diff options
| author | Sebastian Sanchez <sebastian.sanchez@intel.com> | 2017-02-08 05:26:31 -0800 |
|---|---|---|
| committer | Doug Ledford <dledford@redhat.com> | 2017-02-19 09:18:35 -0500 |
| commit | 338adfdddf6abe89726e1146ad3102ce9663a634 (patch) | |
| tree | e509ec29d80f6cd81097ffea338a8a7222ec7389 /include/rdma | |
| parent | f3e862cb6894389a35d0beb10f73d62eb3317beb (diff) | |
| download | linux-338adfdddf6abe89726e1146ad3102ce9663a634.tar.bz2 | |
IB/rdmavt: Use per-CPU reference count for MRs
Having per-CPU reference count for each MR prevents
cache-line bouncing across the system. Thus, it
prevents bottlenecks. Use per-CPU reference counts
per MR.
The per-CPU reference count for FMRs is used in
atomic mode to allow accurate testing of the busy
state. Other MR types run in per-CPU mode MR until
they're freed.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Diffstat (limited to 'include/rdma')
| -rw-r--r-- | include/rdma/rdmavt_mr.h | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/include/rdma/rdmavt_mr.h b/include/rdma/rdmavt_mr.h index de59de28b6a2..05698d8d9c6f 100644 --- a/include/rdma/rdmavt_mr.h +++ b/include/rdma/rdmavt_mr.h @@ -52,6 +52,7 @@ * For Memory Regions. This stuff should probably be moved into rdmavt/mr.h once * drivers no longer need access to the MR directly. */ +#include <linux/percpu-refcount.h> /* * A segment is a linear region of low physical memory. @@ -79,11 +80,11 @@ struct rvt_mregion { int access_flags; u32 max_segs; /* number of rvt_segs in all the arrays */ u32 mapsz; /* size of the map array */ + atomic_t lkey_invalid; /* true if current lkey is invalid */ u8 page_shift; /* 0 - non unform/non powerof2 sizes */ u8 lkey_published; /* in global table */ - atomic_t lkey_invalid; /* true if current lkey is invalid */ + struct percpu_ref refcount; struct completion comp; /* complete when refcount goes to zero */ - atomic_t refcount; struct rvt_segarray *map[0]; /* the segments */ }; @@ -123,13 +124,12 @@ struct rvt_sge_state { static inline void rvt_put_mr(struct rvt_mregion *mr) { - if (unlikely(atomic_dec_and_test(&mr->refcount))) - complete(&mr->comp); + percpu_ref_put(&mr->refcount); } static inline void rvt_get_mr(struct rvt_mregion *mr) { - atomic_inc(&mr->refcount); + percpu_ref_get(&mr->refcount); } static inline void rvt_put_ss(struct rvt_sge_state *ss) |