aboutsummaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/cxgb4/cm.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband/hw/cxgb4/cm.c')
-rw-r--r--drivers/infiniband/hw/cxgb4/cm.c645
1 files changed, 452 insertions, 193 deletions
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 12fef76c791..768a0fb67dd 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2009-2010 Chelsio, Inc. All rights reserved.
+ * Copyright (c) 2009-2014 Chelsio, Inc. 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
@@ -47,6 +47,8 @@
#include <net/ip6_route.h>
#include <net/addrconf.h>
+#include <rdma/ib_addr.h>
+
#include "iw_cxgb4.h"
static char *states[] = {
@@ -98,9 +100,9 @@ int c4iw_debug;
module_param(c4iw_debug, int, 0644);
MODULE_PARM_DESC(c4iw_debug, "Enable debug logging (default=0)");
-static int peer2peer;
+static int peer2peer = 1;
module_param(peer2peer, int, 0644);
-MODULE_PARM_DESC(peer2peer, "Support peer2peer ULPs (default=0)");
+MODULE_PARM_DESC(peer2peer, "Support peer2peer ULPs (default=1)");
static int p2p_type = FW_RI_INIT_P2PTYPE_READ_REQ;
module_param(p2p_type, int, 0644);
@@ -173,12 +175,15 @@ static void start_ep_timer(struct c4iw_ep *ep)
add_timer(&ep->timer);
}
-static void stop_ep_timer(struct c4iw_ep *ep)
+static int stop_ep_timer(struct c4iw_ep *ep)
{
PDBG("%s ep %p stopping\n", __func__, ep);
del_timer_sync(&ep->timer);
- if (!test_and_set_bit(TIMEOUT, &ep->com.flags))
+ if (!test_and_set_bit(TIMEOUT, &ep->com.flags)) {
c4iw_put_ep(&ep->com);
+ return 0;
+ }
+ return 1;
}
static int c4iw_l2t_send(struct c4iw_rdev *rdev, struct sk_buff *skb,
@@ -229,12 +234,16 @@ static void release_tid(struct c4iw_rdev *rdev, u32 hwtid, struct sk_buff *skb)
static void set_emss(struct c4iw_ep *ep, u16 opt)
{
- ep->emss = ep->com.dev->rdev.lldi.mtus[GET_TCPOPT_MSS(opt)] - 40;
+ ep->emss = ep->com.dev->rdev.lldi.mtus[GET_TCPOPT_MSS(opt)] -
+ sizeof(struct iphdr) - sizeof(struct tcphdr);
ep->mss = ep->emss;
if (GET_TCPOPT_TSTAMP(opt))
ep->emss -= 12;
if (ep->emss < 128)
ep->emss = 128;
+ if (ep->emss & 7)
+ PDBG("Warning: misaligned mtu idx %u mss %u emss=%u\n",
+ GET_TCPOPT_MSS(opt), ep->mss, ep->emss);
PDBG("%s mss_idx %u mss %u emss=%u\n", __func__, GET_TCPOPT_MSS(opt),
ep->mss, ep->emss);
}
@@ -291,6 +300,12 @@ void _c4iw_free_ep(struct kref *kref)
dst_release(ep->dst);
cxgb4_l2t_release(ep->l2t);
}
+ if (test_bit(RELEASE_MAPINFO, &ep->com.flags)) {
+ print_addr(&ep->com, __func__, "remove_mapinfo/mapping");
+ iwpm_remove_mapinfo(&ep->com.local_addr,
+ &ep->com.mapped_local_addr);
+ iwpm_remove_mapping(&ep->com.local_addr, RDMA_NL_C4IW);
+ }
kfree(ep);
}
@@ -338,10 +353,7 @@ static struct sk_buff *get_skb(struct sk_buff *skb, int len, gfp_t gfp)
static struct net_device *get_real_dev(struct net_device *egress_dev)
{
- struct net_device *phys_dev = egress_dev;
- if (egress_dev->priv_flags & IFF_802_1Q_VLAN)
- phys_dev = vlan_dev_real_dev(egress_dev);
- return phys_dev;
+ return rdma_vlan_dev_real_dev(egress_dev) ? : egress_dev;
}
static int our_interface(struct c4iw_dev *dev, struct net_device *egress_dev)
@@ -400,7 +412,8 @@ static struct dst_entry *find_route(struct c4iw_dev *dev, __be32 local_ip,
n = dst_neigh_lookup(&rt->dst, &peer_ip);
if (!n)
return NULL;
- if (!our_interface(dev, n->dev)) {
+ if (!our_interface(dev, n->dev) &&
+ !(n->dev->flags & IFF_LOOPBACK)) {
dst_release(&rt->dst);
return NULL;
}
@@ -419,8 +432,17 @@ static void arp_failure_discard(void *handle, struct sk_buff *skb)
*/
static void act_open_req_arp_failure(void *handle, struct sk_buff *skb)
{
+ struct c4iw_ep *ep = handle;
+
printk(KERN_ERR MOD "ARP failure duing connect\n");
kfree_skb(skb);
+ connect_reply_upcall(ep, -EHOSTUNREACH);
+ state_set(&ep->com, DEAD);
+ remove_handle(ep->com.dev, &ep->com.dev->atid_idr, ep->atid);
+ cxgb4_free_atid(ep->com.dev->rdev.lldi.tids, ep->atid);
+ dst_release(ep->dst);
+ cxgb4_l2t_release(ep->l2t);
+ c4iw_put_ep(&ep->com);
}
/*
@@ -464,7 +486,7 @@ static void send_flowc(struct c4iw_ep *ep, struct sk_buff *skb)
flowc->mnemval[5].mnemonic = FW_FLOWC_MNEM_RCVNXT;
flowc->mnemval[5].val = cpu_to_be32(ep->rcv_seq);
flowc->mnemval[6].mnemonic = FW_FLOWC_MNEM_SNDBUF;
- flowc->mnemval[6].val = cpu_to_be32(snd_win);
+ flowc->mnemval[6].val = cpu_to_be32(ep->snd_win);
flowc->mnemval[7].mnemonic = FW_FLOWC_MNEM_MSS;
flowc->mnemval[7].val = cpu_to_be32(ep->emss);
/* Pad WR to 16 byte boundary */
@@ -524,48 +546,47 @@ static int send_abort(struct c4iw_ep *ep, struct sk_buff *skb, gfp_t gfp)
return c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
}
-#define VLAN_NONE 0xfff
-#define FILTER_SEL_VLAN_NONE 0xffff
-#define FILTER_SEL_WIDTH_P_FC (3+1) /* port uses 3 bits, FCoE one bit */
-#define FILTER_SEL_WIDTH_VIN_P_FC \
- (6 + 7 + FILTER_SEL_WIDTH_P_FC) /* 6 bits are unused, VF uses 7 bits*/
-#define FILTER_SEL_WIDTH_TAG_P_FC \
- (3 + FILTER_SEL_WIDTH_VIN_P_FC) /* PF uses 3 bits */
-#define FILTER_SEL_WIDTH_VLD_TAG_P_FC (1 + FILTER_SEL_WIDTH_TAG_P_FC)
+/*
+ * c4iw_form_pm_msg - Form a port mapper message with mapping info
+ */
+static void c4iw_form_pm_msg(struct c4iw_ep *ep,
+ struct iwpm_sa_data *pm_msg)
+{
+ memcpy(&pm_msg->loc_addr, &ep->com.local_addr,
+ sizeof(ep->com.local_addr));
+ memcpy(&pm_msg->rem_addr, &ep->com.remote_addr,
+ sizeof(ep->com.remote_addr));
+}
-static unsigned int select_ntuple(struct c4iw_dev *dev, struct dst_entry *dst,
- struct l2t_entry *l2t)
+/*
+ * c4iw_form_reg_msg - Form a port mapper message with dev info
+ */
+static void c4iw_form_reg_msg(struct c4iw_dev *dev,
+ struct iwpm_dev_data *pm_msg)
{
- unsigned int ntuple = 0;
- u32 viid;
+ memcpy(pm_msg->dev_name, dev->ibdev.name, IWPM_DEVNAME_SIZE);
+ memcpy(pm_msg->if_name, dev->rdev.lldi.ports[0]->name,
+ IWPM_IFNAME_SIZE);
+}
- switch (dev->rdev.lldi.filt_mode) {
+static void c4iw_record_pm_msg(struct c4iw_ep *ep,
+ struct iwpm_sa_data *pm_msg)
+{
+ memcpy(&ep->com.mapped_local_addr, &pm_msg->mapped_loc_addr,
+ sizeof(ep->com.mapped_local_addr));
+ memcpy(&ep->com.mapped_remote_addr, &pm_msg->mapped_rem_addr,
+ sizeof(ep->com.mapped_remote_addr));
+}
- /* default filter mode */
- case HW_TPL_FR_MT_PR_IV_P_FC:
- if (l2t->vlan == VLAN_NONE)
- ntuple |= FILTER_SEL_VLAN_NONE << FILTER_SEL_WIDTH_P_FC;
- else {
- ntuple |= l2t->vlan << FILTER_SEL_WIDTH_P_FC;
- ntuple |= 1 << FILTER_SEL_WIDTH_TAG_P_FC;
- }
- ntuple |= l2t->lport << S_PORT | IPPROTO_TCP <<
- FILTER_SEL_WIDTH_VLD_TAG_P_FC;
- break;
- case HW_TPL_FR_MT_PR_OV_P_FC: {
- viid = cxgb4_port_viid(l2t->neigh->dev);
-
- ntuple |= FW_VIID_VIN_GET(viid) << FILTER_SEL_WIDTH_P_FC;
- ntuple |= FW_VIID_PFN_GET(viid) << FILTER_SEL_WIDTH_VIN_P_FC;
- ntuple |= FW_VIID_VIVLD_GET(viid) << FILTER_SEL_WIDTH_TAG_P_FC;
- ntuple |= l2t->lport << S_PORT | IPPROTO_TCP <<
- FILTER_SEL_WIDTH_VLD_TAG_P_FC;
- break;
- }
- default:
- break;
- }
- return ntuple;
+static void best_mtu(const unsigned short *mtus, unsigned short mtu,
+ unsigned int *idx, int use_ts)
+{
+ unsigned short hdr_size = sizeof(struct iphdr) +
+ sizeof(struct tcphdr) +
+ (use_ts ? 12 : 0);
+ unsigned short data_size = mtu - hdr_size;
+
+ cxgb4_best_aligned_mtu(mtus, hdr_size, data_size, 8, idx);
}
static int send_connect(struct c4iw_ep *ep)
@@ -586,10 +607,15 @@ static int send_connect(struct c4iw_ep *ep)
int sizev6 = is_t4(ep->com.dev->rdev.lldi.adapter_type) ?
sizeof(struct cpl_act_open_req6) :
sizeof(struct cpl_t5_act_open_req6);
- struct sockaddr_in *la = (struct sockaddr_in *)&ep->com.local_addr;
- struct sockaddr_in *ra = (struct sockaddr_in *)&ep->com.remote_addr;
- struct sockaddr_in6 *la6 = (struct sockaddr_in6 *)&ep->com.local_addr;
- struct sockaddr_in6 *ra6 = (struct sockaddr_in6 *)&ep->com.remote_addr;
+ struct sockaddr_in *la = (struct sockaddr_in *)
+ &ep->com.mapped_local_addr;
+ struct sockaddr_in *ra = (struct sockaddr_in *)
+ &ep->com.mapped_remote_addr;
+ struct sockaddr_in6 *la6 = (struct sockaddr_in6 *)
+ &ep->com.mapped_local_addr;
+ struct sockaddr_in6 *ra6 = (struct sockaddr_in6 *)
+ &ep->com.mapped_remote_addr;
+ int win;
wrlen = (ep->com.remote_addr.ss_family == AF_INET) ?
roundup(sizev4, 16) :
@@ -605,8 +631,18 @@ static int send_connect(struct c4iw_ep *ep)
}
set_wr_txq(skb, CPL_PRIORITY_SETUP, ep->ctrlq_idx);
- cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx);
+ best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx,
+ enable_tcp_timestamps);
wscale = compute_wscale(rcv_win);
+
+ /*
+ * Specify the largest window that will fit in opt0. The
+ * remainder will be specified in the rx_data_ack.
+ */
+ win = ep->rcv_win >> 10;
+ if (win > RCV_BUFSIZ_MASK)
+ win = RCV_BUFSIZ_MASK;
+
opt0 = (nocong ? NO_CONG(1) : 0) |
KEEP_ALIVE(1) |
DELACK(1) |
@@ -617,7 +653,7 @@ static int send_connect(struct c4iw_ep *ep)
SMAC_SEL(ep->smac_idx) |
DSCP(ep->tos) |
ULP_MODE(ULP_MODE_TCPDDP) |
- RCV_BUFSIZ(rcv_win>>10);
+ RCV_BUFSIZ(win);
opt2 = RX_CHANNEL(0) |
CCTRL_ECN(enable_ecn) |
RSS_QUEUE_VALID | RSS_QUEUE(ep->rss_qid);
@@ -627,7 +663,11 @@ static int send_connect(struct c4iw_ep *ep)
opt2 |= SACK_EN(1);
if (wscale && enable_tcp_window_scaling)
opt2 |= WND_SCALE_EN(1);
- t4_set_arp_err_handler(skb, NULL, act_open_req_arp_failure);
+ if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) {
+ opt2 |= T5_OPT_2_VALID;
+ opt2 |= V_CONG_CNTRL(CONG_ALG_TAHOE);
+ }
+ t4_set_arp_err_handler(skb, ep, act_open_req_arp_failure);
if (is_t4(ep->com.dev->rdev.lldi.adapter_type)) {
if (ep->com.remote_addr.ss_family == AF_INET) {
@@ -641,8 +681,9 @@ static int send_connect(struct c4iw_ep *ep)
req->local_ip = la->sin_addr.s_addr;
req->peer_ip = ra->sin_addr.s_addr;
req->opt0 = cpu_to_be64(opt0);
- req->params = cpu_to_be32(select_ntuple(ep->com.dev,
- ep->dst, ep->l2t));
+ req->params = cpu_to_be32(cxgb4_select_ntuple(
+ ep->com.dev->rdev.lldi.ports[0],
+ ep->l2t));
req->opt2 = cpu_to_be32(opt2);
} else {
req6 = (struct cpl_act_open_req6 *)skb_put(skb, wrlen);
@@ -662,12 +703,19 @@ static int send_connect(struct c4iw_ep *ep)
req6->peer_ip_lo = *((__be64 *)
(ra6->sin6_addr.s6_addr + 8));
req6->opt0 = cpu_to_be64(opt0);
- req6->params = cpu_to_be32(
- select_ntuple(ep->com.dev, ep->dst,
- ep->l2t));
+ req6->params = cpu_to_be32(cxgb4_select_ntuple(
+ ep->com.dev->rdev.lldi.ports[0],
+ ep->l2t));
req6->opt2 = cpu_to_be32(opt2);
}
} else {
+ u32 isn = (prandom_u32() & ~7UL) - 1;
+
+ opt2 |= T5_OPT_2_VALID;
+ opt2 |= CONG_CNTRL_VALID; /* OPT_2_ISS for T5 */
+ if (peer2peer)
+ isn += 4;
+
if (ep->com.remote_addr.ss_family == AF_INET) {
t5_req = (struct cpl_t5_act_open_req *)
skb_put(skb, wrlen);
@@ -681,8 +729,12 @@ static int send_connect(struct c4iw_ep *ep)
t5_req->peer_ip = ra->sin_addr.s_addr;
t5_req->opt0 = cpu_to_be64(opt0);
t5_req->params = cpu_to_be64(V_FILTER_TUPLE(
- select_ntuple(ep->com.dev,
- ep->dst, ep->l2t)));
+ cxgb4_select_ntuple(
+ ep->com.dev->rdev.lldi.ports[0],
+ ep->l2t)));
+ t5_req->rsvd = cpu_to_be32(isn);
+ PDBG("%s snd_isn %u\n", __func__,
+ be32_to_cpu(t5_req->rsvd));
t5_req->opt2 = cpu_to_be32(opt2);
} else {
t5_req6 = (struct cpl_t5_act_open_req6 *)
@@ -703,7 +755,12 @@ static int send_connect(struct c4iw_ep *ep)
(ra6->sin6_addr.s6_addr + 8));
t5_req6->opt0 = cpu_to_be64(opt0);
t5_req6->params = (__force __be64)cpu_to_be32(
- select_ntuple(ep->com.dev, ep->dst, ep->l2t));
+ cxgb4_select_ntuple(
+ ep->com.dev->rdev.lldi.ports[0],
+ ep->l2t));
+ t5_req6->rsvd = cpu_to_be32(isn);
+ PDBG("%s snd_isn %u\n", __func__,
+ be32_to_cpu(t5_req6->rsvd));
t5_req6->opt2 = cpu_to_be32(opt2);
}
}
@@ -799,8 +856,9 @@ static void send_mpa_req(struct c4iw_ep *ep, struct sk_buff *skb,
ep->mpa_skb = skb;
c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
start_ep_timer(ep);
- state_set(&ep->com, MPA_REQ_SENT);
+ __state_set(&ep->com, MPA_REQ_SENT);
ep->mpa_attr.initiator = 1;
+ ep->snd_seq += mpalen;
return;
}
@@ -880,6 +938,7 @@ static int send_mpa_reject(struct c4iw_ep *ep, const void *pdata, u8 plen)
t4_set_arp_err_handler(skb, NULL, arp_failure_discard);
BUG_ON(ep->mpa_skb);
ep->mpa_skb = skb;
+ ep->snd_seq += mpalen;
return c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
}
@@ -963,7 +1022,8 @@ static int send_mpa_reply(struct c4iw_ep *ep, const void *pdata, u8 plen)
skb_get(skb);
t4_set_arp_err_handler(skb, NULL, arp_failure_discard);
ep->mpa_skb = skb;
- state_set(&ep->com, MPA_REP_SENT);
+ __state_set(&ep->com, MPA_REP_SENT);
+ ep->snd_seq += mpalen;
return c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
}
@@ -980,6 +1040,7 @@ static int act_establish(struct c4iw_dev *dev, struct sk_buff *skb)
PDBG("%s ep %p tid %u snd_isn %u rcv_isn %u\n", __func__, ep, tid,
be32_to_cpu(req->snd_isn), be32_to_cpu(req->rcv_isn));
+ mutex_lock(&ep->com.mutex);
dst_confirm(ep->dst);
/* setup the hwtid for this connection */
@@ -1003,17 +1064,18 @@ static int act_establish(struct c4iw_dev *dev, struct sk_buff *skb)
send_mpa_req(ep, skb, 1);
else
send_mpa_req(ep, skb, mpa_rev);
-
+ mutex_unlock(&ep->com.mutex);
return 0;
}
-static void close_complete_upcall(struct c4iw_ep *ep)
+static void close_complete_upcall(struct c4iw_ep *ep, int status)
{
struct iw_cm_event event;
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
memset(&event, 0, sizeof(event));
event.event = IW_CM_EVENT_CLOSE;
+ event.status = status;
if (ep->com.cm_id) {
PDBG("close complete delivered ep %p cm_id %p tid %u\n",
ep, ep->com.cm_id, ep->hwtid);
@@ -1027,8 +1089,7 @@ static void close_complete_upcall(struct c4iw_ep *ep)
static int abort_connection(struct c4iw_ep *ep, struct sk_buff *skb, gfp_t gfp)
{
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
- close_complete_upcall(ep);
- state_set(&ep->com, ABORTING);
+ __state_set(&ep->com, ABORTING);
set_bit(ABORT_CONN, &ep->com.history);
return send_abort(ep, skb, gfp);
}
@@ -1106,9 +1167,10 @@ static void connect_reply_upcall(struct c4iw_ep *ep, int status)
}
}
-static void connect_request_upcall(struct c4iw_ep *ep)
+static int connect_request_upcall(struct c4iw_ep *ep)
{
struct iw_cm_event event;
+ int ret;
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
memset(&event, 0, sizeof(event));
@@ -1133,15 +1195,14 @@ static void connect_request_upcall(struct c4iw_ep *ep)
event.private_data_len = ep->plen;
event.private_data = ep->mpa_pkt + sizeof(struct mpa_message);
}
- if (state_read(&ep->parent_ep->com) != DEAD) {
- c4iw_get_ep(&ep->com);
- ep->parent_ep->com.cm_id->event_handler(
- ep->parent_ep->com.cm_id,
- &event);
- }
+ c4iw_get_ep(&ep->com);
+ ret = ep->parent_ep->com.cm_id->event_handler(ep->parent_ep->com.cm_id,
+ &event);
+ if (ret)
+ c4iw_put_ep(&ep->com);
set_bit(CONNREQ_UPCALL, &ep->com.history);
c4iw_put_ep(&ep->parent_ep->com);
- ep->parent_ep = NULL;
+ return ret;
}
static void established_upcall(struct c4iw_ep *ep)
@@ -1173,6 +1234,14 @@ static int update_rx_credits(struct c4iw_ep *ep, u32 credits)
return 0;
}
+ /*
+ * If we couldn't specify the entire rcv window at connection setup
+ * due to the limit in the number of bits in the RCV_BUFSIZ field,
+ * then add the overage in to the credits returned.
+ */
+ if (ep->rcv_win > RCV_BUFSIZ_MASK * 1024)
+ credits += ep->rcv_win - RCV_BUFSIZ_MASK * 1024;
+
req = (struct cpl_rx_data_ack *) skb_put(skb, wrlen);
memset(req, 0, wrlen);
INIT_TP_WR(req, ep->hwtid);
@@ -1186,7 +1255,7 @@ static int update_rx_credits(struct c4iw_ep *ep, u32 credits)
return credits;
}
-static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
+static int process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
{
struct mpa_message *mpa;
struct mpa_v2_conn_params *mpa_v2_params;
@@ -1196,17 +1265,17 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
struct c4iw_qp_attributes attrs;
enum c4iw_qp_attr_mask mask;
int err;
+ int disconnect = 0;
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
/*
- * Stop mpa timer. If it expired, then the state has
- * changed and we bail since ep_timeout already aborted
- * the connection.
+ * Stop mpa timer. If it expired, then
+ * we ignore the MPA reply. process_timeout()
+ * will abort the connection.
*/
- stop_ep_timer(ep);
- if (state_read(&ep->com) != MPA_REQ_SENT)
- return;
+ if (stop_ep_timer(ep))
+ return 0;
/*
* If we get more than the supported amount of private data
@@ -1228,7 +1297,7 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
* if we don't even have the mpa message, then bail.
*/
if (ep->mpa_pkt_len < sizeof(*mpa))
- return;
+ return 0;
mpa = (struct mpa_message *) ep->mpa_pkt;
/* Validate MPA header. */
@@ -1268,7 +1337,7 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
* We'll continue process when more data arrives.
*/
if (ep->mpa_pkt_len < (sizeof(*mpa) + plen))
- return;
+ return 0;
if (mpa->flags & MPA_REJECT) {
err = -ECONNREFUSED;
@@ -1280,7 +1349,7 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
* start reply message including private data. And
* the MPA header is valid.
*/
- state_set(&ep->com, FPDU_MODE);
+ __state_set(&ep->com, FPDU_MODE);
ep->mpa_attr.crc_enabled = (mpa->flags & MPA_CRC) | crc_enabled ? 1 : 0;
ep->mpa_attr.recv_marker_enabled = markers_enabled;
ep->mpa_attr.xmit_marker_enabled = mpa->flags & MPA_MARKERS ? 1 : 0;
@@ -1370,9 +1439,11 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
attrs.layer_etype = LAYER_MPA | DDP_LLP;
attrs.ecode = MPA_NOMATCH_RTR;
attrs.next_state = C4IW_QP_STATE_TERMINATE;
+ attrs.send_term = 1;
err = c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
- C4IW_QP_ATTR_NEXT_STATE, &attrs, 0);
+ C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
err = -ENOMEM;
+ disconnect = 1;
goto out;
}
@@ -1388,18 +1459,20 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
attrs.layer_etype = LAYER_MPA | DDP_LLP;
attrs.ecode = MPA_INSUFF_IRD;
attrs.next_state = C4IW_QP_STATE_TERMINATE;
+ attrs.send_term = 1;
err = c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
- C4IW_QP_ATTR_NEXT_STATE, &attrs, 0);
+ C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
err = -ENOMEM;
+ disconnect = 1;
goto out;
}
goto out;
err:
- state_set(&ep->com, ABORTING);
+ __state_set(&ep->com, ABORTING);
send_abort(ep, skb, GFP_KERNEL);
out:
connect_reply_upcall(ep, err);
- return;
+ return disconnect;
}
static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb)
@@ -1410,15 +1483,12 @@ static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb)
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
- if (state_read(&ep->com) != MPA_REQ_WAIT)
- return;
-
/*
* If we get more than the supported amount of private data
* then we must fail this connection.
*/
if (ep->mpa_pkt_len + skb->len > sizeof(ep->mpa_pkt)) {
- stop_ep_timer(ep);
+ (void)stop_ep_timer(ep);
abort_connection(ep, skb, GFP_KERNEL);
return;
}
@@ -1440,7 +1510,6 @@ static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb)
return;
PDBG("%s enter (%s line %u)\n", __func__, __FILE__, __LINE__);
- stop_ep_timer(ep);
mpa = (struct mpa_message *) ep->mpa_pkt;
/*
@@ -1449,13 +1518,13 @@ static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb)
if (mpa->revision > mpa_rev) {
printk(KERN_ERR MOD "%s MPA version mismatch. Local = %d,"
" Received = %d\n", __func__, mpa_rev, mpa->revision);
- stop_ep_timer(ep);
+ (void)stop_ep_timer(ep);
abort_connection(ep, skb, GFP_KERNEL);
return;
}
if (memcmp(mpa->key, MPA_KEY_REQ, sizeof(mpa->key))) {
- stop_ep_timer(ep);
+ (void)stop_ep_timer(ep);
abort_connection(ep, skb, GFP_KERNEL);
return;
}
@@ -1466,7 +1535,7 @@ static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb)
* Fail if there's too much private data.
*/
if (plen > MPA_MAX_PRIVATE_DATA) {
- stop_ep_timer(ep);
+ (void)stop_ep_timer(ep);
abort_connection(ep, skb, GFP_KERNEL);
return;
}
@@ -1475,7 +1544,7 @@ static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb)
* If plen does not account for pkt size
*/
if (ep->mpa_pkt_len > (sizeof(*mpa) + plen)) {
- stop_ep_timer(ep);
+ (void)stop_ep_timer(ep);
abort_connection(ep, skb, GFP_KERNEL);
return;
}
@@ -1532,10 +1601,24 @@ static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb)
ep->mpa_attr.xmit_marker_enabled, ep->mpa_attr.version,
ep->mpa_attr.p2p_type);
- state_set(&ep->com, MPA_REQ_RCVD);
-
- /* drive upcall */
- connect_request_upcall(ep);
+ /*
+ * If the endpoint timer already expired, then we ignore
+ * the start request. process_timeout() will abort
+ * the connection.
+ */
+ if (!stop_ep_timer(ep)) {
+ __state_set(&ep->com, MPA_REQ_RCVD);
+
+ /* drive upcall */
+ mutex_lock(&ep->parent_ep->com.mutex);
+ if (ep->parent_ep->com.state != DEAD) {
+ if (connect_request_upcall(ep))
+ abort_connection(ep, skb, GFP_KERNEL);
+ } else {
+ abort_connection(ep, skb, GFP_KERNEL);
+ }
+ mutex_unlock(&ep->parent_ep->com.mutex);
+ }
return;
}
@@ -1547,19 +1630,23 @@ static int rx_data(struct c4iw_dev *dev, struct sk_buff *skb)
unsigned int tid = GET_TID(hdr);
struct tid_info *t = dev->rdev.lldi.tids;
__u8 status = hdr->status;
+ int disconnect = 0;
ep = lookup_tid(t, tid);
+ if (!ep)
+ return 0;
PDBG("%s ep %p tid %u dlen %u\n", __func__, ep, ep->hwtid, dlen);
skb_pull(skb, sizeof(*hdr));
skb_trim(skb, dlen);
+ mutex_lock(&ep->com.mutex);
/* update RX credits */
update_rx_credits(ep, dlen);
- switch (state_read(&ep->com)) {
+ switch (ep->com.state) {
case MPA_REQ_SENT:
ep->rcv_seq += dlen;
- process_mpa_reply(ep, skb);
+ disconnect = process_mpa_reply(ep, skb);
break;
case MPA_REQ_WAIT:
ep->rcv_seq += dlen;
@@ -1572,15 +1659,19 @@ static int rx_data(struct c4iw_dev *dev, struct sk_buff *skb)
pr_err("%s Unexpected streaming data." \
" qpid %u ep %p state %d tid %u status %d\n",
__func__, ep->com.qp->wq.sq.qid, ep,
- state_read(&ep->com), ep->hwtid, status);
+ ep->com.state, ep->hwtid, status);
attrs.next_state = C4IW_QP_STATE_TERMINATE;
c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
- C4IW_QP_ATTR_NEXT_STATE, &attrs, 0);
+ C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
+ disconnect = 1;
break;
}
default:
break;
}
+ mutex_unlock(&ep->com.mutex);
+ if (disconnect)
+ c4iw_ep_disconnect(ep, 0, GFP_KERNEL);
return 0;
}
@@ -1624,18 +1715,20 @@ static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid)
unsigned int mtu_idx;
int wscale;
struct sockaddr_in *sin;
+ int win;
skb = get_skb(NULL, sizeof(*req), GFP_KERNEL);
req = (struct fw_ofld_connection_wr *)__skb_put(skb, sizeof(*req));
memset(req, 0, sizeof(*req));
req->op_compl = htonl(V_WR_OP(FW_OFLD_CONNECTION_WR));
req->len16_pkd = htonl(FW_WR_LEN16(DIV_ROUND_UP(sizeof(*req), 16)));
- req->le.filter = cpu_to_be32(select_ntuple(ep->com.dev, ep->dst,
+ req->le.filter = cpu_to_be32(cxgb4_select_ntuple(
+ ep->com.dev->rdev.lldi.ports[0],
ep->l2t));
- sin = (struct sockaddr_in *)&ep->com.local_addr;
+ sin = (struct sockaddr_in *)&ep->com.mapped_local_addr;
req->le.lport = sin->sin_port;
req->le.u.ipv4.lip = sin->sin_addr.s_addr;
- sin = (struct sockaddr_in *)&ep->com.remote_addr;
+ sin = (struct sockaddr_in *)&ep->com.mapped_remote_addr;
req->le.pport = sin->sin_port;
req->le.u.ipv4.pip = sin->sin_addr.s_addr;
req->tcb.t_state_to_astid =
@@ -1645,8 +1738,18 @@ static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid)
htons(F_FW_OFLD_CONNECTION_WR_CPLRXDATAACK);
req->tcb.tx_max = (__force __be32) jiffies;
req->tcb.rcv_adv = htons(1);
- cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx);
+ best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx,
+ enable_tcp_timestamps);
wscale = compute_wscale(rcv_win);
+
+ /*
+ * Specify the largest window that will fit in opt0. The
+ * remainder will be specified in the rx_data_ack.
+ */
+ win = ep->rcv_win >> 10;
+ if (win > RCV_BUFSIZ_MASK)
+ win = RCV_BUFSIZ_MASK;
+
req->tcb.opt0 = (__force __be64) (TCAM_BYPASS(1) |
(nocong ? NO_CONG(1) : 0) |
KEEP_ALIVE(1) |
@@ -1658,7 +1761,7 @@ static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid)
SMAC_SEL(ep->smac_idx) |
DSCP(ep->tos) |
ULP_MODE(ULP_MODE_TCPDDP) |
- RCV_BUFSIZ(rcv_win >> 10));
+ RCV_BUFSIZ(win));
req->tcb.opt2 = (__force __be32) (PACE(1) |
TX_QUEUE(ep->com.dev->rdev.lldi.tx_modq[ep->tx_chan]) |
RX_CHANNEL(0) |
@@ -1686,6 +1789,22 @@ static inline int act_open_has_tid(int status)
status != CPL_ERR_ARP_MISS;
}
+/* Returns whether a CPL status conveys negative advice.
+ */
+static int is_neg_adv(unsigned int status)
+{
+ return status == CPL_ERR_RTX_NEG_ADVICE ||
+ status == CPL_ERR_PERSIST_NEG_ADVICE ||
+ status == CPL_ERR_KEEPALV_NEG_ADVICE;
+}
+
+static void set_tcp_window(struct c4iw_ep *ep, struct port_info *pi)
+{
+ ep->snd_win = snd_win;
+ ep->rcv_win = rcv_win;
+ PDBG("%s snd_win %d rcv_win %d\n", __func__, ep->snd_win, ep->rcv_win);
+}
+
#define ACT_OPEN_RETRY_COUNT 2
static int import_ep(struct c4iw_ep *ep, int iptype, __u8 *peer_ip,
@@ -1734,6 +1853,7 @@ static int import_ep(struct c4iw_ep *ep, int iptype, __u8 *peer_ip,
ep->ctrlq_idx = cxgb4_port_idx(pdev);
ep->rss_qid = cdev->rdev.lldi.rxq_ids[
cxgb4_port_idx(pdev) * step];
+ set_tcp_window(ep, (struct port_info *)netdev_priv(pdev));
dev_put(pdev);
} else {
pdev = get_real_dev(n->dev);
@@ -1742,16 +1862,17 @@ static int import_ep(struct c4iw_ep *ep, int iptype, __u8 *peer_ip,
if (!ep->l2t)
goto out;
ep->mtu = dst_mtu(dst);
- ep->tx_chan = cxgb4_port_chan(n->dev);
- ep->smac_idx = (cxgb4_port_viid(n->dev) & 0x7F) << 1;
+ ep->tx_chan = cxgb4_port_chan(pdev);
+ ep->smac_idx = (cxgb4_port_viid(pdev) & 0x7F) << 1;
step = cdev->rdev.lldi.ntxq /
cdev->rdev.lldi.nchan;
- ep->txq_idx = cxgb4_port_idx(n->dev) * step;
- ep->ctrlq_idx = cxgb4_port_idx(n->dev);
+ ep->txq_idx = cxgb4_port_idx(pdev) * step;
+ ep->ctrlq_idx = cxgb4_port_idx(pdev);
step = cdev->rdev.lldi.nrxq /
cdev->rdev.lldi.nchan;
ep->rss_qid = cdev->rdev.lldi.rxq_ids[
- cxgb4_port_idx(n->dev) * step];
+ cxgb4_port_idx(pdev) * step];
+ set_tcp_window(ep, (struct port_info *)netdev_priv(pdev));
if (clear_mpa_v1) {
ep->retry_with_mpa_v1 = 0;
@@ -1866,15 +1987,15 @@ static int act_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
struct sockaddr_in6 *ra6;
ep = lookup_atid(t, atid);
- la = (struct sockaddr_in *)&ep->com.local_addr;
- ra = (struct sockaddr_in *)&ep->com.remote_addr;
- la6 = (struct sockaddr_in6 *)&ep->com.local_addr;
- ra6 = (struct sockaddr_in6 *)&ep->com.remote_addr;
+ la = (struct sockaddr_in *)&ep->com.mapped_local_addr;
+ ra = (struct sockaddr_in *)&ep->com.mapped_remote_addr;
+ la6 = (struct sockaddr_in6 *)&ep->com.mapped_local_addr;
+ ra6 = (struct sockaddr_in6 *)&ep->com.mapped_remote_addr;
PDBG("%s ep %p atid %u status %u errno %d\n", __func__, ep, atid,
status, status2errno(status));
- if (status == CPL_ERR_RTX_NEG_ADVICE) {
+ if (is_neg_adv(status)) {
printk(KERN_WARNING MOD "Connection problems for atid %u\n",
atid);
return 0;
@@ -1982,13 +2103,36 @@ static void accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
u64 opt0;
u32 opt2;
int wscale;
+ struct cpl_t5_pass_accept_rpl *rpl5 = NULL;
+ int win;
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
BUG_ON(skb_cloned(skb));
- skb_trim(skb, sizeof(*rpl));
+
skb_get(skb);
- cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx);
+ rpl = cplhdr(skb);
+ if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) {
+ skb_trim(skb, roundup(sizeof(*rpl5), 16));
+ rpl5 = (void *)rpl;
+ INIT_TP_WR(rpl5, ep->hwtid);
+ } else {
+ skb_trim(skb, sizeof(*rpl));
+ INIT_TP_WR(rpl, ep->hwtid);
+ }
+ OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL,
+ ep->hwtid));
+
+ best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx,
+ enable_tcp_timestamps && req->tcpopt.tstamp);
wscale = compute_wscale(rcv_win);
+
+ /*
+ * Specify the largest window that will fit in opt0. The
+ * remainder will be specified in the rx_data_ack.
+ */
+ win = ep->rcv_win >> 10;
+ if (win > RCV_BUFSIZ_MASK)
+ win = RCV_BUFSIZ_MASK;
opt0 = (nocong ? NO_CONG(1) : 0) |
KEEP_ALIVE(1) |
DELACK(1) |
@@ -1999,7 +2143,7 @@ static void accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
SMAC_SEL(ep->smac_idx) |
DSCP(ep->tos >> 2) |
ULP_MODE(ULP_MODE_TCPDDP) |
- RCV_BUFSIZ(rcv_win>>10);
+ RCV_BUFSIZ(win);
opt2 = RX_CHANNEL(0) |
RSS_QUEUE_VALID | RSS_QUEUE(ep->rss_qid);
@@ -2018,11 +2162,19 @@ static void accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
if (tcph->ece && tcph->cwr)
opt2 |= CCTRL_ECN(1);
}
+ if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) {
+ u32 isn = (prandom_u32() & ~7UL) - 1;
+ opt2 |= T5_OPT_2_VALID;
+ opt2 |= V_CONG_CNTRL(CONG_ALG_TAHOE);
+ opt2 |= CONG_CNTRL_VALID; /* OPT_2_ISS for T5 */
+ rpl5 = (void *)rpl;
+ memset(&rpl5->iss, 0, roundup(sizeof(*rpl5)-sizeof(*rpl), 16));
+ if (peer2peer)
+ isn += 4;
+ rpl5->iss = cpu_to_be32(isn);
+ PDBG("%s iss %u\n", __func__, be32_to_cpu(rpl5->iss));
+ }
- rpl = cplhdr(skb);
- INIT_TP_WR(rpl, ep->hwtid);
- OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL,
- ep->hwtid));
rpl->opt0 = cpu_to_be64(opt0);
rpl->opt2 = cpu_to_be32(opt2);
set_wr_txq(skb, CPL_PRIORITY_SETUP, ep->ctrlq_idx);
@@ -2037,7 +2189,6 @@ static void reject_cr(struct c4iw_dev *dev, u32 hwtid, struct sk_buff *skb)
PDBG("%s c4iw_dev %p tid %u\n", __func__, dev, hwtid);
BUG_ON(skb_cloned(skb));
skb_trim(skb, sizeof(struct cpl_tid_release));
- skb_get(skb);
release_tid(&dev->rdev, hwtid, skb);
return;
}
@@ -2087,6 +2238,7 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
int err;
u16 peer_mss = ntohs(req->tcpopt.mss);
int iptype;
+ unsigned short hdrs;
parent_ep = lookup_stid(t, stid);
if (!parent_ep) {
@@ -2144,8 +2296,10 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
goto reject;
}
- if (peer_mss && child_ep->mtu > (peer_mss + 40))
- child_ep->mtu = peer_mss + 40;
+ hdrs = sizeof(struct iphdr) + sizeof(struct tcphdr) +
+ ((enable_tcp_timestamps && req->tcpopt.tstamp) ? 12 : 0);
+ if (peer_mss && child_ep->mtu > (peer_mss + hdrs))
+ child_ep->mtu = peer_mss + hdrs;
state_set(&child_ep->com, CONNECTING);
child_ep->com.dev = dev;
@@ -2279,13 +2433,13 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
disconnect = 0;
break;
case MORIBUND:
- stop_ep_timer(ep);
+ (void)stop_ep_timer(ep);
if (ep->com.cm_id && ep->com.qp) {
attrs.next_state = C4IW_QP_STATE_IDLE;
c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
}
- close_complete_upcall(ep);
+ close_complete_upcall(ep, 0);
__state_set(&ep->com, DEAD);
release = 1;
disconnect = 0;
@@ -2304,15 +2458,6 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
return 0;
}
-/*
- * Returns whether an ABORT_REQ_RSS message is a negative advice.
- */
-static int is_neg_adv_abort(unsigned int status)
-{
- return status == CPL_ERR_RTX_NEG_ADVICE ||
- status == CPL_ERR_PERSIST_NEG_ADVICE;
-}
-
static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
{
struct cpl_abort_req_rss *req = cplhdr(skb);
@@ -2326,7 +2471,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
unsigned int tid = GET_TID(req);
ep = lookup_tid(t, tid);
- if (is_neg_adv_abort(req->status)) {
+ if (is_neg_adv(req->status)) {
PDBG("%s neg_adv_abort ep %p tid %u\n", __func__, ep,
ep->hwtid);
return 0;
@@ -2348,10 +2493,10 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
case CONNECTING:
break;
case MPA_REQ_WAIT:
- stop_ep_timer(ep);
+ (void)stop_ep_timer(ep);
break;
case MPA_REQ_SENT:
- stop_ep_timer(ep);
+ (void)stop_ep_timer(ep);
if (mpa_rev == 1 || (mpa_rev == 2 && ep->tried_with_mpa_v1))
connect_reply_upcall(ep, -ECONNRESET);
else {
@@ -2456,7 +2601,7 @@ static int close_con_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
__state_set(&ep->com, MORIBUND);
break;
case MORIBUND:
- stop_ep_timer(ep);
+ (void)stop_ep_timer(ep);
if ((ep->com.cm_id) && (ep->com.qp)) {
attrs.next_state = C4IW_QP_STATE_IDLE;
c4iw_modify_qp(ep->com.qp->rhp,
@@ -2464,7 +2609,7 @@ static int close_con_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
C4IW_QP_ATTR_NEXT_STATE,
&attrs, 1);
}
- close_complete_upcall(ep);
+ close_complete_upcall(ep, 0);
__state_set(&ep->com, DEAD);
release = 1;
break;
@@ -2539,22 +2684,28 @@ static int fw4_ack(struct c4iw_dev *dev, struct sk_buff *skb)
int c4iw_reject_cr(struct iw_cm_id *cm_id, const void *pdata, u8 pdata_len)
{
- int err;
+ int err = 0;
+ int disconnect = 0;
struct c4iw_ep *ep = to_ep(cm_id);
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
- if (state_read(&ep->com) == DEAD) {
+ mutex_lock(&ep->com.mutex);
+ if (ep->com.state == DEAD) {
+ mutex_unlock(&ep->com.mutex);
c4iw_put_ep(&ep->com);
return -ECONNRESET;
}
set_bit(ULP_REJECT, &ep->com.history);
- BUG_ON(state_read(&ep->com) != MPA_REQ_RCVD);
+ BUG_ON(ep->com.state != MPA_REQ_RCVD);
if (mpa_rev == 0)
abort_connection(ep, NULL, GFP_KERNEL);
else {
err = send_mpa_reject(ep, pdata, pdata_len);
- err = c4iw_ep_disconnect(ep, 0, GFP_KERNEL);
+ disconnect = 1;
}
+ mutex_unlock(&ep->com.mutex);
+ if (disconnect)
+ err = c4iw_ep_disconnect(ep, 0, GFP_KERNEL);
c4iw_put_ep(&ep->com);
return 0;
}
@@ -2569,12 +2720,14 @@ int c4iw_accept_cr(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
struct c4iw_qp *qp = get_qhp(h, conn_param->qpn);
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
- if (state_read(&ep->com) == DEAD) {
+
+ mutex_lock(&ep->com.mutex);
+ if (ep->com.state == DEAD) {
err = -ECONNRESET;
goto err;
}
- BUG_ON(state_read(&ep->com) != MPA_REQ_RCVD);
+ BUG_ON(ep->com.state != MPA_REQ_RCVD);
BUG_ON(!qp);
set_bit(ULP_ACCEPT, &ep->com.history);
@@ -2643,14 +2796,16 @@ int c4iw_accept_cr(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
if (err)
goto err1;
- state_set(&ep->com, FPDU_MODE);
+ __state_set(&ep->com, FPDU_MODE);
established_upcall(ep);
+ mutex_unlock(&ep->com.mutex);
c4iw_put_ep(&ep->com);
return 0;
err1:
ep->com.cm_id = NULL;
cm_id->rem_ref(cm_id);
err:
+ mutex_unlock(&ep->com.mutex);
c4iw_put_ep(&ep->com);
return err;
}
@@ -2721,13 +2876,15 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
struct c4iw_dev *dev = to_c4iw_dev(cm_id->device);
struct c4iw_ep *ep;
int err = 0;
- struct sockaddr_in *laddr = (struct sockaddr_in *)&cm_id->local_addr;
- struct sockaddr_in *raddr = (struct sockaddr_in *)&cm_id->remote_addr;
- struct sockaddr_in6 *laddr6 = (struct sockaddr_in6 *)&cm_id->local_addr;
- struct sockaddr_in6 *raddr6 = (struct sockaddr_in6 *)
- &cm_id->remote_addr;
+ struct sockaddr_in *laddr;
+ struct sockaddr_in *raddr;
+ struct sockaddr_in6 *laddr6;
+ struct sockaddr_in6 *raddr6;
+ struct iwpm_dev_data pm_reg_msg;
+ struct iwpm_sa_data pm_msg;
__u8 *ra;
int iptype;
+ int iwpm_err = 0;
if ((conn_param->ord > c4iw_max_read_depth) ||
(conn_param->ird > c4iw_max_read_depth)) {
@@ -2758,7 +2915,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
if (!ep->com.qp) {
PDBG("%s qpn 0x%x not found!\n", __func__, conn_param->qpn);
err = -EINVAL;
- goto fail2;
+ goto fail1;
}
ref_qp(ep);
PDBG("%s qpn 0x%x qp %p cm_id %p\n", __func__, conn_param->qpn,
@@ -2771,10 +2928,50 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
if (ep->atid == -1) {
printk(KERN_ERR MOD "%s - cannot alloc atid.\n", __func__);
err = -ENOMEM;
- goto fail2;
+ goto fail1;
}
insert_handle(dev, &dev->atid_idr, ep, ep->atid);
+ memcpy(&ep->com.local_addr, &cm_id->local_addr,
+ sizeof(ep->com.local_addr));
+ memcpy(&ep->com.remote_addr, &cm_id->remote_addr,
+ sizeof(ep->com.remote_addr));
+
+ /* No port mapper available, go with the specified peer information */
+ memcpy(&ep->com.mapped_local_addr, &cm_id->local_addr,
+ sizeof(ep->com.mapped_local_addr));
+ memcpy(&ep->com.mapped_remote_addr, &cm_id->remote_addr,
+ sizeof(ep->com.mapped_remote_addr));
+
+ c4iw_form_reg_msg(dev, &pm_reg_msg);
+ iwpm_err = iwpm_register_pid(&pm_reg_msg, RDMA_NL_C4IW);
+ if (iwpm_err) {
+ PDBG("%s: Port Mapper reg pid fail (err = %d).\n",
+ __func__, iwpm_err);
+ }
+ if (iwpm_valid_pid() && !iwpm_err) {
+ c4iw_form_pm_msg(ep, &pm_msg);
+ iwpm_err = iwpm_add_and_query_mapping(&pm_msg, RDMA_NL_C4IW);
+ if (iwpm_err)
+ PDBG("%s: Port Mapper query fail (err = %d).\n",
+ __func__, iwpm_err);
+ else
+ c4iw_record_pm_msg(ep, &pm_msg);
+ }
+ if (iwpm_create_mapinfo(&ep->com.local_addr,
+ &ep->com.mapped_local_addr, RDMA_NL_C4IW)) {
+ iwpm_remove_mapping(&ep->com.local_addr, RDMA_NL_C4IW);
+ err = -ENOMEM;
+ goto fail1;
+ }
+ print_addr(&ep->com, __func__, "add_query/create_mapinfo");
+ set_bit(RELEASE_MAPINFO, &ep->com.flags);
+
+ laddr = (struct sockaddr_in *)&ep->com.mapped_local_addr;
+ raddr = (struct sockaddr_in *)&ep->com.mapped_remote_addr;
+ laddr6 = (struct sockaddr_in6 *)&ep->com.mapped_local_addr;
+ raddr6 = (struct sockaddr_in6 *) &ep->com.mapped_remote_addr;
+
if (cm_id->remote_addr.ss_family == AF_INET) {
iptype = 4;
ra = (__u8 *)&raddr->sin_addr;
@@ -2785,7 +2982,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
if ((__force int)raddr->sin_addr.s_addr == INADDR_ANY) {
err = pick_local_ipaddrs(dev, cm_id);
if (err)
- goto fail2;
+ goto fail1;
}
/* find a route */
@@ -2805,7 +3002,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
if (ipv6_addr_type(&raddr6->sin6_addr) == IPV6_ADDR_ANY) {
err = pick_local_ip6addrs(dev, cm_id);
if (err)
- goto fail2;
+ goto fail1;
}
/* find a route */
@@ -2821,13 +3018,13 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
if (!ep->dst) {
printk(KERN_ERR MOD "%s - cannot find route.\n", __func__);
err = -EHOSTUNREACH;
- goto fail3;
+ goto fail2;
}
err = import_ep(ep, iptype, ra, ep->dst, ep->com.dev, true);
if (err) {
printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__);
- goto fail4;
+ goto fail3;
}
PDBG("%s txq_idx %u tx_chan %u smac_idx %u rss_qid %u l2t_idx %u\n",
@@ -2836,10 +3033,6 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
state_set(&ep->com, CONNECTING);
ep->tos = 0;
- memcpy(&ep->com.local_addr, &cm_id->local_addr,
- sizeof(ep->com.local_addr));
- memcpy(&ep->com.remote_addr, &cm_id->remote_addr,
- sizeof(ep->com.remote_addr));
/* send connect request to rnic */
err = send_connect(ep);
@@ -2847,12 +3040,12 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
goto out;
cxgb4_l2t_release(ep->l2t);
-fail4:
- dst_release(ep->dst);
fail3:
+ dst_release(ep->dst);
+fail2:
remove_handle(ep->com.dev, &ep->com.dev->atid_idr, ep->atid);
cxgb4_free_atid(ep->com.dev->rdev.lldi.tids, ep->atid);
-fail2:
+fail1:
cm_id->rem_ref(cm_id);
c4iw_put_ep(&ep->com);
out:
@@ -2862,7 +3055,8 @@ out:
static int create_server6(struct c4iw_dev *dev, struct c4iw_listen_ep *ep)
{
int err;
- struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&ep->com.local_addr;
+ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)
+ &ep->com.mapped_local_addr;
c4iw_init_wr_wait(&ep->com.wr_wait);
err = cxgb4_create_server6(ep->com.dev->rdev.lldi.ports[0],
@@ -2883,7 +3077,8 @@ static int create_server6(struct c4iw_dev *dev, struct c4iw_listen_ep *ep)
static int create_server4(struct c4iw_dev *dev, struct c4iw_listen_ep *ep)
{
int err;
- struct sockaddr_in *sin = (struct sockaddr_in *)&ep->com.local_addr;
+ struct sockaddr_in *sin = (struct sockaddr_in *)
+ &ep->com.mapped_local_addr;
if (dev->rdev.lldi.enable_fw_ofld_conn) {
do {
@@ -2918,6 +3113,9 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
int err = 0;
struct c4iw_dev *dev = to_c4iw_dev(cm_id->device);
struct c4iw_listen_ep *ep;
+ struct iwpm_dev_data pm_reg_msg;
+ struct iwpm_sa_data pm_msg;
+ int iwpm_err = 0;
might_sleep();
@@ -2938,7 +3136,8 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
/*
* Allocate a server TID.
*/
- if (dev->rdev.lldi.enable_fw_ofld_conn)
+ if (dev->rdev.lldi.enable_fw_ofld_conn &&
+ ep->com.local_addr.ss_family == AF_INET)
ep->stid = cxgb4_alloc_sftid(dev->rdev.lldi.tids,
cm_id->local_addr.ss_family, ep);
else
@@ -2951,6 +3150,37 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
goto fail2;
}
insert_handle(dev, &dev->stid_idr, ep, ep->stid);
+
+ /* No port mapper available, go with the specified info */
+ memcpy(&ep->com.mapped_local_addr, &cm_id->local_addr,
+ sizeof(ep->com.mapped_local_addr));
+
+ c4iw_form_reg_msg(dev, &pm_reg_msg);
+ iwpm_err = iwpm_register_pid(&pm_reg_msg, RDMA_NL_C4IW);
+ if (iwpm_err) {
+ PDBG("%s: Port Mapper reg pid fail (err = %d).\n",
+ __func__, iwpm_err);
+ }
+ if (iwpm_valid_pid() && !iwpm_err) {
+ memcpy(&pm_msg.loc_addr, &ep->com.local_addr,
+ sizeof(ep->com.local_addr));
+ iwpm_err = iwpm_add_mapping(&pm_msg, RDMA_NL_C4IW);
+ if (iwpm_err)
+ PDBG("%s: Port Mapper query fail (err = %d).\n",
+ __func__, iwpm_err);
+ else
+ memcpy(&ep->com.mapped_local_addr,
+ &pm_msg.mapped_loc_addr,
+ sizeof(ep->com.mapped_local_addr));
+ }
+ if (iwpm_create_mapinfo(&ep->com.local_addr,
+ &ep->com.mapped_local_addr, RDMA_NL_C4IW)) {
+ err = -ENOMEM;
+ goto fail3;
+ }
+ print_addr(&ep->com, __func__, "add_mapping/create_mapinfo");
+
+ set_bit(RELEASE_MAPINFO, &ep->com.flags);
state_set(&ep->com, LISTEN);
if (ep->com.local_addr.ss_family == AF_INET)
err = create_server4(dev, ep);
@@ -2960,6 +3190,8 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
cm_id->provider_data = ep;
goto out;
}
+
+fail3:
cxgb4_free_stid(ep->com.dev->rdev.lldi.tids, ep->stid,
ep->com.local_addr.ss_family);
fail2:
@@ -3018,7 +3250,7 @@ int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp)
rdev = &ep->com.dev->rdev;
if (c4iw_fatal_error(rdev)) {
fatal = 1;
- close_complete_upcall(ep);
+ close_complete_upcall(ep, -EIO);
ep->com.state = DEAD;
}
switch (ep->com.state) {
@@ -3040,7 +3272,7 @@ int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp)
if (!test_and_set_bit(CLOSE_SENT, &ep->com.flags)) {
close = 1;
if (abrupt) {
- stop_ep_timer(ep);
+ (void)stop_ep_timer(ep);
ep->com.state = ABORTING;
} else
ep->com.state = MORIBUND;
@@ -3060,7 +3292,7 @@ int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp)
if (close) {
if (abrupt) {
set_bit(EP_DISC_ABORT, &ep->com.history);
- close_complete_upcall(ep);
+ close_complete_upcall(ep, -ECONNRESET);
ret = send_abort(ep, NULL, gfp);
} else {
set_bit(EP_DISC_CLOSE, &ep->com.history);
@@ -3241,6 +3473,7 @@ static void send_fw_pass_open_req(struct c4iw_dev *dev, struct sk_buff *skb,
struct sk_buff *req_skb;
struct fw_ofld_connection_wr *req;
struct cpl_pass_accept_req *cpl = cplhdr(skb);
+ int ret;
req_skb = alloc_skb(sizeof(struct fw_ofld_connection_wr), GFP_KERNEL);
req = (struct fw_ofld_connection_wr *)__skb_put(req_skb, sizeof(*req));
@@ -3277,7 +3510,13 @@ static void send_fw_pass_open_req(struct c4iw_dev *dev, struct sk_buff *skb,
req->cookie = (unsigned long)skb;
set_wr_txq(req_skb, CPL_PRIORITY_CONTROL, port_id);
- cxgb4_ofld_send(dev->rdev.lldi.ports[0], req_skb);
+ ret = cxgb4_ofld_send(dev->rdev.lldi.ports[0], req_skb);
+ if (ret < 0) {
+ pr_err("%s - cxgb4_ofld_send error %d - dropping\n", __func__,
+ ret);
+ kfree_skb(skb);
+ kfree_skb(req_skb);
+ }
}
/*
@@ -3323,9 +3562,7 @@ static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb)
/*
* Calculate the server tid from filter hit index from cpl_rx_pkt.
*/
- stid = (__force int) cpu_to_be32((__force u32) rss->hash_val)
- - dev->rdev.lldi.tids->sftid_base
- + dev->rdev.lldi.tids->nstids;
+ stid = (__force int) cpu_to_be32((__force u32) rss->hash_val);
lep = (struct c4iw_ep *)lookup_stid(dev->rdev.lldi.tids, stid);
if (!lep) {
@@ -3386,6 +3623,7 @@ static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb)
pi = (struct port_info *)netdev_priv(pdev);
tx_chan = cxgb4_port_chan(pdev);
}
+ neigh_release(neigh);
if (!e) {
pr_err("%s - failed to allocate l2t entry!\n",
__func__);
@@ -3397,7 +3635,9 @@ static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb)
window = (__force u16) htons((__force u16)tcph->window);
/* Calcuate filter portion for LE region. */
- filter = (__force unsigned int) cpu_to_be32(select_ntuple(dev, dst, e));
+ filter = (__force unsigned int) cpu_to_be32(cxgb4_select_ntuple(
+ dev->rdev.lldi.ports[0],
+ e));
/*
* Synthesize the cpl_pass_accept_req. We have everything except the
@@ -3464,15 +3704,26 @@ static void process_timeout(struct c4iw_ep *ep)
&attrs, 1);
}
__state_set(&ep->com, ABORTING);
+ close_complete_upcall(ep, -ETIMEDOUT);
+ break;
+ case ABORTING:
+ case DEAD:
+
+ /*
+ * These states are expected if the ep timed out at the same
+ * time as another thread was calling stop_ep_timer().
+ * So we silently do nothing for these states.
+ */
+ abort = 0;
break;
default:
WARN(1, "%s unexpected state ep %p tid %u state %u\n",
__func__, ep, ep->hwtid, ep->com.state);
abort = 0;
}
- mutex_unlock(&ep->com.mutex);
if (abort)
abort_connection(ep, NULL, GFP_KERNEL);
+ mutex_unlock(&ep->com.mutex);
c4iw_put_ep(&ep->com);
}
@@ -3486,6 +3737,8 @@ static void process_timedout_eps(void)
tmp = timeout_list.next;
list_del(tmp);
+ tmp->next = NULL;
+ tmp->prev = NULL;
spin_unlock_irq(&timeout_lock);
ep = list_entry(tmp, struct c4iw_ep, entry);
process_timeout(ep);
@@ -3502,6 +3755,7 @@ static void process_work(struct work_struct *work)
unsigned int opcode;
int ret;
+ process_timedout_eps();
while ((skb = skb_dequeue(&rxq))) {
rpl = cplhdr(skb);
dev = *((struct c4iw_dev **) (skb->cb + sizeof(void *)));
@@ -3511,8 +3765,8 @@ static void process_work(struct work_struct *work)
ret = work_handlers[opcode](dev, skb);
if (!ret)
kfree_skb(skb);
+ process_timedout_eps();
}
- process_timedout_eps();
}
static DECLARE_WORK(skb_work, process_work);
@@ -3524,8 +3778,13 @@ static void ep_timeout(unsigned long arg)
spin_lock(&timeout_lock);
if (!test_and_set_bit(TIMEOUT, &ep->com.flags)) {
- list_add_tail(&ep->entry, &timeout_list);
- kickit = 1;
+ /*
+ * Only insert if it is not already on the list.
+ */
+ if (!ep->entry.next) {
+ list_add_tail(&ep->entry, &timeout_list);
+ kickit = 1;
+ }
}
spin_unlock(&timeout_lock);
if (kickit)
@@ -3607,7 +3866,7 @@ static int peer_abort_intr(struct c4iw_dev *dev, struct sk_buff *skb)
kfree_skb(skb);
return 0;
}
- if (is_neg_adv_abort(req->status)) {
+ if (is_neg_adv(req->status)) {
PDBG("%s neg_adv_abort ep %p tid %u\n", __func__, ep,
ep->hwtid);
kfree_skb(skb);
@@ -3666,7 +3925,7 @@ int __init c4iw_cm_init(void)
return 0;
}
-void __exit c4iw_cm_term(void)
+void c4iw_cm_term(void)
{
WARN_ON(!list_empty(&timeout_list));
flush_workqueue(workq);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-04 01:24:54 +0000