/*
* Copyright (c) 2004 Topspin Communications. All rights reserved.
- * Copyright (c) 2005 Voltaire, Inc. All rights reserved.
+ * Copyright (c) 2005 Voltaire, Inc. All rights reserved.
* Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
*
* This software is available to you under a choice of one of two
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*
- * $Id: user_mad.c 4010 2005-11-09 23:11:56Z roland $
+ * $Id: user_mad.c 5596 2006-03-03 01:00:07Z sean.hefty $
*/
#include <linux/module.h>
struct ib_umad_file {
struct ib_umad_port *port;
struct list_head recv_list;
+ struct list_head send_list;
struct list_head port_list;
spinlock_t recv_lock;
+ spinlock_t send_lock;
wait_queue_head_t recv_wait;
struct ib_mad_agent *agent[IB_UMAD_MAX_AGENTS];
int agents_dead;
struct ib_umad_packet {
struct ib_mad_send_buf *msg;
+ struct ib_mad_recv_wc *recv_wc;
struct list_head list;
int length;
struct ib_user_mad mad;
return ret;
}
+static void dequeue_send(struct ib_umad_file *file,
+ struct ib_umad_packet *packet)
+ {
+ spin_lock_irq(&file->send_lock);
+ list_del(&packet->list);
+ spin_unlock_irq(&file->send_lock);
+ }
+
static void send_handler(struct ib_mad_agent *agent,
struct ib_mad_send_wc *send_wc)
{
struct ib_umad_file *file = agent->context;
- struct ib_umad_packet *timeout;
struct ib_umad_packet *packet = send_wc->send_buf->context[0];
+ dequeue_send(file, packet);
ib_destroy_ah(packet->msg->ah);
ib_free_send_mad(packet->msg);
if (send_wc->status == IB_WC_RESP_TIMEOUT_ERR) {
- timeout = kzalloc(sizeof *timeout + IB_MGMT_MAD_HDR, GFP_KERNEL);
- if (!timeout)
- goto out;
-
- timeout->length = IB_MGMT_MAD_HDR;
- timeout->mad.hdr.id = packet->mad.hdr.id;
- timeout->mad.hdr.status = ETIMEDOUT;
- memcpy(timeout->mad.data, packet->mad.data,
- sizeof (struct ib_mad_hdr));
-
- if (queue_packet(file, agent, timeout))
- kfree(timeout);
+ packet->length = IB_MGMT_MAD_HDR;
+ packet->mad.hdr.status = ETIMEDOUT;
+ if (!queue_packet(file, agent, packet))
+ return;
}
-out:
kfree(packet);
}
{
struct ib_umad_file *file = agent->context;
struct ib_umad_packet *packet;
- int length;
if (mad_recv_wc->wc->status != IB_WC_SUCCESS)
- goto out;
+ goto err1;
- length = mad_recv_wc->mad_len;
- packet = kzalloc(sizeof *packet + length, GFP_KERNEL);
+ packet = kzalloc(sizeof *packet, GFP_KERNEL);
if (!packet)
- goto out;
-
- packet->length = length;
+ goto err1;
- ib_coalesce_recv_mad(mad_recv_wc, packet->mad.data);
+ packet->length = mad_recv_wc->mad_len;
+ packet->recv_wc = mad_recv_wc;
packet->mad.hdr.status = 0;
- packet->mad.hdr.length = length + sizeof (struct ib_user_mad);
+ packet->mad.hdr.length = sizeof (struct ib_user_mad) +
+ mad_recv_wc->mad_len;
packet->mad.hdr.qpn = cpu_to_be32(mad_recv_wc->wc->src_qp);
packet->mad.hdr.lid = cpu_to_be16(mad_recv_wc->wc->slid);
packet->mad.hdr.sl = mad_recv_wc->wc->sl;
}
if (queue_packet(file, agent, packet))
- kfree(packet);
+ goto err2;
+ return;
-out:
+err2:
+ kfree(packet);
+err1:
ib_free_recv_mad(mad_recv_wc);
}
+static ssize_t copy_recv_mad(char __user *buf, struct ib_umad_packet *packet,
+ size_t count)
+{
+ struct ib_mad_recv_buf *recv_buf;
+ int left, seg_payload, offset, max_seg_payload;
+
+ /* We need enough room to copy the first (or only) MAD segment. */
+ recv_buf = &packet->recv_wc->recv_buf;
+ if ((packet->length <= sizeof (*recv_buf->mad) &&
+ count < sizeof (packet->mad) + packet->length) ||
+ (packet->length > sizeof (*recv_buf->mad) &&
+ count < sizeof (packet->mad) + sizeof (*recv_buf->mad)))
+ return -EINVAL;
+
+ if (copy_to_user(buf, &packet->mad, sizeof (packet->mad)))
+ return -EFAULT;
+
+ buf += sizeof (packet->mad);
+ seg_payload = min_t(int, packet->length, sizeof (*recv_buf->mad));
+ if (copy_to_user(buf, recv_buf->mad, seg_payload))
+ return -EFAULT;
+
+ if (seg_payload < packet->length) {
+ /*
+ * Multipacket RMPP MAD message. Copy remainder of message.
+ * Note that last segment may have a shorter payload.
+ */
+ if (count < sizeof (packet->mad) + packet->length) {
+ /*
+ * The buffer is too small, return the first RMPP segment,
+ * which includes the RMPP message length.
+ */
+ return -ENOSPC;
+ }
+ offset = ib_get_mad_data_offset(recv_buf->mad->mad_hdr.mgmt_class);
+ max_seg_payload = sizeof (struct ib_mad) - offset;
+
+ for (left = packet->length - seg_payload, buf += seg_payload;
+ left; left -= seg_payload, buf += seg_payload) {
+ recv_buf = container_of(recv_buf->list.next,
+ struct ib_mad_recv_buf, list);
+ seg_payload = min(left, max_seg_payload);
+ if (copy_to_user(buf, ((void *) recv_buf->mad) + offset,
+ seg_payload))
+ return -EFAULT;
+ }
+ }
+ return sizeof (packet->mad) + packet->length;
+}
+
+static ssize_t copy_send_mad(char __user *buf, struct ib_umad_packet *packet,
+ size_t count)
+{
+ ssize_t size = sizeof (packet->mad) + packet->length;
+
+ if (count < size)
+ return -EINVAL;
+
+ if (copy_to_user(buf, &packet->mad, size))
+ return -EFAULT;
+
+ return size;
+}
+
static ssize_t ib_umad_read(struct file *filp, char __user *buf,
size_t count, loff_t *pos)
{
struct ib_umad_packet *packet;
ssize_t ret;
- if (count < sizeof (struct ib_user_mad) + sizeof (struct ib_mad))
+ if (count < sizeof (struct ib_user_mad))
return -EINVAL;
spin_lock_irq(&file->recv_lock);
spin_unlock_irq(&file->recv_lock);
- if (count < packet->length + sizeof (struct ib_user_mad)) {
- /* Return length needed (and first RMPP segment) if too small */
- if (copy_to_user(buf, &packet->mad,
- sizeof (struct ib_user_mad) + sizeof (struct ib_mad)))
- ret = -EFAULT;
- else
- ret = -ENOSPC;
- } else if (copy_to_user(buf, &packet->mad,
- packet->length + sizeof (struct ib_user_mad)))
- ret = -EFAULT;
+ if (packet->recv_wc)
+ ret = copy_recv_mad(buf, packet, count);
else
- ret = packet->length + sizeof (struct ib_user_mad);
+ ret = copy_send_mad(buf, packet, count);
+
if (ret < 0) {
/* Requeue packet */
spin_lock_irq(&file->recv_lock);
list_add(&packet->list, &file->recv_list);
spin_unlock_irq(&file->recv_lock);
- } else
+ } else {
+ if (packet->recv_wc)
+ ib_free_recv_mad(packet->recv_wc);
kfree(packet);
+ }
return ret;
}
+static int copy_rmpp_mad(struct ib_mad_send_buf *msg, const char __user *buf)
+{
+ int left, seg;
+
+ /* Copy class specific header */
+ if ((msg->hdr_len > IB_MGMT_RMPP_HDR) &&
+ copy_from_user(msg->mad + IB_MGMT_RMPP_HDR, buf + IB_MGMT_RMPP_HDR,
+ msg->hdr_len - IB_MGMT_RMPP_HDR))
+ return -EFAULT;
+
+ /* All headers are in place. Copy data segments. */
+ for (seg = 1, left = msg->data_len, buf += msg->hdr_len; left > 0;
+ seg++, left -= msg->seg_size, buf += msg->seg_size) {
+ if (copy_from_user(ib_get_rmpp_segment(msg, seg), buf,
+ min(left, msg->seg_size)))
+ return -EFAULT;
+ }
+ return 0;
+}
+
+static int same_destination(struct ib_user_mad_hdr *hdr1,
+ struct ib_user_mad_hdr *hdr2)
+{
+ if (!hdr1->grh_present && !hdr2->grh_present)
+ return (hdr1->lid == hdr2->lid);
+
+ if (hdr1->grh_present && hdr2->grh_present)
+ return !memcmp(hdr1->gid, hdr2->gid, 16);
+
+ return 0;
+}
+
+static int is_duplicate(struct ib_umad_file *file,
+ struct ib_umad_packet *packet)
+{
+ struct ib_umad_packet *sent_packet;
+ struct ib_mad_hdr *sent_hdr, *hdr;
+
+ hdr = (struct ib_mad_hdr *) packet->mad.data;
+ list_for_each_entry(sent_packet, &file->send_list, list) {
+ sent_hdr = (struct ib_mad_hdr *) sent_packet->mad.data;
+
+ if ((hdr->tid != sent_hdr->tid) ||
+ (hdr->mgmt_class != sent_hdr->mgmt_class))
+ continue;
+
+ /*
+ * No need to be overly clever here. If two new operations have
+ * the same TID, reject the second as a duplicate. This is more
+ * restrictive than required by the spec.
+ */
+ if (!ib_response_mad((struct ib_mad *) hdr)) {
+ if (!ib_response_mad((struct ib_mad *) sent_hdr))
+ return 1;
+ continue;
+ } else if (!ib_response_mad((struct ib_mad *) sent_hdr))
+ continue;
+
+ if (same_destination(&packet->mad.hdr, &sent_packet->mad.hdr))
+ return 1;
+ }
+
+ return 0;
+}
+
static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
size_t count, loff_t *pos)
{
struct ib_ah_attr ah_attr;
struct ib_ah *ah;
struct ib_rmpp_mad *rmpp_mad;
- u8 method;
__be64 *tid;
- int ret, length, hdr_len, copy_offset;
- int rmpp_active, has_rmpp_header;
+ int ret, data_len, hdr_len, copy_offset, rmpp_active;
if (count < sizeof (struct ib_user_mad) + IB_MGMT_RMPP_HDR)
return -EINVAL;
- length = count - sizeof (struct ib_user_mad);
- packet = kmalloc(sizeof *packet + IB_MGMT_RMPP_HDR, GFP_KERNEL);
+ packet = kzalloc(sizeof *packet + IB_MGMT_RMPP_HDR, GFP_KERNEL);
if (!packet)
return -ENOMEM;
}
rmpp_mad = (struct ib_rmpp_mad *) packet->mad.data;
- if (rmpp_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_ADM) {
- hdr_len = IB_MGMT_SA_HDR;
- copy_offset = IB_MGMT_RMPP_HDR;
- has_rmpp_header = 1;
- } else if (rmpp_mad->mad_hdr.mgmt_class >= IB_MGMT_CLASS_VENDOR_RANGE2_START &&
- rmpp_mad->mad_hdr.mgmt_class <= IB_MGMT_CLASS_VENDOR_RANGE2_END) {
- hdr_len = IB_MGMT_VENDOR_HDR;
- copy_offset = IB_MGMT_RMPP_HDR;
- has_rmpp_header = 1;
- } else {
- hdr_len = IB_MGMT_MAD_HDR;
+ hdr_len = ib_get_mad_data_offset(rmpp_mad->mad_hdr.mgmt_class);
+ if (!ib_is_mad_class_rmpp(rmpp_mad->mad_hdr.mgmt_class)) {
copy_offset = IB_MGMT_MAD_HDR;
- has_rmpp_header = 0;
- }
-
- if (has_rmpp_header)
+ rmpp_active = 0;
+ } else {
+ copy_offset = IB_MGMT_RMPP_HDR;
rmpp_active = ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) &
IB_MGMT_RMPP_FLAG_ACTIVE;
- else
- rmpp_active = 0;
-
- /* Validate that the management class can support RMPP */
- if (rmpp_active && !agent->rmpp_version) {
- ret = -EINVAL;
- goto err_ah;
}
+ data_len = count - sizeof (struct ib_user_mad) - hdr_len;
packet->msg = ib_create_send_mad(agent,
be32_to_cpu(packet->mad.hdr.qpn),
- 0, rmpp_active,
- hdr_len, length - hdr_len,
- GFP_KERNEL);
+ 0, rmpp_active, hdr_len,
+ data_len, GFP_KERNEL);
if (IS_ERR(packet->msg)) {
ret = PTR_ERR(packet->msg);
goto err_ah;
packet->msg->retries = packet->mad.hdr.retries;
packet->msg->context[0] = packet;
- /* Copy MAD headers (RMPP header in place) */
+ /* Copy MAD header. Any RMPP header is already in place. */
memcpy(packet->msg->mad, packet->mad.data, IB_MGMT_MAD_HDR);
- /* Now, copy rest of message from user into send buffer */
- if (copy_from_user(packet->msg->mad + copy_offset,
- buf + sizeof (struct ib_user_mad) + copy_offset,
- length - copy_offset)) {
- ret = -EFAULT;
- goto err_msg;
+ buf += sizeof (struct ib_user_mad);
+
+ if (!rmpp_active) {
+ if (copy_from_user(packet->msg->mad + copy_offset,
+ buf + copy_offset,
+ hdr_len + data_len - copy_offset)) {
+ ret = -EFAULT;
+ goto err_msg;
+ }
+ } else {
+ ret = copy_rmpp_mad(packet->msg, buf);
+ if (ret)
+ goto err_msg;
}
/*
- * If userspace is generating a request that will generate a
- * response, we need to make sure the high-order part of the
- * transaction ID matches the agent being used to send the
- * MAD.
+ * Set the high-order part of the transaction ID to make MADs from
+ * different agents unique, and allow routing responses back to the
+ * original requestor.
*/
- method = ((struct ib_mad_hdr *) packet->msg->mad)->method;
-
- if (!(method & IB_MGMT_METHOD_RESP) &&
- method != IB_MGMT_METHOD_TRAP_REPRESS &&
- method != IB_MGMT_METHOD_SEND) {
+ if (!ib_response_mad(packet->msg->mad)) {
tid = &((struct ib_mad_hdr *) packet->msg->mad)->tid;
*tid = cpu_to_be64(((u64) agent->hi_tid) << 32 |
(be64_to_cpup(tid) & 0xffffffff));
+ rmpp_mad->mad_hdr.tid = *tid;
+ }
+
+ spin_lock_irq(&file->send_lock);
+ ret = is_duplicate(file, packet);
+ if (!ret)
+ list_add_tail(&packet->list, &file->send_list);
+ spin_unlock_irq(&file->send_lock);
+ if (ret) {
+ ret = -EINVAL;
+ goto err_msg;
}
ret = ib_post_send_mad(packet->msg, NULL);
if (ret)
- goto err_msg;
+ goto err_send;
up_read(&file->port->mutex);
-
return count;
+err_send:
+ dequeue_send(file, packet);
err_msg:
ib_free_send_mad(packet->msg);
-
err_ah:
ib_destroy_ah(ah);
-
err_up:
up_read(&file->port->mutex);
-
err:
kfree(packet);
return ret;
}
spin_lock_init(&file->recv_lock);
+ spin_lock_init(&file->send_lock);
INIT_LIST_HEAD(&file->recv_list);
+ INIT_LIST_HEAD(&file->send_list);
init_waitqueue_head(&file->recv_wait);
file->port = port;
already_dead = file->agents_dead;
file->agents_dead = 1;
- list_for_each_entry_safe(packet, tmp, &file->recv_list, list)
+ list_for_each_entry_safe(packet, tmp, &file->recv_list, list) {
+ if (packet->recv_wc)
+ ib_free_recv_mad(packet->recv_wc);
kfree(packet);
+ }
list_del(&file->port_list);
struct ib_umad_device *umad_dev;
int s, e, i;
- if (device->node_type == IB_NODE_SWITCH)
+ if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
+ return;
+
+ if (device->node_type == RDMA_NODE_IB_SWITCH)
s = e = 0;
else {
s = 1;