summaryrefslogtreecommitdiff
path: root/include/rdma/rdma_vt.h
diff options
context:
space:
mode:
authorSebastian Sanchez <sebastian.sanchez@intel.com>2018-05-02 16:43:55 +0300
committerDoug Ledford <dledford@redhat.com>2018-05-09 22:53:30 +0300
commit5d18ee67d4c1735f5c1f757e89228ec68e4f4ef3 (patch)
treebee1ad21ecea953b9048b94fd05b2c86a4128c27 /include/rdma/rdma_vt.h
parentcf38ea100edfcc0ec0a5797966d69ec4e10fe4f1 (diff)
downloadlinux-5d18ee67d4c1735f5c1f757e89228ec68e4f4ef3.tar.xz
IB/{hfi1, rdmavt, qib}: Implement CQ completion vector support
Currently the driver doesn't support completion vectors. These are used to indicate which sets of CQs should be grouped together into the same vector. A vector is a CQ processing thread that runs on a specific CPU. If an application has several CQs bound to different completion vectors, and each completion vector runs on different CPUs, then the completion queue workload is balanced. This helps scale as more nodes are used. Implement CQ completion vector support using a global workqueue where a CQ entry is queued to the CPU corresponding to the CQ's completion vector. Since the workqueue is global, it's guaranteed to always be there when queueing CQ entries; Therefore, the RCU locking for cq->rdi->worker in the hot path is superfluous. Each completion vector is assigned to a different CPU. The number of completion vectors available is computed by taking the number of online, physical CPUs from the local NUMA node and subtracting the CPUs used for kernel receive queues and the general interrupt. Special use cases: * If there are no CPUs left for completion vectors, the same CPU for the general interrupt is used; Therefore, there would only be one completion vector available. * For multi-HFI systems, the number of completion vectors available for each device is the total number of completion vectors in the local NUMA node divided by the number of devices in the same NUMA node. If there's a division remainder, the first device to get initialized gets an extra completion vector. Upon a CQ creation, an invalid completion vector could be specified. Handle it as follows: * If the completion vector is less than 0, set it to 0. * Set the completion vector to the result of the passed completion vector moded with the number of device completion vectors available. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
Diffstat (limited to 'include/rdma/rdma_vt.h')
-rw-r--r--include/rdma/rdma_vt.h7
1 files changed, 4 insertions, 3 deletions
diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h
index eec495e68823..e79229a0cf01 100644
--- a/include/rdma/rdma_vt.h
+++ b/include/rdma/rdma_vt.h
@@ -2,7 +2,7 @@
#define DEF_RDMA_VT_H
/*
- * Copyright(c) 2016 Intel Corporation.
+ * Copyright(c) 2016 - 2018 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
@@ -167,7 +167,6 @@ struct rvt_driver_params {
int qpn_res_end;
int nports;
int npkeys;
- char cq_name[RVT_CQN_MAX];
int node;
int psn_mask;
int psn_shift;
@@ -347,6 +346,9 @@ struct rvt_driver_provided {
/* Notify driver to restart rc */
void (*notify_restart_rc)(struct rvt_qp *qp, u32 psn, int wait);
+
+ /* Get and return CPU to pin CQ processing thread */
+ int (*comp_vect_cpu_lookup)(struct rvt_dev_info *rdi, int comp_vect);
};
struct rvt_dev_info {
@@ -402,7 +404,6 @@ struct rvt_dev_info {
spinlock_t pending_lock; /* protect pending mmap list */
/* CQ */
- struct kthread_worker __rcu *worker; /* per device cq worker */
u32 n_cqs_allocated; /* number of CQs allocated for device */
spinlock_t n_cqs_lock; /* protect count of in use cqs */