mirror of
https://github.com/torvalds/linux
synced 2024-09-20 02:57:25 +00:00
c66f67414c
When creating many MAD agents in a short period of time, receive packet processing can be delayed long enough to cause timeouts while new agents are being added to the atomic notifier chain with IRQs disabled. Notifier chain registration and unregstration is an O(n) operation. With large numbers of MAD agents being created and destroyed simultaneously the CPUs spend too much time with interrupts disabled. Instead of each MAD agent registering for it's own LSM notification, maintain a list of agents internally and register once, this registration already existed for handling the PKeys. This list is write mostly, so a normal spin lock is used vs a read/write lock. All MAD agents must be checked, so a single list is used instead of breaking them down per device. Notifier calls are done under rcu_read_lock, so there isn't a risk of similar packet timeouts while checking the MAD agents security settings when notified. Signed-off-by: Daniel Jurgens <danielj@mellanox.com> Reviewed-by: Parav Pandit <parav@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Acked-by: Paul Moore <paul@paul-moore.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com> |
||
|---|---|---|
| .. | ||
| ib.h | ||
| ib_addr.h | ||
| ib_cache.h | ||
| ib_cm.h | ||
| ib_fmr_pool.h | ||
| ib_hdrs.h | ||
| ib_mad.h | ||
| ib_marshall.h | ||
| ib_pack.h | ||
| ib_pma.h | ||
| ib_sa.h | ||
| ib_smi.h | ||
| ib_umem.h | ||
| ib_umem_odp.h | ||
| ib_verbs.h | ||
| iw_cm.h | ||
| iw_portmap.h | ||
| mr_pool.h | ||
| opa_addr.h | ||
| opa_port_info.h | ||
| opa_smi.h | ||
| opa_vnic.h | ||
| rdma_cm.h | ||
| rdma_cm_ib.h | ||
| rdma_netlink.h | ||
| rdma_vt.h | ||
| rdmavt_cq.h | ||
| rdmavt_mr.h | ||
| rdmavt_qp.h | ||
| restrack.h | ||
| rw.h | ||
| uverbs_ioctl.h | ||
| uverbs_named_ioctl.h | ||
| uverbs_std_types.h | ||
| uverbs_types.h | ||