diff options
| author | Jay Freyensee <james_p_freyensee@linux.intel.com> | 2016-08-17 15:00:26 -0700 |
|---|---|---|
| committer | Sagi Grimberg <sagi@grimberg.me> | 2016-08-18 09:58:05 +0300 |
| commit | f994d9dc28bc27353acde2caaf718222d92a3e24 (patch) | |
| tree | f54079f734752cc79dc3269a2dd3de2370200d9f /drivers/nvme | |
| parent | b825b44c4ef4dabfdaf4e82db2263d377ac45d67 (diff) | |
fabrics: define admin sqsize min default, per spec
Upon admin queue connect(), the rdma qp was being
set based on NVMF_AQ_DEPTH. However, the fabrics layer was
using the sqsize field value set for I/O queues for the admin
queue, which threw the nvme layer and rdma layer off-whack:
root@fedora23-fabrics-host1 nvmf]# dmesg
[ 3507.798642] nvme_fabrics: nvmf_connect_admin_queue():admin sqsize
being sent is: 128
[ 3507.798858] nvme nvme0: creating 16 I/O queues.
[ 3507.896407] nvme nvme0: new ctrl: NQN "nullside-nqn", addr
192.168.1.3:4420
Thus, to have a different admin queue value, we use
NVMF_AQ_DEPTH for connect() and RDMA private data
as the minimum depth specified in the NVMe-over-Fabrics 1.0 spec
(and in that RDMA private data we treat hrqsize as 1's-based
value, per current understanding of the fabrics spec).
Reported-by: Daniel Verkamp <daniel.verkamp@intel.com>
Signed-off-by: Jay Freyensee <james_p_freyensee@linux.intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Diffstat (limited to 'drivers/nvme')
| -rw-r--r-- | drivers/nvme/host/fabrics.c | 9 | ||||
| -rw-r--r-- | drivers/nvme/host/rdma.c | 13 |
2 files changed, 19 insertions, 3 deletions
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index dc996761042f..020302c6ea57 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -363,7 +363,14 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) cmd.connect.opcode = nvme_fabrics_command; cmd.connect.fctype = nvme_fabrics_type_connect; cmd.connect.qid = 0; - cmd.connect.sqsize = cpu_to_le16(ctrl->sqsize); + + /* + * fabrics spec sets a minimum of depth 32 for admin queue, + * so set the queue with this depth always until + * justification otherwise. + */ + cmd.connect.sqsize = cpu_to_le16(NVMF_AQ_DEPTH - 1); + /* * Set keep-alive timeout in seconds granularity (ms * 1000) * and add a grace period for controller kato enforcement diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 9c69393f6d1f..d44809e6b03f 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1278,8 +1278,17 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue) priv.recfmt = cpu_to_le16(NVME_RDMA_CM_FMT_1_0); priv.qid = cpu_to_le16(nvme_rdma_queue_idx(queue)); - priv.hrqsize = cpu_to_le16(queue->queue_size); - priv.hsqsize = cpu_to_le16(queue->queue_size); + /* + * set the admin queue depth to the minimum size + * specified by the Fabrics standard. + */ + if (priv.qid == 0) { + priv.hrqsize = cpu_to_le16(NVMF_AQ_DEPTH); + priv.hsqsize = cpu_to_le16(NVMF_AQ_DEPTH - 1); + } else { + priv.hrqsize = cpu_to_le16(queue->queue_size); + priv.hsqsize = cpu_to_le16(queue->queue_size); + } ret = rdma_connect(queue->cm_id, ¶m); if (ret) { |