diff options
Diffstat (limited to 'drivers/infiniband/sw')
26 files changed, 1143 insertions, 349 deletions
diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c index 601d18dda1f5..34b7af6ab9c2 100644 --- a/drivers/infiniband/sw/rdmavt/mr.c +++ b/drivers/infiniband/sw/rdmavt/mr.c @@ -101,8 +101,8 @@ int rvt_driver_mr_init(struct rvt_dev_info *rdi) } /** - *rvt_mr_exit: clean up MR - *@rdi: rvt dev structure + * rvt_mr_exit - clean up MR + * @rdi: rvt dev structure * * called when drivers have unregistered or perhaps failed to register with us */ diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 9d13db68283c..e9f3d356b361 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -984,7 +984,8 @@ static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, spin_unlock_irq(&qp->r_lock); } -/** rvt_free_qpn - Free a qpn from the bit map +/** + * rvt_free_qpn - Free a qpn from the bit map * @qpt: QP table * @qpn: queue pair number to free */ diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c index 12ebe041a5da..ac17209816cd 100644 --- a/drivers/infiniband/sw/rdmavt/vt.c +++ b/drivers/infiniband/sw/rdmavt/vt.c @@ -144,7 +144,7 @@ static int rvt_modify_device(struct ib_device *device, } /** - * rvt_query_port: Passes the query port call to the driver + * rvt_query_port - Passes the query port call to the driver * @ibdev: Verbs IB dev * @port_num: port number, 1 based from ib core * @props: structure to hold returned properties @@ -175,7 +175,7 @@ static int rvt_query_port(struct ib_device *ibdev, u32 port_num, } /** - * rvt_modify_port + * rvt_modify_port - modify port * @ibdev: Verbs IB dev * @port_num: Port number, 1 based from ib core * @port_modify_mask: How to change the port @@ -418,7 +418,7 @@ static noinline int check_support(struct rvt_dev_info *rdi, int verb) * These functions are not part of verbs specifically but are * required for rdmavt to function. */ - if ((!rdi->ibdev.ops.init_port) || + if ((!rdi->ibdev.ops.port_groups) || (!rdi->driver_f.get_pci_dev)) return -EINVAL; break; diff --git a/drivers/infiniband/sw/rxe/Makefile b/drivers/infiniband/sw/rxe/Makefile index 66af72dca759..1e24673e9318 100644 --- a/drivers/infiniband/sw/rxe/Makefile +++ b/drivers/infiniband/sw/rxe/Makefile @@ -15,6 +15,7 @@ rdma_rxe-y := \ rxe_qp.o \ rxe_cq.o \ rxe_mr.o \ + rxe_mw.o \ rxe_opcode.o \ rxe_mmap.o \ rxe_icrc.o \ diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index 95f0de0c8b49..8e0f9c489cab 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -54,6 +54,7 @@ static void rxe_init_device_param(struct rxe_dev *rxe) rxe->attr.max_cq = RXE_MAX_CQ; rxe->attr.max_cqe = (1 << RXE_MAX_LOG_CQE) - 1; rxe->attr.max_mr = RXE_MAX_MR; + rxe->attr.max_mw = RXE_MAX_MW; rxe->attr.max_pd = RXE_MAX_PD; rxe->attr.max_qp_rd_atom = RXE_MAX_QP_RD_ATOM; rxe->attr.max_res_rd_atom = RXE_MAX_RES_RD_ATOM; diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index a6712e373eed..58ad9c2644f3 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -103,6 +103,7 @@ static enum ib_wc_opcode wr_to_wc_opcode(enum ib_wr_opcode opcode) case IB_WR_RDMA_READ_WITH_INV: return IB_WC_RDMA_READ; case IB_WR_LOCAL_INV: return IB_WC_LOCAL_INV; case IB_WR_REG_MR: return IB_WC_REG_MR; + case IB_WR_BIND_MW: return IB_WC_BIND_MW; default: return 0xff; @@ -141,7 +142,10 @@ static inline enum comp_state get_wqe(struct rxe_qp *qp, /* we come here whether or not we found a response packet to see if * there are any posted WQEs */ - wqe = queue_head(qp->sq.queue); + if (qp->is_user) + wqe = queue_head(qp->sq.queue, QUEUE_TYPE_FROM_USER); + else + wqe = queue_head(qp->sq.queue, QUEUE_TYPE_KERNEL); *wqe_p = wqe; /* no WQE or requester has not started it yet */ @@ -345,7 +349,7 @@ static inline enum comp_state do_read(struct rxe_qp *qp, ret = copy_data(qp->pd, IB_ACCESS_LOCAL_WRITE, &wqe->dma, payload_addr(pkt), - payload_size(pkt), to_mr_obj, NULL); + payload_size(pkt), RXE_TO_MR_OBJ, NULL); if (ret) { wqe->status = IB_WC_LOC_PROT_ERR; return COMPST_ERROR; @@ -367,7 +371,7 @@ static inline enum comp_state do_atomic(struct rxe_qp *qp, ret = copy_data(qp->pd, IB_ACCESS_LOCAL_WRITE, &wqe->dma, &atomic_orig, - sizeof(u64), to_mr_obj, NULL); + sizeof(u64), RXE_TO_MR_OBJ, NULL); if (ret) { wqe->status = IB_WC_LOC_PROT_ERR; return COMPST_ERROR; @@ -418,16 +422,23 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe) { struct rxe_dev *rxe = to_rdev(qp->ibqp.device); struct rxe_cqe cqe; + bool post; + + /* do we need to post a completion */ + post = ((qp->sq_sig_type == IB_SIGNAL_ALL_WR) || + (wqe->wr.send_flags & IB_SEND_SIGNALED) || + wqe->status != IB_WC_SUCCESS); - if ((qp->sq_sig_type == IB_SIGNAL_ALL_WR) || - (wqe->wr.send_flags & IB_SEND_SIGNALED) || - wqe->status != IB_WC_SUCCESS) { + if (post) make_send_cqe(qp, wqe, &cqe); - advance_consumer(qp->sq.queue); + + if (qp->is_user) + advance_consumer(qp->sq.queue, QUEUE_TYPE_FROM_USER); + else + advance_consumer(qp->sq.queue, QUEUE_TYPE_KERNEL); + + if (post) rxe_cq_post(qp->scq, &cqe, 0); - } else { - advance_consumer(qp->sq.queue); - } if (wqe->wr.opcode == IB_WR_SEND || wqe->wr.opcode == IB_WR_SEND_WITH_IMM || @@ -515,6 +526,7 @@ static void rxe_drain_resp_pkts(struct rxe_qp *qp, bool notify) { struct sk_buff *skb; struct rxe_send_wqe *wqe; + struct rxe_queue *q = qp->sq.queue; while ((skb = skb_dequeue(&qp->resp_pkts))) { rxe_drop_ref(qp); @@ -522,12 +534,12 @@ static void rxe_drain_resp_pkts(struct rxe_qp *qp, bool notify) ib_device_put(qp->ibqp.device); } - while ((wqe = queue_head(qp->sq.queue))) { + while ((wqe = queue_head(q, q->type))) { if (notify) { wqe->status = IB_WC_WR_FLUSH_ERR; do_complete(qp, wqe); } else { - advance_consumer(qp->sq.queue); + advance_consumer(q, q->type); } } } diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c index b315ebf041ac..aef288f164fd 100644 --- a/drivers/infiniband/sw/rxe/rxe_cq.c +++ b/drivers/infiniband/sw/rxe/rxe_cq.c @@ -25,7 +25,11 @@ int rxe_cq_chk_attr(struct rxe_dev *rxe, struct rxe_cq *cq, } if (cq) { - count = queue_count(cq->queue); + if (cq->is_user) + count = queue_count(cq->queue, QUEUE_TYPE_TO_USER); + else + count = queue_count(cq->queue, QUEUE_TYPE_KERNEL); + if (cqe < count) { pr_warn("cqe(%d) < current # elements in queue (%d)", cqe, count); @@ -59,9 +63,11 @@ int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe, struct rxe_create_cq_resp __user *uresp) { int err; + enum queue_type type; + type = uresp ? QUEUE_TYPE_TO_USER : QUEUE_TYPE_KERNEL; cq->queue = rxe_queue_init(rxe, &cqe, - sizeof(struct rxe_cqe)); + sizeof(struct rxe_cqe), type); if (!cq->queue) { pr_warn("unable to create cq\n"); return -ENOMEM; @@ -106,10 +112,17 @@ int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited) { struct ib_event ev; unsigned long flags; + int full; + void *addr; spin_lock_irqsave(&cq->cq_lock, flags); - if (unlikely(queue_full(cq->queue))) { + if (cq->is_user) + full = queue_full(cq->queue, QUEUE_TYPE_TO_USER); + else + full = queue_full(cq->queue, QUEUE_TYPE_KERNEL); + + if (unlikely(full)) { spin_unlock_irqrestore(&cq->cq_lock, flags); if (cq->ibcq.event_handler) { ev.device = cq->ibcq.device; @@ -121,9 +134,18 @@ int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited) return -EBUSY; } - memcpy(producer_addr(cq->queue), cqe, sizeof(*cqe)); + if (cq->is_user) + addr = producer_addr(cq->queue, QUEUE_TYPE_TO_USER); + else + addr = producer_addr(cq->queue, QUEUE_TYPE_KERNEL); + + memcpy(addr, cqe, sizeof(*cqe)); + + if (cq->is_user) + advance_producer(cq->queue, QUEUE_TYPE_TO_USER); + else + advance_producer(cq->queue, QUEUE_TYPE_KERNEL); - advance_producer(cq->queue); spin_unlock_irqrestore(&cq->cq_lock, flags); if ((cq->notify == IB_CQ_NEXT_COMP) || diff --git a/drivers/infiniband/sw/rxe/rxe_hw_counters.c b/drivers/infiniband/sw/rxe/rxe_hw_counters.c index f469fd1c753d..d5ceb706d964 100644 --- a/drivers/infiniband/sw/rxe/rxe_hw_counters.c +++ b/drivers/infiniband/sw/rxe/rxe_hw_counters.c @@ -40,13 +40,10 @@ int rxe_ib_get_hw_stats(struct ib_device *ibdev, return ARRAY_SIZE(rxe_counter_name); } -struct rdma_hw_stats *rxe_ib_alloc_hw_stats(struct ib_device *ibdev, - u32 port_num) +struct rdma_hw_stats *rxe_ib_alloc_hw_port_stats(struct ib_device *ibdev, + u32 port_num) { BUILD_BUG_ON(ARRAY_SIZE(rxe_counter_name) != RXE_NUM_OF_COUNTERS); - /* We support only per port stats */ - if (!port_num) - return NULL; return rdma_alloc_hw_stats_struct(rxe_counter_name, ARRAY_SIZE(rxe_counter_name), diff --git a/drivers/infiniband/sw/rxe/rxe_hw_counters.h b/drivers/infiniband/sw/rxe/rxe_hw_counters.h index 2f369acb46d7..71f4d4fa9dc8 100644 --- a/drivers/infiniband/sw/rxe/rxe_hw_counters.h +++ b/drivers/infiniband/sw/rxe/rxe_hw_counters.h @@ -29,8 +29,8 @@ enum rxe_counters { RXE_NUM_OF_COUNTERS }; -struct rdma_hw_stats *rxe_ib_alloc_hw_stats(struct ib_device *ibdev, - u32 port_num); +struct rdma_hw_stats *rxe_ib_alloc_hw_port_stats(struct ib_device *ibdev, + u32 port_num); int rxe_ib_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats, u32 port, int index); diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h index ef8061d2fbe0..1ddb20855dee 100644 --- a/drivers/infiniband/sw/rxe/rxe_loc.h +++ b/drivers/infiniband/sw/rxe/rxe_loc.h @@ -71,40 +71,32 @@ struct rxe_mmap_info *rxe_create_mmap_info(struct rxe_dev *dev, u32 size, int rxe_mmap(struct ib_ucontext *context, struct vm_area_struct *vma); /* rxe_mr.c */ -enum copy_direction { - to_mr_obj, - from_mr_obj, -}; - +u8 rxe_get_next_key(u32 last_key); void rxe_mr_init_dma(struct rxe_pd *pd, int access, struct rxe_mr *mr); - int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova, - int access, struct ib_udata *udata, struct rxe_mr *mr); - + int access, struct rxe_mr *mr); int rxe_mr_init_fast(struct rxe_pd *pd, int max_pages, struct rxe_mr *mr); - int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length, - enum copy_direction dir, u32 *crcp); - + enum rxe_mr_copy_dir dir, u32 *crcp); int copy_data(struct rxe_pd *pd, int access, struct rxe_dma_info *dma, void *addr, int length, - enum copy_direction dir, u32 *crcp); - + enum rxe_mr_copy_dir dir, u32 *crcp); void *iova_to_vaddr(struct rxe_mr *mr, u64 iova, int length); - -enum lookup_type { - lookup_local, - lookup_remote, -}; - struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key, - enum lookup_type type); - + enum rxe_mr_lookup_type type); int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length); - +int advance_dma_data(struct rxe_dma_info *dma, unsigned int length); +int rxe_invalidate_mr(struct rxe_qp *qp, u32 rkey); +int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata); void rxe_mr_cleanup(struct rxe_pool_entry *arg); -int advance_dma_data(struct rxe_dma_info *dma, unsigned int length); +/* rxe_mw.c */ +int rxe_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata); +int rxe_dealloc_mw(struct ib_mw *ibmw); +int rxe_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe); +int rxe_invalidate_mw(struct rxe_qp *qp, u32 rkey); +struct rxe_mw *rxe_lookup_mw(struct rxe_qp *qp, int access, u32 rkey); +void rxe_mw_cleanup(struct rxe_pool_entry *arg); /* rxe_net.c */ void rxe_loopback(struct sk_buff *skb); diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c index 9f63947bab12..6aabcb4de235 100644 --- a/drivers/infiniband/sw/rxe/rxe_mr.c +++ b/drivers/infiniband/sw/rxe/rxe_mr.c @@ -7,19 +7,17 @@ #include "rxe.h" #include "rxe_loc.h" -/* - * lfsr (linear feedback shift register) with period 255 +/* Return a random 8 bit key value that is + * different than the last_key. Set last_key to -1 + * if this is the first key for an MR or MW */ -static u8 rxe_get_key(void) +u8 rxe_get_next_key(u32 last_key) { - static u32 key = 1; - - key = key << 1; + u8 key; - key |= (0 != (key & 0x100)) ^ (0 != (key & 0x10)) - ^ (0 != (key & 0x80)) ^ (0 != (key & 0x40)); - - key &= 0xff; + do { + get_random_bytes(&key, 1); + } while (key == last_key); return key; } @@ -47,7 +45,7 @@ int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length) static void rxe_mr_init(int access, struct rxe_mr *mr) { - u32 lkey = mr->pelem.index << 8 | rxe_get_key(); + u32 lkey = mr->pelem.index << 8 | rxe_get_next_key(-1); u32 rkey = (access & IB_ACCESS_REMOTE) ? lkey : 0; mr->ibmr.lkey = lkey; @@ -57,21 +55,6 @@ static void rxe_mr_init(int access, struct rxe_mr *mr) mr->map_shift = ilog2(RXE_BUF_PER_MAP); } -void rxe_mr_cleanup(struct rxe_pool_entry *arg) -{ - struct rxe_mr *mr = container_of(arg, typeof(*mr), pelem); - int i; - - ib_umem_release(mr->umem); - - if (mr->map) { - for (i = 0; i < mr->num_map; i++) - kfree(mr->map[i]); - - kfree(mr->map); - } -} - static int rxe_mr_alloc(struct rxe_mr *mr, int num_buf) { int i; @@ -121,7 +104,7 @@ void rxe_mr_init_dma(struct rxe_pd *pd, int access, struct rxe_mr *mr) } int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova, - int access, struct ib_udata *udata, struct rxe_mr *mr) + int access, struct rxe_mr *mr) { struct rxe_map **map; struct rxe_phys_buf *buf = NULL; @@ -135,7 +118,7 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova, if (IS_ERR(umem)) { pr_warn("err %d from rxe_umem_get\n", (int)PTR_ERR(umem)); - err = -EINVAL; + err = PTR_ERR(umem); goto err1; } @@ -300,7 +283,7 @@ out: * crc32 if crcp is not zero. caller must hold a reference to mr */ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length, - enum copy_direction dir, u32 *crcp) + enum rxe_mr_copy_dir dir, u32 *crcp) { int err; int bytes; @@ -318,9 +301,9 @@ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length, if (mr->type == RXE_MR_TYPE_DMA) { u8 *src, *dest; - src = (dir == to_mr_obj) ? addr : ((void *)(uintptr_t)iova); + src = (dir == RXE_TO_MR_OBJ) ? addr : ((void *)(uintptr_t)iova); - dest = (dir == to_mr_obj) ? ((void *)(uintptr_t)iova) : addr; + dest = (dir == RXE_TO_MR_OBJ) ? ((void *)(uintptr_t)iova) : addr; memcpy(dest, src, length); @@ -348,8 +331,8 @@ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length, u8 *src, *dest; va = (u8 *)(uintptr_t)buf->addr + offset; - src = (dir == to_mr_obj) ? addr : va; - dest = (dir == to_mr_obj) ? va : addr; + src = (dir == RXE_TO_MR_OBJ) ? addr : va; + dest = (dir == RXE_TO_MR_OBJ) ? va : addr; bytes = buf->size - offset; @@ -394,7 +377,7 @@ int copy_data( struct rxe_dma_info *dma, void *addr, int length, - enum copy_direction dir, + enum rxe_mr_copy_dir dir, u32 *crcp) { int bytes; @@ -414,7 +397,7 @@ int copy_data( } if (sge->length && (offset < sge->length)) { - mr = lookup_mr(pd, access, sge->lkey, lookup_local); + mr = lookup_mr(pd, access, sge->lkey, RXE_LOOKUP_LOCAL); if (!mr) { err = -EINVAL; goto err1; @@ -440,7 +423,7 @@ int copy_data( if (sge->length) { mr = lookup_mr(pd, access, sge->lkey, - lookup_local); + RXE_LOOKUP_LOCAL); if (!mr) { err = -EINVAL; goto err1; @@ -522,7 +505,7 @@ int advance_dma_data(struct rxe_dma_info *dma, unsigned int length) * (4) verify that mr state is valid */ struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key, - enum lookup_type type) + enum rxe_mr_lookup_type type) { struct rxe_mr *mr; struct rxe_dev *rxe = to_rdev(pd->ibpd.device); @@ -532,8 +515,8 @@ struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key, if (!mr) return NULL; - if (unlikely((type == lookup_local && mr_lkey(mr) != key) || - (type == lookup_remote && mr_rkey(mr) != key) || + if (unlikely((type == RXE_LOOKUP_LOCAL && mr_lkey(mr) != key) || + (type == RXE_LOOKUP_REMOTE && mr_rkey(mr) != key) || mr_pd(mr) != pd || (access && !(access & mr->access)) || mr->state != RXE_MR_STATE_VALID)) { rxe_drop_ref(mr); @@ -542,3 +525,72 @@ struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key, return mr; } + +int rxe_invalidate_mr(struct rxe_qp *qp, u32 rkey) +{ + struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + struct rxe_mr *mr; + int ret; + + mr = rxe_pool_get_index(&rxe->mr_pool, rkey >> 8); + if (!mr) { + pr_err("%s: No MR for rkey %#x\n", __func__, rkey); + ret = -EINVAL; + goto err; + } + + if (rkey != mr->ibmr.rkey) { + pr_err("%s: rkey (%#x) doesn't match mr->ibmr.rkey (%#x)\n", + __func__, rkey, mr->ibmr.rkey); + ret = -EINVAL; + goto err_drop_ref; + } + + if (atomic_read(&mr->num_mw) > 0) { + pr_warn("%s: Attempt to invalidate an MR while bound to MWs\n", + __func__); + ret = -EINVAL; + goto err_drop_ref; + } + + mr->state = RXE_MR_STATE_FREE; + ret = 0; + +err_drop_ref: + rxe_drop_ref(mr); +err: + return ret; +} + +int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata) +{ + struct rxe_mr *mr = to_rmr(ibmr); + + if (atomic_read(&mr->num_mw) > 0) { + pr_warn("%s: Attempt to deregister an MR while bound to MWs\n", + __func__); + return -EINVAL; + } + + mr->state = RXE_MR_STATE_ZOMBIE; + rxe_drop_ref(mr_pd(mr)); + rxe_drop_index(mr); + rxe_drop_ref(mr); + + return 0; +} + +void rxe_mr_cleanup(struct rxe_pool_entry *arg) +{ + struct rxe_mr *mr = container_of(arg, typeof(*mr), pelem); + int i; + + ib_umem_release(mr->umem); + + if (mr->map) { + for (i = 0; i < mr->num_map; i++) + kfree(mr->map[i]); + + kfree(mr->map); + } +} diff --git a/drivers/infiniband/sw/rxe/rxe_mw.c b/drivers/infiniband/sw/rxe/rxe_mw.c new file mode 100644 index 000000000000..5ba77df7598e --- /dev/null +++ b/drivers/infiniband/sw/rxe/rxe_mw.c @@ -0,0 +1,343 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* + * Copyright (c) 2020 Hewlett Packard Enterprise, Inc. All rights reserved. + */ + +#include "rxe.h" + +int rxe_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata) +{ + struct rxe_mw *mw = to_rmw(ibmw); + struct rxe_pd *pd = to_rpd(ibmw->pd); + struct rxe_dev *rxe = to_rdev(ibmw->device); + int ret; + + rxe_add_ref(pd); + + ret = rxe_add_to_pool(&rxe->mw_pool, mw); + if (ret) { + rxe_drop_ref(pd); + return ret; + } + + rxe_add_index(mw); + ibmw->rkey = (mw->pelem.index << 8) | rxe_get_next_key(-1); + mw->state = (mw->ibmw.type == IB_MW_TYPE_2) ? + RXE_MW_STATE_FREE : RXE_MW_STATE_VALID; + spin_lock_init(&mw->lock); + + return 0; +} + +static void rxe_do_dealloc_mw(struct rxe_mw *mw) +{ + if (mw->mr) { + struct rxe_mr *mr = mw->mr; + + mw->mr = NULL; + atomic_dec(&mr->num_mw); + rxe_drop_ref(mr); + } + + if (mw->qp) { + struct rxe_qp *qp = mw->qp; + + mw->qp = NULL; + rxe_drop_ref(qp); + } + + mw->access = 0; + mw->addr = 0; + mw->length = 0; + mw->state = RXE_MW_STATE_INVALID; +} + +int rxe_dealloc_mw(struct ib_mw *ibmw) +{ + struct rxe_mw *mw = to_rmw(ibmw); + struct rxe_pd *pd = to_rpd(ibmw->pd); + unsigned long flags; + + spin_lock_irqsave(&mw->lock, flags); + rxe_do_dealloc_mw(mw); + spin_unlock_irqrestore(&mw->lock, flags); + + rxe_drop_ref(mw); + rxe_drop_ref(pd); + + return 0; +} + +static int rxe_check_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe, + struct rxe_mw *mw, struct rxe_mr *mr) +{ + if (mw->ibmw.type == IB_MW_TYPE_1) { + if (unlikely(mw->state != RXE_MW_STATE_VALID)) { + pr_err_once( + "attempt to bind a type 1 MW not in the valid state\n"); + return -EINVAL; + } + + /* o10-36.2.2 */ + if (unlikely((mw->access & IB_ZERO_BASED))) { + pr_err_once("attempt to bind a zero based type 1 MW\n"); + return -EINVAL; + } + } + + if (mw->ibmw.type == IB_MW_TYPE_2) { + /* o10-37.2.30 */ + if (unlikely(mw->state != RXE_MW_STATE_FREE)) { + pr_err_once( + "attempt to bind a type 2 MW not in the free state\n"); + return -EINVAL; + } + + /* C10-72 */ + if (unlikely(qp->pd != to_rpd(mw->ibmw.pd))) { + pr_err_once( + "attempt to bind type 2 MW with qp with different PD\n"); + return -EINVAL; + } + + /* o10-37.2.40 */ + if (unlikely(!mr || wqe->wr.wr.mw.length == 0)) { + pr_err_once( + "attempt to invalidate type 2 MW by binding with NULL or zero length MR\n"); + return -EINVAL; + } + } + + if (unlikely((wqe->wr.wr.mw.rkey & 0xff) == (mw->ibmw.rkey & 0xff))) { + pr_err_once("attempt to bind MW with same key\n"); + return -EINVAL; + } + + /* remaining checks only apply to a nonzero MR */ + if (!mr) + return 0; + + if (unlikely(mr->access & IB_ZERO_BASED)) { + pr_err_once("attempt to bind MW to zero based MR\n"); + return -EINVAL; + } + + /* C10-73 */ + if (unlikely(!(mr->access & IB_ACCESS_MW_BIND))) { + pr_err_once( + "attempt to bind an MW to an MR without bind access\n"); + return -EINVAL; + } + + /* C10-74 */ + if (unlikely((mw->access & + (IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_ATOMIC)) && + !(mr->access & IB_ACCESS_LOCAL_WRITE))) { + pr_err_once( + "attempt to bind an writeable MW to an MR without local write access\n"); + return -EINVAL; + } + + /* C10-75 */ + if (mw->access & IB_ZERO_BASED) { + if (unlikely(wqe->wr.wr.mw.length > mr->length)) { + pr_err_once( + "attempt to bind a ZB MW outside of the MR\n"); + return -EINVAL; + } + } else { + if (unlikely((wqe->wr.wr.mw.addr < mr->iova) || + ((wqe->wr.wr.mw.addr + wqe->wr.wr.mw.length) > + (mr->iova + mr->length)))) { + pr_err_once( + "attempt to bind a VA MW outside of the MR\n"); + return -EINVAL; + } + } + + return 0; +} + +static void rxe_do_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe, + struct rxe_mw *mw, struct rxe_mr *mr) +{ + u32 rkey; + u32 new_rkey; + + rkey = mw->ibmw.rkey; + new_rkey = (rkey & 0xffffff00) | (wqe->wr.wr.mw.rkey & 0x000000ff); + + mw->ibmw.rkey = new_rkey; + mw->access = wqe->wr.wr.mw.access; + mw->state = RXE_MW_STATE_VALID; + mw->addr = wqe->wr.wr.mw.addr; + mw->length = wqe->wr.wr.mw.length; + + if (mw->mr) { + rxe_drop_ref(mw->mr); + atomic_dec(&mw->mr->num_mw); + mw->mr = NULL; + } + + if (mw->length) { + mw->mr = mr; + atomic_inc(&mr->num_mw); + rxe_add_ref(mr); + } + + if (mw->ibmw.type == IB_MW_TYPE_2) { + rxe_add_ref(qp); + mw->qp = qp; + } +} + +int rxe_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe) +{ + int ret; + struct rxe_mw *mw; + struct rxe_mr *mr; + struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + unsigned long flags; + + mw = rxe_pool_get_index(&rxe->mw_pool, + wqe->wr.wr.mw.mw_rkey >> 8); + if (unlikely(!mw)) { + ret = -EINVAL; + goto err; + } + + if (unlikely(mw->ibmw.rkey != wqe->wr.wr.mw.mw_rkey)) { + ret = -EINVAL; + goto err_drop_mw; + } + + if (likely(wqe->wr.wr.mw.length)) { + mr = rxe_pool_get_index(&rxe->mr_pool, + wqe->wr.wr.mw.mr_lkey >> 8); + if (unlikely(!mr)) { + ret = -EINVAL; + goto err_drop_mw; + } + + if (unlikely(mr->ibmr.lkey != wqe->wr.wr.mw.mr_lkey)) { + ret = -EINVAL; + goto err_drop_mr; + } + } else { + mr = NULL; + } + + spin_lock_irqsave(&mw->lock, flags); + + ret = rxe_check_bind_mw(qp, wqe, mw, mr); + if (ret) + goto err_unlock; + + rxe_do_bind_mw(qp, wqe, mw, mr); +err_unlock: + spin_unlock_irqrestore(&mw->lock, flags); +err_drop_mr: + if (mr) + rxe_drop_ref(mr); +err_drop_mw: + rxe_drop_ref(mw); +err: + return ret; +} + +static int rxe_check_invalidate_mw(struct rxe_qp *qp, struct rxe_mw *mw) +{ + if (unlikely(mw->state == RXE_MW_STATE_INVALID)) + return -EINVAL; + + /* o10-37.2.26 */ + if (unlikely(mw->ibmw.type == IB_MW_TYPE_1)) + return -EINVAL; + + return 0; +} + +static void rxe_do_invalidate_mw(struct rxe_mw *mw) +{ + struct rxe_qp *qp; + struct rxe_mr *mr; + + /* valid type 2 MW will always have a QP pointer */ + qp = mw->qp; + mw->qp = NULL; + rxe_drop_ref(qp); + + /* valid type 2 MW will always have an MR pointer */ + mr = mw->mr; + mw->mr = NULL; + atomic_dec(&mr->num_mw); + rxe_drop_ref(mr); + + mw->access = 0; + mw->addr = 0; + mw->length = 0; + mw->state = RXE_MW_STATE_FREE; +} + +int rxe_invalidate_mw(struct rxe_qp *qp, u32 rkey) +{ + struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + unsigned long flags; + struct rxe_mw *mw; + int ret; + + mw = rxe_pool_get_index(&rxe->mw_pool, rkey >> 8); + if (!mw) { + ret = -EINVAL; + goto err; + } + + if (rkey != mw->ibmw.rkey) { + ret = -EINVAL; + goto err_drop_ref; + } + + spin_lock_irqsave(&mw->lock, flags); + + ret = rxe_check_invalidate_mw(qp, mw); + if (ret) + goto err_unlock; + + rxe_do_invalidate_mw(mw); +err_unlock: + spin_unlock_irqrestore(&mw->lock, flags); +err_drop_ref: + rxe_drop_ref(mw); +err: + return ret; +} + +struct rxe_mw *rxe_lookup_mw(struct rxe_qp *qp, int access, u32 rkey) +{ + struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + struct rxe_pd *pd = to_rpd(qp->ibqp.pd); + struct rxe_mw *mw; + int index = rkey >> 8; + + mw = rxe_pool_get_index(&rxe->mw_pool, index); + if (!mw) + return NULL; + + if (unlikely((rxe_mw_rkey(mw) != rkey) || rxe_mw_pd(mw) != pd || + (mw->ibmw.type == IB_MW_TYPE_2 && mw->qp != qp) || + (mw->length == 0) || + (access && !(access & mw->access)) || + mw->state != RXE_MW_STATE_VALID)) { + rxe_drop_ref(mw); + return NULL; + } + + return mw; +} + +void rxe_mw_cleanup(struct rxe_pool_entry *elem) +{ + struct rxe_mw *mw = container_of(elem, typeof(*mw), pelem); + + rxe_drop_index(mw); +} diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 01662727dca0..fc1ba4904279 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -207,10 +207,8 @@ static struct socket *rxe_setup_udp_tunnel(struct net *net, __be16 port, /* Create UDP socket */ err = udp_sock_create(net, &udp_cfg, &sock); - if (err < 0) { - pr_err("failed to create udp socket. err = %d\n", err); + if (err < 0) return ERR_PTR(err); - } tnl_cfg.encap_type = 1; tnl_cfg.encap_rcv = rxe_udp_encap_recv; @@ -619,6 +617,12 @@ static int rxe_net_ipv6_init(void) recv_sockets.sk6 = rxe_setup_udp_tunnel(&init_net, htons(ROCE_V2_UDP_DPORT), true); + if (PTR_ERR(recv_sockets.sk6) == -EAFNOSUPPORT) { + recv_sockets.sk6 = NULL; + pr_warn("IPv6 is not supported, can not create a UDPv6 socket\n"); + return 0; + } + if (IS_ERR(recv_sockets.sk6)) { recv_sockets.sk6 = NULL; pr_err("Failed to create IPv6 UDP tunnel\n"); diff --git a/drivers/infiniband/sw/rxe/rxe_opcode.c b/drivers/infiniband/sw/rxe/rxe_opcode.c index 0cb4b01fd910..3ef5a10a6efd 100644 --- a/drivers/infiniband/sw/rxe/rxe_opcode.c +++ b/drivers/infiniband/sw/rxe/rxe_opcode.c @@ -87,13 +87,20 @@ struct rxe_wr_opcode_info rxe_wr_opcode_info[] = { [IB_WR_LOCAL_INV] = { .name = "IB_WR_LOCAL_INV", .mask = { - [IB_QPT_RC] = WR_REG_MASK, + [IB_QPT_RC] = WR_LOCAL_OP_MASK, }, }, [IB_WR_REG_MR] = { .name = "IB_WR_REG_MR", .mask = { - [IB_QPT_RC] = WR_REG_MASK, + [IB_QPT_RC] = WR_LOCAL_OP_MASK, + }, + }, + [IB_WR_BIND_MW] = { + .name = "IB_WR_BIND_MW", + .mask = { + [IB_QPT_RC] = WR_LOCAL_OP_MASK, + [IB_QPT_UC] = WR_LOCAL_OP_MASK, }, }, }; diff --git a/drivers/infiniband/sw/rxe/rxe_opcode.h b/drivers/infiniband/sw/rxe/rxe_opcode.h index 1041ac9a9233..e02f039b8c44 100644 --- a/drivers/infiniband/sw/rxe/rxe_opcode.h +++ b/drivers/infiniband/sw/rxe/rxe_opcode.h @@ -19,8 +19,7 @@ enum rxe_wr_mask { WR_SEND_MASK = BIT(2), WR_READ_MASK = BIT(3), WR_WRITE_MASK = BIT(4), - WR_LOCAL_MASK = BIT(5), - WR_REG_MASK = BIT(6), + WR_LOCAL_OP_MASK = BIT(5), WR_READ_OR_WRITE_MASK = WR_READ_MASK | WR_WRITE_MASK, WR_READ_WRITE_OR_SEND_MASK = WR_READ_OR_WRITE_MASK | WR_SEND_MASK, diff --git a/drivers/infiniband/sw/rxe/rxe_param.h b/drivers/infiniband/sw/rxe/rxe_param.h index 25ab50d9b7c2..742e6ec93686 100644 --- a/drivers/infiniband/sw/rxe/rxe_param.h +++ b/drivers/infiniband/sw/rxe/rxe_param.h @@ -37,7 +37,6 @@ static inline enum ib_mtu eth_mtu_int_to_enum(int mtu) enum rxe_device_param { RXE_MAX_MR_SIZE = -1ull, RXE_PAGE_SIZE_CAP = 0xfffff000, - RXE_MAX_QP = 0x10000, RXE_MAX_QP_WR = 0x4000, RXE_DEVICE_CAP_FLAGS = IB_DEVICE_BAD_PKEY_CNTR | IB_DEVICE_BAD_QKEY_CNTR @@ -49,7 +48,10 @@ enum rxe_device_param { | IB_DEVICE_RC_RNR_NAK_GEN | IB_DEVICE_SRQ_RESIZE | IB_DEVICE_MEM_MGT_EXTENSIONS - | IB_DEVICE_ALLOW_USER_UNREG, + | IB_DEVICE_ALLOW_USER_UNREG + | IB_DEVICE_MEM_WINDOW + | IB_DEVICE_MEM_WINDOW_TYPE_2A + | IB_DEVICE_MEM_WINDOW_TYPE_2B, RXE_MAX_SGE = 32, RXE_MAX_WQE_SIZE = sizeof(struct rxe_send_wqe) + sizeof(struct ib_sge) * RXE_MAX_SGE, @@ -58,7 +60,6 @@ enum rxe_device_param { RXE_MAX_SGE_RD = 32, RXE_MAX_CQ = 16384, RXE_MAX_LOG_CQE = 15, - RXE_MAX_MR = 256 * 1024, RXE_MAX_PD = 0x7ffc, RXE_MAX_QP_RD_ATOM = 128, RXE_MAX_RES_RD_ATOM = 0x3f000, @@ -67,7 +68,6 @@ enum rxe_device_param { RXE_MAX_MCAST_QP_ATTACH = 56, RXE_MAX_TOT_MCAST_QP_ATTACH = 0x70000, RXE_MAX_AH = 100, - RXE_MAX_SRQ = 960, RXE_MAX_SRQ_WR = 0x4000, RXE_MIN_SRQ_WR = 1, RXE_MAX_SRQ_SGE = 27, @@ -80,16 +80,21 @@ enum rxe_device_param { RXE_NUM_PORT = 1, + RXE_MAX_QP = 0x10000, RXE_MIN_QP_INDEX = 16, RXE_MAX_QP_INDEX = 0x00020000, + RXE_MAX_SRQ = 0x00001000, RXE_MIN_SRQ_INDEX = 0x00020001, RXE_MAX_SRQ_INDEX = 0x00040000, + RXE_MAX_MR = 0x00001000, + RXE_MAX_MW = 0x00001000, RXE_MIN_MR_INDEX = 0x00000001, - RXE_MAX_MR_INDEX = 0x00040000, - RXE_MIN_MW_INDEX = 0x00040001, - RXE_MAX_MW_INDEX = 0x00060000, + RXE_MAX_MR_INDEX = 0x00010000, + RXE_MIN_MW_INDEX = 0x00010001, + RXE_MAX_MW_INDEX = 0x00020000, + RXE_MAX_PKT_PER_ACK = 64, RXE_MAX_UNACKED_PSNS = 128, diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c index d24901f2af3f..0b8e7c6255a2 100644 --- a/drivers/infiniband/sw/rxe/rxe_pool.c +++ b/drivers/infiniband/sw/rxe/rxe_pool.c @@ -65,6 +65,7 @@ struct rxe_type_info rxe_type_info[RXE_NUM_TYPES] = { .name = "rxe-mw", .size = sizeof(struct rxe_mw), .elem_offset = offsetof(struct rxe_mw, pelem), + .cleanup = rxe_mw_cleanup, .flags = RXE_POOL_INDEX | RXE_POOL_NO_ALLOC, .max_index = RXE_MAX_MW_INDEX, .min_index = RXE_MIN_MW_INDEX, @@ -183,7 +184,7 @@ static u32 alloc_index(struct rxe_pool *pool) return index + pool->index.min_index; } -static void insert_index(struct rxe_pool *pool, struct rxe_pool_entry *new) +static int rxe_insert_index(struct rxe_pool *pool, struct rxe_pool_entry *new) { struct rb_node **link = &pool->index.tree.rb_node; struct rb_node *parent = NULL; @@ -195,7 +196,7 @@ static void insert_index(struct rxe_pool *pool, struct rxe_pool_entry *new) if (elem->index == new->index) { pr_warn("element already exists!\n"); - goto out; + return -EINVAL; } if (elem->index > new->index) @@ -206,11 +207,11 @@ static void insert_index(struct rxe_pool *pool, struct rxe_pool_entry *new) rb_link_node(&new->index_node, parent, link); rb_insert_color(&new->index_node, &pool->index.tree); -out: - return; + + return 0; } -static void insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new) +static int rxe_insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new) { struct rb_node **link = &pool->key.tree.rb_node; struct rb_node *parent = NULL; @@ -226,7 +227,7 @@ static void insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new) if (cmp == 0) { pr_warn("key already exists!\n"); - goto out; + return -EINVAL; } if (cmp > 0) @@ -237,26 +238,32 @@ static void insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new) rb_link_node(&new->key_node, parent, link); rb_insert_color(&new->key_node, &pool->key.tree); -out: - return; + + return 0; } -void __rxe_add_key_locked(struct rxe_pool_entry *elem, void *key) +int __rxe_add_key_locked(struct rxe_pool_entry *elem, void *key) { struct rxe_pool *pool = elem->pool; + int err; memcpy((u8 *)elem + pool->key.key_offset, key, pool->key.key_size); - insert_key(pool, elem); + err = rxe_insert_key(pool, elem); + + return err; } -void __rxe_add_key(struct rxe_pool_entry *elem, void *key) +int __rxe_add_key(struct rxe_pool_entry *elem, void *key) { struct rxe_pool *pool = elem->pool; unsigned long flags; + int err; write_lock_irqsave(&pool->pool_lock, flags); - __rxe_add_key_locked(elem, key); + err = __rxe_add_key_locked(elem, key); write_unlock_irqrestore(&pool->pool_lock, flags); + + return err; } void __rxe_drop_key_locked(struct rxe_pool_entry *elem) @@ -276,22 +283,28 @@ void __rxe_drop_key(struct rxe_pool_entry *elem) write_unlock_irqrestore(&pool->pool_lock, flags); } -void __rxe_add_index_locked(struct rxe_pool_entry *elem) +int __rxe_add_index_locked(struct rxe_pool_entry *elem) { struct rxe_pool *pool = elem->pool; + int err; elem->index = alloc_index(pool); - insert_index(pool, elem); + err = rxe_insert_index(pool, elem); + + return err; } -void __rxe_add_index(struct rxe_pool_entry *elem) +int __rxe_add_index(struct rxe_pool_entry *elem) { struct rxe_pool *pool = elem->pool; unsigned long flags; + int err; write_lock_irqsave(&pool->pool_lock, flags); - __rxe_add_index_locked(elem); + err = __rxe_add_index_locked(elem); write_unlock_irqrestore(&pool->pool_lock, flags); + + return err; } void __rxe_drop_index_locked(struct rxe_pool_entry *elem) diff --git a/drivers/infiniband/sw/rxe/rxe_pool.h b/drivers/infiniband/sw/rxe/rxe_pool.h index 61210b300a78..1feca1bffced 100644 --- a/drivers/infiniband/sw/rxe/rxe_pool.h +++ b/drivers/infiniband/sw/rxe/rxe_pool.h @@ -111,11 +111,11 @@ int __rxe_add_to_pool(struct rxe_pool *pool, struct rxe_pool_entry *elem); /* assign an index to an indexed object and insert object into * pool's rb tree holding and not holding the pool_lock */ -void __rxe_add_index_locked(struct rxe_pool_entry *elem); +int __rxe_add_index_locked(struct rxe_pool_entry *elem); #define rxe_add_index_locked(obj) __rxe_add_index_locked(&(obj)->pelem) -void __rxe_add_index(struct rxe_pool_entry *elem); +int __rxe_add_index(struct rxe_pool_entry *elem); #define rxe_add_index(obj) __rxe_add_index(&(obj)->pelem) @@ -133,11 +133,11 @@ void __rxe_drop_index(struct rxe_pool_entry *elem); /* assign a key to a keyed object and insert object into * pool's rb tree holding and not holding pool_lock */ -void __rxe_add_key_locked(struct rxe_pool_entry *elem, void *key); +int __rxe_add_key_locked(struct rxe_pool_entry *elem, void *key); #define rxe_add_key_locked(obj, key) __rxe_add_key_locked(&(obj)->pelem, key) -void __rxe_add_key(struct rxe_pool_entry *elem, void *key); +int __rxe_add_key(struct rxe_pool_entry *elem, void *key); #define rxe_add_key(obj, key) __rxe_add_key(&(obj)->pelem, key) diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index b0f350d674fd..1ab6af7ddb25 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -136,7 +136,6 @@ static void free_rd_atomic_resources(struct rxe_qp *qp) void free_rd_atomic_resource(struct rxe_qp *qp, struct resp_res *res) { if (res->type == RXE_ATOMIC_MASK) { - rxe_drop_ref(qp); kfree_skb(res->atomic.skb); } else if (res->type == RXE_READ_MASK) { if (res->read.mr) @@ -206,6 +205,7 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp, { int err; int wqe_size; + enum queue_type type; err = sock_create_kern(&init_net, AF_INET, SOCK_DGRAM, 0, &qp->sk); if (err < 0) @@ -231,7 +231,9 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp, qp->sq.max_inline = init->cap.max_inline_data = wqe_size; wqe_size += sizeof(struct rxe_send_wqe); - qp->sq.queue = rxe_queue_init(rxe, &qp->sq.max_wr, wqe_size); + type = uresp ? QUEUE_TYPE_FROM_USER : QUEUE_TYPE_KERNEL; + qp->sq.queue = rxe_queue_init(rxe, &qp->sq.max_wr, + wqe_size, type); if (!qp->sq.queue) return -ENOMEM; @@ -246,7 +248,13 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp, return err; } - qp->req.wqe_index = producer_index(qp->sq.queue); + if (qp->is_user) + qp->req.wqe_index = producer_index(qp->sq.queue, + QUEUE_TYPE_FROM_USER); + else + qp->req.wqe_index = producer_index(qp->sq.queue, + QUEUE_TYPE_KERNEL); + qp->req.state = QP_STATE_RESET; qp->req.opcode = -1; qp->comp.opcode = -1; @@ -274,6 +282,7 @@ static int rxe_qp_init_resp(struct rxe_dev *rxe, struct rxe_qp *qp, { int err; int wqe_size; + enum queue_type type; if (!qp->srq) { qp->rq.max_wr = init->cap.max_recv_wr; @@ -284,9 +293,9 @@ static int rxe_qp_init_resp(struct rxe_dev *rxe, struct rxe_qp *qp, pr_debug("qp#%d max_wr = %d, max_sge = %d, wqe_size = %d\n", qp_num(qp), qp->rq.max_wr, qp->rq.max_sge, wqe_size); - qp->rq.queue = rxe_queue_init(rxe, - &qp->rq.max_wr, - wqe_size); + type = uresp ? QUEUE_TYPE_FROM_USER : QUEUE_TYPE_KERNEL; + qp->rq.queue = rxe_queue_init(rxe, &qp->rq.max_wr, + wqe_size, type); if (!qp->rq.queue) return -ENOMEM; @@ -304,6 +313,8 @@ static int rxe_qp_init_resp(struct rxe_dev *rxe, struct rxe_qp *qp, spin_lock_init(&qp->rq.producer_lock); spin_lock_init(&qp->rq.consumer_lock); + qp->rq.is_user = qp->is_user; + skb_queue_head_init(&qp->resp_pkts); rxe_init_task(rxe, &qp->resp.task, qp, diff --git a/drivers/infiniband/sw/rxe/rxe_queue.c b/drivers/infiniband/sw/rxe/rxe_queue.c index fa69241b1187..85b812586ed4 100644 --- a/drivers/infiniband/sw/rxe/rxe_queue.c +++ b/drivers/infiniband/sw/rxe/rxe_queue.c @@ -52,9 +52,8 @@ inline void rxe_queue_reset(struct rxe_queue *q) memset(q->buf->data, 0, q->buf_size - sizeof(struct rxe_queue_buf)); } -struct rxe_queue *rxe_queue_init(struct rxe_dev *rxe, - int *num_elem, - unsigned int elem_size) +struct rxe_queue *rxe_queue_init(struct rxe_dev *rxe, int *num_elem, + unsigned int elem_size, enum queue_type type) { struct rxe_queue *q; size_t buf_size; @@ -69,6 +68,7 @@ struct rxe_queue *rxe_queue_init(struct rxe_dev *rxe, goto err1; q->rxe = rxe; + q->type = type; /* used in resize, only need to copy used part of queue */ q->elem_size = elem_size; @@ -111,14 +111,15 @@ err1: static int resize_finish(struct rxe_queue *q, struct rxe_queue *new_q, unsigned int num_elem) { - if (!queue_empty(q) && (num_elem < queue_count(q))) + if (!queue_empty(q, q->type) && (num_elem < queue_count(q, q->type))) return -EINVAL; - while (!queue_empty(q)) { - memcpy(producer_addr(new_q), consumer_addr(q), - new_q->elem_size); - advance_producer(new_q); - advance_consumer(q); + while (!queue_empty(q, q->type)) { + memcpy(producer_addr(new_q, new_q->type), + consumer_addr(q, q->type), + new_q->elem_size); + advance_producer(new_q, new_q->type); + advance_consumer(q, q->type); } swap(*q, *new_q); @@ -136,7 +137,7 @@ int rxe_queue_resize(struct rxe_queue *q, unsigned int *num_elem_p, int err; unsigned long flags = 0, flags1; - new_q = rxe_queue_init(q->rxe, &num_elem, elem_size); + new_q = rxe_queue_init(q->rxe, &num_elem, elem_size, q->type); if (!new_q) return -ENOMEM; diff --git a/drivers/infiniband/sw/rxe/rxe_queue.h b/drivers/infiniband/sw/rxe/rxe_queue.h index 2902ca7b288c..2702b0e55fc3 100644 --- a/drivers/infiniband/sw/rxe/rxe_queue.h +++ b/drivers/infiniband/sw/rxe/rxe_queue.h @@ -17,8 +17,29 @@ * up to a power of 2. Since the queue is empty when the * producer and consumer indices match the maximum capacity * of the queue is one less than the number of element slots + * + * Notes: + * - Kernel space indices are always masked off to q->index_mask + * before storing so do not need to be checked on reads. + * - User space indices may be out of range and must be + * masked before use when read. + * - The kernel indices for shared queues must not be written + * by user space so a local copy is used and a shared copy is + * stored when the local copy changes. + * - By passing the type in the parameter list separate from q + * the compiler can eliminate the switch statement when the + * actual queue type is known when the function is called. + * In the performance path this is done. In less critical + * paths just q->type is passed. */ +/* type of queue */ +enum queue_type { + QUEUE_TYPE_KERNEL, + QUEUE_TYPE_TO_USER, + QUEUE_TYPE_FROM_USER, +}; + struct rxe_queue { struct rxe_dev *rxe; struct rxe_queue_buf *buf; @@ -27,6 +48,13 @@ struct rxe_queue { size_t elem_size; unsigned int log2_elem_size; u32 index_mask; + enum queue_type type; + /* private copy of index for shared queues between + * kernel space and user space. Kernel reads and writes + * this copy and then replicates to rxe_queue_buf + * for read access by user space. + */ + u32 index; }; int do_mmap_info(struct rxe_dev *rxe, struct mminfo __user *outbuf, @@ -35,9 +63,8 @@ int do_mmap_info(struct rxe_dev *rxe, struct mminfo __user *outbuf, void rxe_queue_reset(struct rxe_queue *q); -struct rxe_queue *rxe_queue_init(struct rxe_dev *rxe, - int *num_elem, - unsigned int elem_size); +struct rxe_queue *rxe_queue_init(struct rxe_dev *rxe, int *num_elem, + unsigned int elem_size, enum queue_type type); int rxe_queue_resize(struct rxe_queue *q, unsigned int *num_elem_p, unsigned int elem_size, struct ib_udata *udata, @@ -54,120 +81,235 @@ static inline int next_index(struct rxe_queue *q, int index) return (index + 1) & q->buf->index_mask; } -static inline int queue_empty(struct rxe_queue *q) +static inline int queue_empty(struct rxe_queue *q, enum queue_type type) { u32 prod; u32 cons; - /* make sure all changes to queue complete before - * testing queue empty - */ - prod = smp_load_acquire(&q->buf->producer_index); - /* same */ - cons = smp_load_acquire(&q->buf->consumer_index); + switch (type) { + case QUEUE_TYPE_FROM_USER: + /* protect user space index */ + prod = smp_load_acquire(&q->buf->producer_index); + cons = q->index; + break; + case QUEUE_TYPE_TO_USER: + prod = q->index; + /* protect user space index */ + cons = smp_load_acquire(&q->buf->consumer_index); + break; + case QUEUE_TYPE_KERNEL: + prod = q->buf->producer_index; + cons = q->buf->consumer_index; + break; + } return ((prod - cons) & q->index_mask) == 0; } -static inline int queue_full(struct rxe_queue *q) +static inline int queue_full(struct rxe_queue *q, enum queue_type type) { u32 prod; u32 cons; - /* make sure all changes to queue complete before - * testing queue full - */ - prod = smp_load_acquire(&q->buf->producer_index); - /* same */ - cons = smp_load_acquire(&q->buf->consumer_index); + switch (type) { + case QUEUE_TYPE_FROM_USER: + /* protect user space index */ + prod = smp_load_acquire(&q->buf->producer_index); + cons = q->index; + break; + case QUEUE_TYPE_TO_USER: + prod = q->index; + /* protect user space index */ + cons = smp_load_acquire(&q->buf->consumer_index); + break; + case QUEUE_TYPE_KERNEL: + prod = q->buf->producer_index; + cons = q->buf->consumer_index; + break; + } return ((prod + 1 - cons) & q->index_mask) == 0; } -static inline void advance_producer(struct rxe_queue *q) +static inline unsigned int queue_count(const struct rxe_queue *q, + enum queue_type type) { u32 prod; + u32 cons; - prod = (q->buf->producer_index + 1) & q->index_mask; + switch (type) { + case QUEUE_TYPE_FROM_USER: + /* protect user space index */ + prod = smp_load_acquire(&q->buf->producer_index); + cons = q->index; + break; + case QUEUE_TYPE_TO_USER: + prod = q->index; + /* protect user space index */ + cons = smp_load_acquire(&q->buf->consumer_index); + break; + case QUEUE_TYPE_KERNEL: + prod = q->buf->producer_index; + cons = q->buf->consumer_index; + break; + } + + return (prod - cons) & q->index_mask; +} - /* make sure all changes to queue complete before - * changing producer index - */ - smp_store_release(&q->buf->producer_index, prod); +static inline void advance_producer(struct rxe_queue *q, enum queue_type type) +{ + u32 prod; + + switch (type) { + case QUEUE_TYPE_FROM_USER: + pr_warn_once("Normally kernel should not write user space index\n"); + /* protect user space index */ + prod = smp_load_acquire(&q->buf->producer_index); + prod = (prod + 1) & q->index_mask; + /* same */ + smp_store_release(&q->buf->producer_index, prod); + break; + case QUEUE_TYPE_TO_USER: + prod = q->index; + q->index = (prod + 1) & q->index_mask; + q->buf->producer_index = q->index; + break; + case QUEUE_TYPE_KERNEL: + prod = q->buf->producer_index; + q->buf->producer_index = (prod + 1) & q->index_mask; + break; + } } -static inline void advance_consumer(struct rxe_queue *q) +static inline void advance_consumer(struct rxe_queue *q, enum queue_type type) { u32 cons; - cons = (q->buf->consumer_index + 1) & q->index_mask; - - /* make sure all changes to queue complete before - * changing consumer index - */ - smp_store_release(&q->buf->consumer_index, cons); + switch (type) { + case QUEUE_TYPE_FROM_USER: + cons = q->index; + q->index = (cons + 1) & q->index_mask; + q->buf->consumer_index = q->index; + break; + case QUEUE_TYPE_TO_USER: + pr_warn_once("Normally kernel should not write user space index\n"); + /* protect user space index */ + cons = smp_load_acquire(&q->buf->consumer_index); + cons = (cons + 1) & q->index_mask; + /* same */ + smp_store_release(&q->buf->consumer_index, cons); + break; + case QUEUE_TYPE_KERNEL: + cons = q->buf->consumer_index; + q->buf->consumer_index = (cons + 1) & q->index_mask; + break; + } } -static inline void *producer_addr(struct rxe_queue *q) +static inline void *producer_addr(struct rxe_queue *q, enum queue_type type) { - return q->buf->data + ((q->buf->producer_index & q->index_mask) - << q->log2_elem_size); + u32 prod; + + switch (type) { + case QUEUE_TYPE_FROM_USER: + /* protect user space index */ + prod = smp_load_acquire(&q->buf->producer_index); + prod &= q->index_mask; + break; + case QUEUE_TYPE_TO_USER: + prod = q->index; + break; + case QUEUE_TYPE_KERNEL: + prod = q->buf->producer_index; + break; + } + + return q->buf->data + (prod << q->log2_elem_size); } -static inline void *consumer_addr(struct rxe_queue *q) +static inline void *consumer_addr(struct rxe_queue *q, enum queue_type type) { - return q->buf->data + ((q->buf->consumer_index & q->index_mask) - << q->log2_elem_size); + u32 cons; + + switch (type) { + case QUEUE_TYPE_FROM_USER: + cons = q->index; + break; + case QUEUE_TYPE_TO_USER: + /* protect user space index */ + cons = smp_load_acquire(&q->buf->consumer_index); + cons &= q->index_mask; + break; + case QUEUE_TYPE_KERNEL: + cons = q->buf->consumer_index; + break; + } + + return q->buf->data + (cons << q->log2_elem_size); } -static inline unsigned int producer_index(struct rxe_queue *q) +static inline unsigned int producer_index(struct rxe_queue *q, + enum queue_type type) { - u32 index; - - /* make sure all changes to queue - * complete before getting producer index - */ - index = smp_load_acquire(&q->buf->producer_index); - index &= q->index_mask; + u32 prod; - return index; + switch (type) { + case QUEUE_TYPE_FROM_USER: + /* protect user space index */ + prod = smp_load_acquire(&q->buf->producer_index); + prod &= q->index_mask; + break; + case QUEUE_TYPE_TO_USER: + prod = q->index; + break; + case QUEUE_TYPE_KERNEL: + prod = q->buf->producer_index; + break; + } + + return prod; } -static inline unsigned int consumer_index(struct rxe_queue *q) +static inline unsigned int consumer_index(struct rxe_queue *q, + enum queue_type type) { - u32 index; - - /* make sure all changes to queue - * complete before getting consumer index - */ - index = smp_load_acquire(&q->buf->consumer_index); - index &= q->index_mask; + u32 cons; - return index; + switch (type) { + case QUEUE_TYPE_FROM_USER: + cons = q->index; + break; + case QUEUE_TYPE_TO_USER: + /* protect user space index */ + cons = smp_load_acquire(&q->buf->consumer_index); + cons &= q->index_mask; + break; + case QUEUE_TYPE_KERNEL: + cons = q->buf->consumer_index; + break; + } + + return cons; } -static inline void *addr_from_index(struct rxe_queue *q, unsigned int index) +static inline void *addr_from_index(struct rxe_queue *q, + unsigned int index) { return q->buf->data + ((index & q->index_mask) << q->buf->log2_elem_size); } static inline unsigned int index_from_addr(const struct rxe_queue *q, - const void *addr) + const void *addr) { return (((u8 *)addr - q->buf->data) >> q->log2_elem_size) - & q->index_mask; -} - -static inline unsigned int queue_count(const struct rxe_queue *q) -{ - return (q->buf->producer_index - q->buf->consumer_index) - & q->index_mask; + & q->index_mask; } -static inline void *queue_head(struct rxe_queue *q) +static inline void *queue_head(struct rxe_queue *q, enum queue_type type) { - return queue_empty(q) ? NULL : consumer_addr(q); + return queue_empty(q, type) ? NULL : consumer_addr(q, type); } #endif /* RXE_QUEUE_H */ diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index 3664cdae7e1f..c57699cc6578 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -45,14 +45,24 @@ static void req_retry(struct rxe_qp *qp) unsigned int mask; int npsn; int first = 1; + struct rxe_queue *q = qp->sq.queue; + unsigned int cons; + unsigned int prod; - qp->req.wqe_index = consumer_index(qp->sq.queue); + if (qp->is_user) { + cons = consumer_index(q, QUEUE_TYPE_FROM_USER); + prod = producer_index(q, QUEUE_TYPE_FROM_USER); + } else { + cons = consumer_index(q, QUEUE_TYPE_KERNEL); + prod = producer_index(q, QUEUE_TYPE_KERNEL); + } + + qp->req.wqe_index = cons; qp->req.psn = qp->comp.psn; qp->req.opcode = -1; - for (wqe_index = consumer_index(qp->sq.queue); - wqe_index != producer_index(qp->sq.queue); - wqe_index = next_index(qp->sq.queue, wqe_index)) { + for (wqe_index = cons; wqe_index != prod; + wqe_index = next_index(q, wqe_index)) { wqe = addr_from_index(qp->sq.queue, wqe_index); mask = wr_opcode_mask(wqe->wr.opcode, qp); @@ -104,8 +114,22 @@ void rnr_nak_timer(struct timer_list *t) static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) { - struct rxe_send_wqe *wqe = queue_head(qp->sq.queue); + struct rxe_send_wqe *wqe; unsigned long flags; + struct rxe_queue *q = qp->sq.queue; + unsigned int index = qp->req.wqe_index; + unsigned int cons; + unsigned int prod; + + if (qp->is_user) { + wqe = queue_head(q, QUEUE_TYPE_FROM_USER); + cons = consumer_index(q, QUEUE_TYPE_FROM_USER); + prod = producer_index(q, QUEUE_TYPE_FROM_USER); + } else { + wqe = queue_head(q, QUEUE_TYPE_KERNEL); + cons = consumer_index(q, QUEUE_TYPE_KERNEL); + prod = producer_index(q, QUEUE_TYPE_KERNEL); + } if (unlikely(qp->req.state == QP_STATE_DRAIN)) { /* check to see if we are drained; @@ -120,8 +144,7 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) break; } - if (wqe && ((qp->req.wqe_index != - consumer_index(qp->sq.queue)) || + if (wqe && ((index != cons) || (wqe->state != wqe_state_posted))) { /* comp not done yet */ spin_unlock_irqrestore(&qp->state_lock, @@ -144,10 +167,10 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) } while (0); } - if (qp->req.wqe_index == producer_index(qp->sq.queue)) + if (index == prod) return NULL; - wqe = addr_from_index(qp->sq.queue, qp->req.wqe_index); + wqe = addr_from_index(q, index); if (unlikely((qp->req.state == QP_STATE_DRAIN || qp->req.state == QP_STATE_DRAINED) && @@ -155,7 +178,7 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) return NULL; if (unlikely((wqe->wr.send_flags & IB_SEND_FENCE) && - (qp->req.wqe_index != consumer_index(qp->sq.queue)))) { + (index != cons))) { qp->req.wait_fence = 1; return NULL; } @@ -439,7 +462,7 @@ static struct sk_buff *init_req_packet(struct rxe_qp *qp, return skb; } -static int fill_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe, +static int finish_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe, struct rxe_pkt_info *pkt, struct sk_buff *skb, int paylen) { @@ -464,7 +487,7 @@ static int fill_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe, } else { err = copy_data(qp->pd, 0, &wqe->dma, payload_addr(pkt), paylen, - from_mr_obj, + RXE_FROM_MR_OBJ, &crc); if (err) return err; @@ -555,6 +578,60 @@ static void update_state(struct rxe_qp *qp, struct rxe_send_wqe *wqe, jiffies + qp->qp_timeout_jiffies); } +static int rxe_do_local_ops(struct rxe_qp *qp, struct rxe_send_wqe *wqe) +{ + u8 opcode = wqe->wr.opcode; + struct rxe_mr *mr; + u32 rkey; + int ret; + + switch (opcode) { + case IB_WR_LOCAL_INV: + rkey = wqe->wr.ex.invalidate_rkey; + if (rkey_is_mw(rkey)) + ret = rxe_invalidate_mw(qp, rkey); + else + ret = rxe_invalidate_mr(qp, rkey); + + if (unlikely(ret)) { + wqe->status = IB_WC_LOC_QP_OP_ERR; + return ret; + } + break; + case IB_WR_REG_MR: + mr = to_rmr(wqe->wr.wr.reg.mr); + rxe_add_ref(mr); + mr->state = RXE_MR_STATE_VALID; + mr->access = wqe->wr.wr.reg.access; + mr->ibmr.lkey = wqe->wr.wr.reg.key; + mr->ibmr.rkey = wqe->wr.wr.reg.key; + mr->iova = wqe->wr.wr.reg.mr->iova; + rxe_drop_ref(mr); + break; + case IB_WR_BIND_MW: + ret = rxe_bind_mw(qp, wqe); + if (unlikely(ret)) { + wqe->status = IB_WC_MW_BIND_ERR; + return ret; + } + break; + default: + pr_err("Unexpected send wqe opcode %d\n", opcode); + wqe->status = IB_WC_LOC_QP_OP_ERR; + return -EINVAL; + } + + wqe->state = wqe_state_done; + wqe->status = IB_WC_SUCCESS; + qp->req.wqe_index = next_index(qp->sq.queue, qp->req.wqe_index); + + if ((wqe->wr.send_flags & IB_SEND_SIGNALED) || + qp->sq_sig_type == IB_SIGNAL_ALL_WR) + rxe_run_task(&qp->comp.task, 1); + + return 0; +} + int rxe_requester(void *arg) { struct rxe_qp *qp = (struct rxe_qp *)arg; @@ -568,6 +645,7 @@ int rxe_requester(void *arg) int ret; struct rxe_send_wqe rollback_wqe; u32 rollback_psn; + struct rxe_queue *q = qp->sq.queue; rxe_add_ref(qp); @@ -576,7 +654,7 @@ next_wqe: goto exit; if (unlikely(qp->req.state == QP_STATE_RESET)) { - qp->req.wqe_index = consumer_index(qp->sq.queue); + qp->req.wqe_index = consumer_index(q, q->type); qp->req.opcode = -1; qp->req.need_rd_atomic = 0; qp->req.wait_psn = 0; @@ -593,43 +671,12 @@ next_wqe: if (unlikely(!wqe)) goto exit; - if (wqe->mask & WR_REG_MASK) { - if (wqe->wr.opcode == IB_WR_LOCAL_INV) { - struct rxe_dev *rxe = to_rdev(qp->ibqp.device); - struct rxe_mr *rmr; - - rmr = rxe_pool_get_index(&rxe->mr_pool, - wqe->wr.ex.invalidate_rkey >> 8); - if (!rmr) { - pr_err("No mr for key %#x\n", - wqe->wr.ex.invalidate_rkey); - wqe->state = wqe_state_error; - wqe->status = IB_WC_MW_BIND_ERR; - goto exit; - } - rmr->state = RXE_MR_STATE_FREE; - rxe_drop_ref(rmr); - wqe->state = wqe_state_done; - wqe->status = IB_WC_SUCCESS; - } else if (wqe->wr.opcode == IB_WR_REG_MR) { - struct rxe_mr *rmr = to_rmr(wqe->wr.wr.reg.mr); - - rmr->state = RXE_MR_STATE_VALID; - rmr->access = wqe->wr.wr.reg.access; - rmr->ibmr.lkey = wqe->wr.wr.reg.key; - rmr->ibmr.rkey = wqe->wr.wr.reg.key; - rmr->iova = wqe->wr.wr.reg.mr->iova; - wqe->state = wqe_state_done; - wqe->status = IB_WC_SUCCESS; - } else { - goto exit; - } - if ((wqe->wr.send_flags & IB_SEND_SIGNALED) || - qp->sq_sig_type == IB_SIGNAL_ALL_WR) - rxe_run_task(&qp->comp.task, 1); - qp->req.wqe_index = next_index(qp->sq.queue, - qp->req.wqe_index); - goto next_wqe; + if (wqe->mask & WR_LOCAL_OP_MASK) { + ret = rxe_do_local_ops(qp, wqe); + if (unlikely(ret)) + goto err; + else + goto next_wqe; } if (unlikely(qp_type(qp) == IB_QPT_RC && @@ -687,11 +734,17 @@ next_wqe: skb = init_req_packet(qp, wqe, opcode, payload, &pkt); if (unlikely(!skb)) { pr_err("qp#%d Failed allocating skb\n", qp_num(qp)); + wqe->status = IB_WC_LOC_QP_OP_ERR; goto err; } - if (fill_packet(qp, wqe, &pkt, skb, payload)) { - pr_debug("qp#%d Error during fill packet\n", qp_num(qp)); + ret = finish_packet(qp, wqe, &pkt, skb, payload); + if (unlikely(ret)) { + pr_debug("qp#%d Error during finish packet\n", qp_num(qp)); + if (ret == -EFAULT) + wqe->status = IB_WC_LOC_PROT_ERR; + else + wqe->status = IB_WC_LOC_QP_OP_ERR; kfree_skb(skb); goto err; } @@ -716,6 +769,7 @@ next_wqe: goto exit; } + wqe->status = IB_WC_LOC_QP_OP_ERR; goto err; } @@ -724,7 +778,6 @@ next_wqe: goto next_wqe; err: - wqe->status = IB_WC_LOC_PROT_ERR; wqe->state = wqe_state_error; __rxe_do_task(&qp->comp.task); diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 2b220659bddb..f8a7ccd4d8b7 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -35,6 +35,7 @@ enum resp_states { RESPST_ERR_TOO_MANY_RDMA_ATM_REQ, RESPST_ERR_RNR, RESPST_ERR_RKEY_VIOLATION, + RESPST_ERR_INVALIDATE_RKEY, RESPST_ERR_LENGTH, RESPST_ERR_CQ_OVERFLOW, RESPST_ERROR, @@ -68,6 +69,7 @@ static char *resp_state_name[] = { [RESPST_ERR_TOO_MANY_RDMA_ATM_REQ] = "ERR_TOO_MANY_RDMA_ATM_REQ", [RESPST_ERR_RNR] = "ERR_RNR", [RESPST_ERR_RKEY_VIOLATION] = "ERR_RKEY_VIOLATION", + [RESPST_ERR_INVALIDATE_RKEY] = "ERR_INVALIDATE_RKEY_VIOLATION", [RESPST_ERR_LENGTH] = "ERR_LENGTH", [RESPST_ERR_CQ_OVERFLOW] = "ERR_CQ_OVERFLOW", [RESPST_ERROR] = "ERROR", @@ -293,13 +295,17 @@ static enum resp_states get_srq_wqe(struct rxe_qp *qp) struct rxe_queue *q = srq->rq.queue; struct rxe_recv_wqe *wqe; struct ib_event ev; + unsigned int count; if (srq->error) return RESPST_ERR_RNR; spin_lock_bh(&srq->rq.consumer_lock); - wqe = queue_head(q); + if (qp->is_user) + wqe = queue_head(q, QUEUE_TYPE_FROM_USER); + else + wqe = queue_head(q, QUEUE_TYPE_KERNEL); if (!wqe) { spin_unlock_bh(&srq->rq.consumer_lock); return RESPST_ERR_RNR; @@ -309,10 +315,15 @@ static enum resp_states get_srq_wqe(struct rxe_qp *qp) memcpy(&qp->resp.srq_wqe, wqe, sizeof(qp->resp.srq_wqe)); qp->resp.wqe = &qp->resp.srq_wqe.wqe; - advance_consumer(q); + if (qp->is_user) { + advance_consumer(q, QUEUE_TYPE_FROM_USER); + count = queue_count(q, QUEUE_TYPE_FROM_USER); + } else { + advance_consumer(q, QUEUE_TYPE_KERNEL); + count = queue_count(q, QUEUE_TYPE_KERNEL); + } - if (srq->limit && srq->ibsrq.event_handler && - (queue_count(q) < srq->limit)) { + if (srq->limit && srq->ibsrq.event_handler && (count < srq->limit)) { srq->limit = 0; goto event; } @@ -339,7 +350,12 @@ static enum resp_states check_resource(struct rxe_qp *qp, qp->resp.status = IB_WC_WR_FLUSH_ERR; return RESPST_COMPLETE; } else if (!srq) { - qp->resp.wqe = queue_head(qp->rq.queue); + if (qp->is_user) + qp->resp.wqe = queue_head(qp->rq.queue, + QUEUE_TYPE_FROM_USER); + else + qp->resp.wqe = queue_head(qp->rq.queue, + QUEUE_TYPE_KERNEL); if (qp->resp.wqe) { qp->resp.status = IB_WC_WR_FLUSH_ERR; return RESPST_COMPLETE; @@ -366,7 +382,12 @@ static enum resp_states check_resource(struct rxe_qp *qp, if (srq) return get_srq_wqe(qp); - qp->resp.wqe = queue_head(qp->rq.queue); + if (qp->is_user) + qp->resp.wqe = queue_head(qp->rq.queue, + QUEUE_TYPE_FROM_USER); + else + qp->resp.wqe = queue_head(qp->rq.queue, + QUEUE_TYPE_KERNEL); return (qp->resp.wqe) ? RESPST_CHK_LENGTH : RESPST_ERR_RNR; } @@ -392,6 +413,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { struct rxe_mr *mr = NULL; + struct rxe_mw *mw = NULL; u64 va; u32 rkey; u32 resid; @@ -403,6 +425,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp, if (pkt->mask & (RXE_READ_MASK | RXE_WRITE_MASK)) { if (pkt->mask & RXE_RETH_MASK) { qp->resp.va = reth_va(pkt); + qp->resp.offset = 0; qp->resp.rkey = reth_rkey(pkt); qp->resp.resid = reth_len(pkt); qp->resp.length = reth_len(pkt); @@ -411,6 +434,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp, : IB_ACCESS_REMOTE_WRITE; } else if (pkt->mask & RXE_ATOMIC_MASK) { qp->resp.va = atmeth_va(pkt); + qp->resp.offset = 0; qp->resp.rkey = atmeth_rkey(pkt); qp->resp.resid = sizeof(u64); access = IB_ACCESS_REMOTE_ATOMIC; @@ -430,18 +454,36 @@ static enum resp_states check_rkey(struct rxe_qp *qp, resid = qp->resp.resid; pktlen = payload_size(pkt); - mr = lookup_mr(qp->pd, access, rkey, lookup_remote); - if (!mr) { - state = RESPST_ERR_RKEY_VIOLATION; - goto err; - } + if (rkey_is_mw(rkey)) { + mw = rxe_lookup_mw(qp, access, rkey); + if (!mw) { + pr_err("%s: no MW matches rkey %#x\n", __func__, rkey); + state = RESPST_ERR_RKEY_VIOLATION; + goto err; + } - if (unlikely(mr->state == RXE_MR_STATE_FREE)) { - state = RESPST_ERR_RKEY_VIOLATION; - goto err; + mr = mw->mr; + if (!mr) { + pr_err("%s: MW doesn't have an MR\n", __func__); + state = RESPST_ERR_RKEY_VIOLATION; + goto err; + } + + if (mw->access & IB_ZERO_BASED) + qp->resp.offset = mw->addr; + + rxe_drop_ref(mw); + rxe_add_ref(mr); + } else { + mr = lookup_mr(qp->pd, access, rkey, RXE_LOOKUP_REMOTE); + if (!mr) { + pr_err("%s: no MR matches rkey %#x\n", __func__, rkey); + state = RESPST_ERR_RKEY_VIOLATION; + goto err; + } } - if (mr_check_range(mr, va, resid)) { + if (mr_check_range(mr, va + qp->resp.offset, resid)) { state = RESPST_ERR_RKEY_VIOLATION; goto err; } @@ -475,6 +517,9 @@ static enum resp_states check_rkey(struct rxe_qp *qp, err: if (mr) rxe_drop_ref(mr); + if (mw) + rxe_drop_ref(mw); + return state; } @@ -484,7 +529,7 @@ static enum resp_states send_data_in(struct rxe_qp *qp, void *data_addr, int err; err = copy_data(qp->pd, IB_ACCESS_LOCAL_WRITE, &qp->resp.wqe->dma, - data_addr, data_len, to_mr_obj, NULL); + data_addr, data_len, RXE_TO_MR_OBJ, NULL); if (unlikely(err)) return (err == -ENOSPC) ? RESPST_ERR_LENGTH : RESPST_ERR_MALFORMED_WQE; @@ -499,8 +544,8 @@ static enum resp_states write_data_in(struct rxe_qp *qp, int err; int data_len = payload_size(pkt); - err = rxe_mr_copy(qp->resp.mr, qp->resp.va, payload_addr(pkt), data_len, - to_mr_obj, NULL); + err = rxe_mr_copy(qp->resp.mr, qp->resp.va + qp->resp.offset, + payload_addr(pkt), data_len, RXE_TO_MR_OBJ, NULL); if (err) { rc = RESPST_ERR_RKEY_VIOLATION; goto out; @@ -519,7 +564,6 @@ static DEFINE_SPINLOCK(atomic_ops_lock); static enum resp_states process_atomic(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { - u64 iova = atmeth_va(pkt); u64 *vaddr; enum resp_states ret; struct rxe_mr *mr = qp->resp.mr; @@ -529,7 +573,7 @@ static enum resp_states process_atomic(struct rxe_qp *qp, goto out; } - vaddr = iova_to_vaddr(mr, iova, sizeof(u64)); + vaddr = iova_to_vaddr(mr, qp->resp.va + qp->resp.offset, sizeof(u64)); /* check vaddr is 8 bytes aligned. */ if (!vaddr || (uintptr_t)vaddr & 7) { @@ -653,8 +697,10 @@ static enum resp_states read_reply(struct rxe_qp *qp, res->type = RXE_READ_MASK; res->replay = 0; - res->read.va = qp->resp.va; - res->read.va_org = qp->resp.va; + res->read.va = qp->resp.va + + qp->resp.offset; + res->read.va_org = qp->resp.va + + qp->resp.offset; res->first_psn = req_pkt->psn; @@ -701,7 +747,7 @@ static enum resp_states read_reply(struct rxe_qp *qp, return RESPST_ERR_RNR; err = rxe_mr_copy(res->read.mr, res->read.va, payload_addr(&ack_pkt), - payload, from_mr_obj, &icrc); + payload, RXE_FROM_MR_OBJ, &icrc); if (err) pr_err("Failed copying memory\n"); @@ -751,6 +797,14 @@ static void build_rdma_network_hdr(union rdma_network_hdr *hdr, memcpy(&hdr->ibgrh, ipv6_hdr(skb), sizeof(hdr->ibgrh)); } +static int invalidate_rkey(struct rxe_qp *qp, u32 rkey) +{ + if (rkey_is_mw(rkey)) + return rxe_invalidate_mw(qp, rkey); + else + return rxe_invalidate_mr(qp, rkey); +} + /* Executes a new request. A retried request never reach that function (send * and writes are discarded, and reads and atomics are retried elsewhere. */ @@ -790,6 +844,14 @@ static enum resp_states execute(struct rxe_qp *qp, struct rxe_pkt_info *pkt) WARN_ON_ONCE(1); } + if (pkt->mask & RXE_IETH_MASK) { + u32 rkey = ieth_rkey(pkt); + + err = invalidate_rkey(qp, rkey); + if (err) + return RESPST_ERR_INVALIDATE_RKEY; + } + /* next expected psn, read handles this separately */ qp->resp.psn = (pkt->psn + 1) & BTH_PSN_MASK; qp->resp.ack_psn = qp->resp.psn; @@ -822,13 +884,13 @@ static enum resp_states do_complete(struct rxe_qp *qp, memset(&cqe, 0, sizeof(cqe)); if (qp->rcq->is_user) { - uwc->status = qp->resp.status; - uwc->qp_num = qp->ibqp.qp_num; - uwc->wr_id = wqe->wr_id; + uwc->status = qp->resp.status; + uwc->qp_num = qp->ibqp.qp_num; + uwc->wr_id = wqe->wr_id; } else { - wc->status = qp->resp.status; - wc->qp = &qp->ibqp; - wc->wr_id = wqe->wr_id; + wc->status = qp->resp.status; + wc->qp = &qp->ibqp; + wc->wr_id = wqe->wr_id; } if (wc->status == IB_WC_SUCCESS) { @@ -883,34 +945,25 @@ static enum resp_states do_complete(struct rxe_qp *qp, } if (pkt->mask & RXE_IETH_MASK) { - struct rxe_mr *rmr; - wc->wc_flags |= IB_WC_WITH_INVALIDATE; wc->ex.invalidate_rkey = ieth_rkey(pkt); - - rmr = rxe_pool_get_index(&rxe->mr_pool, - wc->ex.invalidate_rkey >> 8); - if (unlikely(!rmr)) { - pr_err("Bad rkey %#x invalidation\n", - wc->ex.invalidate_rkey); - return RESPST_ERROR; - } - rmr->state = RXE_MR_STATE_FREE; - rxe_drop_ref(rmr); } - wc->qp = &qp->ibqp; - if (pkt->mask & RXE_DETH_MASK) wc->src_qp = deth_sqp(pkt); + wc->qp = &qp->ibqp; wc->port_num = qp->attr.port_num; } } /* have copy for srq and reference for !srq */ - if (!qp->srq) - advance_consumer(qp->rq.queue); + if (!qp->srq) { + if (qp->is_user) + advance_consumer(qp->rq.queue, QUEUE_TYPE_FROM_USER); + else + advance_consumer(qp->rq.queue, QUEUE_TYPE_KERNEL); + } qp->resp.wqe = NULL; @@ -966,8 +1019,6 @@ static int send_atomic_ack(struct rxe_qp *qp, struct rxe_pkt_info *pkt, goto out; } - rxe_add_ref(qp); - res = &qp->resp.resources[qp->resp.res_head]; free_rd_atomic_resource(qp, res); rxe_advance_resp_resource(qp); @@ -1176,6 +1227,7 @@ static enum resp_states do_class_d1e_error(struct rxe_qp *qp) static void rxe_drain_req_pkts(struct rxe_qp *qp, bool notify) { struct sk_buff *skb; + struct rxe_queue *q = qp->rq.queue; while ((skb = skb_dequeue(&qp->req_pkts))) { rxe_drop_ref(qp); @@ -1186,8 +1238,8 @@ static void rxe_drain_req_pkts(struct rxe_qp *qp, bool notify) if (notify) return; - while (!qp->srq && qp->rq.queue && queue_head(qp->rq.queue)) - advance_consumer(qp->rq.queue); + while (!qp->srq && q && queue_head(q, q->type)) + advance_consumer(q, q->type); } int rxe_responder(void *arg) @@ -1314,6 +1366,13 @@ int rxe_responder(void *arg) } break; + case RESPST_ERR_INVALIDATE_RKEY: + /* RC - Class J. */ + qp->resp.goto_error = 1; + qp->resp.status = IB_WC_REM_INV_REQ_ERR; + state = RESPST_COMPLETE; + break; + case RESPST_ERR_LENGTH: if (qp_type(qp) == IB_QPT_RC) { /* Class C */ diff --git a/drivers/infiniband/sw/rxe/rxe_srq.c b/drivers/infiniband/sw/rxe/rxe_srq.c index 41b0d1e11baf..610c98d24b5c 100644 --- a/drivers/infiniband/sw/rxe/rxe_srq.c +++ b/drivers/infiniband/sw/rxe/rxe_srq.c @@ -78,6 +78,7 @@ int rxe_srq_from_init(struct rxe_dev *rxe, struct rxe_srq *srq, int err; int srq_wqe_size; struct rxe_queue *q; + enum queue_type type; srq->ibsrq.event_handler = init->event_handler; srq->ibsrq.srq_context = init->srq_context; @@ -85,14 +86,16 @@ int rxe_srq_from_init(struct rxe_dev *rxe, struct rxe_srq *srq, srq->srq_num = srq->pelem.index; srq->rq.max_wr = init->attr.max_wr; srq->rq.max_sge = init->attr.max_sge; + srq->rq.is_user = srq->is_user; srq_wqe_size = rcv_wqe_size(srq->rq.max_sge); spin_lock_init(&srq->rq.producer_lock); spin_lock_init(&srq->rq.consumer_lock); + type = uresp ? QUEUE_TYPE_FROM_USER : QUEUE_TYPE_KERNEL; q = rxe_queue_init(rxe, &srq->rq.max_wr, - srq_wqe_size); + srq_wqe_size, type); if (!q) { pr_warn("unable to allocate queue for srq\n"); return -ENOMEM; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index aeb5e232c195..c223959ac174 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -216,8 +216,14 @@ static int post_one_recv(struct rxe_rq *rq, const struct ib_recv_wr *ibwr) u32 length; struct rxe_recv_wqe *recv_wqe; int num_sge = ibwr->num_sge; + int full; - if (unlikely(queue_full(rq->queue))) { + if (rq->is_user) + full = queue_full(rq->queue, QUEUE_TYPE_FROM_USER); + else + full = queue_full(rq->queue, QUEUE_TYPE_KERNEL); + + if (unlikely(full)) { err = -ENOMEM; goto err1; } @@ -231,7 +237,11 @@ static int post_one_recv(struct rxe_rq *rq, const struct ib_recv_wr *ibwr) for (i = 0; i < num_sge; i++) length += ibwr->sg_list[i].length; - recv_wqe = producer_addr(rq->queue); + if (rq->is_user) + recv_wqe = producer_addr(rq->queue, QUEUE_TYPE_FROM_USER); + else + recv_wqe = producer_addr(rq->queue, QUEUE_TYPE_KERNEL); + recv_wqe->wr_id = ibwr->wr_id; recv_wqe->num_sge = num_sge; @@ -244,7 +254,11 @@ static int post_one_recv(struct rxe_rq *rq, const struct ib_recv_wr *ibwr) recv_wqe->dma.cur_sge = 0; recv_wqe->dma.sge_offset = 0; - advance_producer(rq->queue); + if (rq->is_user) + advance_producer(rq->queue, QUEUE_TYPE_FROM_USER); + else + advance_producer(rq->queue, QUEUE_TYPE_KERNEL); + return 0; err1: @@ -267,6 +281,9 @@ static int rxe_create_srq(struct ib_srq *ibsrq, struct ib_srq_init_attr *init, if (udata->outlen < sizeof(*uresp)) return -EINVAL; uresp = udata->outbuf; + srq->is_user = true; + } else { + srq->is_user = false; } err = rxe_srq_chk_attr(rxe, NULL, &init->attr, IB_SRQ_INIT_MASK); @@ -408,7 +425,9 @@ static struct ib_qp *rxe_create_qp(struct ib_pd *ibpd, err = -EINVAL; goto err2; } - qp->is_user = 1; + qp->is_user = true; + } else { + qp->is_user = false; } rxe_add_index(qp); @@ -577,7 +596,7 @@ static void init_send_wqe(struct rxe_qp *qp, const struct ib_send_wr *ibwr, init_send_wr(qp, &wqe->wr, ibwr); /* local operation */ - if (unlikely(mask & WR_REG_MASK)) { + if (unlikely(mask & WR_LOCAL_OP_MASK)) { wqe->mask = mask; wqe->state = wqe_state_posted; return; @@ -613,6 +632,7 @@ static int post_one_send(struct rxe_qp *qp, const struct ib_send_wr *ibwr, struct rxe_sq *sq = &qp->sq; struct rxe_send_wqe *send_wqe; unsigned long flags; + int full; err = validate_send_wr(qp, ibwr, mask, length); if (err) @@ -620,22 +640,31 @@ static int post_one_send(struct rxe_qp *qp, const struct ib_send_wr *ibwr, spin_lock_irqsave(&qp->sq.sq_lock, flags); - if (unlikely(queue_full(sq->queue))) { - err = -ENOMEM; - goto err1; + if (qp->is_user) + full = queue_full(sq->queue, QUEUE_TYPE_FROM_USER); + else + full = queue_full(sq->queue, QUEUE_TYPE_KERNEL); + + if (unlikely(full)) { + spin_unlock_irqrestore(&qp->sq.sq_lock, flags); + return -ENOMEM; } - send_wqe = producer_addr(sq->queue); + if (qp->is_user) + send_wqe = producer_addr(sq->queue, QUEUE_TYPE_FROM_USER); + else + send_wqe = producer_addr(sq->queue, QUEUE_TYPE_KERNEL); + init_send_wqe(qp, ibwr, mask, length, send_wqe); - advance_producer(sq->queue); + if (qp->is_user) + advance_producer(sq->queue, QUEUE_TYPE_FROM_USER); + else + advance_producer(sq->queue, QUEUE_TYPE_KERNEL); + spin_unlock_irqrestore(&qp->sq.sq_lock, flags); return 0; - -err1: - spin_unlock_irqrestore(&qp->sq.sq_lock, flags); - return err; } static int rxe_post_send_kernel(struct rxe_qp *qp, const struct ib_send_wr *wr, @@ -823,12 +852,18 @@ static int rxe_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) spin_lock_irqsave(&cq->cq_lock, flags); for (i = 0; i < num_entries; i++) { - cqe = queue_head(cq->queue); + if (cq->is_user) + cqe = queue_head(cq->queue, QUEUE_TYPE_TO_USER); + else + cqe = queue_head(cq->queue, QUEUE_TYPE_KERNEL); if (!cqe) break; memcpy(wc++, &cqe->ibwc, sizeof(*wc)); - advance_consumer(cq->queue); + if (cq->is_user) + advance_consumer(cq->queue, QUEUE_TYPE_TO_USER); + else + advance_consumer(cq->queue, QUEUE_TYPE_KERNEL); } spin_unlock_irqrestore(&cq->cq_lock, flags); @@ -838,7 +873,12 @@ static int rxe_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) static int rxe_peek_cq(struct ib_cq *ibcq, int wc_cnt) { struct rxe_cq *cq = to_rcq(ibcq); - int count = queue_count(cq->queue); + int count; + + if (cq->is_user) + count = queue_count(cq->queue, QUEUE_TYPE_TO_USER); + else + count = queue_count(cq->queue, QUEUE_TYPE_KERNEL); return (count > wc_cnt) ? wc_cnt : count; } @@ -848,12 +888,18 @@ static int rxe_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags) struct rxe_cq *cq = to_rcq(ibcq); unsigned long irq_flags; int ret = 0; + int empty; spin_lock_irqsave(&cq->cq_lock, irq_flags); if (cq->notify != IB_CQ_NEXT_COMP) cq->notify = flags & IB_CQ_SOLICITED_MASK; - if ((flags & IB_CQ_REPORT_MISSED_EVENTS) && !queue_empty(cq->queue)) + if (cq->is_user) + empty = queue_empty(cq->queue, QUEUE_TYPE_TO_USER); + else + empty = queue_empty(cq->queue, QUEUE_TYPE_KERNEL); + + if ((flags & IB_CQ_REPORT_MISSED_EVENTS) && !empty) ret = 1; spin_unlock_irqrestore(&cq->cq_lock, irq_flags); @@ -899,7 +945,7 @@ static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd, rxe_add_ref(pd); - err = rxe_mr_init_user(pd, start, length, iova, access, udata, mr); + err = rxe_mr_init_user(pd, start, length, iova, access, mr); if (err) goto err3; @@ -913,17 +959,6 @@ err2: return ERR_PTR(err); } -static int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata) -{ - struct rxe_mr *mr = to_rmr(ibmr); - - mr->state = RXE_MR_STATE_ZOMBIE; - rxe_drop_ref(mr_pd(mr)); - rxe_drop_index(mr); - rxe_drop_ref(mr); - return 0; -} - static struct ib_mr *rxe_alloc_mr(struct ib_pd *ibpd, enum ib_mr_type mr_type, u32 max_num_sg) { @@ -1058,8 +1093,9 @@ static const struct ib_device_ops rxe_dev_ops = { .driver_id = RDMA_DRIVER_RXE, .uverbs_abi_ver = RXE_UVERBS_ABI_VERSION, - .alloc_hw_stats = rxe_ib_alloc_hw_stats, + .alloc_hw_port_stats = rxe_ib_alloc_hw_port_stats, .alloc_mr = rxe_alloc_mr, + .alloc_mw = rxe_alloc_mw, .alloc_pd = rxe_alloc_pd, .alloc_ucontext = rxe_alloc_ucontext, .attach_mcast = rxe_attach_mcast, @@ -1069,6 +1105,7 @@ static const struct ib_device_ops rxe_dev_ops = { .create_srq = rxe_create_srq, .create_user_ah = rxe_create_ah, .dealloc_driver = rxe_dealloc, + .dealloc_mw = rxe_dealloc_mw, .dealloc_pd = rxe_dealloc_pd, .dealloc_ucontext = rxe_dealloc_ucontext, .dereg_mr = rxe_dereg_mr, @@ -1077,6 +1114,7 @@ static const struct ib_device_ops rxe_dev_ops = { .destroy_qp = rxe_destroy_qp, .destroy_srq = rxe_destroy_srq, .detach_mcast = rxe_detach_mcast, + .device_group = &rxe_attr_group, .enable_driver = rxe_enable_driver, .get_dma_mr = rxe_get_dma_mr, .get_hw_stats = rxe_ib_get_hw_stats, @@ -1143,7 +1181,6 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name) } rxe->tfm = tfm; - rdma_set_device_sysfs_group(dev, &rxe_attr_group); err = ib_register_device(dev, ibdev_name, NULL); if (err) pr_warn("%s failed with error %d\n", __func__, err); diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h index 11eba7a3ba8f..959a3260fcab 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.h +++ b/drivers/infiniband/sw/rxe/rxe_verbs.h @@ -77,6 +77,7 @@ enum wqe_state { }; struct rxe_sq { + bool is_user; int max_wr; int max_sge; int max_inline; @@ -85,6 +86,7 @@ struct rxe_sq { }; struct rxe_rq { + bool is_user; int max_wr; int max_sge; spinlock_t producer_lock; /* guard queue producer */ @@ -98,6 +100,7 @@ struct rxe_srq { struct rxe_pd *pd; struct rxe_rq rq; u32 srq_num; + bool is_user; int limit; int error; @@ -183,6 +186,7 @@ struct rxe_resp_info { /* RDMA read / atomic only */ u64 va; + u64 offset; struct rxe_mr *mr; u32 resid; u32 rkey; @@ -211,7 +215,7 @@ struct rxe_qp { struct ib_qp_attr attr; unsigned int valid; unsigned int mtu; - int is_user; + bool is_user; struct rxe_pd *pd; struct rxe_srq *srq; @@ -273,7 +277,16 @@ enum rxe_mr_type { RXE_MR_TYPE_NONE, RXE_MR_TYPE_DMA, RXE_MR_TYPE_MR, - RXE_MR_TYPE_MW, +}; + +enum rxe_mr_copy_dir { + RXE_TO_MR_OBJ, + RXE_FROM_MR_OBJ, +}; + +enum rxe_mr_lookup_type { + RXE_LOOKUP_LOCAL, + RXE_LOOKUP_REMOTE, }; #define RXE_BUF_PER_MAP (PAGE_SIZE / sizeof(struct rxe_phys_buf)) @@ -287,6 +300,13 @@ struct rxe_map { struct rxe_phys_buf buf[RXE_BUF_PER_MAP]; }; +static inline int rkey_is_mw(u32 rkey) +{ + u32 index = rkey >> 8; + + return (index >= RXE_MIN_MW_INDEX) && (index <= RXE_MAX_MW_INDEX); +} + struct rxe_mr { struct rxe_pool_entry pelem; struct ib_mr ibmr; @@ -312,18 +332,27 @@ struct rxe_mr { u32 max_buf; u32 num_map; + atomic_t num_mw; + struct rxe_map **map; }; enum rxe_mw_state { - RXE_MW_STATE_INVALID = RXE_MR_STATE_INVALID, - RXE_MW_STATE_FREE = RXE_MR_STATE_FREE, - RXE_MW_STATE_VALID = RXE_MR_STATE_VALID, + RXE_MW_STATE_INVALID = RXE_MR_STATE_INVALID, + RXE_MW_STATE_FREE = RXE_MR_STATE_FREE, + RXE_MW_STATE_VALID = RXE_MR_STATE_VALID, }; struct rxe_mw { - struct ib_mw ibmw; - struct rxe_pool_entry pelem; + struct ib_mw ibmw; + struct rxe_pool_entry pelem; + spinlock_t lock; + enum rxe_mw_state state; + struct rxe_qp *qp; /* Type 2 only */ + struct rxe_mr *mr; + int access; + u64 addr; + u64 length; }; struct rxe_mc_grp { @@ -455,6 +484,16 @@ static inline u32 mr_rkey(struct rxe_mr *mr) return mr->ibmr.rkey; } +static inline struct rxe_pd *rxe_mw_pd(struct rxe_mw *mw) +{ + return to_rpd(mw->ibmw.pd); +} + +static inline u32 rxe_mw_rkey(struct rxe_mw *mw) +{ + return mw->ibmw.rkey; +} + int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name); void rxe_mc_cleanup(struct rxe_pool_entry *arg); |