From: Greg Kroah-Hartman Date: Sat, 19 Dec 2020 11:02:26 +0000 (+0100) Subject: 5.4-stable patches X-Git-Tag: v5.4.85~17 X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=0b633d2a7a81d306c4134ba36e3b29a688dd28d8;p=thirdparty%2Fkernel%2Fstable-queue.git 5.4-stable patches added patches: bridge-fix-a-deadlock-when-enabling-multicast-snooping.patch enetc-fix-reporting-of-h-w-packet-counters.patch ipv4-fix-error-return-code-in-rtm_to_fib_config.patch lan743x-fix-for-potential-null-pointer-dereference-with-bare-card.patch mac80211-mesh-fix-mesh_pathtbl_init-error-path.patch net-bridge-vlan-fix-error-return-code-in-__vlan_add.patch net-hns3-remove-a-misused-pragma-packed.patch net-ll_temac-fix-potential-null-dereference-in-temac_probe.patch net-mlx4_en-avoid-scheduling-restart-task-if-it-is-already-running.patch net-mlx4_en-handle-tx-error-cqe.patch net-stmmac-delete-the-eee_ctrl_timer-after-napi-disabled.patch net-stmmac-dwmac-meson8b-fix-mask-definition-of-the-m250_sel-mux.patch net-stmmac-free-tx-skb-buffer-in-stmmac_resume.patch tcp-fix-cwnd-limited-bug-for-tso-deferral-where-we-send-nothing.patch tcp-select-sane-initial-rcvq_space.space-for-big-mss.patch udp-fix-the-proto-value-passed-to-ip_protocol_deliver_rcu-for-the-segments.patch vrf-packets-with-lladdr-src-needs-dst-at-input-with-orig_iif-when-needs-strict.patch --- diff --git a/queue-5.4/bridge-fix-a-deadlock-when-enabling-multicast-snooping.patch b/queue-5.4/bridge-fix-a-deadlock-when-enabling-multicast-snooping.patch new file mode 100644 index 00000000000..19ac0912765 --- /dev/null +++ b/queue-5.4/bridge-fix-a-deadlock-when-enabling-multicast-snooping.patch @@ -0,0 +1,201 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Joseph Huang +Date: Fri, 4 Dec 2020 18:56:28 -0500 +Subject: bridge: Fix a deadlock when enabling multicast snooping + +From: Joseph Huang + +[ Upstream commit 851d0a73c90e6c8c63fef106c6c1e73df7e05d9d ] + +When enabling multicast snooping, bridge module deadlocks on multicast_lock +if 1) IPv6 is enabled, and 2) there is an existing querier on the same L2 +network. + +The deadlock was caused by the following sequence: While holding the lock, +br_multicast_open calls br_multicast_join_snoopers, which eventually causes +IP stack to (attempt to) send out a Listener Report (in igmp6_join_group). +Since the destination Ethernet address is a multicast address, br_dev_xmit +feeds the packet back to the bridge via br_multicast_rcv, which in turn +calls br_multicast_add_group, which then deadlocks on multicast_lock. + +The fix is to move the call br_multicast_join_snoopers outside of the +critical section. This works since br_multicast_join_snoopers only deals +with IP and does not modify any multicast data structures of the bridge, +so there's no need to hold the lock. + +Steps to reproduce: +1. sysctl net.ipv6.conf.all.force_mld_version=1 +2. have another querier +3. ip link set dev bridge type bridge mcast_snooping 0 && \ + ip link set dev bridge type bridge mcast_snooping 1 < deadlock > + +A typical call trace looks like the following: + +[ 936.251495] _raw_spin_lock+0x5c/0x68 +[ 936.255221] br_multicast_add_group+0x40/0x170 [bridge] +[ 936.260491] br_multicast_rcv+0x7ac/0xe30 [bridge] +[ 936.265322] br_dev_xmit+0x140/0x368 [bridge] +[ 936.269689] dev_hard_start_xmit+0x94/0x158 +[ 936.273876] __dev_queue_xmit+0x5ac/0x7f8 +[ 936.277890] dev_queue_xmit+0x10/0x18 +[ 936.281563] neigh_resolve_output+0xec/0x198 +[ 936.285845] ip6_finish_output2+0x240/0x710 +[ 936.290039] __ip6_finish_output+0x130/0x170 +[ 936.294318] ip6_output+0x6c/0x1c8 +[ 936.297731] NF_HOOK.constprop.0+0xd8/0xe8 +[ 936.301834] igmp6_send+0x358/0x558 +[ 936.305326] igmp6_join_group.part.0+0x30/0xf0 +[ 936.309774] igmp6_group_added+0xfc/0x110 +[ 936.313787] __ipv6_dev_mc_inc+0x1a4/0x290 +[ 936.317885] ipv6_dev_mc_inc+0x10/0x18 +[ 936.321677] br_multicast_open+0xbc/0x110 [bridge] +[ 936.326506] br_multicast_toggle+0xec/0x140 [bridge] + +Fixes: 4effd28c1245 ("bridge: join all-snoopers multicast address") +Signed-off-by: Joseph Huang +Acked-by: Nikolay Aleksandrov +Link: https://lore.kernel.org/r/20201204235628.50653-1-Joseph.Huang@garmin.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Greg Kroah-Hartman +--- + net/bridge/br_device.c | 6 ++++++ + net/bridge/br_multicast.c | 34 +++++++++++++++++++++++++--------- + net/bridge/br_private.h | 10 ++++++++++ + 3 files changed, 41 insertions(+), 9 deletions(-) + +--- a/net/bridge/br_device.c ++++ b/net/bridge/br_device.c +@@ -168,6 +168,9 @@ static int br_dev_open(struct net_device + br_stp_enable_bridge(br); + br_multicast_open(br); + ++ if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) ++ br_multicast_join_snoopers(br); ++ + return 0; + } + +@@ -188,6 +191,9 @@ static int br_dev_stop(struct net_device + br_stp_disable_bridge(br); + br_multicast_stop(br); + ++ if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) ++ br_multicast_leave_snoopers(br); ++ + netif_stop_queue(dev); + + return 0; +--- a/net/bridge/br_multicast.c ++++ b/net/bridge/br_multicast.c +@@ -1848,7 +1848,7 @@ static inline void br_ip6_multicast_join + } + #endif + +-static void br_multicast_join_snoopers(struct net_bridge *br) ++void br_multicast_join_snoopers(struct net_bridge *br) + { + br_ip4_multicast_join_snoopers(br); + br_ip6_multicast_join_snoopers(br); +@@ -1879,7 +1879,7 @@ static inline void br_ip6_multicast_leav + } + #endif + +-static void br_multicast_leave_snoopers(struct net_bridge *br) ++void br_multicast_leave_snoopers(struct net_bridge *br) + { + br_ip4_multicast_leave_snoopers(br); + br_ip6_multicast_leave_snoopers(br); +@@ -1898,9 +1898,6 @@ static void __br_multicast_open(struct n + + void br_multicast_open(struct net_bridge *br) + { +- if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) +- br_multicast_join_snoopers(br); +- + __br_multicast_open(br, &br->ip4_own_query); + #if IS_ENABLED(CONFIG_IPV6) + __br_multicast_open(br, &br->ip6_own_query); +@@ -1916,9 +1913,6 @@ void br_multicast_stop(struct net_bridge + del_timer_sync(&br->ip6_other_query.timer); + del_timer_sync(&br->ip6_own_query.timer); + #endif +- +- if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) +- br_multicast_leave_snoopers(br); + } + + void br_multicast_dev_del(struct net_bridge *br) +@@ -2049,6 +2043,7 @@ static void br_multicast_start_querier(s + int br_multicast_toggle(struct net_bridge *br, unsigned long val) + { + struct net_bridge_port *port; ++ bool change_snoopers = false; + + spin_lock_bh(&br->multicast_lock); + if (!!br_opt_get(br, BROPT_MULTICAST_ENABLED) == !!val) +@@ -2057,7 +2052,7 @@ int br_multicast_toggle(struct net_bridg + br_mc_disabled_update(br->dev, val); + br_opt_toggle(br, BROPT_MULTICAST_ENABLED, !!val); + if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) { +- br_multicast_leave_snoopers(br); ++ change_snoopers = true; + goto unlock; + } + +@@ -2068,9 +2063,30 @@ int br_multicast_toggle(struct net_bridg + list_for_each_entry(port, &br->port_list, list) + __br_multicast_enable_port(port); + ++ change_snoopers = true; ++ + unlock: + spin_unlock_bh(&br->multicast_lock); + ++ /* br_multicast_join_snoopers has the potential to cause ++ * an MLD Report/Leave to be delivered to br_multicast_rcv, ++ * which would in turn call br_multicast_add_group, which would ++ * attempt to acquire multicast_lock. This function should be ++ * called after the lock has been released to avoid deadlocks on ++ * multicast_lock. ++ * ++ * br_multicast_leave_snoopers does not have the problem since ++ * br_multicast_rcv first checks BROPT_MULTICAST_ENABLED, and ++ * returns without calling br_multicast_ipv4/6_rcv if it's not ++ * enabled. Moved both functions out just for symmetry. ++ */ ++ if (change_snoopers) { ++ if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) ++ br_multicast_join_snoopers(br); ++ else ++ br_multicast_leave_snoopers(br); ++ } ++ + return 0; + } + +--- a/net/bridge/br_private.h ++++ b/net/bridge/br_private.h +@@ -665,6 +665,8 @@ void br_multicast_del_port(struct net_br + void br_multicast_enable_port(struct net_bridge_port *port); + void br_multicast_disable_port(struct net_bridge_port *port); + void br_multicast_init(struct net_bridge *br); ++void br_multicast_join_snoopers(struct net_bridge *br); ++void br_multicast_leave_snoopers(struct net_bridge *br); + void br_multicast_open(struct net_bridge *br); + void br_multicast_stop(struct net_bridge *br); + void br_multicast_dev_del(struct net_bridge *br); +@@ -792,6 +794,14 @@ static inline void br_multicast_init(str + { + } + ++static inline void br_multicast_join_snoopers(struct net_bridge *br) ++{ ++} ++ ++static inline void br_multicast_leave_snoopers(struct net_bridge *br) ++{ ++} ++ + static inline void br_multicast_open(struct net_bridge *br) + { + } diff --git a/queue-5.4/enetc-fix-reporting-of-h-w-packet-counters.patch b/queue-5.4/enetc-fix-reporting-of-h-w-packet-counters.patch new file mode 100644 index 00000000000..b8c67f9ec4d --- /dev/null +++ b/queue-5.4/enetc-fix-reporting-of-h-w-packet-counters.patch @@ -0,0 +1,80 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Claudiu Manoil +Date: Fri, 4 Dec 2020 19:15:05 +0200 +Subject: enetc: Fix reporting of h/w packet counters + +From: Claudiu Manoil + +[ Upstream commit eb96b686fc2c601e78903cc61b6cf4588ddde013 ] + +Noticed some inconsistencies in packet statistics reporting. +This patch adds the missing Tx packet counter registers to +ethtool reporting and fixes the information strings for a +few of them. + +Fixes: 16eb4c85c964 ("enetc: Add ethtool statistics") +Signed-off-by: Claudiu Manoil +Link: https://lore.kernel.org/r/20201204171505.21389-1-claudiu.manoil@nxp.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/freescale/enetc/enetc_ethtool.c | 10 +++++++--- + drivers/net/ethernet/freescale/enetc/enetc_hw.h | 10 +++++++--- + 2 files changed, 14 insertions(+), 6 deletions(-) + +--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c ++++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +@@ -141,8 +141,8 @@ static const struct { + { ENETC_PM0_R255, "MAC rx 128-255 byte packets" }, + { ENETC_PM0_R511, "MAC rx 256-511 byte packets" }, + { ENETC_PM0_R1023, "MAC rx 512-1023 byte packets" }, +- { ENETC_PM0_R1518, "MAC rx 1024-1518 byte packets" }, +- { ENETC_PM0_R1519X, "MAC rx 1519 to max-octet packets" }, ++ { ENETC_PM0_R1522, "MAC rx 1024-1522 byte packets" }, ++ { ENETC_PM0_R1523X, "MAC rx 1523 to max-octet packets" }, + { ENETC_PM0_ROVR, "MAC rx oversized packets" }, + { ENETC_PM0_RJBR, "MAC rx jabber packets" }, + { ENETC_PM0_RFRG, "MAC rx fragment packets" }, +@@ -161,9 +161,13 @@ static const struct { + { ENETC_PM0_TBCA, "MAC tx broadcast frames" }, + { ENETC_PM0_TPKT, "MAC tx packets" }, + { ENETC_PM0_TUND, "MAC tx undersized packets" }, ++ { ENETC_PM0_T64, "MAC tx 64 byte packets" }, + { ENETC_PM0_T127, "MAC tx 65-127 byte packets" }, ++ { ENETC_PM0_T255, "MAC tx 128-255 byte packets" }, ++ { ENETC_PM0_T511, "MAC tx 256-511 byte packets" }, + { ENETC_PM0_T1023, "MAC tx 512-1023 byte packets" }, +- { ENETC_PM0_T1518, "MAC tx 1024-1518 byte packets" }, ++ { ENETC_PM0_T1522, "MAC tx 1024-1522 byte packets" }, ++ { ENETC_PM0_T1523X, "MAC tx 1523 to max-octet packets" }, + { ENETC_PM0_TCNP, "MAC tx control packets" }, + { ENETC_PM0_TDFR, "MAC tx deferred packets" }, + { ENETC_PM0_TMCOL, "MAC tx multiple collisions" }, +--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h ++++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h +@@ -239,8 +239,8 @@ enum enetc_bdr_type {TX, RX}; + #define ENETC_PM0_R255 0x8180 + #define ENETC_PM0_R511 0x8188 + #define ENETC_PM0_R1023 0x8190 +-#define ENETC_PM0_R1518 0x8198 +-#define ENETC_PM0_R1519X 0x81A0 ++#define ENETC_PM0_R1522 0x8198 ++#define ENETC_PM0_R1523X 0x81A0 + #define ENETC_PM0_ROVR 0x81A8 + #define ENETC_PM0_RJBR 0x81B0 + #define ENETC_PM0_RFRG 0x81B8 +@@ -259,9 +259,13 @@ enum enetc_bdr_type {TX, RX}; + #define ENETC_PM0_TBCA 0x8250 + #define ENETC_PM0_TPKT 0x8260 + #define ENETC_PM0_TUND 0x8268 ++#define ENETC_PM0_T64 0x8270 + #define ENETC_PM0_T127 0x8278 ++#define ENETC_PM0_T255 0x8280 ++#define ENETC_PM0_T511 0x8288 + #define ENETC_PM0_T1023 0x8290 +-#define ENETC_PM0_T1518 0x8298 ++#define ENETC_PM0_T1522 0x8298 ++#define ENETC_PM0_T1523X 0x82A0 + #define ENETC_PM0_TCNP 0x82C0 + #define ENETC_PM0_TDFR 0x82D0 + #define ENETC_PM0_TMCOL 0x82D8 diff --git a/queue-5.4/ipv4-fix-error-return-code-in-rtm_to_fib_config.patch b/queue-5.4/ipv4-fix-error-return-code-in-rtm_to_fib_config.patch new file mode 100644 index 00000000000..c9076ef1113 --- /dev/null +++ b/queue-5.4/ipv4-fix-error-return-code-in-rtm_to_fib_config.patch @@ -0,0 +1,34 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Zhang Changzhong +Date: Fri, 4 Dec 2020 16:48:14 +0800 +Subject: ipv4: fix error return code in rtm_to_fib_config() + +From: Zhang Changzhong + +[ Upstream commit b410f04eb5b482b5efc4eee90de81ad35d3d923b ] + +Fix to return a negative error code from the error handling +case instead of 0, as done elsewhere in this function. + +Fixes: d15662682db2 ("ipv4: Allow ipv6 gateway with ipv4 routes") +Reported-by: Hulk Robot +Signed-off-by: Zhang Changzhong +Reviewed-by: David Ahern +Link: https://lore.kernel.org/r/1607071695-33740-1-git-send-email-zhangchangzhong@huawei.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/fib_frontend.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/net/ipv4/fib_frontend.c ++++ b/net/ipv4/fib_frontend.c +@@ -835,7 +835,7 @@ static int rtm_to_fib_config(struct net + if (has_gw && has_via) { + NL_SET_ERR_MSG(extack, + "Nexthop configuration can not contain both GATEWAY and VIA"); +- goto errout; ++ return -EINVAL; + } + + return 0; diff --git a/queue-5.4/lan743x-fix-for-potential-null-pointer-dereference-with-bare-card.patch b/queue-5.4/lan743x-fix-for-potential-null-pointer-dereference-with-bare-card.patch new file mode 100644 index 00000000000..dc85b616a25 --- /dev/null +++ b/queue-5.4/lan743x-fix-for-potential-null-pointer-dereference-with-bare-card.patch @@ -0,0 +1,87 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Sergej Bauer +Date: Mon, 2 Nov 2020 01:35:55 +0300 +Subject: lan743x: fix for potential NULL pointer dereference with bare card + +From: Sergej Bauer + +[ Upstream commit e9e13b6adc338be1eb88db87bcb392696144bd02 ] + +This is the 3rd revision of the patch fix for potential null pointer dereference +with lan743x card. + +The simpliest way to reproduce: boot with bare lan743x and issue "ethtool ethN" +commant where ethN is the interface with lan743x card. Example: + +$ sudo ethtool eth7 +dmesg: +[ 103.510336] BUG: kernel NULL pointer dereference, address: 0000000000000340 +... +[ 103.510836] RIP: 0010:phy_ethtool_get_wol+0x5/0x30 [libphy] +... +[ 103.511629] Call Trace: +[ 103.511666] lan743x_ethtool_get_wol+0x21/0x40 [lan743x] +[ 103.511724] dev_ethtool+0x1507/0x29d0 +[ 103.511769] ? avc_has_extended_perms+0x17f/0x440 +[ 103.511820] ? tomoyo_init_request_info+0x84/0x90 +[ 103.511870] ? tomoyo_path_number_perm+0x68/0x1e0 +[ 103.511919] ? tty_insert_flip_string_fixed_flag+0x82/0xe0 +[ 103.511973] ? inet_ioctl+0x187/0x1d0 +[ 103.512016] dev_ioctl+0xb5/0x560 +[ 103.512055] sock_do_ioctl+0xa0/0x140 +[ 103.512098] sock_ioctl+0x2cb/0x3c0 +[ 103.512139] __x64_sys_ioctl+0x84/0xc0 +[ 103.512183] do_syscall_64+0x33/0x80 +[ 103.512224] entry_SYSCALL_64_after_hwframe+0x44/0xa9 +[ 103.512274] RIP: 0033:0x7f54a9cba427 +... + +Previous versions can be found at: +v1: +initial version + https://lkml.org/lkml/2020/10/28/921 + +v2: +do not return from lan743x_ethtool_set_wol if netdev->phydev == NULL, just skip +the call of phy_ethtool_set_wol() instead. + https://lkml.org/lkml/2020/10/31/380 + +v3: +in function lan743x_ethtool_set_wol: +use ternary operator instead of if-else sentence (review by Markus Elfring) +return -ENETDOWN insted of -EIO (review by Andrew Lunn) + +Signed-off-by: Sergej Bauer + +Link: https://lore.kernel.org/r/20201101223556.16116-1-sbauer@blackbox.su +Signed-off-by: Jakub Kicinski +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/microchip/lan743x_ethtool.c | 9 +++++---- + 1 file changed, 5 insertions(+), 4 deletions(-) + +--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c ++++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c +@@ -780,7 +780,9 @@ static void lan743x_ethtool_get_wol(stru + + wol->supported = 0; + wol->wolopts = 0; +- phy_ethtool_get_wol(netdev->phydev, wol); ++ ++ if (netdev->phydev) ++ phy_ethtool_get_wol(netdev->phydev, wol); + + wol->supported |= WAKE_BCAST | WAKE_UCAST | WAKE_MCAST | + WAKE_MAGIC | WAKE_PHY | WAKE_ARP; +@@ -809,9 +811,8 @@ static int lan743x_ethtool_set_wol(struc + + device_set_wakeup_enable(&adapter->pdev->dev, (bool)wol->wolopts); + +- phy_ethtool_set_wol(netdev->phydev, wol); +- +- return 0; ++ return netdev->phydev ? phy_ethtool_set_wol(netdev->phydev, wol) ++ : -ENETDOWN; + } + #endif /* CONFIG_PM */ + diff --git a/queue-5.4/mac80211-mesh-fix-mesh_pathtbl_init-error-path.patch b/queue-5.4/mac80211-mesh-fix-mesh_pathtbl_init-error-path.patch new file mode 100644 index 00000000000..0610fbd3abf --- /dev/null +++ b/queue-5.4/mac80211-mesh-fix-mesh_pathtbl_init-error-path.patch @@ -0,0 +1,91 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Eric Dumazet +Date: Fri, 4 Dec 2020 08:24:28 -0800 +Subject: mac80211: mesh: fix mesh_pathtbl_init() error path + +From: Eric Dumazet + +[ Upstream commit 905b2032fa424f253d9126271439cc1db2b01130 ] + +If tbl_mpp can not be allocated, we call mesh_table_free(tbl_path) +while tbl_path rhashtable has not yet been initialized, which causes +panics. + +Simply factorize the rhashtable_init() call into mesh_table_alloc() + +WARNING: CPU: 1 PID: 8474 at kernel/workqueue.c:3040 __flush_work kernel/workqueue.c:3040 [inline] +WARNING: CPU: 1 PID: 8474 at kernel/workqueue.c:3040 __cancel_work_timer+0x514/0x540 kernel/workqueue.c:3136 +Modules linked in: +CPU: 1 PID: 8474 Comm: syz-executor663 Not tainted 5.10.0-rc6-syzkaller #0 +Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 +RIP: 0010:__flush_work kernel/workqueue.c:3040 [inline] +RIP: 0010:__cancel_work_timer+0x514/0x540 kernel/workqueue.c:3136 +Code: 5d c3 e8 bf ae 29 00 0f 0b e9 f0 fd ff ff e8 b3 ae 29 00 0f 0b 43 80 3c 3e 00 0f 85 31 ff ff ff e9 34 ff ff ff e8 9c ae 29 00 <0f> 0b e9 dc fe ff ff 89 e9 80 e1 07 80 c1 03 38 c1 0f 8c 7d fd ff +RSP: 0018:ffffc9000165f5a0 EFLAGS: 00010293 +RAX: ffffffff814b7064 RBX: 0000000000000001 RCX: ffff888021c80000 +RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 +RBP: ffff888024039ca0 R08: dffffc0000000000 R09: fffffbfff1dd3e64 +R10: fffffbfff1dd3e64 R11: 0000000000000000 R12: 1ffff920002cbebd +R13: ffff888024039c88 R14: 1ffff11004807391 R15: dffffc0000000000 +FS: 0000000001347880(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000 +CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +CR2: 0000000020000140 CR3: 000000002cc0a000 CR4: 00000000001506e0 +DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 +DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 +Call Trace: + rhashtable_free_and_destroy+0x25/0x9c0 lib/rhashtable.c:1137 + mesh_table_free net/mac80211/mesh_pathtbl.c:69 [inline] + mesh_pathtbl_init+0x287/0x2e0 net/mac80211/mesh_pathtbl.c:785 + ieee80211_mesh_init_sdata+0x2ee/0x530 net/mac80211/mesh.c:1591 + ieee80211_setup_sdata+0x733/0xc40 net/mac80211/iface.c:1569 + ieee80211_if_add+0xd5c/0x1cd0 net/mac80211/iface.c:1987 + ieee80211_add_iface+0x59/0x130 net/mac80211/cfg.c:125 + rdev_add_virtual_intf net/wireless/rdev-ops.h:45 [inline] + nl80211_new_interface+0x563/0xb40 net/wireless/nl80211.c:3855 + genl_family_rcv_msg_doit net/netlink/genetlink.c:739 [inline] + genl_family_rcv_msg net/netlink/genetlink.c:783 [inline] + genl_rcv_msg+0xe4e/0x1280 net/netlink/genetlink.c:800 + netlink_rcv_skb+0x190/0x3a0 net/netlink/af_netlink.c:2494 + genl_rcv+0x24/0x40 net/netlink/genetlink.c:811 + netlink_unicast_kernel net/netlink/af_netlink.c:1304 [inline] + netlink_unicast+0x780/0x930 net/netlink/af_netlink.c:1330 + netlink_sendmsg+0x9a8/0xd40 net/netlink/af_netlink.c:1919 + sock_sendmsg_nosec net/socket.c:651 [inline] + sock_sendmsg net/socket.c:671 [inline] + ____sys_sendmsg+0x519/0x800 net/socket.c:2353 + ___sys_sendmsg net/socket.c:2407 [inline] + __sys_sendmsg+0x2b1/0x360 net/socket.c:2440 + do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 + entry_SYSCALL_64_after_hwframe+0x44/0xa9 + +Fixes: 60854fd94573 ("mac80211: mesh: convert path table to rhashtable") +Signed-off-by: Eric Dumazet +Reported-by: syzbot +Reviewed-by: Johannes Berg +Link: https://lore.kernel.org/r/20201204162428.2583119-1-eric.dumazet@gmail.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Greg Kroah-Hartman +--- + net/mac80211/mesh_pathtbl.c | 4 +--- + 1 file changed, 1 insertion(+), 3 deletions(-) + +--- a/net/mac80211/mesh_pathtbl.c ++++ b/net/mac80211/mesh_pathtbl.c +@@ -60,6 +60,7 @@ static struct mesh_table *mesh_table_all + atomic_set(&newtbl->entries, 0); + spin_lock_init(&newtbl->gates_lock); + spin_lock_init(&newtbl->walk_lock); ++ rhashtable_init(&newtbl->rhead, &mesh_rht_params); + + return newtbl; + } +@@ -775,9 +776,6 @@ int mesh_pathtbl_init(struct ieee80211_s + goto free_path; + } + +- rhashtable_init(&tbl_path->rhead, &mesh_rht_params); +- rhashtable_init(&tbl_mpp->rhead, &mesh_rht_params); +- + sdata->u.mesh.mesh_paths = tbl_path; + sdata->u.mesh.mpp_paths = tbl_mpp; + diff --git a/queue-5.4/net-bridge-vlan-fix-error-return-code-in-__vlan_add.patch b/queue-5.4/net-bridge-vlan-fix-error-return-code-in-__vlan_add.patch new file mode 100644 index 00000000000..f8c8bf31dae --- /dev/null +++ b/queue-5.4/net-bridge-vlan-fix-error-return-code-in-__vlan_add.patch @@ -0,0 +1,37 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Zhang Changzhong +Date: Fri, 4 Dec 2020 16:48:56 +0800 +Subject: net: bridge: vlan: fix error return code in __vlan_add() + +From: Zhang Changzhong + +[ Upstream commit ee4f52a8de2c6f78b01f10b4c330867d88c1653a ] + +Fix to return a negative error code from the error handling +case instead of 0, as done elsewhere in this function. + +Fixes: f8ed289fab84 ("bridge: vlan: use br_vlan_(get|put)_master to deal with refcounts") +Reported-by: Hulk Robot +Signed-off-by: Zhang Changzhong +Acked-by: Nikolay Aleksandrov +Link: https://lore.kernel.org/r/1607071737-33875-1-git-send-email-zhangchangzhong@huawei.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Greg Kroah-Hartman +--- + net/bridge/br_vlan.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +--- a/net/bridge/br_vlan.c ++++ b/net/bridge/br_vlan.c +@@ -260,8 +260,10 @@ static int __vlan_add(struct net_bridge_ + } + + masterv = br_vlan_get_master(br, v->vid, extack); +- if (!masterv) ++ if (!masterv) { ++ err = -ENOMEM; + goto out_filt; ++ } + v->brvlan = masterv; + if (br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)) { + v->stats = netdev_alloc_pcpu_stats(struct br_vlan_stats); diff --git a/queue-5.4/net-hns3-remove-a-misused-pragma-packed.patch b/queue-5.4/net-hns3-remove-a-misused-pragma-packed.patch new file mode 100644 index 00000000000..063b8327145 --- /dev/null +++ b/queue-5.4/net-hns3-remove-a-misused-pragma-packed.patch @@ -0,0 +1,51 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Huazhong Tan +Date: Mon, 7 Dec 2020 15:20:25 +0800 +Subject: net: hns3: remove a misused pragma packed + +From: Huazhong Tan + +[ Upstream commit 61f54de2e9194f01874d5eda12037b0978e77519 ] + +hclge_dbg_reg_info[] is defined as an array of packed structure +accidentally. However, this array contains pointers, which are +no longer aligned naturally, and cannot be relocated on PPC64. +Hence, when compile-testing this driver on PPC64 with +CONFIG_RELOCATABLE=y (e.g. PowerPC allyesconfig), there will be +some warnings. + +Since each field in structure hclge_qos_pri_map_cmd and +hclge_dbg_bitmap_cmd is type u8, the pragma packed is unnecessary +for these two structures as well, so remove the pragma packed in +hclge_debugfs.h to fix this issue, and this increases +hclge_dbg_reg_info[] by 4 bytes per entry. + +Fixes: a582b78dfc33 ("net: hns3: code optimization for debugfs related to "dump reg"") +Reported-by: Stephen Rothwell +Signed-off-by: Huazhong Tan +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h | 4 ---- + 1 file changed, 4 deletions(-) + +--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h ++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h +@@ -35,8 +35,6 @@ + + #define HCLGE_DBG_DFX_SSU_2_OFFSET 12 + +-#pragma pack(1) +- + struct hclge_qos_pri_map_cmd { + u8 pri0_tc : 4, + pri1_tc : 4; +@@ -85,8 +83,6 @@ struct hclge_dbg_reg_type_info { + struct hclge_dbg_reg_common_msg reg_msg; + }; + +-#pragma pack() +- + static struct hclge_dbg_dfx_message hclge_dbg_bios_common_reg[] = { + {false, "Reserved"}, + {true, "BP_CPU_STATE"}, diff --git a/queue-5.4/net-ll_temac-fix-potential-null-dereference-in-temac_probe.patch b/queue-5.4/net-ll_temac-fix-potential-null-dereference-in-temac_probe.patch new file mode 100644 index 00000000000..42609991a46 --- /dev/null +++ b/queue-5.4/net-ll_temac-fix-potential-null-dereference-in-temac_probe.patch @@ -0,0 +1,49 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Zhang Changzhong +Date: Tue, 8 Dec 2020 09:53:42 +0800 +Subject: net: ll_temac: Fix potential NULL dereference in temac_probe() + +From: Zhang Changzhong + +[ Upstream commit cc6596fc7295e9dcd78156ed42f9f8e1221f7530 ] + +platform_get_resource() may fail and in this case a NULL dereference +will occur. + +Fix it to use devm_platform_ioremap_resource() instead of calling +platform_get_resource() and devm_ioremap(). + +This is detected by Coccinelle semantic patch. + +@@ +expression pdev, res, n, t, e, e1, e2; +@@ + +res = \(platform_get_resource\|platform_get_resource_byname\)(pdev, t, n); ++ if (!res) ++ return -EINVAL; +... when != res == NULL +e = devm_ioremap(e1, res->start, e2); + +Fixes: 8425c41d1ef7 ("net: ll_temac: Extend support to non-device-tree platforms") +Signed-off-by: Zhang Changzhong +Acked-by: Esben Haabendal +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/xilinx/ll_temac_main.c | 4 +--- + 1 file changed, 1 insertion(+), 3 deletions(-) + +--- a/drivers/net/ethernet/xilinx/ll_temac_main.c ++++ b/drivers/net/ethernet/xilinx/ll_temac_main.c +@@ -1425,9 +1425,7 @@ static int temac_probe(struct platform_d + of_node_put(dma_np); + } else if (pdata) { + /* 2nd memory resource specifies DMA registers */ +- res = platform_get_resource(pdev, IORESOURCE_MEM, 1); +- lp->sdma_regs = devm_ioremap_nocache(&pdev->dev, res->start, +- resource_size(res)); ++ lp->sdma_regs = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(lp->sdma_regs)) { + dev_err(&pdev->dev, + "could not map DMA registers\n"); diff --git a/queue-5.4/net-mlx4_en-avoid-scheduling-restart-task-if-it-is-already-running.patch b/queue-5.4/net-mlx4_en-avoid-scheduling-restart-task-if-it-is-already-running.patch new file mode 100644 index 00000000000..3ffb23718d1 --- /dev/null +++ b/queue-5.4/net-mlx4_en-avoid-scheduling-restart-task-if-it-is-already-running.patch @@ -0,0 +1,124 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Moshe Shemesh +Date: Wed, 9 Dec 2020 15:03:38 +0200 +Subject: net/mlx4_en: Avoid scheduling restart task if it is already running + +From: Moshe Shemesh + +[ Upstream commit fed91613c9dd455dd154b22fa8e11b8526466082 ] + +Add restarting state flag to avoid scheduling another restart task while +such task is already running. Change task name from watchdog_task to +restart_task to better fit the task role. + +Fixes: 1e338db56e5a ("mlx4_en: Fix a race at restart task") +Signed-off-by: Moshe Shemesh +Signed-off-by: Tariq Toukan +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 20 +++++++++++++------- + drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 7 ++++++- + 2 files changed, 19 insertions(+), 8 deletions(-) + +--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c ++++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +@@ -1383,8 +1383,10 @@ static void mlx4_en_tx_timeout(struct ne + } + + priv->port_stats.tx_timeout++; +- en_dbg(DRV, priv, "Scheduling watchdog\n"); +- queue_work(mdev->workqueue, &priv->watchdog_task); ++ if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state)) { ++ en_dbg(DRV, priv, "Scheduling port restart\n"); ++ queue_work(mdev->workqueue, &priv->restart_task); ++ } + } + + +@@ -1834,6 +1836,7 @@ int mlx4_en_start_port(struct net_device + local_bh_enable(); + } + ++ clear_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state); + netif_tx_start_all_queues(dev); + netif_device_attach(dev); + +@@ -2004,7 +2007,7 @@ void mlx4_en_stop_port(struct net_device + static void mlx4_en_restart(struct work_struct *work) + { + struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv, +- watchdog_task); ++ restart_task); + struct mlx4_en_dev *mdev = priv->mdev; + struct net_device *dev = priv->dev; + +@@ -2386,7 +2389,7 @@ static int mlx4_en_change_mtu(struct net + if (netif_running(dev)) { + mutex_lock(&mdev->state_lock); + if (!mdev->device_up) { +- /* NIC is probably restarting - let watchdog task reset ++ /* NIC is probably restarting - let restart task reset + * the port */ + en_dbg(DRV, priv, "Change MTU called with card down!?\n"); + } else { +@@ -2395,7 +2398,9 @@ static int mlx4_en_change_mtu(struct net + if (err) { + en_err(priv, "Failed restarting port:%d\n", + priv->port); +- queue_work(mdev->workqueue, &priv->watchdog_task); ++ if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, ++ &priv->state)) ++ queue_work(mdev->workqueue, &priv->restart_task); + } + } + mutex_unlock(&mdev->state_lock); +@@ -2865,7 +2870,8 @@ static int mlx4_xdp_set(struct net_devic + if (err) { + en_err(priv, "Failed starting port %d for XDP change\n", + priv->port); +- queue_work(mdev->workqueue, &priv->watchdog_task); ++ if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state)) ++ queue_work(mdev->workqueue, &priv->restart_task); + } + } + +@@ -3263,7 +3269,7 @@ int mlx4_en_init_netdev(struct mlx4_en_d + priv->counter_index = MLX4_SINK_COUNTER_INDEX(mdev->dev); + spin_lock_init(&priv->stats_lock); + INIT_WORK(&priv->rx_mode_task, mlx4_en_do_set_rx_mode); +- INIT_WORK(&priv->watchdog_task, mlx4_en_restart); ++ INIT_WORK(&priv->restart_task, mlx4_en_restart); + INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate); + INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats); + INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task); +--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h ++++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +@@ -530,6 +530,10 @@ struct mlx4_en_stats_bitmap { + struct mutex mutex; /* for mutual access to stats bitmap */ + }; + ++enum { ++ MLX4_EN_STATE_FLAG_RESTARTING, ++}; ++ + struct mlx4_en_priv { + struct mlx4_en_dev *mdev; + struct mlx4_en_port_profile *prof; +@@ -595,7 +599,7 @@ struct mlx4_en_priv { + struct mlx4_en_cq *rx_cq[MAX_RX_RINGS]; + struct mlx4_qp drop_qp; + struct work_struct rx_mode_task; +- struct work_struct watchdog_task; ++ struct work_struct restart_task; + struct work_struct linkstate_task; + struct delayed_work stats_task; + struct delayed_work service_task; +@@ -643,6 +647,7 @@ struct mlx4_en_priv { + u32 pflags; + u8 rss_key[MLX4_EN_RSS_KEY_SIZE]; + u8 rss_hash_fn; ++ unsigned long state; + }; + + enum mlx4_en_wol { diff --git a/queue-5.4/net-mlx4_en-handle-tx-error-cqe.patch b/queue-5.4/net-mlx4_en-handle-tx-error-cqe.patch new file mode 100644 index 00000000000..3b8a8efde35 --- /dev/null +++ b/queue-5.4/net-mlx4_en-handle-tx-error-cqe.patch @@ -0,0 +1,114 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Moshe Shemesh +Date: Wed, 9 Dec 2020 15:03:39 +0200 +Subject: net/mlx4_en: Handle TX error CQE + +From: Moshe Shemesh + +[ Upstream commit ba603d9d7b1215c72513d7c7aa02b6775fd4891b ] + +In case error CQE was found while polling TX CQ, the QP is in error +state and all posted WQEs will generate error CQEs without any data +transmitted. Fix it by reopening the channels, via same method used for +TX timeout handling. + +In addition add some more info on error CQE and WQE for debug. + +Fixes: bd2f631d7c60 ("net/mlx4_en: Notify user when TX ring in error state") +Signed-off-by: Moshe Shemesh +Signed-off-by: Tariq Toukan +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 1 + drivers/net/ethernet/mellanox/mlx4/en_tx.c | 40 ++++++++++++++++++++----- + drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 5 +++ + 3 files changed, 39 insertions(+), 7 deletions(-) + +--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c ++++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +@@ -1740,6 +1740,7 @@ int mlx4_en_start_port(struct net_device + mlx4_en_deactivate_cq(priv, cq); + goto tx_err; + } ++ clear_bit(MLX4_EN_TX_RING_STATE_RECOVERING, &tx_ring->state); + if (t != TX_XDP) { + tx_ring->tx_queue = netdev_get_tx_queue(dev, i); + tx_ring->recycle_ring = NULL; +--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c ++++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c +@@ -392,6 +392,35 @@ int mlx4_en_free_tx_buf(struct net_devic + return cnt; + } + ++static void mlx4_en_handle_err_cqe(struct mlx4_en_priv *priv, struct mlx4_err_cqe *err_cqe, ++ u16 cqe_index, struct mlx4_en_tx_ring *ring) ++{ ++ struct mlx4_en_dev *mdev = priv->mdev; ++ struct mlx4_en_tx_info *tx_info; ++ struct mlx4_en_tx_desc *tx_desc; ++ u16 wqe_index; ++ int desc_size; ++ ++ en_err(priv, "CQE error - cqn 0x%x, ci 0x%x, vendor syndrome: 0x%x syndrome: 0x%x\n", ++ ring->sp_cqn, cqe_index, err_cqe->vendor_err_syndrome, err_cqe->syndrome); ++ print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, err_cqe, sizeof(*err_cqe), ++ false); ++ ++ wqe_index = be16_to_cpu(err_cqe->wqe_index) & ring->size_mask; ++ tx_info = &ring->tx_info[wqe_index]; ++ desc_size = tx_info->nr_txbb << LOG_TXBB_SIZE; ++ en_err(priv, "Related WQE - qpn 0x%x, wqe index 0x%x, wqe size 0x%x\n", ring->qpn, ++ wqe_index, desc_size); ++ tx_desc = ring->buf + (wqe_index << LOG_TXBB_SIZE); ++ print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, tx_desc, desc_size, false); ++ ++ if (test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state)) ++ return; ++ ++ en_err(priv, "Scheduling port restart\n"); ++ queue_work(mdev->workqueue, &priv->restart_task); ++} ++ + bool mlx4_en_process_tx_cq(struct net_device *dev, + struct mlx4_en_cq *cq, int napi_budget) + { +@@ -438,13 +467,10 @@ bool mlx4_en_process_tx_cq(struct net_de + dma_rmb(); + + if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == +- MLX4_CQE_OPCODE_ERROR)) { +- struct mlx4_err_cqe *cqe_err = (struct mlx4_err_cqe *)cqe; +- +- en_err(priv, "CQE error - vendor syndrome: 0x%x syndrome: 0x%x\n", +- cqe_err->vendor_err_syndrome, +- cqe_err->syndrome); +- } ++ MLX4_CQE_OPCODE_ERROR)) ++ if (!test_and_set_bit(MLX4_EN_TX_RING_STATE_RECOVERING, &ring->state)) ++ mlx4_en_handle_err_cqe(priv, (struct mlx4_err_cqe *)cqe, index, ++ ring); + + /* Skip over last polled CQE */ + new_index = be16_to_cpu(cqe->wqe_index) & size_mask; +--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h ++++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +@@ -271,6 +271,10 @@ struct mlx4_en_page_cache { + } buf[MLX4_EN_CACHE_SIZE]; + }; + ++enum { ++ MLX4_EN_TX_RING_STATE_RECOVERING, ++}; ++ + struct mlx4_en_priv; + + struct mlx4_en_tx_ring { +@@ -317,6 +321,7 @@ struct mlx4_en_tx_ring { + * Only queue_stopped might be used if BQL is not properly working. + */ + unsigned long queue_stopped; ++ unsigned long state; + struct mlx4_hwq_resources sp_wqres; + struct mlx4_qp sp_qp; + struct mlx4_qp_context sp_context; diff --git a/queue-5.4/net-stmmac-delete-the-eee_ctrl_timer-after-napi-disabled.patch b/queue-5.4/net-stmmac-delete-the-eee_ctrl_timer-after-napi-disabled.patch new file mode 100644 index 00000000000..bef8df22f71 --- /dev/null +++ b/queue-5.4/net-stmmac-delete-the-eee_ctrl_timer-after-napi-disabled.patch @@ -0,0 +1,62 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Fugang Duan +Date: Mon, 7 Dec 2020 18:51:40 +0800 +Subject: net: stmmac: delete the eee_ctrl_timer after napi disabled + +From: Fugang Duan + +[ Upstream commit 5f58591323bf3f342920179f24515935c4b5fd60 ] + +There have chance to re-enable the eee_ctrl_timer and fire the timer +in napi callback after delete the timer in .stmmac_release(), which +introduces to access eee registers in the timer function after clocks +are disabled then causes system hang. Found this issue when do +suspend/resume and reboot stress test. + +It is safe to delete the timer after napi disabled and disable lpi mode. + +Fixes: d765955d2ae0b ("stmmac: add the Energy Efficient Ethernet support") +Signed-off-by: Fugang Duan +Signed-off-by: Joakim Zhang +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 13 ++++++++++--- + 1 file changed, 10 insertions(+), 3 deletions(-) + +--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c ++++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +@@ -2758,9 +2758,6 @@ static int stmmac_release(struct net_dev + struct stmmac_priv *priv = netdev_priv(dev); + u32 chan; + +- if (priv->eee_enabled) +- del_timer_sync(&priv->eee_ctrl_timer); +- + /* Stop and disconnect the PHY */ + phylink_stop(priv->phylink); + phylink_disconnect_phy(priv->phylink); +@@ -2777,6 +2774,11 @@ static int stmmac_release(struct net_dev + if (priv->lpi_irq > 0) + free_irq(priv->lpi_irq, dev); + ++ if (priv->eee_enabled) { ++ priv->tx_path_in_lpi_mode = false; ++ del_timer_sync(&priv->eee_ctrl_timer); ++ } ++ + /* Stop TX/RX DMA and clear the descriptors */ + stmmac_stop_all_dma(priv); + +@@ -4761,6 +4763,11 @@ int stmmac_suspend(struct device *dev) + for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++) + del_timer_sync(&priv->tx_queue[chan].txtimer); + ++ if (priv->eee_enabled) { ++ priv->tx_path_in_lpi_mode = false; ++ del_timer_sync(&priv->eee_ctrl_timer); ++ } ++ + /* Stop TX/RX DMA */ + stmmac_stop_all_dma(priv); + diff --git a/queue-5.4/net-stmmac-dwmac-meson8b-fix-mask-definition-of-the-m250_sel-mux.patch b/queue-5.4/net-stmmac-dwmac-meson8b-fix-mask-definition-of-the-m250_sel-mux.patch new file mode 100644 index 00000000000..d957e2e9635 --- /dev/null +++ b/queue-5.4/net-stmmac-dwmac-meson8b-fix-mask-definition-of-the-m250_sel-mux.patch @@ -0,0 +1,50 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Martin Blumenstingl +Date: Sat, 5 Dec 2020 22:32:07 +0100 +Subject: net: stmmac: dwmac-meson8b: fix mask definition of the m250_sel mux + +From: Martin Blumenstingl + +[ Upstream commit 82ca4c922b8992013a238d65cf4e60cc33e12f36 ] + +The m250_sel mux clock uses bit 4 in the PRG_ETH0 register. Fix this by +shifting the PRG_ETH0_CLK_M250_SEL_MASK accordingly as the "mask" in +struct clk_mux expects the mask relative to the "shift" field in the +same struct. + +While here, get rid of the PRG_ETH0_CLK_M250_SEL_SHIFT macro and use +__ffs() to determine it from the existing PRG_ETH0_CLK_M250_SEL_MASK +macro. + +Fixes: 566e8251625304 ("net: stmmac: add a glue driver for the Amlogic Meson 8b / GXBB DWMAC") +Signed-off-by: Martin Blumenstingl +Reviewed-by: Jerome Brunet +Link: https://lore.kernel.org/r/20201205213207.519341-1-martin.blumenstingl@googlemail.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c ++++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +@@ -29,7 +29,6 @@ + #define PRG_ETH0_EXT_RMII_MODE 4 + + /* mux to choose between fclk_div2 (bit unset) and mpll2 (bit set) */ +-#define PRG_ETH0_CLK_M250_SEL_SHIFT 4 + #define PRG_ETH0_CLK_M250_SEL_MASK GENMASK(4, 4) + + #define PRG_ETH0_TXDLY_SHIFT 5 +@@ -143,8 +142,9 @@ static int meson8b_init_rgmii_tx_clk(str + } + + clk_configs->m250_mux.reg = dwmac->regs + PRG_ETH0; +- clk_configs->m250_mux.shift = PRG_ETH0_CLK_M250_SEL_SHIFT; +- clk_configs->m250_mux.mask = PRG_ETH0_CLK_M250_SEL_MASK; ++ clk_configs->m250_mux.shift = __ffs(PRG_ETH0_CLK_M250_SEL_MASK); ++ clk_configs->m250_mux.mask = PRG_ETH0_CLK_M250_SEL_MASK >> ++ clk_configs->m250_mux.shift; + clk = meson8b_dwmac_register_clk(dwmac, "m250_sel", mux_parent_names, + MUX_CLK_NUM_PARENTS, &clk_mux_ops, + &clk_configs->m250_mux.hw); diff --git a/queue-5.4/net-stmmac-free-tx-skb-buffer-in-stmmac_resume.patch b/queue-5.4/net-stmmac-free-tx-skb-buffer-in-stmmac_resume.patch new file mode 100644 index 00000000000..44e02b62499 --- /dev/null +++ b/queue-5.4/net-stmmac-free-tx-skb-buffer-in-stmmac_resume.patch @@ -0,0 +1,111 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Fugang Duan +Date: Mon, 7 Dec 2020 18:51:39 +0800 +Subject: net: stmmac: free tx skb buffer in stmmac_resume() + +From: Fugang Duan + +[ Upstream commit 4ec236c7c51f89abb0224a4da4a6b77f9beb6600 ] + +When do suspend/resume test, there have WARN_ON() log dump from +stmmac_xmit() funciton, the code logic: + entry = tx_q->cur_tx; + first_entry = entry; + WARN_ON(tx_q->tx_skbuff[first_entry]); + +In normal case, tx_q->tx_skbuff[txq->cur_tx] should be NULL because +the skb should be handled and freed in stmmac_tx_clean(). + +But stmmac_resume() reset queue parameters like below, skb buffers +may not be freed. + tx_q->cur_tx = 0; + tx_q->dirty_tx = 0; + +So free tx skb buffer in stmmac_resume() to avoid warning and +memory leak. + +log: +[ 46.139824] ------------[ cut here ]------------ +[ 46.144453] WARNING: CPU: 0 PID: 0 at drivers/net/ethernet/stmicro/stmmac/stmmac_main.c:3235 stmmac_xmit+0x7a0/0x9d0 +[ 46.154969] Modules linked in: crct10dif_ce vvcam(O) flexcan can_dev +[ 46.161328] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G O 5.4.24-2.1.0+g2ad925d15481 #1 +[ 46.170369] Hardware name: NXP i.MX8MPlus EVK board (DT) +[ 46.175677] pstate: 80000005 (Nzcv daif -PAN -UAO) +[ 46.180465] pc : stmmac_xmit+0x7a0/0x9d0 +[ 46.184387] lr : dev_hard_start_xmit+0x94/0x158 +[ 46.188913] sp : ffff800010003cc0 +[ 46.192224] x29: ffff800010003cc0 x28: ffff000177e2a100 +[ 46.197533] x27: ffff000176ef0840 x26: ffff000176ef0090 +[ 46.202842] x25: 0000000000000000 x24: 0000000000000000 +[ 46.208151] x23: 0000000000000003 x22: ffff8000119ddd30 +[ 46.213460] x21: ffff00017636f000 x20: ffff000176ef0cc0 +[ 46.218769] x19: 0000000000000003 x18: 0000000000000000 +[ 46.224078] x17: 0000000000000000 x16: 0000000000000000 +[ 46.229386] x15: 0000000000000079 x14: 0000000000000000 +[ 46.234695] x13: 0000000000000003 x12: 0000000000000003 +[ 46.240003] x11: 0000000000000010 x10: 0000000000000010 +[ 46.245312] x9 : ffff00017002b140 x8 : 0000000000000000 +[ 46.250621] x7 : ffff00017636f000 x6 : 0000000000000010 +[ 46.255930] x5 : 0000000000000001 x4 : ffff000176ef0000 +[ 46.261238] x3 : 0000000000000003 x2 : 00000000ffffffff +[ 46.266547] x1 : ffff000177e2a000 x0 : 0000000000000000 +[ 46.271856] Call trace: +[ 46.274302] stmmac_xmit+0x7a0/0x9d0 +[ 46.277874] dev_hard_start_xmit+0x94/0x158 +[ 46.282056] sch_direct_xmit+0x11c/0x338 +[ 46.285976] __qdisc_run+0x118/0x5f0 +[ 46.289549] net_tx_action+0x110/0x198 +[ 46.293297] __do_softirq+0x120/0x23c +[ 46.296958] irq_exit+0xb8/0xd8 +[ 46.300098] __handle_domain_irq+0x64/0xb8 +[ 46.304191] gic_handle_irq+0x5c/0x148 +[ 46.307936] el1_irq+0xb8/0x180 +[ 46.311076] cpuidle_enter_state+0x84/0x360 +[ 46.315256] cpuidle_enter+0x34/0x48 +[ 46.318829] call_cpuidle+0x18/0x38 +[ 46.322314] do_idle+0x1e0/0x280 +[ 46.325539] cpu_startup_entry+0x24/0x40 +[ 46.329460] rest_init+0xd4/0xe0 +[ 46.332687] arch_call_rest_init+0xc/0x14 +[ 46.336695] start_kernel+0x420/0x44c +[ 46.340353] ---[ end trace bc1ee695123cbacd ]--- + +Fixes: 47dd7a540b8a0 ("net: add support for STMicroelectronics Ethernet controllers.") +Signed-off-by: Fugang Duan +Signed-off-by: Joakim Zhang +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 14 ++++++++++++++ + 1 file changed, 14 insertions(+) + +--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c ++++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +@@ -1442,6 +1442,19 @@ static void dma_free_tx_skbufs(struct st + } + + /** ++ * stmmac_free_tx_skbufs - free TX skb buffers ++ * @priv: private structure ++ */ ++static void stmmac_free_tx_skbufs(struct stmmac_priv *priv) ++{ ++ u32 tx_queue_cnt = priv->plat->tx_queues_to_use; ++ u32 queue; ++ ++ for (queue = 0; queue < tx_queue_cnt; queue++) ++ dma_free_tx_skbufs(priv, queue); ++} ++ ++/** + * free_dma_rx_desc_resources - free RX dma desc resources + * @priv: private structure + */ +@@ -4846,6 +4859,7 @@ int stmmac_resume(struct device *dev) + + stmmac_reset_queues_param(priv); + ++ stmmac_free_tx_skbufs(priv); + stmmac_clear_descriptors(priv); + + stmmac_hw_setup(ndev, false); diff --git a/queue-5.4/series b/queue-5.4/series index 1ee0ea3de83..5e735bec283 100644 --- a/queue-5.4/series +++ b/queue-5.4/series @@ -1 +1,18 @@ ptrace-prevent-kernel-infoleak-in-ptrace_get_syscall_info.patch +ipv4-fix-error-return-code-in-rtm_to_fib_config.patch +mac80211-mesh-fix-mesh_pathtbl_init-error-path.patch +net-bridge-vlan-fix-error-return-code-in-__vlan_add.patch +vrf-packets-with-lladdr-src-needs-dst-at-input-with-orig_iif-when-needs-strict.patch +net-hns3-remove-a-misused-pragma-packed.patch +udp-fix-the-proto-value-passed-to-ip_protocol_deliver_rcu-for-the-segments.patch +enetc-fix-reporting-of-h-w-packet-counters.patch +bridge-fix-a-deadlock-when-enabling-multicast-snooping.patch +net-stmmac-free-tx-skb-buffer-in-stmmac_resume.patch +tcp-select-sane-initial-rcvq_space.space-for-big-mss.patch +tcp-fix-cwnd-limited-bug-for-tso-deferral-where-we-send-nothing.patch +net-mlx4_en-avoid-scheduling-restart-task-if-it-is-already-running.patch +lan743x-fix-for-potential-null-pointer-dereference-with-bare-card.patch +net-mlx4_en-handle-tx-error-cqe.patch +net-ll_temac-fix-potential-null-dereference-in-temac_probe.patch +net-stmmac-dwmac-meson8b-fix-mask-definition-of-the-m250_sel-mux.patch +net-stmmac-delete-the-eee_ctrl_timer-after-napi-disabled.patch diff --git a/queue-5.4/tcp-fix-cwnd-limited-bug-for-tso-deferral-where-we-send-nothing.patch b/queue-5.4/tcp-fix-cwnd-limited-bug-for-tso-deferral-where-we-send-nothing.patch new file mode 100644 index 00000000000..bc9b12b2235 --- /dev/null +++ b/queue-5.4/tcp-fix-cwnd-limited-bug-for-tso-deferral-where-we-send-nothing.patch @@ -0,0 +1,86 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Neal Cardwell +Date: Tue, 8 Dec 2020 22:57:59 -0500 +Subject: tcp: fix cwnd-limited bug for TSO deferral where we send nothing + +From: Neal Cardwell + +[ Upstream commit 299bcb55ecd1412f6df606e9dc0912d55610029e ] + +When cwnd is not a multiple of the TSO skb size of N*MSS, we can get +into persistent scenarios where we have the following sequence: + +(1) ACK for full-sized skb of N*MSS arrives + -> tcp_write_xmit() transmit full-sized skb with N*MSS + -> move pacing release time forward + -> exit tcp_write_xmit() because pacing time is in the future + +(2) TSQ callback or TCP internal pacing timer fires + -> try to transmit next skb, but TSO deferral finds remainder of + available cwnd is not big enough to trigger an immediate send + now, so we defer sending until the next ACK. + +(3) repeat... + +So we can get into a case where we never mark ourselves as +cwnd-limited for many seconds at a time, even with +bulk/infinite-backlog senders, because: + +o In case (1) above, every time in tcp_write_xmit() we have enough +cwnd to send a full-sized skb, we are not fully using the cwnd +(because cwnd is not a multiple of the TSO skb size). So every time we +send data, we are not cwnd limited, and so in the cwnd-limited +tracking code in tcp_cwnd_validate() we mark ourselves as not +cwnd-limited. + +o In case (2) above, every time in tcp_write_xmit() that we try to +transmit the "remainder" of the cwnd but defer, we set the local +variable is_cwnd_limited to true, but we do not send any packets, so +sent_pkts is zero, so we don't call the cwnd-limited logic to update +tp->is_cwnd_limited. + +Fixes: ca8a22634381 ("tcp: make cwnd-limited checks measurement-based, and gentler") +Reported-by: Ingemar Johansson +Signed-off-by: Neal Cardwell +Signed-off-by: Yuchung Cheng +Acked-by: Soheil Hassas Yeganeh +Signed-off-by: Eric Dumazet +Link: https://lore.kernel.org/r/20201209035759.1225145-1-ncardwell.kernel@gmail.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/tcp_output.c | 9 ++++++--- + 1 file changed, 6 insertions(+), 3 deletions(-) + +--- a/net/ipv4/tcp_output.c ++++ b/net/ipv4/tcp_output.c +@@ -1654,7 +1654,8 @@ static void tcp_cwnd_validate(struct soc + * window, and remember whether we were cwnd-limited then. + */ + if (!before(tp->snd_una, tp->max_packets_seq) || +- tp->packets_out > tp->max_packets_out) { ++ tp->packets_out > tp->max_packets_out || ++ is_cwnd_limited) { + tp->max_packets_out = tp->packets_out; + tp->max_packets_seq = tp->snd_nxt; + tp->is_cwnd_limited = is_cwnd_limited; +@@ -2476,6 +2477,10 @@ repair: + else + tcp_chrono_stop(sk, TCP_CHRONO_RWND_LIMITED); + ++ is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd); ++ if (likely(sent_pkts || is_cwnd_limited)) ++ tcp_cwnd_validate(sk, is_cwnd_limited); ++ + if (likely(sent_pkts)) { + if (tcp_in_cwnd_reduction(sk)) + tp->prr_out += sent_pkts; +@@ -2483,8 +2488,6 @@ repair: + /* Send one loss probe per tail loss episode. */ + if (push_one != 2) + tcp_schedule_loss_probe(sk, false); +- is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd); +- tcp_cwnd_validate(sk, is_cwnd_limited); + return false; + } + return !tp->packets_out && !tcp_write_queue_empty(sk); diff --git a/queue-5.4/tcp-select-sane-initial-rcvq_space.space-for-big-mss.patch b/queue-5.4/tcp-select-sane-initial-rcvq_space.space-for-big-mss.patch new file mode 100644 index 00000000000..0b52181932e --- /dev/null +++ b/queue-5.4/tcp-select-sane-initial-rcvq_space.space-for-big-mss.patch @@ -0,0 +1,67 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Eric Dumazet +Date: Tue, 8 Dec 2020 08:21:31 -0800 +Subject: tcp: select sane initial rcvq_space.space for big MSS + +From: Eric Dumazet + +[ Upstream commit 72d05c00d7ecda85df29abd046da7e41cc071c17 ] + +Before commit a337531b942b ("tcp: up initial rmem to 128KB and SYN rwin to around 64KB") +small tcp_rmem[1] values were overridden by tcp_fixup_rcvbuf() to accommodate various MSS. + +This is no longer the case, and Hazem Mohamed Abuelfotoh reported +that DRS would not work for MTU 9000 endpoints receiving regular (1500 bytes) frames. + +Root cause is that tcp_init_buffer_space() uses tp->rcv_wnd for upper limit +of rcvq_space.space computation, while it can select later a smaller +value for tp->rcv_ssthresh and tp->window_clamp. + +ss -temoi on receiver would show : + +skmem:(r0,rb131072,t0,tb46080,f0,w0,o0,bl0,d0) rcv_space:62496 rcv_ssthresh:56596 + +This means that TCP can not increase its window in tcp_grow_window(), +and that DRS can never kick. + +Fix this by making sure that rcvq_space.space is not bigger than number of bytes +that can be held in TCP receive queue. + +People unable/unwilling to change their kernel can work around this issue by +selecting a bigger tcp_rmem[1] value as in : + +echo "4096 196608 6291456" >/proc/sys/net/ipv4/tcp_rmem + +Based on an initial report and patch from Hazem Mohamed Abuelfotoh + https://lore.kernel.org/netdev/20201204180622.14285-1-abuehaze@amazon.com/ + +Fixes: a337531b942b ("tcp: up initial rmem to 128KB and SYN rwin to around 64KB") +Fixes: 041a14d26715 ("tcp: start receiver buffer autotuning sooner") +Reported-by: Hazem Mohamed Abuelfotoh +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 | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +--- a/net/ipv4/tcp_input.c ++++ b/net/ipv4/tcp_input.c +@@ -446,7 +446,6 @@ void tcp_init_buffer_space(struct sock * + if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) + tcp_sndbuf_expand(sk); + +- tp->rcvq_space.space = min_t(u32, tp->rcv_wnd, TCP_INIT_CWND * tp->advmss); + tcp_mstamp_refresh(tp); + tp->rcvq_space.time = tp->tcp_mstamp; + tp->rcvq_space.seq = tp->copied_seq; +@@ -470,6 +469,8 @@ void tcp_init_buffer_space(struct sock * + + tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp); + tp->snd_cwnd_stamp = tcp_jiffies32; ++ tp->rcvq_space.space = min3(tp->rcv_ssthresh, tp->rcv_wnd, ++ (u32)TCP_INIT_CWND * tp->advmss); + } + + /* 4. Recalculate window clamp after socket hit its memory bounds. */ diff --git a/queue-5.4/udp-fix-the-proto-value-passed-to-ip_protocol_deliver_rcu-for-the-segments.patch b/queue-5.4/udp-fix-the-proto-value-passed-to-ip_protocol_deliver_rcu-for-the-segments.patch new file mode 100644 index 00000000000..8c48dda76c1 --- /dev/null +++ b/queue-5.4/udp-fix-the-proto-value-passed-to-ip_protocol_deliver_rcu-for-the-segments.patch @@ -0,0 +1,38 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Xin Long +Date: Mon, 7 Dec 2020 15:55:40 +0800 +Subject: udp: fix the proto value passed to ip_protocol_deliver_rcu for the segments + +From: Xin Long + +[ Upstream commit 10c678bd0a035ac2c64a9b26b222f20556227a53 ] + +Guillaume noticed that: for segments udp_queue_rcv_one_skb() returns the +proto, and it should pass "ret" unmodified to ip_protocol_deliver_rcu(). +Otherwize, with a negtive value passed, it will underflow inet_protos. + +This can be reproduced with IPIP FOU: + + # ip fou add port 5555 ipproto 4 + # ethtool -K eth1 rx-gro-list on + +Fixes: cf329aa42b66 ("udp: cope with UDP GRO packet misdirection") +Reported-by: Guillaume Nault +Signed-off-by: Xin Long +Signed-off-by: David S. Miller +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/udp.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/net/ipv4/udp.c ++++ b/net/ipv4/udp.c +@@ -2117,7 +2117,7 @@ static int udp_queue_rcv_skb(struct sock + __skb_pull(skb, skb_transport_offset(skb)); + ret = udp_queue_rcv_one_skb(sk, skb); + if (ret > 0) +- ip_protocol_deliver_rcu(dev_net(skb->dev), skb, -ret); ++ ip_protocol_deliver_rcu(dev_net(skb->dev), skb, ret); + } + return 0; + } diff --git a/queue-5.4/vrf-packets-with-lladdr-src-needs-dst-at-input-with-orig_iif-when-needs-strict.patch b/queue-5.4/vrf-packets-with-lladdr-src-needs-dst-at-input-with-orig_iif-when-needs-strict.patch new file mode 100644 index 00000000000..4896822b1c9 --- /dev/null +++ b/queue-5.4/vrf-packets-with-lladdr-src-needs-dst-at-input-with-orig_iif-when-needs-strict.patch @@ -0,0 +1,174 @@ +From foo@baz Sat Dec 19 11:44:48 AM CET 2020 +From: Stephen Suryaputra +Date: Thu, 3 Dec 2020 22:06:04 -0500 +Subject: vrf: packets with lladdr src needs dst at input with orig_iif when needs strict + +From: Stephen Suryaputra + +[ Upstream commit 205704c618af0ab2366015d2281a3b0814d918a0 ] + +Depending on the order of the routes to fe80::/64 are installed on the +VRF table, the NS for the source link-local address of the originator +might be sent to the wrong interface. + +This patch ensures that packets with link-local addr source is doing a +lookup with the orig_iif when the destination addr indicates that it +is strict. + +Add the reproducer as a use case in self test script fcnal-test.sh. + +Fixes: b4869aa2f881 ("net: vrf: ipv6 support for local traffic to local addresses") +Signed-off-by: Stephen Suryaputra +Reviewed-by: David Ahern +Link: https://lore.kernel.org/r/20201204030604.18828-1-ssuryaextr@gmail.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Greg Kroah-Hartman +--- + drivers/net/vrf.c | 10 ++- + tools/testing/selftests/net/fcnal-test.sh | 95 ++++++++++++++++++++++++++++++ + 2 files changed, 103 insertions(+), 2 deletions(-) + +--- a/drivers/net/vrf.c ++++ b/drivers/net/vrf.c +@@ -1038,11 +1038,17 @@ static struct sk_buff *vrf_ip6_rcv(struc + int orig_iif = skb->skb_iif; + bool need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr); + bool is_ndisc = ipv6_ndisc_frame(skb); ++ bool is_ll_src; + + /* loopback, multicast & non-ND link-local traffic; do not push through +- * packet taps again. Reset pkt_type for upper layers to process skb ++ * packet taps again. Reset pkt_type for upper layers to process skb. ++ * for packets with lladdr src, however, skip so that the dst can be ++ * determine at input using original ifindex in the case that daddr ++ * needs strict + */ +- if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) { ++ is_ll_src = ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL; ++ if (skb->pkt_type == PACKET_LOOPBACK || ++ (need_strict && !is_ndisc && !is_ll_src)) { + skb->dev = vrf_dev; + skb->skb_iif = vrf_dev->ifindex; + IP6CB(skb)->flags |= IP6SKB_L3SLAVE; +--- a/tools/testing/selftests/net/fcnal-test.sh ++++ b/tools/testing/selftests/net/fcnal-test.sh +@@ -239,6 +239,28 @@ setup_cmd_nsb() + fi + } + ++setup_cmd_nsc() ++{ ++ local cmd="$*" ++ local rc ++ ++ run_cmd_nsc ${cmd} ++ rc=$? ++ if [ $rc -ne 0 ]; then ++ # show user the command if not done so already ++ if [ "$VERBOSE" = "0" ]; then ++ echo "setup command: $cmd" ++ fi ++ echo "failed. stopping tests" ++ if [ "${PAUSE_ON_FAIL}" = "yes" ]; then ++ echo ++ echo "hit enter to continue" ++ read a ++ fi ++ exit $rc ++ fi ++} ++ + # set sysctl values in NS-A + set_sysctl() + { +@@ -447,6 +469,36 @@ setup() + sleep 1 + } + ++setup_lla_only() ++{ ++ # make sure we are starting with a clean slate ++ kill_procs ++ cleanup 2>/dev/null ++ ++ log_debug "Configuring network namespaces" ++ set -e ++ ++ create_ns ${NSA} "-" "-" ++ create_ns ${NSB} "-" "-" ++ create_ns ${NSC} "-" "-" ++ connect_ns ${NSA} ${NSA_DEV} "-" "-" \ ++ ${NSB} ${NSB_DEV} "-" "-" ++ connect_ns ${NSA} ${NSA_DEV2} "-" "-" \ ++ ${NSC} ${NSC_DEV} "-" "-" ++ ++ NSA_LINKIP6=$(get_linklocal ${NSA} ${NSA_DEV}) ++ NSB_LINKIP6=$(get_linklocal ${NSB} ${NSB_DEV}) ++ NSC_LINKIP6=$(get_linklocal ${NSC} ${NSC_DEV}) ++ ++ create_vrf ${NSA} ${VRF} ${VRF_TABLE} "-" "-" ++ ip -netns ${NSA} link set dev ${NSA_DEV} vrf ${VRF} ++ ip -netns ${NSA} link set dev ${NSA_DEV2} vrf ${VRF} ++ ++ set +e ++ ++ sleep 1 ++} ++ + ################################################################################ + # IPv4 + +@@ -3329,10 +3381,53 @@ use_case_br() + setup_cmd_nsb ip li del vlan100 2>/dev/null + } + ++# VRF only. ++# ns-A device is connected to both ns-B and ns-C on a single VRF but only has ++# LLA on the interfaces ++use_case_ping_lla_multi() ++{ ++ setup_lla_only ++ # only want reply from ns-A ++ setup_cmd_nsb sysctl -qw net.ipv6.icmp.echo_ignore_multicast=1 ++ setup_cmd_nsc sysctl -qw net.ipv6.icmp.echo_ignore_multicast=1 ++ ++ log_start ++ run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV} ++ log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Pre cycle, ping out ns-B" ++ ++ run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV} ++ log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Pre cycle, ping out ns-C" ++ ++ # cycle/flap the first ns-A interface ++ setup_cmd ip link set ${NSA_DEV} down ++ setup_cmd ip link set ${NSA_DEV} up ++ sleep 1 ++ ++ log_start ++ run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV} ++ log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV}, ping out ns-B" ++ run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV} ++ log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV}, ping out ns-C" ++ ++ # cycle/flap the second ns-A interface ++ setup_cmd ip link set ${NSA_DEV2} down ++ setup_cmd ip link set ${NSA_DEV2} up ++ sleep 1 ++ ++ log_start ++ run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV} ++ log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV2}, ping out ns-B" ++ run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV} ++ log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV2}, ping out ns-C" ++} ++ + use_cases() + { + log_section "Use cases" ++ log_subsection "Device enslaved to bridge" + use_case_br ++ log_subsection "Ping LLA with multiple interfaces" ++ use_case_ping_lla_multi + } + + ################################################################################