* [PATCH net-next 09/11] net: Remove all_adj_list and its references
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri, netdev, davem
Cc: dledford, sean.hefty, hal.rosenstock, linux-rdma, j.vosburgh,
vfalico, andy, jeffrey.t.kirsher, intel-wired-lan, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa@cumulusnetworks.com>
Only direct adjacencies are maintained. All upper or lower devices can
be learned via the new walk API which recursively walks the adj_list for
upper devices or lower devices.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
include/linux/netdevice.h | 25 -----
net/core/dev.c | 229 +++++-----------------------------------------
2 files changed, 21 insertions(+), 233 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 053f6f75f26a..8215908556ec 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1456,7 +1456,6 @@ enum netdev_priv_flags {
* @ptype_specific: Device-specific, protocol-specific packet handlers
*
* @adj_list: Directly linked devices, like slaves for bonding
- * @all_adj_list: All linked devices, *including* neighbours
* @features: Currently active device features
* @hw_features: User-changeable features
*
@@ -1673,11 +1672,6 @@ struct net_device {
struct list_head lower;
} adj_list;
- struct {
- struct list_head upper;
- struct list_head lower;
- } all_adj_list;
-
netdev_features_t features;
netdev_features_t hw_features;
netdev_features_t wanted_features;
@@ -3832,13 +3826,6 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
updev; \
updev = netdev_upper_get_next_dev_rcu(dev, &(iter)))
-/* iterate through upper list, must be called under RCU read lock */
-#define netdev_for_each_all_upper_dev_rcu(dev, updev, iter) \
- for (iter = &(dev)->all_adj_list.upper, \
- updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)); \
- updev; \
- updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)))
-
int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *lower_dev,
void *data),
@@ -3878,18 +3865,6 @@ struct net_device *netdev_all_lower_get_next(struct net_device *dev,
struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
struct list_head **iter);
-#define netdev_for_each_all_lower_dev(dev, ldev, iter) \
- for (iter = (dev)->all_adj_list.lower.next, \
- ldev = netdev_all_lower_get_next(dev, &(iter)); \
- ldev; \
- ldev = netdev_all_lower_get_next(dev, &(iter)))
-
-#define netdev_for_each_all_lower_dev_rcu(dev, ldev, iter) \
- for (iter = (dev)->all_adj_list.lower.next, \
- ldev = netdev_all_lower_get_next_rcu(dev, &(iter)); \
- ldev; \
- ldev = netdev_all_lower_get_next_rcu(dev, &(iter)))
-
int netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *lower_dev,
void *data),
diff --git a/net/core/dev.c b/net/core/dev.c
index fcf3641db783..0f9b0985a84c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5273,6 +5273,16 @@ static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev,
return NULL;
}
+static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data)
+{
+ struct net_device *dev = (struct net_device *)data;
+
+ if (upper_dev == dev)
+ return 1;
+
+ return 0;
+}
+
/**
* netdev_has_upper_dev - Check if device is linked to an upper device
* @dev: device
@@ -5287,7 +5297,8 @@ bool netdev_has_upper_dev(struct net_device *dev,
{
ASSERT_RTNL();
- return __netdev_find_adj(upper_dev, &dev->all_adj_list.upper);
+ return netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev,
+ upper_dev);
}
EXPORT_SYMBOL(netdev_has_upper_dev);
@@ -5301,16 +5312,6 @@ EXPORT_SYMBOL(netdev_has_upper_dev);
* The caller must hold rcu lock.
*/
-static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data)
-{
- struct net_device *dev = (struct net_device *)data;
-
- if (upper_dev == dev)
- return 1;
-
- return 0;
-}
-
bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
struct net_device *upper_dev)
{
@@ -5333,7 +5334,7 @@ static bool netdev_has_any_upper_dev(struct net_device *dev)
{
ASSERT_RTNL();
- return !list_empty(&dev->all_adj_list.upper);
+ return !list_empty(&dev->adj_list.upper);
}
/**
@@ -5396,32 +5397,6 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
}
EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
-/**
- * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list
- * @dev: device
- * @iter: list_head ** of the current position
- *
- * Gets the next device from the dev's upper list, starting from iter
- * position. The caller must hold RCU read lock.
- */
-struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
- struct list_head **iter)
-{
- struct netdev_adjacent *upper;
-
- WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
-
- upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
-
- if (&upper->list == &dev->all_adj_list.upper)
- return NULL;
-
- *iter = &upper->list;
-
- return upper->dev;
-}
-EXPORT_SYMBOL(netdev_all_upper_get_next_dev_rcu);
-
static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
struct list_head **iter)
{
@@ -5548,31 +5523,6 @@ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
}
EXPORT_SYMBOL(netdev_lower_get_next);
-/**
- * netdev_all_lower_get_next - Get the next device from all lower neighbour list
- * @dev: device
- * @iter: list_head ** of the current position
- *
- * Gets the next netdev_adjacent from the dev's all lower neighbour
- * list, starting from iter position. The caller must hold RTNL lock or
- * its own locking that guarantees that the neighbour all lower
- * list will remain unchanged.
- */
-struct net_device *netdev_all_lower_get_next(struct net_device *dev, struct list_head **iter)
-{
- struct netdev_adjacent *lower;
-
- lower = list_entry(*iter, struct netdev_adjacent, list);
-
- if (&lower->list == &dev->all_adj_list.lower)
- return NULL;
-
- *iter = lower->list.next;
-
- return lower->dev;
-}
-EXPORT_SYMBOL(netdev_all_lower_get_next);
-
static struct net_device *netdev_next_lower_dev(struct net_device *dev,
struct list_head **iter)
{
@@ -5616,27 +5566,6 @@ int netdev_walk_all_lower_dev(struct net_device *dev,
}
EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev);
-/**
- * netdev_all_lower_get_next_rcu - Get the next device from all
- * lower neighbour list, RCU variant
- * @dev: device
- * @iter: list_head ** of the current position
- *
- * Gets the next netdev_adjacent from the dev's all lower neighbour
- * list, starting from iter position. The caller must hold RCU read lock.
- */
-struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
- struct list_head **iter)
-{
- struct netdev_adjacent *lower;
-
- lower = list_first_or_null_rcu(&dev->all_adj_list.lower,
- struct netdev_adjacent, list);
-
- return lower ? lower->dev : NULL;
-}
-EXPORT_SYMBOL(netdev_all_lower_get_next_rcu);
-
static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
struct list_head **iter)
{
@@ -5861,15 +5790,6 @@ static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
return 0;
}
-static int __netdev_adjacent_dev_link(struct net_device *dev,
- struct net_device *upper_dev)
-{
- return __netdev_adjacent_dev_link_lists(dev, upper_dev,
- &dev->all_adj_list.upper,
- &upper_dev->all_adj_list.lower,
- NULL, false);
-}
-
static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
struct net_device *upper_dev,
u16 ref_nr,
@@ -5880,40 +5800,19 @@ static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
__netdev_adjacent_dev_remove(upper_dev, dev, ref_nr, down_list);
}
-static void __netdev_adjacent_dev_unlink(struct net_device *dev,
- struct net_device *upper_dev,
- u16 ref_nr)
-{
- __netdev_adjacent_dev_unlink_lists(dev, upper_dev, ref_nr,
- &dev->all_adj_list.upper,
- &upper_dev->all_adj_list.lower);
-}
-
static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
struct net_device *upper_dev,
void *private, bool master)
{
- int ret = __netdev_adjacent_dev_link(dev, upper_dev);
-
- if (ret)
- return ret;
-
- ret = __netdev_adjacent_dev_link_lists(dev, upper_dev,
- &dev->adj_list.upper,
- &upper_dev->adj_list.lower,
- private, master);
- if (ret) {
- __netdev_adjacent_dev_unlink(dev, upper_dev, 1);
- return ret;
- }
-
- return 0;
+ return __netdev_adjacent_dev_link_lists(dev, upper_dev,
+ &dev->adj_list.upper,
+ &upper_dev->adj_list.lower,
+ private, master);
}
static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
struct net_device *upper_dev)
{
- __netdev_adjacent_dev_unlink(dev, upper_dev, 1);
__netdev_adjacent_dev_unlink_lists(dev, upper_dev, 1,
&dev->adj_list.upper,
&upper_dev->adj_list.lower);
@@ -5924,7 +5823,6 @@ static int __netdev_upper_dev_link(struct net_device *dev,
void *upper_priv, void *upper_info)
{
struct netdev_notifier_changeupper_info changeupper_info;
- struct netdev_adjacent *i, *j, *to_i, *to_j;
int ret = 0;
ASSERT_RTNL();
@@ -5933,10 +5831,10 @@ static int __netdev_upper_dev_link(struct net_device *dev,
return -EBUSY;
/* To prevent loops, check if dev is not upper device to upper_dev. */
- if (__netdev_find_adj(dev, &upper_dev->all_adj_list.upper))
+ if (netdev_has_upper_dev(upper_dev, dev))
return -EBUSY;
- if (__netdev_find_adj(upper_dev, &dev->adj_list.upper))
+ if (netdev_has_upper_dev(dev, upper_dev))
return -EEXIST;
if (master && netdev_master_upper_dev_get(dev))
@@ -5958,80 +5856,15 @@ static int __netdev_upper_dev_link(struct net_device *dev,
if (ret)
return ret;
- /* Now that we linked these devs, make all the upper_dev's
- * all_adj_list.upper visible to every dev's all_adj_list.lower an
- * versa, and don't forget the devices itself. All of these
- * links are non-neighbours.
- */
- list_for_each_entry(i, &dev->all_adj_list.lower, list) {
- list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
- pr_debug("Interlinking %s with %s, non-neighbour\n",
- i->dev->name, j->dev->name);
- ret = __netdev_adjacent_dev_link(i->dev, j->dev);
- if (ret)
- goto rollback_mesh;
- }
- }
-
- /* add dev to every upper_dev's upper device */
- list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
- pr_debug("linking %s's upper device %s with %s\n",
- upper_dev->name, i->dev->name, dev->name);
- ret = __netdev_adjacent_dev_link(dev, i->dev);
- if (ret)
- goto rollback_upper_mesh;
- }
-
- /* add upper_dev to every dev's lower device */
- list_for_each_entry(i, &dev->all_adj_list.lower, list) {
- pr_debug("linking %s's lower device %s with %s\n", dev->name,
- i->dev->name, upper_dev->name);
- ret = __netdev_adjacent_dev_link(i->dev, upper_dev);
- if (ret)
- goto rollback_lower_mesh;
- }
-
ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
&changeupper_info.info);
ret = notifier_to_errno(ret);
if (ret)
- goto rollback_lower_mesh;
+ goto rollback;
return 0;
-rollback_lower_mesh:
- to_i = i;
- list_for_each_entry(i, &dev->all_adj_list.lower, list) {
- if (i == to_i)
- break;
- __netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr);
- }
-
- i = NULL;
-
-rollback_upper_mesh:
- to_i = i;
- list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
- if (i == to_i)
- break;
- __netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr);
- }
-
- i = j = NULL;
-
-rollback_mesh:
- to_i = i;
- to_j = j;
- list_for_each_entry(i, &dev->all_adj_list.lower, list) {
- list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
- if (i == to_i && j == to_j)
- break;
- __netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr);
- }
- if (i == to_i)
- break;
- }
-
+rollback:
__netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
return ret;
@@ -6088,7 +5921,6 @@ void netdev_upper_dev_unlink(struct net_device *dev,
struct net_device *upper_dev)
{
struct netdev_notifier_changeupper_info changeupper_info;
- struct netdev_adjacent *i, *j;
ASSERT_RTNL();
changeupper_info.upper_dev = upper_dev;
@@ -6100,23 +5932,6 @@ void netdev_upper_dev_unlink(struct net_device *dev,
__netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
- /* Here is the tricky part. We must remove all dev's lower
- * devices from all upper_dev's upper devices and vice
- * versa, to maintain the graph relationship.
- */
- list_for_each_entry(i, &dev->all_adj_list.lower, list)
- list_for_each_entry(j, &upper_dev->all_adj_list.upper, list)
- __netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr);
-
- /* remove also the devices itself from lower/upper device
- * list
- */
- list_for_each_entry(i, &dev->all_adj_list.lower, list)
- __netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr);
-
- list_for_each_entry(i, &upper_dev->all_adj_list.upper, list)
- __netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr);
-
call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
&changeupper_info.info);
}
@@ -7809,8 +7624,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
INIT_LIST_HEAD(&dev->link_watch_list);
INIT_LIST_HEAD(&dev->adj_list.upper);
INIT_LIST_HEAD(&dev->adj_list.lower);
- INIT_LIST_HEAD(&dev->all_adj_list.upper);
- INIT_LIST_HEAD(&dev->all_adj_list.lower);
INIT_LIST_HEAD(&dev->ptype_all);
INIT_LIST_HEAD(&dev->ptype_specific);
#ifdef CONFIG_NET_SCHED
--
2.1.4
^ permalink raw reply related
* [PATCH net-next 08/11] rocker: Flip to the new dev walk API
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA,
sean.hefty-ral2JQCrhuEAvxtiuMwx3w,
hal.rosenstock-Re5JQEeQqe8AvxtiuMwx3w,
linux-rdma-u79uwXL29TY76Z2rM5mHXA,
j.vosburgh-Re5JQEeQqe8AvxtiuMwx3w, vfalico-Re5JQEeQqe8AvxtiuMwx3w,
andy-QlMahl40kYEqcZcGjlUOXw,
jeffrey.t.kirsher-ral2JQCrhuEAvxtiuMwx3w,
intel-wired-lan-qjLDD68F18P21nG7glBr7A, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa-qUQiAmfTcIp+XZJcv9eMoEEOCMrvLtNR@public.gmane.org>
Convert rocker to the new dev walk API. This is just a code conversion;
no functional change is intended.
Signed-off-by: David Ahern <dsa-qUQiAmfTcIp+XZJcv9eMoEEOCMrvLtNR@public.gmane.org>
---
drivers/net/ethernet/rocker/rocker_main.c | 31 ++++++++++++++++++++++++-------
1 file changed, 24 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 5424fb341613..9310adc0bcbb 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2839,20 +2839,37 @@ static bool rocker_port_dev_check_under(const struct net_device *dev,
return true;
}
+struct rocker_walk_data {
+ struct rocker *rocker;
+ struct rocker_port *port;
+};
+
+static int rocker_lower_dev_walk(struct net_device *lower_dev, void *_data)
+{
+ struct rocker_walk_data *data = (struct rocker_walk_data *)_data;
+ int ret = 0;
+
+ if (rocker_port_dev_check_under(lower_dev, data->rocker)) {
+ data->port = netdev_priv(lower_dev);
+ ret = 1;
+ }
+
+ return ret;
+}
+
struct rocker_port *rocker_port_dev_lower_find(struct net_device *dev,
struct rocker *rocker)
{
- struct net_device *lower_dev;
- struct list_head *iter;
+ struct rocker_walk_data data;
if (rocker_port_dev_check_under(dev, rocker))
return netdev_priv(dev);
- netdev_for_each_all_lower_dev(dev, lower_dev, iter) {
- if (rocker_port_dev_check_under(lower_dev, rocker))
- return netdev_priv(lower_dev);
- }
- return NULL;
+ data.rocker = rocker;
+ data.port = NULL;
+ netdev_walk_all_lower_dev(dev, rocker_lower_dev_walk, &data);
+
+ return data.port;
}
static int rocker_netdevice_event(struct notifier_block *unused,
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH net-next 07/11] mlxsw: Flip to the new dev walk API
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri, netdev, davem
Cc: dledford, sean.hefty, hal.rosenstock, linux-rdma, j.vosburgh,
vfalico, andy, jeffrey.t.kirsher, intel-wired-lan, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa@cumulusnetworks.com>
Convert mlxsw users to new dev walk API. This is just a move to the
new API; no functional change is intended.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 37 ++++++++++++++++----------
1 file changed, 23 insertions(+), 14 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 1ec0a4ce3c46..1d5434ff02bb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3090,19 +3090,30 @@ static bool mlxsw_sp_port_dev_check(const struct net_device *dev)
return dev->netdev_ops == &mlxsw_sp_port_netdev_ops;
}
+static int mlxsw_lower_dev_walk(struct net_device *lower_dev, void *data)
+{
+ struct mlxsw_sp_port **port = data;
+ int ret = 0;
+
+ if (mlxsw_sp_port_dev_check(lower_dev)) {
+ *port = netdev_priv(lower_dev);
+ ret = 1;
+ }
+
+ return ret;
+}
+
static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev)
{
- struct net_device *lower_dev;
- struct list_head *iter;
+ struct mlxsw_sp_port *port;
if (mlxsw_sp_port_dev_check(dev))
return netdev_priv(dev);
- netdev_for_each_all_lower_dev(dev, lower_dev, iter) {
- if (mlxsw_sp_port_dev_check(lower_dev))
- return netdev_priv(lower_dev);
- }
- return NULL;
+ port = NULL;
+ netdev_walk_all_lower_dev(dev, mlxsw_lower_dev_walk, &port);
+
+ return port;
}
static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev)
@@ -3115,17 +3126,15 @@ static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev)
static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev)
{
- struct net_device *lower_dev;
- struct list_head *iter;
+ struct mlxsw_sp_port *port;
if (mlxsw_sp_port_dev_check(dev))
return netdev_priv(dev);
- netdev_for_each_all_lower_dev_rcu(dev, lower_dev, iter) {
- if (mlxsw_sp_port_dev_check(lower_dev))
- return netdev_priv(lower_dev);
- }
- return NULL;
+ port = NULL;
+ netdev_walk_all_lower_dev_rcu(dev, mlxsw_lower_dev_walk, &port);
+
+ return port;
}
struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev)
--
2.1.4
^ permalink raw reply related
* [PATCH net-next 06/11] ixgbe: Flip to the new dev walk API
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri, netdev, davem
Cc: dledford, sean.hefty, hal.rosenstock, linux-rdma, j.vosburgh,
vfalico, andy, jeffrey.t.kirsher, intel-wired-lan, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa@cumulusnetworks.com>
Convert ixgbe users of the old macros to new dev walk API.
This is just a move to the new API; no functional change is intended.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 132 ++++++++++++++++----------
1 file changed, 82 insertions(+), 50 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a244d9a67264..aae5e0349d93 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -5012,24 +5012,23 @@ static int ixgbe_fwd_ring_up(struct net_device *vdev,
return err;
}
-static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter)
+static int ixgbe_upper_dev_walk(struct net_device *upper, void *data)
{
- struct net_device *upper;
- struct list_head *iter;
- int err;
-
- netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) {
- if (netif_is_macvlan(upper)) {
- struct macvlan_dev *dfwd = netdev_priv(upper);
- struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv;
+ if (netif_is_macvlan(upper)) {
+ struct macvlan_dev *dfwd = netdev_priv(upper);
+ struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv;
- if (dfwd->fwd_priv) {
- err = ixgbe_fwd_ring_up(upper, vadapter);
- if (err)
- continue;
- }
- }
+ if (dfwd->fwd_priv)
+ ixgbe_fwd_ring_up(upper, vadapter);
}
+
+ return 0;
+}
+
+static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter)
+{
+ netdev_walk_all_upper_dev_rcu(adapter->netdev,
+ ixgbe_upper_dev_walk, NULL);
}
static void ixgbe_configure(struct ixgbe_adapter *adapter)
@@ -5448,12 +5447,25 @@ static void ixgbe_fdir_filter_exit(struct ixgbe_adapter *adapter)
spin_unlock(&adapter->fdir_perfect_lock);
}
+static int ixgbe_disable_macvlan(struct net_device *upper, void *data)
+{
+ if (netif_is_macvlan(upper)) {
+ struct macvlan_dev *vlan = netdev_priv(upper);
+
+ if (vlan->fwd_priv) {
+ netif_tx_stop_all_queues(upper);
+ netif_carrier_off(upper);
+ netif_tx_disable(upper);
+ }
+ }
+
+ return 0;
+}
+
void ixgbe_down(struct ixgbe_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
struct ixgbe_hw *hw = &adapter->hw;
- struct net_device *upper;
- struct list_head *iter;
int i;
/* signal that we are down to the interrupt handler */
@@ -5477,17 +5489,8 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
netif_tx_disable(netdev);
/* disable any upper devices */
- netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) {
- if (netif_is_macvlan(upper)) {
- struct macvlan_dev *vlan = netdev_priv(upper);
-
- if (vlan->fwd_priv) {
- netif_tx_stop_all_queues(upper);
- netif_carrier_off(upper);
- netif_tx_disable(upper);
- }
- }
- }
+ netdev_walk_all_upper_dev_rcu(adapter->netdev,
+ ixgbe_disable_macvlan, NULL);
ixgbe_irq_disable(adapter);
@@ -6728,6 +6731,18 @@ static void ixgbe_update_default_up(struct ixgbe_adapter *adapter)
#endif
}
+static int ixgbe_enable_macvlan(struct net_device *upper, void *data)
+{
+ if (netif_is_macvlan(upper)) {
+ struct macvlan_dev *vlan = netdev_priv(upper);
+
+ if (vlan->fwd_priv)
+ netif_tx_wake_all_queues(upper);
+ }
+
+ return 0;
+}
+
/**
* ixgbe_watchdog_link_is_up - update netif_carrier status and
* print link up message
@@ -6737,8 +6752,6 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
struct ixgbe_hw *hw = &adapter->hw;
- struct net_device *upper;
- struct list_head *iter;
u32 link_speed = adapter->link_speed;
const char *speed_str;
bool flow_rx, flow_tx;
@@ -6809,14 +6822,8 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter)
/* enable any upper devices */
rtnl_lock();
- netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) {
- if (netif_is_macvlan(upper)) {
- struct macvlan_dev *vlan = netdev_priv(upper);
-
- if (vlan->fwd_priv)
- netif_tx_wake_all_queues(upper);
- }
- }
+ netdev_walk_all_upper_dev_rcu(adapter->netdev,
+ ixgbe_enable_macvlan, NULL);
rtnl_unlock();
/* update the default user priority for VFs */
@@ -8350,12 +8357,38 @@ static int ixgbe_configure_clsu32_del_hnode(struct ixgbe_adapter *adapter,
}
#ifdef CONFIG_NET_CLS_ACT
+struct upper_walk_data {
+ struct ixgbe_adapter *adapter;
+ int ifindex;
+ u64 action;
+ u8 queue;
+};
+
+static int get_macvlan_queue(struct net_device *upper, void *_data)
+{
+ if (netif_is_macvlan(upper)) {
+ struct macvlan_dev *dfwd = netdev_priv(upper);
+ struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv;
+ struct upper_walk_data *data = _data;
+ struct ixgbe_adapter *adapter = data->adapter;
+ int ifindex = data->ifindex;
+
+ if (vadapter && vadapter->netdev->ifindex == ifindex) {
+ data->queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx;
+ data->action = data->queue;
+ return 1;
+ }
+ }
+
+ return 0;
+}
+
static int handle_redirect_action(struct ixgbe_adapter *adapter, int ifindex,
u8 *queue, u64 *action)
{
unsigned int num_vfs = adapter->num_vfs, vf;
+ struct upper_walk_data data;
struct net_device *upper;
- struct list_head *iter;
/* redirect to a SRIOV VF */
for (vf = 0; vf < num_vfs; ++vf) {
@@ -8373,17 +8406,16 @@ static int handle_redirect_action(struct ixgbe_adapter *adapter, int ifindex,
}
/* redirect to a offloaded macvlan netdev */
- netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) {
- if (netif_is_macvlan(upper)) {
- struct macvlan_dev *dfwd = netdev_priv(upper);
- struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv;
-
- if (vadapter && vadapter->netdev->ifindex == ifindex) {
- *queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx;
- *action = *queue;
- return 0;
- }
- }
+ data.adapter = adapter;
+ data.ifindex = ifindex;
+ data.action = 0;
+ data.queue = 0;
+ if (netdev_walk_all_upper_dev_rcu(adapter->netdev,
+ get_macvlan_queue, &data)) {
+ *action = data.action;
+ *queue = data.queue;
+
+ return 0;
}
return -EINVAL;
--
2.1.4
^ permalink raw reply related
* [PATCH net-next 05/11] IB/ipoib: Flip to new dev walk API
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA,
sean.hefty-ral2JQCrhuEAvxtiuMwx3w,
hal.rosenstock-Re5JQEeQqe8AvxtiuMwx3w,
linux-rdma-u79uwXL29TY76Z2rM5mHXA,
j.vosburgh-Re5JQEeQqe8AvxtiuMwx3w, vfalico-Re5JQEeQqe8AvxtiuMwx3w,
andy-QlMahl40kYEqcZcGjlUOXw,
jeffrey.t.kirsher-ral2JQCrhuEAvxtiuMwx3w,
intel-wired-lan-qjLDD68F18P21nG7glBr7A, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa-qUQiAmfTcIp+XZJcv9eMoEEOCMrvLtNR@public.gmane.org>
Convert ipoib_get_net_dev_match_addr to the new upper device walk API.
This is just a move to the new API; no functional change is intended.
Signed-off-by: David Ahern <dsa-qUQiAmfTcIp+XZJcv9eMoEEOCMrvLtNR@public.gmane.org>
---
drivers/infiniband/ulp/ipoib/ipoib_main.c | 37 +++++++++++++++++++++----------
1 file changed, 25 insertions(+), 12 deletions(-)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 5636fc3da6b8..624855ab7205 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -292,6 +292,25 @@ static struct net_device *ipoib_get_master_net_dev(struct net_device *dev)
return dev;
}
+struct ipoib_walk_data {
+ const struct sockaddr *addr;
+ struct net_device *result;
+};
+
+static int ipoib_upper_walk(struct net_device *upper, void *_data)
+{
+ struct ipoib_walk_data *data = (struct ipoib_walk_data *)_data;
+ int ret = 0;
+
+ if (ipoib_is_dev_match_addr_rcu(data->addr, upper)) {
+ dev_hold(upper);
+ data->result = upper;
+ ret = 1;
+ }
+
+ return ret;
+}
+
/**
* Find a net_device matching the given address, which is an upper device of
* the given net_device.
@@ -304,27 +323,21 @@ static struct net_device *ipoib_get_master_net_dev(struct net_device *dev)
static struct net_device *ipoib_get_net_dev_match_addr(
const struct sockaddr *addr, struct net_device *dev)
{
- struct net_device *upper,
- *result = NULL;
- struct list_head *iter;
+ struct ipoib_walk_data data = {
+ .addr = addr,
+ };
rcu_read_lock();
if (ipoib_is_dev_match_addr_rcu(addr, dev)) {
dev_hold(dev);
- result = dev;
+ data.result = dev;
goto out;
}
- netdev_for_each_all_upper_dev_rcu(dev, upper, iter) {
- if (ipoib_is_dev_match_addr_rcu(addr, upper)) {
- dev_hold(upper);
- result = upper;
- break;
- }
- }
+ netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &data);
out:
rcu_read_unlock();
- return result;
+ return data.result;
}
/* returns the number of IPoIB netdevs on top a given ipoib device matching a
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH net-next 04/11] IB/core: Flip to the new dev walk API
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri, netdev, davem
Cc: dledford, sean.hefty, hal.rosenstock, linux-rdma, j.vosburgh,
vfalico, andy, jeffrey.t.kirsher, intel-wired-lan, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa@cumulusnetworks.com>
Convert rdma_is_upper_dev_rcu, handle_netdev_upper and
ipoib_get_net_dev_match_addr to the new upper device walk API.
This is just a move to the new API; no functional change is intended.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
drivers/infiniband/core/core_priv.h | 9 +------
drivers/infiniband/core/roce_gid_mgmt.c | 42 ++++++++++++++++++---------------
2 files changed, 24 insertions(+), 27 deletions(-)
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 19d499dcab76..0c0bea091de8 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -127,14 +127,7 @@ void ib_cache_release_one(struct ib_device *device);
static inline bool rdma_is_upper_dev_rcu(struct net_device *dev,
struct net_device *upper)
{
- struct net_device *_upper = NULL;
- struct list_head *iter;
-
- netdev_for_each_all_upper_dev_rcu(dev, _upper, iter)
- if (_upper == upper)
- break;
-
- return _upper == upper;
+ return netdev_has_upper_dev_all_rcu(dev, upper);
}
int addr_init(void);
diff --git a/drivers/infiniband/core/roce_gid_mgmt.c b/drivers/infiniband/core/roce_gid_mgmt.c
index 06556c34606d..db759a68d948 100644
--- a/drivers/infiniband/core/roce_gid_mgmt.c
+++ b/drivers/infiniband/core/roce_gid_mgmt.c
@@ -437,6 +437,28 @@ static void callback_for_addr_gid_device_scan(struct ib_device *device,
&parsed->gid_attr);
}
+struct upper_list {
+ struct list_head list;
+ struct net_device *upper;
+};
+
+static int netdev_upper_walk(struct net_device *upper, void *data)
+{
+ struct upper_list *entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
+ struct list_head *upper_list = (struct list_head *)data;
+
+ if (!entry) {
+ pr_info("roce_gid_mgmt: couldn't allocate entry to delete ndev\n");
+ return 0;
+ }
+
+ list_add_tail(&entry->list, upper_list);
+ dev_hold(upper);
+ entry->upper = upper;
+
+ return 0;
+}
+
static void handle_netdev_upper(struct ib_device *ib_dev, u8 port,
void *cookie,
void (*handle_netdev)(struct ib_device *ib_dev,
@@ -444,30 +466,12 @@ static void handle_netdev_upper(struct ib_device *ib_dev, u8 port,
struct net_device *ndev))
{
struct net_device *ndev = (struct net_device *)cookie;
- struct upper_list {
- struct list_head list;
- struct net_device *upper;
- };
- struct net_device *upper;
- struct list_head *iter;
struct upper_list *upper_iter;
struct upper_list *upper_temp;
LIST_HEAD(upper_list);
rcu_read_lock();
- netdev_for_each_all_upper_dev_rcu(ndev, upper, iter) {
- struct upper_list *entry = kmalloc(sizeof(*entry),
- GFP_ATOMIC);
-
- if (!entry) {
- pr_info("roce_gid_mgmt: couldn't allocate entry to delete ndev\n");
- continue;
- }
-
- list_add_tail(&entry->list, &upper_list);
- dev_hold(upper);
- entry->upper = upper;
- }
+ netdev_walk_all_upper_dev_rcu(ndev, netdev_upper_walk, &upper_list);
rcu_read_unlock();
handle_netdev(ib_dev, port, ndev);
--
2.1.4
^ permalink raw reply related
* [PATCH net-next 03/11] net: bonding: Flip to the new dev walk API
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri, netdev, davem
Cc: dledford, sean.hefty, hal.rosenstock, linux-rdma, j.vosburgh,
vfalico, andy, jeffrey.t.kirsher, intel-wired-lan, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa@cumulusnetworks.com>
Convert alb_send_learning_packets and bond_has_this_ip to use the new
netdev_walk_all_upper_dev_rcu API. In both cases this is just a move
to the new API; no functional change is intended.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
drivers/net/bonding/bond_alb.c | 82 ++++++++++++++++++++++++++---------------
drivers/net/bonding/bond_main.c | 21 +++++++----
2 files changed, 65 insertions(+), 38 deletions(-)
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 551f0f8dead3..1ddedec61900 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -950,13 +950,61 @@ static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[],
dev_queue_xmit(skb);
}
+struct alb_walk_data {
+ struct bonding *bond;
+ struct slave *slave;
+ u8 *mac_addr;
+ bool strict_match;
+};
+
+static int alb_upper_dev_walk(struct net_device *upper, void *data)
+{
+ struct alb_walk_data *_data = (struct alb_walk_data *)data;
+ bool strict_match = _data->strict_match;
+ struct bonding *bond = _data->bond;
+ struct slave *slave = _data->slave;
+ u8 *mac_addr = _data->mac_addr;
+ struct bond_vlan_tag *tags;
+
+ if (is_vlan_dev(upper) && vlan_get_encap_level(upper) == 0) {
+ if (strict_match &&
+ ether_addr_equal_64bits(mac_addr,
+ upper->dev_addr)) {
+ alb_send_lp_vid(slave, mac_addr,
+ vlan_dev_vlan_proto(upper),
+ vlan_dev_vlan_id(upper));
+ } else if (!strict_match) {
+ alb_send_lp_vid(slave, upper->dev_addr,
+ vlan_dev_vlan_proto(upper),
+ vlan_dev_vlan_id(upper));
+ }
+ }
+
+ /* If this is a macvlan device, then only send updates
+ * when strict_match is turned off.
+ */
+ if (netif_is_macvlan(upper) && !strict_match) {
+ tags = bond_verify_device_path(bond->dev, upper, 0);
+ if (IS_ERR_OR_NULL(tags))
+ BUG();
+ alb_send_lp_vid(slave, upper->dev_addr,
+ tags[0].vlan_proto, tags[0].vlan_id);
+ kfree(tags);
+ }
+
+ return 0;
+}
+
static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
bool strict_match)
{
struct bonding *bond = bond_get_bond_by_slave(slave);
- struct net_device *upper;
- struct list_head *iter;
- struct bond_vlan_tag *tags;
+ struct alb_walk_data data = {
+ .strict_match = strict_match,
+ .mac_addr = mac_addr,
+ .slave = slave,
+ .bond = bond,
+ };
/* send untagged */
alb_send_lp_vid(slave, mac_addr, 0, 0);
@@ -965,33 +1013,7 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
* for that device.
*/
rcu_read_lock();
- netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) {
- if (is_vlan_dev(upper) && vlan_get_encap_level(upper) == 0) {
- if (strict_match &&
- ether_addr_equal_64bits(mac_addr,
- upper->dev_addr)) {
- alb_send_lp_vid(slave, mac_addr,
- vlan_dev_vlan_proto(upper),
- vlan_dev_vlan_id(upper));
- } else if (!strict_match) {
- alb_send_lp_vid(slave, upper->dev_addr,
- vlan_dev_vlan_proto(upper),
- vlan_dev_vlan_id(upper));
- }
- }
-
- /* If this is a macvlan device, then only send updates
- * when strict_match is turned off.
- */
- if (netif_is_macvlan(upper) && !strict_match) {
- tags = bond_verify_device_path(bond->dev, upper, 0);
- if (IS_ERR_OR_NULL(tags))
- BUG();
- alb_send_lp_vid(slave, upper->dev_addr,
- tags[0].vlan_proto, tags[0].vlan_id);
- kfree(tags);
- }
- }
+ netdev_walk_all_upper_dev_rcu(bond->dev, alb_upper_dev_walk, &data);
rcu_read_unlock();
}
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 3f31ca32f52b..2b4134d5e081 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2270,22 +2270,27 @@ static void bond_mii_monitor(struct work_struct *work)
}
}
+static int bond_upper_dev_walk(struct net_device *upper, void *data)
+{
+ __be32 ip = *((__be32 *)data);
+ int ret = 0;
+
+ if (ip == bond_confirm_addr(upper, 0, ip))
+ ret = 1;
+
+ return ret;
+}
+
static bool bond_has_this_ip(struct bonding *bond, __be32 ip)
{
- struct net_device *upper;
- struct list_head *iter;
bool ret = false;
if (ip == bond_confirm_addr(bond->dev, 0, ip))
return true;
rcu_read_lock();
- netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) {
- if (ip == bond_confirm_addr(upper, 0, ip)) {
- ret = true;
- break;
- }
- }
+ if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_upper_dev_walk, &ip))
+ ret = true;
rcu_read_unlock();
return ret;
--
2.1.4
^ permalink raw reply related
* [PATCH net-next 02/11] net: Introduce new api for walking upper and lower devices
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri, netdev, davem
Cc: dledford, sean.hefty, hal.rosenstock, linux-rdma, j.vosburgh,
vfalico, andy, jeffrey.t.kirsher, intel-wired-lan, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa@cumulusnetworks.com>
This patch introduces netdev_walk_all_upper_dev_rcu,
netdev_walk_all_lower_dev and netdev_walk_all_lower_dev_rcu. These
functions recursively walk the adj_list of devices to determine all upper
and lower devices.
The functions take a callback function that is invoked for each device
in the list. If the callback returns non-0, the walk is terminated and
the functions return that code back to callers.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
include/linux/netdevice.h | 17 +++++
net/core/dev.c | 158 ++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 175 insertions(+)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 136ae6bbe81e..053f6f75f26a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3839,6 +3839,14 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
updev; \
updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)))
+int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
+ int (*fn)(struct net_device *lower_dev,
+ void *data),
+ void *data);
+
+bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
+ struct net_device *upper_dev);
+
void *netdev_lower_get_next_private(struct net_device *dev,
struct list_head **iter);
void *netdev_lower_get_next_private_rcu(struct net_device *dev,
@@ -3882,6 +3890,15 @@ struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
ldev; \
ldev = netdev_all_lower_get_next_rcu(dev, &(iter)))
+int netdev_walk_all_lower_dev(struct net_device *dev,
+ int (*fn)(struct net_device *lower_dev,
+ void *data),
+ void *data);
+int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
+ int (*fn)(struct net_device *lower_dev,
+ void *data),
+ void *data);
+
void *netdev_adjacent_get_private(struct list_head *adj_list);
void *netdev_lower_get_first_private_rcu(struct net_device *dev);
struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
diff --git a/net/core/dev.c b/net/core/dev.c
index 5aaa12a9e369..fcf3641db783 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5292,6 +5292,37 @@ bool netdev_has_upper_dev(struct net_device *dev,
EXPORT_SYMBOL(netdev_has_upper_dev);
/**
+ * netdev_has_upper_dev_all - Check if device is linked to an upper device
+ * @dev: device
+ * @upper_dev: upper device to check
+ *
+ * Find out if a device is linked to specified upper device and return true
+ * in case it is. Note that this checks the entire upper device chain.
+ * The caller must hold rcu lock.
+ */
+
+static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data)
+{
+ struct net_device *dev = (struct net_device *)data;
+
+ if (upper_dev == dev)
+ return 1;
+
+ return 0;
+}
+
+bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
+ struct net_device *upper_dev)
+{
+ if (netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev,
+ upper_dev))
+ return true;
+
+ return false;
+}
+EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu);
+
+/**
* netdev_has_any_upper_dev - Check if device is linked to some device
* @dev: device
*
@@ -5391,6 +5422,51 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
}
EXPORT_SYMBOL(netdev_all_upper_get_next_dev_rcu);
+static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
+ struct list_head **iter)
+{
+ struct netdev_adjacent *upper;
+
+ WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
+
+ upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
+
+ if (&upper->list == &dev->adj_list.upper)
+ return NULL;
+
+ *iter = &upper->list;
+
+ return upper->dev;
+}
+
+int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
+ int (*fn)(struct net_device *dev,
+ void *data),
+ void *data)
+{
+ struct list_head *iter;
+ struct net_device *udev;
+ int ret;
+
+ for (iter = &(dev)->adj_list.upper,
+ udev = netdev_next_upper_dev_rcu(dev, &(iter));
+ udev;
+ udev = netdev_next_upper_dev_rcu(dev, &(iter))) {
+ /* first is the upper device itself */
+ ret = fn(udev, data);
+ if (ret)
+ return ret;
+
+ /* then look at all of its upper devices */
+ ret = netdev_walk_all_upper_dev_rcu(udev, fn, data);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu);
+
/**
* netdev_lower_get_next_private - Get the next ->private from the
* lower neighbour list
@@ -5497,6 +5573,49 @@ struct net_device *netdev_all_lower_get_next(struct net_device *dev, struct list
}
EXPORT_SYMBOL(netdev_all_lower_get_next);
+static struct net_device *netdev_next_lower_dev(struct net_device *dev,
+ struct list_head **iter)
+{
+ struct netdev_adjacent *lower;
+
+ lower = list_entry(*iter, struct netdev_adjacent, list);
+
+ if (&lower->list == &dev->adj_list.lower)
+ return NULL;
+
+ *iter = lower->list.next;
+
+ return lower->dev;
+}
+
+int netdev_walk_all_lower_dev(struct net_device *dev,
+ int (*fn)(struct net_device *dev,
+ void *data),
+ void *data)
+{
+ struct list_head *iter;
+ struct net_device *ldev;
+ int ret;
+
+ for (iter = &(dev)->adj_list.lower,
+ ldev = netdev_next_lower_dev(dev, &(iter));
+ ldev;
+ ldev = netdev_next_lower_dev(dev, &(iter))) {
+ /* first is the lower device itself */
+ ret = fn(ldev, data);
+ if (ret)
+ return ret;
+
+ /* then look at all of its lower devices */
+ ret = netdev_walk_all_lower_dev(ldev, fn, data);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev);
+
/**
* netdev_all_lower_get_next_rcu - Get the next device from all
* lower neighbour list, RCU variant
@@ -5518,6 +5637,45 @@ struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
}
EXPORT_SYMBOL(netdev_all_lower_get_next_rcu);
+static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
+ struct list_head **iter)
+{
+ struct netdev_adjacent *lower;
+
+ lower = list_first_or_null_rcu(&dev->adj_list.lower,
+ struct netdev_adjacent, list);
+
+ return lower ? lower->dev : NULL;
+}
+
+int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
+ int (*fn)(struct net_device *dev,
+ void *data),
+ void *data)
+{
+ struct list_head *iter;
+ struct net_device *ldev;
+ int ret;
+
+ for (iter = &(dev)->adj_list.lower,
+ ldev = netdev_next_lower_dev_rcu(dev, &(iter));
+ ldev;
+ ldev = netdev_next_lower_dev_rcu(dev, &(iter))) {
+ /* first is the lower device itself */
+ ret = fn(ldev, data);
+ if (ret)
+ return ret;
+
+ /* then look at all of its lower devices */
+ ret = netdev_walk_all_lower_dev_rcu(ldev, fn, data);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev_rcu);
+
/**
* netdev_lower_get_first_private_rcu - Get the first ->private from the
* lower neighbour list, RCU
--
2.1.4
^ permalink raw reply related
* [PATCH net-next 01/11] net: Remove refnr arg when inserting link adjacencies
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA,
sean.hefty-ral2JQCrhuEAvxtiuMwx3w,
hal.rosenstock-Re5JQEeQqe8AvxtiuMwx3w,
linux-rdma-u79uwXL29TY76Z2rM5mHXA,
j.vosburgh-Re5JQEeQqe8AvxtiuMwx3w, vfalico-Re5JQEeQqe8AvxtiuMwx3w,
andy-QlMahl40kYEqcZcGjlUOXw,
jeffrey.t.kirsher-ral2JQCrhuEAvxtiuMwx3w,
intel-wired-lan-qjLDD68F18P21nG7glBr7A, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa-qUQiAmfTcIp+XZJcv9eMoEEOCMrvLtNR@public.gmane.org>
Commit 93409033ae65 ("net: Add netdev all_adj_list refcnt propagation to
fix panic") propagated the refnr to insert and remove functions tracking
the netdev adjacency graph. However, for the insert path the refnr can
only be 1. Accordingly, remove the refnr argument to make that clear.
ie., the refnr arg in 93409033ae65 was only needed for the remove path.
Signed-off-by: David Ahern <dsa-qUQiAmfTcIp+XZJcv9eMoEEOCMrvLtNR@public.gmane.org>
---
net/core/dev.c | 27 ++++++++++++---------------
1 file changed, 12 insertions(+), 15 deletions(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index f1fe26f66458..5aaa12a9e369 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5589,7 +5589,6 @@ static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev,
static int __netdev_adjacent_dev_insert(struct net_device *dev,
struct net_device *adj_dev,
- u16 ref_nr,
struct list_head *dev_list,
void *private, bool master)
{
@@ -5599,7 +5598,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
adj = __netdev_find_adj(adj_dev, dev_list);
if (adj) {
- adj->ref_nr += ref_nr;
+ adj->ref_nr += 1;
return 0;
}
@@ -5609,7 +5608,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
adj->dev = adj_dev;
adj->master = master;
- adj->ref_nr = ref_nr;
+ adj->ref_nr = 1;
adj->private = private;
dev_hold(adj_dev);
@@ -5683,22 +5682,21 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev,
static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
struct net_device *upper_dev,
- u16 ref_nr,
struct list_head *up_list,
struct list_head *down_list,
void *private, bool master)
{
int ret;
- ret = __netdev_adjacent_dev_insert(dev, upper_dev, ref_nr, up_list,
+ ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list,
private, master);
if (ret)
return ret;
- ret = __netdev_adjacent_dev_insert(upper_dev, dev, ref_nr, down_list,
+ ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list,
private, false);
if (ret) {
- __netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list);
+ __netdev_adjacent_dev_remove(dev, upper_dev, 1, up_list);
return ret;
}
@@ -5706,10 +5704,9 @@ static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
}
static int __netdev_adjacent_dev_link(struct net_device *dev,
- struct net_device *upper_dev,
- u16 ref_nr)
+ struct net_device *upper_dev)
{
- return __netdev_adjacent_dev_link_lists(dev, upper_dev, ref_nr,
+ return __netdev_adjacent_dev_link_lists(dev, upper_dev,
&dev->all_adj_list.upper,
&upper_dev->all_adj_list.lower,
NULL, false);
@@ -5738,12 +5735,12 @@ static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
struct net_device *upper_dev,
void *private, bool master)
{
- int ret = __netdev_adjacent_dev_link(dev, upper_dev, 1);
+ int ret = __netdev_adjacent_dev_link(dev, upper_dev);
if (ret)
return ret;
- ret = __netdev_adjacent_dev_link_lists(dev, upper_dev, 1,
+ ret = __netdev_adjacent_dev_link_lists(dev, upper_dev,
&dev->adj_list.upper,
&upper_dev->adj_list.lower,
private, master);
@@ -5812,7 +5809,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
pr_debug("Interlinking %s with %s, non-neighbour\n",
i->dev->name, j->dev->name);
- ret = __netdev_adjacent_dev_link(i->dev, j->dev, i->ref_nr);
+ ret = __netdev_adjacent_dev_link(i->dev, j->dev);
if (ret)
goto rollback_mesh;
}
@@ -5822,7 +5819,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
pr_debug("linking %s's upper device %s with %s\n",
upper_dev->name, i->dev->name, dev->name);
- ret = __netdev_adjacent_dev_link(dev, i->dev, i->ref_nr);
+ ret = __netdev_adjacent_dev_link(dev, i->dev);
if (ret)
goto rollback_upper_mesh;
}
@@ -5831,7 +5828,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
list_for_each_entry(i, &dev->all_adj_list.lower, list) {
pr_debug("linking %s's lower device %s with %s\n", dev->name,
i->dev->name, upper_dev->name);
- ret = __netdev_adjacent_dev_link(i->dev, upper_dev, i->ref_nr);
+ ret = __netdev_adjacent_dev_link(i->dev, upper_dev);
if (ret)
goto rollback_lower_mesh;
}
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH net-next 00/11] net: Fix netdev adjacency tracking
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA,
sean.hefty-ral2JQCrhuEAvxtiuMwx3w,
hal.rosenstock-Re5JQEeQqe8AvxtiuMwx3w,
linux-rdma-u79uwXL29TY76Z2rM5mHXA,
j.vosburgh-Re5JQEeQqe8AvxtiuMwx3w, vfalico-Re5JQEeQqe8AvxtiuMwx3w,
andy-QlMahl40kYEqcZcGjlUOXw,
jeffrey.t.kirsher-ral2JQCrhuEAvxtiuMwx3w,
intel-wired-lan-qjLDD68F18P21nG7glBr7A, David Ahern
The netdev adjacency tracking is failing to create proper dependencies
for some topologies. For example this topology
+--------+
| myvrf |
+--------+
| |
| +---------+
| | macvlan |
| +---------+
| |
+----------+
| bridge |
+----------+
|
+--------+
| bond0 |
+--------+
|
+--------+
| eth3 |
+--------+
hits 1 of 2 problems depending on the order of enslavement. The base set of
commands for both cases:
ip link add bond1 type bond
ip link set bond1 up
ip link set eth3 down
ip link set eth3 master bond1
ip link set eth3 up
ip link add bridge type bridge
ip link set bridge up
ip link add macvlan link bridge type macvlan
ip link set macvlan up
ip link add myvrf type vrf table 1234
ip link set myvrf up
ip link set bridge master myvrf
Case 1 enslave macvlan to the vrf before enslaving the bond to the bridge:
ip link set macvlan master myvrf
ip link set bond1 master bridge
Attempts to delete the VRF:
ip link delete myvrf
trigger the BUG in __netdev_adjacent_dev_remove:
[ 587.405260] tried to remove device eth3 from myvrf
[ 587.407269] ------------[ cut here ]------------
[ 587.408918] kernel BUG at /home/dsa/kernel.git/net/core/dev.c:5661!
[ 587.411113] invalid opcode: 0000 [#1] SMP
[ 587.412454] Modules linked in: macvlan bridge stp llc bonding vrf
[ 587.414765] CPU: 0 PID: 726 Comm: ip Not tainted 4.8.0+ #109
[ 587.416766] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
[ 587.420241] task: ffff88013ab6eec0 task.stack: ffffc90000628000
[ 587.422163] RIP: 0010:[<ffffffff813cef03>] [<ffffffff813cef03>] __netdev_adjacent_dev_remove+0x40/0x12c
...
[ 587.446053] Call Trace:
[ 587.446424] [<ffffffff813d1542>] __netdev_adjacent_dev_unlink+0x20/0x3c
[ 587.447390] [<ffffffff813d16a3>] netdev_upper_dev_unlink+0xfa/0x15e
[ 587.448297] [<ffffffffa00003a3>] vrf_del_slave+0x13/0x2a [vrf]
[ 587.449153] [<ffffffffa00004a4>] vrf_dev_uninit+0xea/0x114 [vrf]
[ 587.450036] [<ffffffff813d19b0>] rollback_registered_many+0x22b/0x2da
[ 587.450974] [<ffffffff813d1aac>] unregister_netdevice_many+0x17/0x48
[ 587.451903] [<ffffffff813de444>] rtnl_delete_link+0x3c/0x43
[ 587.452719] [<ffffffff813dedcd>] rtnl_dellink+0x180/0x194
When the BUG is converted to a WARN_ON it shows 4 missing adjacencies:
eth3 - myvrf, mvrf - eth3, bond1 - myvrf and myvrf - bond1
All of those are because the __netdev_upper_dev_link function does not
properly link macvlan lower devices to myvrf when it is enslaved.
The second case just flips the ordering of the enslavements:
ip link set bond1 master bridge
ip link set macvlan master myvrf
Then run:
ip link delete bond1
ip link delete myvrf
The vrf delete command hangs because myvrf has a reference that has not
been released. In this case the removal code does not account for 2 paths
between eth3 and myvrf - one from bridge to vrf and the other through the
macvlan.
Rather than try to maintain a linked list of all upper and lower devices
per netdevice, only track the direct neighbors. The remaining stack can
be determined by recursively walking the neighbors.
The existing netdev_for_each_all_upper_dev_rcu,
netdev_for_each_all_lower_dev and netdev_for_each_all_lower_dev_rcu macros
are replaced with APIs that walk the upper and lower device lists. The
new APIs take a callback function and a data arg that is passed to the
callback for each device in the list. Drivers using the old macros are
converted in separate patches to make it easier on reviewers. It is an
API conversion only; no functional change is intended.
DaveM: Given the impact of this bug (both cases requiring a reboot) I
would like to get this backported to at least the 4.8 tree which as I
understand it has been targeted as the next LTS.
David Ahern (11):
net: Remove refnr arg when inserting link adjacencies
net: Introduce new api for walking upper and lower devices
net: bonding: Flip to the new dev walk API
IB/core: Flip to the new dev walk API
IB/ipoib: Flip to new dev walk API
ixgbe: Flip to the new dev walk API
mlxsw: Flip to the new dev walk API
rocker: Flip to the new dev walk API
net: Remove all_adj_list and its references
net: Add warning if any lower device is still in adjacency list
net: dev: Improve debug statements for adjacency tracking
drivers/infiniband/core/core_priv.h | 9 +-
drivers/infiniband/core/roce_gid_mgmt.c | 42 +--
drivers/infiniband/ulp/ipoib/ipoib_main.c | 37 ++-
drivers/net/bonding/bond_alb.c | 82 +++---
drivers/net/bonding/bond_main.c | 21 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 132 ++++++----
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 37 ++-
drivers/net/ethernet/rocker/rocker_main.c | 31 ++-
include/linux/netdevice.h | 38 ++-
net/core/dev.c | 349 ++++++++++++-------------
10 files changed, 428 insertions(+), 350 deletions(-)
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* RE: rdma-core release?
From: Woodruff, Robert J @ 2016-10-12 19:00 UTC (permalink / raw)
To: Jason Gunthorpe
Cc: 'Christoph Hellwig', Steve Wise, 'Doug Ledford',
'Leon Romanovsky', 'linux-rdma',
'Vladimir Sokolovsky', Davis, Arlin R
In-Reply-To: <20161012183548.GA31053-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
Jason wrote,
>What does OFED do, and what do you want? Closeness to current distro packaging? Closeness to future packaging? Something OFED >specific?
I think this is still a TBD and needs further discussion within the OFA EWG and with Vlad to see what makes the most sense.
We clearly have to comprehend things like upgrading from older versions of OFED and consider things that the Linux distro
might want us to do to make their lives easier, and the answer to that is likely different depending on the Linux distro.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: rdma-core release?
From: Jason Gunthorpe @ 2016-10-12 18:35 UTC (permalink / raw)
To: Woodruff, Robert J
Cc: 'Christoph Hellwig', Steve Wise, 'Doug Ledford',
'Leon Romanovsky', 'linux-rdma',
'Vladimir Sokolovsky', Davis, Arlin R
In-Reply-To: <9C6B67F36DCAFC479B1CF6A967258A8C7DE23B5D-8oqHQFITsIFqS6EAlXoojrfspsVTdybXVpNB7YpNyf8@public.gmane.org>
On Wed, Oct 12, 2016 at 06:17:45PM +0000, Woodruff, Robert J wrote:
> and wait till all packaging was flushed out before moving to the new
> code base. I think it would be desirable if there were some kind of
> official release tar ball or at least official release git tag that
> is recommended by you guys that we should use in OFED.
It is pretty fluid at this point, if OFED says, hey we are happy with
this commit, I'm sure Doug can tag it. I suspect we will produce tar
files out of github, so a tag means a tar will appear.
The current git HEAD should be a suitable starting point for OFED, I
think. It is no worse than what OFED had from the individual tar
files, and contins various important driver updates.
> I have not followed this really closely, but have you guys finalized
> how the packaging in SRPMs will/should work ? Or is that an exercise
> left up to the Linux distros and/or OFED to decide on ?
As Doug touched on this, the distros have to decide based on their own
internal policies how this should look, so we will help but not
dictate. SuSE and CentOS already use quite different packaging and
even different rpm names from what I can see.
What does OFED do, and what do you want? Closeness to current distro
packaging? Closeness to future packaging? Something OFED specific?
Jason
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH] IB/ipoib: move back the IB LL address into the hard header
From: Doug Ledford @ 2016-10-12 18:21 UTC (permalink / raw)
To: Jason Gunthorpe
Cc: Paolo Abeni, linux-rdma, Sean Hefty, Hal Rosenstock, netdev
In-Reply-To: <9bed7085-949b-c68b-91ed-f930702a6a94@redhat.com>
[-- Attachment #1.1: Type: text/plain, Size: 1339 bytes --]
On 10/11/2016 2:50 PM, Doug Ledford wrote:
> On 10/11/2016 2:30 PM, Jason Gunthorpe wrote:
>> On Tue, Oct 11, 2016 at 02:17:51PM -0400, Doug Ledford wrote:
>>
>>> Well, not exactly. Even if we put 65520 into the scripts, the kernel
>>> will silently drop it down to 65504. It actually won't require anyone
>>> change anything, they just won't get the full value. I experimented
>>> with this in the past for other reasons and an overly large MTU setting
>>> just resulted in the max MTU. I don't know if that's changed, but if it
>>> still works that way, this is much less of an issue than it might
>>> otherwise be.
>>
>> So it is just docs and relying on PMTU? That is not as bad..
>>
>> Still would be nice to avoid if at all possible..
>
> I agree, but we have a test getting ready to commence. We'll know
> shortly how much the reduced MTU effects things because they aren't
> going to alter any of their setup, just put the new kernel in place, and
> see what happens.
>
>
Long story short on the MTU stuff, the setups whined a bit about not
being able to set the desired MTU, used the new max MTU instead, and
things otherwise worked fine. But, Paolo submitted a v2 patch that
removes this change, so it's all moot anyway.
--
Doug Ledford <dledford@redhat.com>
GPG Key ID: 0E572FDD
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 884 bytes --]
^ permalink raw reply
* RE: rdma-core release?
From: Woodruff, Robert J @ 2016-10-12 18:17 UTC (permalink / raw)
To: Jason Gunthorpe, 'Christoph Hellwig'
Cc: Steve Wise, 'Doug Ledford', 'Leon Romanovsky',
'linux-rdma', 'Vladimir Sokolovsky',
Davis, Arlin R
In-Reply-To: <20161012164759.GB18838-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
Jason wrote,
>One of the best ways to get it tested is to get it to go through the full OFED process.
>Woody, what could we do to help make that happen? Do you know of any blocker?
>I think this will be the best for everyone. I also predict that OFED will be under pressure to quickly take up the new drivers that will land in >4.9, and their user space will live in rdma-core.
>I also propose we give someone from the OFED team repo access and they can maintain a public branch for ofed-4.8 with any backported >fixes.
>Jason
We have just started work on OFED-4.8, so there is still a possibility to move to the new tree as the basis for the user-space code that
that goes into OFED. I think that Vlad (who is the OFED integration engineer) was waiting till things were a little more finalized
and wait till all packaging was flushed out before moving to the new code base. I think it would be desirable if there were some kind of official release tar ball or at least official release git tag that is recommended by you guys that we should use in OFED.
Currently the way OFED handles user-space packages is that we wait till the maintainer of a user-space package produces a release for their user-space component, which is a tar ball with the spec files that can be used to produce SRPMS.
I have not followed this really closely, but have you guys finalized how the packaging in SRPMs will/should work ? Or is that an exercise left up to the Linux distros and/or OFED to decide on ?
In any case, Vlad is on vacation for a couple weeks, so he probably cannot re-look at this until after Nov 1 when he returns, so you have some time to decide on how you want to handle releases for this.
woody
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: rdma-core release?
From: Doug Ledford @ 2016-10-12 18:15 UTC (permalink / raw)
To: Leon Romanovsky, Jason Gunthorpe
Cc: 'Christoph Hellwig', Steve Wise, 'linux-rdma',
robert.j.woodruff-ral2JQCrhuEAvxtiuMwx3w
In-Reply-To: <20161012173702.GW9282-2ukJVAZIZ/Y@public.gmane.org>
[-- Attachment #1.1: Type: text/plain, Size: 2238 bytes --]
On 10/12/2016 1:37 PM, Leon Romanovsky wrote:
> On Wed, Oct 12, 2016 at 10:47:59AM -0600, Jason Gunthorpe wrote:
>> On Wed, Oct 12, 2016 at 09:31:49AM -0700, 'Christoph Hellwig' wrote:
>>> On Wed, Oct 12, 2016 at 09:43:08AM -0500, Steve Wise wrote:
>>>> I recommend we release something for OFED-4.8 to pull in. That
>>>> might help flush out the release process earlier rather than
>>>> later. Either way, though, I want the latest libcxgb4 in OFED-4.8
>>>> to support the new chelsio HW. But we talked about the repo being
>>>> "always stable", so I guess the OFA could just pull the code and
>>>> use it? Still would be nice to have it released...
>>>
>>> Yeah, I'd much prefer to release early, release often. If people
>>> don't feel quite comfortable with the new bundle yet we can officially
>>> call it a pre-release.
>>
>> One of the best ways to get it tested is to get it to go through the
>> full OFED process.
>
> No problem, I'll grab all remaining patches from ML tomorrow and we will
> be ready for first release.
I wouldn't mind a pre-release, but I know for a fact that Jarod is
working on proper distro specific spec file(s), systemd units, etc. So,
I wouldn't call it a release because until we sort out the specifics of
how we want the package to build/look/etc., it might change. It would
be bad from for release 1 to have things packaged one way, and release 2
to totally revamp that. We need to give Jarod time to sort through what
he's working on and post it to the list.
>>
>> Woody, what could we do to help make that happen? Do you know of any
>> blocker?
>>
>> I think this will be the best for everyone. I also predict that OFED
>> will be under pressure to quickly take up the new drivers that will
>> land in 4.9, and their user space will live in rdma-core.
>>
>> I also propose we give someone from the OFED team repo access and they
>> can maintain a public branch for ofed-4.8 with any backported fixes.
>
> First of them, they need to express desire :)
> Let's start from pull request model and see if it is enough/not enough.
>
>>
>> Jason
--
Doug Ledford <dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
GPG Key ID: 0E572FDD
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 884 bytes --]
^ permalink raw reply
* Re: [PATCH 26/28] Avoid gcc 5.4 warning -Wunused-result
From: Doug Ledford @ 2016-10-12 18:07 UTC (permalink / raw)
To: Yishai Hadas, Jason Gunthorpe
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, Devesh Sharma, Hal Rosenstock,
Mike Marciniszyn, Moni Shoua, Sean Hefty, Steve Wise,
Tatyana Nikolova, Vladimir Sokolovsky, Yishai Hadas
In-Reply-To: <1e022827-f28c-e2cd-2b6a-edfb713ed0b5-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
[-- Attachment #1.1: Type: text/plain, Size: 853 bytes --]
On 10/10/2016 6:06 AM, Yishai Hadas wrote:
> On 10/10/2016 2:19 AM, Jason Gunthorpe wrote:
>> On Sun, Oct 09, 2016 at 04:31:17PM +0300, Yishai Hadas wrote:
>>
>>>> - if (write(connfd, msg, sizeof msg) != sizeof msg) {
>>>> - fprintf(stderr, "Couldn't send local address\n");
>>>> + if (write(connfd, msg, sizeof msg) != sizeof msg ||
>>>> + read(connfd, msg, sizeof msg) != sizeof msg) {
>>>> + fprintf(stderr, "Couldn't send/recv local address\n");
>>>
>>> At that step the server expects to read a "done" response from its
>>> client,
>>> checking whether the read was done for sizeof msg which is much
>>> larger will
>>> fail.
>>
>> This OK?
>
> Yes, below patch solves the issue.
Merged, thanks.
--
Doug Ledford <dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
GPG Key ID: 0E572FDD
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 884 bytes --]
^ permalink raw reply
* Re: [PATCH rdma-core 0/5] clang support
From: Doug Ledford @ 2016-10-12 18:07 UTC (permalink / raw)
To: Jason Gunthorpe, linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1475879772-29458-1-git-send-email-jgunthorpe-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
[-- Attachment #1.1: Type: text/plain, Size: 1518 bytes --]
On 10/7/2016 6:36 PM, Jason Gunthorpe wrote:
> This series gets clang running warning free and has travis run the build
> through clang-3.9 so we don't break it again.
>
> Jason Gunthorpe (5):
> Pull uninitialized_var into util/compiler.h
> ibacm: Avoid clang 3.8 warning -Wmissing-field-initializers
> mthca: Avoid bogus gcc 4.8 warning -Wmaybe-uninitialized
> Improve linker flag detection to work with clang and -Werror
> Update TravisCI to use clang 3.9 as well
>
> .travis.yml | 20 +++++++++++++++++---
> CMakeLists.txt | 22 ++++++++++++++--------
> buildlib/FindLDSymVer.cmake | 16 ++++++++++++----
> buildlib/RDMA_EnableCStd.cmake | 25 +++++++++++++++++++++++++
> ibacm/prov/acmp/src/acmp.c | 2 +-
> providers/cxgb4/cq.c | 1 +
> providers/cxgb4/libcxgb4.h | 2 --
> providers/cxgb4/qp.c | 1 +
> providers/mlx4/mlx4.h | 4 ----
> providers/mlx4/qp.c | 1 +
> providers/mlx5/mlx5.h | 4 ----
> providers/mlx5/qp.c | 1 +
> providers/mthca/qp.c | 23 +++++------------------
> util/CMakeLists.txt | 3 +++
> util/compiler.h | 18 ++++++++++++++++++
> 15 files changed, 99 insertions(+), 44 deletions(-)
> create mode 100644 util/CMakeLists.txt
> create mode 100644 util/compiler.h
>
Series merged. Thanks.
--
Doug Ledford <dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
GPG Key ID: 0E572FDD
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 884 bytes --]
^ permalink raw reply
* Re: rdma-core release?
From: Leon Romanovsky @ 2016-10-12 17:37 UTC (permalink / raw)
To: Jason Gunthorpe
Cc: 'Christoph Hellwig', Steve Wise, 'Doug Ledford',
'linux-rdma', robert.j.woodruff-ral2JQCrhuEAvxtiuMwx3w
In-Reply-To: <20161012164759.GB18838-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
[-- Attachment #1: Type: text/plain, Size: 1548 bytes --]
On Wed, Oct 12, 2016 at 10:47:59AM -0600, Jason Gunthorpe wrote:
> On Wed, Oct 12, 2016 at 09:31:49AM -0700, 'Christoph Hellwig' wrote:
> > On Wed, Oct 12, 2016 at 09:43:08AM -0500, Steve Wise wrote:
> > > I recommend we release something for OFED-4.8 to pull in. That
> > > might help flush out the release process earlier rather than
> > > later. Either way, though, I want the latest libcxgb4 in OFED-4.8
> > > to support the new chelsio HW. But we talked about the repo being
> > > "always stable", so I guess the OFA could just pull the code and
> > > use it? Still would be nice to have it released...
> >
> > Yeah, I'd much prefer to release early, release often. If people
> > don't feel quite comfortable with the new bundle yet we can officially
> > call it a pre-release.
>
> One of the best ways to get it tested is to get it to go through the
> full OFED process.
No problem, I'll grab all remaining patches from ML tomorrow and we will
be ready for first release.
>
> Woody, what could we do to help make that happen? Do you know of any
> blocker?
>
> I think this will be the best for everyone. I also predict that OFED
> will be under pressure to quickly take up the new drivers that will
> land in 4.9, and their user space will live in rdma-core.
>
> I also propose we give someone from the OFED team repo access and they
> can maintain a public branch for ofed-4.8 with any backported fixes.
First of them, they need to express desire :)
Let's start from pull request model and see if it is enough/not enough.
>
> Jason
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]
^ permalink raw reply
* Re: [PATCH] add a build.sh helper to allow for a one-stop build
From: Leon Romanovsky @ 2016-10-12 17:31 UTC (permalink / raw)
To: Jason Gunthorpe
Cc: Christoph Hellwig, Bart Van Assche,
linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <20161012163834.GA18838-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
[-- Attachment #1: Type: text/plain, Size: 262 bytes --]
On Wed, Oct 12, 2016 at 10:38:34AM -0600, Jason Gunthorpe wrote:
> On Wed, Oct 12, 2016 at 03:22:20PM +0300, Leon Romanovsky wrote:
>
> > Done, applied.
>
> Are you going to sweep up the rest of the list patches too?
Yes, I'll do it tomorrow.
Thanks
>
> Jason
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]
^ permalink raw reply
* Re: rdma-core release?
From: Jason Gunthorpe @ 2016-10-12 16:47 UTC (permalink / raw)
To: 'Christoph Hellwig'
Cc: Steve Wise, 'Doug Ledford', 'Leon Romanovsky',
'linux-rdma', robert.j.woodruff-ral2JQCrhuEAvxtiuMwx3w
In-Reply-To: <20161012163149.GA20174-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
On Wed, Oct 12, 2016 at 09:31:49AM -0700, 'Christoph Hellwig' wrote:
> On Wed, Oct 12, 2016 at 09:43:08AM -0500, Steve Wise wrote:
> > I recommend we release something for OFED-4.8 to pull in. That
> > might help flush out the release process earlier rather than
> > later. Either way, though, I want the latest libcxgb4 in OFED-4.8
> > to support the new chelsio HW. But we talked about the repo being
> > "always stable", so I guess the OFA could just pull the code and
> > use it? Still would be nice to have it released...
>
> Yeah, I'd much prefer to release early, release often. If people
> don't feel quite comfortable with the new bundle yet we can officially
> call it a pre-release.
One of the best ways to get it tested is to get it to go through the
full OFED process.
Woody, what could we do to help make that happen? Do you know of any
blocker?
I think this will be the best for everyone. I also predict that OFED
will be under pressure to quickly take up the new drivers that will
land in 4.9, and their user space will live in rdma-core.
I also propose we give someone from the OFED team repo access and they
can maintain a public branch for ofed-4.8 with any backported fixes.
Jason
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH] add a build.sh helper to allow for a one-stop build
From: Jason Gunthorpe @ 2016-10-12 16:38 UTC (permalink / raw)
To: Leon Romanovsky
Cc: Christoph Hellwig, Bart Van Assche,
linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <20161012122220.GU9282-2ukJVAZIZ/Y@public.gmane.org>
On Wed, Oct 12, 2016 at 03:22:20PM +0300, Leon Romanovsky wrote:
> Done, applied.
Are you going to sweep up the rest of the list patches too?
Jason
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: rdma-core release?
From: 'Christoph Hellwig' @ 2016-10-12 16:31 UTC (permalink / raw)
To: Steve Wise
Cc: 'Doug Ledford', 'Leon Romanovsky',
'Christoph Hellwig', 'linux-rdma'
In-Reply-To: <00c801d22496$f31798f0$d946cad0$@opengridcomputing.com>
On Wed, Oct 12, 2016 at 09:43:08AM -0500, Steve Wise wrote:
> I recommend we release something for OFED-4.8 to pull in. That might help flush out the release process earlier rather than later. Either way, though, I want the latest libcxgb4 in OFED-4.8 to support the new chelsio HW. But we talked about the repo being "always stable", so I guess the OFA could just pull the code and use it? Still would be nice to have it released...
Yeah, I'd much prefer to release early, release often. If people
don't feel quite comfortable with the new bundle yet we can officially
call it a pre-release.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* RE: rdma-core release?
From: Steve Wise @ 2016-10-12 14:43 UTC (permalink / raw)
To: 'Doug Ledford', 'Leon Romanovsky',
'Christoph Hellwig'
Cc: 'linux-rdma'
In-Reply-To: <59ebde13-0fcd-0640-e750-bb6e57bfb921-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
>
> On 10/12/2016 7:43 AM, Leon Romanovsky wrote:
> > On Wed, Oct 12, 2016 at 1:51 PM, Christoph Hellwig <hch-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org> wrote:
> >> Are we planning on having a rdma-core release now that 4.8 is out
> >> and we want a matching userspace release?
> >
> > As far as I remember, the initial plan was to use this library
> > immediately, but first release was planned to be at the 4.9
> > announcement to ensure that it runs smoothly.
>
> Correct.
>
I recommend we release something for OFED-4.8 to pull in. That might help flush out the release process earlier rather than later. Either way, though, I want the latest libcxgb4 in OFED-4.8 to support the new chelsio HW. But we talked about the repo being "always stable", so I guess the OFA could just pull the code and use it? Still would be nice to have it released...
Steve.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH v2] IB/ipoib: move back IB LL address into the hard header
From: Paolo Abeni @ 2016-10-12 14:30 UTC (permalink / raw)
To: linux-rdma
Cc: Doug Ledford, Sean Hefty, Hal Rosenstock, Jason Gunthorpe, netdev
After the commit 9207f9d45b0a ("net: preserve IP control block
during GSO segmentation"), the GSO CB and the IPoIB CB conflict.
That destroy the IPoIB address information cached there,
causing a severe performance regression, as better described here:
http://marc.info/?l=linux-kernel&m=146787279825501&w=2
This change moves the data cached by the IPoIB driver from the
skb control lock into the IPoIB hard header, as done before
the commit 936d7de3d736 ("IPoIB: Stop lying about hard_header_len
and use skb->cb to stash LL addresses").
In order to avoid GRO issue, on packet reception, the IPoIB driver
stash into the skb a dummy pseudo header, so that the received
packets have actually a hard header matching the declared length.
To avoid changing the connected mode maximum mtu, the allocated
head buffer size is increased by the pseudo header length.
After this commit, IPoIB performances are back to pre-regression
value.
v1 -> v2: avoid changing the max mtu, increasing the head buf size
Fixes: 9207f9d45b0a ("net: preserve IP control block during GSO segmentation")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/infiniband/ulp/ipoib/ipoib.h | 20 +++++++---
drivers/infiniband/ulp/ipoib/ipoib_cm.c | 15 +++----
drivers/infiniband/ulp/ipoib/ipoib_ib.c | 12 +++---
drivers/infiniband/ulp/ipoib/ipoib_main.c | 54 ++++++++++++++++----------
drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 6 ++-
5 files changed, 64 insertions(+), 43 deletions(-)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 9dbfcc0..5ff64af 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -63,6 +63,8 @@ enum ipoib_flush_level {
enum {
IPOIB_ENCAP_LEN = 4,
+ IPOIB_PSEUDO_LEN = 20,
+ IPOIB_HARD_LEN = IPOIB_ENCAP_LEN + IPOIB_PSEUDO_LEN,
IPOIB_UD_HEAD_SIZE = IB_GRH_BYTES + IPOIB_ENCAP_LEN,
IPOIB_UD_RX_SG = 2, /* max buffer needed for 4K mtu */
@@ -134,15 +136,21 @@ struct ipoib_header {
u16 reserved;
};
-struct ipoib_cb {
- struct qdisc_skb_cb qdisc_cb;
- u8 hwaddr[INFINIBAND_ALEN];
+struct ipoib_pseudo_header {
+ u8 hwaddr[INFINIBAND_ALEN];
};
-static inline struct ipoib_cb *ipoib_skb_cb(const struct sk_buff *skb)
+static inline void skb_add_pseudo_hdr(struct sk_buff *skb)
{
- BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct ipoib_cb));
- return (struct ipoib_cb *)skb->cb;
+ char *data = skb_push(skb, IPOIB_PSEUDO_LEN);
+
+ /*
+ * only the ipoib header is present now, make room for a dummy
+ * pseudo header and set skb field accordingly
+ */
+ memset(data, 0, IPOIB_PSEUDO_LEN);
+ skb_reset_mac_header(skb);
+ skb_pull(skb, IPOIB_HARD_LEN);
}
/* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 4ad297d..339a1ee 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -63,6 +63,8 @@ MODULE_PARM_DESC(cm_data_debug_level,
#define IPOIB_CM_RX_DELAY (3 * 256 * HZ)
#define IPOIB_CM_RX_UPDATE_MASK (0x3)
+#define IPOIB_CM_RX_RESERVE (ALIGN(IPOIB_HARD_LEN, 16) - IPOIB_ENCAP_LEN)
+
static struct ib_qp_attr ipoib_cm_err_attr = {
.qp_state = IB_QPS_ERR
};
@@ -146,15 +148,15 @@ static struct sk_buff *ipoib_cm_alloc_rx_skb(struct net_device *dev,
struct sk_buff *skb;
int i;
- skb = dev_alloc_skb(IPOIB_CM_HEAD_SIZE + 12);
+ skb = dev_alloc_skb(ALIGN(IPOIB_CM_HEAD_SIZE + IPOIB_PSEUDO_LEN, 16));
if (unlikely(!skb))
return NULL;
/*
- * IPoIB adds a 4 byte header. So we need 12 more bytes to align the
+ * IPoIB adds a IPOIB_ENCAP_LEN byte header, this will align the
* IP header to a multiple of 16.
*/
- skb_reserve(skb, 12);
+ skb_reserve(skb, IPOIB_CM_RX_RESERVE);
mapping[0] = ib_dma_map_single(priv->ca, skb->data, IPOIB_CM_HEAD_SIZE,
DMA_FROM_DEVICE);
@@ -624,9 +626,9 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
if (wc->byte_len < IPOIB_CM_COPYBREAK) {
int dlen = wc->byte_len;
- small_skb = dev_alloc_skb(dlen + 12);
+ small_skb = dev_alloc_skb(dlen + IPOIB_CM_RX_RESERVE);
if (small_skb) {
- skb_reserve(small_skb, 12);
+ skb_reserve(small_skb, IPOIB_CM_RX_RESERVE);
ib_dma_sync_single_for_cpu(priv->ca, rx_ring[wr_id].mapping[0],
dlen, DMA_FROM_DEVICE);
skb_copy_from_linear_data(skb, small_skb->data, dlen);
@@ -663,8 +665,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
copied:
skb->protocol = ((struct ipoib_header *) skb->data)->proto;
- skb_reset_mac_header(skb);
- skb_pull(skb, IPOIB_ENCAP_LEN);
+ skb_add_pseudo_hdr(skb);
++dev->stats.rx_packets;
dev->stats.rx_bytes += skb->len;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index be11d5d..830fecb 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -128,16 +128,15 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id)
buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);
- skb = dev_alloc_skb(buf_size + IPOIB_ENCAP_LEN);
+ skb = dev_alloc_skb(buf_size + IPOIB_HARD_LEN);
if (unlikely(!skb))
return NULL;
/*
- * IB will leave a 40 byte gap for a GRH and IPoIB adds a 4 byte
- * header. So we need 4 more bytes to get to 48 and align the
- * IP header to a multiple of 16.
+ * the IP header will be at IPOIP_HARD_LEN + IB_GRH_BYTES, that is
+ * 64 bytes aligned
*/
- skb_reserve(skb, 4);
+ skb_reserve(skb, sizeof(struct ipoib_pseudo_header));
mapping = priv->rx_ring[id].mapping;
mapping[0] = ib_dma_map_single(priv->ca, skb->data, buf_size,
@@ -253,8 +252,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
skb_pull(skb, IB_GRH_BYTES);
skb->protocol = ((struct ipoib_header *) skb->data)->proto;
- skb_reset_mac_header(skb);
- skb_pull(skb, IPOIB_ENCAP_LEN);
+ skb_add_pseudo_hdr(skb);
++dev->stats.rx_packets;
dev->stats.rx_bytes += skb->len;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index cc1c1b0..823a528 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -925,9 +925,12 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
ipoib_neigh_free(neigh);
goto err_drop;
}
- if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)
+ if (skb_queue_len(&neigh->queue) <
+ IPOIB_MAX_PATH_REC_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, IPOIB_PSEUDO_LEN);
__skb_queue_tail(&neigh->queue, skb);
- else {
+ } else {
ipoib_warn(priv, "queue length limit %d. Packet drop.\n",
skb_queue_len(&neigh->queue));
goto err_drop;
@@ -964,7 +967,7 @@ err_drop:
}
static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
- struct ipoib_cb *cb)
+ struct ipoib_pseudo_header *phdr)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_path *path;
@@ -972,16 +975,18 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
spin_lock_irqsave(&priv->lock, flags);
- path = __path_find(dev, cb->hwaddr + 4);
+ path = __path_find(dev, phdr->hwaddr + 4);
if (!path || !path->valid) {
int new_path = 0;
if (!path) {
- path = path_rec_create(dev, cb->hwaddr + 4);
+ path = path_rec_create(dev, phdr->hwaddr + 4);
new_path = 1;
}
if (path) {
if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, IPOIB_PSEUDO_LEN);
__skb_queue_tail(&path->queue, skb);
} else {
++dev->stats.tx_dropped;
@@ -1009,10 +1014,12 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
be16_to_cpu(path->pathrec.dlid));
spin_unlock_irqrestore(&priv->lock, flags);
- ipoib_send(dev, skb, path->ah, IPOIB_QPN(cb->hwaddr));
+ ipoib_send(dev, skb, path->ah, IPOIB_QPN(phdr->hwaddr));
return;
} else if ((path->query || !path_rec_start(dev, path)) &&
skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, IPOIB_PSEUDO_LEN);
__skb_queue_tail(&path->queue, skb);
} else {
++dev->stats.tx_dropped;
@@ -1026,13 +1033,15 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_neigh *neigh;
- struct ipoib_cb *cb = ipoib_skb_cb(skb);
+ struct ipoib_pseudo_header *phdr;
struct ipoib_header *header;
unsigned long flags;
+ phdr = (struct ipoib_pseudo_header *) skb->data;
+ skb_pull(skb, sizeof(*phdr));
header = (struct ipoib_header *) skb->data;
- if (unlikely(cb->hwaddr[4] == 0xff)) {
+ if (unlikely(phdr->hwaddr[4] == 0xff)) {
/* multicast, arrange "if" according to probability */
if ((header->proto != htons(ETH_P_IP)) &&
(header->proto != htons(ETH_P_IPV6)) &&
@@ -1045,13 +1054,13 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
}
/* Add in the P_Key for multicast*/
- cb->hwaddr[8] = (priv->pkey >> 8) & 0xff;
- cb->hwaddr[9] = priv->pkey & 0xff;
+ phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff;
+ phdr->hwaddr[9] = priv->pkey & 0xff;
- neigh = ipoib_neigh_get(dev, cb->hwaddr);
+ neigh = ipoib_neigh_get(dev, phdr->hwaddr);
if (likely(neigh))
goto send_using_neigh;
- ipoib_mcast_send(dev, cb->hwaddr, skb);
+ ipoib_mcast_send(dev, phdr->hwaddr, skb);
return NETDEV_TX_OK;
}
@@ -1060,16 +1069,16 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
case htons(ETH_P_IP):
case htons(ETH_P_IPV6):
case htons(ETH_P_TIPC):
- neigh = ipoib_neigh_get(dev, cb->hwaddr);
+ neigh = ipoib_neigh_get(dev, phdr->hwaddr);
if (unlikely(!neigh)) {
- neigh_add_path(skb, cb->hwaddr, dev);
+ neigh_add_path(skb, phdr->hwaddr, dev);
return NETDEV_TX_OK;
}
break;
case htons(ETH_P_ARP):
case htons(ETH_P_RARP):
/* for unicast ARP and RARP should always perform path find */
- unicast_arp_send(skb, dev, cb);
+ unicast_arp_send(skb, dev, phdr);
return NETDEV_TX_OK;
default:
/* ethertype not supported by IPoIB */
@@ -1086,11 +1095,13 @@ send_using_neigh:
goto unref;
}
} else if (neigh->ah) {
- ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(cb->hwaddr));
+ ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(phdr->hwaddr));
goto unref;
}
if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, sizeof(*phdr));
spin_lock_irqsave(&priv->lock, flags);
__skb_queue_tail(&neigh->queue, skb);
spin_unlock_irqrestore(&priv->lock, flags);
@@ -1122,8 +1133,8 @@ static int ipoib_hard_header(struct sk_buff *skb,
unsigned short type,
const void *daddr, const void *saddr, unsigned len)
{
+ struct ipoib_pseudo_header *phdr;
struct ipoib_header *header;
- struct ipoib_cb *cb = ipoib_skb_cb(skb);
header = (struct ipoib_header *) skb_push(skb, sizeof *header);
@@ -1132,12 +1143,13 @@ static int ipoib_hard_header(struct sk_buff *skb,
/*
* we don't rely on dst_entry structure, always stuff the
- * destination address into skb->cb so we can figure out where
+ * destination address into skb hard header so we can figure out where
* to send the packet later.
*/
- memcpy(cb->hwaddr, daddr, INFINIBAND_ALEN);
+ phdr = (struct ipoib_pseudo_header *) skb_push(skb, sizeof(*phdr));
+ memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN);
- return sizeof *header;
+ return IPOIB_HARD_LEN;
}
static void ipoib_set_mcast_list(struct net_device *dev)
@@ -1759,7 +1771,7 @@ void ipoib_setup(struct net_device *dev)
dev->flags |= IFF_BROADCAST | IFF_MULTICAST;
- dev->hard_header_len = IPOIB_ENCAP_LEN;
+ dev->hard_header_len = IPOIB_HARD_LEN;
dev->addr_len = INFINIBAND_ALEN;
dev->type = ARPHRD_INFINIBAND;
dev->tx_queue_len = ipoib_sendq_size * 2;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index d3394b6..1909dd2 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -796,9 +796,11 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb)
__ipoib_mcast_add(dev, mcast);
list_add_tail(&mcast->list, &priv->multicast_list);
}
- if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE)
+ if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, sizeof(struct ipoib_pseudo_header));
skb_queue_tail(&mcast->pkt_queue, skb);
- else {
+ } else {
++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
}
--
1.8.3.1
^ permalink raw reply related
* false checkpatch finding?
From: Marciniszyn, Mike @ 2016-10-12 14:04 UTC (permalink / raw)
To: Andy Whitcroft, Joe Perches
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
<4.8 tree>/scripts/checkpatch.pl -F foo.h
WARNING: Missing a blank line after declarations
#3: FILE: foo.h:3:
+ unsigned long f1;
+ volatile __le64 f2.
WARNING: Use of volatile is usually wrong: see Documentation/volatile-considered-harmful.txt
#3: FILE: foo.h:3:
+ volatile __le64 f2.
total: 0 errors, 2 warnings, 4 lines checked
NOTE: For some of the reported defects, checkpatch may be able to
mechanically convert to the typical style using --fix or --fix-inplace.
foo.h has style problems, please review.
NOTE: If any of the errors are false positives, please report
them to the maintainer, see CHECKPATCH in MAINTAINERS.
Adding a gratuitous blank line after f1 silences the bogus warning.
The volatile warning is ok because this is a hardware written field.
Snip the test file from below.
Mike
<snip foo.h>
struct foo {
unsigned long f1;
volatile __le64 f2.
};
</snip foo.h>
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox