aboutsummaryrefslogtreecommitdiff
path: root/net/smc
diff options
context:
space:
mode:
Diffstat (limited to 'net/smc')
-rw-r--r--net/smc/af_smc.c6
-rw-r--r--net/smc/smc_core.c14
-rw-r--r--net/smc/smc_core.h2
-rw-r--r--net/smc/smc_llc.c2
-rw-r--r--net/smc/smc_llc.h1
-rw-r--r--net/smc/smc_netlink.c3
-rw-r--r--net/smc/smc_pnet.c3
-rw-r--r--net/smc/smc_sysctl.c30
-rw-r--r--net/smc/smc_wr.c5
-rw-r--r--net/smc/smc_wr.h5
10 files changed, 60 insertions, 11 deletions
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 0939cc3b915a..3ccbf3c201cd 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -379,6 +379,8 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock,
sk->sk_state = SMC_INIT;
sk->sk_destruct = smc_destruct;
sk->sk_protocol = protocol;
+ WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(net->smc.sysctl_wmem));
+ WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(net->smc.sysctl_rmem));
smc = smc_sk(sk);
INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
INIT_WORK(&smc->connect_work, smc_connect_work);
@@ -427,6 +429,7 @@ static int smc_bind(struct socket *sock, struct sockaddr *uaddr,
goto out_rel;
smc->clcsock->sk->sk_reuse = sk->sk_reuse;
+ smc->clcsock->sk->sk_reuseport = sk->sk_reuseport;
rc = kernel_bind(smc->clcsock, uaddr, addr_len);
out_rel:
@@ -3253,9 +3256,6 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol,
smc->clcsock = clcsock;
}
- smc->sk.sk_sndbuf = max(smc->clcsock->sk->sk_sndbuf, SMC_BUF_MIN_SIZE);
- smc->sk.sk_rcvbuf = max(smc->clcsock->sk->sk_rcvbuf, SMC_BUF_MIN_SIZE);
-
out:
return rc;
}
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index ff49a11f57b8..e6ee797640b4 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -757,6 +757,7 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk,
lnk->lgr = lgr;
smc_lgr_hold(lgr); /* lgr_put in smcr_link_clear() */
lnk->link_idx = link_idx;
+ lnk->wr_rx_id_compl = 0;
smc_ibdev_cnt_inc(lnk);
smcr_copy_dev_info_to_link(lnk);
atomic_set(&lnk->conn_cnt, 0);
@@ -2238,7 +2239,7 @@ out:
static int smcr_buf_map_usable_links(struct smc_link_group *lgr,
struct smc_buf_desc *buf_desc, bool is_rmb)
{
- int i, rc = 0;
+ int i, rc = 0, cnt = 0;
/* protect against parallel link reconfiguration */
mutex_lock(&lgr->llc_conf_mutex);
@@ -2251,9 +2252,12 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr,
rc = -ENOMEM;
goto out;
}
+ cnt++;
}
out:
mutex_unlock(&lgr->llc_conf_mutex);
+ if (!rc && !cnt)
+ rc = -EINVAL;
return rc;
}
@@ -2306,10 +2310,10 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
if (is_rmb)
/* use socket recv buffer size (w/o overhead) as start value */
- sk_buf_size = smc->sk.sk_rcvbuf / 2;
+ sk_buf_size = smc->sk.sk_rcvbuf;
else
/* use socket send buffer size (w/o overhead) as start value */
- sk_buf_size = smc->sk.sk_sndbuf / 2;
+ sk_buf_size = smc->sk.sk_sndbuf;
for (bufsize_short = smc_compress_bufsize(sk_buf_size, is_smcd, is_rmb);
bufsize_short >= 0; bufsize_short--) {
@@ -2368,7 +2372,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
if (is_rmb) {
conn->rmb_desc = buf_desc;
conn->rmbe_size_short = bufsize_short;
- smc->sk.sk_rcvbuf = bufsize * 2;
+ smc->sk.sk_rcvbuf = bufsize;
atomic_set(&conn->bytes_to_rcv, 0);
conn->rmbe_update_limit =
smc_rmb_wnd_update_limit(buf_desc->len);
@@ -2376,7 +2380,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */
} else {
conn->sndbuf_desc = buf_desc;
- smc->sk.sk_sndbuf = bufsize * 2;
+ smc->sk.sk_sndbuf = bufsize;
atomic_set(&conn->sndbuf_space, bufsize);
}
return 0;
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index fe8b524ad846..285f9bd8e232 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -115,8 +115,10 @@ struct smc_link {
dma_addr_t wr_rx_dma_addr; /* DMA address of wr_rx_bufs */
dma_addr_t wr_rx_v2_dma_addr; /* DMA address of v2 rx buf*/
u64 wr_rx_id; /* seq # of last recv WR */
+ u64 wr_rx_id_compl; /* seq # of last completed WR */
u32 wr_rx_cnt; /* number of WR recv buffers */
unsigned long wr_rx_tstamp; /* jiffies when last buf rx */
+ wait_queue_head_t wr_rx_empty_wait; /* wait for RQ empty */
struct ib_reg_wr wr_reg; /* WR register memory region */
wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 175026ae33ae..524649d0ab65 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -2127,7 +2127,7 @@ void smc_llc_lgr_init(struct smc_link_group *lgr, struct smc_sock *smc)
init_waitqueue_head(&lgr->llc_flow_waiter);
init_waitqueue_head(&lgr->llc_msg_waiter);
mutex_init(&lgr->llc_conf_mutex);
- lgr->llc_testlink_time = READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time);
+ lgr->llc_testlink_time = READ_ONCE(net->smc.sysctl_smcr_testlink_time);
}
/* called after lgr was removed from lgr_list */
diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h
index 4404e52b3346..7e7a3162c68b 100644
--- a/net/smc/smc_llc.h
+++ b/net/smc/smc_llc.h
@@ -19,6 +19,7 @@
#define SMC_LLC_WAIT_FIRST_TIME (5 * HZ)
#define SMC_LLC_WAIT_TIME (2 * HZ)
+#define SMC_LLC_TESTLINK_DEFAULT_TIME (30 * HZ)
enum smc_llc_reqresp {
SMC_LLC_REQ,
diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c
index c5a62f6f52ba..621c46c70073 100644
--- a/net/smc/smc_netlink.c
+++ b/net/smc/smc_netlink.c
@@ -142,7 +142,8 @@ struct genl_family smc_gen_nl_family __ro_after_init = {
.netnsok = true,
.module = THIS_MODULE,
.ops = smc_gen_nl_ops,
- .n_ops = ARRAY_SIZE(smc_gen_nl_ops)
+ .n_ops = ARRAY_SIZE(smc_gen_nl_ops),
+ .resv_start_op = SMC_NETLINK_DISABLE_HS_LIMITATION + 1,
};
int __init smc_nl_init(void)
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 4c3bf6db7038..25fb2fd186e2 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -715,7 +715,8 @@ static struct genl_family smc_pnet_nl_family __ro_after_init = {
.netnsok = true,
.module = THIS_MODULE,
.ops = smc_pnet_ops,
- .n_ops = ARRAY_SIZE(smc_pnet_ops)
+ .n_ops = ARRAY_SIZE(smc_pnet_ops),
+ .resv_start_op = SMC_PNETID_FLUSH + 1,
};
bool smc_pnet_is_ndev_pnetid(struct net *net, u8 *pnetid)
diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c
index 0613868fdb97..b6f79fabb9d3 100644
--- a/net/smc/smc_sysctl.c
+++ b/net/smc/smc_sysctl.c
@@ -16,8 +16,12 @@
#include "smc.h"
#include "smc_core.h"
+#include "smc_llc.h"
#include "smc_sysctl.h"
+static int min_sndbuf = SMC_BUF_MIN_SIZE;
+static int min_rcvbuf = SMC_BUF_MIN_SIZE;
+
static struct ctl_table smc_table[] = {
{
.procname = "autocorking_size",
@@ -35,6 +39,29 @@ static struct ctl_table smc_table[] = {
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO,
},
+ {
+ .procname = "smcr_testlink_time",
+ .data = &init_net.smc.sysctl_smcr_testlink_time,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
+ {
+ .procname = "wmem",
+ .data = &init_net.smc.sysctl_wmem,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &min_sndbuf,
+ },
+ {
+ .procname = "rmem",
+ .data = &init_net.smc.sysctl_rmem,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &min_rcvbuf,
+ },
{ }
};
@@ -60,6 +87,9 @@ int __net_init smc_sysctl_net_init(struct net *net)
net->smc.sysctl_autocorking_size = SMC_AUTOCORKING_DEFAULT_SIZE;
net->smc.sysctl_smcr_buf_type = SMCR_PHYS_CONT_BUFS;
+ net->smc.sysctl_smcr_testlink_time = SMC_LLC_TESTLINK_DEFAULT_TIME;
+ WRITE_ONCE(net->smc.sysctl_wmem, READ_ONCE(net->ipv4.sysctl_tcp_wmem[1]));
+ WRITE_ONCE(net->smc.sysctl_rmem, READ_ONCE(net->ipv4.sysctl_tcp_rmem[1]));
return 0;
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 26f8f240d9e8..b0678a417e09 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -454,6 +454,7 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num)
for (i = 0; i < num; i++) {
link = wc[i].qp->qp_context;
+ link->wr_rx_id_compl = wc[i].wr_id;
if (wc[i].status == IB_WC_SUCCESS) {
link->wr_rx_tstamp = jiffies;
smc_wr_rx_demultiplex(&wc[i]);
@@ -465,6 +466,8 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num)
case IB_WC_RNR_RETRY_EXC_ERR:
case IB_WC_WR_FLUSH_ERR:
smcr_link_down_cond_sched(link);
+ if (link->wr_rx_id_compl == link->wr_rx_id)
+ wake_up(&link->wr_rx_empty_wait);
break;
default:
smc_wr_rx_post(link); /* refill WR RX */
@@ -639,6 +642,7 @@ void smc_wr_free_link(struct smc_link *lnk)
return;
ibdev = lnk->smcibdev->ibdev;
+ smc_wr_drain_cq(lnk);
smc_wr_wakeup_reg_wait(lnk);
smc_wr_wakeup_tx_wait(lnk);
@@ -889,6 +893,7 @@ int smc_wr_create_link(struct smc_link *lnk)
atomic_set(&lnk->wr_tx_refcnt, 0);
init_waitqueue_head(&lnk->wr_reg_wait);
atomic_set(&lnk->wr_reg_refcnt, 0);
+ init_waitqueue_head(&lnk->wr_rx_empty_wait);
return rc;
dma_unmap:
diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h
index a54e90a1110f..45e9b894d3f8 100644
--- a/net/smc/smc_wr.h
+++ b/net/smc/smc_wr.h
@@ -73,6 +73,11 @@ static inline void smc_wr_tx_link_put(struct smc_link *link)
wake_up_all(&link->wr_tx_wait);
}
+static inline void smc_wr_drain_cq(struct smc_link *lnk)
+{
+ wait_event(lnk->wr_rx_empty_wait, lnk->wr_rx_id_compl == lnk->wr_rx_id);
+}
+
static inline void smc_wr_wakeup_tx_wait(struct smc_link *lnk)
{
wake_up_all(&lnk->wr_tx_wait);