* [PATCH mlx5-next 13/15] net/mlx5: Add new fields to Port Type and Speed register
From: Saeed Mahameed @ 2019-02-13 6:55 UTC (permalink / raw)
To: Saeed Mahameed, Leon Romanovsky
Cc: netdev, linux-rdma, Aya Levin, Eran Ben Elisha
In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
Register Port Type and Speed (PTYS) introduces three new fields
extending the speed/protocols the can be reported and configured.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
include/linux/mlx5/mlx5_ifc.h | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 565046830559..5decffe565fb 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -7826,21 +7826,23 @@ struct mlx5_ifc_ptys_reg_bits {
u8 proto_mask[0x3];
u8 an_status[0x4];
- u8 reserved_at_24[0x3c];
+ u8 reserved_at_24[0x1c];
+
+ u8 ext_eth_proto_capability[0x20];
u8 eth_proto_capability[0x20];
u8 ib_link_width_capability[0x10];
u8 ib_proto_capability[0x10];
- u8 reserved_at_a0[0x20];
+ u8 ext_eth_proto_admin[0x20];
u8 eth_proto_admin[0x20];
u8 ib_link_width_admin[0x10];
u8 ib_proto_admin[0x10];
- u8 reserved_at_100[0x20];
+ u8 ext_eth_proto_oper[0x20];
u8 eth_proto_oper[0x20];
@@ -8289,7 +8291,9 @@ struct mlx5_ifc_mpegc_reg_bits {
struct mlx5_ifc_pcam_enhanced_features_bits {
u8 reserved_at_0[0x6d];
u8 rx_icrc_encapsulated_counter[0x1];
- u8 reserved_at_6e[0x8];
+ u8 reserved_at_6e[0x4];
+ u8 ptys_extended_ethernet[0x1];
+ u8 reserved_at_73[0x3];
u8 pfcc_mask[0x1];
u8 reserved_at_77[0x3];
u8 per_lane_error_counters[0x1];
--
2.20.1
^ permalink raw reply related
* [PATCH mlx5-next 12/15] net/mlx5: Refactor queries to speed fields in Port Type and Speed register
From: Saeed Mahameed @ 2019-02-13 6:55 UTC (permalink / raw)
To: Saeed Mahameed, Leon Romanovsky
Cc: netdev, linux-rdma, Aya Levin, Eran Ben Elisha
In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
This patch fascicles queries to speed related fields in Port Type and
Speed register (PTYS) into a single API. I addition, this patch
refactors functions which serves only Ethernet driver: remove the
protocol type as an input parameter, move code from 'core' directory
into 'en' directory and add 'eth' prefix to the function's name. The
patch also encapsulates functions that are not used outside the Ethernet
driver removes redundant include files.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/infiniband/hw/mlx5/main.c | 6 +-
.../net/ethernet/mellanox/mlx5/core/en/port.c | 75 +++++++++++--
.../net/ethernet/mellanox/mlx5/core/en/port.h | 12 ++
.../ethernet/mellanox/mlx5/core/en_ethtool.c | 23 ++--
.../net/ethernet/mellanox/mlx5/core/port.c | 106 ------------------
include/linux/mlx5/port.h | 11 --
6 files changed, 91 insertions(+), 142 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 87ce62e44898..efd08b41126c 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -393,6 +393,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
struct ib_port_attr *props)
{
struct mlx5_ib_dev *dev = to_mdev(device);
+ u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0};
struct mlx5_core_dev *mdev;
struct net_device *ndev, *upper;
enum ib_mtu ndev_ib_mtu;
@@ -416,10 +417,11 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
/* Possible bad flows are checked before filling out props so in case
* of an error it will still be zeroed out.
*/
- err = mlx5_query_port_eth_proto_oper(mdev, ð_prot_oper,
- mdev_port_num);
+ err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN,
+ mdev_port_num);
if (err)
goto out;
+ eth_prot_oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
props->active_width = IB_WIDTH_4X;
props->active_speed = IB_SPEED_QDR;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 4a37713023be..9a1c2b2f87d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -63,6 +63,67 @@ static const u32 mlx5e_link_speed[MLX5E_LINK_MODES_NUMBER] = {
[MLX5E_50GBASE_KR2] = 50000,
};
+int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port,
+ struct mlx5e_port_eth_proto *eproto)
+{
+ u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+ int err;
+
+ if (!eproto)
+ return -EINVAL;
+
+ err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, port);
+ if (err)
+ return err;
+
+ eproto->cap = MLX5_GET(ptys_reg, out, eth_proto_capability);
+ eproto->admin = MLX5_GET(ptys_reg, out, eth_proto_admin);
+ eproto->oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
+ return 0;
+}
+
+void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status,
+ u8 *an_disable_cap, u8 *an_disable_admin)
+{
+ u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+
+ *an_status = 0;
+ *an_disable_cap = 0;
+ *an_disable_admin = 0;
+
+ if (mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, 1))
+ return;
+
+ *an_status = MLX5_GET(ptys_reg, out, an_status);
+ *an_disable_cap = MLX5_GET(ptys_reg, out, an_disable_cap);
+ *an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
+}
+
+int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
+ u32 proto_admin)
+{
+ u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+ u32 in[MLX5_ST_SZ_DW(ptys_reg)];
+ u8 an_disable_admin;
+ u8 an_disable_cap;
+ u8 an_status;
+
+ mlx5_port_query_eth_autoneg(dev, &an_status, &an_disable_cap,
+ &an_disable_admin);
+ if (!an_disable_cap && an_disable)
+ return -EPERM;
+
+ memset(in, 0, sizeof(in));
+
+ MLX5_SET(ptys_reg, in, local_port, 1);
+ MLX5_SET(ptys_reg, in, an_disable_admin, an_disable);
+ MLX5_SET(ptys_reg, in, proto_mask, MLX5_PTYS_EN);
+ MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin);
+
+ return mlx5_core_access_reg(dev, in, sizeof(in), out,
+ sizeof(out), MLX5_REG_PTYS, 0, 1);
+}
+
u32 mlx5e_port_ptys2speed(u32 eth_proto_oper)
{
unsigned long temp = eth_proto_oper;
@@ -78,16 +139,14 @@ u32 mlx5e_port_ptys2speed(u32 eth_proto_oper)
int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
{
- u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {};
- u32 eth_proto_oper;
+ struct mlx5e_port_eth_proto eproto;
int err;
- err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, 1);
+ err = mlx5_port_query_eth_proto(mdev, 1, &eproto);
if (err)
return err;
- eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
- *speed = mlx5e_port_ptys2speed(eth_proto_oper);
+ *speed = mlx5e_port_ptys2speed(eproto.oper);
if (!(*speed))
err = -EINVAL;
@@ -96,17 +155,17 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
{
+ struct mlx5e_port_eth_proto eproto;
u32 max_speed = 0;
- u32 proto_cap;
int err;
int i;
- err = mlx5_query_port_proto_cap(mdev, &proto_cap, MLX5_PTYS_EN);
+ err = mlx5_port_query_eth_proto(mdev, 1, &eproto);
if (err)
return err;
for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i)
- if (proto_cap & MLX5E_PROT_MASK(i))
+ if (eproto.cap & MLX5E_PROT_MASK(i))
max_speed = max(max_speed, mlx5e_link_speed[i]);
*speed = max_speed;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
index cd2160b8c9bf..4bdab8be10af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
@@ -36,6 +36,18 @@
#include <linux/mlx5/driver.h>
#include "en.h"
+struct mlx5e_port_eth_proto {
+ u32 cap;
+ u32 admin;
+ u32 oper;
+};
+
+int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port,
+ struct mlx5e_port_eth_proto *eproto);
+void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status,
+ u8 *an_disable_cap, u8 *an_disable_admin);
+int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
+ u32 proto_admin);
u32 mlx5e_port_ptys2speed(u32 eth_proto_oper);
int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index c9df08133718..c29e141d72fb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -882,7 +882,7 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
const struct ethtool_link_ksettings *link_ksettings)
{
struct mlx5_core_dev *mdev = priv->mdev;
- u32 eth_proto_cap, eth_proto_admin;
+ struct mlx5e_port_eth_proto eproto;
bool an_changes = false;
u8 an_disable_admin;
u8 an_disable_cap;
@@ -898,14 +898,14 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
mlx5e_ethtool2ptys_adver_link(link_ksettings->link_modes.advertising) :
mlx5e_port_speed2linkmodes(speed);
- err = mlx5_query_port_proto_cap(mdev, ð_proto_cap, MLX5_PTYS_EN);
+ err = mlx5_port_query_eth_proto(mdev, 1, &eproto);
if (err) {
- netdev_err(priv->netdev, "%s: query port eth proto cap failed: %d\n",
+ netdev_err(priv->netdev, "%s: query port eth proto failed: %d\n",
__func__, err);
goto out;
}
- link_modes = link_modes & eth_proto_cap;
+ link_modes = link_modes & eproto.cap;
if (!link_modes) {
netdev_err(priv->netdev, "%s: Not supported link mode(s) requested",
__func__);
@@ -913,24 +913,17 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
goto out;
}
- err = mlx5_query_port_proto_admin(mdev, ð_proto_admin, MLX5_PTYS_EN);
- if (err) {
- netdev_err(priv->netdev, "%s: query port eth proto admin failed: %d\n",
- __func__, err);
- goto out;
- }
-
- mlx5_query_port_autoneg(mdev, MLX5_PTYS_EN, &an_status,
- &an_disable_cap, &an_disable_admin);
+ mlx5_port_query_eth_autoneg(mdev, &an_status, &an_disable_cap,
+ &an_disable_admin);
an_disable = link_ksettings->base.autoneg == AUTONEG_DISABLE;
an_changes = ((!an_disable && an_disable_admin) ||
(an_disable && !an_disable_admin));
- if (!an_changes && link_modes == eth_proto_admin)
+ if (!an_changes && link_modes == eproto.admin)
goto out;
- mlx5_set_port_ptys(mdev, an_disable, link_modes, MLX5_PTYS_EN);
+ mlx5_port_set_eth_ptys(mdev, an_disable, link_modes);
mlx5_toggle_port_link(mdev);
out:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 2b82f35f4c35..b81542820528 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -30,10 +30,7 @@
* SOFTWARE.
*/
-#include <linux/module.h>
-#include <linux/mlx5/driver.h>
#include <linux/mlx5/port.h>
-#include <linux/mlx5/cmd.h>
#include "mlx5_core.h"
int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in,
@@ -157,44 +154,6 @@ int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration)
sizeof(out), MLX5_REG_MLCR, 0, 1);
}
-int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev,
- u32 *proto_cap, int proto_mask)
-{
- u32 out[MLX5_ST_SZ_DW(ptys_reg)];
- int err;
-
- err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1);
- if (err)
- return err;
-
- if (proto_mask == MLX5_PTYS_EN)
- *proto_cap = MLX5_GET(ptys_reg, out, eth_proto_capability);
- else
- *proto_cap = MLX5_GET(ptys_reg, out, ib_proto_capability);
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(mlx5_query_port_proto_cap);
-
-int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev,
- u32 *proto_admin, int proto_mask)
-{
- u32 out[MLX5_ST_SZ_DW(ptys_reg)];
- int err;
-
- err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1);
- if (err)
- return err;
-
- if (proto_mask == MLX5_PTYS_EN)
- *proto_admin = MLX5_GET(ptys_reg, out, eth_proto_admin);
- else
- *proto_admin = MLX5_GET(ptys_reg, out, ib_proto_admin);
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(mlx5_query_port_proto_admin);
-
int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
u8 *link_width_oper, u8 local_port)
{
@@ -211,23 +170,6 @@ int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
}
EXPORT_SYMBOL_GPL(mlx5_query_port_link_width_oper);
-int mlx5_query_port_eth_proto_oper(struct mlx5_core_dev *dev,
- u32 *proto_oper, u8 local_port)
-{
- u32 out[MLX5_ST_SZ_DW(ptys_reg)];
- int err;
-
- err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN,
- local_port);
- if (err)
- return err;
-
- *proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
-
- return 0;
-}
-EXPORT_SYMBOL(mlx5_query_port_eth_proto_oper);
-
int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev,
u8 *proto_oper, u8 local_port)
{
@@ -245,35 +187,6 @@ int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev,
}
EXPORT_SYMBOL(mlx5_query_port_ib_proto_oper);
-int mlx5_set_port_ptys(struct mlx5_core_dev *dev, bool an_disable,
- u32 proto_admin, int proto_mask)
-{
- u32 out[MLX5_ST_SZ_DW(ptys_reg)];
- u32 in[MLX5_ST_SZ_DW(ptys_reg)];
- u8 an_disable_admin;
- u8 an_disable_cap;
- u8 an_status;
-
- mlx5_query_port_autoneg(dev, proto_mask, &an_status,
- &an_disable_cap, &an_disable_admin);
- if (!an_disable_cap && an_disable)
- return -EPERM;
-
- memset(in, 0, sizeof(in));
-
- MLX5_SET(ptys_reg, in, local_port, 1);
- MLX5_SET(ptys_reg, in, an_disable_admin, an_disable);
- MLX5_SET(ptys_reg, in, proto_mask, proto_mask);
- if (proto_mask == MLX5_PTYS_EN)
- MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin);
- else
- MLX5_SET(ptys_reg, in, ib_proto_admin, proto_admin);
-
- return mlx5_core_access_reg(dev, in, sizeof(in), out,
- sizeof(out), MLX5_REG_PTYS, 0, 1);
-}
-EXPORT_SYMBOL_GPL(mlx5_set_port_ptys);
-
/* This function should be used after setting a port register only */
void mlx5_toggle_port_link(struct mlx5_core_dev *dev)
{
@@ -606,25 +519,6 @@ int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx)
}
EXPORT_SYMBOL_GPL(mlx5_query_port_pfc);
-void mlx5_query_port_autoneg(struct mlx5_core_dev *dev, int proto_mask,
- u8 *an_status,
- u8 *an_disable_cap, u8 *an_disable_admin)
-{
- u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-
- *an_status = 0;
- *an_disable_cap = 0;
- *an_disable_admin = 0;
-
- if (mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1))
- return;
-
- *an_status = MLX5_GET(ptys_reg, out, an_status);
- *an_disable_cap = MLX5_GET(ptys_reg, out, an_disable_cap);
- *an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
-}
-EXPORT_SYMBOL_GPL(mlx5_query_port_autoneg);
-
int mlx5_max_tc(struct mlx5_core_dev *mdev)
{
u8 num_tc = MLX5_CAP_GEN(mdev, max_tc) ? : 8;
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index bf4bc01ffb0c..5be7eefa6d75 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -110,27 +110,16 @@ enum mlx5e_connector_type {
int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps);
int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys,
int ptys_size, int proto_mask, u8 local_port);
-int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev,
- u32 *proto_cap, int proto_mask);
-int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev,
- u32 *proto_admin, int proto_mask);
int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
u8 *link_width_oper, u8 local_port);
int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev,
u8 *proto_oper, u8 local_port);
-int mlx5_query_port_eth_proto_oper(struct mlx5_core_dev *dev,
- u32 *proto_oper, u8 local_port);
-int mlx5_set_port_ptys(struct mlx5_core_dev *dev, bool an_disable,
- u32 proto_admin, int proto_mask);
void mlx5_toggle_port_link(struct mlx5_core_dev *dev);
int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
enum mlx5_port_status status);
int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
enum mlx5_port_status *status);
int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration);
-void mlx5_query_port_autoneg(struct mlx5_core_dev *dev, int proto_mask,
- u8 *an_status,
- u8 *an_disable_cap, u8 *an_disable_admin);
int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port);
void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port);
--
2.20.1
^ permalink raw reply related
* [PATCH mlx5-next 14/15] net/mlx5: Add support to ext_* fields introduced in Port Type and Speed register
From: Saeed Mahameed @ 2019-02-13 6:55 UTC (permalink / raw)
To: Saeed Mahameed, Leon Romanovsky
Cc: netdev, linux-rdma, Aya Levin, Eran Ben Elisha
In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
This patch exposes new link modes (including 50Gbps per lane), and ext_*
fields which describes the new link modes in Port Type and Speed
register (PTYS).
Access functions, translation functions (speed <-> HW bits) and
link max speed function were modified.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/infiniband/hw/mlx5/main.c | 3 +-
.../net/ethernet/mellanox/mlx5/core/en/port.c | 85 ++++++++++++++-----
.../net/ethernet/mellanox/mlx5/core/en/port.h | 8 +-
.../ethernet/mellanox/mlx5/core/en_ethtool.c | 9 +-
include/linux/mlx5/port.h | 19 +++++
5 files changed, 94 insertions(+), 30 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index efd08b41126c..3677c00fa3bb 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -421,7 +421,8 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
mdev_port_num);
if (err)
goto out;
- eth_prot_oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
+ eth_prot_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, false,
+ eth_proto_oper);
props->active_width = IB_WIDTH_4X;
props->active_speed = IB_SPEED_QDR;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 9a1c2b2f87d8..122927f3a600 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -63,7 +63,31 @@ static const u32 mlx5e_link_speed[MLX5E_LINK_MODES_NUMBER] = {
[MLX5E_50GBASE_KR2] = 50000,
};
-int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port,
+static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = {
+ [MLX5E_SGMII_100M] = 100,
+ [MLX5E_1000BASE_X_SGMII] = 1000,
+ [MLX5E_5GBASE_R] = 5000,
+ [MLX5E_10GBASE_XFI_XAUI_1] = 10000,
+ [MLX5E_40GBASE_XLAUI_4_XLPPI_4] = 40000,
+ [MLX5E_25GAUI_1_25GBASE_CR_KR] = 25000,
+ [MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2] = 50000,
+ [MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR] = 50000,
+ [MLX5E_CAUI_4_100GBASE_CR4_KR4] = 100000,
+ [MLX5E_200GAUI_4_200GBASE_CR4_KR4] = 200000,
+ [MLX5E_400GAUI_8] = 400000,
+};
+
+static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev,
+ const u32 **arr, u32 *size)
+{
+ bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+
+ *size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) :
+ ARRAY_SIZE(mlx5e_link_speed);
+ *arr = ext ? mlx5e_ext_link_speed : mlx5e_link_speed;
+}
+
+int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
struct mlx5e_port_eth_proto *eproto)
{
u32 out[MLX5_ST_SZ_DW(ptys_reg)];
@@ -72,13 +96,17 @@ int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port,
if (!eproto)
return -EINVAL;
+ if (ext != MLX5_CAP_PCAM_FEATURE(dev, ptys_extended_ethernet))
+ return -EOPNOTSUPP;
+
err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, port);
if (err)
return err;
- eproto->cap = MLX5_GET(ptys_reg, out, eth_proto_capability);
- eproto->admin = MLX5_GET(ptys_reg, out, eth_proto_admin);
- eproto->oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
+ eproto->cap = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
+ eth_proto_capability);
+ eproto->admin = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_admin);
+ eproto->oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper);
return 0;
}
@@ -100,7 +128,7 @@ void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status,
}
int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
- u32 proto_admin)
+ u32 proto_admin, bool ext)
{
u32 out[MLX5_ST_SZ_DW(ptys_reg)];
u32 in[MLX5_ST_SZ_DW(ptys_reg)];
@@ -118,38 +146,46 @@ int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
MLX5_SET(ptys_reg, in, local_port, 1);
MLX5_SET(ptys_reg, in, an_disable_admin, an_disable);
MLX5_SET(ptys_reg, in, proto_mask, MLX5_PTYS_EN);
- MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin);
+ if (ext)
+ MLX5_SET(ptys_reg, in, ext_eth_proto_admin, proto_admin);
+ else
+ MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin);
return mlx5_core_access_reg(dev, in, sizeof(in), out,
sizeof(out), MLX5_REG_PTYS, 0, 1);
}
-u32 mlx5e_port_ptys2speed(u32 eth_proto_oper)
+u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper)
{
unsigned long temp = eth_proto_oper;
+ const u32 *table;
u32 speed = 0;
+ u32 max_size;
int i;
- i = find_first_bit(&temp, MLX5E_LINK_MODES_NUMBER);
- if (i < MLX5E_LINK_MODES_NUMBER)
- speed = mlx5e_link_speed[i];
-
+ mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+ i = find_first_bit(&temp, max_size);
+ if (i < max_size)
+ speed = table[i];
return speed;
}
int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
{
struct mlx5e_port_eth_proto eproto;
+ bool ext;
int err;
- err = mlx5_port_query_eth_proto(mdev, 1, &eproto);
+ ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+ err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
if (err)
- return err;
+ goto out;
- *speed = mlx5e_port_ptys2speed(eproto.oper);
+ *speed = mlx5e_port_ptys2speed(mdev, eproto.oper);
if (!(*speed))
err = -EINVAL;
+out:
return err;
}
@@ -157,31 +193,38 @@ int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
{
struct mlx5e_port_eth_proto eproto;
u32 max_speed = 0;
+ const u32 *table;
+ u32 max_size;
+ bool ext;
int err;
int i;
- err = mlx5_port_query_eth_proto(mdev, 1, &eproto);
+ ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+ err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
if (err)
return err;
- for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i)
+ mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+ for (i = 0; i < max_size; ++i)
if (eproto.cap & MLX5E_PROT_MASK(i))
- max_speed = max(max_speed, mlx5e_link_speed[i]);
+ max_speed = max(max_speed, table[i]);
*speed = max_speed;
return 0;
}
-u32 mlx5e_port_speed2linkmodes(u32 speed)
+u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed)
{
u32 link_modes = 0;
+ const u32 *table;
+ u32 max_size;
int i;
- for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) {
- if (mlx5e_link_speed[i] == speed)
+ mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+ for (i = 0; i < max_size; ++i) {
+ if (table[i] == speed)
link_modes |= MLX5E_PROT_MASK(i);
}
-
return link_modes;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
index 4bdab8be10af..70f536ec51c4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
@@ -42,16 +42,16 @@ struct mlx5e_port_eth_proto {
u32 oper;
};
-int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port,
+int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
struct mlx5e_port_eth_proto *eproto);
void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status,
u8 *an_disable_cap, u8 *an_disable_admin);
int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
- u32 proto_admin);
-u32 mlx5e_port_ptys2speed(u32 eth_proto_oper);
+ u32 proto_admin, bool ext);
+u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper);
int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
-u32 mlx5e_port_speed2linkmodes(u32 speed);
+u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed);
int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out);
int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index c29e141d72fb..8343cf7d292c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -695,13 +695,14 @@ static void get_speed_duplex(struct net_device *netdev,
u32 eth_proto_oper,
struct ethtool_link_ksettings *link_ksettings)
{
+ struct mlx5e_priv *priv = netdev_priv(netdev);
u32 speed = SPEED_UNKNOWN;
u8 duplex = DUPLEX_UNKNOWN;
if (!netif_carrier_ok(netdev))
goto out;
- speed = mlx5e_port_ptys2speed(eth_proto_oper);
+ speed = mlx5e_port_ptys2speed(priv->mdev, eth_proto_oper);
if (!speed) {
speed = SPEED_UNKNOWN;
goto out;
@@ -896,9 +897,9 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
link_modes = link_ksettings->base.autoneg == AUTONEG_ENABLE ?
mlx5e_ethtool2ptys_adver_link(link_ksettings->link_modes.advertising) :
- mlx5e_port_speed2linkmodes(speed);
+ mlx5e_port_speed2linkmodes(mdev, speed);
- err = mlx5_port_query_eth_proto(mdev, 1, &eproto);
+ err = mlx5_port_query_eth_proto(mdev, 1, false, &eproto);
if (err) {
netdev_err(priv->netdev, "%s: query port eth proto failed: %d\n",
__func__, err);
@@ -923,7 +924,7 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
if (!an_changes && link_modes == eproto.admin)
goto out;
- mlx5_port_set_eth_ptys(mdev, an_disable, link_modes);
+ mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, false);
mlx5_toggle_port_link(mdev);
out:
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index 5be7eefa6d75..814fa194663b 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -92,6 +92,22 @@ enum mlx5e_link_mode {
MLX5E_LINK_MODES_NUMBER,
};
+enum mlx5e_ext_link_mode {
+ MLX5E_SGMII_100M = 0,
+ MLX5E_1000BASE_X_SGMII = 1,
+ MLX5E_5GBASE_R = 3,
+ MLX5E_10GBASE_XFI_XAUI_1 = 4,
+ MLX5E_40GBASE_XLAUI_4_XLPPI_4 = 5,
+ MLX5E_25GAUI_1_25GBASE_CR_KR = 6,
+ MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2 = 7,
+ MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR = 8,
+ MLX5E_CAUI_4_100GBASE_CR4_KR4 = 9,
+ MLX5E_100GAUI_2_100GBASE_CR2_KR2 = 10,
+ MLX5E_200GAUI_4_200GBASE_CR4_KR4 = 12,
+ MLX5E_400GAUI_8 = 15,
+ MLX5E_EXT_LINK_MODES_NUMBER,
+};
+
enum mlx5e_connector_type {
MLX5E_PORT_UNKNOWN = 0,
MLX5E_PORT_NONE = 1,
@@ -106,6 +122,9 @@ enum mlx5e_connector_type {
};
#define MLX5E_PROT_MASK(link_mode) (1 << link_mode)
+#define MLX5_GET_ETH_PROTO(reg, out, ext, field) \
+ (ext ? MLX5_GET(reg, out, ext_##field) : \
+ MLX5_GET(reg, out, field))
int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps);
int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys,
--
2.20.1
^ permalink raw reply related
* [PATCH mlx5-next 15/15] IB/mlx5: Add support for 50Gbps per lane link modes
From: Saeed Mahameed @ 2019-02-13 6:55 UTC (permalink / raw)
To: Saeed Mahameed, Leon Romanovsky; +Cc: netdev, linux-rdma, Aya Levin
In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
Driver now supports new link modes: 50Gbps per lane support for
50G/100G/200G. This patch reads the correct field (legacy vs. extended)
based on a FW indication bit, and adds a translation function (link
modes to IB width and speed) to the new link modes.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/infiniband/hw/mlx5/main.c | 66 ++++++++++++++++++++++++++++---
1 file changed, 61 insertions(+), 5 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 3677c00fa3bb..581ae11e2fc9 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -331,8 +331,8 @@ void mlx5_ib_put_native_port_mdev(struct mlx5_ib_dev *ibdev, u8 port_num)
spin_unlock(&port->mp.mpi_lock);
}
-static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed,
- u8 *active_width)
+static int translate_eth_legacy_proto_oper(u32 eth_proto_oper, u8 *active_speed,
+ u8 *active_width)
{
switch (eth_proto_oper) {
case MLX5E_PROT_MASK(MLX5E_1000BASE_CX_SGMII):
@@ -389,6 +389,61 @@ static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed,
return 0;
}
+static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u8 *active_speed,
+ u8 *active_width)
+{
+ switch (eth_proto_oper) {
+ case MLX5E_PROT_MASK(MLX5E_SGMII_100M):
+ case MLX5E_PROT_MASK(MLX5E_1000BASE_X_SGMII):
+ *active_width = IB_WIDTH_1X;
+ *active_speed = IB_SPEED_SDR;
+ break;
+ case MLX5E_PROT_MASK(MLX5E_5GBASE_R):
+ *active_width = IB_WIDTH_1X;
+ *active_speed = IB_SPEED_DDR;
+ break;
+ case MLX5E_PROT_MASK(MLX5E_10GBASE_XFI_XAUI_1):
+ *active_width = IB_WIDTH_1X;
+ *active_speed = IB_SPEED_QDR;
+ break;
+ case MLX5E_PROT_MASK(MLX5E_40GBASE_XLAUI_4_XLPPI_4):
+ *active_width = IB_WIDTH_4X;
+ *active_speed = IB_SPEED_QDR;
+ break;
+ case MLX5E_PROT_MASK(MLX5E_25GAUI_1_25GBASE_CR_KR):
+ *active_width = IB_WIDTH_1X;
+ *active_speed = IB_SPEED_EDR;
+ break;
+ case MLX5E_PROT_MASK(MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2):
+ case MLX5E_PROT_MASK(MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR):
+ *active_width = IB_WIDTH_1X;
+ *active_speed = IB_SPEED_HDR;
+ break;
+ case MLX5E_PROT_MASK(MLX5E_100GAUI_2_100GBASE_CR2_KR2):
+ *active_width = IB_WIDTH_2X;
+ *active_speed = IB_SPEED_HDR;
+ break;
+ case MLX5E_PROT_MASK(MLX5E_200GAUI_4_200GBASE_CR4_KR4):
+ *active_width = IB_WIDTH_4X;
+ *active_speed = IB_SPEED_HDR;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed,
+ u8 *active_width, bool ext)
+{
+ return ext ?
+ translate_eth_ext_proto_oper(eth_proto_oper, active_speed,
+ active_width) :
+ translate_eth_legacy_proto_oper(eth_proto_oper, active_speed,
+ active_width);
+}
+
static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
struct ib_port_attr *props)
{
@@ -401,6 +456,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
u16 qkey_viol_cntr;
u32 eth_prot_oper;
u8 mdev_port_num;
+ bool ext;
int err;
mdev = mlx5_ib_get_native_port_mdev(dev, port_num, &mdev_port_num);
@@ -421,14 +477,14 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
mdev_port_num);
if (err)
goto out;
- eth_prot_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, false,
- eth_proto_oper);
+ ext = MLX5_CAP_PCAM_FEATURE(dev->mdev, ptys_extended_ethernet);
+ eth_prot_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper);
props->active_width = IB_WIDTH_4X;
props->active_speed = IB_SPEED_QDR;
translate_eth_proto_oper(eth_prot_oper, &props->active_speed,
- &props->active_width);
+ &props->active_width, ext);
props->port_cap_flags |= IB_PORT_CM_SUP;
props->ip_gids = true;
--
2.20.1
^ permalink raw reply related
* Re: [PATCH] net: phy: at803x: disable delay only for RGMII mode
From: Peter Ujfalusi @ 2019-02-13 7:02 UTC (permalink / raw)
To: Vinod Koul, David S Miller
Cc: linux-arm-msm, Bjorn Andersson, netdev, Niklas Cassel,
Andrew Lunn, Florian Fainelli, Nori, Sekhar, Marc Gonzalez
In-Reply-To: <20190212141922.12849-1-vkoul@kernel.org>
Hi Vinod,
On 12/02/2019 16.19, Vinod Koul wrote:
> Per "Documentation/devicetree/bindings/net/ethernet.txt" RGMII mode
> should not have delay in PHY whereas RGMII_ID and RGMII_RXID/RGMII_TXID
> can have delay in phy.
>
> So disable the delay only for RGMII mode and disable for other modes
s/disable for other modes/enable for other modes
Works fine on am335x-evmsk:
Tested-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
and few comment
> Fixes: cd28d1d6e52e: ("net: phy: at803x: Disable phy delay for RGMII mode")
> Reported-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
> Signed-off-by: Vinod Koul <vkoul@kernel.org>
> ---
> drivers/net/phy/at803x.c | 33 ++++++++++++++++++++++++++-------
> 1 file changed, 26 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
> index 8ff12938ab47..7b54b54e3316 100644
> --- a/drivers/net/phy/at803x.c
> +++ b/drivers/net/phy/at803x.c
> @@ -110,6 +110,18 @@ static int at803x_debug_reg_mask(struct phy_device *phydev, u16 reg,
> return phy_write(phydev, AT803X_DEBUG_DATA, val);
> }
>
> +static inline int at803x_enable_rx_delay(struct phy_device *phydev)
> +{
> + return at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_0, 0,
> + AT803X_DEBUG_RX_CLK_DLY_EN);
> +}
static inline int at803x_select_rx_delay(struct phy_device *phydev,
bool enable)
{
}
> +
> +static inline int at803x_enable_tx_delay(struct phy_device *phydev)
> +{
> + return at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_5, 0,
> + AT803X_DEBUG_TX_CLK_DLY_EN);
> +}
static inline int at803x_select_tx_delay(struct phy_device *phydev,
bool enable)
{
}
perhaps?
> +
> static inline int at803x_disable_rx_delay(struct phy_device *phydev)
> {
> return at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_0,
> @@ -255,18 +267,25 @@ static int at803x_config_init(struct phy_device *phydev)
> if (ret < 0)
> return ret;
>
> - if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID ||
> - phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
> - phydev->interface == PHY_INTERFACE_MODE_RGMII) {
> + if (phydev->interface == PHY_INTERFACE_MODE_RGMII) {
> ret = at803x_disable_rx_delay(phydev);
> if (ret < 0)
> return ret;
> + ret = at803x_disable_tx_delay(phydev);
> + if (ret < 0)
> + return ret;
is it a possibility to have PHY_INTERFACE_MODE_RGMII and other RGMII_ID
|| RGMII_TXID || RGMII_RXID set at the same time?
if not you can just return from here, no need to check for other RGMII
modes?
> + };
> +
> + if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
> + phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) {
> + ret = at803x_enable_rx_delay(phydev);
> + if (ret < 0)
> + return ret;
> }
>
> - if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID ||
> - phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
> - phydev->interface == PHY_INTERFACE_MODE_RGMII) {
> - ret = at803x_disable_tx_delay(phydev);
> + if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
> + phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) {
> + ret = at803x_enable_tx_delay(phydev);
> if (ret < 0)
> return ret;
> }
>
- Péter
Texas Instruments Finland Oy, Porkkalankatu 22, 00180 Helsinki.
Y-tunnus/Business ID: 0615521-4. Kotipaikka/Domicile: Helsinki
^ permalink raw reply
* Re: [PATCH] rpc: properly check debugfs dentry before using it
From: gregkh @ 2019-02-13 7:24 UTC (permalink / raw)
To: Schumaker, Anna
Cc: bfields@fieldses.org, trond.myklebust@hammerspace.com,
jlayton@kernel.org, netdev@vger.kernel.org,
linux-nfs@vger.kernel.org, dhowells@redhat.com
In-Reply-To: <2a029733e094460e2f57bb2d3fc28e7e1757b83e.camel@netapp.com>
On Tue, Feb 12, 2019 at 08:52:53PM +0000, Schumaker, Anna wrote:
> On Tue, 2019-02-12 at 19:27 +0100, Greg Kroah-Hartman wrote:
> > debugfs can now report an error code if something went wrong instead of
> > just NULL. So if the return value is to be used as a "real" dentry, it
> > needs to be checked if it is an error before dereferencing it.
> >
> > This is now happening because of ff9fb72bc077 ("debugfs: return error
> > values, not NULL"), but why debugfs files are not being created properly
> > is an older issue, probably one that has always been there and should
> > probably be looked at...
> >
> > Cc: "J. Bruce Fields" <bfields@fieldses.org>
> > Cc: Jeff Layton <jlayton@kernel.org>
> > Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
> > Cc: Anna Schumaker <anna.schumaker@netapp.com>
> > Cc: linux-nfs@vger.kernel.org
> > Cc: netdev@vger.kernel.org
> > Reported-by: David Howells <dhowells@redhat.com>
> > Tested-by: David Howells <dhowells@redhat.com>
> > Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
> >
> > ---
> > net/sunrpc/debugfs.c | 2 +-
> > 1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > I can take this through my tree if people don't object, or it can go
> > through the NFS tree. It does need to get merged before 5.0-final
> > though.
>
> I'm planning another bugfixes pull for 5.0, so I can take this patch and send it
> with the others this week.
Wonderful, thanks for doing this, and sorry for the regression.
greg k-h
^ permalink raw reply
* Re: linux-next: Tree for Feb 11 (wireless/80211)
From: Johannes Berg @ 2019-02-13 8:04 UTC (permalink / raw)
To: Randy Dunlap, Stephen Rothwell, Linux Next Mailing List
Cc: Linux Kernel Mailing List, linux-wireless, netdev@vger.kernel.org
In-Reply-To: <80b32344-08c9-0d8b-fdae-1db9b1003f60@infradead.org>
Thanks for the heads-up, Randy. We'd seen separate build bot reports on
this as well.
> ERROR: "__umoddi3" [net/wireless/cfg80211.ko] undefined!
> ERROR: "__umoddi3" [net/mac80211/mac80211.ko] undefined!
Should be fixed as of yesterday, let me know if it reappears.
johannes
^ permalink raw reply
* [PATCH net] net: dsa: bcm_sf2: potential array overflow in bcm_sf2_sw_suspend()
From: Dan Carpenter @ 2019-02-13 8:23 UTC (permalink / raw)
To: Andrew Lunn, Florian Fainelli
Cc: Vivien Didelot, David S. Miller, netdev, kernel-janitors
The value of ->num_ports comes from bcm_sf2_sw_probe() and it is less
than or equal to DSA_MAX_PORTS. The ds->ports[] array is used inside
the dsa_is_user_port() and dsa_is_cpu_port() functions. The ds->ports[]
array is allocated in dsa_switch_alloc() and it has ds->num_ports
elements so this leads to a static checker warning about a potential out
of bounds read.
Fixes: 8cfa94984c9c ("net: dsa: bcm_sf2: add suspend/resume callbacks")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
---
drivers/net/dsa/bcm_sf2.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 5193da67dcdc..98696a88fa1c 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -690,7 +690,7 @@ static int bcm_sf2_sw_suspend(struct dsa_switch *ds)
* port, the other ones have already been disabled during
* bcm_sf2_sw_setup
*/
- for (port = 0; port < DSA_MAX_PORTS; port++) {
+ for (port = 0; port < ds->num_ports; port++) {
if (dsa_is_user_port(ds, port) || dsa_is_cpu_port(ds, port))
bcm_sf2_port_disable(ds, port, NULL);
}
--
2.17.1
^ permalink raw reply related
* Re: KASAN: use-after-free Read in sctp_outq_tail
From: Dmitry Vyukov @ 2019-02-13 8:27 UTC (permalink / raw)
To: Marcelo Ricardo Leitner
Cc: syzbot, David Miller, LKML, linux-sctp, netdev, Neil Horman,
syzkaller-bugs, Vladislav Yasevich
In-Reply-To: <20190212191920.GI10665@localhost.localdomain>
On Tue, Feb 12, 2019 at 8:19 PM Marcelo Ricardo Leitner
<marcelo.leitner@gmail.com> wrote:
>
> On Tue, Feb 12, 2019 at 11:04:27AM -0800, syzbot wrote:
> > Hello,
> >
> > syzbot found the following crash on:
> >
> > HEAD commit: d4104460aec1 Add linux-next specific files for 20190211
> > git tree: linux-next
>
> I can't find this commit. How can I know for sure which commits are in?
> Recent patches are involved with this code, but not sure what was
> included on the test.
Hi Marcelo,
linux-next is weird. Not sure why a so recent commit is not in
linux-next, maybe one needs to fetch tags or something. Fetching
git://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next-history.git
helped me to get this commit:
$ git show d4104460aec1
commit d4104460aec152e23cf80ab1f950f414bf94f4ea (HEAD, tag: next-20190211)
Author: Stephen Rothwell
Date: Mon Feb 11 18:37:26 2019 +1100
Add linux-next specific files for 20190211
^ permalink raw reply
* Re: KASAN: use-after-free Read in sctp_outq_tail
From: Dmitry Vyukov @ 2019-02-13 8:29 UTC (permalink / raw)
To: Xin Long
Cc: syzbot, davem, LKML, linux-sctp, Marcelo Ricardo Leitner,
network dev, Neil Horman, syzkaller-bugs, Vlad Yasevich
In-Reply-To: <CADvbK_dndFMxyUZk=k8qEy9=PNbLc81F++2L0fbdtUdbupq4Xg@mail.gmail.com>
On Wed, Feb 13, 2019 at 5:36 AM Xin Long <lucien.xin@gmail.com> wrote:
>
> On Wed, Feb 13, 2019 at 4:00 AM syzbot
> <syzbot+7823fa3f3e2d69341ea8@syzkaller.appspotmail.com> wrote:
> >
> > Hello,
> >
> > syzbot found the following crash on:
> >
> > HEAD commit: d4104460aec1 Add linux-next specific files for 20190211
> > git tree: linux-next
> > console output: https://syzkaller.appspot.com/x/log.txt?x=14140124c00000
> > kernel config: https://syzkaller.appspot.com/x/.config?x=c8a112d3b0d6719b
> > dashboard link: https://syzkaller.appspot.com/bug?extid=7823fa3f3e2d69341ea8
> > compiler: gcc (GCC) 9.0.0 20181231 (experimental)
> >
> > Unfortunately, I don't have any reproducer for this crash yet.
> >
> > IMPORTANT: if you fix the bug, please add the following tag to the commit:
> > Reported-by: syzbot+7823fa3f3e2d69341ea8@syzkaller.appspotmail.com
> >
> > ==================================================================
> > BUG: KASAN: use-after-free in list_add_tail include/linux/list.h:93 [inline]
> > BUG: KASAN: use-after-free in sctp_outq_tail_data net/sctp/outqueue.c:105
> > [inline]
> > BUG: KASAN: use-after-free in sctp_outq_tail+0x816/0x930
> > net/sctp/outqueue.c:313
> > Read of size 8 at addr ffff88807b19a7b8 by task syz-executor.0/30745
> I think https://patchwork.ozlabs.org/patch/1040500/ will fix this.
Let's mark it then to not return later:
#syz fix:
sctp: set stream ext to NULL after freeing it in sctp_stream_outq_migrate
> > CPU: 1 PID: 30745 Comm: syz-executor.0 Not tainted 5.0.0-rc5-next-20190211
> > #32
> > Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
> > Google 01/01/2011
> > Call Trace:
> > __dump_stack lib/dump_stack.c:77 [inline]
> > dump_stack+0x172/0x1f0 lib/dump_stack.c:113
> > print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187
> > kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317
> > __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:132
> > list_add_tail include/linux/list.h:93 [inline]
> > sctp_outq_tail_data net/sctp/outqueue.c:105 [inline]
> > sctp_outq_tail+0x816/0x930 net/sctp/outqueue.c:313
> > sctp_cmd_send_msg net/sctp/sm_sideeffect.c:1109 [inline]
> > sctp_cmd_interpreter net/sctp/sm_sideeffect.c:1784 [inline]
> > sctp_side_effects net/sctp/sm_sideeffect.c:1220 [inline]
> > sctp_do_sm+0x68e/0x5380 net/sctp/sm_sideeffect.c:1191
> > sctp_primitive_SEND+0xa0/0xd0 net/sctp/primitive.c:178
> > sctp_sendmsg_to_asoc+0xa63/0x17b0 net/sctp/socket.c:1955
> > sctp_sendmsg+0x10a9/0x17e0 net/sctp/socket.c:2113
> > inet_sendmsg+0x147/0x5d0 net/ipv4/af_inet.c:798
> > sock_sendmsg_nosec net/socket.c:621 [inline]
> > sock_sendmsg+0xdd/0x130 net/socket.c:631
> > ___sys_sendmsg+0x806/0x930 net/socket.c:2136
> > __sys_sendmsg+0x105/0x1d0 net/socket.c:2174
> > __do_sys_sendmsg net/socket.c:2183 [inline]
> > __se_sys_sendmsg net/socket.c:2181 [inline]
> > __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2181
> > do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
> > entry_SYSCALL_64_after_hwframe+0x49/0xbe
> > RIP: 0033:0x457e39
> > Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7
> > 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff
> > ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
> > RSP: 002b:00007fa9b8630c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
> > RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457e39
> > RDX: 0000000000000000 RSI: 0000000020000140 RDI: 0000000000000003
> > RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000
> > R10: 0000000000000000 R11: 0000000000000246 R12: 00007fa9b86316d4
> > R13: 00000000004c4e2b R14: 00000000004d8ab8 R15: 00000000ffffffff
> >
> > Allocated by task 30745:
> > save_stack+0x45/0xd0 mm/kasan/common.c:75
> > set_track mm/kasan/common.c:87 [inline]
> > __kasan_kmalloc mm/kasan/common.c:498 [inline]
> > __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:471
> > kasan_kmalloc+0x9/0x10 mm/kasan/common.c:506
> > kmem_cache_alloc_trace+0x151/0x760 mm/slab.c:3615
> > kmalloc include/linux/slab.h:548 [inline]
> > kzalloc include/linux/slab.h:743 [inline]
> > sctp_stream_init_ext+0x51/0x110 net/sctp/stream.c:172
> > sctp_sendmsg_to_asoc+0x1273/0x17b0 net/sctp/socket.c:1896
> > sctp_sendmsg+0x10a9/0x17e0 net/sctp/socket.c:2113
> > inet_sendmsg+0x147/0x5d0 net/ipv4/af_inet.c:798
> > sock_sendmsg_nosec net/socket.c:621 [inline]
> > sock_sendmsg+0xdd/0x130 net/socket.c:631
> > ___sys_sendmsg+0x806/0x930 net/socket.c:2136
> > __sys_sendmsg+0x105/0x1d0 net/socket.c:2174
> > __do_sys_sendmsg net/socket.c:2183 [inline]
> > __se_sys_sendmsg net/socket.c:2181 [inline]
> > __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2181
> > do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
> > entry_SYSCALL_64_after_hwframe+0x49/0xbe
> >
> > Freed by task 30745:
> > save_stack+0x45/0xd0 mm/kasan/common.c:75
> > set_track mm/kasan/common.c:87 [inline]
> > __kasan_slab_free+0x102/0x150 mm/kasan/common.c:460
> > kasan_slab_free+0xe/0x10 mm/kasan/common.c:468
> > __cache_free mm/slab.c:3491 [inline]
> > kfree+0xcf/0x230 mm/slab.c:3816
> > sctp_stream_outq_migrate+0x3e6/0x540 net/sctp/stream.c:88
> > sctp_stream_init+0xbc/0x410 net/sctp/stream.c:139
> > sctp_process_init+0x21c3/0x2b20 net/sctp/sm_make_chunk.c:2466
> > sctp_cmd_process_init net/sctp/sm_sideeffect.c:682 [inline]
> > sctp_cmd_interpreter net/sctp/sm_sideeffect.c:1410 [inline]
> > sctp_side_effects net/sctp/sm_sideeffect.c:1220 [inline]
> > sctp_do_sm+0x3145/0x5380 net/sctp/sm_sideeffect.c:1191
> > sctp_assoc_bh_rcv+0x343/0x660 net/sctp/associola.c:1074
> > sctp_inq_push+0x1ea/0x290 net/sctp/inqueue.c:95
> > sctp_backlog_rcv+0x196/0xbe0 net/sctp/input.c:354
> > sk_backlog_rcv include/net/sock.h:937 [inline]
> > __release_sock+0x12e/0x3a0 net/core/sock.c:2379
> > release_sock+0x59/0x1c0 net/core/sock.c:2895
> > sctp_wait_for_connect+0x316/0x540 net/sctp/socket.c:8998
> > sctp_sendmsg_to_asoc+0x13e3/0x17b0 net/sctp/socket.c:1967
> > sctp_sendmsg+0x10a9/0x17e0 net/sctp/socket.c:2113
> > inet_sendmsg+0x147/0x5d0 net/ipv4/af_inet.c:798
> > sock_sendmsg_nosec net/socket.c:621 [inline]
> > sock_sendmsg+0xdd/0x130 net/socket.c:631
> > ___sys_sendmsg+0x806/0x930 net/socket.c:2136
> > __sys_sendmsg+0x105/0x1d0 net/socket.c:2174
> > __do_sys_sendmsg net/socket.c:2183 [inline]
> > __se_sys_sendmsg net/socket.c:2181 [inline]
> > __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2181
> > do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
> > entry_SYSCALL_64_after_hwframe+0x49/0xbe
> >
> > The buggy address belongs to the object at ffff88807b19a780
> > which belongs to the cache kmalloc-96 of size 96
> > The buggy address is located 56 bytes inside of
> > 96-byte region [ffff88807b19a780, ffff88807b19a7e0)
> > The buggy address belongs to the page:
> > page:ffffea0001ec6680 count:1 mapcount:0 mapping:ffff88812c3f04c0
> > index:0xffff88807b19a800
> > flags: 0x1fffc0000000200(slab)
> > raw: 01fffc0000000200 ffffea000262acc8 ffffea0001448348 ffff88812c3f04c0
> > raw: ffff88807b19a800 ffff88807b19a000 000000010000001d 0000000000000000
> > page dumped because: kasan: bad access detected
> >
> > Memory state around the buggy address:
> > ffff88807b19a680: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
> > ffff88807b19a700: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
> > > ffff88807b19a780: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
> > ^
> > ffff88807b19a800: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
> > ffff88807b19a880: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
> > ==================================================================
> >
> >
> > ---
> > This bug is generated by a bot. It may contain errors.
> > See https://goo.gl/tpsmEJ for more information about syzbot.
> > syzbot engineers can be reached at syzkaller@googlegroups.com.
> >
> > syzbot will keep track of this bug report. See:
> > https://goo.gl/tpsmEJ#bug-status-tracking for how to communicate with
> > syzbot.
>
> --
> You received this message because you are subscribed to the Google Groups "syzkaller-bugs" group.
> To unsubscribe from this group and stop receiving emails from it, send an email to syzkaller-bugs+unsubscribe@googlegroups.com.
> To view this discussion on the web visit https://groups.google.com/d/msgid/syzkaller-bugs/CADvbK_dndFMxyUZk%3Dk8qEy9%3DPNbLc81F%2B%2B2L0fbdtUdbupq4Xg%40mail.gmail.com.
> For more options, visit https://groups.google.com/d/optout.
^ permalink raw reply
* Re: [PATCH iproute2 net-next v2 3/4] ss: Buffer raw fields first, then render them as a table
From: Stefano Brivio @ 2019-02-13 8:37 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Stephen Hemminger, netdev, Sabrina Dubroca
In-Reply-To: <82f1bc98-df6d-2b0a-17e5-fa057563284e@gmail.com>
On Tue, 12 Feb 2019 16:42:04 -0800
Eric Dumazet <eric.dumazet@gmail.com> wrote:
> I do not get it.
>
> "ss -emoi " uses almost 1KB per socket.
>
> 10,000,000 sockets -> we need about 10GB of memory ???
>
> This is a serious regression.
I guess this is rather subjective: the worst case I considered back then
was the output of 'ss -tei0' (less than 500 bytes) for one million
sockets, which gives 500M of memory, which should in turn be fine on a
machine handling one million sockets.
Now, if 'ss -emoi' on 10 million sockets is an actual use case (out of
curiosity: how are you going to process that output? Would JSON help?),
I see two easy options to solve this:
1. flush the output every time we reach a given buffer size (1M
perhaps). This might make the resulting blocks slightly unaligned,
with occasional loss of readability on lines occurring every 1k to
10k sockets approximately, even though after 1k sockets column sizes
won't change much (it looks anyway better than the original), and I
don't expect anybody to actually scroll that output
2. add a switch for unbuffered output, but then you need to remember to
pass it manually, and the whole output would be as bad as the
original in case you need the switch.
I'd rather go with 1., it's easy to implement (we already have partial
flushing with '--events') and it looks like a good compromise on
usability. Thoughts?
--
Stefano
^ permalink raw reply
* Re: [RFC, PATCH] net: page_pool: Don't use page->private to store dma_addr_t
From: Tariq Toukan @ 2019-02-13 8:46 UTC (permalink / raw)
To: Alexander Duyck, Eric Dumazet
Cc: Tariq Toukan, Ilias Apalodimas, Matthew Wilcox, brouer@redhat.com,
David Miller, toke@redhat.com, netdev@vger.kernel.org,
mgorman@techsingularity.net, linux-mm@kvack.org
In-Reply-To: <CAKgT0UfG08aYoN=zO_aVyx+OgNPmN9pVkBNeZMPTF2KL7XqoBQ@mail.gmail.com>
On 2/12/2019 8:13 PM, Alexander Duyck wrote:
> On Tue, Feb 12, 2019 at 7:16 AM Eric Dumazet <eric.dumazet@gmail.com> wrote:
>>
>>
>>
>> On 02/12/2019 04:39 AM, Tariq Toukan wrote:
>>>
>>>
>>> On 2/11/2019 7:14 PM, Eric Dumazet wrote:
>>>>
>>>>
>>>> On 02/11/2019 12:53 AM, Tariq Toukan wrote:
>>>>>
>>>>
>>>>> Hi,
>>>>>
>>>>> It's great to use the struct page to store its dma mapping, but I am
>>>>> worried about extensibility.
>>>>> page_pool is evolving, and it would need several more per-page fields.
>>>>> One of them would be pageref_bias, a planned optimization to reduce the
>>>>> number of the costly atomic pageref operations (and replace existing
>>>>> code in several drivers).
>>>>>
>>>>
>>>> But the point about pageref_bias is to place it in a different cache line than "struct page"
>>>>
>>>> The major cost is having a cache line bouncing between producer and consumer.
>>>>
>>>
>>> pageref_bias is meant to be dirtied only by the page requester, i.e. the
>>> NIC driver / page_pool.
>>> All other components (basically, SKB release flow / put_page) should
>>> continue working with the atomic page_refcnt, and not dirty the
>>> pageref_bias.
>>
>> This is exactly my point.
>>
>> You suggested to put pageref_bias in struct page, which breaks this completely.
>>
>> pageref_bias is better kept in a driver structure, with appropriate prefetching
>> since most NIC use a ring buffer for their queues.
>>
>> The dma address _can_ be put in the struct page, since the driver does not dirty it
>> and does not even read it when page can be recycled.
>
> Instead of maintaining the pageref_bias in the page itself it could be
> maintained in some sort of separate structure. You could just maintain
> a pointer to a slot in an array somewhere. Then you can still access
> it if needed, the pointer would be static for as long as it is in the
> page pool, and you could invalidate the pointer prior to removing the
> bias from the page.
>
Hi Alex,
That's right.
But as I describe in my other reply yesterday, there is a more serious
issue with combining the pageref_bias feature with the new page_pool
capability for elevated refcount pages.
It won't work on top, and that's fine, as the idea of the new elevated
refcount queue capability is more promising and important, and it wins here.
Regards,
Tariq
^ permalink raw reply
* Re: [RFC, PATCH] net: page_pool: Don't use page->private to store dma_addr_t
From: Tariq Toukan @ 2019-02-13 8:50 UTC (permalink / raw)
To: Ilias Apalodimas, Alexander Duyck
Cc: Eric Dumazet, Tariq Toukan, Matthew Wilcox, brouer@redhat.com,
David Miller, toke@redhat.com, netdev@vger.kernel.org,
mgorman@techsingularity.net, linux-mm@kvack.org
In-Reply-To: <20190212182031.GA23057@apalos>
On 2/12/2019 8:20 PM, Ilias Apalodimas wrote:
> Hi Alexander,
>
> On Tue, Feb 12, 2019 at 10:13:30AM -0800, Alexander Duyck wrote:
>> On Tue, Feb 12, 2019 at 7:16 AM Eric Dumazet <eric.dumazet@gmail.com> wrote:
>>>
>>>
>>>
>>> On 02/12/2019 04:39 AM, Tariq Toukan wrote:
>>>>
>>>>
>>>> On 2/11/2019 7:14 PM, Eric Dumazet wrote:
>>>>>
>>>>>
>>>>> On 02/11/2019 12:53 AM, Tariq Toukan wrote:
>>>>>>
>>>>>
>>>>>> Hi,
>>>>>>
>>>>>> It's great to use the struct page to store its dma mapping, but I am
>>>>>> worried about extensibility.
>>>>>> page_pool is evolving, and it would need several more per-page fields.
>>>>>> One of them would be pageref_bias, a planned optimization to reduce the
>>>>>> number of the costly atomic pageref operations (and replace existing
>>>>>> code in several drivers).
>>>>>>
>>>>>
>>>>> But the point about pageref_bias is to place it in a different cache line than "struct page"
>>>>>
>>>>> The major cost is having a cache line bouncing between producer and consumer.
>>>>>
>>>>
>>>> pageref_bias is meant to be dirtied only by the page requester, i.e. the
>>>> NIC driver / page_pool.
>>>> All other components (basically, SKB release flow / put_page) should
>>>> continue working with the atomic page_refcnt, and not dirty the
>>>> pageref_bias.
>>>
>>> This is exactly my point.
>>>
>>> You suggested to put pageref_bias in struct page, which breaks this completely.
>>>
>>> pageref_bias is better kept in a driver structure, with appropriate prefetching
>>> since most NIC use a ring buffer for their queues.
>>>
>>> The dma address _can_ be put in the struct page, since the driver does not dirty it
>>> and does not even read it when page can be recycled.
>>
>> Instead of maintaining the pageref_bias in the page itself it could be
>> maintained in some sort of separate structure. You could just maintain
>> a pointer to a slot in an array somewhere. Then you can still access
>> it if needed, the pointer would be static for as long as it is in the
>> page pool, and you could invalidate the pointer prior to removing the
>> bias from the page.
>
> I think that's what Tariq was suggesting in the first place.
>
> /Ilias
>
Correct.
But not relevant anymore, as it won't work for other reasons.
Tariq
^ permalink raw reply
* [PATCH 1/3 net-next] lib: objagg: Fix an error code in objagg_hints_get()
From: Dan Carpenter @ 2019-02-13 8:56 UTC (permalink / raw)
To: Jiri Pirko; +Cc: netdev, Ido Schimmel, kernel-janitors
We need to set the error code on this path otherwise we return
ERR_PTR(0) which would result in a NULL dereference in the caller.
Fixes: 9069a3817d82 ("lib: objagg: implement optimization hints assembly and use hints for object creation")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
---
lib/objagg.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/lib/objagg.c b/lib/objagg.c
index 781f41c3c47d..d552ec9c60ed 100644
--- a/lib/objagg.c
+++ b/lib/objagg.c
@@ -968,8 +968,10 @@ struct objagg_hints *objagg_hints_get(struct objagg *objagg,
if (err)
goto err_fillup_hints;
- if (WARN_ON(objagg_hints->node_count != objagg->obj_count))
+ if (WARN_ON(objagg_hints->node_count != objagg->obj_count)) {
+ err = -EINVAL;
goto err_node_count_check;
+ }
return objagg_hints;
--
2.17.1
^ permalink raw reply related
* [PATCH 2/3 net-next] test_objagg: Test the correct variable
From: Dan Carpenter @ 2019-02-13 8:58 UTC (permalink / raw)
To: Jiri Pirko; +Cc: netdev, kernel-janitors
In-Reply-To: <20190213085650.GB14113@kadam>
There is a typo here. We intended to check "objagg2" but we instead
test "objagg" which is not an error pointer.
Fixes: 9069a3817d82 ("lib: objagg: implement optimization hints assembly and use hints for object creation")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
---
lib/test_objagg.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/lib/test_objagg.c b/lib/test_objagg.c
index 3744573b6365..3dd45777b13c 100644
--- a/lib/test_objagg.c
+++ b/lib/test_objagg.c
@@ -952,8 +952,8 @@ static int test_hints_case(const struct hints_case *hints_case)
}
objagg2 = objagg_create(&delta_ops, hints, &world2);
- if (IS_ERR(objagg))
- return PTR_ERR(objagg);
+ if (IS_ERR(objagg2))
+ return PTR_ERR(objagg2);
for (i = 0; i < hints_case->key_ids_count; i++) {
objagg_obj = world_obj_get(&world2, objagg2,
--
2.17.1
^ permalink raw reply related
* [PATCH 3/3 net-next] test_objagg: Uninitialized variable in error handling
From: Dan Carpenter @ 2019-02-13 8:59 UTC (permalink / raw)
To: Jiri Pirko; +Cc: netdev, kernel-janitors
In-Reply-To: <20190213085650.GB14113@kadam>
We need to set the error message on this path otherwise some of the
callers, such as test_hints_case(), print from an uninitialized pointer.
We had a similar bug earlier and set "errmsg" to NULL in the caller,
test_delta_action_item(). That code is no longer required so I have
removed it.
Fixes: 9069a3817d82 ("lib: objagg: implement optimization hints assembly and use hints for object creation")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
---
lib/test_objagg.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/lib/test_objagg.c b/lib/test_objagg.c
index 3dd45777b13c..72c1abfa154d 100644
--- a/lib/test_objagg.c
+++ b/lib/test_objagg.c
@@ -745,8 +745,10 @@ static int check_expect_stats(struct objagg *objagg,
int err;
stats = objagg_stats_get(objagg);
- if (IS_ERR(stats))
+ if (IS_ERR(stats)) {
+ *errmsg = "objagg_stats_get() failed.";
return PTR_ERR(stats);
+ }
err = __check_expect_stats(stats, expect_stats, errmsg);
objagg_stats_put(stats);
return err;
@@ -786,7 +788,6 @@ static int test_delta_action_item(struct world *world,
if (err)
goto errout;
- errmsg = NULL;
err = check_expect_stats(objagg, &action_item->expect_stats, &errmsg);
if (err) {
pr_err("Key %u: Stats: %s\n", action_item->key_id, errmsg);
--
2.17.1
^ permalink raw reply related
* [PATCH 01/21] batman-adv: fix memory leak in in batadv_dat_put_dhcp
From: Simon Wunderlich @ 2019-02-13 9:55 UTC (permalink / raw)
To: davem; +Cc: netdev, b.a.t.m.a.n, Martin Weinelt, Sven Eckelmann,
Simon Wunderlich
In-Reply-To: <20190213095524.10147-1-sw@simonwunderlich.de>
From: Martin Weinelt <martin@linuxlounge.net>
batadv_dat_put_dhcp is creating a new ARP packet via
batadv_dat_arp_create_reply and tries to forward it via
batadv_dat_send_data to different peers in the DHT. The original skb is not
consumed by batadv_dat_send_data and thus has to be consumed by the caller.
Fixes: b61ec31c8575 ("batman-adv: Snoop DHCPACKs for DAT")
Signed-off-by: Martin Weinelt <martin@linuxlounge.net>
[sven@narfation.org: add commit message]
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
net/batman-adv/distributed-arp-table.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index 899ab051ffce..310a4f353008 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -1711,6 +1711,8 @@ static void batadv_dat_put_dhcp(struct batadv_priv *bat_priv, u8 *chaddr,
batadv_dat_send_data(bat_priv, skb, yiaddr, vid, BATADV_P_DAT_DHT_PUT);
batadv_dat_send_data(bat_priv, skb, ip_dst, vid, BATADV_P_DAT_DHT_PUT);
+ consume_skb(skb);
+
batadv_dbg(BATADV_DBG_DAT, bat_priv,
"Snooped from outgoing DHCPACK (server address): %pI4, %pM (vid: %i)\n",
&ip_dst, hw_dst, batadv_print_vid(vid));
--
2.11.0
^ permalink raw reply related
* [PATCH 02/21] batman-adv: Fix typo "reseved" -> "reserved"
From: Simon Wunderlich @ 2019-02-13 9:55 UTC (permalink / raw)
To: davem; +Cc: netdev, b.a.t.m.a.n, Sven Eckelmann, Simon Wunderlich
In-Reply-To: <20190213095524.10147-1-sw@simonwunderlich.de>
From: Sven Eckelmann <sven@narfation.org>
checkpatch.pl complains since commit 45e417022023 ("scripts/spelling.txt:
add more spellings to spelling.txt") about an additional spelling mistake
in batman-adv:`
CHECK: 'reseved' may be misspelled - perhaps 'reserved'?
#232: FILE: include/uapi/linux/batadv_packet.h:232:
+ * @flags: reseved for routing relevant flags - currently always 0
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
include/uapi/linux/batadv_packet.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h
index 7eb2936a8e22..c99336f4eefe 100644
--- a/include/uapi/linux/batadv_packet.h
+++ b/include/uapi/linux/batadv_packet.h
@@ -229,7 +229,7 @@ struct batadv_ogm_packet {
* @packet_type: batman-adv packet type, part of the general header
* @version: batman-adv protocol version, part of the general header
* @ttl: time to live for this packet, part of the general header
- * @flags: reseved for routing relevant flags - currently always 0
+ * @flags: reserved for routing relevant flags - currently always 0
* @seqno: sequence number
* @orig: originator mac address
* @tvlv_len: length of the appended tvlv buffer (in bytes)
--
2.11.0
^ permalink raw reply related
* [PATCH 03/21] batman-adv: Move common genl doit code pre/post hooks
From: Simon Wunderlich @ 2019-02-13 9:55 UTC (permalink / raw)
To: davem; +Cc: netdev, b.a.t.m.a.n, Sven Eckelmann, Simon Wunderlich
In-Reply-To: <20190213095524.10147-1-sw@simonwunderlich.de>
From: Sven Eckelmann <sven@narfation.org>
The commit ff4c92d85c6f ("genetlink: introduce pre_doit/post_doit hooks")
intoduced a mechanism to run specific code for doit hooks before/after the
hooks are run. Since all doit hooks are requiring the batadv softif, it
should be retrieved/freed in these helpers to simplify the code.
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
net/batman-adv/netlink.c | 143 +++++++++++++++++++++++++++++++++--------------
1 file changed, 100 insertions(+), 43 deletions(-)
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index 5fe833cc9507..e56c40d1bfe0 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -20,8 +20,10 @@
#include "main.h"
#include <linux/atomic.h>
+#include <linux/bitops.h>
#include <linux/byteorder/generic.h>
#include <linux/cache.h>
+#include <linux/err.h>
#include <linux/errno.h>
#include <linux/export.h>
#include <linux/genetlink.h>
@@ -54,6 +56,8 @@
#include "tp_meter.h"
#include "translation-table.h"
+struct net;
+
struct genl_family batadv_netlink_family;
/* multicast groups */
@@ -61,6 +65,18 @@ enum batadv_netlink_multicast_groups {
BATADV_NL_MCGRP_TPMETER,
};
+/**
+ * enum batadv_genl_ops_flags - flags for genl_ops's internal_flags
+ */
+enum batadv_genl_ops_flags {
+ /**
+ * @BATADV_FLAG_NEED_MESH: request requires valid soft interface in
+ * attribute BATADV_ATTR_MESH_IFINDEX and expects a pointer to it to be
+ * saved in info->user_ptr[0]
+ */
+ BATADV_FLAG_NEED_MESH = BIT(0),
+};
+
static const struct genl_multicast_group batadv_netlink_mcgrps[] = {
[BATADV_NL_MCGRP_TPMETER] = { .name = BATADV_NL_MCAST_GROUP_TPMETER },
};
@@ -329,40 +345,24 @@ int batadv_netlink_tpmeter_notify(struct batadv_priv *bat_priv, const u8 *dst,
static int
batadv_netlink_tp_meter_start(struct sk_buff *skb, struct genl_info *info)
{
- struct net *net = genl_info_net(info);
- struct net_device *soft_iface;
- struct batadv_priv *bat_priv;
+ struct batadv_priv *bat_priv = info->user_ptr[0];
struct sk_buff *msg = NULL;
u32 test_length;
void *msg_head;
- int ifindex;
u32 cookie;
u8 *dst;
int ret;
- if (!info->attrs[BATADV_ATTR_MESH_IFINDEX])
- return -EINVAL;
-
if (!info->attrs[BATADV_ATTR_ORIG_ADDRESS])
return -EINVAL;
if (!info->attrs[BATADV_ATTR_TPMETER_TEST_TIME])
return -EINVAL;
- ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]);
- if (!ifindex)
- return -EINVAL;
-
dst = nla_data(info->attrs[BATADV_ATTR_ORIG_ADDRESS]);
test_length = nla_get_u32(info->attrs[BATADV_ATTR_TPMETER_TEST_TIME]);
- soft_iface = dev_get_by_index(net, ifindex);
- if (!soft_iface || !batadv_softif_is_valid(soft_iface)) {
- ret = -ENODEV;
- goto out;
- }
-
msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!msg) {
ret = -ENOMEM;
@@ -377,15 +377,11 @@ batadv_netlink_tp_meter_start(struct sk_buff *skb, struct genl_info *info)
goto out;
}
- bat_priv = netdev_priv(soft_iface);
batadv_tp_start(bat_priv, dst, test_length, &cookie);
ret = batadv_netlink_tp_meter_put(msg, cookie);
out:
- if (soft_iface)
- dev_put(soft_iface);
-
if (ret) {
if (msg)
nlmsg_free(msg);
@@ -406,38 +402,17 @@ batadv_netlink_tp_meter_start(struct sk_buff *skb, struct genl_info *info)
static int
batadv_netlink_tp_meter_cancel(struct sk_buff *skb, struct genl_info *info)
{
- struct net *net = genl_info_net(info);
- struct net_device *soft_iface;
- struct batadv_priv *bat_priv;
- int ifindex;
+ struct batadv_priv *bat_priv = info->user_ptr[0];
u8 *dst;
int ret = 0;
- if (!info->attrs[BATADV_ATTR_MESH_IFINDEX])
- return -EINVAL;
-
if (!info->attrs[BATADV_ATTR_ORIG_ADDRESS])
return -EINVAL;
- ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]);
- if (!ifindex)
- return -EINVAL;
-
dst = nla_data(info->attrs[BATADV_ATTR_ORIG_ADDRESS]);
- soft_iface = dev_get_by_index(net, ifindex);
- if (!soft_iface || !batadv_softif_is_valid(soft_iface)) {
- ret = -ENODEV;
- goto out;
- }
-
- bat_priv = netdev_priv(soft_iface);
batadv_tp_stop(bat_priv, dst, BATADV_TP_REASON_CANCEL);
-out:
- if (soft_iface)
- dev_put(soft_iface);
-
return ret;
}
@@ -545,6 +520,84 @@ batadv_netlink_dump_hardifs(struct sk_buff *msg, struct netlink_callback *cb)
return msg->len;
}
+/**
+ * batadv_get_softif_from_info() - Retrieve soft interface from genl attributes
+ * @net: the applicable net namespace
+ * @info: receiver information
+ *
+ * Return: Pointer to soft interface (with increased refcnt) on success, error
+ * pointer on error
+ */
+static struct net_device *
+batadv_get_softif_from_info(struct net *net, struct genl_info *info)
+{
+ struct net_device *soft_iface;
+ int ifindex;
+
+ if (!info->attrs[BATADV_ATTR_MESH_IFINDEX])
+ return ERR_PTR(-EINVAL);
+
+ ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]);
+
+ soft_iface = dev_get_by_index(net, ifindex);
+ if (!soft_iface)
+ return ERR_PTR(-ENODEV);
+
+ if (!batadv_softif_is_valid(soft_iface))
+ goto err_put_softif;
+
+ return soft_iface;
+
+err_put_softif:
+ dev_put(soft_iface);
+
+ return ERR_PTR(-EINVAL);
+}
+
+/**
+ * batadv_pre_doit() - Prepare batman-adv genl doit request
+ * @ops: requested netlink operation
+ * @skb: Netlink message with request data
+ * @info: receiver information
+ *
+ * Return: 0 on success or negative error number in case of failure
+ */
+static int batadv_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ struct net_device *soft_iface;
+ struct batadv_priv *bat_priv;
+
+ if (ops->internal_flags & BATADV_FLAG_NEED_MESH) {
+ soft_iface = batadv_get_softif_from_info(net, info);
+ if (IS_ERR(soft_iface))
+ return PTR_ERR(soft_iface);
+
+ bat_priv = netdev_priv(soft_iface);
+ info->user_ptr[0] = bat_priv;
+ }
+
+ return 0;
+}
+
+/**
+ * batadv_post_doit() - End batman-adv genl doit request
+ * @ops: requested netlink operation
+ * @skb: Netlink message with request data
+ * @info: receiver information
+ */
+static void batadv_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct batadv_priv *bat_priv;
+
+ if (ops->internal_flags & BATADV_FLAG_NEED_MESH && info->user_ptr[0]) {
+ bat_priv = info->user_ptr[0];
+ dev_put(bat_priv->soft_iface);
+ }
+}
+
static const struct genl_ops batadv_netlink_ops[] = {
{
.cmd = BATADV_CMD_GET_MESH_INFO,
@@ -557,12 +610,14 @@ static const struct genl_ops batadv_netlink_ops[] = {
.flags = GENL_ADMIN_PERM,
.policy = batadv_netlink_policy,
.doit = batadv_netlink_tp_meter_start,
+ .internal_flags = BATADV_FLAG_NEED_MESH,
},
{
.cmd = BATADV_CMD_TP_METER_CANCEL,
.flags = GENL_ADMIN_PERM,
.policy = batadv_netlink_policy,
.doit = batadv_netlink_tp_meter_cancel,
+ .internal_flags = BATADV_FLAG_NEED_MESH,
},
{
.cmd = BATADV_CMD_GET_ROUTING_ALGOS,
@@ -639,6 +694,8 @@ struct genl_family batadv_netlink_family __ro_after_init = {
.version = 1,
.maxattr = BATADV_ATTR_MAX,
.netnsok = true,
+ .pre_doit = batadv_pre_doit,
+ .post_doit = batadv_post_doit,
.module = THIS_MODULE,
.ops = batadv_netlink_ops,
.n_ops = ARRAY_SIZE(batadv_netlink_ops),
--
2.11.0
^ permalink raw reply related
* [PATCH 04/21] batman-adv: Prepare framework for mesh genl config
From: Simon Wunderlich @ 2019-02-13 9:55 UTC (permalink / raw)
To: davem; +Cc: netdev, b.a.t.m.a.n, Sven Eckelmann, Simon Wunderlich
In-Reply-To: <20190213095524.10147-1-sw@simonwunderlich.de>
From: Sven Eckelmann <sven@narfation.org>
The batman-adv configuration interface was implemented solely using sysfs.
This approach was condemned by non-batadv developers as "huge mistake".
Instead a netlink/genl based implementation was suggested.
The main objects for this configuration is the mesh/soft-interface object.
Its actual object in memory already contains most of the available
configuration settings. The genl interface reflects this by allowing to
get/set it using the mesh specific commands.
The BATADV_CMD_GET_MESH_INFO (or short version BATADV_CMD_GET_MESH) is
reused as get command because it already provides the content of other
information from the mesh/soft-interface which are not yet configuration
specific.
The set command BATADV_CMD_SET_MESH will also notify interested userspace
listeners of the "config" mcast group using the BATADV_CMD_SET_MESH command
message type that settings might have been changed and what the current
values are.
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
include/uapi/linux/batman_adv.h | 16 +++-
net/batman-adv/netlink.c | 160 ++++++++++++++++++++++++----------------
2 files changed, 111 insertions(+), 65 deletions(-)
diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h
index a28e76a7e0a2..b3394aac9a88 100644
--- a/include/uapi/linux/batman_adv.h
+++ b/include/uapi/linux/batman_adv.h
@@ -27,6 +27,7 @@
#define BATADV_NL_NAME "batadv"
+#define BATADV_NL_MCAST_GROUP_CONFIG "config"
#define BATADV_NL_MCAST_GROUP_TPMETER "tpmeter"
/**
@@ -372,10 +373,14 @@ enum batadv_nl_commands {
BATADV_CMD_UNSPEC,
/**
- * @BATADV_CMD_GET_MESH_INFO: Query basic information about batman-adv
- * device
+ * @BATADV_CMD_GET_MESH: Get attributes from softif/mesh
*/
- BATADV_CMD_GET_MESH_INFO,
+ BATADV_CMD_GET_MESH,
+
+ /**
+ * @BATADV_CMD_GET_MESH_INFO: Alias for @BATADV_CMD_GET_MESH
+ */
+ BATADV_CMD_GET_MESH_INFO = BATADV_CMD_GET_MESH,
/**
* @BATADV_CMD_TP_METER: Start a tp meter session
@@ -443,6 +448,11 @@ enum batadv_nl_commands {
*/
BATADV_CMD_GET_MCAST_FLAGS,
+ /**
+ * @BATADV_CMD_SET_MESH: Set attributes for softif/mesh
+ */
+ BATADV_CMD_SET_MESH,
+
/* add new commands above here */
/**
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index e56c40d1bfe0..179cc7cfcb70 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -62,6 +62,7 @@ struct genl_family batadv_netlink_family;
/* multicast groups */
enum batadv_netlink_multicast_groups {
+ BATADV_NL_MCGRP_CONFIG,
BATADV_NL_MCGRP_TPMETER,
};
@@ -78,6 +79,7 @@ enum batadv_genl_ops_flags {
};
static const struct genl_multicast_group batadv_netlink_mcgrps[] = {
+ [BATADV_NL_MCGRP_CONFIG] = { .name = BATADV_NL_MCAST_GROUP_CONFIG },
[BATADV_NL_MCGRP_TPMETER] = { .name = BATADV_NL_MCAST_GROUP_TPMETER },
};
@@ -138,20 +140,29 @@ batadv_netlink_get_ifindex(const struct nlmsghdr *nlh, int attrtype)
}
/**
- * batadv_netlink_mesh_info_put() - fill in generic information about mesh
- * interface
- * @msg: netlink message to be sent back
- * @soft_iface: interface for which the data should be taken
+ * batadv_netlink_mesh_fill() - Fill message with mesh attributes
+ * @msg: Netlink message to dump into
+ * @bat_priv: the bat priv with all the soft interface information
+ * @cmd: type of message to generate
+ * @portid: Port making netlink request
+ * @seq: sequence number for message
+ * @flags: Additional flags for message
*
- * Return: 0 on success, < 0 on error
+ * Return: 0 on success or negative error number in case of failure
*/
-static int
-batadv_netlink_mesh_info_put(struct sk_buff *msg, struct net_device *soft_iface)
+static int batadv_netlink_mesh_fill(struct sk_buff *msg,
+ struct batadv_priv *bat_priv,
+ enum batadv_nl_commands cmd,
+ u32 portid, u32 seq, int flags)
{
- struct batadv_priv *bat_priv = netdev_priv(soft_iface);
+ struct net_device *soft_iface = bat_priv->soft_iface;
struct batadv_hard_iface *primary_if = NULL;
struct net_device *hard_iface;
- int ret = -ENOBUFS;
+ void *hdr;
+
+ hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd);
+ if (!hdr)
+ return -ENOBUFS;
if (nla_put_string(msg, BATADV_ATTR_VERSION, BATADV_SOURCE_VERSION) ||
nla_put_string(msg, BATADV_ATTR_ALGO_NAME,
@@ -162,16 +173,16 @@ batadv_netlink_mesh_info_put(struct sk_buff *msg, struct net_device *soft_iface)
soft_iface->dev_addr) ||
nla_put_u8(msg, BATADV_ATTR_TT_TTVN,
(u8)atomic_read(&bat_priv->tt.vn)))
- goto out;
+ goto nla_put_failure;
#ifdef CONFIG_BATMAN_ADV_BLA
if (nla_put_u16(msg, BATADV_ATTR_BLA_CRC,
ntohs(bat_priv->bla.claim_dest.group)))
- goto out;
+ goto nla_put_failure;
#endif
if (batadv_mcast_mesh_info_put(msg, bat_priv))
- goto out;
+ goto nla_put_failure;
primary_if = batadv_primary_if_get_selected(bat_priv);
if (primary_if && primary_if->if_status == BATADV_IF_ACTIVE) {
@@ -183,77 +194,95 @@ batadv_netlink_mesh_info_put(struct sk_buff *msg, struct net_device *soft_iface)
hard_iface->name) ||
nla_put(msg, BATADV_ATTR_HARD_ADDRESS, ETH_ALEN,
hard_iface->dev_addr))
- goto out;
+ goto nla_put_failure;
}
- ret = 0;
+ if (primary_if)
+ batadv_hardif_put(primary_if);
- out:
+ genlmsg_end(msg, hdr);
+ return 0;
+
+nla_put_failure:
if (primary_if)
batadv_hardif_put(primary_if);
- return ret;
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
}
/**
- * batadv_netlink_get_mesh_info() - handle incoming BATADV_CMD_GET_MESH_INFO
- * netlink request
- * @skb: received netlink message
- * @info: receiver information
+ * batadv_netlink_notify_mesh() - send softif attributes to listener
+ * @bat_priv: the bat priv with all the soft interface information
*
* Return: 0 on success, < 0 on error
*/
-static int
-batadv_netlink_get_mesh_info(struct sk_buff *skb, struct genl_info *info)
+static int batadv_netlink_notify_mesh(struct batadv_priv *bat_priv)
{
- struct net *net = genl_info_net(info);
- struct net_device *soft_iface;
- struct sk_buff *msg = NULL;
- void *msg_head;
- int ifindex;
+ struct sk_buff *msg;
int ret;
- if (!info->attrs[BATADV_ATTR_MESH_IFINDEX])
- return -EINVAL;
-
- ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]);
- if (!ifindex)
- return -EINVAL;
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
- soft_iface = dev_get_by_index(net, ifindex);
- if (!soft_iface || !batadv_softif_is_valid(soft_iface)) {
- ret = -ENODEV;
- goto out;
+ ret = batadv_netlink_mesh_fill(msg, bat_priv, BATADV_CMD_SET_MESH,
+ 0, 0, 0);
+ if (ret < 0) {
+ nlmsg_free(msg);
+ return ret;
}
- msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!msg) {
- ret = -ENOMEM;
- goto out;
- }
+ genlmsg_multicast_netns(&batadv_netlink_family,
+ dev_net(bat_priv->soft_iface), msg, 0,
+ BATADV_NL_MCGRP_CONFIG, GFP_KERNEL);
- msg_head = genlmsg_put(msg, info->snd_portid, info->snd_seq,
- &batadv_netlink_family, 0,
- BATADV_CMD_GET_MESH_INFO);
- if (!msg_head) {
- ret = -ENOBUFS;
- goto out;
- }
+ return 0;
+}
- ret = batadv_netlink_mesh_info_put(msg, soft_iface);
+/**
+ * batadv_netlink_get_mesh() - Get softif attributes
+ * @skb: Netlink message with request data
+ * @info: receiver information
+ *
+ * Return: 0 on success or negative error number in case of failure
+ */
+static int batadv_netlink_get_mesh(struct sk_buff *skb, struct genl_info *info)
+{
+ struct batadv_priv *bat_priv = info->user_ptr[0];
+ struct sk_buff *msg;
+ int ret;
- out:
- if (soft_iface)
- dev_put(soft_iface);
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
- if (ret) {
- if (msg)
- nlmsg_free(msg);
+ ret = batadv_netlink_mesh_fill(msg, bat_priv, BATADV_CMD_GET_MESH,
+ info->snd_portid, info->snd_seq, 0);
+ if (ret < 0) {
+ nlmsg_free(msg);
return ret;
}
- genlmsg_end(msg, msg_head);
- return genlmsg_reply(msg, info);
+ ret = genlmsg_reply(msg, info);
+
+ return ret;
+}
+
+/**
+ * batadv_netlink_set_mesh() - Set softif attributes
+ * @skb: Netlink message with request data
+ * @info: receiver information
+ *
+ * Return: 0 on success or negative error number in case of failure
+ */
+static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info)
+{
+ struct batadv_priv *bat_priv = info->user_ptr[0];
+
+ batadv_netlink_notify_mesh(bat_priv);
+
+ return 0;
}
/**
@@ -600,10 +629,11 @@ static void batadv_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
static const struct genl_ops batadv_netlink_ops[] = {
{
- .cmd = BATADV_CMD_GET_MESH_INFO,
- .flags = GENL_ADMIN_PERM,
+ .cmd = BATADV_CMD_GET_MESH,
+ /* can be retrieved by unprivileged users */
.policy = batadv_netlink_policy,
- .doit = batadv_netlink_get_mesh_info,
+ .doit = batadv_netlink_get_mesh,
+ .internal_flags = BATADV_FLAG_NEED_MESH,
},
{
.cmd = BATADV_CMD_TP_METER,
@@ -685,7 +715,13 @@ static const struct genl_ops batadv_netlink_ops[] = {
.policy = batadv_netlink_policy,
.dumpit = batadv_mcast_flags_dump,
},
-
+ {
+ .cmd = BATADV_CMD_SET_MESH,
+ .flags = GENL_ADMIN_PERM,
+ .policy = batadv_netlink_policy,
+ .doit = batadv_netlink_set_mesh,
+ .internal_flags = BATADV_FLAG_NEED_MESH,
+ },
};
struct genl_family batadv_netlink_family __ro_after_init = {
--
2.11.0
^ permalink raw reply related
* [PATCH 06/21] batman-adv: Prepare framework for vlan genl config
From: Simon Wunderlich @ 2019-02-13 9:55 UTC (permalink / raw)
To: davem; +Cc: netdev, b.a.t.m.a.n, Sven Eckelmann, Simon Wunderlich
In-Reply-To: <20190213095524.10147-1-sw@simonwunderlich.de>
From: Sven Eckelmann <sven@narfation.org>
The batman-adv configuration interface was implemented solely using sysfs.
This approach was condemned by non-batadv developers as "huge mistake".
Instead a netlink/genl based implementation was suggested.
Beside the mesh/soft-interface specific configuration, the VLANs on top of
the mesh/soft-interface have configuration settings. The genl interface
reflects this by allowing to get/set it using the vlan specific commands
BATADV_CMD_GET_VLAN/BATADV_CMD_SET_VLAN.
The set command BATADV_CMD_SET_MESH will also notify interested userspace
listeners of the "config" mcast group using the BATADV_CMD_SET_VLAN command
message type that settings might have been changed and what the current
values are.
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
include/uapi/linux/batman_adv.h | 17 ++++
net/batman-adv/netlink.c | 191 +++++++++++++++++++++++++++++++++++++++-
2 files changed, 206 insertions(+), 2 deletions(-)
diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h
index 62456a087ef6..10f3cc34fe16 100644
--- a/include/uapi/linux/batman_adv.h
+++ b/include/uapi/linux/batman_adv.h
@@ -345,6 +345,11 @@ enum batadv_nl_attrs {
*/
BATADV_ATTR_MCAST_FLAGS_PRIV,
+ /**
+ * @BATADV_ATTR_VLANID: VLAN id on top of soft interface
+ */
+ BATADV_ATTR_VLANID,
+
/* add attributes above here, update the policy in netlink.c */
/**
@@ -465,6 +470,18 @@ enum batadv_nl_commands {
*/
BATADV_CMD_SET_HARDIF,
+ /**
+ * @BATADV_CMD_GET_VLAN: Get attributes from a VLAN of the
+ * current softif
+ */
+ BATADV_CMD_GET_VLAN,
+
+ /**
+ * @BATADV_CMD_SET_VLAN: Set attributes for VLAN of the
+ * current softif
+ */
+ BATADV_CMD_SET_VLAN,
+
/* add new commands above here */
/**
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index a184e4225fb5..d40913bb9031 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -30,6 +30,7 @@
#include <linux/genetlink.h>
#include <linux/gfp.h>
#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/list.h>
@@ -84,6 +85,13 @@ enum batadv_genl_ops_flags {
* saved in info->user_ptr[1]
*/
BATADV_FLAG_NEED_HARDIF = BIT(1),
+
+ /**
+ * @BATADV_FLAG_NEED_VLAN: request requires valid vlan in
+ * attribute BATADV_ATTR_VLANID and expects a pointer to it to be
+ * saved in info->user_ptr[1]
+ */
+ BATADV_FLAG_NEED_VLAN = BIT(2),
};
static const struct genl_multicast_group batadv_netlink_mcgrps[] = {
@@ -130,6 +138,7 @@ static const struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = {
[BATADV_ATTR_DAT_CACHE_VID] = { .type = NLA_U16 },
[BATADV_ATTR_MCAST_FLAGS] = { .type = NLA_U32 },
[BATADV_ATTR_MCAST_FLAGS_PRIV] = { .type = NLA_U32 },
+ [BATADV_ATTR_VLANID] = { .type = NLA_U16 },
};
/**
@@ -654,6 +663,123 @@ batadv_netlink_dump_hardif(struct sk_buff *msg, struct netlink_callback *cb)
}
/**
+ * batadv_netlink_vlan_fill() - Fill message with vlan attributes
+ * @msg: Netlink message to dump into
+ * @bat_priv: the bat priv with all the soft interface information
+ * @vlan: vlan which was modified
+ * @cmd: type of message to generate
+ * @portid: Port making netlink request
+ * @seq: sequence number for message
+ * @flags: Additional flags for message
+ *
+ * Return: 0 on success or negative error number in case of failure
+ */
+static int batadv_netlink_vlan_fill(struct sk_buff *msg,
+ struct batadv_priv *bat_priv,
+ struct batadv_softif_vlan *vlan,
+ enum batadv_nl_commands cmd,
+ u32 portid, u32 seq, int flags)
+{
+ void *hdr;
+
+ hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd);
+ if (!hdr)
+ return -ENOBUFS;
+
+ if (nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX,
+ bat_priv->soft_iface->ifindex))
+ goto nla_put_failure;
+
+ if (nla_put_u32(msg, BATADV_ATTR_VLANID, vlan->vid & VLAN_VID_MASK))
+ goto nla_put_failure;
+
+ genlmsg_end(msg, hdr);
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
+}
+
+/**
+ * batadv_netlink_notify_vlan() - send vlan attributes to listener
+ * @bat_priv: the bat priv with all the soft interface information
+ * @vlan: vlan which was modified
+ *
+ * Return: 0 on success, < 0 on error
+ */
+static int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv,
+ struct batadv_softif_vlan *vlan)
+{
+ struct sk_buff *msg;
+ int ret;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ ret = batadv_netlink_vlan_fill(msg, bat_priv, vlan,
+ BATADV_CMD_SET_VLAN, 0, 0, 0);
+ if (ret < 0) {
+ nlmsg_free(msg);
+ return ret;
+ }
+
+ genlmsg_multicast_netns(&batadv_netlink_family,
+ dev_net(bat_priv->soft_iface), msg, 0,
+ BATADV_NL_MCGRP_CONFIG, GFP_KERNEL);
+
+ return 0;
+}
+
+/**
+ * batadv_netlink_get_vlan() - Get vlan attributes
+ * @skb: Netlink message with request data
+ * @info: receiver information
+ *
+ * Return: 0 on success or negative error number in case of failure
+ */
+static int batadv_netlink_get_vlan(struct sk_buff *skb, struct genl_info *info)
+{
+ struct batadv_softif_vlan *vlan = info->user_ptr[1];
+ struct batadv_priv *bat_priv = info->user_ptr[0];
+ struct sk_buff *msg;
+ int ret;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ ret = batadv_netlink_vlan_fill(msg, bat_priv, vlan, BATADV_CMD_GET_VLAN,
+ info->snd_portid, info->snd_seq, 0);
+ if (ret < 0) {
+ nlmsg_free(msg);
+ return ret;
+ }
+
+ ret = genlmsg_reply(msg, info);
+
+ return ret;
+}
+
+/**
+ * batadv_netlink_set_vlan() - Get vlan attributes
+ * @skb: Netlink message with request data
+ * @info: receiver information
+ *
+ * Return: 0 on success or negative error number in case of failure
+ */
+static int batadv_netlink_set_vlan(struct sk_buff *skb, struct genl_info *info)
+{
+ struct batadv_softif_vlan *vlan = info->user_ptr[1];
+ struct batadv_priv *bat_priv = info->user_ptr[0];
+
+ batadv_netlink_notify_vlan(bat_priv, vlan);
+
+ return 0;
+}
+
+/**
* batadv_get_softif_from_info() - Retrieve soft interface from genl attributes
* @net: the applicable net namespace
* @info: receiver information
@@ -734,6 +860,34 @@ batadv_get_hardif_from_info(struct batadv_priv *bat_priv, struct net *net,
}
/**
+ * batadv_get_vlan_from_info() - Retrieve vlan from genl attributes
+ * @bat_priv: the bat priv with all the soft interface information
+ * @net: the applicable net namespace
+ * @info: receiver information
+ *
+ * Return: Pointer to vlan on success (with increased refcnt), error pointer
+ * on error
+ */
+static struct batadv_softif_vlan *
+batadv_get_vlan_from_info(struct batadv_priv *bat_priv, struct net *net,
+ struct genl_info *info)
+{
+ struct batadv_softif_vlan *vlan;
+ u16 vid;
+
+ if (!info->attrs[BATADV_ATTR_VLANID])
+ return ERR_PTR(-EINVAL);
+
+ vid = nla_get_u16(info->attrs[BATADV_ATTR_VLANID]);
+
+ vlan = batadv_softif_vlan_get(bat_priv, vid | BATADV_VLAN_HAS_TAG);
+ if (!vlan)
+ return ERR_PTR(-ENOENT);
+
+ return vlan;
+}
+
+/**
* batadv_pre_doit() - Prepare batman-adv genl doit request
* @ops: requested netlink operation
* @skb: Netlink message with request data
@@ -747,16 +901,17 @@ static int batadv_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
struct net *net = genl_info_net(info);
struct batadv_hard_iface *hard_iface;
struct batadv_priv *bat_priv = NULL;
+ struct batadv_softif_vlan *vlan;
struct net_device *soft_iface;
u8 user_ptr1_flags;
u8 mesh_dep_flags;
int ret;
- user_ptr1_flags = BATADV_FLAG_NEED_HARDIF;
+ user_ptr1_flags = BATADV_FLAG_NEED_HARDIF | BATADV_FLAG_NEED_VLAN;
if (WARN_ON(hweight8(ops->internal_flags & user_ptr1_flags) > 1))
return -EINVAL;
- mesh_dep_flags = BATADV_FLAG_NEED_HARDIF;
+ mesh_dep_flags = BATADV_FLAG_NEED_HARDIF | BATADV_FLAG_NEED_VLAN;
if (WARN_ON((ops->internal_flags & mesh_dep_flags) &&
(~ops->internal_flags & BATADV_FLAG_NEED_MESH)))
return -EINVAL;
@@ -780,6 +935,16 @@ static int batadv_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
info->user_ptr[1] = hard_iface;
}
+ if (ops->internal_flags & BATADV_FLAG_NEED_VLAN) {
+ vlan = batadv_get_vlan_from_info(bat_priv, net, info);
+ if (IS_ERR(vlan)) {
+ ret = PTR_ERR(vlan);
+ goto err_put_softif;
+ }
+
+ info->user_ptr[1] = vlan;
+ }
+
return 0;
err_put_softif:
@@ -799,6 +964,7 @@ static void batadv_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
struct genl_info *info)
{
struct batadv_hard_iface *hard_iface;
+ struct batadv_softif_vlan *vlan;
struct batadv_priv *bat_priv;
if (ops->internal_flags & BATADV_FLAG_NEED_HARDIF &&
@@ -808,6 +974,11 @@ static void batadv_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
batadv_hardif_put(hard_iface);
}
+ if (ops->internal_flags & BATADV_FLAG_NEED_VLAN && info->user_ptr[1]) {
+ vlan = info->user_ptr[1];
+ batadv_softif_vlan_put(vlan);
+ }
+
if (ops->internal_flags & BATADV_FLAG_NEED_MESH && info->user_ptr[0]) {
bat_priv = info->user_ptr[0];
dev_put(bat_priv->soft_iface);
@@ -920,6 +1091,22 @@ static const struct genl_ops batadv_netlink_ops[] = {
.internal_flags = BATADV_FLAG_NEED_MESH |
BATADV_FLAG_NEED_HARDIF,
},
+ {
+ .cmd = BATADV_CMD_GET_VLAN,
+ /* can be retrieved by unprivileged users */
+ .policy = batadv_netlink_policy,
+ .doit = batadv_netlink_get_vlan,
+ .internal_flags = BATADV_FLAG_NEED_MESH |
+ BATADV_FLAG_NEED_VLAN,
+ },
+ {
+ .cmd = BATADV_CMD_SET_VLAN,
+ .flags = GENL_ADMIN_PERM,
+ .policy = batadv_netlink_policy,
+ .doit = batadv_netlink_set_vlan,
+ .internal_flags = BATADV_FLAG_NEED_MESH |
+ BATADV_FLAG_NEED_VLAN,
+ },
};
struct genl_family batadv_netlink_family __ro_after_init = {
--
2.11.0
^ permalink raw reply related
* [PATCH 05/21] batman-adv: Prepare framework for hardif genl config
From: Simon Wunderlich @ 2019-02-13 9:55 UTC (permalink / raw)
To: davem; +Cc: netdev, b.a.t.m.a.n, Sven Eckelmann, Simon Wunderlich
In-Reply-To: <20190213095524.10147-1-sw@simonwunderlich.de>
From: Sven Eckelmann <sven@narfation.org>
The batman-adv configuration interface was implemented solely using sysfs.
This approach was condemned by non-batadv developers as "huge mistake".
Instead a netlink/genl based implementation was suggested.
Beside the mesh/soft-interface specific configuration, the
slave/hard-interface have B.A.T.M.A.N. V specific configuration settings.
The genl interface reflects this by allowing to get/set it using the
hard-interface specific commands.
The BATADV_CMD_GET_HARDIFS (or short version BATADV_CMD_GET_HARDIF) is
reused as get command because it already allow sto dump the content of
other information from the slave/hard-interface which are not yet
configuration specific.
The set command BATADV_CMD_SET_HARDIF will also notify interested userspace
listeners of the "config" mcast group using the BATADV_CMD_SET_HARDIF
command message type that settings might have been changed and what the
current values are.
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
include/uapi/linux/batman_adv.h | 16 ++-
net/batman-adv/netlink.c | 240 ++++++++++++++++++++++++++++++++++++----
2 files changed, 233 insertions(+), 23 deletions(-)
diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h
index b3394aac9a88..62456a087ef6 100644
--- a/include/uapi/linux/batman_adv.h
+++ b/include/uapi/linux/batman_adv.h
@@ -398,9 +398,15 @@ enum batadv_nl_commands {
BATADV_CMD_GET_ROUTING_ALGOS,
/**
- * @BATADV_CMD_GET_HARDIFS: Query list of hard interfaces
+ * @BATADV_CMD_GET_HARDIF: Get attributes from a hardif of the
+ * current softif
*/
- BATADV_CMD_GET_HARDIFS,
+ BATADV_CMD_GET_HARDIF,
+
+ /**
+ * @BATADV_CMD_GET_HARDIFS: Alias for @BATADV_CMD_GET_HARDIF
+ */
+ BATADV_CMD_GET_HARDIFS = BATADV_CMD_GET_HARDIF,
/**
* @BATADV_CMD_GET_TRANSTABLE_LOCAL: Query list of local translations
@@ -453,6 +459,12 @@ enum batadv_nl_commands {
*/
BATADV_CMD_SET_MESH,
+ /**
+ * @BATADV_CMD_SET_HARDIF: Set attributes for hardif of the
+ * current softif
+ */
+ BATADV_CMD_SET_HARDIF,
+
/* add new commands above here */
/**
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index 179cc7cfcb70..a184e4225fb5 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -21,6 +21,7 @@
#include <linux/atomic.h>
#include <linux/bitops.h>
+#include <linux/bug.h>
#include <linux/byteorder/generic.h>
#include <linux/cache.h>
#include <linux/err.h>
@@ -76,6 +77,13 @@ enum batadv_genl_ops_flags {
* saved in info->user_ptr[0]
*/
BATADV_FLAG_NEED_MESH = BIT(0),
+
+ /**
+ * @BATADV_FLAG_NEED_HARDIF: request requires valid hard interface in
+ * attribute BATADV_ATTR_HARD_IFINDEX and expects a pointer to it to be
+ * saved in info->user_ptr[1]
+ */
+ BATADV_FLAG_NEED_HARDIF = BIT(1),
};
static const struct genl_multicast_group batadv_netlink_mcgrps[] = {
@@ -446,29 +454,38 @@ batadv_netlink_tp_meter_cancel(struct sk_buff *skb, struct genl_info *info)
}
/**
- * batadv_netlink_dump_hardif_entry() - Dump one hard interface into a message
+ * batadv_netlink_hardif_fill() - Fill message with hardif attributes
* @msg: Netlink message to dump into
+ * @bat_priv: the bat priv with all the soft interface information
+ * @hard_iface: hard interface which was modified
+ * @cmd: type of message to generate
* @portid: Port making netlink request
+ * @seq: sequence number for message
+ * @flags: Additional flags for message
* @cb: Control block containing additional options
- * @hard_iface: Hard interface to dump
*
- * Return: error code, or 0 on success
+ * Return: 0 on success or negative error number in case of failure
*/
-static int
-batadv_netlink_dump_hardif_entry(struct sk_buff *msg, u32 portid,
- struct netlink_callback *cb,
- struct batadv_hard_iface *hard_iface)
+static int batadv_netlink_hardif_fill(struct sk_buff *msg,
+ struct batadv_priv *bat_priv,
+ struct batadv_hard_iface *hard_iface,
+ enum batadv_nl_commands cmd,
+ u32 portid, u32 seq, int flags,
+ struct netlink_callback *cb)
{
struct net_device *net_dev = hard_iface->net_dev;
void *hdr;
- hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq,
- &batadv_netlink_family, NLM_F_MULTI,
- BATADV_CMD_GET_HARDIFS);
+ hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd);
if (!hdr)
- return -EMSGSIZE;
+ return -ENOBUFS;
+
+ if (cb)
+ genl_dump_check_consistent(cb, hdr);
- genl_dump_check_consistent(cb, hdr);
+ if (nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX,
+ bat_priv->soft_iface->ifindex))
+ goto nla_put_failure;
if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX,
net_dev->ifindex) ||
@@ -486,24 +503,107 @@ batadv_netlink_dump_hardif_entry(struct sk_buff *msg, u32 portid,
genlmsg_end(msg, hdr);
return 0;
- nla_put_failure:
+nla_put_failure:
genlmsg_cancel(msg, hdr);
return -EMSGSIZE;
}
/**
- * batadv_netlink_dump_hardifs() - Dump all hard interface into a messages
+ * batadv_netlink_notify_hardif() - send hardif attributes to listener
+ * @bat_priv: the bat priv with all the soft interface information
+ * @hard_iface: hard interface which was modified
+ *
+ * Return: 0 on success, < 0 on error
+ */
+static int batadv_netlink_notify_hardif(struct batadv_priv *bat_priv,
+ struct batadv_hard_iface *hard_iface)
+{
+ struct sk_buff *msg;
+ int ret;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ ret = batadv_netlink_hardif_fill(msg, bat_priv, hard_iface,
+ BATADV_CMD_SET_HARDIF, 0, 0, 0, NULL);
+ if (ret < 0) {
+ nlmsg_free(msg);
+ return ret;
+ }
+
+ genlmsg_multicast_netns(&batadv_netlink_family,
+ dev_net(bat_priv->soft_iface), msg, 0,
+ BATADV_NL_MCGRP_CONFIG, GFP_KERNEL);
+
+ return 0;
+}
+
+/**
+ * batadv_netlink_get_hardif() - Get hardif attributes
+ * @skb: Netlink message with request data
+ * @info: receiver information
+ *
+ * Return: 0 on success or negative error number in case of failure
+ */
+static int batadv_netlink_get_hardif(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct batadv_hard_iface *hard_iface = info->user_ptr[1];
+ struct batadv_priv *bat_priv = info->user_ptr[0];
+ struct sk_buff *msg;
+ int ret;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ ret = batadv_netlink_hardif_fill(msg, bat_priv, hard_iface,
+ BATADV_CMD_GET_HARDIF,
+ info->snd_portid, info->snd_seq, 0,
+ NULL);
+ if (ret < 0) {
+ nlmsg_free(msg);
+ return ret;
+ }
+
+ ret = genlmsg_reply(msg, info);
+
+ return ret;
+}
+
+/**
+ * batadv_netlink_set_hardif() - Set hardif attributes
+ * @skb: Netlink message with request data
+ * @info: receiver information
+ *
+ * Return: 0 on success or negative error number in case of failure
+ */
+static int batadv_netlink_set_hardif(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct batadv_hard_iface *hard_iface = info->user_ptr[1];
+ struct batadv_priv *bat_priv = info->user_ptr[0];
+
+ batadv_netlink_notify_hardif(bat_priv, hard_iface);
+
+ return 0;
+}
+
+/**
+ * batadv_netlink_dump_hardif() - Dump all hard interface into a messages
* @msg: Netlink message to dump into
* @cb: Parameters from query
*
* Return: error code, or length of reply message on success
*/
static int
-batadv_netlink_dump_hardifs(struct sk_buff *msg, struct netlink_callback *cb)
+batadv_netlink_dump_hardif(struct sk_buff *msg, struct netlink_callback *cb)
{
struct net *net = sock_net(cb->skb->sk);
struct net_device *soft_iface;
struct batadv_hard_iface *hard_iface;
+ struct batadv_priv *bat_priv;
int ifindex;
int portid = NETLINK_CB(cb->skb).portid;
int skip = cb->args[0];
@@ -523,6 +623,8 @@ batadv_netlink_dump_hardifs(struct sk_buff *msg, struct netlink_callback *cb)
return -ENODEV;
}
+ bat_priv = netdev_priv(soft_iface);
+
rtnl_lock();
cb->seq = batadv_hardif_generation << 1 | 1;
@@ -533,8 +635,10 @@ batadv_netlink_dump_hardifs(struct sk_buff *msg, struct netlink_callback *cb)
if (i++ < skip)
continue;
- if (batadv_netlink_dump_hardif_entry(msg, portid, cb,
- hard_iface)) {
+ if (batadv_netlink_hardif_fill(msg, bat_priv, hard_iface,
+ BATADV_CMD_GET_HARDIF,
+ portid, cb->nlh->nlmsg_seq,
+ NLM_F_MULTI, cb)) {
i--;
break;
}
@@ -584,6 +688,52 @@ batadv_get_softif_from_info(struct net *net, struct genl_info *info)
}
/**
+ * batadv_get_hardif_from_info() - Retrieve hardif from genl attributes
+ * @bat_priv: the bat priv with all the soft interface information
+ * @net: the applicable net namespace
+ * @info: receiver information
+ *
+ * Return: Pointer to hard interface (with increased refcnt) on success, error
+ * pointer on error
+ */
+static struct batadv_hard_iface *
+batadv_get_hardif_from_info(struct batadv_priv *bat_priv, struct net *net,
+ struct genl_info *info)
+{
+ struct batadv_hard_iface *hard_iface;
+ struct net_device *hard_dev;
+ unsigned int hardif_index;
+
+ if (!info->attrs[BATADV_ATTR_HARD_IFINDEX])
+ return ERR_PTR(-EINVAL);
+
+ hardif_index = nla_get_u32(info->attrs[BATADV_ATTR_HARD_IFINDEX]);
+
+ hard_dev = dev_get_by_index(net, hardif_index);
+ if (!hard_dev)
+ return ERR_PTR(-ENODEV);
+
+ hard_iface = batadv_hardif_get_by_netdev(hard_dev);
+ if (!hard_iface)
+ goto err_put_harddev;
+
+ if (hard_iface->soft_iface != bat_priv->soft_iface)
+ goto err_put_hardif;
+
+ /* hard_dev is referenced by hard_iface and not needed here */
+ dev_put(hard_dev);
+
+ return hard_iface;
+
+err_put_hardif:
+ batadv_hardif_put(hard_iface);
+err_put_harddev:
+ dev_put(hard_dev);
+
+ return ERR_PTR(-EINVAL);
+}
+
+/**
* batadv_pre_doit() - Prepare batman-adv genl doit request
* @ops: requested netlink operation
* @skb: Netlink message with request data
@@ -595,8 +745,21 @@ static int batadv_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
struct genl_info *info)
{
struct net *net = genl_info_net(info);
+ struct batadv_hard_iface *hard_iface;
+ struct batadv_priv *bat_priv = NULL;
struct net_device *soft_iface;
- struct batadv_priv *bat_priv;
+ u8 user_ptr1_flags;
+ u8 mesh_dep_flags;
+ int ret;
+
+ user_ptr1_flags = BATADV_FLAG_NEED_HARDIF;
+ if (WARN_ON(hweight8(ops->internal_flags & user_ptr1_flags) > 1))
+ return -EINVAL;
+
+ mesh_dep_flags = BATADV_FLAG_NEED_HARDIF;
+ if (WARN_ON((ops->internal_flags & mesh_dep_flags) &&
+ (~ops->internal_flags & BATADV_FLAG_NEED_MESH)))
+ return -EINVAL;
if (ops->internal_flags & BATADV_FLAG_NEED_MESH) {
soft_iface = batadv_get_softif_from_info(net, info);
@@ -607,7 +770,23 @@ static int batadv_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
info->user_ptr[0] = bat_priv;
}
+ if (ops->internal_flags & BATADV_FLAG_NEED_HARDIF) {
+ hard_iface = batadv_get_hardif_from_info(bat_priv, net, info);
+ if (IS_ERR(hard_iface)) {
+ ret = PTR_ERR(hard_iface);
+ goto err_put_softif;
+ }
+
+ info->user_ptr[1] = hard_iface;
+ }
+
return 0;
+
+err_put_softif:
+ if (bat_priv)
+ dev_put(bat_priv->soft_iface);
+
+ return ret;
}
/**
@@ -619,8 +798,16 @@ static int batadv_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
static void batadv_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
struct genl_info *info)
{
+ struct batadv_hard_iface *hard_iface;
struct batadv_priv *bat_priv;
+ if (ops->internal_flags & BATADV_FLAG_NEED_HARDIF &&
+ info->user_ptr[1]) {
+ hard_iface = info->user_ptr[1];
+
+ batadv_hardif_put(hard_iface);
+ }
+
if (ops->internal_flags & BATADV_FLAG_NEED_MESH && info->user_ptr[0]) {
bat_priv = info->user_ptr[0];
dev_put(bat_priv->soft_iface);
@@ -656,10 +843,13 @@ static const struct genl_ops batadv_netlink_ops[] = {
.dumpit = batadv_algo_dump,
},
{
- .cmd = BATADV_CMD_GET_HARDIFS,
- .flags = GENL_ADMIN_PERM,
+ .cmd = BATADV_CMD_GET_HARDIF,
+ /* can be retrieved by unprivileged users */
.policy = batadv_netlink_policy,
- .dumpit = batadv_netlink_dump_hardifs,
+ .dumpit = batadv_netlink_dump_hardif,
+ .doit = batadv_netlink_get_hardif,
+ .internal_flags = BATADV_FLAG_NEED_MESH |
+ BATADV_FLAG_NEED_HARDIF,
},
{
.cmd = BATADV_CMD_GET_TRANSTABLE_LOCAL,
@@ -722,6 +912,14 @@ static const struct genl_ops batadv_netlink_ops[] = {
.doit = batadv_netlink_set_mesh,
.internal_flags = BATADV_FLAG_NEED_MESH,
},
+ {
+ .cmd = BATADV_CMD_SET_HARDIF,
+ .flags = GENL_ADMIN_PERM,
+ .policy = batadv_netlink_policy,
+ .doit = batadv_netlink_set_hardif,
+ .internal_flags = BATADV_FLAG_NEED_MESH |
+ BATADV_FLAG_NEED_HARDIF,
+ },
};
struct genl_family batadv_netlink_family __ro_after_init = {
--
2.11.0
^ permalink raw reply related
* [PATCH 07/21] batman-adv: Add aggregated_ogms mesh genl configuration
From: Simon Wunderlich @ 2019-02-13 9:55 UTC (permalink / raw)
To: davem; +Cc: netdev, b.a.t.m.a.n, Sven Eckelmann, Simon Wunderlich
In-Reply-To: <20190213095524.10147-1-sw@simonwunderlich.de>
From: Sven Eckelmann <sven@narfation.org>
The mesh interface can delay OGM messages to aggregate different ogms
together in a single OGM packet.
The BATADV_CMD_SET_MESH/BATADV_CMD_GET_MESH commands allow to set/get the
configuration of this feature using the BATADV_ATTR_AGGREGATED_OGMS_ENABLED
attribute. Setting the u8 to zero will disable this feature and setting it
to something else is enabling this feature.
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
include/uapi/linux/batman_adv.h | 6 ++++++
net/batman-adv/netlink.c | 12 ++++++++++++
2 files changed, 18 insertions(+)
diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h
index 10f3cc34fe16..f8941e80d6b4 100644
--- a/include/uapi/linux/batman_adv.h
+++ b/include/uapi/linux/batman_adv.h
@@ -350,6 +350,12 @@ enum batadv_nl_attrs {
*/
BATADV_ATTR_VLANID,
+ /**
+ * @BATADV_ATTR_AGGREGATED_OGMS_ENABLED: whether the batman protocol
+ * messages of the mesh interface shall be aggregated or not.
+ */
+ BATADV_ATTR_AGGREGATED_OGMS_ENABLED,
+
/* add attributes above here, update the policy in netlink.c */
/**
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index d40913bb9031..82665dc2eb2b 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -139,6 +139,7 @@ static const struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = {
[BATADV_ATTR_MCAST_FLAGS] = { .type = NLA_U32 },
[BATADV_ATTR_MCAST_FLAGS_PRIV] = { .type = NLA_U32 },
[BATADV_ATTR_VLANID] = { .type = NLA_U16 },
+ [BATADV_ATTR_AGGREGATED_OGMS_ENABLED] = { .type = NLA_U8 },
};
/**
@@ -214,6 +215,10 @@ static int batadv_netlink_mesh_fill(struct sk_buff *msg,
goto nla_put_failure;
}
+ if (nla_put_u8(msg, BATADV_ATTR_AGGREGATED_OGMS_ENABLED,
+ !!atomic_read(&bat_priv->aggregated_ogms)))
+ goto nla_put_failure;
+
if (primary_if)
batadv_hardif_put(primary_if);
@@ -296,6 +301,13 @@ static int batadv_netlink_get_mesh(struct sk_buff *skb, struct genl_info *info)
static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info)
{
struct batadv_priv *bat_priv = info->user_ptr[0];
+ struct nlattr *attr;
+
+ if (info->attrs[BATADV_ATTR_AGGREGATED_OGMS_ENABLED]) {
+ attr = info->attrs[BATADV_ATTR_AGGREGATED_OGMS_ENABLED];
+
+ atomic_set(&bat_priv->aggregated_ogms, !!nla_get_u8(attr));
+ }
batadv_netlink_notify_mesh(bat_priv);
--
2.11.0
^ permalink raw reply related
* [PATCH 12/21] batman-adv: Add fragmentation mesh genl configuration
From: Simon Wunderlich @ 2019-02-13 9:55 UTC (permalink / raw)
To: davem; +Cc: netdev, b.a.t.m.a.n, Sven Eckelmann, Simon Wunderlich
In-Reply-To: <20190213095524.10147-1-sw@simonwunderlich.de>
From: Sven Eckelmann <sven@narfation.org>
The mesh interface can fragment unicast packets when the packet size
exceeds the outgoing slave/hard-interface MTU.
The BATADV_CMD_SET_MESH/BATADV_CMD_GET_MESH commands allow to set/get the
configuration of this feature using the BATADV_ATTR_FRAGMENTATION_ENABLED
attribute. Setting the u8 to zero will disable this feature and setting it
to something else is enabling this feature.
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
include/uapi/linux/batman_adv.h | 7 +++++++
net/batman-adv/netlink.c | 12 ++++++++++++
2 files changed, 19 insertions(+)
diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h
index f303a1496476..847841b8de5d 100644
--- a/include/uapi/linux/batman_adv.h
+++ b/include/uapi/linux/batman_adv.h
@@ -396,6 +396,13 @@ enum batadv_nl_attrs {
*/
BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED,
+ /**
+ * @BATADV_ATTR_FRAGMENTATION_ENABLED: whether the data traffic going
+ * through the mesh will be fragmented or silently discarded if the
+ * packet size exceeds the outgoing interface MTU.
+ */
+ BATADV_ATTR_FRAGMENTATION_ENABLED,
+
/* add attributes above here, update the policy in netlink.c */
/**
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index 3028c2a5c782..5b2160d2f482 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -146,6 +146,7 @@ static const struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = {
[BATADV_ATTR_BONDING_ENABLED] = { .type = NLA_U8 },
[BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED] = { .type = NLA_U8 },
[BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED] = { .type = NLA_U8 },
+ [BATADV_ATTR_FRAGMENTATION_ENABLED] = { .type = NLA_U8 },
};
/**
@@ -298,6 +299,10 @@ static int batadv_netlink_mesh_fill(struct sk_buff *msg,
goto nla_put_failure;
#endif /* CONFIG_BATMAN_ADV_DAT */
+ if (nla_put_u8(msg, BATADV_ATTR_FRAGMENTATION_ENABLED,
+ !!atomic_read(&bat_priv->fragmentation)))
+ goto nla_put_failure;
+
if (primary_if)
batadv_hardif_put(primary_if);
@@ -432,6 +437,13 @@ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info)
}
#endif /* CONFIG_BATMAN_ADV_DAT */
+ if (info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED]) {
+ attr = info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED];
+
+ atomic_set(&bat_priv->fragmentation, !!nla_get_u8(attr));
+ batadv_update_min_mtu(bat_priv->soft_iface);
+ }
+
batadv_netlink_notify_mesh(bat_priv);
return 0;
--
2.11.0
^ permalink raw reply related
* [PATCH 14/21] batman-adv: Add hop_penalty mesh genl configuration
From: Simon Wunderlich @ 2019-02-13 9:55 UTC (permalink / raw)
To: davem; +Cc: netdev, b.a.t.m.a.n, Sven Eckelmann, Simon Wunderlich
In-Reply-To: <20190213095524.10147-1-sw@simonwunderlich.de>
From: Sven Eckelmann <sven@narfation.org>
The TQ (B.A.T.M.A.N. IV) and throughput values (B.A.T.M.A.N. V) are reduced
when they are forwarded. One of the reductions is the penalty for
traversing an additional hop. This hop_penalty (0-255) defines the
percentage of reduction (0-100%).
The BATADV_CMD_SET_MESH/BATADV_CMD_GET_MESH commands allow to set/get the
configuration of this feature using the u8 BATADV_ATTR_HOP_PENALTY
attribute.
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
include/uapi/linux/batman_adv.h | 6 ++++++
net/batman-adv/netlink.c | 11 +++++++++++
2 files changed, 17 insertions(+)
diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h
index 165272be6878..b37cb923332e 100644
--- a/include/uapi/linux/batman_adv.h
+++ b/include/uapi/linux/batman_adv.h
@@ -443,6 +443,12 @@ enum batadv_nl_attrs {
*/
BATADV_ATTR_GW_SEL_CLASS,
+ /**
+ * @BATADV_ATTR_HOP_PENALTY: defines the penalty which will be applied
+ * to an originator message's tq-field on every hop.
+ */
+ BATADV_ATTR_HOP_PENALTY,
+
/* add attributes above here, update the policy in netlink.c */
/**
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index 473467afea91..ce6e6f078765 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -152,6 +152,7 @@ static const struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = {
[BATADV_ATTR_GW_BANDWIDTH_UP] = { .type = NLA_U32 },
[BATADV_ATTR_GW_MODE] = { .type = NLA_U8 },
[BATADV_ATTR_GW_SEL_CLASS] = { .type = NLA_U32 },
+ [BATADV_ATTR_HOP_PENALTY] = { .type = NLA_U8 },
};
/**
@@ -330,6 +331,10 @@ static int batadv_netlink_mesh_fill(struct sk_buff *msg,
goto nla_put_failure;
}
+ if (nla_put_u8(msg, BATADV_ATTR_HOP_PENALTY,
+ atomic_read(&bat_priv->hop_penalty)))
+ goto nla_put_failure;
+
if (primary_if)
batadv_hardif_put(primary_if);
@@ -536,6 +541,12 @@ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info)
}
}
+ if (info->attrs[BATADV_ATTR_HOP_PENALTY]) {
+ attr = info->attrs[BATADV_ATTR_HOP_PENALTY];
+
+ atomic_set(&bat_priv->hop_penalty, nla_get_u8(attr));
+ }
+
batadv_netlink_notify_mesh(bat_priv);
return 0;
--
2.11.0
^ permalink raw reply related
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