aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/core/cm.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband/core/cm.c')
-rw-r--r--drivers/infiniband/core/cm.c2117
1 files changed, 1075 insertions, 1042 deletions
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 15e99a888427..1f9938a2c475 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -25,8 +25,10 @@
#include <rdma/ib_cache.h>
#include <rdma/ib_cm.h>
+#include <rdma/ib_sysfs.h>
#include "cm_msgs.h"
#include "core_priv.h"
+#include "cm_trace.h"
MODULE_AUTHOR("Sean Hefty");
MODULE_DESCRIPTION("InfiniBand CM");
@@ -66,6 +68,8 @@ static const char * const ibcm_rej_reason_strs[] = {
[IB_CM_REJ_INVALID_CLASS_VERSION] = "invalid class version",
[IB_CM_REJ_INVALID_FLOW_LABEL] = "invalid flow label",
[IB_CM_REJ_INVALID_ALT_FLOW_LABEL] = "invalid alt flow label",
+ [IB_CM_REJ_VENDOR_OPTION_NOT_SUPPORTED] =
+ "vendor option is not supported",
};
const char *__attribute_const__ ibcm_reject_msg(int reason)
@@ -80,8 +84,22 @@ const char *__attribute_const__ ibcm_reject_msg(int reason)
}
EXPORT_SYMBOL(ibcm_reject_msg);
-static void cm_add_one(struct ib_device *device);
+struct cm_id_private;
+struct cm_work;
+static int cm_add_one(struct ib_device *device);
static void cm_remove_one(struct ib_device *device, void *client_data);
+static void cm_process_work(struct cm_id_private *cm_id_priv,
+ struct cm_work *work);
+static int cm_send_sidr_rep_locked(struct cm_id_private *cm_id_priv,
+ struct ib_cm_sidr_rep_param *param);
+static int cm_send_dreq_locked(struct cm_id_private *cm_id_priv,
+ const void *private_data, u8 private_data_len);
+static int cm_send_drep_locked(struct cm_id_private *cm_id_priv,
+ void *private_data, u8 private_data_len);
+static int cm_send_rej_locked(struct cm_id_private *cm_id_priv,
+ enum ib_cm_rej_reason reason, void *ari,
+ u8 ari_length, const void *private_data,
+ u8 private_data_len);
static struct ib_client cm_client = {
.name = "cm",
@@ -104,8 +122,6 @@ static struct ib_cm {
__be32 random_id_operand;
struct list_head timewait_list;
struct workqueue_struct *wq;
- /* Sync on cm change port state */
- spinlock_t state_lock;
} cm;
/* Counter indexes ordered by attribute ID */
@@ -133,77 +149,33 @@ enum {
CM_COUNTER_GROUPS
};
-static char const counter_group_names[CM_COUNTER_GROUPS]
- [sizeof("cm_rx_duplicates")] = {
- "cm_tx_msgs", "cm_tx_retries",
- "cm_rx_msgs", "cm_rx_duplicates"
-};
-
-struct cm_counter_group {
- struct kobject obj;
- atomic_long_t counter[CM_ATTR_COUNT];
-};
-
struct cm_counter_attribute {
- struct attribute attr;
- int index;
-};
-
-#define CM_COUNTER_ATTR(_name, _index) \
-struct cm_counter_attribute cm_##_name##_counter_attr = { \
- .attr = { .name = __stringify(_name), .mode = 0444 }, \
- .index = _index \
-}
-
-static CM_COUNTER_ATTR(req, CM_REQ_COUNTER);
-static CM_COUNTER_ATTR(mra, CM_MRA_COUNTER);
-static CM_COUNTER_ATTR(rej, CM_REJ_COUNTER);
-static CM_COUNTER_ATTR(rep, CM_REP_COUNTER);
-static CM_COUNTER_ATTR(rtu, CM_RTU_COUNTER);
-static CM_COUNTER_ATTR(dreq, CM_DREQ_COUNTER);
-static CM_COUNTER_ATTR(drep, CM_DREP_COUNTER);
-static CM_COUNTER_ATTR(sidr_req, CM_SIDR_REQ_COUNTER);
-static CM_COUNTER_ATTR(sidr_rep, CM_SIDR_REP_COUNTER);
-static CM_COUNTER_ATTR(lap, CM_LAP_COUNTER);
-static CM_COUNTER_ATTR(apr, CM_APR_COUNTER);
-
-static struct attribute *cm_counter_default_attrs[] = {
- &cm_req_counter_attr.attr,
- &cm_mra_counter_attr.attr,
- &cm_rej_counter_attr.attr,
- &cm_rep_counter_attr.attr,
- &cm_rtu_counter_attr.attr,
- &cm_dreq_counter_attr.attr,
- &cm_drep_counter_attr.attr,
- &cm_sidr_req_counter_attr.attr,
- &cm_sidr_rep_counter_attr.attr,
- &cm_lap_counter_attr.attr,
- &cm_apr_counter_attr.attr,
- NULL
+ struct ib_port_attribute attr;
+ unsigned short group;
+ unsigned short index;
};
struct cm_port {
struct cm_device *cm_dev;
struct ib_mad_agent *mad_agent;
- struct kobject port_obj;
- u8 port_num;
- struct list_head cm_priv_prim_list;
- struct list_head cm_priv_altr_list;
- struct cm_counter_group counter_group[CM_COUNTER_GROUPS];
+ u32 port_num;
+ atomic_long_t counters[CM_COUNTER_GROUPS][CM_ATTR_COUNT];
};
struct cm_device {
+ struct kref kref;
struct list_head list;
+ spinlock_t mad_agent_lock;
struct ib_device *ib_device;
u8 ack_delay;
int going_down;
- struct cm_port *port[0];
+ struct cm_port *port[];
};
struct cm_av {
struct cm_port *port;
- union ib_gid dgid;
struct rdma_ah_attr ah_attr;
+ u16 dlid_datapath;
u16 pkey_index;
u8 timeout;
};
@@ -216,7 +188,7 @@ struct cm_work {
__be32 local_id; /* Established / timewait */
__be32 remote_id;
struct ib_cm_event cm_event;
- struct sa_path_rec path[0];
+ struct sa_path_rec path[];
};
struct cm_timewait_info {
@@ -235,11 +207,13 @@ struct cm_id_private {
struct rb_node service_node;
struct rb_node sidr_id_node;
+ u32 sidr_slid;
spinlock_t lock; /* Do not acquire inside cm.lock */
struct completion comp;
refcount_t refcount;
/* Number of clients sharing this ib_cm_id. Only valid for listeners.
- * Protected by the cm.lock spinlock. */
+ * Protected by the cm.lock spinlock.
+ */
int listen_sharecount;
struct rcu_head rcu;
@@ -261,7 +235,6 @@ struct cm_id_private {
__be16 pkey;
u8 private_data_len;
u8 max_cm_retries;
- u8 peer_to_peer;
u8 responder_resources;
u8 initiator_depth;
u8 retry_count;
@@ -269,16 +242,28 @@ struct cm_id_private {
u8 service_timeout;
u8 target_ack_delay;
- struct list_head prim_list;
- struct list_head altr_list;
- /* Indicates that the send port mad is registered and av is set */
- int prim_send_port_not_ready;
- int altr_send_port_not_ready;
-
struct list_head work_list;
atomic_t work_count;
+
+ struct rdma_ucm_ece ece;
};
+static void cm_dev_release(struct kref *kref)
+{
+ struct cm_device *cm_dev = container_of(kref, struct cm_device, kref);
+ u32 i;
+
+ rdma_for_each_port(cm_dev->ib_device, i)
+ kfree(cm_dev->port[i - 1]);
+
+ kfree(cm_dev);
+}
+
+static void cm_device_put(struct cm_device *cm_dev)
+{
+ kref_put(&cm_dev->kref, cm_dev_release);
+}
+
static void cm_work_handler(struct work_struct *work);
static inline void cm_deref_id(struct cm_id_private *cm_id_priv)
@@ -287,52 +272,37 @@ static inline void cm_deref_id(struct cm_id_private *cm_id_priv)
complete(&cm_id_priv->comp);
}
-static int cm_alloc_msg(struct cm_id_private *cm_id_priv,
- struct ib_mad_send_buf **msg)
+static struct ib_mad_send_buf *cm_alloc_msg(struct cm_id_private *cm_id_priv)
{
struct ib_mad_agent *mad_agent;
struct ib_mad_send_buf *m;
struct ib_ah *ah;
- struct cm_av *av;
- unsigned long flags, flags2;
- int ret = 0;
- /* don't let the port to be released till the agent is down */
- spin_lock_irqsave(&cm.state_lock, flags2);
- spin_lock_irqsave(&cm.lock, flags);
- if (!cm_id_priv->prim_send_port_not_ready)
- av = &cm_id_priv->av;
- else if (!cm_id_priv->altr_send_port_not_ready &&
- (cm_id_priv->alt_av.port))
- av = &cm_id_priv->alt_av;
- else {
- pr_info("%s: not valid CM id\n", __func__);
- ret = -ENODEV;
- spin_unlock_irqrestore(&cm.lock, flags);
- goto out;
- }
- spin_unlock_irqrestore(&cm.lock, flags);
- /* Make sure the port haven't released the mad yet */
+ lockdep_assert_held(&cm_id_priv->lock);
+
+ if (!cm_id_priv->av.port)
+ return ERR_PTR(-EINVAL);
+
+ spin_lock(&cm_id_priv->av.port->cm_dev->mad_agent_lock);
mad_agent = cm_id_priv->av.port->mad_agent;
if (!mad_agent) {
- pr_info("%s: not a valid MAD agent\n", __func__);
- ret = -ENODEV;
+ m = ERR_PTR(-EINVAL);
goto out;
}
- ah = rdma_create_ah(mad_agent->qp->pd, &av->ah_attr, 0);
+
+ ah = rdma_create_ah(mad_agent->qp->pd, &cm_id_priv->av.ah_attr, 0);
if (IS_ERR(ah)) {
- ret = PTR_ERR(ah);
+ m = ERR_CAST(ah);
goto out;
}
m = ib_create_send_mad(mad_agent, cm_id_priv->id.remote_cm_qpn,
- av->pkey_index,
+ cm_id_priv->av.pkey_index,
0, IB_MGMT_MAD_HDR, IB_MGMT_MAD_DATA,
GFP_ATOMIC,
IB_MGMT_BASE_VERSION);
if (IS_ERR(m)) {
rdma_destroy_ah(ah, 0);
- ret = PTR_ERR(m);
goto out;
}
@@ -342,11 +312,49 @@ static int cm_alloc_msg(struct cm_id_private *cm_id_priv,
refcount_inc(&cm_id_priv->refcount);
m->context[0] = cm_id_priv;
- *msg = m;
out:
- spin_unlock_irqrestore(&cm.state_lock, flags2);
- return ret;
+ spin_unlock(&cm_id_priv->av.port->cm_dev->mad_agent_lock);
+ return m;
+}
+
+static void cm_free_msg(struct ib_mad_send_buf *msg)
+{
+ struct cm_id_private *cm_id_priv = msg->context[0];
+
+ if (msg->ah)
+ rdma_destroy_ah(msg->ah, 0);
+ cm_deref_id(cm_id_priv);
+ ib_free_send_mad(msg);
+}
+
+static struct ib_mad_send_buf *
+cm_alloc_priv_msg(struct cm_id_private *cm_id_priv)
+{
+ struct ib_mad_send_buf *msg;
+
+ lockdep_assert_held(&cm_id_priv->lock);
+
+ msg = cm_alloc_msg(cm_id_priv);
+ if (IS_ERR(msg))
+ return msg;
+ cm_id_priv->msg = msg;
+ return msg;
+}
+
+static void cm_free_priv_msg(struct ib_mad_send_buf *msg)
+{
+ struct cm_id_private *cm_id_priv = msg->context[0];
+
+ lockdep_assert_held(&cm_id_priv->lock);
+
+ if (!WARN_ON(cm_id_priv->msg != msg))
+ cm_id_priv->msg = NULL;
+
+ if (msg->ah)
+ rdma_destroy_ah(msg->ah, 0);
+ cm_deref_id(cm_id_priv);
+ ib_free_send_mad(msg);
}
static struct ib_mad_send_buf *cm_alloc_response_msg_no_ah(struct cm_port *port,
@@ -373,15 +381,6 @@ static int cm_create_response_msg_ah(struct cm_port *port,
return 0;
}
-static void cm_free_msg(struct ib_mad_send_buf *msg)
-{
- if (msg->ah)
- rdma_destroy_ah(msg->ah, 0);
- if (msg->context[0])
- cm_deref_id(msg->context[0]);
- ib_free_send_mad(msg);
-}
-
static int cm_alloc_response_msg(struct cm_port *port,
struct ib_mad_recv_wc *mad_recv_wc,
struct ib_mad_send_buf **msg)
@@ -395,7 +394,7 @@ static int cm_alloc_response_msg(struct cm_port *port,
ret = cm_create_response_msg_ah(port, mad_recv_wc, m);
if (ret) {
- cm_free_msg(m);
+ ib_free_send_mad(m);
return ret;
}
@@ -403,8 +402,14 @@ static int cm_alloc_response_msg(struct cm_port *port,
return 0;
}
-static void * cm_copy_private_data(const void *private_data,
- u8 private_data_len)
+static void cm_free_response_msg(struct ib_mad_send_buf *msg)
+{
+ if (msg->ah)
+ rdma_destroy_ah(msg->ah, 0);
+ ib_free_send_mad(msg);
+}
+
+static void *cm_copy_private_data(const void *private_data, u8 private_data_len)
{
void *data;
@@ -428,62 +433,38 @@ static void cm_set_private_data(struct cm_id_private *cm_id_priv,
cm_id_priv->private_data_len = private_data_len;
}
-static int cm_init_av_for_lap(struct cm_port *port, struct ib_wc *wc,
- struct ib_grh *grh, struct cm_av *av)
+static void cm_set_av_port(struct cm_av *av, struct cm_port *port)
{
- struct rdma_ah_attr new_ah_attr;
- int ret;
+ struct cm_port *old_port = av->port;
- av->port = port;
- av->pkey_index = wc->pkey_index;
+ if (old_port == port)
+ return;
- /*
- * av->ah_attr might be initialized based on past wc during incoming
- * connect request or while sending out connect request. So initialize
- * a new ah_attr on stack. If initialization fails, old ah_attr is
- * used for sending any responses. If initialization is successful,
- * than new ah_attr is used by overwriting old one.
- */
- ret = ib_init_ah_attr_from_wc(port->cm_dev->ib_device,
- port->port_num, wc,
- grh, &new_ah_attr);
- if (ret)
- return ret;
+ av->port = port;
+ if (old_port)
+ cm_device_put(old_port->cm_dev);
+ if (port)
+ kref_get(&port->cm_dev->kref);
+}
- rdma_move_ah_attr(&av->ah_attr, &new_ah_attr);
- return 0;
+static void cm_init_av_for_lap(struct cm_port *port, struct ib_wc *wc,
+ struct rdma_ah_attr *ah_attr, struct cm_av *av)
+{
+ cm_set_av_port(av, port);
+ av->pkey_index = wc->pkey_index;
+ rdma_move_ah_attr(&av->ah_attr, ah_attr);
}
static int cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc,
struct ib_grh *grh, struct cm_av *av)
{
- av->port = port;
+ cm_set_av_port(av, port);
av->pkey_index = wc->pkey_index;
return ib_init_ah_attr_from_wc(port->cm_dev->ib_device,
port->port_num, wc,
grh, &av->ah_attr);
}
-static int add_cm_id_to_port_list(struct cm_id_private *cm_id_priv,
- struct cm_av *av,
- struct cm_port *port)
-{
- unsigned long flags;
- int ret = 0;
-
- spin_lock_irqsave(&cm.lock, flags);
-
- if (&cm_id_priv->av == av)
- list_add_tail(&cm_id_priv->prim_list, &port->cm_priv_prim_list);
- else if (&cm_id_priv->alt_av == av)
- list_add_tail(&cm_id_priv->altr_list, &port->cm_priv_altr_list);
- else
- ret = -EINVAL;
-
- spin_unlock_irqrestore(&cm.lock, flags);
- return ret;
-}
-
static struct cm_port *
get_cm_port_from_path(struct sa_path_rec *path, const struct ib_gid_attr *attr)
{
@@ -527,8 +508,7 @@ get_cm_port_from_path(struct sa_path_rec *path, const struct ib_gid_attr *attr)
static int cm_init_av_by_path(struct sa_path_rec *path,
const struct ib_gid_attr *sgid_attr,
- struct cm_av *av,
- struct cm_id_private *cm_id_priv)
+ struct cm_av *av)
{
struct rdma_ah_attr new_ah_attr;
struct cm_device *cm_dev;
@@ -545,7 +525,7 @@ static int cm_init_av_by_path(struct sa_path_rec *path,
if (ret)
return ret;
- av->port = port;
+ cm_set_av_port(av, port);
/*
* av->ah_attr might be initialized based on wc or during
@@ -562,36 +542,29 @@ static int cm_init_av_by_path(struct sa_path_rec *path,
return ret;
av->timeout = path->packet_life_time + 1;
-
- ret = add_cm_id_to_port_list(cm_id_priv, av, port);
- if (ret) {
- rdma_destroy_ah_attr(&new_ah_attr);
- return ret;
- }
rdma_move_ah_attr(&av->ah_attr, &new_ah_attr);
return 0;
}
-static int cm_alloc_id(struct cm_id_private *cm_id_priv)
+/* Move av created by cm_init_av_by_path(), so av.dgid is not moved */
+static void cm_move_av_from_path(struct cm_av *dest, struct cm_av *src)
{
- int err;
- u32 id;
-
- err = xa_alloc_cyclic_irq(&cm.local_id_table, &id, cm_id_priv,
- xa_limit_32b, &cm.local_id_next, GFP_KERNEL);
-
- cm_id_priv->id.local_id = (__force __be32)id ^ cm.random_id_operand;
- return err;
+ cm_set_av_port(dest, src->port);
+ cm_set_av_port(src, NULL);
+ dest->pkey_index = src->pkey_index;
+ rdma_move_ah_attr(&dest->ah_attr, &src->ah_attr);
+ dest->timeout = src->timeout;
}
-static u32 cm_local_id(__be32 local_id)
+static void cm_destroy_av(struct cm_av *av)
{
- return (__force u32) (local_id ^ cm.random_id_operand);
+ rdma_destroy_ah_attr(&av->ah_attr);
+ cm_set_av_port(av, NULL);
}
-static void cm_free_id(__be32 local_id)
+static u32 cm_local_id(__be32 local_id)
{
- xa_erase_irq(&cm.local_id_table, cm_local_id(local_id));
+ return (__force u32) (local_id ^ cm.random_id_operand);
}
static struct cm_id_private *cm_acquire_id(__be32 local_id, __be32 remote_id)
@@ -633,22 +606,25 @@ static int be64_gt(__be64 a, __be64 b)
return (__force u64) a > (__force u64) b;
}
-static struct cm_id_private * cm_insert_listen(struct cm_id_private *cm_id_priv)
+/*
+ * Inserts a new cm_id_priv into the listen_service_table. Returns cm_id_priv
+ * if the new ID was inserted, NULL if it could not be inserted due to a
+ * collision, or the existing cm_id_priv ready for shared usage.
+ */
+static struct cm_id_private *cm_insert_listen(struct cm_id_private *cm_id_priv,
+ ib_cm_handler shared_handler)
{
struct rb_node **link = &cm.listen_service_table.rb_node;
struct rb_node *parent = NULL;
struct cm_id_private *cur_cm_id_priv;
__be64 service_id = cm_id_priv->id.service_id;
- __be64 service_mask = cm_id_priv->id.service_mask;
+ unsigned long flags;
+ spin_lock_irqsave(&cm.lock, flags);
while (*link) {
parent = *link;
cur_cm_id_priv = rb_entry(parent, struct cm_id_private,
service_node);
- if ((cur_cm_id_priv->id.service_mask & service_id) ==
- (service_mask & cur_cm_id_priv->id.service_id) &&
- (cm_id_priv->id.device == cur_cm_id_priv->id.device))
- return cur_cm_id_priv;
if (cm_id_priv->id.device < cur_cm_id_priv->id.device)
link = &(*link)->rb_left;
@@ -658,26 +634,38 @@ static struct cm_id_private * cm_insert_listen(struct cm_id_private *cm_id_priv)
link = &(*link)->rb_left;
else if (be64_gt(service_id, cur_cm_id_priv->id.service_id))
link = &(*link)->rb_right;
- else
- link = &(*link)->rb_right;
+ else {
+ /*
+ * Sharing an ib_cm_id with different handlers is not
+ * supported
+ */
+ if (cur_cm_id_priv->id.cm_handler != shared_handler ||
+ cur_cm_id_priv->id.context ||
+ WARN_ON(!cur_cm_id_priv->id.cm_handler)) {
+ spin_unlock_irqrestore(&cm.lock, flags);
+ return NULL;
+ }
+ refcount_inc(&cur_cm_id_priv->refcount);
+ cur_cm_id_priv->listen_sharecount++;
+ spin_unlock_irqrestore(&cm.lock, flags);
+ return cur_cm_id_priv;
+ }
}
+ cm_id_priv->listen_sharecount++;
rb_link_node(&cm_id_priv->service_node, parent, link);
rb_insert_color(&cm_id_priv->service_node, &cm.listen_service_table);
- return NULL;
+ spin_unlock_irqrestore(&cm.lock, flags);
+ return cm_id_priv;
}
-static struct cm_id_private * cm_find_listen(struct ib_device *device,
- __be64 service_id)
+static struct cm_id_private *cm_find_listen(struct ib_device *device,
+ __be64 service_id)
{
struct rb_node *node = cm.listen_service_table.rb_node;
struct cm_id_private *cm_id_priv;
while (node) {
cm_id_priv = rb_entry(node, struct cm_id_private, service_node);
- if ((cm_id_priv->id.service_mask & service_id) ==
- cm_id_priv->id.service_id &&
- (cm_id_priv->id.device == device))
- return cm_id_priv;
if (device < cm_id_priv->id.device)
node = node->rb_left;
@@ -687,14 +675,16 @@ static struct cm_id_private * cm_find_listen(struct ib_device *device,
node = node->rb_left;
else if (be64_gt(service_id, cm_id_priv->id.service_id))
node = node->rb_right;
- else
- node = node->rb_right;
+ else {
+ refcount_inc(&cm_id_priv->refcount);
+ return cm_id_priv;
+ }
}
return NULL;
}
-static struct cm_timewait_info * cm_insert_remote_id(struct cm_timewait_info
- *timewait_info)
+static struct cm_timewait_info *
+cm_insert_remote_id(struct cm_timewait_info *timewait_info)
{
struct rb_node **link = &cm.remote_id_table.rb_node;
struct rb_node *parent = NULL;
@@ -723,12 +713,14 @@ static struct cm_timewait_info * cm_insert_remote_id(struct cm_timewait_info
return NULL;
}
-static struct cm_timewait_info * cm_find_remote_id(__be64 remote_ca_guid,
- __be32 remote_id)
+static struct cm_id_private *cm_find_remote_id(__be64 remote_ca_guid,
+ __be32 remote_id)
{
struct rb_node *node = cm.remote_id_table.rb_node;
struct cm_timewait_info *timewait_info;
+ struct cm_id_private *res = NULL;
+ spin_lock_irq(&cm.lock);
while (node) {
timewait_info = rb_entry(node, struct cm_timewait_info,
remote_id_node);
@@ -740,14 +732,18 @@ static struct cm_timewait_info * cm_find_remote_id(__be64 remote_ca_guid,
node = node->rb_left;
else if (be64_gt(remote_ca_guid, timewait_info->remote_ca_guid))
node = node->rb_right;
- else
- return timewait_info;
+ else {
+ res = cm_acquire_id(timewait_info->work.local_id,
+ timewait_info->work.remote_id);
+ break;
+ }
}
- return NULL;
+ spin_unlock_irq(&cm.lock);
+ return res;
}
-static struct cm_timewait_info * cm_insert_remote_qpn(struct cm_timewait_info
- *timewait_info)
+static struct cm_timewait_info *
+cm_insert_remote_qpn(struct cm_timewait_info *timewait_info)
{
struct rb_node **link = &cm.remote_qp_table.rb_node;
struct rb_node *parent = NULL;
@@ -776,13 +772,12 @@ static struct cm_timewait_info * cm_insert_remote_qpn(struct cm_timewait_info
return NULL;
}
-static struct cm_id_private * cm_insert_remote_sidr(struct cm_id_private
- *cm_id_priv)
+static struct cm_id_private *
+cm_insert_remote_sidr(struct cm_id_private *cm_id_priv)
{
struct rb_node **link = &cm.remote_sidr_table.rb_node;
struct rb_node *parent = NULL;
struct cm_id_private *cur_cm_id_priv;
- union ib_gid *port_gid = &cm_id_priv->av.dgid;
__be32 remote_id = cm_id_priv->id.remote_id;
while (*link) {
@@ -794,12 +789,9 @@ static struct cm_id_private * cm_insert_remote_sidr(struct cm_id_private
else if (be32_gt(remote_id, cur_cm_id_priv->id.remote_id))
link = &(*link)->rb_right;
else {
- int cmp;
- cmp = memcmp(port_gid, &cur_cm_id_priv->av.dgid,
- sizeof *port_gid);
- if (cmp < 0)
+ if (cur_cm_id_priv->sidr_slid < cm_id_priv->sidr_slid)
link = &(*link)->rb_left;
- else if (cmp > 0)
+ else if (cur_cm_id_priv->sidr_slid > cm_id_priv->sidr_slid)
link = &(*link)->rb_right;
else
return cur_cm_id_priv;
@@ -810,21 +802,12 @@ static struct cm_id_private * cm_insert_remote_sidr(struct cm_id_private
return NULL;
}
-static void cm_reject_sidr_req(struct cm_id_private *cm_id_priv,
- enum ib_cm_sidr_status status)
-{
- struct ib_cm_sidr_rep_param param;
-
- memset(&param, 0, sizeof param);
- param.status = status;
- ib_send_cm_sidr_rep(&cm_id_priv->id, &param);
-}
-
-struct ib_cm_id *ib_create_cm_id(struct ib_device *device,
- ib_cm_handler cm_handler,
- void *context)
+static struct cm_id_private *cm_alloc_id_priv(struct ib_device *device,
+ ib_cm_handler cm_handler,
+ void *context)
{
struct cm_id_private *cm_id_priv;
+ u32 id;
int ret;
cm_id_priv = kzalloc(sizeof *cm_id_priv, GFP_KERNEL);
@@ -836,26 +819,54 @@ struct ib_cm_id *ib_create_cm_id(struct ib_device *device,
cm_id_priv->id.cm_handler = cm_handler;
cm_id_priv->id.context = context;
cm_id_priv->id.remote_cm_qpn = 1;
- ret = cm_alloc_id(cm_id_priv);
- if (ret)
- goto error;
+ RB_CLEAR_NODE(&cm_id_priv->service_node);
+ RB_CLEAR_NODE(&cm_id_priv->sidr_id_node);
spin_lock_init(&cm_id_priv->lock);
init_completion(&cm_id_priv->comp);
INIT_LIST_HEAD(&cm_id_priv->work_list);
- INIT_LIST_HEAD(&cm_id_priv->prim_list);
- INIT_LIST_HEAD(&cm_id_priv->altr_list);
atomic_set(&cm_id_priv->work_count, -1);
refcount_set(&cm_id_priv->refcount, 1);
- return &cm_id_priv->id;
+
+ ret = xa_alloc_cyclic(&cm.local_id_table, &id, NULL, xa_limit_32b,
+ &cm.local_id_next, GFP_KERNEL);
+ if (ret < 0)
+ goto error;
+ cm_id_priv->id.local_id = (__force __be32)id ^ cm.random_id_operand;
+
+ return cm_id_priv;
error:
kfree(cm_id_priv);
- return ERR_PTR(-ENOMEM);
+ return ERR_PTR(ret);
+}
+
+/*
+ * Make the ID visible to the MAD handlers and other threads that use the
+ * xarray.
+ */
+static void cm_finalize_id(struct cm_id_private *cm_id_priv)
+{
+ xa_store(&cm.local_id_table, cm_local_id(cm_id_priv->id.local_id),
+ cm_id_priv, GFP_ATOMIC);
+}
+
+struct ib_cm_id *ib_create_cm_id(struct ib_device *device,
+ ib_cm_handler cm_handler,
+ void *context)
+{
+ struct cm_id_private *cm_id_priv;
+
+ cm_id_priv = cm_alloc_id_priv(device, cm_handler, context);
+ if (IS_ERR(cm_id_priv))
+ return ERR_CAST(cm_id_priv);
+
+ cm_finalize_id(cm_id_priv);
+ return &cm_id_priv->id;
}
EXPORT_SYMBOL(ib_create_cm_id);
-static struct cm_work * cm_dequeue_work(struct cm_id_private *cm_id_priv)
+static struct cm_work *cm_dequeue_work(struct cm_id_private *cm_id_priv)
{
struct cm_work *work;
@@ -874,6 +885,36 @@ static void cm_free_work(struct cm_work *work)
kfree(work);
}
+static void cm_queue_work_unlock(struct cm_id_private *cm_id_priv,
+ struct cm_work *work)
+ __releases(&cm_id_priv->lock)
+{
+ bool immediate;
+
+ /*
+ * To deliver the event to the user callback we have the drop the
+ * spinlock, however, we need to ensure that the user callback is single
+ * threaded and receives events in the temporal order. If there are
+ * already events being processed then thread new events onto a list,
+ * the thread currently processing will pick them up.
+ */
+ immediate = atomic_inc_and_test(&cm_id_priv->work_count);
+ if (!immediate) {
+ list_add_tail(&work->list, &cm_id_priv->work_list);
+ /*
+ * This routine always consumes incoming reference. Once queued
+ * to the work_list then a reference is held by the thread
+ * currently running cm_process_work() and this reference is not
+ * needed.
+ */
+ cm_deref_id(cm_id_priv);
+ }
+ spin_unlock_irq(&cm_id_priv->lock);
+
+ if (immediate)
+ cm_process_work(cm_id_priv, work);
+}
+
static inline int cm_convert_to_ms(int iba_time)
{
/* approximate conversion to ms from 4.096us x 2^iba_time */
@@ -899,8 +940,10 @@ static u8 cm_ack_timeout(u8 ca_ack_delay, u8 packet_life_time)
return min(31, ack_timeout);
}
-static void cm_cleanup_timewait(struct cm_timewait_info *timewait_info)
+static void cm_remove_remote(struct cm_id_private *cm_id_priv)
{
+ struct cm_timewait_info *timewait_info = cm_id_priv->timewait_info;
+
if (timewait_info->inserted_remote_id) {
rb_erase(&timewait_info->remote_id_node, &cm.remote_id_table);
timewait_info->inserted_remote_id = 0;
@@ -912,7 +955,7 @@ static void cm_cleanup_timewait(struct cm_timewait_info *timewait_info)
}
}
-static struct cm_timewait_info * cm_create_timewait_info(__be32 local_id)
+static struct cm_timewait_info *cm_create_timewait_info(__be32 local_id)
{
struct cm_timewait_info *timewait_info;
@@ -932,12 +975,14 @@ static void cm_enter_timewait(struct cm_id_private *cm_id_priv)
unsigned long flags;
struct cm_device *cm_dev;
+ lockdep_assert_held(&cm_id_priv->lock);
+
cm_dev = ib_get_client_data(cm_id_priv->id.device, &cm_client);
if (!cm_dev)
return;
spin_lock_irqsave(&cm.lock, flags);
- cm_cleanup_timewait(cm_id_priv->timewait_info);
+ cm_remove_remote(cm_id_priv);
list_add_tail(&cm_id_priv->timewait_info->list, &cm.timewait_list);
spin_unlock_irqrestore(&cm.lock, flags);
@@ -956,6 +1001,11 @@ static void cm_enter_timewait(struct cm_id_private *cm_id_priv)
msecs_to_jiffies(wait_time));
spin_unlock_irqrestore(&cm.lock, flags);
+ /*
+ * The timewait_info is converted into a work and gets freed during
+ * cm_free_work() in cm_timewait_handler().
+ */
+ BUILD_BUG_ON(offsetof(struct cm_timewait_info, work) != 0);
cm_id_priv->timewait_info = NULL;
}
@@ -963,10 +1013,12 @@ static void cm_reset_to_idle(struct cm_id_private *cm_id_priv)
{
unsigned long flags;
+ lockdep_assert_held(&cm_id_priv->lock);
+
cm_id_priv->id.state = IB_CM_IDLE;
if (cm_id_priv->timewait_info) {
spin_lock_irqsave(&cm.lock, flags);
- cm_cleanup_timewait(cm_id_priv->timewait_info);
+ cm_remove_remote(cm_id_priv);
spin_unlock_irqrestore(&cm.lock, flags);
kfree(cm_id_priv->timewait_info);
cm_id_priv->timewait_info = NULL;
@@ -979,104 +1031,116 @@ static void cm_destroy_id(struct ib_cm_id *cm_id, int err)
struct cm_work *work;
cm_id_priv = container_of(cm_id, struct cm_id_private, id);
-retest:
spin_lock_irq(&cm_id_priv->lock);
+retest:
switch (cm_id->state) {
case IB_CM_LISTEN:
- spin_unlock_irq(&cm_id_priv->lock);
-
- spin_lock_irq(&cm.lock);
+ spin_lock(&cm.lock);
if (--cm_id_priv->listen_sharecount > 0) {
/* The id is still shared. */
+ WARN_ON(refcount_read(&cm_id_priv->refcount) == 1);
+ spin_unlock(&cm.lock);
+ spin_unlock_irq(&cm_id_priv->lock);
cm_deref_id(cm_id_priv);
- spin_unlock_irq(&cm.lock);
return;
}
+ cm_id->state = IB_CM_IDLE;
rb_erase(&cm_id_priv->service_node, &cm.listen_service_table);
- spin_unlock_irq(&cm.lock);
+ RB_CLEAR_NODE(&cm_id_priv->service_node);
+ spin_unlock(&cm.lock);
break;
case IB_CM_SIDR_REQ_SENT:
cm_id->state = IB_CM_IDLE;
- ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
- spin_unlock_irq(&cm_id_priv->lock);
+ ib_cancel_mad(cm_id_priv->msg);
break;
case IB_CM_SIDR_REQ_RCVD:
- spin_unlock_irq(&cm_id_priv->lock);
- cm_reject_sidr_req(cm_id_priv, IB_SIDR_REJECT);
- spin_lock_irq(&cm.lock);
- if (!RB_EMPTY_NODE(&cm_id_priv->sidr_id_node))
- rb_erase(&cm_id_priv->sidr_id_node,
- &cm.remote_sidr_table);
- spin_unlock_irq(&cm.lock);
+ cm_send_sidr_rep_locked(cm_id_priv,
+ &(struct ib_cm_sidr_rep_param){
+ .status = IB_SIDR_REJECT });
+ /* cm_send_sidr_rep_locked will not move to IDLE if it fails */
+ cm_id->state = IB_CM_IDLE;
break;
case IB_CM_REQ_SENT:
case IB_CM_MRA_REQ_RCVD:
- ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
- spin_unlock_irq(&cm_id_priv->lock);
- ib_send_cm_rej(cm_id, IB_CM_REJ_TIMEOUT,
- &cm_id_priv->id.device->node_guid,
- sizeof cm_id_priv->id.device->node_guid,
- NULL, 0);
+ ib_cancel_mad(cm_id_priv->msg);
+ cm_send_rej_locked(cm_id_priv, IB_CM_REJ_TIMEOUT,
+ &cm_id_priv->id.device->node_guid,
+ sizeof(cm_id_priv->id.device->node_guid),
+ NULL, 0);
break;
case IB_CM_REQ_RCVD:
if (err == -ENOMEM) {
/* Do not reject to allow future retries. */
cm_reset_to_idle(cm_id_priv);
- spin_unlock_irq(&cm_id_priv->lock);
} else {
- spin_unlock_irq(&cm_id_priv->lock);
- ib_send_cm_rej(cm_id, IB_CM_REJ_CONSUMER_DEFINED,
- NULL, 0, NULL, 0);
+ cm_send_rej_locked(cm_id_priv,
+ IB_CM_REJ_CONSUMER_DEFINED, NULL, 0,
+ NULL, 0);
}
break;
case IB_CM_REP_SENT:
case IB_CM_MRA_REP_RCVD:
- ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
- /* Fall through */
+ ib_cancel_mad(cm_id_priv->msg);
+ cm_send_rej_locked(cm_id_priv, IB_CM_REJ_CONSUMER_DEFINED, NULL,
+ 0, NULL, 0);
+ goto retest;
case IB_CM_MRA_REQ_SENT:
case IB_CM_REP_RCVD:
case IB_CM_MRA_REP_SENT:
- spin_unlock_irq(&cm_id_priv->lock);
- ib_send_cm_rej(cm_id, IB_CM_REJ_CONSUMER_DEFINED,
- NULL, 0, NULL, 0);
+ cm_send_rej_locked(cm_id_priv, IB_CM_REJ_CONSUMER_DEFINED, NULL,
+ 0, NULL, 0);
break;
case IB_CM_ESTABLISHED:
- spin_unlock_irq(&cm_id_priv->lock);
- if (cm_id_priv->qp_type == IB_QPT_XRC_TGT)
+ if (cm_id_priv->qp_type == IB_QPT_XRC_TGT) {
+ cm_id->state = IB_CM_IDLE;
break;
- ib_send_cm_dreq(cm_id, NULL, 0);
+ }
+ cm_send_dreq_locked(cm_id_priv, NULL, 0);
goto retest;
case IB_CM_DREQ_SENT:
- ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
+ ib_cancel_mad(cm_id_priv->msg);
cm_enter_timewait(cm_id_priv);
- spin_unlock_irq(&cm_id_priv->lock);
- break;
+ goto retest;
case IB_CM_DREQ_RCVD:
- spin_unlock_irq(&cm_id_priv->lock);
- ib_send_cm_drep(cm_id, NULL, 0);
+ cm_send_drep_locked(cm_id_priv, NULL, 0);
+ WARN_ON(cm_id->state != IB_CM_TIMEWAIT);
+ goto retest;
+ case IB_CM_TIMEWAIT:
+ /*
+ * The cm_acquire_id in cm_timewait_handler will stop working
+ * once we do xa_erase below, so just move to idle here for
+ * consistency.
+ */
+ cm_id->state = IB_CM_IDLE;
break;
- default:
- spin_unlock_irq(&cm_id_priv->lock);
+ case IB_CM_IDLE:
break;
}
+ WARN_ON(cm_id->state != IB_CM_IDLE);
- spin_lock_irq(&cm.lock);
- if (!list_empty(&cm_id_priv->altr_list) &&
- (!cm_id_priv->altr_send_port_not_ready))
- list_del(&cm_id_priv->altr_list);
- if (!list_empty(&cm_id_priv->prim_list) &&
- (!cm_id_priv->prim_send_port_not_ready))
- list_del(&cm_id_priv->prim_list);
- spin_unlock_irq(&cm.lock);
+ spin_lock(&cm.lock);
+ /* Required for cleanup paths related cm_req_handler() */
+ if (cm_id_priv->timewait_info) {
+ cm_remove_remote(cm_id_priv);
+ kfree(cm_id_priv->timewait_info);
+ cm_id_priv->timewait_info = NULL;
+ }
- cm_free_id(cm_id->local_id);
+ WARN_ON(cm_id_priv->listen_sharecount);
+ WARN_ON(!RB_EMPTY_NODE(&cm_id_priv->service_node));
+ if (!RB_EMPTY_NODE(&cm_id_priv->sidr_id_node))
+ rb_erase(&cm_id_priv->sidr_id_node, &cm.remote_sidr_table);
+ spin_unlock(&cm.lock);
+ spin_unlock_irq(&cm_id_priv->lock);
+
+ xa_erase(&cm.local_id_table, cm_local_id(cm_id->local_id));
cm_deref_id(cm_id_priv);
wait_for_completion(&cm_id_priv->comp);
while ((work = cm_dequeue_work(cm_id_priv)) != NULL)
cm_free_work(work);
- rdma_destroy_ah_attr(&cm_id_priv->av.ah_attr);
- rdma_destroy_ah_attr(&cm_id_priv->alt_av.ah_attr);
+ cm_destroy_av(&cm_id_priv->av);
+ cm_destroy_av(&cm_id_priv->alt_av);
kfree(cm_id_priv->private_data);
kfree_rcu(cm_id_priv, rcu);
}
@@ -1087,70 +1151,63 @@ void ib_destroy_cm_id(struct ib_cm_id *cm_id)
}
EXPORT_SYMBOL(ib_destroy_cm_id);
+static int cm_init_listen(struct cm_id_private *cm_id_priv, __be64 service_id)
+{
+ if ((service_id & IB_SERVICE_ID_AGN_MASK) == IB_CM_ASSIGN_SERVICE_ID &&
+ (service_id != IB_CM_ASSIGN_SERVICE_ID))
+ return -EINVAL;
+
+ if (service_id == IB_CM_ASSIGN_SERVICE_ID)
+ cm_id_priv->id.service_id = cpu_to_be64(cm.listen_service_id++);
+ else
+ cm_id_priv->id.service_id = service_id;
+
+ return 0;
+}
+
/**
- * __ib_cm_listen - Initiates listening on the specified service ID for
+ * ib_cm_listen - Initiates listening on the specified service ID for
* connection and service ID resolution requests.
* @cm_id: Connection identifier associated with the listen request.
* @service_id: Service identifier matched against incoming connection
* and service ID resolution requests. The service ID should be specified
* network-byte order. If set to IB_CM_ASSIGN_SERVICE_ID, the CM will
* assign a service ID to the caller.
- * @service_mask: Mask applied to service ID used to listen across a
- * range of service IDs. If set to 0, the service ID is matched
- * exactly. This parameter is ignored if %service_id is set to
- * IB_CM_ASSIGN_SERVICE_ID.
*/
-static int __ib_cm_listen(struct ib_cm_id *cm_id, __be64 service_id,
- __be64 service_mask)
+int ib_cm_listen(struct ib_cm_id *cm_id, __be64 service_id)
{
- struct cm_id_private *cm_id_priv, *cur_cm_id_priv;
- int ret = 0;
-
- service_mask = service_mask ? service_mask : ~cpu_to_be64(0);
- service_id &= service_mask;
- if ((service_id & IB_SERVICE_ID_AGN_MASK) == IB_CM_ASSIGN_SERVICE_ID &&
- (service_id != IB_CM_ASSIGN_SERVICE_ID))
- return -EINVAL;
-
- cm_id_priv = container_of(cm_id, struct cm_id_private, id);
- if (cm_id->state != IB_CM_IDLE)
- return -EINVAL;
-
- cm_id->state = IB_CM_LISTEN;
- ++cm_id_priv->listen_sharecount;
+ struct cm_id_private *cm_id_priv =
+ container_of(cm_id, struct cm_id_private, id);
+ unsigned long flags;
+ int ret;
- if (service_id == IB_CM_ASSIGN_SERVICE_ID) {
- cm_id->service_id = cpu_to_be64(cm.listen_service_id++);
- cm_id->service_mask = ~cpu_to_be64(0);
- } else {
- cm_id->service_id = service_id;
- cm_id->service_mask = service_mask;
+ spin_lock_irqsave(&cm_id_priv->lock, flags);
+ if (cm_id_priv->id.state != IB_CM_IDLE) {
+ ret = -EINVAL;
+ goto out;
}
- cur_cm_id_priv = cm_insert_listen(cm_id_priv);
- if (cur_cm_id_priv) {
- cm_id->state = IB_CM_IDLE;
- --cm_id_priv->listen_sharecount;
+ ret = cm_init_listen(cm_id_priv, service_id);
+ if (ret)
+ goto out;
+
+ if (!cm_insert_listen(cm_id_priv, NULL)) {
ret = -EBUSY;
+ goto out;
}
- return ret;
-}
-
-int ib_cm_listen(struct ib_cm_id *cm_id, __be64 service_id, __be64 service_mask)
-{
- unsigned long flags;
- int ret;
- spin_lock_irqsave(&cm.lock, flags);
- ret = __ib_cm_listen(cm_id, service_id, service_mask);
- spin_unlock_irqrestore(&cm.lock, flags);
+ cm_id_priv->id.state = IB_CM_LISTEN;
+ ret = 0;
+out:
+ spin_unlock_irqrestore(&cm_id_priv->lock, flags);
return ret;
}
EXPORT_SYMBOL(ib_cm_listen);
/**
- * Create a new listening ib_cm_id and listen on the given service ID.
+ * ib_cm_insert_listen - Create a new listening ib_cm_id and listen on
+ * the given service ID.
*
* If there's an existing ID listening on that same device and service ID,
* return it.
@@ -1169,60 +1226,57 @@ struct ib_cm_id *ib_cm_insert_listen(struct ib_device *device,
ib_cm_handler cm_handler,
__be64 service_id)
{
+ struct cm_id_private *listen_id_priv;
struct cm_id_private *cm_id_priv;
- struct ib_cm_id *cm_id;
- unsigned long flags;
int err = 0;
/* Create an ID in advance, since the creation may sleep */
- cm_id = ib_create_cm_id(device, cm_handler, NULL);
- if (IS_ERR(cm_id))
- return cm_id;
+ cm_id_priv = cm_alloc_id_priv(device, cm_handler, NULL);
+ if (IS_ERR(cm_id_priv))
+ return ERR_CAST(cm_id_priv);
- spin_lock_irqsave(&cm.lock, flags);
+ err = cm_init_listen(cm_id_priv, service_id);
+ if (err) {
+ ib_destroy_cm_id(&cm_id_priv->id);
+ return ERR_PTR(err);
+ }
- if (service_id == IB_CM_ASSIGN_SERVICE_ID)
- goto new_id;
-
- /* Find an existing ID */
- cm_id_priv = cm_find_listen(device, service_id);
- if (cm_id_priv) {
- if (cm_id->cm_handler != cm_handler || cm_id->context) {
- /* Sharing an ib_cm_id with different handlers is not
- * supported */
- spin_unlock_irqrestore(&cm.lock, flags);
- ib_destroy_cm_id(cm_id);
+ spin_lock_irq(&cm_id_priv->lock);
+ listen_id_priv = cm_insert_listen(cm_id_priv, cm_handler);
+ if (listen_id_priv != cm_id_priv) {
+ spin_unlock_irq(&cm_id_priv->lock);
+ ib_destroy_cm_id(&cm_id_priv->id);
+ if (!listen_id_priv)
return ERR_PTR(-EINVAL);
- }
- refcount_inc(&cm_id_priv->refcount);
- ++cm_id_priv->listen_sharecount;
- spin_unlock_irqrestore(&cm.lock, flags);
-
- ib_destroy_cm_id(cm_id);
- cm_id = &cm_id_priv->id;
- return cm_id;
+ return &listen_id_priv->id;
}
+ cm_id_priv->id.state = IB_CM_LISTEN;
+ spin_unlock_irq(&cm_id_priv->lock);
-new_id:
- /* Use newly created ID */
- err = __ib_cm_listen(cm_id, service_id, 0);
-
- spin_unlock_irqrestore(&cm.lock, flags);
+ /*
+ * A listen ID does not need to be in the xarray since it does not
+ * receive mads, is not placed in the remote_id or remote_qpn rbtree,
+ * and does not enter timewait.
+ */
- if (err) {
- ib_destroy_cm_id(cm_id);
- return ERR_PTR(err);
- }
- return cm_id;
+ return &cm_id_priv->id;
}
EXPORT_SYMBOL(ib_cm_insert_listen);
static __be64 cm_form_tid(struct cm_id_private *cm_id_priv)
{
- u64 hi_tid, low_tid;
+ u64 hi_tid = 0, low_tid;
- hi_tid = ((u64) cm_id_priv->av.port->mad_agent->hi_tid) << 32;
- low_tid = (u64)cm_id_priv->id.local_id;
+ lockdep_assert_held(&cm_id_priv->lock);
+
+ low_tid = (u64)cm_id_priv->id.local_id;
+ if (!cm_id_priv->av.port)
+ return cpu_to_be64(low_tid);
+
+ spin_lock(&cm_id_priv->av.port->cm_dev->mad_agent_lock);
+ if (cm_id_priv->av.port->mad_agent)
+ hi_tid = ((u64)cm_id_priv->av.port->mad_agent->hi_tid) << 32;
+ spin_unlock(&cm_id_priv->av.port->cm_dev->mad_agent_lock);
return cpu_to_be64(hi_tid | low_tid);
}
@@ -1237,6 +1291,13 @@ static void cm_format_mad_hdr(struct ib_mad_hdr *hdr,
hdr->tid = tid;
}
+static void cm_format_mad_ece_hdr(struct ib_mad_hdr *hdr, __be16 attr_id,
+ __be64 tid, u32 attr_mod)
+{
+ cm_format_mad_hdr(hdr, attr_id, tid);
+ hdr->attr_mod = cpu_to_be32(attr_mod);
+}
+
static void cm_format_req(struct cm_req_msg *req_msg,
struct cm_id_private *cm_id_priv,
struct ib_cm_req_param *param)
@@ -1244,13 +1305,14 @@ static void cm_format_req(struct cm_req_msg *req_msg,
struct sa_path_rec *pri_path = param->primary_path;
struct sa_path_rec *alt_path = param->alternate_path;
bool pri_ext = false;
+ __be16 lid;
if (pri_path->rec_type == SA_PATH_REC_TYPE_OPA)
pri_ext = opa_is_extended_lid(pri_path->opa.dlid,
pri_path->opa.slid);
- cm_format_mad_hdr(&req_msg->hdr, CM_REQ_ATTR_ID,
- cm_form_tid(cm_id_priv));
+ cm_format_mad_ece_hdr(&req_msg->hdr, CM_REQ_ATTR_ID,
+ cm_form_tid(cm_id_priv), param->ece.attr_mod);
IBA_SET(CM_REQ_LOCAL_COMM_ID, req_msg,
be32_to_cpu(cm_id_priv->id.local_id));
@@ -1303,9 +1365,16 @@ static void cm_format_req(struct cm_req_msg *req_msg,
htons(ntohl(sa_path_get_dlid(
pri_path)))));
} else {
+
+ if (param->primary_path_inbound) {
+ lid = param->primary_path_inbound->ib.dlid;
+ IBA_SET(CM_REQ_PRIMARY_LOCAL_PORT_LID, req_msg,
+ be16_to_cpu(lid));
+ } else
+ IBA_SET(CM_REQ_PRIMARY_LOCAL_PORT_LID, req_msg,
+ be16_to_cpu(IB_LID_PERMISSIVE));
+
/* Work-around until there's a way to obtain remote LID info */
- IBA_SET(CM_REQ_PRIMARY_LOCAL_PORT_LID, req_msg,
- be16_to_cpu(IB_LID_PERMISSIVE));
IBA_SET(CM_REQ_PRIMARY_REMOTE_PORT_LID, req_msg,
be16_to_cpu(IB_LID_PERMISSIVE));
}
@@ -1373,6 +1442,7 @@ static void cm_format_req(struct cm_req_msg *req_msg,
cm_ack_timeout(cm_id_priv->av.port->cm_dev->ack_delay,
alt_path->packet_life_time));
}
+ IBA_SET(CM_REQ_VENDOR_ID, req_msg, param->ece.vendor_id);
if (param->private_data && param->private_data_len)
IBA_SET_MEM(CM_REQ_PRIVATE_DATA, req_msg, param->private_data,
@@ -1381,10 +1451,6 @@ static void cm_format_req(struct cm_req_msg *req_msg,
static int cm_validate_req_param(struct ib_cm_req_param *param)
{
- /* peer-to-peer not supported */
- if (param->peer_to_peer)
- return -EINVAL;
-
if (!param->primary_path)
return -EINVAL;
@@ -1407,7 +1473,9 @@ static int cm_validate_req_param(struct ib_cm_req_param *param)
int ib_send_cm_req(struct ib_cm_id *cm_id,
struct ib_cm_req_param *param)
{
+ struct cm_av av = {}, alt_av = {};
struct cm_id_private *cm_id_priv;
+ struct ib_mad_send_buf *msg;
struct cm_req_msg *req_msg;
unsigned long flags;
int ret;
@@ -1419,10 +1487,9 @@ int ib_send_cm_req(struct ib_cm_id *cm_id,
/* Verify that we're not in timewait. */
cm_id_priv = container_of(cm_id, struct cm_id_private, id);
spin_lock_irqsave(&cm_id_priv->lock, flags);
- if (cm_id->state != IB_CM_IDLE) {
+ if (cm_id->state != IB_CM_IDLE || WARN_ON(cm_id_priv->timewait_info)) {
spin_unlock_irqrestore(&cm_id_priv->lock, flags);
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
spin_unlock_irqrestore(&cm_id_priv->lock, flags);
@@ -1430,22 +1497,23 @@ int ib_send_cm_req(struct ib_cm_id *cm_id,
id.local_id);
if (IS_ERR(cm_id_priv->timewait_info)) {
ret = PTR_ERR(cm_id_priv->timewait_info);
- goto out;
+ cm_id_priv->timewait_info = NULL;
+ return ret;
}
ret = cm_init_av_by_path(param->primary_path,
- param->ppath_sgid_attr, &cm_id_priv->av,
- cm_id_priv);
+ param->ppath_sgid_attr, &av);
if (ret)
- goto error1;
+ return ret;
if (param->alternate_path) {
ret = cm_init_av_by_path(param->alternate_path, NULL,
- &cm_id_priv->alt_av, cm_id_priv);
- if (ret)
- goto error1;
+ &alt_av);
+ if (ret) {
+ cm_destroy_av(&av);
+ return ret;
+ }
}
cm_id->service_id = param->service_id;
- cm_id->service_mask = ~cpu_to_be64(0);
cm_id_priv->timeout_ms = cm_convert_to_ms(
param->primary_path->packet_life_time) * 2 +
cm_convert_to_ms(
@@ -1458,33 +1526,44 @@ int ib_send_cm_req(struct ib_cm_id *cm_id,
cm_id_priv->pkey = param->primary_path->pkey;
cm_id_priv->qp_type = param->qp_type;
- ret = cm_alloc_msg(cm_id_priv, &cm_id_priv->msg);
- if (ret)
- goto error1;
+ spin_lock_irqsave(&cm_id_priv->lock, flags);
+
+ cm_move_av_from_path(&cm_id_priv->av, &av);
+ if (param->primary_path_outbound)
+ cm_id_priv->av.dlid_datapath =
+ be16_to_cpu(param->primary_path_outbound->ib.dlid);
+
+ if (param->alternate_path)
+ cm_move_av_from_path(&cm_id_priv->alt_av, &alt_av);
- req_msg = (struct cm_req_msg *) cm_id_priv->msg->mad;
+ msg = cm_alloc_priv_msg(cm_id_priv);
+ if (IS_ERR(msg)) {
+ ret = PTR_ERR(msg);
+ goto out_unlock;
+ }
+
+ req_msg = (struct cm_req_msg *)msg->mad;
cm_format_req(req_msg, cm_id_priv, param);
cm_id_priv->tid = req_msg->hdr.tid;
- cm_id_priv->msg->timeout_ms = cm_id_priv->timeout_ms;
- cm_id_priv->msg->context[1] = (void *) (unsigned long) IB_CM_REQ_SENT;
+ msg->timeout_ms = cm_id_priv->timeout_ms;
+ msg->context[1] = (void *)(unsigned long)IB_CM_REQ_SENT;
cm_id_priv->local_qpn = cpu_to_be32(IBA_GET(CM_REQ_LOCAL_QPN, req_msg));
cm_id_priv->rq_psn = cpu_to_be32(IBA_GET(CM_REQ_STARTING_PSN, req_msg));
- spin_lock_irqsave(&cm_id_priv->lock, flags);
- ret = ib_post_send_mad(cm_id_priv->msg, NULL);
- if (ret) {
- spin_unlock_irqrestore(&cm_id_priv->lock, flags);
- goto error2;
- }
+ trace_icm_send_req(&cm_id_priv->id);
+ ret = ib_post_send_mad(msg, NULL);
+ if (ret)
+ goto out_free;
BUG_ON(cm_id->state != IB_CM_IDLE);
cm_id->state = IB_CM_REQ_SENT;
spin_unlock_irqrestore(&cm_id_priv->lock, flags);
return 0;
-
-error2: cm_free_msg(cm_id_priv->msg);
-error1: kfree(cm_id_priv->timewait_info);
-out: return ret;
+out_free:
+ cm_free_priv_msg(msg);
+out_unlock:
+ spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+ return ret;
}
EXPORT_SYMBOL(ib_send_cm_req);
@@ -1519,9 +1598,12 @@ static int cm_issue_rej(struct cm_port *port,
IBA_SET_MEM(CM_REJ_ARI, rej_msg, ari, ari_length);
}
+ trace_icm_issue_rej(
+ IBA_GET(CM_REJ_LOCAL_COMM_ID, rcv_msg),
+ IBA_GET(CM_REJ_REMOTE_COMM_ID, rcv_msg));
ret = ib_post_send_mad(msg, NULL);
if (ret)
- cm_free_msg(msg);
+ cm_free_response_msg(msg);
return ret;
}
@@ -1534,7 +1616,7 @@ static bool cm_req_has_alt_path(struct cm_req_msg *req_msg)
req_msg))));
}
-static void cm_path_set_rec_type(struct ib_device *ib_device, u8 port_num,
+static void cm_path_set_rec_type(struct ib_device *ib_device, u32 port_num,
struct sa_path_rec *path, union ib_gid *gid)
{
if (ib_is_opa_gid(gid) && rdma_cap_opa_ah(ib_device, port_num))
@@ -1545,14 +1627,13 @@ static void cm_path_set_rec_type(struct ib_device *ib_device, u8 port_num,
static void cm_format_path_lid_from_req(struct cm_req_msg *req_msg,
struct sa_path_rec *primary_path,
- struct sa_path_rec *alt_path)
+ struct sa_path_rec *alt_path,
+ struct ib_wc *wc)
{
u32 lid;
if (primary_path->rec_type != SA_PATH_REC_TYPE_OPA) {
- sa_path_set_dlid(primary_path,
- IBA_GET(CM_REQ_PRIMARY_LOCAL_PORT_LID,
- req_msg));
+ sa_path_set_dlid(primary_path, wc->slid);
sa_path_set_slid(primary_path,
IBA_GET(CM_REQ_PRIMARY_REMOTE_PORT_LID,
req_msg));
@@ -1589,7 +1670,8 @@ static void cm_format_path_lid_from_req(struct cm_req_msg *req_msg,
static void cm_format_paths_from_req(struct cm_req_msg *req_msg,
struct sa_path_rec *primary_path,
- struct sa_path_rec *alt_path)
+ struct sa_path_rec *alt_path,
+ struct ib_wc *wc)
{
primary_path->dgid =
*IBA_GET_MEM_PTR(CM_REQ_PRIMARY_LOCAL_PORT_GID, req_msg);
@@ -1647,20 +1729,20 @@ static void cm_format_paths_from_req(struct cm_req_msg *req_msg,
if (sa_path_is_roce(alt_path))
alt_path->roce.route_resolved = false;
}
- cm_format_path_lid_from_req(req_msg, primary_path, alt_path);
+ cm_format_path_lid_from_req(req_msg, primary_path, alt_path, wc);
}
static u16 cm_get_bth_pkey(struct cm_work *work)
{
struct ib_device *ib_dev = work->port->cm_dev->ib_device;
- u8 port_num = work->port->port_num;
+ u32 port_num = work->port->port_num;
u16 pkey_index = work->mad_recv_wc->wc->pkey_index;
u16 pkey;
int ret;
ret = ib_get_cached_pkey(ib_dev, port_num, pkey_index, &pkey);
if (ret) {
- dev_warn_ratelimited(&ib_dev->dev, "ib_cm: Couldn't retrieve pkey for incoming request (port %d, pkey index %d). %d\n",
+ dev_warn_ratelimited(&ib_dev->dev, "ib_cm: Couldn't retrieve pkey for incoming request (port %u, pkey index %u). %d\n",
port_num, pkey_index, ret);
return 0;
}
@@ -1669,7 +1751,7 @@ static u16 cm_get_bth_pkey(struct cm_work *work)
}
/**
- * Convert OPA SGID to IB SGID
+ * cm_opa_to_ib_sgid - Convert OPA SGID to IB SGID
* ULPs (such as IPoIB) do not understand OPA GIDs and will
* reject them as the local_gid will not match the sgid. Therefore,
* change the pathrec's SGID to an IB SGID.
@@ -1681,7 +1763,7 @@ static void cm_opa_to_ib_sgid(struct cm_work *work,
struct sa_path_rec *path)
{
struct ib_device *dev = work->port->cm_dev->ib_device;
- u8 port_num = work->port->port_num;
+ u32 port_num = work->port->port_num;
if (rdma_cap_opa_ah(dev, port_num) &&
(ib_is_opa_gid(&path->sgid))) {
@@ -1734,6 +1816,9 @@ static void cm_format_req_event(struct cm_work *work,
param->rnr_retry_count = IBA_GET(CM_REQ_RNR_RETRY_COUNT, req_msg);
param->srq = IBA_GET(CM_REQ_SRQ, req_msg);
param->ppath_sgid_attr = cm_id_priv->av.ah_attr.grh.sgid_attr;
+ param->ece.vendor_id = IBA_GET(CM_REQ_VENDOR_ID, req_msg);
+ param->ece.attr_mod = be32_to_cpu(req_msg->hdr.attr_mod);
+
work->cm_event.private_data =
IBA_GET_MEM_PTR(CM_REQ_PRIVATE_DATA, req_msg);
}
@@ -1783,17 +1868,17 @@ static void cm_format_mra(struct cm_mra_msg *mra_msg,
static void cm_format_rej(struct cm_rej_msg *rej_msg,
struct cm_id_private *cm_id_priv,
- enum ib_cm_rej_reason reason,
- void *ari,
- u8 ari_length,
- const void *private_data,
- u8 private_data_len)
+ enum ib_cm_rej_reason reason, void *ari,
+ u8 ari_length, const void *private_data,
+ u8 private_data_len, enum ib_cm_state state)
{
+ lockdep_assert_held(&cm_id_priv->lock);
+
cm_format_mad_hdr(&rej_msg->hdr, CM_REJ_ATTR_ID, cm_id_priv->tid);
IBA_SET(CM_REJ_REMOTE_COMM_ID, rej_msg,
be32_to_cpu(cm_id_priv->id.remote_id));
- switch(cm_id_priv->id.state) {
+ switch (state) {
case IB_CM_REQ_RCVD:
IBA_SET(CM_REJ_LOCAL_COMM_ID, rej_msg, be32_to_cpu(0));
IBA_SET(CM_REJ_MESSAGE_REJECTED, rej_msg, CM_MSG_RESPONSE_REQ);
@@ -1834,12 +1919,16 @@ static void cm_dup_req_handler(struct cm_work *work,
struct ib_mad_send_buf *msg = NULL;
int ret;
- atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
- counter[CM_REQ_COUNTER]);
+ atomic_long_inc(
+ &work->port->counters[CM_RECV_DUPLICATES][CM_REQ_COUNTER]);
/* Quick state check to discard duplicate REQs. */
- if (cm_id_priv->id.state == IB_CM_REQ_RCVD)
+ spin_lock_irq(&cm_id_priv->lock);
+ if (cm_id_priv->id.state == IB_CM_REQ_RCVD) {
+ spin_unlock_irq(&cm_id_priv->lock);
return;
+ }
+ spin_unlock_irq(&cm_id_priv->lock);
ret = cm_alloc_response_msg(work->port, work->mad_recv_wc, &msg);
if (ret)
@@ -1854,30 +1943,31 @@ static void cm_dup_req_handler(struct cm_work *work,
cm_id_priv->private_data_len);
break;
case IB_CM_TIMEWAIT:
- cm_format_rej((struct cm_rej_msg *) msg->mad, cm_id_priv,
- IB_CM_REJ_STALE_CONN, NULL, 0, NULL, 0);
+ cm_format_rej((struct cm_rej_msg *)msg->mad, cm_id_priv,
+ IB_CM_REJ_STALE_CONN, NULL, 0, NULL, 0,
+ IB_CM_TIMEWAIT);
break;
default:
goto unlock;
}
spin_unlock_irq(&cm_id_priv->lock);
+ trace_icm_send_dup_req(&cm_id_priv->id);
ret = ib_post_send_mad(msg, NULL);
if (ret)
goto free;
return;
unlock: spin_unlock_irq(&cm_id_priv->lock);
-free: cm_free_msg(msg);
+free: cm_free_response_msg(msg);
}
-static struct cm_id_private * cm_match_req(struct cm_work *work,
- struct cm_id_private *cm_id_priv)
+static struct cm_id_private *cm_match_req(struct cm_work *work,
+ struct cm_id_private *cm_id_priv)
{
struct cm_id_private *listen_cm_id_priv, *cur_cm_id_priv;
struct cm_timewait_info *timewait_info;
struct cm_req_msg *req_msg;
- struct ib_cm_id *cm_id;
req_msg = (struct cm_req_msg *)work->mad_recv_wc->recv_buf.mad;
@@ -1898,7 +1988,7 @@ static struct cm_id_private * cm_match_req(struct cm_work *work,
/* Check for stale connections. */
timewait_info = cm_insert_remote_qpn(cm_id_priv->timewait_info);
if (timewait_info) {
- cm_cleanup_timewait(cm_id_priv->timewait_info);
+ cm_remove_remote(cm_id_priv);
cur_cm_id_priv = cm_acquire_id(timewait_info->work.local_id,
timewait_info->work.remote_id);
@@ -1907,8 +1997,7 @@ static struct cm_id_private * cm_match_req(struct cm_work *work,
IB_CM_REJ_STALE_CONN, CM_MSG_RESPONSE_REQ,
NULL, 0);
if (cur_cm_id_priv) {
- cm_id = &cur_cm_id_priv->id;
- ib_send_cm_dreq(cm_id, NULL, 0);
+ ib_send_cm_dreq(&cur_cm_id_priv->id, NULL, 0);
cm_deref_id(cur_cm_id_priv);
}
return NULL;
@@ -1919,19 +2008,14 @@ static struct cm_id_private * cm_match_req(struct cm_work *work,
cm_id_priv->id.device,
cpu_to_be64(IBA_GET(CM_REQ_SERVICE_ID, req_msg)));
if (!listen_cm_id_priv) {
- cm_cleanup_timewait(cm_id_priv->timewait_info);
+ cm_remove_remote(cm_id_priv);
spin_unlock_irq(&cm.lock);
cm_issue_rej(work->port, work->mad_recv_wc,
IB_CM_REJ_INVALID_SERVICE_ID, CM_MSG_RESPONSE_REQ,
NULL, 0);
- goto out;
+ return NULL;
}
- refcount_inc(&listen_cm_id_priv->refcount);
- refcount_inc(&cm_id_priv->refcount);
- cm_id_priv->id.state = IB_CM_REQ_RCVD;
- atomic_inc(&cm_id_priv->work_count);
spin_unlock_irq(&cm.lock);
-out:
return listen_cm_id_priv;
}
@@ -1973,7 +2057,6 @@ static void cm_process_routed_req(struct cm_req_msg *req_msg, struct ib_wc *wc)
static int cm_req_handler(struct cm_work *work)
{
- struct ib_cm_id *cm_id;
struct cm_id_private *cm_id_priv, *listen_cm_id_priv;
struct cm_req_msg *req_msg;
const struct ib_global_route *grh;
@@ -1982,13 +2065,32 @@ static int cm_req_handler(struct cm_work *work)
req_msg = (struct cm_req_msg *)work->mad_recv_wc->recv_buf.mad;
- cm_id = ib_create_cm_id(work->port->cm_dev->ib_device, NULL, NULL);
- if (IS_ERR(cm_id))
- return PTR_ERR(cm_id);
+ cm_id_priv =
+ cm_alloc_id_priv(work->port->cm_dev->ib_device, NULL, NULL);
+ if (IS_ERR(cm_id_priv))
+ return PTR_ERR(cm_id_priv);
- cm_id_priv = container_of(cm_id, struct cm_id_private, id);
cm_id_priv->id.remote_id =
cpu_to_be32(IBA_GET(CM_REQ_LOCAL_COMM_ID, req_msg));
+ cm_id_priv->id.service_id =
+ cpu_to_be64(IBA_GET(CM_REQ_SERVICE_ID, req_msg));
+ cm_id_priv->tid = req_msg->hdr.tid;
+ cm_id_priv->timeout_ms = cm_convert_to_ms(
+ IBA_GET(CM_REQ_LOCAL_CM_RESPONSE_TIMEOUT, req_msg));
+ cm_id_priv->max_cm_retries = IBA_GET(CM_REQ_MAX_CM_RETRIES, req_msg);
+ cm_id_priv->remote_qpn =
+ cpu_to_be32(IBA_GET(CM_REQ_LOCAL_QPN, req_msg));
+ cm_id_priv->initiator_depth =
+ IBA_GET(CM_REQ_RESPONDER_RESOURCES, req_msg);
+ cm_id_priv->responder_resources =
+ IBA_GET(CM_REQ_INITIATOR_DEPTH, req_msg);
+ cm_id_priv->path_mtu = IBA_GET(CM_REQ_PATH_PACKET_PAYLOAD_MTU, req_msg);
+ cm_id_priv->pkey = cpu_to_be16(IBA_GET(CM_REQ_PARTITION_KEY, req_msg));
+ cm_id_priv->sq_psn = cpu_to_be32(IBA_GET(CM_REQ_STARTING_PSN, req_msg));
+ cm_id_priv->retry_count = IBA_GET(CM_REQ_RETRY_COUNT, req_msg);
+ cm_id_priv->rnr_retry_count = IBA_GET(CM_REQ_RNR_RETRY_COUNT, req_msg);
+ cm_id_priv->qp_type = cm_req_get_qp_type(req_msg);
+
ret = cm_init_av_for_response(work->port, work->mad_recv_wc->wc,
work->mad_recv_wc->recv_buf.grh,
&cm_id_priv->av);
@@ -1998,43 +2100,39 @@ static int cm_req_handler(struct cm_work *work)
id.local_id);
if (IS_ERR(cm_id_priv->timewait_info)) {
ret = PTR_ERR(cm_id_priv->timewait_info);
+ cm_id_priv->timewait_info = NULL;
goto destroy;
}
- cm_id_priv->timewait_info->work.remote_id =
- cpu_to_be32(IBA_GET(CM_REQ_LOCAL_COMM_ID, req_msg));
+ cm_id_priv->timewait_info->work.remote_id = cm_id_priv->id.remote_id;
cm_id_priv->timewait_info->remote_ca_guid =
cpu_to_be64(IBA_GET(CM_REQ_LOCAL_CA_GUID, req_msg));
- cm_id_priv->timewait_info->remote_qpn =
- cpu_to_be32(IBA_GET(CM_REQ_LOCAL_QPN, req_msg));
+ cm_id_priv->timewait_info->remote_qpn = cm_id_priv->remote_qpn;
+
+ /*
+ * Note that the ID pointer is not in the xarray at this point,
+ * so this set is only visible to the local thread.
+ */
+ cm_id_priv->id.state = IB_CM_REQ_RCVD;
listen_cm_id_priv = cm_match_req(work, cm_id_priv);
if (!listen_cm_id_priv) {
- pr_debug("%s: local_id %d, no listen_cm_id_priv\n", __func__,
- be32_to_cpu(cm_id->local_id));
+ trace_icm_no_listener_err(&cm_id_priv->id);
+ cm_id_priv->id.state = IB_CM_IDLE;
ret = -EINVAL;
- goto free_timeinfo;
+ goto destroy;
}
- cm_id_priv->id.cm_handler = listen_cm_id_priv->id.cm_handler;
- cm_id_priv->id.context = listen_cm_id_priv->id.context;
- cm_id_priv->id.service_id =
- cpu_to_be64(IBA_GET(CM_REQ_SERVICE_ID, req_msg));
- cm_id_priv->id.service_mask = ~cpu_to_be64(0);
-
- cm_process_routed_req(req_msg, work->mad_recv_wc->wc);
-
memset(&work->path[0], 0, sizeof(work->path[0]));
if (cm_req_has_alt_path(req_msg))
memset(&work->path[1], 0, sizeof(work->path[1]));
grh = rdma_ah_read_grh(&cm_id_priv->av.ah_attr);
gid_attr = grh->sgid_attr;
- if (gid_attr &&
- rdma_protocol_roce(work->port->cm_dev->ib_device,
- work->port->port_num)) {
+ if (cm_id_priv->av.ah_attr.type == RDMA_AH_ATTR_TYPE_ROCE) {
work->path[0].rec_type =
sa_conv_gid_to_pathrec_type(gid_attr->gid_type);
} else {
+ cm_process_routed_req(req_msg, work->mad_recv_wc->wc);
cm_path_set_rec_type(
work->port->cm_dev->ib_device, work->port->port_num,
&work->path[0],
@@ -2044,13 +2142,15 @@ static int cm_req_handler(struct cm_work *work)
if (cm_req_has_alt_path(req_msg))
work->path[1].rec_type = work->path[0].rec_type;
cm_format_paths_from_req(req_msg, &work->path[0],
- &work->path[1]);
+ &work->path[1], work->mad_recv_wc->wc);
if (cm_id_priv->av.ah_attr.type == RDMA_AH_ATTR_TYPE_ROCE)
sa_path_set_dmac(&work->path[0],
cm_id_priv->av.ah_attr.roce.dmac);
work->path[0].hop_limit = grh->hop_limit;
- ret = cm_init_av_by_path(&work->path[0], gid_attr, &cm_id_priv->av,
- cm_id_priv);
+
+ /* This destroy call is needed to pair with cm_init_av_for_response */
+ cm_destroy_av(&cm_id_priv->av);
+ ret = cm_init_av_by_path(&work->path[0], gid_attr, &cm_id_priv->av);
if (ret) {
int err;
@@ -2058,54 +2158,55 @@ static int cm_req_handler(struct cm_work *work)
work->port->port_num, 0,
&work->path[0].sgid);
if (err)
- ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_GID,
+ ib_send_cm_rej(&cm_id_priv->id, IB_CM_REJ_INVALID_GID,
NULL, 0, NULL, 0);
else
- ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_GID,
+ ib_send_cm_rej(&cm_id_priv->id, IB_CM_REJ_INVALID_GID,
&work->path[0].sgid,
sizeof(work->path[0].sgid),
NULL, 0);
goto rejected;
}
+ if (cm_id_priv->av.ah_attr.type == RDMA_AH_ATTR_TYPE_IB)
+ cm_id_priv->av.dlid_datapath =
+ IBA_GET(CM_REQ_PRIMARY_LOCAL_PORT_LID, req_msg);
+
if (cm_req_has_alt_path(req_msg)) {
ret = cm_init_av_by_path(&work->path[1], NULL,
- &cm_id_priv->alt_av, cm_id_priv);
+ &cm_id_priv->alt_av);
if (ret) {
- ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_ALT_GID,
+ ib_send_cm_rej(&cm_id_priv->id,
+ IB_CM_REJ_INVALID_ALT_GID,
&work->path[0].sgid,
sizeof(work->path[0].sgid), NULL, 0);
goto rejected;
}
}
- cm_id_priv->tid = req_msg->hdr.tid;
- cm_id_priv->timeout_ms = cm_convert_to_ms(
- IBA_GET(CM_REQ_LOCAL_CM_RESPONSE_TIMEOUT, req_msg));
- cm_id_priv->max_cm_retries = IBA_GET(CM_REQ_MAX_CM_RETRIES, req_msg);
- cm_id_priv->remote_qpn =
- cpu_to_be32(IBA_GET(CM_REQ_LOCAL_QPN, req_msg));
- cm_id_priv->initiator_depth =
- IBA_GET(CM_REQ_RESPONDER_RESOURCES, req_msg);
- cm_id_priv->responder_resources =
- IBA_GET(CM_REQ_INITIATOR_DEPTH, req_msg);
- cm_id_priv->path_mtu = IBA_GET(CM_REQ_PATH_PACKET_PAYLOAD_MTU, req_msg);
- cm_id_priv->pkey = cpu_to_be16(IBA_GET(CM_REQ_PARTITION_KEY, req_msg));
- cm_id_priv->sq_psn = cpu_to_be32(IBA_GET(CM_REQ_STARTING_PSN, req_msg));
- cm_id_priv->retry_count = IBA_GET(CM_REQ_RETRY_COUNT, req_msg);
- cm_id_priv->rnr_retry_count = IBA_GET(CM_REQ_RNR_RETRY_COUNT, req_msg);
- cm_id_priv->qp_type = cm_req_get_qp_type(req_msg);
+ cm_id_priv->id.cm_handler = listen_cm_id_priv->id.cm_handler;
+ cm_id_priv->id.context = listen_cm_id_priv->id.context;
cm_format_req_event(work, cm_id_priv, &listen_cm_id_priv->id);
- cm_process_work(cm_id_priv, work);
+
+ /* Now MAD handlers can see the new ID */
+ spin_lock_irq(&cm_id_priv->lock);
+ cm_finalize_id(cm_id_priv);
+
+ /* Refcount belongs to the event, pairs with cm_process_work() */
+ refcount_inc(&cm_id_priv->refcount);
+ cm_queue_work_unlock(cm_id_priv, work);
+ /*
+ * Since this ID was just created and was not made visible to other MAD
+ * handlers until the cm_finalize_id() above we know that the
+ * cm_process_work() will deliver the event and the listen_cm_id
+ * embedded in the event can be derefed here.
+ */
cm_deref_id(listen_cm_id_priv);
return 0;
rejected:
- refcount_dec(&cm_id_priv->refcount);
cm_deref_id(listen_cm_id_priv);
-free_timeinfo:
- kfree(cm_id_priv->timewait_info);
destroy:
- ib_destroy_cm_id(cm_id);
+ ib_destroy_cm_id(&cm_id_priv->id);
return ret;
}
@@ -2113,7 +2214,8 @@ static void cm_format_rep(struct cm_rep_msg *rep_msg,
struct cm_id_private *cm_id_priv,
struct ib_cm_rep_param *param)
{
- cm_format_mad_hdr(&rep_msg->hdr, CM_REP_ATTR_ID, cm_id_priv->tid);
+ cm_format_mad_ece_hdr(&rep_msg->hdr, CM_REP_ATTR_ID, cm_id_priv->tid,
+ param->ece.attr_mod);
IBA_SET(CM_REP_LOCAL_COMM_ID, rep_msg,
be32_to_cpu(cm_id_priv->id.local_id));
IBA_SET(CM_REP_REMOTE_COMM_ID, rep_msg,
@@ -2140,6 +2242,10 @@ static void cm_format_rep(struct cm_rep_msg *rep_msg,
IBA_SET(CM_REP_LOCAL_EE_CONTEXT_NUMBER, rep_msg, param->qp_num);
}
+ IBA_SET(CM_REP_VENDOR_ID_L, rep_msg, param->ece.vendor_id);
+ IBA_SET(CM_REP_VENDOR_ID_M, rep_msg, param->ece.vendor_id >> 8);
+ IBA_SET(CM_REP_VENDOR_ID_H, rep_msg, param->ece.vendor_id >> 16);
+
if (param->private_data && param->private_data_len)
IBA_SET_MEM(CM_REP_PRIVATE_DATA, rep_msg, param->private_data,
param->private_data_len);
@@ -2162,36 +2268,42 @@ int ib_send_cm_rep(struct ib_cm_id *cm_id,
spin_lock_irqsave(&cm_id_priv->lock, flags);
if (cm_id->state != IB_CM_REQ_RCVD &&
cm_id->state != IB_CM_MRA_REQ_SENT) {
- pr_debug("%s: local_comm_id %d, cm_id->state: %d\n", __func__,
- be32_to_cpu(cm_id_priv->id.local_id), cm_id->state);
+ trace_icm_send_rep_err(cm_id_priv->id.local_id, cm_id->state);
ret = -EINVAL;
goto out;
}
- ret = cm_alloc_msg(cm_id_priv, &msg);
- if (ret)
+ msg = cm_alloc_priv_msg(cm_id_priv);
+ if (IS_ERR(msg)) {
+ ret = PTR_ERR(msg);
goto out;
+ }
rep_msg = (struct cm_rep_msg *) msg->mad;
cm_format_rep(rep_msg, cm_id_priv, param);
msg->timeout_ms = cm_id_priv->timeout_ms;
msg->context[1] = (void *) (unsigned long) IB_CM_REP_SENT;
+ trace_icm_send_rep(cm_id);
ret = ib_post_send_mad(msg, NULL);
- if (ret) {
- spin_unlock_irqrestore(&cm_id_priv->lock, flags);
- cm_free_msg(msg);
- return ret;
- }
+ if (ret)
+ goto out_free;
cm_id->state = IB_CM_REP_SENT;
- cm_id_priv->msg = msg;
cm_id_priv->initiator_depth = param->initiator_depth;
cm_id_priv->responder_resources = param->responder_resources;
cm_id_priv->rq_psn = cpu_to_be32(IBA_GET(CM_REP_STARTING_PSN, rep_msg));
+ WARN_ONCE(param->qp_num & 0xFF000000,
+ "IBTA declares QPN to be 24 bits, but it is 0x%X\n",
+ param->qp_num);
cm_id_priv->local_qpn = cpu_to_be32(param->qp_num & 0xFFFFFF);
+ spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+ return 0;
-out: spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+out_free:
+ cm_free_priv_msg(msg);
+out:
+ spin_unlock_irqrestore(&cm_id_priv->lock, flags);
return ret;
}
EXPORT_SYMBOL(ib_send_cm_rep);
@@ -2233,19 +2345,21 @@ int ib_send_cm_rtu(struct ib_cm_id *cm_id,
spin_lock_irqsave(&cm_id_priv->lock, flags);
if (cm_id->state != IB_CM_REP_RCVD &&
cm_id->state != IB_CM_MRA_REP_SENT) {
- pr_debug("%s: local_id %d, cm_id->state %d\n", __func__,
- be32_to_cpu(cm_id->local_id), cm_id->state);
+ trace_icm_send_cm_rtu_err(cm_id);
ret = -EINVAL;
goto error;
}
- ret = cm_alloc_msg(cm_id_priv, &msg);
- if (ret)
+ msg = cm_alloc_msg(cm_id_priv);
+ if (IS_ERR(msg)) {
+ ret = PTR_ERR(msg);
goto error;
+ }
cm_format_rtu((struct cm_rtu_msg *) msg->mad, cm_id_priv,
private_data, private_data_len);
+ trace_icm_send_rtu(cm_id);
ret = ib_post_send_mad(msg, NULL);
if (ret) {
spin_unlock_irqrestore(&cm_id_priv->lock, flags);
@@ -2284,6 +2398,11 @@ static void cm_format_rep_event(struct cm_work *work, enum ib_qp_type qp_type)
param->flow_control = IBA_GET(CM_REP_END_TO_END_FLOW_CONTROL, rep_msg);
param->rnr_retry_count = IBA_GET(CM_REP_RNR_RETRY_COUNT, rep_msg);
param->srq = IBA_GET(CM_REP_SRQ, rep_msg);
+ param->ece.vendor_id = IBA_GET(CM_REP_VENDOR_ID_H, rep_msg) << 16;
+ param->ece.vendor_id |= IBA_GET(CM_REP_VENDOR_ID_M, rep_msg) << 8;
+ param->ece.vendor_id |= IBA_GET(CM_REP_VENDOR_ID_L, rep_msg);
+ param->ece.attr_mod = be32_to_cpu(rep_msg->hdr.attr_mod);
+
work->cm_event.private_data =
IBA_GET_MEM_PTR(CM_REP_PRIVATE_DATA, rep_msg);
}
@@ -2302,8 +2421,8 @@ static void cm_dup_rep_handler(struct cm_work *work)
if (!cm_id_priv)
return;
- atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
- counter[CM_REP_COUNTER]);
+ atomic_long_inc(
+ &work->port->counters[CM_RECV_DUPLICATES][CM_REP_COUNTER]);
ret = cm_alloc_response_msg(work->port, work->mad_recv_wc, &msg);
if (ret)
goto deref;
@@ -2322,13 +2441,14 @@ static void cm_dup_rep_handler(struct cm_work *work)
goto unlock;
spin_unlock_irq(&cm_id_priv->lock);
+ trace_icm_send_dup_rep(&cm_id_priv->id);
ret = ib_post_send_mad(msg, NULL);
if (ret)
goto free;
goto deref;
unlock: spin_unlock_irq(&cm_id_priv->lock);
-free: cm_free_msg(msg);
+free: cm_free_response_msg(msg);
deref: cm_deref_id(cm_id_priv);
}
@@ -2338,7 +2458,6 @@ static int cm_rep_handler(struct cm_work *work)
struct cm_rep_msg *rep_msg;
int ret;
struct cm_id_private *cur_cm_id_priv;
- struct ib_cm_id *cm_id;
struct cm_timewait_info *timewait_info;
rep_msg = (struct cm_rep_msg *)work->mad_recv_wc->recv_buf.mad;
@@ -2346,7 +2465,7 @@ static int cm_rep_handler(struct cm_work *work)
cpu_to_be32(IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg)), 0);
if (!cm_id_priv) {
cm_dup_rep_handler(work);
- pr_debug("%s: remote_comm_id %d, no cm_id_priv\n", __func__,
+ trace_icm_remote_no_priv_err(
IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg));
return -EINVAL;
}
@@ -2359,13 +2478,12 @@ static int cm_rep_handler(struct cm_work *work)
case IB_CM_MRA_REQ_RCVD:
break;
default:
- spin_unlock_irq(&cm_id_priv->lock);
ret = -EINVAL;
- pr_debug(
- "%s: cm_id_priv->id.state: %d, local_comm_id %d, remote_comm_id %d\n",
- __func__, cm_id_priv->id.state,
+ trace_icm_rep_unknown_err(
IBA_GET(CM_REP_LOCAL_COMM_ID, rep_msg),
- IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg));
+ IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg),
+ cm_id_priv->id.state);
+ spin_unlock_irq(&cm_id_priv->lock);
goto error;
}
@@ -2381,16 +2499,14 @@ static int cm_rep_handler(struct cm_work *work)
spin_unlock(&cm.lock);
spin_unlock_irq(&cm_id_priv->lock);
ret = -EINVAL;
- pr_debug("%s: Failed to insert remote id %d\n", __func__,
+ trace_icm_insert_failed_err(
IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg));
goto error;
}
/* Check for a stale connection. */
timewait_info = cm_insert_remote_qpn(cm_id_priv->timewait_info);
if (timewait_info) {
- rb_erase(&cm_id_priv->timewait_info->remote_id_node,
- &cm.remote_id_table);
- cm_id_priv->timewait_info->inserted_remote_id = 0;
+ cm_remove_remote(cm_id_priv);
cur_cm_id_priv = cm_acquire_id(timewait_info->work.local_id,
timewait_info->work.remote_id);
@@ -2400,14 +2516,12 @@ static int cm_rep_handler(struct cm_work *work)
IB_CM_REJ_STALE_CONN, CM_MSG_RESPONSE_REP,
NULL, 0);
ret = -EINVAL;
- pr_debug(
- "%s: Stale connection. local_comm_id %d, remote_comm_id %d\n",
- __func__, IBA_GET(CM_REP_LOCAL_COMM_ID, rep_msg),
+ trace_icm_staleconn_err(
+ IBA_GET(CM_REP_LOCAL_COMM_ID, rep_msg),
IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg));
if (cur_cm_id_priv) {
- cm_id = &cur_cm_id_priv->id;
- ib_send_cm_dreq(cm_id, NULL, 0);
+ ib_send_cm_dreq(&cur_cm_id_priv->id, NULL, 0);
cm_deref_id(cur_cm_id_priv);
}
@@ -2434,18 +2548,8 @@ static int cm_rep_handler(struct cm_work *work)
cm_ack_timeout(cm_id_priv->target_ack_delay,
cm_id_priv->alt_av.timeout - 1);
- /* todo: handle peer_to_peer */
-
- ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
- ret = atomic_inc_and_test(&cm_id_priv->work_count);
- if (!ret)
- list_add_tail(&work->list, &cm_id_priv->work_list);
- spin_unlock_irq(&cm_id_priv->lock);
-
- if (ret)
- cm_process_work(cm_id_priv, work);
- else
- cm_deref_id(cm_id_priv);
+ ib_cancel_mad(cm_id_priv->msg);
+ cm_queue_work_unlock(cm_id_priv, work);
return 0;
error:
@@ -2456,7 +2560,6 @@ error:
static int cm_establish_handler(struct cm_work *work)
{
struct cm_id_private *cm_id_priv;
- int ret;
/* See comment in cm_establish about lookup. */
cm_id_priv = cm_acquire_id(work->local_id, work->remote_id);
@@ -2469,16 +2572,8 @@ static int cm_establish_handler(struct cm_work *work)
goto out;
}
- ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
- ret = atomic_inc_and_test(&cm_id_priv->work_count);
- if (!ret)
- list_add_tail(&work->list, &cm_id_priv->work_list);
- spin_unlock_irq(&cm_id_priv->lock);
-
- if (ret)
- cm_process_work(cm_id_priv, work);
- else
- cm_deref_id(cm_id_priv);
+ ib_cancel_mad(cm_id_priv->msg);
+ cm_queue_work_unlock(cm_id_priv, work);
return 0;
out:
cm_deref_id(cm_id_priv);
@@ -2489,7 +2584,6 @@ static int cm_rtu_handler(struct cm_work *work)
{
struct cm_id_private *cm_id_priv;
struct cm_rtu_msg *rtu_msg;
- int ret;
rtu_msg = (struct cm_rtu_msg *)work->mad_recv_wc->recv_buf.mad;
cm_id_priv = cm_acquire_id(
@@ -2505,22 +2599,14 @@ static int cm_rtu_handler(struct cm_work *work)
if (cm_id_priv->id.state != IB_CM_REP_SENT &&
cm_id_priv->id.state != IB_CM_MRA_REP_RCVD) {
spin_unlock_irq(&cm_id_priv->lock);
- atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
- counter[CM_RTU_COUNTER]);
+ atomic_long_inc(&work->port->counters[CM_RECV_DUPLICATES]
+ [CM_RTU_COUNTER]);
goto out;
}
cm_id_priv->id.state = IB_CM_ESTABLISHED;
- ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
- ret = atomic_inc_and_test(&cm_id_priv->work_count);
- if (!ret)
- list_add_tail(&work->list, &cm_id_priv->work_list);
- spin_unlock_irq(&cm_id_priv->lock);
-
- if (ret)
- cm_process_work(cm_id_priv, work);
- else
- cm_deref_id(cm_id_priv);
+ ib_cancel_mad(cm_id_priv->msg);
+ cm_queue_work_unlock(cm_id_priv, work);
return 0;
out:
cm_deref_id(cm_id_priv);
@@ -2546,35 +2632,30 @@ static void cm_format_dreq(struct cm_dreq_msg *dreq_msg,
private_data_len);
}
-int ib_send_cm_dreq(struct ib_cm_id *cm_id,
- const void *private_data,
- u8 private_data_len)
+static int cm_send_dreq_locked(struct cm_id_private *cm_id_priv,
+ const void *private_data, u8 private_data_len)
{
- struct cm_id_private *cm_id_priv;
struct ib_mad_send_buf *msg;
- unsigned long flags;
int ret;
+ lockdep_assert_held(&cm_id_priv->lock);
+
if (private_data && private_data_len > IB_CM_DREQ_PRIVATE_DATA_SIZE)
return -EINVAL;
- cm_id_priv = container_of(cm_id, struct cm_id_private, id);
- spin_lock_irqsave(&cm_id_priv->lock, flags);
- if (cm_id->state != IB_CM_ESTABLISHED) {
- pr_debug("%s: local_id %d, cm_id->state: %d\n", __func__,
- be32_to_cpu(cm_id->local_id), cm_id->state);
- ret = -EINVAL;
- goto out;
+ if (cm_id_priv->id.state != IB_CM_ESTABLISHED) {
+ trace_icm_dreq_skipped(&cm_id_priv->id);
+ return -EINVAL;
}
- if (cm_id->lap_state == IB_CM_LAP_SENT ||
- cm_id->lap_state == IB_CM_MRA_LAP_RCVD)
- ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
+ if (cm_id_priv->id.lap_state == IB_CM_LAP_SENT ||
+ cm_id_priv->id.lap_state == IB_CM_MRA_LAP_RCVD)
+ ib_cancel_mad(cm_id_priv->msg);
- ret = cm_alloc_msg(cm_id_priv, &msg);
- if (ret) {
+ msg = cm_alloc_priv_msg(cm_id_priv);
+ if (IS_ERR(msg)) {
cm_enter_timewait(cm_id_priv);
- goto out;
+ return PTR_ERR(msg);
}
cm_format_dreq((struct cm_dreq_msg *) msg->mad, cm_id_priv,
@@ -2582,17 +2663,29 @@ int ib_send_cm_dreq(struct ib_cm_id *cm_id,
msg->timeout_ms = cm_id_priv->timeout_ms;
msg->context[1] = (void *) (unsigned long) IB_CM_DREQ_SENT;
+ trace_icm_send_dreq(&cm_id_priv->id);
ret = ib_post_send_mad(msg, NULL);
if (ret) {
cm_enter_timewait(cm_id_priv);
- spin_unlock_irqrestore(&cm_id_priv->lock, flags);
- cm_free_msg(msg);
+ cm_free_priv_msg(msg);
return ret;
}
- cm_id->state = IB_CM_DREQ_SENT;
- cm_id_priv->msg = msg;
-out: spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+ cm_id_priv->id.state = IB_CM_DREQ_SENT;
+ return 0;
+}
+
+int ib_send_cm_dreq(struct ib_cm_id *cm_id, const void *private_data,
+ u8 private_data_len)
+{
+ struct cm_id_private *cm_id_priv =
+ container_of(cm_id, struct cm_id_private, id);
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&cm_id_priv->lock, flags);
+ ret = cm_send_dreq_locked(cm_id_priv, private_data, private_data_len);
+ spin_unlock_irqrestore(&cm_id_priv->lock, flags);
return ret;
}
EXPORT_SYMBOL(ib_send_cm_dreq);
@@ -2613,51 +2706,58 @@ static void cm_format_drep(struct cm_drep_msg *drep_msg,
private_data_len);
}
-int ib_send_cm_drep(struct ib_cm_id *cm_id,
- const void *private_data,
- u8 private_data_len)
+static int cm_send_drep_locked(struct cm_id_private *cm_id_priv,
+ void *private_data, u8 private_data_len)
{
- struct cm_id_private *cm_id_priv;
struct ib_mad_send_buf *msg;
- unsigned long flags;
- void *data;
int ret;
+ lockdep_assert_held(&cm_id_priv->lock);
+
if (private_data && private_data_len > IB_CM_DREP_PRIVATE_DATA_SIZE)
return -EINVAL;
- data = cm_copy_private_data(private_data, private_data_len);
- if (IS_ERR(data))
- return PTR_ERR(data);
-
- cm_id_priv = container_of(cm_id, struct cm_id_private, id);
- spin_lock_irqsave(&cm_id_priv->lock, flags);
- if (cm_id->state != IB_CM_DREQ_RCVD) {
- spin_unlock_irqrestore(&cm_id_priv->lock, flags);
- kfree(data);
- pr_debug("%s: local_id %d, cm_idcm_id->state(%d) != IB_CM_DREQ_RCVD\n",
- __func__, be32_to_cpu(cm_id->local_id), cm_id->state);
+ if (cm_id_priv->id.state != IB_CM_DREQ_RCVD) {
+ trace_icm_send_drep_err(&cm_id_priv->id);
+ kfree(private_data);
return -EINVAL;
}
- cm_set_private_data(cm_id_priv, data, private_data_len);
+ cm_set_private_data(cm_id_priv, private_data, private_data_len);
cm_enter_timewait(cm_id_priv);
- ret = cm_alloc_msg(cm_id_priv, &msg);
- if (ret)
- goto out;
+ msg = cm_alloc_msg(cm_id_priv);
+ if (IS_ERR(msg))
+ return PTR_ERR(msg);
cm_format_drep((struct cm_drep_msg *) msg->mad, cm_id_priv,
private_data, private_data_len);
+ trace_icm_send_drep(&cm_id_priv->id);
ret = ib_post_send_mad(msg, NULL);
if (ret) {
- spin_unlock_irqrestore(&cm_id_priv->lock, flags);
cm_free_msg(msg);
return ret;
}
+ return 0;
+}
-out: spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+int ib_send_cm_drep(struct ib_cm_id *cm_id, const void *private_data,
+ u8 private_data_len)
+{
+ struct cm_id_private *cm_id_priv =
+ container_of(cm_id, struct cm_id_private, id);
+ unsigned long flags;
+ void *data;
+ int ret;
+
+ data = cm_copy_private_data(private_data, private_data_len);
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
+ spin_lock_irqsave(&cm_id_priv->lock, flags);
+ ret = cm_send_drep_locked(cm_id_priv, data, private_data_len);
+ spin_unlock_irqrestore(&cm_id_priv->lock, flags);
return ret;
}
EXPORT_SYMBOL(ib_send_cm_drep);
@@ -2683,9 +2783,12 @@ static int cm_issue_drep(struct cm_port *port,
IBA_SET(CM_DREP_LOCAL_COMM_ID, drep_msg,
IBA_GET(CM_DREQ_REMOTE_COMM_ID, dreq_msg));
+ trace_icm_issue_drep(
+ IBA_GET(CM_DREQ_LOCAL_COMM_ID, dreq_msg),
+ IBA_GET(CM_DREQ_REMOTE_COMM_ID, dreq_msg));
ret = ib_post_send_mad(msg, NULL);
if (ret)
- cm_free_msg(msg);
+ cm_free_response_msg(msg);
return ret;
}
@@ -2695,19 +2798,17 @@ static int cm_dreq_handler(struct cm_work *work)
struct cm_id_private *cm_id_priv;
struct cm_dreq_msg *dreq_msg;
struct ib_mad_send_buf *msg = NULL;
- int ret;
dreq_msg = (struct cm_dreq_msg *)work->mad_recv_wc->recv_buf.mad;
cm_id_priv = cm_acquire_id(
cpu_to_be32(IBA_GET(CM_DREQ_REMOTE_COMM_ID, dreq_msg)),
cpu_to_be32(IBA_GET(CM_DREQ_LOCAL_COMM_ID, dreq_msg)));
if (!cm_id_priv) {
- atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
- counter[CM_DREQ_COUNTER]);
+ atomic_long_inc(&work->port->counters[CM_RECV_DUPLICATES]
+ [CM_DREQ_COUNTER]);
cm_issue_drep(work->port, work->mad_recv_wc);
- pr_debug(
- "%s: no cm_id_priv, local_comm_id %d, remote_comm_id %d\n",
- __func__, IBA_GET(CM_DREQ_LOCAL_COMM_ID, dreq_msg),
+ trace_icm_no_priv_err(
+ IBA_GET(CM_DREQ_LOCAL_COMM_ID, dreq_msg),
IBA_GET(CM_DREQ_REMOTE_COMM_ID, dreq_msg));
return -EINVAL;
}
@@ -2723,18 +2824,17 @@ static int cm_dreq_handler(struct cm_work *work)
switch (cm_id_priv->id.state) {
case IB_CM_REP_SENT:
case IB_CM_DREQ_SENT:
- ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
+ case IB_CM_MRA_REP_RCVD:
+ ib_cancel_mad(cm_id_priv->msg);
break;
case IB_CM_ESTABLISHED:
if (cm_id_priv->id.lap_state == IB_CM_LAP_SENT ||
cm_id_priv->id.lap_state == IB_CM_MRA_LAP_RCVD)
- ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
- break;
- case IB_CM_MRA_REP_RCVD:
+ ib_cancel_mad(cm_id_priv->msg);
break;
case IB_CM_TIMEWAIT:
- atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
- counter[CM_DREQ_COUNTER]);
+ atomic_long_inc(&work->port->counters[CM_RECV_DUPLICATES]
+ [CM_DREQ_COUNTER]);
msg = cm_alloc_response_msg_no_ah(work->port, work->mad_recv_wc);
if (IS_ERR(msg))
goto unlock;
@@ -2746,29 +2846,19 @@ static int cm_dreq_handler(struct cm_work *work)
if (cm_create_response_msg_ah(work->port, work->mad_recv_wc, msg) ||
ib_post_send_mad(msg, NULL))
- cm_free_msg(msg);
+ cm_free_response_msg(msg);
goto deref;
case IB_CM_DREQ_RCVD:
- atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
- counter[CM_DREQ_COUNTER]);
+ atomic_long_inc(&work->port->counters[CM_RECV_DUPLICATES]
+ [CM_DREQ_COUNTER]);
goto unlock;
default:
- pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
- __func__, be32_to_cpu(cm_id_priv->id.local_id),
- cm_id_priv->id.state);
+ trace_icm_dreq_unknown_err(&cm_id_priv->id);
goto unlock;
}
cm_id_priv->id.state = IB_CM_DREQ_RCVD;
cm_id_priv->tid = dreq_msg->hdr.tid;
- ret = atomic_inc_and_test(&cm_id_priv->work_count);
- if (!ret)
- list_add_tail(&work->list, &cm_id_priv->work_list);
- spin_unlock_irq(&cm_id_priv->lock);
-
- if (ret)
- cm_process_work(cm_id_priv, work);
- else
- cm_deref_id(cm_id_priv);
+ cm_queue_work_unlock(cm_id_priv, work);
return 0;
unlock: spin_unlock_irq(&cm_id_priv->lock);
@@ -2780,7 +2870,6 @@ static int cm_drep_handler(struct cm_work *work)
{
struct cm_id_private *cm_id_priv;
struct cm_drep_msg *drep_msg;
- int ret;
drep_msg = (struct cm_drep_msg *)work->mad_recv_wc->recv_buf.mad;
cm_id_priv = cm_acquire_id(
@@ -2800,81 +2889,82 @@ static int cm_drep_handler(struct cm_work *work)
}
cm_enter_timewait(cm_id_priv);
- ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
- ret = atomic_inc_and_test(&cm_id_priv->work_count);
- if (!ret)
- list_add_tail(&work->list, &cm_id_priv->work_list);
- spin_unlock_irq(&cm_id_priv->lock);
-
- if (ret)
- cm_process_work(cm_id_priv, work);
- else
- cm_deref_id(cm_id_priv);
+ ib_cancel_mad(cm_id_priv->msg);
+ cm_queue_work_unlock(cm_id_priv, work);
return 0;
out:
cm_deref_id(cm_id_priv);
return -EINVAL;
}
-int ib_send_cm_rej(struct ib_cm_id *cm_id,
- enum ib_cm_rej_reason reason,
- void *ari,
- u8 ari_length,
- const void *private_data,
- u8 private_data_len)
+static int cm_send_rej_locked(struct cm_id_private *cm_id_priv,
+ enum ib_cm_rej_reason reason, void *ari,
+ u8 ari_length, const void *private_data,
+ u8 private_data_len)
{
- struct cm_id_private *cm_id_priv;
+ enum ib_cm_state state = cm_id_priv->id.state;
struct ib_mad_send_buf *msg;
- unsigned long flags;
int ret;
+ lockdep_assert_held(&cm_id_priv->lock);
+
if ((private_data && private_data_len > IB_CM_REJ_PRIVATE_DATA_SIZE) ||
(ari && ari_length > IB_CM_REJ_ARI_LENGTH))
return -EINVAL;
- cm_id_priv = container_of(cm_id, struct cm_id_private, id);
-
- spin_lock_irqsave(&cm_id_priv->lock, flags);
- switch (cm_id->state) {
+ switch (state) {
case IB_CM_REQ_SENT:
case IB_CM_MRA_REQ_RCVD:
case IB_CM_REQ_RCVD:
case IB_CM_MRA_REQ_SENT:
case IB_CM_REP_RCVD:
case IB_CM_MRA_REP_SENT:
- ret = cm_alloc_msg(cm_id_priv, &msg);
- if (!ret)
- cm_format_rej((struct cm_rej_msg *) msg->mad,
- cm_id_priv, reason, ari, ari_length,
- private_data, private_data_len);
-
cm_reset_to_idle(cm_id_priv);
+ msg = cm_alloc_msg(cm_id_priv);
+ if (IS_ERR(msg))
+ return PTR_ERR(msg);
+ cm_format_rej((struct cm_rej_msg *)msg->mad, cm_id_priv, reason,
+ ari, ari_length, private_data, private_data_len,
+ state);
break;
case IB_CM_REP_SENT:
case IB_CM_MRA_REP_RCVD:
- ret = cm_alloc_msg(cm_id_priv, &msg);
- if (!ret)
- cm_format_rej((struct cm_rej_msg *) msg->mad,
- cm_id_priv, reason, ari, ari_length,
- private_data, private_data_len);
-
cm_enter_timewait(cm_id_priv);
+ msg = cm_alloc_msg(cm_id_priv);
+ if (IS_ERR(msg))
+ return PTR_ERR(msg);
+ cm_format_rej((struct cm_rej_msg *)msg->mad, cm_id_priv, reason,
+ ari, ari_length, private_data, private_data_len,
+ state);
break;
default:
- pr_debug("%s: local_id %d, cm_id->state: %d\n", __func__,
- be32_to_cpu(cm_id_priv->id.local_id), cm_id->state);
- ret = -EINVAL;
- goto out;
+ trace_icm_send_unknown_rej_err(&cm_id_priv->id);
+ return -EINVAL;
}
- if (ret)
- goto out;
-
+ trace_icm_send_rej(&cm_id_priv->id, reason);
ret = ib_post_send_mad(msg, NULL);
- if (ret)
+ if (ret) {
cm_free_msg(msg);
+ return ret;
+ }
+
+ return 0;
+}
+
+int ib_send_cm_rej(struct ib_cm_id *cm_id, enum ib_cm_rej_reason reason,
+ void *ari, u8 ari_length, const void *private_data,
+ u8 private_data_len)
+{
+ struct cm_id_private *cm_id_priv =
+ container_of(cm_id, struct cm_id_private, id);
+ unsigned long flags;
+ int ret;
-out: spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+ spin_lock_irqsave(&cm_id_priv->lock, flags);
+ ret = cm_send_rej_locked(cm_id_priv, reason, ari, ari_length,
+ private_data, private_data_len);
+ spin_unlock_irqrestore(&cm_id_priv->lock, flags);
return ret;
}
EXPORT_SYMBOL(ib_send_cm_rej);
@@ -2893,26 +2983,17 @@ static void cm_format_rej_event(struct cm_work *work)
IBA_GET_MEM_PTR(CM_REJ_PRIVATE_DATA, rej_msg);
}
-static struct cm_id_private * cm_acquire_rejected_id(struct cm_rej_msg *rej_msg)
+static struct cm_id_private *cm_acquire_rejected_id(struct cm_rej_msg *rej_msg)
{
- struct cm_timewait_info *timewait_info;
struct cm_id_private *cm_id_priv;
__be32 remote_id;
remote_id = cpu_to_be32(IBA_GET(CM_REJ_LOCAL_COMM_ID, rej_msg));
if (IBA_GET(CM_REJ_REASON, rej_msg) == IB_CM_REJ_TIMEOUT) {
- spin_lock_irq(&cm.lock);
- timewait_info = cm_find_remote_id(
+ cm_id_priv = cm_find_remote_id(
*((__be64 *)IBA_GET_MEM_PTR(CM_REJ_ARI, rej_msg)),
remote_id);
- if (!timewait_info) {
- spin_unlock_irq(&cm.lock);
- return NULL;
- }
- cm_id_priv =
- cm_acquire_id(timewait_info->work.local_id, remote_id);
- spin_unlock_irq(&cm.lock);
} else if (IBA_GET(CM_REJ_MESSAGE_REJECTED, rej_msg) ==
CM_MSG_RESPONSE_REQ)
cm_id_priv = cm_acquire_id(
@@ -2930,7 +3011,6 @@ static int cm_rej_handler(struct cm_work *work)
{
struct cm_id_private *cm_id_priv;
struct cm_rej_msg *rej_msg;
- int ret;
rej_msg = (struct cm_rej_msg *)work->mad_recv_wc->recv_buf.mad;
cm_id_priv = cm_acquire_rejected_id(rej_msg);
@@ -2945,8 +3025,8 @@ static int cm_rej_handler(struct cm_work *work)
case IB_CM_MRA_REQ_RCVD:
case IB_CM_REP_SENT:
case IB_CM_MRA_REP_RCVD:
- ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
- /* fall through */
+ ib_cancel_mad(cm_id_priv->msg);
+ fallthrough;
case IB_CM_REQ_RCVD:
case IB_CM_MRA_REQ_SENT:
if (IBA_GET(CM_REJ_REASON, rej_msg) == IB_CM_REJ_STALE_CONN)
@@ -2955,8 +3035,8 @@ static int cm_rej_handler(struct cm_work *work)
cm_reset_to_idle(cm_id_priv);
break;
case IB_CM_DREQ_SENT:
- ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
- /* fall through */
+ ib_cancel_mad(cm_id_priv->msg);
+ fallthrough;
case IB_CM_REP_RCVD:
case IB_CM_MRA_REP_SENT:
cm_enter_timewait(cm_id_priv);
@@ -2965,30 +3045,18 @@ static int cm_rej_handler(struct cm_work *work)
if (cm_id_priv->id.lap_state == IB_CM_LAP_UNINIT ||
cm_id_priv->id.lap_state == IB_CM_LAP_SENT) {
if (cm_id_priv->id.lap_state == IB_CM_LAP_SENT)
- ib_cancel_mad(cm_id_priv->av.port->mad_agent,
- cm_id_priv->msg);
+ ib_cancel_mad(cm_id_priv->msg);
cm_enter_timewait(cm_id_priv);
break;
}
- /* fall through */
+ fallthrough;
default:
+ trace_icm_rej_unknown_err(&cm_id_priv->id);
spin_unlock_irq(&cm_id_priv->lock);
- pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
- __func__, be32_to_cpu(cm_id_priv->id.local_id),
- cm_id_priv->id.state);
- ret = -EINVAL;
goto out;
}
- ret = atomic_inc_and_test(&cm_id_priv->work_count);
- if (!ret)
- list_add_tail(&work->list, &cm_id_priv->work_list);
- spin_unlock_irq(&cm_id_priv->lock);
-
- if (ret)
- cm_process_work(cm_id_priv, work);
- else
- cm_deref_id(cm_id_priv);
+ cm_queue_work_unlock(cm_id_priv, work);
return 0;
out:
cm_deref_id(cm_id_priv);
@@ -3019,7 +3087,7 @@ int ib_send_cm_mra(struct ib_cm_id *cm_id,
cm_id_priv = container_of(cm_id, struct cm_id_private, id);
spin_lock_irqsave(&cm_id_priv->lock, flags);
- switch(cm_id_priv->id.state) {
+ switch (cm_id_priv->id.state) {
case IB_CM_REQ_RCVD:
cm_state = IB_CM_MRA_REQ_SENT;
lap_state = cm_id->lap_state;
@@ -3037,26 +3105,27 @@ int ib_send_cm_mra(struct ib_cm_id *cm_id,
msg_response = CM_MSG_RESPONSE_OTHER;
break;
}
- /* fall through */
+ fallthrough;
default:
- pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
- __func__, be32_to_cpu(cm_id_priv->id.local_id),
- cm_id_priv->id.state);
+ trace_icm_send_mra_unknown_err(&cm_id_priv->id);
ret = -EINVAL;
- goto error1;
+ goto error_unlock;
}
if (!(service_timeout & IB_CM_MRA_FLAG_DELAY)) {
- ret = cm_alloc_msg(cm_id_priv, &msg);
- if (ret)
- goto error1;
+ msg = cm_alloc_msg(cm_id_priv);
+ if (IS_ERR(msg)) {
+ ret = PTR_ERR(msg);
+ goto error_unlock;
+ }
cm_format_mra((struct cm_mra_msg *) msg->mad, cm_id_priv,
msg_response, service_timeout,
private_data, private_data_len);
+ trace_icm_send_mra(cm_id);
ret = ib_post_send_mad(msg, NULL);
if (ret)
- goto error2;
+ goto error_free_msg;
}
cm_id->state = cm_state;
@@ -3066,18 +3135,16 @@ int ib_send_cm_mra(struct ib_cm_id *cm_id,
spin_unlock_irqrestore(&cm_id_priv->lock, flags);
return 0;
-error1: spin_unlock_irqrestore(&cm_id_priv->lock, flags);
- kfree(data);
- return ret;
-
-error2: spin_unlock_irqrestore(&cm_id_priv->lock, flags);
- kfree(data);
+error_free_msg:
cm_free_msg(msg);
+error_unlock:
+ spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+ kfree(data);
return ret;
}
EXPORT_SYMBOL(ib_send_cm_mra);
-static struct cm_id_private * cm_acquire_mraed_id(struct cm_mra_msg *mra_msg)
+static struct cm_id_private *cm_acquire_mraed_id(struct cm_mra_msg *mra_msg)
{
switch (IBA_GET(CM_MRA_MESSAGE_MRAED, mra_msg)) {
case CM_MSG_RESPONSE_REQ:
@@ -3098,7 +3165,7 @@ static int cm_mra_handler(struct cm_work *work)
{
struct cm_id_private *cm_id_priv;
struct cm_mra_msg *mra_msg;
- int timeout, ret;
+ int timeout;
mra_msg = (struct cm_mra_msg *)work->mad_recv_wc->recv_buf.mad;
cm_id_priv = cm_acquire_mraed_id(mra_msg);
@@ -3117,16 +3184,14 @@ static int cm_mra_handler(struct cm_work *work)
case IB_CM_REQ_SENT:
if (IBA_GET(CM_MRA_MESSAGE_MRAED, mra_msg) !=
CM_MSG_RESPONSE_REQ ||
- ib_modify_mad(cm_id_priv->av.port->mad_agent,
- cm_id_priv->msg, timeout))
+ ib_modify_mad(cm_id_priv->msg, timeout))
goto out;
cm_id_priv->id.state = IB_CM_MRA_REQ_RCVD;
break;
case IB_CM_REP_SENT:
if (IBA_GET(CM_MRA_MESSAGE_MRAED, mra_msg) !=
CM_MSG_RESPONSE_REP ||
- ib_modify_mad(cm_id_priv->av.port->mad_agent,
- cm_id_priv->msg, timeout))
+ ib_modify_mad(cm_id_priv->msg, timeout))
goto out;
cm_id_priv->id.state = IB_CM_MRA_REP_RCVD;
break;
@@ -3134,39 +3199,28 @@ static int cm_mra_handler(struct cm_work *work)
if (IBA_GET(CM_MRA_MESSAGE_MRAED, mra_msg) !=
CM_MSG_RESPONSE_OTHER ||
cm_id_priv->id.lap_state != IB_CM_LAP_SENT ||
- ib_modify_mad(cm_id_priv->av.port->mad_agent,
- cm_id_priv->msg, timeout)) {
+ ib_modify_mad(cm_id_priv->msg, timeout)) {
if (cm_id_priv->id.lap_state == IB_CM_MRA_LAP_RCVD)
- atomic_long_inc(&work->port->
- counter_group[CM_RECV_DUPLICATES].
- counter[CM_MRA_COUNTER]);
+ atomic_long_inc(
+ &work->port->counters[CM_RECV_DUPLICATES]
+ [CM_MRA_COUNTER]);
goto out;
}
cm_id_priv->id.lap_state = IB_CM_MRA_LAP_RCVD;
break;
case IB_CM_MRA_REQ_RCVD:
case IB_CM_MRA_REP_RCVD:
- atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
- counter[CM_MRA_COUNTER]);
- /* fall through */
+ atomic_long_inc(&work->port->counters[CM_RECV_DUPLICATES]
+ [CM_MRA_COUNTER]);
+ fallthrough;
default:
- pr_debug("%s local_id %d, cm_id_priv->id.state: %d\n",
- __func__, be32_to_cpu(cm_id_priv->id.local_id),
- cm_id_priv->id.state);
+ trace_icm_mra_unknown_err(&cm_id_priv->id);
goto out;
}
cm_id_priv->msg->context[1] = (void *) (unsigned long)
cm_id_priv->id.state;
- ret = atomic_inc_and_test(&cm_id_priv->work_count);
- if (!ret)
- list_add_tail(&work->list, &cm_id_priv->work_list);
- spin_unlock_irq(&cm_id_priv->lock);
-
- if (ret)
- cm_process_work(cm_id_priv, work);
- else
- cm_deref_id(cm_id_priv);
+ cm_queue_work_unlock(cm_id_priv, work);
return 0;
out:
spin_unlock_irq(&cm_id_priv->lock);
@@ -3226,6 +3280,8 @@ static int cm_lap_handler(struct cm_work *work)
struct cm_lap_msg *lap_msg;
struct ib_cm_lap_event_param *param;
struct ib_mad_send_buf *msg = NULL;
+ struct rdma_ah_attr ah_attr;
+ struct cm_av alt_av = {};
int ret;
/* Currently Alternate path messages are not supported for
@@ -3254,7 +3310,25 @@ static int cm_lap_handler(struct cm_work *work)
work->cm_event.private_data =
IBA_GET_MEM_PTR(CM_LAP_PRIVATE_DATA, lap_msg);
+ ret = ib_init_ah_attr_from_wc(work->port->cm_dev->ib_device,
+ work->port->port_num,
+ work->mad_recv_wc->wc,
+ work->mad_recv_wc->recv_buf.grh,
+ &ah_attr);
+ if (ret)
+ goto deref;
+
+ ret = cm_init_av_by_path(param->alternate_path, NULL, &alt_av);
+ if (ret) {
+ rdma_destroy_ah_attr(&ah_attr);
+ goto deref;
+ }
+
spin_lock_irq(&cm_id_priv->lock);
+ cm_init_av_for_lap(work->port, work->mad_recv_wc->wc,
+ &ah_attr, &cm_id_priv->av);
+ cm_move_av_from_path(&cm_id_priv->alt_av, &alt_av);
+
if (cm_id_priv->id.state != IB_CM_ESTABLISHED)
goto unlock;
@@ -3263,8 +3337,8 @@ static int cm_lap_handler(struct cm_work *work)
case IB_CM_LAP_IDLE:
break;
case IB_CM_MRA_LAP_SENT:
- atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
- counter[CM_LAP_COUNTER]);
+ atomic_long_inc(&work->port->counters[CM_RECV_DUPLICATES]
+ [CM_LAP_COUNTER]);
msg = cm_alloc_response_msg_no_ah(work->port, work->mad_recv_wc);
if (IS_ERR(msg))
goto unlock;
@@ -3278,38 +3352,19 @@ static int cm_lap_handler(struct cm_work *work)
if (cm_create_response_msg_ah(work->port, work->mad_recv_wc, msg) ||
ib_post_send_mad(msg, NULL))
- cm_free_msg(msg);
+ cm_free_response_msg(msg);
goto deref;
case IB_CM_LAP_RCVD:
- atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
- counter[CM_LAP_COUNTER]);
+ atomic_long_inc(&work->port->counters[CM_RECV_DUPLICATES]
+ [CM_LAP_COUNTER]);
goto unlock;
default:
goto unlock;
}
- ret = cm_init_av_for_lap(work->port, work->mad_recv_wc->wc,
- work->mad_recv_wc->recv_buf.grh,
- &cm_id_priv->av);
- if (ret)
- goto unlock;
-
- ret = cm_init_av_by_path(param->alternate_path, NULL,
- &cm_id_priv->alt_av, cm_id_priv);
- if (ret)
- goto unlock;
-
cm_id_priv->id.lap_state = IB_CM_LAP_RCVD;
cm_id_priv->tid = lap_msg->hdr.tid;
- ret = atomic_inc_and_test(&cm_id_priv->work_count);
- if (!ret)
- list_add_tail(&work->list, &cm_id_priv->work_list);
- spin_unlock_irq(&cm_id_priv->lock);
-
- if (ret)
- cm_process_work(cm_id_priv, work);
- else
- cm_deref_id(cm_id_priv);
+ cm_queue_work_unlock(cm_id_priv, work);
return 0;
unlock: spin_unlock_irq(&cm_id_priv->lock);
@@ -3321,7 +3376,6 @@ static int cm_apr_handler(struct cm_work *work)
{
struct cm_id_private *cm_id_priv;
struct cm_apr_msg *apr_msg;
- int ret;
/* Currently Alternate path messages are not supported for
* RoCE link layer.
@@ -3354,18 +3408,8 @@ static int cm_apr_handler(struct cm_work *work)
goto out;
}
cm_id_priv->id.lap_state = IB_CM_LAP_IDLE;
- ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
- cm_id_priv->msg = NULL;
-
- ret = atomic_inc_and_test(&cm_id_priv->work_count);
- if (!ret)
- list_add_tail(&work->list, &cm_id_priv->work_list);
- spin_unlock_irq(&cm_id_priv->lock);
-
- if (ret)
- cm_process_work(cm_id_priv, work);
- else
- cm_deref_id(cm_id_priv);
+ ib_cancel_mad(cm_id_priv->msg);
+ cm_queue_work_unlock(cm_id_priv, work);
return 0;
out:
cm_deref_id(cm_id_priv);
@@ -3376,7 +3420,6 @@ static int cm_timewait_handler(struct cm_work *work)
{
struct cm_timewait_info *timewait_info;
struct cm_id_private *cm_id_priv;
- int ret;
timewait_info = container_of(work, struct cm_timewait_info, work);
spin_lock_irq(&cm.lock);
@@ -3395,15 +3438,7 @@ static int cm_timewait_handler(struct cm_work *work)
goto out;
}
cm_id_priv->id.state = IB_CM_IDLE;
- ret = atomic_inc_and_test(&cm_id_priv->work_count);
- if (!ret)
- list_add_tail(&work->list, &cm_id_priv->work_list);
- spin_unlock_irq(&cm_id_priv->lock);
-
- if (ret)
- cm_process_work(cm_id_priv, work);
- else
- cm_deref_id(cm_id_priv);
+ cm_queue_work_unlock(cm_id_priv, work);
return 0;
out:
cm_deref_id(cm_id_priv);
@@ -3433,6 +3468,7 @@ int ib_send_cm_sidr_req(struct ib_cm_id *cm_id,
{
struct cm_id_private *cm_id_priv;
struct ib_mad_send_buf *msg;
+ struct cm_av av = {};
unsigned long flags;
int ret;
@@ -3441,40 +3477,42 @@ int ib_send_cm_sidr_req(struct ib_cm_id *cm_id,
return -EINVAL;
cm_id_priv = container_of(cm_id, struct cm_id_private, id);
- ret = cm_init_av_by_path(param->path, param->sgid_attr,
- &cm_id_priv->av,
- cm_id_priv);
+ ret = cm_init_av_by_path(param->path, param->sgid_attr, &av);
if (ret)
- goto out;
+ return ret;
+ spin_lock_irqsave(&cm_id_priv->lock, flags);
+ cm_move_av_from_path(&cm_id_priv->av, &av);
cm_id->service_id = param->service_id;
- cm_id->service_mask = ~cpu_to_be64(0);
cm_id_priv->timeout_ms = param->timeout_ms;
cm_id_priv->max_cm_retries = param->max_cm_retries;
- ret = cm_alloc_msg(cm_id_priv, &msg);
- if (ret)
- goto out;
+ if (cm_id->state != IB_CM_IDLE) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
+ msg = cm_alloc_priv_msg(cm_id_priv);
+ if (IS_ERR(msg)) {
+ ret = PTR_ERR(msg);
+ goto out_unlock;
+ }
- cm_format_sidr_req((struct cm_sidr_req_msg *) msg->mad, cm_id_priv,
+ cm_format_sidr_req((struct cm_sidr_req_msg *)msg->mad, cm_id_priv,
param);
msg->timeout_ms = cm_id_priv->timeout_ms;
- msg->context[1] = (void *) (unsigned long) IB_CM_SIDR_REQ_SENT;
+ msg->context[1] = (void *)(unsigned long)IB_CM_SIDR_REQ_SENT;
- spin_lock_irqsave(&cm_id_priv->lock, flags);
- if (cm_id->state == IB_CM_IDLE)
- ret = ib_post_send_mad(msg, NULL);
- else
- ret = -EINVAL;
-
- if (ret) {
- spin_unlock_irqrestore(&cm_id_priv->lock, flags);
- cm_free_msg(msg);
- goto out;
- }
+ trace_icm_send_sidr_req(&cm_id_priv->id);
+ ret = ib_post_send_mad(msg, NULL);
+ if (ret)
+ goto out_free;
cm_id->state = IB_CM_SIDR_REQ_SENT;
- cm_id_priv->msg = msg;
spin_unlock_irqrestore(&cm_id_priv->lock, flags);
-out:
+ return 0;
+out_free:
+ cm_free_priv_msg(msg);
+out_unlock:
+ spin_unlock_irqrestore(&cm_id_priv->lock, flags);
return ret;
}
EXPORT_SYMBOL(ib_send_cm_sidr_req);
@@ -3502,64 +3540,73 @@ static void cm_format_sidr_req_event(struct cm_work *work,
static int cm_sidr_req_handler(struct cm_work *work)
{
- struct ib_cm_id *cm_id;
- struct cm_id_private *cm_id_priv, *cur_cm_id_priv;
+ struct cm_id_private *cm_id_priv, *listen_cm_id_priv;
struct cm_sidr_req_msg *sidr_req_msg;
struct ib_wc *wc;
int ret;
- cm_id = ib_create_cm_id(work->port->cm_dev->ib_device, NULL, NULL);
- if (IS_ERR(cm_id))
- return PTR_ERR(cm_id);
- cm_id_priv = container_of(cm_id, struct cm_id_private, id);
+ cm_id_priv =
+ cm_alloc_id_priv(work->port->cm_dev->ib_device, NULL, NULL);
+ if (IS_ERR(cm_id_priv))
+ return PTR_ERR(cm_id_priv);
/* Record SGID/SLID and request ID for lookup. */
sidr_req_msg = (struct cm_sidr_req_msg *)
work->mad_recv_wc->recv_buf.mad;
+
+ cm_id_priv->id.remote_id =
+ cpu_to_be32(IBA_GET(CM_SIDR_REQ_REQUESTID, sidr_req_msg));
+ cm_id_priv->id.service_id =
+ cpu_to_be64(IBA_GET(CM_SIDR_REQ_SERVICEID, sidr_req_msg));
+ cm_id_priv->tid = sidr_req_msg->hdr.tid;
+
wc = work->mad_recv_wc->wc;
- cm_id_priv->av.dgid.global.subnet_prefix = cpu_to_be64(wc->slid);
- cm_id_priv->av.dgid.global.interface_id = 0;
+ cm_id_priv->sidr_slid = wc->slid;
ret = cm_init_av_for_response(work->port, work->mad_recv_wc->wc,
work->mad_recv_wc->recv_buf.grh,
&cm_id_priv->av);
if (ret)
goto out;
- cm_id_priv->id.remote_id =
- cpu_to_be32(IBA_GET(CM_SIDR_REQ_REQUESTID, sidr_req_msg));
- cm_id_priv->tid = sidr_req_msg->hdr.tid;
- atomic_inc(&cm_id_priv->work_count);
-
spin_lock_irq(&cm.lock);
- cur_cm_id_priv = cm_insert_remote_sidr(cm_id_priv);
- if (cur_cm_id_priv) {
+ listen_cm_id_priv = cm_insert_remote_sidr(cm_id_priv);
+ if (listen_cm_id_priv) {
spin_unlock_irq(&cm.lock);
- atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
- counter[CM_SIDR_REQ_COUNTER]);
+ atomic_long_inc(&work->port->counters[CM_RECV_DUPLICATES]
+ [CM_SIDR_REQ_COUNTER]);
goto out; /* Duplicate message. */
}
cm_id_priv->id.state = IB_CM_SIDR_REQ_RCVD;
- cur_cm_id_priv = cm_find_listen(
- cm_id->device,
- cpu_to_be64(IBA_GET(CM_SIDR_REQ_SERVICEID, sidr_req_msg)));
- if (!cur_cm_id_priv) {
+ listen_cm_id_priv = cm_find_listen(cm_id_priv->id.device,
+ cm_id_priv->id.service_id);
+ if (!listen_cm_id_priv) {
spin_unlock_irq(&cm.lock);
- cm_reject_sidr_req(cm_id_priv, IB_SIDR_UNSUPPORTED);
+ ib_send_cm_sidr_rep(&cm_id_priv->id,
+ &(struct ib_cm_sidr_rep_param){
+ .status = IB_SIDR_UNSUPPORTED });
goto out; /* No match. */
}
- refcount_inc(&cur_cm_id_priv->refcount);
- refcount_inc(&cm_id_priv->refcount);
spin_unlock_irq(&cm.lock);
- cm_id_priv->id.cm_handler = cur_cm_id_priv->id.cm_handler;
- cm_id_priv->id.context = cur_cm_id_priv->id.context;
- cm_id_priv->id.service_id =
- cpu_to_be64(IBA_GET(CM_SIDR_REQ_SERVICEID, sidr_req_msg));
- cm_id_priv->id.service_mask = ~cpu_to_be64(0);
+ cm_id_priv->id.cm_handler = listen_cm_id_priv->id.cm_handler;
+ cm_id_priv->id.context = listen_cm_id_priv->id.context;
- cm_format_sidr_req_event(work, cm_id_priv, &cur_cm_id_priv->id);
- cm_process_work(cm_id_priv, work);
- cm_deref_id(cur_cm_id_priv);
+ /*
+ * A SIDR ID does not need to be in the xarray since it does not receive
+ * mads, is not placed in the remote_id or remote_qpn rbtree, and does
+ * not enter timewait.
+ */
+
+ cm_format_sidr_req_event(work, cm_id_priv, &listen_cm_id_priv->id);
+ ret = cm_id_priv->id.cm_handler(&cm_id_priv->id, &work->cm_event);
+ cm_free_work(work);
+ /*
+ * A pointer to the listen_cm_id is held in the event, so this deref
+ * must be after the event is delivered above.
+ */
+ cm_deref_id(listen_cm_id_priv);
+ if (ret)
+ cm_destroy_id(&cm_id_priv->id, ret);
return 0;
out:
ib_destroy_cm_id(&cm_id_priv->id);
@@ -3570,8 +3617,8 @@ static void cm_format_sidr_rep(struct cm_sidr_rep_msg *sidr_rep_msg,
struct cm_id_private *cm_id_priv,
struct ib_cm_sidr_rep_param *param)
{
- cm_format_mad_hdr(&sidr_rep_msg->hdr, CM_SIDR_REP_ATTR_ID,
- cm_id_priv->tid);
+ cm_format_mad_ece_hdr(&sidr_rep_msg->hdr, CM_SIDR_REP_ATTR_ID,
+ cm_id_priv->tid, param->ece.attr_mod);
IBA_SET(CM_SIDR_REP_REQUESTID, sidr_rep_msg,
be32_to_cpu(cm_id_priv->id.remote_id));
IBA_SET(CM_SIDR_REP_STATUS, sidr_rep_msg, param->status);
@@ -3579,6 +3626,10 @@ static void cm_format_sidr_rep(struct cm_sidr_rep_msg *sidr_rep_msg,
IBA_SET(CM_SIDR_REP_SERVICEID, sidr_rep_msg,
be64_to_cpu(cm_id_priv->id.service_id));
IBA_SET(CM_SIDR_REP_Q_KEY, sidr_rep_msg, param->qkey);
+ IBA_SET(CM_SIDR_REP_VENDOR_ID_L, sidr_rep_msg,
+ param->ece.vendor_id & 0xFF);
+ IBA_SET(CM_SIDR_REP_VENDOR_ID_H, sidr_rep_msg,
+ (param->ece.vendor_id >> 8) & 0xFF);
if (param->info && param->info_length)
IBA_SET_MEM(CM_SIDR_REP_ADDITIONAL_INFORMATION, sidr_rep_msg,
@@ -3589,41 +3640,36 @@ static void cm_format_sidr_rep(struct cm_sidr_rep_msg *sidr_rep_msg,
param->private_data, param->private_data_len);
}
-int ib_send_cm_sidr_rep(struct ib_cm_id *cm_id,
- struct ib_cm_sidr_rep_param *param)
+static int cm_send_sidr_rep_locked(struct cm_id_private *cm_id_priv,
+ struct ib_cm_sidr_rep_param *param)
{
- struct cm_id_private *cm_id_priv;
struct ib_mad_send_buf *msg;
unsigned long flags;
int ret;
+ lockdep_assert_held(&cm_id_priv->lock);
+
if ((param->info && param->info_length > IB_CM_SIDR_REP_INFO_LENGTH) ||
(param->private_data &&
param->private_data_len > IB_CM_SIDR_REP_PRIVATE_DATA_SIZE))
return -EINVAL;
- cm_id_priv = container_of(cm_id, struct cm_id_private, id);
- spin_lock_irqsave(&cm_id_priv->lock, flags);
- if (cm_id->state != IB_CM_SIDR_REQ_RCVD) {
- ret = -EINVAL;
- goto error;
- }
+ if (cm_id_priv->id.state != IB_CM_SIDR_REQ_RCVD)
+ return -EINVAL;
- ret = cm_alloc_msg(cm_id_priv, &msg);
- if (ret)
- goto error;
+ msg = cm_alloc_msg(cm_id_priv);
+ if (IS_ERR(msg))
+ return PTR_ERR(msg);
cm_format_sidr_rep((struct cm_sidr_rep_msg *) msg->mad, cm_id_priv,
param);
+ trace_icm_send_sidr_rep(&cm_id_priv->id);
ret = ib_post_send_mad(msg, NULL);
if (ret) {
- spin_unlock_irqrestore(&cm_id_priv->lock, flags);
cm_free_msg(msg);
return ret;
}
- cm_id->state = IB_CM_IDLE;
- spin_unlock_irqrestore(&cm_id_priv->lock, flags);
-
+ cm_id_priv->id.state = IB_CM_IDLE;
spin_lock_irqsave(&cm.lock, flags);
if (!RB_EMPTY_NODE(&cm_id_priv->sidr_id_node)) {
rb_erase(&cm_id_priv->sidr_id_node, &cm.remote_sidr_table);
@@ -3631,8 +3677,19 @@ int ib_send_cm_sidr_rep(struct ib_cm_id *cm_id,
}
spin_unlock_irqrestore(&cm.lock, flags);
return 0;
+}
-error: spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+int ib_send_cm_sidr_rep(struct ib_cm_id *cm_id,
+ struct ib_cm_sidr_rep_param *param)
+{
+ struct cm_id_private *cm_id_priv =
+ container_of(cm_id, struct cm_id_private, id);
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&cm_id_priv->lock, flags);
+ ret = cm_send_sidr_rep_locked(cm_id_priv, param);
+ spin_unlock_irqrestore(&cm_id_priv->lock, flags);
return ret;
}
EXPORT_SYMBOL(ib_send_cm_sidr_rep);
@@ -3676,7 +3733,7 @@ static int cm_sidr_rep_handler(struct cm_work *work)
goto out;
}
cm_id_priv->id.state = IB_CM_IDLE;
- ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
+ ib_cancel_mad(cm_id_priv->msg);
spin_unlock_irq(&cm_id_priv->lock);
cm_format_sidr_rep_event(work, cm_id_priv);
@@ -3687,25 +3744,28 @@ out:
return -EINVAL;
}
-static void cm_process_send_error(struct ib_mad_send_buf *msg,
+static void cm_process_send_error(struct cm_id_private *cm_id_priv,
+ struct ib_mad_send_buf *msg,
+ enum ib_cm_state state,
enum ib_wc_status wc_status)
{
- struct cm_id_private *cm_id_priv;
- struct ib_cm_event cm_event;
- enum ib_cm_state state;
+ struct ib_cm_event cm_event = {};
int ret;
- memset(&cm_event, 0, sizeof cm_event);
- cm_id_priv = msg->context[0];
-
/* Discard old sends or ones without a response. */
spin_lock_irq(&cm_id_priv->lock);
- state = (enum ib_cm_state) (unsigned long) msg->context[1];
- if (msg != cm_id_priv->msg || state != cm_id_priv->id.state)
- goto discard;
+ if (msg != cm_id_priv->msg) {
+ spin_unlock_irq(&cm_id_priv->lock);
+ cm_free_msg(msg);
+ return;
+ }
+ cm_free_priv_msg(msg);
+
+ if (state != cm_id_priv->id.state || wc_status == IB_WC_SUCCESS ||
+ wc_status == IB_WC_WR_FLUSH_ERR)
+ goto out_unlock;
- pr_debug_ratelimited("CM: failed sending MAD in state %d. (%s)\n",
- state, ib_wc_status_msg(wc_status));
+ trace_icm_mad_send_err(state, wc_status);
switch (state) {
case IB_CM_REQ_SENT:
case IB_CM_MRA_REQ_RCVD:
@@ -3726,26 +3786,27 @@ static void cm_process_send_error(struct ib_mad_send_buf *msg,
cm_event.event = IB_CM_SIDR_REQ_ERROR;
break;
default:
- goto discard;
+ goto out_unlock;
}
spin_unlock_irq(&cm_id_priv->lock);
cm_event.param.send_status = wc_status;
/* No other events can occur on the cm_id at this point. */
ret = cm_id_priv->id.cm_handler(&cm_id_priv->id, &cm_event);
- cm_free_msg(msg);
if (ret)
ib_destroy_cm_id(&cm_id_priv->id);
return;
-discard:
+out_unlock:
spin_unlock_irq(&cm_id_priv->lock);
- cm_free_msg(msg);
}
static void cm_send_handler(struct ib_mad_agent *mad_agent,
struct ib_mad_send_wc *mad_send_wc)
{
struct ib_mad_send_buf *msg = mad_send_wc->send_buf;
+ struct cm_id_private *cm_id_priv = msg->context[0];
+ enum ib_cm_state state =
+ (enum ib_cm_state)(unsigned long)msg->context[1];
struct cm_port *port;
u16 attr_index;
@@ -3758,28 +3819,19 @@ static void cm_send_handler(struct ib_mad_agent *mad_agent,
* set to a cm_id), and is not a REJ, then it is a send that was
* manually retried.
*/
- if (!msg->context[0] && (attr_index != CM_REJ_COUNTER))
+ if (!cm_id_priv && (attr_index != CM_REJ_COUNTER))
msg->retries = 1;
- atomic_long_add(1 + msg->retries,
- &port->counter_group[CM_XMIT].counter[attr_index]);
+ atomic_long_add(1 + msg->retries, &port->counters[CM_XMIT][attr_index]);
if (msg->retries)
atomic_long_add(msg->retries,
- &port->counter_group[CM_XMIT_RETRIES].
- counter[attr_index]);
+ &port->counters[CM_XMIT_RETRIES][attr_index]);
- switch (mad_send_wc->status) {
- case IB_WC_SUCCESS:
- case IB_WC_WR_FLUSH_ERR:
- cm_free_msg(msg);
- break;
- default:
- if (msg->context[0] && msg->context[1])
- cm_process_send_error(msg, mad_send_wc->status);
- else
- cm_free_msg(msg);
- break;
- }
+ if (cm_id_priv)
+ cm_process_send_error(cm_id_priv, msg, state,
+ mad_send_wc->status);
+ else
+ cm_free_response_msg(msg);
}
static void cm_work_handler(struct work_struct *_work)
@@ -3828,7 +3880,7 @@ static void cm_work_handler(struct work_struct *_work)
ret = cm_timewait_handler(work);
break;
default:
- pr_debug("cm_event.event: 0x%x\n", work->cm_event.event);
+ trace_icm_handler_err(work->cm_event.event);
ret = -EINVAL;
break;
}
@@ -3854,8 +3906,7 @@ static int cm_establish(struct ib_cm_id *cm_id)
cm_id_priv = container_of(cm_id, struct cm_id_private, id);
spin_lock_irqsave(&cm_id_priv->lock, flags);
- switch (cm_id->state)
- {
+ switch (cm_id->state) {
case IB_CM_REP_SENT:
case IB_CM_MRA_REP_RCVD:
cm_id->state = IB_CM_ESTABLISHED;
@@ -3864,8 +3915,7 @@ static int cm_establish(struct ib_cm_id *cm_id)
ret = -EISCONN;
break;
default:
- pr_debug("%s: local_id %d, cm_id->state: %d\n", __func__,
- be32_to_cpu(cm_id->local_id), cm_id->state);
+ trace_icm_establish_err(cm_id);
ret = -EINVAL;
break;
}
@@ -3905,9 +3955,7 @@ out:
static int cm_migrate(struct ib_cm_id *cm_id)
{
struct cm_id_private *cm_id_priv;
- struct cm_av tmp_av;
unsigned long flags;
- int tmp_send_port_not_ready;
int ret = 0;
cm_id_priv = container_of(cm_id, struct cm_id_private, id);
@@ -3916,14 +3964,7 @@ static int cm_migrate(struct ib_cm_id *cm_id)
(cm_id->lap_state == IB_CM_LAP_UNINIT ||
cm_id->lap_state == IB_CM_LAP_IDLE)) {
cm_id->lap_state = IB_CM_LAP_IDLE;
- /* Swap address vector */
- tmp_av = cm_id_priv->av;
cm_id_priv->av = cm_id_priv->alt_av;
- cm_id_priv->alt_av = tmp_av;
- /* Swap port send ready state */
- tmp_send_port_not_ready = cm_id_priv->prim_send_port_not_ready;
- cm_id_priv->prim_send_port_not_ready = cm_id_priv->altr_send_port_not_ready;
- cm_id_priv->altr_send_port_not_ready = tmp_send_port_not_ready;
} else
ret = -EINVAL;
spin_unlock_irqrestore(&cm_id_priv->lock, flags);
@@ -4005,8 +4046,7 @@ static void cm_recv_handler(struct ib_mad_agent *mad_agent,
}
attr_id = be16_to_cpu(mad_recv_wc->recv_buf.mad->mad_hdr.attr_id);
- atomic_long_inc(&port->counter_group[CM_RECV].
- counter[attr_id - CM_ATTR_ID_OFFSET]);
+ atomic_long_inc(&port->counters[CM_RECV][attr_id - CM_ATTR_ID_OFFSET]);
work = kmalloc(struct_size(work, path, paths), GFP_KERNEL);
if (!work) {
@@ -4058,13 +4098,12 @@ static int cm_init_qp_init_attr(struct cm_id_private *cm_id_priv,
qp_attr->qp_access_flags |= IB_ACCESS_REMOTE_READ |
IB_ACCESS_REMOTE_ATOMIC;
qp_attr->pkey_index = cm_id_priv->av.pkey_index;
- qp_attr->port_num = cm_id_priv->av.port->port_num;
+ if (cm_id_priv->av.port)
+ qp_attr->port_num = cm_id_priv->av.port->port_num;
ret = 0;
break;
default:
- pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
- __func__, be32_to_cpu(cm_id_priv->id.local_id),
- cm_id_priv->id.state);
+ trace_icm_qp_init_err(&cm_id_priv->id);
ret = -EINVAL;
break;
}
@@ -4091,6 +4130,10 @@ static int cm_init_qp_rtr_attr(struct cm_id_private *cm_id_priv,
*qp_attr_mask = IB_QP_STATE | IB_QP_AV | IB_QP_PATH_MTU |
IB_QP_DEST_QPN | IB_QP_RQ_PSN;
qp_attr->ah_attr = cm_id_priv->av.ah_attr;
+ if ((qp_attr->ah_attr.type == RDMA_AH_ATTR_TYPE_IB) &&
+ cm_id_priv->av.dlid_datapath &&
+ (cm_id_priv->av.dlid_datapath != 0xffff))
+ qp_attr->ah_attr.ib.dlid = cm_id_priv->av.dlid_datapath;
qp_attr->path_mtu = cm_id_priv->path_mtu;
qp_attr->dest_qp_num = be32_to_cpu(cm_id_priv->remote_qpn);
qp_attr->rq_psn = be32_to_cpu(cm_id_priv->rq_psn);
@@ -4102,7 +4145,8 @@ static int cm_init_qp_rtr_attr(struct cm_id_private *cm_id_priv,
cm_id_priv->responder_resources;
qp_attr->min_rnr_timer = 0;
}
- if (rdma_ah_get_dlid(&cm_id_priv->alt_av.ah_attr)) {
+ if (rdma_ah_get_dlid(&cm_id_priv->alt_av.ah_attr) &&
+ cm_id_priv->alt_av.port) {
*qp_attr_mask |= IB_QP_ALT_PATH;
qp_attr->alt_port_num = cm_id_priv->alt_av.port->port_num;
qp_attr->alt_pkey_index = cm_id_priv->alt_av.pkey_index;
@@ -4112,9 +4156,7 @@ static int cm_init_qp_rtr_attr(struct cm_id_private *cm_id_priv,
ret = 0;
break;
default:
- pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
- __func__, be32_to_cpu(cm_id_priv->id.local_id),
- cm_id_priv->id.state);
+ trace_icm_qp_rtr_err(&cm_id_priv->id);
ret = -EINVAL;
break;
}
@@ -4151,7 +4193,7 @@ static int cm_init_qp_rts_attr(struct cm_id_private *cm_id_priv,
qp_attr->retry_cnt = cm_id_priv->retry_count;
qp_attr->rnr_retry = cm_id_priv->rnr_retry_count;
qp_attr->max_rd_atomic = cm_id_priv->initiator_depth;
- /* fall through */
+ fallthrough;
case IB_QPT_XRC_TGT:
*qp_attr_mask |= IB_QP_TIMEOUT;
qp_attr->timeout = cm_id_priv->av.timeout;
@@ -4165,7 +4207,9 @@ static int cm_init_qp_rts_attr(struct cm_id_private *cm_id_priv,
}
} else {
*qp_attr_mask = IB_QP_ALT_PATH | IB_QP_PATH_MIG_STATE;
- qp_attr->alt_port_num = cm_id_priv->alt_av.port->port_num;
+ if (cm_id_priv->alt_av.port)
+ qp_attr->alt_port_num =
+ cm_id_priv->alt_av.port->port_num;
qp_attr->alt_pkey_index = cm_id_priv->alt_av.pkey_index;
qp_attr->alt_timeout = cm_id_priv->alt_av.timeout;
qp_attr->alt_ah_attr = cm_id_priv->alt_av.ah_attr;
@@ -4174,9 +4218,7 @@ static int cm_init_qp_rts_attr(struct cm_id_private *cm_id_priv,
ret = 0;
break;
default:
- pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
- __func__, be32_to_cpu(cm_id_priv->id.local_id),
- cm_id_priv->id.state);
+ trace_icm_qp_rts_err(&cm_id_priv->id);
ret = -EINVAL;
break;
}
@@ -4210,75 +4252,76 @@ int ib_cm_init_qp_attr(struct ib_cm_id *cm_id,
}
EXPORT_SYMBOL(ib_cm_init_qp_attr);
-static ssize_t cm_show_counter(struct kobject *obj, struct attribute *attr,
- char *buf)
+static ssize_t cm_show_counter(struct ib_device *ibdev, u32 port_num,
+ struct ib_port_attribute *attr, char *buf)
{
- struct cm_counter_group *group;
- struct cm_counter_attribute *cm_attr;
-
- group = container_of(obj, struct cm_counter_group, obj);
- cm_attr = container_of(attr, struct cm_counter_attribute, attr);
-
- return sprintf(buf, "%ld\n",
- atomic_long_read(&group->counter[cm_attr->index]));
-}
-
-static const struct sysfs_ops cm_counter_ops = {
- .show = cm_show_counter
-};
+ struct cm_counter_attribute *cm_attr =
+ container_of(attr, struct cm_counter_attribute, attr);
+ struct cm_device *cm_dev = ib_get_client_data(ibdev, &cm_client);
-static struct kobj_type cm_counter_obj_type = {
- .sysfs_ops = &cm_counter_ops,
- .default_attrs = cm_counter_default_attrs
-};
+ if (WARN_ON(!cm_dev))
+ return -EINVAL;
-static char *cm_devnode(struct device *dev, umode_t *mode)
-{
- if (mode)
- *mode = 0666;
- return kasprintf(GFP_KERNEL, "infiniband/%s", dev_name(dev));
+ return sysfs_emit(
+ buf, "%ld\n",
+ atomic_long_read(
+ &cm_dev->port[port_num - 1]
+ ->counters[cm_attr->group][cm_attr->index]));
}
-struct class cm_class = {
- .owner = THIS_MODULE,
- .name = "infiniband_cm",
- .devnode = cm_devnode,
-};
-EXPORT_SYMBOL(cm_class);
-
-static int cm_create_port_fs(struct cm_port *port)
-{
- int i, ret;
-
- for (i = 0; i < CM_COUNTER_GROUPS; i++) {
- ret = ib_port_register_module_stat(port->cm_dev->ib_device,
- port->port_num,
- &port->counter_group[i].obj,
- &cm_counter_obj_type,
- counter_group_names[i]);
- if (ret)
- goto error;
+#define CM_COUNTER_ATTR(_name, _group, _index) \
+ { \
+ .attr = __ATTR(_name, 0444, cm_show_counter, NULL), \
+ .group = _group, .index = _index \
}
- return 0;
-
-error:
- while (i--)
- ib_port_unregister_module_stat(&port->counter_group[i].obj);
- return ret;
-
-}
-
-static void cm_remove_port_fs(struct cm_port *port)
-{
- int i;
-
- for (i = 0; i < CM_COUNTER_GROUPS; i++)
- ib_port_unregister_module_stat(&port->counter_group[i].obj);
+#define CM_COUNTER_GROUP(_group, _name) \
+ static struct cm_counter_attribute cm_counter_attr_##_group[] = { \
+ CM_COUNTER_ATTR(req, _group, CM_REQ_COUNTER), \
+ CM_COUNTER_ATTR(mra, _group, CM_MRA_COUNTER), \
+ CM_COUNTER_ATTR(rej, _group, CM_REJ_COUNTER), \
+ CM_COUNTER_ATTR(rep, _group, CM_REP_COUNTER), \
+ CM_COUNTER_ATTR(rtu, _group, CM_RTU_COUNTER), \
+ CM_COUNTER_ATTR(dreq, _group, CM_DREQ_COUNTER), \
+ CM_COUNTER_ATTR(drep, _group, CM_DREP_COUNTER), \
+ CM_COUNTER_ATTR(sidr_req, _group, CM_SIDR_REQ_COUNTER), \
+ CM_COUNTER_ATTR(sidr_rep, _group, CM_SIDR_REP_COUNTER), \
+ CM_COUNTER_ATTR(lap, _group, CM_LAP_COUNTER), \
+ CM_COUNTER_ATTR(apr, _group, CM_APR_COUNTER), \
+ }; \
+ static struct attribute *cm_counter_attrs_##_group[] = { \
+ &cm_counter_attr_##_group[0].attr.attr, \
+ &cm_counter_attr_##_group[1].attr.attr, \
+ &cm_counter_attr_##_group[2].attr.attr, \
+ &cm_counter_attr_##_group[3].attr.attr, \
+ &cm_counter_attr_##_group[4].attr.attr, \
+ &cm_counter_attr_##_group[5].attr.attr, \
+ &cm_counter_attr_##_group[6].attr.attr, \
+ &cm_counter_attr_##_group[7].attr.attr, \
+ &cm_counter_attr_##_group[8].attr.attr, \
+ &cm_counter_attr_##_group[9].attr.attr, \
+ &cm_counter_attr_##_group[10].attr.attr, \
+ NULL, \
+ }; \
+ static const struct attribute_group cm_counter_group_##_group = { \
+ .name = _name, \
+ .attrs = cm_counter_attrs_##_group, \
+ };
-}
+CM_COUNTER_GROUP(CM_XMIT, "cm_tx_msgs")
+CM_COUNTER_GROUP(CM_XMIT_RETRIES, "cm_tx_retries")
+CM_COUNTER_GROUP(CM_RECV, "cm_rx_msgs")
+CM_COUNTER_GROUP(CM_RECV_DUPLICATES, "cm_rx_duplicates")
+
+static const struct attribute_group *cm_counter_groups[] = {
+ &cm_counter_group_CM_XMIT,
+ &cm_counter_group_CM_XMIT_RETRIES,
+ &cm_counter_group_CM_RECV,
+ &cm_counter_group_CM_RECV_DUPLICATES,
+ NULL,
+};
-static void cm_add_one(struct ib_device *ib_device)
+static int cm_add_one(struct ib_device *ib_device)
{
struct cm_device *cm_dev;
struct cm_port *port;
@@ -4292,34 +4335,38 @@ static void cm_add_one(struct ib_device *ib_device)
unsigned long flags;
int ret;
int count = 0;
- u8 i;
+ u32 i;
cm_dev = kzalloc(struct_size(cm_dev, port, ib_device->phys_port_cnt),
GFP_KERNEL);
if (!cm_dev)
- return;
+ return -ENOMEM;
+ kref_init(&cm_dev->kref);
+ spin_lock_init(&cm_dev->mad_agent_lock);
cm_dev->ib_device = ib_device;
cm_dev->ack_delay = ib_device->attrs.local_ca_ack_delay;
cm_dev->going_down = 0;
+ ib_set_client_data(ib_device, &cm_client, cm_dev);
+
set_bit(IB_MGMT_METHOD_SEND, reg_req.method_mask);
- for (i = 1; i <= ib_device->phys_port_cnt; i++) {
+ rdma_for_each_port (ib_device, i) {
if (!rdma_cap_ib_cm(ib_device, i))
continue;
port = kzalloc(sizeof *port, GFP_KERNEL);
- if (!port)
+ if (!port) {
+ ret = -ENOMEM;
goto error1;
+ }
cm_dev->port[i-1] = port;
port->cm_dev = cm_dev;
port->port_num = i;
- INIT_LIST_HEAD(&port->cm_priv_prim_list);
- INIT_LIST_HEAD(&port->cm_priv_altr_list);
-
- ret = cm_create_port_fs(port);
+ ret = ib_port_register_client_groups(ib_device, i,
+ cm_counter_groups);
if (ret)
goto error1;
@@ -4331,8 +4378,10 @@ static void cm_add_one(struct ib_device *ib_device)
cm_recv_handler,
port,
0);
- if (IS_ERR(port->mad_agent))
+ if (IS_ERR(port->mad_agent)) {
+ ret = PTR_ERR(port->mad_agent);
goto error2;
+ }
ret = ib_modify_port(ib_device, i, 0, &port_modify);
if (ret)
@@ -4341,24 +4390,23 @@ static void cm_add_one(struct ib_device *ib_device)
count++;
}
- if (!count)
+ if (!count) {
+ ret = -EOPNOTSUPP;
goto free;
-
- ib_set_client_data(ib_device, &cm_client, cm_dev);
+ }
write_lock_irqsave(&cm.device_lock, flags);
list_add_tail(&cm_dev->list, &cm.device_list);
write_unlock_irqrestore(&cm.device_lock, flags);
- return;
+ return 0;
error3:
ib_unregister_mad_agent(port->mad_agent);
error2:
- cm_remove_port_fs(port);
+ ib_port_unregister_client_groups(ib_device, i, cm_counter_groups);
error1:
port_modify.set_port_cap_mask = 0;
port_modify.clr_port_cap_mask = IB_PORT_CM_SUP;
- kfree(port);
while (--i) {
if (!rdma_cap_ib_cm(ib_device, i))
continue;
@@ -4366,27 +4414,23 @@ error1:
port = cm_dev->port[i-1];
ib_modify_port(ib_device, port->port_num, 0, &port_modify);
ib_unregister_mad_agent(port->mad_agent);
- cm_remove_port_fs(port);
- kfree(port);
+ ib_port_unregister_client_groups(ib_device, i,
+ cm_counter_groups);
}
free:
- kfree(cm_dev);
+ cm_device_put(cm_dev);
+ return ret;
}
static void cm_remove_one(struct ib_device *ib_device, void *client_data)
{
struct cm_device *cm_dev = client_data;
struct cm_port *port;
- struct cm_id_private *cm_id_priv;
- struct ib_mad_agent *cur_mad_agent;
struct ib_port_modify port_modify = {
.clr_port_cap_mask = IB_PORT_CM_SUP
};
unsigned long flags;
- int i;
-
- if (!cm_dev)
- return;
+ u32 i;
write_lock_irqsave(&cm.device_lock, flags);
list_del(&cm_dev->list);
@@ -4396,35 +4440,34 @@ static void cm_remove_one(struct ib_device *ib_device, void *client_data)
cm_dev->going_down = 1;
spin_unlock_irq(&cm.lock);
- for (i = 1; i <= ib_device->phys_port_cnt; i++) {
+ rdma_for_each_port (ib_device, i) {
+ struct ib_mad_agent *mad_agent;
+
if (!rdma_cap_ib_cm(ib_device, i))
continue;
port = cm_dev->port[i-1];
+ mad_agent = port->mad_agent;
ib_modify_port(ib_device, port->port_num, 0, &port_modify);
- /* Mark all the cm_id's as not valid */
- spin_lock_irq(&cm.lock);
- list_for_each_entry(cm_id_priv, &port->cm_priv_altr_list, altr_list)
- cm_id_priv->altr_send_port_not_ready = 1;
- list_for_each_entry(cm_id_priv, &port->cm_priv_prim_list, prim_list)
- cm_id_priv->prim_send_port_not_ready = 1;
- spin_unlock_irq(&cm.lock);
/*
* We flush the queue here after the going_down set, this
* verify that no new works will be queued in the recv handler,
* after that we can call the unregister_mad_agent
*/
flush_workqueue(cm.wq);
- spin_lock_irq(&cm.state_lock);
- cur_mad_agent = port->mad_agent;
+ /*
+ * The above ensures no call paths from the work are running,
+ * the remaining paths all take the mad_agent_lock.
+ */
+ spin_lock(&cm_dev->mad_agent_lock);
port->mad_agent = NULL;
- spin_unlock_irq(&cm.state_lock);
- ib_unregister_mad_agent(cur_mad_agent);
- cm_remove_port_fs(port);
- kfree(port);
+ spin_unlock(&cm_dev->mad_agent_lock);
+ ib_unregister_mad_agent(mad_agent);
+ ib_port_unregister_client_groups(ib_device, i,
+ cm_counter_groups);
}
- kfree(cm_dev);
+ cm_device_put(cm_dev);
}
static int __init ib_cm_init(void)
@@ -4434,22 +4477,15 @@ static int __init ib_cm_init(void)
INIT_LIST_HEAD(&cm.device_list);
rwlock_init(&cm.device_lock);
spin_lock_init(&cm.lock);
- spin_lock_init(&cm.state_lock);
cm.listen_service_table = RB_ROOT;
cm.listen_service_id = be64_to_cpu(IB_CM_ASSIGN_SERVICE_ID);
cm.remote_id_table = RB_ROOT;
cm.remote_qp_table = RB_ROOT;
cm.remote_sidr_table = RB_ROOT;
- xa_init_flags(&cm.local_id_table, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
+ xa_init_flags(&cm.local_id_table, XA_FLAGS_ALLOC);
get_random_bytes(&cm.random_id_operand, sizeof cm.random_id_operand);
INIT_LIST_HEAD(&cm.timewait_list);
- ret = class_register(&cm_class);
- if (ret) {
- ret = -ENOMEM;
- goto error1;
- }
-
cm.wq = alloc_workqueue("ib_cm", 0, 1);
if (!cm.wq) {
ret = -ENOMEM;
@@ -4464,8 +4500,6 @@ static int __init ib_cm_init(void)
error3:
destroy_workqueue(cm.wq);
error2:
- class_unregister(&cm_class);
-error1:
return ret;
}
@@ -4486,7 +4520,6 @@ static void __exit ib_cm_cleanup(void)
kfree(timewait_info);
}
- class_unregister(&cm_class);
WARN_ON(!xa_empty(&cm.local_id_table));
}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.