summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/hw/cxgb4
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband/hw/cxgb4')
-rw-r--r--drivers/infiniband/hw/cxgb4/Kconfig6
-rw-r--r--drivers/infiniband/hw/cxgb4/cm.c242
-rw-r--r--drivers/infiniband/hw/cxgb4/cq.c55
-rw-r--r--drivers/infiniband/hw/cxgb4/device.c220
-rw-r--r--drivers/infiniband/hw/cxgb4/iw_cxgb4.h14
-rw-r--r--drivers/infiniband/hw/cxgb4/mem.c61
-rw-r--r--drivers/infiniband/hw/cxgb4/provider.c47
-rw-r--r--drivers/infiniband/hw/cxgb4/qp.c217
-rw-r--r--drivers/infiniband/hw/cxgb4/resource.c10
-rw-r--r--drivers/infiniband/hw/cxgb4/t4.h78
-rw-r--r--drivers/infiniband/hw/cxgb4/t4fw_ri_api.h14
-rw-r--r--drivers/infiniband/hw/cxgb4/user.h5
12 files changed, 638 insertions, 331 deletions
diff --git a/drivers/infiniband/hw/cxgb4/Kconfig b/drivers/infiniband/hw/cxgb4/Kconfig
index d4e8983fba53..23f38cf2c5cd 100644
--- a/drivers/infiniband/hw/cxgb4/Kconfig
+++ b/drivers/infiniband/hw/cxgb4/Kconfig
@@ -1,10 +1,10 @@
config INFINIBAND_CXGB4
- tristate "Chelsio T4 RDMA Driver"
+ tristate "Chelsio T4/T5 RDMA Driver"
depends on CHELSIO_T4 && INET && (IPV6 || IPV6=n)
select GENERIC_ALLOCATOR
---help---
- This is an iWARP/RDMA driver for the Chelsio T4 1GbE and
- 10GbE adapters.
+ This is an iWARP/RDMA driver for the Chelsio T4 and T5
+ 1GbE, 10GbE adapters and T5 40GbE adapter.
For general information about Chelsio and our products, visit
our website at <http://www.chelsio.com>.
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index d286bdebe2ab..1f863a96a480 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -98,9 +98,9 @@ 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 +173,15 @@ static void start_ep_timer(struct c4iw_ep *ep)
add_timer(&ep->timer);
}
-static void stop_ep_timer(struct c4iw_ep *ep)
+static int stop_ep_timer(struct c4iw_ep *ep)
{
PDBG("%s ep %p stopping\n", __func__, ep);
del_timer_sync(&ep->timer);
- if (!test_and_set_bit(TIMEOUT, &ep->com.flags))
+ if (!test_and_set_bit(TIMEOUT, &ep->com.flags)) {
c4iw_put_ep(&ep->com);
+ return 0;
+ }
+ return 1;
}
static int c4iw_l2t_send(struct c4iw_rdev *rdev, struct sk_buff *skb,
@@ -400,7 +403,8 @@ 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;
}
@@ -583,6 +587,10 @@ static int send_connect(struct c4iw_ep *ep)
opt2 |= SACK_EN(1);
if (wscale && enable_tcp_window_scaling)
opt2 |= WND_SCALE_EN(1);
+ 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, NULL, act_open_req_arp_failure);
if (is_t4(ep->com.dev->rdev.lldi.adapter_type)) {
@@ -759,8 +767,9 @@ 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;
}
@@ -840,6 +849,7 @@ 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);
}
@@ -923,7 +933,8 @@ 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);
}
@@ -940,6 +951,7 @@ 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 */
@@ -963,17 +975,18 @@ 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);
@@ -987,8 +1000,7 @@ 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);
}
@@ -1066,9 +1078,10 @@ 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));
@@ -1093,15 +1106,14 @@ 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)
@@ -1146,7 +1158,7 @@ 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;
@@ -1156,17 +1168,17 @@ 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
@@ -1188,7 +1200,7 @@ 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. */
@@ -1228,7 +1240,7 @@ 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;
@@ -1240,7 +1252,7 @@ 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;
@@ -1330,9 +1342,11 @@ 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;
}
@@ -1348,18 +1362,20 @@ 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)
@@ -1370,15 +1386,12 @@ 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;
}
@@ -1400,7 +1413,6 @@ 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;
/*
@@ -1409,13 +1421,13 @@ 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;
}
@@ -1426,7 +1438,7 @@ 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;
}
@@ -1435,7 +1447,7 @@ 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;
}
@@ -1492,10 +1504,24 @@ 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;
}
@@ -1507,19 +1533,23 @@ 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;
@@ -1532,15 +1562,19 @@ 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;
}
@@ -1647,6 +1681,15 @@ 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;
+}
+
#define ACT_OPEN_RETRY_COUNT 2
static int import_ep(struct c4iw_ep *ep, int iptype, __u8 *peer_ip,
@@ -1835,7 +1878,7 @@ static int act_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
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;
@@ -1979,6 +2022,10 @@ 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)) {
+ opt2 |= T5_OPT_2_VALID;
+ opt2 |= V_CONG_CNTRL(CONG_ALG_TAHOE);
+ }
rpl = cplhdr(skb);
INIT_TP_WR(rpl, ep->hwtid);
@@ -2240,13 +2287,13 @@ 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;
@@ -2265,15 +2312,6 @@ 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);
@@ -2287,7 +2325,7 @@ 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;
@@ -2309,10 +2347,10 @@ 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 {
@@ -2417,7 +2455,7 @@ 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,
@@ -2425,7 +2463,7 @@ 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;
@@ -2500,22 +2538,28 @@ 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;
}
@@ -2530,12 +2574,14 @@ 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);
@@ -2604,14 +2650,16 @@ 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;
}
@@ -2980,7 +3028,7 @@ 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) {
@@ -3002,7 +3050,7 @@ 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;
@@ -3022,7 +3070,7 @@ 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);
@@ -3203,6 +3251,7 @@ 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));
@@ -3239,7 +3288,13 @@ 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);
+ }
}
/*
@@ -3346,13 +3401,13 @@ 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__);
goto free_dst;
}
- neigh_release(neigh);
step = dev->rdev.lldi.nrxq / dev->rdev.lldi.nchan;
rss_qid = dev->rdev.lldi.rxq_ids[pi->port_id * step];
window = (__force u16) htons((__force u16)tcph->window);
@@ -3427,15 +3482,26 @@ 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);
}
@@ -3449,6 +3515,8 @@ 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);
@@ -3465,6 +3533,7 @@ 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 *)));
@@ -3474,8 +3543,8 @@ 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);
@@ -3487,8 +3556,13 @@ 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)
@@ -3570,7 +3644,7 @@ 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);
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index 88de3aa9c5b0..cfaa56ada189 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -235,27 +235,21 @@ int c4iw_flush_sq(struct c4iw_qp *qhp)
struct t4_cq *cq = &chp->cq;
int idx;
struct t4_swsqe *swsqe;
- int error = (qhp->attr.state != C4IW_QP_STATE_CLOSING &&
- qhp->attr.state != C4IW_QP_STATE_IDLE);
if (wq->sq.flush_cidx == -1)
wq->sq.flush_cidx = wq->sq.cidx;
idx = wq->sq.flush_cidx;
BUG_ON(idx >= wq->sq.size);
while (idx != wq->sq.pidx) {
- if (error) {
- swsqe = &wq->sq.sw_sq[idx];
- BUG_ON(swsqe->flushed);
- swsqe->flushed = 1;
- insert_sq_cqe(wq, cq, swsqe);
- if (wq->sq.oldest_read == swsqe) {
- BUG_ON(swsqe->opcode != FW_RI_READ_REQ);
- advance_oldest_read(wq);
- }
- flushed++;
- } else {
- t4_sq_consume(wq);
+ swsqe = &wq->sq.sw_sq[idx];
+ BUG_ON(swsqe->flushed);
+ swsqe->flushed = 1;
+ insert_sq_cqe(wq, cq, swsqe);
+ if (wq->sq.oldest_read == swsqe) {
+ BUG_ON(swsqe->opcode != FW_RI_READ_REQ);
+ advance_oldest_read(wq);
}
+ flushed++;
if (++idx == wq->sq.size)
idx = 0;
}
@@ -365,8 +359,14 @@ void c4iw_flush_hw_cq(struct c4iw_cq *chp)
if (CQE_OPCODE(hw_cqe) == FW_RI_READ_RESP) {
- /*
- * drop peer2peer RTR reads.
+ /* If we have reached here because of async
+ * event or other error, and have egress error
+ * then drop
+ */
+ if (CQE_TYPE(hw_cqe) == 1)
+ goto next_cqe;
+
+ /* drop peer2peer RTR reads.
*/
if (CQE_WRID_STAG(hw_cqe) == 1)
goto next_cqe;
@@ -511,8 +511,18 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe,
*/
if (RQ_TYPE(hw_cqe) && (CQE_OPCODE(hw_cqe) == FW_RI_READ_RESP)) {
- /*
- * If this is an unsolicited read response, then the read
+ /* If we have reached here because of async
+ * event or other error, and have egress error
+ * then drop
+ */
+ if (CQE_TYPE(hw_cqe) == 1) {
+ if (CQE_STATUS(hw_cqe))
+ t4_set_wq_in_error(wq);
+ ret = -EAGAIN;
+ goto skip_cqe;
+ }
+
+ /* If this is an unsolicited read response, then the read
* was generated by the kernel driver as part of peer-2-peer
* connection setup. So ignore the completion.
*/
@@ -603,7 +613,7 @@ proc_cqe:
*/
if (SQ_TYPE(hw_cqe)) {
int idx = CQE_WRID_SQ_IDX(hw_cqe);
- BUG_ON(idx > wq->sq.size);
+ BUG_ON(idx >= wq->sq.size);
/*
* Account for any unsignaled completions completed by
@@ -617,7 +627,7 @@ proc_cqe:
wq->sq.in_use -= wq->sq.size + idx - wq->sq.cidx;
else
wq->sq.in_use -= idx - wq->sq.cidx;
- BUG_ON(wq->sq.in_use < 0 && wq->sq.in_use < wq->sq.size);
+ BUG_ON(wq->sq.in_use <= 0 && wq->sq.in_use >= wq->sq.size);
wq->sq.cidx = (uint16_t)idx;
PDBG("%s completing sq idx %u\n", __func__, wq->sq.cidx);
@@ -662,7 +672,7 @@ skip_cqe:
static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc)
{
struct c4iw_qp *qhp = NULL;
- struct t4_cqe cqe = {0, 0}, *rd_cqe;
+ struct t4_cqe uninitialized_var(cqe), *rd_cqe;
struct t4_wq *wq;
u32 credit = 0;
u8 cqe_flushed;
@@ -881,7 +891,7 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
/*
* Make actual HW queue 2x to avoid cdix_inc overflows.
*/
- hwentries = entries * 2;
+ hwentries = min(entries * 2, T4_MAX_IQ_SIZE);
/*
* Make HW queue at least 64 entries so GTS updates aren't too
@@ -930,6 +940,7 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
if (!mm2)
goto err4;
+ memset(&uresp, 0, sizeof(uresp));
uresp.qid_mask = rhp->rdev.cqmask;
uresp.cqid = chp->cq.cqid;
uresp.size = chp->cq.size;
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index 4a033853312e..f4fa50a609e2 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -64,6 +64,10 @@ struct uld_ctx {
static LIST_HEAD(uld_ctx_list);
static DEFINE_MUTEX(dev_mutex);
+#define DB_FC_RESUME_SIZE 64
+#define DB_FC_RESUME_DELAY 1
+#define DB_FC_DRAIN_THRESH 0
+
static struct dentry *c4iw_debugfs_root;
struct c4iw_debugfs_data {
@@ -282,7 +286,7 @@ static const struct file_operations stag_debugfs_fops = {
.llseek = default_llseek,
};
-static char *db_state_str[] = {"NORMAL", "FLOW_CONTROL", "RECOVERY"};
+static char *db_state_str[] = {"NORMAL", "FLOW_CONTROL", "RECOVERY", "STOPPED"};
static int stats_show(struct seq_file *seq, void *v)
{
@@ -311,9 +315,10 @@ static int stats_show(struct seq_file *seq, void *v)
seq_printf(seq, " DB FULL: %10llu\n", dev->rdev.stats.db_full);
seq_printf(seq, " DB EMPTY: %10llu\n", dev->rdev.stats.db_empty);
seq_printf(seq, " DB DROP: %10llu\n", dev->rdev.stats.db_drop);
- seq_printf(seq, " DB State: %s Transitions %llu\n",
+ seq_printf(seq, " DB State: %s Transitions %llu FC Interruptions %llu\n",
db_state_str[dev->db_state],
- dev->rdev.stats.db_state_transitions);
+ dev->rdev.stats.db_state_transitions,
+ dev->rdev.stats.db_fc_interruptions);
seq_printf(seq, "TCAM_FULL: %10llu\n", dev->rdev.stats.tcam_full);
seq_printf(seq, "ACT_OFLD_CONN_FAILS: %10llu\n",
dev->rdev.stats.act_ofld_conn_fails);
@@ -643,6 +648,12 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
printk(KERN_ERR MOD "error %d initializing ocqp pool\n", err);
goto err4;
}
+ rdev->status_page = (struct t4_dev_status_page *)
+ __get_free_page(GFP_KERNEL);
+ if (!rdev->status_page) {
+ pr_err(MOD "error allocating status page\n");
+ goto err4;
+ }
return 0;
err4:
c4iw_rqtpool_destroy(rdev);
@@ -656,6 +667,7 @@ err1:
static void c4iw_rdev_close(struct c4iw_rdev *rdev)
{
+ free_page((unsigned long)rdev->status_page);
c4iw_pblpool_destroy(rdev);
c4iw_rqtpool_destroy(rdev);
c4iw_destroy_resource(&rdev->resource);
@@ -670,7 +682,10 @@ static void c4iw_dealloc(struct uld_ctx *ctx)
idr_destroy(&ctx->dev->hwtid_idr);
idr_destroy(&ctx->dev->stid_idr);
idr_destroy(&ctx->dev->atid_idr);
- iounmap(ctx->dev->rdev.oc_mw_kva);
+ if (ctx->dev->rdev.bar2_kva)
+ iounmap(ctx->dev->rdev.bar2_kva);
+ if (ctx->dev->rdev.oc_mw_kva)
+ iounmap(ctx->dev->rdev.oc_mw_kva);
ib_dealloc_device(&ctx->dev->ibdev);
ctx->dev = NULL;
}
@@ -703,18 +718,6 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop)
pr_info("%s: On-Chip Queues not supported on this device.\n",
pci_name(infop->pdev));
- if (!is_t4(infop->adapter_type)) {
- if (!allow_db_fc_on_t5) {
- db_fc_threshold = 100000;
- pr_info("DB Flow Control Disabled.\n");
- }
-
- if (!allow_db_coalescing_on_t5) {
- db_coalescing_threshold = -1;
- pr_info("DB Coalescing Disabled.\n");
- }
- }
-
devp = (struct c4iw_dev *)ib_alloc_device(sizeof(*devp));
if (!devp) {
printk(KERN_ERR MOD "Cannot allocate ib device\n");
@@ -722,11 +725,31 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop)
}
devp->rdev.lldi = *infop;
- devp->rdev.oc_mw_pa = pci_resource_start(devp->rdev.lldi.pdev, 2) +
- (pci_resource_len(devp->rdev.lldi.pdev, 2) -
- roundup_pow_of_two(devp->rdev.lldi.vr->ocq.size));
- devp->rdev.oc_mw_kva = ioremap_wc(devp->rdev.oc_mw_pa,
- devp->rdev.lldi.vr->ocq.size);
+ /*
+ * For T5 devices, we map all of BAR2 with WC.
+ * For T4 devices with onchip qp mem, we map only that part
+ * of BAR2 with WC.
+ */
+ devp->rdev.bar2_pa = pci_resource_start(devp->rdev.lldi.pdev, 2);
+ if (is_t5(devp->rdev.lldi.adapter_type)) {
+ devp->rdev.bar2_kva = ioremap_wc(devp->rdev.bar2_pa,
+ pci_resource_len(devp->rdev.lldi.pdev, 2));
+ if (!devp->rdev.bar2_kva) {
+ pr_err(MOD "Unable to ioremap BAR2\n");
+ return ERR_PTR(-EINVAL);
+ }
+ } else if (ocqp_supported(infop)) {
+ devp->rdev.oc_mw_pa =
+ pci_resource_start(devp->rdev.lldi.pdev, 2) +
+ pci_resource_len(devp->rdev.lldi.pdev, 2) -
+ roundup_pow_of_two(devp->rdev.lldi.vr->ocq.size);
+ devp->rdev.oc_mw_kva = ioremap_wc(devp->rdev.oc_mw_pa,
+ devp->rdev.lldi.vr->ocq.size);
+ if (!devp->rdev.oc_mw_kva) {
+ pr_err(MOD "Unable to ioremap onchip mem\n");
+ return ERR_PTR(-EINVAL);
+ }
+ }
PDBG(KERN_INFO MOD "ocq memory: "
"hw_start 0x%x size %u mw_pa 0x%lx mw_kva %p\n",
@@ -749,6 +772,7 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop)
spin_lock_init(&devp->lock);
mutex_init(&devp->rdev.stats.lock);
mutex_init(&devp->db_mutex);
+ INIT_LIST_HEAD(&devp->db_fc_list);
if (c4iw_debugfs_root) {
devp->debugfs_root = debugfs_create_dir(
@@ -897,11 +921,13 @@ static int c4iw_uld_rx_handler(void *handle, const __be64 *rsp,
}
opcode = *(u8 *)rsp;
- if (c4iw_handlers[opcode])
+ if (c4iw_handlers[opcode]) {
c4iw_handlers[opcode](dev, skb);
- else
+ } else {
pr_info("%s no handler opcode 0x%x...\n", __func__,
opcode);
+ kfree_skb(skb);
+ }
return 0;
nomem:
@@ -977,13 +1003,16 @@ static int disable_qp_db(int id, void *p, void *data)
static void stop_queues(struct uld_ctx *ctx)
{
- spin_lock_irq(&ctx->dev->lock);
- if (ctx->dev->db_state == NORMAL) {
- ctx->dev->rdev.stats.db_state_transitions++;
- ctx->dev->db_state = FLOW_CONTROL;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ctx->dev->lock, flags);
+ ctx->dev->rdev.stats.db_state_transitions++;
+ ctx->dev->db_state = STOPPED;
+ if (ctx->dev->rdev.flags & T4_STATUS_PAGE_DISABLED)
idr_for_each(&ctx->dev->qpidr, disable_qp_db, NULL);
- }
- spin_unlock_irq(&ctx->dev->lock);
+ else
+ ctx->dev->rdev.status_page->db_off = 1;
+ spin_unlock_irqrestore(&ctx->dev->lock, flags);
}
static int enable_qp_db(int id, void *p, void *data)
@@ -994,15 +1023,72 @@ static int enable_qp_db(int id, void *p, void *data)
return 0;
}
+static void resume_rc_qp(struct c4iw_qp *qp)
+{
+ spin_lock(&qp->lock);
+ t4_ring_sq_db(&qp->wq, qp->wq.sq.wq_pidx_inc,
+ is_t5(qp->rhp->rdev.lldi.adapter_type), NULL);
+ qp->wq.sq.wq_pidx_inc = 0;
+ t4_ring_rq_db(&qp->wq, qp->wq.rq.wq_pidx_inc,
+ is_t5(qp->rhp->rdev.lldi.adapter_type), NULL);
+ qp->wq.rq.wq_pidx_inc = 0;
+ spin_unlock(&qp->lock);
+}
+
+static void resume_a_chunk(struct uld_ctx *ctx)
+{
+ int i;
+ struct c4iw_qp *qp;
+
+ for (i = 0; i < DB_FC_RESUME_SIZE; i++) {
+ qp = list_first_entry(&ctx->dev->db_fc_list, struct c4iw_qp,
+ db_fc_entry);
+ list_del_init(&qp->db_fc_entry);
+ resume_rc_qp(qp);
+ if (list_empty(&ctx->dev->db_fc_list))
+ break;
+ }
+}
+
static void resume_queues(struct uld_ctx *ctx)
{
spin_lock_irq(&ctx->dev->lock);
- if (ctx->dev->qpcnt <= db_fc_threshold &&
- ctx->dev->db_state == FLOW_CONTROL) {
- ctx->dev->db_state = NORMAL;
- ctx->dev->rdev.stats.db_state_transitions++;
- idr_for_each(&ctx->dev->qpidr, enable_qp_db, NULL);
+ if (ctx->dev->db_state != STOPPED)
+ goto out;
+ ctx->dev->db_state = FLOW_CONTROL;
+ while (1) {
+ if (list_empty(&ctx->dev->db_fc_list)) {
+ WARN_ON(ctx->dev->db_state != FLOW_CONTROL);
+ ctx->dev->db_state = NORMAL;
+ ctx->dev->rdev.stats.db_state_transitions++;
+ if (ctx->dev->rdev.flags & T4_STATUS_PAGE_DISABLED) {
+ idr_for_each(&ctx->dev->qpidr, enable_qp_db,
+ NULL);
+ } else {
+ ctx->dev->rdev.status_page->db_off = 0;
+ }
+ break;
+ } else {
+ if (cxgb4_dbfifo_count(ctx->dev->rdev.lldi.ports[0], 1)
+ < (ctx->dev->rdev.lldi.dbfifo_int_thresh <<
+ DB_FC_DRAIN_THRESH)) {
+ resume_a_chunk(ctx);
+ }
+ if (!list_empty(&ctx->dev->db_fc_list)) {
+ spin_unlock_irq(&ctx->dev->lock);
+ if (DB_FC_RESUME_DELAY) {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ schedule_timeout(DB_FC_RESUME_DELAY);
+ }
+ spin_lock_irq(&ctx->dev->lock);
+ if (ctx->dev->db_state != FLOW_CONTROL)
+ break;
+ }
+ }
}
+out:
+ if (ctx->dev->db_state != NORMAL)
+ ctx->dev->rdev.stats.db_fc_interruptions++;
spin_unlock_irq(&ctx->dev->lock);
}
@@ -1028,12 +1114,12 @@ static int count_qps(int id, void *p, void *data)
return 0;
}
-static void deref_qps(struct qp_list qp_list)
+static void deref_qps(struct qp_list *qp_list)
{
int idx;
- for (idx = 0; idx < qp_list.idx; idx++)
- c4iw_qp_rem_ref(&qp_list.qps[idx]->ibqp);
+ for (idx = 0; idx < qp_list->idx; idx++)
+ c4iw_qp_rem_ref(&qp_list->qps[idx]->ibqp);
}
static void recover_lost_dbs(struct uld_ctx *ctx, struct qp_list *qp_list)
@@ -1044,17 +1130,22 @@ static void recover_lost_dbs(struct uld_ctx *ctx, struct qp_list *qp_list)
for (idx = 0; idx < qp_list->idx; idx++) {
struct c4iw_qp *qp = qp_list->qps[idx];
+ spin_lock_irq(&qp->rhp->lock);
+ spin_lock(&qp->lock);
ret = cxgb4_sync_txq_pidx(qp->rhp->rdev.lldi.ports[0],
qp->wq.sq.qid,
t4_sq_host_wq_pidx(&qp->wq),
t4_sq_wq_size(&qp->wq));
if (ret) {
- printk(KERN_ERR MOD "%s: Fatal error - "
+ pr_err(KERN_ERR MOD "%s: Fatal error - "
"DB overflow recovery failed - "
"error syncing SQ qid %u\n",
pci_name(ctx->lldi.pdev), qp->wq.sq.qid);
+ spin_unlock(&qp->lock);
+ spin_unlock_irq(&qp->rhp->lock);
return;
}
+ qp->wq.sq.wq_pidx_inc = 0;
ret = cxgb4_sync_txq_pidx(qp->rhp->rdev.lldi.ports[0],
qp->wq.rq.qid,
@@ -1062,12 +1153,17 @@ static void recover_lost_dbs(struct uld_ctx *ctx, struct qp_list *qp_list)
t4_rq_wq_size(&qp->wq));
if (ret) {
- printk(KERN_ERR MOD "%s: Fatal error - "
+ pr_err(KERN_ERR MOD "%s: Fatal error - "
"DB overflow recovery failed - "
"error syncing RQ qid %u\n",
pci_name(ctx->lldi.pdev), qp->wq.rq.qid);
+ spin_unlock(&qp->lock);
+ spin_unlock_irq(&qp->rhp->lock);
return;
}
+ qp->wq.rq.wq_pidx_inc = 0;
+ spin_unlock(&qp->lock);
+ spin_unlock_irq(&qp->rhp->lock);
/* Wait for the dbfifo to drain */
while (cxgb4_dbfifo_count(qp->rhp->rdev.lldi.ports[0], 1) > 0) {
@@ -1083,36 +1179,22 @@ static void recover_queues(struct uld_ctx *ctx)
struct qp_list qp_list;
int ret;
- /* lock out kernel db ringers */
- mutex_lock(&ctx->dev->db_mutex);
-
- /* put all queues in to recovery mode */
- spin_lock_irq(&ctx->dev->lock);
- ctx->dev->db_state = RECOVERY;
- ctx->dev->rdev.stats.db_state_transitions++;
- idr_for_each(&ctx->dev->qpidr, disable_qp_db, NULL);
- spin_unlock_irq(&ctx->dev->lock);
-
/* slow everybody down */
set_current_state(TASK_UNINTERRUPTIBLE);
schedule_timeout(usecs_to_jiffies(1000));
- /* Wait for the dbfifo to completely drain. */
- while (cxgb4_dbfifo_count(ctx->dev->rdev.lldi.ports[0], 1) > 0) {
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(usecs_to_jiffies(10));
- }
-
/* flush the SGE contexts */
ret = cxgb4_flush_eq_cache(ctx->dev->rdev.lldi.ports[0]);
if (ret) {
printk(KERN_ERR MOD "%s: Fatal error - DB overflow recovery failed\n",
pci_name(ctx->lldi.pdev));
- goto out;
+ return;
}
/* Count active queues so we can build a list of queues to recover */
spin_lock_irq(&ctx->dev->lock);
+ WARN_ON(ctx->dev->db_state != STOPPED);
+ ctx->dev->db_state = RECOVERY;
idr_for_each(&ctx->dev->qpidr, count_qps, &count);
qp_list.qps = kzalloc(count * sizeof *qp_list.qps, GFP_ATOMIC);
@@ -1120,7 +1202,7 @@ static void recover_queues(struct uld_ctx *ctx)
printk(KERN_ERR MOD "%s: Fatal error - DB overflow recovery failed\n",
pci_name(ctx->lldi.pdev));
spin_unlock_irq(&ctx->dev->lock);
- goto out;
+ return;
}
qp_list.idx = 0;
@@ -1133,29 +1215,13 @@ static void recover_queues(struct uld_ctx *ctx)
recover_lost_dbs(ctx, &qp_list);
/* we're almost done! deref the qps and clean up */
- deref_qps(qp_list);
+ deref_qps(&qp_list);
kfree(qp_list.qps);
- /* Wait for the dbfifo to completely drain again */
- while (cxgb4_dbfifo_count(ctx->dev->rdev.lldi.ports[0], 1) > 0) {
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(usecs_to_jiffies(10));
- }
-
- /* resume the queues */
spin_lock_irq(&ctx->dev->lock);
- if (ctx->dev->qpcnt > db_fc_threshold)
- ctx->dev->db_state = FLOW_CONTROL;
- else {
- ctx->dev->db_state = NORMAL;
- idr_for_each(&ctx->dev->qpidr, enable_qp_db, NULL);
- }
- ctx->dev->rdev.stats.db_state_transitions++;
+ WARN_ON(ctx->dev->db_state != RECOVERY);
+ ctx->dev->db_state = STOPPED;
spin_unlock_irq(&ctx->dev->lock);
-
-out:
- /* start up kernel db ringers again */
- mutex_unlock(&ctx->dev->db_mutex);
}
static int c4iw_uld_control(void *handle, enum cxgb4_control control, ...)
@@ -1165,9 +1231,7 @@ static int c4iw_uld_control(void *handle, enum cxgb4_control control, ...)
switch (control) {
case CXGB4_CONTROL_DB_FULL:
stop_queues(ctx);
- mutex_lock(&ctx->dev->rdev.stats.lock);
ctx->dev->rdev.stats.db_full++;
- mutex_unlock(&ctx->dev->rdev.stats.lock);
break;
case CXGB4_CONTROL_DB_EMPTY:
resume_queues(ctx);
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 23eaeabab93b..7474b490760a 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -109,6 +109,7 @@ struct c4iw_dev_ucontext {
enum c4iw_rdev_flags {
T4_FATAL_ERROR = (1<<0),
+ T4_STATUS_PAGE_DISABLED = (1<<1),
};
struct c4iw_stat {
@@ -130,6 +131,7 @@ struct c4iw_stats {
u64 db_empty;
u64 db_drop;
u64 db_state_transitions;
+ u64 db_fc_interruptions;
u64 tcam_full;
u64 act_ofld_conn_fails;
u64 pas_ofld_conn_fails;
@@ -147,9 +149,12 @@ struct c4iw_rdev {
struct gen_pool *ocqp_pool;
u32 flags;
struct cxgb4_lld_info lldi;
+ unsigned long bar2_pa;
+ void __iomem *bar2_kva;
unsigned long oc_mw_pa;
void __iomem *oc_mw_kva;
struct c4iw_stats stats;
+ struct t4_dev_status_page *status_page;
};
static inline int c4iw_fatal_error(struct c4iw_rdev *rdev)
@@ -211,7 +216,8 @@ static inline int c4iw_wait_for_reply(struct c4iw_rdev *rdev,
enum db_state {
NORMAL = 0,
FLOW_CONTROL = 1,
- RECOVERY = 2
+ RECOVERY = 2,
+ STOPPED = 3
};
struct c4iw_dev {
@@ -225,10 +231,10 @@ struct c4iw_dev {
struct mutex db_mutex;
struct dentry *debugfs_root;
enum db_state db_state;
- int qpcnt;
struct idr hwtid_idr;
struct idr atid_idr;
struct idr stid_idr;
+ struct list_head db_fc_list;
};
static inline struct c4iw_dev *to_c4iw_dev(struct ib_device *ibdev)
@@ -369,6 +375,7 @@ struct c4iw_fr_page_list {
DEFINE_DMA_UNMAP_ADDR(mapping);
dma_addr_t dma_addr;
struct c4iw_dev *dev;
+ int pll_len;
};
static inline struct c4iw_fr_page_list *to_c4iw_fr_page_list(
@@ -428,10 +435,12 @@ struct c4iw_qp_attributes {
u8 ecode;
u16 sq_db_inc;
u16 rq_db_inc;
+ u8 send_term;
};
struct c4iw_qp {
struct ib_qp ibqp;
+ struct list_head db_fc_entry;
struct c4iw_dev *rhp;
struct c4iw_ep *ep;
struct c4iw_qp_attributes attr;
@@ -441,6 +450,7 @@ struct c4iw_qp {
atomic_t refcnt;
wait_queue_head_t wait;
struct timer_list timer;
+ int sq_sig_all;
};
static inline struct c4iw_qp *to_c4iw_qp(struct ib_qp *ibqp)
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 41b11951a30a..ec7a2988a703 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -37,9 +37,9 @@
#include "iw_cxgb4.h"
-int use_dsgl = 1;
+int use_dsgl = 0;
module_param(use_dsgl, int, 0644);
-MODULE_PARM_DESC(use_dsgl, "Use DSGL for PBL/FastReg (default=1)");
+MODULE_PARM_DESC(use_dsgl, "Use DSGL for PBL/FastReg (default=0)");
#define T4_ULPTX_MIN_IO 32
#define C4IW_MAX_INLINE_SIZE 96
@@ -259,8 +259,12 @@ static int write_tpt_entry(struct c4iw_rdev *rdev, u32 reset_tpt_entry,
if ((!reset_tpt_entry) && (*stag == T4_STAG_UNSET)) {
stag_idx = c4iw_get_resource(&rdev->resource.tpt_table);
- if (!stag_idx)
+ if (!stag_idx) {
+ mutex_lock(&rdev->stats.lock);
+ rdev->stats.stag.fail++;
+ mutex_unlock(&rdev->stats.lock);
return -ENOMEM;
+ }
mutex_lock(&rdev->stats.lock);
rdev->stats.stag.cur += 32;
if (rdev->stats.stag.cur > rdev->stats.stag.max)
@@ -678,9 +682,9 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
{
__be64 *pages;
int shift, n, len;
- int i, j, k;
+ int i, k, entry;
int err = 0;
- struct ib_umem_chunk *chunk;
+ struct scatterlist *sg;
struct c4iw_dev *rhp;
struct c4iw_pd *php;
struct c4iw_mr *mhp;
@@ -710,10 +714,7 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
shift = ffs(mhp->umem->page_size) - 1;
- n = 0;
- list_for_each_entry(chunk, &mhp->umem->chunk_list, list)
- n += chunk->nents;
-
+ n = mhp->umem->nmap;
err = alloc_pbl(mhp, n);
if (err)
goto err;
@@ -726,24 +727,22 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
i = n = 0;
- list_for_each_entry(chunk, &mhp->umem->chunk_list, list)
- for (j = 0; j < chunk->nmap; ++j) {
- len = sg_dma_len(&chunk->page_list[j]) >> shift;
- for (k = 0; k < len; ++k) {
- pages[i++] = cpu_to_be64(sg_dma_address(
- &chunk->page_list[j]) +
- mhp->umem->page_size * k);
- if (i == PAGE_SIZE / sizeof *pages) {
- err = write_pbl(&mhp->rhp->rdev,
- pages,
- mhp->attr.pbl_addr + (n << 3), i);
- if (err)
- goto pbl_done;
- n += i;
- i = 0;
- }
+ for_each_sg(mhp->umem->sg_head.sgl, sg, mhp->umem->nmap, entry) {
+ len = sg_dma_len(sg) >> shift;
+ for (k = 0; k < len; ++k) {
+ pages[i++] = cpu_to_be64(sg_dma_address(sg) +
+ mhp->umem->page_size * k);
+ if (i == PAGE_SIZE / sizeof *pages) {
+ err = write_pbl(&mhp->rhp->rdev,
+ pages,
+ mhp->attr.pbl_addr + (n << 3), i);
+ if (err)
+ goto pbl_done;
+ n += i;
+ i = 0;
}
}
+ }
if (i)
err = write_pbl(&mhp->rhp->rdev, pages,
@@ -903,7 +902,11 @@ struct ib_fast_reg_page_list *c4iw_alloc_fastreg_pbl(struct ib_device *device,
dma_unmap_addr_set(c4pl, mapping, dma_addr);
c4pl->dma_addr = dma_addr;
c4pl->dev = dev;
- c4pl->ibpl.max_page_list_len = pll_len;
+ c4pl->pll_len = pll_len;
+
+ PDBG("%s c4pl %p pll_len %u page_list %p dma_addr %pad\n",
+ __func__, c4pl, c4pl->pll_len, c4pl->ibpl.page_list,
+ &c4pl->dma_addr);
return &c4pl->ibpl;
}
@@ -912,8 +915,12 @@ void c4iw_free_fastreg_pbl(struct ib_fast_reg_page_list *ibpl)
{
struct c4iw_fr_page_list *c4pl = to_c4iw_fr_page_list(ibpl);
+ PDBG("%s c4pl %p pll_len %u page_list %p dma_addr %pad\n",
+ __func__, c4pl, c4pl->pll_len, c4pl->ibpl.page_list,
+ &c4pl->dma_addr);
+
dma_free_coherent(&c4pl->dev->rdev.lldi.pdev->dev,
- c4pl->ibpl.max_page_list_len,
+ c4pl->pll_len,
c4pl->ibpl.page_list, dma_unmap_addr(c4pl, mapping));
kfree(c4pl);
}
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 7e94c9a656a1..a94a3e12c349 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -106,15 +106,56 @@ static struct ib_ucontext *c4iw_alloc_ucontext(struct ib_device *ibdev,
{
struct c4iw_ucontext *context;
struct c4iw_dev *rhp = to_c4iw_dev(ibdev);
+ static int warned;
+ struct c4iw_alloc_ucontext_resp uresp;
+ int ret = 0;
+ struct c4iw_mm_entry *mm = NULL;
PDBG("%s ibdev %p\n", __func__, ibdev);
context = kzalloc(sizeof(*context), GFP_KERNEL);
- if (!context)
- return ERR_PTR(-ENOMEM);
+ if (!context) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
c4iw_init_dev_ucontext(&rhp->rdev, &context->uctx);
INIT_LIST_HEAD(&context->mmaps);
spin_lock_init(&context->mmap_lock);
+
+ if (udata->outlen < sizeof(uresp)) {
+ if (!warned++)
+ pr_err(MOD "Warning - downlevel libcxgb4 (non-fatal), device status page disabled.");
+ rhp->rdev.flags |= T4_STATUS_PAGE_DISABLED;
+ } else {
+ mm = kmalloc(sizeof(*mm), GFP_KERNEL);
+ if (!mm) {
+ ret = -ENOMEM;
+ goto err_free;
+ }
+
+ uresp.status_page_size = PAGE_SIZE;
+
+ spin_lock(&context->mmap_lock);
+ uresp.status_page_key = context->key;
+ context->key += PAGE_SIZE;
+ spin_unlock(&context->mmap_lock);
+
+ ret = ib_copy_to_udata(udata, &uresp, sizeof(uresp));
+ if (ret)
+ goto err_mm;
+
+ mm->key = uresp.status_page_key;
+ mm->addr = virt_to_phys(rhp->rdev.status_page);
+ mm->len = PAGE_SIZE;
+ insert_mmap(context, mm);
+ }
return &context->ibucontext;
+err_mm:
+ kfree(mm);
+err_free:
+ kfree(context);
+err:
+ return ERR_PTR(ret);
}
static int c4iw_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
@@ -287,7 +328,7 @@ static int c4iw_query_device(struct ib_device *ibdev,
props->max_mr = c4iw_num_stags(&dev->rdev);
props->max_pd = T4_MAX_NUM_PD;
props->local_ca_ack_delay = 0;
- props->max_fast_reg_page_list_len = T4_MAX_FR_DEPTH;
+ props->max_fast_reg_page_list_len = t4_max_fr_depth(use_dsgl);
return 0;
}
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 582936708e6e..086f62f5dc9e 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -212,13 +212,23 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
wq->db = rdev->lldi.db_reg;
wq->gts = rdev->lldi.gts_reg;
- if (user) {
- wq->sq.udb = (u64)pci_resource_start(rdev->lldi.pdev, 2) +
- (wq->sq.qid << rdev->qpshift);
- wq->sq.udb &= PAGE_MASK;
- wq->rq.udb = (u64)pci_resource_start(rdev->lldi.pdev, 2) +
- (wq->rq.qid << rdev->qpshift);
- wq->rq.udb &= PAGE_MASK;
+ if (user || is_t5(rdev->lldi.adapter_type)) {
+ u32 off;
+
+ off = (wq->sq.qid << rdev->qpshift) & PAGE_MASK;
+ if (user) {
+ wq->sq.udb = (u64 __iomem *)(rdev->bar2_pa + off);
+ } else {
+ off += 128 * (wq->sq.qid & rdev->qpmask) + 8;
+ wq->sq.udb = (u64 __iomem *)(rdev->bar2_kva + off);
+ }
+ off = (wq->rq.qid << rdev->qpshift) & PAGE_MASK;
+ if (user) {
+ wq->rq.udb = (u64 __iomem *)(rdev->bar2_pa + off);
+ } else {
+ off += 128 * (wq->rq.qid & rdev->qpmask) + 8;
+ wq->rq.udb = (u64 __iomem *)(rdev->bar2_kva + off);
+ }
}
wq->rdev = rdev;
wq->rq.msn = 1;
@@ -299,9 +309,10 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
if (ret)
goto free_dma;
- PDBG("%s sqid 0x%x rqid 0x%x kdb 0x%p squdb 0x%llx rqudb 0x%llx\n",
+ PDBG("%s sqid 0x%x rqid 0x%x kdb 0x%p squdb 0x%lx rqudb 0x%lx\n",
__func__, wq->sq.qid, wq->rq.qid, wq->db,
- (unsigned long long)wq->sq.udb, (unsigned long long)wq->rq.udb);
+ (__force unsigned long) wq->sq.udb,
+ (__force unsigned long) wq->rq.udb);
return 0;
free_dma:
@@ -425,6 +436,8 @@ static int build_rdma_send(struct t4_sq *sq, union t4_wr *wqe,
default:
return -EINVAL;
}
+ wqe->send.r3 = 0;
+ wqe->send.r4 = 0;
plen = 0;
if (wr->num_sge) {
@@ -555,7 +568,8 @@ static int build_fastreg(struct t4_sq *sq, union t4_wr *wqe,
int pbllen = roundup(wr->wr.fast_reg.page_list_len * sizeof(u64), 32);
int rem;
- if (wr->wr.fast_reg.page_list_len > T4_MAX_FR_DEPTH)
+ if (wr->wr.fast_reg.page_list_len >
+ t4_max_fr_depth(use_dsgl))
return -EINVAL;
wqe->fr.qpbinde_to_dcacpu = 0;
@@ -638,6 +652,48 @@ void c4iw_qp_rem_ref(struct ib_qp *qp)
wake_up(&(to_c4iw_qp(qp)->wait));
}
+static void add_to_fc_list(struct list_head *head, struct list_head *entry)
+{
+ if (list_empty(entry))
+ list_add_tail(entry, head);
+}
+
+static int ring_kernel_sq_db(struct c4iw_qp *qhp, u16 inc)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&qhp->rhp->lock, flags);
+ spin_lock(&qhp->lock);
+ if (qhp->rhp->db_state == NORMAL)
+ t4_ring_sq_db(&qhp->wq, inc,
+ is_t5(qhp->rhp->rdev.lldi.adapter_type), NULL);
+ else {
+ add_to_fc_list(&qhp->rhp->db_fc_list, &qhp->db_fc_entry);
+ qhp->wq.sq.wq_pidx_inc += inc;
+ }
+ spin_unlock(&qhp->lock);
+ spin_unlock_irqrestore(&qhp->rhp->lock, flags);
+ return 0;
+}
+
+static int ring_kernel_rq_db(struct c4iw_qp *qhp, u16 inc)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&qhp->rhp->lock, flags);
+ spin_lock(&qhp->lock);
+ if (qhp->rhp->db_state == NORMAL)
+ t4_ring_rq_db(&qhp->wq, inc,
+ is_t5(qhp->rhp->rdev.lldi.adapter_type), NULL);
+ else {
+ add_to_fc_list(&qhp->rhp->db_fc_list, &qhp->db_fc_entry);
+ qhp->wq.rq.wq_pidx_inc += inc;
+ }
+ spin_unlock(&qhp->lock);
+ spin_unlock_irqrestore(&qhp->rhp->lock, flags);
+ return 0;
+}
+
int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
struct ib_send_wr **bad_wr)
{
@@ -646,7 +702,7 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
enum fw_wr_opcodes fw_opcode = 0;
enum fw_ri_wr_flags fw_flags;
struct c4iw_qp *qhp;
- union t4_wr *wqe;
+ union t4_wr *wqe = NULL;
u32 num_wrs;
struct t4_swsqe *swsqe;
unsigned long flag;
@@ -675,7 +731,7 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
fw_flags = 0;
if (wr->send_flags & IB_SEND_SOLICITED)
fw_flags |= FW_RI_SOLICITED_EVENT_FLAG;
- if (wr->send_flags & IB_SEND_SIGNALED)
+ if (wr->send_flags & IB_SEND_SIGNALED || qhp->sq_sig_all)
fw_flags |= FW_RI_COMPLETION_FLAG;
swsqe = &qhp->wq.sq.sw_sq[qhp->wq.sq.pidx];
switch (wr->opcode) {
@@ -736,7 +792,8 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
}
swsqe->idx = qhp->wq.sq.pidx;
swsqe->complete = 0;
- swsqe->signaled = (wr->send_flags & IB_SEND_SIGNALED);
+ swsqe->signaled = (wr->send_flags & IB_SEND_SIGNALED) ||
+ qhp->sq_sig_all;
swsqe->flushed = 0;
swsqe->wr_id = wr->wr_id;
@@ -750,9 +807,14 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
t4_sq_produce(&qhp->wq, len16);
idx += DIV_ROUND_UP(len16*16, T4_EQ_ENTRY_SIZE);
}
- if (t4_wq_db_enabled(&qhp->wq))
- t4_ring_sq_db(&qhp->wq, idx);
- spin_unlock_irqrestore(&qhp->lock, flag);
+ if (!qhp->rhp->rdev.status_page->db_off) {
+ t4_ring_sq_db(&qhp->wq, idx,
+ is_t5(qhp->rhp->rdev.lldi.adapter_type), wqe);
+ spin_unlock_irqrestore(&qhp->lock, flag);
+ } else {
+ spin_unlock_irqrestore(&qhp->lock, flag);
+ ring_kernel_sq_db(qhp, idx);
+ }
return err;
}
@@ -761,7 +823,7 @@ int c4iw_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr,
{
int err = 0;
struct c4iw_qp *qhp;
- union t4_recv_wr *wqe;
+ union t4_recv_wr *wqe = NULL;
u32 num_wrs;
u8 len16 = 0;
unsigned long flag;
@@ -812,9 +874,14 @@ int c4iw_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr,
wr = wr->next;
num_wrs--;
}
- if (t4_wq_db_enabled(&qhp->wq))
- t4_ring_rq_db(&qhp->wq, idx);
- spin_unlock_irqrestore(&qhp->lock, flag);
+ if (!qhp->rhp->rdev.status_page->db_off) {
+ t4_ring_rq_db(&qhp->wq, idx,
+ is_t5(qhp->rhp->rdev.lldi.adapter_type), wqe);
+ spin_unlock_irqrestore(&qhp->lock, flag);
+ } else {
+ spin_unlock_irqrestore(&qhp->lock, flag);
+ ring_kernel_rq_db(qhp, idx);
+ }
return err;
}
@@ -1200,35 +1267,6 @@ out:
return ret;
}
-/*
- * Called by the library when the qp has user dbs disabled due to
- * a DB_FULL condition. This function will single-thread all user
- * DB rings to avoid overflowing the hw db-fifo.
- */
-static int ring_kernel_db(struct c4iw_qp *qhp, u32 qid, u16 inc)
-{
- int delay = db_delay_usecs;
-
- mutex_lock(&qhp->rhp->db_mutex);
- do {
-
- /*
- * The interrupt threshold is dbfifo_int_thresh << 6. So
- * make sure we don't cross that and generate an interrupt.
- */
- if (cxgb4_dbfifo_count(qhp->rhp->rdev.lldi.ports[0], 1) <
- (qhp->rhp->rdev.lldi.dbfifo_int_thresh << 5)) {
- writel(QID(qid) | PIDX(inc), qhp->wq.db);
- break;
- }
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(usecs_to_jiffies(delay));
- delay = min(delay << 1, 2000);
- } while (1);
- mutex_unlock(&qhp->rhp->db_mutex);
- return 0;
-}
-
int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
enum c4iw_qp_attr_mask mask,
struct c4iw_qp_attributes *attrs,
@@ -1278,11 +1316,11 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
}
if (mask & C4IW_QP_ATTR_SQ_DB) {
- ret = ring_kernel_db(qhp, qhp->wq.sq.qid, attrs->sq_db_inc);
+ ret = ring_kernel_sq_db(qhp, attrs->sq_db_inc);
goto out;
}
if (mask & C4IW_QP_ATTR_RQ_DB) {
- ret = ring_kernel_db(qhp, qhp->wq.rq.qid, attrs->rq_db_inc);
+ ret = ring_kernel_rq_db(qhp, attrs->rq_db_inc);
goto out;
}
@@ -1332,6 +1370,7 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
switch (attrs->next_state) {
case C4IW_QP_STATE_CLOSING:
BUG_ON(atomic_read(&qhp->ep->com.kref.refcount) < 2);
+ t4_set_wq_in_error(&qhp->wq);
set_state(qhp, C4IW_QP_STATE_CLOSING);
ep = qhp->ep;
if (!internal) {
@@ -1339,30 +1378,30 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
disconnect = 1;
c4iw_get_ep(&qhp->ep->com);
}
- t4_set_wq_in_error(&qhp->wq);
ret = rdma_fini(rhp, qhp, ep);
if (ret)
goto err;
break;
case C4IW_QP_STATE_TERMINATE:
+ t4_set_wq_in_error(&qhp->wq);
set_state(qhp, C4IW_QP_STATE_TERMINATE);
qhp->attr.layer_etype = attrs->layer_etype;
qhp->attr.ecode = attrs->ecode;
- t4_set_wq_in_error(&qhp->wq);
ep = qhp->ep;
- disconnect = 1;
- if (!internal)
+ if (!internal) {
+ c4iw_get_ep(&qhp->ep->com);
terminate = 1;
- else {
+ disconnect = 1;
+ } else {
+ terminate = qhp->attr.send_term;
ret = rdma_fini(rhp, qhp, ep);
if (ret)
goto err;
}
- c4iw_get_ep(&qhp->ep->com);
break;
case C4IW_QP_STATE_ERROR:
- set_state(qhp, C4IW_QP_STATE_ERROR);
t4_set_wq_in_error(&qhp->wq);
+ set_state(qhp, C4IW_QP_STATE_ERROR);
if (!internal) {
abort = 1;
disconnect = 1;
@@ -1465,14 +1504,6 @@ out:
return ret;
}
-static int enable_qp_db(int id, void *p, void *data)
-{
- struct c4iw_qp *qp = p;
-
- t4_enable_wq_db(&qp->wq);
- return 0;
-}
-
int c4iw_destroy_qp(struct ib_qp *ib_qp)
{
struct c4iw_dev *rhp;
@@ -1490,22 +1521,15 @@ int c4iw_destroy_qp(struct ib_qp *ib_qp)
c4iw_modify_qp(rhp, qhp, C4IW_QP_ATTR_NEXT_STATE, &attrs, 0);
wait_event(qhp->wait, !qhp->ep);
- spin_lock_irq(&rhp->lock);
- remove_handle_nolock(rhp, &rhp->qpidr, qhp->wq.sq.qid);
- rhp->qpcnt--;
- BUG_ON(rhp->qpcnt < 0);
- if (rhp->qpcnt <= db_fc_threshold && rhp->db_state == FLOW_CONTROL) {
- rhp->rdev.stats.db_state_transitions++;
- rhp->db_state = NORMAL;
- idr_for_each(&rhp->qpidr, enable_qp_db, NULL);
- }
- if (db_coalescing_threshold >= 0)
- if (rhp->qpcnt <= db_coalescing_threshold)
- cxgb4_enable_db_coalescing(rhp->rdev.lldi.ports[0]);
- spin_unlock_irq(&rhp->lock);
+ remove_handle(rhp, &rhp->qpidr, qhp->wq.sq.qid);
atomic_dec(&qhp->refcnt);
wait_event(qhp->wait, !atomic_read(&qhp->refcnt));
+ spin_lock_irq(&rhp->lock);
+ if (!list_empty(&qhp->db_fc_entry))
+ list_del_init(&qhp->db_fc_entry);
+ spin_unlock_irq(&rhp->lock);
+
ucontext = ib_qp->uobject ?
to_c4iw_ucontext(ib_qp->uobject->context) : NULL;
destroy_qp(&rhp->rdev, &qhp->wq,
@@ -1516,14 +1540,6 @@ int c4iw_destroy_qp(struct ib_qp *ib_qp)
return 0;
}
-static int disable_qp_db(int id, void *p, void *data)
-{
- struct c4iw_qp *qp = p;
-
- t4_disable_wq_db(&qp->wq);
- return 0;
-}
-
struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
struct ib_udata *udata)
{
@@ -1533,7 +1549,7 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
struct c4iw_cq *schp;
struct c4iw_cq *rchp;
struct c4iw_create_qp_resp uresp;
- int sqsize, rqsize;
+ unsigned int sqsize, rqsize;
struct c4iw_ucontext *ucontext;
int ret;
struct c4iw_mm_entry *mm1, *mm2, *mm3, *mm4, *mm5 = NULL;
@@ -1605,25 +1621,13 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
qhp->attr.enable_bind = 1;
qhp->attr.max_ord = 1;
qhp->attr.max_ird = 1;
+ qhp->sq_sig_all = attrs->sq_sig_type == IB_SIGNAL_ALL_WR;
spin_lock_init(&qhp->lock);
mutex_init(&qhp->mutex);
init_waitqueue_head(&qhp->wait);
atomic_set(&qhp->refcnt, 1);
- spin_lock_irq(&rhp->lock);
- if (rhp->db_state != NORMAL)
- t4_disable_wq_db(&qhp->wq);
- rhp->qpcnt++;
- if (rhp->qpcnt > db_fc_threshold && rhp->db_state == NORMAL) {
- rhp->rdev.stats.db_state_transitions++;
- rhp->db_state = FLOW_CONTROL;
- idr_for_each(&rhp->qpidr, disable_qp_db, NULL);
- }
- if (db_coalescing_threshold >= 0)
- if (rhp->qpcnt > db_coalescing_threshold)
- cxgb4_disable_db_coalescing(rhp->rdev.lldi.ports[0]);
- ret = insert_handle_nolock(rhp, &rhp->qpidr, qhp, qhp->wq.sq.qid);
- spin_unlock_irq(&rhp->lock);
+ ret = insert_handle(rhp, &rhp->qpidr, qhp, qhp->wq.sq.qid);
if (ret)
goto err2;
@@ -1692,11 +1696,11 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
mm2->len = PAGE_ALIGN(qhp->wq.rq.memsize);
insert_mmap(ucontext, mm2);
mm3->key = uresp.sq_db_gts_key;
- mm3->addr = qhp->wq.sq.udb;
+ mm3->addr = (__force unsigned long) qhp->wq.sq.udb;
mm3->len = PAGE_SIZE;
insert_mmap(ucontext, mm3);
mm4->key = uresp.rq_db_gts_key;
- mm4->addr = qhp->wq.rq.udb;
+ mm4->addr = (__force unsigned long) qhp->wq.rq.udb;
mm4->len = PAGE_SIZE;
insert_mmap(ucontext, mm4);
if (mm5) {
@@ -1709,6 +1713,7 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
}
qhp->ibqp.qp_num = qhp->wq.sq.qid;
init_timer(&(qhp->timer));
+ INIT_LIST_HEAD(&qhp->db_fc_entry);
PDBG("%s qhp %p sq_num_entries %d, rq_num_entries %d qpid 0x%0x\n",
__func__, qhp, qhp->attr.sq_num_entries, qhp->attr.rq_num_entries,
qhp->wq.sq.qid);
@@ -1772,11 +1777,15 @@ int c4iw_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
/*
* Use SQ_PSN and RQ_PSN to pass in IDX_INC values for
* ringing the queue db when we're in DB_FULL mode.
+ * Only allow this on T4 devices.
*/
attrs.sq_db_inc = attr->sq_psn;
attrs.rq_db_inc = attr->rq_psn;
mask |= (attr_mask & IB_QP_SQ_PSN) ? C4IW_QP_ATTR_SQ_DB : 0;
mask |= (attr_mask & IB_QP_RQ_PSN) ? C4IW_QP_ATTR_RQ_DB : 0;
+ if (is_t5(to_c4iw_qp(ibqp)->rhp->rdev.lldi.adapter_type) &&
+ (mask & (C4IW_QP_ATTR_SQ_DB|C4IW_QP_ATTR_RQ_DB)))
+ return -EINVAL;
return c4iw_modify_qp(rhp, qhp, mask, &attrs, 0);
}
diff --git a/drivers/infiniband/hw/cxgb4/resource.c b/drivers/infiniband/hw/cxgb4/resource.c
index cdef4d7fb6d8..67df71a7012e 100644
--- a/drivers/infiniband/hw/cxgb4/resource.c
+++ b/drivers/infiniband/hw/cxgb4/resource.c
@@ -179,8 +179,12 @@ u32 c4iw_get_qpid(struct c4iw_rdev *rdev, struct c4iw_dev_ucontext *uctx)
kfree(entry);
} else {
qid = c4iw_get_resource(&rdev->resource.qid_table);
- if (!qid)
+ if (!qid) {
+ mutex_lock(&rdev->stats.lock);
+ rdev->stats.qid.fail++;
+ mutex_unlock(&rdev->stats.lock);
goto out;
+ }
mutex_lock(&rdev->stats.lock);
rdev->stats.qid.cur += rdev->qpmask + 1;
mutex_unlock(&rdev->stats.lock);
@@ -322,8 +326,8 @@ u32 c4iw_rqtpool_alloc(struct c4iw_rdev *rdev, int size)
unsigned long addr = gen_pool_alloc(rdev->rqt_pool, size << 6);
PDBG("%s addr 0x%x size %d\n", __func__, (u32)addr, size << 6);
if (!addr)
- printk_ratelimited(KERN_WARNING MOD "%s: Out of RQT memory\n",
- pci_name(rdev->lldi.pdev));
+ pr_warn_ratelimited(MOD "%s: Out of RQT memory\n",
+ pci_name(rdev->lldi.pdev));
mutex_lock(&rdev->stats.lock);
if (addr) {
rdev->stats.rqt.cur += roundup(size << 6, 1 << MIN_RQT_SHIFT);
diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h
index e73ace739183..2178f3198410 100644
--- a/drivers/infiniband/hw/cxgb4/t4.h
+++ b/drivers/infiniband/hw/cxgb4/t4.h
@@ -84,7 +84,14 @@ struct t4_status_page {
sizeof(struct fw_ri_isgl)) / sizeof(struct fw_ri_sge))
#define T4_MAX_FR_IMMD ((T4_SQ_NUM_BYTES - sizeof(struct fw_ri_fr_nsmr_wr) - \
sizeof(struct fw_ri_immd)) & ~31UL)
-#define T4_MAX_FR_DEPTH (1024 / sizeof(u64))
+#define T4_MAX_FR_IMMD_DEPTH (T4_MAX_FR_IMMD / sizeof(u64))
+#define T4_MAX_FR_DSGL 1024
+#define T4_MAX_FR_DSGL_DEPTH (T4_MAX_FR_DSGL / sizeof(u64))
+
+static inline int t4_max_fr_depth(int use_dsgl)
+{
+ return use_dsgl ? T4_MAX_FR_DSGL_DEPTH : T4_MAX_FR_IMMD_DEPTH;
+}
#define T4_RQ_NUM_SLOTS 2
#define T4_RQ_NUM_BYTES (T4_EQ_ENTRY_SIZE * T4_RQ_NUM_SLOTS)
@@ -292,7 +299,7 @@ struct t4_sq {
unsigned long phys_addr;
struct t4_swsqe *sw_sq;
struct t4_swsqe *oldest_read;
- u64 udb;
+ u64 __iomem *udb;
size_t memsize;
u32 qid;
u16 in_use;
@@ -300,6 +307,7 @@ struct t4_sq {
u16 cidx;
u16 pidx;
u16 wq_pidx;
+ u16 wq_pidx_inc;
u16 flags;
short flush_cidx;
};
@@ -313,7 +321,7 @@ struct t4_rq {
dma_addr_t dma_addr;
DEFINE_DMA_UNMAP_ADDR(mapping);
struct t4_swrqe *sw_rq;
- u64 udb;
+ u64 __iomem *udb;
size_t memsize;
u32 qid;
u32 msn;
@@ -324,6 +332,7 @@ struct t4_rq {
u16 cidx;
u16 pidx;
u16 wq_pidx;
+ u16 wq_pidx_inc;
};
struct t4_wq {
@@ -433,15 +442,67 @@ static inline u16 t4_sq_wq_size(struct t4_wq *wq)
return wq->sq.size * T4_SQ_NUM_SLOTS;
}
-static inline void t4_ring_sq_db(struct t4_wq *wq, u16 inc)
+/* This function copies 64 byte coalesced work request to memory
+ * mapped BAR2 space. For coalesced WRs, the SGE fetches data
+ * from the FIFO instead of from Host.
+ */
+static inline void pio_copy(u64 __iomem *dst, u64 *src)
+{
+ int count = 8;
+
+ while (count) {
+ writeq(*src, dst);
+ src++;
+ dst++;
+ count--;
+ }
+}
+
+static inline void t4_ring_sq_db(struct t4_wq *wq, u16 inc, u8 t5,
+ union t4_wr *wqe)
{
+
+ /* Flush host queue memory writes. */
wmb();
+ if (t5) {
+ if (inc == 1 && wqe) {
+ PDBG("%s: WC wq->sq.pidx = %d\n",
+ __func__, wq->sq.pidx);
+ pio_copy(wq->sq.udb + 7, (void *)wqe);
+ } else {
+ PDBG("%s: DB wq->sq.pidx = %d\n",
+ __func__, wq->sq.pidx);
+ writel(PIDX_T5(inc), wq->sq.udb);
+ }
+
+ /* Flush user doorbell area writes. */
+ wmb();
+ return;
+ }
writel(QID(wq->sq.qid) | PIDX(inc), wq->db);
}
-static inline void t4_ring_rq_db(struct t4_wq *wq, u16 inc)
+static inline void t4_ring_rq_db(struct t4_wq *wq, u16 inc, u8 t5,
+ union t4_recv_wr *wqe)
{
+
+ /* Flush host queue memory writes. */
wmb();
+ if (t5) {
+ if (inc == 1 && wqe) {
+ PDBG("%s: WC wq->rq.pidx = %d\n",
+ __func__, wq->rq.pidx);
+ pio_copy(wq->rq.udb + 7, (void *)wqe);
+ } else {
+ PDBG("%s: DB wq->rq.pidx = %d\n",
+ __func__, wq->rq.pidx);
+ writel(PIDX_T5(inc), wq->rq.udb);
+ }
+
+ /* Flush user doorbell area writes. */
+ wmb();
+ return;
+ }
writel(QID(wq->rq.qid) | PIDX(inc), wq->db);
}
@@ -566,6 +627,9 @@ static inline int t4_next_hw_cqe(struct t4_cq *cq, struct t4_cqe **cqe)
printk(KERN_ERR MOD "cq overflow cqid %u\n", cq->cqid);
BUG_ON(1);
} else if (t4_valid_cqe(cq, &cq->queue[cq->cidx])) {
+
+ /* Ensure CQE is flushed to memory */
+ rmb();
*cqe = &cq->queue[cq->cidx];
ret = 0;
} else
@@ -609,3 +673,7 @@ static inline void t4_set_cq_in_error(struct t4_cq *cq)
((struct t4_status_page *)&cq->queue[cq->size])->qp_err = 1;
}
#endif
+
+struct t4_dev_status_page {
+ u8 db_off;
+};
diff --git a/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h b/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
index dc193c292671..6121ca08fe58 100644
--- a/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
+++ b/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
@@ -836,4 +836,18 @@ struct ulptx_idata {
#define V_RX_DACK_CHANGE(x) ((x) << S_RX_DACK_CHANGE)
#define F_RX_DACK_CHANGE V_RX_DACK_CHANGE(1U)
+enum { /* TCP congestion control algorithms */
+ CONG_ALG_RENO,
+ CONG_ALG_TAHOE,
+ CONG_ALG_NEWRENO,
+ CONG_ALG_HIGHSPEED
+};
+
+#define S_CONG_CNTRL 14
+#define M_CONG_CNTRL 0x3
+#define V_CONG_CNTRL(x) ((x) << S_CONG_CNTRL)
+#define G_CONG_CNTRL(x) (((x) >> S_CONG_CNTRL) & M_CONG_CNTRL)
+
+#define T5_OPT_2_VALID (1 << 31)
+
#endif /* _T4FW_RI_API_H_ */
diff --git a/drivers/infiniband/hw/cxgb4/user.h b/drivers/infiniband/hw/cxgb4/user.h
index 32b754c35ab7..11ccd276e5d9 100644
--- a/drivers/infiniband/hw/cxgb4/user.h
+++ b/drivers/infiniband/hw/cxgb4/user.h
@@ -70,4 +70,9 @@ struct c4iw_create_qp_resp {
__u32 qid_mask;
__u32 flags;
};
+
+struct c4iw_alloc_ucontext_resp {
+ __u64 status_page_key;
+ __u32 status_page_size;
+};
#endif
generated by cgit v1.2.3 (git 2.39.1) at 2025-02-04 02:54:36 +0100