diff options
Diffstat (limited to 'drivers/infiniband/hw')
26 files changed, 206 insertions, 128 deletions
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index 6e7050ab9e16..14d7eeb09be6 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -300,16 +300,15 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node) const struct cpumask *node_mask, *proc_mask = tsk_cpus_allowed(current); struct cpu_mask_set *set = &dd->affinity->proc; - char buf[1024]; /* * check whether process/context affinity has already * been set */ if (cpumask_weight(proc_mask) == 1) { - scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(proc_mask)); - hfi1_cdbg(PROC, "PID %u %s affinity set to CPU %s", - current->pid, current->comm, buf); + hfi1_cdbg(PROC, "PID %u %s affinity set to CPU %*pbl", + current->pid, current->comm, + cpumask_pr_args(proc_mask)); /* * Mark the pre-set CPU as used. This is atomic so we don't * need the lock @@ -318,9 +317,9 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node) cpumask_set_cpu(cpu, &set->used); goto done; } else if (cpumask_weight(proc_mask) < cpumask_weight(&set->mask)) { - scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(proc_mask)); - hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %s", - current->pid, current->comm, buf); + hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %*pbl", + current->pid, current->comm, + cpumask_pr_args(proc_mask)); goto done; } @@ -356,8 +355,8 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node) cpumask_or(intrs, intrs, (dd->affinity->rcv_intr.gen ? &dd->affinity->rcv_intr.mask : &dd->affinity->rcv_intr.used)); - scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(intrs)); - hfi1_cdbg(PROC, "CPUs used by interrupts: %s", buf); + hfi1_cdbg(PROC, "CPUs used by interrupts: %*pbl", + cpumask_pr_args(intrs)); /* * If we don't have a NUMA node requested, preference is towards @@ -366,18 +365,16 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node) if (node == -1) node = dd->node; node_mask = cpumask_of_node(node); - scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(node_mask)); - hfi1_cdbg(PROC, "device on NUMA %u, CPUs %s", node, buf); + hfi1_cdbg(PROC, "device on NUMA %u, CPUs %*pbl", node, + cpumask_pr_args(node_mask)); /* diff will hold all unused cpus */ cpumask_andnot(diff, &set->mask, &set->used); - scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(diff)); - hfi1_cdbg(PROC, "unused CPUs (all) %s", buf); + hfi1_cdbg(PROC, "unused CPUs (all) %*pbl", cpumask_pr_args(diff)); /* get cpumask of available CPUs on preferred NUMA */ cpumask_and(mask, diff, node_mask); - scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(mask)); - hfi1_cdbg(PROC, "available cpus on NUMA %s", buf); + hfi1_cdbg(PROC, "available cpus on NUMA %*pbl", cpumask_pr_args(mask)); /* * At first, we don't want to place processes on the same @@ -395,8 +392,8 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node) cpumask_andnot(diff, &set->mask, &set->used); cpumask_andnot(mask, diff, node_mask); } - scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(mask)); - hfi1_cdbg(PROC, "possible CPUs for process %s", buf); + hfi1_cdbg(PROC, "possible CPUs for process %*pbl", + cpumask_pr_args(mask)); cpu = cpumask_first(mask); if (cpu >= nr_cpu_ids) /* empty */ diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 3b876da745a1..f5de85178055 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -1037,7 +1037,7 @@ static void dc_shutdown(struct hfi1_devdata *); static void dc_start(struct hfi1_devdata *); static int qos_rmt_entries(struct hfi1_devdata *dd, unsigned int *mp, unsigned int *np); -static void remove_full_mgmt_pkey(struct hfi1_pportdata *ppd); +static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd); /* * Error interrupt table entry. This is used as input to the interrupt @@ -6962,8 +6962,6 @@ void handle_link_down(struct work_struct *work) } reset_neighbor_info(ppd); - if (ppd->mgmt_allowed) - remove_full_mgmt_pkey(ppd); /* disable the port */ clear_rcvctrl(ppd->dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK); @@ -7070,12 +7068,16 @@ static void add_full_mgmt_pkey(struct hfi1_pportdata *ppd) __func__, ppd->pkeys[2], FULL_MGMT_P_KEY); ppd->pkeys[2] = FULL_MGMT_P_KEY; (void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0); + hfi1_event_pkey_change(ppd->dd, ppd->port); } -static void remove_full_mgmt_pkey(struct hfi1_pportdata *ppd) +static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd) { - ppd->pkeys[2] = 0; - (void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0); + if (ppd->pkeys[2] != 0) { + ppd->pkeys[2] = 0; + (void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0); + hfi1_event_pkey_change(ppd->dd, ppd->port); + } } /* @@ -7832,8 +7834,8 @@ static void handle_dcc_err(struct hfi1_devdata *dd, u32 unused, u64 reg) * save first 2 flits in the packet that caused * the error */ - dd->err_info_rcvport.packet_flit1 = hdr0; - dd->err_info_rcvport.packet_flit2 = hdr1; + dd->err_info_rcvport.packet_flit1 = hdr0; + dd->err_info_rcvport.packet_flit2 = hdr1; } switch (info) { case 1: @@ -9168,6 +9170,13 @@ int start_link(struct hfi1_pportdata *ppd) return 0; } + /* + * FULL_MGMT_P_KEY is cleared from the pkey table, so that the + * pkey table can be configured properly if the HFI unit is connected + * to switch port with MgmtAllowed=NO + */ + clear_full_mgmt_pkey(ppd); + return set_link_state(ppd, HLS_DN_POLL); } @@ -9777,7 +9786,7 @@ static void set_send_length(struct hfi1_pportdata *ppd) u64 len1 = 0, len2 = (((dd->vld[15].mtu + max_hb) >> 2) & SEND_LEN_CHECK1_LEN_VL15_MASK) << SEND_LEN_CHECK1_LEN_VL15_SHIFT; - int i; + int i, j; u32 thres; for (i = 0; i < ppd->vls_supported; i++) { @@ -9801,7 +9810,10 @@ static void set_send_length(struct hfi1_pportdata *ppd) sc_mtu_to_threshold(dd->vld[i].sc, dd->vld[i].mtu, dd->rcd[0]->rcvhdrqentsize)); - sc_set_cr_threshold(dd->vld[i].sc, thres); + for (j = 0; j < INIT_SC_PER_VL; j++) + sc_set_cr_threshold( + pio_select_send_context_vl(dd, j, i), + thres); } thres = min(sc_percent_to_threshold(dd->vld[15].sc, 50), sc_mtu_to_threshold(dd->vld[15].sc, @@ -11906,7 +11918,7 @@ static void update_synth_timer(unsigned long opaque) hfi1_cdbg(CNTR, "[%d] No update necessary", dd->unit); } -mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME); + mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME); } #define C_MAX_NAME 13 /* 12 chars + one for /0 */ diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 7a5b0e676cc7..c702a009608f 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -203,6 +203,9 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd, switch (cmd) { case HFI1_IOCTL_ASSIGN_CTXT: + if (uctxt) + return -EINVAL; + if (copy_from_user(&uinfo, (struct hfi1_user_info __user *)arg, sizeof(uinfo))) diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index 5cc492e5776d..eed971ccd2a1 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -1337,7 +1337,7 @@ static void cleanup_device_data(struct hfi1_devdata *dd) dma_free_coherent(&dd->pcidev->dev, sizeof(u64), (void *)dd->rcvhdrtail_dummy_kvaddr, dd->rcvhdrtail_dummy_physaddr); - dd->rcvhdrtail_dummy_kvaddr = NULL; + dd->rcvhdrtail_dummy_kvaddr = NULL; } for (ctxt = 0; tmp && ctxt < dd->num_rcv_contexts; ctxt++) { @@ -1383,7 +1383,7 @@ static void postinit_cleanup(struct hfi1_devdata *dd) static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { int ret = 0, j, pidx, initfail; - struct hfi1_devdata *dd = NULL; + struct hfi1_devdata *dd = ERR_PTR(-EINVAL); struct hfi1_pportdata *ppd; /* First, lock the non-writable module parameters */ diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c index 219029576ba0..fca07a1d6c28 100644 --- a/drivers/infiniband/hw/hfi1/mad.c +++ b/drivers/infiniband/hw/hfi1/mad.c @@ -78,6 +78,16 @@ static inline void clear_opa_smp_data(struct opa_smp *smp) memset(data, 0, size); } +void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port) +{ + struct ib_event event; + + event.event = IB_EVENT_PKEY_CHANGE; + event.device = &dd->verbs_dev.rdi.ibdev; + event.element.port_num = port; + ib_dispatch_event(&event); +} + static void send_trap(struct hfi1_ibport *ibp, void *data, unsigned len) { struct ib_mad_send_buf *send_buf; @@ -1418,15 +1428,10 @@ static int set_pkeys(struct hfi1_devdata *dd, u8 port, u16 *pkeys) } if (changed) { - struct ib_event event; - (void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0); - - event.event = IB_EVENT_PKEY_CHANGE; - event.device = &dd->verbs_dev.rdi.ibdev; - event.element.port_num = port; - ib_dispatch_event(&event); + hfi1_event_pkey_change(dd, port); } + return 0; } diff --git a/drivers/infiniband/hw/hfi1/mad.h b/drivers/infiniband/hw/hfi1/mad.h index 55ee08675333..8b734aaae88a 100644 --- a/drivers/infiniband/hw/hfi1/mad.h +++ b/drivers/infiniband/hw/hfi1/mad.h @@ -434,4 +434,6 @@ struct sc2vlnt { COUNTER_MASK(1, 3) | \ COUNTER_MASK(1, 4)) +void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port); + #endif /* _HFI1_MAD_H */ diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index d5edb1afbb8f..d4022450b73f 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -995,7 +995,7 @@ static void sc_wait_for_packet_egress(struct send_context *sc, int pause) /* counter is reset if occupancy count changes */ if (reg != reg_prev) loop = 0; - if (loop > 500) { + if (loop > 50000) { /* timed out - bounce the link */ dd_dev_err(dd, "%s: context %u(%u) timeout waiting for packets to egress, remaining count %u, bouncing link\n", @@ -1798,6 +1798,21 @@ static void pio_map_rcu_callback(struct rcu_head *list) } /* + * Set credit return threshold for the kernel send context + */ +static void set_threshold(struct hfi1_devdata *dd, int scontext, int i) +{ + u32 thres; + + thres = min(sc_percent_to_threshold(dd->kernel_send_context[scontext], + 50), + sc_mtu_to_threshold(dd->kernel_send_context[scontext], + dd->vld[i].mtu, + dd->rcd[0]->rcvhdrqentsize)); + sc_set_cr_threshold(dd->kernel_send_context[scontext], thres); +} + +/* * pio_map_init - called when #vls change * @dd: hfi1_devdata * @port: port number @@ -1872,11 +1887,16 @@ int pio_map_init(struct hfi1_devdata *dd, u8 port, u8 num_vls, u8 *vl_scontexts) if (!newmap->map[i]) goto bail; newmap->map[i]->mask = (1 << ilog2(sz)) - 1; - /* assign send contexts */ + /* + * assign send contexts and + * adjust credit return threshold + */ for (j = 0; j < sz; j++) { - if (dd->kernel_send_context[scontext]) + if (dd->kernel_send_context[scontext]) { newmap->map[i]->ksc[j] = dd->kernel_send_context[scontext]; + set_threshold(dd, scontext, i); + } if (++scontext >= first_scontext + vl_scontexts[i]) /* wrap back to first send context */ diff --git a/drivers/infiniband/hw/hfi1/qsfp.c b/drivers/infiniband/hw/hfi1/qsfp.c index 2441669f0817..9fb561682c66 100644 --- a/drivers/infiniband/hw/hfi1/qsfp.c +++ b/drivers/infiniband/hw/hfi1/qsfp.c @@ -579,7 +579,8 @@ int qsfp_dump(struct hfi1_pportdata *ppd, char *buf, int len) if (ppd->qsfp_info.cache_valid) { if (QSFP_IS_CU(cache[QSFP_MOD_TECH_OFFS])) - sprintf(lenstr, "%dM ", cache[QSFP_MOD_LEN_OFFS]); + snprintf(lenstr, sizeof(lenstr), "%dM ", + cache[QSFP_MOD_LEN_OFFS]); power_byte = cache[QSFP_MOD_PWR_OFFS]; sofar += scnprintf(buf + sofar, len - sofar, "PWR:%.3sW\n", diff --git a/drivers/infiniband/hw/hfi1/trace.c b/drivers/infiniband/hw/hfi1/trace.c index 79b2952c0dfb..4cfb13771897 100644 --- a/drivers/infiniband/hw/hfi1/trace.c +++ b/drivers/infiniband/hw/hfi1/trace.c @@ -214,19 +214,6 @@ const char *print_u32_array( return ret; } -const char *print_u64_array( - struct trace_seq *p, - u64 *arr, int len) -{ - int i; - const char *ret = trace_seq_buffer_ptr(p); - - for (i = 0; i < len; i++) - trace_seq_printf(p, "%s0x%016llx", i == 0 ? "" : " ", arr[i]); - trace_seq_putc(p, 0); - return ret; -} - __hfi1_trace_fn(PKT); __hfi1_trace_fn(PROC); __hfi1_trace_fn(SDMA); diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index 29f4795f866c..47ffd273ecbd 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -183,7 +183,7 @@ struct user_sdma_iovec { struct sdma_mmu_node *node; }; -#define SDMA_CACHE_NODE_EVICT BIT(0) +#define SDMA_CACHE_NODE_EVICT 0 struct sdma_mmu_node { struct mmu_rb_node rb; @@ -1355,11 +1355,11 @@ static int set_txreq_header(struct user_sdma_request *req, */ SDMA_DBG(req, "TID offset %ubytes %uunits om%u", req->tidoffset, req->tidoffset / req->omfactor, - !!(req->omfactor - KDETH_OM_SMALL)); + req->omfactor != KDETH_OM_SMALL); KDETH_SET(hdr->kdeth.ver_tid_offset, OFFSET, req->tidoffset / req->omfactor); KDETH_SET(hdr->kdeth.ver_tid_offset, OM, - !!(req->omfactor - KDETH_OM_SMALL)); + req->omfactor != KDETH_OM_SMALL); } done: trace_hfi1_sdma_user_header(pq->dd, pq->ctxt, pq->subctxt, diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.c b/drivers/infiniband/hw/hfi1/verbs_txreq.c index bc95c4112c61..d8fb056526f8 100644 --- a/drivers/infiniband/hw/hfi1/verbs_txreq.c +++ b/drivers/infiniband/hw/hfi1/verbs_txreq.c @@ -92,11 +92,10 @@ void hfi1_put_txreq(struct verbs_txreq *tx) struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev, struct rvt_qp *qp) + __must_hold(&qp->s_lock) { struct verbs_txreq *tx = ERR_PTR(-EBUSY); - unsigned long flags; - spin_lock_irqsave(&qp->s_lock, flags); write_seqlock(&dev->iowait_lock); if (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) { struct hfi1_qp_priv *priv; @@ -116,7 +115,6 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev, } out: write_sequnlock(&dev->iowait_lock); - spin_unlock_irqrestore(&qp->s_lock, flags); return tx; } diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.h b/drivers/infiniband/hw/hfi1/verbs_txreq.h index 1cf69b2fe4a5..a1d6e0807f97 100644 --- a/drivers/infiniband/hw/hfi1/verbs_txreq.h +++ b/drivers/infiniband/hw/hfi1/verbs_txreq.h @@ -73,6 +73,7 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev, static inline struct verbs_txreq *get_txreq(struct hfi1_ibdev *dev, struct rvt_qp *qp) + __must_hold(&qp->slock) { struct verbs_txreq *tx; struct hfi1_qp_priv *priv = qp->priv; diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h index 8b9532034558..b738acdb9b02 100644 --- a/drivers/infiniband/hw/i40iw/i40iw.h +++ b/drivers/infiniband/hw/i40iw/i40iw.h @@ -113,6 +113,8 @@ #define IW_HMC_OBJ_TYPE_NUM ARRAY_SIZE(iw_hmc_obj_types) #define IW_CFG_FPM_QP_COUNT 32768 +#define I40IW_MAX_PAGES_PER_FMR 512 +#define I40IW_MIN_PAGES_PER_FMR 1 #define I40IW_MTU_TO_MSS 40 #define I40IW_DEFAULT_MSS 1460 diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 02a735b64208..33959ed14563 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -79,6 +79,7 @@ static int i40iw_query_device(struct ib_device *ibdev, props->max_qp_init_rd_atom = props->max_qp_rd_atom; props->atomic_cap = IB_ATOMIC_NONE; props->max_map_per_fmr = 1; + props->max_fast_reg_page_list_len = I40IW_MAX_PAGES_PER_FMR; return 0; } @@ -1527,7 +1528,7 @@ static struct ib_mr *i40iw_alloc_mr(struct ib_pd *pd, mutex_lock(&iwdev->pbl_mutex); status = i40iw_get_pble(&iwdev->sc_dev, iwdev->pble_rsrc, palloc, iwmr->page_cnt); mutex_unlock(&iwdev->pbl_mutex); - if (!status) + if (status) goto err1; if (palloc->level != I40IW_LEVEL_1) @@ -2149,6 +2150,7 @@ static int i40iw_post_send(struct ib_qp *ibqp, struct i40iw_sc_dev *dev = &iwqp->iwdev->sc_dev; struct i40iw_fast_reg_stag_info info; + memset(&info, 0, sizeof(info)); info.access_rights = I40IW_ACCESS_FLAGS_LOCALREAD; info.access_rights |= i40iw_get_user_access(flags); info.stag_key = reg_wr(ib_wr)->key & 0xff; @@ -2158,10 +2160,14 @@ static int i40iw_post_send(struct ib_qp *ibqp, info.addr_type = I40IW_ADDR_TYPE_VA_BASED; info.va = (void *)(uintptr_t)iwmr->ibmr.iova; info.total_len = iwmr->ibmr.length; + info.reg_addr_pa = *(u64 *)palloc->level1.addr; info.first_pm_pbl_index = palloc->level1.idx; info.local_fence = ib_wr->send_flags & IB_SEND_FENCE; info.signaled = ib_wr->send_flags & IB_SEND_SIGNALED; + if (iwmr->npages > I40IW_MIN_PAGES_PER_FMR) + info.chunk_size = 1; + if (page_shift == 21) info.page_size = 1; /* 2M page */ @@ -2327,13 +2333,16 @@ static int i40iw_req_notify_cq(struct ib_cq *ibcq, { struct i40iw_cq *iwcq; struct i40iw_cq_uk *ukcq; - enum i40iw_completion_notify cq_notify = IW_CQ_COMPL_SOLICITED; + unsigned long flags; + enum i40iw_completion_notify cq_notify = IW_CQ_COMPL_EVENT; iwcq = (struct i40iw_cq *)ibcq; ukcq = &iwcq->sc_cq.cq_uk; - if (notify_flags == IB_CQ_NEXT_COMP) - cq_notify = IW_CQ_COMPL_EVENT; + if (notify_flags == IB_CQ_SOLICITED) + cq_notify = IW_CQ_COMPL_SOLICITED; + spin_lock_irqsave(&iwcq->lock, flags); ukcq->ops.iw_cq_request_notification(ukcq, cq_notify); + spin_unlock_irqrestore(&iwcq->lock, flags); return 0; } diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c index 105246fba2e7..5fc623362731 100644 --- a/drivers/infiniband/hw/mlx4/ah.c +++ b/drivers/infiniband/hw/mlx4/ah.c @@ -47,6 +47,7 @@ static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr, ah->av.ib.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24)); ah->av.ib.g_slid = ah_attr->src_path_bits; + ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28); if (ah_attr->ah_flags & IB_AH_GRH) { ah->av.ib.g_slid |= 0x80; ah->av.ib.gid_index = ah_attr->grh.sgid_index; @@ -64,7 +65,6 @@ static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr, !(1 << ah->av.ib.stat_rate & dev->caps.stat_rate_support)) --ah->av.ib.stat_rate; } - ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28); return &ah->ibah; } diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index d68f506c1922..9c2e53d28f98 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -527,7 +527,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port, tun_tx_ix = (++tun_qp->tx_ix_head) & (MLX4_NUM_TUNNEL_BUFS - 1); spin_unlock(&tun_qp->tx_lock); if (ret) - goto out; + goto end; tun_mad = (struct mlx4_rcv_tunnel_mad *) (tun_qp->tx_ring[tun_tx_ix].buf.addr); if (tun_qp->tx_ring[tun_tx_ix].ah) @@ -596,9 +596,15 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port, wr.wr.send_flags = IB_SEND_SIGNALED; ret = ib_post_send(src_qp, &wr.wr, &bad_wr); -out: - if (ret) - ib_destroy_ah(ah); + if (!ret) + return 0; + out: + spin_lock(&tun_qp->tx_lock); + tun_qp->tx_ix_tail++; + spin_unlock(&tun_qp->tx_lock); + tun_qp->tx_ring[tun_tx_ix].ah = NULL; +end: + ib_destroy_ah(ah); return ret; } @@ -1326,9 +1332,15 @@ int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port, ret = ib_post_send(send_qp, &wr.wr, &bad_wr); + if (!ret) + return 0; + + spin_lock(&sqp->tx_lock); + sqp->tx_ix_tail++; + spin_unlock(&sqp->tx_lock); + sqp->tx_ring[wire_tx_ix].ah = NULL; out: - if (ret) - ib_destroy_ah(ah); + ib_destroy_ah(ah); return ret; } diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index b01ef6eee6e8..42a46078d7d5 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -505,9 +505,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2B; else props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2A; - if (dev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED) - props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING; } + if (dev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED) + props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING; props->device_cap_flags |= IB_DEVICE_RAW_IP_CSUM; @@ -1704,6 +1704,9 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, struct mlx4_dev *dev = (to_mdev(qp->device))->dev; int is_bonded = mlx4_is_bonded(dev); + if (flow_attr->port < 1 || flow_attr->port > qp->device->phys_port_cnt) + return ERR_PTR(-EINVAL); + if ((flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP) && (flow_attr->type != IB_FLOW_ATTR_NORMAL)) return ERR_PTR(-EOPNOTSUPP); diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index 6c5ac5d8f32f..29acda249612 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -139,7 +139,7 @@ struct mlx4_ib_mr { u32 max_pages; struct mlx4_mr mmr; struct ib_umem *umem; - void *pages_alloc; + size_t page_map_size; }; struct mlx4_ib_mw { diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c index 631272172a0b..5d73989d9771 100644 --- a/drivers/infiniband/hw/mlx4/mr.c +++ b/drivers/infiniband/hw/mlx4/mr.c @@ -277,20 +277,23 @@ mlx4_alloc_priv_pages(struct ib_device *device, struct mlx4_ib_mr *mr, int max_pages) { - int size = max_pages * sizeof(u64); - int add_size; int ret; - add_size = max_t(int, MLX4_MR_PAGES_ALIGN - ARCH_KMALLOC_MINALIGN, 0); + /* Ensure that size is aligned to DMA cacheline + * requirements. + * max_pages is limited to MLX4_MAX_FAST_REG_PAGES + * so page_map_size will never cross PAGE_SIZE. + */ + mr->page_map_size = roundup(max_pages * sizeof(u64), + MLX4_MR_PAGES_ALIGN); - mr->pages_alloc = kzalloc(size + add_size, GFP_KERNEL); - if (!mr->pages_alloc) + /* Prevent cross page boundary allocation. */ + mr->pages = (__be64 *)get_zeroed_page(GFP_KERNEL); + if (!mr->pages) return -ENOMEM; - mr->pages = PTR_ALIGN(mr->pages_alloc, MLX4_MR_PAGES_ALIGN); - mr->page_map = dma_map_single(device->dma_device, mr->pages, - size, DMA_TO_DEVICE); + mr->page_map_size, DMA_TO_DEVICE); if (dma_mapping_error(device->dma_device, mr->page_map)) { ret = -ENOMEM; @@ -298,9 +301,9 @@ mlx4_alloc_priv_pages(struct ib_device *device, } return 0; -err: - kfree(mr->pages_alloc); +err: + free_page((unsigned long)mr->pages); return ret; } @@ -309,11 +312,10 @@ mlx4_free_priv_pages(struct mlx4_ib_mr *mr) { if (mr->pages) { struct ib_device *device = mr->ibmr.device; - int size = mr->max_pages * sizeof(u64); dma_unmap_single(device->dma_device, mr->page_map, - size, DMA_TO_DEVICE); - kfree(mr->pages_alloc); + mr->page_map_size, DMA_TO_DEVICE); + free_page((unsigned long)mr->pages); mr->pages = NULL; } } @@ -537,14 +539,12 @@ int mlx4_ib_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents, mr->npages = 0; ib_dma_sync_single_for_cpu(ibmr->device, mr->page_map, - sizeof(u64) * mr->max_pages, - DMA_TO_DEVICE); + mr->page_map_size, DMA_TO_DEVICE); rc = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, mlx4_set_page); ib_dma_sync_single_for_device(ibmr->device, mr->page_map, - sizeof(u64) * mr->max_pages, - DMA_TO_DEVICE); + mr->page_map_size, DMA_TO_DEVICE); return rc; } diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 81b0e1fbec1d..8db8405c1e99 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -362,7 +362,7 @@ static int send_wqe_overhead(enum mlx4_ib_qp_type type, u32 flags) sizeof (struct mlx4_wqe_raddr_seg); case MLX4_IB_QPT_RC: return sizeof (struct mlx4_wqe_ctrl_seg) + - sizeof (struct mlx4_wqe_atomic_seg) + + sizeof (struct mlx4_wqe_masked_atomic_seg) + sizeof (struct mlx4_wqe_raddr_seg); case MLX4_IB_QPT_SMI: case MLX4_IB_QPT_GSI: @@ -1191,8 +1191,10 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd, { err = create_qp_common(to_mdev(pd->device), pd, init_attr, udata, 0, &qp, gfp); - if (err) + if (err) { + kfree(qp); return ERR_PTR(err); + } qp->ibqp.qp_num = qp->mqp.qpn; qp->xrcdn = xrcdn; diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index dabcc65bd65e..9c0e67bd2ba7 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -822,7 +822,8 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, int eqn; int err; - if (entries < 0) + if (entries < 0 || + (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)))) return ERR_PTR(-EINVAL); if (check_cq_create_flags(attr->flags)) @@ -1168,11 +1169,16 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata) return -ENOSYS; } - if (entries < 1) + if (entries < 1 || + entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))) { + mlx5_ib_warn(dev, "wrong entries number %d, max %d\n", + entries, + 1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)); return -EINVAL; + } entries = roundup_pow_of_two(entries + 1); - if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)) + 1) + if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)) + 1) return -EINVAL; if (entries == ibcq->cqe + 1) diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index 1534af113058..364aab9f3c9e 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -121,7 +121,7 @@ static void pma_cnt_ext_assign(struct ib_pma_portcounters_ext *pma_cnt_ext, pma_cnt_ext->port_xmit_data = cpu_to_be64(MLX5_SUM_CNT(out, transmitted_ib_unicast.octets, transmitted_ib_multicast.octets) >> 2); - pma_cnt_ext->port_xmit_data = + pma_cnt_ext->port_rcv_data = cpu_to_be64(MLX5_SUM_CNT(out, received_ib_unicast.octets, received_ib_multicast.octets) >> 2); pma_cnt_ext->port_xmit_packets = diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index c72797cd9e4f..b48ad85315dc 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -524,6 +524,9 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, MLX5_CAP_ETH(dev->mdev, scatter_fcs)) props->device_cap_flags |= IB_DEVICE_RAW_SCATTER_FCS; + if (mlx5_get_flow_namespace(dev->mdev, MLX5_FLOW_NAMESPACE_BYPASS)) + props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING; + props->vendor_part_id = mdev->pdev->device; props->hw_ver = mdev->pdev->revision; @@ -915,7 +918,8 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, num_uars = req.total_num_uuars / MLX5_NON_FP_BF_REGS_PER_PAGE; gross_uuars = num_uars * MLX5_BF_REGS_PER_PAGE; resp.qp_tab_size = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp); - resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size); + if (mlx5_core_is_pf(dev->mdev) && MLX5_CAP_GEN(dev->mdev, bf)) + resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size); resp.cache_line_size = L1_CACHE_BYTES; resp.max_sq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq); resp.max_rq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq); @@ -988,7 +992,14 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, if (field_avail(typeof(resp), cqe_version, udata->outlen)) resp.response_length += sizeof(resp.cqe_version); - if (field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) { + /* + * We don't want to expose information from the PCI bar that is located + * after 4096 bytes, so if the arch only supports larger pages, let's + * pretend we don't support reading the HCA's core clock. This is also + * forced by mmap function. + */ + if (PAGE_SIZE <= 4096 && + field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) { resp.comp_mask |= MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET; resp.hca_core_clock_offset = @@ -1798,7 +1809,7 @@ static ssize_t show_fw_ver(struct device *device, struct device_attribute *attr, { struct mlx5_ib_dev *dev = container_of(device, struct mlx5_ib_dev, ib_dev.dev); - return sprintf(buf, "%d.%d.%d\n", fw_rev_maj(dev->mdev), + return sprintf(buf, "%d.%d.%04d\n", fw_rev_maj(dev->mdev), fw_rev_min(dev->mdev), fw_rev_sub(dev->mdev)); } @@ -1866,14 +1877,11 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context, break; case MLX5_DEV_EVENT_PORT_DOWN: + case MLX5_DEV_EVENT_PORT_INITIALIZED: ibev.event = IB_EVENT_PORT_ERR; port = (u8)param; break; - case MLX5_DEV_EVENT_PORT_INITIALIZED: - /* not used by ULPs */ - return; - case MLX5_DEV_EVENT_LID_CHANGE: ibev.event = IB_EVENT_LID_CHANGE; port = (u8)param; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 504117657d41..ce0a7ab35a22 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -235,6 +235,8 @@ static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap, qp->rq.max_gs = 0; qp->rq.wqe_cnt = 0; qp->rq.wqe_shift = 0; + cap->max_recv_wr = 0; + cap->max_recv_sge = 0; } else { if (ucmd) { qp->rq.wqe_cnt = ucmd->rq_wqe_count; @@ -1851,13 +1853,15 @@ static int modify_raw_packet_eth_prio(struct mlx5_core_dev *dev, static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, const struct ib_ah_attr *ah, struct mlx5_qp_path *path, u8 port, int attr_mask, - u32 path_flags, const struct ib_qp_attr *attr) + u32 path_flags, const struct ib_qp_attr *attr, + bool alt) { enum rdma_link_layer ll = rdma_port_get_link_layer(&dev->ib_dev, port); int err; if (attr_mask & IB_QP_PKEY_INDEX) - path->pkey_index = attr->pkey_index; + path->pkey_index = cpu_to_be16(alt ? attr->alt_pkey_index : + attr->pkey_index); if (ah->ah_flags & IB_AH_GRH) { if (ah->grh.sgid_index >= @@ -1877,9 +1881,9 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, ah->grh.sgid_index); path->dci_cfi_prio_sl = (ah->sl & 0x7) << 4; } else { - path->fl = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0; - path->free_ar = (path_flags & MLX5_PATH_FLAG_FREE_AR) ? 0x80 : - 0; + path->fl_free_ar = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0; + path->fl_free_ar |= + (path_flags & MLX5_PATH_FLAG_FREE_AR) ? 0x40 : 0; path->rlid = cpu_to_be16(ah->dlid); path->grh_mlid = ah->src_path_bits & 0x7f; if (ah->ah_flags & IB_AH_GRH) @@ -1903,7 +1907,7 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, path->port = port; if (attr_mask & IB_QP_TIMEOUT) - path->ackto_lt = attr->timeout << 3; + path->ackto_lt = (alt ? attr->alt_timeout : attr->timeout) << 3; if ((qp->ibqp.qp_type == IB_QPT_RAW_PACKET) && qp->sq.wqe_cnt) return modify_raw_packet_eth_prio(dev->mdev, @@ -2264,7 +2268,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, context->log_pg_sz_remote_qpn = cpu_to_be32(attr->dest_qp_num); if (attr_mask & IB_QP_PKEY_INDEX) - context->pri_path.pkey_index = attr->pkey_index; + context->pri_path.pkey_index = cpu_to_be16(attr->pkey_index); /* todo implement counter_index functionality */ @@ -2277,7 +2281,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, if (attr_mask & IB_QP_AV) { err = mlx5_set_path(dev, qp, &attr->ah_attr, &context->pri_path, attr_mask & IB_QP_PORT ? attr->port_num : qp->port, - attr_mask, 0, attr); + attr_mask, 0, attr, false); if (err) goto out; } @@ -2288,7 +2292,9 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, if (attr_mask & IB_QP_ALT_PATH) { err = mlx5_set_path(dev, qp, &attr->alt_ah_attr, &context->alt_path, - attr->alt_port_num, attr_mask, 0, attr); + attr->alt_port_num, + attr_mask | IB_QP_PKEY_INDEX | IB_QP_TIMEOUT, + 0, attr, true); if (err) goto out; } @@ -3326,10 +3332,11 @@ static u8 get_fence(u8 fence, struct ib_send_wr *wr) return MLX5_FENCE_MODE_SMALL_AND_FENCE; else return fence; - - } else { - return 0; + } else if (unlikely(wr->send_flags & IB_SEND_FENCE)) { + return MLX5_FENCE_MODE_FENCE; } + + return 0; } static int begin_wqe(struct mlx5_ib_qp *qp, void **seg, @@ -4013,11 +4020,12 @@ static int query_qp_attr(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, if (qp->ibqp.qp_type == IB_QPT_RC || qp->ibqp.qp_type == IB_QPT_UC) { to_ib_ah_attr(dev, &qp_attr->ah_attr, &context->pri_path); to_ib_ah_attr(dev, &qp_attr->alt_ah_attr, &context->alt_path); - qp_attr->alt_pkey_index = context->alt_path.pkey_index & 0x7f; + qp_attr->alt_pkey_index = + be16_to_cpu(context->alt_path.pkey_index); qp_attr->alt_port_num = qp_attr->alt_ah_attr.port_num; } - qp_attr->pkey_index = context->pri_path.pkey_index & 0x7f; + qp_attr->pkey_index = be16_to_cpu(context->pri_path.pkey_index); qp_attr->port_num = context->pri_path.port; /* qp_attr->en_sqd_async_notify is only applicable in modify qp */ @@ -4079,17 +4087,19 @@ int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, qp_attr->cap.max_recv_sge = qp->rq.max_gs; if (!ibqp->uobject) { - qp_attr->cap.max_send_wr = qp->sq.wqe_cnt; + qp_attr->cap.max_send_wr = qp->sq.max_post; qp_attr->cap.max_send_sge = qp->sq.max_gs; + qp_init_attr->qp_context = ibqp->qp_context; } else { qp_attr->cap.max_send_wr = 0; qp_attr->cap.max_send_sge = 0; } - /* We don't support inline sends for kernel QPs (yet), and we - * don't know what userspace's value should be. - */ - qp_attr->cap.max_inline_data = 0; + qp_init_attr->qp_type = ibqp->qp_type; + qp_init_attr->recv_cq = ibqp->recv_cq; + qp_init_attr->send_cq = ibqp->send_cq; + qp_init_attr->srq = ibqp->srq; + qp_attr->cap.max_inline_data = qp->max_inline_data; qp_init_attr->cap = qp_attr->cap; diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index ff946d5f59e4..382466a90da7 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -2178,6 +2178,11 @@ static ssize_t qib_write(struct file *fp, const char __user *data, switch (cmd.type) { case QIB_CMD_ASSIGN_CTXT: + if (rcd) { + ret = -EINVAL; + goto bail; + } + ret = qib_assign_ctxt(fp, &cmd.cmd.user_info); if (ret) goto bail; diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c index 7209fbc03ccb..a0b6ebee4d8a 100644 --- a/drivers/infiniband/hw/usnic/usnic_uiom.c +++ b/drivers/infiniband/hw/usnic/usnic_uiom.c @@ -36,7 +36,6 @@ #include <linux/dma-mapping.h> #include <linux/sched.h> #include <linux/hugetlb.h> -#include <linux/dma-attrs.h> #include <linux/iommu.h> #include <linux/workqueue.h> #include <linux/list.h> @@ -112,10 +111,6 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable, int i; int flags; dma_addr_t pa; - DEFINE_DMA_ATTRS(attrs); - - if (dmasync) - dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs); if (!can_do_mlock()) return -EPERM; |