From 347fcfbed261fdd11f46fa03d524e1bddddab3a6 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 30 Apr 2007 17:30:28 -0700 Subject: IPoIB/cm: Fix error handling in ipoib_cm_dev_open() If skb allocation fails when we start the device, we call ipoib_cm_dev_stop() even though ipoib_cm_dev_open() did not run to completion, so we pass an invalid pointer to ib_destroy_cm_id and get an oops. Fix by clearing cm.id on error, and testing it in cm_dev_stop(). This fixes Signed-off-by: Michael S. Tsirkin Signed-off-by: Roland Dreier --- drivers/infiniband/ulp/ipoib/ipoib_cm.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'drivers/infiniband/ulp/ipoib') diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 0c4e59b906c..76717410660 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -592,7 +592,9 @@ int ipoib_cm_dev_open(struct net_device *dev) priv->cm.id = ib_create_cm_id(priv->ca, ipoib_cm_rx_handler, dev); if (IS_ERR(priv->cm.id)) { printk(KERN_WARNING "%s: failed to create CM ID\n", priv->ca->name); - return IS_ERR(priv->cm.id); + ret = PTR_ERR(priv->cm.id); + priv->cm.id = NULL; + return ret; } ret = ib_cm_listen(priv->cm.id, cpu_to_be64(IPOIB_CM_IETF_ID | priv->qp->qp_num), @@ -601,6 +603,7 @@ int ipoib_cm_dev_open(struct net_device *dev) printk(KERN_WARNING "%s: failed to listen on ID 0x%llx\n", priv->ca->name, IPOIB_CM_IETF_ID | priv->qp->qp_num); ib_destroy_cm_id(priv->cm.id); + priv->cm.id = NULL; return ret; } return 0; @@ -611,10 +614,11 @@ void ipoib_cm_dev_stop(struct net_device *dev) struct ipoib_dev_priv *priv = netdev_priv(dev); struct ipoib_cm_rx *p; - if (!IPOIB_CM_SUPPORTED(dev->dev_addr)) + if (!IPOIB_CM_SUPPORTED(dev->dev_addr) || !priv->cm.id) return; ib_destroy_cm_id(priv->cm.id); + priv->cm.id = NULL; spin_lock_irq(&priv->lock); while (!list_empty(&priv->cm.passive_ids)) { p = list_entry(priv->cm.passive_ids.next, typeof(*p), list); -- cgit v1.2.3 From d6ef7d68f6f51c5b9de01c542dab8b90067a9c27 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 2 May 2007 15:31:12 +0300 Subject: IPoIB/cm: Don't crash if remote side uses one QP for both directions The IPoIB CM spec allows the use of a single connection in both active->passive and passive->active directions. The current Linux code uses one connection for both directions, but if another node only uses one connection for both directions, we oops when we try to look up the passive connection. Fix by checking that qp_context is non-NULL before dereferencing it. Signed-off-by: Michael S. Tsirkin --- drivers/infiniband/ulp/ipoib/ipoib_cm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/infiniband/ulp/ipoib') diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 76717410660..1e27930077e 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -370,7 +370,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) if (!likely(wr_id & IPOIB_CM_RX_UPDATE_MASK)) { p = wc->qp->qp_context; - if (time_after_eq(jiffies, p->jiffies + IPOIB_CM_RX_UPDATE_TIME)) { + if (p && time_after_eq(jiffies, p->jiffies + IPOIB_CM_RX_UPDATE_TIME)) { spin_lock_irqsave(&priv->lock, flags); p->jiffies = jiffies; /* Move this entry to list head, but do -- cgit v1.2.3 From f4fd0b224d60044d2da5ca02f8f2b5150c1d8731 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 3 May 2007 13:48:47 +0300 Subject: IB: Add CQ comp_vector support Add a num_comp_vectors member to struct ib_device and extend ib_create_cq() to pass in a comp_vector parameter -- this parallels the userspace libibverbs API. Update all hardware drivers to set num_comp_vectors to 1 and have all ULPs pass 0 for the comp_vector value. Pass the value of num_comp_vectors to userspace rather than hard-coding a value of 1. We want multiple CQ event vector support (via MSI-X or similar for adapters that can generate multiple interrupts), but it's not clear how many vectors we want, or how we want to deal with policy issues such as how to decide which vector to use or how to set up interrupt affinity. This patch is useful for experimenting, since no core changes will be necessary when updating a driver to support multiple vectors, and we know that we want to make at least these changes anyway. Signed-off-by: Michael S. Tsirkin Signed-off-by: Roland Dreier --- drivers/infiniband/ulp/ipoib/ipoib_cm.c | 2 +- drivers/infiniband/ulp/ipoib/ipoib_verbs.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/infiniband/ulp/ipoib') diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 1e27930077e..b8089a04158 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -793,7 +793,7 @@ static int ipoib_cm_tx_init(struct ipoib_cm_tx *p, u32 qpn, } p->cq = ib_create_cq(priv->ca, ipoib_cm_tx_completion, NULL, p, - ipoib_sendq_size + 1); + ipoib_sendq_size + 1, 0); if (IS_ERR(p->cq)) { ret = PTR_ERR(p->cq); ipoib_warn(priv, "failed to allocate tx cq: %d\n", ret); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c index 7f3ec205e35..5c3c6a43a52 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c @@ -187,7 +187,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) if (!ret) size += ipoib_recvq_size; - priv->cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL, dev, size); + priv->cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL, dev, size, 0); if (IS_ERR(priv->cq)) { printk(KERN_WARNING "%s: failed to create CQ\n", ca->name); goto out_free_mr; -- cgit v1.2.3 From 8d1cc86a6278687efbab7b8c294ab01efe4d4231 Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Sun, 6 May 2007 21:05:32 -0700 Subject: IPoIB: Convert to NAPI Convert the IP-over-InfiniBand network device driver over to using NAPI to handle completions for the main CQ. This covers all receives as well as datagram mode sends; send completions for connected mode connections are still handled from interrupt context. Signed-off-by: Roland Dreier --- drivers/infiniband/ulp/ipoib/ipoib.h | 1 + drivers/infiniband/ulp/ipoib/ipoib_cm.c | 2 +- drivers/infiniband/ulp/ipoib/ipoib_ib.c | 89 ++++++++++++++++++++++++------- drivers/infiniband/ulp/ipoib/ipoib_main.c | 2 + 4 files changed, 74 insertions(+), 20 deletions(-) (limited to 'drivers/infiniband/ulp/ipoib') diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index fd558267d1c..15867af33c4 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -311,6 +311,7 @@ extern struct workqueue_struct *ipoib_workqueue; /* functions */ +int ipoib_poll(struct net_device *dev, int *budget); void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr); struct ipoib_ah *ipoib_create_ah(struct net_device *dev, diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index b8089a04158..785bc8505f2 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -416,7 +416,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) skb->dev = dev; /* XXX get correct PACKET_ type here */ skb->pkt_type = PACKET_HOST; - netif_rx_ni(skb); + netif_receive_skb(skb); repost: if (unlikely(ipoib_cm_post_receive(dev, wr_id))) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 1bdb9101911..68d72c6f7ff 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -226,7 +226,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) skb->dev = dev; /* XXX get correct PACKET_ type here */ skb->pkt_type = PACKET_HOST; - netif_rx_ni(skb); + netif_receive_skb(skb); } else { ipoib_dbg_data(priv, "dropping loopback packet\n"); dev_kfree_skb_any(skb); @@ -280,28 +280,63 @@ static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) wc->status, wr_id, wc->vendor_err); } -static void ipoib_ib_handle_wc(struct net_device *dev, struct ib_wc *wc) +int ipoib_poll(struct net_device *dev, int *budget) { - if (wc->wr_id & IPOIB_CM_OP_SRQ) - ipoib_cm_handle_rx_wc(dev, wc); - else if (wc->wr_id & IPOIB_OP_RECV) - ipoib_ib_handle_rx_wc(dev, wc); - else - ipoib_ib_handle_tx_wc(dev, wc); + struct ipoib_dev_priv *priv = netdev_priv(dev); + int max = min(*budget, dev->quota); + int done; + int t; + int empty; + int n, i; + + done = 0; + empty = 0; + + while (max) { + t = min(IPOIB_NUM_WC, max); + n = ib_poll_cq(priv->cq, t, priv->ibwc); + + for (i = 0; i < n; ++i) { + struct ib_wc *wc = priv->ibwc + i; + + if (wc->wr_id & IPOIB_CM_OP_SRQ) { + ++done; + --max; + ipoib_cm_handle_rx_wc(dev, wc); + } else if (wc->wr_id & IPOIB_OP_RECV) { + ++done; + --max; + ipoib_ib_handle_rx_wc(dev, wc); + } else + ipoib_ib_handle_tx_wc(dev, wc); + } + + if (n != t) { + empty = 1; + break; + } + } + + dev->quota -= done; + *budget -= done; + + if (empty) { + netif_rx_complete(dev); + if (unlikely(ib_req_notify_cq(priv->cq, + IB_CQ_NEXT_COMP | + IB_CQ_REPORT_MISSED_EVENTS)) && + netif_rx_reschedule(dev, 0)) + return 1; + + return 0; + } + + return 1; } void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr) { - struct net_device *dev = (struct net_device *) dev_ptr; - struct ipoib_dev_priv *priv = netdev_priv(dev); - int n, i; - - ib_req_notify_cq(cq, IB_CQ_NEXT_COMP); - do { - n = ib_poll_cq(cq, IPOIB_NUM_WC, priv->ibwc); - for (i = 0; i < n; ++i) - ipoib_ib_handle_wc(dev, priv->ibwc + i); - } while (n == IPOIB_NUM_WC); + netif_rx_schedule(dev_ptr); } static inline int post_send(struct ipoib_dev_priv *priv, @@ -514,9 +549,10 @@ int ipoib_ib_dev_stop(struct net_device *dev) struct ib_qp_attr qp_attr; unsigned long begin; struct ipoib_tx_buf *tx_req; - int i; + int i, n; clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags); + netif_poll_disable(dev); ipoib_cm_dev_stop(dev); @@ -568,6 +604,18 @@ int ipoib_ib_dev_stop(struct net_device *dev) goto timeout; } + do { + n = ib_poll_cq(priv->cq, IPOIB_NUM_WC, priv->ibwc); + for (i = 0; i < n; ++i) { + if (priv->ibwc[i].wr_id & IPOIB_CM_OP_SRQ) + ipoib_cm_handle_rx_wc(dev, priv->ibwc + i); + else if (priv->ibwc[i].wr_id & IPOIB_OP_RECV) + ipoib_ib_handle_rx_wc(dev, priv->ibwc + i); + else + ipoib_ib_handle_tx_wc(dev, priv->ibwc + i); + } + } while (n == IPOIB_NUM_WC); + msleep(1); } @@ -596,6 +644,9 @@ timeout: msleep(1); } + netif_poll_enable(dev); + ib_req_notify_cq(priv->cq, IB_CQ_NEXT_COMP); + return 0; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index b4c380c5a3b..0a428f2b05c 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -948,6 +948,8 @@ static void ipoib_setup(struct net_device *dev) dev->hard_header = ipoib_hard_header; dev->set_multicast_list = ipoib_set_mcast_list; dev->neigh_setup = ipoib_neigh_setup_dev; + dev->poll = ipoib_poll; + dev->weight = 100; dev->watchdog_timeo = HZ; -- cgit v1.2.3