linux-toradex.git/include/linux/rtnetlink.h, branch v5.10-rc3 Linux kernel for Apalis and Colibri modules net: sched: extend Qdisc with rcu 2018-09-26T03:17:35+00:00 Vlad Buslov vladbu@mellanox.com 2018-09-24T16:22:51+00:00 3a7d0d07a386716b459b00783b11a8211cefcc0f Currently, Qdisc API functions assume that users have rtnl lock taken. To implement rtnl unlocked classifiers update interface, Qdisc API must be extended with functions that do not require rtnl lock. Extend Qdisc structure with rcu. Implement special version of put function qdisc_put_unlocked() that is called without rtnl lock taken. This function only takes rtnl lock if Qdisc reference counter reached zero and is intended to be used as optimization. Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Currently, Qdisc API functions assume that users have rtnl lock taken. To
implement rtnl unlocked classifiers update interface, Qdisc API must be
extended with functions that do not require rtnl lock.

Extend Qdisc structure with rcu. Implement special version of put function
qdisc_put_unlocked() that is called without rtnl lock taken. This function
only takes rtnl lock if Qdisc reference counter reached zero and is
intended to be used as optimization.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net: core: netlink: add helper refcount dec and lock function 2018-09-26T03:17:35+00:00 Vlad Buslov vladbu@mellanox.com 2018-09-24T16:22:49+00:00 6f99528e9797794b91b43321fbbc93fe772b0803 Rtnl lock is encapsulated in netlink and cannot be accessed by other modules directly. This means that reference counted objects that rely on rtnl lock cannot use it with refcounter helper function that atomically releases decrements reference and obtains mutex. This patch implements simple wrapper function around refcount_dec_and_lock that obtains rtnl lock if reference counter value reached 0. Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Rtnl lock is encapsulated in netlink and cannot be accessed by other
modules directly. This means that reference counted objects that rely on
rtnl lock cannot use it with refcounter helper function that atomically
releases decrements reference and obtains mutex.

This patch implements simple wrapper function around refcount_dec_and_lock
that obtains rtnl lock if reference counter value reached 0.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net: Introduce net_rwsem to protect net_namespace_list 2018-03-29T17:47:53+00:00 Kirill Tkhai ktkhai@virtuozzo.com 2018-03-29T16:20:32+00:00 f0b07bb151b098d291fd1fd71ef7a2df56fb124a rtnl_lock() is used everywhere, and contention is very high. When someone wants to iterate over alive net namespaces, he/she has no a possibility to do that without exclusive lock. But the exclusive rtnl_lock() in such places is overkill, and it just increases the contention. Yes, there is already for_each_net_rcu() in kernel, but it requires rcu_read_lock(), and this can't be sleepable. Also, sometimes it may be need really prevent net_namespace_list growth, so for_each_net_rcu() is not fit there. This patch introduces new rw_semaphore, which will be used instead of rtnl_mutex to protect net_namespace_list. It is sleepable and allows not-exclusive iterations over net namespaces list. It allows to stop using rtnl_lock() in several places (what is made in next patches) and makes less the time, we keep rtnl_mutex. Here we just add new lock, while the explanation of we can remove rtnl_lock() there are in next patches. Fine grained locks generally are better, then one big lock, so let's do that with net_namespace_list, while the situation allows that. Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
rtnl_lock() is used everywhere, and contention is very high.
When someone wants to iterate over alive net namespaces,
he/she has no a possibility to do that without exclusive lock.
But the exclusive rtnl_lock() in such places is overkill,
and it just increases the contention. Yes, there is already
for_each_net_rcu() in kernel, but it requires rcu_read_lock(),
and this can't be sleepable. Also, sometimes it may be need
really prevent net_namespace_list growth, so for_each_net_rcu()
is not fit there.

This patch introduces new rw_semaphore, which will be used
instead of rtnl_mutex to protect net_namespace_list. It is
sleepable and allows not-exclusive iterations over net
namespaces list. It allows to stop using rtnl_lock()
in several places (what is made in next patches) and makes
less the time, we keep rtnl_mutex. Here we just add new lock,
while the explanation of we can remove rtnl_lock() there are
in next patches.

Fine grained locks generally are better, then one big lock,
so let's do that with net_namespace_list, while the situation
allows that.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net: Rename net_sem to pernet_ops_rwsem 2018-03-27T17:18:09+00:00 Kirill Tkhai ktkhai@virtuozzo.com 2018-03-27T15:02:23+00:00 4420bf21fb6c0306e36ad58ade1e741fba57ce65 net_sem is some undefined area name, so it will be better to make the area more defined. Rename it to pernet_ops_rwsem for better readability and better intelligibility. Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
net_sem is some undefined area name, so it will be better
to make the area more defined.

Rename it to pernet_ops_rwsem for better readability and
better intelligibility.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net: Add rtnl_lock_killable() 2018-03-16T16:31:19+00:00 Kirill Tkhai ktkhai@virtuozzo.com 2018-03-14T19:17:20+00:00 79ffdfc6522ae33d8a33e971070c08ee5f27439b rtnl_lock() is widely used mutex in kernel. Some of kernel code does memory allocations under it. In case of memory deficit this may invoke OOM killer, but the problem is a killed task can't exit if it's waiting for the mutex. This may be a reason of deadlock and panic. This patch adds a new primitive, which responds on SIGKILL, and it allows to use it in the places, where we don't want to sleep forever. Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
rtnl_lock() is widely used mutex in kernel. Some of kernel code
does memory allocations under it. In case of memory deficit this
may invoke OOM killer, but the problem is a killed task can't
exit if it's waiting for the mutex. This may be a reason of deadlock
and panic.

This patch adds a new primitive, which responds on SIGKILL, and
it allows to use it in the places, where we don't want to sleep
forever.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net: Kill net_mutex 2018-02-20T18:23:13+00:00 Kirill Tkhai ktkhai@virtuozzo.com 2018-02-19T09:58:38+00:00 19efbd93e6fb05eab81856b4fc8d64211dd37088 We take net_mutex, when there are !async pernet_operations registered, and read locking of net_sem is not enough. But we may get rid of taking the mutex, and just change the logic to write lock net_sem in such cases. This obviously reduces the number of lock operations, we do. Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
We take net_mutex, when there are !async pernet_operations
registered, and read locking of net_sem is not enough. But
we may get rid of taking the mutex, and just change the logic
to write lock net_sem in such cases. This obviously reduces
the number of lock operations, we do.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net: Introduce net_sem for protection of pernet_list 2018-02-13T15:36:04+00:00 Kirill Tkhai ktkhai@virtuozzo.com 2018-02-13T09:26:23+00:00 1a57feb847c56d6193f67d0e892c24e71f9e3ab1 Currently, the mutex is mostly used to protect pernet operations list. It orders setup_net() and cleanup_net() with parallel {un,}register_pernet_operations() calls, so ->exit{,batch} methods of the same pernet operations are executed for a dying net, as were used to call ->init methods, even after the net namespace is unlinked from net_namespace_list in cleanup_net(). But there are several problems with scalability. The first one is that more than one net can't be created or destroyed at the same moment on the node. For big machines with many cpus running many containers it's very sensitive. The second one is that it's need to synchronize_rcu() after net is removed from net_namespace_list(): Destroy net_ns: cleanup_net() mutex_lock(&net_mutex) list_del_rcu(&net->list) synchronize_rcu() <--- Sleep there for ages list_for_each_entry_reverse(ops, &pernet_list, list) ops_exit_list(ops, &net_exit_list) list_for_each_entry_reverse(ops, &pernet_list, list) ops_free_list(ops, &net_exit_list) mutex_unlock(&net_mutex) This primitive is not fast, especially on the systems with many processors and/or when preemptible RCU is enabled in config. So, all the time, while cleanup_net() is waiting for RCU grace period, creation of new net namespaces is not possible, the tasks, who makes it, are sleeping on the same mutex: Create net_ns: copy_net_ns() mutex_lock_killable(&net_mutex) <--- Sleep there for ages I observed 20-30 seconds hangs of "unshare -n" on ordinary 8-cpu laptop with preemptible RCU enabled after CRIU tests round is finished. The solution is to convert net_mutex to the rw_semaphore and add fine grain locks to really small number of pernet_operations, what really need them. Then, pernet_operations::init/::exit methods, modifying the net-related data, will require down_read() locking only, while down_write() will be used for changing pernet_list (i.e., when modules are being loaded and unloaded). This gives signify performance increase, after all patch set is applied, like you may see here: %for i in {1..10000}; do unshare -n bash -c exit; done *before* real 1m40,377s user 0m9,672s sys 0m19,928s *after* real 0m17,007s user 0m5,311s sys 0m11,779 (5.8 times faster) This patch starts replacing net_mutex to net_sem. It adds rw_semaphore, describes the variables it protects, and makes to use, where appropriate. net_mutex is still present, and next patches will kick it out step-by-step. Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com> Acked-by: Andrei Vagin <avagin@virtuozzo.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Currently, the mutex is mostly used to protect pernet operations
list. It orders setup_net() and cleanup_net() with parallel
{un,}register_pernet_operations() calls, so ->exit{,batch} methods
of the same pernet operations are executed for a dying net, as
were used to call ->init methods, even after the net namespace
is unlinked from net_namespace_list in cleanup_net().

But there are several problems with scalability. The first one
is that more than one net can't be created or destroyed
at the same moment on the node. For big machines with many cpus
running many containers it's very sensitive.

The second one is that it's need to synchronize_rcu() after net
is removed from net_namespace_list():

Destroy net_ns:
cleanup_net()
  mutex_lock(&net_mutex)
  list_del_rcu(&net->list)
  synchronize_rcu()                                  <--- Sleep there for ages
  list_for_each_entry_reverse(ops, &pernet_list, list)
    ops_exit_list(ops, &net_exit_list)
  list_for_each_entry_reverse(ops, &pernet_list, list)
    ops_free_list(ops, &net_exit_list)
  mutex_unlock(&net_mutex)

This primitive is not fast, especially on the systems with many processors
and/or when preemptible RCU is enabled in config. So, all the time, while
cleanup_net() is waiting for RCU grace period, creation of new net namespaces
is not possible, the tasks, who makes it, are sleeping on the same mutex:

Create net_ns:
copy_net_ns()
  mutex_lock_killable(&net_mutex)                    <--- Sleep there for ages

I observed 20-30 seconds hangs of "unshare -n" on ordinary 8-cpu laptop
with preemptible RCU enabled after CRIU tests round is finished.

The solution is to convert net_mutex to the rw_semaphore and add fine grain
locks to really small number of pernet_operations, what really need them.

Then, pernet_operations::init/::exit methods, modifying the net-related data,
will require down_read() locking only, while down_write() will be used
for changing pernet_list (i.e., when modules are being loaded and unloaded).

This gives signify performance increase, after all patch set is applied,
like you may see here:

%for i in {1..10000}; do unshare -n bash -c exit; done

*before*
real 1m40,377s
user 0m9,672s
sys 0m19,928s

*after*
real 0m17,007s
user 0m5,311s
sys 0m11,779

(5.8 times faster)

This patch starts replacing net_mutex to net_sem. It adds rw_semaphore,
describes the variables it protects, and makes to use, where appropriate.
net_mutex is still present, and next patches will kick it out step-by-step.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Acked-by: Andrei Vagin <avagin@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next 2018-01-31T22:31:10+00:00 Linus Torvalds torvalds@linux-foundation.org 2018-01-31T22:31:10+00:00 b2fe5fa68642860e7de76167c3111623aa0d5de1 Pull networking updates from David Miller: 1) Significantly shrink the core networking routing structures. Result of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf 2) Add netdevsim driver for testing various offloads, from Jakub Kicinski. 3) Support cross-chip FDB operations in DSA, from Vivien Didelot. 4) Add a 2nd listener hash table for TCP, similar to what was done for UDP. From Martin KaFai Lau. 5) Add eBPF based queue selection to tun, from Jason Wang. 6) Lockless qdisc support, from John Fastabend. 7) SCTP stream interleave support, from Xin Long. 8) Smoother TCP receive autotuning, from Eric Dumazet. 9) Lots of erspan tunneling enhancements, from William Tu. 10) Add true function call support to BPF, from Alexei Starovoitov. 11) Add explicit support for GRO HW offloading, from Michael Chan. 12) Support extack generation in more netlink subsystems. From Alexander Aring, Quentin Monnet, and Jakub Kicinski. 13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From Russell King. 14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso. 15) Many improvements and simplifications to the NFP driver bpf JIT, from Jakub Kicinski. 16) Support for ipv6 non-equal cost multipath routing, from Ido Schimmel. 17) Add resource abstration to devlink, from Arkadi Sharshevsky. 18) Packet scheduler classifier shared filter block support, from Jiri Pirko. 19) Avoid locking in act_csum, from Davide Caratti. 20) devinet_ioctl() simplifications from Al viro. 21) More TCP bpf improvements from Lawrence Brakmo. 22) Add support for onlink ipv6 route flag, similar to ipv4, from David Ahern. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits) tls: Add support for encryption using async offload accelerator ip6mr: fix stale iterator net/sched: kconfig: Remove blank help texts openvswitch: meter: Use 64-bit arithmetic instead of 32-bit tcp_nv: fix potential integer overflow in tcpnv_acked r8169: fix RTL8168EP take too long to complete driver initialization. qmi_wwan: Add support for Quectel EP06 rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK ipmr: Fix ptrdiff_t print formatting ibmvnic: Wait for device response when changing MAC qlcnic: fix deadlock bug tcp: release sk_frag.page in tcp_disconnect ipv4: Get the address of interface correctly. net_sched: gen_estimator: fix lockdep splat net: macb: Handle HRESP error net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring ipv6: addrconf: break critical section in addrconf_verify_rtnl() ipv6: change route cache aging logic i40e/i40evf: Update DESC_NEEDED value to reflect larger value bnxt_en: cleanup DIM work on device shutdown ... 
Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...
dev: advertise the new ifindex when the netns iface changes 2018-01-29T17:23:52+00:00 Nicolas Dichtel nicolas.dichtel@6wind.com 2018-01-25T14:01:39+00:00 38e01b30563a5b5ade7b54e5d739d16a2b02fe82 The goal is to let the user follow an interface that moves to another netns. CC: Jiri Benc <jbenc@redhat.com> CC: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Reviewed-by: Jiri Benc <jbenc@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
The goal is to let the user follow an interface that moves to another
netns.

CC: Jiri Benc <jbenc@redhat.com>
CC: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
rtnetlink: Replace implementation of ASSERT_RTNL() macro with WARN_ONCE() 2017-12-26T17:30:02+00:00 Leon Romanovsky leonro@mellanox.com 2017-12-21T09:40:04+00:00 66364bdf3a7e0470e84590d48fc11d902eca7fa9 ASSERT_RTNL() macro is actual open-coded variant of WARN_ONCE() with two exceptions. First, it prints stack for multiple hits and not only once as WARN_ONCE() does. Second, the user can disable prints of WARN_ONCE by setting CONFIG_BUG to N. The multiple prints of dump stack are actually not needed, because calls without rtnl lock are programming errors and user can't do anything about them except to complain to the mailing list after first occurrence of such failure. The user who disabled BUG/WARN prints did it explicitly because by default in upstream kernel and distributions this option is enabled. It means that user doesn't want to see prints about missing locks too. This patch replaces open-coded variant in favor of already existing macro and change error prints to be once only. Reviewed-by: Mark Bloch <markb@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
ASSERT_RTNL() macro is actual open-coded variant of WARN_ONCE() with
two exceptions. First, it prints stack for multiple hits and not only
once as WARN_ONCE() does. Second, the user can disable prints of
WARN_ONCE by setting CONFIG_BUG to N.

The multiple prints of dump stack are actually not needed, because calls
without rtnl lock are programming errors and user can't do anything
about them except to complain to the mailing list after first occurrence
of such failure.

The user who disabled BUG/WARN prints did it explicitly because by default
in upstream kernel and distributions this option is enabled. It means
that user doesn't want to see prints about missing locks too.

This patch replaces open-coded variant in favor of already existing
macro and change error prints to be once only.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>