summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/ulp
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband/ulp')
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib.h28
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_cm.c15
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_ib.c12
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_main.c57
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_multicast.c6
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_verbs.c4
-rw-r--r--drivers/infiniband/ulp/iser/iscsi_iser.h1
-rw-r--r--drivers/infiniband/ulp/iser/iser_memory.c6
-rw-r--r--drivers/infiniband/ulp/iser/iser_verbs.c22
-rw-r--r--drivers/infiniband/ulp/isert/ib_isert.c2
-rw-r--r--drivers/infiniband/ulp/srp/ib_srp.c56
-rw-r--r--drivers/infiniband/ulp/srp/ib_srp.h3
-rw-r--r--drivers/infiniband/ulp/srpt/ib_srpt.c2
13 files changed, 112 insertions, 102 deletions
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 9dbfcc0ab577..da12717a3eb7 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -63,6 +63,8 @@ enum ipoib_flush_level {
enum {
IPOIB_ENCAP_LEN = 4,
+ IPOIB_PSEUDO_LEN = 20,
+ IPOIB_HARD_LEN = IPOIB_ENCAP_LEN + IPOIB_PSEUDO_LEN,
IPOIB_UD_HEAD_SIZE = IB_GRH_BYTES + IPOIB_ENCAP_LEN,
IPOIB_UD_RX_SG = 2, /* max buffer needed for 4K mtu */
@@ -134,15 +136,21 @@ struct ipoib_header {
u16 reserved;
};
-struct ipoib_cb {
- struct qdisc_skb_cb qdisc_cb;
- u8 hwaddr[INFINIBAND_ALEN];
+struct ipoib_pseudo_header {
+ u8 hwaddr[INFINIBAND_ALEN];
};
-static inline struct ipoib_cb *ipoib_skb_cb(const struct sk_buff *skb)
+static inline void skb_add_pseudo_hdr(struct sk_buff *skb)
{
- BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct ipoib_cb));
- return (struct ipoib_cb *)skb->cb;
+ char *data = skb_push(skb, IPOIB_PSEUDO_LEN);
+
+ /*
+ * only the ipoib header is present now, make room for a dummy
+ * pseudo header and set skb field accordingly
+ */
+ memset(data, 0, IPOIB_PSEUDO_LEN);
+ skb_reset_mac_header(skb);
+ skb_pull(skb, IPOIB_HARD_LEN);
}
/* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */
@@ -772,7 +780,13 @@ static inline void ipoib_unregister_debugfs(void) { }
#define ipoib_printk(level, priv, format, arg...) \
printk(level "%s: " format, ((struct ipoib_dev_priv *) priv)->dev->name , ## arg)
#define ipoib_warn(priv, format, arg...) \
- ipoib_printk(KERN_WARNING, priv, format , ## arg)
+do { \
+ static DEFINE_RATELIMIT_STATE(_rs, \
+ 10 * HZ /*10 seconds */, \
+ 100); \
+ if (__ratelimit(&_rs)) \
+ ipoib_printk(KERN_WARNING, priv, format , ## arg);\
+} while (0)
extern int ipoib_sendq_size;
extern int ipoib_recvq_size;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 4ad297d3de89..339a1eecdfe3 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -63,6 +63,8 @@ MODULE_PARM_DESC(cm_data_debug_level,
#define IPOIB_CM_RX_DELAY (3 * 256 * HZ)
#define IPOIB_CM_RX_UPDATE_MASK (0x3)
+#define IPOIB_CM_RX_RESERVE (ALIGN(IPOIB_HARD_LEN, 16) - IPOIB_ENCAP_LEN)
+
static struct ib_qp_attr ipoib_cm_err_attr = {
.qp_state = IB_QPS_ERR
};
@@ -146,15 +148,15 @@ static struct sk_buff *ipoib_cm_alloc_rx_skb(struct net_device *dev,
struct sk_buff *skb;
int i;
- skb = dev_alloc_skb(IPOIB_CM_HEAD_SIZE + 12);
+ skb = dev_alloc_skb(ALIGN(IPOIB_CM_HEAD_SIZE + IPOIB_PSEUDO_LEN, 16));
if (unlikely(!skb))
return NULL;
/*
- * IPoIB adds a 4 byte header. So we need 12 more bytes to align the
+ * IPoIB adds a IPOIB_ENCAP_LEN byte header, this will align the
* IP header to a multiple of 16.
*/
- skb_reserve(skb, 12);
+ skb_reserve(skb, IPOIB_CM_RX_RESERVE);
mapping[0] = ib_dma_map_single(priv->ca, skb->data, IPOIB_CM_HEAD_SIZE,
DMA_FROM_DEVICE);
@@ -624,9 +626,9 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
if (wc->byte_len < IPOIB_CM_COPYBREAK) {
int dlen = wc->byte_len;
- small_skb = dev_alloc_skb(dlen + 12);
+ small_skb = dev_alloc_skb(dlen + IPOIB_CM_RX_RESERVE);
if (small_skb) {
- skb_reserve(small_skb, 12);
+ skb_reserve(small_skb, IPOIB_CM_RX_RESERVE);
ib_dma_sync_single_for_cpu(priv->ca, rx_ring[wr_id].mapping[0],
dlen, DMA_FROM_DEVICE);
skb_copy_from_linear_data(skb, small_skb->data, dlen);
@@ -663,8 +665,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
copied:
skb->protocol = ((struct ipoib_header *) skb->data)->proto;
- skb_reset_mac_header(skb);
- skb_pull(skb, IPOIB_ENCAP_LEN);
+ skb_add_pseudo_hdr(skb);
++dev->stats.rx_packets;
dev->stats.rx_bytes += skb->len;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index be11d5d5b8c1..830fecb6934c 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -128,16 +128,15 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id)
buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);
- skb = dev_alloc_skb(buf_size + IPOIB_ENCAP_LEN);
+ skb = dev_alloc_skb(buf_size + IPOIB_HARD_LEN);
if (unlikely(!skb))
return NULL;
/*
- * IB will leave a 40 byte gap for a GRH and IPoIB adds a 4 byte
- * header. So we need 4 more bytes to get to 48 and align the
- * IP header to a multiple of 16.
+ * the IP header will be at IPOIP_HARD_LEN + IB_GRH_BYTES, that is
+ * 64 bytes aligned
*/
- skb_reserve(skb, 4);
+ skb_reserve(skb, sizeof(struct ipoib_pseudo_header));
mapping = priv->rx_ring[id].mapping;
mapping[0] = ib_dma_map_single(priv->ca, skb->data, buf_size,
@@ -253,8 +252,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
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);
+ skb_add_pseudo_hdr(skb);
++dev->stats.rx_packets;
dev->stats.rx_bytes += skb->len;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index cc1c1b062ea5..b58d9dca5c93 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -925,9 +925,12 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
ipoib_neigh_free(neigh);
goto err_drop;
}
- if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)
+ if (skb_queue_len(&neigh->queue) <
+ IPOIB_MAX_PATH_REC_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, IPOIB_PSEUDO_LEN);
__skb_queue_tail(&neigh->queue, skb);
- else {
+ } else {
ipoib_warn(priv, "queue length limit %d. Packet drop.\n",
skb_queue_len(&neigh->queue));
goto err_drop;
@@ -964,7 +967,7 @@ err_drop:
}
static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
- struct ipoib_cb *cb)
+ struct ipoib_pseudo_header *phdr)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_path *path;
@@ -972,16 +975,18 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
spin_lock_irqsave(&priv->lock, flags);
- path = __path_find(dev, cb->hwaddr + 4);
+ path = __path_find(dev, phdr->hwaddr + 4);
if (!path || !path->valid) {
int new_path = 0;
if (!path) {
- path = path_rec_create(dev, cb->hwaddr + 4);
+ path = path_rec_create(dev, phdr->hwaddr + 4);
new_path = 1;
}
if (path) {
if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, IPOIB_PSEUDO_LEN);
__skb_queue_tail(&path->queue, skb);
} else {
++dev->stats.tx_dropped;
@@ -1009,10 +1014,12 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
be16_to_cpu(path->pathrec.dlid));
spin_unlock_irqrestore(&priv->lock, flags);
- ipoib_send(dev, skb, path->ah, IPOIB_QPN(cb->hwaddr));
+ ipoib_send(dev, skb, path->ah, IPOIB_QPN(phdr->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, IPOIB_PSEUDO_LEN);
__skb_queue_tail(&path->queue, skb);
} else {
++dev->stats.tx_dropped;
@@ -1026,13 +1033,15 @@ 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 = ipoib_skb_cb(skb);
+ struct ipoib_pseudo_header *phdr;
struct ipoib_header *header;
unsigned long flags;
+ phdr = (struct ipoib_pseudo_header *) skb->data;
+ skb_pull(skb, sizeof(*phdr));
header = (struct ipoib_header *) skb->data;
- if (unlikely(cb->hwaddr[4] == 0xff)) {
+ if (unlikely(phdr->hwaddr[4] == 0xff)) {
/* multicast, arrange "if" according to probability */
if ((header->proto != htons(ETH_P_IP)) &&
(header->proto != htons(ETH_P_IPV6)) &&
@@ -1045,13 +1054,13 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
}
/* Add in the P_Key for multicast*/
- cb->hwaddr[8] = (priv->pkey >> 8) & 0xff;
- cb->hwaddr[9] = priv->pkey & 0xff;
+ phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff;
+ phdr->hwaddr[9] = priv->pkey & 0xff;
- neigh = ipoib_neigh_get(dev, cb->hwaddr);
+ neigh = ipoib_neigh_get(dev, phdr->hwaddr);
if (likely(neigh))
goto send_using_neigh;
- ipoib_mcast_send(dev, cb->hwaddr, skb);
+ ipoib_mcast_send(dev, phdr->hwaddr, skb);
return NETDEV_TX_OK;
}
@@ -1060,16 +1069,16 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
case htons(ETH_P_IP):
case htons(ETH_P_IPV6):
case htons(ETH_P_TIPC):
- neigh = ipoib_neigh_get(dev, cb->hwaddr);
+ neigh = ipoib_neigh_get(dev, phdr->hwaddr);
if (unlikely(!neigh)) {
- neigh_add_path(skb, cb->hwaddr, dev);
+ neigh_add_path(skb, phdr->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);
+ unicast_arp_send(skb, dev, phdr);
return NETDEV_TX_OK;
default:
/* ethertype not supported by IPoIB */
@@ -1086,11 +1095,13 @@ send_using_neigh:
goto unref;
}
} else if (neigh->ah) {
- ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(cb->hwaddr));
+ ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(phdr->hwaddr));
goto unref;
}
if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, sizeof(*phdr));
spin_lock_irqsave(&priv->lock, flags);
__skb_queue_tail(&neigh->queue, skb);
spin_unlock_irqrestore(&priv->lock, flags);
@@ -1122,8 +1133,8 @@ static int ipoib_hard_header(struct sk_buff *skb,
unsigned short type,
const void *daddr, const void *saddr, unsigned len)
{
+ struct ipoib_pseudo_header *phdr;
struct ipoib_header *header;
- struct ipoib_cb *cb = ipoib_skb_cb(skb);
header = (struct ipoib_header *) skb_push(skb, sizeof *header);
@@ -1132,12 +1143,13 @@ static int ipoib_hard_header(struct sk_buff *skb,
/*
* we don't rely on dst_entry structure, always stuff the
- * destination address into skb->cb so we can figure out where
+ * destination address into skb hard header so we can figure out where
* to send the packet later.
*/
- memcpy(cb->hwaddr, daddr, INFINIBAND_ALEN);
+ phdr = (struct ipoib_pseudo_header *) skb_push(skb, sizeof(*phdr));
+ memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN);
- return sizeof *header;
+ return IPOIB_HARD_LEN;
}
static void ipoib_set_mcast_list(struct net_device *dev)
@@ -1759,7 +1771,7 @@ void ipoib_setup(struct net_device *dev)
dev->flags |= IFF_BROADCAST | IFF_MULTICAST;
- dev->hard_header_len = IPOIB_ENCAP_LEN;
+ dev->hard_header_len = IPOIB_HARD_LEN;
dev->addr_len = INFINIBAND_ALEN;
dev->type = ARPHRD_INFINIBAND;
dev->tx_queue_len = ipoib_sendq_size * 2;
@@ -2196,7 +2208,8 @@ static int __init ipoib_init_module(void)
* its private workqueue, and we only queue up flush events
* on our global flush workqueue. This avoids the deadlocks.
*/
- ipoib_workqueue = create_singlethread_workqueue("ipoib_flush");
+ ipoib_workqueue = alloc_ordered_workqueue("ipoib_flush",
+ WQ_MEM_RECLAIM);
if (!ipoib_workqueue) {
ret = -ENOMEM;
goto err_fs;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index d3394b6add24..1909dd252c94 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -796,9 +796,11 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb)
__ipoib_mcast_add(dev, mcast);
list_add_tail(&mcast->list, &priv->multicast_list);
}
- if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE)
+ if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, sizeof(struct ipoib_pseudo_header));
skb_queue_tail(&mcast->pkt_queue, skb);
- else {
+ } else {
++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
}
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index c55ecb2c3736..189dcd1709d2 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -147,7 +147,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
int ret, size;
int i;
- priv->pd = ib_alloc_pd(priv->ca);
+ priv->pd = ib_alloc_pd(priv->ca, 0);
if (IS_ERR(priv->pd)) {
printk(KERN_WARNING "%s: failed to allocate PD\n", ca->name);
return -ENODEV;
@@ -157,7 +157,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
* the various IPoIB tasks assume they will never race against
* themselves, so always use a single thread workqueue
*/
- priv->wq = create_singlethread_workqueue("ipoib_wq");
+ priv->wq = alloc_ordered_workqueue("ipoib_wq", WQ_MEM_RECLAIM);
if (!priv->wq) {
printk(KERN_WARNING "ipoib: failed to allocate device WQ\n");
goto out_free_pd;
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 0351059783b1..0be6a7c5ddb5 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -374,7 +374,6 @@ struct iser_reg_ops {
struct iser_device {
struct ib_device *ib_device;
struct ib_pd *pd;
- struct ib_mr *mr;
struct ib_event_handler event_handler;
struct list_head ig_list;
int refcount;
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index 90be56893414..9c3e9ab53a41 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -199,7 +199,11 @@ iser_reg_dma(struct iser_device *device, struct iser_data_buf *mem,
* FIXME: rework the registration code path to differentiate
* rkey/lkey use cases
*/
- reg->rkey = device->mr ? device->mr->rkey : 0;
+
+ if (device->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY)
+ reg->rkey = device->pd->unsafe_global_rkey;
+ else
+ reg->rkey = 0;
reg->sge.addr = ib_sg_dma_address(device->ib_device, &sg[0]);
reg->sge.length = ib_sg_dma_len(device->ib_device, &sg[0]);
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 1b4945367e4f..a4b791dfaa1d 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -88,7 +88,8 @@ static int iser_create_device_ib_res(struct iser_device *device)
device->comps_used, ib_dev->name,
ib_dev->num_comp_vectors, max_cqe);
- device->pd = ib_alloc_pd(ib_dev);
+ device->pd = ib_alloc_pd(ib_dev,
+ iser_always_reg ? 0 : IB_PD_UNSAFE_GLOBAL_RKEY);
if (IS_ERR(device->pd))
goto pd_err;
@@ -103,26 +104,13 @@ static int iser_create_device_ib_res(struct iser_device *device)
}
}
- if (!iser_always_reg) {
- int access = IB_ACCESS_LOCAL_WRITE |
- IB_ACCESS_REMOTE_WRITE |
- IB_ACCESS_REMOTE_READ;
-
- device->mr = ib_get_dma_mr(device->pd, access);
- if (IS_ERR(device->mr))
- goto cq_err;
- }
-
INIT_IB_EVENT_HANDLER(&device->event_handler, ib_dev,
iser_event_handler);
if (ib_register_event_handler(&device->event_handler))
- goto handler_err;
+ goto cq_err;
return 0;
-handler_err:
- if (device->mr)
- ib_dereg_mr(device->mr);
cq_err:
for (i = 0; i < device->comps_used; i++) {
struct iser_comp *comp = &device->comps[i];
@@ -154,14 +142,10 @@ static void iser_free_device_ib_res(struct iser_device *device)
}
(void)ib_unregister_event_handler(&device->event_handler);
- if (device->mr)
- (void)ib_dereg_mr(device->mr);
ib_dealloc_pd(device->pd);
kfree(device->comps);
device->comps = NULL;
-
- device->mr = NULL;
device->pd = NULL;
}
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index cae9bbcc27e7..6dd43f63238e 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -309,7 +309,7 @@ isert_create_device_ib_res(struct isert_device *device)
if (ret)
goto out;
- device->pd = ib_alloc_pd(ib_dev);
+ device->pd = ib_alloc_pd(ib_dev, 0);
if (IS_ERR(device->pd)) {
ret = PTR_ERR(device->pd);
isert_err("failed to allocate pd, device %p, ret=%d\n",
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 3322ed750172..d980fb458ad4 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -1262,6 +1262,7 @@ static int srp_map_finish_fmr(struct srp_map_state *state,
{
struct srp_target_port *target = ch->target;
struct srp_device *dev = target->srp_host->srp_dev;
+ struct ib_pd *pd = target->pd;
struct ib_pool_fmr *fmr;
u64 io_addr = 0;
@@ -1273,9 +1274,9 @@ static int srp_map_finish_fmr(struct srp_map_state *state,
if (state->npages == 0)
return 0;
- if (state->npages == 1 && target->global_mr) {
+ if (state->npages == 1 && (pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY)) {
srp_map_desc(state, state->base_dma_addr, state->dma_len,
- target->global_mr->rkey);
+ pd->unsafe_global_rkey);
goto reset_state;
}
@@ -1315,6 +1316,7 @@ static int srp_map_finish_fr(struct srp_map_state *state,
{
struct srp_target_port *target = ch->target;
struct srp_device *dev = target->srp_host->srp_dev;
+ struct ib_pd *pd = target->pd;
struct ib_send_wr *bad_wr;
struct ib_reg_wr wr;
struct srp_fr_desc *desc;
@@ -1326,12 +1328,12 @@ static int srp_map_finish_fr(struct srp_map_state *state,
WARN_ON_ONCE(!dev->use_fast_reg);
- if (sg_nents == 1 && target->global_mr) {
+ if (sg_nents == 1 && (pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY)) {
unsigned int sg_offset = sg_offset_p ? *sg_offset_p : 0;
srp_map_desc(state, sg_dma_address(state->sg) + sg_offset,
sg_dma_len(state->sg) - sg_offset,
- target->global_mr->rkey);
+ pd->unsafe_global_rkey);
if (sg_offset_p)
*sg_offset_p = 0;
return 1;
@@ -1386,7 +1388,7 @@ static int srp_map_finish_fr(struct srp_map_state *state,
static int srp_map_sg_entry(struct srp_map_state *state,
struct srp_rdma_ch *ch,
- struct scatterlist *sg, int sg_index)
+ struct scatterlist *sg)
{
struct srp_target_port *target = ch->target;
struct srp_device *dev = target->srp_host->srp_dev;
@@ -1400,7 +1402,9 @@ static int srp_map_sg_entry(struct srp_map_state *state,
while (dma_len) {
unsigned offset = dma_addr & ~dev->mr_page_mask;
- if (state->npages == dev->max_pages_per_mr || offset != 0) {
+
+ if (state->npages == dev->max_pages_per_mr ||
+ (state->npages > 0 && offset != 0)) {
ret = srp_map_finish_fmr(state, ch);
if (ret)
return ret;
@@ -1417,12 +1421,12 @@ static int srp_map_sg_entry(struct srp_map_state *state,
}
/*
- * If the last entry of the MR wasn't a full page, then we need to
+ * If the end of the MR is not on a page boundary then we need to
* close it out and start a new one -- we can only merge at page
* boundaries.
*/
ret = 0;
- if (len != dev->mr_page_size)
+ if ((dma_addr & ~dev->mr_page_mask) != 0)
ret = srp_map_finish_fmr(state, ch);
return ret;
}
@@ -1439,7 +1443,7 @@ static int srp_map_sg_fmr(struct srp_map_state *state, struct srp_rdma_ch *ch,
state->fmr.end = req->fmr_list + ch->target->mr_per_cmd;
for_each_sg(scat, sg, count, i) {
- ret = srp_map_sg_entry(state, ch, sg, i);
+ ret = srp_map_sg_entry(state, ch, sg);
if (ret)
return ret;
}
@@ -1491,7 +1495,7 @@ static int srp_map_sg_dma(struct srp_map_state *state, struct srp_rdma_ch *ch,
for_each_sg(scat, sg, count, i) {
srp_map_desc(state, ib_sg_dma_address(dev->dev, sg),
ib_sg_dma_len(dev->dev, sg),
- target->global_mr->rkey);
+ target->pd->unsafe_global_rkey);
}
return 0;
@@ -1591,6 +1595,7 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch,
struct srp_request *req)
{
struct srp_target_port *target = ch->target;
+ struct ib_pd *pd = target->pd;
struct scatterlist *scat;
struct srp_cmd *cmd = req->cmd->buf;
int len, nents, count, ret;
@@ -1626,7 +1631,7 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch,
fmt = SRP_DATA_DESC_DIRECT;
len = sizeof (struct srp_cmd) + sizeof (struct srp_direct_buf);
- if (count == 1 && target->global_mr) {
+ if (count == 1 && (pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY)) {
/*
* The midlayer only generated a single gather/scatter
* entry, or DMA mapping coalesced everything to a
@@ -1636,7 +1641,7 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch,
struct srp_direct_buf *buf = (void *) cmd->add_data;
buf->va = cpu_to_be64(ib_sg_dma_address(ibdev, scat));
- buf->key = cpu_to_be32(target->global_mr->rkey);
+ buf->key = cpu_to_be32(pd->unsafe_global_rkey);
buf->len = cpu_to_be32(ib_sg_dma_len(ibdev, scat));
req->nmdesc = 0;
@@ -1709,14 +1714,14 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch,
memcpy(indirect_hdr->desc_list, req->indirect_desc,
count * sizeof (struct srp_direct_buf));
- if (!target->global_mr) {
+ if (!(pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY)) {
ret = srp_map_idb(ch, req, state.gen.next, state.gen.end,
idb_len, &idb_rkey);
if (ret < 0)
goto unmap;
req->nmdesc++;
} else {
- idb_rkey = cpu_to_be32(target->global_mr->rkey);
+ idb_rkey = cpu_to_be32(pd->unsafe_global_rkey);
}
indirect_hdr->table_desc.va = cpu_to_be64(req->indirect_dma_addr);
@@ -3268,8 +3273,8 @@ static ssize_t srp_create_target(struct device *dev,
target->io_class = SRP_REV16A_IB_IO_CLASS;
target->scsi_host = target_host;
target->srp_host = host;
+ target->pd = host->srp_dev->pd;
target->lkey = host->srp_dev->pd->local_dma_lkey;
- target->global_mr = host->srp_dev->global_mr;
target->cmd_sg_cnt = cmd_sg_entries;
target->sg_tablesize = indirect_sg_entries ? : cmd_sg_entries;
target->allow_ext_sg = allow_ext_sg;
@@ -3524,6 +3529,7 @@ static void srp_add_one(struct ib_device *device)
struct srp_host *host;
int mr_page_shift, p;
u64 max_pages_per_mr;
+ unsigned int flags = 0;
srp_dev = kzalloc(sizeof(*srp_dev), GFP_KERNEL);
if (!srp_dev)
@@ -3558,6 +3564,10 @@ static void srp_add_one(struct ib_device *device)
srp_dev->use_fmr = !srp_dev->use_fast_reg && srp_dev->has_fmr;
}
+ if (never_register || !register_always ||
+ (!srp_dev->has_fmr && !srp_dev->has_fr))
+ flags |= IB_PD_UNSAFE_GLOBAL_RKEY;
+
if (srp_dev->use_fast_reg) {
srp_dev->max_pages_per_mr =
min_t(u32, srp_dev->max_pages_per_mr,
@@ -3573,19 +3583,10 @@ static void srp_add_one(struct ib_device *device)
INIT_LIST_HEAD(&srp_dev->dev_list);
srp_dev->dev = device;
- srp_dev->pd = ib_alloc_pd(device);
+ srp_dev->pd = ib_alloc_pd(device, flags);
if (IS_ERR(srp_dev->pd))
goto free_dev;
- if (never_register || !register_always ||
- (!srp_dev->has_fmr && !srp_dev->has_fr)) {
- srp_dev->global_mr = ib_get_dma_mr(srp_dev->pd,
- IB_ACCESS_LOCAL_WRITE |
- IB_ACCESS_REMOTE_READ |
- IB_ACCESS_REMOTE_WRITE);
- if (IS_ERR(srp_dev->global_mr))
- goto err_pd;
- }
for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) {
host = srp_add_port(srp_dev, p);
@@ -3596,9 +3597,6 @@ static void srp_add_one(struct ib_device *device)
ib_set_client_data(device, &srp_client, srp_dev);
return;
-err_pd:
- ib_dealloc_pd(srp_dev->pd);
-
free_dev:
kfree(srp_dev);
}
@@ -3638,8 +3636,6 @@ static void srp_remove_one(struct ib_device *device, void *client_data)
kfree(host);
}
- if (srp_dev->global_mr)
- ib_dereg_mr(srp_dev->global_mr);
ib_dealloc_pd(srp_dev->pd);
kfree(srp_dev);
diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h
index 26bb9b0a7a63..21c69695f9d4 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.h
+++ b/drivers/infiniband/ulp/srp/ib_srp.h
@@ -90,7 +90,6 @@ struct srp_device {
struct list_head dev_list;
struct ib_device *dev;
struct ib_pd *pd;
- struct ib_mr *global_mr;
u64 mr_page_mask;
int mr_page_size;
int mr_max_size;
@@ -179,7 +178,7 @@ struct srp_target_port {
spinlock_t lock;
/* read only in the hot path */
- struct ib_mr *global_mr;
+ struct ib_pd *pd;
struct srp_rdma_ch *ch;
u32 ch_count;
u32 lkey;
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 883bbfe08e0e..0b1f69ed2e92 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -2480,7 +2480,7 @@ static void srpt_add_one(struct ib_device *device)
init_waitqueue_head(&sdev->ch_releaseQ);
mutex_init(&sdev->mutex);
- sdev->pd = ib_alloc_pd(device);
+ sdev->pd = ib_alloc_pd(device, 0);
if (IS_ERR(sdev->pd))
goto free_dev;
OpenPOWER on IntegriCloud