linux-toradex.git/net/sched/sch_netem.c, branch v5.1

net: netem: fix skb length BUG_ON in __skb_to_sgvec

2019-02-28T18:31:31+00:00

It can be reproduced by following steps:
1. virtio_net NIC is configured with gso/tso on
2. configure nginx as http server with an index file bigger than 1M bytes
3. use tc netem to produce duplicate packets and delay:
   tc qdisc add dev eth0 root netem delay 100ms 10ms 30% duplicate 90%
4. continually curl the nginx http server to get index file on client
5. BUG_ON is seen quickly

[10258690.371129] kernel BUG at net/core/skbuff.c:4028!
[10258690.371748] invalid opcode: 0000 [#1] SMP PTI
[10258690.372094] CPU: 5 PID: 0 Comm: swapper/5 Tainted: G        W         5.0.0-rc6 #2
[10258690.372094] RSP: 0018:ffffa05797b43da0 EFLAGS: 00010202
[10258690.372094] RBP: 00000000000005ea R08: 0000000000000000 R09: 00000000000005ea
[10258690.372094] R10: ffffa0579334d800 R11: 00000000000002c0 R12: 0000000000000002
[10258690.372094] R13: 0000000000000000 R14: ffffa05793122900 R15: ffffa0578f7cb028
[10258690.372094] FS:  0000000000000000(0000) GS:ffffa05797b40000(0000) knlGS:0000000000000000
[10258690.372094] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[10258690.372094] CR2: 00007f1a6dc00868 CR3: 000000001000e000 CR4: 00000000000006e0
[10258690.372094] Call Trace:
[10258690.372094]  
[10258690.372094]  skb_to_sgvec+0x11/0x40
[10258690.372094]  start_xmit+0x38c/0x520 [virtio_net]
[10258690.372094]  dev_hard_start_xmit+0x9b/0x200
[10258690.372094]  sch_direct_xmit+0xff/0x260
[10258690.372094]  __qdisc_run+0x15e/0x4e0
[10258690.372094]  net_tx_action+0x137/0x210
[10258690.372094]  __do_softirq+0xd6/0x2a9
[10258690.372094]  irq_exit+0xde/0xf0
[10258690.372094]  smp_apic_timer_interrupt+0x74/0x140
[10258690.372094]  apic_timer_interrupt+0xf/0x20
[10258690.372094]  

In __skb_to_sgvec(), the skb->len is not equal to the sum of the skb's
linear data size and nonlinear data size, thus BUG_ON triggered.
Because the skb is cloned and a part of nonlinear data is split off.

Duplicate packet is cloned in netem_enqueue() and may be delayed
some time in qdisc. When qdisc len reached the limit and returns
NET_XMIT_DROP, the skb will be retransmit later in write queue.
the skb will be fragmented by tso_fragment(), the limit size
that depends on cwnd and mss decrease, the skb's nonlinear
data will be split off. The length of the skb cloned by netem
will not be updated. When we use virtio_net NIC and invoke skb_to_sgvec(),
the BUG_ON trigger.

To fix it, netem returns NET_XMIT_SUCCESS to upper stack
when it clones a duplicate packet.

Fixes: 35d889d1 ("sch_netem: fix skb leak in netem_enqueue()")
Signed-off-by: Sheng Lan 
Reported-by: Qin Ji 
Suggested-by: Eric Dumazet 
Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller

Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

2018-12-10T05:43:31+00:00

Several conflicts, seemingly all over the place.

I used Stephen Rothwell's sample resolutions for many of these, if not
just to double check my own work, so definitely the credit largely
goes to him.

The NFP conflict consisted of a bug fix (moving operations
past the rhashtable operation) while chaning the initial
argument in the function call in the moved code.

The net/dsa/master.c conflict had to do with a bug fix intermixing of
making dsa_master_set_mtu() static with the fixing of the tagging
attribute location.

cls_flower had a conflict because the dup reject fix from Or
overlapped with the addition of port range classifiction.

__set_phy_supported()'s conflict was relatively easy to resolve
because Andrew fixed it in both trees, so it was just a matter
of taking the net-next copy.  Or at least I think it was :-)

Joe Stringer's fix to the handling of netns id 0 in bpf_sk_lookup()
intermixed with changes on how the sdif and caller_net are calculated
in these code paths in net-next.

The remaining BPF conflicts were largely about the addition of the
__bpf_md_ptr stuff in 'net' overlapping with adjustments and additions
to the relevant data structure where the MD pointer macros are used.

Signed-off-by: David S. Miller

net: netem: use a list in addition to rbtree

2018-12-06T04:18:41+00:00

When testing high-bandwidth TCP streams with large windows,
high latency, and low jitter, netem consumes a lot of CPU cycles
doing rbtree rebalancing.

This patch uses a linear list/queue in addition to the rbtree:
if an incoming packet is past the tail of the linear queue, it is
added there, otherwise it is inserted into the rbtree.

Without this patch, perf shows netem_enqueue, netem_dequeue,
and rb_* functions among the top offenders. With this patch,
only netem_enqueue is noticeable if jitter is low/absent.

Suggested-by: Eric Dumazet 
Signed-off-by: Peter Oskolkov 
Reviewed-by: Eric Dumazet 
Signed-off-by: David S. Miller

net: Prevent invalid access to skb->prev in __qdisc_drop_all

2018-11-30T00:27:27+00:00

__qdisc_drop_all() accesses skb->prev to get to the tail of the
segment-list.

With commit 68d2f84a1368 ("net: gro: properly remove skb from list")
the skb-list handling has been changed to set skb->next to NULL and set
the list-poison on skb->prev.

With that change, __qdisc_drop_all() will panic when it tries to
dereference skb->prev.

Since commit 992cba7e276d ("net: Add and use skb_list_del_init().")
__list_del_entry is used, leaving skb->prev unchanged (thus,
pointing to the list-head if it's the first skb of the list).
This will make __qdisc_drop_all modify the next-pointer of the list-head
and result in a panic later on:

[   34.501053] general protection fault: 0000 [#1] SMP KASAN PTI
[   34.501968] CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.20.0-rc2.mptcp #108
[   34.502887] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.5.1 01/01/2011
[   34.504074] RIP: 0010:dev_gro_receive+0x343/0x1f90
[   34.504751] Code: e0 48 c1 e8 03 42 80 3c 30 00 0f 85 4a 1c 00 00 4d 8b 24 24 4c 39 65 d0 0f 84 0a 04 00 00 49 8d 7c 24 38 48 89 f8 48 c1 e8 03 <42> 0f b6 04 30 84 c0 74 08 3c 04
[   34.507060] RSP: 0018:ffff8883af507930 EFLAGS: 00010202
[   34.507761] RAX: 0000000000000007 RBX: ffff8883970b2c80 RCX: 1ffff11072e165a6
[   34.508640] RDX: 1ffff11075867008 RSI: ffff8883ac338040 RDI: 0000000000000038
[   34.509493] RBP: ffff8883af5079d0 R08: ffff8883970b2d40 R09: 0000000000000062
[   34.510346] R10: 0000000000000034 R11: 0000000000000000 R12: 0000000000000000
[   34.511215] R13: 0000000000000000 R14: dffffc0000000000 R15: ffff8883ac338008
[   34.512082] FS:  0000000000000000(0000) GS:ffff8883af500000(0000) knlGS:0000000000000000
[   34.513036] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   34.513741] CR2: 000055ccc3e9d020 CR3: 00000003abf32000 CR4: 00000000000006e0
[   34.514593] Call Trace:
[   34.514893]  
[   34.515157]  napi_gro_receive+0x93/0x150
[   34.515632]  receive_buf+0x893/0x3700
[   34.516094]  ? __netif_receive_skb+0x1f/0x1a0
[   34.516629]  ? virtnet_probe+0x1b40/0x1b40
[   34.517153]  ? __stable_node_chain+0x4d0/0x850
[   34.517684]  ? kfree+0x9a/0x180
[   34.518067]  ? __kasan_slab_free+0x171/0x190
[   34.518582]  ? detach_buf+0x1df/0x650
[   34.519061]  ? lapic_next_event+0x5a/0x90
[   34.519539]  ? virtqueue_get_buf_ctx+0x280/0x7f0
[   34.520093]  virtnet_poll+0x2df/0xd60
[   34.520533]  ? receive_buf+0x3700/0x3700
[   34.521027]  ? qdisc_watchdog_schedule_ns+0xd5/0x140
[   34.521631]  ? htb_dequeue+0x1817/0x25f0
[   34.522107]  ? sch_direct_xmit+0x142/0xf30
[   34.522595]  ? virtqueue_napi_schedule+0x26/0x30
[   34.523155]  net_rx_action+0x2f6/0xc50
[   34.523601]  ? napi_complete_done+0x2f0/0x2f0
[   34.524126]  ? kasan_check_read+0x11/0x20
[   34.524608]  ? _raw_spin_lock+0x7d/0xd0
[   34.525070]  ? _raw_spin_lock_bh+0xd0/0xd0
[   34.525563]  ? kvm_guest_apic_eoi_write+0x6b/0x80
[   34.526130]  ? apic_ack_irq+0x9e/0xe0
[   34.526567]  __do_softirq+0x188/0x4b5
[   34.527015]  irq_exit+0x151/0x180
[   34.527417]  do_IRQ+0xdb/0x150
[   34.527783]  common_interrupt+0xf/0xf
[   34.528223]  

This patch makes sure that skb->prev is set to NULL when entering
netem_enqueue.

Cc: Prashant Bhole 
Cc: Tyler Hicks 
Cc: Eric Dumazet 
Fixes: 68d2f84a1368 ("net: gro: properly remove skb from list")
Suggested-by: Eric Dumazet 
Signed-off-by: Christoph Paasch 
Reviewed-by: Eric Dumazet 
Signed-off-by: David S. Miller

act_mirred: clear skb->tstamp on redirect

2018-11-11T18:21:31+00:00

If sch_fq is used at ingress, skbs that might have been
timestamped by net_timestamp_set() if a packet capture
is requesting timestamps could be delayed by arbitrary
amount of time, since sch_fq time base is MONOTONIC.

Fix this problem by moving code from sch_netem.c to act_mirred.c.

Fixes: fb420d5d91c1 ("tcp/fq: move back to CLOCK_MONOTONIC")
Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller

net: sched: rename qdisc_destroy() to qdisc_put()

2018-09-26T03:17:35+00:00

Current implementation of qdisc_destroy() decrements Qdisc reference
counter and only actually destroy Qdisc if reference counter value reached
zero. Rename qdisc_destroy() to qdisc_put() in order for it to better
describe the way in which this function currently implemented and used.

Extract code that deallocates Qdisc into new private qdisc_destroy()
function. It is intended to be shared between regular qdisc_put() and its
unlocked version that is introduced in next patch in this series.

Signed-off-by: Vlad Buslov 
Acked-by: Jiri Pirko 
Signed-off-by: David S. Miller

net: Add and use skb_mark_not_on_list().

2018-09-10T17:06:54+00:00

An SKB is not on a list if skb->next is NULL.

Codify this convention into a helper function and use it
where we are dequeueing an SKB and need to mark it as such.

Signed-off-by: David S. Miller

sch_netem: Move private queue handler to generic location.

2018-09-10T17:06:53+00:00

By hand copies of SKB list handlers do not belong in individual packet
schedulers.

Signed-off-by: David S. Miller

netem: slotting with non-uniform distribution

2018-06-28T13:06:24+00:00

Extend slotting with support for non-uniform distributions. This is
similar to netem's non-uniform distribution delay feature.

Commit f043efeae2f1 ("netem: support delivering packets in delayed
time slots") added the slotting feature to approximate the behaviors
of media with packet aggregation but only supported a uniform
distribution for delays between transmission attempts. Tests with TCP
BBR with emulated wifi links with non-uniform distributions produced
more useful results.

Syntax:
   slot dist DISTRIBUTION DELAY JITTER [packets MAX_PACKETS] \
      [bytes MAX_BYTES]

The syntax and use of the distribution table is the same as in the
non-uniform distribution delay feature. A file DISTRIBUTION must be
present in TC_LIB_DIR (e.g. /usr/lib/tc) containing numbers scaled by
NETEM_DIST_SCALE. A random value x is selected from the table and it
takes DELAY + ( x * JITTER ) as delay. Correlation between values is not
supported.

Examples:
  Normal distribution delay with mean = 800us and stdev = 100us.
  > tc qdisc add dev eth0 root netem slot dist normal 800us 100us

  Optionally set the max slot size in bytes and/or packets.
  > tc qdisc add dev eth0 root netem slot dist normal 800us 100us \
    bytes 64k packets 42

Signed-off-by: Yousuk Seung 
Acked-by: Eric Dumazet 
Acked-by: Neal Cardwell 
Signed-off-by: David S. Miller

sch_netem: fix skb leak in netem_enqueue()

2018-03-07T16:18:14+00:00

When we exceed current packets limit and we have more than one
segment in the list returned by skb_gso_segment(), netem drops
only the first one, skipping the rest, hence kmemleak reports:

unreferenced object 0xffff880b5d23b600 (size 1024):
  comm "softirq", pid 0, jiffies 4384527763 (age 2770.629s)
  hex dump (first 32 bytes):
    00 80 23 5d 0b 88 ff ff 00 00 00 00 00 00 00 00  ..#]............
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<00000000d8a19b9d>] __alloc_skb+0xc9/0x520
    [<000000001709b32f>] skb_segment+0x8c8/0x3710
    [<00000000c7b9bb88>] tcp_gso_segment+0x331/0x1830
    [<00000000c921cba1>] inet_gso_segment+0x476/0x1370
    [<000000008b762dd4>] skb_mac_gso_segment+0x1f9/0x510
    [<000000002182660a>] __skb_gso_segment+0x1dd/0x620
    [<00000000412651b9>] netem_enqueue+0x1536/0x2590 [sch_netem]
    [<0000000005d3b2a9>] __dev_queue_xmit+0x1167/0x2120
    [<00000000fc5f7327>] ip_finish_output2+0x998/0xf00
    [<00000000d309e9d3>] ip_output+0x1aa/0x2c0
    [<000000007ecbd3a4>] tcp_transmit_skb+0x18db/0x3670
    [<0000000042d2a45f>] tcp_write_xmit+0x4d4/0x58c0
    [<0000000056a44199>] tcp_tasklet_func+0x3d9/0x540
    [<0000000013d06d02>] tasklet_action+0x1ca/0x250
    [<00000000fcde0b8b>] __do_softirq+0x1b4/0x5a3
    [<00000000e7ed027c>] irq_exit+0x1e2/0x210

Fix it by adding the rest of the segments, if any, to skb 'to_free'
list. Add new __qdisc_drop_all() and qdisc_drop_all() functions
because they can be useful in the future if we need to drop segmented
GSO packets in other places.

Fixes: 6071bd1aa13e ("netem: Segment GSO packets on enqueue")
Signed-off-by: Alexey Kodanev 
Acked-by: Neil Horman 
Signed-off-by: David S. Miller