* [PATCH net-next 08/10] IB/mlx4: Add port aggregation support
From: Or Gerlitz @ 2015-02-03 14:48 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Roland Dreier, Amir Vadai, Tal Alon, Moni Shoua,
Or Gerlitz
In-Reply-To: <1422974919-28084-1-git-send-email-ogerlitz@mellanox.com>
From: Moni Shoua <monis@mellanox.com>
Register the interface with the mlx4 core driver with port aggregation support
and check for port aggregation mode when the 'add' function is called.
In this mode, only one physical port is reported to the upper layer
(RoCE/IB core stack and ULPs).
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/infiniband/hw/mlx4/main.c | 76 ++++++++++++++++++++++++++++++++++---
1 files changed, 70 insertions(+), 6 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 9db258f..ed21ae6 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -351,6 +351,7 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port,
enum ib_mtu tmp;
struct mlx4_cmd_mailbox *mailbox;
int err = 0;
+ int is_bonded = mlx4_is_bonded(mdev->dev);
mailbox = mlx4_alloc_cmd_mailbox(mdev->dev);
if (IS_ERR(mailbox))
@@ -374,8 +375,12 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port,
props->state = IB_PORT_DOWN;
props->phys_state = state_to_phys_state(props->state);
props->active_mtu = IB_MTU_256;
+ if (is_bonded)
+ rtnl_lock(); /* required to get upper dev */
spin_lock_bh(&iboe->lock);
ndev = iboe->netdevs[port - 1];
+ if (ndev && is_bonded)
+ ndev = netdev_master_upper_dev_get(ndev);
if (!ndev)
goto out_unlock;
@@ -387,6 +392,8 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port,
props->phys_state = state_to_phys_state(props->state);
out_unlock:
spin_unlock_bh(&iboe->lock);
+ if (is_bonded)
+ rtnl_unlock();
out:
mlx4_free_cmd_mailbox(mdev->dev, mailbox);
return err;
@@ -1440,6 +1447,7 @@ static void update_gids_task(struct work_struct *work)
union ib_gid *gids;
int err;
struct mlx4_dev *dev = gw->dev->dev;
+ int is_bonded = mlx4_is_bonded(dev);
if (!gw->dev->ib_active)
return;
@@ -1459,7 +1467,10 @@ static void update_gids_task(struct work_struct *work)
if (err)
pr_warn("set port command failed\n");
else
- mlx4_ib_dispatch_event(gw->dev, gw->port, IB_EVENT_GID_CHANGE);
+ if ((gw->port == 1) || !is_bonded)
+ mlx4_ib_dispatch_event(gw->dev,
+ is_bonded ? 1 : gw->port,
+ IB_EVENT_GID_CHANGE);
mlx4_free_cmd_mailbox(dev, mailbox);
kfree(gw);
@@ -1875,7 +1886,8 @@ static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev,
* don't want the bond IP based gids in the table since
* flows that select port by gid may get the down port.
*/
- if (port_state == IB_PORT_DOWN) {
+ if (port_state == IB_PORT_DOWN &&
+ !mlx4_is_bonded(ibdev->dev)) {
reset_gid_table(ibdev, port);
mlx4_ib_set_default_gid(ibdev,
curr_netdev,
@@ -2047,6 +2059,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
int err;
struct mlx4_ib_iboe *iboe;
int ib_num_ports = 0;
+ int num_req_counters;
pr_info_once("%s", mlx4_ib_version);
@@ -2086,7 +2099,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
ibdev->ib_dev.node_type = RDMA_NODE_IB_CA;
ibdev->ib_dev.local_dma_lkey = dev->caps.reserved_lkey;
ibdev->num_ports = num_ports;
- ibdev->ib_dev.phys_port_cnt = ibdev->num_ports;
+ ibdev->ib_dev.phys_port_cnt = mlx4_is_bonded(dev) ?
+ 1 : ibdev->num_ports;
ibdev->ib_dev.num_comp_vectors = dev->caps.num_comp_vectors;
ibdev->ib_dev.dma_device = &dev->persist->pdev->dev;
@@ -2207,7 +2221,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
if (init_node_data(ibdev))
goto err_map;
- for (i = 0; i < ibdev->num_ports; ++i) {
+ num_req_counters = mlx4_is_bonded(dev) ? 1 : ibdev->num_ports;
+ for (i = 0; i < num_req_counters; ++i) {
mutex_init(&ibdev->qp1_proxy_lock[i]);
if (mlx4_ib_port_link_layer(&ibdev->ib_dev, i + 1) ==
IB_LINK_LAYER_ETHERNET) {
@@ -2218,6 +2233,10 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
ibdev->counters[i] = -1;
}
}
+ if (mlx4_is_bonded(dev))
+ for (i = 1; i < ibdev->num_ports ; ++i)
+ ibdev->counters[i] = ibdev->counters[0];
+
mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
ib_num_ports++;
@@ -2538,6 +2557,38 @@ out:
return;
}
+static void handle_bonded_port_state_event(struct work_struct *work)
+{
+ struct ib_event_work *ew =
+ container_of(work, struct ib_event_work, work);
+ struct mlx4_ib_dev *ibdev = ew->ib_dev;
+ enum ib_port_state bonded_port_state = IB_PORT_NOP;
+ int i;
+ struct ib_event ibev;
+
+ kfree(ew);
+ spin_lock_bh(&ibdev->iboe.lock);
+ for (i = 0; i < MLX4_MAX_PORTS; ++i) {
+ struct net_device *curr_netdev = ibdev->iboe.netdevs[i];
+
+ enum ib_port_state curr_port_state =
+ (netif_running(curr_netdev) &&
+ netif_carrier_ok(curr_netdev)) ?
+ IB_PORT_ACTIVE : IB_PORT_DOWN;
+
+ bonded_port_state = (bonded_port_state != IB_PORT_ACTIVE) ?
+ curr_port_state : IB_PORT_ACTIVE;
+ }
+ spin_unlock_bh(&ibdev->iboe.lock);
+
+ ibev.device = &ibdev->ib_dev;
+ ibev.element.port_num = 1;
+ ibev.event = (bonded_port_state == IB_PORT_ACTIVE) ?
+ IB_EVENT_PORT_ACTIVE : IB_EVENT_PORT_ERR;
+
+ ib_dispatch_event(&ibev);
+}
+
static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
enum mlx4_dev_event event, unsigned long param)
{
@@ -2547,6 +2598,18 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
struct ib_event_work *ew;
int p = 0;
+ if (mlx4_is_bonded(dev) &&
+ ((event == MLX4_DEV_EVENT_PORT_UP) ||
+ (event == MLX4_DEV_EVENT_PORT_DOWN))) {
+ ew = kmalloc(sizeof(*ew), GFP_ATOMIC);
+ if (!ew)
+ return;
+ INIT_WORK(&ew->work, handle_bonded_port_state_event);
+ ew->ib_dev = ibdev;
+ queue_work(wq, &ew->work);
+ return;
+ }
+
if (event == MLX4_DEV_EVENT_PORT_MGMT_CHANGE)
eqe = (struct mlx4_eqe *)param;
else
@@ -2607,7 +2670,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
}
ibev.device = ibdev_ptr;
- ibev.element.port_num = (u8) p;
+ ibev.element.port_num = mlx4_is_bonded(ibdev->dev) ? 1 : (u8)p;
ib_dispatch_event(&ibev);
}
@@ -2616,7 +2679,8 @@ static struct mlx4_interface mlx4_ib_interface = {
.add = mlx4_ib_add,
.remove = mlx4_ib_remove,
.event = mlx4_ib_event,
- .protocol = MLX4_PROT_IB_IPV6
+ .protocol = MLX4_PROT_IB_IPV6,
+ .flags = MLX4_INTFF_BONDING
};
static int __init mlx4_ib_init(void)
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 05/10] net/mlx4_core: Port aggregation upper layer interface
From: Or Gerlitz @ 2015-02-03 14:48 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Roland Dreier, Amir Vadai, Tal Alon, Moni Shoua,
Or Gerlitz
In-Reply-To: <1422974919-28084-1-git-send-email-ogerlitz@mellanox.com>
From: Moni Shoua <monis@mellanox.com>
Supply interface functions to bond and unbond ports of a mlx4 internal
interfaces. Example for such an interface is the one registered by the
mlx4 IB driver under RoCE.
There are
1. Functions to go in/out to/from bonded mode
2. Function to remap virtual ports to physical ports
The bond_mutex prevents simultaneous access to data that keep status of
the device in bonded mode.
The upper mlx4 interface marks to the mlx4 core module that they
want to be subject for such bonding by setting the MLX4_INTFF_BONDING
flag. Interface which goes to/from bonded mode is re-created.
The mlx4 Ethernet driver does not set this flag when registering the
interface, the IB driver does.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_resources.c | 8 ++-
drivers/net/ethernet/mellanox/mlx4/intf.c | 54 ++++++++++++
drivers/net/ethernet/mellanox/mlx4/main.c | 89 ++++++++++++++++++++
drivers/net/ethernet/mellanox/mlx4/mlx4.h | 3 +
drivers/net/ethernet/mellanox/mlx4/qp.c | 2 +
.../net/ethernet/mellanox/mlx4/resource_tracker.c | 3 +
include/linux/mlx4/device.h | 1 +
include/linux/mlx4/driver.h | 19 ++++
8 files changed, 177 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
index f1a5500..34f2fdf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
@@ -50,10 +50,14 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride,
context->mtu_msgmax = 0xff;
if (!is_tx && !rss)
context->rq_size_stride = ilog2(size) << 3 | (ilog2(stride) - 4);
- if (is_tx)
+ if (is_tx) {
context->sq_size_stride = ilog2(size) << 3 | (ilog2(stride) - 4);
- else
+ if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP)
+ context->params2 |= MLX4_QP_BIT_FPP;
+
+ } else {
context->sq_size_stride = ilog2(TXBB_SIZE) - 4;
+ }
context->usr_page = cpu_to_be32(mdev->priv_uar.index);
context->local_qpn = cpu_to_be32(qpn);
context->pri_path.ackto = 1 & 0x07;
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 68d2bad..6fce587 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -33,11 +33,13 @@
#include <linux/slab.h>
#include <linux/export.h>
+#include <linux/errno.h>
#include "mlx4.h"
struct mlx4_device_context {
struct list_head list;
+ struct list_head bond_list;
struct mlx4_interface *intf;
void *context;
};
@@ -115,6 +117,58 @@ void mlx4_unregister_interface(struct mlx4_interface *intf)
}
EXPORT_SYMBOL_GPL(mlx4_unregister_interface);
+int mlx4_do_bond(struct mlx4_dev *dev, bool enable)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_device_context *dev_ctx = NULL, *temp_dev_ctx;
+ unsigned long flags;
+ int ret;
+ LIST_HEAD(bond_list);
+
+ if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP))
+ return -ENOTSUPP;
+
+ ret = mlx4_disable_rx_port_check(dev, enable);
+ if (ret) {
+ mlx4_err(dev, "Fail to %s rx port check\n",
+ enable ? "enable" : "disable");
+ return ret;
+ }
+ if (enable) {
+ dev->flags |= MLX4_FLAG_BONDED;
+ } else {
+ ret = mlx4_virt2phy_port_map(dev, 1, 2);
+ if (ret) {
+ mlx4_err(dev, "Fail to reset port map\n");
+ return ret;
+ }
+ dev->flags &= ~MLX4_FLAG_BONDED;
+ }
+
+ spin_lock_irqsave(&priv->ctx_lock, flags);
+ list_for_each_entry_safe(dev_ctx, temp_dev_ctx, &priv->ctx_list, list) {
+ if (dev_ctx->intf->flags & MLX4_INTFF_BONDING) {
+ list_add_tail(&dev_ctx->bond_list, &bond_list);
+ list_del(&dev_ctx->list);
+ }
+ }
+ spin_unlock_irqrestore(&priv->ctx_lock, flags);
+
+ list_for_each_entry(dev_ctx, &bond_list, bond_list) {
+ dev_ctx->intf->remove(dev, dev_ctx->context);
+ dev_ctx->context = dev_ctx->intf->add(dev);
+
+ spin_lock_irqsave(&priv->ctx_lock, flags);
+ list_add_tail(&dev_ctx->list, &priv->ctx_list);
+ spin_unlock_irqrestore(&priv->ctx_lock, flags);
+
+ mlx4_dbg(dev, "Inrerface for protocol %d restarted with when bonded mode is %s\n",
+ dev_ctx->intf->protocol, enable ?
+ "enabled" : "disabled");
+ }
+ return 0;
+}
+
void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type,
unsigned long param)
{
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index cc9f484..f3245fe 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1160,6 +1160,91 @@ err_set_port:
return err ? err : count;
}
+int mlx4_bond(struct mlx4_dev *dev)
+{
+ int ret = 0;
+ struct mlx4_priv *priv = mlx4_priv(dev);
+
+ mutex_lock(&priv->bond_mutex);
+
+ if (!mlx4_is_bonded(dev))
+ ret = mlx4_do_bond(dev, true);
+ else
+ ret = 0;
+
+ mutex_unlock(&priv->bond_mutex);
+ if (ret)
+ mlx4_err(dev, "Failed to bond device: %d\n", ret);
+ else
+ mlx4_dbg(dev, "Device is bonded\n");
+ return ret;
+}
+EXPORT_SYMBOL_GPL(mlx4_bond);
+
+int mlx4_unbond(struct mlx4_dev *dev)
+{
+ int ret = 0;
+ struct mlx4_priv *priv = mlx4_priv(dev);
+
+ mutex_lock(&priv->bond_mutex);
+
+ if (mlx4_is_bonded(dev))
+ ret = mlx4_do_bond(dev, false);
+
+ mutex_unlock(&priv->bond_mutex);
+ if (ret)
+ mlx4_err(dev, "Failed to unbond device: %d\n", ret);
+ else
+ mlx4_dbg(dev, "Device is unbonded\n");
+ return ret;
+}
+EXPORT_SYMBOL_GPL(mlx4_unbond);
+
+
+int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p)
+{
+ u8 port1 = v2p->port1;
+ u8 port2 = v2p->port2;
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ int err;
+
+ if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP))
+ return -ENOTSUPP;
+
+ mutex_lock(&priv->bond_mutex);
+
+ /* zero means keep current mapping for this port */
+ if (port1 == 0)
+ port1 = priv->v2p.port1;
+ if (port2 == 0)
+ port2 = priv->v2p.port2;
+
+ if ((port1 < 1) || (port1 > MLX4_MAX_PORTS) ||
+ (port2 < 1) || (port2 > MLX4_MAX_PORTS) ||
+ (port1 == 2 && port2 == 1)) {
+ /* besides boundary checks cross mapping makes
+ * no sense and therefore not allowed */
+ err = -EINVAL;
+ } else if ((port1 == priv->v2p.port1) &&
+ (port2 == priv->v2p.port2)) {
+ err = 0;
+ } else {
+ err = mlx4_virt2phy_port_map(dev, port1, port2);
+ if (!err) {
+ mlx4_dbg(dev, "port map changed: [%d][%d]\n",
+ port1, port2);
+ priv->v2p.port1 = port1;
+ priv->v2p.port2 = port2;
+ } else {
+ mlx4_err(dev, "Failed to change port mape: %d\n", err);
+ }
+ }
+
+ mutex_unlock(&priv->bond_mutex);
+ return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_port_map_set);
+
static int mlx4_load_fw(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
@@ -2638,6 +2723,7 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
spin_lock_init(&priv->ctx_lock);
mutex_init(&priv->port_mutex);
+ mutex_init(&priv->bond_mutex);
INIT_LIST_HEAD(&priv->pgdir_list);
mutex_init(&priv->pgdir_mutex);
@@ -2934,6 +3020,9 @@ slave_start:
goto err_port;
}
+ priv->v2p.port1 = 1;
+ priv->v2p.port2 = 2;
+
err = mlx4_register_device(dev);
if (err)
goto err_port;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 148dc09..803f176 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -885,6 +885,8 @@ struct mlx4_priv {
int reserved_mtts;
int fs_hash_mode;
u8 virt2phys_pkey[MLX4_MFUNC_MAX][MLX4_MAX_PORTS][MLX4_MAX_PORT_PKEYS];
+ struct mlx4_port_map v2p; /* cached port mapping configuration */
+ struct mutex bond_mutex; /* for bond mode */
__be64 slave_node_guids[MLX4_MFUNC_MAX];
atomic_t opreq_count;
@@ -1364,6 +1366,7 @@ int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave, int port);
/* Returns the VF index of slave */
int mlx4_get_vf_indx(struct mlx4_dev *dev, int slave);
int mlx4_config_mad_demux(struct mlx4_dev *dev);
+int mlx4_do_bond(struct mlx4_dev *dev, bool enable);
enum mlx4_zone_flags {
MLX4_ZONE_ALLOW_ALLOC_FROM_LOWER_PRIO = 1UL << 0,
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 1586ecc..2bb8553 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -882,6 +882,8 @@ int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
for (i = 0; i < ARRAY_SIZE(states) - 1; i++) {
context->flags &= cpu_to_be32(~(0xf << 28));
context->flags |= cpu_to_be32(states[i + 1] << 28);
+ if (states[i + 1] != MLX4_QP_STATE_RTR)
+ context->params2 &= ~MLX4_QP_BIT_FPP;
err = mlx4_qp_modify(dev, mtt, states[i], states[i + 1],
context, 0, 0, qp);
if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 79feeb6..c5f3dfc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2944,6 +2944,9 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
qp_type = (be32_to_cpu(qp_ctx->flags) >> 16) & 0xff;
optpar = be32_to_cpu(*(__be32 *) inbox->buf);
+ if (slave != mlx4_master_func_num(dev))
+ qp_ctx->params2 &= ~MLX4_QP_BIT_FPP;
+
switch (qp_type) {
case MLX4_QP_ST_RC:
case MLX4_QP_ST_XRC:
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index d9afd99..977b0b1 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -70,6 +70,7 @@ enum {
MLX4_FLAG_SLAVE = 1 << 3,
MLX4_FLAG_SRIOV = 1 << 4,
MLX4_FLAG_OLD_REG_MAC = 1 << 6,
+ MLX4_FLAG_BONDED = 1 << 7
};
enum {
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index 022055c..9553a73 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -49,6 +49,10 @@ enum mlx4_dev_event {
MLX4_DEV_EVENT_SLAVE_SHUTDOWN,
};
+enum {
+ MLX4_INTFF_BONDING = 1 << 0
+};
+
struct mlx4_interface {
void * (*add) (struct mlx4_dev *dev);
void (*remove)(struct mlx4_dev *dev, void *context);
@@ -57,11 +61,26 @@ struct mlx4_interface {
void * (*get_dev)(struct mlx4_dev *dev, void *context, u8 port);
struct list_head list;
enum mlx4_protocol protocol;
+ int flags;
};
int mlx4_register_interface(struct mlx4_interface *intf);
void mlx4_unregister_interface(struct mlx4_interface *intf);
+int mlx4_bond(struct mlx4_dev *dev);
+int mlx4_unbond(struct mlx4_dev *dev);
+static inline int mlx4_is_bonded(struct mlx4_dev *dev)
+{
+ return !!(dev->flags & MLX4_FLAG_BONDED);
+}
+
+struct mlx4_port_map {
+ u8 port1;
+ u8 port2;
+};
+
+int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p);
+
void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port);
static inline u64 mlx4_mac_to_u64(u8 *addr)
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 07/10] IB/mlx4: Reuse mlx4_mac_to_u64()
From: Or Gerlitz @ 2015-02-03 14:48 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Roland Dreier, Amir Vadai, Tal Alon, Moni Shoua,
Or Gerlitz
In-Reply-To: <1422974919-28084-1-git-send-email-ogerlitz@mellanox.com>
From: Moni Shoua <monis@mellanox.com>
This function is implemented twice... get rid of one copy.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/infiniband/hw/mlx4/qp.c | 12 +-----------
1 files changed, 1 insertions(+), 11 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index cf000b7..2f85fc7 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -40,6 +40,7 @@
#include <rdma/ib_addr.h>
#include <rdma/ib_mad.h>
+#include <linux/mlx4/driver.h>
#include <linux/mlx4/qp.h>
#include "mlx4_ib.h"
@@ -93,17 +94,6 @@ enum {
#ifndef ETH_ALEN
#define ETH_ALEN 6
#endif
-static inline u64 mlx4_mac_to_u64(u8 *addr)
-{
- u64 mac = 0;
- int i;
-
- for (i = 0; i < ETH_ALEN; i++) {
- mac <<= 8;
- mac |= addr[i];
- }
- return mac;
-}
static const __be32 mlx4_ib_opcode[] = {
[IB_WR_SEND] = cpu_to_be32(MLX4_OPCODE_SEND),
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 06/10] net/mlx4_en: Port aggregation configuration
From: Or Gerlitz @ 2015-02-03 14:48 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Roland Dreier, Amir Vadai, Tal Alon, Moni Shoua,
Or Gerlitz
In-Reply-To: <1422974919-28084-1-git-send-email-ogerlitz@mellanox.com>
From: Moni Shoua <monis@mellanox.com>
Capture NETDEV events generated by the bonding driver and based on that
make decisions of how to configure port aggregation in the mlx4 core driver.
This includes setting the V2P port table and re-creating the interested
interfaces in bonded/non-bonded mode.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_main.c | 8 +
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 176 ++++++++++++++++++++++++
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 5 +
3 files changed, 189 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index c643d2b..58d5a07 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -214,6 +214,8 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr)
iounmap(mdev->uar_map);
mlx4_uar_free(dev, &mdev->priv_uar);
mlx4_pd_free(dev, mdev->priv_pdn);
+ if (mdev->nb.notifier_call)
+ unregister_netdevice_notifier(&mdev->nb);
kfree(mdev);
}
@@ -298,6 +300,12 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
if (mlx4_en_init_netdev(mdev, i, &mdev->profile.prof[i]))
mdev->pndev[i] = NULL;
}
+ /* register notifier */
+ mdev->nb.notifier_call = mlx4_en_netdev_event;
+ if (register_netdevice_notifier(&mdev->nb)) {
+ mdev->nb.notifier_call = NULL;
+ mlx4_err(mdev, "Failed to create notifier\n");
+ }
return mdev;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index e075ff1..028937b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2062,6 +2062,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
/* Detach the netdev so tasks would not attempt to access it */
mutex_lock(&mdev->state_lock);
mdev->pndev[priv->port] = NULL;
+ mdev->upper[priv->port] = NULL;
mutex_unlock(&mdev->state_lock);
mlx4_en_free_resources(priv);
@@ -2441,6 +2442,180 @@ static const struct net_device_ops mlx4_netdev_ops_master = {
#endif
};
+struct mlx4_en_bond {
+ struct work_struct work;
+ struct mlx4_en_priv *priv;
+ int is_bonded;
+ struct mlx4_port_map port_map;
+};
+
+static void mlx4_en_bond_work(struct work_struct *work)
+{
+ struct mlx4_en_bond *bond = container_of(work,
+ struct mlx4_en_bond,
+ work);
+ int err = 0;
+ struct mlx4_dev *dev = bond->priv->mdev->dev;
+
+ if (bond->is_bonded) {
+ if (!mlx4_is_bonded(dev)) {
+ err = mlx4_bond(dev);
+ if (err)
+ en_err(bond->priv, "Fail to bond device\n");
+ }
+ if (!err) {
+ err = mlx4_port_map_set(dev, &bond->port_map);
+ if (err)
+ en_err(bond->priv, "Fail to set port map [%d][%d]: %d\n",
+ bond->port_map.port1,
+ bond->port_map.port2,
+ err);
+ }
+ } else if (mlx4_is_bonded(dev)) {
+ err = mlx4_unbond(dev);
+ if (err)
+ en_err(bond->priv, "Fail to unbond device\n");
+ }
+ dev_put(bond->priv->dev);
+ kfree(bond);
+}
+
+static int mlx4_en_queue_bond_work(struct mlx4_en_priv *priv, int is_bonded,
+ u8 v2p_p1, u8 v2p_p2)
+{
+ struct mlx4_en_bond *bond = NULL;
+
+ bond = kzalloc(sizeof(*bond), GFP_ATOMIC);
+ if (!bond)
+ return -ENOMEM;
+
+ INIT_WORK(&bond->work, mlx4_en_bond_work);
+ bond->priv = priv;
+ bond->is_bonded = is_bonded;
+ bond->port_map.port1 = v2p_p1;
+ bond->port_map.port2 = v2p_p2;
+ dev_hold(priv->dev);
+ queue_work(priv->mdev->workqueue, &bond->work);
+ return 0;
+}
+
+int mlx4_en_netdev_event(struct notifier_block *this,
+ unsigned long event, void *ptr)
+{
+ struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
+ u8 port = 0;
+ struct mlx4_en_dev *mdev;
+ struct mlx4_dev *dev;
+ int i, num_eth_ports = 0;
+ bool do_bond = true;
+ struct mlx4_en_priv *priv;
+ u8 v2p_port1 = 0;
+ u8 v2p_port2 = 0;
+
+ if (!net_eq(dev_net(ndev), &init_net))
+ return NOTIFY_DONE;
+
+ mdev = container_of(this, struct mlx4_en_dev, nb);
+ dev = mdev->dev;
+
+ /* Go into this mode only when two network devices set on two ports
+ * of the same mlx4 device are slaves of the same bonding master
+ */
+ mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) {
+ ++num_eth_ports;
+ if (!port && (mdev->pndev[i] == ndev))
+ port = i;
+ mdev->upper[i] = mdev->pndev[i] ?
+ netdev_master_upper_dev_get(mdev->pndev[i]) : NULL;
+ /* condition not met: network device is a slave */
+ if (!mdev->upper[i])
+ do_bond = false;
+ if (num_eth_ports < 2)
+ continue;
+ /* condition not met: same master */
+ if (mdev->upper[i] != mdev->upper[i-1])
+ do_bond = false;
+ }
+ /* condition not met: 2 salves */
+ do_bond = (num_eth_ports == 2) ? do_bond : false;
+
+ /* handle only events that come with enough info */
+ if ((do_bond && (event != NETDEV_BONDING_INFO)) || !port)
+ return NOTIFY_DONE;
+
+ priv = netdev_priv(ndev);
+ if (do_bond) {
+ struct netdev_notifier_bonding_info *notifier_info = ptr;
+ struct netdev_bonding_info *bonding_info =
+ ¬ifier_info->bonding_info;
+
+ /* required mode 1, 2 or 4 */
+ if ((bonding_info->master.bond_mode != BOND_MODE_ACTIVEBACKUP) &&
+ (bonding_info->master.bond_mode != BOND_MODE_XOR) &&
+ (bonding_info->master.bond_mode != BOND_MODE_8023AD))
+ do_bond = false;
+
+ /* require exactly 2 slaves */
+ if (bonding_info->master.num_slaves != 2)
+ do_bond = false;
+
+ /* calc v2p */
+ if (do_bond) {
+ if (bonding_info->master.bond_mode ==
+ BOND_MODE_ACTIVEBACKUP) {
+ /* in active-backup mode virtual ports are
+ * mapped to the physical port of the active
+ * slave */
+ if (bonding_info->slave.state ==
+ BOND_STATE_BACKUP) {
+ if (port == 1) {
+ v2p_port1 = 2;
+ v2p_port2 = 2;
+ } else {
+ v2p_port1 = 1;
+ v2p_port2 = 1;
+ }
+ } else { /* BOND_STATE_ACTIVE */
+ if (port == 1) {
+ v2p_port1 = 1;
+ v2p_port2 = 1;
+ } else {
+ v2p_port1 = 2;
+ v2p_port2 = 2;
+ }
+ }
+ } else { /* Active-Active */
+ /* in active-active mode a virtual port is
+ * mapped to the native physical port if and only
+ * if the physical port is up */
+ __s8 link = bonding_info->slave.link;
+
+ if (port == 1)
+ v2p_port2 = 2;
+ else
+ v2p_port1 = 1;
+ if ((link == BOND_LINK_UP) ||
+ (link == BOND_LINK_FAIL)) {
+ if (port == 1)
+ v2p_port1 = 1;
+ else
+ v2p_port2 = 2;
+ } else { /* BOND_LINK_DOWN || BOND_LINK_BACK */
+ if (port == 1)
+ v2p_port1 = 2;
+ else
+ v2p_port2 = 1;
+ }
+ }
+ }
+ }
+
+ mlx4_en_queue_bond_work(priv, do_bond,
+ v2p_port1, v2p_port2);
+
+ return NOTIFY_DONE;
+}
+
int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
struct mlx4_en_port_profile *prof)
{
@@ -2623,6 +2798,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
}
mdev->pndev[port] = dev;
+ mdev->upper[port] = NULL;
netif_carrier_off(dev);
mlx4_en_set_default_moderation(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 944a112..2a8268e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -390,6 +390,7 @@ struct mlx4_en_dev {
struct pci_dev *pdev;
struct mutex state_lock;
struct net_device *pndev[MLX4_MAX_PORTS + 1];
+ struct net_device *upper[MLX4_MAX_PORTS + 1];
u32 port_cnt;
bool device_up;
struct mlx4_en_profile profile;
@@ -410,6 +411,7 @@ struct mlx4_en_dev {
unsigned long overflow_period;
struct ptp_clock *ptp_clock;
struct ptp_clock_info ptp_clock_info;
+ struct notifier_block nb;
};
@@ -845,6 +847,9 @@ int mlx4_en_reset_config(struct net_device *dev,
struct hwtstamp_config ts_config,
netdev_features_t new_features);
+int mlx4_en_netdev_event(struct notifier_block *this,
+ unsigned long event, void *ptr);
+
/*
* Functions for time stamping
*/
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 04/10] net/mlx4_core: Port aggregation low level interface
From: Or Gerlitz @ 2015-02-03 14:48 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Roland Dreier, Amir Vadai, Tal Alon, Moni Shoua,
Or Gerlitz
In-Reply-To: <1422974919-28084-1-git-send-email-ogerlitz@mellanox.com>
From: Moni Shoua <monis@mellanox.com>
Implement the hardware interface required for port aggregation.
1. Disable RX port check on receive - don't perform a validity check
that matches to QP's port and the port where the packet is received.
2. Virtual to physical port remap - configure virtual to physical port
mapping. Port remap capability for virtual functions.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/cmd.c | 9 +++++
drivers/net/ethernet/mellanox/mlx4/fw.c | 56 +++++++++++++++++++++++++++---
include/linux/mlx4/cmd.h | 7 ++++
include/linux/mlx4/device.h | 10 +++++-
include/linux/mlx4/qp.h | 1 +
5 files changed, 77 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 154effb..a681d7c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -1583,6 +1583,15 @@ static struct mlx4_cmd_info cmd_info[] = {
.verify = NULL,
.wrapper = mlx4_CMD_EPERM_wrapper
},
+ {
+ .opcode = MLX4_CMD_VIRT_PORT_MAP,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_CMD_EPERM_wrapper
+ },
};
static int mlx4_master_process_vhcr(struct mlx4_dev *dev, int slave,
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index dbabfae..4b08a39 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -142,7 +142,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
[17] = "Asymmetric EQs support",
[18] = "More than 80 VFs support",
[19] = "Performance optimized for limited rule configuration flow steering support",
- [20] = "Recoverable error events support"
+ [20] = "Recoverable error events support",
+ [21] = "Port Remap support"
};
int i;
@@ -863,6 +864,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_EQE_STRIDE;
MLX4_GET(dev_cap->bmme_flags, outbox,
QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
+ if (dev_cap->bmme_flags & MLX4_FLAG_PORT_REMAP)
+ dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_PORT_REMAP;
MLX4_GET(field, outbox, QUERY_DEV_CAP_CONFIG_DEV_OFFSET);
if (field & 0x20)
dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_CONFIG_DEV;
@@ -1120,9 +1123,10 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave,
field &= 0x7f;
MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_BF_OFFSET);
- /* For guests, disable mw type 2 */
+ /* For guests, disable mw type 2 and port remap*/
MLX4_GET(bmme_flags, outbox->buf, QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
bmme_flags &= ~MLX4_BMME_FLAG_TYPE_2_WIN;
+ bmme_flags &= ~MLX4_FLAG_PORT_REMAP;
MLX4_PUT(outbox->buf, bmme_flags, QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
/* turn off device-managed steering capability if not enabled */
@@ -2100,13 +2104,16 @@ struct mlx4_config_dev {
__be32 rsvd1[3];
__be16 vxlan_udp_dport;
__be16 rsvd2;
- __be32 rsvd3[27];
- __be16 rsvd4;
- u8 rsvd5;
+ __be32 rsvd3;
+ __be32 roce_flags;
+ __be32 rsvd4[25];
+ __be16 rsvd5;
+ u8 rsvd6;
u8 rx_checksum_val;
};
#define MLX4_VXLAN_UDP_DPORT (1 << 0)
+#define MLX4_DISABLE_RX_PORT BIT(18)
static int mlx4_CONFIG_DEV_set(struct mlx4_dev *dev, struct mlx4_config_dev *config_dev)
{
@@ -2209,6 +2216,45 @@ int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port)
}
EXPORT_SYMBOL_GPL(mlx4_config_vxlan_port);
+#define CONFIG_DISABLE_RX_PORT BIT(15)
+int mlx4_disable_rx_port_check(struct mlx4_dev *dev, bool dis)
+{
+ struct mlx4_config_dev config_dev;
+
+ memset(&config_dev, 0, sizeof(config_dev));
+ config_dev.update_flags = cpu_to_be32(MLX4_DISABLE_RX_PORT);
+ if (dis)
+ config_dev.roce_flags =
+ cpu_to_be32(CONFIG_DISABLE_RX_PORT);
+
+ return mlx4_CONFIG_DEV_set(dev, &config_dev);
+}
+
+int mlx4_virt2phy_port_map(struct mlx4_dev *dev, u32 port1, u32 port2)
+{
+ struct mlx4_cmd_mailbox *mailbox;
+ struct {
+ __be32 v_port1;
+ __be32 v_port2;
+ } *v2p;
+ int err;
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return -ENOMEM;
+
+ v2p = mailbox->buf;
+ v2p->v_port1 = cpu_to_be32(port1);
+ v2p->v_port2 = cpu_to_be32(port2);
+
+ err = mlx4_cmd(dev, mailbox->dma, 0,
+ MLX4_SET_PORT_VIRT2PHY, MLX4_CMD_VIRT_PORT_MAP,
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
+
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ return err;
+}
+
int mlx4_SET_ICM_SIZE(struct mlx4_dev *dev, u64 icm_size, u64 *aux_pages)
{
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index ae95adc..7b6d4e9 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -71,6 +71,7 @@ enum {
/*master notify fw on finish for slave's flr*/
MLX4_CMD_INFORM_FLR_DONE = 0x5b,
+ MLX4_CMD_VIRT_PORT_MAP = 0x5c,
MLX4_CMD_GET_OP_REQ = 0x59,
/* TPT commands */
@@ -171,6 +172,12 @@ enum {
};
enum {
+ /* virtual to physical port mapping opcode modifiers */
+ MLX4_GET_PORT_VIRT2PHY = 0x0,
+ MLX4_SET_PORT_VIRT2PHY = 0x1,
+};
+
+enum {
MLX4_MAILBOX_SIZE = 4096,
MLX4_ACCESS_MEM_ALIGN = 256,
};
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index c95d659..d9afd99 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -201,7 +201,8 @@ enum {
MLX4_DEV_CAP_FLAG2_SYS_EQS = 1LL << 17,
MLX4_DEV_CAP_FLAG2_80_VFS = 1LL << 18,
MLX4_DEV_CAP_FLAG2_FS_A0 = 1LL << 19,
- MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT = 1LL << 20
+ MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT = 1LL << 20,
+ MLX4_DEV_CAP_FLAG2_PORT_REMAP = 1LL << 21
};
enum {
@@ -253,9 +254,14 @@ enum {
MLX4_BMME_FLAG_TYPE_2_WIN = 1 << 9,
MLX4_BMME_FLAG_RESERVED_LKEY = 1 << 10,
MLX4_BMME_FLAG_FAST_REG_WR = 1 << 11,
+ MLX4_BMME_FLAG_PORT_REMAP = 1 << 24,
MLX4_BMME_FLAG_VSD_INIT2RTR = 1 << 28,
};
+enum {
+ MLX4_FLAG_PORT_REMAP = MLX4_BMME_FLAG_PORT_REMAP
+};
+
enum mlx4_event {
MLX4_EVENT_TYPE_COMP = 0x00,
MLX4_EVENT_TYPE_PATH_MIG = 0x01,
@@ -1378,6 +1384,8 @@ int mlx4_phys_to_slave_port(struct mlx4_dev *dev, int slave, int port);
int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave, int port);
int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port);
+int mlx4_disable_rx_port_check(struct mlx4_dev *dev, bool dis);
+int mlx4_virt2phy_port_map(struct mlx4_dev *dev, u32 port1, u32 port2);
int mlx4_vf_smi_enabled(struct mlx4_dev *dev, int slave, int port);
int mlx4_vf_get_enable_smi_admin(struct mlx4_dev *dev, int slave, int port);
int mlx4_vf_set_enable_smi_admin(struct mlx4_dev *dev, int slave, int port,
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 467ccdf..2bbc62a 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -96,6 +96,7 @@ enum {
MLX4_QP_BIT_RRE = 1 << 15,
MLX4_QP_BIT_RWE = 1 << 14,
MLX4_QP_BIT_RAE = 1 << 13,
+ MLX4_QP_BIT_FPP = 1 << 3,
MLX4_QP_BIT_RIC = 1 << 4,
};
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 03/10] net/bonding: Notify state change on slaves
From: Or Gerlitz @ 2015-02-03 14:48 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Roland Dreier, Amir Vadai, Tal Alon, Moni Shoua,
Or Gerlitz
In-Reply-To: <1422974919-28084-1-git-send-email-ogerlitz@mellanox.com>
From: Moni Shoua <monis@mellanox.com>
Use notifier chain to dispatch an event upon a change in slave state.
Event is dispatched with slave specific info.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/bonding/bond_main.c | 42 +++++++++++++++++++++++++++++++++++++++
include/net/bonding.h | 12 +++++++++++
2 files changed, 54 insertions(+), 0 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 0665608..c9771f3 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1191,6 +1191,47 @@ static void bond_fill_ifslave(struct slave *slave, struct ifslave *info)
info->link_failure_count = slave->link_failure_count;
}
+static void bond_netdev_notify(struct slave *slave, struct net_device *dev)
+{
+ struct bonding *bond = slave->bond;
+ struct netdev_bonding_info bonding_info;
+
+ rtnl_lock();
+ /* make sure that slave is still valid */
+ if (dev->priv_flags & IFF_BONDING) {
+ bond_fill_ifslave(slave, &bonding_info.slave);
+ bond_fill_ifbond(bond, &bonding_info.master);
+ netdev_bonding_info_change(slave->dev, &bonding_info);
+ }
+ rtnl_unlock();
+}
+
+static void bond_netdev_notify_work(struct work_struct *_work)
+{
+ struct netdev_notify_work *w =
+ container_of(_work, struct netdev_notify_work, work.work);
+
+ bond_netdev_notify(w->slave, w->dev);
+ dev_put(w->dev);
+}
+
+void bond_queue_slave_event(struct slave *slave)
+{
+ struct netdev_notify_work *nnw = kzalloc(sizeof(*nnw), GFP_ATOMIC);
+
+ if (!nnw)
+ return;
+
+ INIT_DELAYED_WORK(&nnw->work, bond_netdev_notify_work);
+ nnw->slave = slave;
+ nnw->dev = slave->dev;
+
+ if (queue_delayed_work(slave->bond->wq, &nnw->work, 0))
+ dev_hold(slave->dev);
+ else
+ kfree(nnw);
+}
+
/* enslave device <slave> to bond device <master> */
int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
{
@@ -1585,6 +1626,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
new_slave->link != BOND_LINK_DOWN ? "an up" : "a down");
/* enslave is successful */
+ bond_queue_slave_event(new_slave);
return 0;
/* Undo stages on error */
diff --git a/include/net/bonding.h b/include/net/bonding.h
index d1367ec..4e17095 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -150,6 +150,12 @@ struct bond_parm_tbl {
int mode;
};
+struct netdev_notify_work {
+ struct delayed_work work;
+ struct slave *slave;
+ struct net_device *dev;
+};
+
struct slave {
struct net_device *dev; /* first - useful for panic debug */
struct bonding *bond; /* our master */
@@ -243,6 +249,8 @@ struct bonding {
#define bond_slave_get_rtnl(dev) \
((struct slave *) rtnl_dereference(dev->rx_handler_data))
+void bond_queue_slave_event(struct slave *slave);
+
struct bond_vlan_tag {
__be16 vlan_proto;
unsigned short vlan_id;
@@ -315,6 +323,7 @@ static inline void bond_set_active_slave(struct slave *slave)
{
if (slave->backup) {
slave->backup = 0;
+ bond_queue_slave_event(slave);
rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
}
}
@@ -323,6 +332,7 @@ static inline void bond_set_backup_slave(struct slave *slave)
{
if (!slave->backup) {
slave->backup = 1;
+ bond_queue_slave_event(slave);
rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
}
}
@@ -336,6 +346,7 @@ static inline void bond_set_slave_state(struct slave *slave,
slave->backup = slave_state;
if (notify) {
rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
+ bond_queue_slave_event(slave);
slave->should_notify = 0;
} else {
if (slave->should_notify)
@@ -493,6 +504,7 @@ static inline bool bond_is_slave_inactive(struct slave *slave)
static inline void bond_set_slave_link_state(struct slave *slave, int state)
{
slave->link = state;
+ bond_queue_slave_event(slave);
}
static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local)
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 02/10] net/bonding: Move slave state changes to a helper function
From: Or Gerlitz @ 2015-02-03 14:48 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Roland Dreier, Amir Vadai, Tal Alon, Moni Shoua,
Or Gerlitz
In-Reply-To: <1422974919-28084-1-git-send-email-ogerlitz@mellanox.com>
From: Moni Shoua <monis@mellanox.com>
Move slave state changes to a helper function, this is a pre-step for adding
functionality of dispatching an event when this helper is called.
This commit doesn't add new functionality.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/bonding/bond_main.c | 64 +++++++++++++++++++++++----------------
include/net/bonding.h | 5 +++
2 files changed, 43 insertions(+), 26 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index e229a86..0665608 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -789,7 +789,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
}
new_active->delay = 0;
- new_active->link = BOND_LINK_UP;
+ bond_set_slave_link_state(new_active, BOND_LINK_UP);
if (BOND_MODE(bond) == BOND_MODE_8023AD)
bond_3ad_handle_link_change(new_active, BOND_LINK_UP);
@@ -1176,6 +1176,21 @@ static void bond_free_slave(struct slave *slave)
kfree(slave);
}
+static void bond_fill_ifbond(struct bonding *bond, struct ifbond *info)
+{
+ info->bond_mode = BOND_MODE(bond);
+ info->miimon = bond->params.miimon;
+ info->num_slaves = bond->slave_cnt;
+}
+
+static void bond_fill_ifslave(struct slave *slave, struct ifslave *info)
+{
+ strcpy(info->slave_name, slave->dev->name);
+ info->link = slave->link;
+ info->state = bond_slave_state(slave);
+ info->link_failure_count = slave->link_failure_count;
+}
+
/* enslave device <slave> to bond device <master> */
int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
{
@@ -1439,19 +1454,22 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
if (bond->params.miimon) {
if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) {
if (bond->params.updelay) {
- new_slave->link = BOND_LINK_BACK;
+ bond_set_slave_link_state(new_slave,
+ BOND_LINK_BACK);
new_slave->delay = bond->params.updelay;
} else {
- new_slave->link = BOND_LINK_UP;
+ bond_set_slave_link_state(new_slave,
+ BOND_LINK_UP);
}
} else {
- new_slave->link = BOND_LINK_DOWN;
+ bond_set_slave_link_state(new_slave, BOND_LINK_DOWN);
}
} else if (bond->params.arp_interval) {
- new_slave->link = (netif_carrier_ok(slave_dev) ?
- BOND_LINK_UP : BOND_LINK_DOWN);
+ bond_set_slave_link_state(new_slave,
+ (netif_carrier_ok(slave_dev) ?
+ BOND_LINK_UP : BOND_LINK_DOWN));
} else {
- new_slave->link = BOND_LINK_UP;
+ bond_set_slave_link_state(new_slave, BOND_LINK_UP);
}
if (new_slave->link != BOND_LINK_DOWN)
@@ -1816,11 +1834,7 @@ static int bond_release_and_destroy(struct net_device *bond_dev,
static int bond_info_query(struct net_device *bond_dev, struct ifbond *info)
{
struct bonding *bond = netdev_priv(bond_dev);
-
- info->bond_mode = BOND_MODE(bond);
- info->miimon = bond->params.miimon;
- info->num_slaves = bond->slave_cnt;
-
+ bond_fill_ifbond(bond, info);
return 0;
}
@@ -1834,10 +1848,7 @@ static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *in
bond_for_each_slave(bond, slave, iter) {
if (i++ == (int)info->slave_id) {
res = 0;
- strcpy(info->slave_name, slave->dev->name);
- info->link = slave->link;
- info->state = bond_slave_state(slave);
- info->link_failure_count = slave->link_failure_count;
+ bond_fill_ifslave(slave, info);
break;
}
}
@@ -1867,7 +1878,7 @@ static int bond_miimon_inspect(struct bonding *bond)
if (link_state)
continue;
- slave->link = BOND_LINK_FAIL;
+ bond_set_slave_link_state(slave, BOND_LINK_FAIL);
slave->delay = bond->params.downdelay;
if (slave->delay) {
netdev_info(bond->dev, "link status down for %sinterface %s, disabling it in %d ms\n",
@@ -1882,7 +1893,7 @@ static int bond_miimon_inspect(struct bonding *bond)
case BOND_LINK_FAIL:
if (link_state) {
/* recovered before downdelay expired */
- slave->link = BOND_LINK_UP;
+ bond_set_slave_link_state(slave, BOND_LINK_UP);
slave->last_link_up = jiffies;
netdev_info(bond->dev, "link status up again after %d ms for interface %s\n",
(bond->params.downdelay - slave->delay) *
@@ -1904,7 +1915,7 @@ static int bond_miimon_inspect(struct bonding *bond)
if (!link_state)
continue;
- slave->link = BOND_LINK_BACK;
+ bond_set_slave_link_state(slave, BOND_LINK_BACK);
slave->delay = bond->params.updelay;
if (slave->delay) {
@@ -1917,7 +1928,8 @@ static int bond_miimon_inspect(struct bonding *bond)
/*FALLTHRU*/
case BOND_LINK_BACK:
if (!link_state) {
- slave->link = BOND_LINK_DOWN;
+ bond_set_slave_link_state(slave,
+ BOND_LINK_DOWN);
netdev_info(bond->dev, "link status down again after %d ms for interface %s\n",
(bond->params.updelay - slave->delay) *
bond->params.miimon,
@@ -1955,7 +1967,7 @@ static void bond_miimon_commit(struct bonding *bond)
continue;
case BOND_LINK_UP:
- slave->link = BOND_LINK_UP;
+ bond_set_slave_link_state(slave, BOND_LINK_UP);
slave->last_link_up = jiffies;
primary = rtnl_dereference(bond->primary_slave);
@@ -1995,7 +2007,7 @@ static void bond_miimon_commit(struct bonding *bond)
if (slave->link_failure_count < UINT_MAX)
slave->link_failure_count++;
- slave->link = BOND_LINK_DOWN;
+ bond_set_slave_link_state(slave, BOND_LINK_DOWN);
if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP ||
BOND_MODE(bond) == BOND_MODE_8023AD)
@@ -2578,7 +2590,7 @@ static void bond_ab_arp_commit(struct bonding *bond)
struct slave *current_arp_slave;
current_arp_slave = rtnl_dereference(bond->current_arp_slave);
- slave->link = BOND_LINK_UP;
+ bond_set_slave_link_state(slave, BOND_LINK_UP);
if (current_arp_slave) {
bond_set_slave_inactive_flags(
current_arp_slave,
@@ -2601,7 +2613,7 @@ static void bond_ab_arp_commit(struct bonding *bond)
if (slave->link_failure_count < UINT_MAX)
slave->link_failure_count++;
- slave->link = BOND_LINK_DOWN;
+ bond_set_slave_link_state(slave, BOND_LINK_DOWN);
bond_set_slave_inactive_flags(slave,
BOND_SLAVE_NOTIFY_NOW);
@@ -2680,7 +2692,7 @@ static bool bond_ab_arp_probe(struct bonding *bond)
* up when it is actually down
*/
if (!bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) {
- slave->link = BOND_LINK_DOWN;
+ bond_set_slave_link_state(slave, BOND_LINK_DOWN);
if (slave->link_failure_count < UINT_MAX)
slave->link_failure_count++;
@@ -2700,7 +2712,7 @@ static bool bond_ab_arp_probe(struct bonding *bond)
if (!new_slave)
goto check_state;
- new_slave->link = BOND_LINK_BACK;
+ bond_set_slave_link_state(new_slave, BOND_LINK_BACK);
bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER);
bond_arp_send_all(bond, new_slave);
new_slave->last_link_up = jiffies;
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 29f53ea..d1367ec 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -490,6 +490,11 @@ static inline bool bond_is_slave_inactive(struct slave *slave)
return slave->inactive;
}
+static inline void bond_set_slave_link_state(struct slave *slave, int state)
+{
+ slave->link = state;
+}
+
static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local)
{
struct in_device *in_dev;
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 01/10] net/core: Add event for a change in slave state
From: Or Gerlitz @ 2015-02-03 14:48 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Roland Dreier, Amir Vadai, Tal Alon, Moni Shoua,
Or Gerlitz
In-Reply-To: <1422974919-28084-1-git-send-email-ogerlitz@mellanox.com>
From: Moni Shoua <monis@mellanox.com>
Add event which provides an indication on a change in the state
of a bonding slave. The event handler should cast the pointer to the
appropriate type (struct netdev_bonding_info) in order to get the
full info about the slave.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
include/linux/netdevice.h | 15 +++++++++++++++
net/core/dev.c | 20 ++++++++++++++++++++
net/core/rtnetlink.c | 1 +
3 files changed, 36 insertions(+), 0 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3d37c6e..0b13915 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -51,6 +51,7 @@
#include <linux/netdev_features.h>
#include <linux/neighbour.h>
#include <uapi/linux/netdevice.h>
+#include <uapi/linux/if_bonding.h>
struct netpoll_info;
struct device;
@@ -2054,6 +2055,7 @@ struct pcpu_sw_netstats {
#define NETDEV_RESEND_IGMP 0x0016
#define NETDEV_PRECHANGEMTU 0x0017 /* notify before mtu change happened */
#define NETDEV_CHANGEINFODATA 0x0018
+#define NETDEV_BONDING_INFO 0x0019
int register_netdevice_notifier(struct notifier_block *nb);
int unregister_netdevice_notifier(struct notifier_block *nb);
@@ -3477,6 +3479,19 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
netdev_features_t features);
+struct netdev_bonding_info {
+ ifslave slave;
+ ifbond master;
+};
+
+struct netdev_notifier_bonding_info {
+ struct netdev_notifier_info info; /* must be first */
+ struct netdev_bonding_info bonding_info;
+};
+
+void netdev_bonding_info_change(struct net_device *dev,
+ struct netdev_bonding_info *bonding_info);
+
static inline
struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features)
{
diff --git a/net/core/dev.c b/net/core/dev.c
index 1d564d6..ede0b16 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5355,6 +5355,26 @@ void netdev_upper_dev_unlink(struct net_device *dev,
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
+/**
+ * netdev_bonding_info_change - Dispatch event about slave change
+ * @dev: device
+ * @netdev_bonding_info: info to dispatch
+ *
+ * Send NETDEV_BONDING_INFO to netdev notifiers with info.
+ * The caller must hold the RTNL lock.
+ */
+void netdev_bonding_info_change(struct net_device *dev,
+ struct netdev_bonding_info *bonding_info)
+{
+ struct netdev_notifier_bonding_info info;
+
+ memcpy(&info.bonding_info, bonding_info,
+ sizeof(struct netdev_bonding_info));
+ call_netdevice_notifiers_info(NETDEV_BONDING_INFO, dev,
+ &info.info);
+}
+EXPORT_SYMBOL(netdev_bonding_info_change);
+
void netdev_adjacent_add_links(struct net_device *dev)
{
struct netdev_adjacent *iter;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index fedd7ab..0fb51f7 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3178,6 +3178,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
case NETDEV_UNREGISTER_FINAL:
case NETDEV_RELEASE:
case NETDEV_JOIN:
+ case NETDEV_BONDING_INFO:
break;
default:
rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
--
1.7.1
^ permalink raw reply related
* [PATCH 00/10] Add HA and LAG support to mlx4 RoCE and SRIOV services
From: Or Gerlitz @ 2015-02-03 14:48 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Roland Dreier, Amir Vadai, Tal Alon, Or Gerlitz
Hi Dave,
This series takes advanges of bonding mlx4 Ethernet devices to support
a model of High-Availability and Link Aggregation for more environments.
The mlx4 driver reacts on netdev events generated by bonding when
slave state changes happen by programming a HW V2P (Virt-to-Phys)
port table. Bonding was extended to expose these state changes
through netdev events.
When an mlx4 interface such as the mlx4 IB/RoCE driver is subject to
this policy, QPs are created over virtual ports which are mapped
to one of the two physical ports. When a failure happens, the
re-programming of the V2P table allows traffic to keep flowing.
The mlx4 Ethernet driver interfaces are not subject to this
policy and act as usual.
A 2nd use-case for this model would be to add HA and Link Aggregation
support to single ported mlx4 Ethernet VFs. In this case, the PF Ethernet
intrfaces are bonded, all the VFs see single port devices (which is
supported already today), and VF QPs are subject to V2P.
Moni and Or.
Moni Shoua (10):
net/core: Add event for a change in slave state
net/bonding: Move slave state changes to a helper function
net/bonding: Notify state change on slaves
net/mlx4_core: Port aggregation low level interface
net/mlx4_core: Port aggregation upper layer interface
net/mlx4_en: Port aggregation configuration
IB/mlx4: Reuse mlx4_mac_to_u64()
IB/mlx4: Add port aggregation support
IB/mlx4: Create mirror flows in port aggregation mode
IB/mlx4: Load balance ports in port aggregation mode
drivers/infiniband/hw/mlx4/ah.c | 1 +
drivers/infiniband/hw/mlx4/main.c | 161 ++++++++++++++++--
drivers/infiniband/hw/mlx4/mlx4_ib.h | 17 ++-
drivers/infiniband/hw/mlx4/qp.c | 31 +++--
drivers/net/bonding/bond_main.c | 106 +++++++++---
drivers/net/ethernet/mellanox/mlx4/cmd.c | 9 +
drivers/net/ethernet/mellanox/mlx4/en_main.c | 8 +
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 176 ++++++++++++++++++++
drivers/net/ethernet/mellanox/mlx4/en_resources.c | 8 +-
drivers/net/ethernet/mellanox/mlx4/fw.c | 56 ++++++-
drivers/net/ethernet/mellanox/mlx4/intf.c | 54 ++++++
drivers/net/ethernet/mellanox/mlx4/main.c | 89 ++++++++++
drivers/net/ethernet/mellanox/mlx4/mlx4.h | 3 +
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 5 +
drivers/net/ethernet/mellanox/mlx4/qp.c | 2 +
.../net/ethernet/mellanox/mlx4/resource_tracker.c | 3 +
include/linux/mlx4/cmd.h | 7 +
include/linux/mlx4/device.h | 11 +-
include/linux/mlx4/driver.h | 19 ++
include/linux/mlx4/qp.h | 1 +
include/linux/netdevice.h | 15 ++
include/net/bonding.h | 17 ++
net/core/dev.c | 20 +++
net/core/rtnetlink.c | 1 +
24 files changed, 756 insertions(+), 64 deletions(-)
^ permalink raw reply
* Re: [PATCH] ath9k_htc: add adaptive usb flow control to repair soft lockup with monitor mode
From: Oleksij Rempel @ 2015-02-03 14:35 UTC (permalink / raw)
To: Kalle Valo, yuweizheng-7R9yAhoRP9E
Cc: linux-kernel-u79uwXL29TY76Z2rM5mHXA,
ath9k-devel-xDcbHBWguxHbcTqmT+pZeQ,
linux-wireless-u79uwXL29TY76Z2rM5mHXA,
ath9k-devel-A+ZNKFmMK5xy9aJCnZT0Uw, netdev-u79uwXL29TY76Z2rM5mHXA,
Yuwei Zheng
In-Reply-To: <87fvanxldu.fsf-HodKDYzPHsUD5k0oWYwrnHL1okKdlPRT@public.gmane.org>
[-- Attachment #1: Type: text/plain, Size: 1185 bytes --]
It seems to work without noticeable regressions.
Am 03.02.2015 um 12:52 schrieb Kalle Valo:
> yuweizheng-7R9yAhoRP9E@public.gmane.org writes:
>
>> From: Yuwei Zheng <yuweizheng-7R9yAhoRP9E@public.gmane.org>
>>
>> In the environment with heavy wifi traffic, set the ar9271 into monitor mode, will
>> trigger a deadloop panic.
>>
>> The ath9k_hif_usb_rx_cb function excute on the interrupt context, and ath9k_rx_tasklet excute
>> on the soft irq context. In other words, the ath9k_hif_usb_rx_cb have more chance to excute than
>> ath9k_rx_tasklet. So in the worst condition, the rx.rxbuf receive list is always full,
>> and the do {}while(true) loop will not be break. The kernel get a soft lockup panic.
>
> The word wrapping is still wrong, please limit the width to 72 chars or
> so. But no need to wrap log snippets, they can exceed the limit.
>
>> Signed-off-by: Yuwei Zheng <zhengyuwei-z+sInHIpZSw@public.gmane.org>
>> Signed-off-by: Yuwei Zheng <yuweizheng-7R9yAhoRP9E@public.gmane.org>
>
> Why two of these? Please use just one Signed-off-by line. Unless these
> are two different persons with the same name :)
>
--
Regards,
Oleksij
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 213 bytes --]
^ permalink raw reply
* Re: Throughput regression with `tcp: refine TSO autosizing`
From: Eric Dumazet @ 2015-02-03 14:27 UTC (permalink / raw)
To: Michal Kazior
Cc: linux-wireless, Network Development,
eyalpe-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb
In-Reply-To: <CA+BoTQkMikA8wxm1ce2DkKhPB0HiKeAqT7f+sQ=91W40z=X0Rg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On Tue, 2015-02-03 at 12:50 +0100, Michal Kazior wrote:
> On 3 February 2015 at 02:18, Eric Dumazet <eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> wrote:
> > On Mon, 2015-02-02 at 10:52 -0800, Eric Dumazet wrote:
> >
> >> It seems to break ACK clocking badly (linux stack has a somewhat buggy
> >> tcp_tso_should_defer(), which relies on ACK being received smoothly, as
> >> no timer is setup to split the TSO packet.)
> >
> > Following patch might help the TSO split defer logic.
> >
> > It would avoid setting the TSO defer 'pseudo timer' twice, if/when TCP
> > Small Queue logic prevented the xmit at the expiration of first 'timer'.
> >
> > This patch clears the tso_deferred variable only if we could really
> > send something.
> >
> > Please try it, thanks !
> [..patch..]
>
> I've done a second round of tests. I've added the A-MSDU count
> parameter I've mentioned in my other email into the mix.
>
> net - net/master (includes stretch ack patches)
> net-tso - net/master + your TSO defer patch
> net-gro - net/master + my ath10k GRO patch
> net-gro-tso - net/master + duh
>
> Here's the best of amsdu count 1 and 3:
>
> ; for (i in */output.txt) { echo $i; for (j in (1 3)) { cat $i | awk
> 'x && /Mbits/ {y=$0}; x && y && !/Mbits/ {print y; x=0; y=""}; /set
> amsdu cnt to '$j'/{x=1}' | awk '{ if (x < $(NF-1)) {x=$(NF-1)} }
> END{print "A-MSDU limit='$j', " x " Mbits/sec"}' } }
> net-gro-tso/output.txt
> A-MSDU limit=1, 436 Mbits/sec
> A-MSDU limit=3, 284 Mbits/sec
> net-gro/output.txt
> A-MSDU limit=1, 444 Mbits/sec
> A-MSDU limit=3, 283 Mbits/sec
> net-tso/output.txt
> A-MSDU limit=1, 376 Mbits/sec
> A-MSDU limit=3, 251 Mbits/sec
> net/output.txt
> A-MSDU limit=1, 387 Mbits/sec
> A-MSDU limit=3, 260 Mbits/sec
>
> IOW:
> - stretch acks / TSO defer don't seem to help much (when compared to
> throughput results from yesterday)
> - GRO helps
> - disabling A-MSDU on sender helps
> - net/master+GRO still doesn't reach the performance from before the
> regression (~600mbps w/ GRO)
>
> You can grab logs and dumps here: http://www.filedropper.com/test2tar
>
Thanks for these traces.
There is absolutely a problem at the sender, as we can see a big 2ms
delay between reception of ACK and send of following packets.
TCP stack should generate them immediately.
Are you using some kind of netem qdisc ?
These 2ms delays, in a flow with a 5ms RTT are terrible.
06:54:57.408391 IP 192.168.1.2.5001 > 192.168.1.3.51645: Flags [.], ack 4294899240, win 11268, options [nop,nop,TS val 1053302 ecr 1052250], length 0
06:54:57.408418 IP 192.168.1.2.5001 > 192.168.1.3.51645: Flags [.], ack 4294910824, win 11268, options [nop,nop,TS val 1053303 ecr 1052251], length 0
06:54:57.408431 IP 192.168.1.2.5001 > 192.168.1.3.51645: Flags [.], ack 4294936888, win 11268, options [nop,nop,TS val 1053303 ecr 1052251], length 0
06:54:57.408453 IP 192.168.1.2.5001 > 192.168.1.3.51645: Flags [.], ack 4294962952, win 11268, options [nop,nop,TS val 1053303 ecr 1052251], length 0
06:54:57.408474 IP 192.168.1.2.5001 > 192.168.1.3.51645: Flags [.], ack 0, win 11268, options [nop,nop,TS val 1053303 ecr 1052251], length 0
<this 2ms delay is not generated by TCP stack.>
06:54:57.410243 IP 192.168.1.3.51645 > 192.168.1.2.5001: Flags [.], seq 82536:83984, ack 1, win 457, options [nop,nop,TS val 1052256 ecr 1053303], length 1448
06:54:57.410271 IP 192.168.1.3.51645 > 192.168.1.2.5001: Flags [.], seq 83984:85432, ack 1, win 457, options [nop,nop,TS val 1052256 ecr 1053303], length 1448
06:54:57.410289 IP 192.168.1.3.51645 > 192.168.1.2.5001: Flags [.], seq 85432:86880, ack 1, win 457, options [nop,nop,TS val 1052256 ecr 1053303], length 1448
06:54:57.410310 IP 192.168.1.3.51645 > 192.168.1.2.5001: Flags [.], seq 86880:88328, ack 1, win 457, options [nop,nop,TS val 1052256 ecr 1053303], length 1448
06:54:57.410326 IP 192.168.1.3.51645 > 192.168.1.2.5001: Flags [.], seq 88328:89776, ack 1, win 457, options [nop,nop,TS val 1052256 ecr 1053303], length 1448
06:54:57.410339 IP 192.168.1.3.51645 > 192.168.1.2.5001: Flags [.], seq 89776:91224, ack 1, win 457, options [nop,nop,TS val 1052256 ecr 1053303], length 1448
06:54:57.410353 IP 192.168.1.3.51645 > 192.168.1.2.5001: Flags [.], seq 91224:92672, ack 1, win 457, options [nop,nop,TS val 1052256 ecr 1053303], length 1448
06:54:57.410370 IP 192.168.1.3.51645 > 192.168.1.2.5001: Flags [.], seq 92672:94120, ack 1, win 457, options [nop,nop,TS val 1052256 ecr 1053303], length 1448
...
06:54:57.411178 IP 192.168.1.2.5001 > 192.168.1.3.51645: Flags [.], ack 28960, win 11268, options [nop,nop,TS val 1053306 ecr 1052253], length 0
06:54:57.411190 IP 192.168.1.2.5001 > 192.168.1.3.51645: Flags [.], ack 52128, win 11268, options [nop,nop,TS val 1053306 ecr 1052254], length 0
06:54:57.411220 IP 192.168.1.2.5001 > 192.168.1.3.51645: Flags [.], ack 78192, win 11268, options [nop,nop,TS val 1053306 ecr 1052254], length 0
06:54:57.411243 IP 192.168.1.2.5001 > 192.168.1.3.51645: Flags [.], ack 82536, win 11268, options [nop,nop,TS val 1053306 ecr 1052254], length 0
< same 2ms unexplained gap here >
06:54:57.412912 IP 192.168.1.3.51645 > 192.168.1.2.5001: Flags [.], seq 165072:166520, ack 1, win 457, options [nop,nop,TS val 1052259 ecr 1053306], length 1448
06:54:57.412935 IP 192.168.1.3.51645 > 192.168.1.2.5001: Flags [.], seq 166520:167968, ack 1, win 457, options [nop,nop,TS val 1052259 ecr 1053306], length 1448
06:54:57.412948 IP 192.168.1.3.51645 > 192.168.1.2.5001: Flags [.], seq 167968:169416, ack 1, win 457, options [nop,nop,TS val 1052259 ecr 1053306], length 1448
...
06:54:57.413650 IP 192.168.1.3.51645 > 192.168.1.2.5001: Flags [.], seq 244712:246160, ack 1, win 457, options [nop,nop,TS val 1052260 ecr 1053306], length 1448
06:54:57.413662 IP 192.168.1.3.51645 > 192.168.1.2.5001: Flags [.], seq 246160:247608, ack 1, win 457, options [nop,nop,TS val 1052260 ecr 1053306], length 1448
06:54:57.413712 IP 192.168.1.2.5001 > 192.168.1.3.51645: Flags [.], ack 112944, win 11268, options [nop,nop,TS val 1053308 ecr 1052256], length 0
06:54:57.413730 IP 192.168.1.2.5001 > 192.168.1.3.51645: Flags [.], ack 130320, win 11268, options [nop,nop,TS val 1053308 ecr 1052257], length 0
06:54:57.413754 IP 192.168.1.2.5001 > 192.168.1.3.51645: Flags [.], ack 160728, win 11268, options [nop,nop,TS val 1053309 ecr 1052257], length 0
06:54:57.413779 IP 192.168.1.2.5001 > 192.168.1.3.51645: Flags [.], ack 165072, win 11268, options [nop,nop,TS val 1053309 ecr 1052257], length 0
< same 2ms delay >
06:54:57.415682 IP 192.168.1.3.51645 > 192.168.1.2.5001: Flags [.], seq 247608:249056, ack 1, win 457, options [nop,nop,TS val 1052262 ecr 1053309], length 1448
06:54:57.415709 IP 192.168.1.3.51645 > 192.168.1.2.5001: Flags [.], seq 249056:250504, ack 1, win 457, options [nop,nop,TS val 1052262 ecr 1053309], length 1448
Are packets TX completed after a timer or something ?
Some very heavy stuff might run from tasklet (or other softirq triggered) event.
BTW, traces tend to show that you 'receive' multiple ACK in the same burst,
its not clear if they are delayed at one side or the other.
GRO should delay only GRO candidates. ACK packets are not GRO candidates.
Have you tried to disable GSO on sender ?
(Or maybe wifi drivers should start to use skb->xmit_more as a signal to end aggregation)
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" 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 v2 08/17] {macvtap,tun}_get_user(): switch to iov_iter
From: Al Viro @ 2015-02-03 14:27 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: David Miller, netdev, linux-kernel
In-Reply-To: <20150203101044.GA5081@redhat.com>
On Tue, Feb 03, 2015 at 12:10:44PM +0200, Michael S. Tsirkin wrote:
> Hmm does copy_from_iter actually modify the iovec?
> If so, won't this break aio on tun/macvtap, by
> reversing the effect of
> commit 6f26c9a7555e5bcca3560919db9b852015077dae
> tun: fix tun_chr_aio_write so that aio works
> ?
>
>
> Maybe we should change iovec_iter to avoid modifying the
> underlying iovec?
iov_iter never changes the underlying iovec (or kvec, or bvec).
iter->iov_offset changes as you go and once you have consumed an
entire iovec element ->iov is incremented to point to the next one
(and ->iov_offset is reset to 0 at that point). *Contents* of
iter->iov is never modified.
^ permalink raw reply
* RFC: Fix "tc filter show" for basic filters
From: Ignacy Gawedzki @ 2015-02-03 14:11 UTC (permalink / raw)
To: netdev
Hi everyone,
I have a problem with tc filter and very simple "basic" filters with no
associated action.
The thing is I have an HTB qdisc with handle 1: with a single class 1:1
attached to it. When I add a basic filter that does nothing,
tc filter add dev eth0 prio 1 handle 1 parent 1: basic classid 1:1
it doesn't completely appear when I type
tc filter show dev eth0
When debugging basic_dump() in net/sched/cls_basic.c, I noticed that
tcf_exts_dump_stats() returns -1, which triggers a jump to nla_put_failure
which ends up removing all the added attributes so far. When looking at
tcf_action_copy_stats() in net/sched/act_api.c, which is ultimately called by
tcf_exts_dump_stats(), I see that the returned error is triggered by a->priv
being NULL.
Although I confess I didn't make the effort of understanding all the workings
of a->priv in this context, it seems to me that if that is NULL, this is
probably not a good reason to return an error. I made the change below and so
far it works for me.
Can anyone take a critical look at this?
Thanks.
Ignacy
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 3d43e49..6dd46be 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -602,7 +602,7 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct
tc_action *a,
struct tcf_common *p = a->priv;
if (p == NULL)
- goto errout;
+ return 0;
/* compat_mode being true specifies a call that is supposed
* to add additional backward compatibility statistic TLVs.
--
Ignacy Gawędzki
R&D Engineer
Green Communications
^ permalink raw reply related
* Re: [PATCHv3, ipsec-next] xfrm: Do not parse 32bits compiled xfrm netlink msg on 64bits host
From: Nicolas Dichtel @ 2015-02-03 14:02 UTC (permalink / raw)
To: Steffen Klassert; +Cc: Fan Du, herbert, davem, netdev, fengyuleidian0615
In-Reply-To: <20150203122432.GV13046@secunet.com>
Le 03/02/2015 13:24, Steffen Klassert a écrit :
> On Mon, Feb 02, 2015 at 10:02:50AM +0100, Nicolas Dichtel wrote:
>
> I tend to apply this patch unless you can come up with a real world
> application that will break if we do so.
It's a custom patch made for strongswan (not included upstream).
My suggestion was to display an error message instead of rejecting the message.
But fair enough, let's apply this patch, it will force people to come up with a
proper solution.
^ permalink raw reply
* [PATCH net-next 4/4] tipc: separate link starting event from link timeout event
From: Jon Maloy @ 2015-02-03 13:59 UTC (permalink / raw)
To: davem; +Cc: Jon Maloy, netdev, Paul Gortmaker, tipc-discussion
In-Reply-To: <1422971960-9172-1-git-send-email-jon.maloy@ericsson.com>
When a new link instance is created, it is trigged to start by
sending it a TIPC_STARTING_EVT, whereafter a regular link
reset is applied to it.
The starting event is codewise treated as a timeout event, and prompts
a link RESET message to be sent to the peer node, carrying a link
session identifier. The later link_reset() call nudges this session
identifier, whereafter all subsequent RESET messages will be sent out
with the new identifier. The latter session number overrides the former,
causing the peer to unconditionally accept it irrespective of its
current working state.
We don't think that this causes any problem, but it is not in accordance
with the protocol spec, and may cause confusion when debugging TIPC
sessions.
To avoid this, we make the starting event distinct from the
subsequent timeout events, by not allowing the former to send
out any RESET message. This eliminates the described problem.
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
---
net/tipc/link.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 46aa599..77c7ccd 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -649,7 +649,9 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
break;
case STARTING_EVT:
l_ptr->flags |= LINK_STARTED;
- /* fall through */
+ l_ptr->fsm_msg_cnt++;
+ link_set_timer(l_ptr, cont_intv);
+ break;
case TIMEOUT_EVT:
tipc_link_proto_xmit(l_ptr, RESET_MSG, 0, 0, 0, 0, 0);
l_ptr->fsm_msg_cnt++;
--
1.9.1
------------------------------------------------------------------------------
Dive into the World of Parallel Programming. The Go Parallel Website,
sponsored by Intel and developed in partnership with Slashdot Media, is your
hub for all things parallel software development, from weekly thought
leadership blogs to news, videos, case studies, tutorials and more. Take a
look and join the conversation now. http://goparallel.sourceforge.net/
^ permalink raw reply related
* [PATCH net-next 3/4] tipc: eliminate race during node creation
From: Jon Maloy @ 2015-02-03 13:59 UTC (permalink / raw)
To: davem; +Cc: Jon Maloy, netdev, Paul Gortmaker, tipc-discussion
In-Reply-To: <1422971960-9172-1-git-send-email-jon.maloy@ericsson.com>
Instances of struct node are created in the function tipc_disc_rcv()
under the assumption that there is no race between received discovery
messages arriving from the same node. This assumption is wrong.
When we use more than one bearer, it is possible that discovery
messages from the same node arrive at the same moment, resulting in
creation of two instances of struct tipc_node. This may later cause
confusion during link establishment, and may result in one of the links
never becoming activated.
We fix this by making lookup and potential creation of nodes atomic.
Instead of first looking up the node, and in case of failure, create it,
we now start with looking up the node inside node_link_create(), and
return a reference to that one if found. Otherwise, we go ahead and
create the node as we did before.
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
---
net/tipc/discover.c | 9 ++-------
net/tipc/node.c | 11 +++++------
2 files changed, 7 insertions(+), 13 deletions(-)
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index 5b40cb8..a580a40 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -1,7 +1,7 @@
/*
* net/tipc/discover.c
*
- * Copyright (c) 2003-2006, 2014, Ericsson AB
+ * Copyright (c) 2003-2006, 2014-2015, Ericsson AB
* Copyright (c) 2005-2006, 2010-2011, Wind River Systems
* All rights reserved.
*
@@ -47,7 +47,6 @@
/* indicates no timer in use */
#define TIPC_LINK_REQ_INACTIVE 0xffffffff
-
/**
* struct tipc_link_req - information about an ongoing link setup request
* @bearer_id: identity of bearer issuing requests
@@ -163,13 +162,9 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *buf,
if (!tipc_in_scope(bearer->domain, onode))
return;
- /* Locate, or if necessary, create, node: */
- node = tipc_node_find(net, onode);
- if (!node)
- node = tipc_node_create(net, onode);
+ node = tipc_node_create(net, onode);
if (!node)
return;
-
tipc_node_lock(node);
link = node->links[bearer->identity];
diff --git a/net/tipc/node.c b/net/tipc/node.c
index d4cb8c1..842bd7a 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -96,14 +96,14 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr)
struct tipc_node *n_ptr, *temp_node;
spin_lock_bh(&tn->node_list_lock);
-
+ n_ptr = tipc_node_find(net, addr);
+ if (n_ptr)
+ goto exit;
n_ptr = kzalloc(sizeof(*n_ptr), GFP_ATOMIC);
if (!n_ptr) {
- spin_unlock_bh(&tn->node_list_lock);
pr_warn("Node creation failed, no memory\n");
- return NULL;
+ goto exit;
}
-
n_ptr->addr = addr;
n_ptr->net = net;
spin_lock_init(&n_ptr->lock);
@@ -123,9 +123,8 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr)
list_add_tail_rcu(&n_ptr->list, &temp_node->list);
n_ptr->action_flags = TIPC_WAIT_PEER_LINKS_DOWN;
n_ptr->signature = INVALID_NODE_SIG;
-
tn->num_nodes++;
-
+exit:
spin_unlock_bh(&tn->node_list_lock);
return n_ptr;
}
--
1.9.1
------------------------------------------------------------------------------
Dive into the World of Parallel Programming. The Go Parallel Website,
sponsored by Intel and developed in partnership with Slashdot Media, is your
hub for all things parallel software development, from weekly thought
leadership blogs to news, videos, case studies, tutorials and more. Take a
look and join the conversation now. http://goparallel.sourceforge.net/
^ permalink raw reply related
* [PATCH net-next 2/4] tipc: avoid stale link after aborted failover
From: Jon Maloy @ 2015-02-03 13:59 UTC (permalink / raw)
To: davem; +Cc: Jon Maloy, netdev, Paul Gortmaker, tipc-discussion
In-Reply-To: <1422971960-9172-1-git-send-email-jon.maloy@ericsson.com>
During link failover it may happen that the remaining link goes
down while it is still in the process of taking over traffic
from a previously failed link. When this happens, we currently
abort the failover procedure and reset the first failed link to
non-failover mode, so that it will be ready to re-establish
contact with its peer when it comes available.
However, if the first link goes down because its bearer was manually
disabled, it is not enough to reset it; it must also be deleted;
which is supposed to happen when the failover procedure is finished.
Otherwise it will remain a zombie link: attached to the owner node
structure, in mode LINK_STOPPED, and permanently blocking any re-
establishing of the link to the peer via the interface in question.
We fix this by amending the failover abort procedure. Apart from
resetting the link to non-failover state, we test if the link is
also in LINK_STOPPED mode. If so, we delete it, using the conditional
tipc_link_delete() function introduced in the previous commit.
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
---
net/tipc/link.h | 1 +
net/tipc/node.c | 4 ++++
2 files changed, 5 insertions(+)
diff --git a/net/tipc/link.h b/net/tipc/link.h
index f06b779..3e3432b 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -202,6 +202,7 @@ struct tipc_port;
struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
struct tipc_bearer *b_ptr,
const struct tipc_media_addr *media_addr);
+void tipc_link_delete(struct tipc_link *link);
void tipc_link_delete_list(struct net *net, unsigned int bearer_id,
bool shutting_down);
void tipc_link_failover_send_queue(struct tipc_link *l_ptr);
diff --git a/net/tipc/node.c b/net/tipc/node.c
index ee5d33c..d4cb8c1 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -406,6 +406,10 @@ static void node_lost_contact(struct tipc_node *n_ptr)
l_ptr->reset_checkpoint = l_ptr->next_in_no;
l_ptr->exp_msg_count = 0;
tipc_link_reset_fragments(l_ptr);
+
+ /* Link marked for deletion after failover? => do it now */
+ if (l_ptr->flags & LINK_STOPPED)
+ tipc_link_delete(l_ptr);
}
n_ptr->action_flags &= ~TIPC_WAIT_OWN_LINKS_DOWN;
--
1.9.1
------------------------------------------------------------------------------
Dive into the World of Parallel Programming. The Go Parallel Website,
sponsored by Intel and developed in partnership with Slashdot Media, is your
hub for all things parallel software development, from weekly thought
leadership blogs to news, videos, case studies, tutorials and more. Take a
look and join the conversation now. http://goparallel.sourceforge.net/
^ permalink raw reply related
* [PATCH net-next 1/4] tipc: add reference count to struct tipc_link
From: Jon Maloy @ 2015-02-03 13:59 UTC (permalink / raw)
To: davem; +Cc: Jon Maloy, netdev, Paul Gortmaker, tipc-discussion
In-Reply-To: <1422971960-9172-1-git-send-email-jon.maloy@ericsson.com>
When a bearer is disabled, all pertaining links will be reset and
deleted. However, if there is a second active link towards a killed
link's destination, the delete has to be postponed until the failover
is finished. During this interval, we currently put the link in zombie
mode, i.e., we take it out of traffic, delete its timer, but leave it
attached to the owner node structure until all missing packets have
been received. When this is done, we detach the link from its node
and delete it, assuming that the synchronous timer deletion that was
initiated earlier in a different thread has finished.
This is unsafe, as the failover may finish before del_timer_sync()
has returned in the other thread.
We fix this by adding an atomic reference counter of type kref in
struct tipc_link. The counter keeps track of the references kept
to the link by the owner node and the timer. We then do a conditional
delete, based on the reference counter, both after the failover has
been finished and when the timer expires, if applicable. Whoever
comes last, will actually delete the link. This approach also implies
that we can make the deletion of the timer asynchronous.
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
---
net/tipc/link.c | 79 +++++++++++++++++++++++++++++++++++----------------------
net/tipc/link.h | 2 ++
2 files changed, 50 insertions(+), 31 deletions(-)
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 2846ad80..46aa599 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -127,6 +127,21 @@ static unsigned int align(unsigned int i)
return (i + 3) & ~3u;
}
+static void tipc_link_release(struct kref *kref)
+{
+ kfree(container_of(kref, struct tipc_link, ref));
+}
+
+static void tipc_link_get(struct tipc_link *l_ptr)
+{
+ kref_get(&l_ptr->ref);
+}
+
+static void tipc_link_put(struct tipc_link *l_ptr)
+{
+ kref_put(&l_ptr->ref, tipc_link_release);
+}
+
static void link_init_max_pkt(struct tipc_link *l_ptr)
{
struct tipc_node *node = l_ptr->owner;
@@ -222,11 +237,13 @@ static void link_timeout(unsigned long data)
tipc_link_push_packets(l_ptr);
tipc_node_unlock(l_ptr->owner);
+ tipc_link_put(l_ptr);
}
static void link_set_timer(struct tipc_link *link, unsigned long time)
{
- mod_timer(&link->timer, jiffies + time);
+ if (!mod_timer(&link->timer, jiffies + time))
+ tipc_link_get(link);
}
/**
@@ -267,7 +284,7 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
pr_warn("Link creation failed, no memory\n");
return NULL;
}
-
+ kref_init(&l_ptr->ref);
l_ptr->addr = peer;
if_name = strchr(b_ptr->name, ':') + 1;
sprintf(l_ptr->name, "%u.%u.%u:%s-%u.%u.%u:unknown",
@@ -305,46 +322,48 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
skb_queue_head_init(&l_ptr->waiting_sks);
link_reset_statistics(l_ptr);
-
tipc_node_attach_link(n_ptr, l_ptr);
-
setup_timer(&l_ptr->timer, link_timeout, (unsigned long)l_ptr);
-
link_state_event(l_ptr, STARTING_EVT);
return l_ptr;
}
+/**
+ * link_delete - Conditional deletion of link.
+ * If timer still running, real delete is done when it expires
+ * @link: link to be deleted
+ */
+void tipc_link_delete(struct tipc_link *link)
+{
+ tipc_link_reset_fragments(link);
+ tipc_node_detach_link(link->owner, link);
+ tipc_link_put(link);
+}
+
void tipc_link_delete_list(struct net *net, unsigned int bearer_id,
bool shutting_down)
{
struct tipc_net *tn = net_generic(net, tipc_net_id);
- struct tipc_link *l_ptr;
- struct tipc_node *n_ptr;
+ struct tipc_link *link;
+ struct tipc_node *node;
rcu_read_lock();
- list_for_each_entry_rcu(n_ptr, &tn->node_list, list) {
- tipc_node_lock(n_ptr);
- l_ptr = n_ptr->links[bearer_id];
- if (l_ptr) {
- tipc_link_reset(l_ptr);
- if (shutting_down || !tipc_node_is_up(n_ptr)) {
- tipc_node_detach_link(l_ptr->owner, l_ptr);
- tipc_link_reset_fragments(l_ptr);
- tipc_node_unlock(n_ptr);
-
- /* Nobody else can access this link now: */
- del_timer_sync(&l_ptr->timer);
- kfree(l_ptr);
- } else {
- /* Detach/delete when failover is finished: */
- l_ptr->flags |= LINK_STOPPED;
- tipc_node_unlock(n_ptr);
- del_timer_sync(&l_ptr->timer);
- }
+ list_for_each_entry_rcu(node, &tn->node_list, list) {
+ tipc_node_lock(node);
+ link = node->links[bearer_id];
+ if (!link) {
+ tipc_node_unlock(node);
continue;
}
- tipc_node_unlock(n_ptr);
+ tipc_link_reset(link);
+ if (del_timer(&link->timer))
+ tipc_link_put(link);
+ link->flags |= LINK_STOPPED;
+ /* Delete link now, or when failover is finished: */
+ if (shutting_down || !tipc_node_is_up(node))
+ tipc_link_delete(link);
+ tipc_node_unlock(node);
}
rcu_read_unlock();
}
@@ -1837,10 +1856,8 @@ static struct sk_buff *tipc_link_failover_rcv(struct tipc_link *l_ptr,
}
}
exit:
- if ((l_ptr->exp_msg_count == 0) && (l_ptr->flags & LINK_STOPPED)) {
- tipc_node_detach_link(l_ptr->owner, l_ptr);
- kfree(l_ptr);
- }
+ if ((!l_ptr->exp_msg_count) && (l_ptr->flags & LINK_STOPPED))
+ tipc_link_delete(l_ptr);
return buf;
}
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 9df7fa4..f06b779 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -103,6 +103,7 @@ struct tipc_stats {
* @media_addr: media address to use when sending messages over link
* @timer: link timer
* @owner: pointer to peer node
+ * @refcnt: reference counter for permanent references (owner node & timer)
* @flags: execution state flags for link endpoint instance
* @checkpoint: reference point for triggering link continuity checking
* @peer_session: link session # being used by peer end of link
@@ -142,6 +143,7 @@ struct tipc_link {
struct tipc_media_addr media_addr;
struct timer_list timer;
struct tipc_node *owner;
+ struct kref ref;
/* Management and link supervision data */
unsigned int flags;
--
1.9.1
------------------------------------------------------------------------------
Dive into the World of Parallel Programming. The Go Parallel Website,
sponsored by Intel and developed in partnership with Slashdot Media, is your
hub for all things parallel software development, from weekly thought
leadership blogs to news, videos, case studies, tutorials and more. Take a
look and join the conversation now. http://goparallel.sourceforge.net/
^ permalink raw reply related
* [PATCH net-next 0/4] tipc: some small fixes
From: Jon Maloy @ 2015-02-03 13:59 UTC (permalink / raw)
To: davem; +Cc: Jon Maloy, netdev, Paul Gortmaker, tipc-discussion
During extensive testing and analysis of running dual links between
nodes, we have encountered some issues that potentially may cause
problems. We choose to fix those proactively in this series.
Jon Maloy (4):
tipc: add reference count to struct tipc_link
tipc: avoid stale link after aborted failover
tipc: eliminate race during node creation
tipc: separate link starting event from link timeout event
net/tipc/discover.c | 9 ++----
net/tipc/link.c | 83 ++++++++++++++++++++++++++++++++---------------------
net/tipc/link.h | 3 ++
net/tipc/node.c | 15 ++++++----
4 files changed, 65 insertions(+), 45 deletions(-)
--
1.9.1
------------------------------------------------------------------------------
Dive into the World of Parallel Programming. The Go Parallel Website,
sponsored by Intel and developed in partnership with Slashdot Media, is your
hub for all things parallel software development, from weekly thought
leadership blogs to news, videos, case studies, tutorials and more. Take a
look and join the conversation now. http://goparallel.sourceforge.net/
^ permalink raw reply
* [PATCH] net: rds: use correct size for max unacked packets and bytes
From: Sasha Levin @ 2015-02-03 13:55 UTC (permalink / raw)
To: linux-kernel
Cc: Sasha Levin, Chien Yen, David S. Miller,
moderated list:RDS - RELIABLE DA...,
open list:NETWORKING [GENERAL]
Max unacked packets/bytes is an int while sizeof(long) was used in the
sysctl table.
This means that when they were getting read we'd also leak kernel memory
to userspace along with the timeout values.
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
---
net/rds/sysctl.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c
index c3b0cd4..c173f69 100644
--- a/net/rds/sysctl.c
+++ b/net/rds/sysctl.c
@@ -71,14 +71,14 @@ static struct ctl_table rds_sysctl_rds_table[] = {
{
.procname = "max_unacked_packets",
.data = &rds_sysctl_max_unacked_packets,
- .maxlen = sizeof(unsigned long),
+ .maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "max_unacked_bytes",
.data = &rds_sysctl_max_unacked_bytes,
- .maxlen = sizeof(unsigned long),
+ .maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
--
1.7.10.4
^ permalink raw reply related
* pull-request: mac80211-next 2015-02-03
From: Johannes Berg @ 2015-02-03 13:51 UTC (permalink / raw)
To: David Miller; +Cc: netdev, linux-wireless
Hi,
Here's a last pull request for net-next - I hope it can still make it,
we fixed a fairly large number of issues. Also there's a bunch of new
ciphers, but see the details below.
Let me know if there's any problem.
Thanks,
johannes
The following changes since commit c1e140bf79d817d4a7aa9932eb98b0359c87af33:
mac80211: delete the assoc/auth timer upon suspend (2015-01-19 18:59:20 +0100)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git tags/mac80211-next-for-davem-2015-02-03
for you to fetch changes up to 79044f60caa7c377333dc8f13cf1e48c144e2521:
net: rfkill: Add Broadcom BCM2E40 bluetooth ACPI ID (2015-02-03 14:38:22 +0100)
----------------------------------------------------------------
Last round of updates for net-next:
* revert a patch that caused a regression with mesh userspace (Bob)
* fix a number of suspend/resume related races
(from Emmanuel, Luca and myself - we'll look at backporting later)
* add software implementations for new ciphers (Jouni)
* add a new ACPI ID for Broadcom's rfkill (Mika)
* allow using netns FD for wireless (Vadim)
* some other cleanups (various)
----------------------------------------------------------------
Bob Copeland (1):
Revert "mac80211: keep sending peer candidate events while in listen state"
Emmanuel Grumbach (2):
mac80211: synchronize_net() before flushing the queues
mac80211: avoid races related to suspend flow
Johannes Berg (9):
mac80211: fix HW registration error paths
mac80211: allow drivers to control software crypto
nl80211: suppress smatch warnings
mac80211: tdls: remove shadowing variable
mac80211: tdls: disentangle HT supported conditions
mac80211: fix per-TID RX-MSDU counter
mac80211: support beacon statistics
ath10k: use IEEE80211_HW_SW_CRYPTO_CONTROL
nl80211: don't document per-wiphy interface dump
Jouni Malinen (6):
cfg80211: Fix BIP (AES-CMAC) cipher validation
cfg80211: Add new GCMP, CCMP-256, BIP-GMAC, BIP-CMAC-256 ciphers
mac80111: Add GCMP and GCMP-256 ciphers
mac80111: Add CCMP-256 cipher
mac80111: Add BIP-CMAC-256 cipher
mac80111: Add BIP-GMAC-128 and BIP-GMAC-256 ciphers
Lorenzo Bianconi (1):
mac80211: enable TPC through mac80211 stack
Luciano Coelho (3):
nl80211: add an attribute to allow delaying the first scheduled scan cycle
mac80211: complete scan work immediately if quiesced or suspended
mac80211: handle potential race between suspend and scan completion
Mika Westerberg (1):
net: rfkill: Add Broadcom BCM2E40 bluetooth ACPI ID
Sharon Dvir (1):
wireless: docs: fix 'make pdfdocs' failure
Vadim Kochan (1):
nl80211: Allow set network namespace by fd
Documentation/DocBook/80211.tmpl | 4 +-
drivers/net/wireless/ath/ath10k/mac.c | 16 +-
include/linux/ieee80211.h | 27 +++
include/net/cfg80211.h | 5 +
include/net/mac80211.h | 39 ++-
include/uapi/linux/nl80211.h | 26 +-
net/core/net_namespace.c | 1 +
net/mac80211/Kconfig | 1 +
net/mac80211/Makefile | 2 +
net/mac80211/aes_ccm.c | 21 +-
net/mac80211/aes_ccm.h | 10 +-
net/mac80211/aes_cmac.c | 34 ++-
net/mac80211/aes_cmac.h | 5 +-
net/mac80211/aes_gcm.c | 95 ++++++++
net/mac80211/aes_gcm.h | 22 ++
net/mac80211/aes_gmac.c | 84 +++++++
net/mac80211/aes_gmac.h | 20 ++
net/mac80211/cfg.c | 50 +++-
net/mac80211/chan.c | 4 +-
net/mac80211/debugfs_key.c | 55 +++++
net/mac80211/ieee80211_i.h | 36 ++-
net/mac80211/iface.c | 12 +-
net/mac80211/key.c | 185 +++++++++++++-
net/mac80211/key.h | 18 ++
net/mac80211/main.c | 107 +++++---
net/mac80211/mesh_plink.c | 7 -
net/mac80211/mlme.c | 3 +
net/mac80211/rx.c | 48 +++-
net/mac80211/scan.c | 5 +
net/mac80211/sta_info.c | 14 ++
net/mac80211/tdls.c | 37 ++-
net/mac80211/tx.c | 20 +-
net/mac80211/util.c | 27 ++-
net/mac80211/wpa.c | 443 +++++++++++++++++++++++++++++++++-
net/mac80211/wpa.h | 19 +-
net/rfkill/rfkill-gpio.c | 1 +
net/wireless/nl80211.c | 31 ++-
net/wireless/util.c | 68 +++++-
38 files changed, 1426 insertions(+), 176 deletions(-)
create mode 100644 net/mac80211/aes_gcm.c
create mode 100644 net/mac80211/aes_gcm.h
create mode 100644 net/mac80211/aes_gmac.c
create mode 100644 net/mac80211/aes_gmac.h
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" 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: [V2,for,3.19,3/7] rtlwifi: rtl8192ee: Fix adhoc fail
From: Kalle Valo @ 2015-02-03 13:23 UTC (permalink / raw)
To: Larry Finger; +Cc: linux-wireless, Troy Tan, netdev, Stable
In-Reply-To: <20150203131516.799471409D0@smtp.codeaurora.org>
Kalle Valo <kvalo@codeaurora.org> writes:
>> From: Troy Tan <troy_tan@realsil.com.cn>
>>
>> When the buffer descriptor index exceeds 2, then a TX HANG condition
>> will result.
>>
>> Signed-off-by: Troy Tan <troy_tan@realsil.com.cn>
>> Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
>> Cc: Stable <stable@vger.kernel.org> [V3.18]
>
> Thanks, 4 patches applied to wireless-drivers-next.git:
>
> b661a5da5776 rtlwifi: rtl8192ee: Fix adhoc fail
> 6e5f44361628 rtlwifi: rtl8192ee: Fix TX hang due to failure to update TX write point
> 92ff754240b8 rtlwifi: rtl8192ee: Fix parsing of received packet
> 21b39ddb5bb2 rtlwifi: rtl8192ee: Fix DMA stalls
>
> 3 patches skipped:
I had to skip these three patches because of my mistake. So what I did
was that I had merged ("fast forwarded") the net tree into my
wireless-drivers tree and not realising I should not do that. So now I
can't merge wireless-drivers into wireless-drivers-next anymore, as it
will pull unnecessary net changes.
> [V2,for,3.19,1/7] rtlwifi: Remove logging statement that is no longer
> needed
I'll apply this after 3.20-rc1 is released, it should apply then without
problems (or the conflicts are easy for me to fix). Luckily this is just
a cosmetic error and can wait for 3.20-rc2, right?
> [V2,for,3.19,2/7] rtlwifi: rtl8192ee: Fix handling of new style descriptors
> [V2,for,3.19,6/7] rtlwifi: rtl8192ee: Fix problems with calculating free space in FIFO
Not sure what to do with these one. Should you rebase and send them now?
--
Kalle Valo
^ permalink raw reply
* Re: [V2,for,3.19,3/7] rtlwifi: rtl8192ee: Fix adhoc fail
From: Kalle Valo @ 2015-02-03 13:15 UTC (permalink / raw)
To: Larry Finger; +Cc: linux-wireless, Troy Tan, netdev, Larry Finger, Stable
In-Reply-To: <1421773286-1039-4-git-send-email-Larry.Finger@lwfinger.net>
> From: Troy Tan <troy_tan@realsil.com.cn>
>
> When the buffer descriptor index exceeds 2, then a TX HANG condition
> will result.
>
> Signed-off-by: Troy Tan <troy_tan@realsil.com.cn>
> Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
> Cc: Stable <stable@vger.kernel.org> [V3.18]
Thanks, 4 patches applied to wireless-drivers-next.git:
b661a5da5776 rtlwifi: rtl8192ee: Fix adhoc fail
6e5f44361628 rtlwifi: rtl8192ee: Fix TX hang due to failure to update TX write point
92ff754240b8 rtlwifi: rtl8192ee: Fix parsing of received packet
21b39ddb5bb2 rtlwifi: rtl8192ee: Fix DMA stalls
3 patches skipped:
[V2,for,3.19,1/7] rtlwifi: Remove logging statement that is no longer needed
[V2,for,3.19,2/7] rtlwifi: rtl8192ee: Fix handling of new style descriptors
[V2,for,3.19,6/7] rtlwifi: rtl8192ee: Fix problems with calculating free space in FIFO
Kalle Valo
^ permalink raw reply
* Re: [PATCH] brcmfmac: avoid duplicated suspend/resume operation
From: Kalle Valo @ 2015-02-03 13:08 UTC (permalink / raw)
To: Fu, Zhonghui
Cc: brudley, Arend van Spriel, Franky Lin, meuleman, linville,
pieterpg, hdegoede, wens, linux-wireless, brcm80211-dev-list,
netdev, linux-kernel@vger.kernel.org
In-Reply-To: <54C5AA8C.4010005@linux.intel.com>
"Fu, Zhonghui" <zhonghui.fu@linux.intel.com> writes:
>>From ff39ed4af9f1c50358fe92ec4c8eaac9db183e00 Mon Sep 17 00:00:00 2001
> From: Zhonghui Fu <zhonghui.fu@linux.intel.com>
> Date: Mon, 26 Jan 2015 10:13:21 +0800
> Subject: [PATCH] brcmfmac: avoid duplicated suspend/resume operation
>
> WiFi chip has 2 SDIO functions, and PM core will trigger
> twice suspend/resume operations for one WiFi chip to do
> the same things. This patch avoid this case.
>
> Acked-by: Arend van Spriel<arend@broadcom.com>
> Signed-off-by: Zhonghui Fu <zhonghui.fu@linux.intel.com>
This doesn't apply:
Applying: brcmfmac: avoid duplicated suspend/resume operation
Using index info to reconstruct a base tree...
Falling back to patching base and 3-way merge...
Auto-merging drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c
CONFLICT (content): Merge conflict in drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c
Failed to merge in the changes.
Patch failed at 0001 brcmfmac: avoid duplicated suspend/resume operation
BTW, when you resend a patch please use "[PATCH v2]" (or v3, v4...) in
the Subject field.
--
Kalle Valo
^ permalink raw reply
* Re: [PATCH V2 1/6] rtlwifi: Change logging level for key change
From: Kalle Valo @ 2015-02-03 13:01 UTC (permalink / raw)
To: Larry Finger; +Cc: linux-wireless, netdev
In-Reply-To: <54CBA794.90508@lwfinger.net>
Larry Finger <Larry.Finger@lwfinger.net> writes:
> On 01/26/2015 02:42 PM, Larry Finger wrote:
>> A recent change in key handling included logging of these changes for
>> all debug levels. Such key changes should only be logged when a high
>> level of debugging is enabled.
>>
>> Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
>> ---
>> drivers/net/wireless/rtlwifi/cam.c | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/drivers/net/wireless/rtlwifi/cam.c b/drivers/net/wireless/rtlwifi/cam.c
>> index 3ef870d..6e64792 100644
>> --- a/drivers/net/wireless/rtlwifi/cam.c
>> +++ b/drivers/net/wireless/rtlwifi/cam.c
>> @@ -406,7 +406,7 @@ u8 rtl_cam_get_free_entry(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
>> }
>> }
>> if (found) {
>> - RT_TRACE(rtlpriv, COMP_SEC, DBG_EMERG,
>> + RT_TRACE(rtlpriv, COMP_SEC, DBG_DMESG,
>> "key_index=%d,cam_bitmap: 0x%x entry_idx=%d\n",
>> key_index, rtlpriv->sec.cam_bitmap, entry_idx);
>> return entry_idx;
>>
>
> Kalle,
>
> Please include this patch even though the rest of this set should be
> dropped.
I tried to do that but it failed:
Applying: rtlwifi: Change logging level for key change
fatal: sha1 information is lacking or useless (drivers/net/wireless/rtlwifi/cam.c).
Repository lacks necessary blobs to fall back on 3-way merge.
Cannot fall back to three-way merge.
Patch failed at 0001 rtlwifi: Change logging level for key change
I was not even able to find that code from cam.c. Have I missed a patch?
> Once the wifi-BT communications problem is resolved, new versions of
> those will be presented.
Sounds good.
> I'm sorry that my commit message was not as informative as it could
> have been. I was presented with this material that I did not
> understand. One saving grace is that the RTL8812AE hardware is
> apparently rare - I certainly do not have any samples. I'm not sure of
> the value of a 1x1 implementation of 802.11ac, but that may be another
> example of my ignorance.
No worries. But stuff like this is usually best to send as RFC first and
ask people to analyse it before sending it officially.
--
Kalle Valo
^ 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