The current implementation gets a spin_lock, and at any scale with
qib and hfi1 post send, the lock contention grows exponentially
with the number of QPs.

idr_find() is RCU compatibile, so read doesn't need the lock.

Change to use rcu_read_lock() and rcu_read_unlock() in
__idr_get_uobj().

kfree_rcu() is used to insure a grace period between the
idr removal and actual free.

Reviewed-by: Ira Weiny <[email protected]>
Signed-off-by: Mike Marciniszyn <[email protected]>
---
 drivers/infiniband/core/uverbs_cmd.c |   12 +++++++-----
 include/rdma/ib_verbs.h              |    1 +
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/infiniband/core/uverbs_cmd.c 
b/drivers/infiniband/core/uverbs_cmd.c
index be4cb9f..eb7f74f 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -62,9 +62,11 @@ static struct uverbs_lock_class rule_lock_class = { .name = 
"RULE-uobj" };
  * The ib_uobject locking scheme is as follows:
  *
  * - ib_uverbs_idr_lock protects the uverbs idrs themselves, so it
- *   needs to be held during all idr operations.  When an object is
+ *   needs to be held during all idr write operations.  When an object is
  *   looked up, a reference must be taken on the object's kref before
- *   dropping this lock.
+ *   dropping this lock.  For read operations, the rcu_read_lock()
+ *   and rcu_write_lock() but similarly the kref reference is grabbed
+ *   before the rcu_read_unlock().
  *
  * - Each object also has an rwsem.  This rwsem must be held for
  *   reading while an operation that uses the object is performed.
@@ -96,7 +98,7 @@ static void init_uobj(struct ib_uobject *uobj, u64 
user_handle,
 
 static void release_uobj(struct kref *kref)
 {
-       kfree(container_of(kref, struct ib_uobject, ref));
+       kfree_rcu(container_of(kref, struct ib_uobject, ref), rcu);
 }
 
 static void put_uobj(struct ib_uobject *uobj)
@@ -145,7 +147,7 @@ static struct ib_uobject *__idr_get_uobj(struct idr *idr, 
int id,
 {
        struct ib_uobject *uobj;
 
-       spin_lock(&ib_uverbs_idr_lock);
+       rcu_read_lock();
        uobj = idr_find(idr, id);
        if (uobj) {
                if (uobj->context == context)
@@ -153,7 +155,7 @@ static struct ib_uobject *__idr_get_uobj(struct idr *idr, 
int id,
                else
                        uobj = NULL;
        }
-       spin_unlock(&ib_uverbs_idr_lock);
+       rcu_read_unlock();
 
        return uobj;
 }
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 7845fae..f46092f 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1246,6 +1246,7 @@ struct ib_uobject {
        int                     id;             /* index into kernel idr */
        struct kref             ref;
        struct rw_semaphore     mutex;          /* protects .live */
+       struct rcu_head         rcu;            /* kfree_rcu() overhead */
        int                     live;
 };
 

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to