Skip to content

L
linux
Switch branch/tag
  1. 14 Dec, 2023 3 commits
    • Jakub Kicinski's avatar
      Merge branch 'net-sched-optimizations-around-action-binding-and-init' · a25ebbf3
      Jakub Kicinski authored 
      Pedro Tammela says:

====================
net/sched: optimizations around action binding and init

Scaling optimizations for action binding in rtnl-less filters.
We saw a noticeable lock contention around idrinfo->lock when
testing in a 56 core system, which disappeared after the patches.
====================

Link: https://lore.kernel.org/r/20231211181807.96028-1-pctammela@mojatatu.comSigned-off-by: default avatarJakub Kicinski <kuba@kernel.org>
      a25ebbf3
    • Pedro Tammela's avatar
      net/sched: act_api: skip idr replace on bound actions · 1dd7f18f
      Pedro Tammela authored 
      tcf_idr_insert_many will replace the allocated -EBUSY pointer in
tcf_idr_check_alloc with the real action pointer, exposing it
to all operations. This operation is only needed when the action pointer
is created (ACT_P_CREATED). For actions which are bound to (returned 0),
the pointer already resides in the idr making such operation a nop.

Even though it's a nop, it's still not a cheap operation as internally
the idr code walks the idr and then does a replace on the appropriate slot.
So if the action was bound, better skip the idr replace entirely.
Signed-off-by: default avatarPedro Tammela <pctammela@mojatatu.com>
Acked-by: default avatarJamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: default avatarVlad Buslov <vladbu@nvidia.com>
Link: https://lore.kernel.org/r/20231211181807.96028-3-pctammela@mojatatu.comSigned-off-by: default avatarJakub Kicinski <kuba@kernel.org>
      1dd7f18f
    • Pedro Tammela's avatar
      net/sched: act_api: rely on rcu in tcf_idr_check_alloc · 4b55e867
      Pedro Tammela authored 
      Instead of relying only on the idrinfo->lock mutex for
bind/alloc logic, rely on a combination of rcu + mutex + atomics
to better scale the case where multiple rtnl-less filters are
binding to the same action object.

Action binding happens when an action index is specified explicitly and
an action exists which such index exists. Example:
  tc actions add action drop index 1
  tc filter add ... matchall action drop index 1
  tc filter add ... matchall action drop index 1
  tc filter add ... matchall action drop index 1
  tc filter ls ...
     filter protocol all pref 49150 matchall chain 0 filter protocol all pref 49150 matchall chain 0 handle 0x1
     not_in_hw
           action order 1: gact action drop
            random type none pass val 0
            index 1 ref 4 bind 3

   filter protocol all pref 49151 matchall chain 0 filter protocol all pref 49151 matchall chain 0 handle 0x1
     not_in_hw
           action order 1: gact action drop
            random type none pass val 0
            index 1 ref 4 bind 3

   filter protocol all pref 49152 matchall chain 0 filter protocol all pref 49152 matchall chain 0 handle 0x1
     not_in_hw
           action order 1: gact action drop
            random type none pass val 0
            index 1 ref 4 bind 3

When no index is specified, as before, grab the mutex and allocate
in the idr the next available id. In this version, as opposed to before,
it's simplified to store the -EBUSY pointer instead of the previous
alloc + replace combination.

When an index is specified, rely on rcu to find if there's an object in
such index. If there's none, fallback to the above, serializing on the
mutex and reserving the specified id. If there's one, it can be an -EBUSY
pointer, in which case we just try again until it's an action, or an action.
Given the rcu guarantees, the action found could be dead and therefore
we need to bump the refcount if it's not 0, handling the case it's
in fact 0.

As bind and the action refcount are already atomics, these increments can
happen without the mutex protection while many tcf_idr_check_alloc race
to bind to the same action instance.

In case binding encounters a parallel delete or add, it will return
-EAGAIN in order to try again. Both filter and action apis already
have the retry machinery in-place. In case it's an unlocked filter it
retries under the rtnl lock.
Signed-off-by: default avatarPedro Tammela <pctammela@mojatatu.com>
Acked-by: default avatarJamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: default avatarVlad Buslov <vladbu@nvidia.com>
Link: https://lore.kernel.org/r/20231211181807.96028-2-pctammela@mojatatu.comSigned-off-by: default avatarJakub Kicinski <kuba@kernel.org>
      4b55e867
  3. 13 Dec, 2023 37 commits
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7