aboutsummaryrefslogtreecommitdiff
path: root/drivers/infiniband/ulp/ipoib
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband/ulp/ipoib')
-rw-r--r--drivers/infiniband/ulp/ipoib/Kconfig3
-rw-r--r--drivers/infiniband/ulp/ipoib/Makefile3
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib.h104
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_cm.c138
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_ethtool.c83
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_fs.c9
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_ib.c203
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_main.c904
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_multicast.c130
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_netlink.c182
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_verbs.c5
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_vlan.c152
12 files changed, 1280 insertions, 636 deletions
diff --git a/drivers/infiniband/ulp/ipoib/Kconfig b/drivers/infiniband/ulp/ipoib/Kconfig
index 9d9a9dc51f1..cda8eac55ff 100644
--- a/drivers/infiniband/ulp/ipoib/Kconfig
+++ b/drivers/infiniband/ulp/ipoib/Kconfig
@@ -1,7 +1,6 @@
config INFINIBAND_IPOIB
tristate "IP-over-InfiniBand"
depends on NETDEVICES && INET && (IPV6 || IPV6=n)
- select INET_LRO
---help---
Support for the IP-over-InfiniBand protocol (IPoIB). This
transports IP packets over InfiniBand so you can use your IB
@@ -25,7 +24,7 @@ config INFINIBAND_IPOIB_CM
unless you limit mtu for these destinations to 2044.
config INFINIBAND_IPOIB_DEBUG
- bool "IP-over-InfiniBand debugging" if EMBEDDED
+ bool "IP-over-InfiniBand debugging" if EXPERT
depends on INFINIBAND_IPOIB
default y
---help---
diff --git a/drivers/infiniband/ulp/ipoib/Makefile b/drivers/infiniband/ulp/ipoib/Makefile
index 3090100f0de..e5430dd5076 100644
--- a/drivers/infiniband/ulp/ipoib/Makefile
+++ b/drivers/infiniband/ulp/ipoib/Makefile
@@ -5,7 +5,8 @@ ib_ipoib-y := ipoib_main.o \
ipoib_multicast.o \
ipoib_verbs.o \
ipoib_vlan.o \
- ipoib_ethtool.o
+ ipoib_ethtool.o \
+ ipoib_netlink.o
ib_ipoib-$(CONFIG_INFINIBAND_IPOIB_CM) += ipoib_cm.o
ib_ipoib-$(CONFIG_INFINIBAND_IPOIB_DEBUG) += ipoib_fs.o
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 753a983a5fd..c639f90cfda 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -44,13 +44,14 @@
#include <linux/mutex.h>
#include <net/neighbour.h>
+#include <net/sch_generic.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
#include <rdma/ib_verbs.h>
#include <rdma/ib_pack.h>
#include <rdma/ib_sa.h>
-#include <linux/inet_lro.h>
+#include <linux/sched.h>
/* constants */
@@ -91,7 +92,8 @@ enum {
IPOIB_STOP_REAPER = 7,
IPOIB_FLAG_ADMIN_CM = 9,
IPOIB_FLAG_UMCAST = 10,
- IPOIB_FLAG_CSUM = 11,
+ IPOIB_STOP_NEIGH_GC = 11,
+ IPOIB_NEIGH_TBL_FLUSH = 12,
IPOIB_MAX_BACKOFF_SECONDS = 16,
@@ -99,12 +101,14 @@ enum {
IPOIB_MCAST_FLAG_SENDONLY = 1,
IPOIB_MCAST_FLAG_BUSY = 2, /* joining or already joined */
IPOIB_MCAST_FLAG_ATTACHED = 3,
-
- IPOIB_MAX_LRO_DESCRIPTORS = 8,
- IPOIB_LRO_MAX_AGGR = 64,
+ IPOIB_MCAST_JOIN_STARTED = 4,
MAX_SEND_CQE = 16,
IPOIB_CM_COPYBREAK = 256,
+
+ IPOIB_NON_CHILD = 0,
+ IPOIB_LEGACY_CHILD = 1,
+ IPOIB_RTNL_CHILD = 2,
};
#define IPOIB_OP_RECV (1ul << 31)
@@ -114,6 +118,8 @@ enum {
#define IPOIB_OP_CM (0)
#endif
+#define IPOIB_QPN_MASK ((__force u32) cpu_to_be32(0xFFFFFF))
+
/* structs */
struct ipoib_header {
@@ -121,8 +127,9 @@ struct ipoib_header {
u16 reserved;
};
-struct ipoib_pseudoheader {
- u8 hwaddr[INFINIBAND_ALEN];
+struct ipoib_cb {
+ struct qdisc_skb_cb qdisc_cb;
+ u8 hwaddr[INFINIBAND_ALEN];
};
/* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */
@@ -145,6 +152,7 @@ struct ipoib_mcast {
struct sk_buff_head pkt_queue;
struct net_device *dev;
+ struct completion done;
};
struct ipoib_rx_buf {
@@ -262,9 +270,21 @@ struct ipoib_ethtool_st {
u16 max_coalesced_frames;
};
-struct ipoib_lro {
- struct net_lro_mgr lro_mgr;
- struct net_lro_desc lro_desc[IPOIB_MAX_LRO_DESCRIPTORS];
+struct ipoib_neigh_table;
+
+struct ipoib_neigh_hash {
+ struct ipoib_neigh_table *ntbl;
+ struct ipoib_neigh __rcu **buckets;
+ struct rcu_head rcu;
+ u32 mask;
+ u32 size;
+};
+
+struct ipoib_neigh_table {
+ struct ipoib_neigh_hash __rcu *htbl;
+ atomic_t entries;
+ struct completion flushed;
+ struct completion deleted;
};
/*
@@ -281,11 +301,13 @@ struct ipoib_dev_priv {
unsigned long flags;
- struct mutex vlan_mutex;
+ struct rw_semaphore vlan_rwsem;
struct rb_root path_tree;
struct list_head path_list;
+ struct ipoib_neigh_table ntbl;
+
struct ipoib_mcast *broadcast;
struct list_head multicast_list;
struct rb_root multicast_tree;
@@ -298,7 +320,7 @@ struct ipoib_dev_priv {
struct work_struct flush_heavy;
struct work_struct restart_task;
struct delayed_work ah_reap_task;
-
+ struct delayed_work neigh_reap_task;
struct ib_device *ca;
u8 port;
u16 pkey;
@@ -339,6 +361,7 @@ struct ipoib_dev_priv {
struct net_device *parent;
struct list_head child_intfs;
struct list_head list;
+ int child_type;
#ifdef CONFIG_INFINIBAND_IPOIB_CM
struct ipoib_cm_dev_priv cm;
@@ -352,8 +375,6 @@ struct ipoib_dev_priv {
int hca_caps;
struct ipoib_ethtool_st ethtool;
struct timer_list poll_timer;
-
- struct ipoib_lro lro;
};
struct ipoib_ah {
@@ -386,13 +407,16 @@ struct ipoib_neigh {
#ifdef CONFIG_INFINIBAND_IPOIB_CM
struct ipoib_cm_tx *cm;
#endif
- union ib_gid dgid;
+ u8 daddr[INFINIBAND_ALEN];
struct sk_buff_head queue;
- struct neighbour *neighbour;
struct net_device *dev;
struct list_head list;
+ struct ipoib_neigh __rcu *hnext;
+ struct rcu_head rcu;
+ atomic_t refcnt;
+ unsigned long alive;
};
#define IPOIB_UD_MTU(ib_mtu) (ib_mtu - IPOIB_ENCAP_LEN)
@@ -403,21 +427,17 @@ static inline int ipoib_ud_need_sg(unsigned int ib_mtu)
return IPOIB_UD_BUF_SIZE(ib_mtu) > PAGE_SIZE;
}
-/*
- * We stash a pointer to our private neighbour information after our
- * hardware address in neigh->ha. The ALIGN() expression here makes
- * sure that this pointer is stored aligned so that an unaligned
- * load is not needed to dereference it.
- */
-static inline struct ipoib_neigh **to_ipoib_neigh(struct neighbour *neigh)
+void ipoib_neigh_dtor(struct ipoib_neigh *neigh);
+static inline void ipoib_neigh_put(struct ipoib_neigh *neigh)
{
- return (void*) neigh + ALIGN(offsetof(struct neighbour, ha) +
- INFINIBAND_ALEN, sizeof(void *));
+ if (atomic_dec_and_test(&neigh->refcnt))
+ ipoib_neigh_dtor(neigh);
}
-
-struct ipoib_neigh *ipoib_neigh_alloc(struct neighbour *neigh,
+struct ipoib_neigh *ipoib_neigh_get(struct net_device *dev, u8 *daddr);
+struct ipoib_neigh *ipoib_neigh_alloc(u8 *daddr,
struct net_device *dev);
-void ipoib_neigh_free(struct net_device *dev, struct ipoib_neigh *neigh);
+void ipoib_neigh_free(struct ipoib_neigh *neigh);
+void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid);
extern struct workqueue_struct *ipoib_workqueue;
@@ -434,7 +454,6 @@ static inline void ipoib_put_ah(struct ipoib_ah *ah)
{
kref_put(&ah->ref, ipoib_free_ah);
}
-
int ipoib_open(struct net_device *dev);
int ipoib_add_pkey_attr(struct net_device *dev);
int ipoib_add_umcast_attr(struct net_device *dev);
@@ -464,7 +483,7 @@ void ipoib_dev_cleanup(struct net_device *dev);
void ipoib_mcast_join_task(struct work_struct *work);
void ipoib_mcast_carrier_on_task(struct work_struct *work);
-void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb);
+void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb);
void ipoib_mcast_restart_task(struct work_struct *work);
int ipoib_mcast_start_thread(struct net_device *dev);
@@ -502,6 +521,17 @@ void ipoib_event(struct ib_event_handler *handler,
int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey);
int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey);
+int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
+ u16 pkey, int child_type);
+
+int __init ipoib_netlink_init(void);
+void __exit ipoib_netlink_fini(void);
+
+void ipoib_set_umcast(struct net_device *ndev, int umcast_val);
+int ipoib_set_mode(struct net_device *dev, const char *buf);
+
+void ipoib_setup(struct net_device *dev);
+
void ipoib_pkey_poll(struct work_struct *work);
int ipoib_pkey_dev_delay_open(struct net_device *dev);
void ipoib_drain_cq(struct net_device *dev);
@@ -509,14 +539,14 @@ void ipoib_drain_cq(struct net_device *dev);
void ipoib_set_ethtool_ops(struct net_device *dev);
int ipoib_set_dev_features(struct ipoib_dev_priv *priv, struct ib_device *hca);
-#ifdef CONFIG_INFINIBAND_IPOIB_CM
-
#define IPOIB_FLAGS_RC 0x80
#define IPOIB_FLAGS_UC 0x40
/* We don't support UC connections at the moment */
#define IPOIB_CM_SUPPORTED(ha) (ha[0] & (IPOIB_FLAGS_RC))
+#ifdef CONFIG_INFINIBAND_IPOIB_CM
+
extern int ipoib_max_conn_qp;
static inline int ipoib_cm_admin_enabled(struct net_device *dev)
@@ -526,10 +556,10 @@ static inline int ipoib_cm_admin_enabled(struct net_device *dev)
test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
}
-static inline int ipoib_cm_enabled(struct net_device *dev, struct neighbour *n)
+static inline int ipoib_cm_enabled(struct net_device *dev, u8 *hwaddr)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
- return IPOIB_CM_SUPPORTED(n->ha) &&
+ return IPOIB_CM_SUPPORTED(hwaddr) &&
test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
}
@@ -584,7 +614,7 @@ static inline int ipoib_cm_admin_enabled(struct net_device *dev)
{
return 0;
}
-static inline int ipoib_cm_enabled(struct net_device *dev, struct neighbour *n)
+static inline int ipoib_cm_enabled(struct net_device *dev, u8 *hwaddr)
{
return 0;
@@ -734,4 +764,6 @@ extern int ipoib_debug_level;
#define IPOIB_QPN(ha) (be32_to_cpup((__be32 *) ha) & 0xffffff)
+extern const char ipoib_driver_version[];
+
#endif /* _IPOIB_H */
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 47d588ba2a7..933efcea0d0 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -31,12 +31,13 @@
*/
#include <rdma/ib_cm.h>
-#include <rdma/ib_cache.h>
#include <net/dst.h>
#include <net/icmp.h>
#include <linux/icmpv6.h>
#include <linux/delay.h>
+#include <linux/slab.h>
#include <linux/vmalloc.h>
+#include <linux/moduleparam.h>
#include "ipoib.h"
@@ -84,7 +85,7 @@ static void ipoib_cm_dma_unmap_rx(struct ipoib_dev_priv *priv, int frags,
ib_dma_unmap_single(priv->ca, mapping[0], IPOIB_CM_HEAD_SIZE, DMA_FROM_DEVICE);
for (i = 0; i < frags; ++i)
- ib_dma_unmap_single(priv->ca, mapping[i + 1], PAGE_SIZE, DMA_FROM_DEVICE);
+ ib_dma_unmap_page(priv->ca, mapping[i + 1], PAGE_SIZE, DMA_FROM_DEVICE);
}
static int ipoib_cm_post_receive_srq(struct net_device *dev, int id)
@@ -139,7 +140,8 @@ static int ipoib_cm_post_receive_nonsrq(struct net_device *dev,
static struct sk_buff *ipoib_cm_alloc_rx_skb(struct net_device *dev,
struct ipoib_cm_rx_buf *rx_ring,
int id, int frags,
- u64 mapping[IPOIB_CM_RX_SG])
+ u64 mapping[IPOIB_CM_RX_SG],
+ gfp_t gfp)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct sk_buff *skb;
@@ -163,13 +165,13 @@ static struct sk_buff *ipoib_cm_alloc_rx_skb(struct net_device *dev,
}
for (i = 0; i < frags; i++) {
- struct page *page = alloc_page(GFP_ATOMIC);
+ struct page *page = alloc_page(gfp);
if (!page)
goto partial_error;
skb_fill_page_desc(skb, i, page, 0, PAGE_SIZE);
- mapping[i + 1] = ib_dma_map_page(priv->ca, skb_shinfo(skb)->frags[i].page,
+ mapping[i + 1] = ib_dma_map_page(priv->ca, page,
0, PAGE_SIZE, DMA_FROM_DEVICE);
if (unlikely(ib_dma_mapping_error(priv->ca, mapping[i + 1])))
goto partial_error;
@@ -183,7 +185,7 @@ partial_error:
ib_dma_unmap_single(priv->ca, mapping[0], IPOIB_CM_HEAD_SIZE, DMA_FROM_DEVICE);
for (; i > 0; --i)
- ib_dma_unmap_single(priv->ca, mapping[i], PAGE_SIZE, DMA_FROM_DEVICE);
+ ib_dma_unmap_page(priv->ca, mapping[i], PAGE_SIZE, DMA_FROM_DEVICE);
dev_kfree_skb_any(skb);
return NULL;
@@ -352,15 +354,13 @@ static int ipoib_cm_nonsrq_init_rx(struct net_device *dev, struct ib_cm_id *cm_i
int ret;
int i;
- rx->rx_ring = vmalloc(ipoib_recvq_size * sizeof *rx->rx_ring);
+ rx->rx_ring = vzalloc(ipoib_recvq_size * sizeof *rx->rx_ring);
if (!rx->rx_ring) {
printk(KERN_WARNING "%s: failed to allocate CM non-SRQ ring (%d entries)\n",
priv->ca->name, ipoib_recvq_size);
return -ENOMEM;
}
- memset(rx->rx_ring, 0, ipoib_recvq_size * sizeof *rx->rx_ring);
-
t = kmalloc(sizeof *t, GFP_KERNEL);
if (!t) {
ret = -ENOMEM;
@@ -383,7 +383,8 @@ static int ipoib_cm_nonsrq_init_rx(struct net_device *dev, struct ib_cm_id *cm_i
for (i = 0; i < ipoib_recvq_size; ++i) {
if (!ipoib_cm_alloc_rx_skb(dev, rx->rx_ring, i, IPOIB_CM_RX_SG - 1,
- rx->rx_ring[i].mapping)) {
+ rx->rx_ring[i].mapping,
+ GFP_KERNEL)) {
ipoib_warn(priv, "failed to allocate receive buffer %d\n", i);
ret = -ENOMEM;
goto err_count;
@@ -461,7 +462,7 @@ static int ipoib_cm_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *even
goto err_qp;
}
- psn = random32() & 0xffffff;
+ psn = prandom_u32() & 0xffffff;
ret = ipoib_cm_modify_rx_qp(dev, cm_id, p->qp, psn);
if (ret)
goto err_modify;
@@ -539,12 +540,13 @@ static void skb_put_frags(struct sk_buff *skb, unsigned int hdr_space,
if (length == 0) {
/* don't need this page */
- skb_fill_page_desc(toskb, i, frag->page, 0, PAGE_SIZE);
+ skb_fill_page_desc(toskb, i, skb_frag_page(frag),
+ 0, PAGE_SIZE);
--skb_shinfo(skb)->nr_frags;
} else {
size = min(length, (unsigned) PAGE_SIZE);
- frag->size = size;
+ skb_frag_size_set(frag, size);
skb->data_len += size;
skb->truesize += size;
skb->len += size;
@@ -639,7 +641,8 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
frags = PAGE_ALIGN(wc->byte_len - min(wc->byte_len,
(unsigned)IPOIB_CM_HEAD_SIZE)) / PAGE_SIZE;
- newskb = ipoib_cm_alloc_rx_skb(dev, rx_ring, wr_id, frags, mapping);
+ newskb = ipoib_cm_alloc_rx_skb(dev, rx_ring, wr_id, frags,
+ mapping, GFP_ATOMIC);
if (unlikely(!newskb)) {
/*
* If we can't allocate a new RX buffer, dump
@@ -663,7 +666,6 @@ copied:
skb_reset_mac_header(skb);
skb_pull(skb, IPOIB_ENCAP_LEN);
- dev->last_rx = jiffies;
++dev->stats.rx_packets;
dev->stats.rx_bytes += skb->len;
@@ -710,6 +712,7 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_cm_tx_buf *tx_req;
u64 addr;
+ int rc;
if (unlikely(skb->len > tx->mtu)) {
ipoib_warn(priv, "packet len %d (> %d) too long to send, dropping\n",
@@ -741,9 +744,13 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_
tx_req->mapping = addr;
- if (unlikely(post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1),
- addr, skb->len))) {
- ipoib_warn(priv, "post_send failed\n");
+ skb_orphan(skb);
+ skb_dst_drop(skb);
+
+ rc = post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1),
+ addr, skb->len);
+ if (unlikely(rc)) {
+ ipoib_warn(priv, "post_send failed, error %d\n", rc);
++dev->stats.tx_errors;
ib_dma_unmap_single(priv->ca, addr, skb->len, DMA_TO_DEVICE);
dev_kfree_skb_any(skb);
@@ -755,6 +762,12 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_
ipoib_dbg(priv, "TX ring 0x%x full, stopping kernel net queue\n",
tx->qp->qp_num);
netif_stop_queue(dev);
+ rc = ib_req_notify_cq(priv->send_cq,
+ IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS);
+ if (rc < 0)
+ ipoib_warn(priv, "request notify on send CQ failed\n");
+ else if (rc)
+ ipoib_send_comp_handler(priv->send_cq, dev);
}
}
}
@@ -807,10 +820,7 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
if (neigh) {
neigh->cm = NULL;
- list_del(&neigh->list);
- if (neigh->ah)
- ipoib_put_ah(neigh->ah);
- ipoib_neigh_free(dev, neigh);
+ ipoib_neigh_free(neigh);
tx->neigh = NULL;
}
@@ -1020,10 +1030,20 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_
.cap.max_send_sge = 1,
.sq_sig_type = IB_SIGNAL_ALL_WR,
.qp_type = IB_QPT_RC,
- .qp_context = tx
+ .qp_context = tx,
+ .create_flags = IB_QP_CREATE_USE_GFP_NOIO
};
- return ib_create_qp(priv->pd, &attr);
+ struct ib_qp *tx_qp;
+
+ tx_qp = ib_create_qp(priv->pd, &attr);
+ if (PTR_ERR(tx_qp) == -EINVAL) {
+ ipoib_warn(priv, "can't use GFP_NOIO for QPs on device %s, using GFP_KERNEL\n",
+ priv->ca->name);
+ attr.create_flags &= ~IB_QP_CREATE_USE_GFP_NOIO;
+ tx_qp = ib_create_qp(priv->pd, &attr);
+ }
+ return tx_qp;
}
static int ipoib_cm_send_req(struct net_device *dev,
@@ -1094,7 +1114,8 @@ static int ipoib_cm_tx_init(struct ipoib_cm_tx *p, u32 qpn,
struct ipoib_dev_priv *priv = netdev_priv(p->dev);
int ret;
- p->tx_ring = vmalloc(ipoib_sendq_size * sizeof *p->tx_ring);
+ p->tx_ring = __vmalloc(ipoib_sendq_size * sizeof *p->tx_ring,
+ GFP_NOIO, PAGE_KERNEL);
if (!p->tx_ring) {
ipoib_warn(priv, "failed to allocate tx ring\n");
ret = -ENOMEM;
@@ -1227,10 +1248,7 @@ static int ipoib_cm_tx_handler(struct ib_cm_id *cm_id,
if (neigh) {
neigh->cm = NULL;
- list_del(&neigh->list);
- if (neigh->ah)
- ipoib_put_ah(neigh->ah);
- ipoib_neigh_free(dev, neigh);
+ ipoib_neigh_free(neigh);
tx->neigh = NULL;
}
@@ -1273,12 +1291,15 @@ struct ipoib_cm_tx *ipoib_cm_create_tx(struct net_device *dev, struct ipoib_path
void ipoib_cm_destroy_tx(struct ipoib_cm_tx *tx)
{
struct ipoib_dev_priv *priv = netdev_priv(tx->dev);
+ unsigned long flags;
if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) {
+ spin_lock_irqsave(&priv->lock, flags);
list_move(&tx->list, &priv->cm.reap_list);
queue_work(ipoib_workqueue, &priv->cm.reap_task);
ipoib_dbg(priv, "Reap connection for gid %pI6\n",
- tx->neigh->dgid.raw);
+ tx->neigh->daddr + 4);
tx->neigh = NULL;
+ spin_unlock_irqrestore(&priv->lock, flags);
}
}
@@ -1302,7 +1323,7 @@ static void ipoib_cm_tx_start(struct work_struct *work)
p = list_entry(priv->cm.start_list.next, typeof(*p), list);
list_del_init(&p->list);
neigh = p->neigh;
- qpn = IPOIB_QPN(neigh->neighbour->ha);
+ qpn = IPOIB_QPN(neigh->daddr);
memcpy(&pathrec, &p->path->pathrec, sizeof pathrec);
spin_unlock_irqrestore(&priv->lock, flags);
@@ -1317,10 +1338,7 @@ static void ipoib_cm_tx_start(struct work_struct *work)
neigh = p->neigh;
if (neigh) {
neigh->cm = NULL;
- list_del(&neigh->list);
- if (neigh->ah)
- ipoib_put_ah(neigh->ah);
- ipoib_neigh_free(dev, neigh);
+ ipoib_neigh_free(neigh);
}
list_del(&p->list);
kfree(p);
@@ -1374,9 +1392,9 @@ static void ipoib_cm_skb_reap(struct work_struct *work)
if (skb->protocol == htons(ETH_P_IP))
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6))
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, priv->dev);
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
#endif
dev_kfree_skb_any(skb);
@@ -1394,8 +1412,8 @@ void ipoib_cm_skb_too_long(struct net_device *dev, struct sk_buff *skb,
struct ipoib_dev_priv *priv = netdev_priv(dev);
int e = skb_queue_empty(&priv->cm.skb_queue);
- if (skb->dst)
- skb->dst->ops->update_pmtu(skb->dst, mtu);
+ if (skb_dst(skb))
+ skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
skb_queue_tail(&priv->cm.skb_queue, skb);
if (e)
@@ -1453,40 +1471,19 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
const char *buf, size_t count)
{
struct net_device *dev = to_net_dev(d);
- struct ipoib_dev_priv *priv = netdev_priv(dev);
-
- /* flush paths if we switch modes so that connections are restarted */
- if (IPOIB_CM_SUPPORTED(dev->dev_addr) && !strcmp(buf, "connected\n")) {
- set_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
- ipoib_warn(priv, "enabling connected mode "
- "will cause multicast packet drops\n");
-
- rtnl_lock();
- dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_SG | NETIF_F_TSO);
- rtnl_unlock();
- priv->tx_wr.send_flags &= ~IB_SEND_IP_CSUM;
+ int ret;
- ipoib_flush_paths(dev);
- return count;
- }
+ if (!rtnl_trylock())
+ return restart_syscall();
- if (!strcmp(buf, "datagram\n")) {
- clear_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
+ ret = ipoib_set_mode(dev, buf);
- rtnl_lock();
- if (test_bit(IPOIB_FLAG_CSUM, &priv->flags)) {
- dev->features |= NETIF_F_IP_CSUM | NETIF_F_SG;
- if (priv->hca_caps & IB_DEVICE_UD_TSO)
- dev->features |= NETIF_F_TSO;
- }
- dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu));
- rtnl_unlock();
- ipoib_flush_paths(dev);
+ rtnl_unlock();
+ if (!ret)
return count;
- }
- return -EINVAL;
+ return ret;
}
static DEVICE_ATTR(mode, S_IWUSR | S_IRUGO, show_mode, set_mode);
@@ -1500,6 +1497,7 @@ static void ipoib_cm_create_srq(struct net_device *dev, int max_sge)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ib_srq_init_attr srq_init_attr = {
+ .srq_type = IB_SRQT_BASIC,
.attr = {
.max_wr = ipoib_recvq_size,
.max_sge = max_sge
@@ -1515,7 +1513,7 @@ static void ipoib_cm_create_srq(struct net_device *dev, int max_sge)
return;
}
- priv->cm.srq_ring = vmalloc(ipoib_recvq_size * sizeof *priv->cm.srq_ring);
+ priv->cm.srq_ring = vzalloc(ipoib_recvq_size * sizeof *priv->cm.srq_ring);
if (!priv->cm.srq_ring) {
printk(KERN_WARNING "%s: failed to allocate CM SRQ ring (%d entries)\n",
priv->ca->name, ipoib_recvq_size);
@@ -1524,7 +1522,6 @@ static void ipoib_cm_create_srq(struct net_device *dev, int max_sge)
return;
}
- memset(priv->cm.srq_ring, 0, ipoib_recvq_size * sizeof *priv->cm.srq_ring);
}
int ipoib_cm_dev_init(struct net_device *dev)
@@ -1574,7 +1571,8 @@ int ipoib_cm_dev_init(struct net_device *dev)
for (i = 0; i < ipoib_recvq_size; ++i) {
if (!ipoib_cm_alloc_rx_skb(dev, priv->cm.srq_ring, i,
priv->cm.num_frags - 1,
- priv->cm.srq_ring[i].mapping)) {
+ priv->cm.srq_ring[i].mapping,
+ GFP_KERNEL)) {
ipoib_warn(priv, "failed to allocate "
"receive buffer %d\n", i);
ipoib_cm_dev_cleanup(dev);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
index e9795f60e5d..078cadd6c79 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
@@ -39,14 +39,24 @@
static void ipoib_get_drvinfo(struct net_device *netdev,
struct ethtool_drvinfo *drvinfo)
{
- strncpy(drvinfo->driver, "ipoib", sizeof(drvinfo->driver) - 1);
-}
+ struct ipoib_dev_priv *priv = netdev_priv(netdev);
+ struct ib_device_attr *attr;
-static u32 ipoib_get_rx_csum(struct net_device *dev)
-{
- struct ipoib_dev_priv *priv = netdev_priv(dev);
- return test_bit(IPOIB_FLAG_CSUM, &priv->flags) &&
- !test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
+ attr = kmalloc(sizeof(*attr), GFP_KERNEL);
+ if (attr && !ib_query_device(priv->ca, attr))
+ snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+ "%d.%d.%d", (int)(attr->fw_ver >> 32),
+ (int)(attr->fw_ver >> 16) & 0xffff,
+ (int)attr->fw_ver & 0xffff);
+ kfree(attr);
+
+ strlcpy(drvinfo->bus_info, dev_name(priv->ca->dma_device),
+ sizeof(drvinfo->bus_info));
+
+ strlcpy(drvinfo->version, ipoib_driver_version,
+ sizeof(drvinfo->version));
+
+ strlcpy(drvinfo->driver, "ib_ipoib", sizeof(drvinfo->driver));
}
static int ipoib_get_coalesce(struct net_device *dev,
@@ -55,9 +65,7 @@ static int ipoib_get_coalesce(struct net_device *dev,
struct ipoib_dev_priv *priv = netdev_priv(dev);
coal->rx_coalesce_usecs = priv->ethtool.coalesce_usecs;
- coal->tx_coalesce_usecs = priv->ethtool.coalesce_usecs;
coal->rx_max_coalesced_frames = priv->ethtool.max_coalesced_frames;
- coal->tx_max_coalesced_frames = priv->ethtool.max_coalesced_frames;
return 0;
}
@@ -69,10 +77,8 @@ static int ipoib_set_coalesce(struct net_device *dev,
int ret;
/*
- * Since IPoIB uses a single CQ for both rx and tx, we assume
- * that rx params dictate the configuration. These values are
- * saved in the private data and returned when ipoib_get_coalesce()
- * is called.
+ * These values are saved in the private data and returned
+ * when ipoib_get_coalesce() is called
*/
if (coal->rx_coalesce_usecs > 0xffff ||
coal->rx_max_coalesced_frames > 0xffff)
@@ -85,68 +91,19 @@ static int ipoib_set_coalesce(struct net_device *dev,
return ret;
}
- coal->tx_coalesce_usecs = coal->rx_coalesce_usecs;
- coal->tx_max_coalesced_frames = coal->rx_max_coalesced_frames;
priv->ethtool.coalesce_usecs = coal->rx_coalesce_usecs;
priv->ethtool.max_coalesced_frames = coal->rx_max_coalesced_frames;
return 0;
}
-static const char ipoib_stats_keys[][ETH_GSTRING_LEN] = {
- "LRO aggregated", "LRO flushed",
- "LRO avg aggr", "LRO no desc"
-};
-
-static void ipoib_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
-{
- switch (stringset) {
- case ETH_SS_STATS:
- memcpy(data, *ipoib_stats_keys, sizeof(ipoib_stats_keys));
- break;
- }
-}
-
-static int ipoib_get_sset_count(struct net_device *dev, int sset)
-{
- switch (sset) {
- case ETH_SS_STATS:
- return ARRAY_SIZE(ipoib_stats_keys);
- default:
- return -EOPNOTSUPP;
- }
-}
-
-static void ipoib_get_ethtool_stats(struct net_device *dev,
- struct ethtool_stats *stats, uint64_t *data)
-{
- struct ipoib_dev_priv *priv = netdev_priv(dev);
- int index = 0;
-
- /* Get LRO statistics */
- data[index++] = priv->lro.lro_mgr.stats.aggregated;
- data[index++] = priv->lro.lro_mgr.stats.flushed;
- if (priv->lro.lro_mgr.stats.flushed)
- data[index++] = priv->lro.lro_mgr.stats.aggregated /
- priv->lro.lro_mgr.stats.flushed;
- else
- data[index++] = 0;
- data[index++] = priv->lro.lro_mgr.stats.no_desc;
-}
-
static const struct ethtool_ops ipoib_ethtool_ops = {
.get_drvinfo = ipoib_get_drvinfo,
- .get_rx_csum = ipoib_get_rx_csum,
.get_coalesce = ipoib_get_coalesce,
.set_coalesce = ipoib_set_coalesce,
- .get_flags = ethtool_op_get_flags,
- .set_flags = ethtool_op_set_flags,
- .get_strings = ipoib_get_strings,
- .get_sset_count = ipoib_get_sset_count,
- .get_ethtool_stats = ipoib_get_ethtool_stats,
};
void ipoib_set_ethtool_ops(struct net_device *dev)
{
- SET_ETHTOOL_OPS(dev, &ipoib_ethtool_ops);
+ dev->ethtool_ops = &ipoib_ethtool_ops;
}
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_fs.c b/drivers/infiniband/ulp/ipoib/ipoib_fs.c
index 961c585da21..50061854616 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_fs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_fs.c
@@ -32,10 +32,12 @@
#include <linux/err.h>
#include <linux/seq_file.h>
+#include <linux/slab.h>
struct file_operations;
#include <linux/debugfs.h>
+#include <linux/export.h>
#include "ipoib.h"
@@ -211,16 +213,15 @@ static int ipoib_path_seq_show(struct seq_file *file, void *iter_ptr)
gid_buf, path.pathrec.dlid ? "yes" : "no");
if (path.pathrec.dlid) {
- rate = ib_rate_to_mult(path.pathrec.rate) * 25;
+ rate = ib_rate_to_mbps(path.pathrec.rate);
seq_printf(file,
" DLID: 0x%04x\n"
" SL: %12d\n"
- " rate: %*d%s Gb/sec\n",
+ " rate: %8d.%d Gb/sec\n",
be16_to_cpu(path.pathrec.dlid),
path.pathrec.sl,
- 10 - ((rate % 10) ? 2 : 0),
- rate / 10, rate % 10 ? ".5" : "");
+ rate / 1000, rate % 1000);
}
seq_putc(file, '\n');
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index a1925810be3..6a7003ddb0b 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -34,9 +34,10 @@
*/
#include <linux/delay.h>
+#include <linux/moduleparam.h>
#include <linux/dma-mapping.h>
+#include <linux/slab.h>
-#include <rdma/ib_cache.h>
#include <linux/ip.h>
#include <linux/tcp.h>
@@ -56,21 +57,24 @@ struct ipoib_ah *ipoib_create_ah(struct net_device *dev,
struct ib_pd *pd, struct ib_ah_attr *attr)
{
struct ipoib_ah *ah;
+ struct ib_ah *vah;
ah = kmalloc(sizeof *ah, GFP_KERNEL);
if (!ah)
- return NULL;
+ return ERR_PTR(-ENOMEM);
ah->dev = dev;
ah->last_send = 0;
kref_init(&ah->ref);
- ah->ah = ib_create_ah(pd, attr);
- if (IS_ERR(ah->ah)) {
+ vah = ib_create_ah(pd, attr);
+ if (IS_ERR(vah)) {
kfree(ah);
- ah = NULL;
- } else
+ ah = (struct ipoib_ah *)vah;
+ } else {
+ ah->ah = vah;
ipoib_dbg(netdev_priv(dev), "Created ah %p\n", ah->ah);
+ }
return ah;
}
@@ -117,9 +121,9 @@ static void ipoib_ud_skb_put_frags(struct ipoib_dev_priv *priv,
size = length - IPOIB_UD_HEAD_SIZE;
- frag->size = size;
+ skb_frag_size_set(frag, size);
skb->data_len += size;
- skb->truesize += size;
+ skb->truesize += PAGE_SIZE;
} else
skb_put(skb, length);
@@ -152,14 +156,18 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id)
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct sk_buff *skb;
int buf_size;
+ int tailroom;
u64 *mapping;
- if (ipoib_ud_need_sg(priv->max_ib_mtu))
+ if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
buf_size = IPOIB_UD_HEAD_SIZE;
- else
+ tailroom = 128; /* reserve some tailroom for IP/TCP headers */
+ } else {
buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);
+ tailroom = 0;
+ }
- skb = dev_alloc_skb(buf_size + 4);
+ skb = dev_alloc_skb(buf_size + tailroom + 4);
if (unlikely(!skb))
return NULL;
@@ -182,7 +190,7 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id)
goto partial_error;
skb_fill_page_desc(skb, 0, page, 0, PAGE_SIZE);
mapping[1] =
- ib_dma_map_page(priv->ca, skb_shinfo(skb)->frags[0].page,
+ ib_dma_map_page(priv->ca, page,
0, PAGE_SIZE, DMA_FROM_DEVICE);
if (unlikely(ib_dma_mapping_error(priv->ca, mapping[1])))
goto partial_error;
@@ -223,6 +231,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
unsigned int wr_id = wc->wr_id & ~IPOIB_OP_RECV;
struct sk_buff *skb;
u64 mapping[IPOIB_UD_RX_SG];
+ union ib_gid *dgid;
ipoib_dbg_data(priv, "recv completion: id %d, status: %d\n",
wr_id, wc->status);
@@ -271,27 +280,31 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
ipoib_ud_dma_unmap_rx(priv, mapping);
ipoib_ud_skb_put_frags(priv, skb, wc->byte_len);
+ /* First byte of dgid signals multicast when 0xff */
+ dgid = &((struct ib_grh *)skb->data)->dgid;
+
+ if (!(wc->wc_flags & IB_WC_GRH) || dgid->raw[0] != 0xff)
+ skb->pkt_type = PACKET_HOST;
+ else if (memcmp(dgid, dev->broadcast + 4, sizeof(union ib_gid)) == 0)
+ skb->pkt_type = PACKET_BROADCAST;
+ else
+ skb->pkt_type = PACKET_MULTICAST;
+
skb_pull(skb, IB_GRH_BYTES);
skb->protocol = ((struct ipoib_header *) skb->data)->proto;
skb_reset_mac_header(skb);
skb_pull(skb, IPOIB_ENCAP_LEN);
- dev->last_rx = jiffies;
++dev->stats.rx_packets;
dev->stats.rx_bytes += skb->len;
skb->dev = dev;
- /* XXX get correct PACKET_ type here */
- skb->pkt_type = PACKET_HOST;
-
- if (test_bit(IPOIB_FLAG_CSUM, &priv->flags) && likely(wc->csum_ok))
+ if ((dev->features & NETIF_F_RXCSUM) &&
+ likely(wc->wc_flags & IB_WC_IP_CSUM_OK))
skb->ip_summed = CHECKSUM_UNNECESSARY;
- if (dev->features & NETIF_F_LRO)
- lro_receive_skb(&priv->lro.lro_mgr, skb, NULL);
- else
- netif_receive_skb(skb);
+ napi_gro_receive(&priv->napi, skb);
repost:
if (unlikely(ipoib_ib_post_receive(dev, wr_id)))
@@ -318,9 +331,10 @@ static int ipoib_dma_map_tx(struct ib_device *ca,
off = 0;
for (i = 0; i < skb_shinfo(skb)->nr_frags; ++i) {
- skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
- mapping[i + off] = ib_dma_map_page(ca, frag->page,
- frag->page_offset, frag->size,
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+ mapping[i + off] = ib_dma_map_page(ca,
+ skb_frag_page(frag),
+ frag->page_offset, skb_frag_size(frag),
DMA_TO_DEVICE);
if (unlikely(ib_dma_mapping_error(ca, mapping[i + off])))
goto partial_error;
@@ -329,8 +343,9 @@ static int ipoib_dma_map_tx(struct ib_device *ca,
partial_error:
for (; i > 0; --i) {
- skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
- ib_dma_unmap_page(ca, mapping[i - !off], frag->size, DMA_TO_DEVICE);
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
+
+ ib_dma_unmap_page(ca, mapping[i - !off], skb_frag_size(frag), DMA_TO_DEVICE);
}
if (off)
@@ -354,8 +369,9 @@ static void ipoib_dma_unmap_tx(struct ib_device *ca,
off = 0;
for (i = 0; i < skb_shinfo(skb)->nr_frags; ++i) {
- skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
- ib_dma_unmap_page(ca, mapping[i + off], frag->size,
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+ ib_dma_unmap_page(ca, mapping[i + off], skb_frag_size(frag),
DMA_TO_DEVICE);
}
}
@@ -443,14 +459,11 @@ poll_more:
}
if (done < budget) {
- if (dev->features & NETIF_F_LRO)
- lro_flush_all(&priv->lro.lro_mgr);
-
- netif_rx_complete(napi);
+ napi_complete(napi);
if (unlikely(ib_req_notify_cq(priv->recv_cq,
IB_CQ_NEXT_COMP |
IB_CQ_REPORT_MISSED_EVENTS)) &&
- netif_rx_reschedule(napi))
+ napi_reschedule(napi))
goto poll_more;
}
@@ -462,7 +475,7 @@ void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr)
struct net_device *dev = dev_ptr;
struct ipoib_dev_priv *priv = netdev_priv(dev);
- netif_rx_schedule(&priv->napi);
+ napi_schedule(&priv->napi);
}
static void drain_tx_cq(struct net_device *dev)
@@ -508,7 +521,7 @@ static inline int post_send(struct ipoib_dev_priv *priv,
for (i = 0; i < nr_frags; ++i) {
priv->tx_sge[i + off].addr = mapping[i + off];
- priv->tx_sge[i + off].length = frags[i].size;
+ priv->tx_sge[i + off].length = skb_frag_size(&frags[i]);
}
priv->tx_wr.num_sge = nr_frags + off;
priv->tx_wr.wr_id = wr_id;
@@ -531,7 +544,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb,
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_tx_buf *tx_req;
- int hlen;
+ int hlen, rc;
void *phead;
if (skb_is_gso(skb)) {
@@ -587,9 +600,13 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb,
netif_stop_queue(dev);
}
- if (unlikely(post_send(priv, priv->tx_head & (ipoib_sendq_size - 1),
- address->ah, qpn, tx_req, phead, hlen))) {
- ipoib_warn(priv, "post_send failed\n");
+ skb_orphan(skb);
+ skb_dst_drop(skb);
+
+ rc = post_send(priv, priv->tx_head & (ipoib_sendq_size - 1),
+ address->ah, qpn, tx_req, phead, hlen);
+ if (unlikely(rc)) {
+ ipoib_warn(priv, "post_send failed, error %d\n", rc);
++dev->stats.tx_errors;
--priv->tx_outstanding;
ipoib_dma_unmap_tx(priv->ca, tx_req);
@@ -601,8 +618,6 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb,
address->last_send = priv->tx_head;
++priv->tx_head;
- skb_orphan(skb);
-
}
if (unlikely(priv->tx_outstanding > MAX_SEND_CQE))
@@ -670,24 +685,28 @@ int ipoib_ib_dev_open(struct net_device *dev)
ret = ipoib_ib_post_receives(dev);
if (ret) {
ipoib_warn(priv, "ipoib_ib_post_receives returned %d\n", ret);
- ipoib_ib_dev_stop(dev, 1);
- return -1;
+ goto dev_stop;
}
ret = ipoib_cm_dev_open(dev);
if (ret) {
ipoib_warn(priv, "ipoib_cm_dev_open returned %d\n", ret);
- ipoib_ib_dev_stop(dev, 1);
- return -1;
+ goto dev_stop;
}
clear_bit(IPOIB_STOP_REAPER, &priv->flags);
queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task,
round_jiffies_relative(HZ));
- set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);
+ if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
+ napi_enable(&priv->napi);
return 0;
+dev_stop:
+ if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
+ napi_enable(&priv->napi);
+ ipoib_ib_dev_stop(dev, 1);
+ return -1;
}
static void ipoib_pkey_dev_check_presence(struct net_device *dev)
@@ -730,10 +749,8 @@ int ipoib_ib_dev_down(struct net_device *dev, int flush)
if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) {
mutex_lock(&pkey_mutex);
set_bit(IPOIB_PKEY_STOP, &priv->flags);
- cancel_delayed_work(&priv->pkey_poll_task);
+ cancel_delayed_work_sync(&priv->pkey_poll_task);
mutex_unlock(&pkey_mutex);
- if (flush)
- flush_workqueue(ipoib_workqueue);
}
ipoib_mcast_stop_thread(dev, flush);
@@ -804,7 +821,8 @@ int ipoib_ib_dev_stop(struct net_device *dev, int flush)
struct ipoib_tx_buf *tx_req;
int i;
- clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);
+ if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
+ napi_disable(&priv->napi);
ipoib_cm_dev_stop(dev);
@@ -915,14 +933,49 @@ int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
return 0;
}
+/*
+ * Takes whatever value which is in pkey index 0 and updates priv->pkey
+ * returns 0 if the pkey value was changed.
+ */
+static inline int update_parent_pkey(struct ipoib_dev_priv *priv)
+{
+ int result;
+ u16 prev_pkey;
+
+ prev_pkey = priv->pkey;
+ result = ib_query_pkey(priv->ca, priv->port, 0, &priv->pkey);
+ if (result) {
+ ipoib_warn(priv, "ib_query_pkey port %d failed (ret = %d)\n",
+ priv->port, result);
+ return result;
+ }
+
+ priv->pkey |= 0x8000;
+
+ if (prev_pkey != priv->pkey) {
+ ipoib_dbg(priv, "pkey changed from 0x%x to 0x%x\n",
+ prev_pkey, priv->pkey);
+ /*
+ * Update the pkey in the broadcast address, while making sure to set
+ * the full membership bit, so that we join the right broadcast group.
+ */
+ priv->dev->broadcast[8] = priv->pkey >> 8;
+ priv->dev->broadcast[9] = priv->pkey & 0xff;
+ return 0;
+ }
+
+ return 1;
+}
+
static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
enum ipoib_flush_level level)
{
struct ipoib_dev_priv *cpriv;
struct net_device *dev = priv->dev;
u16 new_index;
+ int result;
- mutex_lock(&priv->vlan_mutex);
+ down_read(&priv->vlan_rwsem);
/*
* Flush any child interfaces too -- they might be up even if
@@ -931,9 +984,13 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
list_for_each_entry(cpriv, &priv->child_intfs, list)
__ipoib_ib_dev_flush(cpriv, level);
- mutex_unlock(&priv->vlan_mutex);
+ up_read(&priv->vlan_rwsem);
if (!test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) {
+ /* for non-child devices must check/update the pkey value here */
+ if (level == IPOIB_FLUSH_HEAVY &&
+ !test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags))
+ update_parent_pkey(priv);
ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_INITIALIZED not set.\n");
return;
}
@@ -944,21 +1001,32 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
}
if (level == IPOIB_FLUSH_HEAVY) {
- if (ib_find_pkey(priv->ca, priv->port, priv->pkey, &new_index)) {
- clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
- ipoib_ib_dev_down(dev, 0);
- ipoib_ib_dev_stop(dev, 0);
- if (ipoib_pkey_dev_delay_open(dev))
+ /* child devices chase their origin pkey value, while non-child
+ * (parent) devices should always takes what present in pkey index 0
+ */
+ if (test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
+ if (ib_find_pkey(priv->ca, priv->port, priv->pkey, &new_index)) {
+ clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
+ ipoib_ib_dev_down(dev, 0);
+ ipoib_ib_dev_stop(dev, 0);
+ if (ipoib_pkey_dev_delay_open(dev))
+ return;
+ }
+ /* restart QP only if P_Key index is changed */
+ if (test_and_set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags) &&
+ new_index == priv->pkey_index) {
+ ipoib_dbg(priv, "Not flushing - P_Key index not changed.\n");
return;
+ }
+ priv->pkey_index = new_index;
+ } else {
+ result = update_parent_pkey(priv);
+ /* restart QP only if P_Key value changed */
+ if (result) {
+ ipoib_dbg(priv, "Not flushing - P_Key value not changed.\n");
+ return;
+ }
}
-
- /* restart QP only if P_Key index is changed */
- if (test_and_set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags) &&
- new_index == priv->pkey_index) {
- ipoib_dbg(priv, "Not flushing - P_Key index not changed.\n");
- return;
- }
- priv->pkey_index = new_index;
}
if (level == IPOIB_FLUSH_LIGHT) {
@@ -1014,6 +1082,11 @@ void ipoib_ib_dev_cleanup(struct net_device *dev)
struct ipoib_dev_priv *priv = netdev_priv(dev);
ipoib_dbg(priv, "cleaning up ib_dev\n");
+ /*
+ * We must make sure there are no more (path) completions
+ * that may wish to touch priv fields that are no longer valid
+ */
+ ipoib_flush_paths(dev);
ipoib_mcast_stop_thread(dev, 1);
ipoib_mcast_dev_flush(dev);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 0bd2a4ff084..5786a78ff8b 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -46,11 +46,17 @@
#include <linux/ip.h>
#include <linux/in.h>
-#include <net/dst.h>
+#include <linux/jhash.h>
+#include <net/arp.h>
+
+#define DRV_VERSION "1.0.0"
+
+const char ipoib_driver_version[] = DRV_VERSION;
MODULE_AUTHOR("Roland Dreier");
MODULE_DESCRIPTION("IP-over-InfiniBand net driver");
MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION(DRV_VERSION);
int ipoib_sendq_size __read_mostly = IPOIB_TX_RING_SIZE;
int ipoib_recvq_size __read_mostly = IPOIB_RX_RING_SIZE;
@@ -60,15 +66,6 @@ MODULE_PARM_DESC(send_queue_size, "Number of descriptors in send queue");
module_param_named(recv_queue_size, ipoib_recvq_size, int, 0444);
MODULE_PARM_DESC(recv_queue_size, "Number of descriptors in receive queue");
-static int lro;
-module_param(lro, bool, 0444);
-MODULE_PARM_DESC(lro, "Enable LRO (Large Receive Offload)");
-
-static int lro_max_aggr = IPOIB_LRO_MAX_AGGR;
-module_param(lro_max_aggr, int, 0644);
-MODULE_PARM_DESC(lro_max_aggr, "LRO: Max packets to be aggregated "
- "(default = 64)");
-
#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
int ipoib_debug_level;
@@ -93,6 +90,7 @@ struct ib_sa_client ipoib_sa_client;
static void ipoib_add_one(struct ib_device *device);
static void ipoib_remove_one(struct ib_device *device);
+static void ipoib_neigh_reclaim(struct rcu_head *rp);
static struct ib_client ipoib_client = {
.name = "ipoib",
@@ -106,8 +104,9 @@ int ipoib_open(struct net_device *dev)
ipoib_dbg(priv, "bringing up interface\n");
- if (!test_and_set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
- napi_enable(&priv->napi);
+ netif_carrier_off(dev);
+
+ set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
if (ipoib_pkey_dev_delay_open(dev))
return 0;
@@ -122,7 +121,7 @@ int ipoib_open(struct net_device *dev)
struct ipoib_dev_priv *cpriv;
/* Bring up any child interfaces too */
- mutex_lock(&priv->vlan_mutex);
+ down_read(&priv->vlan_rwsem);
list_for_each_entry(cpriv, &priv->child_intfs, list) {
int flags;
@@ -132,7 +131,7 @@ int ipoib_open(struct net_device *dev)
dev_change_flags(cpriv->dev, flags | IFF_UP);
}
- mutex_unlock(&priv->vlan_mutex);
+ up_read(&priv->vlan_rwsem);
}
netif_start_queue(dev);
@@ -143,7 +142,6 @@ err_stop:
ipoib_ib_dev_stop(dev, 1);
err_disable:
- napi_disable(&priv->napi);
clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
return -EINVAL;
@@ -156,18 +154,17 @@ static int ipoib_stop(struct net_device *dev)
ipoib_dbg(priv, "stopping interface\n");
clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
- napi_disable(&priv->napi);
netif_stop_queue(dev);
- ipoib_ib_dev_down(dev, 0);
+ ipoib_ib_dev_down(dev, 1);
ipoib_ib_dev_stop(dev, 0);
if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
struct ipoib_dev_priv *cpriv;
/* Bring down any child interfaces too */
- mutex_lock(&priv->vlan_mutex);
+ down_read(&priv->vlan_rwsem);
list_for_each_entry(cpriv, &priv->child_intfs, list) {
int flags;
@@ -177,12 +174,27 @@ static int ipoib_stop(struct net_device *dev)
dev_change_flags(cpriv->dev, flags & ~IFF_UP);
}
- mutex_unlock(&priv->vlan_mutex);
+ up_read(&priv->vlan_rwsem);
}
return 0;
}
+static void ipoib_uninit(struct net_device *dev)
+{
+ ipoib_dev_cleanup(dev);
+}
+
+static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_features_t features)
+{
+ struct ipoib_dev_priv *priv = netdev_priv(dev);
+
+ if (test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags))
+ features &= ~(NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO);
+
+ return features;
+}
+
static int ipoib_change_mtu(struct net_device *dev, int new_mtu)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -210,6 +222,37 @@ static int ipoib_change_mtu(struct net_device *dev, int new_mtu)
return 0;
}
+int ipoib_set_mode(struct net_device *dev, const char *buf)
+{
+ struct ipoib_dev_priv *priv = netdev_priv(dev);
+
+ /* flush paths if we switch modes so that connections are restarted */
+ if (IPOIB_CM_SUPPORTED(dev->dev_addr) && !strcmp(buf, "connected\n")) {
+ set_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
+ ipoib_warn(priv, "enabling connected mode "
+ "will cause multicast packet drops\n");
+ netdev_update_features(dev);
+ rtnl_unlock();
+ priv->tx_wr.send_flags &= ~IB_SEND_IP_CSUM;
+
+ ipoib_flush_paths(dev);
+ rtnl_lock();
+ return 0;
+ }
+
+ if (!strcmp(buf, "datagram\n")) {
+ clear_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
+ netdev_update_features(dev);
+ dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu));
+ rtnl_unlock();
+ ipoib_flush_paths(dev);
+ rtnl_lock();
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
static struct ipoib_path *__path_find(struct net_device *dev, void *gid)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -266,30 +309,15 @@ static int __path_add(struct net_device *dev, struct ipoib_path *path)
static void path_free(struct net_device *dev, struct ipoib_path *path)
{
- struct ipoib_dev_priv *priv = netdev_priv(dev);
- struct ipoib_neigh *neigh, *tn;
struct sk_buff *skb;
- unsigned long flags;
while ((skb = __skb_dequeue(&path->queue)))
dev_kfree_skb_irq(skb);
- spin_lock_irqsave(&priv->lock, flags);
-
- list_for_each_entry_safe(neigh, tn, &path->neigh_list, list) {
- /*
- * It's safe to call ipoib_put_ah() inside priv->lock
- * here, because we know that path->ah will always
- * hold one more reference, so ipoib_put_ah() will
- * never do more than decrement the ref count.
- */
- if (neigh->ah)
- ipoib_put_ah(neigh->ah);
-
- ipoib_neigh_free(dev, neigh);
- }
+ ipoib_dbg(netdev_priv(dev), "path_free\n");
- spin_unlock_irqrestore(&priv->lock, flags);
+ /* remove all neigh connected to this path */
+ ipoib_del_neighs_by_gid(dev, path->pathrec.dgid.raw);
if (path->ah)
ipoib_put_ah(path->ah);
@@ -434,7 +462,7 @@ static void path_rec_completion(int status,
spin_lock_irqsave(&priv->lock, flags);
- if (ah) {
+ if (!IS_ERR_OR_NULL(ah)) {
path->pathrec = *pathrec;
old_ah = path->ah;
@@ -460,19 +488,14 @@ static void path_rec_completion(int status,
}
kref_get(&path->ah->ref);
neigh->ah = path->ah;
- memcpy(&neigh->dgid.raw, &path->pathrec.dgid.raw,
- sizeof(union ib_gid));
- if (ipoib_cm_enabled(dev, neigh->neighbour)) {
+ if (ipoib_cm_enabled(dev, neigh->daddr)) {
if (!ipoib_cm_get(neigh))
ipoib_cm_set(neigh, ipoib_cm_create_tx(dev,
path,
neigh));
if (!ipoib_cm_get(neigh)) {
- list_del(&neigh->list);
- if (neigh->ah)
- ipoib_put_ah(neigh->ah);
- ipoib_neigh_free(dev, neigh);
+ ipoib_neigh_free(neigh);
continue;
}
}
@@ -488,6 +511,9 @@ static void path_rec_completion(int status,
spin_unlock_irqrestore(&priv->lock, flags);
+ if (IS_ERR_OR_NULL(ah))
+ ipoib_del_neighs_by_gid(dev, path->pathrec.dgid.raw);
+
if (old_ah)
ipoib_put_ah(old_ah);
@@ -557,25 +583,26 @@ static int path_rec_start(struct net_device *dev,
return 0;
}
-static void neigh_add_path(struct sk_buff *skb, struct net_device *dev)
+static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
+ struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_path *path;
struct ipoib_neigh *neigh;
unsigned long flags;
- neigh = ipoib_neigh_alloc(skb->dst->neighbour, skb->dev);
+ spin_lock_irqsave(&priv->lock, flags);
+ neigh = ipoib_neigh_alloc(daddr, dev);
if (!neigh) {
+ spin_unlock_irqrestore(&priv->lock, flags);
++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
return;
}
- spin_lock_irqsave(&priv->lock, flags);
-
- path = __path_find(dev, skb->dst->neighbour->ha + 4);
+ path = __path_find(dev, daddr + 4);
if (!path) {
- path = path_rec_create(dev, skb->dst->neighbour->ha + 4);
+ path = path_rec_create(dev, daddr + 4);
if (!path)
goto err_path;
@@ -587,17 +614,12 @@ static void neigh_add_path(struct sk_buff *skb, struct net_device *dev)
if (path->ah) {
kref_get(&path->ah->ref);
neigh->ah = path->ah;
- memcpy(&neigh->dgid.raw, &path->pathrec.dgid.raw,
- sizeof(union ib_gid));
- if (ipoib_cm_enabled(dev, neigh->neighbour)) {
+ if (ipoib_cm_enabled(dev, neigh->daddr)) {
if (!ipoib_cm_get(neigh))
ipoib_cm_set(neigh, ipoib_cm_create_tx(dev, path, neigh));
if (!ipoib_cm_get(neigh)) {
- list_del(&neigh->list);
- if (neigh->ah)
- ipoib_put_ah(neigh->ah);
- ipoib_neigh_free(dev, neigh);
+ ipoib_neigh_free(neigh);
goto err_drop;
}
if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)
@@ -607,50 +629,37 @@ static void neigh_add_path(struct sk_buff *skb, struct net_device *dev)
skb_queue_len(&neigh->queue));
goto err_drop;
}
- } else
- ipoib_send(dev, skb, path->ah, IPOIB_QPN(skb->dst->neighbour->ha));
+ } else {
+ spin_unlock_irqrestore(&priv->lock, flags);
+ ipoib_send(dev, skb, path->ah, IPOIB_QPN(daddr));
+ ipoib_neigh_put(neigh);
+ return;
+ }
} else {
neigh->ah = NULL;
if (!path->query && path_rec_start(dev, path))
- goto err_list;
+ goto err_path;
__skb_queue_tail(&neigh->queue, skb);
}
spin_unlock_irqrestore(&priv->lock, flags);
+ ipoib_neigh_put(neigh);
return;
-err_list:
- list_del(&neigh->list);
-
err_path:
- ipoib_neigh_free(dev, neigh);
+ ipoib_neigh_free(neigh);
err_drop:
++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
spin_unlock_irqrestore(&priv->lock, flags);
-}
-
-static void ipoib_path_lookup(struct sk_buff *skb, struct net_device *dev)
-{
- struct ipoib_dev_priv *priv = netdev_priv(skb->dev);
-
- /* Look up path record for unicasts */
- if (skb->dst->neighbour->ha[4] != 0xff) {
- neigh_add_path(skb, dev);
- return;
- }
-
- /* Add in the P_Key for multicasts */
- skb->dst->neighbour->ha[8] = (priv->pkey >> 8) & 0xff;
- skb->dst->neighbour->ha[9] = priv->pkey & 0xff;
- ipoib_mcast_send(dev, skb->dst->neighbour->ha + 4, skb);
+ ipoib_neigh_put(neigh);
}
static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
- struct ipoib_pseudoheader *phdr)
+ struct ipoib_cb *cb)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_path *path;
@@ -658,18 +667,21 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
spin_lock_irqsave(&priv->lock, flags);
- path = __path_find(dev, phdr->hwaddr + 4);
+ path = __path_find(dev, cb->hwaddr + 4);
if (!path || !path->valid) {
- if (!path)
- path = path_rec_create(dev, phdr->hwaddr + 4);
+ int new_path = 0;
+
+ if (!path) {
+ path = path_rec_create(dev, cb->hwaddr + 4);
+ new_path = 1;
+ }
if (path) {
- /* put pseudoheader back on for next time */
- skb_push(skb, sizeof *phdr);
__skb_queue_tail(&path->queue, skb);
if (!path->query && path_rec_start(dev, path)) {
spin_unlock_irqrestore(&priv->lock, flags);
- path_free(dev, path);
+ if (new_path)
+ path_free(dev, path);
return;
} else
__path_add(dev, path);
@@ -686,11 +698,11 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
ipoib_dbg(priv, "Send unicast ARP to %04x\n",
be16_to_cpu(path->pathrec.dlid));
- ipoib_send(dev, skb, path->ah, IPOIB_QPN(phdr->hwaddr));
+ spin_unlock_irqrestore(&priv->lock, flags);
+ ipoib_send(dev, skb, path->ah, IPOIB_QPN(cb->hwaddr));
+ return;
} else if ((path->query || !path_rec_start(dev, path)) &&
skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
- /* put pseudoheader back on for next time */
- skb_push(skb, sizeof *phdr);
__skb_queue_tail(&path->queue, skb);
} else {
++dev->stats.tx_dropped;
@@ -704,85 +716,82 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_neigh *neigh;
+ struct ipoib_cb *cb = (struct ipoib_cb *) skb->cb;
+ struct ipoib_header *header;
unsigned long flags;
- if (likely(skb->dst && skb->dst->neighbour)) {
- if (unlikely(!*to_ipoib_neigh(skb->dst->neighbour))) {
- ipoib_path_lookup(skb, dev);
- return NETDEV_TX_OK;
- }
+ header = (struct ipoib_header *) skb->data;
- neigh = *to_ipoib_neigh(skb->dst->neighbour);
-
- if (unlikely((memcmp(&neigh->dgid.raw,
- skb->dst->neighbour->ha + 4,
- sizeof(union ib_gid))) ||
- (neigh->dev != dev))) {
- spin_lock_irqsave(&priv->lock, flags);
- /*
- * It's safe to call ipoib_put_ah() inside
- * priv->lock here, because we know that
- * path->ah will always hold one more reference,
- * so ipoib_put_ah() will never do more than
- * decrement the ref count.
- */
- if (neigh->ah)
- ipoib_put_ah(neigh->ah);
- list_del(&neigh->list);
- ipoib_neigh_free(dev, neigh);
- spin_unlock_irqrestore(&priv->lock, flags);
- ipoib_path_lookup(skb, dev);
+ if (unlikely(cb->hwaddr[4] == 0xff)) {
+ /* multicast, arrange "if" according to probability */
+ if ((header->proto != htons(ETH_P_IP)) &&
+ (header->proto != htons(ETH_P_IPV6)) &&
+ (header->proto != htons(ETH_P_ARP)) &&
+ (header->proto != htons(ETH_P_RARP)) &&
+ (header->proto != htons(ETH_P_TIPC))) {
+ /* ethertype not supported by IPoIB */
+ ++dev->stats.tx_dropped;
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
+ /* Add in the P_Key for multicast*/
+ cb->hwaddr[8] = (priv->pkey >> 8) & 0xff;
+ cb->hwaddr[9] = priv->pkey & 0xff;
+
+ neigh = ipoib_neigh_get(dev, cb->hwaddr);
+ if (likely(neigh))
+ goto send_using_neigh;
+ ipoib_mcast_send(dev, cb->hwaddr, skb);
+ return NETDEV_TX_OK;
+ }
- if (ipoib_cm_get(neigh)) {
- if (ipoib_cm_up(neigh)) {
- ipoib_cm_send(dev, skb, ipoib_cm_get(neigh));
- return NETDEV_TX_OK;
- }
- } else if (neigh->ah) {
- ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(skb->dst->neighbour->ha));
+ /* unicast, arrange "switch" according to probability */
+ switch (header->proto) {
+ case htons(ETH_P_IP):
+ case htons(ETH_P_IPV6):
+ case htons(ETH_P_TIPC):
+ neigh = ipoib_neigh_get(dev, cb->hwaddr);
+ if (unlikely(!neigh)) {
+ neigh_add_path(skb, cb->hwaddr, dev);
return NETDEV_TX_OK;
}
+ break;
+ case htons(ETH_P_ARP):
+ case htons(ETH_P_RARP):
+ /* for unicast ARP and RARP should always perform path find */
+ unicast_arp_send(skb, dev, cb);
+ return NETDEV_TX_OK;
+ default:
+ /* ethertype not supported by IPoIB */
+ ++dev->stats.tx_dropped;
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
+ }
- if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
- spin_lock_irqsave(&priv->lock, flags);
- __skb_queue_tail(&neigh->queue, skb);
- spin_unlock_irqrestore(&priv->lock, flags);
- } else {
- ++dev->stats.tx_dropped;
- dev_kfree_skb_any(skb);
+send_using_neigh:
+ /* note we now hold a ref to neigh */
+ if (ipoib_cm_get(neigh)) {
+ if (ipoib_cm_up(neigh)) {
+ ipoib_cm_send(dev, skb, ipoib_cm_get(neigh));
+ goto unref;
}
- } else {
- struct ipoib_pseudoheader *phdr =
- (struct ipoib_pseudoheader *) skb->data;
- skb_pull(skb, sizeof *phdr);
-
- if (phdr->hwaddr[4] == 0xff) {
- /* Add in the P_Key for multicast*/
- phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff;
- phdr->hwaddr[9] = priv->pkey & 0xff;
-
- ipoib_mcast_send(dev, phdr->hwaddr + 4, skb);
- } else {
- /* unicast GID -- should be ARP or RARP reply */
-
- if ((be16_to_cpup((__be16 *) skb->data) != ETH_P_ARP) &&
- (be16_to_cpup((__be16 *) skb->data) != ETH_P_RARP)) {
- ipoib_warn(priv, "Unicast, no %s: type %04x, QPN %06x %pI6\n",
- skb->dst ? "neigh" : "dst",
- be16_to_cpup((__be16 *) skb->data),
- IPOIB_QPN(phdr->hwaddr),
- phdr->hwaddr + 4);
- dev_kfree_skb_any(skb);
- ++dev->stats.tx_dropped;
- return NETDEV_TX_OK;
- }
+ } else if (neigh->ah) {
+ ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(cb->hwaddr));
+ goto unref;
+ }
- unicast_arp_send(skb, dev, phdr);
- }
+ if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+ spin_lock_irqsave(&priv->lock, flags);
+ __skb_queue_tail(&neigh->queue, skb);
+ spin_unlock_irqrestore(&priv->lock, flags);
+ } else {
+ ++dev->stats.tx_dropped;
+ dev_kfree_skb_any(skb);
}
+unref:
+ ipoib_neigh_put(neigh);
+
return NETDEV_TX_OK;
}
@@ -804,6 +813,7 @@ static int ipoib_hard_header(struct sk_buff *skb,
const void *daddr, const void *saddr, unsigned len)
{
struct ipoib_header *header;
+ struct ipoib_cb *cb = (struct ipoib_cb *) skb->cb;
header = (struct ipoib_header *) skb_push(skb, sizeof *header);
@@ -811,17 +821,13 @@ static int ipoib_hard_header(struct sk_buff *skb,
header->reserved = 0;
/*
- * If we don't have a neighbour structure, stuff the
- * destination address onto the front of the skb so we can
- * figure out where to send the packet later.
+ * we don't rely on dst_entry structure, always stuff the
+ * destination address into skb->cb so we can figure out where
+ * to send the packet later.
*/
- if ((!skb->dst || !skb->dst->neighbour) && daddr) {
- struct ipoib_pseudoheader *phdr =
- (struct ipoib_pseudoheader *) skb_push(skb, sizeof *phdr);
- memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN);
- }
+ memcpy(cb->hwaddr, daddr, INFINIBAND_ALEN);
- return 0;
+ return sizeof *header;
}
static void ipoib_set_mcast_list(struct net_device *dev)
@@ -836,94 +842,443 @@ static void ipoib_set_mcast_list(struct net_device *dev)
queue_work(ipoib_workqueue, &priv->restart_task);
}
-static void ipoib_neigh_cleanup(struct neighbour *n)
+static u32 ipoib_addr_hash(struct ipoib_neigh_hash *htbl, u8 *daddr)
{
- struct ipoib_neigh *neigh;
- struct ipoib_dev_priv *priv = netdev_priv(n->dev);
+ /*
+ * Use only the address parts that contributes to spreading
+ * The subnet prefix is not used as one can not connect to
+ * same remote port (GUID) using the same remote QPN via two
+ * different subnets.
+ */
+ /* qpn octets[1:4) & port GUID octets[12:20) */
+ u32 *d32 = (u32 *) daddr;
+ u32 hv;
+
+ hv = jhash_3words(d32[3], d32[4], IPOIB_QPN_MASK & d32[0], 0);
+ return hv & htbl->mask;
+}
+
+struct ipoib_neigh *ipoib_neigh_get(struct net_device *dev, u8 *daddr)
+{
+ struct ipoib_dev_priv *priv = netdev_priv(dev);
+ struct ipoib_neigh_table *ntbl = &priv->ntbl;
+ struct ipoib_neigh_hash *htbl;
+ struct ipoib_neigh *neigh = NULL;
+ u32 hash_val;
+
+ rcu_read_lock_bh();
+
+ htbl = rcu_dereference_bh(ntbl->htbl);
+
+ if (!htbl)
+ goto out_unlock;
+
+ hash_val = ipoib_addr_hash(htbl, daddr);
+ for (neigh = rcu_dereference_bh(htbl->buckets[hash_val]);
+ neigh != NULL;
+ neigh = rcu_dereference_bh(neigh->hnext)) {
+ if (memcmp(daddr, neigh->daddr, INFINIBAND_ALEN) == 0) {
+ /* found, take one ref on behalf of the caller */
+ if (!atomic_inc_not_zero(&neigh->refcnt)) {
+ /* deleted */
+ neigh = NULL;
+ goto out_unlock;
+ }
+ neigh->alive = jiffies;
+ goto out_unlock;
+ }
+ }
+
+out_unlock:
+ rcu_read_unlock_bh();
+ return neigh;
+}
+
+static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
+{
+ struct ipoib_neigh_table *ntbl = &priv->ntbl;
+ struct ipoib_neigh_hash *htbl;
+ unsigned long neigh_obsolete;
+ unsigned long dt;
unsigned long flags;
- struct ipoib_ah *ah = NULL;
+ int i;
- neigh = *to_ipoib_neigh(n);
- if (neigh)
- priv = netdev_priv(neigh->dev);
- else
+ if (test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
return;
- ipoib_dbg(priv,
- "neigh_cleanup for %06x %pI6\n",
- IPOIB_QPN(n->ha),
- n->ha + 4);
spin_lock_irqsave(&priv->lock, flags);
- if (neigh->ah)
- ah = neigh->ah;
- list_del(&neigh->list);
- ipoib_neigh_free(n->dev, neigh);
+ htbl = rcu_dereference_protected(ntbl->htbl,
+ lockdep_is_held(&priv->lock));
+
+ if (!htbl)
+ goto out_unlock;
+
+ /* neigh is obsolete if it was idle for two GC periods */
+ dt = 2 * arp_tbl.gc_interval;
+ neigh_obsolete = jiffies - dt;
+ /* handle possible race condition */
+ if (test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
+ goto out_unlock;
+
+ for (i = 0; i < htbl->size; i++) {
+ struct ipoib_neigh *neigh;
+ struct ipoib_neigh __rcu **np = &htbl->buckets[i];
+
+ while ((neigh = rcu_dereference_protected(*np,
+ lockdep_is_held(&priv->lock))) != NULL) {
+ /* was the neigh idle for two GC periods */
+ if (time_after(neigh_obsolete, neigh->alive)) {
+ rcu_assign_pointer(*np,
+ rcu_dereference_protected(neigh->hnext,
+ lockdep_is_held(&priv->lock)));
+ /* remove from path/mc list */
+ list_del(&neigh->list);
+ call_rcu(&neigh->rcu, ipoib_neigh_reclaim);
+ } else {
+ np = &neigh->hnext;
+ }
+
+ }
+ }
+out_unlock:
spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static void ipoib_reap_neigh(struct work_struct *work)
+{
+ struct ipoib_dev_priv *priv =
+ container_of(work, struct ipoib_dev_priv, neigh_reap_task.work);
+
+ __ipoib_reap_neigh(priv);
- if (ah)
- ipoib_put_ah(ah);
+ if (!test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
+ queue_delayed_work(ipoib_workqueue, &priv->neigh_reap_task,
+ arp_tbl.gc_interval);
}
-struct ipoib_neigh *ipoib_neigh_alloc(struct neighbour *neighbour,
+
+static struct ipoib_neigh *ipoib_neigh_ctor(u8 *daddr,
struct net_device *dev)
{
struct ipoib_neigh *neigh;
- neigh = kmalloc(sizeof *neigh, GFP_ATOMIC);
+ neigh = kzalloc(sizeof *neigh, GFP_ATOMIC);
if (!neigh)
return NULL;
- neigh->neighbour = neighbour;
neigh->dev = dev;
- *to_ipoib_neigh(neighbour) = neigh;
+ memcpy(&neigh->daddr, daddr, sizeof(neigh->daddr));
skb_queue_head_init(&neigh->queue);
+ INIT_LIST_HEAD(&neigh->list);
ipoib_cm_set(neigh, NULL);
+ /* one ref on behalf of the caller */
+ atomic_set(&neigh->refcnt, 1);
+
+ return neigh;
+}
+
+struct ipoib_neigh *ipoib_neigh_alloc(u8 *daddr,
+ struct net_device *dev)
+{
+ struct ipoib_dev_priv *priv = netdev_priv(dev);
+ struct ipoib_neigh_table *ntbl = &priv->ntbl;
+ struct ipoib_neigh_hash *htbl;
+ struct ipoib_neigh *neigh;
+ u32 hash_val;
+
+ htbl = rcu_dereference_protected(ntbl->htbl,
+ lockdep_is_held(&priv->lock));
+ if (!htbl) {
+ neigh = NULL;
+ goto out_unlock;
+ }
+
+ /* need to add a new neigh, but maybe some other thread succeeded?
+ * recalc hash, maybe hash resize took place so we do a search
+ */
+ hash_val = ipoib_addr_hash(htbl, daddr);
+ for (neigh = rcu_dereference_protected(htbl->buckets[hash_val],
+ lockdep_is_held(&priv->lock));
+ neigh != NULL;
+ neigh = rcu_dereference_protected(neigh->hnext,
+ lockdep_is_held(&priv->lock))) {
+ if (memcmp(daddr, neigh->daddr, INFINIBAND_ALEN) == 0) {
+ /* found, take one ref on behalf of the caller */
+ if (!atomic_inc_not_zero(&neigh->refcnt)) {
+ /* deleted */
+ neigh = NULL;
+ break;
+ }
+ neigh->alive = jiffies;
+ goto out_unlock;
+ }
+ }
+
+ neigh = ipoib_neigh_ctor(daddr, dev);
+ if (!neigh)
+ goto out_unlock;
+
+ /* one ref on behalf of the hash table */
+ atomic_inc(&neigh->refcnt);
+ neigh->alive = jiffies;
+ /* put in hash */
+ rcu_assign_pointer(neigh->hnext,
+ rcu_dereference_protected(htbl->buckets[hash_val],
+ lockdep_is_held(&priv->lock)));
+ rcu_assign_pointer(htbl->buckets[hash_val], neigh);
+ atomic_inc(&ntbl->entries);
+
+out_unlock:
return neigh;
}
-void ipoib_neigh_free(struct net_device *dev, struct ipoib_neigh *neigh)
+void ipoib_neigh_dtor(struct ipoib_neigh *neigh)
{
+ /* neigh reference count was dropprd to zero */
+ struct net_device *dev = neigh->dev;
+ struct ipoib_dev_priv *priv = netdev_priv(dev);
struct sk_buff *skb;
- *to_ipoib_neigh(neigh->neighbour) = NULL;
+ if (neigh->ah)
+ ipoib_put_ah(neigh->ah);
while ((skb = __skb_dequeue(&neigh->queue))) {
++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
}
if (ipoib_cm_get(neigh))
ipoib_cm_destroy_tx(ipoib_cm_get(neigh));
+ ipoib_dbg(netdev_priv(dev),
+ "neigh free for %06x %pI6\n",
+ IPOIB_QPN(neigh->daddr),
+ neigh->daddr + 4);
kfree(neigh);
+ if (atomic_dec_and_test(&priv->ntbl.entries)) {
+ if (test_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags))
+ complete(&priv->ntbl.flushed);
+ }
}
-static int ipoib_neigh_setup_dev(struct net_device *dev, struct neigh_parms *parms)
+static void ipoib_neigh_reclaim(struct rcu_head *rp)
{
- parms->neigh_cleanup = ipoib_neigh_cleanup;
+ /* Called as a result of removal from hash table */
+ struct ipoib_neigh *neigh = container_of(rp, struct ipoib_neigh, rcu);
+ /* note TX context may hold another ref */
+ ipoib_neigh_put(neigh);
+}
+
+void ipoib_neigh_free(struct ipoib_neigh *neigh)
+{
+ struct net_device *dev = neigh->dev;
+ struct ipoib_dev_priv *priv = netdev_priv(dev);
+ struct ipoib_neigh_table *ntbl = &priv->ntbl;
+ struct ipoib_neigh_hash *htbl;
+ struct ipoib_neigh __rcu **np;
+ struct ipoib_neigh *n;
+ u32 hash_val;
+
+ htbl = rcu_dereference_protected(ntbl->htbl,
+ lockdep_is_held(&priv->lock));
+ if (!htbl)
+ return;
+
+ hash_val = ipoib_addr_hash(htbl, neigh->daddr);
+ np = &htbl->buckets[hash_val];
+ for (n = rcu_dereference_protected(*np,
+ lockdep_is_held(&priv->lock));
+ n != NULL;
+ n = rcu_dereference_protected(*np,
+ lockdep_is_held(&priv->lock))) {
+ if (n == neigh) {
+ /* found */
+ rcu_assign_pointer(*np,
+ rcu_dereference_protected(neigh->hnext,
+ lockdep_is_held(&priv->lock)));
+ /* remove from parent list */
+ list_del(&neigh->list);
+ call_rcu(&neigh->rcu, ipoib_neigh_reclaim);
+ return;
+ } else {
+ np = &n->hnext;
+ }
+ }
+}
+
+static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv)
+{
+ struct ipoib_neigh_table *ntbl = &priv->ntbl;
+ struct ipoib_neigh_hash *htbl;
+ struct ipoib_neigh **buckets;
+ u32 size;
+
+ clear_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags);
+ ntbl->htbl = NULL;
+ htbl = kzalloc(sizeof(*htbl), GFP_KERNEL);
+ if (!htbl)
+ return -ENOMEM;
+ set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
+ size = roundup_pow_of_two(arp_tbl.gc_thresh3);
+ buckets = kzalloc(size * sizeof(*buckets), GFP_KERNEL);
+ if (!buckets) {
+ kfree(htbl);
+ return -ENOMEM;
+ }
+ htbl->size = size;
+ htbl->mask = (size - 1);
+ htbl->buckets = buckets;
+ ntbl->htbl = htbl;
+ htbl->ntbl = ntbl;
+ atomic_set(&ntbl->entries, 0);
+
+ /* start garbage collection */
+ clear_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
+ queue_delayed_work(ipoib_workqueue, &priv->neigh_reap_task,
+ arp_tbl.gc_interval);
return 0;
}
+static void neigh_hash_free_rcu(struct rcu_head *head)
+{
+ struct ipoib_neigh_hash *htbl = container_of(head,
+ struct ipoib_neigh_hash,
+ rcu);
+ struct ipoib_neigh __rcu **buckets = htbl->buckets;
+ struct ipoib_neigh_table *ntbl = htbl->ntbl;
+
+ kfree(buckets);
+ kfree(htbl);
+ complete(&ntbl->deleted);
+}
+
+void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid)
+{
+ struct ipoib_dev_priv *priv = netdev_priv(dev);
+ struct ipoib_neigh_table *ntbl = &priv->ntbl;
+ struct ipoib_neigh_hash *htbl;
+ unsigned long flags;
+ int i;
+
+ /* remove all neigh connected to a given path or mcast */
+ spin_lock_irqsave(&priv->lock, flags);
+
+ htbl = rcu_dereference_protected(ntbl->htbl,
+ lockdep_is_held(&priv->lock));
+
+ if (!htbl)
+ goto out_unlock;
+
+ for (i = 0; i < htbl->size; i++) {
+ struct ipoib_neigh *neigh;
+ struct ipoib_neigh __rcu **np = &htbl->buckets[i];
+
+ while ((neigh = rcu_dereference_protected(*np,
+ lockdep_is_held(&priv->lock))) != NULL) {
+ /* delete neighs belong to this parent */
+ if (!memcmp(gid, neigh->daddr + 4, sizeof (union ib_gid))) {
+ rcu_assign_pointer(*np,
+ rcu_dereference_protected(neigh->hnext,
+ lockdep_is_held(&priv->lock)));
+ /* remove from parent list */
+ list_del(&neigh->list);
+ call_rcu(&neigh->rcu, ipoib_neigh_reclaim);
+ } else {
+ np = &neigh->hnext;
+ }
+
+ }
+ }
+out_unlock:
+ spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static void ipoib_flush_neighs(struct ipoib_dev_priv *priv)
+{
+ struct ipoib_neigh_table *ntbl = &priv->ntbl;
+ struct ipoib_neigh_hash *htbl;
+ unsigned long flags;
+ int i, wait_flushed = 0;
+
+ init_completion(&priv->ntbl.flushed);
+
+ spin_lock_irqsave(&priv->lock, flags);
+
+ htbl = rcu_dereference_protected(ntbl->htbl,
+ lockdep_is_held(&priv->lock));
+ if (!htbl)
+ goto out_unlock;
+
+ wait_flushed = atomic_read(&priv->ntbl.entries);
+ if (!wait_flushed)
+ goto free_htbl;
+
+ for (i = 0; i < htbl->size; i++) {
+ struct ipoib_neigh *neigh;
+ struct ipoib_neigh __rcu **np = &htbl->buckets[i];
+
+ while ((neigh = rcu_dereference_protected(*np,
+ lockdep_is_held(&priv->lock))) != NULL) {
+ rcu_assign_pointer(*np,
+ rcu_dereference_protected(neigh->hnext,
+ lockdep_is_held(&priv->lock)));
+ /* remove from path/mc list */
+ list_del(&neigh->list);
+ call_rcu(&neigh->rcu, ipoib_neigh_reclaim);
+ }
+ }
+
+free_htbl:
+ rcu_assign_pointer(ntbl->htbl, NULL);
+ call_rcu(&htbl->rcu, neigh_hash_free_rcu);
+
+out_unlock:
+ spin_unlock_irqrestore(&priv->lock, flags);
+ if (wait_flushed)
+ wait_for_completion(&priv->ntbl.flushed);
+}
+
+static void ipoib_neigh_hash_uninit(struct net_device *dev)
+{
+ struct ipoib_dev_priv *priv = netdev_priv(dev);
+ int stopped;
+
+ ipoib_dbg(priv, "ipoib_neigh_hash_uninit\n");
+ init_completion(&priv->ntbl.deleted);
+ set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags);
+
+ /* Stop GC if called at init fail need to cancel work */
+ stopped = test_and_set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
+ if (!stopped)
+ cancel_delayed_work(&priv->neigh_reap_task);
+
+ ipoib_flush_neighs(priv);
+
+ wait_for_completion(&priv->ntbl.deleted);
+}
+
+
int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
+ if (ipoib_neigh_hash_init(priv) < 0)
+ goto out;
/* Allocate RX/TX "rings" to hold queued skbs */
priv->rx_ring = kzalloc(ipoib_recvq_size * sizeof *priv->rx_ring,
GFP_KERNEL);
if (!priv->rx_ring) {
printk(KERN_WARNING "%s: failed to allocate RX ring (%d entries)\n",
ca->name, ipoib_recvq_size);
- goto out;
+ goto out_neigh_hash_cleanup;
}
- priv->tx_ring = vmalloc(ipoib_sendq_size * sizeof *priv->tx_ring);
+ priv->tx_ring = vzalloc(ipoib_sendq_size * sizeof *priv->tx_ring);
if (!priv->tx_ring) {
printk(KERN_WARNING "%s: failed to allocate TX ring (%d entries)\n",
ca->name, ipoib_sendq_size);
goto out_rx_ring_cleanup;
}
- memset(priv->tx_ring, 0, ipoib_sendq_size * sizeof *priv->tx_ring);
/* priv->tx_head, tx_tail & tx_outstanding are already 0 */
@@ -938,6 +1293,8 @@ out_tx_ring_cleanup:
out_rx_ring_cleanup:
kfree(priv->rx_ring);
+out_neigh_hash_cleanup:
+ ipoib_neigh_hash_uninit(dev);
out:
return -ENOMEM;
}
@@ -945,15 +1302,20 @@ out:
void ipoib_dev_cleanup(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev), *cpriv, *tcpriv;
+ LIST_HEAD(head);
+
+ ASSERT_RTNL();
ipoib_delete_debug_files(dev);
/* Delete any child interfaces first */
list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) {
- unregister_netdev(cpriv->dev);
- ipoib_dev_cleanup(cpriv->dev);
- free_netdev(cpriv->dev);
+ /* Stop GC on child */
+ set_bit(IPOIB_STOP_NEIGH_GC, &cpriv->flags);
+ cancel_delayed_work(&cpriv->neigh_reap_task);
+ unregister_netdevice_queue(cpriv->dev, &head);
}
+ unregister_netdevice_many(&head);
ipoib_ib_dev_cleanup(dev);
@@ -962,103 +1324,55 @@ void ipoib_dev_cleanup(struct net_device *dev)
priv->rx_ring = NULL;
priv->tx_ring = NULL;
+
+ ipoib_neigh_hash_uninit(dev);
}
static const struct header_ops ipoib_header_ops = {
.create = ipoib_hard_header,
};
-static int get_skb_hdr(struct sk_buff *skb, void **iphdr,
- void **tcph, u64 *hdr_flags, void *priv)
-{
- unsigned int ip_len;
- struct iphdr *iph;
-
- if (unlikely(skb->protocol != htons(ETH_P_IP)))
- return -1;
-
- /*
- * In the future we may add an else clause that verifies the
- * checksum and allows devices which do not calculate checksum
- * to use LRO.
- */
- if (unlikely(skb->ip_summed != CHECKSUM_UNNECESSARY))
- return -1;
-
- /* Check for non-TCP packet */
- skb_reset_network_header(skb);
- iph = ip_hdr(skb);
- if (iph->protocol != IPPROTO_TCP)
- return -1;
-
- ip_len = ip_hdrlen(skb);
- skb_set_transport_header(skb, ip_len);
- *tcph = tcp_hdr(skb);
-
- /* check if IP header and TCP header are complete */
- if (ntohs(iph->tot_len) < ip_len + tcp_hdrlen(skb))
- return -1;
-
- *hdr_flags = LRO_IPV4 | LRO_TCP;
- *iphdr = iph;
-
- return 0;
-}
-
-static void ipoib_lro_setup(struct ipoib_dev_priv *priv)
-{
- priv->lro.lro_mgr.max_aggr = lro_max_aggr;
- priv->lro.lro_mgr.max_desc = IPOIB_MAX_LRO_DESCRIPTORS;
- priv->lro.lro_mgr.lro_arr = priv->lro.lro_desc;
- priv->lro.lro_mgr.get_skb_header = get_skb_hdr;
- priv->lro.lro_mgr.features = LRO_F_NAPI;
- priv->lro.lro_mgr.dev = priv->dev;
- priv->lro.lro_mgr.ip_summed_aggr = CHECKSUM_UNNECESSARY;
-}
+static const struct net_device_ops ipoib_netdev_ops = {
+ .ndo_uninit = ipoib_uninit,
+ .ndo_open = ipoib_open,
+ .ndo_stop = ipoib_stop,
+ .ndo_change_mtu = ipoib_change_mtu,
+ .ndo_fix_features = ipoib_fix_features,
+ .ndo_start_xmit = ipoib_start_xmit,
+ .ndo_tx_timeout = ipoib_timeout,
+ .ndo_set_rx_mode = ipoib_set_mcast_list,
+};
-static void ipoib_setup(struct net_device *dev)
+void ipoib_setup(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
- dev->open = ipoib_open;
- dev->stop = ipoib_stop;
- dev->change_mtu = ipoib_change_mtu;
- dev->hard_start_xmit = ipoib_start_xmit;
- dev->tx_timeout = ipoib_timeout;
+ dev->netdev_ops = &ipoib_netdev_ops;
dev->header_ops = &ipoib_header_ops;
- dev->set_multicast_list = ipoib_set_mcast_list;
- dev->neigh_setup = ipoib_neigh_setup_dev;
ipoib_set_ethtool_ops(dev);
- netif_napi_add(dev, &priv->napi, ipoib_poll, 100);
+ netif_napi_add(dev, &priv->napi, ipoib_poll, NAPI_POLL_WEIGHT);
dev->watchdog_timeo = HZ;
dev->flags |= IFF_BROADCAST | IFF_MULTICAST;
- /*
- * We add in INFINIBAND_ALEN to allow for the destination
- * address "pseudoheader" for skbs without neighbour struct.
- */
- dev->hard_header_len = IPOIB_ENCAP_LEN + INFINIBAND_ALEN;
+ dev->hard_header_len = IPOIB_ENCAP_LEN;
dev->addr_len = INFINIBAND_ALEN;
dev->type = ARPHRD_INFINIBAND;
dev->tx_queue_len = ipoib_sendq_size * 2;
dev->features = (NETIF_F_VLAN_CHALLENGED |
NETIF_F_HIGHDMA);
+ dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN);
- netif_carrier_off(dev);
-
priv->dev = dev;
- ipoib_lro_setup(priv);
-
spin_lock_init(&priv->lock);
- mutex_init(&priv->vlan_mutex);
+ init_rwsem(&priv->vlan_rwsem);
INIT_LIST_HEAD(&priv->path_list);
INIT_LIST_HEAD(&priv->child_intfs);
@@ -1073,6 +1387,7 @@ static void ipoib_setup(struct net_device *dev)
INIT_WORK(&priv->flush_heavy, ipoib_ib_dev_flush_heavy);
INIT_WORK(&priv->restart_task, ipoib_mcast_restart_task);
INIT_DELAYED_WORK(&priv->ah_reap_task, ipoib_reap_ah);
+ INIT_DELAYED_WORK(&priv->neigh_reap_task, ipoib_reap_neigh);
}
struct ipoib_dev_priv *ipoib_intf_alloc(const char *name)
@@ -1104,12 +1419,9 @@ static ssize_t show_umcast(struct device *dev,
return sprintf(buf, "%d\n", test_bit(IPOIB_FLAG_UMCAST, &priv->flags));
}
-static ssize_t set_umcast(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+void ipoib_set_umcast(struct net_device *ndev, int umcast_val)
{
- struct ipoib_dev_priv *priv = netdev_priv(to_net_dev(dev));
- unsigned long umcast_val = simple_strtoul(buf, NULL, 0);
+ struct ipoib_dev_priv *priv = netdev_priv(ndev);
if (umcast_val > 0) {
set_bit(IPOIB_FLAG_UMCAST, &priv->flags);
@@ -1117,6 +1429,15 @@ static ssize_t set_umcast(struct device *dev,
"by userspace\n");
} else
clear_bit(IPOIB_FLAG_UMCAST, &priv->flags);
+}
+
+static ssize_t set_umcast(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ unsigned long umcast_val = simple_strtoul(buf, NULL, 0);
+
+ ipoib_set_umcast(to_net_dev(dev), umcast_val);
return count;
}
@@ -1137,7 +1458,7 @@ static ssize_t create_child(struct device *dev,
if (sscanf(buf, "%i", &pkey) != 1)
return -EINVAL;
- if (pkey < 0 || pkey > 0xffff)
+ if (pkey <= 0 || pkey > 0xffff || pkey == 0x8000)
return -EINVAL;
/*
@@ -1150,7 +1471,7 @@ static ssize_t create_child(struct device *dev,
return ret ? ret : count;
}
-static DEVICE_ATTR(create_child, S_IWUGO, NULL, create_child);
+static DEVICE_ATTR(create_child, S_IWUSR, NULL, create_child);
static ssize_t delete_child(struct device *dev,
struct device_attribute *attr,
@@ -1170,7 +1491,7 @@ static ssize_t delete_child(struct device *dev,
return ret ? ret : count;
}
-static DEVICE_ATTR(delete_child, S_IWUGO, NULL, delete_child);
+static DEVICE_ATTR(delete_child, S_IWUSR, NULL, delete_child);
int ipoib_add_pkey_attr(struct net_device *dev)
{
@@ -1201,20 +1522,18 @@ int ipoib_set_dev_features(struct ipoib_dev_priv *priv, struct ib_device *hca)
kfree(device_attr);
if (priv->hca_caps & IB_DEVICE_UD_IP_CSUM) {
- set_bit(IPOIB_FLAG_CSUM, &priv->flags);
- priv->dev->features |= NETIF_F_SG | NETIF_F_IP_CSUM;
- }
+ priv->dev->hw_features = NETIF_F_SG |
+ NETIF_F_IP_CSUM | NETIF_F_RXCSUM;
- if (lro)
- priv->dev->features |= NETIF_F_LRO;
+ if (priv->hca_caps & IB_DEVICE_UD_TSO)
+ priv->dev->hw_features |= NETIF_F_TSO;
- if (priv->dev->features & NETIF_F_SG && priv->hca_caps & IB_DEVICE_UD_TSO)
- priv->dev->features |= NETIF_F_TSO;
+ priv->dev->features |= priv->dev->hw_features;
+ }
return 0;
}
-
static struct net_device *ipoib_add_port(const char *format,
struct ib_device *hca, u8 port)
{
@@ -1227,6 +1546,7 @@ static struct net_device *ipoib_add_port(const char *format,
goto alloc_mem_failed;
SET_NETDEV_DEV(priv->dev, hca->dma_device);
+ priv->dev->dev_id = port - 1;
if (!ib_query_port(hca, port, &attr))
priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
@@ -1240,6 +1560,8 @@ static struct net_device *ipoib_add_port(const char *format,
priv->dev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu);
priv->mcast_mtu = priv->admin_mtu = priv->dev->mtu;
+ priv->dev->neigh_priv_len = sizeof(struct ipoib_neigh);
+
result = ib_query_pkey(hca, port, 0, &priv->pkey);
if (result) {
printk(KERN_WARNING "%s: ib_query_pkey port %d failed (ret = %d)\n",
@@ -1312,6 +1634,9 @@ sysfs_failed:
register_failed:
ib_unregister_event_handler(&priv->event_handler);
+ /* Stop GC if started before flush */
+ set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
+ cancel_delayed_work(&priv->neigh_reap_task);
flush_workqueue(ipoib_workqueue);
event_failed:
@@ -1349,6 +1674,8 @@ static void ipoib_add_one(struct ib_device *device)
}
for (p = s; p <= e; ++p) {
+ if (rdma_port_get_link_layer(device, p) != IB_LINK_LAYER_INFINIBAND)
+ continue;
dev = ipoib_add_port("ib%d", device, p);
if (!IS_ERR(dev)) {
priv = netdev_priv(dev);
@@ -1368,6 +1695,8 @@ static void ipoib_remove_one(struct ib_device *device)
return;
dev_list = ib_get_client_data(device, &ipoib_client);
+ if (!dev_list)
+ return;
list_for_each_entry_safe(priv, tmp, dev_list, list) {
ib_unregister_event_handler(&priv->event_handler);
@@ -1376,10 +1705,12 @@ static void ipoib_remove_one(struct ib_device *device)
dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP);
rtnl_unlock();
+ /* Stop GC */
+ set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
+ cancel_delayed_work(&priv->neigh_reap_task);
flush_workqueue(ipoib_workqueue);
unregister_netdev(priv->dev);
- ipoib_dev_cleanup(priv->dev);
free_netdev(priv->dev);
}
@@ -1396,8 +1727,7 @@ static int __init ipoib_init_module(void)
ipoib_sendq_size = roundup_pow_of_two(ipoib_sendq_size);
ipoib_sendq_size = min(ipoib_sendq_size, IPOIB_MAX_QUEUE_SIZE);
- ipoib_sendq_size = max(ipoib_sendq_size, max(2 * MAX_SEND_CQE,
- IPOIB_MIN_QUEUE_SIZE));
+ ipoib_sendq_size = max3(ipoib_sendq_size, 2 * MAX_SEND_CQE, IPOIB_MIN_QUEUE_SIZE);
#ifdef CONFIG_INFINIBAND_IPOIB_CM
ipoib_max_conn_qp = min(ipoib_max_conn_qp, IPOIB_CM_MAX_CONN_QP);
#endif
@@ -1432,8 +1762,15 @@ static int __init ipoib_init_module(void)
if (ret)
goto err_sa;
+ ret = ipoib_netlink_init();
+ if (ret)
+ goto err_client;
+
return 0;
+err_client:
+ ib_unregister_client(&ipoib_client);
+
err_sa:
ib_sa_unregister_client(&ipoib_sa_client);
destroy_workqueue(ipoib_workqueue);
@@ -1446,6 +1783,7 @@ err_fs:
static void __exit ipoib_cleanup_module(void)
{
+ ipoib_netlink_fini();
ib_unregister_client(&ipoib_client);
ib_sa_unregister_client(&ipoib_sa_client);
ipoib_unregister_debugfs();
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 425e31112ed..d4e005720d0 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -34,12 +34,14 @@
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
+#include <linux/moduleparam.h>
#include <linux/ip.h>
#include <linux/in.h>
#include <linux/igmp.h>
#include <linux/inetdevice.h>
#include <linux/delay.h>
#include <linux/completion.h>
+#include <linux/slab.h>
#include <net/dst.h>
@@ -67,28 +69,13 @@ struct ipoib_mcast_iter {
static void ipoib_mcast_free(struct ipoib_mcast *mcast)
{
struct net_device *dev = mcast->dev;
- struct ipoib_dev_priv *priv = netdev_priv(dev);
- struct ipoib_neigh *neigh, *tmp;
int tx_dropped = 0;
ipoib_dbg_mcast(netdev_priv(dev), "deleting multicast group %pI6\n",
mcast->mcmember.mgid.raw);
- spin_lock_irq(&priv->lock);
-
- list_for_each_entry_safe(neigh, tmp, &mcast->neigh_list, list) {
- /*
- * It's safe to call ipoib_put_ah() inside priv->lock
- * here, because we know that mcast->ah will always
- * hold one more reference, so ipoib_put_ah() will
- * never do more than decrement the ref count.
- */
- if (neigh->ah)
- ipoib_put_ah(neigh->ah);
- ipoib_neigh_free(dev, neigh);
- }
-
- spin_unlock_irq(&priv->lock);
+ /* remove all neigh connected to this mcast */
+ ipoib_del_neighs_by_gid(dev, mcast->mcmember.mgid.raw);
if (mcast->ah)
ipoib_put_ah(mcast->ah);
@@ -188,7 +175,9 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
mcast->mcmember = *mcmember;
- /* Set the cached Q_Key before we attach if it's the broadcast group */
+ /* Set the multicast MTU and cached Q_Key before we attach if it's
+ * the broadcast group.
+ */
if (!memcmp(mcast->mcmember.mgid.raw, priv->dev->broadcast + 4,
sizeof (union ib_gid))) {
spin_lock_irq(&priv->lock);
@@ -196,10 +185,17 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
spin_unlock_irq(&priv->lock);
return -EAGAIN;
}
+ priv->mcast_mtu = IPOIB_UD_MTU(ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu));
priv->qkey = be32_to_cpu(priv->broadcast->mcmember.qkey);
spin_unlock_irq(&priv->lock);
priv->tx_wr.wr.ud.remote_qkey = priv->qkey;
set_qkey = 1;
+
+ if (!ipoib_cm_admin_enabled(dev)) {
+ rtnl_lock();
+ dev_set_mtu(dev, min(priv->mcast_mtu, priv->admin_mtu));
+ rtnl_unlock();
+ }
}
if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
@@ -238,8 +234,11 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
av.grh.dgid = mcast->mcmember.mgid;
ah = ipoib_create_ah(dev, priv->pd, &av);
- if (!ah) {
- ipoib_warn(priv, "ib_address_create failed\n");
+ if (IS_ERR(ah)) {
+ ipoib_warn(priv, "ib_address_create failed %ld\n",
+ -PTR_ERR(ah));
+ /* use original error */
+ return PTR_ERR(ah);
} else {
spin_lock_irq(&priv->lock);
mcast->ah = ah;
@@ -257,17 +256,13 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
netif_tx_lock_bh(dev);
while (!skb_queue_empty(&mcast->pkt_queue)) {
struct sk_buff *skb = skb_dequeue(&mcast->pkt_queue);
+
netif_tx_unlock_bh(dev);
skb->dev = dev;
-
- if (!skb->dst || !skb->dst->neighbour) {
- /* put pseudoheader back on for next time */
- skb_push(skb, sizeof (struct ipoib_pseudoheader));
- }
-
if (dev_queue_xmit(skb))
ipoib_warn(priv, "dev_queue_xmit failed to requeue packet\n");
+
netif_tx_lock_bh(dev);
}
netif_tx_unlock_bh(dev);
@@ -362,12 +357,19 @@ void ipoib_mcast_carrier_on_task(struct work_struct *work)
{
struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv,
carrier_on_task);
+ struct ib_port_attr attr;
/*
* Take rtnl_lock to avoid racing with ipoib_stop() and
* turning the carrier back on while a device is being
* removed.
*/
+ if (ib_query_port(priv->ca, priv->port, &attr) ||
+ attr.state != IB_PORT_ACTIVE) {
+ ipoib_dbg(priv, "Keeping carrier off until IB port is active\n");
+ return;
+ }
+
rtnl_lock();
netif_carrier_on(priv->dev);
rtnl_unlock();
@@ -384,8 +386,10 @@ static int ipoib_mcast_join_complete(int status,
mcast->mcmember.mgid.raw, status);
/* We trap for port events ourselves. */
- if (status == -ENETRESET)
- return 0;
+ if (status == -ENETRESET) {
+ status = 0;
+ goto out;
+ }
if (!status)
status = ipoib_mcast_join_finish(mcast, &multicast->rec);
@@ -405,7 +409,8 @@ static int ipoib_mcast_join_complete(int status,
if (mcast == priv->broadcast)
queue_work(ipoib_workqueue, &priv->carrier_on_task);
- return 0;
+ status = 0;
+ goto out;
}
if (mcast->logcount++ < 20) {
@@ -432,7 +437,8 @@ static int ipoib_mcast_join_complete(int status,
mcast->backoff * HZ);
spin_unlock_irq(&priv->lock);
mutex_unlock(&mcast_mutex);
-
+out:
+ complete(&mcast->done);
return status;
}
@@ -482,11 +488,15 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast,
}
set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
+ init_completion(&mcast->done);
+ set_bit(IPOIB_MCAST_JOIN_STARTED, &mcast->flags);
+
mcast->mc = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port,
&rec, comp_mask, GFP_KERNEL,
ipoib_mcast_join_complete, mcast);
if (IS_ERR(mcast->mc)) {
clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
+ complete(&mcast->done);
ret = PTR_ERR(mcast->mc);
ipoib_warn(priv, "ib_sa_join_multicast failed, status %d\n", ret);
@@ -508,10 +518,18 @@ void ipoib_mcast_join_task(struct work_struct *work)
struct ipoib_dev_priv *priv =
container_of(work, struct ipoib_dev_priv, mcast_task.work);
struct net_device *dev = priv->dev;
+ struct ib_port_attr port_attr;
if (!test_bit(IPOIB_MCAST_RUN, &priv->flags))
return;
+ if (ib_query_port(priv->ca, priv->port, &port_attr) ||
+ port_attr.state != IB_PORT_ACTIVE) {
+ ipoib_dbg(priv, "port state is not ACTIVE (state = %d) suspending join task\n",
+ port_attr.state);
+ return;
+ }
+
if (ib_query_gid(priv->ca, priv->port, 0, &priv->local_gid))
ipoib_warn(priv, "ib_query_gid() failed\n");
else
@@ -581,14 +599,6 @@ void ipoib_mcast_join_task(struct work_struct *work)
return;
}
- priv->mcast_mtu = IPOIB_UD_MTU(ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu));
-
- if (!ipoib_cm_admin_enabled(dev)) {
- rtnl_lock();
- dev_set_mtu(dev, min(priv->mcast_mtu, priv->admin_mtu));
- rtnl_unlock();
- }
-
ipoib_dbg_mcast(priv, "successfully joined all multicast groups\n");
clear_bit(IPOIB_MCAST_RUN, &priv->flags);
@@ -647,11 +657,12 @@ static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
return 0;
}
-void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb)
+void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_mcast *mcast;
unsigned long flags;
+ void *mgid = daddr + 4;
spin_lock_irqsave(&priv->lock, flags);
@@ -707,20 +718,24 @@ void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb)
out:
if (mcast && mcast->ah) {
- if (skb->dst &&
- skb->dst->neighbour &&
- !*to_ipoib_neigh(skb->dst->neighbour)) {
- struct ipoib_neigh *neigh = ipoib_neigh_alloc(skb->dst->neighbour,
- skb->dev);
+ struct ipoib_neigh *neigh;
+ spin_unlock_irqrestore(&priv->lock, flags);
+ neigh = ipoib_neigh_get(dev, daddr);
+ spin_lock_irqsave(&priv->lock, flags);
+ if (!neigh) {
+ neigh = ipoib_neigh_alloc(daddr, dev);
if (neigh) {
kref_get(&mcast->ah->ref);
neigh->ah = mcast->ah;
list_add_tail(&neigh->list, &mcast->neigh_list);
}
}
-
+ spin_unlock_irqrestore(&priv->lock, flags);
ipoib_send(dev, skb, mcast->ah, IB_MULTICAST_QPN);
+ if (neigh)
+ ipoib_neigh_put(neigh);
+ return;
}
unlock:
@@ -752,18 +767,34 @@ void ipoib_mcast_dev_flush(struct net_device *dev)
spin_unlock_irqrestore(&priv->lock, flags);
+ /* seperate between the wait to the leave*/
+ list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
+ if (test_bit(IPOIB_MCAST_JOIN_STARTED, &mcast->flags))
+ wait_for_completion(&mcast->done);
+
list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
ipoib_mcast_leave(dev, mcast);
ipoib_mcast_free(mcast);
}
}
+static int ipoib_mcast_addr_is_valid(const u8 *addr, const u8 *broadcast)
+{
+ /* reserved QPN, prefix, scope */
+ if (memcmp(addr, broadcast, 6))
+ return 0;
+ /* signature lower, pkey */
+ if (memcmp(addr + 7, broadcast + 7, 3))
+ return 0;
+ return 1;
+}
+
void ipoib_mcast_restart_task(struct work_struct *work)
{
struct ipoib_dev_priv *priv =
container_of(work, struct ipoib_dev_priv, restart_task);
struct net_device *dev = priv->dev;
- struct dev_mc_list *mclist;
+ struct netdev_hw_addr *ha;
struct ipoib_mcast *mcast, *tmcast;
LIST_HEAD(remove_list);
unsigned long flags;
@@ -788,10 +819,13 @@ void ipoib_mcast_restart_task(struct work_struct *work)
clear_bit(IPOIB_MCAST_FLAG_FOUND, &mcast->flags);
/* Mark all of the entries that are found or don't exist */
- for (mclist = dev->mc_list; mclist; mclist = mclist->next) {
+ netdev_for_each_mc_addr(ha, dev) {
union ib_gid mgid;
- memcpy(mgid.raw, mclist->dmi_addr + 4, sizeof mgid);
+ if (!ipoib_mcast_addr_is_valid(ha->addr, dev->broadcast))
+ continue;
+
+ memcpy(mgid.raw, ha->addr + 4, sizeof mgid);
mcast = __ipoib_mcast_find(dev, &mgid);
if (!mcast || test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
new file mode 100644
index 00000000000..cdc7df4fdb8
--- /dev/null
+++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
@@ -0,0 +1,182 @@
+/*
+ * Copyright (c) 2012 Mellanox Technologies. - All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * 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.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/if_arp.h> /* For ARPHRD_xxx */
+#include <linux/module.h>
+#include <net/rtnetlink.h>
+#include "ipoib.h"
+
+static const struct nla_policy ipoib_policy[IFLA_IPOIB_MAX + 1] = {
+ [IFLA_IPOIB_PKEY] = { .type = NLA_U16 },
+ [IFLA_IPOIB_MODE] = { .type = NLA_U16 },
+ [IFLA_IPOIB_UMCAST] = { .type = NLA_U16 },
+};
+
+static int ipoib_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+ struct ipoib_dev_priv *priv = netdev_priv(dev);
+ u16 val;
+
+ if (nla_put_u16(skb, IFLA_IPOIB_PKEY, priv->pkey))
+ goto nla_put_failure;
+
+ val = test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
+ if (nla_put_u16(skb, IFLA_IPOIB_MODE, val))
+ goto nla_put_failure;
+
+ val = test_bit(IPOIB_FLAG_UMCAST, &priv->flags);
+ if (nla_put_u16(skb, IFLA_IPOIB_UMCAST, val))
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
+static int ipoib_changelink(struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[])
+{
+ u16 mode, umcast;
+ int ret = 0;
+
+ if (data[IFLA_IPOIB_MODE]) {
+ mode = nla_get_u16(data[IFLA_IPOIB_MODE]);
+ if (mode == IPOIB_MODE_DATAGRAM)
+ ret = ipoib_set_mode(dev, "datagram\n");
+ else if (mode == IPOIB_MODE_CONNECTED)
+ ret = ipoib_set_mode(dev, "connected\n");
+ else
+ ret = -EINVAL;
+
+ if (ret < 0)
+ goto out_err;
+ }
+
+ if (data[IFLA_IPOIB_UMCAST]) {
+ umcast = nla_get_u16(data[IFLA_IPOIB_UMCAST]);
+ ipoib_set_umcast(dev, umcast);
+ }
+
+out_err:
+ return ret;
+}
+
+static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[])
+{
+ struct net_device *pdev;
+ struct ipoib_dev_priv *ppriv;
+ u16 child_pkey;
+ int err;
+
+ if (!tb[IFLA_LINK])
+ return -EINVAL;
+
+ pdev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
+ if (!pdev || pdev->type != ARPHRD_INFINIBAND)
+ return -ENODEV;
+
+ ppriv = netdev_priv(pdev);
+
+ if (test_bit(IPOIB_FLAG_SUBINTERFACE, &ppriv->flags)) {
+ ipoib_warn(ppriv, "child creation disallowed for child devices\n");
+ return -EINVAL;
+ }
+
+ if (!data || !data[IFLA_IPOIB_PKEY]) {
+ ipoib_dbg(ppriv, "no pkey specified, using parent pkey\n");
+ child_pkey = ppriv->pkey;
+ } else
+ child_pkey = nla_get_u16(data[IFLA_IPOIB_PKEY]);
+
+ if (child_pkey == 0 || child_pkey == 0x8000)
+ return -EINVAL;
+
+ /*
+ * Set the full membership bit, so that we join the right
+ * broadcast group, etc.
+ */
+ child_pkey |= 0x8000;
+
+ err = __ipoib_vlan_add(ppriv, netdev_priv(dev), child_pkey, IPOIB_RTNL_CHILD);
+
+ if (!err && data)
+ err = ipoib_changelink(dev, tb, data);
+ return err;
+}
+
+static void ipoib_unregister_child_dev(struct net_device *dev, struct list_head *head)
+{
+ struct ipoib_dev_priv *priv, *ppriv;
+
+ priv = netdev_priv(dev);
+ ppriv = netdev_priv(priv->parent);
+
+ down_write(&ppriv->vlan_rwsem);
+ unregister_netdevice_queue(dev, head);
+ list_del(&priv->list);
+ up_write(&ppriv->vlan_rwsem);
+}
+
+static size_t ipoib_get_size(const struct net_device *dev)
+{
+ return nla_total_size(2) + /* IFLA_IPOIB_PKEY */
+ nla_total_size(2) + /* IFLA_IPOIB_MODE */
+ nla_total_size(2); /* IFLA_IPOIB_UMCAST */
+}
+
+static struct rtnl_link_ops ipoib_link_ops __read_mostly = {
+ .kind = "ipoib",
+ .maxtype = IFLA_IPOIB_MAX,
+ .policy = ipoib_policy,
+ .priv_size = sizeof(struct ipoib_dev_priv),
+ .setup = ipoib_setup,
+ .newlink = ipoib_new_child_link,
+ .changelink = ipoib_changelink,
+ .dellink = ipoib_unregister_child_dev,
+ .get_size = ipoib_get_size,
+ .fill_info = ipoib_fill_info,
+};
+
+int __init ipoib_netlink_init(void)
+{
+ return rtnl_link_register(&ipoib_link_ops);
+}
+
+void __exit ipoib_netlink_fini(void)
+{
+ rtnl_link_unregister(&ipoib_link_ops);
+}
+
+MODULE_ALIAS_RTNL_LINK("ipoib");
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index 68325119f74..c56d5d44c53 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -31,6 +31,8 @@
* SOFTWARE.
*/
+#include <linux/slab.h>
+
#include "ipoib.h"
int ipoib_mcast_attach(struct net_device *dev, u16 mlid, union ib_gid *mgid, int set_qkey)
@@ -190,6 +192,9 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
if (priv->hca_caps & IB_DEVICE_BLOCK_MULTICAST_LOOPBACK)
init_attr.create_flags |= IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK;
+ if (priv->hca_caps & IB_DEVICE_MANAGED_FLOW_STEERING)
+ init_attr.create_flags |= IB_QP_CREATE_NETIF_QP;
+
if (dev->features & NETIF_F_SG)
init_attr.cap.max_send_sge = MAX_SKB_FRAGS + 1;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index 5a76a551035..9fad7b5ac8b 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -33,7 +33,6 @@
#include <linux/module.h>
#include <linux/init.h>
-#include <linux/slab.h>
#include <linux/seq_file.h>
#include <asm/uaccess.h>
@@ -50,44 +49,11 @@ static ssize_t show_parent(struct device *d, struct device_attribute *attr,
}
static DEVICE_ATTR(parent, S_IRUGO, show_parent, NULL);
-int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
+int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
+ u16 pkey, int type)
{
- struct ipoib_dev_priv *ppriv, *priv;
- char intf_name[IFNAMSIZ];
int result;
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
-
- ppriv = netdev_priv(pdev);
-
- rtnl_lock();
- mutex_lock(&ppriv->vlan_mutex);
-
- /*
- * First ensure this isn't a duplicate. We check the parent device and
- * then all of the child interfaces to make sure the Pkey doesn't match.
- */
- if (ppriv->pkey == pkey) {
- result = -ENOTUNIQ;
- goto err;
- }
-
- list_for_each_entry(priv, &ppriv->child_intfs, list) {
- if (priv->pkey == pkey) {
- result = -ENOTUNIQ;
- goto err;
- }
- }
-
- snprintf(intf_name, sizeof intf_name, "%s.%04x",
- ppriv->dev->name, pkey);
- priv = ipoib_intf_alloc(intf_name);
- if (!priv) {
- result = -ENOMEM;
- goto err;
- }
-
priv->max_ib_mtu = ppriv->max_ib_mtu;
/* MTU will be reset when mcast join happens */
priv->dev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu);
@@ -96,7 +62,7 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
result = ipoib_set_dev_features(priv, ppriv->ca);
if (result)
- goto device_init_failed;
+ goto err;
priv->pkey = pkey;
@@ -109,7 +75,7 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
ipoib_warn(ppriv, "failed to initialize subinterface: "
"device %s, port %d",
ppriv->ca->name, ppriv->port);
- goto device_init_failed;
+ goto err;
}
result = register_netdevice(priv->dev);
@@ -122,64 +88,122 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
ipoib_create_debug_files(priv->dev);
- if (ipoib_cm_add_mode_attr(priv->dev))
- goto sysfs_failed;
- if (ipoib_add_pkey_attr(priv->dev))
- goto sysfs_failed;
- if (ipoib_add_umcast_attr(priv->dev))
- goto sysfs_failed;
-
- if (device_create_file(&priv->dev->dev, &dev_attr_parent))
- goto sysfs_failed;
+ /* RTNL childs don't need proprietary sysfs entries */
+ if (type == IPOIB_LEGACY_CHILD) {
+ if (ipoib_cm_add_mode_attr(priv->dev))
+ goto sysfs_failed;
+ if (ipoib_add_pkey_attr(priv->dev))
+ goto sysfs_failed;
+ if (ipoib_add_umcast_attr(priv->dev))
+ goto sysfs_failed;
+
+ if (device_create_file(&priv->dev->dev, &dev_attr_parent))
+ goto sysfs_failed;
+ }
+ priv->child_type = type;
+ priv->dev->iflink = ppriv->dev->ifindex;
list_add_tail(&priv->list, &ppriv->child_intfs);
- mutex_unlock(&ppriv->vlan_mutex);
- rtnl_unlock();
-
return 0;
sysfs_failed:
+ result = -ENOMEM;
ipoib_delete_debug_files(priv->dev);
unregister_netdevice(priv->dev);
register_failed:
ipoib_dev_cleanup(priv->dev);
-device_init_failed:
- free_netdev(priv->dev);
-
err:
- mutex_unlock(&ppriv->vlan_mutex);
+ return result;
+}
+
+int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
+{
+ struct ipoib_dev_priv *ppriv, *priv;
+ char intf_name[IFNAMSIZ];
+ struct ipoib_dev_priv *tpriv;
+ int result;
+
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ ppriv = netdev_priv(pdev);
+
+ snprintf(intf_name, sizeof intf_name, "%s.%04x",
+ ppriv->dev->name, pkey);
+ priv = ipoib_intf_alloc(intf_name);
+ if (!priv)
+ return -ENOMEM;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ down_write(&ppriv->vlan_rwsem);
+
+ /*
+ * First ensure this isn't a duplicate. We check the parent device and
+ * then all of the legacy child interfaces to make sure the Pkey
+ * doesn't match.
+ */
+ if (ppriv->pkey == pkey) {
+ result = -ENOTUNIQ;
+ goto out;
+ }
+
+ list_for_each_entry(tpriv, &ppriv->child_intfs, list) {
+ if (tpriv->pkey == pkey &&
+ tpriv->child_type == IPOIB_LEGACY_CHILD) {
+ result = -ENOTUNIQ;
+ goto out;
+ }
+ }
+
+ result = __ipoib_vlan_add(ppriv, priv, pkey, IPOIB_LEGACY_CHILD);
+
+out:
+ up_write(&ppriv->vlan_rwsem);
+
+ if (result)
+ free_netdev(priv->dev);
+
rtnl_unlock();
+
return result;
}
int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
{
struct ipoib_dev_priv *ppriv, *priv, *tpriv;
- int ret = -ENOENT;
+ struct net_device *dev = NULL;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
ppriv = netdev_priv(pdev);
- rtnl_lock();
- mutex_lock(&ppriv->vlan_mutex);
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ down_write(&ppriv->vlan_rwsem);
list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) {
- if (priv->pkey == pkey) {
+ if (priv->pkey == pkey &&
+ priv->child_type == IPOIB_LEGACY_CHILD) {
unregister_netdevice(priv->dev);
- ipoib_dev_cleanup(priv->dev);
list_del(&priv->list);
- free_netdev(priv->dev);
-
- ret = 0;
+ dev = priv->dev;
break;
}
}
- mutex_unlock(&ppriv->vlan_mutex);
+ up_write(&ppriv->vlan_rwsem);
+
rtnl_unlock();
- return ret;
+ if (dev) {
+ free_netdev(dev);
+ return 0;
+ }
+
+ return -ENODEV;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-12-11 03:24:03 +0000