTCP to reflect ECN */ + tcp_dec_quickack_mode(sk, pkts); + inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); + } +@@ -1010,7 +1015,7 @@ static int __tcp_transmit_skb(struct soc + icsk->icsk_af_ops->send_check(sk, skb); + + if (likely(tcb->tcp_flags & TCPHDR_ACK)) +- tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); ++ tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); + + if (skb->len != tcp_header_size) { + tcp_event_data_sent(tp, sk); +@@ -3529,12 +3534,12 @@ void __tcp_send_ack(struct sock *sk, u32 + skb_mstamp_get(&buff->skb_mstamp); + __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt); + } ++EXPORT_SYMBOL_GPL(__tcp_send_ack); + + void tcp_send_ack(struct sock *sk) + { + __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt); + } +-EXPORT_SYMBOL_GPL(tcp_send_ack); + + /* This routine sends a packet with an out of date sequence + * number. It assumes the other end will try to ack it. diff --git a/queue-4.9/tcp-do-not-delay-ack-in-dctcp-upon-ce-status-change.patch b/queue-4.9/tcp-do-not-delay-ack-in-dctcp-upon-ce-status-change.patch new file mode 100644 index 00000000000..5f2f89144b3 --- /dev/null +++ b/queue-4.9/tcp-do-not-delay-ack-in-dctcp-upon-ce-status-change.patch @@ -0,0 +1,138 @@ +From foo@baz Fri Jul 27 08:53:18 CEST 2018 +From: Yuchung Cheng +Date: Wed, 18 Jul 2018 13:56:36 -0700 +Subject: tcp: do not delay ACK in DCTCP upon CE status change + +From: Yuchung Cheng + +[ Upstream commit a0496ef2c23b3b180902dd185d0d63ccbc624cf8 ] + +Per DCTCP RFC8257 (Section 3.2) the ACK reflecting the CE status change +has to be sent immediately so the sender can respond quickly: + +""" When receiving packets, the CE codepoint MUST be processed as follows: + + 1. If the CE codepoint is set and DCTCP.CE is false, set DCTCP.CE to + true and send an immediate ACK. + + 2. If the CE codepoint is not set and DCTCP.CE is true, set DCTCP.CE + to false and send an immediate ACK. +""" + +Previously DCTCP implementation may continue to delay the ACK. This +patch fixes that to implement the RFC by forcing an immediate ACK. + +Tested with this packetdrill script provided by Larry Brakmo + +0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0.000 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0 +0.000 bind(3, ..., ...) = 0 +0.000 listen(3, 1) = 0 + +0.100 < [ect0] SEW 0:0(0) win 32792 +0.100 > SE. 0:0(0) ack 1 +0.110 < [ect0] . 1:1(0) ack 1 win 257 +0.200 accept(3, ..., ...) = 4 + +0 setsockopt(4, SOL_SOCKET, SO_DEBUG, [1], 4) = 0 + +0.200 < [ect0] . 1:1001(1000) ack 1 win 257 +0.200 > [ect01] . 1:1(0) ack 1001 + +0.200 write(4, ..., 1) = 1 +0.200 > [ect01] P. 1:2(1) ack 1001 + +0.200 < [ect0] . 1001:2001(1000) ack 2 win 257 ++0.005 < [ce] . 2001:3001(1000) ack 2 win 257 + ++0.000 > [ect01] . 2:2(0) ack 2001 +// Previously the ACK below would be delayed by 40ms ++0.000 > [ect01] E. 2:2(0) ack 3001 + ++0.500 < F. 9501:9501(0) ack 4 win 257 + +Signed-off-by: Yuchung Cheng +Acked-by: Neal Cardwell +Signed-off-by: Eric Dumazet +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + include/net/tcp.h | 1 + + net/ipv4/tcp_dctcp.c | 30 ++++++++++++++++++------------ + net/ipv4/tcp_input.c | 3 ++- + 3 files changed, 21 insertions(+), 13 deletions(-) + +--- a/include/net/tcp.h ++++ b/include/net/tcp.h +@@ -363,6 +363,7 @@ ssize_t tcp_splice_read(struct socket *s + struct pipe_inode_info *pipe, size_t len, + unsigned int flags); + ++void tcp_enter_quickack_mode(struct sock *sk); + static inline void tcp_dec_quickack_mode(struct sock *sk, + const unsigned int pkts) + { +--- a/net/ipv4/tcp_dctcp.c ++++ b/net/ipv4/tcp_dctcp.c +@@ -131,12 +131,15 @@ static void dctcp_ce_state_0_to_1(struct + struct dctcp *ca = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk); + +- /* State has changed from CE=0 to CE=1 and delayed +- * ACK has not sent yet. +- */ +- if (!ca->ce_state && +- inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) +- __tcp_send_ack(sk, ca->prior_rcv_nxt); ++ if (!ca->ce_state) { ++ /* State has changed from CE=0 to CE=1, force an immediate ++ * ACK to reflect the new CE state. If an ACK was delayed, ++ * send that first to reflect the prior CE state. ++ */ ++ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) ++ __tcp_send_ack(sk, ca->prior_rcv_nxt); ++ tcp_enter_quickack_mode(sk); ++ } + + ca->prior_rcv_nxt = tp->rcv_nxt; + ca->ce_state = 1; +@@ -149,12 +152,15 @@ static void dctcp_ce_state_1_to_0(struct + struct dctcp *ca = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk); + +- /* State has changed from CE=1 to CE=0 and delayed +- * ACK has not sent yet. +- */ +- if (ca->ce_state && +- inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) +- __tcp_send_ack(sk, ca->prior_rcv_nxt); ++ if (ca->ce_state) { ++ /* State has changed from CE=1 to CE=0, force an immediate ++ * ACK to reflect the new CE state. If an ACK was delayed, ++ * send that first to reflect the prior CE state. ++ */ ++ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) ++ __tcp_send_ack(sk, ca->prior_rcv_nxt); ++ tcp_enter_quickack_mode(sk); ++ } + + ca->prior_rcv_nxt = tp->rcv_nxt; + ca->ce_state = 0; +--- a/net/ipv4/tcp_input.c ++++ b/net/ipv4/tcp_input.c +@@ -209,13 +209,14 @@ static void tcp_incr_quickack(struct soc + icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS); + } + +-static void tcp_enter_quickack_mode(struct sock *sk) ++void tcp_enter_quickack_mode(struct sock *sk) + { + struct inet_connection_sock *icsk = inet_csk(sk); + tcp_incr_quickack(sk); + icsk->icsk_ack.pingpong = 0; + icsk->icsk_ack.ato = TCP_ATO_MIN; + } ++EXPORT_SYMBOL(tcp_enter_quickack_mode); + + /* Send ACKs quickly, if "quick" count is not exhausted + * and the session is not interactive. diff --git a/queue-4.9/tcp-fix-dctcp-delayed-ack-schedule.patch b/queue-4.9/tcp-fix-dctcp-delayed-ack-schedule.patch new file mode 100644 index 00000000000..a1bbc8fa2e2 --- /dev/null +++ b/queue-4.9/tcp-fix-dctcp-delayed-ack-schedule.patch @@ -0,0 +1,98 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Yuchung Cheng +Date: Thu, 12 Jul 2018 06:04:52 -0700 +Subject: tcp: fix dctcp delayed ACK schedule + +From: Yuchung Cheng + +[ Upstream commit b0c05d0e99d98d7f0cd41efc1eeec94efdc3325d ] + +Previously, when a data segment was sent an ACK was piggybacked +on the data segment without generating a CA_EVENT_NON_DELAYED_ACK +event to notify congestion control modules. So the DCTCP +ca->delayed_ack_reserved flag could incorrectly stay set when +in fact there were no delayed ACKs being reserved. This could result +in sending a special ECN notification ACK that carries an older +ACK sequence, when in fact there was no need for such an ACK. +DCTCP keeps track of the delayed ACK status with its own separate +state ca->delayed_ack_reserved. Previously it may accidentally cancel +the delayed ACK without updating this field upon sending a special +ACK that carries a older ACK sequence. This inconsistency would +lead to DCTCP receiver never acknowledging the latest data until the +sender times out and retry in some cases. + +Packetdrill script (provided by Larry Brakmo) + +0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0.000 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0 +0.000 bind(3, ..., ...) = 0 +0.000 listen(3, 1) = 0 + +0.100 < [ect0] SEW 0:0(0) win 32792 +0.100 > SE. 0:0(0) ack 1 +0.110 < [ect0] . 1:1(0) ack 1 win 257 +0.200 accept(3, ..., ...) = 4 + +0.200 < [ect0] . 1:1001(1000) ack 1 win 257 +0.200 > [ect01] . 1:1(0) ack 1001 + +0.200 write(4, ..., 1) = 1 +0.200 > [ect01] P. 1:2(1) ack 1001 + +0.200 < [ect0] . 1001:2001(1000) ack 2 win 257 +0.200 write(4, ..., 1) = 1 +0.200 > [ect01] P. 2:3(1) ack 2001 + +0.200 < [ect0] . 2001:3001(1000) ack 3 win 257 +0.200 < [ect0] . 3001:4001(1000) ack 3 win 257 +0.200 > [ect01] . 3:3(0) ack 4001 + +0.210 < [ce] P. 4001:4501(500) ack 3 win 257 + ++0.001 read(4, ..., 4500) = 4500 ++0 write(4, ..., 1) = 1 ++0 > [ect01] PE. 3:4(1) ack 4501 + ++0.010 < [ect0] W. 4501:5501(1000) ack 4 win 257 +// Previously the ACK sequence below would be 4501, causing a long RTO ++0.040~+0.045 > [ect01] . 4:4(0) ack 5501 // delayed ack + ++0.311 < [ect0] . 5501:6501(1000) ack 4 win 257 // More data ++0 > [ect01] . 4:4(0) ack 6501 // now acks everything + ++0.500 < F. 9501:9501(0) ack 4 win 257 + +Reported-by: Larry Brakmo +Signed-off-by: Yuchung Cheng +Signed-off-by: Eric Dumazet +Acked-by: Neal Cardwell +Acked-by: Lawrence Brakmo +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/tcp_dctcp.c | 6 ++++-- + 1 file changed, 4 insertions(+), 2 deletions(-) + +--- a/net/ipv4/tcp_dctcp.c ++++ b/net/ipv4/tcp_dctcp.c +@@ -134,7 +134,8 @@ static void dctcp_ce_state_0_to_1(struct + /* State has changed from CE=0 to CE=1 and delayed + * ACK has not sent yet. + */ +- if (!ca->ce_state && ca->delayed_ack_reserved) { ++ if (!ca->ce_state && ++ inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { + u32 tmp_rcv_nxt; + + /* Save current rcv_nxt. */ +@@ -164,7 +165,8 @@ static void dctcp_ce_state_1_to_0(struct + /* State has changed from CE=1 to CE=0 and delayed + * ACK has not sent yet. + */ +- if (ca->ce_state && ca->delayed_ack_reserved) { ++ if (ca->ce_state && ++ inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { + u32 tmp_rcv_nxt; + + /* Save current rcv_nxt. */ diff --git a/queue-4.9/tcp-free-batches-of-packets-in-tcp_prune_ofo_queue.patch b/queue-4.9/tcp-free-batches-of-packets-in-tcp_prune_ofo_queue.patch new file mode 100644 index 00000000000..87ba00aea6b --- /dev/null +++ b/queue-4.9/tcp-free-batches-of-packets-in-tcp_prune_ofo_queue.patch @@ -0,0 +1,88 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Eric Dumazet +Date: Mon, 23 Jul 2018 09:28:17 -0700 +Subject: tcp: free batches of packets in tcp_prune_ofo_queue() + +From: Eric Dumazet + +[ Upstream commit 72cd43ba64fc172a443410ce01645895850844c8 ] + +Juha-Matti Tilli reported that malicious peers could inject tiny +packets in out_of_order_queue, forcing very expensive calls +to tcp_collapse_ofo_queue() and tcp_prune_ofo_queue() for +every incoming packet. out_of_order_queue rb-tree can contain +thousands of nodes, iterating over all of them is not nice. + +Before linux-4.9, we would have pruned all packets in ofo_queue +in one go, every XXXX packets. XXXX depends on sk_rcvbuf and skbs +truesize, but is about 7000 packets with tcp_rmem[2] default of 6 MB. + +Since we plan to increase tcp_rmem[2] in the future to cope with +modern BDP, can not revert to the old behavior, without great pain. + +Strategy taken in this patch is to purge ~12.5 % of the queue capacity. + +Fixes: 36a6503fedda ("tcp: refine tcp_prune_ofo_queue() to not drop all packets") +Signed-off-by: Eric Dumazet +Reported-by: Juha-Matti Tilli +Acked-by: Yuchung Cheng +Acked-by: Soheil Hassas Yeganeh +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + include/linux/skbuff.h | 2 ++ + net/ipv4/tcp_input.c | 15 +++++++++++---- + 2 files changed, 13 insertions(+), 4 deletions(-) + +--- a/include/linux/skbuff.h ++++ b/include/linux/skbuff.h +@@ -2982,6 +2982,8 @@ static inline int __skb_grow_rcsum(struc + return __skb_grow(skb, len); + } + ++#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode) ++ + #define skb_queue_walk(queue, skb) \ + for (skb = (queue)->next; \ + skb != (struct sk_buff *)(queue); \ +--- a/net/ipv4/tcp_input.c ++++ b/net/ipv4/tcp_input.c +@@ -4965,6 +4965,7 @@ new_range: + * 2) not add too big latencies if thousands of packets sit there. + * (But if application shrinks SO_RCVBUF, we could still end up + * freeing whole queue here) ++ * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks. + * + * Return true if queue has shrunk. + */ +@@ -4972,20 +4973,26 @@ static bool tcp_prune_ofo_queue(struct s + { + struct tcp_sock *tp = tcp_sk(sk); + struct rb_node *node, *prev; ++ int goal; + + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) + return false; + + NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); ++ goal = sk->sk_rcvbuf >> 3; + node = &tp->ooo_last_skb->rbnode; + do { + prev = rb_prev(node); + rb_erase(node, &tp->out_of_order_queue); ++ goal -= rb_to_skb(node)->truesize; + tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode)); +- sk_mem_reclaim(sk); +- if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && +- !tcp_under_memory_pressure(sk)) +- break; ++ if (!prev || goal <= 0) { ++ sk_mem_reclaim(sk); ++ if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && ++ !tcp_under_memory_pressure(sk)) ++ break; ++ goal = sk->sk_rcvbuf >> 3; ++ } + node = prev; + } while (node); + tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode); diff --git a/queue-4.9/tcp-helpers-to-send-special-dctcp-ack.patch b/queue-4.9/tcp-helpers-to-send-special-dctcp-ack.patch new file mode 100644 index 00000000000..a3450b65f31 --- /dev/null +++ b/queue-4.9/tcp-helpers-to-send-special-dctcp-ack.patch @@ -0,0 +1,79 @@ +From foo@baz Fri Jul 27 08:45:05 CEST 2018 +From: Yuchung Cheng +Date: Wed, 18 Jul 2018 13:56:34 -0700 +Subject: tcp: helpers to send special DCTCP ack + +From: Yuchung Cheng + +[ Upstream commit 2987babb6982306509380fc11b450227a844493b ] + +Refactor and create helpers to send the special ACK in DCTCP. + +Signed-off-by: Yuchung Cheng +Acked-by: Neal Cardwell +Signed-off-by: Eric Dumazet +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/tcp_output.c | 22 +++++++++++++++++----- + 1 file changed, 17 insertions(+), 5 deletions(-) + +--- a/net/ipv4/tcp_output.c ++++ b/net/ipv4/tcp_output.c +@@ -905,8 +905,8 @@ out: + * We are working here with either a clone of the original + * SKB, or a fresh unique copy made by the retransmit engine. + */ +-static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, +- gfp_t gfp_mask) ++static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, ++ int clone_it, gfp_t gfp_mask, u32 rcv_nxt) + { + const struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_sock *inet; +@@ -969,7 +969,7 @@ static int tcp_transmit_skb(struct sock + th->source = inet->inet_sport; + th->dest = inet->inet_dport; + th->seq = htonl(tcb->seq); +- th->ack_seq = htonl(tp->rcv_nxt); ++ th->ack_seq = htonl(rcv_nxt); + *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | + tcb->tcp_flags); + +@@ -1046,6 +1046,13 @@ static int tcp_transmit_skb(struct sock + return err; + } + ++static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, ++ gfp_t gfp_mask) ++{ ++ return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask, ++ tcp_sk(sk)->rcv_nxt); ++} ++ + /* This routine just queues the buffer for sending. + * + * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames, +@@ -3482,7 +3489,7 @@ void tcp_send_delayed_ack(struct sock *s + } + + /* This routine sends an ack and also updates the window. */ +-void tcp_send_ack(struct sock *sk) ++void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) + { + struct sk_buff *buff; + +@@ -3520,7 +3527,12 @@ void tcp_send_ack(struct sock *sk) + + /* Send it off, this clears delayed acks for us. */ + skb_mstamp_get(&buff->skb_mstamp); +- tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0); ++ __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt); ++} ++ ++void tcp_send_ack(struct sock *sk) ++{ ++ __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt); + } + EXPORT_SYMBOL_GPL(tcp_send_ack); +