summaryrefslogtreecommitdiff
path: root/net/rds
diff options
context:
space:
mode:
Diffstat (limited to 'net/rds')
-rw-r--r--net/rds/af_rds.c8
-rw-r--r--net/rds/cong.c2
-rw-r--r--net/rds/ib.h2
-rw-r--r--net/rds/ib_cm.c2
-rw-r--r--net/rds/ib_rdma.c5
-rw-r--r--net/rds/ib_recv.c35
-rw-r--r--net/rds/iw.h2
-rw-r--r--net/rds/iw_cm.c2
-rw-r--r--net/rds/iw_rdma.c5
-rw-r--r--net/rds/iw_recv.c35
-rw-r--r--net/rds/rdma.c24
-rw-r--r--net/rds/rdma.h1
-rw-r--r--net/rds/tcp_listen.c8
13 files changed, 99 insertions, 32 deletions
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index 98e05382fd3c..e25d8d5ce8df 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -265,6 +265,9 @@ static int rds_setsockopt(struct socket *sock, int level, int optname,
case RDS_GET_MR:
ret = rds_get_mr(rs, optval, optlen);
break;
+ case RDS_GET_MR_FOR_DEST:
+ ret = rds_get_mr_for_dest(rs, optval, optlen);
+ break;
case RDS_FREE_MR:
ret = rds_free_mr(rs, optval, optlen);
break;
@@ -407,7 +410,8 @@ static int __rds_create(struct socket *sock, struct sock *sk, int protocol)
return 0;
}
-static int rds_create(struct net *net, struct socket *sock, int protocol)
+static int rds_create(struct net *net, struct socket *sock, int protocol,
+ int kern)
{
struct sock *sk;
@@ -431,7 +435,7 @@ void rds_sock_put(struct rds_sock *rs)
sock_put(rds_rs_to_sk(rs));
}
-static struct net_proto_family rds_family_ops = {
+static const struct net_proto_family rds_family_ops = {
.family = AF_RDS,
.create = rds_create,
.owner = THIS_MODULE,
diff --git a/net/rds/cong.c b/net/rds/cong.c
index dd2711df640b..6d06cac2649c 100644
--- a/net/rds/cong.c
+++ b/net/rds/cong.c
@@ -218,6 +218,8 @@ void rds_cong_queue_updates(struct rds_cong_map *map)
spin_lock_irqsave(&rds_cong_lock, flags);
list_for_each_entry(conn, &map->m_conn_list, c_map_item) {
+ if (conn->c_loopback)
+ continue;
if (!test_and_set_bit(0, &conn->c_map_queued)) {
rds_stats_inc(s_cong_update_queued);
queue_delayed_work(rds_wq, &conn->c_send_w, 0);
diff --git a/net/rds/ib.h b/net/rds/ib.h
index 1378b854cac0..64df4e79b29f 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -98,6 +98,7 @@ struct rds_ib_connection {
struct rds_ib_send_work *i_sends;
/* rx */
+ struct tasklet_struct i_recv_tasklet;
struct mutex i_recv_mutex;
struct rds_ib_work_ring i_recv_ring;
struct rds_ib_incoming *i_ibinc;
@@ -303,6 +304,7 @@ void rds_ib_inc_free(struct rds_incoming *inc);
int rds_ib_inc_copy_to_user(struct rds_incoming *inc, struct iovec *iov,
size_t size);
void rds_ib_recv_cq_comp_handler(struct ib_cq *cq, void *context);
+void rds_ib_recv_tasklet_fn(unsigned long data);
void rds_ib_recv_init_ring(struct rds_ib_connection *ic);
void rds_ib_recv_clear_ring(struct rds_ib_connection *ic);
void rds_ib_recv_init_ack(struct rds_ib_connection *ic);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index c2d372f13dbb..9d320692a4fc 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -694,6 +694,8 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp)
return -ENOMEM;
INIT_LIST_HEAD(&ic->ib_node);
+ tasklet_init(&ic->i_recv_tasklet, rds_ib_recv_tasklet_fn,
+ (unsigned long) ic);
mutex_init(&ic->i_recv_mutex);
#ifndef KERNEL_HAS_ATOMIC64
spin_lock_init(&ic->i_ack_lock);
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index ef3ab5b7283e..c5e916598c14 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -187,11 +187,8 @@ void __rds_ib_destroy_conns(struct list_head *list, spinlock_t *list_lock)
INIT_LIST_HEAD(list);
spin_unlock_irq(list_lock);
- list_for_each_entry_safe(ic, _ic, &tmp_list, ib_node) {
- if (ic->conn->c_passive)
- rds_conn_destroy(ic->conn->c_passive);
+ list_for_each_entry_safe(ic, _ic, &tmp_list, ib_node)
rds_conn_destroy(ic->conn);
- }
}
struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_ibdev)
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index cd7a6cfcab03..fe5ab8c6b964 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -143,15 +143,16 @@ static int rds_ib_recv_refill_one(struct rds_connection *conn,
int ret = -ENOMEM;
if (recv->r_ibinc == NULL) {
- if (atomic_read(&rds_ib_allocation) >= rds_ib_sysctl_max_recv_allocation) {
+ if (!atomic_add_unless(&rds_ib_allocation, 1, rds_ib_sysctl_max_recv_allocation)) {
rds_ib_stats_inc(s_ib_rx_alloc_limit);
goto out;
}
recv->r_ibinc = kmem_cache_alloc(rds_ib_incoming_slab,
kptr_gfp);
- if (recv->r_ibinc == NULL)
+ if (recv->r_ibinc == NULL) {
+ atomic_dec(&rds_ib_allocation);
goto out;
- atomic_inc(&rds_ib_allocation);
+ }
INIT_LIST_HEAD(&recv->r_ibinc->ii_frags);
rds_inc_init(&recv->r_ibinc->ii_inc, conn, conn->c_faddr);
}
@@ -824,17 +825,22 @@ void rds_ib_recv_cq_comp_handler(struct ib_cq *cq, void *context)
{
struct rds_connection *conn = context;
struct rds_ib_connection *ic = conn->c_transport_data;
- struct ib_wc wc;
- struct rds_ib_ack_state state = { 0, };
- struct rds_ib_recv_work *recv;
rdsdebug("conn %p cq %p\n", conn, cq);
rds_ib_stats_inc(s_ib_rx_cq_call);
- ib_req_notify_cq(cq, IB_CQ_SOLICITED);
+ tasklet_schedule(&ic->i_recv_tasklet);
+}
+
+static inline void rds_poll_cq(struct rds_ib_connection *ic,
+ struct rds_ib_ack_state *state)
+{
+ struct rds_connection *conn = ic->conn;
+ struct ib_wc wc;
+ struct rds_ib_recv_work *recv;
- while (ib_poll_cq(cq, 1, &wc) > 0) {
+ while (ib_poll_cq(ic->i_recv_cq, 1, &wc) > 0) {
rdsdebug("wc wr_id 0x%llx status %u byte_len %u imm_data %u\n",
(unsigned long long)wc.wr_id, wc.status, wc.byte_len,
be32_to_cpu(wc.ex.imm_data));
@@ -852,7 +858,7 @@ void rds_ib_recv_cq_comp_handler(struct ib_cq *cq, void *context)
if (rds_conn_up(conn) || rds_conn_connecting(conn)) {
/* We expect errors as the qp is drained during shutdown */
if (wc.status == IB_WC_SUCCESS) {
- rds_ib_process_recv(conn, recv, wc.byte_len, &state);
+ rds_ib_process_recv(conn, recv, wc.byte_len, state);
} else {
rds_ib_conn_error(conn, "recv completion on "
"%pI4 had status %u, disconnecting and "
@@ -863,6 +869,17 @@ void rds_ib_recv_cq_comp_handler(struct ib_cq *cq, void *context)
rds_ib_ring_free(&ic->i_recv_ring, 1);
}
+}
+
+void rds_ib_recv_tasklet_fn(unsigned long data)
+{
+ struct rds_ib_connection *ic = (struct rds_ib_connection *) data;
+ struct rds_connection *conn = ic->conn;
+ struct rds_ib_ack_state state = { 0, };
+
+ rds_poll_cq(ic, &state);
+ ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED);
+ rds_poll_cq(ic, &state);
if (state.ack_next_valid)
rds_ib_set_ack(ic, state.ack_next, state.ack_required);
diff --git a/net/rds/iw.h b/net/rds/iw.h
index dd72b62bd506..eef2f0c28476 100644
--- a/net/rds/iw.h
+++ b/net/rds/iw.h
@@ -119,6 +119,7 @@ struct rds_iw_connection {
struct rds_iw_send_work *i_sends;
/* rx */
+ struct tasklet_struct i_recv_tasklet;
struct mutex i_recv_mutex;
struct rds_iw_work_ring i_recv_ring;
struct rds_iw_incoming *i_iwinc;
@@ -330,6 +331,7 @@ void rds_iw_inc_free(struct rds_incoming *inc);
int rds_iw_inc_copy_to_user(struct rds_incoming *inc, struct iovec *iov,
size_t size);
void rds_iw_recv_cq_comp_handler(struct ib_cq *cq, void *context);
+void rds_iw_recv_tasklet_fn(unsigned long data);
void rds_iw_recv_init_ring(struct rds_iw_connection *ic);
void rds_iw_recv_clear_ring(struct rds_iw_connection *ic);
void rds_iw_recv_init_ack(struct rds_iw_connection *ic);
diff --git a/net/rds/iw_cm.c b/net/rds/iw_cm.c
index a416b0d492b1..394cf6b4d0aa 100644
--- a/net/rds/iw_cm.c
+++ b/net/rds/iw_cm.c
@@ -696,6 +696,8 @@ int rds_iw_conn_alloc(struct rds_connection *conn, gfp_t gfp)
return -ENOMEM;
INIT_LIST_HEAD(&ic->iw_node);
+ tasklet_init(&ic->i_recv_tasklet, rds_iw_recv_tasklet_fn,
+ (unsigned long) ic);
mutex_init(&ic->i_recv_mutex);
#ifndef KERNEL_HAS_ATOMIC64
spin_lock_init(&ic->i_ack_lock);
diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c
index de4a1b16bf7b..b25d785e49fc 100644
--- a/net/rds/iw_rdma.c
+++ b/net/rds/iw_rdma.c
@@ -245,11 +245,8 @@ void __rds_iw_destroy_conns(struct list_head *list, spinlock_t *list_lock)
INIT_LIST_HEAD(list);
spin_unlock_irq(list_lock);
- list_for_each_entry_safe(ic, _ic, &tmp_list, iw_node) {
- if (ic->conn->c_passive)
- rds_conn_destroy(ic->conn->c_passive);
+ list_for_each_entry_safe(ic, _ic, &tmp_list, iw_node)
rds_conn_destroy(ic->conn);
- }
}
static void rds_iw_set_scatterlist(struct rds_iw_scatterlist *sg,
diff --git a/net/rds/iw_recv.c b/net/rds/iw_recv.c
index 8683f5f66c4b..24fc53f03833 100644
--- a/net/rds/iw_recv.c
+++ b/net/rds/iw_recv.c
@@ -143,15 +143,16 @@ static int rds_iw_recv_refill_one(struct rds_connection *conn,
int ret = -ENOMEM;
if (recv->r_iwinc == NULL) {
- if (atomic_read(&rds_iw_allocation) >= rds_iw_sysctl_max_recv_allocation) {
+ if (!atomic_add_unless(&rds_iw_allocation, 1, rds_iw_sysctl_max_recv_allocation)) {
rds_iw_stats_inc(s_iw_rx_alloc_limit);
goto out;
}
recv->r_iwinc = kmem_cache_alloc(rds_iw_incoming_slab,
kptr_gfp);
- if (recv->r_iwinc == NULL)
+ if (recv->r_iwinc == NULL) {
+ atomic_dec(&rds_iw_allocation);
goto out;
- atomic_inc(&rds_iw_allocation);
+ }
INIT_LIST_HEAD(&recv->r_iwinc->ii_frags);
rds_inc_init(&recv->r_iwinc->ii_inc, conn, conn->c_faddr);
}
@@ -783,17 +784,22 @@ void rds_iw_recv_cq_comp_handler(struct ib_cq *cq, void *context)
{
struct rds_connection *conn = context;
struct rds_iw_connection *ic = conn->c_transport_data;
- struct ib_wc wc;
- struct rds_iw_ack_state state = { 0, };
- struct rds_iw_recv_work *recv;
rdsdebug("conn %p cq %p\n", conn, cq);
rds_iw_stats_inc(s_iw_rx_cq_call);
- ib_req_notify_cq(cq, IB_CQ_SOLICITED);
+ tasklet_schedule(&ic->i_recv_tasklet);
+}
+
+static inline void rds_poll_cq(struct rds_iw_connection *ic,
+ struct rds_iw_ack_state *state)
+{
+ struct rds_connection *conn = ic->conn;
+ struct ib_wc wc;
+ struct rds_iw_recv_work *recv;
- while (ib_poll_cq(cq, 1, &wc) > 0) {
+ while (ib_poll_cq(ic->i_recv_cq, 1, &wc) > 0) {
rdsdebug("wc wr_id 0x%llx status %u byte_len %u imm_data %u\n",
(unsigned long long)wc.wr_id, wc.status, wc.byte_len,
be32_to_cpu(wc.ex.imm_data));
@@ -811,7 +817,7 @@ void rds_iw_recv_cq_comp_handler(struct ib_cq *cq, void *context)
if (rds_conn_up(conn) || rds_conn_connecting(conn)) {
/* We expect errors as the qp is drained during shutdown */
if (wc.status == IB_WC_SUCCESS) {
- rds_iw_process_recv(conn, recv, wc.byte_len, &state);
+ rds_iw_process_recv(conn, recv, wc.byte_len, state);
} else {
rds_iw_conn_error(conn, "recv completion on "
"%pI4 had status %u, disconnecting and "
@@ -822,6 +828,17 @@ void rds_iw_recv_cq_comp_handler(struct ib_cq *cq, void *context)
rds_iw_ring_free(&ic->i_recv_ring, 1);
}
+}
+
+void rds_iw_recv_tasklet_fn(unsigned long data)
+{
+ struct rds_iw_connection *ic = (struct rds_iw_connection *) data;
+ struct rds_connection *conn = ic->conn;
+ struct rds_iw_ack_state state = { 0, };
+
+ rds_poll_cq(ic, &state);
+ ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED);
+ rds_poll_cq(ic, &state);
if (state.ack_next_valid)
rds_iw_set_ack(ic, state.ack_next, state.ack_required);
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 8dc83d2caa58..971b5a668458 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -317,6 +317,30 @@ int rds_get_mr(struct rds_sock *rs, char __user *optval, int optlen)
return __rds_rdma_map(rs, &args, NULL, NULL);
}
+int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen)
+{
+ struct rds_get_mr_for_dest_args args;
+ struct rds_get_mr_args new_args;
+
+ if (optlen != sizeof(struct rds_get_mr_for_dest_args))
+ return -EINVAL;
+
+ if (copy_from_user(&args, (struct rds_get_mr_for_dest_args __user *)optval,
+ sizeof(struct rds_get_mr_for_dest_args)))
+ return -EFAULT;
+
+ /*
+ * Initially, just behave like get_mr().
+ * TODO: Implement get_mr as wrapper around this
+ * and deprecate it.
+ */
+ new_args.vec = args.vec;
+ new_args.cookie_addr = args.cookie_addr;
+ new_args.flags = args.flags;
+
+ return __rds_rdma_map(rs, &new_args, NULL, NULL);
+}
+
/*
* Free the MR indicated by the given R_Key
*/
diff --git a/net/rds/rdma.h b/net/rds/rdma.h
index 425512098b0b..909c39835a5d 100644
--- a/net/rds/rdma.h
+++ b/net/rds/rdma.h
@@ -61,6 +61,7 @@ static inline u32 rds_rdma_cookie_offset(rds_rdma_cookie_t cookie)
}
int rds_get_mr(struct rds_sock *rs, char __user *optval, int optlen);
+int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen);
int rds_free_mr(struct rds_sock *rs, char __user *optval, int optlen);
void rds_rdma_drop_keys(struct rds_sock *rs);
int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 24b743eb0b1b..45474a436862 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -67,11 +67,11 @@ static int rds_tcp_accept_one(struct socket *sock)
inet = inet_sk(new_sock->sk);
rdsdebug("accepted tcp %u.%u.%u.%u:%u -> %u.%u.%u.%u:%u\n",
- NIPQUAD(inet->saddr), ntohs(inet->sport),
- NIPQUAD(inet->daddr), ntohs(inet->dport));
+ NIPQUAD(inet->inet_saddr), ntohs(inet->inet_sport),
+ NIPQUAD(inet->inet_daddr), ntohs(inet->inet_dport));
- conn = rds_conn_create(inet->saddr, inet->daddr, &rds_tcp_transport,
- GFP_KERNEL);
+ conn = rds_conn_create(inet->inet_saddr, inet->inet_daddr,
+ &rds_tcp_transport, GFP_KERNEL);
if (IS_ERR(conn)) {
ret = PTR_ERR(conn);
goto out;
generated by cgit v1.2.3 (git 2.0.4) at 2025-12-09 15:36:46 +0000