Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 06 9月, 2019 1 次提交
    • P
      net: openvswitch: Set OvS recirc_id from tc chain index · 95a7233c
      由 Paul Blakey 提交于 
      Offloaded OvS datapath rules are translated one to one to tc rules,
for example the following simplified OvS rule:

recirc_id(0),in_port(dev1),eth_type(0x0800),ct_state(-trk) actions:ct(),recirc(2)

Will be translated to the following tc rule:

$ tc filter add dev dev1 ingress \
	    prio 1 chain 0 proto ip \
		flower tcp ct_state -trk \
		action ct pipe \
		action goto chain 2

Received packets will first travel though tc, and if they aren't stolen
by it, like in the above rule, they will continue to OvS datapath.
Since we already did some actions (action ct in this case) which might
modify the packets, and updated action stats, we would like to continue
the proccessing with the correct recirc_id in OvS (here recirc_id(2))
where we left off.

To support this, introduce a new skb extension for tc, which
will be used for translating tc chain to ovs recirc_id to
handle these miss cases. Last tc chain index will be set
by tc goto chain action and read by OvS datapath.
Signed-off-by: NPaul Blakey <paulb@mellanox.com>
Signed-off-by: NVlad Buslov <vladbu@mellanox.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NPravin B Shelar <pshelar@ovn.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      95a7233c
  3. 01 9月, 2019 3 次提交
  5. 28 8月, 2019 1 次提交
    • F
      net: fix skb use after free in netpoll · 2c1644cf
      由 Feng Sun 提交于 
      After commit baeababb
("tun: return NET_XMIT_DROP for dropped packets"),
when tun_net_xmit drop packets, it will free skb and return NET_XMIT_DROP,
netpoll_send_skb_on_dev will run into following use after free cases:
1. retry netpoll_start_xmit with freed skb;
2. queue freed skb in npinfo->txq.
queue_process will also run into use after free case.

hit netpoll_send_skb_on_dev first case with following kernel log:

[  117.864773] kernel BUG at mm/slub.c:306!
[  117.864773] invalid opcode: 0000 [#1] SMP PTI
[  117.864774] CPU: 3 PID: 2627 Comm: loop_printmsg Kdump: loaded Tainted: P           OE     5.3.0-050300rc5-generic #201908182231
[  117.864775] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
[  117.864775] RIP: 0010:kmem_cache_free+0x28d/0x2b0
[  117.864781] Call Trace:
[  117.864781]  ? tun_net_xmit+0x21c/0x460
[  117.864781]  kfree_skbmem+0x4e/0x60
[  117.864782]  kfree_skb+0x3a/0xa0
[  117.864782]  tun_net_xmit+0x21c/0x460
[  117.864782]  netpoll_start_xmit+0x11d/0x1b0
[  117.864788]  netpoll_send_skb_on_dev+0x1b8/0x200
[  117.864789]  __br_forward+0x1b9/0x1e0 [bridge]
[  117.864789]  ? skb_clone+0x53/0xd0
[  117.864790]  ? __skb_clone+0x2e/0x120
[  117.864790]  deliver_clone+0x37/0x50 [bridge]
[  117.864790]  maybe_deliver+0x89/0xc0 [bridge]
[  117.864791]  br_flood+0x6c/0x130 [bridge]
[  117.864791]  br_dev_xmit+0x315/0x3c0 [bridge]
[  117.864792]  netpoll_start_xmit+0x11d/0x1b0
[  117.864792]  netpoll_send_skb_on_dev+0x1b8/0x200
[  117.864792]  netpoll_send_udp+0x2c6/0x3e8
[  117.864793]  write_msg+0xd9/0xf0 [netconsole]
[  117.864793]  console_unlock+0x386/0x4e0
[  117.864793]  vprintk_emit+0x17e/0x280
[  117.864794]  vprintk_default+0x29/0x50
[  117.864794]  vprintk_func+0x4c/0xbc
[  117.864794]  printk+0x58/0x6f
[  117.864795]  loop_fun+0x24/0x41 [printmsg_loop]
[  117.864795]  kthread+0x104/0x140
[  117.864795]  ? 0xffffffffc05b1000
[  117.864796]  ? kthread_park+0x80/0x80
[  117.864796]  ret_from_fork+0x35/0x40
Signed-off-by: NFeng Sun <loyou85@gmail.com>
Signed-off-by: NXiaojun Zhao <xiaojunzhao141@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      2c1644cf
  7. 25 8月, 2019 2 次提交
  9. 24 8月, 2019 3 次提交
  11. 20 8月, 2019 2 次提交
    • E
      tcp: make sure EPOLLOUT wont be missed · ef8d8ccd
      由 Eric Dumazet 提交于 
      As Jason Baron explained in commit 790ba456 ("tcp: set SOCK_NOSPACE
under memory pressure"), it is crucial we properly set SOCK_NOSPACE
when needed.

However, Jason patch had a bug, because the 'nonblocking' status
as far as sk_stream_wait_memory() is concerned is governed
by MSG_DONTWAIT flag passed at sendmsg() time :

    long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);

So it is very possible that tcp sendmsg() calls sk_stream_wait_memory(),
and that sk_stream_wait_memory() returns -EAGAIN with SOCK_NOSPACE
cleared, if sk->sk_sndtimeo has been set to a small (but not zero)
value.

This patch removes the 'noblock' variable since we must always
set SOCK_NOSPACE if -EAGAIN is returned.

It also renames the do_nonblock label since we might reach this
code path even if we were in blocking mode.

Fixes: 790ba456 ("tcp: set SOCK_NOSPACE under memory pressure")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Jason Baron <jbaron@akamai.com>
Reported-by: NVladimir Rutsky  <rutsky@google.com>
Acked-by: NSoheil Hassas Yeganeh <soheil@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Acked-by: NJason Baron <jbaron@akamai.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      ef8d8ccd
    • V
      net: flow_offload: convert block_ing_cb_list to regular list type · 607f625b
      由 Vlad Buslov 提交于 
      RCU list block_ing_cb_list is protected by rcu read lock in
flow_block_ing_cmd() and with flow_indr_block_ing_cb_lock mutex in all
functions that use it. However, flow_block_ing_cmd() needs to call blocking
functions while iterating block_ing_cb_list which leads to following
suspicious RCU usage warning:

[  401.510948] =============================
[  401.510952] WARNING: suspicious RCU usage
[  401.510993] 5.3.0-rc3+ #589 Not tainted
[  401.510996] -----------------------------
[  401.511001] include/linux/rcupdate.h:265 Illegal context switch in RCU read-side critical section!
[  401.511004]
               other info that might help us debug this:

[  401.511008]
               rcu_scheduler_active = 2, debug_locks = 1
[  401.511012] 7 locks held by test-ecmp-add-v/7576:
[  401.511015]  #0: 00000000081d71a5 (sb_writers#4){.+.+}, at: vfs_write+0x166/0x1d0
[  401.511037]  #1: 000000002bd338c3 (&of->mutex){+.+.}, at: kernfs_fop_write+0xef/0x1b0
[  401.511051]  #2: 00000000c921c634 (kn->count#317){.+.+}, at: kernfs_fop_write+0xf7/0x1b0
[  401.511062]  #3: 00000000a19cdd56 (&dev->mutex){....}, at: sriov_numvfs_store+0x6b/0x130
[  401.511079]  #4: 000000005425fa52 (pernet_ops_rwsem){++++}, at: unregister_netdevice_notifier+0x30/0x140
[  401.511092]  #5: 00000000c5822793 (rtnl_mutex){+.+.}, at: unregister_netdevice_notifier+0x35/0x140
[  401.511101]  #6: 00000000c2f3507e (rcu_read_lock){....}, at: flow_block_ing_cmd+0x5/0x130
[  401.511115]
               stack backtrace:
[  401.511121] CPU: 21 PID: 7576 Comm: test-ecmp-add-v Not tainted 5.3.0-rc3+ #589
[  401.511124] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017
[  401.511127] Call Trace:
[  401.511138]  dump_stack+0x85/0xc0
[  401.511146]  ___might_sleep+0x100/0x180
[  401.511154]  __mutex_lock+0x5b/0x960
[  401.511162]  ? find_held_lock+0x2b/0x80
[  401.511173]  ? __tcf_get_next_chain+0x1d/0xb0
[  401.511179]  ? mark_held_locks+0x49/0x70
[  401.511194]  ? __tcf_get_next_chain+0x1d/0xb0
[  401.511198]  __tcf_get_next_chain+0x1d/0xb0
[  401.511251]  ? uplink_rep_async_event+0x70/0x70 [mlx5_core]
[  401.511261]  tcf_block_playback_offloads+0x39/0x160
[  401.511276]  tcf_block_setup+0x1b0/0x240
[  401.511312]  ? mlx5e_rep_indr_setup_tc_cb+0xca/0x290 [mlx5_core]
[  401.511347]  ? mlx5e_rep_indr_tc_block_unbind+0x50/0x50 [mlx5_core]
[  401.511359]  tc_indr_block_get_and_ing_cmd+0x11b/0x1e0
[  401.511404]  ? mlx5e_rep_indr_tc_block_unbind+0x50/0x50 [mlx5_core]
[  401.511414]  flow_block_ing_cmd+0x7e/0x130
[  401.511453]  ? mlx5e_rep_indr_tc_block_unbind+0x50/0x50 [mlx5_core]
[  401.511462]  __flow_indr_block_cb_unregister+0x7f/0xf0
[  401.511502]  mlx5e_nic_rep_netdevice_event+0x75/0xb0 [mlx5_core]
[  401.511513]  unregister_netdevice_notifier+0xe9/0x140
[  401.511554]  mlx5e_cleanup_rep_tx+0x6f/0xe0 [mlx5_core]
[  401.511597]  mlx5e_detach_netdev+0x4b/0x60 [mlx5_core]
[  401.511637]  mlx5e_vport_rep_unload+0x71/0xc0 [mlx5_core]
[  401.511679]  esw_offloads_disable+0x5b/0x90 [mlx5_core]
[  401.511724]  mlx5_eswitch_disable.cold+0xdf/0x176 [mlx5_core]
[  401.511759]  mlx5_device_disable_sriov+0xab/0xb0 [mlx5_core]
[  401.511794]  mlx5_core_sriov_configure+0xaf/0xd0 [mlx5_core]
[  401.511805]  sriov_numvfs_store+0xf8/0x130
[  401.511817]  kernfs_fop_write+0x122/0x1b0
[  401.511826]  vfs_write+0xdb/0x1d0
[  401.511835]  ksys_write+0x65/0xe0
[  401.511847]  do_syscall_64+0x5c/0xb0
[  401.511857]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  401.511862] RIP: 0033:0x7fad892d30f8
[  401.511868] Code: 89 02 48 c7 c0 ff ff ff ff eb bb 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 25 96 0d 00 8b 00 85 c0 75 17 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 60 c3 0f 1f 80 00 00 00 00 48 83
 ec 28 48 89
[  401.511871] RSP: 002b:00007ffca2a9fad8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
[  401.511875] RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007fad892d30f8
[  401.511878] RDX: 0000000000000002 RSI: 000055afeb072a90 RDI: 0000000000000001
[  401.511881] RBP: 000055afeb072a90 R08: 00000000ffffffff R09: 000000000000000a
[  401.511884] R10: 000055afeb058710 R11: 0000000000000246 R12: 0000000000000002
[  401.511887] R13: 00007fad893a8780 R14: 0000000000000002 R15: 00007fad893a3740

To fix the described incorrect RCU usage, convert block_ing_cb_list from
RCU list to regular list and protect it with flow_indr_block_ing_cb_lock
mutex in flow_block_ing_cmd().

Fixes: 1150ab0f ("flow_offload: support get multi-subsystem block")
Signed-off-by: NVlad Buslov <vladbu@mellanox.com>
Acked-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      607f625b
  13. 18 8月, 2019 9 次提交
  15. 16 8月, 2019 2 次提交
  17. 14 8月, 2019 2 次提交
  19. 12 8月, 2019 10 次提交
  21. 10 8月, 2019 2 次提交
    • D
      sock: make cookie generation global instead of per netns · cd48bdda
      由 Daniel Borkmann 提交于 
      Generating and retrieving socket cookies are a useful feature that is
exposed to BPF for various program types through bpf_get_socket_cookie()
helper.

The fact that the cookie counter is per netns is quite a limitation
for BPF in practice in particular for programs in host namespace that
use socket cookies as part of a map lookup key since they will be
causing socket cookie collisions e.g. when attached to BPF cgroup hooks
or cls_bpf on tc egress in host namespace handling container traffic
from veth or ipvlan devices with peer in different netns. Change the
counter to be global instead.

Socket cookie consumers must assume the value as opqaue in any case.
Not every socket must have a cookie generated and knowledge of the
counter value itself does not provide much value either way hence
conversion to global is fine.
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Martynas Pumputis <m@lambda.lt>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      cd48bdda
    • J
      devlink: remove pointless data_len arg from region snapshot create · 3a5e5234
      由 Jiri Pirko 提交于 
      The size of the snapshot has to be the same as the size of the region,
therefore no need to pass it again during snapshot creation. Remove the
arg and use region->size instead.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      3a5e5234
  23. 09 8月, 2019 3 次提交
    • J
      net/tls: prevent skb_orphan() from leaking TLS plain text with offload · 41477662
      由 Jakub Kicinski 提交于 
      sk_validate_xmit_skb() and drivers depend on the sk member of
struct sk_buff to identify segments requiring encryption.
Any operation which removes or does not preserve the original TLS
socket such as skb_orphan() or skb_clone() will cause clear text
leaks.

Make the TCP socket underlying an offloaded TLS connection
mark all skbs as decrypted, if TLS TX is in offload mode.
Then in sk_validate_xmit_skb() catch skbs which have no socket
(or a socket with no validation) and decrypted flag set.

Note that CONFIG_SOCK_VALIDATE_XMIT, CONFIG_TLS_DEVICE and
sk->sk_validate_xmit_skb are slightly interchangeable right now,
they all imply TLS offload. The new checks are guarded by
CONFIG_TLS_DEVICE because that's the option guarding the
sk_buff->decrypted member.

Second, smaller issue with orphaning is that it breaks
the guarantee that packets will be delivered to device
queues in-order. All TLS offload drivers depend on that
scheduling property. This means skb_orphan_partial()'s
trick of preserving partial socket references will cause
issues in the drivers. We need a full orphan, and as a
result netem delay/throttling will cause all TLS offload
skbs to be dropped.

Reusing the sk_buff->decrypted flag also protects from
leaking clear text when incoming, decrypted skb is redirected
(e.g. by TC).

See commit 0608c69c ("bpf: sk_msg, sock{map|hash} redirect
through ULP") for justification why the internal flag is safe.
The only location which could leak the flag in is tcp_bpf_sendmsg(),
which is taken care of by clearing the previously unused bit.

v2:
 - remove superfluous decrypted mark copy (Willem);
 - remove the stale doc entry (Boris);
 - rely entirely on EOR marking to prevent coalescing (Boris);
 - use an internal sendpages flag instead of marking the socket
   (Boris).
v3 (Willem):
 - reorganize the can_skb_orphan_partial() condition;
 - fix the flag leak-in through tcp_bpf_sendmsg.
Signed-off-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: NWillem de Bruijn <willemb@google.com>
Reviewed-by: NBoris Pismenny <borisp@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      41477662
    • W
      flow_offload: support get multi-subsystem block · 1150ab0f
      由 wenxu 提交于 
      It provide a callback list to find the blocks of tc
and nft subsystems
Signed-off-by: Nwenxu <wenxu@ucloud.cn>
Acked-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      1150ab0f
    • W
      flow_offload: move tc indirect block to flow offload · 4e481908
      由 wenxu 提交于 
      move tc indirect block to flow_offload and rename
it to flow indirect block.The nf_tables can use the
indr block architecture.
Signed-off-by: Nwenxu <wenxu@ucloud.cn>
Acked-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      4e481908