- 13 Nov, 2018 40 commits
-
-
Eric Dumazet authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit 0e1d6eca ] We have an impressive number of syzkaller bugs that are linked to the fact that syzbot was able to create a networking device with millions of TX (or RX) queues. Let's limit the number of RX/TX queues to 4096, this really should cover all known cases. A separate patch will add various cond_resched() in the loops handling sysfs entries at device creation and dismantle. Tested: lpaa6:~# ip link add gre-4097 numtxqueues 4097 numrxqueues 4097 type ip6gretap RTNETLINK answers: Invalid argument lpaa6:~# time ip link add gre-4096 numtxqueues 4096 numrxqueues 4096 type ip6gretap real 0m0.180s user 0m0.000s sys 0m0.107s Fixes: 76ff5cc9 ("rtnl: allow to specify number of rx and tx queues on device creation") Signed-off-by:
Eric Dumazet <edumazet@google.com> Reported-by:
syzbot <syzkaller@googlegroups.com> Signed-off-by:
David S. Miller <davem@davemloft.net> Signed-off-by:
Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by:
Juerg Haefliger <juergh@canonical.com> Signed-off-by:
Khalid Elmously <khalid.elmously@canonical.com>
-
Florian Fainelli authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit 45ec3185 ] The AON_PM_L2 is normally used to trigger and identify the source of a wake-up event. Since the RX_SYS clock is no longer turned off, we also have an interrupt being sent to the SYSTEMPORT INTRL_2_0 controller, and that interrupt remains active up until the magic packet detector is disabled which happens much later during the driver resumption. The race happens if we have a CPU that is entering the SYSTEMPORT INTRL2_0 handler during resume, and another CPU has managed to clear the wake-up interrupt during bcm_sysport_resume_from_wol(). In that case, we have the first CPU stuck in the interrupt handler with an interrupt cause that has been cleared under its feet, and so we keep returning IRQ_NONE and we never make any progress. This was not a problem before because we would always turn off the RX_SYS clock during WoL, so the SYSTEMPORT INTRL2_0 would also be turned off as well, thus not latching the interrupt. The fix is to make sure we do not enable either the MPD or BRCM_TAG_MATCH interrupts since those are redundant with what the AON_PM_L2 interrupt controller already processes and they would cause such a race to occur. Fixes: bb9051a2 ("net: systemport: Add support for WAKE_FILTER") Fixes: 83e82f4c ("net: systemport: add Wake-on-LAN support") Signed-off-by:
Florian Fainelli <f.fainelli@gmail.com> Signed-off-by:
-
Maxime Chevallier authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit 35f3625c ] When offloading the L3 and L4 csum computation on TX, we need to extract the l3_proto from the ethtype, independently of the presence of a vlan tag. The actual driver uses skb->protocol as-is, resulting in packets with the wrong L4 checksum being sent when there's a vlan tag in the packet header and checksum offloading is enabled. This commit makes use of vlan_protocol_get() to get the correct ethtype regardless the presence of a vlan tag. Fixes: 3f518509 ("ethernet: Add new driver for Marvell Armada 375 network unit") Signed-off-by:
Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by:
-
Ido Schimmel authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit 471b83bd ] team's ndo_add_slave() acquires 'team->lock' and later tries to open the newly enslaved device via dev_open(). This emits a 'NETDEV_UP' event that causes the VLAN driver to add VLAN 0 on the team device. team's ndo_vlan_rx_add_vid() will also try to acquire 'team->lock' and deadlock. Fix this by checking early at the enslavement function that a team device is not being enslaved to itself. A similar check was added to the bond driver in commit 09a89c21 ("bonding: disallow enslaving a bond to itself"). WARNING: possible recursive locking detected 4.18.0-rc7+ #176 Not tainted -------------------------------------------- syz-executor4/6391 is trying to acquire lock: (____ptrval____) (&team->lock){+.+.}, at: team_vlan_rx_add_vid+0x3b/0x1e0 drivers/net/team/team.c:1868 but task is already holding lock: (____ptrval____) (&team->lock){+.+.}, at: team_add_slave+0xdb/0x1c30 drivers/net/team/team.c:1947 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&team->lock); lock(&team->lock); *** DEADLOCK *** May be due to missing lock nesting notation 2 locks held by syz-executor4/6391: #0: (____ptrval____) (rtnl_mutex){+.+.}, at: rtnl_lock net/core/rtnetlink.c:77 [inline] #0: (____ptrval____) (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x412/0xc30 net/core/rtnetlink.c:4662 #1: (____ptrval____) (&team->lock){+.+.}, at: team_add_slave+0xdb/0x1c30 drivers/net/team/team.c:1947 stack backtrace: CPU: 1 PID: 6391 Comm: syz-executor4 Not tainted 4.18.0-rc7+ #176 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+0x1c9/0x2b4 lib/dump_stack.c:113 print_deadlock_bug kernel/locking/lockdep.c:1765 [inline] check_deadlock kernel/locking/lockdep.c:1809 [inline] validate_chain kernel/locking/lockdep.c:2405 [inline] __lock_acquire.cold.64+0x1fb/0x486 kernel/locking/lockdep.c:3435 lock_acquire+0x1e4/0x540 kernel/locking/lockdep.c:3924 __mutex_lock_common kernel/locking/mutex.c:757 [inline] __mutex_lock+0x176/0x1820 kernel/locking/mutex.c:894 mutex_lock_nested+0x16/0x20 kernel/locking/mutex.c:909 team_vlan_rx_add_vid+0x3b/0x1e0 drivers/net/team/team.c:1868 vlan_add_rx_filter_info+0x14a/0x1d0 net/8021q/vlan_core.c:210 __vlan_vid_add net/8021q/vlan_core.c:278 [inline] vlan_vid_add+0x63e/0x9d0 net/8021q/vlan_core.c:308 vlan_device_event.cold.12+0x2a/0x2f net/8021q/vlan.c:381 notifier_call_chain+0x180/0x390 kernel/notifier.c:93 __raw_notifier_call_chain kernel/notifier.c:394 [inline] raw_notifier_call_chain+0x2d/0x40 kernel/notifier.c:401 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1735 call_netdevice_notifiers net/core/dev.c:1753 [inline] dev_open+0x173/0x1b0 net/core/dev.c:1433 team_port_add drivers/net/team/team.c:1219 [inline] team_add_slave+0xa8b/0x1c30 drivers/net/team/team.c:1948 do_set_master+0x1c9/0x220 net/core/rtnetlink.c:2248 do_setlink+0xba4/0x3e10 net/core/rtnetlink.c:2382 rtnl_setlink+0x2a9/0x400 net/core/rtnetlink.c:2636 rtnetlink_rcv_msg+0x46e/0xc30 net/core/rtnetlink.c:4665 netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2455 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:4683 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x5a0/0x760 net/netlink/af_netlink.c:1343 netlink_sendmsg+0xa18/0xfd0 net/netlink/af_netlink.c:1908 sock_sendmsg_nosec net/socket.c:642 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:652 ___sys_sendmsg+0x7fd/0x930 net/socket.c:2126 __sys_sendmsg+0x11d/0x290 net/socket.c:2164 __do_sys_sendmsg net/socket.c:2173 [inline] __se_sys_sendmsg net/socket.c:2171 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2171 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x456b29 Code: fd b4 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 cb b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f9706bf8c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f9706bf96d4 RCX: 0000000000456b29 RDX: 0000000000000000 RSI: 0000000020000240 RDI: 0000000000000004 RBP: 00000000009300a0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff R13: 00000000004d3548 R14: 00000000004c8227 R15: 0000000000000000 Fixes: 87002b03 ("net: introduce vlan_vid_[add/del] and use them instead of direct [add/kill]_vid ndo calls") Signed-off-by:
Ido Schimmel <idosch@mellanox.com> Reported-and-tested-by: syzbot+bd051aba086537515cdb@syzkaller.appspotmail.com Signed-off-by:
-
Shahed Shaikh authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit c333fa0c ] In regular NIC transmission flow, driver always configures MAC using Tx queue zero descriptor as a part of MAC learning flow. But with multi Tx queue supported NIC, regular transmission can occur on any non-zero Tx queue and from that context it uses Tx queue zero descriptor to configure MAC, at the same time TX queue zero could be used by another CPU for regular transmission which could lead to Tx queue zero descriptor corruption and cause FW abort. This patch fixes this in such a way that driver always configures learned MAC address from the same Tx queue which is used for regular transmission. Fixes: 7e2cf4fe ("qlcnic: change driver hardware interface mechanism") Signed-off-by:
Shahed Shaikh <shahed.shaikh@cavium.com> Signed-off-by:
-
Yu Zhao authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit f7b2a56e ] Cancel pending work before freeing smsc75xx private data structure during binding. This fixes the following crash in the driver: BUG: unable to handle kernel NULL pointer dereference at 0000000000000050 IP: mutex_lock+0x2b/0x3f <snipped> Workqueue: events smsc75xx_deferred_multicast_write [smsc75xx] task: ffff8caa83e85700 task.stack: ffff948b80518000 RIP: 0010:mutex_lock+0x2b/0x3f <snipped> Call Trace: smsc75xx_deferred_multicast_write+0x40/0x1af [smsc75xx] process_one_work+0x18d/0x2fc worker_thread+0x1a2/0x269 ? pr_cont_work+0x58/0x58 kthread+0xfa/0x10a ? pr_cont_work+0x58/0x58 ? rcu_read_unlock_sched_notrace+0x48/0x48 ret_from_fork+0x22/0x40 Signed-off-by:
Yu Zhao <yuzhao@google.com> Signed-off-by:
-
Sean Tranchetti authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit f88b4c01 ] netlbl_unlabel_addrinfo_get() assumes that if it finds the NLBL_UNLABEL_A_IPV4ADDR attribute, it must also have the NLBL_UNLABEL_A_IPV4MASK attribute as well. However, this is not necessarily the case as the current checks in netlbl_unlabel_staticadd() and friends are not sufficent to enforce this. If passed a netlink message with NLBL_UNLABEL_A_IPV4ADDR, NLBL_UNLABEL_A_IPV6ADDR, and NLBL_UNLABEL_A_IPV6MASK attributes, these functions will all call netlbl_unlabel_addrinfo_get() which will then attempt dereference NULL when fetching the non-existent NLBL_UNLABEL_A_IPV4MASK attribute: Unable to handle kernel NULL pointer dereference at virtual address 0 Process unlab (pid: 31762, stack limit = 0xffffff80502d8000) Call trace: netlbl_unlabel_addrinfo_get+0x44/0xd8 netlbl_unlabel_staticremovedef+0x98/0xe0 genl_rcv_msg+0x354/0x388 netlink_rcv_skb+0xac/0x118 genl_rcv+0x34/0x48 netlink_unicast+0x158/0x1f0 netlink_sendmsg+0x32c/0x338 sock_sendmsg+0x44/0x60 ___sys_sendmsg+0x1d0/0x2a8 __sys_sendmsg+0x64/0xb4 SyS_sendmsg+0x34/0x4c el0_svc_naked+0x34/0x38 Code: 51001149 7100113f 540000a0 f9401508 (79400108) ---[ end trace f6438a488e737143 ]--- Kernel panic - not syncing: Fatal exception Signed-off-by:
Sean Tranchetti <stranche@codeaurora.org> Signed-off-by:
-
Jeff Barnhill authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit 86f9bd1f ] The backend handling for /proc/net/if_inet6 in addrconf.c doesn't properly handle starting/stopping the iteration. The problem is that at some point during the iteration, an overflow is detected and the process is subsequently stopped. The item being shown via seq_printf() when the overflow occurs is not actually shown, though. When start() is subsequently called to resume iterating, it returns the next item, and thus the item that was being processed when the overflow occurred never gets printed. Alter the meaning of the private data member "offset". Currently, when it is not 0 (which only happens at the very beginning), "offset" represents the next hlist item to be printed. After this change, "offset" always represents the current item. This is also consistent with the private data member "bucket", which represents the current bucket, and also the use of "pos" as defined in seq_file.txt: The pos passed to start() will always be either zero, or the most recent pos used in the previous session. Signed-off-by:
Jeff Barnhill <0xeffeff@gmail.com> Signed-off-by:
-
Sabrina Dubroca authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit af7d6cce ] Since commit 5aad1de5 ("ipv4: use separate genid for next hop exceptions"), exceptions get deprecated separately from cached routes. In particular, administrative changes don't clear PMTU anymore. As Stefano described in commit e9fa1495 ("ipv6: Reflect MTU changes on PMTU of exceptions for MTU-less routes"), the PMTU discovered before the local MTU change can become stale: - if the local MTU is now lower than the PMTU, that PMTU is now incorrect - if the local MTU was the lowest value in the path, and is increased, we might discover a higher PMTU Similarly to what commit e9fa1495 did for IPv6, update PMTU in those cases. If the exception was locked, the discovered PMTU was smaller than the minimal accepted PMTU. In that case, if the new local MTU is smaller than the current PMTU, let PMTU discovery figure out if locking of the exception is still needed. To do this, we need to know the old link MTU in the NETDEV_CHANGEMTU notifier. By the time the notifier is called, dev->mtu has been changed. This patch adds the old MTU as additional information in the notifier structure, and a new call_netdevice_notifiers_u32() function. Fixes: 5aad1de5 ("ipv4: use separate genid for next hop exceptions") Signed-off-by:
Sabrina Dubroca <sd@queasysnail.net> Reviewed-by:
Stefano Brivio <sbrivio@redhat.com> Reviewed-by:
David Ahern <dsahern@gmail.com> Signed-off-by:
-
Eric Dumazet authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit 64199fc0 ] Caching ip_hdr(skb) before a call to pskb_may_pull() is buggy, do not do it. Fixes: 2efd4fca ("ip: in cmsg IP(V6)_ORIGDSTADDR call pskb_may_pull") Signed-off-by:
Willem de Bruijn <willemb@google.com> Signed-off-by:
-
Paolo Abeni authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit ccfec9e5] Cong noted that we need the same checks introduced by commit 76c0ddd8 ("ip6_tunnel: be careful when accessing the inner header") even for ipv4 tunnels. Fixes: c5441932 ("GRE: Refactor GRE tunneling code.") Suggested-by:
Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by:
Paolo Abeni <pabeni@redhat.com> Signed-off-by:
-
Paolo Abeni authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit 76c0ddd8 ] the ip6 tunnel xmit ndo assumes that the processed skb always contains an ip[v6] header, but syzbot has found a way to send frames that fall short of this assumption, leading to the following splat: BUG: KMSAN: uninit-value in ip6ip6_tnl_xmit net/ipv6/ip6_tunnel.c:1307 [inline] BUG: KMSAN: uninit-value in ip6_tnl_start_xmit+0x7d2/0x1ef0 net/ipv6/ip6_tunnel.c:1390 CPU: 0 PID: 4504 Comm: syz-executor558 Not tainted 4.16.0+ #87 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:683 ip6ip6_tnl_xmit net/ipv6/ip6_tunnel.c:1307 [inline] ip6_tnl_start_xmit+0x7d2/0x1ef0 net/ipv6/ip6_tunnel.c:1390 __netdev_start_xmit include/linux/netdevice.h:4066 [inline] netdev_start_xmit include/linux/netdevice.h:4075 [inline] xmit_one net/core/dev.c:3026 [inline] dev_hard_start_xmit+0x5f1/0xc70 net/core/dev.c:3042 __dev_queue_xmit+0x27ee/0x3520 net/core/dev.c:3557 dev_queue_xmit+0x4b/0x60 net/core/dev.c:3590 packet_snd net/packet/af_packet.c:2944 [inline] packet_sendmsg+0x7c70/0x8a30 net/packet/af_packet.c:2969 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] ___sys_sendmsg+0xec0/0x1310 net/socket.c:2046 __sys_sendmmsg+0x42d/0x800 net/socket.c:2136 SYSC_sendmmsg+0xc4/0x110 net/socket.c:2167 SyS_sendmmsg+0x63/0x90 net/socket.c:2162 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x441819 RSP: 002b:00007ffe58ee8268 EFLAGS: 00000213 ORIG_RAX: 0000000000000133 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000441819 RDX: 0000000000000002 RSI: 0000000020000100 RDI: 0000000000000003 RBP: 00000000006cd018 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000213 R12: 0000000000402510 R13: 00000000004025a0 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline] kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321 slab_post_alloc_hook mm/slab.h:445 [inline] slab_alloc_node mm/slub.c:2737 [inline] __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369 __kmalloc_reserve net/core/skbuff.c:138 [inline] __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206 alloc_skb include/linux/skbuff.h:984 [inline] alloc_skb_with_frags+0x1d4/0xb20 net/core/skbuff.c:5234 sock_alloc_send_pskb+0xb56/0x1190 net/core/sock.c:2085 packet_alloc_skb net/packet/af_packet.c:2803 [inline] packet_snd net/packet/af_packet.c:2894 [inline] packet_sendmsg+0x6454/0x8a30 net/packet/af_packet.c:2969 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] ___sys_sendmsg+0xec0/0x1310 net/socket.c:2046 __sys_sendmmsg+0x42d/0x800 net/socket.c:2136 SYSC_sendmmsg+0xc4/0x110 net/socket.c:2167 SyS_sendmmsg+0x63/0x90 net/socket.c:2162 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 This change addresses the issue adding the needed check before accessing the inner header. The ipv4 side of the issue is apparently there since the ipv4 over ipv6 initial support, and the ipv6 side predates git history. Fixes: c4d3efaf ("[IPV6] IP6TUNNEL: Add support to IPv4 over IPv6 tunnel.") Fixes: 1da177e4 ("Linux-2.6.12-rc2") Reported-by: syzbot+3fde91d4d394747d6db4@syzkaller.appspotmail.com Tested-by:
Alexander Potapenko <glider@google.com> Signed-off-by:
-
Mahesh Bandewar authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit d4859d74 ] Syzkaller reported this on a slightly older kernel but it's still applicable to the current kernel - ====================================================== WARNING: possible circular locking dependency detected 4.18.0-next-20180823+ #46 Not tainted ------------------------------------------------------ syz-executor4/26841 is trying to acquire lock: 00000000dd41ef48 ((wq_completion)bond_dev->name){+.+.}, at: flush_workqueue+0x2db/0x1e10 kernel/workqueue.c:2652 but task is already holding lock: 00000000768ab431 (rtnl_mutex){+.+.}, at: rtnl_lock net/core/rtnetlink.c:77 [inline] 00000000768ab431 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x412/0xc30 net/core/rtnetlink.c:4708 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (rtnl_mutex){+.+.}: __mutex_lock_common kernel/locking/mutex.c:925 [inline] __mutex_lock+0x171/0x1700 kernel/locking/mutex.c:1073 mutex_lock_nested+0x16/0x20 kernel/locking/mutex.c:1088 rtnl_lock+0x17/0x20 net/core/rtnetlink.c:77 bond_netdev_notify drivers/net/bonding/bond_main.c:1310 [inline] bond_netdev_notify_work+0x44/0xd0 drivers/net/bonding/bond_main.c:1320 process_one_work+0xc73/0x1aa0 kernel/workqueue.c:2153 worker_thread+0x189/0x13c0 kernel/workqueue.c:2296 kthread+0x35a/0x420 kernel/kthread.c:246 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:415 -> #1 ((work_completion)(&(&nnw->work)->work)){+.+.}: process_one_work+0xc0b/0x1aa0 kernel/workqueue.c:2129 worker_thread+0x189/0x13c0 kernel/workqueue.c:2296 kthread+0x35a/0x420 kernel/kthread.c:246 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:415 -> #0 ((wq_completion)bond_dev->name){+.+.}: lock_acquire+0x1e4/0x4f0 kernel/locking/lockdep.c:3901 flush_workqueue+0x30a/0x1e10 kernel/workqueue.c:2655 drain_workqueue+0x2a9/0x640 kernel/workqueue.c:2820 destroy_workqueue+0xc6/0x9d0 kernel/workqueue.c:4155 __alloc_workqueue_key+0xef9/0x1190 kernel/workqueue.c:4138 bond_init+0x269/0x940 drivers/net/bonding/bond_main.c:4734 register_netdevice+0x337/0x1100 net/core/dev.c:8410 bond_newlink+0x49/0xa0 drivers/net/bonding/bond_netlink.c:453 rtnl_newlink+0xef4/0x1d50 net/core/rtnetlink.c:3099 rtnetlink_rcv_msg+0x46e/0xc30 net/core/rtnetlink.c:4711 netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2454 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:4729 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x5a0/0x760 net/netlink/af_netlink.c:1343 netlink_sendmsg+0xa18/0xfc0 net/netlink/af_netlink.c:1908 sock_sendmsg_nosec net/socket.c:622 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:632 ___sys_sendmsg+0x7fd/0x930 net/socket.c:2115 __sys_sendmsg+0x11d/0x290 net/socket.c:2153 __do_sys_sendmsg net/socket.c:2162 [inline] __se_sys_sendmsg net/socket.c:2160 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2160 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe other info that might help us debug this: Chain exists of: (wq_completion)bond_dev->name --> (work_completion)(&(&nnw->work)->work) --> rtnl_mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(rtnl_mutex); lock((work_completion)(&(&nnw->work)->work)); lock(rtnl_mutex); lock((wq_completion)bond_dev->name); *** DEADLOCK *** 1 lock held by syz-executor4/26841: stack backtrace: CPU: 1 PID: 26841 Comm: syz-executor4 Not tainted 4.18.0-next-20180823+ #46 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+0x1c9/0x2b4 lib/dump_stack.c:113 print_circular_bug.isra.34.cold.55+0x1bd/0x27d kernel/locking/lockdep.c:1222 check_prev_add kernel/locking/lockdep.c:1862 [inline] check_prevs_add kernel/locking/lockdep.c:1975 [inline] validate_chain kernel/locking/lockdep.c:2416 [inline] __lock_acquire+0x3449/0x5020 kernel/locking/lockdep.c:3412 lock_acquire+0x1e4/0x4f0 kernel/locking/lockdep.c:3901 flush_workqueue+0x30a/0x1e10 kernel/workqueue.c:2655 drain_workqueue+0x2a9/0x640 kernel/workqueue.c:2820 destroy_workqueue+0xc6/0x9d0 kernel/workqueue.c:4155 __alloc_workqueue_key+0xef9/0x1190 kernel/workqueue.c:4138 bond_init+0x269/0x940 drivers/net/bonding/bond_main.c:4734 register_netdevice+0x337/0x1100 net/core/dev.c:8410 bond_newlink+0x49/0xa0 drivers/net/bonding/bond_netlink.c:453 rtnl_newlink+0xef4/0x1d50 net/core/rtnetlink.c:3099 rtnetlink_rcv_msg+0x46e/0xc30 net/core/rtnetlink.c:4711 netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2454 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:4729 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x5a0/0x760 net/netlink/af_netlink.c:1343 netlink_sendmsg+0xa18/0xfc0 net/netlink/af_netlink.c:1908 sock_sendmsg_nosec net/socket.c:622 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:632 ___sys_sendmsg+0x7fd/0x930 net/socket.c:2115 __sys_sendmsg+0x11d/0x290 net/socket.c:2153 __do_sys_sendmsg net/socket.c:2162 [inline] __se_sys_sendmsg net/socket.c:2160 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2160 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x457089 Code: fd b4 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 cb b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f2df20a5c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f2df20a66d4 RCX: 0000000000457089 RDX: 0000000000000000 RSI: 0000000020000180 RDI: 0000000000000003 RBP: 0000000000930140 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff R13: 00000000004d40b8 R14: 00000000004c8ad8 R15: 0000000000000001 Signed-off-by:
Mahesh Bandewar <maheshb@google.com> Signed-off-by:
-
Michael Chan authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit 73f21c65 ] The current netpoll implementation in the bnxt_en driver has problems that may miss TX completion events. bnxt_poll_work() in effect is only handling at most 1 TX packet before exiting. In addition, there may be in flight TX completions that ->poll() may miss even after we fix bnxt_poll_work() to handle all visible TX completions. netpoll may not call ->poll() again and HW may not generate IRQ because the driver does not ARM the IRQ when the budget (0 for netpoll) is reached. We fix it by handling all TX completions and to always ARM the IRQ when we exit ->poll() with 0 budget. Also, the logic to ACK the completion ring in case it is almost filled with TX completions need to be adjusted to take care of the 0 budget case, as discussed with Eric Dumazet <edumazet@google.com> Reported-by:
Song Liu <songliubraving@fb.com> Reviewed-by:
Michael Chan <michael.chan@broadcom.com> Signed-off-by:
-
Hou Tao authored
BugLink: https://bugs.launchpad.net/bugs/1801900 When a file have multiple xattrs and the passed buffer is smaller than the required size, jffs2_listxattr() should return -ERANGE instead of continue, else Oops may occur due to memory corruption. Also remove the unnecessary check ("rc < 0"), because xhandle->list(...) will not return an error number. Spotted by generic/377 in xfstests-dev. NB: The problem had been fixed by commit 764a5c6b ("xattr handlers: Simplify list operation") in v4.5-rc1, but the modification in that commit may be too much because it modifies all file-systems which implement xattr, so I create a single patch for jffs2 to fix the problem. Signed-off-by:
Hou Tao <houtao1@huawei.com> Cc: David Woodhouse <dwmw2@infradead.org> Signed-off-by:
-
Mathias Nyman authored
BugLink: https://bugs.launchpad.net/bugs/1801900 commit 1208d8a8 upstream. When disabling a USB3 port the hub driver will set the port link state to U3 to prevent "ejected" or "safely removed" devices that are still physically connected from immediately re-enumerating. If the device was really unplugged, then error messages were printed as the hub tries to set the U3 link state for a port that is no longer enabled. xhci-hcd ee000000.usb: Cannot set link state. usb usb8-port1: cannot disable (err = -32) Don't print error message in xhci-hub if hub tries to set port link state for a disabled port. Return -ENODEV instead which also silences hub driver. Signed-off-by:
Mathias Nyman <mathias.nyman@linux.intel.com> Tested-by:
Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com> Signed-off-by:
Ross Zwisler <zwisler@google.com> Signed-off-by:
-
Edgar Cherkasov authored
BugLink: https://bugs.launchpad.net/bugs/1801900 commit 08d9db00 upstream. The i2c-scmi driver crashes when the SMBus Write Block transaction is executed: WARNING: CPU: 9 PID: 2194 at mm/page_alloc.c:3931 __alloc_pages_slowpath+0x9db/0xec0 Call Trace: ? get_page_from_freelist+0x49d/0x11f0 ? alloc_pages_current+0x6a/0xe0 ? new_slab+0x499/0x690 __alloc_pages_nodemask+0x265/0x280 alloc_pages_current+0x6a/0xe0 kmalloc_order+0x18/0x40 kmalloc_order_trace+0x24/0xb0 ? acpi_ut_allocate_object_desc_dbg+0x62/0x10c __kmalloc+0x203/0x220 acpi_os_allocate_zeroed+0x34/0x36 acpi_ut_copy_eobject_to_iobject+0x266/0x31e acpi_evaluate_object+0x166/0x3b2 acpi_smbus_cmi_access+0x144/0x530 [i2c_scmi] i2c_smbus_xfer+0xda/0x370 i2cdev_ioctl_smbus+0x1bd/0x270 i2cdev_ioctl+0xaa/0x250 do_vfs_ioctl+0xa4/0x600 SyS_ioctl+0x79/0x90 do_syscall_64+0x73/0x130 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 ACPI Error: Evaluating _SBW: 4 (20170831/smbus_cmi-185) This problem occurs because the length of ACPI Buffer object is not defined/initialized in the code before a corresponding ACPI method is called. The obvious patch below fixes this issue. Signed-off-by:
Edgar Cherkasov <echerkasov@dev.rtsoft.ru> Acked-by:
Viktor Krasnov <vkrasnov@dev.rtsoft.ru> Acked-by:
Michael Brunner <Michael.Brunner@kontron.com> Signed-off-by:
Wolfram Sang <wsa@the-dreams.de> Signed-off-by:
-
Adrian Hunter authored
BugLink: https://bugs.launchpad.net/bugs/1801900 commit 25e11700 upstream. Occasional export failures were found to be caused by truncating 64-bit pointers to 32-bits. Fix by explicitly setting types for all ctype arguments and results. Signed-off-by:
Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20180911114504.28516-2-adrian.hunter@intel.comSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by:
-
Mikulas Patocka authored
BugLink: https://bugs.launchpad.net/bugs/1801900 commit 76ebebd2 upstream. On Sun Ultra 5, it happens that the dot clock is not set up properly for some videomodes. For example, if we set the videomode "r1024x768x60" in the firmware, Linux would incorrectly set a videomode with refresh rate 180Hz when booting (suprisingly, my LCD monitor can display it, although display quality is very low). The reason is this: Older mach64 cards set the divider in the register VCLK_POST_DIV. The register has four 2-bit fields (the field that is actually used is specified in the lowest two bits of the register CLOCK_CNTL). The 2 bits select divider "1, 2, 4, 8". On newer mach64 cards, there's another bit added - the top four bits of PLL_EXT_CNTL extend the divider selection, so we have possible dividers "1, 2, 4, 8, 3, 5, 6, 12". The Linux driver clears the top four bits of PLL_EXT_CNTL and never sets them, so it can work regardless if the card supports them. However, the sparc64 firmware may set these extended dividers during boot - and the mach64 driver detects incorrect dot clock in this case. This patch makes the driver read the additional divider bit from PLL_EXT_CNTL and calculate the initial refresh rate properly. Signed-off-by:
Mikulas Patocka <mpatocka@redhat.com> Cc: stable@vger.kernel.org Acked-by:
Ville Syrjälä <syrjala@sci.fi> Signed-off-by:
-
Jann Horn authored
BugLink: https://bugs.launchpad.net/bugs/1801900 commit 28e2c4bb upstream. 7a9cdebd ("mm: get rid of vmacache_flush_all() entirely") removed the VMACACHE_FULL_FLUSHES statistics, but didn't remove the corresponding entry in vmstat_text. This causes an out-of-bounds access in vmstat_show(). Luckily this only affects kernels with CONFIG_DEBUG_VM_VMACACHE=y, which is probably very rare. Link: http://lkml.kernel.org/r/20181001143138.95119-1-jannh@google.com Fixes: 7a9cdebd ("mm: get rid of vmacache_flush_all() entirely") Signed-off-by:
Jann Horn <jannh@google.com> Reviewed-by:
Kees Cook <keescook@chromium.org> Reviewed-by:
Andrew Morton <akpm@linux-foundation.org> Acked-by:
Michal Hocko <mhocko@suse.com> Acked-by:
Roman Gushchin <guro@fb.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Christoph Lameter <clameter@sgi.com> Cc: Kemi Wang <kemi.wang@intel.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Signed-off-by:
-
Theodore Ts'o authored
BugLink: https://bugs.launchpad.net/bugs/1801900 commit 5369a762 upstream. In theory this should have been caught earlier when the xattr list was verified, but in case it got missed, it's simple enough to add check to make sure we don't overrun the xattr buffer. This addresses CVE-2018-10879. https://bugzilla.kernel.org/show_bug.cgi?id=200001Signed-off-by:
Theodore Ts'o <tytso@mit.edu> Reviewed-by:
Andreas Dilger <adilger@dilger.ca> [bwh: Backported to 3.16: - Add inode parameter to ext4_xattr_set_entry() and update callers - Adjust context] Signed-off-by:
Ben Hutchings <ben@decadent.org.uk> [adjusted for 4.4 context] Signed-off-by:
Daniel Rosenberg <drosen@google.com> Signed-off-by:
-
Amber Lin authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit caaa4c8a ] A wrong register bit was examinated for checking SDMA status so it reports false failures. This typo only appears on gfx_v7. gfx_v8 checks the correct bit. Acked-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Amber Lin <Amber.Lin@amd.com> Reviewed-by:
Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by:
Sasha Levin <alexander.levin@microsoft.com> Signed-off-by:
-
Nicolas Ferre authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit 321cc359 ] We need this new compatibility string as we experienced different behavior for this 10/100Mbits/s macb interface on this particular SoC. Backward compatibility is preserved as we keep the alternative strings. Signed-off-by:
Nicolas Ferre <nicolas.ferre@microchip.com> Signed-off-by:
-
Nicolas Ferre authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit eb4ed8e2 ] Create a new configuration for the sama5d3-macb new compatibility string. This configuration disables scatter-gather because we experienced lock down of the macb interface of this particular SoC under very high load. Signed-off-by:
-
Jongsung Kim authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit edf2ef72 ] Synopsys DWC Ethernet MAC can be configured to have 1..32, 64, or 128 unicast filter entries. (Table 7-8 MAC Address Registers from databook) Fix dwmac1000_validate_ucast_entries() to accept values between 1 and 32 in addition. Signed-off-by:
Jongsung Kim <neidhard.kim@lge.com> Signed-off-by:
-
Yu Zhao authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit b61749a8 ] In snd_hdac_bus_init_chip(), we enable interrupt before snd_hdac_bus_init_cmd_io() initializing dma buffers. If irq has been acquired and irq handler uses the dma buffer, kernel may crash when interrupt comes in. Fix the problem by postponing enabling irq after dma buffer initialization. And warn once on null dma buffer pointer during the initialization. Reviewed-by:
Takashi Iwai <tiwai@suse.de> Signed-off-by:
Mark Brown <broonie@kernel.org> Signed-off-by:
-
Tony Lindgren authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit 10492ee8 ] It currently only works if the parent bus uses "simple-bus". We currently try to probe children with non-existing compatible values. And we're missing .probe. I noticed this while testing devices configured to probe using ti-sysc interconnect target module driver. For that we also may want to rebind the driver, so let's remove __init and __exit. Signed-off-by:
Tony Lindgren <tony@atomide.com> Acked-by:
Roger Quadros <rogerq@ti.com> Signed-off-by:
Lee Jones <lee.jones@linaro.org> Signed-off-by:
-
Lei Yang authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit 53cf59d6 ] add config file Signed-off-by:
Lei Yang <Lei.Yang@windriver.com> Signed-off-by:
Shuah Khan (Samsung OSG) <shuah@kernel.org> Signed-off-by:
-
Danny Smith authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit 5ea752c6 ] Fixed range in safeload conditional to allow safeload to up to 20 bytes, without a lower limit. Signed-off-by:
Danny Smith <dannys@axis.com> Acked-by:
Lars-Peter Clausen <lars@metafoo.de> Signed-off-by:
-
Pierre-Louis Bossart authored
BugLink: https://bugs.launchpad.net/bugs/1801900 [ Upstream commit 960cdd50 ] HID made of either Wolfson/CirrusLogic PCI ID + 8804 identifier. This helps enumerate the HifiBerry Digi+ HAT boards on the Up2 platform. The scripts at https://github.com/thesofproject/acpi-scripts can be used to add the ACPI initrd overlays. Signed-off-by:
Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Acked-by:
Charles Keepax <ckeepax@opensource.cirrus.com> Signed-off-by:
-
Greg Kroah-Hartman authored
BugLink: https://bugs.launchpad.net/bugs/1801893Signed-off-by:
-
Gao Feng authored
BugLink: https://bugs.launchpad.net/bugs/1801893 commit c953d635 upstream. The info->target comes from userspace and it would be used directly. So we need to add the sanity check to make sure it is a valid standard target, although the ebtables tool has already checked it. Kernel needs to validate anything coming from userspace. If the target is set as an evil value, it would break the ebtables and cause a panic. Because the non-standard target is treated as one offset. Now add one helper function ebt_invalid_target, and we would replace the macro INVALID_TARGET later. Signed-off-by:
Gao Feng <gfree.wind@vip.163.com> Signed-off-by:
Pablo Neira Ayuso <pablo@netfilter.org> Cc: Loic <hackurx@opensec.fr> Signed-off-by:
-
Zhi Chen authored
BugLink: https://bugs.launchpad.net/bugs/1801893 commit c8291988 upstream. Length of WMI scan message was not calculated correctly. The allocated buffer was smaller than what we expected. So WMI message corrupted skb_info, which is at the end of skb->data. This fix takes TLV header into account even if the element is zero-length. Crash log: [49.629986] Unhandled kernel unaligned access[#1]: [49.634932] CPU: 0 PID: 1176 Comm: logd Not tainted 4.4.60 #180 [49.641040] task: 83051460 ti: 8329c000 task.ti: 8329c000 [49.646608] $ 0 : 00000000 00000001 80984a80 00000000 [49.652038] $ 4 : 45259e89 8046d484 8046df30 8024ba70 [49.657468] $ 8 : 00000000 804cc4c0 00000001 20306320 [49.662898] $12 : 33322037 000110f2 00000000 31203930 [49.668327] $16 : 82792b40 80984a80 00000001 804207fc [49.673757] $20 : 00000000 0000012c 00000040 80470000 [49.679186] $24 : 00000000 8024af7c [49.684617] $28 : 8329c000 8329db88 00000001 802c58d0 [49.690046] Hi : 00000000 [49.693022] Lo : 453c0000 [49.696013] epc : 800efae4 put_page+0x0/0x58 [49.700615] ra : 802c58d0 skb_release_data+0x148/0x1d4 [49.706184] Status: 1000fc03 KERNEL EXL IE [49.710531] Cause : 00800010 (ExcCode 04) [49.714669] BadVA : 45259e89 [49.717644] PrId : 00019374 (MIPS 24Kc) Signed-off-by:
Zhi Chen <zhichen@codeaurora.org> Signed-off-by:
Kalle Valo <kvalo@codeaurora.org> Cc: Brian Norris <briannorris@chromium.org> Signed-off-by:
-
Eric Dumazet authored
BugLink: https://bugs.launchpad.net/bugs/1801893 [ Upstream commit 58152ecb ] In case skb in out_or_order_queue is the result of multiple skbs coalescing, we would like to get a proper gso_segs counter tracking, so that future tcp_drop() can report an accurate number. I chose to not implement this tracking for skbs in receive queue, since they are not dropped, unless socket is disconnected. Signed-off-by:
Soheil Hassas Yeganeh <soheil@google.com> Acked-by:
Yuchung Cheng <ycheng@google.com> Signed-off-by:
Mao Wenan <maowenan@huawei.com> Signed-off-by:
-
Eric Dumazet authored
BugLink: https://bugs.launchpad.net/bugs/1801893 [ Upstream commit 8541b21e ] In order to be able to give better diagnostics and detect malicious traffic, we need to have better sk->sk_drops tracking. Fixes: 9f5afeae ("tcp: use an RB tree for ooo receive queue") Signed-off-by:
-
Eric Dumazet authored
BugLink: https://bugs.launchpad.net/bugs/1801893 [ Upstream commit 72cd43ba ] 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: 36a6503f ("tcp: refine tcp_prune_ofo_queue() to not drop all packets") Signed-off-by:
Juha-Matti Tilli <juha-matti.tilli@iki.fi> Acked-by:
-
Eric Dumazet authored
BugLink: https://bugs.launchpad.net/bugs/1801893 [ Upstream commit 76f0dcbb ] When skb replaces another one in ooo queue, I forgot to also update tp->ooo_last_skb as well, if the replaced skb was the last one in the queue. To fix this, we simply can re-use the code that runs after an insertion, trying to merge skbs at the right of current skb. This not only fixes the bug, but also remove all small skbs that might be a subset of the new one. Example: We receive segments 2001:3001, 4001:5001 Then we receive 2001:8001 : We should replace 2001:3001 with the big skb, but also remove 4001:50001 from the queue to save space. packetdrill test demonstrating the bug 0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0 bind(3, ..., ...) = 0 +0 listen(3, 1) = 0 +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 7> +0.100 < . 1:1(0) ack 1 win 1024 +0 accept(3, ..., ...) = 4 +0.01 < . 1001:2001(1000) ack 1 win 1024 +0 > . 1:1(0) ack 1 <nop,nop, sack 1001:2001> +0.01 < . 1001:3001(2000) ack 1 win 1024 +0 > . 1:1(0) ack 1 <nop,nop, sack 1001:2001 1001:3001> Fixes: 9f5afeae ("tcp: use an RB tree for ooo receive queue") Signed-off-by:
-
Yaogong Wang authored
BugLink: https://bugs.launchpad.net/bugs/1801893 [ Upstream commit 9f5afeae ] Over the years, TCP BDP has increased by several orders of magnitude, and some people are considering to reach the 2 Gbytes limit. Even with current window scale limit of 14, ~1 Gbytes maps to ~740,000 MSS. In presence of packet losses (or reorders), TCP stores incoming packets into an out of order queue, and number of skbs sitting there waiting for the missing packets to be received can be in the 10^5 range. Most packets are appended to the tail of this queue, and when packets can finally be transferred to receive queue, we scan the queue from its head. However, in presence of heavy losses, we might have to find an arbitrary point in this queue, involving a linear scan for every incoming packet, throwing away cpu caches. This patch converts it to a RB tree, to get bounded latencies. Yaogong wrote a preliminary patch about 2 years ago. Eric did the rebase, added ofo_last_skb cache, polishing and tests. Tested with network dropping between 1 and 10 % packets, with good success (about 30 % increase of throughput in stress tests) Next step would be to also use an RB tree for the write queue at sender side ;) Signed-off-by:
Yaogong Wang <wygivan@google.com> Signed-off-by:
Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by:
-
Eric Dumazet authored
BugLink: https://bugs.launchpad.net/bugs/1801893 [ Upstream commit 532182cd ] Now ss can report sk_drops, we can instruct TCP to increment this per socket counter when it drops an incoming frame, to refine monitoring and debugging. Following patch takes care of listeners drops. Signed-off-by:
-
Richard Weinberger authored
BugLink: https://bugs.launchpad.net/bugs/1801893 commit 37f31b6c upstream. The requested device name can be NULL or an empty string. Check for that and refuse to continue. UBIFS has to do this manually since we cannot use mount_bdev(), which checks for this condition. Fixes: 1e51764a ("UBIFS: add new flash file system") Reported-by: syzbot+38bd0f7865e5c6379280@syzkaller.appspotmail.com Signed-off-by:
Richard Weinberger <richard@nod.at> Signed-off-by:
-
