| Message ID | 20210527235902.2185-8-smalin@marvell.com (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
| Series | NVMeTCP Offload ULP and QEDN Device Driver | expand |
| Context | Check | Description |
|---|---|---|
| netdev/cover_letter | success | Link |
| netdev/fixes_present | success | Link |
| netdev/patch_count | fail | Series longer than 15 patches |
| netdev/tree_selection | success | Guessed tree name to be net-next |
| netdev/subject_prefix | success | Link |
| netdev/cc_maintainers | success | CCed 7 of 7 maintainers |
| netdev/source_inline | fail | Was 0 now: 2 |
| netdev/verify_signedoff | success | Link |
| netdev/module_param | success | Was 0 now: 0 |
| netdev/build_32bit | success | Errors and warnings before: 6 this patch: 6 |
| netdev/kdoc | success | Errors and warnings before: 0 this patch: 0 |
| netdev/verify_fixes | success | Link |
| netdev/checkpatch | warning | WARNING: line length of 81 exceeds 80 columns WARNING: line length of 83 exceeds 80 columns WARNING: line length of 92 exceeds 80 columns |
| netdev/build_allmodconfig_warn | success | Errors and warnings before: 6 this patch: 6 |
| netdev/header_inline | success | Link |
On 5/28/21 1:58 AM, Shai Malin wrote: > From: Dean Balandin <dbalandin@marvell.com> > > In this patch we implement queue level functionality. > The implementation is similar to the nvme-tcp module, the main > difference being that we call the vendor specific create_queue op which > creates the TCP connection, and NVMeTPC connection including > icreq+icresp negotiation. > Once create_queue returns successfully, we can move on to the fabrics > connect. > > Acked-by: Igor Russkikh <irusskikh@marvell.com> > Signed-off-by: Dean Balandin <dbalandin@marvell.com> > Signed-off-by: Prabhakar Kushwaha <pkushwaha@marvell.com> > Signed-off-by: Omkar Kulkarni <okulkarni@marvell.com> > Signed-off-by: Michal Kalderon <mkalderon@marvell.com> > Signed-off-by: Ariel Elior <aelior@marvell.com> > Signed-off-by: Shai Malin <smalin@marvell.com> > Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com> > --- > drivers/nvme/host/tcp-offload.c | 418 +++++++++++++++++++++++++++++--- > drivers/nvme/host/tcp-offload.h | 4 + > 2 files changed, 394 insertions(+), 28 deletions(-) > > diff --git a/drivers/nvme/host/tcp-offload.c b/drivers/nvme/host/tcp-offload.c > index 52d310f7636a..eff10e31f17f 100644 > --- a/drivers/nvme/host/tcp-offload.c > +++ b/drivers/nvme/host/tcp-offload.c > @@ -22,6 +22,11 @@ static inline struct nvme_tcp_ofld_ctrl *to_tcp_ofld_ctrl(struct nvme_ctrl *nctr > return container_of(nctrl, struct nvme_tcp_ofld_ctrl, nctrl); > } > > +static inline int nvme_tcp_ofld_qid(struct nvme_tcp_ofld_queue *queue) > +{ > + return queue - queue->ctrl->queues; > +} > + > /** > * nvme_tcp_ofld_register_dev() - NVMeTCP Offload Library registration > * function. > @@ -182,19 +187,125 @@ nvme_tcp_ofld_alloc_tagset(struct nvme_ctrl *nctrl, bool admin) > return set; > } > > +static void __nvme_tcp_ofld_stop_queue(struct nvme_tcp_ofld_queue *queue) > +{ > + queue->dev->ops->drain_queue(queue); > +} > + > +static void nvme_tcp_ofld_stop_queue(struct nvme_ctrl *nctrl, int qid) > +{ > + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); > + struct nvme_tcp_ofld_queue *queue = &ctrl->queues[qid]; > + > + mutex_lock(&queue->queue_lock); > + if (test_and_clear_bit(NVME_TCP_OFLD_Q_LIVE, &queue->flags)) > + __nvme_tcp_ofld_stop_queue(queue); > + mutex_unlock(&queue->queue_lock); > +} > + > +static void nvme_tcp_ofld_stop_io_queues(struct nvme_ctrl *ctrl) > +{ > + int i; > + > + for (i = 1; i < ctrl->queue_count; i++) > + nvme_tcp_ofld_stop_queue(ctrl, i); > +} > + > +static void __nvme_tcp_ofld_free_queue(struct nvme_tcp_ofld_queue *queue) > +{ > + queue->dev->ops->destroy_queue(queue); > +} > + > +static void nvme_tcp_ofld_free_queue(struct nvme_ctrl *nctrl, int qid) > +{ > + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); > + struct nvme_tcp_ofld_queue *queue = &ctrl->queues[qid]; > + > + test_and_clear_bit(NVME_TCP_OFLD_Q_ALLOCATED, &queue->flags); You really want to make this an 'if' clause to avoid double free > + > + __nvme_tcp_ofld_free_queue(queue); > + > + mutex_destroy(&queue->queue_lock); > +} > + > +static void > +nvme_tcp_ofld_free_io_queues(struct nvme_ctrl *nctrl) > +{ > + int i; > + > + for (i = 1; i < nctrl->queue_count; i++) > + nvme_tcp_ofld_free_queue(nctrl, i); > +} > + > +static void nvme_tcp_ofld_destroy_io_queues(struct nvme_ctrl *nctrl, bool remove) > +{ > + nvme_tcp_ofld_stop_io_queues(nctrl); > + if (remove) { > + blk_cleanup_queue(nctrl->connect_q); > + blk_mq_free_tag_set(nctrl->tagset); > + } > + nvme_tcp_ofld_free_io_queues(nctrl); > +} > + > +static void nvme_tcp_ofld_destroy_admin_queue(struct nvme_ctrl *nctrl, bool remove) > +{ > + nvme_tcp_ofld_stop_queue(nctrl, 0); > + if (remove) { > + blk_cleanup_queue(nctrl->admin_q); > + blk_cleanup_queue(nctrl->fabrics_q); > + blk_mq_free_tag_set(nctrl->admin_tagset); > + } > + nvme_tcp_ofld_free_queue(nctrl, 0); > +} > + > +static int nvme_tcp_ofld_start_queue(struct nvme_ctrl *nctrl, int qid) > +{ > + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); > + struct nvme_tcp_ofld_queue *queue = &ctrl->queues[qid]; > + int rc; > + > + queue = &ctrl->queues[qid]; > + if (qid) { > + queue->cmnd_capsule_len = nctrl->ioccsz * 16; > + rc = nvmf_connect_io_queue(nctrl, qid, false); > + } else { > + queue->cmnd_capsule_len = sizeof(struct nvme_command) + NVME_TCP_ADMIN_CCSZ; > + rc = nvmf_connect_admin_queue(nctrl); > + } > + > + if (!rc) { > + set_bit(NVME_TCP_OFLD_Q_LIVE, &queue->flags); > + } else { > + if (test_bit(NVME_TCP_OFLD_Q_ALLOCATED, &queue->flags)) > + __nvme_tcp_ofld_stop_queue(queue); Why do you need to call 'stop_queue' here? A failure indicates that the queue wasn't started, no? > + dev_err(nctrl->device, > + "failed to connect queue: %d ret=%d\n", qid, rc); > + } > + > + return rc; > +} > + > static int nvme_tcp_ofld_configure_admin_queue(struct nvme_ctrl *nctrl, > bool new) > { > + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); > + struct nvme_tcp_ofld_queue *queue = &ctrl->queues[0]; > int rc; > > - /* Placeholder - alloc_admin_queue */ > + mutex_init(&queue->queue_lock); > + > + rc = ctrl->dev->ops->create_queue(queue, 0, NVME_AQ_DEPTH); > + if (rc) > + return rc; > + > + set_bit(NVME_TCP_OFLD_Q_ALLOCATED, &queue->flags); > if (new) { > nctrl->admin_tagset = > nvme_tcp_ofld_alloc_tagset(nctrl, true); > if (IS_ERR(nctrl->admin_tagset)) { > rc = PTR_ERR(nctrl->admin_tagset); > nctrl->admin_tagset = NULL; > - goto out_destroy_queue; > + goto out_free_queue; > } > > nctrl->fabrics_q = blk_mq_init_queue(nctrl->admin_tagset); > @@ -212,7 +323,9 @@ static int nvme_tcp_ofld_configure_admin_queue(struct nvme_ctrl *nctrl, > } > } > > - /* Placeholder - nvme_tcp_ofld_start_queue */ > + rc = nvme_tcp_ofld_start_queue(nctrl, 0); > + if (rc) > + goto out_cleanup_queue; > > rc = nvme_enable_ctrl(nctrl); > if (rc) > @@ -229,19 +342,143 @@ static int nvme_tcp_ofld_configure_admin_queue(struct nvme_ctrl *nctrl, > out_quiesce_queue: > blk_mq_quiesce_queue(nctrl->admin_q); > blk_sync_queue(nctrl->admin_q); > - > out_stop_queue: > - /* Placeholder - stop offload queue */ > + nvme_tcp_ofld_stop_queue(nctrl, 0); > nvme_cancel_admin_tagset(nctrl); > - > +out_cleanup_queue: > + if (new) > + blk_cleanup_queue(nctrl->admin_q); > out_cleanup_fabrics_q: > if (new) > blk_cleanup_queue(nctrl->fabrics_q); > out_free_tagset: > if (new) > blk_mq_free_tag_set(nctrl->admin_tagset); > -out_destroy_queue: > - /* Placeholder - free admin queue */ > +out_free_queue: > + nvme_tcp_ofld_free_queue(nctrl, 0); > + > + return rc; > +} > + > +static unsigned int nvme_tcp_ofld_nr_io_queues(struct nvme_ctrl *nctrl) > +{ > + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); > + struct nvme_tcp_ofld_dev *dev = ctrl->dev; > + u32 hw_vectors = dev->num_hw_vectors; > + u32 nr_write_queues, nr_poll_queues; > + u32 nr_io_queues, nr_total_queues; > + > + nr_io_queues = min3(nctrl->opts->nr_io_queues, num_online_cpus(), > + hw_vectors); > + nr_write_queues = min3(nctrl->opts->nr_write_queues, num_online_cpus(), > + hw_vectors); > + nr_poll_queues = min3(nctrl->opts->nr_poll_queues, num_online_cpus(), > + hw_vectors); > + > + nr_total_queues = nr_io_queues + nr_write_queues + nr_poll_queues; > + > + return nr_total_queues; > +} > + > +static void > +nvme_tcp_ofld_set_io_queues(struct nvme_ctrl *nctrl, unsigned int nr_io_queues) > +{ > + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); > + struct nvmf_ctrl_options *opts = nctrl->opts; > + > + if (opts->nr_write_queues && opts->nr_io_queues < nr_io_queues) { > + /* > + * separate read/write queues > + * hand out dedicated default queues only after we have > + * sufficient read queues. > + */ > + ctrl->io_queues[HCTX_TYPE_READ] = opts->nr_io_queues; > + nr_io_queues -= ctrl->io_queues[HCTX_TYPE_READ]; > + ctrl->io_queues[HCTX_TYPE_DEFAULT] = > + min(opts->nr_write_queues, nr_io_queues); > + nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT]; > + } else { > + /* > + * shared read/write queues > + * either no write queues were requested, or we don't have > + * sufficient queue count to have dedicated default queues. > + */ > + ctrl->io_queues[HCTX_TYPE_DEFAULT] = > + min(opts->nr_io_queues, nr_io_queues); > + nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT]; > + } > + > + if (opts->nr_poll_queues && nr_io_queues) { > + /* map dedicated poll queues only if we have queues left */ > + ctrl->io_queues[HCTX_TYPE_POLL] = > + min(opts->nr_poll_queues, nr_io_queues); > + } > +} > + > +static int nvme_tcp_ofld_create_io_queues(struct nvme_ctrl *nctrl) > +{ > + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); > + int i, rc; > + > + for (i = 1; i < nctrl->queue_count; i++) { > + mutex_init(&ctrl->queues[i].queue_lock); > + > + rc = ctrl->dev->ops->create_queue(&ctrl->queues[i], > + i, nctrl->sqsize + 1); > + if (rc) > + goto out_free_queues; > + > + set_bit(NVME_TCP_OFLD_Q_ALLOCATED, &ctrl->queues[i].flags); > + } > + > + return 0; > + > +out_free_queues: > + for (i--; i >= 1; i--) > + nvme_tcp_ofld_free_queue(nctrl, i); > + > + return rc; > +} > + > +static int nvme_tcp_ofld_alloc_io_queues(struct nvme_ctrl *nctrl) > +{ > + unsigned int nr_io_queues; > + int rc; > + > + nr_io_queues = nvme_tcp_ofld_nr_io_queues(nctrl); > + rc = nvme_set_queue_count(nctrl, &nr_io_queues); > + if (rc) > + return rc; > + > + nctrl->queue_count = nr_io_queues + 1; > + if (nctrl->queue_count < 2) { > + dev_err(nctrl->device, > + "unable to set any I/O queues\n"); > + > + return -ENOMEM; > + } > + > + dev_info(nctrl->device, "creating %d I/O queues.\n", nr_io_queues); > + nvme_tcp_ofld_set_io_queues(nctrl, nr_io_queues); > + > + return nvme_tcp_ofld_create_io_queues(nctrl); > +} > + > +static int nvme_tcp_ofld_start_io_queues(struct nvme_ctrl *nctrl) > +{ > + int i, rc = 0; > + > + for (i = 1; i < nctrl->queue_count; i++) { > + rc = nvme_tcp_ofld_start_queue(nctrl, i); > + if (rc) > + goto out_stop_queues; > + } > + > + return 0; > + > +out_stop_queues: > + for (i--; i >= 1; i--) > + nvme_tcp_ofld_stop_queue(nctrl, i); > > return rc; > } > @@ -249,9 +486,10 @@ static int nvme_tcp_ofld_configure_admin_queue(struct nvme_ctrl *nctrl, > static int > nvme_tcp_ofld_configure_io_queues(struct nvme_ctrl *nctrl, bool new) > { > - int rc; > + int rc = nvme_tcp_ofld_alloc_io_queues(nctrl); > > - /* Placeholder - alloc_io_queues */ > + if (rc) > + return rc; > > if (new) { > nctrl->tagset = nvme_tcp_ofld_alloc_tagset(nctrl, false); > @@ -269,7 +507,9 @@ nvme_tcp_ofld_configure_io_queues(struct nvme_ctrl *nctrl, bool new) > } > } > > - /* Placeholder - start_io_queues */ > + rc = nvme_tcp_ofld_start_io_queues(nctrl); > + if (rc) > + goto out_cleanup_connect_q; > > if (!new) { > nvme_start_queues(nctrl); > @@ -291,16 +531,16 @@ nvme_tcp_ofld_configure_io_queues(struct nvme_ctrl *nctrl, bool new) > out_wait_freeze_timed_out: > nvme_stop_queues(nctrl); > nvme_sync_io_queues(nctrl); > - > - /* Placeholder - Stop IO queues */ > - > + nvme_tcp_ofld_stop_io_queues(nctrl); > +out_cleanup_connect_q: > + nvme_cancel_tagset(nctrl); > if (new) > blk_cleanup_queue(nctrl->connect_q); > out_free_tag_set: > if (new) > blk_mq_free_tag_set(nctrl->tagset); > out_free_io_queues: > - /* Placeholder - free_io_queues */ > + nvme_tcp_ofld_free_io_queues(nctrl); > > return rc; > } > @@ -327,6 +567,17 @@ static void nvme_tcp_ofld_reconnect_or_remove(struct nvme_ctrl *nctrl) > } > } > > +static int > +nvme_tcp_ofld_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data, > + unsigned int hctx_idx) > +{ > + struct nvme_tcp_ofld_ctrl *ctrl = data; > + > + hctx->driver_data = &ctrl->queues[0]; > + > + return 0; > +} > + > static int nvme_tcp_ofld_setup_ctrl(struct nvme_ctrl *nctrl, bool new) > { > struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); > @@ -388,9 +639,19 @@ static int nvme_tcp_ofld_setup_ctrl(struct nvme_ctrl *nctrl, bool new) > return 0; > > destroy_io: > - /* Placeholder - stop and destroy io queues*/ > + if (nctrl->queue_count > 1) { > + nvme_stop_queues(nctrl); > + nvme_sync_io_queues(nctrl); > + nvme_tcp_ofld_stop_io_queues(nctrl); > + nvme_cancel_tagset(nctrl); > + nvme_tcp_ofld_destroy_io_queues(nctrl, new); > + } > destroy_admin: > - /* Placeholder - stop and destroy admin queue*/ > + blk_mq_quiesce_queue(nctrl->admin_q); > + blk_sync_queue(nctrl->admin_q); > + nvme_tcp_ofld_stop_queue(nctrl, 0); > + nvme_cancel_admin_tagset(nctrl); > + nvme_tcp_ofld_destroy_admin_queue(nctrl, new); > out_release_ctrl: > ctrl->dev->ops->release_ctrl(ctrl); > > @@ -439,15 +700,37 @@ static void nvme_tcp_ofld_free_ctrl(struct nvme_ctrl *nctrl) > } > > static void > -nvme_tcp_ofld_teardown_admin_queue(struct nvme_ctrl *ctrl, bool remove) > +nvme_tcp_ofld_teardown_admin_queue(struct nvme_ctrl *nctrl, bool remove) > { > - /* Placeholder - teardown_admin_queue */ > + blk_mq_quiesce_queue(nctrl->admin_q); > + blk_sync_queue(nctrl->admin_q); > + > + nvme_tcp_ofld_stop_queue(nctrl, 0); > + nvme_cancel_admin_tagset(nctrl); > + > + if (remove) > + blk_mq_unquiesce_queue(nctrl->admin_q); > + > + nvme_tcp_ofld_destroy_admin_queue(nctrl, remove); > } > > static void > nvme_tcp_ofld_teardown_io_queues(struct nvme_ctrl *nctrl, bool remove) > { > - /* Placeholder - teardown_io_queues */ > + if (nctrl->queue_count <= 1) > + return; > + > + blk_mq_quiesce_queue(nctrl->admin_q); > + nvme_start_freeze(nctrl); > + nvme_stop_queues(nctrl); > + nvme_sync_io_queues(nctrl); > + nvme_tcp_ofld_stop_io_queues(nctrl); > + nvme_cancel_tagset(nctrl); > + > + if (remove) > + nvme_start_queues(nctrl); That looks odd. Surely all requests need to be flushed even for the not-remove case? > + > + nvme_tcp_ofld_destroy_io_queues(nctrl, remove); > } > > static void nvme_tcp_ofld_reconnect_ctrl_work(struct work_struct *work) > @@ -562,6 +845,12 @@ nvme_tcp_ofld_init_request(struct blk_mq_tag_set *set, > return 0; > } > > +inline size_t nvme_tcp_ofld_inline_data_size(struct nvme_tcp_ofld_queue *queue) > +{ > + return queue->cmnd_capsule_len - sizeof(struct nvme_command); > +} > +EXPORT_SYMBOL_GPL(nvme_tcp_ofld_inline_data_size); > + > static blk_status_t > nvme_tcp_ofld_queue_rq(struct blk_mq_hw_ctx *hctx, > const struct blk_mq_queue_data *bd) > @@ -573,22 +862,95 @@ nvme_tcp_ofld_queue_rq(struct blk_mq_hw_ctx *hctx, > return BLK_STS_OK; > } > > +static void > +nvme_tcp_ofld_exit_request(struct blk_mq_tag_set *set, > + struct request *rq, unsigned int hctx_idx) > +{ > + /* > + * Nothing is allocated in nvme_tcp_ofld_init_request, > + * hence empty. > + */ > +} > + > +static int > +nvme_tcp_ofld_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, > + unsigned int hctx_idx) > +{ > + struct nvme_tcp_ofld_ctrl *ctrl = data; > + > + hctx->driver_data = &ctrl->queues[hctx_idx + 1]; > + > + return 0; > +} > + > +static int nvme_tcp_ofld_map_queues(struct blk_mq_tag_set *set) > +{ > + struct nvme_tcp_ofld_ctrl *ctrl = set->driver_data; > + struct nvmf_ctrl_options *opts = ctrl->nctrl.opts; > + > + if (opts->nr_write_queues && ctrl->io_queues[HCTX_TYPE_READ]) { > + /* separate read/write queues */ > + set->map[HCTX_TYPE_DEFAULT].nr_queues = > + ctrl->io_queues[HCTX_TYPE_DEFAULT]; > + set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; > + set->map[HCTX_TYPE_READ].nr_queues = > + ctrl->io_queues[HCTX_TYPE_READ]; > + set->map[HCTX_TYPE_READ].queue_offset = > + ctrl->io_queues[HCTX_TYPE_DEFAULT]; > + } else { > + /* shared read/write queues */ > + set->map[HCTX_TYPE_DEFAULT].nr_queues = > + ctrl->io_queues[HCTX_TYPE_DEFAULT]; > + set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; > + set->map[HCTX_TYPE_READ].nr_queues = > + ctrl->io_queues[HCTX_TYPE_DEFAULT]; > + set->map[HCTX_TYPE_READ].queue_offset = 0; > + } > + blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); > + blk_mq_map_queues(&set->map[HCTX_TYPE_READ]); > + > + if (opts->nr_poll_queues && ctrl->io_queues[HCTX_TYPE_POLL]) { > + /* map dedicated poll queues only if we have queues left */ > + set->map[HCTX_TYPE_POLL].nr_queues = > + ctrl->io_queues[HCTX_TYPE_POLL]; > + set->map[HCTX_TYPE_POLL].queue_offset = > + ctrl->io_queues[HCTX_TYPE_DEFAULT] + > + ctrl->io_queues[HCTX_TYPE_READ]; > + blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]); > + } > + > + dev_info(ctrl->nctrl.device, > + "mapped %d/%d/%d default/read/poll queues.\n", > + ctrl->io_queues[HCTX_TYPE_DEFAULT], > + ctrl->io_queues[HCTX_TYPE_READ], > + ctrl->io_queues[HCTX_TYPE_POLL]); > + > + return 0; > +} > + > +static int nvme_tcp_ofld_poll(struct blk_mq_hw_ctx *hctx) > +{ > + /* Placeholder - Implement polling mechanism */ > + > + return 0; > +} > + > static struct blk_mq_ops nvme_tcp_ofld_mq_ops = { > .queue_rq = nvme_tcp_ofld_queue_rq, > + .complete = nvme_complete_rq, > .init_request = nvme_tcp_ofld_init_request, > - /* > - * All additional ops will be also implemented and registered similar to > - * tcp.c > - */ > + .exit_request = nvme_tcp_ofld_exit_request, > + .init_hctx = nvme_tcp_ofld_init_hctx, > + .map_queues = nvme_tcp_ofld_map_queues, > + .poll = nvme_tcp_ofld_poll, > }; > > static struct blk_mq_ops nvme_tcp_ofld_admin_mq_ops = { > .queue_rq = nvme_tcp_ofld_queue_rq, > + .complete = nvme_complete_rq, > .init_request = nvme_tcp_ofld_init_request, > - /* > - * All additional ops will be also implemented and registered similar to > - * tcp.c > - */ > + .exit_request = nvme_tcp_ofld_exit_request, > + .init_hctx = nvme_tcp_ofld_init_admin_hctx, > }; > > static const struct nvme_ctrl_ops nvme_tcp_ofld_ctrl_ops = { > diff --git a/drivers/nvme/host/tcp-offload.h b/drivers/nvme/host/tcp-offload.h > index b80cdef8511a..fcc377680d9f 100644 > --- a/drivers/nvme/host/tcp-offload.h > +++ b/drivers/nvme/host/tcp-offload.h > @@ -65,6 +65,9 @@ struct nvme_tcp_ofld_queue { > unsigned long flags; > size_t cmnd_capsule_len; > > + /* mutex used during stop_queue */ > + struct mutex queue_lock; > + > u8 hdr_digest; > u8 data_digest; > u8 tos; > @@ -197,3 +200,4 @@ struct nvme_tcp_ofld_ops { > int nvme_tcp_ofld_register_dev(struct nvme_tcp_ofld_dev *dev); > void nvme_tcp_ofld_unregister_dev(struct nvme_tcp_ofld_dev *dev); > void nvme_tcp_ofld_error_recovery(struct nvme_ctrl *nctrl); > +inline size_t nvme_tcp_ofld_inline_data_size(struct nvme_tcp_ofld_queue *queue); > Cheers, Hannes
On 5/28/21 2:30 PM, Hannes Reinecke wrote: > On 5/28/21 1:58 AM, Shai Malin wrote: > > From: Dean Balandin <dbalandin@marvell.com> > > > > In this patch we implement queue level functionality. > > The implementation is similar to the nvme-tcp module, the main > > difference being that we call the vendor specific create_queue op which > > creates the TCP connection, and NVMeTPC connection including > > icreq+icresp negotiation. > > Once create_queue returns successfully, we can move on to the fabrics > > connect. > > > > Acked-by: Igor Russkikh <irusskikh@marvell.com> > > Signed-off-by: Dean Balandin <dbalandin@marvell.com> > > Signed-off-by: Prabhakar Kushwaha <pkushwaha@marvell.com> > > Signed-off-by: Omkar Kulkarni <okulkarni@marvell.com> > > Signed-off-by: Michal Kalderon <mkalderon@marvell.com> > > Signed-off-by: Ariel Elior <aelior@marvell.com> > > Signed-off-by: Shai Malin <smalin@marvell.com> > > Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com> > > --- > > drivers/nvme/host/tcp-offload.c | 418 +++++++++++++++++++++++++++++--- > > drivers/nvme/host/tcp-offload.h | 4 + > > 2 files changed, 394 insertions(+), 28 deletions(-) > > > > diff --git a/drivers/nvme/host/tcp-offload.c b/drivers/nvme/host/tcp-offload.c > > index 52d310f7636a..eff10e31f17f 100644 > > --- a/drivers/nvme/host/tcp-offload.c > > +++ b/drivers/nvme/host/tcp-offload.c > > @@ -22,6 +22,11 @@ static inline struct nvme_tcp_ofld_ctrl *to_tcp_ofld_ctrl(struct nvme_ctrl *nctr > > return container_of(nctrl, struct nvme_tcp_ofld_ctrl, nctrl); > > } > > > > +static inline int nvme_tcp_ofld_qid(struct nvme_tcp_ofld_queue *queue) > > +{ > > + return queue - queue->ctrl->queues; > > +} > > + > > /** > > * nvme_tcp_ofld_register_dev() - NVMeTCP Offload Library registration > > * function. > > @@ -182,19 +187,125 @@ nvme_tcp_ofld_alloc_tagset(struct nvme_ctrl *nctrl, bool admin) > > return set; > > } > > > > +static void __nvme_tcp_ofld_stop_queue(struct nvme_tcp_ofld_queue *queue) > > +{ > > + queue->dev->ops->drain_queue(queue); > > +} > > + > > +static void nvme_tcp_ofld_stop_queue(struct nvme_ctrl *nctrl, int qid) > > +{ > > + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); > > + struct nvme_tcp_ofld_queue *queue = &ctrl->queues[qid]; > > + > > + mutex_lock(&queue->queue_lock); > > + if (test_and_clear_bit(NVME_TCP_OFLD_Q_LIVE, &queue->flags)) > > + __nvme_tcp_ofld_stop_queue(queue); > > + mutex_unlock(&queue->queue_lock); > > +} > > + > > +static void nvme_tcp_ofld_stop_io_queues(struct nvme_ctrl *ctrl) > > +{ > > + int i; > > + > > + for (i = 1; i < ctrl->queue_count; i++) > > + nvme_tcp_ofld_stop_queue(ctrl, i); > > +} > > + > > +static void __nvme_tcp_ofld_free_queue(struct nvme_tcp_ofld_queue *queue) > > +{ > > + queue->dev->ops->destroy_queue(queue); > > +} > > + > > +static void nvme_tcp_ofld_free_queue(struct nvme_ctrl *nctrl, int qid) > > +{ > > + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); > > + struct nvme_tcp_ofld_queue *queue = &ctrl->queues[qid]; > > + > > + test_and_clear_bit(NVME_TCP_OFLD_Q_ALLOCATED, &queue->flags); > > You really want to make this an 'if' clause to avoid double free Thanks. Will be fixed. > > > + > > + __nvme_tcp_ofld_free_queue(queue); > > + > > + mutex_destroy(&queue->queue_lock); > > +} > > + > > +static void > > +nvme_tcp_ofld_free_io_queues(struct nvme_ctrl *nctrl) > > +{ > > + int i; > > + > > + for (i = 1; i < nctrl->queue_count; i++) > > + nvme_tcp_ofld_free_queue(nctrl, i); > > +} > > + > > +static void nvme_tcp_ofld_destroy_io_queues(struct nvme_ctrl *nctrl, bool remove) > > +{ > > + nvme_tcp_ofld_stop_io_queues(nctrl); > > + if (remove) { > > + blk_cleanup_queue(nctrl->connect_q); > > + blk_mq_free_tag_set(nctrl->tagset); > > + } > > + nvme_tcp_ofld_free_io_queues(nctrl); > > +} > > + > > +static void nvme_tcp_ofld_destroy_admin_queue(struct nvme_ctrl *nctrl, bool remove) > > +{ > > + nvme_tcp_ofld_stop_queue(nctrl, 0); > > + if (remove) { > > + blk_cleanup_queue(nctrl->admin_q); > > + blk_cleanup_queue(nctrl->fabrics_q); > > + blk_mq_free_tag_set(nctrl->admin_tagset); > > + } > > + nvme_tcp_ofld_free_queue(nctrl, 0); > > +} > > + > > +static int nvme_tcp_ofld_start_queue(struct nvme_ctrl *nctrl, int qid) > > +{ > > + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); > > + struct nvme_tcp_ofld_queue *queue = &ctrl->queues[qid]; > > + int rc; > > + > > + queue = &ctrl->queues[qid]; > > + if (qid) { > > + queue->cmnd_capsule_len = nctrl->ioccsz * 16; > > + rc = nvmf_connect_io_queue(nctrl, qid, false); > > + } else { > > + queue->cmnd_capsule_len = sizeof(struct nvme_command) + NVME_TCP_ADMIN_CCSZ; > > + rc = nvmf_connect_admin_queue(nctrl); > > + } > > + > > + if (!rc) { > > + set_bit(NVME_TCP_OFLD_Q_LIVE, &queue->flags); > > + } else { > > + if (test_bit(NVME_TCP_OFLD_Q_ALLOCATED, &queue->flags)) > > + __nvme_tcp_ofld_stop_queue(queue); > > Why do you need to call 'stop_queue' here? > A failure indicates that the queue wasn't started, no? It is in order to clear any pending requests. It's the same design as tcp.c. Please refer commit f34e25898a6083("nvme-tcp: fix possible null deref on a timed out io queue connect"). > > > + dev_err(nctrl->device, > > + "failed to connect queue: %d ret=%d\n", qid, rc); > > + } > > + > > + return rc; > > +} > > + > > static int nvme_tcp_ofld_configure_admin_queue(struct nvme_ctrl *nctrl, > > bool new) > > { > > + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); > > + struct nvme_tcp_ofld_queue *queue = &ctrl->queues[0]; > > int rc; > > > > - /* Placeholder - alloc_admin_queue */ > > + mutex_init(&queue->queue_lock); > > + > > + rc = ctrl->dev->ops->create_queue(queue, 0, NVME_AQ_DEPTH); > > + if (rc) > > + return rc; > > + > > + set_bit(NVME_TCP_OFLD_Q_ALLOCATED, &queue->flags); > > if (new) { > > nctrl->admin_tagset = > > nvme_tcp_ofld_alloc_tagset(nctrl, true); > > if (IS_ERR(nctrl->admin_tagset)) { > > rc = PTR_ERR(nctrl->admin_tagset); > > nctrl->admin_tagset = NULL; > > - goto out_destroy_queue; > > + goto out_free_queue; > > } > > > > nctrl->fabrics_q = blk_mq_init_queue(nctrl->admin_tagset); > > @@ -212,7 +323,9 @@ static int nvme_tcp_ofld_configure_admin_queue(struct nvme_ctrl *nctrl, > > } > > } > > > > - /* Placeholder - nvme_tcp_ofld_start_queue */ > > + rc = nvme_tcp_ofld_start_queue(nctrl, 0); > > + if (rc) > > + goto out_cleanup_queue; > > > > rc = nvme_enable_ctrl(nctrl); > > if (rc) > > @@ -229,19 +342,143 @@ static int nvme_tcp_ofld_configure_admin_queue(struct nvme_ctrl *nctrl, > > out_quiesce_queue: > > blk_mq_quiesce_queue(nctrl->admin_q); > > blk_sync_queue(nctrl->admin_q); > > - > > out_stop_queue: > > - /* Placeholder - stop offload queue */ > > + nvme_tcp_ofld_stop_queue(nctrl, 0); > > nvme_cancel_admin_tagset(nctrl); > > - > > +out_cleanup_queue: > > + if (new) > > + blk_cleanup_queue(nctrl->admin_q); > > out_cleanup_fabrics_q: > > if (new) > > blk_cleanup_queue(nctrl->fabrics_q); > > out_free_tagset: > > if (new) > > blk_mq_free_tag_set(nctrl->admin_tagset); > > -out_destroy_queue: > > - /* Placeholder - free admin queue */ > > +out_free_queue: > > + nvme_tcp_ofld_free_queue(nctrl, 0); > > + > > + return rc; > > +} > > + > > +static unsigned int nvme_tcp_ofld_nr_io_queues(struct nvme_ctrl *nctrl) > > +{ > > + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); > > + struct nvme_tcp_ofld_dev *dev = ctrl->dev; > > + u32 hw_vectors = dev->num_hw_vectors; > > + u32 nr_write_queues, nr_poll_queues; > > + u32 nr_io_queues, nr_total_queues; > > + > > + nr_io_queues = min3(nctrl->opts->nr_io_queues, num_online_cpus(), > > + hw_vectors); > > + nr_write_queues = min3(nctrl->opts->nr_write_queues, num_online_cpus(), > > + hw_vectors); > > + nr_poll_queues = min3(nctrl->opts->nr_poll_queues, num_online_cpus(), > > + hw_vectors); > > + > > + nr_total_queues = nr_io_queues + nr_write_queues + nr_poll_queues; > > + > > + return nr_total_queues; > > +} > > + > > +static void > > +nvme_tcp_ofld_set_io_queues(struct nvme_ctrl *nctrl, unsigned int nr_io_queues) > > +{ > > + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); > > + struct nvmf_ctrl_options *opts = nctrl->opts; > > + > > + if (opts->nr_write_queues && opts->nr_io_queues < nr_io_queues) { > > + /* > > + * separate read/write queues > > + * hand out dedicated default queues only after we have > > + * sufficient read queues. > > + */ > > + ctrl->io_queues[HCTX_TYPE_READ] = opts->nr_io_queues; > > + nr_io_queues -= ctrl->io_queues[HCTX_TYPE_READ]; > > + ctrl->io_queues[HCTX_TYPE_DEFAULT] = > > + min(opts->nr_write_queues, nr_io_queues); > > + nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT]; > > + } else { > > + /* > > + * shared read/write queues > > + * either no write queues were requested, or we don't have > > + * sufficient queue count to have dedicated default queues. > > + */ > > + ctrl->io_queues[HCTX_TYPE_DEFAULT] = > > + min(opts->nr_io_queues, nr_io_queues); > > + nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT]; > > + } > > + > > + if (opts->nr_poll_queues && nr_io_queues) { > > + /* map dedicated poll queues only if we have queues left */ > > + ctrl->io_queues[HCTX_TYPE_POLL] = > > + min(opts->nr_poll_queues, nr_io_queues); > > + } > > +} > > + > > +static int nvme_tcp_ofld_create_io_queues(struct nvme_ctrl *nctrl) > > +{ > > + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); > > + int i, rc; > > + > > + for (i = 1; i < nctrl->queue_count; i++) { > > + mutex_init(&ctrl->queues[i].queue_lock); > > + > > + rc = ctrl->dev->ops->create_queue(&ctrl->queues[i], > > + i, nctrl->sqsize + 1); > > + if (rc) > > + goto out_free_queues; > > + > > + set_bit(NVME_TCP_OFLD_Q_ALLOCATED, &ctrl->queues[i].flags); > > + } > > + > > + return 0; > > + > > +out_free_queues: > > + for (i--; i >= 1; i--) > > + nvme_tcp_ofld_free_queue(nctrl, i); > > + > > + return rc; > > +} > > + > > +static int nvme_tcp_ofld_alloc_io_queues(struct nvme_ctrl *nctrl) > > +{ > > + unsigned int nr_io_queues; > > + int rc; > > + > > + nr_io_queues = nvme_tcp_ofld_nr_io_queues(nctrl); > > + rc = nvme_set_queue_count(nctrl, &nr_io_queues); > > + if (rc) > > + return rc; > > + > > + nctrl->queue_count = nr_io_queues + 1; > > + if (nctrl->queue_count < 2) { > > + dev_err(nctrl->device, > > + "unable to set any I/O queues\n"); > > + > > + return -ENOMEM; > > + } > > + > > + dev_info(nctrl->device, "creating %d I/O queues.\n", nr_io_queues); > > + nvme_tcp_ofld_set_io_queues(nctrl, nr_io_queues); > > + > > + return nvme_tcp_ofld_create_io_queues(nctrl); > > +} > > + > > +static int nvme_tcp_ofld_start_io_queues(struct nvme_ctrl *nctrl) > > +{ > > + int i, rc = 0; > > + > > + for (i = 1; i < nctrl->queue_count; i++) { > > + rc = nvme_tcp_ofld_start_queue(nctrl, i); > > + if (rc) > > + goto out_stop_queues; > > + } > > + > > + return 0; > > + > > +out_stop_queues: > > + for (i--; i >= 1; i--) > > + nvme_tcp_ofld_stop_queue(nctrl, i); > > > > return rc; > > } > > @@ -249,9 +486,10 @@ static int nvme_tcp_ofld_configure_admin_queue(struct nvme_ctrl *nctrl, > > static int > > nvme_tcp_ofld_configure_io_queues(struct nvme_ctrl *nctrl, bool new) > > { > > - int rc; > > + int rc = nvme_tcp_ofld_alloc_io_queues(nctrl); > > > > - /* Placeholder - alloc_io_queues */ > > + if (rc) > > + return rc; > > > > if (new) { > > nctrl->tagset = nvme_tcp_ofld_alloc_tagset(nctrl, false); > > @@ -269,7 +507,9 @@ nvme_tcp_ofld_configure_io_queues(struct nvme_ctrl *nctrl, bool new) > > } > > } > > > > - /* Placeholder - start_io_queues */ > > + rc = nvme_tcp_ofld_start_io_queues(nctrl); > > + if (rc) > > + goto out_cleanup_connect_q; > > > > if (!new) { > > nvme_start_queues(nctrl); > > @@ -291,16 +531,16 @@ nvme_tcp_ofld_configure_io_queues(struct nvme_ctrl *nctrl, bool new) > > out_wait_freeze_timed_out: > > nvme_stop_queues(nctrl); > > nvme_sync_io_queues(nctrl); > > - > > - /* Placeholder - Stop IO queues */ > > - > > + nvme_tcp_ofld_stop_io_queues(nctrl); > > +out_cleanup_connect_q: > > + nvme_cancel_tagset(nctrl); > > if (new) > > blk_cleanup_queue(nctrl->connect_q); > > out_free_tag_set: > > if (new) > > blk_mq_free_tag_set(nctrl->tagset); > > out_free_io_queues: > > - /* Placeholder - free_io_queues */ > > + nvme_tcp_ofld_free_io_queues(nctrl); > > > > return rc; > > } > > @@ -327,6 +567,17 @@ static void nvme_tcp_ofld_reconnect_or_remove(struct nvme_ctrl *nctrl) > > } > > } > > > > +static int > > +nvme_tcp_ofld_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data, > > + unsigned int hctx_idx) > > +{ > > + struct nvme_tcp_ofld_ctrl *ctrl = data; > > + > > + hctx->driver_data = &ctrl->queues[0]; > > + > > + return 0; > > +} > > + > > static int nvme_tcp_ofld_setup_ctrl(struct nvme_ctrl *nctrl, bool new) > > { > > struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); > > @@ -388,9 +639,19 @@ static int nvme_tcp_ofld_setup_ctrl(struct nvme_ctrl *nctrl, bool new) > > return 0; > > > > destroy_io: > > - /* Placeholder - stop and destroy io queues*/ > > + if (nctrl->queue_count > 1) { > > + nvme_stop_queues(nctrl); > > + nvme_sync_io_queues(nctrl); > > + nvme_tcp_ofld_stop_io_queues(nctrl); > > + nvme_cancel_tagset(nctrl); > > + nvme_tcp_ofld_destroy_io_queues(nctrl, new); > > + } > > destroy_admin: > > - /* Placeholder - stop and destroy admin queue*/ > > + blk_mq_quiesce_queue(nctrl->admin_q); > > + blk_sync_queue(nctrl->admin_q); > > + nvme_tcp_ofld_stop_queue(nctrl, 0); > > + nvme_cancel_admin_tagset(nctrl); > > + nvme_tcp_ofld_destroy_admin_queue(nctrl, new); > > out_release_ctrl: > > ctrl->dev->ops->release_ctrl(ctrl); > > > > @@ -439,15 +700,37 @@ static void nvme_tcp_ofld_free_ctrl(struct nvme_ctrl *nctrl) > > } > > > > static void > > -nvme_tcp_ofld_teardown_admin_queue(struct nvme_ctrl *ctrl, bool remove) > > +nvme_tcp_ofld_teardown_admin_queue(struct nvme_ctrl *nctrl, bool remove) > > { > > - /* Placeholder - teardown_admin_queue */ > > + blk_mq_quiesce_queue(nctrl->admin_q); > > + blk_sync_queue(nctrl->admin_q); > > + > > + nvme_tcp_ofld_stop_queue(nctrl, 0); > > + nvme_cancel_admin_tagset(nctrl); > > + > > + if (remove) > > + blk_mq_unquiesce_queue(nctrl->admin_q); > > + > > + nvme_tcp_ofld_destroy_admin_queue(nctrl, remove); > > } > > > > static void > > nvme_tcp_ofld_teardown_io_queues(struct nvme_ctrl *nctrl, bool remove) > > { > > - /* Placeholder - teardown_io_queues */ > > + if (nctrl->queue_count <= 1) > > + return; > > + > > + blk_mq_quiesce_queue(nctrl->admin_q); > > + nvme_start_freeze(nctrl); > > + nvme_stop_queues(nctrl); > > + nvme_sync_io_queues(nctrl); > > + nvme_tcp_ofld_stop_io_queues(nctrl); > > + nvme_cancel_tagset(nctrl); > > + > > + if (remove) > > + nvme_start_queues(nctrl); > > That looks odd. > Surely all requests need to be flushed even for the not-remove case? In the not-remove case nvme_start_queues() will be invoked from nvme_tcp_ofld_error_recovery_work(). We are keeping the same design as tcp.c. > > > + > > + nvme_tcp_ofld_destroy_io_queues(nctrl, remove); > > } > > > > static void nvme_tcp_ofld_reconnect_ctrl_work(struct work_struct *work) > > @@ -562,6 +845,12 @@ nvme_tcp_ofld_init_request(struct blk_mq_tag_set *set, > > return 0; > > } > > > > +inline size_t nvme_tcp_ofld_inline_data_size(struct nvme_tcp_ofld_queue *queue) > > +{ > > + return queue->cmnd_capsule_len - sizeof(struct nvme_command); > > +} > > +EXPORT_SYMBOL_GPL(nvme_tcp_ofld_inline_data_size); > > + > > static blk_status_t > > nvme_tcp_ofld_queue_rq(struct blk_mq_hw_ctx *hctx, > > const struct blk_mq_queue_data *bd) > > @@ -573,22 +862,95 @@ nvme_tcp_ofld_queue_rq(struct blk_mq_hw_ctx *hctx, > > return BLK_STS_OK; > > } > > > > +static void > > +nvme_tcp_ofld_exit_request(struct blk_mq_tag_set *set, > > + struct request *rq, unsigned int hctx_idx) > > +{ > > + /* > > + * Nothing is allocated in nvme_tcp_ofld_init_request, > > + * hence empty. > > + */ > > +} > > + > > +static int > > +nvme_tcp_ofld_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, > > + unsigned int hctx_idx) > > +{ > > + struct nvme_tcp_ofld_ctrl *ctrl = data; > > + > > + hctx->driver_data = &ctrl->queues[hctx_idx + 1]; > > + > > + return 0; > > +} > > + > > +static int nvme_tcp_ofld_map_queues(struct blk_mq_tag_set *set) > > +{ > > + struct nvme_tcp_ofld_ctrl *ctrl = set->driver_data; > > + struct nvmf_ctrl_options *opts = ctrl->nctrl.opts; > > + > > + if (opts->nr_write_queues && ctrl->io_queues[HCTX_TYPE_READ]) { > > + /* separate read/write queues */ > > + set->map[HCTX_TYPE_DEFAULT].nr_queues = > > + ctrl->io_queues[HCTX_TYPE_DEFAULT]; > > + set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; > > + set->map[HCTX_TYPE_READ].nr_queues = > > + ctrl->io_queues[HCTX_TYPE_READ]; > > + set->map[HCTX_TYPE_READ].queue_offset = > > + ctrl->io_queues[HCTX_TYPE_DEFAULT]; > > + } else { > > + /* shared read/write queues */ > > + set->map[HCTX_TYPE_DEFAULT].nr_queues = > > + ctrl->io_queues[HCTX_TYPE_DEFAULT]; > > + set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; > > + set->map[HCTX_TYPE_READ].nr_queues = > > + ctrl->io_queues[HCTX_TYPE_DEFAULT]; > > + set->map[HCTX_TYPE_READ].queue_offset = 0; > > + } > > + blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); > > + blk_mq_map_queues(&set->map[HCTX_TYPE_READ]); > > + > > + if (opts->nr_poll_queues && ctrl->io_queues[HCTX_TYPE_POLL]) { > > + /* map dedicated poll queues only if we have queues left */ > > + set->map[HCTX_TYPE_POLL].nr_queues = > > + ctrl->io_queues[HCTX_TYPE_POLL]; > > + set->map[HCTX_TYPE_POLL].queue_offset = > > + ctrl->io_queues[HCTX_TYPE_DEFAULT] + > > + ctrl->io_queues[HCTX_TYPE_READ]; > > + blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]); > > + } > > + > > + dev_info(ctrl->nctrl.device, > > + "mapped %d/%d/%d default/read/poll queues.\n", > > + ctrl->io_queues[HCTX_TYPE_DEFAULT], > > + ctrl->io_queues[HCTX_TYPE_READ], > > + ctrl->io_queues[HCTX_TYPE_POLL]); > > + > > + return 0; > > +} > > + > > +static int nvme_tcp_ofld_poll(struct blk_mq_hw_ctx *hctx) > > +{ > > + /* Placeholder - Implement polling mechanism */ > > + > > + return 0; > > +} > > + > > static struct blk_mq_ops nvme_tcp_ofld_mq_ops = { > > .queue_rq = nvme_tcp_ofld_queue_rq, > > + .complete = nvme_complete_rq, > > .init_request = nvme_tcp_ofld_init_request, > > - /* > > - * All additional ops will be also implemented and registered similar to > > - * tcp.c > > - */ > > + .exit_request = nvme_tcp_ofld_exit_request, > > + .init_hctx = nvme_tcp_ofld_init_hctx, > > + .map_queues = nvme_tcp_ofld_map_queues, > > + .poll = nvme_tcp_ofld_poll, > > }; > > > > static struct blk_mq_ops nvme_tcp_ofld_admin_mq_ops = { > > .queue_rq = nvme_tcp_ofld_queue_rq, > > + .complete = nvme_complete_rq, > > .init_request = nvme_tcp_ofld_init_request, > > - /* > > - * All additional ops will be also implemented and registered similar to > > - * tcp.c > > - */ > > + .exit_request = nvme_tcp_ofld_exit_request, > > + .init_hctx = nvme_tcp_ofld_init_admin_hctx, > > }; > > > > static const struct nvme_ctrl_ops nvme_tcp_ofld_ctrl_ops = { > > diff --git a/drivers/nvme/host/tcp-offload.h b/drivers/nvme/host/tcp-offload.h > > index b80cdef8511a..fcc377680d9f 100644 > > --- a/drivers/nvme/host/tcp-offload.h > > +++ b/drivers/nvme/host/tcp-offload.h > > @@ -65,6 +65,9 @@ struct nvme_tcp_ofld_queue { > > unsigned long flags; > > size_t cmnd_capsule_len; > > > > + /* mutex used during stop_queue */ > > + struct mutex queue_lock; > > + > > u8 hdr_digest; > > u8 data_digest; > > u8 tos; > > @@ -197,3 +200,4 @@ struct nvme_tcp_ofld_ops { > > int nvme_tcp_ofld_register_dev(struct nvme_tcp_ofld_dev *dev); > > void nvme_tcp_ofld_unregister_dev(struct nvme_tcp_ofld_dev *dev); > > void nvme_tcp_ofld_error_recovery(struct nvme_ctrl *nctrl); > > +inline size_t nvme_tcp_ofld_inline_data_size(struct nvme_tcp_ofld_queue *queue); > > > Cheers, > > Hannes > -- > Dr. Hannes Reinecke Kernel Storage Architect > hare@suse.de +49 911 74053 688 > SUSE Software Solutions Germany GmbH, 90409 Nürnberg > GF: F. Imendörffer, HRB 36809 (AG Nürnberg)
diff --git a/drivers/nvme/host/tcp-offload.c b/drivers/nvme/host/tcp-offload.c index 52d310f7636a..eff10e31f17f 100644 --- a/drivers/nvme/host/tcp-offload.c +++ b/drivers/nvme/host/tcp-offload.c @@ -22,6 +22,11 @@ static inline struct nvme_tcp_ofld_ctrl *to_tcp_ofld_ctrl(struct nvme_ctrl *nctr return container_of(nctrl, struct nvme_tcp_ofld_ctrl, nctrl); } +static inline int nvme_tcp_ofld_qid(struct nvme_tcp_ofld_queue *queue) +{ + return queue - queue->ctrl->queues; +} + /** * nvme_tcp_ofld_register_dev() - NVMeTCP Offload Library registration * function. @@ -182,19 +187,125 @@ nvme_tcp_ofld_alloc_tagset(struct nvme_ctrl *nctrl, bool admin) return set; } +static void __nvme_tcp_ofld_stop_queue(struct nvme_tcp_ofld_queue *queue) +{ + queue->dev->ops->drain_queue(queue); +} + +static void nvme_tcp_ofld_stop_queue(struct nvme_ctrl *nctrl, int qid) +{ + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); + struct nvme_tcp_ofld_queue *queue = &ctrl->queues[qid]; + + mutex_lock(&queue->queue_lock); + if (test_and_clear_bit(NVME_TCP_OFLD_Q_LIVE, &queue->flags)) + __nvme_tcp_ofld_stop_queue(queue); + mutex_unlock(&queue->queue_lock); +} + +static void nvme_tcp_ofld_stop_io_queues(struct nvme_ctrl *ctrl) +{ + int i; + + for (i = 1; i < ctrl->queue_count; i++) + nvme_tcp_ofld_stop_queue(ctrl, i); +} + +static void __nvme_tcp_ofld_free_queue(struct nvme_tcp_ofld_queue *queue) +{ + queue->dev->ops->destroy_queue(queue); +} + +static void nvme_tcp_ofld_free_queue(struct nvme_ctrl *nctrl, int qid) +{ + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); + struct nvme_tcp_ofld_queue *queue = &ctrl->queues[qid]; + + test_and_clear_bit(NVME_TCP_OFLD_Q_ALLOCATED, &queue->flags); + + __nvme_tcp_ofld_free_queue(queue); + + mutex_destroy(&queue->queue_lock); +} + +static void +nvme_tcp_ofld_free_io_queues(struct nvme_ctrl *nctrl) +{ + int i; + + for (i = 1; i < nctrl->queue_count; i++) + nvme_tcp_ofld_free_queue(nctrl, i); +} + +static void nvme_tcp_ofld_destroy_io_queues(struct nvme_ctrl *nctrl, bool remove) +{ + nvme_tcp_ofld_stop_io_queues(nctrl); + if (remove) { + blk_cleanup_queue(nctrl->connect_q); + blk_mq_free_tag_set(nctrl->tagset); + } + nvme_tcp_ofld_free_io_queues(nctrl); +} + +static void nvme_tcp_ofld_destroy_admin_queue(struct nvme_ctrl *nctrl, bool remove) +{ + nvme_tcp_ofld_stop_queue(nctrl, 0); + if (remove) { + blk_cleanup_queue(nctrl->admin_q); + blk_cleanup_queue(nctrl->fabrics_q); + blk_mq_free_tag_set(nctrl->admin_tagset); + } + nvme_tcp_ofld_free_queue(nctrl, 0); +} + +static int nvme_tcp_ofld_start_queue(struct nvme_ctrl *nctrl, int qid) +{ + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); + struct nvme_tcp_ofld_queue *queue = &ctrl->queues[qid]; + int rc; + + queue = &ctrl->queues[qid]; + if (qid) { + queue->cmnd_capsule_len = nctrl->ioccsz * 16; + rc = nvmf_connect_io_queue(nctrl, qid, false); + } else { + queue->cmnd_capsule_len = sizeof(struct nvme_command) + NVME_TCP_ADMIN_CCSZ; + rc = nvmf_connect_admin_queue(nctrl); + } + + if (!rc) { + set_bit(NVME_TCP_OFLD_Q_LIVE, &queue->flags); + } else { + if (test_bit(NVME_TCP_OFLD_Q_ALLOCATED, &queue->flags)) + __nvme_tcp_ofld_stop_queue(queue); + dev_err(nctrl->device, + "failed to connect queue: %d ret=%d\n", qid, rc); + } + + return rc; +} + static int nvme_tcp_ofld_configure_admin_queue(struct nvme_ctrl *nctrl, bool new) { + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); + struct nvme_tcp_ofld_queue *queue = &ctrl->queues[0]; int rc; - /* Placeholder - alloc_admin_queue */ + mutex_init(&queue->queue_lock); + + rc = ctrl->dev->ops->create_queue(queue, 0, NVME_AQ_DEPTH); + if (rc) + return rc; + + set_bit(NVME_TCP_OFLD_Q_ALLOCATED, &queue->flags); if (new) { nctrl->admin_tagset = nvme_tcp_ofld_alloc_tagset(nctrl, true); if (IS_ERR(nctrl->admin_tagset)) { rc = PTR_ERR(nctrl->admin_tagset); nctrl->admin_tagset = NULL; - goto out_destroy_queue; + goto out_free_queue; } nctrl->fabrics_q = blk_mq_init_queue(nctrl->admin_tagset); @@ -212,7 +323,9 @@ static int nvme_tcp_ofld_configure_admin_queue(struct nvme_ctrl *nctrl, } } - /* Placeholder - nvme_tcp_ofld_start_queue */ + rc = nvme_tcp_ofld_start_queue(nctrl, 0); + if (rc) + goto out_cleanup_queue; rc = nvme_enable_ctrl(nctrl); if (rc) @@ -229,19 +342,143 @@ static int nvme_tcp_ofld_configure_admin_queue(struct nvme_ctrl *nctrl, out_quiesce_queue: blk_mq_quiesce_queue(nctrl->admin_q); blk_sync_queue(nctrl->admin_q); - out_stop_queue: - /* Placeholder - stop offload queue */ + nvme_tcp_ofld_stop_queue(nctrl, 0); nvme_cancel_admin_tagset(nctrl); - +out_cleanup_queue: + if (new) + blk_cleanup_queue(nctrl->admin_q); out_cleanup_fabrics_q: if (new) blk_cleanup_queue(nctrl->fabrics_q); out_free_tagset: if (new) blk_mq_free_tag_set(nctrl->admin_tagset); -out_destroy_queue: - /* Placeholder - free admin queue */ +out_free_queue: + nvme_tcp_ofld_free_queue(nctrl, 0); + + return rc; +} + +static unsigned int nvme_tcp_ofld_nr_io_queues(struct nvme_ctrl *nctrl) +{ + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); + struct nvme_tcp_ofld_dev *dev = ctrl->dev; + u32 hw_vectors = dev->num_hw_vectors; + u32 nr_write_queues, nr_poll_queues; + u32 nr_io_queues, nr_total_queues; + + nr_io_queues = min3(nctrl->opts->nr_io_queues, num_online_cpus(), + hw_vectors); + nr_write_queues = min3(nctrl->opts->nr_write_queues, num_online_cpus(), + hw_vectors); + nr_poll_queues = min3(nctrl->opts->nr_poll_queues, num_online_cpus(), + hw_vectors); + + nr_total_queues = nr_io_queues + nr_write_queues + nr_poll_queues; + + return nr_total_queues; +} + +static void +nvme_tcp_ofld_set_io_queues(struct nvme_ctrl *nctrl, unsigned int nr_io_queues) +{ + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); + struct nvmf_ctrl_options *opts = nctrl->opts; + + if (opts->nr_write_queues && opts->nr_io_queues < nr_io_queues) { + /* + * separate read/write queues + * hand out dedicated default queues only after we have + * sufficient read queues. + */ + ctrl->io_queues[HCTX_TYPE_READ] = opts->nr_io_queues; + nr_io_queues -= ctrl->io_queues[HCTX_TYPE_READ]; + ctrl->io_queues[HCTX_TYPE_DEFAULT] = + min(opts->nr_write_queues, nr_io_queues); + nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT]; + } else { + /* + * shared read/write queues + * either no write queues were requested, or we don't have + * sufficient queue count to have dedicated default queues. + */ + ctrl->io_queues[HCTX_TYPE_DEFAULT] = + min(opts->nr_io_queues, nr_io_queues); + nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT]; + } + + if (opts->nr_poll_queues && nr_io_queues) { + /* map dedicated poll queues only if we have queues left */ + ctrl->io_queues[HCTX_TYPE_POLL] = + min(opts->nr_poll_queues, nr_io_queues); + } +} + +static int nvme_tcp_ofld_create_io_queues(struct nvme_ctrl *nctrl) +{ + struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); + int i, rc; + + for (i = 1; i < nctrl->queue_count; i++) { + mutex_init(&ctrl->queues[i].queue_lock); + + rc = ctrl->dev->ops->create_queue(&ctrl->queues[i], + i, nctrl->sqsize + 1); + if (rc) + goto out_free_queues; + + set_bit(NVME_TCP_OFLD_Q_ALLOCATED, &ctrl->queues[i].flags); + } + + return 0; + +out_free_queues: + for (i--; i >= 1; i--) + nvme_tcp_ofld_free_queue(nctrl, i); + + return rc; +} + +static int nvme_tcp_ofld_alloc_io_queues(struct nvme_ctrl *nctrl) +{ + unsigned int nr_io_queues; + int rc; + + nr_io_queues = nvme_tcp_ofld_nr_io_queues(nctrl); + rc = nvme_set_queue_count(nctrl, &nr_io_queues); + if (rc) + return rc; + + nctrl->queue_count = nr_io_queues + 1; + if (nctrl->queue_count < 2) { + dev_err(nctrl->device, + "unable to set any I/O queues\n"); + + return -ENOMEM; + } + + dev_info(nctrl->device, "creating %d I/O queues.\n", nr_io_queues); + nvme_tcp_ofld_set_io_queues(nctrl, nr_io_queues); + + return nvme_tcp_ofld_create_io_queues(nctrl); +} + +static int nvme_tcp_ofld_start_io_queues(struct nvme_ctrl *nctrl) +{ + int i, rc = 0; + + for (i = 1; i < nctrl->queue_count; i++) { + rc = nvme_tcp_ofld_start_queue(nctrl, i); + if (rc) + goto out_stop_queues; + } + + return 0; + +out_stop_queues: + for (i--; i >= 1; i--) + nvme_tcp_ofld_stop_queue(nctrl, i); return rc; } @@ -249,9 +486,10 @@ static int nvme_tcp_ofld_configure_admin_queue(struct nvme_ctrl *nctrl, static int nvme_tcp_ofld_configure_io_queues(struct nvme_ctrl *nctrl, bool new) { - int rc; + int rc = nvme_tcp_ofld_alloc_io_queues(nctrl); - /* Placeholder - alloc_io_queues */ + if (rc) + return rc; if (new) { nctrl->tagset = nvme_tcp_ofld_alloc_tagset(nctrl, false); @@ -269,7 +507,9 @@ nvme_tcp_ofld_configure_io_queues(struct nvme_ctrl *nctrl, bool new) } } - /* Placeholder - start_io_queues */ + rc = nvme_tcp_ofld_start_io_queues(nctrl); + if (rc) + goto out_cleanup_connect_q; if (!new) { nvme_start_queues(nctrl); @@ -291,16 +531,16 @@ nvme_tcp_ofld_configure_io_queues(struct nvme_ctrl *nctrl, bool new) out_wait_freeze_timed_out: nvme_stop_queues(nctrl); nvme_sync_io_queues(nctrl); - - /* Placeholder - Stop IO queues */ - + nvme_tcp_ofld_stop_io_queues(nctrl); +out_cleanup_connect_q: + nvme_cancel_tagset(nctrl); if (new) blk_cleanup_queue(nctrl->connect_q); out_free_tag_set: if (new) blk_mq_free_tag_set(nctrl->tagset); out_free_io_queues: - /* Placeholder - free_io_queues */ + nvme_tcp_ofld_free_io_queues(nctrl); return rc; } @@ -327,6 +567,17 @@ static void nvme_tcp_ofld_reconnect_or_remove(struct nvme_ctrl *nctrl) } } +static int +nvme_tcp_ofld_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data, + unsigned int hctx_idx) +{ + struct nvme_tcp_ofld_ctrl *ctrl = data; + + hctx->driver_data = &ctrl->queues[0]; + + return 0; +} + static int nvme_tcp_ofld_setup_ctrl(struct nvme_ctrl *nctrl, bool new) { struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl); @@ -388,9 +639,19 @@ static int nvme_tcp_ofld_setup_ctrl(struct nvme_ctrl *nctrl, bool new) return 0; destroy_io: - /* Placeholder - stop and destroy io queues*/ + if (nctrl->queue_count > 1) { + nvme_stop_queues(nctrl); + nvme_sync_io_queues(nctrl); + nvme_tcp_ofld_stop_io_queues(nctrl); + nvme_cancel_tagset(nctrl); + nvme_tcp_ofld_destroy_io_queues(nctrl, new); + } destroy_admin: - /* Placeholder - stop and destroy admin queue*/ + blk_mq_quiesce_queue(nctrl->admin_q); + blk_sync_queue(nctrl->admin_q); + nvme_tcp_ofld_stop_queue(nctrl, 0); + nvme_cancel_admin_tagset(nctrl); + nvme_tcp_ofld_destroy_admin_queue(nctrl, new); out_release_ctrl: ctrl->dev->ops->release_ctrl(ctrl); @@ -439,15 +700,37 @@ static void nvme_tcp_ofld_free_ctrl(struct nvme_ctrl *nctrl) } static void -nvme_tcp_ofld_teardown_admin_queue(struct nvme_ctrl *ctrl, bool remove) +nvme_tcp_ofld_teardown_admin_queue(struct nvme_ctrl *nctrl, bool remove) { - /* Placeholder - teardown_admin_queue */ + blk_mq_quiesce_queue(nctrl->admin_q); + blk_sync_queue(nctrl->admin_q); + + nvme_tcp_ofld_stop_queue(nctrl, 0); + nvme_cancel_admin_tagset(nctrl); + + if (remove) + blk_mq_unquiesce_queue(nctrl->admin_q); + + nvme_tcp_ofld_destroy_admin_queue(nctrl, remove); } static void nvme_tcp_ofld_teardown_io_queues(struct nvme_ctrl *nctrl, bool remove) { - /* Placeholder - teardown_io_queues */ + if (nctrl->queue_count <= 1) + return; + + blk_mq_quiesce_queue(nctrl->admin_q); + nvme_start_freeze(nctrl); + nvme_stop_queues(nctrl); + nvme_sync_io_queues(nctrl); + nvme_tcp_ofld_stop_io_queues(nctrl); + nvme_cancel_tagset(nctrl); + + if (remove) + nvme_start_queues(nctrl); + + nvme_tcp_ofld_destroy_io_queues(nctrl, remove); } static void nvme_tcp_ofld_reconnect_ctrl_work(struct work_struct *work) @@ -562,6 +845,12 @@ nvme_tcp_ofld_init_request(struct blk_mq_tag_set *set, return 0; } +inline size_t nvme_tcp_ofld_inline_data_size(struct nvme_tcp_ofld_queue *queue) +{ + return queue->cmnd_capsule_len - sizeof(struct nvme_command); +} +EXPORT_SYMBOL_GPL(nvme_tcp_ofld_inline_data_size); + static blk_status_t nvme_tcp_ofld_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) @@ -573,22 +862,95 @@ nvme_tcp_ofld_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } +static void +nvme_tcp_ofld_exit_request(struct blk_mq_tag_set *set, + struct request *rq, unsigned int hctx_idx) +{ + /* + * Nothing is allocated in nvme_tcp_ofld_init_request, + * hence empty. + */ +} + +static int +nvme_tcp_ofld_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, + unsigned int hctx_idx) +{ + struct nvme_tcp_ofld_ctrl *ctrl = data; + + hctx->driver_data = &ctrl->queues[hctx_idx + 1]; + + return 0; +} + +static int nvme_tcp_ofld_map_queues(struct blk_mq_tag_set *set) +{ + struct nvme_tcp_ofld_ctrl *ctrl = set->driver_data; + struct nvmf_ctrl_options *opts = ctrl->nctrl.opts; + + if (opts->nr_write_queues && ctrl->io_queues[HCTX_TYPE_READ]) { + /* separate read/write queues */ + set->map[HCTX_TYPE_DEFAULT].nr_queues = + ctrl->io_queues[HCTX_TYPE_DEFAULT]; + set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; + set->map[HCTX_TYPE_READ].nr_queues = + ctrl->io_queues[HCTX_TYPE_READ]; + set->map[HCTX_TYPE_READ].queue_offset = + ctrl->io_queues[HCTX_TYPE_DEFAULT]; + } else { + /* shared read/write queues */ + set->map[HCTX_TYPE_DEFAULT].nr_queues = + ctrl->io_queues[HCTX_TYPE_DEFAULT]; + set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; + set->map[HCTX_TYPE_READ].nr_queues = + ctrl->io_queues[HCTX_TYPE_DEFAULT]; + set->map[HCTX_TYPE_READ].queue_offset = 0; + } + blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); + blk_mq_map_queues(&set->map[HCTX_TYPE_READ]); + + if (opts->nr_poll_queues && ctrl->io_queues[HCTX_TYPE_POLL]) { + /* map dedicated poll queues only if we have queues left */ + set->map[HCTX_TYPE_POLL].nr_queues = + ctrl->io_queues[HCTX_TYPE_POLL]; + set->map[HCTX_TYPE_POLL].queue_offset = + ctrl->io_queues[HCTX_TYPE_DEFAULT] + + ctrl->io_queues[HCTX_TYPE_READ]; + blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]); + } + + dev_info(ctrl->nctrl.device, + "mapped %d/%d/%d default/read/poll queues.\n", + ctrl->io_queues[HCTX_TYPE_DEFAULT], + ctrl->io_queues[HCTX_TYPE_READ], + ctrl->io_queues[HCTX_TYPE_POLL]); + + return 0; +} + +static int nvme_tcp_ofld_poll(struct blk_mq_hw_ctx *hctx) +{ + /* Placeholder - Implement polling mechanism */ + + return 0; +} + static struct blk_mq_ops nvme_tcp_ofld_mq_ops = { .queue_rq = nvme_tcp_ofld_queue_rq, + .complete = nvme_complete_rq, .init_request = nvme_tcp_ofld_init_request, - /* - * All additional ops will be also implemented and registered similar to - * tcp.c - */ + .exit_request = nvme_tcp_ofld_exit_request, + .init_hctx = nvme_tcp_ofld_init_hctx, + .map_queues = nvme_tcp_ofld_map_queues, + .poll = nvme_tcp_ofld_poll, }; static struct blk_mq_ops nvme_tcp_ofld_admin_mq_ops = { .queue_rq = nvme_tcp_ofld_queue_rq, + .complete = nvme_complete_rq, .init_request = nvme_tcp_ofld_init_request, - /* - * All additional ops will be also implemented and registered similar to - * tcp.c - */ + .exit_request = nvme_tcp_ofld_exit_request, + .init_hctx = nvme_tcp_ofld_init_admin_hctx, }; static const struct nvme_ctrl_ops nvme_tcp_ofld_ctrl_ops = { diff --git a/drivers/nvme/host/tcp-offload.h b/drivers/nvme/host/tcp-offload.h index b80cdef8511a..fcc377680d9f 100644 --- a/drivers/nvme/host/tcp-offload.h +++ b/drivers/nvme/host/tcp-offload.h @@ -65,6 +65,9 @@ struct nvme_tcp_ofld_queue { unsigned long flags; size_t cmnd_capsule_len; + /* mutex used during stop_queue */ + struct mutex queue_lock; + u8 hdr_digest; u8 data_digest; u8 tos; @@ -197,3 +200,4 @@ struct nvme_tcp_ofld_ops { int nvme_tcp_ofld_register_dev(struct nvme_tcp_ofld_dev *dev); void nvme_tcp_ofld_unregister_dev(struct nvme_tcp_ofld_dev *dev); void nvme_tcp_ofld_error_recovery(struct nvme_ctrl *nctrl); +inline size_t nvme_tcp_ofld_inline_data_size(struct nvme_tcp_ofld_queue *queue);