From: Steve Wise <sw...@opengridcomputing.com>
40G devices need a bigger windows, so default 40G devices to snd 512K
rcv 1024K.
Fixed a bug that shows up with recv window sizes that exceed the size of
the RCV_BUFSIZ field in opt0 (>= 1024K :). If the recv window exceeds
this, then we specify the max possible in opt0, add add the rest in via
a RX_DATA_ACK credits.
Added module option named adjust_win, defaulted to 1, that allows
disabling the 40G window bump. This allows a user to specify the exact
default window sizes via module options snd_win and rcv_win.
Signed-off-by: Steve Wise <sw...@opengridcomputing.com>
---
drivers/infiniband/hw/cxgb4/cm.c | 63 +++++++++++++++++++++++++--
drivers/infiniband/hw/cxgb4/iw_cxgb4.h | 2 +
drivers/net/ethernet/chelsio/cxgb4/t4_msg.h | 1 +
3 files changed, 62 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 452ae3a..81fbc6e 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -134,6 +134,11 @@ static int snd_win = 128 * 1024;
module_param(snd_win, int, 0644);
MODULE_PARM_DESC(snd_win, "TCP send window in bytes (default=128KB)");
+static int adjust_win = 1;
+module_param(adjust_win, int, 0644);
+MODULE_PARM_DESC(adjust_win,
+ "Adjust TCP window based on link speed (default=1)");
+
static struct workqueue_struct *workq;
static struct sk_buff_head rxq;
@@ -465,7 +470,7 @@ 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 */
@@ -547,6 +552,7 @@ static int send_connect(struct c4iw_ep *ep)
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;
+ int win;
wrlen = (ep->com.remote_addr.ss_family == AF_INET) ?
roundup(sizev4, 16) :
@@ -564,6 +570,15 @@ static int send_connect(struct c4iw_ep *ep)
cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx);
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) |
@@ -574,7 +589,7 @@ 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);
@@ -1134,6 +1149,14 @@ 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);
@@ -1592,6 +1615,7 @@ 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));
@@ -1616,6 +1640,15 @@ static void send_fw_act_open_req(struct c4iw_ep *ep,
unsigned int atid)
req->tcb.rcv_adv = htons(1);
cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx);
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) |
@@ -1627,7 +1660,7 @@ 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) |
@@ -1665,6 +1698,17 @@ static int is_neg_adv(unsigned int status)
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;
+ if (adjust_win && pi->link_cfg.speed == 40000) {
+ ep->snd_win *= 4;
+ ep->rcv_win *= 4;
+ }
+ 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,
@@ -1713,6 +1757,7 @@ 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);
@@ -1731,6 +1776,7 @@ static int import_ep(struct c4iw_ep *ep, int iptype, __u8
*peer_ip,
cdev->rdev.lldi.nchan;
ep->rss_qid = cdev->rdev.lldi.rxq_ids[
cxgb4_port_idx(n->dev) * step];
+ set_tcp_window(ep, (struct port_info *)netdev_priv(pdev));
if (clear_mpa_v1) {
ep->retry_with_mpa_v1 = 0;
@@ -1961,6 +2007,7 @@ static void accept_cr(struct c4iw_ep *ep, struct sk_buff
*skb,
u64 opt0;
u32 opt2;
int wscale;
+ int win;
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
BUG_ON(skb_cloned(skb));
@@ -1968,6 +2015,14 @@ static void accept_cr(struct c4iw_ep *ep, struct sk_buff
*skb,
skb_get(skb);
cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx);
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) |
@@ -1978,7 +2033,7 @@ 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);
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index b75f8f5..3b6cea0 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -804,6 +804,8 @@ struct c4iw_ep {
u8 retry_with_mpa_v1;
u8 tried_with_mpa_v1;
unsigned int retry_count;
+ int snd_win;
+ int rcv_win;
};
static inline struct c4iw_ep *to_ep(struct iw_cm_id *cm_id)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index f2738c7..330bc14 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -227,6 +227,7 @@ struct cpl_pass_open_req {
#define DELACK(x) ((x) << 5)
#define ULP_MODE(x) ((x) << 8)
#define RCV_BUFSIZ(x) ((x) << 12)
+#define RCV_BUFSIZ_MASK 0x3FFU
#define DSCP(x) ((x) << 22)
#define SMAC_SEL(x) ((u64)(x) << 28)
#define L2T_IDX(x) ((u64)(x) << 36)
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
