mirror of
https://github.com/torvalds/linux.git
synced 2026-09-27 11:02:03 +02:00
mlx4_ib_multiplex_cm_handler() allocates an id_map_entry for CM transactions, but the entry is normally released only on DREQ or REJ flows. In the duplicate REP handling scenario, cm_dup_rep_handler() may be invoked when the remote side receives a REP for which no matching cm_id_priv exists. In such cases the CM handshake never reaches RTU, and the sender side may never receive either DREQ or REJ cleanup events. As a result, the allocated id_map_entry remains indefinitely, resulting in a stale mapping leak. Fix this by arming an RTU-abandon cleanup timeout when the id_map_entry is allocated. The timeout uses the mlx4 CM workqueue and the existing schedule_delayed() path, so later DREQ/REJ cleanup can shorten the pending timeout with mod_delayed_work(). Track whether a pending cleanup timeout is still waiting for RTU. RTU cancels only that initial timeout; if DREQ/REJ has already converted it to normal teardown cleanup, a late or duplicate RTU does not cancel the teardown timer. If the RTU timeout callback has already started, leave the entry on the timeout path and make the RTU packet lose that race. Hold id_map_lock while looking up the entry, canceling the RTU timeout, scheduling teardown cleanup, and copying the id values needed by the CM handlers. The delayed-work callback rechecks scheduled_delete under the same lock before removing and freeing the entry, avoiding use-after-free when RTU races with timeout execution. Signed-off-by: Praveen Kumar Kannoju <praveen.kannoju@oracle.com> Link: https://patch.msgid.link/20260715080738.1357072-1-praveen.kannoju@oracle.com Signed-off-by: Leon Romanovsky <leon@kernel.org>
675 lines
18 KiB
C
675 lines
18 KiB
C
/*
|
|
* Copyright (c) 2012 Mellanox Technologies. All rights reserved.
|
|
*
|
|
* This software is available to you under a choice of one of two
|
|
* licenses. You may choose to be licensed under the terms of the GNU
|
|
* General Public License (GPL) Version 2, available from the file
|
|
* COPYING in the main directory of this source tree, or the
|
|
* OpenIB.org BSD license below:
|
|
*
|
|
* Redistribution and use in source and binary forms, with or
|
|
* without modification, are permitted provided that the following
|
|
* conditions are met:
|
|
*
|
|
* - Redistributions of source code must retain the above
|
|
* copyright notice, this list of conditions and the following
|
|
* disclaimer.
|
|
*
|
|
* - Redistributions in binary form must reproduce the above
|
|
* copyright notice, this list of conditions and the following
|
|
* disclaimer in the documentation and/or other materials
|
|
* provided with the distribution.
|
|
*
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
|
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
|
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
|
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
|
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
|
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
|
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
* SOFTWARE.
|
|
*/
|
|
|
|
#include <rdma/ib_mad.h>
|
|
|
|
#include <linux/mlx4/cmd.h>
|
|
#include <linux/rbtree.h>
|
|
#include <linux/idr.h>
|
|
#include <rdma/ib_cm.h>
|
|
|
|
#include "mlx4_ib.h"
|
|
|
|
#define CM_CLEANUP_CACHE_TIMEOUT (30 * HZ)
|
|
#define CM_RTU_TIMEOUT (60 * HZ)
|
|
|
|
struct id_map_entry {
|
|
struct rb_node node;
|
|
|
|
u32 sl_cm_id;
|
|
u32 pv_cm_id;
|
|
int slave_id;
|
|
int scheduled_delete;
|
|
bool rtu_timeout;
|
|
struct mlx4_ib_dev *dev;
|
|
|
|
struct list_head list;
|
|
struct delayed_work timeout;
|
|
};
|
|
|
|
struct rej_tmout_entry {
|
|
int slave;
|
|
u32 rem_pv_cm_id;
|
|
struct delayed_work timeout;
|
|
struct xarray *xa_rej_tmout;
|
|
};
|
|
|
|
struct cm_generic_msg {
|
|
struct ib_mad_hdr hdr;
|
|
|
|
__be32 local_comm_id;
|
|
__be32 remote_comm_id;
|
|
unsigned char unused[2];
|
|
__be16 rej_reason;
|
|
};
|
|
|
|
struct cm_sidr_generic_msg {
|
|
struct ib_mad_hdr hdr;
|
|
__be32 request_id;
|
|
};
|
|
|
|
struct cm_req_msg {
|
|
unsigned char unused[0x60];
|
|
union ib_gid primary_path_sgid;
|
|
};
|
|
|
|
static struct workqueue_struct *cm_wq;
|
|
|
|
static void set_local_comm_id(struct ib_mad *mad, u32 cm_id)
|
|
{
|
|
if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
|
|
struct cm_sidr_generic_msg *msg =
|
|
(struct cm_sidr_generic_msg *)mad;
|
|
msg->request_id = cpu_to_be32(cm_id);
|
|
} else if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
|
|
pr_err("trying to set local_comm_id in SIDR_REP\n");
|
|
return;
|
|
} else {
|
|
struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
|
|
msg->local_comm_id = cpu_to_be32(cm_id);
|
|
}
|
|
}
|
|
|
|
static u32 get_local_comm_id(struct ib_mad *mad)
|
|
{
|
|
if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
|
|
struct cm_sidr_generic_msg *msg =
|
|
(struct cm_sidr_generic_msg *)mad;
|
|
return be32_to_cpu(msg->request_id);
|
|
} else if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
|
|
pr_err("trying to set local_comm_id in SIDR_REP\n");
|
|
return -1;
|
|
} else {
|
|
struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
|
|
return be32_to_cpu(msg->local_comm_id);
|
|
}
|
|
}
|
|
|
|
static void set_remote_comm_id(struct ib_mad *mad, u32 cm_id)
|
|
{
|
|
if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
|
|
struct cm_sidr_generic_msg *msg =
|
|
(struct cm_sidr_generic_msg *)mad;
|
|
msg->request_id = cpu_to_be32(cm_id);
|
|
} else if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
|
|
pr_err("trying to set remote_comm_id in SIDR_REQ\n");
|
|
return;
|
|
} else {
|
|
struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
|
|
msg->remote_comm_id = cpu_to_be32(cm_id);
|
|
}
|
|
}
|
|
|
|
static u32 get_remote_comm_id(struct ib_mad *mad)
|
|
{
|
|
if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
|
|
struct cm_sidr_generic_msg *msg =
|
|
(struct cm_sidr_generic_msg *)mad;
|
|
return be32_to_cpu(msg->request_id);
|
|
} else if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
|
|
pr_err("trying to set remote_comm_id in SIDR_REQ\n");
|
|
return -1;
|
|
} else {
|
|
struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
|
|
return be32_to_cpu(msg->remote_comm_id);
|
|
}
|
|
}
|
|
|
|
static union ib_gid gid_from_req_msg(struct ib_device *ibdev, struct ib_mad *mad)
|
|
{
|
|
struct cm_req_msg *msg = (struct cm_req_msg *)mad;
|
|
|
|
return msg->primary_path_sgid;
|
|
}
|
|
|
|
/* Lock should be taken before called */
|
|
static struct id_map_entry *
|
|
id_map_find_by_sl_id(struct ib_device *ibdev, u32 slave_id, u32 sl_cm_id)
|
|
{
|
|
struct rb_root *sl_id_map = &to_mdev(ibdev)->sriov.sl_id_map;
|
|
struct rb_node *node = sl_id_map->rb_node;
|
|
|
|
while (node) {
|
|
struct id_map_entry *id_map_entry =
|
|
rb_entry(node, struct id_map_entry, node);
|
|
|
|
if (id_map_entry->sl_cm_id > sl_cm_id)
|
|
node = node->rb_left;
|
|
else if (id_map_entry->sl_cm_id < sl_cm_id)
|
|
node = node->rb_right;
|
|
else if (id_map_entry->slave_id > slave_id)
|
|
node = node->rb_left;
|
|
else if (id_map_entry->slave_id < slave_id)
|
|
node = node->rb_right;
|
|
else
|
|
return id_map_entry;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
static void id_map_ent_timeout(struct work_struct *work)
|
|
{
|
|
struct delayed_work *delay = to_delayed_work(work);
|
|
struct id_map_entry *ent = container_of(delay, struct id_map_entry, timeout);
|
|
struct id_map_entry *found_ent;
|
|
struct mlx4_ib_dev *dev = ent->dev;
|
|
struct mlx4_ib_sriov *sriov = &dev->sriov;
|
|
struct rb_root *sl_id_map = &sriov->sl_id_map;
|
|
|
|
spin_lock(&sriov->id_map_lock);
|
|
if (!ent->scheduled_delete) {
|
|
spin_unlock(&sriov->id_map_lock);
|
|
return;
|
|
}
|
|
if (!xa_erase(&sriov->pv_id_table, ent->pv_cm_id))
|
|
goto out;
|
|
found_ent = id_map_find_by_sl_id(&dev->ib_dev, ent->slave_id, ent->sl_cm_id);
|
|
if (found_ent && found_ent == ent)
|
|
rb_erase(&found_ent->node, sl_id_map);
|
|
|
|
out:
|
|
list_del(&ent->list);
|
|
spin_unlock(&sriov->id_map_lock);
|
|
kfree(ent);
|
|
}
|
|
|
|
static void sl_id_map_add(struct ib_device *ibdev, struct id_map_entry *new)
|
|
{
|
|
struct rb_root *sl_id_map = &to_mdev(ibdev)->sriov.sl_id_map;
|
|
struct rb_node **link = &sl_id_map->rb_node, *parent = NULL;
|
|
struct id_map_entry *ent;
|
|
int slave_id = new->slave_id;
|
|
int sl_cm_id = new->sl_cm_id;
|
|
|
|
ent = id_map_find_by_sl_id(ibdev, slave_id, sl_cm_id);
|
|
if (ent) {
|
|
pr_debug("overriding existing sl_id_map entry (cm_id = %x)\n",
|
|
sl_cm_id);
|
|
|
|
rb_replace_node(&ent->node, &new->node, sl_id_map);
|
|
return;
|
|
}
|
|
|
|
/* Go to the bottom of the tree */
|
|
while (*link) {
|
|
parent = *link;
|
|
ent = rb_entry(parent, struct id_map_entry, node);
|
|
|
|
if (ent->sl_cm_id > sl_cm_id || (ent->sl_cm_id == sl_cm_id && ent->slave_id > slave_id))
|
|
link = &(*link)->rb_left;
|
|
else
|
|
link = &(*link)->rb_right;
|
|
}
|
|
|
|
rb_link_node(&new->node, parent, link);
|
|
rb_insert_color(&new->node, sl_id_map);
|
|
}
|
|
|
|
static void schedule_delayed(struct ib_device *ibdev, struct id_map_entry *id,
|
|
unsigned long timeout, bool rtu_timeout);
|
|
|
|
static struct id_map_entry *
|
|
id_map_alloc(struct ib_device *ibdev, int slave_id, u32 sl_cm_id,
|
|
u32 *pv_cm_id)
|
|
{
|
|
int ret;
|
|
struct id_map_entry *ent;
|
|
struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
|
|
|
|
ent = kmalloc_obj(struct id_map_entry);
|
|
if (!ent)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
ent->sl_cm_id = sl_cm_id;
|
|
ent->slave_id = slave_id;
|
|
ent->scheduled_delete = 0;
|
|
ent->rtu_timeout = false;
|
|
ent->dev = to_mdev(ibdev);
|
|
INIT_DELAYED_WORK(&ent->timeout, id_map_ent_timeout);
|
|
|
|
ret = xa_alloc_cyclic(&sriov->pv_id_table, &ent->pv_cm_id, ent,
|
|
xa_limit_32b, &sriov->pv_id_next, GFP_KERNEL);
|
|
if (ret >= 0) {
|
|
spin_lock(&sriov->id_map_lock);
|
|
sl_id_map_add(ibdev, ent);
|
|
list_add_tail(&ent->list, &sriov->cm_list);
|
|
*pv_cm_id = ent->pv_cm_id;
|
|
schedule_delayed(ibdev, ent, CM_RTU_TIMEOUT, true);
|
|
spin_unlock(&sriov->id_map_lock);
|
|
return ent;
|
|
}
|
|
|
|
/*error flow*/
|
|
kfree(ent);
|
|
mlx4_ib_warn(ibdev, "Allocation failed (err:0x%x)\n", ret);
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
|
|
static struct id_map_entry *
|
|
id_map_get(struct ib_device *ibdev, int *pv_cm_id, int slave_id, int sl_cm_id)
|
|
{
|
|
struct id_map_entry *ent;
|
|
struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
|
|
|
|
lockdep_assert_held(&sriov->id_map_lock);
|
|
if (*pv_cm_id == -1) {
|
|
ent = id_map_find_by_sl_id(ibdev, slave_id, sl_cm_id);
|
|
if (ent)
|
|
*pv_cm_id = (int) ent->pv_cm_id;
|
|
} else
|
|
ent = xa_load(&sriov->pv_id_table, *pv_cm_id);
|
|
|
|
return ent;
|
|
}
|
|
|
|
static void schedule_delayed(struct ib_device *ibdev, struct id_map_entry *id,
|
|
unsigned long timeout, bool rtu_timeout)
|
|
{
|
|
struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
|
|
unsigned long flags;
|
|
|
|
lockdep_assert_held(&sriov->id_map_lock);
|
|
spin_lock_irqsave(&sriov->going_down_lock, flags);
|
|
/*make sure that there is no schedule inside the scheduled work.*/
|
|
if (!sriov->is_going_down || id->scheduled_delete) {
|
|
id->scheduled_delete = 1;
|
|
id->rtu_timeout = rtu_timeout;
|
|
mod_delayed_work(cm_wq, &id->timeout, timeout);
|
|
}
|
|
spin_unlock_irqrestore(&sriov->going_down_lock, flags);
|
|
}
|
|
|
|
#define REJ_REASON(m) be16_to_cpu(((struct cm_generic_msg *)(m))->rej_reason)
|
|
int mlx4_ib_multiplex_cm_handler(struct ib_device *ibdev, int port, int slave_id,
|
|
struct ib_mad *mad)
|
|
{
|
|
struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
|
|
struct id_map_entry *id;
|
|
u32 pv_cm_id_to_set = 0;
|
|
u32 sl_cm_id;
|
|
int pv_cm_id = -1;
|
|
|
|
if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID ||
|
|
mad->mad_hdr.attr_id == CM_REP_ATTR_ID ||
|
|
mad->mad_hdr.attr_id == CM_MRA_ATTR_ID ||
|
|
mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID ||
|
|
(mad->mad_hdr.attr_id == CM_REJ_ATTR_ID && REJ_REASON(mad) == IB_CM_REJ_TIMEOUT)) {
|
|
sl_cm_id = get_local_comm_id(mad);
|
|
spin_lock(&sriov->id_map_lock);
|
|
id = id_map_get(ibdev, &pv_cm_id, slave_id, sl_cm_id);
|
|
if (id) {
|
|
pv_cm_id_to_set = id->pv_cm_id;
|
|
if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID)
|
|
schedule_delayed(ibdev, id,
|
|
CM_CLEANUP_CACHE_TIMEOUT,
|
|
false);
|
|
}
|
|
spin_unlock(&sriov->id_map_lock);
|
|
if (id)
|
|
goto cont;
|
|
if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID)
|
|
return 0;
|
|
id = id_map_alloc(ibdev, slave_id, sl_cm_id,
|
|
&pv_cm_id_to_set);
|
|
if (IS_ERR(id)) {
|
|
mlx4_ib_warn(ibdev, "%s: id{slave: %d, sl_cm_id: 0x%x} Failed to id_map_alloc\n",
|
|
__func__, slave_id, sl_cm_id);
|
|
return PTR_ERR(id);
|
|
}
|
|
} else if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID) {
|
|
sl_cm_id = get_local_comm_id(mad);
|
|
spin_lock(&sriov->id_map_lock);
|
|
id = id_map_get(ibdev, &pv_cm_id, slave_id, sl_cm_id);
|
|
if (id) {
|
|
pv_cm_id_to_set = id->pv_cm_id;
|
|
schedule_delayed(ibdev, id, CM_CLEANUP_CACHE_TIMEOUT,
|
|
false);
|
|
}
|
|
spin_unlock(&sriov->id_map_lock);
|
|
if (!id)
|
|
return 0;
|
|
} else if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
|
|
return 0;
|
|
} else {
|
|
sl_cm_id = get_local_comm_id(mad);
|
|
spin_lock(&sriov->id_map_lock);
|
|
id = id_map_get(ibdev, &pv_cm_id, slave_id, sl_cm_id);
|
|
if (id) {
|
|
if (mad->mad_hdr.attr_id == CM_RTU_ATTR_ID &&
|
|
id->rtu_timeout) {
|
|
id->rtu_timeout = false;
|
|
if (cancel_delayed_work(&id->timeout))
|
|
id->scheduled_delete = 0;
|
|
else
|
|
id = NULL;
|
|
}
|
|
if (id)
|
|
pv_cm_id_to_set = id->pv_cm_id;
|
|
if (id && mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID)
|
|
schedule_delayed(ibdev, id,
|
|
CM_CLEANUP_CACHE_TIMEOUT,
|
|
false);
|
|
}
|
|
spin_unlock(&sriov->id_map_lock);
|
|
}
|
|
|
|
if (!id) {
|
|
pr_debug("id{slave: %d, sl_cm_id: 0x%x} is NULL! attr_id: 0x%x\n",
|
|
slave_id, sl_cm_id, be16_to_cpu(mad->mad_hdr.attr_id));
|
|
return -EINVAL;
|
|
}
|
|
|
|
cont:
|
|
set_local_comm_id(mad, pv_cm_id_to_set);
|
|
return 0;
|
|
}
|
|
|
|
static void rej_tmout_timeout(struct work_struct *work)
|
|
{
|
|
struct delayed_work *delay = to_delayed_work(work);
|
|
struct rej_tmout_entry *item = container_of(delay, struct rej_tmout_entry, timeout);
|
|
struct rej_tmout_entry *deleted;
|
|
|
|
deleted = xa_cmpxchg(item->xa_rej_tmout, item->rem_pv_cm_id, item, NULL, 0);
|
|
|
|
if (deleted != item)
|
|
pr_debug("deleted(%p) != item(%p)\n", deleted, item);
|
|
|
|
kfree(item);
|
|
}
|
|
|
|
static int alloc_rej_tmout(struct mlx4_ib_sriov *sriov, u32 rem_pv_cm_id, int slave)
|
|
{
|
|
struct rej_tmout_entry *item;
|
|
struct rej_tmout_entry *old;
|
|
int ret = 0;
|
|
|
|
xa_lock(&sriov->xa_rej_tmout);
|
|
item = xa_load(&sriov->xa_rej_tmout, (unsigned long)rem_pv_cm_id);
|
|
|
|
if (item) {
|
|
if (xa_err(item))
|
|
ret = xa_err(item);
|
|
else
|
|
/* If a retry, adjust delayed work */
|
|
mod_delayed_work(cm_wq, &item->timeout, CM_CLEANUP_CACHE_TIMEOUT);
|
|
goto err_or_exists;
|
|
}
|
|
xa_unlock(&sriov->xa_rej_tmout);
|
|
|
|
item = kmalloc_obj(*item);
|
|
if (!item)
|
|
return -ENOMEM;
|
|
|
|
INIT_DELAYED_WORK(&item->timeout, rej_tmout_timeout);
|
|
item->slave = slave;
|
|
item->rem_pv_cm_id = rem_pv_cm_id;
|
|
item->xa_rej_tmout = &sriov->xa_rej_tmout;
|
|
|
|
old = xa_cmpxchg(&sriov->xa_rej_tmout, (unsigned long)rem_pv_cm_id, NULL, item, GFP_KERNEL);
|
|
if (old) {
|
|
pr_debug(
|
|
"Non-null old entry (%p) or error (%d) when inserting\n",
|
|
old, xa_err(old));
|
|
kfree(item);
|
|
return xa_err(old);
|
|
}
|
|
|
|
queue_delayed_work(cm_wq, &item->timeout, CM_CLEANUP_CACHE_TIMEOUT);
|
|
|
|
return 0;
|
|
|
|
err_or_exists:
|
|
xa_unlock(&sriov->xa_rej_tmout);
|
|
return ret;
|
|
}
|
|
|
|
static int lookup_rej_tmout_slave(struct mlx4_ib_sriov *sriov, u32 rem_pv_cm_id)
|
|
{
|
|
struct rej_tmout_entry *item;
|
|
int slave;
|
|
|
|
xa_lock(&sriov->xa_rej_tmout);
|
|
item = xa_load(&sriov->xa_rej_tmout, (unsigned long)rem_pv_cm_id);
|
|
|
|
if (!item || xa_err(item)) {
|
|
pr_debug("Could not find slave. rem_pv_cm_id 0x%x error: %d\n",
|
|
rem_pv_cm_id, xa_err(item));
|
|
slave = !item ? -ENOENT : xa_err(item);
|
|
} else {
|
|
slave = item->slave;
|
|
}
|
|
xa_unlock(&sriov->xa_rej_tmout);
|
|
|
|
return slave;
|
|
}
|
|
|
|
int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
|
|
struct ib_mad *mad)
|
|
{
|
|
struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
|
|
u32 rem_pv_cm_id = get_local_comm_id(mad);
|
|
u32 pv_cm_id;
|
|
u32 sl_cm_id = 0;
|
|
struct id_map_entry *id;
|
|
int pv_cm_id_int;
|
|
int slave_id = 0;
|
|
int sts;
|
|
|
|
if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID ||
|
|
mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
|
|
union ib_gid gid;
|
|
|
|
if (!slave)
|
|
return 0;
|
|
|
|
gid = gid_from_req_msg(ibdev, mad);
|
|
*slave = mlx4_ib_find_real_gid(ibdev, port, gid.global.interface_id);
|
|
if (*slave < 0) {
|
|
mlx4_ib_warn(ibdev, "failed matching slave_id by gid (0x%llx)\n",
|
|
be64_to_cpu(gid.global.interface_id));
|
|
return -ENOENT;
|
|
}
|
|
|
|
sts = alloc_rej_tmout(sriov, rem_pv_cm_id, *slave);
|
|
if (sts)
|
|
/* Even if this fails, we pass on the REQ to the slave */
|
|
pr_debug("Could not allocate rej_tmout entry. rem_pv_cm_id 0x%x slave %d status %d\n",
|
|
rem_pv_cm_id, *slave, sts);
|
|
|
|
return 0;
|
|
}
|
|
|
|
pv_cm_id = get_remote_comm_id(mad);
|
|
pv_cm_id_int = pv_cm_id;
|
|
spin_lock(&sriov->id_map_lock);
|
|
id = id_map_get(ibdev, &pv_cm_id_int, -1, -1);
|
|
if (id) {
|
|
if (mad->mad_hdr.attr_id == CM_RTU_ATTR_ID &&
|
|
id->rtu_timeout) {
|
|
id->rtu_timeout = false;
|
|
if (cancel_delayed_work(&id->timeout))
|
|
id->scheduled_delete = 0;
|
|
else
|
|
id = NULL;
|
|
}
|
|
if (id && slave)
|
|
slave_id = id->slave_id;
|
|
if (id)
|
|
sl_cm_id = id->sl_cm_id;
|
|
if (id && (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID ||
|
|
mad->mad_hdr.attr_id == CM_REJ_ATTR_ID))
|
|
schedule_delayed(ibdev, id,
|
|
CM_CLEANUP_CACHE_TIMEOUT, false);
|
|
}
|
|
spin_unlock(&sriov->id_map_lock);
|
|
|
|
if (!id) {
|
|
if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID &&
|
|
REJ_REASON(mad) == IB_CM_REJ_TIMEOUT && slave) {
|
|
*slave = lookup_rej_tmout_slave(sriov, rem_pv_cm_id);
|
|
|
|
return (*slave < 0) ? *slave : 0;
|
|
}
|
|
pr_debug("Couldn't find an entry for pv_cm_id 0x%x, attr_id 0x%x\n",
|
|
pv_cm_id, be16_to_cpu(mad->mad_hdr.attr_id));
|
|
return -ENOENT;
|
|
}
|
|
|
|
if (slave)
|
|
*slave = slave_id;
|
|
set_remote_comm_id(mad, sl_cm_id);
|
|
|
|
return 0;
|
|
}
|
|
|
|
void mlx4_ib_cm_paravirt_init(struct mlx4_ib_dev *dev)
|
|
{
|
|
spin_lock_init(&dev->sriov.id_map_lock);
|
|
INIT_LIST_HEAD(&dev->sriov.cm_list);
|
|
dev->sriov.sl_id_map = RB_ROOT;
|
|
xa_init_flags(&dev->sriov.pv_id_table, XA_FLAGS_ALLOC);
|
|
xa_init(&dev->sriov.xa_rej_tmout);
|
|
}
|
|
|
|
static void rej_tmout_xa_cleanup(struct mlx4_ib_sriov *sriov, int slave)
|
|
{
|
|
struct rej_tmout_entry *item;
|
|
bool flush_needed = false;
|
|
unsigned long id;
|
|
int cnt = 0;
|
|
|
|
xa_lock(&sriov->xa_rej_tmout);
|
|
xa_for_each(&sriov->xa_rej_tmout, id, item) {
|
|
if (slave < 0 || slave == item->slave) {
|
|
mod_delayed_work(cm_wq, &item->timeout, 0);
|
|
flush_needed = true;
|
|
++cnt;
|
|
}
|
|
}
|
|
xa_unlock(&sriov->xa_rej_tmout);
|
|
|
|
if (flush_needed) {
|
|
flush_workqueue(cm_wq);
|
|
pr_debug("Deleted %d entries in xarray for slave %d during cleanup\n",
|
|
cnt, slave);
|
|
}
|
|
|
|
if (slave < 0)
|
|
WARN_ON(!xa_empty(&sriov->xa_rej_tmout));
|
|
}
|
|
|
|
/* slave = -1 ==> all slaves */
|
|
/* TBD -- call paravirt clean for single slave. Need for slave RESET event */
|
|
void mlx4_ib_cm_paravirt_clean(struct mlx4_ib_dev *dev, int slave)
|
|
{
|
|
struct mlx4_ib_sriov *sriov = &dev->sriov;
|
|
struct rb_root *sl_id_map = &sriov->sl_id_map;
|
|
struct list_head lh;
|
|
struct rb_node *nd;
|
|
int need_flush = 0;
|
|
struct id_map_entry *map, *tmp_map;
|
|
/* cancel all delayed work queue entries */
|
|
INIT_LIST_HEAD(&lh);
|
|
spin_lock(&sriov->id_map_lock);
|
|
list_for_each_entry_safe(map, tmp_map, &dev->sriov.cm_list, list) {
|
|
if (slave < 0 || slave == map->slave_id) {
|
|
if (map->scheduled_delete)
|
|
need_flush |= !cancel_delayed_work(&map->timeout);
|
|
}
|
|
}
|
|
|
|
spin_unlock(&sriov->id_map_lock);
|
|
|
|
if (need_flush)
|
|
flush_workqueue(cm_wq); /* make sure all timers were flushed */
|
|
|
|
/* now, remove all leftover entries from databases*/
|
|
spin_lock(&sriov->id_map_lock);
|
|
if (slave < 0) {
|
|
while (rb_first(sl_id_map)) {
|
|
struct id_map_entry *ent =
|
|
rb_entry(rb_first(sl_id_map),
|
|
struct id_map_entry, node);
|
|
|
|
rb_erase(&ent->node, sl_id_map);
|
|
xa_erase(&sriov->pv_id_table, ent->pv_cm_id);
|
|
}
|
|
list_splice_init(&dev->sriov.cm_list, &lh);
|
|
} else {
|
|
/* first, move nodes belonging to slave to db remove list */
|
|
nd = rb_first(sl_id_map);
|
|
while (nd) {
|
|
struct id_map_entry *ent =
|
|
rb_entry(nd, struct id_map_entry, node);
|
|
nd = rb_next(nd);
|
|
if (ent->slave_id == slave)
|
|
list_move_tail(&ent->list, &lh);
|
|
}
|
|
/* remove those nodes from databases */
|
|
list_for_each_entry_safe(map, tmp_map, &lh, list) {
|
|
rb_erase(&map->node, sl_id_map);
|
|
xa_erase(&sriov->pv_id_table, map->pv_cm_id);
|
|
}
|
|
|
|
/* add remaining nodes from cm_list */
|
|
list_for_each_entry_safe(map, tmp_map, &dev->sriov.cm_list, list) {
|
|
if (slave == map->slave_id)
|
|
list_move_tail(&map->list, &lh);
|
|
}
|
|
}
|
|
|
|
spin_unlock(&sriov->id_map_lock);
|
|
|
|
/* free any map entries left behind due to cancel_delayed_work above */
|
|
list_for_each_entry_safe(map, tmp_map, &lh, list) {
|
|
list_del(&map->list);
|
|
kfree(map);
|
|
}
|
|
|
|
rej_tmout_xa_cleanup(sriov, slave);
|
|
}
|
|
|
|
int mlx4_ib_cm_init(void)
|
|
{
|
|
cm_wq = alloc_workqueue("mlx4_ib_cm", WQ_PERCPU, 0);
|
|
if (!cm_wq)
|
|
return -ENOMEM;
|
|
|
|
return 0;
|
|
}
|
|
|
|
void mlx4_ib_cm_destroy(void)
|
|
{
|
|
destroy_workqueue(cm_wq);
|
|
}
|