diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-12-15 12:03:32 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-12-15 12:03:32 -0800 |
commit | 4d5b57e05a67c3cfd8e2b2a64ca356245a15b1c6 (patch) | |
tree | d8f3ea3bc3ccfe289f414bbe9a4bdd1e935d9228 /drivers/infiniband/sw | |
parent | 6df8b74b1720db1133ace0861cb6721bfe57819a (diff) | |
parent | 6f94ba20799b98c8badf047b184fb4cd7bc45e44 (diff) | |
download | linux-stable-4d5b57e05a67c3cfd8e2b2a64ca356245a15b1c6.tar.gz linux-stable-4d5b57e05a67c3cfd8e2b2a64ca356245a15b1c6.tar.bz2 linux-stable-4d5b57e05a67c3cfd8e2b2a64ca356245a15b1c6.zip |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma
Pull rdma updates from Doug Ledford:
"This is the complete update for the rdma stack for this release cycle.
Most of it is typical driver and core updates, but there is the
entirely new VMWare pvrdma driver. You may have noticed that there
were changes in DaveM's pull request to the bnxt Ethernet driver to
support a RoCE RDMA driver. The bnxt_re driver was tentatively set to
be pulled in this release cycle, but it simply wasn't ready in time
and was dropped (a few review comments still to address, and some
multi-arch build issues like prefetch() not working across all
arches).
Summary:
- shared mlx5 updates with net stack (will drop out on merge if
Dave's tree has already been merged)
- driver updates: cxgb4, hfi1, hns-roce, i40iw, mlx4, mlx5, qedr, rxe
- debug cleanups
- new connection rejection helpers
- SRP updates
- various misc fixes
- new paravirt driver from vmware"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (210 commits)
IB: Add vmw_pvrdma driver
IB/mlx4: fix improper return value
IB/ocrdma: fix bad initialization
infiniband: nes: return value of skb_linearize should be handled
MAINTAINERS: Update Intel RDMA RNIC driver maintainers
MAINTAINERS: Remove Mitesh Ahuja from emulex maintainers
IB/core: fix unmap_sg argument
qede: fix general protection fault may occur on probe
IB/mthca: Replace pci_pool_alloc by pci_pool_zalloc
mlx5, calc_sq_size(): Make a debug message more informative
mlx5: Remove a set-but-not-used variable
mlx5: Use { } instead of { 0 } to init struct
IB/srp: Make writing the add_target sysfs attr interruptible
IB/srp: Make mapping failures easier to debug
IB/srp: Make login failures easier to debug
IB/srp: Introduce a local variable in srp_add_one()
IB/srp: Fix CONFIG_DYNAMIC_DEBUG=n build
IB/multicast: Check ib_find_pkey() return value
IPoIB: Avoid reading an uninitialized member variable
IB/mad: Fix an array index check
...
Diffstat (limited to 'drivers/infiniband/sw')
22 files changed, 574 insertions, 223 deletions
diff --git a/drivers/infiniband/sw/rdmavt/cq.c b/drivers/infiniband/sw/rdmavt/cq.c index 6d9904a4a0ab..4d0b6992e847 100644 --- a/drivers/infiniband/sw/rdmavt/cq.c +++ b/drivers/infiniband/sw/rdmavt/cq.c @@ -119,18 +119,17 @@ void rvt_cq_enter(struct rvt_cq *cq, struct ib_wc *entry, bool solicited) if (cq->notify == IB_CQ_NEXT_COMP || (cq->notify == IB_CQ_SOLICITED && (solicited || entry->status != IB_WC_SUCCESS))) { - struct kthread_worker *worker; /* * This will cause send_complete() to be called in * another thread. */ - smp_read_barrier_depends(); /* see rvt_cq_exit */ - worker = cq->rdi->worker; - if (likely(worker)) { + spin_lock(&cq->rdi->n_cqs_lock); + if (likely(cq->rdi->worker)) { cq->notify = RVT_CQ_NONE; cq->triggered++; - kthread_queue_work(worker, &cq->comptask); + kthread_queue_work(cq->rdi->worker, &cq->comptask); } + spin_unlock(&cq->rdi->n_cqs_lock); } spin_unlock_irqrestore(&cq->lock, flags); @@ -240,15 +239,15 @@ struct ib_cq *rvt_create_cq(struct ib_device *ibdev, } } - spin_lock(&rdi->n_cqs_lock); + spin_lock_irq(&rdi->n_cqs_lock); if (rdi->n_cqs_allocated == rdi->dparms.props.max_cq) { - spin_unlock(&rdi->n_cqs_lock); + spin_unlock_irq(&rdi->n_cqs_lock); ret = ERR_PTR(-ENOMEM); goto bail_ip; } rdi->n_cqs_allocated++; - spin_unlock(&rdi->n_cqs_lock); + spin_unlock_irq(&rdi->n_cqs_lock); if (cq->ip) { spin_lock_irq(&rdi->pending_lock); @@ -296,9 +295,9 @@ int rvt_destroy_cq(struct ib_cq *ibcq) struct rvt_dev_info *rdi = cq->rdi; kthread_flush_work(&cq->comptask); - spin_lock(&rdi->n_cqs_lock); + spin_lock_irq(&rdi->n_cqs_lock); rdi->n_cqs_allocated--; - spin_unlock(&rdi->n_cqs_lock); + spin_unlock_irq(&rdi->n_cqs_lock); if (cq->ip) kref_put(&cq->ip->ref, rvt_release_mmap_info); else @@ -504,33 +503,23 @@ int rvt_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry) */ int rvt_driver_cq_init(struct rvt_dev_info *rdi) { - int ret = 0; int cpu; - struct task_struct *task; + struct kthread_worker *worker; if (rdi->worker) return 0; + spin_lock_init(&rdi->n_cqs_lock); - rdi->worker = kzalloc(sizeof(*rdi->worker), GFP_KERNEL); - if (!rdi->worker) - return -ENOMEM; - kthread_init_worker(rdi->worker); - task = kthread_create_on_node( - kthread_worker_fn, - rdi->worker, - rdi->dparms.node, - "%s", rdi->dparms.cq_name); - if (IS_ERR(task)) { - kfree(rdi->worker); - rdi->worker = NULL; - return PTR_ERR(task); - } - set_user_nice(task, MIN_NICE); cpu = cpumask_first(cpumask_of_node(rdi->dparms.node)); - kthread_bind(task, cpu); - wake_up_process(task); - return ret; + worker = kthread_create_worker_on_cpu(cpu, 0, + "%s", rdi->dparms.cq_name); + if (IS_ERR(worker)) + return PTR_ERR(worker); + + set_user_nice(worker->task, MIN_NICE); + rdi->worker = worker; + return 0; } /** @@ -541,13 +530,14 @@ void rvt_cq_exit(struct rvt_dev_info *rdi) { struct kthread_worker *worker; - worker = rdi->worker; - if (!worker) + /* block future queuing from send_complete() */ + spin_lock_irq(&rdi->n_cqs_lock); + if (!rdi->worker) { + spin_unlock_irq(&rdi->n_cqs_lock); return; - /* blocks future queuing from send_complete() */ + } rdi->worker = NULL; - smp_wmb(); /* See rdi_cq_enter */ - kthread_flush_worker(worker); - kthread_stop(worker->task); - kfree(worker); + spin_unlock_irq(&rdi->n_cqs_lock); + + kthread_destroy_worker(worker); } diff --git a/drivers/infiniband/sw/rdmavt/mcast.c b/drivers/infiniband/sw/rdmavt/mcast.c index 983d319ac976..05c8c2afb0e3 100644 --- a/drivers/infiniband/sw/rdmavt/mcast.c +++ b/drivers/infiniband/sw/rdmavt/mcast.c @@ -81,7 +81,7 @@ static struct rvt_mcast_qp *rvt_mcast_qp_alloc(struct rvt_qp *qp) goto bail; mqp->qp = qp; - atomic_inc(&qp->refcount); + rvt_get_qp(qp); bail: return mqp; @@ -92,8 +92,7 @@ static void rvt_mcast_qp_free(struct rvt_mcast_qp *mqp) struct rvt_qp *qp = mqp->qp; /* Notify hfi1_destroy_qp() if it is waiting. */ - if (atomic_dec_and_test(&qp->refcount)) - wake_up(&qp->wait); + rvt_put_qp(qp); kfree(mqp); } diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c index 46b64970058e..52fd15276ee6 100644 --- a/drivers/infiniband/sw/rdmavt/mr.c +++ b/drivers/infiniband/sw/rdmavt/mr.c @@ -51,6 +51,7 @@ #include <rdma/rdma_vt.h> #include "vt.h" #include "mr.h" +#include "trace.h" /** * rvt_driver_mr_init - Init MR resources per driver @@ -84,6 +85,7 @@ int rvt_driver_mr_init(struct rvt_dev_info *rdi) lkey_table_size = rdi->dparms.lkey_table_size; } rdi->lkey_table.max = 1 << lkey_table_size; + rdi->lkey_table.shift = 32 - lkey_table_size; lk_tab_size = rdi->lkey_table.max * sizeof(*rdi->lkey_table.table); rdi->lkey_table.table = (struct rvt_mregion __rcu **) vmalloc_node(lk_tab_size, rdi->dparms.node); @@ -402,6 +404,7 @@ struct ib_mr *rvt_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, } mr->mr.map[m]->segs[n].vaddr = vaddr; mr->mr.map[m]->segs[n].length = umem->page_size; + trace_rvt_mr_user_seg(&mr->mr, m, n, vaddr, umem->page_size); n++; if (n == RVT_SEGSZ) { m++; @@ -506,6 +509,7 @@ static int rvt_set_page(struct ib_mr *ibmr, u64 addr) n = mapped_segs % RVT_SEGSZ; mr->mr.map[m]->segs[n].vaddr = (void *)addr; mr->mr.map[m]->segs[n].length = ps; + trace_rvt_mr_page_seg(&mr->mr, m, n, (void *)addr, ps); mr->mr.length += ps; return 0; @@ -692,6 +696,7 @@ int rvt_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list, for (i = 0; i < list_len; i++) { fmr->mr.map[m]->segs[n].vaddr = (void *)page_list[i]; fmr->mr.map[m]->segs[n].length = ps; + trace_rvt_mr_fmr_seg(&fmr->mr, m, n, (void *)page_list[i], ps); if (++n == RVT_SEGSZ) { m++; n = 0; @@ -774,7 +779,6 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd, struct rvt_mregion *mr; unsigned n, m; size_t off; - struct rvt_dev_info *dev = ib_to_rvt(pd->ibpd.device); /* * We use LKEY == zero for kernel virtual addresses @@ -782,12 +786,14 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd, */ rcu_read_lock(); if (sge->lkey == 0) { + struct rvt_dev_info *dev = ib_to_rvt(pd->ibpd.device); + if (pd->user) goto bail; mr = rcu_dereference(dev->dma_mr); if (!mr) goto bail; - atomic_inc(&mr->refcount); + rvt_get_mr(mr); rcu_read_unlock(); isge->mr = mr; @@ -798,8 +804,7 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd, isge->n = 0; goto ok; } - mr = rcu_dereference( - rkt->table[(sge->lkey >> (32 - dev->dparms.lkey_table_size))]); + mr = rcu_dereference(rkt->table[sge->lkey >> rkt->shift]); if (unlikely(!mr || atomic_read(&mr->lkey_invalid) || mr->lkey != sge->lkey || mr->pd != &pd->ibpd)) goto bail; @@ -809,7 +814,7 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd, off + sge->length > mr->length || (mr->access_flags & acc) != acc)) goto bail; - atomic_inc(&mr->refcount); + rvt_get_mr(mr); rcu_read_unlock(); off += mr->offset; @@ -887,7 +892,7 @@ int rvt_rkey_ok(struct rvt_qp *qp, struct rvt_sge *sge, mr = rcu_dereference(rdi->dma_mr); if (!mr) goto bail; - atomic_inc(&mr->refcount); + rvt_get_mr(mr); rcu_read_unlock(); sge->mr = mr; @@ -899,8 +904,7 @@ int rvt_rkey_ok(struct rvt_qp *qp, struct rvt_sge *sge, goto ok; } - mr = rcu_dereference( - rkt->table[(rkey >> (32 - dev->dparms.lkey_table_size))]); + mr = rcu_dereference(rkt->table[rkey >> rkt->shift]); if (unlikely(!mr || atomic_read(&mr->lkey_invalid) || mr->lkey != rkey || qp->ibqp.pd != mr->pd)) goto bail; @@ -909,7 +913,7 @@ int rvt_rkey_ok(struct rvt_qp *qp, struct rvt_sge *sge, if (unlikely(vaddr < mr->iova || off + len > mr->length || (mr->access_flags & acc) == 0)) goto bail; - atomic_inc(&mr->refcount); + rvt_get_mr(mr); rcu_read_unlock(); off += mr->offset; diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 6500c3b5a89c..2a13ac660f2b 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -76,6 +76,23 @@ const int ib_rvt_state_ops[IB_QPS_ERR + 1] = { }; EXPORT_SYMBOL(ib_rvt_state_ops); +/* + * Translate ib_wr_opcode into ib_wc_opcode. + */ +const enum ib_wc_opcode ib_rvt_wc_opcode[] = { + [IB_WR_RDMA_WRITE] = IB_WC_RDMA_WRITE, + [IB_WR_RDMA_WRITE_WITH_IMM] = IB_WC_RDMA_WRITE, + [IB_WR_SEND] = IB_WC_SEND, + [IB_WR_SEND_WITH_IMM] = IB_WC_SEND, + [IB_WR_RDMA_READ] = IB_WC_RDMA_READ, + [IB_WR_ATOMIC_CMP_AND_SWP] = IB_WC_COMP_SWAP, + [IB_WR_ATOMIC_FETCH_AND_ADD] = IB_WC_FETCH_ADD, + [IB_WR_SEND_WITH_INV] = IB_WC_SEND, + [IB_WR_LOCAL_INV] = IB_WC_LOCAL_INV, + [IB_WR_REG_MR] = IB_WC_REG_MR +}; +EXPORT_SYMBOL(ib_rvt_wc_opcode); + static void get_map_page(struct rvt_qpn_table *qpt, struct rvt_qpn_map *map, gfp_t gfp) @@ -884,7 +901,8 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, return ret; bail_ip: - kref_put(&qp->ip->ref, rvt_release_mmap_info); + if (qp->ip) + kref_put(&qp->ip->ref, rvt_release_mmap_info); bail_qpn: free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num); diff --git a/drivers/infiniband/sw/rdmavt/trace.h b/drivers/infiniband/sw/rdmavt/trace.h index 6c0457db5499..e2d23acb6a7d 100644 --- a/drivers/infiniband/sw/rdmavt/trace.h +++ b/drivers/infiniband/sw/rdmavt/trace.h @@ -45,143 +45,10 @@ * */ -#undef TRACE_SYSTEM_VAR -#define TRACE_SYSTEM_VAR rdmavt - -#if !defined(__RDMAVT_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) -#define __RDMAVT_TRACE_H - -#include <linux/tracepoint.h> -#include <linux/trace_seq.h> - -#include <rdma/ib_verbs.h> -#include <rdma/rdma_vt.h> - #define RDI_DEV_ENTRY(rdi) __string(dev, rdi->driver_f.get_card_name(rdi)) #define RDI_DEV_ASSIGN(rdi) __assign_str(dev, rdi->driver_f.get_card_name(rdi)) -#undef TRACE_SYSTEM -#define TRACE_SYSTEM rdmavt - -TRACE_EVENT(rvt_dbg, - TP_PROTO(struct rvt_dev_info *rdi, - const char *msg), - TP_ARGS(rdi, msg), - TP_STRUCT__entry( - RDI_DEV_ENTRY(rdi) - __string(msg, msg) - ), - TP_fast_assign( - RDI_DEV_ASSIGN(rdi); - __assign_str(msg, msg); - ), - TP_printk("[%s]: %s", __get_str(dev), __get_str(msg)) -); - -#undef TRACE_SYSTEM -#define TRACE_SYSTEM rvt_qphash -DECLARE_EVENT_CLASS(rvt_qphash_template, - TP_PROTO(struct rvt_qp *qp, u32 bucket), - TP_ARGS(qp, bucket), - TP_STRUCT__entry( - RDI_DEV_ENTRY(ib_to_rvt(qp->ibqp.device)) - __field(u32, qpn) - __field(u32, bucket) - ), - TP_fast_assign( - RDI_DEV_ASSIGN(ib_to_rvt(qp->ibqp.device)) - __entry->qpn = qp->ibqp.qp_num; - __entry->bucket = bucket; - ), - TP_printk( - "[%s] qpn 0x%x bucket %u", - __get_str(dev), - __entry->qpn, - __entry->bucket - ) -); - -DEFINE_EVENT(rvt_qphash_template, rvt_qpinsert, - TP_PROTO(struct rvt_qp *qp, u32 bucket), - TP_ARGS(qp, bucket)); - -DEFINE_EVENT(rvt_qphash_template, rvt_qpremove, - TP_PROTO(struct rvt_qp *qp, u32 bucket), - TP_ARGS(qp, bucket)); - -#undef TRACE_SYSTEM -#define TRACE_SYSTEM rvt_tx - -#define wr_opcode_name(opcode) { IB_WR_##opcode, #opcode } -#define show_wr_opcode(opcode) \ -__print_symbolic(opcode, \ - wr_opcode_name(RDMA_WRITE), \ - wr_opcode_name(RDMA_WRITE_WITH_IMM), \ - wr_opcode_name(SEND), \ - wr_opcode_name(SEND_WITH_IMM), \ - wr_opcode_name(RDMA_READ), \ - wr_opcode_name(ATOMIC_CMP_AND_SWP), \ - wr_opcode_name(ATOMIC_FETCH_AND_ADD), \ - wr_opcode_name(LSO), \ - wr_opcode_name(SEND_WITH_INV), \ - wr_opcode_name(RDMA_READ_WITH_INV), \ - wr_opcode_name(LOCAL_INV), \ - wr_opcode_name(MASKED_ATOMIC_CMP_AND_SWP), \ - wr_opcode_name(MASKED_ATOMIC_FETCH_AND_ADD)) - -#define POS_PRN \ -"[%s] wr_id %llx qpn %x psn 0x%x lpsn 0x%x length %u opcode 0x%.2x,%s size %u avail %u head %u last %u" - -TRACE_EVENT( - rvt_post_one_wr, - TP_PROTO(struct rvt_qp *qp, struct rvt_swqe *wqe), - TP_ARGS(qp, wqe), - TP_STRUCT__entry( - RDI_DEV_ENTRY(ib_to_rvt(qp->ibqp.device)) - __field(u64, wr_id) - __field(u32, qpn) - __field(u32, psn) - __field(u32, lpsn) - __field(u32, length) - __field(u32, opcode) - __field(u32, size) - __field(u32, avail) - __field(u32, head) - __field(u32, last) - ), - TP_fast_assign( - RDI_DEV_ASSIGN(ib_to_rvt(qp->ibqp.device)) - __entry->wr_id = wqe->wr.wr_id; - __entry->qpn = qp->ibqp.qp_num; - __entry->psn = wqe->psn; - __entry->lpsn = wqe->lpsn; - __entry->length = wqe->length; - __entry->opcode = wqe->wr.opcode; - __entry->size = qp->s_size; - __entry->avail = qp->s_avail; - __entry->head = qp->s_head; - __entry->last = qp->s_last; - ), - TP_printk( - POS_PRN, - __get_str(dev), - __entry->wr_id, - __entry->qpn, - __entry->psn, - __entry->lpsn, - __entry->length, - __entry->opcode, show_wr_opcode(__entry->opcode), - __entry->size, - __entry->avail, - __entry->head, - __entry->last - ) -); - -#endif /* __RDMAVT_TRACE_H */ - -#undef TRACE_INCLUDE_PATH -#undef TRACE_INCLUDE_FILE -#define TRACE_INCLUDE_PATH . -#define TRACE_INCLUDE_FILE trace -#include <trace/define_trace.h> +#include "trace_rvt.h" +#include "trace_qp.h" +#include "trace_tx.h" +#include "trace_mr.h" diff --git a/drivers/infiniband/sw/rdmavt/trace_mr.h b/drivers/infiniband/sw/rdmavt/trace_mr.h new file mode 100644 index 000000000000..3318a6c36373 --- /dev/null +++ b/drivers/infiniband/sw/rdmavt/trace_mr.h @@ -0,0 +1,112 @@ +/* + * Copyright(c) 2016 Intel Corporation. + * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * BSD LICENSE + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * - Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + */ +#if !defined(__RVT_TRACE_MR_H) || defined(TRACE_HEADER_MULTI_READ) +#define __RVT_TRACE_MR_H + +#include <linux/tracepoint.h> +#include <linux/trace_seq.h> + +#include <rdma/ib_verbs.h> +#include <rdma/rdma_vt.h> +#include <rdma/rdmavt_mr.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM rvt_mr +DECLARE_EVENT_CLASS( + rvt_mr_template, + TP_PROTO(struct rvt_mregion *mr, u16 m, u16 n, void *v, size_t len), + TP_ARGS(mr, m, n, v, len), + TP_STRUCT__entry( + RDI_DEV_ENTRY(ib_to_rvt(mr->pd->device)) + __field(void *, vaddr) + __field(struct page *, page) + __field(size_t, len) + __field(u32, lkey) + __field(u16, m) + __field(u16, n) + ), + TP_fast_assign( + RDI_DEV_ASSIGN(ib_to_rvt(mr->pd->device)); + __entry->vaddr = v; + __entry->page = virt_to_page(v); + __entry->m = m; + __entry->n = n; + __entry->len = len; + ), + TP_printk( + "[%s] vaddr %p page %p m %u n %u len %ld", + __get_str(dev), + __entry->vaddr, + __entry->page, + __entry->m, + __entry->n, + __entry->len + ) +); + +DEFINE_EVENT( + rvt_mr_template, rvt_mr_page_seg, + TP_PROTO(struct rvt_mregion *mr, u16 m, u16 n, void *v, size_t len), + TP_ARGS(mr, m, n, v, len)); + +DEFINE_EVENT( + rvt_mr_template, rvt_mr_fmr_seg, + TP_PROTO(struct rvt_mregion *mr, u16 m, u16 n, void *v, size_t len), + TP_ARGS(mr, m, n, v, len)); + +DEFINE_EVENT( + rvt_mr_template, rvt_mr_user_seg, + TP_PROTO(struct rvt_mregion *mr, u16 m, u16 n, void *v, size_t len), + TP_ARGS(mr, m, n, v, len)); + +#endif /* __RVT_TRACE_MR_H */ + +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace_mr +#include <trace/define_trace.h> diff --git a/drivers/infiniband/sw/rdmavt/trace_qp.h b/drivers/infiniband/sw/rdmavt/trace_qp.h new file mode 100644 index 000000000000..4c77a3119bda --- /dev/null +++ b/drivers/infiniband/sw/rdmavt/trace_qp.h @@ -0,0 +1,96 @@ +/* + * Copyright(c) 2016 Intel Corporation. + * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * BSD LICENSE + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * - Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + */ +#if !defined(__RVT_TRACE_QP_H) || defined(TRACE_HEADER_MULTI_READ) +#define __RVT_TRACE_QP_H + +#include <linux/tracepoint.h> +#include <linux/trace_seq.h> + +#include <rdma/ib_verbs.h> +#include <rdma/rdma_vt.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM rvt_qp + +DECLARE_EVENT_CLASS(rvt_qphash_template, + TP_PROTO(struct rvt_qp *qp, u32 bucket), + TP_ARGS(qp, bucket), + TP_STRUCT__entry( + RDI_DEV_ENTRY(ib_to_rvt(qp->ibqp.device)) + __field(u32, qpn) + __field(u32, bucket) + ), + TP_fast_assign( + RDI_DEV_ASSIGN(ib_to_rvt(qp->ibqp.device)) + __entry->qpn = qp->ibqp.qp_num; + __entry->bucket = bucket; + ), + TP_printk( + "[%s] qpn 0x%x bucket %u", + __get_str(dev), + __entry->qpn, + __entry->bucket + ) +); + +DEFINE_EVENT(rvt_qphash_template, rvt_qpinsert, + TP_PROTO(struct rvt_qp *qp, u32 bucket), + TP_ARGS(qp, bucket)); + +DEFINE_EVENT(rvt_qphash_template, rvt_qpremove, + TP_PROTO(struct rvt_qp *qp, u32 bucket), + TP_ARGS(qp, bucket)); + + +#endif /* __RVT_TRACE_QP_H */ + +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace_qp +#include <trace/define_trace.h> + diff --git a/drivers/infiniband/sw/rdmavt/trace_rvt.h b/drivers/infiniband/sw/rdmavt/trace_rvt.h new file mode 100644 index 000000000000..746f33461d9a --- /dev/null +++ b/drivers/infiniband/sw/rdmavt/trace_rvt.h @@ -0,0 +1,81 @@ +/* + * Copyright(c) 2016 Intel Corporation. + * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * BSD LICENSE + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * - Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + */ +#if !defined(__RVT_TRACE_RVT_H) || defined(TRACE_HEADER_MULTI_READ) +#define __RVT_TRACE_RVT_H + +#include <linux/tracepoint.h> +#include <linux/trace_seq.h> + +#include <rdma/ib_verbs.h> +#include <rdma/rdma_vt.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM rvt + +TRACE_EVENT(rvt_dbg, + TP_PROTO(struct rvt_dev_info *rdi, + const char *msg), + TP_ARGS(rdi, msg), + TP_STRUCT__entry( + RDI_DEV_ENTRY(rdi) + __string(msg, msg) + ), + TP_fast_assign( + RDI_DEV_ASSIGN(rdi); + __assign_str(msg, msg); + ), + TP_printk("[%s]: %s", __get_str(dev), __get_str(msg)) +); + +#endif /* __RVT_TRACE_MISC_H */ + +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace_rvt +#include <trace/define_trace.h> + diff --git a/drivers/infiniband/sw/rdmavt/trace_tx.h b/drivers/infiniband/sw/rdmavt/trace_tx.h new file mode 100644 index 000000000000..0e03173662d8 --- /dev/null +++ b/drivers/infiniband/sw/rdmavt/trace_tx.h @@ -0,0 +1,132 @@ +/* + * Copyright(c) 2016 Intel Corporation. + * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * BSD LICENSE + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * - Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + */ +#if !defined(__RVT_TRACE_TX_H) || defined(TRACE_HEADER_MULTI_READ) +#define __RVT_TRACE_TX_H + +#include <linux/tracepoint.h> +#include <linux/trace_seq.h> + +#include <rdma/ib_verbs.h> +#include <rdma/rdma_vt.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM rvt_tx + +#define wr_opcode_name(opcode) { IB_WR_##opcode, #opcode } +#define show_wr_opcode(opcode) \ +__print_symbolic(opcode, \ + wr_opcode_name(RDMA_WRITE), \ + wr_opcode_name(RDMA_WRITE_WITH_IMM), \ + wr_opcode_name(SEND), \ + wr_opcode_name(SEND_WITH_IMM), \ + wr_opcode_name(RDMA_READ), \ + wr_opcode_name(ATOMIC_CMP_AND_SWP), \ + wr_opcode_name(ATOMIC_FETCH_AND_ADD), \ + wr_opcode_name(LSO), \ + wr_opcode_name(SEND_WITH_INV), \ + wr_opcode_name(RDMA_READ_WITH_INV), \ + wr_opcode_name(LOCAL_INV), \ + wr_opcode_name(MASKED_ATOMIC_CMP_AND_SWP), \ + wr_opcode_name(MASKED_ATOMIC_FETCH_AND_ADD)) + +#define POS_PRN \ +"[%s] wr_id %llx qpn %x psn 0x%x lpsn 0x%x length %u opcode 0x%.2x,%s size %u avail %u head %u last %u" + +TRACE_EVENT( + rvt_post_one_wr, + TP_PROTO(struct rvt_qp *qp, struct rvt_swqe *wqe), + TP_ARGS(qp, wqe), + TP_STRUCT__entry( + RDI_DEV_ENTRY(ib_to_rvt(qp->ibqp.device)) + __field(u64, wr_id) + __field(u32, qpn) + __field(u32, psn) + __field(u32, lpsn) + __field(u32, length) + __field(u32, opcode) + __field(u32, size) + __field(u32, avail) + __field(u32, head) + __field(u32, last) + ), + TP_fast_assign( + RDI_DEV_ASSIGN(ib_to_rvt(qp->ibqp.device)) + __entry->wr_id = wqe->wr.wr_id; + __entry->qpn = qp->ibqp.qp_num; + __entry->psn = wqe->psn; + __entry->lpsn = wqe->lpsn; + __entry->length = wqe->length; + __entry->opcode = wqe->wr.opcode; + __entry->size = qp->s_size; + __entry->avail = qp->s_avail; + __entry->head = qp->s_head; + __entry->last = qp->s_last; + ), + TP_printk( + POS_PRN, + __get_str(dev), + __entry->wr_id, + __entry->qpn, + __entry->psn, + __entry->lpsn, + __entry->length, + __entry->opcode, show_wr_opcode(__entry->opcode), + __entry->size, + __entry->avail, + __entry->head, + __entry->last + ) +); + +#endif /* __RVT_TRACE_TX_H */ + +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace_tx +#include <trace/define_trace.h> + diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index 6c5e29db88e3..cd27cbde7652 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -420,11 +420,12 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe) (wqe->wr.send_flags & IB_SEND_SIGNALED) || (qp->req.state == QP_STATE_ERROR)) { make_send_cqe(qp, wqe, &cqe); + advance_consumer(qp->sq.queue); rxe_cq_post(qp->scq, &cqe, 0); + } else { + advance_consumer(qp->sq.queue); } - advance_consumer(qp->sq.queue); - /* * we completed something so let req run again * if it is trying to fence @@ -510,6 +511,8 @@ int rxe_completer(void *arg) struct rxe_pkt_info *pkt = NULL; enum comp_state state; + rxe_add_ref(qp); + if (!qp->valid) { while ((skb = skb_dequeue(&qp->resp_pkts))) { rxe_drop_ref(qp); @@ -739,11 +742,13 @@ exit: /* we come here if we are done with processing and want the task to * exit from the loop calling us */ + rxe_drop_ref(qp); return -EAGAIN; done: /* we come here if we have processed a packet we want the task to call * us again to see if there is anything else to do */ + rxe_drop_ref(qp); return 0; } diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h index 73849a5a91b3..efe4c6a35442 100644 --- a/drivers/infiniband/sw/rxe/rxe_loc.h +++ b/drivers/infiniband/sw/rxe/rxe_loc.h @@ -266,8 +266,6 @@ static inline int rxe_xmit_packet(struct rxe_dev *rxe, struct rxe_qp *qp, return err; } - atomic_inc(&qp->skb_out); - if ((qp_type(qp) != IB_QPT_RC) && (pkt->mask & RXE_END_MASK)) { pkt->wqe->state = wqe_state_done; diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c index 1869152f1d23..d0faca294006 100644 --- a/drivers/infiniband/sw/rxe/rxe_mr.c +++ b/drivers/infiniband/sw/rxe/rxe_mr.c @@ -355,6 +355,9 @@ int rxe_mem_copy(struct rxe_mem *mem, u64 iova, void *addr, int length, size_t offset; u32 crc = crcp ? (*crcp) : 0; + if (length == 0) + return 0; + if (mem->type == RXE_MEM_TYPE_DMA) { u8 *src, *dest; diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index ffff5a54cb34..16967cdb45df 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -46,7 +46,7 @@ #include "rxe_loc.h" static LIST_HEAD(rxe_dev_list); -static spinlock_t dev_list_lock; /* spinlock for device list */ +static DEFINE_SPINLOCK(dev_list_lock); /* spinlock for device list */ struct rxe_dev *net_to_rxe(struct net_device *ndev) { @@ -455,6 +455,8 @@ static int send(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, return -EAGAIN; } + if (pkt->qp) + atomic_inc(&pkt->qp->skb_out); kfree_skb(skb); return 0; @@ -659,8 +661,6 @@ struct notifier_block rxe_net_notifier = { int rxe_net_ipv4_init(void) { - spin_lock_init(&dev_list_lock); - recv_sockets.sk4 = rxe_setup_udp_tunnel(&init_net, htons(ROCE_V2_UDP_DPORT), false); if (IS_ERR(recv_sockets.sk4)) { @@ -676,8 +676,6 @@ int rxe_net_ipv6_init(void) { #if IS_ENABLED(CONFIG_IPV6) - spin_lock_init(&dev_list_lock); - recv_sockets.sk6 = rxe_setup_udp_tunnel(&init_net, htons(ROCE_V2_UDP_DPORT), true); if (IS_ERR(recv_sockets.sk6)) { diff --git a/drivers/infiniband/sw/rxe/rxe_param.h b/drivers/infiniband/sw/rxe/rxe_param.h index f459c43a77c8..13ed2cc6eaa2 100644 --- a/drivers/infiniband/sw/rxe/rxe_param.h +++ b/drivers/infiniband/sw/rxe/rxe_param.h @@ -82,7 +82,7 @@ enum rxe_device_param { RXE_MAX_SGE = 32, RXE_MAX_SGE_RD = 32, RXE_MAX_CQ = 16384, - RXE_MAX_LOG_CQE = 13, + RXE_MAX_LOG_CQE = 15, RXE_MAX_MR = 2 * 1024, RXE_MAX_PD = 0x7ffc, RXE_MAX_QP_RD_ATOM = 128, diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c index 6bac0717c540..d723947a8542 100644 --- a/drivers/infiniband/sw/rxe/rxe_pool.c +++ b/drivers/infiniband/sw/rxe/rxe_pool.c @@ -180,7 +180,6 @@ static int rxe_pool_init_index(struct rxe_pool *pool, u32 max, u32 min) size = BITS_TO_LONGS(max - min + 1) * sizeof(long); pool->table = kmalloc(size, GFP_KERNEL); if (!pool->table) { - pr_warn("no memory for bit table\n"); err = -ENOMEM; goto out; } diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c index 46f062842a9a..252b4d637d45 100644 --- a/drivers/infiniband/sw/rxe/rxe_recv.c +++ b/drivers/infiniband/sw/rxe/rxe_recv.c @@ -391,16 +391,15 @@ int rxe_rcv(struct sk_buff *skb) payload_size(pkt)); calc_icrc = cpu_to_be32(~calc_icrc); if (unlikely(calc_icrc != pack_icrc)) { - char saddr[sizeof(struct in6_addr)]; - if (skb->protocol == htons(ETH_P_IPV6)) - sprintf(saddr, "%pI6", &ipv6_hdr(skb)->saddr); + pr_warn_ratelimited("bad ICRC from %pI6c\n", + &ipv6_hdr(skb)->saddr); else if (skb->protocol == htons(ETH_P_IP)) - sprintf(saddr, "%pI4", &ip_hdr(skb)->saddr); + pr_warn_ratelimited("bad ICRC from %pI4\n", + &ip_hdr(skb)->saddr); else - sprintf(saddr, "unknown"); + pr_warn_ratelimited("bad ICRC from unknown\n"); - pr_warn_ratelimited("bad ICRC from %s\n", saddr); goto drop; } diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index 22bd9630dcd9..73d4a97603a1 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -548,23 +548,23 @@ static void update_wqe_psn(struct rxe_qp *qp, static void save_state(struct rxe_send_wqe *wqe, struct rxe_qp *qp, struct rxe_send_wqe *rollback_wqe, - struct rxe_qp *rollback_qp) + u32 *rollback_psn) { rollback_wqe->state = wqe->state; rollback_wqe->first_psn = wqe->first_psn; rollback_wqe->last_psn = wqe->last_psn; - rollback_qp->req.psn = qp->req.psn; + *rollback_psn = qp->req.psn; } static void rollback_state(struct rxe_send_wqe *wqe, struct rxe_qp *qp, struct rxe_send_wqe *rollback_wqe, - struct rxe_qp *rollback_qp) + u32 rollback_psn) { wqe->state = rollback_wqe->state; wqe->first_psn = rollback_wqe->first_psn; wqe->last_psn = rollback_wqe->last_psn; - qp->req.psn = rollback_qp->req.psn; + qp->req.psn = rollback_psn; } static void update_state(struct rxe_qp *qp, struct rxe_send_wqe *wqe, @@ -593,8 +593,10 @@ int rxe_requester(void *arg) int mtu; int opcode; int ret; - struct rxe_qp rollback_qp; struct rxe_send_wqe rollback_wqe; + u32 rollback_psn; + + rxe_add_ref(qp); next_wqe: if (unlikely(!qp->valid || qp->req.state == QP_STATE_ERROR)) @@ -697,6 +699,7 @@ next_wqe: wqe->state = wqe_state_done; wqe->status = IB_WC_SUCCESS; __rxe_do_task(&qp->comp.task); + rxe_drop_ref(qp); return 0; } payload = mtu; @@ -719,7 +722,7 @@ next_wqe: * rxe_xmit_packet(). * Otherwise, completer might initiate an unjustified retry flow. */ - save_state(wqe, qp, &rollback_wqe, &rollback_qp); + save_state(wqe, qp, &rollback_wqe, &rollback_psn); update_wqe_state(qp, wqe, &pkt); update_wqe_psn(qp, wqe, &pkt, payload); ret = rxe_xmit_packet(to_rdev(qp->ibqp.device), qp, &pkt, skb); @@ -727,7 +730,7 @@ next_wqe: qp->need_req_skb = 1; kfree_skb(skb); - rollback_state(wqe, qp, &rollback_wqe, &rollback_qp); + rollback_state(wqe, qp, &rollback_wqe, rollback_psn); if (ret == -EAGAIN) { rxe_run_task(&qp->req.task, 1); @@ -756,8 +759,7 @@ err: */ wqe->wr.send_flags |= IB_SEND_SIGNALED; __rxe_do_task(&qp->comp.task); - return -EAGAIN; - exit: + rxe_drop_ref(qp); return -EAGAIN; } diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index dd3d88adc003..7a36ec9dbc0c 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -444,6 +444,13 @@ static enum resp_states check_rkey(struct rxe_qp *qp, return RESPST_EXECUTE; } + /* A zero-byte op is not required to set an addr or rkey. */ + if ((pkt->mask & (RXE_READ_MASK | RXE_WRITE_OR_SEND)) && + (pkt->mask & RXE_RETH_MASK) && + reth_len(pkt) == 0) { + return RESPST_EXECUTE; + } + va = qp->resp.va; rkey = qp->resp.rkey; resid = qp->resp.resid; @@ -680,9 +687,14 @@ static enum resp_states read_reply(struct rxe_qp *qp, res->read.va_org = qp->resp.va; res->first_psn = req_pkt->psn; - res->last_psn = req_pkt->psn + - (reth_len(req_pkt) + mtu - 1) / - mtu - 1; + + if (reth_len(req_pkt)) { + res->last_psn = (req_pkt->psn + + (reth_len(req_pkt) + mtu - 1) / + mtu - 1) & BTH_PSN_MASK; + } else { + res->last_psn = res->first_psn; + } res->cur_psn = req_pkt->psn; res->read.resid = qp->resp.resid; @@ -742,7 +754,8 @@ static enum resp_states read_reply(struct rxe_qp *qp, } else { qp->resp.res = NULL; qp->resp.opcode = -1; - qp->resp.psn = res->cur_psn; + if (psn_compare(res->cur_psn, qp->resp.psn) >= 0) + qp->resp.psn = res->cur_psn; state = RESPST_CLEANUP; } @@ -1132,6 +1145,7 @@ static enum resp_states duplicate_request(struct rxe_qp *qp, pkt, skb_copy); if (rc) { pr_err("Failed resending result. This flow is not handled - skb ignored\n"); + rxe_drop_ref(qp); kfree_skb(skb_copy); rc = RESPST_CLEANUP; goto out; @@ -1198,6 +1212,8 @@ int rxe_responder(void *arg) struct rxe_pkt_info *pkt = NULL; int ret = 0; + rxe_add_ref(qp); + qp->resp.aeth_syndrome = AETH_ACK_UNLIMITED; if (!qp->valid) { @@ -1386,5 +1402,6 @@ int rxe_responder(void *arg) exit: ret = -EAGAIN; done: + rxe_drop_ref(qp); return ret; } diff --git a/drivers/infiniband/sw/rxe/rxe_srq.c b/drivers/infiniband/sw/rxe/rxe_srq.c index 2a6e3cd2d4e8..efc832a2d7c6 100644 --- a/drivers/infiniband/sw/rxe/rxe_srq.c +++ b/drivers/infiniband/sw/rxe/rxe_srq.c @@ -169,7 +169,7 @@ int rxe_srq_from_attr(struct rxe_dev *rxe, struct rxe_srq *srq, } } - err = rxe_queue_resize(q, (unsigned int *)&attr->max_wr, + err = rxe_queue_resize(q, &attr->max_wr, rcv_wqe_size(srq->rq.max_sge), srq->rq.queue->ip ? srq->rq.queue->ip->context : diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c index 1e19bf828a6e..d2a14a1bdc7f 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.c +++ b/drivers/infiniband/sw/rxe/rxe_task.c @@ -121,6 +121,7 @@ int rxe_init_task(void *obj, struct rxe_task *task, task->arg = arg; task->func = func; snprintf(task->name, sizeof(task->name), "%s", name); + task->destroyed = false; tasklet_init(&task->tasklet, rxe_do_task, (unsigned long)task); @@ -132,11 +133,29 @@ int rxe_init_task(void *obj, struct rxe_task *task, void rxe_cleanup_task(struct rxe_task *task) { + unsigned long flags; + bool idle; + + /* + * Mark the task, then wait for it to finish. It might be + * running in a non-tasklet (direct call) context. + */ + task->destroyed = true; + + do { + spin_lock_irqsave(&task->state_lock, flags); + idle = (task->state == TASK_STATE_START); + spin_unlock_irqrestore(&task->state_lock, flags); + } while (!idle); + tasklet_kill(&task->tasklet); } void rxe_run_task(struct rxe_task *task, int sched) { + if (task->destroyed) + return; + if (sched) tasklet_schedule(&task->tasklet); else diff --git a/drivers/infiniband/sw/rxe/rxe_task.h b/drivers/infiniband/sw/rxe/rxe_task.h index d14aa6daed05..08ff42d451c6 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.h +++ b/drivers/infiniband/sw/rxe/rxe_task.h @@ -54,6 +54,7 @@ struct rxe_task { int (*func)(void *arg); int ret; char name[16]; + bool destroyed; }; /* diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 19841c863daf..beb7021ff18a 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -316,7 +316,9 @@ static int rxe_init_av(struct rxe_dev *rxe, struct ib_ah_attr *attr, return err; } -static struct ib_ah *rxe_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr) +static struct ib_ah *rxe_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr, + struct ib_udata *udata) + { int err; struct rxe_dev *rxe = to_rdev(ibpd->device); @@ -564,7 +566,7 @@ static struct ib_qp *rxe_create_qp(struct ib_pd *ibpd, if (udata) { if (udata->inlen) { err = -EINVAL; - goto err1; + goto err2; } qp->is_user = 1; } @@ -573,12 +575,13 @@ static struct ib_qp *rxe_create_qp(struct ib_pd *ibpd, err = rxe_qp_from_init(rxe, qp, pd, init, udata, ibpd); if (err) - goto err2; + goto err3; return &qp->ibqp; -err2: +err3: rxe_drop_index(qp); +err2: rxe_drop_ref(qp); err1: return ERR_PTR(err); @@ -1007,11 +1010,19 @@ static int rxe_peek_cq(struct ib_cq *ibcq, int wc_cnt) 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; + spin_lock_irqsave(&cq->cq_lock, irq_flags); if (cq->notify != IB_CQ_NEXT_COMP) cq->notify = flags & IB_CQ_SOLICITED_MASK; - return 0; + if ((flags & IB_CQ_REPORT_MISSED_EVENTS) && !queue_empty(cq->queue)) + ret = 1; + + spin_unlock_irqrestore(&cq->cq_lock, irq_flags); + + return ret; } static struct ib_mr *rxe_get_dma_mr(struct ib_pd *ibpd, int access) |