Skip to content

K
Kernel

openeuler / Kernel
12 个月 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. 16 4月, 2019 1 次提交
    • J
      route: Avoid crash from dereferencing NULL rt->from · 9c69a132
      由 Jonathan Lemon 提交于 
      When __ip6_rt_update_pmtu() is called, rt->from is RCU dereferenced, but is
never checked for null - rt6_flush_exceptions() may have removed the entry.

[ 1913.989004] RIP: 0010:ip6_rt_cache_alloc+0x13/0x170
[ 1914.209410] Call Trace:
[ 1914.214798]  <IRQ>
[ 1914.219226]  __ip6_rt_update_pmtu+0xb0/0x190
[ 1914.228649]  ip6_tnl_xmit+0x2c2/0x970 [ip6_tunnel]
[ 1914.239223]  ? ip6_tnl_parse_tlv_enc_lim+0x32/0x1a0 [ip6_tunnel]
[ 1914.252489]  ? __gre6_xmit+0x148/0x530 [ip6_gre]
[ 1914.262678]  ip6gre_tunnel_xmit+0x17e/0x3c7 [ip6_gre]
[ 1914.273831]  dev_hard_start_xmit+0x8d/0x1f0
[ 1914.283061]  sch_direct_xmit+0xfa/0x230
[ 1914.291521]  __qdisc_run+0x154/0x4b0
[ 1914.299407]  net_tx_action+0x10e/0x1f0
[ 1914.307678]  __do_softirq+0xca/0x297
[ 1914.315567]  irq_exit+0x96/0xa0
[ 1914.322494]  smp_apic_timer_interrupt+0x68/0x130
[ 1914.332683]  apic_timer_interrupt+0xf/0x20
[ 1914.341721]  </IRQ>

Fixes: a68886a6 ("net/ipv6: Make from in rt6_info rcu protected")
Signed-off-by: NJonathan Lemon <jonathan.lemon@gmail.com>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Reviewed-by: NDavid Ahern <dsahern@gmail.com>
Reviewed-by: NMartin KaFai Lau <kafai@fb.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      9c69a132
  3. 13 4月, 2019 2 次提交
  5. 12 4月, 2019 12 次提交
  7. 09 4月, 2019 6 次提交
  9. 08 4月, 2019 1 次提交
    • N
      rhashtable: use bit_spin_locks to protect hash bucket. · 8f0db018
      由 NeilBrown 提交于 
      This patch changes rhashtables to use a bit_spin_lock on BIT(1) of the
bucket pointer to lock the hash chain for that bucket.

The benefits of a bit spin_lock are:
 - no need to allocate a separate array of locks.
 - no need to have a configuration option to guide the
   choice of the size of this array
 - locking cost is often a single test-and-set in a cache line
   that will have to be loaded anyway.  When inserting at, or removing
   from, the head of the chain, the unlock is free - writing the new
   address in the bucket head implicitly clears the lock bit.
   For __rhashtable_insert_fast() we ensure this always happens
   when adding a new key.
 - even when lockings costs 2 updates (lock and unlock), they are
   in a cacheline that needs to be read anyway.

The cost of using a bit spin_lock is a little bit of code complexity,
which I think is quite manageable.

Bit spin_locks are sometimes inappropriate because they are not fair -
if multiple CPUs repeatedly contend of the same lock, one CPU can
easily be starved.  This is not a credible situation with rhashtable.
Multiple CPUs may want to repeatedly add or remove objects, but they
will typically do so at different buckets, so they will attempt to
acquire different locks.

As we have more bit-locks than we previously had spinlocks (by at
least a factor of two) we can expect slightly less contention to
go with the slightly better cache behavior and reduced memory
consumption.

To enhance type checking, a new struct is introduced to represent the
  pointer plus lock-bit
that is stored in the bucket-table.  This is "struct rhash_lock_head"
and is empty.  A pointer to this needs to be cast to either an
unsigned lock, or a "struct rhash_head *" to be useful.
Variables of this type are most often called "bkt".

Previously "pprev" would sometimes point to a bucket, and sometimes a
->next pointer in an rhash_head.  As these are now different types,
pprev is NULL when it would have pointed to the bucket. In that case,
'blk' is used, together with correct locking protocol.
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      8f0db018
  11. 05 4月, 2019 1 次提交
    • L
      ipv6: sit: reset ip header pointer in ipip6_rcv · bb9bd814
      由 Lorenzo Bianconi 提交于 
      ipip6 tunnels run iptunnel_pull_header on received skbs. This can
determine the following use-after-free accessing iph pointer since
the packet will be 'uncloned' running pskb_expand_head if it is a
cloned gso skb (e.g if the packet has been sent though a veth device)

[  706.369655] BUG: KASAN: use-after-free in ipip6_rcv+0x1678/0x16e0 [sit]
[  706.449056] Read of size 1 at addr ffffe01b6bd855f5 by task ksoftirqd/1/=
[  706.669494] Hardware name: HPE ProLiant m400 Server/ProLiant m400 Server, BIOS U02 08/19/2016
[  706.771839] Call trace:
[  706.801159]  dump_backtrace+0x0/0x2f8
[  706.845079]  show_stack+0x24/0x30
[  706.884833]  dump_stack+0xe0/0x11c
[  706.925629]  print_address_description+0x68/0x260
[  706.982070]  kasan_report+0x178/0x340
[  707.025995]  __asan_report_load1_noabort+0x30/0x40
[  707.083481]  ipip6_rcv+0x1678/0x16e0 [sit]
[  707.132623]  tunnel64_rcv+0xd4/0x200 [tunnel4]
[  707.185940]  ip_local_deliver_finish+0x3b8/0x988
[  707.241338]  ip_local_deliver+0x144/0x470
[  707.289436]  ip_rcv_finish+0x43c/0x14b0
[  707.335447]  ip_rcv+0x628/0x1138
[  707.374151]  __netif_receive_skb_core+0x1670/0x2600
[  707.432680]  __netif_receive_skb+0x28/0x190
[  707.482859]  process_backlog+0x1d0/0x610
[  707.529913]  net_rx_action+0x37c/0xf68
[  707.574882]  __do_softirq+0x288/0x1018
[  707.619852]  run_ksoftirqd+0x70/0xa8
[  707.662734]  smpboot_thread_fn+0x3a4/0x9e8
[  707.711875]  kthread+0x2c8/0x350
[  707.750583]  ret_from_fork+0x10/0x18

[  707.811302] Allocated by task 16982:
[  707.854182]  kasan_kmalloc.part.1+0x40/0x108
[  707.905405]  kasan_kmalloc+0xb4/0xc8
[  707.948291]  kasan_slab_alloc+0x14/0x20
[  707.994309]  __kmalloc_node_track_caller+0x158/0x5e0
[  708.053902]  __kmalloc_reserve.isra.8+0x54/0xe0
[  708.108280]  __alloc_skb+0xd8/0x400
[  708.150139]  sk_stream_alloc_skb+0xa4/0x638
[  708.200346]  tcp_sendmsg_locked+0x818/0x2b90
[  708.251581]  tcp_sendmsg+0x40/0x60
[  708.292376]  inet_sendmsg+0xf0/0x520
[  708.335259]  sock_sendmsg+0xac/0xf8
[  708.377096]  sock_write_iter+0x1c0/0x2c0
[  708.424154]  new_sync_write+0x358/0x4a8
[  708.470162]  __vfs_write+0xc4/0xf8
[  708.510950]  vfs_write+0x12c/0x3d0
[  708.551739]  ksys_write+0xcc/0x178
[  708.592533]  __arm64_sys_write+0x70/0xa0
[  708.639593]  el0_svc_handler+0x13c/0x298
[  708.686646]  el0_svc+0x8/0xc

[  708.739019] Freed by task 17:
[  708.774597]  __kasan_slab_free+0x114/0x228
[  708.823736]  kasan_slab_free+0x10/0x18
[  708.868703]  kfree+0x100/0x3d8
[  708.905320]  skb_free_head+0x7c/0x98
[  708.948204]  skb_release_data+0x320/0x490
[  708.996301]  pskb_expand_head+0x60c/0x970
[  709.044399]  __iptunnel_pull_header+0x3b8/0x5d0
[  709.098770]  ipip6_rcv+0x41c/0x16e0 [sit]
[  709.146873]  tunnel64_rcv+0xd4/0x200 [tunnel4]
[  709.200195]  ip_local_deliver_finish+0x3b8/0x988
[  709.255596]  ip_local_deliver+0x144/0x470
[  709.303692]  ip_rcv_finish+0x43c/0x14b0
[  709.349705]  ip_rcv+0x628/0x1138
[  709.388413]  __netif_receive_skb_core+0x1670/0x2600
[  709.446943]  __netif_receive_skb+0x28/0x190
[  709.497120]  process_backlog+0x1d0/0x610
[  709.544169]  net_rx_action+0x37c/0xf68
[  709.589131]  __do_softirq+0x288/0x1018

[  709.651938] The buggy address belongs to the object at ffffe01b6bd85580
                which belongs to the cache kmalloc-1024 of size 1024
[  709.804356] The buggy address is located 117 bytes inside of
                1024-byte region [ffffe01b6bd85580, ffffe01b6bd85980)
[  709.946340] The buggy address belongs to the page:
[  710.003824] page:ffff7ff806daf600 count:1 mapcount:0 mapping:ffffe01c4001f600 index:0x0
[  710.099914] flags: 0xfffff8000000100(slab)
[  710.149059] raw: 0fffff8000000100 dead000000000100 dead000000000200 ffffe01c4001f600
[  710.242011] raw: 0000000000000000 0000000000380038 00000001ffffffff 0000000000000000
[  710.334966] page dumped because: kasan: bad access detected

Fix it resetting iph pointer after iptunnel_pull_header

Fixes: a09a4c8d ("tunnels: Remove encapsulation offloads on decap")
Tested-by: NJianlin Shi <jishi@redhat.com>
Signed-off-by: NLorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      bb9bd814
  13. 04 4月, 2019 2 次提交
  15. 03 4月, 2019 1 次提交
  17. 02 4月, 2019 1 次提交
    • E
      tcp: fix tcp_inet6_sk() for 32bit kernels · f5d54767
      由 Eric Dumazet 提交于 
      It turns out that struct ipv6_pinfo is not located as we think.

inet6_sk_generic() and tcp_inet6_sk() disagree on 32bit kernels by 4-bytes,
because struct tcp_sock has 8-bytes alignment,
but ipv6_pinfo size is not a multiple of 8.

sizeof(struct ipv6_pinfo): 116 (not padded to 8)

I actually first coded tcp_inet6_sk() as this patch does, but thought
that "container_of(tcp_sk(sk), struct tcp6_sock, tcp)" was cleaner.

As Julian told me : Nobody should use tcp6_sock.inet6
directly, it should be accessed via tcp_inet6_sk() or inet6_sk().

This happened when we added the first u64 field in struct tcp_sock.

Fixes: 93a77c11 ("tcp: add tcp_inet6_sk() helper")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Bisected-by: NJulian Anastasov <ja@ssi.bg>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      f5d54767
  19. 30 3月, 2019 9 次提交
  21. 28 3月, 2019 2 次提交
  23. 24 3月, 2019 1 次提交
    • E
      tcp: add one skb cache for rx · 8b27dae5
      由 Eric Dumazet 提交于 
      Often times, recvmsg() system calls and BH handling for a particular
TCP socket are done on different cpus.

This means the incoming skb had to be allocated on a cpu,
but freed on another.

This incurs a high spinlock contention in slab layer for small rpc,
but also a high number of cache line ping pongs for larger packets.

A full size GRO packet might use 45 page fragments, meaning
that up to 45 put_page() can be involved.

More over performing the __kfree_skb() in the recvmsg() context
adds a latency for user applications, and increase probability
of trapping them in backlog processing, since the BH handler
might found the socket owned by the user.

This patch, combined with the prior one increases the rpc
performance by about 10 % on servers with large number of cores.

(tcp_rr workload with 10,000 flows and 112 threads reach 9 Mpps
 instead of 8 Mpps)

This also increases single bulk flow performance on 40Gbit+ links,
since in this case there are often two cpus working in tandem :

 - CPU handling the NIC rx interrupts, feeding the receive queue,
  and (after this patch) freeing the skbs that were consumed.

 - CPU in recvmsg() system call, essentially 100 % busy copying out
  data to user space.

Having at most one skb in a per-socket cache has very little risk
of memory exhaustion, and since it is protected by socket lock,
its management is essentially free.

Note that if rps/rfs is used, we do not enable this feature, because
there is high chance that the same cpu is handling both the recvmsg()
system call and the TCP rx path, but that another cpu did the skb
allocations in the device driver right before the RPS/RFS logic.

To properly handle this case, it seems we would need to record
on which cpu skb was allocated, and use a different channel
to give skbs back to this cpu.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NSoheil Hassas Yeganeh <soheil@google.com>
Acked-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      8b27dae5
  25. 22 3月, 2019 1 次提交
    • J
      genetlink: make policy common to family · 3b0f31f2
      由 Johannes Berg 提交于 
      Since maxattr is common, the policy can't really differ sanely,
so make it common as well.

The only user that did in fact manage to make a non-common policy
is taskstats, which has to be really careful about it (since it's
still using a common maxattr!). This is no longer supported, but
we can fake it using pre_doit.

This reduces the size of e.g. nl80211.o (which has lots of commands):

   text	   data	    bss	    dec	    hex	filename
 398745	  14323	   2240	 415308	  6564c	net/wireless/nl80211.o (before)
 397913	  14331	   2240	 414484	  65314	net/wireless/nl80211.o (after)
--------------------------------
   -832      +8       0    -824

Which is obviously just 8 bytes for each command, and an added 8
bytes for the new policy pointer. I'm not sure why the ops list is
counted as .text though.

Most of the code transformations were done using the following spatch:
    @ops@
    identifier OPS;
    expression POLICY;
    @@
    struct genl_ops OPS[] = {
    ...,
     {
    -	.policy = POLICY,
     },
    ...
    };

    @@
    identifier ops.OPS;
    expression ops.POLICY;
    identifier fam;
    expression M;
    @@
    struct genl_family fam = {
            .ops = OPS,
            .maxattr = M,
    +       .policy = POLICY,
            ...
    };

This also gets rid of devlink_nl_cmd_region_read_dumpit() accessing
the cb->data as ops, which we want to change in a later genl patch.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      3b0f31f2