aboutsummaryrefslogtreecommitdiffstats
path: root/net/rds/ib_cm.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/rds/ib_cm.c')
-rw-r--r--net/rds/ib_cm.c178
1 files changed, 88 insertions, 90 deletions
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index c71f4328d138..26b069e1999d 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -30,13 +30,13 @@
* SOFTWARE.
*
*/
-#include <linux/dmapool.h>
#include <linux/kernel.h>
#include <linux/in.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/ratelimit.h>
#include <net/addrconf.h>
+#include <rdma/ib_cm.h>
#include "rds_single_path.h"
#include "rds.h"
@@ -68,31 +68,6 @@ static void rds_ib_set_flow_control(struct rds_connection *conn, u32 credits)
}
/*
- * Tune RNR behavior. Without flow control, we use a rather
- * low timeout, but not the absolute minimum - this should
- * be tunable.
- *
- * We already set the RNR retry count to 7 (which is the
- * smallest infinite number :-) above.
- * If flow control is off, we want to change this back to 0
- * so that we learn quickly when our credit accounting is
- * buggy.
- *
- * Caller passes in a qp_attr pointer - don't waste stack spacv
- * by allocation this twice.
- */
-static void
-rds_ib_tune_rnr(struct rds_ib_connection *ic, struct ib_qp_attr *attr)
-{
- int ret;
-
- attr->min_rnr_timer = IB_RNR_TIMER_000_32;
- ret = ib_modify_qp(ic->i_cm_id->qp, attr, IB_QP_MIN_RNR_TIMER);
- if (ret)
- printk(KERN_NOTICE "ib_modify_qp(IB_QP_MIN_RNR_TIMER): err=%d\n", -ret);
-}
-
-/*
* Connection established.
* We get here for both outgoing and incoming connection.
*/
@@ -100,7 +75,6 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
{
struct rds_ib_connection *ic = conn->c_transport_data;
const union rds_ib_conn_priv *dp = NULL;
- struct ib_qp_attr qp_attr;
__be64 ack_seq = 0;
__be32 credit = 0;
u8 major = 0;
@@ -168,14 +142,6 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
* the posted credit count. */
rds_ib_recv_refill(conn, 1, GFP_KERNEL);
- /* Tune RNR behavior */
- rds_ib_tune_rnr(ic, &qp_attr);
-
- qp_attr.qp_state = IB_QPS_RTS;
- err = ib_modify_qp(ic->i_cm_id->qp, &qp_attr, IB_QP_STATE);
- if (err)
- printk(KERN_NOTICE "ib_modify_qp(IB_QP_STATE, RTS): err=%d\n", err);
-
/* update ib_device with this local ipaddr */
err = rds_ib_update_ipaddr(ic->rds_ibdev, &conn->c_laddr);
if (err)
@@ -440,42 +406,87 @@ static inline void ibdev_put_vector(struct rds_ib_device *rds_ibdev, int index)
rds_ibdev->vector_load[index]--;
}
+static void rds_dma_hdr_free(struct ib_device *dev, struct rds_header *hdr,
+ dma_addr_t dma_addr, enum dma_data_direction dir)
+{
+ ib_dma_unmap_single(dev, dma_addr, sizeof(*hdr), dir);
+ kfree(hdr);
+}
+
+static struct rds_header *rds_dma_hdr_alloc(struct ib_device *dev,
+ dma_addr_t *dma_addr, enum dma_data_direction dir)
+{
+ struct rds_header *hdr;
+
+ hdr = kzalloc_node(sizeof(*hdr), GFP_KERNEL, ibdev_to_node(dev));
+ if (!hdr)
+ return NULL;
+
+ *dma_addr = ib_dma_map_single(dev, hdr, sizeof(*hdr),
+ DMA_BIDIRECTIONAL);
+ if (ib_dma_mapping_error(dev, *dma_addr)) {
+ kfree(hdr);
+ return NULL;
+ }
+
+ return hdr;
+}
+
+/* Free the DMA memory used to store struct rds_header.
+ *
+ * @dev: the RDS IB device
+ * @hdrs: pointer to the array storing DMA memory pointers
+ * @dma_addrs: pointer to the array storing DMA addresses
+ * @num_hdars: number of headers to free.
+ */
+static void rds_dma_hdrs_free(struct rds_ib_device *dev,
+ struct rds_header **hdrs, dma_addr_t *dma_addrs, u32 num_hdrs,
+ enum dma_data_direction dir)
+{
+ u32 i;
+
+ for (i = 0; i < num_hdrs; i++)
+ rds_dma_hdr_free(dev->dev, hdrs[i], dma_addrs[i], dir);
+ kvfree(hdrs);
+ kvfree(dma_addrs);
+}
+
+
/* Allocate DMA coherent memory to be used to store struct rds_header for
* sending/receiving packets. The pointers to the DMA memory and the
* associated DMA addresses are stored in two arrays.
*
- * @ibdev: the IB device
- * @pool: the DMA memory pool
+ * @dev: the RDS IB device
* @dma_addrs: pointer to the array for storing DMA addresses
* @num_hdrs: number of headers to allocate
*
* It returns the pointer to the array storing the DMA memory pointers. On
* error, NULL pointer is returned.
*/
-struct rds_header **rds_dma_hdrs_alloc(struct ib_device *ibdev,
- struct dma_pool *pool,
- dma_addr_t **dma_addrs, u32 num_hdrs)
+static struct rds_header **rds_dma_hdrs_alloc(struct rds_ib_device *dev,
+ dma_addr_t **dma_addrs, u32 num_hdrs,
+ enum dma_data_direction dir)
{
struct rds_header **hdrs;
dma_addr_t *hdr_daddrs;
u32 i;
hdrs = kvmalloc_node(sizeof(*hdrs) * num_hdrs, GFP_KERNEL,
- ibdev_to_node(ibdev));
+ ibdev_to_node(dev->dev));
if (!hdrs)
return NULL;
hdr_daddrs = kvmalloc_node(sizeof(*hdr_daddrs) * num_hdrs, GFP_KERNEL,
- ibdev_to_node(ibdev));
+ ibdev_to_node(dev->dev));
if (!hdr_daddrs) {
kvfree(hdrs);
return NULL;
}
for (i = 0; i < num_hdrs; i++) {
- hdrs[i] = dma_pool_zalloc(pool, GFP_KERNEL, &hdr_daddrs[i]);
+ hdrs[i] = rds_dma_hdr_alloc(dev->dev, &hdr_daddrs[i], dir);
if (!hdrs[i]) {
- rds_dma_hdrs_free(pool, hdrs, hdr_daddrs, i);
+ rds_dma_hdrs_free(dev, hdrs, hdr_daddrs, i, dir);
return NULL;
}
}
@@ -484,24 +495,6 @@ struct rds_header **rds_dma_hdrs_alloc(struct ib_device *ibdev,
return hdrs;
}
-/* Free the DMA memory used to store struct rds_header.
- *
- * @pool: the DMA memory pool
- * @hdrs: pointer to the array storing DMA memory pointers
- * @dma_addrs: pointer to the array storing DMA addresses
- * @num_hdars: number of headers to free.
- */
-void rds_dma_hdrs_free(struct dma_pool *pool, struct rds_header **hdrs,
- dma_addr_t *dma_addrs, u32 num_hdrs)
-{
- u32 i;
-
- for (i = 0; i < num_hdrs; i++)
- dma_pool_free(pool, hdrs[i], dma_addrs[i]);
- kvfree(hdrs);
- kvfree(dma_addrs);
-}
-
/*
* This needs to be very careful to not leave IS_ERR pointers around for
* cleanup to trip over.
@@ -515,7 +508,6 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
struct rds_ib_device *rds_ibdev;
unsigned long max_wrs;
int ret, fr_queue_space;
- struct dma_pool *pool;
/*
* It's normal to see a null device if an incoming connection races
@@ -526,10 +518,10 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
return -EOPNOTSUPP;
/* The fr_queue_space is currently set to 512, to add extra space on
- * completion queue and send queue. This extra space is used for FRMR
+ * completion queue and send queue. This extra space is used for FRWR
* registration and invalidation work requests
*/
- fr_queue_space = (rds_ibdev->use_fastreg ? RDS_IB_DEFAULT_FR_WR : 0);
+ fr_queue_space = RDS_IB_DEFAULT_FR_WR;
/* add the conn now so that connection establishment has the dev */
rds_ib_add_conn(rds_ibdev, conn);
@@ -611,25 +603,26 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
goto recv_cq_out;
}
- pool = rds_ibdev->rid_hdrs_pool;
- ic->i_send_hdrs = rds_dma_hdrs_alloc(dev, pool, &ic->i_send_hdrs_dma,
- ic->i_send_ring.w_nr);
+ ic->i_send_hdrs = rds_dma_hdrs_alloc(rds_ibdev, &ic->i_send_hdrs_dma,
+ ic->i_send_ring.w_nr,
+ DMA_TO_DEVICE);
if (!ic->i_send_hdrs) {
ret = -ENOMEM;
rdsdebug("DMA send hdrs alloc failed\n");
goto qp_out;
}
- ic->i_recv_hdrs = rds_dma_hdrs_alloc(dev, pool, &ic->i_recv_hdrs_dma,
- ic->i_recv_ring.w_nr);
+ ic->i_recv_hdrs = rds_dma_hdrs_alloc(rds_ibdev, &ic->i_recv_hdrs_dma,
+ ic->i_recv_ring.w_nr,
+ DMA_FROM_DEVICE);
if (!ic->i_recv_hdrs) {
ret = -ENOMEM;
rdsdebug("DMA recv hdrs alloc failed\n");
goto send_hdrs_dma_out;
}
- ic->i_ack = dma_pool_zalloc(pool, GFP_KERNEL,
- &ic->i_ack_dma);
+ ic->i_ack = rds_dma_hdr_alloc(rds_ibdev->dev, &ic->i_ack_dma,
+ DMA_TO_DEVICE);
if (!ic->i_ack) {
ret = -ENOMEM;
rdsdebug("DMA ack header alloc failed\n");
@@ -665,18 +658,19 @@ sends_out:
vfree(ic->i_sends);
ack_dma_out:
- dma_pool_free(pool, ic->i_ack, ic->i_ack_dma);
+ rds_dma_hdr_free(rds_ibdev->dev, ic->i_ack, ic->i_ack_dma,
+ DMA_TO_DEVICE);
ic->i_ack = NULL;
recv_hdrs_dma_out:
- rds_dma_hdrs_free(pool, ic->i_recv_hdrs, ic->i_recv_hdrs_dma,
- ic->i_recv_ring.w_nr);
+ rds_dma_hdrs_free(rds_ibdev, ic->i_recv_hdrs, ic->i_recv_hdrs_dma,
+ ic->i_recv_ring.w_nr, DMA_FROM_DEVICE);
ic->i_recv_hdrs = NULL;
ic->i_recv_hdrs_dma = NULL;
send_hdrs_dma_out:
- rds_dma_hdrs_free(pool, ic->i_send_hdrs, ic->i_send_hdrs_dma,
- ic->i_send_ring.w_nr);
+ rds_dma_hdrs_free(rds_ibdev, ic->i_send_hdrs, ic->i_send_hdrs_dma,
+ ic->i_send_ring.w_nr, DMA_TO_DEVICE);
ic->i_send_hdrs = NULL;
ic->i_send_hdrs_dma = NULL;
@@ -710,7 +704,7 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event, bool isv6)
* original size. The only way to tell the difference is by looking at
* the contents, which are initialized to zero.
* If the protocol version fields aren't set, this is a connection attempt
- * from an older version. This could could be 3.0 or 2.0 - we can't tell.
+ * from an older version. This could be 3.0 or 2.0 - we can't tell.
* We really should have changed this for OFED 1.3 :-(
*/
@@ -919,6 +913,7 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
event->param.conn.responder_resources,
event->param.conn.initiator_depth, isv6);
+ rdma_set_min_rnr_timer(cm_id, IB_RNR_TIMER_000_32);
/* rdma_accept() calls rdma_reject() internally if it fails */
if (rdma_accept(cm_id, &conn_param))
rds_ib_conn_error(conn, "rdma_accept failed\n");
@@ -927,7 +922,8 @@ out:
if (conn)
mutex_unlock(&conn->c_cm_lock);
if (err)
- rdma_reject(cm_id, &err, sizeof(int));
+ rdma_reject(cm_id, &err, sizeof(int),
+ IB_CM_REJ_CONSUMER_DEFINED);
return destroy;
}
@@ -954,9 +950,10 @@ int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6)
rds_ib_cm_fill_conn_param(conn, &conn_param, &dp,
conn->c_proposed_version,
UINT_MAX, UINT_MAX, isv6);
- ret = rdma_connect(cm_id, &conn_param);
+ ret = rdma_connect_locked(cm_id, &conn_param);
if (ret)
- rds_ib_conn_error(conn, "rdma_connect failed (%d)\n", ret);
+ rds_ib_conn_error(conn, "rdma_connect_locked failed (%d)\n",
+ ret);
out:
/* Beware - returning non-zero tells the rdma_cm to destroy
@@ -1107,29 +1104,30 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp)
}
if (ic->rds_ibdev) {
- struct dma_pool *pool;
-
- pool = ic->rds_ibdev->rid_hdrs_pool;
-
/* then free the resources that ib callbacks use */
if (ic->i_send_hdrs) {
- rds_dma_hdrs_free(pool, ic->i_send_hdrs,
+ rds_dma_hdrs_free(ic->rds_ibdev,
+ ic->i_send_hdrs,
ic->i_send_hdrs_dma,
- ic->i_send_ring.w_nr);
+ ic->i_send_ring.w_nr,
+ DMA_TO_DEVICE);
ic->i_send_hdrs = NULL;
ic->i_send_hdrs_dma = NULL;
}
if (ic->i_recv_hdrs) {
- rds_dma_hdrs_free(pool, ic->i_recv_hdrs,
+ rds_dma_hdrs_free(ic->rds_ibdev,
+ ic->i_recv_hdrs,
ic->i_recv_hdrs_dma,
- ic->i_recv_ring.w_nr);
+ ic->i_recv_ring.w_nr,
+ DMA_FROM_DEVICE);
ic->i_recv_hdrs = NULL;
ic->i_recv_hdrs_dma = NULL;
}
if (ic->i_ack) {
- dma_pool_free(pool, ic->i_ack, ic->i_ack_dma);
+ rds_dma_hdr_free(ic->rds_ibdev->dev, ic->i_ack,
+ ic->i_ack_dma, DMA_TO_DEVICE);
ic->i_ack = NULL;
}
} else {
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.