Skip to content

K
Kernel

openeuler / Kernel
大约 1 年 前同步成功

通知 5
Star 0
Fork 0
K
Kernel

体验新版 GitCode，发现更多精彩内容 >>

切换分支/标签
  1. 29 9月, 2014 15 次提交
  3. 27 9月, 2014 5 次提交
  5. 26 9月, 2014 4 次提交
    • E
      net: sched: use pinned timers · 4a8e320c
      由 Eric Dumazet 提交于 
      While using a MQ + NETEM setup, I had confirmation that the default
timer migration ( /proc/sys/kernel/timer_migration ) is killing us.

Installing this on a receiver side of a TCP_STREAM test, (NIC has 8 TX
queues) :

EST="est 1sec 4sec"
for ETH in eth1
do
 tc qd del dev $ETH root 2>/dev/null
 tc qd add dev $ETH root handle 1: mq
 tc qd add dev $ETH parent 1:1 $EST netem limit 70000 delay 6ms
 tc qd add dev $ETH parent 1:2 $EST netem limit 70000 delay 8ms
 tc qd add dev $ETH parent 1:3 $EST netem limit 70000 delay 10ms
 tc qd add dev $ETH parent 1:4 $EST netem limit 70000 delay 12ms
 tc qd add dev $ETH parent 1:5 $EST netem limit 70000 delay 14ms
 tc qd add dev $ETH parent 1:6 $EST netem limit 70000 delay 16ms
 tc qd add dev $ETH parent 1:7 $EST netem limit 80000 delay 18ms
 tc qd add dev $ETH parent 1:8 $EST netem limit 90000 delay 20ms
done

We can see that timers get migrated into a single cpu, presumably idle
at the time timers are set up.
Then all qdisc dequeues run from this cpu and huge lock contention
happens. This single cpu is stuck in softirq mode and cannot dequeue
fast enough.

    39.24%  [kernel]          [k] _raw_spin_lock
     2.65%  [kernel]          [k] netem_enqueue
     1.80%  [kernel]          [k] netem_dequeue
     1.63%  [kernel]          [k] copy_user_enhanced_fast_string
     1.45%  [kernel]          [k] _raw_spin_lock_bh

By pinning qdisc timers on the cpu running the qdisc, we respect proper
XPS setting and remove this lock contention.

     5.84%  [kernel]          [k] netem_enqueue
     4.83%  [kernel]          [k] _raw_spin_lock
     2.92%  [kernel]          [k] copy_user_enhanced_fast_string

Current Qdiscs that benefit from this change are :

	netem, cbq, fq, hfsc, tbf, htb.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      4a8e320c
    • T
      net: Remove gso_send_check as an offload callback · 53e50398
      由 Tom Herbert 提交于 
      The send_check logic was only interesting in cases of TCP offload and
UDP UFO where the checksum needed to be initialized to the pseudo
header checksum. Now we've moved that logic into the related
gso_segment functions so gso_send_check is no longer needed.
Signed-off-by: NTom Herbert <therbert@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      53e50398
    • T
      udp: move logic out of udp[46]_ufo_send_check · f71470b3
      由 Tom Herbert 提交于 
      In udp[46]_ufo_send_check the UDP checksum initialized to the pseudo
header checksum. We can move this logic into udp[46]_ufo_fragment.
After this change udp[64]_ufo_send_check is a no-op.
Signed-off-by: NTom Herbert <therbert@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      f71470b3
    • T
      tcp: move logic out of tcp_v[64]_gso_send_check · d020f8f7
      由 Tom Herbert 提交于 
      In tcp_v[46]_gso_send_check the TCP checksum is initialized to the
pseudo header checksum using __tcp_v[46]_send_check. We can move this
logic into new tcp[46]_gso_segment functions to be done when
ip_summed != CHECKSUM_PARTIAL (ip_summed == CHECKSUM_PARTIAL should be
the common case, possibly always true when taking GSO path). After this
change tcp_v[46]_gso_send_check is no-op.
Signed-off-by: NTom Herbert <therbert@google.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      d020f8f7
  7. 24 9月, 2014 2 次提交
    • E
      tcp: add coalescing attempt in tcp_ofo_queue() · bd1e75ab
      由 Eric Dumazet 提交于 
      In order to make TCP more resilient in presence of reorders, we need
to allow coalescing to happen when skbs from out of order queue are
transferred into receive queue. LRO/GRO can be completely canceled
in some pathological cases, like per packet load balancing on aggregated
links.

I had to move tcp_try_coalesce() up in the file above tcp_ofo_queue()
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      bd1e75ab
    • E
      icmp: add a global rate limitation · 4cdf507d
      由 Eric Dumazet 提交于 
      Current ICMP rate limiting uses inetpeer cache, which is an RBL tree
protected by a lock, meaning that hosts can be stuck hard if all cpus
want to check ICMP limits.

When say a DNS or NTP server process is restarted, inetpeer tree grows
quick and machine comes to its knees.

iptables can not help because the bottleneck happens before ICMP
messages are even cooked and sent.

This patch adds a new global limitation, using a token bucket filter,
controlled by two new sysctl :

icmp_msgs_per_sec - INTEGER
    Limit maximal number of ICMP packets sent per second from this host.
    Only messages whose type matches icmp_ratemask are
    controlled by this limit.
    Default: 1000

icmp_msgs_burst - INTEGER
    icmp_msgs_per_sec controls number of ICMP packets sent per second,
    while icmp_msgs_burst controls the burst size of these packets.
    Default: 50

Note that if we really want to send millions of ICMP messages per
second, we might extend idea and infra added in commit 04ca6973
("ip: make IP identifiers less predictable") :
add a token bucket in the ip_idents hash and no longer rely on inetpeer.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      4cdf507d
  9. 23 9月, 2014 12 次提交
    • E
      ipv4: do not use this_cpu_ptr() in preemptible context · a35165ca
      由 Eric Dumazet 提交于 
      this_cpu_ptr() in preemptible context is generally bad

Sep 22 05:05:55 br kernel: [   94.608310] BUG: using smp_processor_id()
in
preemptible [00000000] code: ip/2261
Sep 22 05:05:55 br kernel: [   94.608316] caller is
tunnel_dst_set.isra.28+0x20/0x60 [ip_tunnel]
Sep 22 05:05:55 br kernel: [   94.608319] CPU: 3 PID: 2261 Comm: ip Not
tainted
3.17.0-rc5 #82

We can simply use raw_cpu_ptr(), as preemption is safe in these
contexts.

Should fix https://bugzilla.kernel.org/show_bug.cgi?id=84991Signed-off-by: NEric Dumazet <edumazet@google.com>
Reported-by: NJoe <joe9mail@gmail.com>
Fixes: 9a4aa9af ("ipv4: Use percpu Cache route in IP tunnels")
Acked-by: NTom Herbert <therbert@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      a35165ca
    • E
      net: sched: fix compile warning in cls_u32 · a2aeb02a
      由 Eric Dumazet 提交于 
      $ grep CONFIG_CLS_U32_MARK .config
# CONFIG_CLS_U32_MARK is not set

net/sched/cls_u32.c: In function 'u32_change':
net/sched/cls_u32.c:852:1: warning: label 'errout' defined but not used
[-Wunused-label]
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      a2aeb02a
    • E
      tcp: avoid possible arithmetic overflows · fcdd1cf4
      由 Eric Dumazet 提交于 
      icsk_rto is a 32bit field, and icsk_backoff can reach 15 by default,
or more if some sysctl (eg tcp_retries2) are changed.

Better use 64bit to perform icsk_rto << icsk_backoff operations

As Joe Perches suggested, add a helper for this.

Yuchung spotted the tcp_v4_err() case.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      fcdd1cf4
    • D
      ipv6: mld: answer mldv2 queries with mldv1 reports in mldv1 fallback · 35f7aa53
      由 Daniel Borkmann 提交于 
      RFC2710 (MLDv1), section 3.7. says:

  The length of a received MLD message is computed by taking the
  IPv6 Payload Length value and subtracting the length of any IPv6
  extension headers present between the IPv6 header and the MLD
  message. If that length is greater than 24 octets, that indicates
  that there are other fields present *beyond* the fields described
  above, perhaps belonging to a *future backwards-compatible* version
  of MLD. An implementation of the version of MLD specified in this
  document *MUST NOT* send an MLD message longer than 24 octets and
  MUST ignore anything past the first 24 octets of a received MLD
  message.

RFC3810 (MLDv2), section 8.2.1. states for *listeners* regarding
presence of MLDv1 routers:

  In order to be compatible with MLDv1 routers, MLDv2 hosts MUST
  operate in version 1 compatibility mode. [...] When Host
  Compatibility Mode is MLDv2, a host acts using the MLDv2 protocol
  on that interface. When Host Compatibility Mode is MLDv1, a host
  acts in MLDv1 compatibility mode, using *only* the MLDv1 protocol,
  on that interface. [...]

While section 8.3.1. specifies *router* behaviour regarding presence
of MLDv1 routers:

  MLDv2 routers may be placed on a network where there is at least
  one MLDv1 router. The following requirements apply:

  If an MLDv1 router is present on the link, the Querier MUST use
  the *lowest* version of MLD present on the network. This must be
  administratively assured. Routers that desire to be compatible
  with MLDv1 MUST have a configuration option to act in MLDv1 mode;
  if an MLDv1 router is present on the link, the system administrator
  must explicitly configure all MLDv2 routers to act in MLDv1 mode.
  When in MLDv1 mode, the Querier MUST send periodic General Queries
  truncated at the Multicast Address field (i.e., 24 bytes long),
  and SHOULD also warn about receiving an MLDv2 Query (such warnings
  must be rate-limited). The Querier MUST also fill in the Maximum
  Response Delay in the Maximum Response Code field, i.e., the
  exponential algorithm described in section 5.1.3. is not used. [...]

That means that we should not get queries from different versions of
MLD. When there's a MLDv1 router present, MLDv2 enforces truncation
and MRC == MRD (both fields are overlapping within the 24 octet range).

Section 8.3.2. specifies behaviour in the presence of MLDv1 multicast
address *listeners*:

  MLDv2 routers may be placed on a network where there are hosts
  that have not yet been upgraded to MLDv2. In order to be compatible
  with MLDv1 hosts, MLDv2 routers MUST operate in version 1 compatibility
  mode. MLDv2 routers keep a compatibility mode per multicast address
  record. The compatibility mode of a multicast address is determined
  from the Multicast Address Compatibility Mode variable, which can be
  in one of the two following states: MLDv1 or MLDv2.

  The Multicast Address Compatibility Mode of a multicast address
  record is set to MLDv1 whenever an MLDv1 Multicast Listener Report is
  *received* for that multicast address. At the same time, the Older
  Version Host Present timer for the multicast address is set to Older
  Version Host Present Timeout seconds. The timer is re-set whenever a
  new MLDv1 Report is received for that multicast address. If the Older
  Version Host Present timer expires, the router switches back to
  Multicast Address Compatibility Mode of MLDv2 for that multicast
  address. [...]

That means, what can happen is the following scenario, that hosts can
act in MLDv1 compatibility mode when they previously have received an
MLDv1 query (or, simply operate in MLDv1 mode-only); and at the same
time, an MLDv2 router could start up and transmits MLDv2 startup query
messages while being unaware of the current operational mode.

Given RFC2710, section 3.7 we would need to answer to that with an MLDv1
listener report, so that the router according to RFC3810, section 8.3.2.
would receive that and internally switch to MLDv1 compatibility as well.

Right now, I believe since the initial implementation of MLDv2, Linux
hosts would just silently drop such MLDv2 queries instead of replying
with an MLDv1 listener report, which would prevent a MLDv2 router going
into fallback mode (until it receives other MLDv1 queries).

Since the mapping of MRC to MRD in exactly such cases can make use of
the exponential algorithm from 5.1.3, we cannot [strictly speaking] be
aware in MLDv1 of the encoding in MRC, it seems also not mentioned by
the RFC. Since encodings are the same up to 32767, assume in such a
situation this value as a hard upper limit we would clamp. We have asked
one of the RFC authors on that regard, and he mentioned that there seem
not to be any implementations that make use of that exponential algorithm
on startup messages. In any case, this patch fixes this MLD
interoperability issue.
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Acked-by: NHannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      35f7aa53
    • L
      net: rfkill: gpio: Fix clock status · fa5c107c
      由 Loic Poulain 提交于 
      Clock is disabled when the device is blocked.
So, clock_enabled is the logical negation of "blocked".
Signed-off-by: NLoic Poulain <loic.poulain@intel.com>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>
      fa5c107c
    • J
      net: sched: cls_u32 changes to knode must appear atomic to readers · de5df632
      由 John Fastabend 提交于 
      Changes to the cls_u32 classifier must appear atomic to the
readers. Before this patch if a change is requested for both
the exts and ifindex, first the ifindex is updated then the
exts with tcf_exts_change(). This opens a small window where
a reader can have a exts chain with an incorrect ifindex. This
violates the the RCU semantics.

Here we resolve this by always passing u32_set_parms() a copy
of the tc_u_knode to work on and then inserting it into the hash
table after the updates have been successfully applied.

Tested with the following short script:

#tc filter add dev p3p2 parent 8001:0 protocol ip prio 99 handle 1: \
	       u32 divisor 256

#tc filter add dev p3p2 parent 8001:0 protocol ip prio 99 \
	       u32 link 1: hashkey mask ffffff00 at 12    \
	       match ip src 192.168.8.0/2

#tc filter add dev p3p2 parent 8001:0 protocol ip prio 102    \
	       handle 1::10 u32 classid 1:2 ht 1: 	      \
	       match ip src 192.168.8.0/8 match ip tos 0x0a 1e

#tc filter change dev p3p2 parent 8001:0 protocol ip prio 102 \
		 handle 1::10 u32 classid 1:2 ht 1:        \
		 match ip src 1.1.0.0/8 match ip tos 0x0b 1e

CC: Eric Dumazet <edumazet@google.com>
CC: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      de5df632
    • J
      net: cls_u32: fix missed pcpu_success free_percpu · a1ddcfee
      由 John Fastabend 提交于 
      This fixes a missed free_percpu in the unwind code path and when
keys are destroyed.
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      a1ddcfee
    • T
      udp: Need to make ip6_udp_tunnel.c have GPL license · 3fcb95a8
      由 Tom Herbert 提交于 
      Unable to load various tunneling modules without this:

[   80.679049] fou: Unknown symbol udp_sock_create6 (err 0)
[   91.439939] ip6_udp_tunnel: Unknown symbol ip6_local_out (err 0)
[   91.439954] ip6_udp_tunnel: Unknown symbol __put_net (err 0)
[   91.457792] vxlan: Unknown symbol udp_sock_create6 (err 0)
[   91.457831] vxlan: Unknown symbol udp_tunnel6_xmit_skb (err 0)
Signed-off-by: NTom Herbert <therbert@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      3fcb95a8
    • J
      net: keep original skb which only needs header checking during software GSO · cecda693
      由 Jason Wang 提交于 
      Commit ce93718f ("net: Don't keep
around original SKB when we software segment GSO frames") frees the
original skb after software GSO even for dodgy gso skbs. This breaks
the stream throughput from untrusted sources, since only header
checking was done during software GSO instead of a true
segmentation. This patch fixes this by freeing the original gso skb
only when it was really segmented by software.

Fixes ce93718f ("net: Don't keep
around original SKB when we software segment GSO frames.")

Cc: David S. Miller <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      cecda693
    • F
      net: dsa: add {get, set}_wol callbacks to slave devices · 19e57c4e
      由 Florian Fainelli 提交于 
      Allow switch drivers to implement per-port Wake-on-LAN getter and
setters.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      19e57c4e
    • F
      net: dsa: allow switch drivers to implement suspend/resume hooks · 24462549
      由 Florian Fainelli 提交于 
      Add an abstraction layer to suspend/resume switch devices, doing the
following split:

- suspend/resume the slave network devices and their corresponding PHY
  devices
- suspend/resume the switch hardware using switch driver callbacks
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      24462549
    • E
      net: sched: shrink struct qdisc_skb_cb to 28 bytes · 25711786
      由 Eric Dumazet 提交于 
      We cannot make struct qdisc_skb_cb bigger without impacting IPoIB,
or increasing skb->cb[] size.

Commit e0f31d84 ("flow_keys: Record IP layer protocol in
skb_flow_dissect()") broke IPoIB.

Only current offender is sch_choke, and this one do not need an
absolutely precise flow key.

If we store 17 bytes of flow key, its more than enough. (Its the actual
size of flow_keys if it was a packed structure, but we might add new
fields at the end of it later)
Signed-off-by: NEric Dumazet <edumazet@google.com>
Fixes: e0f31d84 ("flow_keys: Record IP layer protocol in skb_flow_dissect()")
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      25711786
  11. 20 9月, 2014 2 次提交