From 5fd251c8b4c52da0d0916470a67fbb77b972125e Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 23 May 2016 15:20:48 +0300 Subject: IB/core: Introduce Work Queue object and its verbs Introduce Work Queue object and its create/destroy/modify verbs. QP can be created without internal WQs "packaged" inside it, this QP can be configured to use "external" WQ object as its receive/send queue. WQ is a necessary component for RSS technology since RSS mechanism is supposed to distribute the traffic between multiple Receive Work Queues. WQ associated (many to one) with Completion Queue and it owns WQ properties (PD, WQ size, etc.). WQ has a type, this patch introduces the IB_WQT_RQ (i.e.receive queue), it may be extend to others such as IB_WQT_SQ. (send queue). WQ from type IB_WQT_RQ contains receive work requests. PD is an attribute of a work queue (i.e. send/receive queue), it's used by the hardware for security validation before scattering to a memory region which is pointed by the WQ. For that, an external WQ object needs a PD, letting the hardware makes that validation. When accessing a memory region that is pointed by the WQ its PD is used and not the QP's PD, this behavior is similar to a SRQ and a QP. WQ context is subject to a well-defined state transitions done by the modify_wq verb. When WQ is created its initial state becomes IB_WQS_RESET. >From IB_WQS_RESET it can be modified to itself or to IB_WQS_RDY. >From IB_WQS_RDY it can be modified to itself, to IB_WQS_RESET or to IB_WQS_ERR. >From IB_WQS_ERR it can be modified to IB_WQS_RESET. Note: transition to IB_WQS_ERR might occur implicitly in case there was some HW error. Signed-off-by: Yishai Hadas Signed-off-by: Matan Barak Reviewed-by: Sagi Grimberg Reviewed-by: Sagi Grimberg Signed-off-by: Doug Ledford --- drivers/infiniband/core/verbs.c | 82 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 82 insertions(+) (limited to 'drivers/infiniband/core/verbs.c') diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 1d7d4cf442e3..c096cadc6e23 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1554,6 +1554,88 @@ int ib_dealloc_xrcd(struct ib_xrcd *xrcd) } EXPORT_SYMBOL(ib_dealloc_xrcd); +/** + * ib_create_wq - Creates a WQ associated with the specified protection + * domain. + * @pd: The protection domain associated with the WQ. + * @wq_init_attr: A list of initial attributes required to create the + * WQ. If WQ creation succeeds, then the attributes are updated to + * the actual capabilities of the created WQ. + * + * wq_init_attr->max_wr and wq_init_attr->max_sge determine + * the requested size of the WQ, and set to the actual values allocated + * on return. + * If ib_create_wq() succeeds, then max_wr and max_sge will always be + * at least as large as the requested values. + */ +struct ib_wq *ib_create_wq(struct ib_pd *pd, + struct ib_wq_init_attr *wq_attr) +{ + struct ib_wq *wq; + + if (!pd->device->create_wq) + return ERR_PTR(-ENOSYS); + + wq = pd->device->create_wq(pd, wq_attr, NULL); + if (!IS_ERR(wq)) { + wq->event_handler = wq_attr->event_handler; + wq->wq_context = wq_attr->wq_context; + wq->wq_type = wq_attr->wq_type; + wq->cq = wq_attr->cq; + wq->device = pd->device; + wq->pd = pd; + wq->uobject = NULL; + atomic_inc(&pd->usecnt); + atomic_inc(&wq_attr->cq->usecnt); + atomic_set(&wq->usecnt, 0); + } + return wq; +} +EXPORT_SYMBOL(ib_create_wq); + +/** + * ib_destroy_wq - Destroys the specified WQ. + * @wq: The WQ to destroy. + */ +int ib_destroy_wq(struct ib_wq *wq) +{ + int err; + struct ib_cq *cq = wq->cq; + struct ib_pd *pd = wq->pd; + + if (atomic_read(&wq->usecnt)) + return -EBUSY; + + err = wq->device->destroy_wq(wq); + if (!err) { + atomic_dec(&pd->usecnt); + atomic_dec(&cq->usecnt); + } + return err; +} +EXPORT_SYMBOL(ib_destroy_wq); + +/** + * ib_modify_wq - Modifies the specified WQ. + * @wq: The WQ to modify. + * @wq_attr: On input, specifies the WQ attributes to modify. + * @wq_attr_mask: A bit-mask used to specify which attributes of the WQ + * are being modified. + * On output, the current values of selected WQ attributes are returned. + */ +int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr, + u32 wq_attr_mask) +{ + int err; + + if (!wq->device->modify_wq) + return -ENOSYS; + + err = wq->device->modify_wq(wq, wq_attr, wq_attr_mask, NULL); + return err; +} +EXPORT_SYMBOL(ib_modify_wq); + struct ib_flow *ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_attr, int domain) -- cgit v1.2.3 From 6d39786bf116e476d75eca91f7cfa22586a32e5f Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 23 May 2016 15:20:51 +0300 Subject: IB/core: Introduce Receive Work Queue indirection table Introduce Receive Work Queue (WQ) indirection table. This object can be used to spread incoming traffic to different receive Work Queues. A Receive WQ indirection table points to variable size of WQs. This table is given to a QP in downstream patches. Signed-off-by: Yishai Hadas Signed-off-by: Matan Barak Reviewed-by: Sagi Grimberg Signed-off-by: Doug Ledford --- drivers/infiniband/core/verbs.c | 62 +++++++++++++++++++++++++++++++++++++++++ include/rdma/ib_verbs.h | 23 +++++++++++++++ 2 files changed, 85 insertions(+) (limited to 'drivers/infiniband/core/verbs.c') diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index c096cadc6e23..6b548d7f8753 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1636,6 +1636,68 @@ int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr, } EXPORT_SYMBOL(ib_modify_wq); +/* + * ib_create_rwq_ind_table - Creates a RQ Indirection Table. + * @device: The device on which to create the rwq indirection table. + * @ib_rwq_ind_table_init_attr: A list of initial attributes required to + * create the Indirection Table. + * + * Note: The life time of ib_rwq_ind_table_init_attr->ind_tbl is not less + * than the created ib_rwq_ind_table object and the caller is responsible + * for its memory allocation/free. + */ +struct ib_rwq_ind_table *ib_create_rwq_ind_table(struct ib_device *device, + struct ib_rwq_ind_table_init_attr *init_attr) +{ + struct ib_rwq_ind_table *rwq_ind_table; + int i; + u32 table_size; + + if (!device->create_rwq_ind_table) + return ERR_PTR(-ENOSYS); + + table_size = (1 << init_attr->log_ind_tbl_size); + rwq_ind_table = device->create_rwq_ind_table(device, + init_attr, NULL); + if (IS_ERR(rwq_ind_table)) + return rwq_ind_table; + + rwq_ind_table->ind_tbl = init_attr->ind_tbl; + rwq_ind_table->log_ind_tbl_size = init_attr->log_ind_tbl_size; + rwq_ind_table->device = device; + rwq_ind_table->uobject = NULL; + atomic_set(&rwq_ind_table->usecnt, 0); + + for (i = 0; i < table_size; i++) + atomic_inc(&rwq_ind_table->ind_tbl[i]->usecnt); + + return rwq_ind_table; +} +EXPORT_SYMBOL(ib_create_rwq_ind_table); + +/* + * ib_destroy_rwq_ind_table - Destroys the specified Indirection Table. + * @wq_ind_table: The Indirection Table to destroy. +*/ +int ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *rwq_ind_table) +{ + int err, i; + u32 table_size = (1 << rwq_ind_table->log_ind_tbl_size); + struct ib_wq **ind_tbl = rwq_ind_table->ind_tbl; + + if (atomic_read(&rwq_ind_table->usecnt)) + return -EBUSY; + + err = rwq_ind_table->device->destroy_rwq_ind_table(rwq_ind_table); + if (!err) { + for (i = 0; i < table_size; i++) + atomic_dec(&ind_tbl[i]->usecnt); + } + + return err; +} +EXPORT_SYMBOL(ib_destroy_rwq_ind_table); + struct ib_flow *ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_attr, int domain) diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 0c1956a98573..fa2e0184dcc5 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1473,6 +1473,21 @@ struct ib_wq_attr { enum ib_wq_state curr_wq_state; }; +struct ib_rwq_ind_table { + struct ib_device *device; + struct ib_uobject *uobject; + atomic_t usecnt; + u32 ind_tbl_num; + u32 log_ind_tbl_size; + struct ib_wq **ind_tbl; +}; + +struct ib_rwq_ind_table_init_attr { + u32 log_ind_tbl_size; + /* Each entry is a pointer to Receive Work Queue */ + struct ib_wq **ind_tbl; +}; + struct ib_qp { struct ib_device *device; struct ib_pd *pd; @@ -1974,6 +1989,10 @@ struct ib_device { struct ib_wq_attr *attr, u32 wq_attr_mask, struct ib_udata *udata); + struct ib_rwq_ind_table * (*create_rwq_ind_table)(struct ib_device *device, + struct ib_rwq_ind_table_init_attr *init_attr, + struct ib_udata *udata); + int (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table); struct ib_dma_mapping_ops *dma_ops; struct module *owner; @@ -3224,6 +3243,10 @@ struct ib_wq *ib_create_wq(struct ib_pd *pd, int ib_destroy_wq(struct ib_wq *wq); int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *attr, u32 wq_attr_mask); +struct ib_rwq_ind_table *ib_create_rwq_ind_table(struct ib_device *device, + struct ib_rwq_ind_table_init_attr* + wq_ind_table_init_attr); +int ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table); int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size); -- cgit v1.2.3 From a9017e232ff9eaabeb50eb89841d99310cfc98dc Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 23 May 2016 15:20:54 +0300 Subject: IB/core: Extend create QP to get indirection table Extend create QP to get Receive Work Queue (WQ) indirection table. QP can be created with external Receive Work Queue indirection table, in that case it is ready to receive immediately. Signed-off-by: Yishai Hadas Signed-off-by: Matan Barak Reviewed-by: Sagi Grimberg Signed-off-by: Doug Ledford --- drivers/infiniband/core/verbs.c | 19 +++++++++++++++++-- include/rdma/ib_verbs.h | 2 ++ 2 files changed, 19 insertions(+), 2 deletions(-) (limited to 'drivers/infiniband/core/verbs.c') diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 6b548d7f8753..6916d5c5920b 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -754,6 +754,12 @@ struct ib_qp *ib_create_qp(struct ib_pd *pd, struct ib_qp *qp; int ret; + if (qp_init_attr->rwq_ind_tbl && + (qp_init_attr->recv_cq || + qp_init_attr->srq || qp_init_attr->cap.max_recv_wr || + qp_init_attr->cap.max_recv_sge)) + return ERR_PTR(-EINVAL); + /* * If the callers is using the RDMA API calculate the resources * needed for the RDMA READ/WRITE operations. @@ -771,6 +777,7 @@ struct ib_qp *ib_create_qp(struct ib_pd *pd, qp->real_qp = qp; qp->uobject = NULL; qp->qp_type = qp_init_attr->qp_type; + qp->rwq_ind_tbl = qp_init_attr->rwq_ind_tbl; atomic_set(&qp->usecnt, 0); qp->mrs_used = 0; @@ -788,7 +795,8 @@ struct ib_qp *ib_create_qp(struct ib_pd *pd, qp->srq = NULL; } else { qp->recv_cq = qp_init_attr->recv_cq; - atomic_inc(&qp_init_attr->recv_cq->usecnt); + if (qp_init_attr->recv_cq) + atomic_inc(&qp_init_attr->recv_cq->usecnt); qp->srq = qp_init_attr->srq; if (qp->srq) atomic_inc(&qp_init_attr->srq->usecnt); @@ -799,7 +807,10 @@ struct ib_qp *ib_create_qp(struct ib_pd *pd, qp->xrcd = NULL; atomic_inc(&pd->usecnt); - atomic_inc(&qp_init_attr->send_cq->usecnt); + if (qp_init_attr->send_cq) + atomic_inc(&qp_init_attr->send_cq->usecnt); + if (qp_init_attr->rwq_ind_tbl) + atomic_inc(&qp->rwq_ind_tbl->usecnt); if (qp_init_attr->cap.max_rdma_ctxs) { ret = rdma_rw_init_mrs(qp, qp_init_attr); @@ -1279,6 +1290,7 @@ int ib_destroy_qp(struct ib_qp *qp) struct ib_pd *pd; struct ib_cq *scq, *rcq; struct ib_srq *srq; + struct ib_rwq_ind_table *ind_tbl; int ret; WARN_ON_ONCE(qp->mrs_used > 0); @@ -1293,6 +1305,7 @@ int ib_destroy_qp(struct ib_qp *qp) scq = qp->send_cq; rcq = qp->recv_cq; srq = qp->srq; + ind_tbl = qp->rwq_ind_tbl; if (!qp->uobject) rdma_rw_cleanup_mrs(qp); @@ -1307,6 +1320,8 @@ int ib_destroy_qp(struct ib_qp *qp) atomic_dec(&rcq->usecnt); if (srq) atomic_dec(&srq->usecnt); + if (ind_tbl) + atomic_dec(&ind_tbl->usecnt); } return ret; diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index e305c9a36663..9b2fafe5eb38 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1017,6 +1017,7 @@ struct ib_qp_init_attr { * Only needed for special QP types, or when using the RW API. */ u8 port_num; + struct ib_rwq_ind_table *rwq_ind_tbl; }; struct ib_qp_open_attr { @@ -1511,6 +1512,7 @@ struct ib_qp { void *qp_context; u32 qp_num; enum ib_qp_type qp_type; + struct ib_rwq_ind_table *rwq_ind_tbl; }; struct ib_mr { -- cgit v1.2.3