Commit 38137a51 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband 

Pull infiniband/rdma updates from Roland Dreier:

 - mostly cxgb4 fixes unblocked by the merge of some prerequisites via
   the net tree

 - drop deprecated MSI-X API use.

 - a couple other miscellaneous things.

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
  RDMA/cxgb4: Fix over-dereference when terminating
  RDMA/cxgb4: Use uninitialized_var()
  RDMA/cxgb4: Add missing debug stats
  RDMA/cxgb4: Initialize reserved fields in a FW work request
  RDMA/cxgb4: Use pr_warn_ratelimited
  RDMA/cxgb4: Max fastreg depth depends on DSGL support
  RDMA/cxgb4: SQ flush fix
  RDMA/cxgb4: rmb() after reading valid gen bit
  RDMA/cxgb4: Endpoint timeout fixes
  RDMA/cxgb4: Use the BAR2/WC path for kernel QPs and T5 devices
  IB/mlx5: Add block multicast loopback support
  IB/mthca: Use pci_enable_msix_exact() instead of pci_enable_msix()
  IB/qib: Use pci_enable_msix_range() instead of pci_enable_msix()
parents 64ee9f32 5ae2866f

drivers/infiniband/hw/cxgb4/cm.c

+56 −33
Original line number Diff line number Diff line
@@ -173,12 +173,15 @@ static void start_ep_timer(struct c4iw_ep *ep) 
	add_timer(&ep->timer);

}



static void stop_ep_timer(struct c4iw_ep *ep)

static int stop_ep_timer(struct c4iw_ep *ep)

{

	PDBG("%s ep %p stopping\n", __func__, ep);

	del_timer_sync(&ep->timer);

	if (!test_and_set_bit(TIMEOUT, &ep->com.flags))

	if (!test_and_set_bit(TIMEOUT, &ep->com.flags)) {

		c4iw_put_ep(&ep->com);

		return 0;

	}

	return 1;

}



static int c4iw_l2t_send(struct c4iw_rdev *rdev, struct sk_buff *skb,
@@ -1165,12 +1168,11 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb) 
	PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);



	/*

	 * Stop mpa timer.  If it expired, then the state has

	 * changed and we bail since ep_timeout already aborted

	 * the connection.

	 * Stop mpa timer.  If it expired, then

	 * we ignore the MPA reply.  process_timeout()

	 * will abort the connection.

	 */

	stop_ep_timer(ep);

	if (ep->com.state != MPA_REQ_SENT)

	if (stop_ep_timer(ep))

		return;



	/*
@@ -1375,15 +1377,12 @@ static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) 


	PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);



	if (ep->com.state != MPA_REQ_WAIT)

		return;



	/*

	 * If we get more than the supported amount of private data

	 * then we must fail this connection.

	 */

	if (ep->mpa_pkt_len + skb->len > sizeof(ep->mpa_pkt)) {

		stop_ep_timer(ep);

		(void)stop_ep_timer(ep);

		abort_connection(ep, skb, GFP_KERNEL);

		return;

	}
@@ -1413,13 +1412,13 @@ static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) 
	if (mpa->revision > mpa_rev) {

		printk(KERN_ERR MOD "%s MPA version mismatch. Local = %d,"

		       " Received = %d\n", __func__, mpa_rev, mpa->revision);

		stop_ep_timer(ep);

		(void)stop_ep_timer(ep);

		abort_connection(ep, skb, GFP_KERNEL);

		return;

	}



	if (memcmp(mpa->key, MPA_KEY_REQ, sizeof(mpa->key))) {

		stop_ep_timer(ep);

		(void)stop_ep_timer(ep);

		abort_connection(ep, skb, GFP_KERNEL);

		return;

	}
@@ -1430,7 +1429,7 @@ static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) 
	 * Fail if there's too much private data.

	 */

	if (plen > MPA_MAX_PRIVATE_DATA) {

		stop_ep_timer(ep);

		(void)stop_ep_timer(ep);

		abort_connection(ep, skb, GFP_KERNEL);

		return;

	}
@@ -1439,7 +1438,7 @@ static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) 
	 * If plen does not account for pkt size

	 */

	if (ep->mpa_pkt_len > (sizeof(*mpa) + plen)) {

		stop_ep_timer(ep);

		(void)stop_ep_timer(ep);

		abort_connection(ep, skb, GFP_KERNEL);

		return;

	}
@@ -1496,8 +1495,13 @@ static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) 
	     ep->mpa_attr.xmit_marker_enabled, ep->mpa_attr.version,

	     ep->mpa_attr.p2p_type);



	/*

	 * If the endpoint timer already expired, then we ignore

	 * the start request.  process_timeout() will abort

	 * the connection.

	 */

	if (!stop_ep_timer(ep)) {

		__state_set(&ep->com, MPA_REQ_RCVD);

	stop_ep_timer(ep);



		/* drive upcall */

		mutex_lock(&ep->parent_ep->com.mutex);
@@ -1508,6 +1512,7 @@ static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) 
			abort_connection(ep, skb, GFP_KERNEL);

		}

		mutex_unlock(&ep->parent_ep->com.mutex);

	}

	return;

}
@@ -2265,7 +2270,7 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb) 
		disconnect = 0;

		break;

	case MORIBUND:

		stop_ep_timer(ep);

		(void)stop_ep_timer(ep);

		if (ep->com.cm_id && ep->com.qp) {

			attrs.next_state = C4IW_QP_STATE_IDLE;

			c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
@@ -2325,10 +2330,10 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb) 
	case CONNECTING:

		break;

	case MPA_REQ_WAIT:

		stop_ep_timer(ep);

		(void)stop_ep_timer(ep);

		break;

	case MPA_REQ_SENT:

		stop_ep_timer(ep);

		(void)stop_ep_timer(ep);

		if (mpa_rev == 1 || (mpa_rev == 2 && ep->tried_with_mpa_v1))

			connect_reply_upcall(ep, -ECONNRESET);

		else {
@@ -2433,7 +2438,7 @@ static int close_con_rpl(struct c4iw_dev *dev, struct sk_buff *skb) 
		__state_set(&ep->com, MORIBUND);

		break;

	case MORIBUND:

		stop_ep_timer(ep);

		(void)stop_ep_timer(ep);

		if ((ep->com.cm_id) && (ep->com.qp)) {

			attrs.next_state = C4IW_QP_STATE_IDLE;

			c4iw_modify_qp(ep->com.qp->rhp,
@@ -3028,7 +3033,7 @@ int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp) 
		if (!test_and_set_bit(CLOSE_SENT, &ep->com.flags)) {

			close = 1;

			if (abrupt) {

				stop_ep_timer(ep);

				(void)stop_ep_timer(ep);

				ep->com.state = ABORTING;

			} else

				ep->com.state = MORIBUND;
@@ -3462,6 +3467,16 @@ static void process_timeout(struct c4iw_ep *ep) 
		__state_set(&ep->com, ABORTING);

		close_complete_upcall(ep, -ETIMEDOUT);

		break;

	case ABORTING:

	case DEAD:



		/*

		 * These states are expected if the ep timed out at the same

		 * time as another thread was calling stop_ep_timer().

		 * So we silently do nothing for these states.

		 */

		abort = 0;

		break;

	default:

		WARN(1, "%s unexpected state ep %p tid %u state %u\n",

			__func__, ep, ep->hwtid, ep->com.state);
@@ -3483,6 +3498,8 @@ static void process_timedout_eps(void) 


		tmp = timeout_list.next;

		list_del(tmp);

		tmp->next = NULL;

		tmp->prev = NULL;

		spin_unlock_irq(&timeout_lock);

		ep = list_entry(tmp, struct c4iw_ep, entry);

		process_timeout(ep);
@@ -3499,6 +3516,7 @@ static void process_work(struct work_struct *work) 
	unsigned int opcode;

	int ret;



	process_timedout_eps();

	while ((skb = skb_dequeue(&rxq))) {

		rpl = cplhdr(skb);

		dev = *((struct c4iw_dev **) (skb->cb + sizeof(void *)));
@@ -3508,9 +3526,9 @@ static void process_work(struct work_struct *work) 
		ret = work_handlers[opcode](dev, skb);

		if (!ret)

			kfree_skb(skb);

	}

		process_timedout_eps();

	}

}



static DECLARE_WORK(skb_work, process_work);
@@ -3521,9 +3539,14 @@ static void ep_timeout(unsigned long arg) 


	spin_lock(&timeout_lock);

	if (!test_and_set_bit(TIMEOUT, &ep->com.flags)) {

		/*

		 * Only insert if it is not already on the list.

		 */

		if (!ep->entry.next) {

			list_add_tail(&ep->entry, &timeout_list);

			kickit = 1;

		}

	}

	spin_unlock(&timeout_lock);

	if (kickit)

		queue_work(workq, &skb_work);

drivers/infiniband/hw/cxgb4/cq.c

+9 −15
Original line number Diff line number Diff line
@@ -235,15 +235,12 @@ int c4iw_flush_sq(struct c4iw_qp *qhp) 
	struct t4_cq *cq = &chp->cq;

	int idx;

	struct t4_swsqe *swsqe;

	int error = (qhp->attr.state != C4IW_QP_STATE_CLOSING &&

			qhp->attr.state != C4IW_QP_STATE_IDLE);



	if (wq->sq.flush_cidx == -1)

		wq->sq.flush_cidx = wq->sq.cidx;

	idx = wq->sq.flush_cidx;

	BUG_ON(idx >= wq->sq.size);

	while (idx != wq->sq.pidx) {

		if (error) {

		swsqe = &wq->sq.sw_sq[idx];

		BUG_ON(swsqe->flushed);

		swsqe->flushed = 1;
@@ -253,9 +250,6 @@ int c4iw_flush_sq(struct c4iw_qp *qhp) 
			advance_oldest_read(wq);

		}

		flushed++;

		} else {

			t4_sq_consume(wq);

		}

		if (++idx == wq->sq.size)

			idx = 0;

	}
@@ -678,7 +672,7 @@ skip_cqe: 
static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc)

{

	struct c4iw_qp *qhp = NULL;

	struct t4_cqe cqe = {0, 0}, *rd_cqe;

	struct t4_cqe uninitialized_var(cqe), *rd_cqe;

	struct t4_wq *wq;

	u32 credit = 0;

	u8 cqe_flushed;

drivers/infiniband/hw/cxgb4/device.c

+33 −8
Original line number Diff line number Diff line
@@ -682,6 +682,9 @@ static void c4iw_dealloc(struct uld_ctx *ctx) 
	idr_destroy(&ctx->dev->hwtid_idr);

	idr_destroy(&ctx->dev->stid_idr);

	idr_destroy(&ctx->dev->atid_idr);

	if (ctx->dev->rdev.bar2_kva)

		iounmap(ctx->dev->rdev.bar2_kva);

	if (ctx->dev->rdev.oc_mw_kva)

		iounmap(ctx->dev->rdev.oc_mw_kva);

	ib_dealloc_device(&ctx->dev->ibdev);

	ctx->dev = NULL;
@@ -722,11 +725,31 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop) 
	}

	devp->rdev.lldi = *infop;



	devp->rdev.oc_mw_pa = pci_resource_start(devp->rdev.lldi.pdev, 2) +

		(pci_resource_len(devp->rdev.lldi.pdev, 2) -

		 roundup_pow_of_two(devp->rdev.lldi.vr->ocq.size));

	/*

	 * For T5 devices, we map all of BAR2 with WC.

	 * For T4 devices with onchip qp mem, we map only that part

	 * of BAR2 with WC.

	 */

	devp->rdev.bar2_pa = pci_resource_start(devp->rdev.lldi.pdev, 2);

	if (is_t5(devp->rdev.lldi.adapter_type)) {

		devp->rdev.bar2_kva = ioremap_wc(devp->rdev.bar2_pa,

			pci_resource_len(devp->rdev.lldi.pdev, 2));

		if (!devp->rdev.bar2_kva) {

			pr_err(MOD "Unable to ioremap BAR2\n");

			return ERR_PTR(-EINVAL);

		}

	} else if (ocqp_supported(infop)) {

		devp->rdev.oc_mw_pa =

			pci_resource_start(devp->rdev.lldi.pdev, 2) +

			pci_resource_len(devp->rdev.lldi.pdev, 2) -

			roundup_pow_of_two(devp->rdev.lldi.vr->ocq.size);

		devp->rdev.oc_mw_kva = ioremap_wc(devp->rdev.oc_mw_pa,

			devp->rdev.lldi.vr->ocq.size);

		if (!devp->rdev.oc_mw_kva) {

			pr_err(MOD "Unable to ioremap onchip mem\n");

			return ERR_PTR(-EINVAL);

		}

	}



	PDBG(KERN_INFO MOD "ocq memory: "

	       "hw_start 0x%x size %u mw_pa 0x%lx mw_kva %p\n",
@@ -1003,9 +1026,11 @@ static int enable_qp_db(int id, void *p, void *data) 
static void resume_rc_qp(struct c4iw_qp *qp)

{

	spin_lock(&qp->lock);

	t4_ring_sq_db(&qp->wq, qp->wq.sq.wq_pidx_inc);

	t4_ring_sq_db(&qp->wq, qp->wq.sq.wq_pidx_inc,

		      is_t5(qp->rhp->rdev.lldi.adapter_type), NULL);

	qp->wq.sq.wq_pidx_inc = 0;

	t4_ring_rq_db(&qp->wq, qp->wq.rq.wq_pidx_inc);

	t4_ring_rq_db(&qp->wq, qp->wq.rq.wq_pidx_inc,

		      is_t5(qp->rhp->rdev.lldi.adapter_type), NULL);

	qp->wq.rq.wq_pidx_inc = 0;

	spin_unlock(&qp->lock);

}

drivers/infiniband/hw/cxgb4/iw_cxgb4.h

+2 −0
Original line number Diff line number Diff line
@@ -149,6 +149,8 @@ struct c4iw_rdev { 
	struct gen_pool *ocqp_pool;

	u32 flags;

	struct cxgb4_lld_info lldi;

	unsigned long bar2_pa;

	void __iomem *bar2_kva;

	unsigned long oc_mw_pa;

	void __iomem *oc_mw_kva;

	struct c4iw_stats stats;

drivers/infiniband/hw/cxgb4/mem.c

+5 −1
Original line number Diff line number Diff line
@@ -259,8 +259,12 @@ static int write_tpt_entry(struct c4iw_rdev *rdev, u32 reset_tpt_entry, 


	if ((!reset_tpt_entry) && (*stag == T4_STAG_UNSET)) {

		stag_idx = c4iw_get_resource(&rdev->resource.tpt_table);

		if (!stag_idx)

		if (!stag_idx) {

			mutex_lock(&rdev->stats.lock);

			rdev->stats.stag.fail++;

			mutex_unlock(&rdev->stats.lock);

			return -ENOMEM;

		}

		mutex_lock(&rdev->stats.lock);

		rdev->stats.stag.cur += 32;

		if (rdev->stats.stag.cur > rdev->stats.stag.max)

CRA Git | Maintained and supported by SUSTech CRA and CCSE