summaryrefslogtreecommitdiff
path: root/drivers/net
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net')
-rw-r--r--drivers/net/Kconfig12
-rw-r--r--drivers/net/Makefile3
-rw-r--r--drivers/net/appletalk/cops.c4
-rw-r--r--drivers/net/appletalk/ltpc.c4
-rw-r--r--drivers/net/arcnet/arcnet.c4
-rw-r--r--drivers/net/bonding/bond_main.c33
-rw-r--r--drivers/net/bonding/bond_options.c2
-rw-r--r--drivers/net/caif/caif_hsi.c15
-rw-r--r--drivers/net/can/grcan.c10
-rw-r--r--drivers/net/can/sja1000/peak_pcmcia.c4
-rw-r--r--drivers/net/can/usb/peak_usb/pcan_usb.c5
-rw-r--r--drivers/net/dsa/b53/b53_common.c155
-rw-r--r--drivers/net/dsa/b53/b53_priv.h145
-rw-r--r--drivers/net/dsa/b53/b53_regs.h48
-rw-r--r--drivers/net/dsa/bcm_sf2.c158
-rw-r--r--drivers/net/dsa/bcm_sf2.h2
-rw-r--r--drivers/net/dsa/bcm_sf2_cfp.c6
-rw-r--r--drivers/net/dsa/bcm_sf2_regs.h11
-rw-r--r--drivers/net/dsa/lan9303-core.c40
-rw-r--r--drivers/net/dsa/lan9303_mdio.c5
-rw-r--r--drivers/net/dsa/mt7530.c7
-rw-r--r--drivers/net/dsa/mv88e6060.c2
-rw-r--r--drivers/net/dsa/qca8k.c2
-rw-r--r--drivers/net/dummy.c4
-rw-r--r--drivers/net/eql.c4
-rw-r--r--drivers/net/ethernet/adi/bfin_mac.c5
-rw-r--r--drivers/net/ethernet/agere/et131x.c5
-rw-r--r--drivers/net/ethernet/amazon/ena/ena_com.c4
-rw-r--r--drivers/net/ethernet/amd/a2065.c7
-rw-r--r--drivers/net/ethernet/amd/am79c961a.c4
-rw-r--r--drivers/net/ethernet/amd/amd8111e.c5
-rw-r--r--drivers/net/ethernet/amd/declance.c6
-rw-r--r--drivers/net/ethernet/amd/pcnet32.c5
-rw-r--r--drivers/net/ethernet/amd/sunlance.c5
-rw-r--r--drivers/net/ethernet/broadcom/b44.c4
-rw-r--r--drivers/net/ethernet/broadcom/bcm63xx_enet.c90
-rw-r--r--drivers/net/ethernet/broadcom/bcm63xx_enet.h1
-rw-r--r--drivers/net/ethernet/broadcom/bnx2.c4
-rw-r--r--drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c4
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt.c6
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c1
-rw-r--r--drivers/net/ethernet/broadcom/tg3.c4
-rw-r--r--drivers/net/ethernet/cavium/liquidio/lio_main.c90
-rw-r--r--drivers/net/ethernet/cavium/liquidio/liquidio_image.h1
-rw-r--r--drivers/net/ethernet/cavium/liquidio/octeon_device.c11
-rw-r--r--drivers/net/ethernet/cavium/liquidio/octeon_device.h10
-rw-r--r--drivers/net/ethernet/cavium/thunder/nicvf_main.c1
-rw-r--r--drivers/net/ethernet/chelsio/cxgb/sge.c5
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/Makefile4
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/cxgb4.h5
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c15
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h1
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c107
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c41
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c452
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h66
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h3
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/l2t.c4
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h6
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c6
-rw-r--r--drivers/net/ethernet/cisco/enic/enic_clsf.h5
-rw-r--r--drivers/net/ethernet/cisco/enic/enic_main.c5
-rw-r--r--drivers/net/ethernet/dec/tulip/de4x5.c5
-rw-r--r--drivers/net/ethernet/dec/tulip/dmfe.c4
-rw-r--r--drivers/net/ethernet/dec/tulip/uli526x.c4
-rw-r--r--drivers/net/ethernet/dec/tulip/winbond-840.c4
-rw-r--r--drivers/net/ethernet/dlink/sundance.c4
-rw-r--r--drivers/net/ethernet/fealnx.c8
-rw-r--r--drivers/net/ethernet/freescale/ucc_geth.c5
-rw-r--r--drivers/net/ethernet/hisilicon/Kconfig9
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hnae3.h17
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile4
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h6
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c304
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h21
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c214
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h8
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c231
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h15
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c106
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c106
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h7
-rw-r--r--drivers/net/ethernet/huawei/hinic/hinic_rx.c18
-rw-r--r--drivers/net/ethernet/huawei/hinic/hinic_tx.c14
-rw-r--r--drivers/net/ethernet/ibm/ibmvnic.c2
-rw-r--r--drivers/net/ethernet/intel/e100.c5
-rw-r--r--drivers/net/ethernet/intel/e1000e/netdev.c11
-rw-r--r--drivers/net/ethernet/intel/fm10k/fm10k.h60
-rw-r--r--drivers/net/ethernet/intel/fm10k/fm10k_common.c6
-rw-r--r--drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c4
-rw-r--r--drivers/net/ethernet/intel/fm10k/fm10k_iov.c176
-rw-r--r--drivers/net/ethernet/intel/fm10k/fm10k_main.c6
-rw-r--r--drivers/net/ethernet/intel/fm10k/fm10k_mbx.c4
-rw-r--r--drivers/net/ethernet/intel/fm10k/fm10k_netdev.c207
-rw-r--r--drivers/net/ethernet/intel/fm10k/fm10k_pci.c474
-rw-r--r--drivers/net/ethernet/intel/fm10k/fm10k_pf.c12
-rw-r--r--drivers/net/ethernet/intel/fm10k/fm10k_pf.h3
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e.h2
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_adminq.c12
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h65
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_common.c207
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_ethtool.c154
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_main.c267
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_prototype.h9
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_txrx.c13
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_type.h19
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c177
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h6
-rw-r--r--drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h65
-rw-r--r--drivers/net/ethernet/intel/i40evf/i40e_common.c69
-rw-r--r--drivers/net/ethernet/intel/i40evf/i40e_prototype.h9
-rw-r--r--drivers/net/ethernet/intel/i40evf/i40e_txrx.c12
-rw-r--r--drivers/net/ethernet/intel/i40evf/i40e_type.h20
-rw-r--r--drivers/net/ethernet/intel/i40evf/i40evf.h4
-rw-r--r--drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c38
-rw-r--r--drivers/net/ethernet/intel/i40evf/i40evf_main.c152
-rw-r--r--drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c46
-rw-r--r--drivers/net/ethernet/intel/ixgb/ixgb_main.c5
-rw-r--r--drivers/net/ethernet/intel/ixgbe/ixgbe_main.c29
-rw-r--r--drivers/net/ethernet/korina.c230
-rw-r--r--drivers/net/ethernet/marvell/mvpp2.c1
-rw-r--r--drivers/net/ethernet/marvell/pxa168_eth.c5
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/catas.c4
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/en_rx.c1
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_rx.c1
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/health.c4
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/Makefile3
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c106
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h11
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/reg.h407
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/resources.h2
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum.c98
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum.h12
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c106
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c129
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h44
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c6
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c397
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h1
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c10
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c1011
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h134
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c838
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h43
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c348
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h21
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c417
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/trap.h6
-rw-r--r--drivers/net/ethernet/natsemi/natsemi.c4
-rw-r--r--drivers/net/ethernet/natsemi/ns83820.c4
-rw-r--r--drivers/net/ethernet/netronome/nfp/Makefile3
-rw-r--r--drivers/net/ethernet/netronome/nfp/flower/action.c169
-rw-r--r--drivers/net/ethernet/netronome/nfp/flower/cmsg.c16
-rw-r--r--drivers/net/ethernet/netronome/nfp/flower/cmsg.h87
-rw-r--r--drivers/net/ethernet/netronome/nfp/flower/main.c13
-rw-r--r--drivers/net/ethernet/netronome/nfp/flower/main.h35
-rw-r--r--drivers/net/ethernet/netronome/nfp/flower/match.c75
-rw-r--r--drivers/net/ethernet/netronome/nfp/flower/metadata.c2
-rw-r--r--drivers/net/ethernet/netronome/nfp/flower/offload.c74
-rw-r--r--drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c811
-rw-r--r--drivers/net/ethernet/netronome/nfp/nfp_net_common.c39
-rw-r--r--drivers/net/ethernet/nvidia/forcedeth.c76
-rw-r--r--drivers/net/ethernet/packetengines/hamachi.c4
-rw-r--r--drivers/net/ethernet/packetengines/yellowfin.c4
-rw-r--r--drivers/net/ethernet/qlogic/qed/qed_cxt.c6
-rw-r--r--drivers/net/ethernet/qlogic/qed/qed_iwarp.c52
-rw-r--r--drivers/net/ethernet/qlogic/qed/qed_iwarp.h11
-rw-r--r--drivers/net/ethernet/qlogic/qed/qed_ll2.c1
-rw-r--r--drivers/net/ethernet/qlogic/qed/qed_mcp.c8
-rw-r--r--drivers/net/ethernet/qlogic/qed/qed_rdma.c24
-rw-r--r--drivers/net/ethernet/qlogic/qed/qed_sp_commands.c1
-rw-r--r--drivers/net/ethernet/qlogic/qede/qede_fp.c1
-rw-r--r--drivers/net/ethernet/qlogic/qla3xxx.c4
-rw-r--r--drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c2
-rw-r--r--drivers/net/ethernet/realtek/atp.c4
-rw-r--r--drivers/net/ethernet/renesas/ravb_main.c55
-rw-r--r--drivers/net/ethernet/sis/sis900.c4
-rw-r--r--drivers/net/ethernet/smsc/epic100.c4
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/stmmac_main.c4
-rw-r--r--drivers/net/ethernet/sun/cassini.c5
-rw-r--r--drivers/net/ethernet/sun/ldmvsw.c2
-rw-r--r--drivers/net/ethernet/sun/niu.c4
-rw-r--r--drivers/net/ethernet/sun/sungem.c4
-rw-r--r--drivers/net/ethernet/ti/cpsw_ale.c4
-rw-r--r--drivers/net/ethernet/ti/netcp_ethss.c5
-rw-r--r--drivers/net/ethernet/toshiba/spider_net.c12
-rw-r--r--drivers/net/hamradio/6pack.c4
-rw-r--r--drivers/net/hamradio/baycom_epp.c50
-rw-r--r--drivers/net/hamradio/mkiss.c3
-rw-r--r--drivers/net/hippi/rrunner.c4
-rw-r--r--drivers/net/hyperv/hyperv_net.h2
-rw-r--r--drivers/net/hyperv/netvsc.c14
-rw-r--r--drivers/net/hyperv/netvsc_drv.c10
-rw-r--r--drivers/net/ieee802154/atusb.c317
-rw-r--r--drivers/net/ieee802154/atusb.h8
-rw-r--r--drivers/net/ifb.c3
-rw-r--r--drivers/net/ipvlan/ipvlan_main.c2
-rw-r--r--drivers/net/macsec.c2
-rw-r--r--drivers/net/macvlan.c20
-rw-r--r--drivers/net/macvtap.c2
-rw-r--r--drivers/net/phy/realtek.c54
-rw-r--r--drivers/net/slip/slip.c8
-rw-r--r--drivers/net/team/team.c5
-rw-r--r--drivers/net/team/team_mode_loadbalance.c8
-rw-r--r--drivers/net/thunderbolt.c1362
-rw-r--r--drivers/net/tun.c288
-rw-r--r--drivers/net/usb/asix_common.c2
-rw-r--r--drivers/net/usb/catc.c4
-rw-r--r--drivers/net/usb/qmi_wwan.c2
-rw-r--r--drivers/net/virtio_net.0
-rw-r--r--drivers/net/virtio_net.c86
-rw-r--r--drivers/net/vrf.c24
-rw-r--r--drivers/net/wan/dscc4.c4
-rw-r--r--drivers/net/wan/hdlc_cisco.c4
-rw-r--r--drivers/net/wan/hdlc_fr.c5
-rw-r--r--drivers/net/wan/hdlc_ppp.c4
-rw-r--r--drivers/net/wan/lmc/lmc_main.c4
-rw-r--r--drivers/net/wan/sdla.c4
-rw-r--r--drivers/net/wireless/ath/ath6kl/txrx.c4
-rw-r--r--drivers/net/wireless/atmel/atmel.c5
-rw-r--r--drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c5
-rw-r--r--drivers/net/wireless/rsi/rsi_91x_hal.c5
-rw-r--r--drivers/net/xen-netback/interface.c3
224 files changed, 11635 insertions, 1874 deletions
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index aba0d652095b..0936da592e12 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -483,6 +483,18 @@ config FUJITSU_ES
This driver provides support for Extended Socket network device
on Extended Partitioning of FUJITSU PRIMEQUEST 2000 E2 series.
+config THUNDERBOLT_NET
+ tristate "Networking over Thunderbolt cable"
+ depends on THUNDERBOLT && INET
+ help
+ Select this if you want to create network between two
+ computers over a Thunderbolt cable. The driver supports Apple
+ ThunderboltIP protocol and allows communication with any host
+ supporting the same protocol including Windows and macOS.
+
+ To compile this driver a module, choose M here. The module will be
+ called thunderbolt-net.
+
source "drivers/net/hyperv/Kconfig"
endif # NETDEVICES
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 8dff900085d6..7c8f4dd3a7c5 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -74,3 +74,6 @@ obj-$(CONFIG_HYPERV_NET) += hyperv/
obj-$(CONFIG_NTB_NETDEV) += ntb_netdev.o
obj-$(CONFIG_FUJITSU_ES) += fjes/
+
+thunderbolt-net-y += thunderbolt.o
+obj-$(CONFIG_THUNDERBOLT_NET) += thunderbolt-net.o
diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c
index 486e1e6997fc..caf04284711a 100644
--- a/drivers/net/appletalk/cops.c
+++ b/drivers/net/appletalk/cops.c
@@ -424,9 +424,7 @@ static int cops_open(struct net_device *dev)
*/
if(lp->board==TANGENT) /* Poll 20 times per second */
{
- init_timer(&cops_timer);
- cops_timer.function = cops_poll;
- cops_timer.data = (unsigned long)dev;
+ setup_timer(&cops_timer, cops_poll, (unsigned long)dev);
cops_timer.expires = jiffies + HZ/20;
add_timer(&cops_timer);
}
diff --git a/drivers/net/appletalk/ltpc.c b/drivers/net/appletalk/ltpc.c
index ac755d2950a6..e4aa374caa4d 100644
--- a/drivers/net/appletalk/ltpc.c
+++ b/drivers/net/appletalk/ltpc.c
@@ -1165,9 +1165,7 @@ struct net_device * __init ltpc_probe(void)
dev->irq = 0;
/* polled mode -- 20 times per second */
/* this is really, really slow... should it poll more often? */
- init_timer(&ltpc_timer);
- ltpc_timer.function=ltpc_poll;
- ltpc_timer.data = (unsigned long) dev;
+ setup_timer(&ltpc_timer, ltpc_poll, (unsigned long)dev);
ltpc_timer.expires = jiffies + HZ/20;
add_timer(&ltpc_timer);
diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c
index fcfccbb3d9a2..13236b2cdf13 100644
--- a/drivers/net/arcnet/arcnet.c
+++ b/drivers/net/arcnet/arcnet.c
@@ -450,9 +450,7 @@ struct net_device *alloc_arcdev(const char *name)
lp->dev = dev;
spin_lock_init(&lp->lock);
- init_timer(&lp->timer);
- lp->timer.data = (unsigned long) dev;
- lp->timer.function = arcnet_timer;
+ setup_timer(&lp->timer, arcnet_timer, (unsigned long)dev);
}
return dev;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index c99dc59d729b..172eeeb68152 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1217,14 +1217,15 @@ static enum netdev_lag_tx_type bond_lag_tx_type(struct bonding *bond)
}
}
-static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave)
+static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave,
+ struct netlink_ext_ack *extack)
{
struct netdev_lag_upper_info lag_upper_info;
int err;
lag_upper_info.tx_type = bond_lag_tx_type(bond);
err = netdev_master_upper_dev_link(slave->dev, bond->dev, slave,
- &lag_upper_info);
+ &lag_upper_info, extack);
if (err)
return err;
rtmsg_ifinfo(RTM_NEWLINK, slave->dev, IFF_SLAVE, GFP_KERNEL);
@@ -1328,7 +1329,8 @@ void bond_lower_state_changed(struct slave *slave)
}
/* enslave device <slave> to bond device <master> */
-int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
+int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
+ struct netlink_ext_ack *extack)
{
struct bonding *bond = netdev_priv(bond_dev);
const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
@@ -1346,12 +1348,14 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
/* already in-use? */
if (netdev_is_rx_handler_busy(slave_dev)) {
+ NL_SET_ERR_MSG(extack, "Device is in use and cannot be enslaved");
netdev_err(bond_dev,
"Error: Device is in use and cannot be enslaved\n");
return -EBUSY;
}
if (bond_dev == slave_dev) {
+ NL_SET_ERR_MSG(extack, "Cannot enslave bond to itself.");
netdev_err(bond_dev, "cannot enslave bond to itself.\n");
return -EPERM;
}
@@ -1362,6 +1366,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
netdev_dbg(bond_dev, "%s is NETIF_F_VLAN_CHALLENGED\n",
slave_dev->name);
if (vlan_uses_dev(bond_dev)) {
+ NL_SET_ERR_MSG(extack, "Can not enslave VLAN challenged device to VLAN enabled bond");
netdev_err(bond_dev, "Error: cannot enslave VLAN challenged slave %s on VLAN enabled bond %s\n",
slave_dev->name, bond_dev->name);
return -EPERM;
@@ -1381,6 +1386,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
* enslaving it; the old ifenslave will not.
*/
if (slave_dev->flags & IFF_UP) {
+ NL_SET_ERR_MSG(extack, "Device can not be enslaved while up");
netdev_err(bond_dev, "%s is up - this may be due to an out of date ifenslave\n",
slave_dev->name);
return -EPERM;
@@ -1421,6 +1427,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
bond_dev);
}
} else if (bond_dev->type != slave_dev->type) {
+ NL_SET_ERR_MSG(extack, "Device type is different from other slaves");
netdev_err(bond_dev, "%s ether type (%d) is different from other slaves (%d), can not enslave it\n",
slave_dev->name, slave_dev->type, bond_dev->type);
return -EINVAL;
@@ -1428,6 +1435,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
if (slave_dev->type == ARPHRD_INFINIBAND &&
BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
+ NL_SET_ERR_MSG(extack, "Only active-backup mode is supported for infiniband slaves");
netdev_warn(bond_dev, "Type (%d) supports only active-backup mode\n",
slave_dev->type);
res = -EOPNOTSUPP;
@@ -1443,6 +1451,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
bond->params.fail_over_mac = BOND_FOM_ACTIVE;
netdev_warn(bond_dev, "Setting fail_over_mac to active for active-backup mode\n");
} else {
+ NL_SET_ERR_MSG(extack, "Slave device does not support setting the MAC address, but fail_over_mac is not set to active");
netdev_err(bond_dev, "The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active\n");
res = -EOPNOTSUPP;
goto err_undo_flags;
@@ -1709,7 +1718,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
goto err_detach;
}
- res = bond_master_upper_dev_link(bond, new_slave);
+ res = bond_master_upper_dev_link(bond, new_slave, extack);
if (res) {
netdev_dbg(bond_dev, "Error %d calling bond_master_upper_dev_link\n", res);
goto err_unregister;
@@ -2491,7 +2500,8 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
struct slave *curr_active_slave, *curr_arp_slave;
unsigned char *arp_ptr;
__be32 sip, tip;
- int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP);
+ int is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP);
+ unsigned int alen;
if (!slave_do_arp_validate(bond, slave)) {
if ((slave_do_arp_validate_only(bond) && is_arp) ||
@@ -3072,7 +3082,16 @@ static int bond_slave_netdev_event(unsigned long event,
break;
case NETDEV_UP:
case NETDEV_CHANGE:
- bond_update_speed_duplex(slave);
+ /* For 802.3ad mode only:
+ * Getting invalid Speed/Duplex values here will put slave
+ * in weird state. So mark it as link-down for the time
+ * being and let link-monitoring (miimon) set it right when
+ * correct speeds/duplex are available.
+ */
+ if (bond_update_speed_duplex(slave) &&
+ BOND_MODE(bond) == BOND_MODE_8023AD)
+ slave->link = BOND_LINK_DOWN;
+
if (BOND_MODE(bond) == BOND_MODE_8023AD)
bond_3ad_adapter_speed_duplex_changed(slave);
/* Fallthrough */
@@ -3482,7 +3501,7 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd
switch (cmd) {
case BOND_ENSLAVE_OLD:
case SIOCBONDENSLAVE:
- res = bond_enslave(bond_dev, slave_dev);
+ res = bond_enslave(bond_dev, slave_dev, NULL);
break;
case BOND_RELEASE_OLD:
case SIOCBONDRELEASE:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 5931aa2fe997..8a9b085c2a98 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1383,7 +1383,7 @@ static int bond_option_slaves_set(struct bonding *bond,
switch (command[0]) {
case '+':
netdev_dbg(bond->dev, "Adding slave %s\n", dev->name);
- ret = bond_enslave(bond->dev, dev);
+ ret = bond_enslave(bond->dev, dev, NULL);
break;
case '-':
diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c
index 438966bf51c2..fed75e75207a 100644
--- a/drivers/net/caif/caif_hsi.c
+++ b/drivers/net/caif/caif_hsi.c
@@ -1211,17 +1211,14 @@ static int cfhsi_open(struct net_device *ndev)
init_waitqueue_head(&cfhsi->flush_fifo_wait);
/* Setup the inactivity timer. */
- init_timer(&cfhsi->inactivity_timer);
- cfhsi->inactivity_timer.data = (unsigned long)cfhsi;
- cfhsi->inactivity_timer.function = cfhsi_inactivity_tout;
+ setup_timer(&cfhsi->inactivity_timer, cfhsi_inactivity_tout,
+ (unsigned long)cfhsi);
/* Setup the slowpath RX timer. */
- init_timer(&cfhsi->rx_slowpath_timer);
- cfhsi->rx_slowpath_timer.data = (unsigned long)cfhsi;
- cfhsi->rx_slowpath_timer.function = cfhsi_rx_slowpath;
+ setup_timer(&cfhsi->rx_slowpath_timer, cfhsi_rx_slowpath,
+ (unsigned long)cfhsi);
/* Setup the aggregation timer. */
- init_timer(&cfhsi->aggregation_timer);
- cfhsi->aggregation_timer.data = (unsigned long)cfhsi;
- cfhsi->aggregation_timer.function = cfhsi_aggregation_tout;
+ setup_timer(&cfhsi->aggregation_timer, cfhsi_aggregation_tout,
+ (unsigned long)cfhsi);
/* Activate HSI interface. */
res = cfhsi->ops->cfhsi_up(cfhsi->ops);
diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c
index a7be12d9a139..8570cfdaea75 100644
--- a/drivers/net/can/grcan.c
+++ b/drivers/net/can/grcan.c
@@ -1626,13 +1626,11 @@ static int grcan_setup_netdev(struct platform_device *ofdev,
spin_lock_init(&priv->lock);
if (priv->need_txbug_workaround) {
- init_timer(&priv->rr_timer);
- priv->rr_timer.function = grcan_running_reset;
- priv->rr_timer.data = (unsigned long)dev;
+ setup_timer(&priv->rr_timer, grcan_running_reset,
+ (unsigned long)dev);
- init_timer(&priv->hang_timer);
- priv->hang_timer.function = grcan_initiate_running_reset;
- priv->hang_timer.data = (unsigned long)dev;
+ setup_timer(&priv->hang_timer, grcan_initiate_running_reset,
+ (unsigned long)dev);
}
netif_napi_add(dev, &priv->napi, grcan_poll, GRCAN_NAPI_WEIGHT);
diff --git a/drivers/net/can/sja1000/peak_pcmcia.c b/drivers/net/can/sja1000/peak_pcmcia.c
index dd56133cc461..4b8758e10bd4 100644
--- a/drivers/net/can/sja1000/peak_pcmcia.c
+++ b/drivers/net/can/sja1000/peak_pcmcia.c
@@ -692,9 +692,7 @@ static int pcan_probe(struct pcmcia_device *pdev)
}
/* init the timer which controls the leds */
- init_timer(&card->led_timer);
- card->led_timer.function = pcan_led_timer;
- card->led_timer.data = (unsigned long)card;
+ setup_timer(&card->led_timer, pcan_led_timer, (unsigned long)card);
/* request the given irq */
err = request_irq(pdev->irq, &pcan_isr, IRQF_SHARED, PCC_NAME, card);
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index 838545ce468d..7e10dbdded28 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -798,9 +798,8 @@ static int pcan_usb_init(struct peak_usb_device *dev)
int err;
/* initialize a timer needed to wait for hardware restart */
- init_timer(&pdev->restart_timer);
- pdev->restart_timer.function = pcan_usb_restart;
- pdev->restart_timer.data = (unsigned long)dev;
+ setup_timer(&pdev->restart_timer, pcan_usb_restart,
+ (unsigned long)dev);
/*
* explicit use of dev_xxx() instead of netdev_xxx() here:
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 274f3679f33d..d4ce092def83 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -484,7 +484,7 @@ static int b53_fast_age_vlan(struct b53_device *dev, u16 vid)
return b53_flush_arl(dev, FAST_AGE_VLAN);
}
-static void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port)
+void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port)
{
struct b53_device *dev = ds->priv;
unsigned int i;
@@ -500,9 +500,9 @@ static void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port)
b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), pvlan);
}
}
+EXPORT_SYMBOL(b53_imp_vlan_setup);
-static int b53_enable_port(struct dsa_switch *ds, int port,
- struct phy_device *phy)
+int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
{
struct b53_device *dev = ds->priv;
unsigned int cpu_port = dev->cpu_port;
@@ -523,11 +523,15 @@ static int b53_enable_port(struct dsa_switch *ds, int port,
b53_imp_vlan_setup(ds, cpu_port);
+ /* If EEE was enabled, restore it */
+ if (dev->ports[port].eee.eee_enabled)
+ b53_eee_enable_set(ds, port, true);
+
return 0;
}
+EXPORT_SYMBOL(b53_enable_port);
-static void b53_disable_port(struct dsa_switch *ds, int port,
- struct phy_device *phy)
+void b53_disable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
{
struct b53_device *dev = ds->priv;
u8 reg;
@@ -537,20 +541,67 @@ static void b53_disable_port(struct dsa_switch *ds, int port,
reg |= PORT_CTRL_RX_DISABLE | PORT_CTRL_TX_DISABLE;
b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), reg);
}
+EXPORT_SYMBOL(b53_disable_port);
-static void b53_enable_cpu_port(struct b53_device *dev)
+void b53_brcm_hdr_setup(struct dsa_switch *ds, int port)
+{
+ struct b53_device *dev = ds->priv;
+ u8 hdr_ctl, val;
+ u16 reg;
+
+ /* Resolve which bit controls the Broadcom tag */
+ switch (port) {
+ case 8:
+ val = BRCM_HDR_P8_EN;
+ break;
+ case 7:
+ val = BRCM_HDR_P7_EN;
+ break;
+ case 5:
+ val = BRCM_HDR_P5_EN;
+ break;
+ default:
+ val = 0;
+ break;
+ }
+
+ /* Enable Broadcom tags for IMP port */
+ b53_read8(dev, B53_MGMT_PAGE, B53_BRCM_HDR, &hdr_ctl);
+ hdr_ctl |= val;
+ b53_write8(dev, B53_MGMT_PAGE, B53_BRCM_HDR, hdr_ctl);
+
+ /* Registers below are only accessible on newer devices */
+ if (!is58xx(dev))
+ return;
+
+ /* Enable reception Broadcom tag for CPU TX (switch RX) to
+ * allow us to tag outgoing frames
+ */
+ b53_read16(dev, B53_MGMT_PAGE, B53_BRCM_HDR_RX_DIS, &reg);
+ reg &= ~BIT(port);
+ b53_write16(dev, B53_MGMT_PAGE, B53_BRCM_HDR_RX_DIS, reg);
+
+ /* Enable transmission of Broadcom tags from the switch (CPU RX) to
+ * allow delivering frames to the per-port net_devices
+ */
+ b53_read16(dev, B53_MGMT_PAGE, B53_BRCM_HDR_TX_DIS, &reg);
+ reg &= ~BIT(port);
+ b53_write16(dev, B53_MGMT_PAGE, B53_BRCM_HDR_TX_DIS, reg);
+}
+EXPORT_SYMBOL(b53_brcm_hdr_setup);
+
+static void b53_enable_cpu_port(struct b53_device *dev, int port)
{
- unsigned int cpu_port = dev->cpu_port;
u8 port_ctrl;
/* BCM5325 CPU port is at 8 */
- if ((is5325(dev) || is5365(dev)) && cpu_port == B53_CPU_PORT_25)
- cpu_port = B53_CPU_PORT;
+ if ((is5325(dev) || is5365(dev)) && port == B53_CPU_PORT_25)
+ port = B53_CPU_PORT;
port_ctrl = PORT_CTRL_RX_BCST_EN |
PORT_CTRL_RX_MCST_EN |
PORT_CTRL_RX_UCST_EN;
- b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(cpu_port), port_ctrl);
+ b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), port_ctrl);
}
static void b53_enable_mib(struct b53_device *dev)
@@ -816,12 +867,13 @@ static int b53_setup(struct dsa_switch *ds)
if (ret)
dev_err(ds->dev, "failed to apply configuration\n");
+ /* Configure IMP/CPU port, disable unused ports. Enabled
+ * ports will be configured with .port_enable
+ */
for (port = 0; port < dev->num_ports; port++) {
- if (BIT(port) & ds->enabled_port_mask)
- b53_enable_port(ds, port, NULL);
- else if (dsa_is_cpu_port(ds, port))
- b53_enable_cpu_port(dev);
- else
+ if (dsa_is_cpu_port(ds, port))
+ b53_enable_cpu_port(dev, port);
+ else if (!(BIT(port) & ds->enabled_port_mask))
b53_disable_port(ds, port, NULL);
}
@@ -832,6 +884,7 @@ static void b53_adjust_link(struct dsa_switch *ds, int port,
struct phy_device *phydev)
{
struct b53_device *dev = ds->priv;
+ struct ethtool_eee *p = &dev->ports[port].eee;
u8 rgmii_ctrl = 0, reg = 0, off;
if (!phy_is_pseudo_fixed_link(phydev))
@@ -953,6 +1006,9 @@ static void b53_adjust_link(struct dsa_switch *ds, int port,
b53_write8(dev, B53_CTRL_PAGE, po_reg, gmii_po);
}
}
+
+ /* Re-negotiate EEE if it was enabled already */
+ p->eee_enabled = b53_eee_init(ds, port, phydev);
}
int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering)
@@ -1280,7 +1336,7 @@ EXPORT_SYMBOL(b53_fdb_dump);
int b53_br_join(struct dsa_switch *ds, int port, struct net_device *br)
{
struct b53_device *dev = ds->priv;
- s8 cpu_port = ds->dst->cpu_dp->index;
+ s8 cpu_port = ds->ports[port].cpu_dp->index;
u16 pvlan, reg;
unsigned int i;
@@ -1326,7 +1382,7 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *br)
{
struct b53_device *dev = ds->priv;
struct b53_vlan *vl = &dev->vlans[0];
- s8 cpu_port = ds->dst->cpu_dp->index;
+ s8 cpu_port = ds->ports[port].cpu_dp->index;
unsigned int i;
u16 pvlan, reg, pvid;
@@ -1484,6 +1540,69 @@ void b53_mirror_del(struct dsa_switch *ds, int port,
}
EXPORT_SYMBOL(b53_mirror_del);
+void b53_eee_enable_set(struct dsa_switch *ds, int port, bool enable)
+{
+ struct b53_device *dev = ds->priv;
+ u16 reg;
+
+ b53_read16(dev, B53_EEE_PAGE, B53_EEE_EN_CTRL, &reg);
+ if (enable)
+ reg |= BIT(port);
+ else
+ reg &= ~BIT(port);
+ b53_write16(dev, B53_EEE_PAGE, B53_EEE_EN_CTRL, reg);
+}
+EXPORT_SYMBOL(b53_eee_enable_set);
+
+
+/* Returns 0 if EEE was not enabled, or 1 otherwise
+ */
+int b53_eee_init(struct dsa_switch *ds, int port, struct phy_device *phy)
+{
+ int ret;
+
+ ret = phy_init_eee(phy, 0);
+ if (ret)
+ return 0;
+
+ b53_eee_enable_set(ds, port, true);
+
+ return 1;
+}
+EXPORT_SYMBOL(b53_eee_init);
+
+int b53_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e)
+{
+ struct b53_device *dev = ds->priv;
+ struct ethtool_eee *p = &dev->ports[port].eee;
+ u16 reg;
+
+ if (is5325(dev) || is5365(dev))
+ return -EOPNOTSUPP;
+
+ b53_read16(dev, B53_EEE_PAGE, B53_EEE_LPI_INDICATE, &reg);
+ e->eee_enabled = p->eee_enabled;
+ e->eee_active = !!(reg & BIT(port));
+
+ return 0;
+}
+EXPORT_SYMBOL(b53_get_mac_eee);
+
+int b53_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e)
+{
+ struct b53_device *dev = ds->priv;
+ struct ethtool_eee *p = &dev->ports[port].eee;
+
+ if (is5325(dev) || is5365(dev))
+ return -EOPNOTSUPP;
+
+ p->eee_enabled = e->eee_enabled;
+ b53_eee_enable_set(ds, port, e->eee_enabled);
+
+ return 0;
+}
+EXPORT_SYMBOL(b53_set_mac_eee);
+
static const struct dsa_switch_ops b53_switch_ops = {
.get_tag_protocol = b53_get_tag_protocol,
.setup = b53_setup,
@@ -1495,6 +1614,8 @@ static const struct dsa_switch_ops b53_switch_ops = {
.adjust_link = b53_adjust_link,
.port_enable = b53_enable_port,
.port_disable = b53_disable_port,
+ .get_mac_eee = b53_get_mac_eee,
+ .set_mac_eee = b53_set_mac_eee,
.port_bridge_join = b53_br_join,
.port_bridge_leave = b53_br_leave,
.port_stp_state_set = b53_br_set_stp_state,
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index 01bd8cbe9a3f..603c66d240d8 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -70,6 +70,7 @@ enum {
struct b53_port {
u16 vlan_ctl_mask;
+ struct ethtool_eee eee;
};
struct b53_vlan {
@@ -186,11 +187,6 @@ static inline int is58xx(struct b53_device *dev)
#define B53_CPU_PORT_25 5
#define B53_CPU_PORT 8
-static inline int is_cpu_port(struct b53_device *dev, int port)
-{
- return dev->cpu_port;
-}
-
struct b53_device *b53_switch_alloc(struct device *base,
const struct b53_io_ops *ops,
void *priv);
@@ -204,119 +200,30 @@ static inline void b53_switch_remove(struct b53_device *dev)
dsa_unregister_switch(dev->ds);
}
-static inline int b53_read8(struct b53_device *dev, u8 page, u8 reg, u8 *val)
-{
- int ret;
-
- mutex_lock(&dev->reg_mutex);
- ret = dev->ops->read8(dev, page, reg, val);
- mutex_unlock(&dev->reg_mutex);
-
- return ret;
+#define b53_build_op(type_op_size, val_type) \
+static inline int b53_##type_op_size(struct b53_device *dev, u8 page, \
+ u8 reg, val_type val) \
+{ \
+ int ret; \
+ \
+ mutex_lock(&dev->reg_mutex); \
+ ret = dev->ops->type_op_size(dev, page, reg, val); \
+ mutex_unlock(&dev->reg_mutex); \
+ \
+ return ret; \
}
-static inline int b53_read16(struct b53_device *dev, u8 page, u8 reg, u16 *val)
-{
- int ret;
-
- mutex_lock(&dev->reg_mutex);
- ret = dev->ops->read16(dev, page, reg, val);
- mutex_unlock(&dev->reg_mutex);
-
- return ret;
-}
-
-static inline int b53_read32(struct b53_device *dev, u8 page, u8 reg, u32 *val)
-{
- int ret;
-
- mutex_lock(&dev->reg_mutex);
- ret = dev->ops->read32(dev, page, reg, val);
- mutex_unlock(&dev->reg_mutex);
-
- return ret;
-}
-
-static inline int b53_read48(struct b53_device *dev, u8 page, u8 reg, u64 *val)
-{
- int ret;
-
- mutex_lock(&dev->reg_mutex);
- ret = dev->ops->read48(dev, page, reg, val);
- mutex_unlock(&dev->reg_mutex);
-
- return ret;
-}
-
-static inline int b53_read64(struct b53_device *dev, u8 page, u8 reg, u64 *val)
-{
- int ret;
-
- mutex_lock(&dev->reg_mutex);
- ret = dev->ops->read64(dev, page, reg, val);
- mutex_unlock(&dev->reg_mutex);
-
- return ret;
-}
+b53_build_op(read8, u8 *);
+b53_build_op(read16, u16 *);
+b53_build_op(read32, u32 *);
+b53_build_op(read48, u64 *);
+b53_build_op(read64, u64 *);
-static inline int b53_write8(struct b53_device *dev, u8 page, u8 reg, u8 value)
-{
- int ret;
-
- mutex_lock(&dev->reg_mutex);
- ret = dev->ops->write8(dev, page, reg, value);
- mutex_unlock(&dev->reg_mutex);
-
- return ret;
-}
-
-static inline int b53_write16(struct b53_device *dev, u8 page, u8 reg,
- u16 value)
-{
- int ret;
-
- mutex_lock(&dev->reg_mutex);
- ret = dev->ops->write16(dev, page, reg, value);
- mutex_unlock(&dev->reg_mutex);
-
- return ret;
-}
-
-static inline int b53_write32(struct b53_device *dev, u8 page, u8 reg,
- u32 value)
-{
- int ret;
-
- mutex_lock(&dev->reg_mutex);
- ret = dev->ops->write32(dev, page, reg, value);
- mutex_unlock(&dev->reg_mutex);
-
- return ret;
-}
-
-static inline int b53_write48(struct b53_device *dev, u8 page, u8 reg,
- u64 value)
-{
- int ret;
-
- mutex_lock(&dev->reg_mutex);
- ret = dev->ops->write48(dev, page, reg, value);
- mutex_unlock(&dev->reg_mutex);
-
- return ret;
-}
-
-static inline int b53_write64(struct b53_device *dev, u8 page, u8 reg,
- u64 value)
-{
- int ret;
-
- mutex_lock(&dev->reg_mutex);
- ret = dev->ops->write64(dev, page, reg, value);
- mutex_unlock(&dev->reg_mutex);
-
- return ret;
-}
+b53_build_op(write8, u8);
+b53_build_op(write16, u16);
+b53_build_op(write32, u32);
+b53_build_op(write48, u64);
+b53_build_op(write64, u64);
struct b53_arl_entry {
u8 port;
@@ -377,6 +284,7 @@ static inline int b53_switch_get_reset_gpio(struct b53_device *dev)
#endif
/* Exported functions towards other drivers */
+void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port);
void b53_get_strings(struct dsa_switch *ds, int port, uint8_t *data);
void b53_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data);
int b53_get_sset_count(struct dsa_switch *ds);
@@ -403,5 +311,12 @@ int b53_mirror_add(struct dsa_switch *ds, int port,
struct dsa_mall_mirror_tc_entry *mirror, bool ingress);
void b53_mirror_del(struct dsa_switch *ds, int port,
struct dsa_mall_mirror_tc_entry *mirror);
+int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy);
+void b53_disable_port(struct dsa_switch *ds, int port, struct phy_device *phy);
+void b53_brcm_hdr_setup(struct dsa_switch *ds, int port);
+void b53_eee_enable_set(struct dsa_switch *ds, int port, bool enable);
+int b53_eee_init(struct dsa_switch *ds, int port, struct phy_device *phy);
+int b53_get_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e);
+int b53_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e);
#endif
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index e5c86d44667a..2a9f421680aa 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -50,6 +50,9 @@
/* Jumbo Frame Registers */
#define B53_JUMBO_PAGE 0x40
+/* EEE Control Registers Page */
+#define B53_EEE_PAGE 0x92
+
/* CFP Configuration Registers Page */
#define B53_CFP_PAGE 0xa1
@@ -210,6 +213,7 @@
#define B53_BRCM_HDR 0x03
#define BRCM_HDR_P8_EN BIT(0) /* Enable tagging on port 8 */
#define BRCM_HDR_P5_EN BIT(1) /* Enable tagging on port 5 */
+#define BRCM_HDR_P7_EN BIT(2) /* Enable tagging on port 7 */
/* Mirror capture control register (16 bit) */
#define B53_MIR_CAP_CTL 0x10
@@ -249,6 +253,12 @@
/* Revision ID register (8 bit) */
#define B53_REV_ID 0x40
+/* Broadcom header RX control (16 bit) */
+#define B53_BRCM_HDR_RX_DIS 0x60
+
+/* Broadcom header TX control (16 bit) */
+#define B53_BRCM_HDR_TX_DIS 0x62
+
/*************************************************************************
* ARL Access Page Registers
*************************************************************************/
@@ -465,6 +475,44 @@
#define JMS_MAX_SIZE 9724
/*************************************************************************
+ * EEE Configuration Page Registers
+ *************************************************************************/
+
+/* EEE Enable control register (16 bit) */
+#define B53_EEE_EN_CTRL 0x00
+
+/* EEE LPI assert status register (16 bit) */
+#define B53_EEE_LPI_ASSERT_STS 0x02
+
+/* EEE LPI indicate status register (16 bit) */
+#define B53_EEE_LPI_INDICATE 0x4
+
+/* EEE Receiving idle symbols status register (16 bit) */
+#define B53_EEE_RX_IDLE_SYM_STS 0x6
+
+/* EEE Pipeline timer register (32 bit) */
+#define B53_EEE_PIP_TIMER 0xC
+
+/* EEE Sleep timer Gig register (32 bit) */
+#define B53_EEE_SLEEP_TIMER_GIG(i) (0x10 + 4 * (i))
+
+/* EEE Sleep timer FE register (32 bit) */
+#define B53_EEE_SLEEP_TIMER_FE(i) (0x34 + 4 * (i))
+
+/* EEE Minimum LP timer Gig register (32 bit) */
+#define B53_EEE_MIN_LP_TIMER_GIG(i) (0x58 + 4 * (i))
+
+/* EEE Minimum LP timer FE register (32 bit) */
+#define B53_EEE_MIN_LP_TIMER_FE(i) (0x7c + 4 * (i))
+
+/* EEE Wake timer Gig register (16 bit) */
+#define B53_EEE_WAKE_TIMER_GIG(i) (0xa0 + 2 * (i))
+
+/* EEE Wake timer FE register (16 bit) */
+#define B53_EEE_WAKE_TIMER_FE(i) (0xb2 + 2 * (i))
+
+
+/*************************************************************************
* CFP Configuration Page Registers
*************************************************************************/
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index d7b53d53c116..7aecc98d0a18 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -40,66 +40,6 @@ static enum dsa_tag_protocol bcm_sf2_sw_get_tag_protocol(struct dsa_switch *ds)
return DSA_TAG_PROTO_BRCM;
}
-static void bcm_sf2_imp_vlan_setup(struct dsa_switch *ds, int cpu_port)
-{
- struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
- unsigned int i;
- u32 reg;
-
- /* Enable the IMP Port to be in the same VLAN as the other ports
- * on a per-port basis such that we only have Port i and IMP in
- * the same VLAN.
- */
- for (i = 0; i < priv->hw_params.num_ports; i++) {
- if (!((1 << i) & ds->enabled_port_mask))
- continue;
-
- reg = core_readl(priv, CORE_PORT_VLAN_CTL_PORT(i));
- reg |= (1 << cpu_port);
- core_writel(priv, reg, CORE_PORT_VLAN_CTL_PORT(i));
- }
-}
-
-static void bcm_sf2_brcm_hdr_setup(struct bcm_sf2_priv *priv, int port)
-{
- u32 reg, val;
-
- /* Resolve which bit controls the Broadcom tag */
- switch (port) {
- case 8:
- val = BRCM_HDR_EN_P8;
- break;
- case 7:
- val = BRCM_HDR_EN_P7;
- break;
- case 5:
- val = BRCM_HDR_EN_P5;
- break;
- default:
- val = 0;
- break;
- }
-
- /* Enable Broadcom tags for IMP port */
- reg = core_readl(priv, CORE_BRCM_HDR_CTRL);
- reg |= val;
- core_writel(priv, reg, CORE_BRCM_HDR_CTRL);
-
- /* Enable reception Broadcom tag for CPU TX (switch RX) to
- * allow us to tag outgoing frames
- */
- reg = core_readl(priv, CORE_BRCM_HDR_RX_DIS);
- reg &= ~(1 << port);
- core_writel(priv, reg, CORE_BRCM_HDR_RX_DIS);
-
- /* Enable transmission of Broadcom tags from the switch (CPU RX) to
- * allow delivering frames to the per-port net_devices
- */
- reg = core_readl(priv, CORE_BRCM_HDR_TX_DIS);
- reg &= ~(1 << port);
- core_writel(priv, reg, CORE_BRCM_HDR_TX_DIS);
-}
-
static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
{
struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
@@ -138,7 +78,7 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
reg |= i << (PRT_TO_QID_SHIFT * i);
core_writel(priv, reg, CORE_PORT_TC2_QOS_MAP_PORT(port));
- bcm_sf2_brcm_hdr_setup(priv, port);
+ b53_brcm_hdr_setup(ds, port);
/* Force link status for IMP port */
reg = core_readl(priv, offset);
@@ -146,19 +86,6 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
core_writel(priv, reg, offset);
}
-static void bcm_sf2_eee_enable_set(struct dsa_switch *ds, int port, bool enable)
-{
- struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
- u32 reg;
-
- reg = core_readl(priv, CORE_EEE_EN_CTRL);
- if (enable)
- reg |= 1 << port;
- else
- reg &= ~(1 << port);
- core_writel(priv, reg, CORE_EEE_EN_CTRL);
-}
-
static void bcm_sf2_gphy_enable_set(struct dsa_switch *ds, bool enable)
{
struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
@@ -236,7 +163,6 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port,
struct phy_device *phy)
{
struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
- s8 cpu_port = ds->dst->cpu_dp->index;
unsigned int i;
u32 reg;
@@ -247,7 +173,7 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port,
/* Enable Broadcom tags for that port if requested */
if (priv->brcm_tag_mask & BIT(port))
- bcm_sf2_brcm_hdr_setup(priv, port);
+ b53_brcm_hdr_setup(ds, port);
/* Configure Traffic Class to QoS mapping, allow each priority to map
* to a different queue number
@@ -257,9 +183,6 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port,
reg |= i << (PRT_TO_QID_SHIFT * i);
core_writel(priv, reg, CORE_PORT_TC2_QOS_MAP_PORT(port));
- /* Clear the Rx and Tx disable bits and set to no spanning tree */
- core_writel(priv, 0, CORE_G_PCTL_PORT(port));
-
/* Re-enable the GPHY and re-apply workarounds */
if (priv->int_phy_mask & 1 << port && priv->hw_params.num_gphy == 1) {
bcm_sf2_gphy_enable_set(ds, true);
@@ -282,23 +205,7 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port,
if (port == priv->moca_port)
bcm_sf2_port_intr_enable(priv, port);
- /* Set this port, and only this one to be in the default VLAN,
- * if member of a bridge, restore its membership prior to
- * bringing down this port.
- */
- reg = core_readl(priv, CORE_PORT_VLAN_CTL_PORT(port));
- reg &= ~PORT_VLAN_CTRL_MASK;
- reg |= (1 << port);
- reg |= priv->dev->ports[port].vlan_ctl_mask;
- core_writel(priv, reg, CORE_PORT_VLAN_CTL_PORT(port));
-
- bcm_sf2_imp_vlan_setup(ds, cpu_port);
-
- /* If EEE was enabled, restore it */
- if (priv->port_sts[port].eee.eee_enabled)
- bcm_sf2_eee_enable_set(ds, port, true);
-
- return 0;
+ return b53_enable_port(ds, port, phy);
}
static void bcm_sf2_port_disable(struct dsa_switch *ds, int port,
@@ -321,9 +228,7 @@ static void bcm_sf2_port_disable(struct dsa_switch *ds, int port,
else
off = CORE_G_PCTL_PORT(port);
- reg = core_readl(priv, off);
- reg |= RX_DIS | TX_DIS;
- core_writel(priv, reg, off);
+ b53_disable_port(ds, port, phy);
/* Power down the port memory */
reg = core_readl(priv, CORE_MEM_PSM_VDD_CTRL);
@@ -331,47 +236,6 @@ static void bcm_sf2_port_disable(struct dsa_switch *ds, int port,
core_writel(priv, reg, CORE_MEM_PSM_VDD_CTRL);
}
-/* Returns 0 if EEE was not enabled, or 1 otherwise
- */
-static int bcm_sf2_eee_init(struct dsa_switch *ds, int port,
- struct phy_device *phy)
-{
- int ret;
-
- ret = phy_init_eee(phy, 0);
- if (ret)
- return 0;
-
- bcm_sf2_eee_enable_set(ds, port, true);
-
- return 1;
-}
-
-static int bcm_sf2_sw_get_mac_eee(struct dsa_switch *ds, int port,
- struct ethtool_eee *e)
-{
- struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
- struct ethtool_eee *p = &priv->port_sts[port].eee;
- u32 reg;
-
- reg = core_readl(priv, CORE_EEE_LPI_INDICATE);
- e->eee_enabled = p->eee_enabled;
- e->eee_active = !!(reg & (1 << port));
-
- return 0;
-}
-
-static int bcm_sf2_sw_set_mac_eee(struct dsa_switch *ds, int port,
- struct ethtool_eee *e)
-{
- struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
- struct ethtool_eee *p = &priv->port_sts[port].eee;
-
- p->eee_enabled = e->eee_enabled;
- bcm_sf2_eee_enable_set(ds, port, e->eee_enabled);
-
- return 0;
-}
static int bcm_sf2_sw_indir_rw(struct bcm_sf2_priv *priv, int op, int addr,
int regnum, u16 val)
@@ -606,7 +470,7 @@ static void bcm_sf2_sw_adjust_link(struct dsa_switch *ds, int port,
struct phy_device *phydev)
{
struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
- struct ethtool_eee *p = &priv->port_sts[port].eee;
+ struct ethtool_eee *p = &priv->dev->ports[port].eee;
u32 id_mode_dis = 0, port_mode;
const char *str = NULL;
u32 reg, offset;
@@ -688,7 +552,7 @@ force_link:
core_writel(priv, reg, offset);
if (!phydev->is_pseudo_fixed_link)
- p->eee_enabled = bcm_sf2_eee_init(ds, port, phydev);
+ p->eee_enabled = b53_eee_init(ds, port, phydev);
}
static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
@@ -797,7 +661,7 @@ static int bcm_sf2_sw_resume(struct dsa_switch *ds)
static void bcm_sf2_sw_get_wol(struct dsa_switch *ds, int port,
struct ethtool_wolinfo *wol)
{
- struct net_device *p = ds->dst->cpu_dp->netdev;
+ struct net_device *p = ds->ports[port].cpu_dp->netdev;
struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
struct ethtool_wolinfo pwol;
@@ -820,9 +684,9 @@ static void bcm_sf2_sw_get_wol(struct dsa_switch *ds, int port,
static int bcm_sf2_sw_set_wol(struct dsa_switch *ds, int port,
struct ethtool_wolinfo *wol)
{
- struct net_device *p = ds->dst->cpu_dp->netdev;
+ struct net_device *p = ds->ports[port].cpu_dp->netdev;
struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
- s8 cpu_port = ds->dst->cpu_dp->index;
+ s8 cpu_port = ds->ports[port].cpu_dp->index;
struct ethtool_wolinfo pwol;
p->ethtool_ops->get_wol(p, &pwol);
@@ -1020,8 +884,8 @@ static const struct dsa_switch_ops bcm_sf2_ops = {
.set_wol = bcm_sf2_sw_set_wol,
.port_enable = bcm_sf2_port_setup,
.port_disable = bcm_sf2_port_disable,
- .get_mac_eee = bcm_sf2_sw_get_mac_eee,
- .set_mac_eee = bcm_sf2_sw_set_mac_eee,
+ .get_mac_eee = b53_get_mac_eee,
+ .set_mac_eee = b53_set_mac_eee,
.port_bridge_join = b53_br_join,
.port_bridge_leave = b53_br_leave,
.port_stp_state_set = b53_br_set_stp_state,
diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index 02c499f9c56b..1922e027ff59 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -48,8 +48,6 @@ struct bcm_sf2_hw_params {
struct bcm_sf2_port_status {
unsigned int link;
-
- struct ethtool_eee eee;
};
struct bcm_sf2_cfp_priv {
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 8a1da7e67707..94649e1481ec 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -144,7 +144,7 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
* destination port is enabled and that we are within the
* number of ports supported by the switch
*/
- port_num = fs->ring_cookie / 8;
+ port_num = fs->ring_cookie / SF2_NUM_EGRESS_QUEUES;
if (fs->ring_cookie == RX_CLS_FLOW_DISC ||
!(BIT(port_num) & ds->enabled_port_mask) ||
@@ -280,7 +280,7 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
* We have a small oddity where Port 6 just does not have a
* valid bit here (so we subtract by one).
*/
- queue_num = fs->ring_cookie % 8;
+ queue_num = fs->ring_cookie % SF2_NUM_EGRESS_QUEUES;
if (port_num >= 7)
port_num -= 1;
@@ -401,7 +401,7 @@ static int bcm_sf2_cfp_rule_get(struct bcm_sf2_priv *priv, int port,
/* There is no Port 6, so we compensate for that here */
if (nfc->fs.ring_cookie >= 6)
nfc->fs.ring_cookie++;
- nfc->fs.ring_cookie *= 8;
+ nfc->fs.ring_cookie *= SF2_NUM_EGRESS_QUEUES;
/* Extract the destination queue */
queue_num = (reg >> NEW_TC_SHIFT) & NEW_TC_MASK;
diff --git a/drivers/net/dsa/bcm_sf2_regs.h b/drivers/net/dsa/bcm_sf2_regs.h
index 49695fcc2ea8..d8b8074a47b9 100644
--- a/drivers/net/dsa/bcm_sf2_regs.h
+++ b/drivers/net/dsa/bcm_sf2_regs.h
@@ -205,16 +205,8 @@ enum bcm_sf2_reg_offs {
#define CORE_IMP0_PRT_ID 0x0804
-#define CORE_BRCM_HDR_CTRL 0x0080c
-#define BRCM_HDR_EN_P8 (1 << 0)
-#define BRCM_HDR_EN_P5 (1 << 1)
-#define BRCM_HDR_EN_P7 (1 << 2)
-
#define CORE_RST_MIB_CNT_EN 0x0950
-#define CORE_BRCM_HDR_RX_DIS 0x0980
-#define CORE_BRCM_HDR_TX_DIS 0x0988
-
#define CORE_ARLA_VTBL_RWCTRL 0x1600
#define ARLA_VTBL_CMD_WRITE 0
#define ARLA_VTBL_CMD_READ 1
@@ -252,9 +244,6 @@ enum bcm_sf2_reg_offs {
#define CORE_JOIN_ALL_VLAN_EN 0xd140
-#define CORE_EEE_EN_CTRL 0x24800
-#define CORE_EEE_LPI_INDICATE 0x24810
-
#define CORE_CFP_ACC 0x28000
#define OP_STR_DONE (1 << 0)
#define OP_SEL_SHIFT 1
diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c
index b471413d3df9..07355db2ad81 100644
--- a/drivers/net/dsa/lan9303-core.c
+++ b/drivers/net/dsa/lan9303-core.c
@@ -17,6 +17,7 @@
#include <linux/regmap.h>
#include <linux/mutex.h>
#include <linux/mii.h>
+#include <linux/phy.h>
#include "lan9303.h"
@@ -57,6 +58,7 @@
#define LAN9303_SWITCH_CSR_CMD_LANES (BIT(19) | BIT(18) | BIT(17) | BIT(16))
#define LAN9303_VIRT_PHY_BASE 0x70
#define LAN9303_VIRT_SPECIAL_CTRL 0x77
+#define LAN9303_VIRT_SPECIAL_TURBO BIT(10) /*Turbo MII Enable*/
/*13.4 Switch Fabric Control and Status Registers
* Accessed indirectly via SWITCH_CSR_CMD, SWITCH_CSR_DATA.
@@ -760,6 +762,43 @@ static int lan9303_phy_write(struct dsa_switch *ds, int phy, int regnum,
return chip->ops->phy_write(chip, phy, regnum, val);
}
+static void lan9303_adjust_link(struct dsa_switch *ds, int port,
+ struct phy_device *phydev)
+{
+ struct lan9303 *chip = ds->priv;
+ int ctl, res;
+
+ if (!phy_is_pseudo_fixed_link(phydev))
+ return;
+
+ ctl = lan9303_phy_read(ds, port, MII_BMCR);
+
+ ctl &= ~BMCR_ANENABLE;
+
+ if (phydev->speed == SPEED_100)
+ ctl |= BMCR_SPEED100;
+ else if (phydev->speed == SPEED_10)
+ ctl &= ~BMCR_SPEED100;
+ else
+ dev_err(ds->dev, "unsupported speed: %d\n", phydev->speed);
+
+ if (phydev->duplex == DUPLEX_FULL)
+ ctl |= BMCR_FULLDPLX;
+ else
+ ctl &= ~BMCR_FULLDPLX;
+
+ res = lan9303_phy_write(ds, port, MII_BMCR, ctl);
+
+ if (port == chip->phy_addr_sel_strap) {
+ /* Virtual Phy: Remove Turbo 200Mbit mode */
+ lan9303_read(chip->regmap, LAN9303_VIRT_SPECIAL_CTRL, &ctl);
+
+ ctl &= ~LAN9303_VIRT_SPECIAL_TURBO;
+ res = regmap_write(chip->regmap,
+ LAN9303_VIRT_SPECIAL_CTRL, ctl);
+ }
+}
+
static int lan9303_port_enable(struct dsa_switch *ds, int port,
struct phy_device *phy)
{
@@ -803,6 +842,7 @@ static const struct dsa_switch_ops lan9303_switch_ops = {
.get_strings = lan9303_get_strings,
.phy_read = lan9303_phy_read,
.phy_write = lan9303_phy_write,
+ .adjust_link = lan9303_adjust_link,
.get_ethtool_stats = lan9303_get_ethtool_stats,
.get_sset_count = lan9303_get_sset_count,
.port_enable = lan9303_port_enable,
diff --git a/drivers/net/dsa/lan9303_mdio.c b/drivers/net/dsa/lan9303_mdio.c
index fc16668a487f..0bc56b9900f9 100644
--- a/drivers/net/dsa/lan9303_mdio.c
+++ b/drivers/net/dsa/lan9303_mdio.c
@@ -67,14 +67,15 @@ static int lan9303_mdio_read(void *ctx, uint32_t reg, uint32_t *val)
return 0;
}
-int lan9303_mdio_phy_write(struct lan9303 *chip, int phy, int reg, u16 val)
+static int lan9303_mdio_phy_write(struct lan9303 *chip, int phy, int reg,
+ u16 val)
{
struct lan9303_mdio *sw_dev = dev_get_drvdata(chip->dev);
return mdiobus_write_nested(sw_dev->device->bus, phy, reg, val);
}
-int lan9303_mdio_phy_read(struct lan9303 *chip, int phy, int reg)
+static int lan9303_mdio_phy_read(struct lan9303 *chip, int phy, int reg)
{
struct lan9303_mdio *sw_dev = dev_get_drvdata(chip->dev);
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index c142b97add2c..034241696ce2 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -564,7 +564,8 @@ static int mt7530_phy_read(struct dsa_switch *ds, int port, int regnum)
return mdiobus_read_nested(priv->bus, port, regnum);
}
-int mt7530_phy_write(struct dsa_switch *ds, int port, int regnum, u16 val)
+static int mt7530_phy_write(struct dsa_switch *ds, int port, int regnum,
+ u16 val)
{
struct mt7530_priv *priv = ds->priv;
@@ -928,11 +929,11 @@ mt7530_setup(struct dsa_switch *ds)
struct device_node *dn;
struct mt7530_dummy_poll p;
- /* The parent node of cpu_dp->netdev which holds the common system
+ /* The parent node of master netdev which holds the common system
* controller also is the container for two GMACs nodes representing
* as two netdev instances.
*/
- dn = ds->dst->cpu_dp->netdev->dev.of_node->parent;
+ dn = ds->ports[MT7530_CPU_PORT].netdev->dev.of_node->parent;
priv->ethernet = syscon_node_to_regmap(dn);
if (IS_ERR(priv->ethernet))
return PTR_ERR(priv->ethernet);
diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c
index dce7fa57eb55..621cdc46ad81 100644
--- a/drivers/net/dsa/mv88e6060.c
+++ b/drivers/net/dsa/mv88e6060.c
@@ -176,7 +176,7 @@ static int mv88e6060_setup_port(struct dsa_switch *ds, int p)
((p & 0xf) << PORT_VLAN_MAP_DBNUM_SHIFT) |
(dsa_is_cpu_port(ds, p) ?
ds->enabled_port_mask :
- BIT(ds->dst->cpu_dp->index)));
+ BIT(ds->ports[p].cpu_dp->index)));
/* Port Association Vector: when learning source addresses
* of packets, add the address to the address database using
diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c
index 5ada7a41449c..82f09711ac1a 100644
--- a/drivers/net/dsa/qca8k.c
+++ b/drivers/net/dsa/qca8k.c
@@ -506,7 +506,7 @@ qca8k_setup(struct dsa_switch *ds)
pr_warn("regmap initialization failed");
/* Initialize CPU port pad mode (xMII type, delays...) */
- phy_mode = of_get_phy_mode(ds->dst->cpu_dp->dn);
+ phy_mode = of_get_phy_mode(ds->ports[QCA8K_CPU_PORT].dn);
if (phy_mode < 0) {
pr_err("Can't find phy-mode for master device\n");
return phy_mode;
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index d0a1f9ce3168..58483af80bdb 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -353,7 +353,7 @@ static void dummy_setup(struct net_device *dev)
eth_hw_addr_random(dev);
dev->min_mtu = 0;
- dev->max_mtu = ETH_MAX_MTU;
+ dev->max_mtu = 0;
}
static int dummy_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -388,7 +388,7 @@ static int __init dummy_init_one(void)
int err;
dev_dummy = alloc_netdev(sizeof(struct dummy_priv),
- "dummy%d", NET_NAME_UNKNOWN, dummy_setup);
+ "dummy%d", NET_NAME_ENUM, dummy_setup);
if (!dev_dummy)
return -ENOMEM;
diff --git a/drivers/net/eql.c b/drivers/net/eql.c
index fe13bfea30ac..fccce4b47778 100644
--- a/drivers/net/eql.c
+++ b/drivers/net/eql.c
@@ -178,10 +178,8 @@ static void __init eql_setup(struct net_device *dev)
{
equalizer_t *eql = netdev_priv(dev);
- init_timer(&eql->timer);
- eql->timer.data = (unsigned long) eql;
+ setup_timer(&eql->timer, eql_timer, (unsigned long)eql);
eql->timer.expires = jiffies + EQL_DEFAULT_RESCHED_IVAL;
- eql->timer.function = eql_timer;
spin_lock_init(&eql->queue.lock);
INIT_LIST_HEAD(&eql->queue.all_slaves);
diff --git a/drivers/net/ethernet/adi/bfin_mac.c b/drivers/net/ethernet/adi/bfin_mac.c
index a251de8d9a91..0658cde1586a 100644
--- a/drivers/net/ethernet/adi/bfin_mac.c
+++ b/drivers/net/ethernet/adi/bfin_mac.c
@@ -1650,9 +1650,8 @@ static int bfin_mac_probe(struct platform_device *pdev)
ndev->netdev_ops = &bfin_mac_netdev_ops;
ndev->ethtool_ops = &bfin_mac_ethtool_ops;
- init_timer(&lp->tx_reclaim_timer);
- lp->tx_reclaim_timer.data = (unsigned long)lp;
- lp->tx_reclaim_timer.function = tx_reclaim_skb_timeout;
+ setup_timer(&lp->tx_reclaim_timer, tx_reclaim_skb_timeout,
+ (unsigned long)lp);
lp->flags = 0;
netif_napi_add(ndev, &lp->napi, bfin_mac_poll, CONFIG_BFIN_RX_DESC_NUM);
diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c
index 54eff90e2f02..658e92f79d36 100644
--- a/drivers/net/ethernet/agere/et131x.c
+++ b/drivers/net/ethernet/agere/et131x.c
@@ -3624,11 +3624,10 @@ static int et131x_open(struct net_device *netdev)
int result;
/* Start the timer to track NIC errors */
- init_timer(&adapter->error_timer);
+ setup_timer(&adapter->error_timer, et131x_error_timer_handler,
+ (unsigned long)adapter);
adapter->error_timer.expires = jiffies +
msecs_to_jiffies(TX_ERROR_PERIOD);
- adapter->error_timer.function = et131x_error_timer_handler;
- adapter->error_timer.data = (unsigned long)adapter;
add_timer(&adapter->error_timer);
result = request_irq(irq, et131x_isr,
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 52beba8c7a39..ded29af648c9 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -315,7 +315,7 @@ static struct ena_comp_ctx *ena_com_submit_admin_cmd(struct ena_com_admin_queue
cmd_size_in_bytes,
comp,
comp_size_in_bytes);
- if (unlikely(IS_ERR(comp_ctx)))
+ if (IS_ERR(comp_ctx))
admin_queue->running_state = false;
spin_unlock_irqrestore(&admin_queue->q_lock, flags);
@@ -1130,7 +1130,7 @@ int ena_com_execute_admin_command(struct ena_com_admin_queue *admin_queue,
comp_ctx = ena_com_submit_admin_cmd(admin_queue, cmd, cmd_size,
comp, comp_size);
- if (unlikely(IS_ERR(comp_ctx))) {
+ if (IS_ERR(comp_ctx)) {
if (comp_ctx == ERR_PTR(-ENODEV))
pr_debug("Failed to submit command [%ld]\n",
PTR_ERR(comp_ctx));
diff --git a/drivers/net/ethernet/amd/a2065.c b/drivers/net/ethernet/amd/a2065.c
index e22f976a0d18..998d30e050a6 100644
--- a/drivers/net/ethernet/amd/a2065.c
+++ b/drivers/net/ethernet/amd/a2065.c
@@ -733,10 +733,9 @@ static int a2065_init_one(struct zorro_dev *z,
dev->watchdog_timeo = 5*HZ;
dev->dma = 0;
- init_timer(&priv->multicast_timer);
- priv->multicast_timer.data = (unsigned long) dev;
- priv->multicast_timer.function =
- (void (*)(unsigned long))lance_set_multicast;
+ setup_timer(&priv->multicast_timer,
+ (void(*)(unsigned long))lance_set_multicast,
+ (unsigned long)dev);
err = register_netdev(dev);
if (err) {
diff --git a/drivers/net/ethernet/amd/am79c961a.c b/drivers/net/ethernet/amd/am79c961a.c
index b11e910850f7..0612dbee00d2 100644
--- a/drivers/net/ethernet/amd/am79c961a.c
+++ b/drivers/net/ethernet/amd/am79c961a.c
@@ -728,9 +728,7 @@ static int am79c961_probe(struct platform_device *pdev)
am79c961_banner();
spin_lock_init(&priv->chip_lock);
- init_timer(&priv->timer);
- priv->timer.data = (unsigned long)dev;
- priv->timer.function = am79c961_timer;
+ setup_timer(&priv->timer, am79c961_timer, (unsigned long)dev);
if (am79c961_hw_init(dev))
goto release;
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index 7b5df562f30f..7f22af6e37e0 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -1883,9 +1883,8 @@ static int amd8111e_probe_one(struct pci_dev *pdev,
/* Initialize software ipg timer */
if(lp->options & OPTION_DYN_IPG_ENABLE){
- init_timer(&lp->ipg_data.ipg_timer);
- lp->ipg_data.ipg_timer.data = (unsigned long) dev;
- lp->ipg_data.ipg_timer.function = (void *)&amd8111e_config_ipg;
+ setup_timer(&lp->ipg_data.ipg_timer,
+ (void *)&amd8111e_config_ipg, (unsigned long)dev);
lp->ipg_data.ipg_timer.expires = jiffies +
IPG_CONVERGE_JIFFIES;
lp->ipg_data.ipg = DEFAULT_IPG;
diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c
index 82cc81385033..9bdf81c2cd00 100644
--- a/drivers/net/ethernet/amd/declance.c
+++ b/drivers/net/ethernet/amd/declance.c
@@ -1246,9 +1246,9 @@ static int dec_lance_probe(struct device *bdev, const int type)
* can occur from interrupts (ex. IPv6). So we
* use a timer to try again later when necessary. -DaveM
*/
- init_timer(&lp->multicast_timer);
- lp->multicast_timer.data = (unsigned long) dev;
- lp->multicast_timer.function = lance_set_multicast_retry;
+ setup_timer(&lp->multicast_timer, lance_set_multicast_retry,
+ (unsigned long)dev);
+
ret = register_netdev(dev);
if (ret) {
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index 7f60d17819ce..e46153654016 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -1970,9 +1970,8 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
lp->options |= PCNET32_PORT_MII;
}
- init_timer(&lp->watchdog_timer);
- lp->watchdog_timer.data = (unsigned long)dev;
- lp->watchdog_timer.function = (void *)&pcnet32_watchdog;
+ setup_timer(&lp->watchdog_timer, (void *)&pcnet32_watchdog,
+ (unsigned long)dev);
/* The PCNET32-specific entries in the device structure. */
dev->netdev_ops = &pcnet32_netdev_ops;
diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c
index 291ca5187f12..0183ffb9d3ba 100644
--- a/drivers/net/ethernet/amd/sunlance.c
+++ b/drivers/net/ethernet/amd/sunlance.c
@@ -1459,9 +1459,8 @@ no_link_test:
* can occur from interrupts (ex. IPv6). So we
* use a timer to try again later when necessary. -DaveM
*/
- init_timer(&lp->multicast_timer);
- lp->multicast_timer.data = (unsigned long) dev;
- lp->multicast_timer.function = lance_set_multicast_retry;
+ setup_timer(&lp->multicast_timer, lance_set_multicast_retry,
+ (unsigned long)dev);
if (register_netdev(dev)) {
printk(KERN_ERR "SunLance: Cannot register device.\n");
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index a1125d10c825..42e44fc03a18 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -1474,10 +1474,8 @@ static int b44_open(struct net_device *dev)
goto out;
}
- init_timer(&bp->timer);
+ setup_timer(&bp->timer, b44_timer, (unsigned long)bp);
bp->timer.expires = jiffies + HZ;
- bp->timer.data = (unsigned long) bp;
- bp->timer.function = b44_timer;
add_timer(&bp->timer);
b44_enable_ints(bp);
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 4f3845a58126..f6bc13fe8a99 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -1062,7 +1062,8 @@ static int bcm_enet_open(struct net_device *dev)
val = enet_readl(priv, ENET_CTL_REG);
val |= ENET_CTL_ENABLE_MASK;
enet_writel(priv, val, ENET_CTL_REG);
- enet_dma_writel(priv, ENETDMA_CFG_EN_MASK, ENETDMA_CFG_REG);
+ if (priv->dma_has_sram)
+ enet_dma_writel(priv, ENETDMA_CFG_EN_MASK, ENETDMA_CFG_REG);
enet_dmac_writel(priv, priv->dma_chan_en_mask,
ENETDMAC_CHANCFG, priv->rx_chan);
@@ -1721,10 +1722,8 @@ static int bcm_enet_probe(struct platform_device *pdev)
const char *clk_name;
int i, ret;
- /* stop if shared driver failed, assume driver->probe will be
- * called in the same order we register devices (correct ?) */
if (!bcm_enet_shared_base[0])
- return -ENODEV;
+ return -EPROBE_DEFER;
res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
res_irq_rx = platform_get_resource(pdev, IORESOURCE_IRQ, 1);
@@ -1768,12 +1767,14 @@ static int bcm_enet_probe(struct platform_device *pdev)
clk_name = "enet1";
}
- priv->mac_clk = clk_get(&pdev->dev, clk_name);
+ priv->mac_clk = devm_clk_get(&pdev->dev, clk_name);
if (IS_ERR(priv->mac_clk)) {
ret = PTR_ERR(priv->mac_clk);
goto out;
}
- clk_prepare_enable(priv->mac_clk);
+ ret = clk_prepare_enable(priv->mac_clk);
+ if (ret)
+ goto out;
/* initialize default and fetch platform data */
priv->rx_ring_size = BCMENET_DEF_RX_DESC;
@@ -1801,13 +1802,15 @@ static int bcm_enet_probe(struct platform_device *pdev)
if (priv->mac_id == 0 && priv->has_phy && !priv->use_external_mii) {
/* using internal PHY, enable clock */
- priv->phy_clk = clk_get(&pdev->dev, "ephy");
+ priv->phy_clk = devm_clk_get(&pdev->dev, "ephy");
if (IS_ERR(priv->phy_clk)) {
ret = PTR_ERR(priv->phy_clk);
priv->phy_clk = NULL;
- goto out_put_clk_mac;
+ goto out_disable_clk_mac;
}
- clk_prepare_enable(priv->phy_clk);
+ ret = clk_prepare_enable(priv->phy_clk);
+ if (ret)
+ goto out_disable_clk_mac;
}
/* do minimal hardware init to be able to probe mii bus */
@@ -1857,9 +1860,8 @@ static int bcm_enet_probe(struct platform_device *pdev)
spin_lock_init(&priv->rx_lock);
/* init rx timeout (used for oom) */
- init_timer(&priv->rx_timeout);
- priv->rx_timeout.function = bcm_enet_refill_rx_timer;
- priv->rx_timeout.data = (unsigned long)dev;
+ setup_timer(&priv->rx_timeout, bcm_enet_refill_rx_timer,
+ (unsigned long)dev);
/* init the mib update lock&work */
mutex_init(&priv->mib_update_lock);
@@ -1901,14 +1903,10 @@ out_free_mdio:
out_uninit_hw:
/* turn off mdc clock */
enet_writel(priv, 0, ENET_MIISC_REG);
- if (priv->phy_clk) {
- clk_disable_unprepare(priv->phy_clk);
- clk_put(priv->phy_clk);
- }
+ clk_disable_unprepare(priv->phy_clk);
-out_put_clk_mac:
+out_disable_clk_mac:
clk_disable_unprepare(priv->mac_clk);
- clk_put(priv->mac_clk);
out:
free_netdev(dev);
return ret;
@@ -1944,12 +1942,8 @@ static int bcm_enet_remove(struct platform_device *pdev)
}
/* disable hw block clocks */
- if (priv->phy_clk) {
- clk_disable_unprepare(priv->phy_clk);
- clk_put(priv->phy_clk);
- }
+ clk_disable_unprepare(priv->phy_clk);
clk_disable_unprepare(priv->mac_clk);
- clk_put(priv->mac_clk);
free_netdev(dev);
return 0;
@@ -2332,11 +2326,8 @@ static int bcm_enetsw_open(struct net_device *dev)
}
/* start phy polling timer */
- init_timer(&priv->swphy_poll);
- priv->swphy_poll.function = swphy_poll_timer;
- priv->swphy_poll.data = (unsigned long)priv;
- priv->swphy_poll.expires = jiffies;
- add_timer(&priv->swphy_poll);
+ setup_timer(&priv->swphy_poll, swphy_poll_timer, (unsigned long)priv);
+ mod_timer(&priv->swphy_poll, jiffies);
return 0;
out:
@@ -2692,11 +2683,8 @@ static int bcm_enetsw_probe(struct platform_device *pdev)
struct resource *res_mem;
int ret, irq_rx, irq_tx;
- /* stop if shared driver failed, assume driver->probe will be
- * called in the same order we register devices (correct ?)
- */
if (!bcm_enet_shared_base[0])
- return -ENODEV;
+ return -EPROBE_DEFER;
res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
irq_rx = platform_get_irq(pdev, 0);
@@ -2735,24 +2723,20 @@ static int bcm_enetsw_probe(struct platform_device *pdev)
if (ret)
goto out;
- if (!request_mem_region(res_mem->start, resource_size(res_mem),
- "bcm63xx_enetsw")) {
- ret = -EBUSY;
+ priv->base = devm_ioremap_resource(&pdev->dev, res_mem);
+ if (IS_ERR(priv->base)) {
+ ret = PTR_ERR(priv->base);
goto out;
}
- priv->base = ioremap(res_mem->start, resource_size(res_mem));
- if (priv->base == NULL) {
- ret = -ENOMEM;
- goto out_release_mem;
- }
-
- priv->mac_clk = clk_get(&pdev->dev, "enetsw");
+ priv->mac_clk = devm_clk_get(&pdev->dev, "enetsw");
if (IS_ERR(priv->mac_clk)) {
ret = PTR_ERR(priv->mac_clk);
- goto out_unmap;
+ goto out;
}
- clk_enable(priv->mac_clk);
+ ret = clk_prepare_enable(priv->mac_clk);
+ if (ret)
+ goto out;
priv->rx_chan = 0;
priv->tx_chan = 1;
@@ -2773,7 +2757,7 @@ static int bcm_enetsw_probe(struct platform_device *pdev)
ret = register_netdev(dev);
if (ret)
- goto out_put_clk;
+ goto out_disable_clk;
netif_carrier_off(dev);
platform_set_drvdata(pdev, dev);
@@ -2782,14 +2766,8 @@ static int bcm_enetsw_probe(struct platform_device *pdev)
return 0;
-out_put_clk:
- clk_put(priv->mac_clk);
-
-out_unmap:
- iounmap(priv->base);
-
-out_release_mem:
- release_mem_region(res_mem->start, resource_size(res_mem));
+out_disable_clk:
+ clk_disable_unprepare(priv->mac_clk);
out:
free_netdev(dev);
return ret;
@@ -2801,17 +2779,13 @@ static int bcm_enetsw_remove(struct platform_device *pdev)
{
struct bcm_enet_priv *priv;
struct net_device *dev;
- struct resource *res;
/* stop netdevice */
dev = platform_get_drvdata(pdev);
priv = netdev_priv(dev);
unregister_netdev(dev);
- /* release device resources */
- iounmap(priv->base);
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- release_mem_region(res->start, resource_size(res));
+ clk_disable_unprepare(priv->mac_clk);
free_netdev(dev);
return 0;
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.h b/drivers/net/ethernet/broadcom/bcm63xx_enet.h
index 0a1b7b2e55bd..dd6ae3077433 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.h
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.h
@@ -8,7 +8,6 @@
#include <linux/platform_device.h>
#include <bcm63xx_regs.h>
-#include <bcm63xx_irq.h>
#include <bcm63xx_io.h>
#include <bcm63xx_iudma.h>
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index e3af1f3cb61f..b3055a76dfbf 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -8462,10 +8462,8 @@ bnx2_init_board(struct pci_dev *pdev, struct net_device *dev)
bnx2_set_default_link(bp);
bp->req_flow_ctrl = FLOW_CTRL_RX | FLOW_CTRL_TX;
- init_timer(&bp->timer);
+ setup_timer(&bp->timer, bnx2_timer, (unsigned long)bp);
bp->timer.expires = RUN_AT(BNX2_TIMER_INTERVAL);
- bp->timer.data = (unsigned long) bp;
- bp->timer.function = bnx2_timer;
#ifdef BCM_CNIC
if (bnx2_shmem_rd(bp, BNX2_ISCSI_INITIATOR) & BNX2_ISCSI_INITIATOR_EN)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index c12b4d3e946e..54d1571384a0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -12414,10 +12414,8 @@ static int bnx2x_init_bp(struct bnx2x *bp)
bp->current_interval = CHIP_REV_IS_SLOW(bp) ? 5*HZ : HZ;
- init_timer(&bp->timer);
+ setup_timer(&bp->timer, bnx2x_timer, (unsigned long)bp);
bp->timer.expires = jiffies + bp->current_interval;
- bp->timer.data = (unsigned long) bp;
- bp->timer.function = bnx2x_timer;
if (SHMEM2_HAS(bp, dcbx_lldp_params_offset) &&
SHMEM2_HAS(bp, dcbx_lldp_dcbx_stat_offset) &&
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index aacec8bc19d5..5ba49938ba55 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1491,7 +1491,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons,
(struct rx_tpa_end_cmp *)rxcmp,
(struct rx_tpa_end_cmp_ext *)rxcmp1, event);
- if (unlikely(IS_ERR(skb)))
+ if (IS_ERR(skb))
return -EBUSY;
rc = -ENOMEM;
@@ -7190,9 +7190,7 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev)
bp->stats_coal_ticks = BNXT_DEF_STATS_COAL_TICKS;
- init_timer(&bp->timer);
- bp->timer.data = (unsigned long)bp;
- bp->timer.function = bnxt_timer;
+ setup_timer(&bp->timer, bnxt_timer, (unsigned long)bp);
bp->current_interval = BNXT_TIMER_INTERVAL;
clear_bit(BNXT_STATE_OPEN, &bp->state);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index d8f0c837b72c..06ce63c00821 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -94,6 +94,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
xdp.data_hard_start = *data_ptr - offset;
xdp.data = *data_ptr;
+ xdp_set_data_meta_invalid(&xdp);
xdp.data_end = *data_ptr + *len;
orig_data = xdp.data;
mapping = rx_buf->mapping - bp->rx_dma_offset;
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 656e6af70f0a..d8d5f207c759 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -11087,9 +11087,7 @@ static void tg3_timer_init(struct tg3 *tp)
tp->asf_multiplier = (HZ / tp->timer_offset) *
TG3_FW_UPDATE_FREQ_SEC;
- init_timer(&tp->timer);
- tp->timer.data = (unsigned long) tp;
- tp->timer.function = tg3_timer;
+ setup_timer(&tp->timer, tg3_timer, (unsigned long)tp);
}
static void tg3_timer_start(struct tg3 *tp)
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index e7f54948173f..963803bc6633 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -59,9 +59,9 @@ static int debug = -1;
module_param(debug, int, 0644);
MODULE_PARM_DESC(debug, "NETIF_MSG debug bits");
-static char fw_type[LIO_MAX_FW_TYPE_LEN] = LIO_FW_NAME_TYPE_NIC;
+static char fw_type[LIO_MAX_FW_TYPE_LEN] = LIO_FW_NAME_TYPE_AUTO;
module_param_string(fw_type, fw_type, sizeof(fw_type), 0444);
-MODULE_PARM_DESC(fw_type, "Type of firmware to be loaded. Default \"nic\". Use \"none\" to load firmware from flash.");
+MODULE_PARM_DESC(fw_type, "Type of firmware to be loaded (default is \"auto\"), which uses firmware in flash, if present, else loads \"nic\".");
static u32 console_bitmask;
module_param(console_bitmask, int, 0644);
@@ -1115,10 +1115,10 @@ liquidio_probe(struct pci_dev *pdev,
return 0;
}
-static bool fw_type_is_none(void)
+static bool fw_type_is_auto(void)
{
- return strncmp(fw_type, LIO_FW_NAME_TYPE_NONE,
- sizeof(LIO_FW_NAME_TYPE_NONE)) == 0;
+ return strncmp(fw_type, LIO_FW_NAME_TYPE_AUTO,
+ sizeof(LIO_FW_NAME_TYPE_AUTO)) == 0;
}
/**
@@ -1302,7 +1302,7 @@ static void octeon_destroy_resources(struct octeon_device *oct)
* Implementation note: only soft-reset the device
* if it is a CN6XXX OR the LAST CN23XX device.
*/
- if (fw_type_is_none())
+ if (atomic_read(oct->adapter_fw_state) == FW_IS_PRELOADED)
octeon_pci_flr(oct);
else if (OCTEON_CN6XXX(oct) || !refcount)
oct->fn_list.soft_reset(oct);
@@ -1934,10 +1934,12 @@ static int load_firmware(struct octeon_device *oct)
char fw_name[LIO_MAX_FW_FILENAME_LEN];
char *tmp_fw_type;
- if (fw_type[0] == '\0')
+ if (fw_type_is_auto()) {
tmp_fw_type = LIO_FW_NAME_TYPE_NIC;
- else
+ strncpy(fw_type, tmp_fw_type, sizeof(fw_type));
+ } else {
tmp_fw_type = fw_type;
+ }
sprintf(fw_name, "%s%s%s_%s%s", LIO_FW_DIR, LIO_FW_BASE_NAME,
octeon_get_conf(oct)->card_name, tmp_fw_type,
@@ -3303,7 +3305,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
{
struct lio *lio = NULL;
struct net_device *netdev;
- u8 mac[6], i, j;
+ u8 mac[6], i, j, *fw_ver;
struct octeon_soft_command *sc;
struct liquidio_if_cfg_context *ctx;
struct liquidio_if_cfg_resp *resp;
@@ -3414,6 +3416,22 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
goto setup_nic_dev_fail;
}
+ /* Verify f/w version (in case of 'auto' loading from flash) */
+ fw_ver = octeon_dev->fw_info.liquidio_firmware_version;
+ if (memcmp(LIQUIDIO_BASE_VERSION,
+ fw_ver,
+ strlen(LIQUIDIO_BASE_VERSION))) {
+ dev_err(&octeon_dev->pci_dev->dev,
+ "Unmatched firmware version. Expected %s.x, got %s.\n",
+ LIQUIDIO_BASE_VERSION, fw_ver);
+ goto setup_nic_dev_fail;
+ } else if (atomic_read(octeon_dev->adapter_fw_state) ==
+ FW_IS_PRELOADED) {
+ dev_info(&octeon_dev->pci_dev->dev,
+ "Using auto-loaded firmware version %s.\n",
+ fw_ver);
+ }
+
octeon_swap_8B_data((u64 *)(&resp->cfg_info),
(sizeof(struct liquidio_if_cfg_info)) >> 3);
@@ -3882,9 +3900,9 @@ octeon_recv_vf_drv_notice(struct octeon_recv_info *recv_info, void *buf)
static int octeon_device_init(struct octeon_device *octeon_dev)
{
int j, ret;
- int fw_loaded = 0;
char bootcmd[] = "\n";
char *dbg_enb = NULL;
+ enum lio_fw_state fw_state;
struct octeon_device_priv *oct_priv =
(struct octeon_device_priv *)octeon_dev->priv;
atomic_set(&octeon_dev->status, OCT_DEV_BEGIN_STATE);
@@ -3916,24 +3934,40 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
octeon_dev->app_mode = CVM_DRV_INVALID_APP;
- if (OCTEON_CN23XX_PF(octeon_dev)) {
- if (!cn23xx_fw_loaded(octeon_dev) && !fw_type_is_none()) {
- fw_loaded = 0;
- /* Do a soft reset of the Octeon device. */
- if (octeon_dev->fn_list.soft_reset(octeon_dev))
- return 1;
- /* things might have changed */
- if (!cn23xx_fw_loaded(octeon_dev))
- fw_loaded = 0;
- else
- fw_loaded = 1;
- } else {
- fw_loaded = 1;
- }
- } else if (octeon_dev->fn_list.soft_reset(octeon_dev)) {
- return 1;
+ /* CN23XX supports preloaded firmware if the following is true:
+ *
+ * The adapter indicates that firmware is currently running AND
+ * 'fw_type' is 'auto'.
+ *
+ * (default state is NEEDS_TO_BE_LOADED, override it if appropriate).
+ */
+ if (OCTEON_CN23XX_PF(octeon_dev) &&
+ cn23xx_fw_loaded(octeon_dev) && fw_type_is_auto()) {
+ atomic_cmpxchg(octeon_dev->adapter_fw_state,
+ FW_NEEDS_TO_BE_LOADED, FW_IS_PRELOADED);
}
+ /* If loading firmware, only first device of adapter needs to do so. */
+ fw_state = atomic_cmpxchg(octeon_dev->adapter_fw_state,
+ FW_NEEDS_TO_BE_LOADED,
+ FW_IS_BEING_LOADED);
+
+ /* Here, [local variable] 'fw_state' is set to one of:
+ *
+ * FW_IS_PRELOADED: No firmware is to be loaded (see above)
+ * FW_NEEDS_TO_BE_LOADED: The driver's first instance will load
+ * firmware to the adapter.
+ * FW_IS_BEING_LOADED: The driver's second instance will not load
+ * firmware to the adapter.
+ */
+
+ /* Prior to f/w load, perform a soft reset of the Octeon device;
+ * if error resetting, return w/error.
+ */
+ if (fw_state == FW_NEEDS_TO_BE_LOADED)
+ if (octeon_dev->fn_list.soft_reset(octeon_dev))
+ return 1;
+
/* Initialize the dispatch mechanism used to push packets arriving on
* Octeon Output queues.
*/
@@ -4063,7 +4097,7 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
atomic_set(&octeon_dev->status, OCT_DEV_IO_QUEUES_DONE);
- if ((!OCTEON_CN23XX_PF(octeon_dev)) || !fw_loaded) {
+ if (fw_state == FW_NEEDS_TO_BE_LOADED) {
dev_dbg(&octeon_dev->pci_dev->dev, "Waiting for DDR initialization...\n");
if (!ddr_timeout) {
dev_info(&octeon_dev->pci_dev->dev,
@@ -4125,6 +4159,8 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
dev_err(&octeon_dev->pci_dev->dev, "Could not load firmware to board\n");
return 1;
}
+
+ atomic_set(octeon_dev->adapter_fw_state, FW_HAS_BEEN_LOADED);
}
handshake[octeon_dev->octeon_id].init_ok = 1;
diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_image.h b/drivers/net/ethernet/cavium/liquidio/liquidio_image.h
index 78a3685f6fe0..5bf5e8791dfb 100644
--- a/drivers/net/ethernet/cavium/liquidio/liquidio_image.h
+++ b/drivers/net/ethernet/cavium/liquidio/liquidio_image.h
@@ -24,6 +24,7 @@
#define LIO_FW_BASE_NAME "lio_"
#define LIO_FW_NAME_SUFFIX ".bin"
#define LIO_FW_NAME_TYPE_NIC "nic"
+#define LIO_FW_NAME_TYPE_AUTO "auto"
#define LIO_FW_NAME_TYPE_NONE "none"
#define LIO_MAX_FIRMWARE_VERSION_LEN 16
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index 29d53b1763a7..e4aa3395a578 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -541,6 +541,7 @@ static char oct_dev_app_str[CVM_DRV_APP_COUNT + 1][32] = {
static struct octeon_device *octeon_device[MAX_OCTEON_DEVICES];
static atomic_t adapter_refcounts[MAX_OCTEON_DEVICES];
+static atomic_t adapter_fw_states[MAX_OCTEON_DEVICES];
static u32 octeon_device_count;
/* locks device array (i.e. octeon_device[]) */
@@ -770,6 +771,10 @@ int octeon_register_device(struct octeon_device *oct,
oct->adapter_refcount = &adapter_refcounts[oct->octeon_id];
atomic_set(oct->adapter_refcount, 0);
+ /* Like the reference count, the f/w state is shared 'per-adapter' */
+ oct->adapter_fw_state = &adapter_fw_states[oct->octeon_id];
+ atomic_set(oct->adapter_fw_state, FW_NEEDS_TO_BE_LOADED);
+
spin_lock(&octeon_devices_lock);
for (idx = (int)oct->octeon_id - 1; idx >= 0; idx--) {
if (!octeon_device[idx]) {
@@ -780,11 +785,15 @@ int octeon_register_device(struct octeon_device *oct,
atomic_inc(oct->adapter_refcount);
return 1; /* here, refcount is guaranteed to be 1 */
}
- /* if another device is at same bus/dev, use its refcounter */
+ /* If another device is at same bus/dev, use its refcounter
+ * (and f/w state variable).
+ */
if ((octeon_device[idx]->loc.bus == bus) &&
(octeon_device[idx]->loc.dev == dev)) {
oct->adapter_refcount =
octeon_device[idx]->adapter_refcount;
+ oct->adapter_fw_state =
+ octeon_device[idx]->adapter_fw_state;
break;
}
}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
index 894af199ddef..33d19c4509bc 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -50,6 +50,13 @@ enum octeon_pci_swap_mode {
OCTEON_PCI_32BIT_LW_SWAP = 3
};
+enum lio_fw_state {
+ FW_IS_PRELOADED = 0,
+ FW_NEEDS_TO_BE_LOADED = 1,
+ FW_IS_BEING_LOADED = 2,
+ FW_HAS_BEEN_LOADED = 3,
+};
+
enum {
OCTEON_CONFIG_TYPE_DEFAULT = 0,
NUM_OCTEON_CONFS,
@@ -557,6 +564,9 @@ struct octeon_device {
} loc;
atomic_t *adapter_refcount; /* reference count of adapter */
+
+ atomic_t *adapter_fw_state; /* per-adapter, lio_fw_state */
+
bool ptp_enable;
};
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 49b80da51ba7..d68478afccbf 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -523,6 +523,7 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
xdp.data_hard_start = page_address(page);
xdp.data = (void *)cpu_addr;
+ xdp_set_data_meta_invalid(&xdp);
xdp.data_end = xdp.data + len;
orig_data = xdp.data;
diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c
index 0f13a7f7c1d3..75e439918700 100644
--- a/drivers/net/ethernet/chelsio/cxgb/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb/sge.c
@@ -2075,9 +2075,8 @@ struct sge *t1_sge_create(struct adapter *adapter, struct sge_params *p)
goto nomem_port;
}
- init_timer(&sge->tx_reclaim_timer);
- sge->tx_reclaim_timer.data = (unsigned long)sge;
- sge->tx_reclaim_timer.function = sge_tx_reclaim_cb;
+ setup_timer(&sge->tx_reclaim_timer, sge_tx_reclaim_cb,
+ (unsigned long)sge);
if (is_T2(sge->adapter)) {
init_timer(&sge->espibug_timer);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/Makefile b/drivers/net/ethernet/chelsio/cxgb4/Makefile
index 817212702f0a..fecd7aab673b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/Makefile
+++ b/drivers/net/ethernet/chelsio/cxgb4/Makefile
@@ -4,7 +4,9 @@
obj-$(CONFIG_CHELSIO_T4) += cxgb4.o
-cxgb4-objs := cxgb4_main.o l2t.o t4_hw.o sge.o clip_tbl.o cxgb4_ethtool.o cxgb4_uld.o sched.o cxgb4_filter.o cxgb4_tc_u32.o cxgb4_ptp.o
+cxgb4-objs := cxgb4_main.o l2t.o t4_hw.o sge.o clip_tbl.o cxgb4_ethtool.o \
+ cxgb4_uld.o sched.o cxgb4_filter.o cxgb4_tc_u32.o \
+ cxgb4_ptp.o cxgb4_tc_flower.o
cxgb4-$(CONFIG_CHELSIO_T4_DCB) += cxgb4_dcb.o
cxgb4-$(CONFIG_CHELSIO_T4_FCOE) += cxgb4_fcoe.o
cxgb4-$(CONFIG_DEBUG_FS) += cxgb4_debugfs.o
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index ea72d2d2e1b4..0db3ab6ad094 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -549,6 +549,7 @@ enum { /* adapter flags */
MASTER_PF = (1 << 7),
FW_OFLD_CONN = (1 << 9),
ROOT_NO_RELAXED_ORDERING = (1 << 10),
+ SHUTTING_DOWN = (1 << 11),
};
enum {
@@ -904,6 +905,10 @@ struct adapter {
/* TC u32 offload */
struct cxgb4_tc_u32_table *tc_u32;
struct chcr_stats_debug chcr_stats;
+
+ /* TC flower offload */
+ DECLARE_HASHTABLE(flower_anymatch_tbl, 9);
+ struct timer_list flower_stats_timer;
};
/* Support for "sched-class" command to allow a TX Scheduling Class to be
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c
index 6ee2ed30626b..4e7f72b17e82 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c
@@ -40,8 +40,7 @@ static inline bool cxgb4_dcb_state_synced(enum cxgb4_dcb_state state)
return false;
}
-/* Initialize a port's Data Center Bridging state. Typically used after a
- * Link Down event.
+/* Initialize a port's Data Center Bridging state.
*/
void cxgb4_dcb_state_init(struct net_device *dev)
{
@@ -106,6 +105,15 @@ static void cxgb4_dcb_cleanup_apps(struct net_device *dev)
}
}
+/* Reset a port's Data Center Bridging state. Typically used after a
+ * Link Down event.
+ */
+void cxgb4_dcb_reset(struct net_device *dev)
+{
+ cxgb4_dcb_cleanup_apps(dev);
+ cxgb4_dcb_state_init(dev);
+}
+
/* Finite State machine for Data Center Bridging.
*/
void cxgb4_dcb_state_fsm(struct net_device *dev,
@@ -194,8 +202,7 @@ void cxgb4_dcb_state_fsm(struct net_device *dev,
* state. We need to reset back to a ground state
* of incomplete.
*/
- cxgb4_dcb_cleanup_apps(dev);
- cxgb4_dcb_state_init(dev);
+ cxgb4_dcb_reset(dev);
dcb->state = CXGB4_DCB_STATE_FW_INCOMPLETE;
dcb->supported = CXGB4_DCBX_FW_SUPPORT;
linkwatch_fire_event(dev);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h
index ccf24d3dc982..02040b99c78a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h
@@ -131,6 +131,7 @@ struct port_dcb_info {
void cxgb4_dcb_state_init(struct net_device *);
void cxgb4_dcb_version_init(struct net_device *);
+void cxgb4_dcb_reset(struct net_device *dev);
void cxgb4_dcb_state_fsm(struct net_device *, enum cxgb4_dcb_state_input);
void cxgb4_dcb_handle_fw_update(struct adapter *, const struct fw_port_cmd *);
void cxgb4_dcb_set_caps(struct adapter *, const struct fw_port_cmd *);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index 45b5853ca2f1..15361ca2857c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -148,6 +148,106 @@ static int get_filter_steerq(struct net_device *dev,
return iq;
}
+static int get_filter_count(struct adapter *adapter, unsigned int fidx,
+ u64 *pkts, u64 *bytes)
+{
+ unsigned int tcb_base, tcbaddr;
+ unsigned int word_offset;
+ struct filter_entry *f;
+ __be64 be64_byte_count;
+ int ret;
+
+ tcb_base = t4_read_reg(adapter, TP_CMM_TCB_BASE_A);
+ if ((fidx != (adapter->tids.nftids + adapter->tids.nsftids - 1)) &&
+ fidx >= adapter->tids.nftids)
+ return -E2BIG;
+
+ f = &adapter->tids.ftid_tab[fidx];
+ if (!f->valid)
+ return -EINVAL;
+
+ tcbaddr = tcb_base + f->tid * TCB_SIZE;
+
+ spin_lock(&adapter->win0_lock);
+ if (is_t4(adapter->params.chip)) {
+ __be64 be64_count;
+
+ /* T4 doesn't maintain byte counts in hw */
+ *bytes = 0;
+
+ /* Get pkts */
+ word_offset = 4;
+ ret = t4_memory_rw(adapter, MEMWIN_NIC, MEM_EDC0,
+ tcbaddr + (word_offset * sizeof(__be32)),
+ sizeof(be64_count),
+ (__be32 *)&be64_count,
+ T4_MEMORY_READ);
+ if (ret < 0)
+ goto out;
+ *pkts = be64_to_cpu(be64_count);
+ } else {
+ __be32 be32_count;
+
+ /* Get bytes */
+ word_offset = 4;
+ ret = t4_memory_rw(adapter, MEMWIN_NIC, MEM_EDC0,
+ tcbaddr + (word_offset * sizeof(__be32)),
+ sizeof(be64_byte_count),
+ &be64_byte_count,
+ T4_MEMORY_READ);
+ if (ret < 0)
+ goto out;
+ *bytes = be64_to_cpu(be64_byte_count);
+
+ /* Get pkts */
+ word_offset = 6;
+ ret = t4_memory_rw(adapter, MEMWIN_NIC, MEM_EDC0,
+ tcbaddr + (word_offset * sizeof(__be32)),
+ sizeof(be32_count),
+ &be32_count,
+ T4_MEMORY_READ);
+ if (ret < 0)
+ goto out;
+ *pkts = (u64)be32_to_cpu(be32_count);
+ }
+
+out:
+ spin_unlock(&adapter->win0_lock);
+ return ret;
+}
+
+int cxgb4_get_filter_counters(struct net_device *dev, unsigned int fidx,
+ u64 *hitcnt, u64 *bytecnt)
+{
+ struct adapter *adapter = netdev2adap(dev);
+
+ return get_filter_count(adapter, fidx, hitcnt, bytecnt);
+}
+
+int cxgb4_get_free_ftid(struct net_device *dev, int family)
+{
+ struct adapter *adap = netdev2adap(dev);
+ struct tid_info *t = &adap->tids;
+ int ftid;
+
+ spin_lock_bh(&t->ftid_lock);
+ if (family == PF_INET) {
+ ftid = find_first_zero_bit(t->ftid_bmap, t->nftids);
+ if (ftid >= t->nftids)
+ ftid = -1;
+ } else {
+ ftid = bitmap_find_free_region(t->ftid_bmap, t->nftids, 2);
+ if (ftid < 0)
+ goto out_unlock;
+
+ /* this is only a lookup, keep the found region unallocated */
+ bitmap_release_region(t->ftid_bmap, ftid, 2);
+ }
+out_unlock:
+ spin_unlock_bh(&t->ftid_lock);
+ return ftid;
+}
+
static int cxgb4_set_ftid(struct tid_info *t, int fidx, int family)
{
spin_lock_bh(&t->ftid_lock);
@@ -191,7 +291,8 @@ static int del_filter_wr(struct adapter *adapter, int fidx)
return -ENOMEM;
fwr = __skb_put(skb, len);
- t4_mk_filtdelwr(f->tid, fwr, adapter->sge.fw_evtq.abs_id);
+ t4_mk_filtdelwr(f->tid, fwr, (adapter->flags & SHUTTING_DOWN) ? -1
+ : adapter->sge.fw_evtq.abs_id);
/* Mark the filter as "pending" and ship off the Filter Work Request.
* When we get the Work Request Reply we'll clear the pending status.
@@ -636,6 +737,10 @@ int cxgb4_del_filter(struct net_device *dev, int filter_id)
struct filter_ctx ctx;
int ret;
+ /* If we are shutting down the adapter do not wait for completion */
+ if (netdev2adap(dev)->flags & SHUTTING_DOWN)
+ return __cxgb4_del_filter(dev, filter_id, NULL);
+
init_completion(&ctx.completion);
ret = __cxgb4_del_filter(dev, filter_id, &ctx);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 92d9d795d874..fe4cbe22d5d7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -79,6 +79,7 @@
#include "l2t.h"
#include "sched.h"
#include "cxgb4_tc_u32.h"
+#include "cxgb4_tc_flower.h"
#include "cxgb4_ptp.h"
char cxgb4_driver_name[] = KBUILD_MODNAME;
@@ -280,7 +281,7 @@ void t4_os_link_changed(struct adapter *adapter, int port_id, int link_stat)
else {
#ifdef CONFIG_CHELSIO_T4_DCB
if (cxgb4_dcb_enabled(dev)) {
- cxgb4_dcb_state_init(dev);
+ cxgb4_dcb_reset(dev);
dcb_tx_queue_prio_enable(dev, false);
}
#endif /* CONFIG_CHELSIO_T4_DCB */
@@ -2303,10 +2304,16 @@ static int cxgb_close(struct net_device *dev)
{
struct port_info *pi = netdev_priv(dev);
struct adapter *adapter = pi->adapter;
+ int ret;
netif_tx_stop_all_queues(dev);
netif_carrier_off(dev);
- return t4_enable_vi(adapter, adapter->pf, pi->viid, false, false);
+ ret = t4_enable_vi(adapter, adapter->pf, pi->viid, false, false);
+#ifdef CONFIG_CHELSIO_T4_DCB
+ cxgb4_dcb_reset(dev);
+ dcb_tx_queue_prio_enable(dev, false);
+#endif
+ return ret;
}
int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
@@ -2873,6 +2880,25 @@ static int cxgb_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
return err;
}
+static int cxgb_setup_tc_flower(struct net_device *dev,
+ struct tc_cls_flower_offload *cls_flower)
+{
+ if (!is_classid_clsact_ingress(cls_flower->common.classid) ||
+ cls_flower->common.chain_index)
+ return -EOPNOTSUPP;
+
+ switch (cls_flower->command) {
+ case TC_CLSFLOWER_REPLACE:
+ return cxgb4_tc_flower_replace(dev, cls_flower);
+ case TC_CLSFLOWER_DESTROY:
+ return cxgb4_tc_flower_destroy(dev, cls_flower);
+ case TC_CLSFLOWER_STATS:
+ return cxgb4_tc_flower_stats(dev, cls_flower);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
static int cxgb_setup_tc_cls_u32(struct net_device *dev,
struct tc_cls_u32_offload *cls_u32)
{
@@ -2907,6 +2933,8 @@ static int cxgb_setup_tc(struct net_device *dev, enum tc_setup_type type,
switch (type) {
case TC_SETUP_CLSU32:
return cxgb_setup_tc_cls_u32(dev, type_data);
+ case TC_SETUP_CLSFLOWER:
+ return cxgb_setup_tc_flower(dev, type_data);
default:
return -EOPNOTSUPP;
}
@@ -4615,6 +4643,7 @@ static void free_some_resources(struct adapter *adapter)
kvfree(adapter->l2t);
t4_cleanup_sched(adapter);
kvfree(adapter->tids.tid_tab);
+ cxgb4_cleanup_tc_flower(adapter);
cxgb4_cleanup_tc_u32(adapter);
kfree(adapter->sge.egr_map);
kfree(adapter->sge.ingr_map);
@@ -4995,7 +5024,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
netdev->priv_flags |= IFF_UNICAST_FLT;
/* MTU range: 81 - 9600 */
- netdev->min_mtu = 81;
+ netdev->min_mtu = 81; /* accommodate SACK */
netdev->max_mtu = MAX_MTU;
netdev->netdev_ops = &cxgb4_netdev_ops;
@@ -5083,6 +5112,8 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
if (!adapter->tc_u32)
dev_warn(&pdev->dev,
"could not offload tc u32, continuing\n");
+
+ cxgb4_init_tc_flower(adapter);
}
if (is_offload(adapter)) {
@@ -5254,6 +5285,8 @@ static void remove_one(struct pci_dev *pdev)
return;
}
+ adapter->flags |= SHUTTING_DOWN;
+
if (adapter->pf == 4) {
int i;
@@ -5339,6 +5372,8 @@ static void shutdown_one(struct pci_dev *pdev)
return;
}
+ adapter->flags |= SHUTTING_DOWN;
+
if (adapter->pf == 4) {
int i;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
new file mode 100644
index 000000000000..92a311767381
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
@@ -0,0 +1,452 @@
+/*
+ * This file is part of the Chelsio T4/T5/T6 Ethernet driver for Linux.
+ *
+ * Copyright (c) 2017 Chelsio Communications, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <net/tc_act/tc_gact.h>
+#include <net/tc_act/tc_mirred.h>
+#include <net/tc_act/tc_vlan.h>
+
+#include "cxgb4.h"
+#include "cxgb4_tc_flower.h"
+
+#define STATS_CHECK_PERIOD (HZ / 2)
+
+static struct ch_tc_flower_entry *allocate_flower_entry(void)
+{
+ struct ch_tc_flower_entry *new = kzalloc(sizeof(*new), GFP_KERNEL);
+ spin_lock_init(&new->lock);
+ return new;
+}
+
+/* Must be called with either RTNL or rcu_read_lock */
+static struct ch_tc_flower_entry *ch_flower_lookup(struct adapter *adap,
+ unsigned long flower_cookie)
+{
+ struct ch_tc_flower_entry *flower_entry;
+
+ hash_for_each_possible_rcu(adap->flower_anymatch_tbl, flower_entry,
+ link, flower_cookie)
+ if (flower_entry->tc_flower_cookie == flower_cookie)
+ return flower_entry;
+ return NULL;
+}
+
+static void cxgb4_process_flow_match(struct net_device *dev,
+ struct tc_cls_flower_offload *cls,
+ struct ch_filter_specification *fs)
+{
+ u16 addr_type = 0;
+
+ if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
+ struct flow_dissector_key_control *key =
+ skb_flow_dissector_target(cls->dissector,
+ FLOW_DISSECTOR_KEY_CONTROL,
+ cls->key);
+
+ addr_type = key->addr_type;
+ }
+
+ if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+ struct flow_dissector_key_basic *key =
+ skb_flow_dissector_target(cls->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ cls->key);
+ struct flow_dissector_key_basic *mask =
+ skb_flow_dissector_target(cls->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ cls->mask);
+ u16 ethtype_key = ntohs(key->n_proto);
+ u16 ethtype_mask = ntohs(mask->n_proto);
+
+ if (ethtype_key == ETH_P_ALL) {
+ ethtype_key = 0;
+ ethtype_mask = 0;
+ }
+
+ fs->val.ethtype = ethtype_key;
+ fs->mask.ethtype = ethtype_mask;
+ fs->val.proto = key->ip_proto;
+ fs->mask.proto = mask->ip_proto;
+ }
+
+ if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+ struct flow_dissector_key_ipv4_addrs *key =
+ skb_flow_dissector_target(cls->dissector,
+ FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+ cls->key);
+ struct flow_dissector_key_ipv4_addrs *mask =
+ skb_flow_dissector_target(cls->dissector,
+ FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+ cls->mask);
+ fs->type = 0;
+ memcpy(&fs->val.lip[0], &key->dst, sizeof(key->dst));
+ memcpy(&fs->val.fip[0], &key->src, sizeof(key->src));
+ memcpy(&fs->mask.lip[0], &mask->dst, sizeof(mask->dst));
+ memcpy(&fs->mask.fip[0], &mask->src, sizeof(mask->src));
+ }
+
+ if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+ struct flow_dissector_key_ipv6_addrs *key =
+ skb_flow_dissector_target(cls->dissector,
+ FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+ cls->key);
+ struct flow_dissector_key_ipv6_addrs *mask =
+ skb_flow_dissector_target(cls->dissector,
+ FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+ cls->mask);
+
+ fs->type = 1;
+ memcpy(&fs->val.lip[0], key->dst.s6_addr, sizeof(key->dst));
+ memcpy(&fs->val.fip[0], key->src.s6_addr, sizeof(key->src));
+ memcpy(&fs->mask.lip[0], mask->dst.s6_addr, sizeof(mask->dst));
+ memcpy(&fs->mask.fip[0], mask->src.s6_addr, sizeof(mask->src));
+ }
+
+ if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
+ struct flow_dissector_key_ports *key, *mask;
+
+ key = skb_flow_dissector_target(cls->dissector,
+ FLOW_DISSECTOR_KEY_PORTS,
+ cls->key);
+ mask = skb_flow_dissector_target(cls->dissector,
+ FLOW_DISSECTOR_KEY_PORTS,
+ cls->mask);
+ fs->val.lport = cpu_to_be16(key->dst);
+ fs->mask.lport = cpu_to_be16(mask->dst);
+ fs->val.fport = cpu_to_be16(key->src);
+ fs->mask.fport = cpu_to_be16(mask->src);
+ }
+
+ /* Match only packets coming from the ingress port where this
+ * filter will be created.
+ */
+ fs->val.iport = netdev2pinfo(dev)->port_id;
+ fs->mask.iport = ~0;
+}
+
+static int cxgb4_validate_flow_match(struct net_device *dev,
+ struct tc_cls_flower_offload *cls)
+{
+ if (cls->dissector->used_keys &
+ ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
+ BIT(FLOW_DISSECTOR_KEY_BASIC) |
+ BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+ BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+ BIT(FLOW_DISSECTOR_KEY_PORTS))) {
+ netdev_warn(dev, "Unsupported key used: 0x%x\n",
+ cls->dissector->used_keys);
+ return -EOPNOTSUPP;
+ }
+ return 0;
+}
+
+static void cxgb4_process_flow_actions(struct net_device *in,
+ struct tc_cls_flower_offload *cls,
+ struct ch_filter_specification *fs)
+{
+ const struct tc_action *a;
+ LIST_HEAD(actions);
+
+ tcf_exts_to_list(cls->exts, &actions);
+ list_for_each_entry(a, &actions, list) {
+ if (is_tcf_gact_shot(a)) {
+ fs->action = FILTER_DROP;
+ } else if (is_tcf_mirred_egress_redirect(a)) {
+ int ifindex = tcf_mirred_ifindex(a);
+ struct net_device *out = __dev_get_by_index(dev_net(in),
+ ifindex);
+ struct port_info *pi = netdev_priv(out);
+
+ fs->action = FILTER_SWITCH;
+ fs->eport = pi->port_id;
+ } else if (is_tcf_vlan(a)) {
+ u32 vlan_action = tcf_vlan_action(a);
+ u8 prio = tcf_vlan_push_prio(a);
+ u16 vid = tcf_vlan_push_vid(a);
+ u16 vlan_tci = (prio << VLAN_PRIO_SHIFT) | vid;
+
+ switch (vlan_action) {
+ case TCA_VLAN_ACT_POP:
+ fs->newvlan |= VLAN_REMOVE;
+ break;
+ case TCA_VLAN_ACT_PUSH:
+ fs->newvlan |= VLAN_INSERT;
+ fs->vlan = vlan_tci;
+ break;
+ case TCA_VLAN_ACT_MODIFY:
+ fs->newvlan |= VLAN_REWRITE;
+ fs->vlan = vlan_tci;
+ break;
+ default:
+ break;
+ }
+ }
+ }
+}
+
+static int cxgb4_validate_flow_actions(struct net_device *dev,
+ struct tc_cls_flower_offload *cls)
+{
+ const struct tc_action *a;
+ LIST_HEAD(actions);
+
+ tcf_exts_to_list(cls->exts, &actions);
+ list_for_each_entry(a, &actions, list) {
+ if (is_tcf_gact_shot(a)) {
+ /* Do nothing */
+ } else if (is_tcf_mirred_egress_redirect(a)) {
+ struct adapter *adap = netdev2adap(dev);
+ struct net_device *n_dev;
+ unsigned int i, ifindex;
+ bool found = false;
+
+ ifindex = tcf_mirred_ifindex(a);
+ for_each_port(adap, i) {
+ n_dev = adap->port[i];
+ if (ifindex == n_dev->ifindex) {
+ found = true;
+ break;
+ }
+ }
+
+ /* If interface doesn't belong to our hw, then
+ * the provided output port is not valid
+ */
+ if (!found) {
+ netdev_err(dev, "%s: Out port invalid\n",
+ __func__);
+ return -EINVAL;
+ }
+ } else if (is_tcf_vlan(a)) {
+ u16 proto = be16_to_cpu(tcf_vlan_push_proto(a));
+ u32 vlan_action = tcf_vlan_action(a);
+
+ switch (vlan_action) {
+ case TCA_VLAN_ACT_POP:
+ break;
+ case TCA_VLAN_ACT_PUSH:
+ case TCA_VLAN_ACT_MODIFY:
+ if (proto != ETH_P_8021Q) {
+ netdev_err(dev, "%s: Unsupported vlan proto\n",
+ __func__);
+ return -EOPNOTSUPP;
+ }
+ break;
+ default:
+ netdev_err(dev, "%s: Unsupported vlan action\n",
+ __func__);
+ return -EOPNOTSUPP;
+ }
+ } else {
+ netdev_err(dev, "%s: Unsupported action\n", __func__);
+ return -EOPNOTSUPP;
+ }
+ }
+ return 0;
+}
+
+int cxgb4_tc_flower_replace(struct net_device *dev,
+ struct tc_cls_flower_offload *cls)
+{
+ struct adapter *adap = netdev2adap(dev);
+ struct ch_tc_flower_entry *ch_flower;
+ struct ch_filter_specification *fs;
+ struct filter_ctx ctx;
+ int fidx;
+ int ret;
+
+ if (cxgb4_validate_flow_actions(dev, cls))
+ return -EOPNOTSUPP;
+
+ if (cxgb4_validate_flow_match(dev, cls))
+ return -EOPNOTSUPP;
+
+ ch_flower = allocate_flower_entry();
+ if (!ch_flower) {
+ netdev_err(dev, "%s: ch_flower alloc failed.\n", __func__);
+ return -ENOMEM;
+ }
+
+ fs = &ch_flower->fs;
+ fs->hitcnts = 1;
+ cxgb4_process_flow_actions(dev, cls, fs);
+ cxgb4_process_flow_match(dev, cls, fs);
+
+ fidx = cxgb4_get_free_ftid(dev, fs->type ? PF_INET6 : PF_INET);
+ if (fidx < 0) {
+ netdev_err(dev, "%s: No fidx for offload.\n", __func__);
+ ret = -ENOMEM;
+ goto free_entry;
+ }
+
+ init_completion(&ctx.completion);
+ ret = __cxgb4_set_filter(dev, fidx, fs, &ctx);
+ if (ret) {
+ netdev_err(dev, "%s: filter creation err %d\n",
+ __func__, ret);
+ goto free_entry;
+ }
+
+ /* Wait for reply */
+ ret = wait_for_completion_timeout(&ctx.completion, 10 * HZ);
+ if (!ret) {
+ ret = -ETIMEDOUT;
+ goto free_entry;
+ }
+
+ ret = ctx.result;
+ /* Check if hw returned error for filter creation */
+ if (ret) {
+ netdev_err(dev, "%s: filter creation err %d\n",
+ __func__, ret);
+ goto free_entry;
+ }
+
+ INIT_HLIST_NODE(&ch_flower->link);
+ ch_flower->tc_flower_cookie = cls->cookie;
+ ch_flower->filter_id = ctx.tid;
+ hash_add_rcu(adap->flower_anymatch_tbl, &ch_flower->link, cls->cookie);
+
+ return ret;
+
+free_entry:
+ kfree(ch_flower);
+ return ret;
+}
+
+int cxgb4_tc_flower_destroy(struct net_device *dev,
+ struct tc_cls_flower_offload *cls)
+{
+ struct adapter *adap = netdev2adap(dev);
+ struct ch_tc_flower_entry *ch_flower;
+ int ret;
+
+ ch_flower = ch_flower_lookup(adap, cls->cookie);
+ if (!ch_flower)
+ return -ENOENT;
+
+ ret = cxgb4_del_filter(dev, ch_flower->filter_id);
+ if (ret)
+ goto err;
+
+ hash_del_rcu(&ch_flower->link);
+ kfree_rcu(ch_flower, rcu);
+
+err:
+ return ret;
+}
+
+static void ch_flower_stats_cb(unsigned long data)
+{
+ struct adapter *adap = (struct adapter *)data;
+ struct ch_tc_flower_entry *flower_entry;
+ struct ch_tc_flower_stats *ofld_stats;
+ unsigned int i;
+ u64 packets;
+ u64 bytes;
+ int ret;
+
+ rcu_read_lock();
+ hash_for_each_rcu(adap->flower_anymatch_tbl, i, flower_entry, link) {
+ ret = cxgb4_get_filter_counters(adap->port[0],
+ flower_entry->filter_id,
+ &packets, &bytes);
+ if (!ret) {
+ spin_lock(&flower_entry->lock);
+ ofld_stats = &flower_entry->stats;
+
+ if (ofld_stats->prev_packet_count != packets) {
+ ofld_stats->prev_packet_count = packets;
+ ofld_stats->last_used = jiffies;
+ }
+ spin_unlock(&flower_entry->lock);
+ }
+ }
+ rcu_read_unlock();
+ mod_timer(&adap->flower_stats_timer, jiffies + STATS_CHECK_PERIOD);
+}
+
+int cxgb4_tc_flower_stats(struct net_device *dev,
+ struct tc_cls_flower_offload *cls)
+{
+ struct adapter *adap = netdev2adap(dev);
+ struct ch_tc_flower_stats *ofld_stats;
+ struct ch_tc_flower_entry *ch_flower;
+ u64 packets;
+ u64 bytes;
+ int ret;
+
+ ch_flower = ch_flower_lookup(adap, cls->cookie);
+ if (!ch_flower) {
+ ret = -ENOENT;
+ goto err;
+ }
+
+ ret = cxgb4_get_filter_counters(dev, ch_flower->filter_id,
+ &packets, &bytes);
+ if (ret < 0)
+ goto err;
+
+ spin_lock_bh(&ch_flower->lock);
+ ofld_stats = &ch_flower->stats;
+ if (ofld_stats->packet_count != packets) {
+ if (ofld_stats->prev_packet_count != packets)
+ ofld_stats->last_used = jiffies;
+ tcf_exts_stats_update(cls->exts, bytes - ofld_stats->byte_count,
+ packets - ofld_stats->packet_count,
+ ofld_stats->last_used);
+
+ ofld_stats->packet_count = packets;
+ ofld_stats->byte_count = bytes;
+ ofld_stats->prev_packet_count = packets;
+ }
+ spin_unlock_bh(&ch_flower->lock);
+ return 0;
+
+err:
+ return ret;
+}
+
+void cxgb4_init_tc_flower(struct adapter *adap)
+{
+ hash_init(adap->flower_anymatch_tbl);
+ setup_timer(&adap->flower_stats_timer, ch_flower_stats_cb,
+ (unsigned long)adap);
+ mod_timer(&adap->flower_stats_timer, jiffies + STATS_CHECK_PERIOD);
+}
+
+void cxgb4_cleanup_tc_flower(struct adapter *adap)
+{
+ if (adap->flower_stats_timer.function)
+ del_timer_sync(&adap->flower_stats_timer);
+}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h
new file mode 100644
index 000000000000..604feffc752e
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h
@@ -0,0 +1,66 @@
+/*
+ * This file is part of the Chelsio T4/T5/T6 Ethernet driver for Linux.
+ *
+ * Copyright (c) 2017 Chelsio Communications, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef __CXGB4_TC_FLOWER_H
+#define __CXGB4_TC_FLOWER_H
+
+#include <net/pkt_cls.h>
+
+struct ch_tc_flower_stats {
+ u64 prev_packet_count;
+ u64 packet_count;
+ u64 byte_count;
+ u64 last_used;
+};
+
+struct ch_tc_flower_entry {
+ struct ch_filter_specification fs;
+ struct ch_tc_flower_stats stats;
+ unsigned long tc_flower_cookie;
+ struct hlist_node link;
+ struct rcu_head rcu;
+ spinlock_t lock; /* lock for stats */
+ u32 filter_id;
+};
+
+int cxgb4_tc_flower_replace(struct net_device *dev,
+ struct tc_cls_flower_offload *cls);
+int cxgb4_tc_flower_destroy(struct net_device *dev,
+ struct tc_cls_flower_offload *cls);
+int cxgb4_tc_flower_stats(struct net_device *dev,
+ struct tc_cls_flower_offload *cls);
+
+void cxgb4_init_tc_flower(struct adapter *adap);
+void cxgb4_cleanup_tc_flower(struct adapter *adap);
+#endif /* __CXGB4_TC_FLOWER_H */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 84541fce94c5..52324c77a4fe 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -212,6 +212,7 @@ struct filter_ctx {
struct ch_filter_specification;
+int cxgb4_get_free_ftid(struct net_device *dev, int family);
int __cxgb4_set_filter(struct net_device *dev, int filter_id,
struct ch_filter_specification *fs,
struct filter_ctx *ctx);
@@ -220,6 +221,8 @@ int __cxgb4_del_filter(struct net_device *dev, int filter_id,
int cxgb4_set_filter(struct net_device *dev, int filter_id,
struct ch_filter_specification *fs);
int cxgb4_del_filter(struct net_device *dev, int filter_id);
+int cxgb4_get_filter_counters(struct net_device *dev, unsigned int fidx,
+ u64 *hitcnt, u64 *bytecnt);
static inline void set_wr_txq(struct sk_buff *skb, int prio, int queue)
{
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index f7ef8871dd0b..1817a0307d26 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -422,7 +422,7 @@ struct l2t_entry *cxgb4_l2t_get(struct l2t_data *d, struct neighbour *neigh,
u8 lport;
u16 vlan;
struct l2t_entry *e;
- int addr_len = neigh->tbl->key_len;
+ unsigned int addr_len = neigh->tbl->key_len;
u32 *addr = (u32 *)neigh->primary_key;
int ifidx = neigh->dev->ifindex;
int hash = addr_hash(d, addr, addr_len, ifidx);
@@ -536,7 +536,7 @@ void t4_l2t_update(struct adapter *adap, struct neighbour *neigh)
struct l2t_entry *e;
struct sk_buff_head *arpq = NULL;
struct l2t_data *d = adap->l2t;
- int addr_len = neigh->tbl->key_len;
+ unsigned int addr_len = neigh->tbl->key_len;
u32 *addr = (u32 *) neigh->primary_key;
int ifidx = neigh->dev->ifindex;
int hash = addr_hash(d, addr, addr_len, ifidx);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index aa28299aef5f..633e9751a25e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -176,6 +176,11 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
CH_PCI_ID_TABLE_FENTRY(0x50a2), /* Custom T540-KR4 */
CH_PCI_ID_TABLE_FENTRY(0x50a3), /* Custom T580-KR4 */
CH_PCI_ID_TABLE_FENTRY(0x50a4), /* Custom 2x T540-CR */
+ CH_PCI_ID_TABLE_FENTRY(0x50a5), /* Custom T522-BT */
+ CH_PCI_ID_TABLE_FENTRY(0x50a6), /* Custom T522-BT-SO */
+ CH_PCI_ID_TABLE_FENTRY(0x50a7), /* Custom T580-CR */
+ CH_PCI_ID_TABLE_FENTRY(0x50a8), /* Custom T580-KR */
+ CH_PCI_ID_TABLE_FENTRY(0x50a9), /* Custom T580-KR */
/* T6 adapters:
*/
@@ -197,6 +202,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
CH_PCI_ID_TABLE_FENTRY(0x6082), /* Custom T6225-CR SFP28 */
CH_PCI_ID_TABLE_FENTRY(0x6083), /* Custom T62100-CR QSFP28 */
CH_PCI_ID_TABLE_FENTRY(0x6084), /* Custom T64100-CR QSFP28 */
+ CH_PCI_ID_TABLE_FENTRY(0x6085), /* Custom T6240-SO */
CH_PCI_DEVICE_ID_TABLE_DEFINE_END;
#endif /* __T4_PCI_ID_TBL_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
index a8d94963b4d0..67aec59a14e6 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
@@ -1812,7 +1812,7 @@ int t4vf_eth_eq_free(struct adapter *adapter, unsigned int eqid)
*
* Returns a string representation of the Link Down Reason Code.
*/
-const char *t4vf_link_down_rc_str(unsigned char link_down_rc)
+static const char *t4vf_link_down_rc_str(unsigned char link_down_rc)
{
static const char * const reason[] = {
"Link Down",
@@ -1838,8 +1838,8 @@ const char *t4vf_link_down_rc_str(unsigned char link_down_rc)
*
* Processes a GET_PORT_INFO FW reply message.
*/
-void t4vf_handle_get_port_info(struct port_info *pi,
- const struct fw_port_cmd *cmd)
+static void t4vf_handle_get_port_info(struct port_info *pi,
+ const struct fw_port_cmd *cmd)
{
int action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16));
struct adapter *adapter = pi->adapter;
diff --git a/drivers/net/ethernet/cisco/enic/enic_clsf.h b/drivers/net/ethernet/cisco/enic/enic_clsf.h
index 6aa9f89d073b..4bfbf25f9ddc 100644
--- a/drivers/net/ethernet/cisco/enic/enic_clsf.h
+++ b/drivers/net/ethernet/cisco/enic/enic_clsf.h
@@ -19,9 +19,8 @@ void enic_flow_may_expire(unsigned long data);
static inline void enic_rfs_timer_start(struct enic *enic)
{
- init_timer(&enic->rfs_h.rfs_may_expire);
- enic->rfs_h.rfs_may_expire.function = enic_flow_may_expire;
- enic->rfs_h.rfs_may_expire.data = (unsigned long)enic;
+ setup_timer(&enic->rfs_h.rfs_may_expire, enic_flow_may_expire,
+ (unsigned long)enic);
mod_timer(&enic->rfs_h.rfs_may_expire, jiffies + HZ/4);
}
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index d24ee1ad3be1..4a11baffe02d 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2846,9 +2846,8 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
/* Setup notification timer, HW reset task, and wq locks
*/
- init_timer(&enic->notify_timer);
- enic->notify_timer.function = enic_notify_timer;
- enic->notify_timer.data = (unsigned long)enic;
+ setup_timer(&enic->notify_timer, enic_notify_timer,
+ (unsigned long)enic);
enic_set_rx_coal_setting(enic);
INIT_WORK(&enic->reset, enic_reset);
diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index 0affee9c8aa2..299812e92db7 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -1147,9 +1147,8 @@ de4x5_hw_init(struct net_device *dev, u_long iobase, struct device *gendev)
lp->timeout = -1;
lp->gendev = gendev;
spin_lock_init(&lp->lock);
- init_timer(&lp->timer);
- lp->timer.function = (void (*)(unsigned long))de4x5_ast;
- lp->timer.data = (unsigned long)dev;
+ setup_timer(&lp->timer, (void (*)(unsigned long))de4x5_ast,
+ (unsigned long)dev);
de4x5_parse_params(dev);
/*
diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c
index 07e10a45beaa..6585f737d08b 100644
--- a/drivers/net/ethernet/dec/tulip/dmfe.c
+++ b/drivers/net/ethernet/dec/tulip/dmfe.c
@@ -596,10 +596,8 @@ static int dmfe_open(struct net_device *dev)
netif_wake_queue(dev);
/* set and active a timer process */
- init_timer(&db->timer);
+ setup_timer(&db->timer, dmfe_timer, (unsigned long)dev);
db->timer.expires = DMFE_TIMER_WUT + HZ * 2;
- db->timer.data = (unsigned long)dev;
- db->timer.function = dmfe_timer;
add_timer(&db->timer);
return 0;
diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c
index 7fc248efc4ba..5fbbc0caba99 100644
--- a/drivers/net/ethernet/dec/tulip/uli526x.c
+++ b/drivers/net/ethernet/dec/tulip/uli526x.c
@@ -491,10 +491,8 @@ static int uli526x_open(struct net_device *dev)
netif_wake_queue(dev);
/* set and active a timer process */
- init_timer(&db->timer);
+ setup_timer(&db->timer, uli526x_timer, (unsigned long)dev);
db->timer.expires = ULI526X_TIMER_WUT + HZ * 2;
- db->timer.data = (unsigned long)dev;
- db->timer.function = uli526x_timer;
add_timer(&db->timer);
return 0;
diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c
index 32d7229544fa..6f88d687b6d2 100644
--- a/drivers/net/ethernet/dec/tulip/winbond-840.c
+++ b/drivers/net/ethernet/dec/tulip/winbond-840.c
@@ -655,10 +655,8 @@ static int netdev_open(struct net_device *dev)
netdev_dbg(dev, "Done netdev_open()\n");
/* Set the timer to check for link beat. */
- init_timer(&np->timer);
+ setup_timer(&np->timer, netdev_timer, (unsigned long)dev);
np->timer.expires = jiffies + 1*HZ;
- np->timer.data = (unsigned long)dev;
- np->timer.function = netdev_timer; /* timer handler */
add_timer(&np->timer);
return 0;
out_err:
diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c
index 2704bcf023be..6ca9e981ad57 100644
--- a/drivers/net/ethernet/dlink/sundance.c
+++ b/drivers/net/ethernet/dlink/sundance.c
@@ -913,10 +913,8 @@ static int netdev_open(struct net_device *dev)
ioread16(ioaddr + MACCtrl1), ioread16(ioaddr + MACCtrl0));
/* Set the timer to check for link beat. */
- init_timer(&np->timer);
+ setup_timer(&np->timer, netdev_timer, (unsigned long)dev);
np->timer.expires = jiffies + 3*HZ;
- np->timer.data = (unsigned long)dev;
- np->timer.function = netdev_timer; /* timer handler */
add_timer(&np->timer);
/* Enable interrupts by setting the interrupt mask. */
diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c
index e92859dab7ae..c8982313d850 100644
--- a/drivers/net/ethernet/fealnx.c
+++ b/drivers/net/ethernet/fealnx.c
@@ -909,17 +909,13 @@ static int netdev_open(struct net_device *dev)
printk(KERN_DEBUG "%s: Done netdev_open().\n", dev->name);
/* Set the timer to check for link beat. */
- init_timer(&np->timer);
+ setup_timer(&np->timer, netdev_timer, (unsigned long)dev);
np->timer.expires = RUN_AT(3 * HZ);
- np->timer.data = (unsigned long) dev;
- np->timer.function = netdev_timer;
/* timer handler */
add_timer(&np->timer);
- init_timer(&np->reset_timer);
- np->reset_timer.data = (unsigned long) dev;
- np->reset_timer.function = reset_timer;
+ setup_timer(&np->reset_timer, reset_timer, (unsigned long)dev);
np->reset_timer_armed = 0;
return rc;
}
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index f77ba9fa257b..a96b838cffce 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -3857,8 +3857,9 @@ static int ucc_geth_probe(struct platform_device* ofdev)
}
if (netif_msg_probe(&debug))
- pr_info("UCC%1d at 0x%8x (irq = %d)\n",
- ug_info->uf_info.ucc_num + 1, ug_info->uf_info.regs,
+ pr_info("UCC%1d at 0x%8llx (irq = %d)\n",
+ ug_info->uf_info.ucc_num + 1,
+ (u64)ug_info->uf_info.regs,
ug_info->uf_info.irq);
/* Create an ethernet device instance */
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index 91c7bdb9b43c..9d7cb0387bf7 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -103,4 +103,13 @@ config HNS3_ENET
family of SoCs. This module depends upon HNAE3 driver to access the HNAE3
devices and their associated operations.
+config HNS3_DCB
+ bool "Hisilicon HNS3 Data Center Bridge Support"
+ default n
+ depends on HNS3 && HNS3_HCLGE && DCB
+ ---help---
+ Say Y here if you want to use Data Center Bridging (DCB) in the HNS3 driver.
+
+ If unsure, say N.
+
endif # NET_VENDOR_HISILICON
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 1a01cadfe5f3..c677530841cf 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -28,6 +28,7 @@
*/
#include <linux/acpi.h>
+#include <linux/dcbnl.h>
#include <linux/delay.h>
#include <linux/device.h>
#include <linux/module.h>
@@ -131,6 +132,7 @@ struct hnae3_client_ops {
int (*init_instance)(struct hnae3_handle *handle);
void (*uninit_instance)(struct hnae3_handle *handle, bool reset);
void (*link_status_change)(struct hnae3_handle *handle, bool state);
+ int (*setup_tc)(struct hnae3_handle *handle, u8 tc);
};
#define HNAE3_CLIENT_NAME_LENGTH 16
@@ -363,6 +365,20 @@ struct hnae3_ae_ops {
u16 vlan, u8 qos, __be16 proto);
};
+struct hnae3_dcb_ops {
+ /* IEEE 802.1Qaz std */
+ int (*ieee_getets)(struct hnae3_handle *, struct ieee_ets *);
+ int (*ieee_setets)(struct hnae3_handle *, struct ieee_ets *);
+ int (*ieee_getpfc)(struct hnae3_handle *, struct ieee_pfc *);
+ int (*ieee_setpfc)(struct hnae3_handle *, struct ieee_pfc *);
+
+ /* DCBX configuration */
+ u8 (*getdcbx)(struct hnae3_handle *);
+ u8 (*setdcbx)(struct hnae3_handle *, u8);
+
+ int (*map_update)(struct hnae3_handle *);
+};
+
struct hnae3_ae_algo {
const struct hnae3_ae_ops *ops;
struct list_head node;
@@ -394,6 +410,7 @@ struct hnae3_knic_private_info {
u16 num_tqps; /* total number of TQPs in this handle */
struct hnae3_queue **tqp; /* array base of all TQPs in this instance */
+ const struct hnae3_dcb_ops *dcb_ops;
};
struct hnae3_roce_private_info {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
index 162e8a42acd0..d2b20d01a58c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
@@ -7,5 +7,9 @@ ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3
obj-$(CONFIG_HNS3_HCLGE) += hclge.o
hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o
+hclge-$(CONFIG_HNS3_DCB) += hclge_dcb.o
+
obj-$(CONFIG_HNS3_ENET) += hns3.o
hns3-objs = hns3_enet.o hns3_ethtool.o
+
+hns3-$(CONFIG_HNS3_DCB) += hns3_dcbnl.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 758cf3948131..6b6d28eff664 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -311,6 +311,7 @@ struct hclge_tc_thrd {
struct hclge_priv_buf {
struct hclge_waterline wl; /* Waterline for low and high*/
u32 buf_size; /* TC private buffer size */
+ u32 tx_buf_size;
u32 enable; /* Enable TC private buffer or not */
};
@@ -321,6 +322,11 @@ struct hclge_shared_buf {
u32 buf_size;
};
+struct hclge_pkt_buf_alloc {
+ struct hclge_priv_buf priv_buf[HCLGE_MAX_TC_NUM];
+ struct hclge_shared_buf s_buf;
+};
+
#define HCLGE_RX_COM_WL_EN_B 15
struct hclge_rx_com_wl_buf {
__le16 high_wl;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
new file mode 100644
index 000000000000..1b30a6f966d8
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -0,0 +1,304 @@
+/*
+ * Copyright (c) 2016-2017 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "hclge_main.h"
+#include "hclge_tm.h"
+#include "hnae3.h"
+
+#define BW_PERCENT 100
+
+static int hclge_ieee_ets_to_tm_info(struct hclge_dev *hdev,
+ struct ieee_ets *ets)
+{
+ u8 i;
+
+ for (i = 0; i < HNAE3_MAX_TC; i++) {
+ switch (ets->tc_tsa[i]) {
+ case IEEE_8021QAZ_TSA_STRICT:
+ hdev->tm_info.tc_info[i].tc_sch_mode =
+ HCLGE_SCH_MODE_SP;
+ hdev->tm_info.pg_info[0].tc_dwrr[i] = 0;
+ break;
+ case IEEE_8021QAZ_TSA_ETS:
+ hdev->tm_info.tc_info[i].tc_sch_mode =
+ HCLGE_SCH_MODE_DWRR;
+ hdev->tm_info.pg_info[0].tc_dwrr[i] =
+ ets->tc_tx_bw[i];
+ break;
+ default:
+ /* Hardware only supports SP (strict priority)
+ * or ETS (enhanced transmission selection)
+ * algorithms, if we receive some other value
+ * from dcbnl, then throw an error.
+ */
+ return -EINVAL;
+ }
+ }
+
+ return hclge_tm_prio_tc_info_update(hdev, ets->prio_tc);
+}
+
+static void hclge_tm_info_to_ieee_ets(struct hclge_dev *hdev,
+ struct ieee_ets *ets)
+{
+ u32 i;
+
+ memset(ets, 0, sizeof(*ets));
+ ets->willing = 1;
+ ets->ets_cap = hdev->tc_max;
+
+ for (i = 0; i < HNAE3_MAX_TC; i++) {
+ ets->prio_tc[i] = hdev->tm_info.prio_tc[i];
+ ets->tc_tx_bw[i] = hdev->tm_info.pg_info[0].tc_dwrr[i];
+
+ if (hdev->tm_info.tc_info[i].tc_sch_mode ==
+ HCLGE_SCH_MODE_SP)
+ ets->tc_tsa[i] = IEEE_8021QAZ_TSA_STRICT;
+ else
+ ets->tc_tsa[i] = IEEE_8021QAZ_TSA_ETS;
+ }
+}
+
+/* IEEE std */
+static int hclge_ieee_getets(struct hnae3_handle *h, struct ieee_ets *ets)
+{
+ struct hclge_vport *vport = hclge_get_vport(h);
+ struct hclge_dev *hdev = vport->back;
+
+ hclge_tm_info_to_ieee_ets(hdev, ets);
+
+ return 0;
+}
+
+static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets,
+ u8 *tc, bool *changed)
+{
+ u32 total_ets_bw = 0;
+ u8 max_tc = 0;
+ u8 i;
+
+ for (i = 0; i < HNAE3_MAX_TC; i++) {
+ if (ets->prio_tc[i] >= hdev->tc_max ||
+ i >= hdev->tc_max)
+ return -EINVAL;
+
+ if (ets->prio_tc[i] != hdev->tm_info.prio_tc[i])
+ *changed = true;
+
+ if (ets->prio_tc[i] > max_tc)
+ max_tc = ets->prio_tc[i];
+
+ switch (ets->tc_tsa[i]) {
+ case IEEE_8021QAZ_TSA_STRICT:
+ if (hdev->tm_info.tc_info[i].tc_sch_mode !=
+ HCLGE_SCH_MODE_SP)
+ *changed = true;
+ break;
+ case IEEE_8021QAZ_TSA_ETS:
+ if (hdev->tm_info.tc_info[i].tc_sch_mode !=
+ HCLGE_SCH_MODE_DWRR)
+ *changed = true;
+
+ total_ets_bw += ets->tc_tx_bw[i];
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+
+ if (total_ets_bw != BW_PERCENT)
+ return -EINVAL;
+
+ *tc = max_tc + 1;
+ if (*tc != hdev->tm_info.num_tc)
+ *changed = true;
+
+ return 0;
+}
+
+static int hclge_map_update(struct hnae3_handle *h)
+{
+ struct hclge_vport *vport = hclge_get_vport(h);
+ struct hclge_dev *hdev = vport->back;
+ int ret;
+
+ ret = hclge_tm_map_cfg(hdev);
+ if (ret)
+ return ret;
+
+ ret = hclge_tm_schd_mode_hw(hdev);
+ if (ret)
+ return ret;
+
+ ret = hclge_pause_setup_hw(hdev);
+ if (ret)
+ return ret;
+
+ ret = hclge_buffer_alloc(hdev);
+ if (ret)
+ return ret;
+
+ return hclge_rss_init_hw(hdev);
+}
+
+static int hclge_client_setup_tc(struct hclge_dev *hdev)
+{
+ struct hclge_vport *vport = hdev->vport;
+ struct hnae3_client *client;
+ struct hnae3_handle *handle;
+ int ret;
+ u32 i;
+
+ for (i = 0; i < hdev->num_vmdq_vport + 1; i++) {
+ handle = &vport[i].nic;
+ client = handle->client;
+
+ if (!client || !client->ops || !client->ops->setup_tc)
+ continue;
+
+ ret = client->ops->setup_tc(handle, hdev->tm_info.num_tc);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets)
+{
+ struct hclge_vport *vport = hclge_get_vport(h);
+ struct hclge_dev *hdev = vport->back;
+ bool map_changed = false;
+ u8 num_tc = 0;
+ int ret;
+
+ if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE))
+ return -EINVAL;
+
+ ret = hclge_ets_validate(hdev, ets, &num_tc, &map_changed);
+ if (ret)
+ return ret;
+
+ hclge_tm_schd_info_update(hdev, num_tc);
+
+ ret = hclge_ieee_ets_to_tm_info(hdev, ets);
+ if (ret)
+ return ret;
+
+ if (map_changed) {
+ ret = hclge_client_setup_tc(hdev);
+ if (ret)
+ return ret;
+ }
+
+ return hclge_tm_dwrr_cfg(hdev);
+}
+
+static int hclge_ieee_getpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
+{
+ struct hclge_vport *vport = hclge_get_vport(h);
+ struct hclge_dev *hdev = vport->back;
+ u8 i, j, pfc_map, *prio_tc;
+
+ memset(pfc, 0, sizeof(*pfc));
+ pfc->pfc_cap = hdev->pfc_max;
+ prio_tc = hdev->tm_info.prio_tc;
+ pfc_map = hdev->tm_info.hw_pfc_map;
+
+ /* Pfc setting is based on TC */
+ for (i = 0; i < hdev->tm_info.num_tc; i++) {
+ for (j = 0; j < HNAE3_MAX_USER_PRIO; j++) {
+ if ((prio_tc[j] == i) && (pfc_map & BIT(i)))
+ pfc->pfc_en |= BIT(j);
+ }
+ }
+
+ return 0;
+}
+
+static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
+{
+ struct hclge_vport *vport = hclge_get_vport(h);
+ struct hclge_dev *hdev = vport->back;
+ u8 i, j, pfc_map, *prio_tc;
+
+ if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE))
+ return -EINVAL;
+
+ prio_tc = hdev->tm_info.prio_tc;
+ pfc_map = 0;
+
+ for (i = 0; i < hdev->tm_info.num_tc; i++) {
+ for (j = 0; j < HNAE3_MAX_USER_PRIO; j++) {
+ if ((prio_tc[j] == i) && (pfc->pfc_en & BIT(j))) {
+ pfc_map |= BIT(i);
+ break;
+ }
+ }
+ }
+
+ if (pfc_map == hdev->tm_info.hw_pfc_map)
+ return 0;
+
+ hdev->tm_info.hw_pfc_map = pfc_map;
+
+ return hclge_pause_setup_hw(hdev);
+}
+
+/* DCBX configuration */
+static u8 hclge_getdcbx(struct hnae3_handle *h)
+{
+ struct hclge_vport *vport = hclge_get_vport(h);
+ struct hclge_dev *hdev = vport->back;
+
+ return hdev->dcbx_cap;
+}
+
+static u8 hclge_setdcbx(struct hnae3_handle *h, u8 mode)
+{
+ struct hclge_vport *vport = hclge_get_vport(h);
+ struct hclge_dev *hdev = vport->back;
+
+ /* No support for LLD_MANAGED modes or CEE */
+ if ((mode & DCB_CAP_DCBX_LLD_MANAGED) ||
+ (mode & DCB_CAP_DCBX_VER_CEE) ||
+ !(mode & DCB_CAP_DCBX_HOST))
+ return 1;
+
+ hdev->dcbx_cap = mode;
+
+ return 0;
+}
+
+static const struct hnae3_dcb_ops hns3_dcb_ops = {
+ .ieee_getets = hclge_ieee_getets,
+ .ieee_setets = hclge_ieee_setets,
+ .ieee_getpfc = hclge_ieee_getpfc,
+ .ieee_setpfc = hclge_ieee_setpfc,
+ .getdcbx = hclge_getdcbx,
+ .setdcbx = hclge_setdcbx,
+ .map_update = hclge_map_update,
+};
+
+void hclge_dcb_ops_set(struct hclge_dev *hdev)
+{
+ struct hclge_vport *vport = hdev->vport;
+ struct hnae3_knic_private_info *kinfo;
+
+ /* Hdev does not support DCB or vport is
+ * not a pf, then dcb_ops is not set.
+ */
+ if (!hnae3_dev_dcb_supported(hdev) ||
+ vport->vport_id != 0)
+ return;
+
+ kinfo = &vport->nic.kinfo;
+ kinfo->dcb_ops = &hns3_dcb_ops;
+ hdev->dcbx_cap = DCB_CAP_DCBX_VER_IEEE | DCB_CAP_DCBX_HOST;
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
new file mode 100644
index 000000000000..7d808ee96694
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
@@ -0,0 +1,21 @@
+/*
+ * Copyright (c) 2016~2017 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __HCLGE_DCB_H__
+#define __HCLGE_DCB_H__
+
+#include "hclge_main.h"
+
+#ifdef CONFIG_HNS3_DCB
+void hclge_dcb_ops_set(struct hclge_dev *hdev);
+#else
+static inline void hclge_dcb_ops_set(struct hclge_dev *hdev) {}
+#endif
+
+#endif /* __HCLGE_DCB_H__ */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index c1cdbfd83bdb..1a13614af3de 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -19,6 +19,7 @@
#include <linux/platform_device.h>
#include "hclge_cmd.h"
+#include "hclge_dcb.h"
#include "hclge_main.h"
#include "hclge_mdio.h"
#include "hclge_tm.h"
@@ -30,7 +31,6 @@
#define HCLGE_64BIT_STATS_FIELD_OFF(f) (offsetof(struct hclge_64_bit_stats, f))
#define HCLGE_32BIT_STATS_FIELD_OFF(f) (offsetof(struct hclge_32_bit_stats, f))
-static int hclge_rss_init_hw(struct hclge_dev *hdev);
static int hclge_set_mta_filter_mode(struct hclge_dev *hdev,
enum hclge_mta_dmac_sel_type mta_mac_sel,
bool enable);
@@ -1058,7 +1058,7 @@ static int hclge_configure(struct hclge_dev *hdev)
hdev->hw.mac.phy_addr = cfg.phy_addr;
hdev->num_desc = cfg.tqp_desc_num;
hdev->tm_info.num_pg = 1;
- hdev->tm_info.num_tc = cfg.tc_num;
+ hdev->tc_max = cfg.tc_num;
hdev->tm_info.hw_pfc_map = 0;
ret = hclge_parse_speed(cfg.default_speed, &hdev->hw.mac.speed);
@@ -1067,15 +1067,25 @@ static int hclge_configure(struct hclge_dev *hdev)
return ret;
}
- if ((hdev->tm_info.num_tc > HNAE3_MAX_TC) ||
- (hdev->tm_info.num_tc < 1)) {
+ if ((hdev->tc_max > HNAE3_MAX_TC) ||
+ (hdev->tc_max < 1)) {
dev_warn(&hdev->pdev->dev, "TC num = %d.\n",
- hdev->tm_info.num_tc);
- hdev->tm_info.num_tc = 1;
+ hdev->tc_max);
+ hdev->tc_max = 1;
}
+ /* Dev does not support DCB */
+ if (!hnae3_dev_dcb_supported(hdev)) {
+ hdev->tc_max = 1;
+ hdev->pfc_max = 0;
+ } else {
+ hdev->pfc_max = hdev->tc_max;
+ }
+
+ hdev->tm_info.num_tc = hdev->tc_max;
+
/* Currently not support uncontiuous tc */
- for (i = 0; i < cfg.tc_num; i++)
+ for (i = 0; i < hdev->tm_info.num_tc; i++)
hnae_set_bit(hdev->hw_tc_map, i, 1);
if (!hdev->num_vmdq_vport && !hdev->num_req_vfs)
@@ -1324,7 +1334,8 @@ static int hclge_alloc_vport(struct hclge_dev *hdev)
return 0;
}
-static int hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, u16 buf_size)
+static int hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev,
+ struct hclge_pkt_buf_alloc *buf_alloc)
{
/* TX buffer size is unit by 128 byte */
#define HCLGE_BUF_SIZE_UNIT_SHIFT 7
@@ -1337,10 +1348,13 @@ static int hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, u16 buf_size)
req = (struct hclge_tx_buff_alloc *)desc.data;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, 0);
- for (i = 0; i < HCLGE_TC_NUM; i++)
+ for (i = 0; i < HCLGE_TC_NUM; i++) {
+ u32 buf_size = buf_alloc->priv_buf[i].tx_buf_size;
+
req->tx_pkt_buff[i] =
cpu_to_le16((buf_size >> HCLGE_BUF_SIZE_UNIT_SHIFT) |
HCLGE_BUF_SIZE_UPDATE_EN_MSK);
+ }
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
if (ret) {
@@ -1352,9 +1366,10 @@ static int hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, u16 buf_size)
return 0;
}
-static int hclge_tx_buffer_alloc(struct hclge_dev *hdev, u32 buf_size)
+static int hclge_tx_buffer_alloc(struct hclge_dev *hdev,
+ struct hclge_pkt_buf_alloc *buf_alloc)
{
- int ret = hclge_cmd_alloc_tx_buff(hdev, buf_size);
+ int ret = hclge_cmd_alloc_tx_buff(hdev, buf_alloc);
if (ret) {
dev_err(&hdev->pdev->dev,
@@ -1387,13 +1402,14 @@ static int hclge_get_pfc_enalbe_num(struct hclge_dev *hdev)
}
/* Get the number of pfc enabled TCs, which have private buffer */
-static int hclge_get_pfc_priv_num(struct hclge_dev *hdev)
+static int hclge_get_pfc_priv_num(struct hclge_dev *hdev,
+ struct hclge_pkt_buf_alloc *buf_alloc)
{
struct hclge_priv_buf *priv;
int i, cnt = 0;
for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
- priv = &hdev->priv_buf[i];
+ priv = &buf_alloc->priv_buf[i];
if ((hdev->tm_info.hw_pfc_map & BIT(i)) &&
priv->enable)
cnt++;
@@ -1403,13 +1419,14 @@ static int hclge_get_pfc_priv_num(struct hclge_dev *hdev)
}
/* Get the number of pfc disabled TCs, which have private buffer */
-static int hclge_get_no_pfc_priv_num(struct hclge_dev *hdev)
+static int hclge_get_no_pfc_priv_num(struct hclge_dev *hdev,
+ struct hclge_pkt_buf_alloc *buf_alloc)
{
struct hclge_priv_buf *priv;
int i, cnt = 0;
for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
- priv = &hdev->priv_buf[i];
+ priv = &buf_alloc->priv_buf[i];
if (hdev->hw_tc_map & BIT(i) &&
!(hdev->tm_info.hw_pfc_map & BIT(i)) &&
priv->enable)
@@ -1419,21 +1436,33 @@ static int hclge_get_no_pfc_priv_num(struct hclge_dev *hdev)
return cnt;
}
-static u32 hclge_get_rx_priv_buff_alloced(struct hclge_dev *hdev)
+static u32 hclge_get_rx_priv_buff_alloced(struct hclge_pkt_buf_alloc *buf_alloc)
{
struct hclge_priv_buf *priv;
u32 rx_priv = 0;
int i;
for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
- priv = &hdev->priv_buf[i];
+ priv = &buf_alloc->priv_buf[i];
if (priv->enable)
rx_priv += priv->buf_size;
}
return rx_priv;
}
-static bool hclge_is_rx_buf_ok(struct hclge_dev *hdev, u32 rx_all)
+static u32 hclge_get_tx_buff_alloced(struct hclge_pkt_buf_alloc *buf_alloc)
+{
+ u32 i, total_tx_size = 0;
+
+ for (i = 0; i < HCLGE_MAX_TC_NUM; i++)
+ total_tx_size += buf_alloc->priv_buf[i].tx_buf_size;
+
+ return total_tx_size;
+}
+
+static bool hclge_is_rx_buf_ok(struct hclge_dev *hdev,
+ struct hclge_pkt_buf_alloc *buf_alloc,
+ u32 rx_all)
{
u32 shared_buf_min, shared_buf_tc, shared_std;
int tc_num, pfc_enable_num;
@@ -1454,46 +1483,74 @@ static bool hclge_is_rx_buf_ok(struct hclge_dev *hdev, u32 rx_all)
hdev->mps;
shared_std = max_t(u32, shared_buf_min, shared_buf_tc);
- rx_priv = hclge_get_rx_priv_buff_alloced(hdev);
+ rx_priv = hclge_get_rx_priv_buff_alloced(buf_alloc);
if (rx_all <= rx_priv + shared_std)
return false;
shared_buf = rx_all - rx_priv;
- hdev->s_buf.buf_size = shared_buf;
- hdev->s_buf.self.high = shared_buf;
- hdev->s_buf.self.low = 2 * hdev->mps;
+ buf_alloc->s_buf.buf_size = shared_buf;
+ buf_alloc->s_buf.self.high = shared_buf;
+ buf_alloc->s_buf.self.low = 2 * hdev->mps;
for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
if ((hdev->hw_tc_map & BIT(i)) &&
(hdev->tm_info.hw_pfc_map & BIT(i))) {
- hdev->s_buf.tc_thrd[i].low = hdev->mps;
- hdev->s_buf.tc_thrd[i].high = 2 * hdev->mps;
+ buf_alloc->s_buf.tc_thrd[i].low = hdev->mps;
+ buf_alloc->s_buf.tc_thrd[i].high = 2 * hdev->mps;
} else {
- hdev->s_buf.tc_thrd[i].low = 0;
- hdev->s_buf.tc_thrd[i].high = hdev->mps;
+ buf_alloc->s_buf.tc_thrd[i].low = 0;
+ buf_alloc->s_buf.tc_thrd[i].high = hdev->mps;
}
}
return true;
}
+static int hclge_tx_buffer_calc(struct hclge_dev *hdev,
+ struct hclge_pkt_buf_alloc *buf_alloc)
+{
+ u32 i, total_size;
+
+ total_size = hdev->pkt_buf_size;
+
+ /* alloc tx buffer for all enabled tc */
+ for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
+ struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i];
+
+ if (total_size < HCLGE_DEFAULT_TX_BUF)
+ return -ENOMEM;
+
+ if (hdev->hw_tc_map & BIT(i))
+ priv->tx_buf_size = HCLGE_DEFAULT_TX_BUF;
+ else
+ priv->tx_buf_size = 0;
+
+ total_size -= priv->tx_buf_size;
+ }
+
+ return 0;
+}
+
/* hclge_rx_buffer_calc: calculate the rx private buffer size for all TCs
* @hdev: pointer to struct hclge_dev
- * @tx_size: the allocated tx buffer for all TCs
+ * @buf_alloc: pointer to buffer calculation data
* @return: 0: calculate sucessful, negative: fail
*/
-int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size)
+int hclge_rx_buffer_calc(struct hclge_dev *hdev,
+ struct hclge_pkt_buf_alloc *buf_alloc)
{
- u32 rx_all = hdev->pkt_buf_size - tx_size;
+ u32 rx_all = hdev->pkt_buf_size;
int no_pfc_priv_num, pfc_priv_num;
struct hclge_priv_buf *priv;
int i;
+ rx_all -= hclge_get_tx_buff_alloced(buf_alloc);
+
/* When DCB is not supported, rx private
* buffer is not allocated.
*/
if (!hnae3_dev_dcb_supported(hdev)) {
- if (!hclge_is_rx_buf_ok(hdev, rx_all))
+ if (!hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
return -ENOMEM;
return 0;
@@ -1501,7 +1558,7 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size)
/* step 1, try to alloc private buffer for all enabled tc */
for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
- priv = &hdev->priv_buf[i];
+ priv = &buf_alloc->priv_buf[i];
if (hdev->hw_tc_map & BIT(i)) {
priv->enable = 1;
if (hdev->tm_info.hw_pfc_map & BIT(i)) {
@@ -1522,14 +1579,14 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size)
}
}
- if (hclge_is_rx_buf_ok(hdev, rx_all))
+ if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
return 0;
/* step 2, try to decrease the buffer size of
* no pfc TC's private buffer
*/
for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
- priv = &hdev->priv_buf[i];
+ priv = &buf_alloc->priv_buf[i];
priv->enable = 0;
priv->wl.low = 0;
@@ -1552,18 +1609,18 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size)
}
}
- if (hclge_is_rx_buf_ok(hdev, rx_all))
+ if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
return 0;
/* step 3, try to reduce the number of pfc disabled TCs,
* which have private buffer
*/
/* get the total no pfc enable TC number, which have private buffer */
- no_pfc_priv_num = hclge_get_no_pfc_priv_num(hdev);
+ no_pfc_priv_num = hclge_get_no_pfc_priv_num(hdev, buf_alloc);
/* let the last to be cleared first */
for (i = HCLGE_MAX_TC_NUM - 1; i >= 0; i--) {
- priv = &hdev->priv_buf[i];
+ priv = &buf_alloc->priv_buf[i];
if (hdev->hw_tc_map & BIT(i) &&
!(hdev->tm_info.hw_pfc_map & BIT(i))) {
@@ -1575,22 +1632,22 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size)
no_pfc_priv_num--;
}
- if (hclge_is_rx_buf_ok(hdev, rx_all) ||
+ if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all) ||
no_pfc_priv_num == 0)
break;
}
- if (hclge_is_rx_buf_ok(hdev, rx_all))
+ if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
return 0;
/* step 4, try to reduce the number of pfc enabled TCs
* which have private buffer.
*/
- pfc_priv_num = hclge_get_pfc_priv_num(hdev);
+ pfc_priv_num = hclge_get_pfc_priv_num(hdev, buf_alloc);
/* let the last to be cleared first */
for (i = HCLGE_MAX_TC_NUM - 1; i >= 0; i--) {
- priv = &hdev->priv_buf[i];
+ priv = &buf_alloc->priv_buf[i];
if (hdev->hw_tc_map & BIT(i) &&
hdev->tm_info.hw_pfc_map & BIT(i)) {
@@ -1602,17 +1659,18 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size)
pfc_priv_num--;
}
- if (hclge_is_rx_buf_ok(hdev, rx_all) ||
+ if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all) ||
pfc_priv_num == 0)
break;
}
- if (hclge_is_rx_buf_ok(hdev, rx_all))
+ if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
return 0;
return -ENOMEM;
}
-static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev)
+static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev,
+ struct hclge_pkt_buf_alloc *buf_alloc)
{
struct hclge_rx_priv_buff *req;
struct hclge_desc desc;
@@ -1624,7 +1682,7 @@ static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev)
/* Alloc private buffer TCs */
for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
- struct hclge_priv_buf *priv = &hdev->priv_buf[i];
+ struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i];
req->buf_num[i] =
cpu_to_le16(priv->buf_size >> HCLGE_BUF_UNIT_S);
@@ -1633,7 +1691,7 @@ static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev)
}
req->shared_buf =
- cpu_to_le16((hdev->s_buf.buf_size >> HCLGE_BUF_UNIT_S) |
+ cpu_to_le16((buf_alloc->s_buf.buf_size >> HCLGE_BUF_UNIT_S) |
(1 << HCLGE_TC0_PRI_BUF_EN_B));
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -1648,7 +1706,8 @@ static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev)
#define HCLGE_PRIV_ENABLE(a) ((a) > 0 ? 1 : 0)
-static int hclge_rx_priv_wl_config(struct hclge_dev *hdev)
+static int hclge_rx_priv_wl_config(struct hclge_dev *hdev,
+ struct hclge_pkt_buf_alloc *buf_alloc)
{
struct hclge_rx_priv_wl_buf *req;
struct hclge_priv_buf *priv;
@@ -1668,7 +1727,9 @@ static int hclge_rx_priv_wl_config(struct hclge_dev *hdev)
desc[i].flag &= ~cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
for (j = 0; j < HCLGE_TC_NUM_ONE_DESC; j++) {
- priv = &hdev->priv_buf[i * HCLGE_TC_NUM_ONE_DESC + j];
+ u32 idx = i * HCLGE_TC_NUM_ONE_DESC + j;
+
+ priv = &buf_alloc->priv_buf[idx];
req->tc_wl[j].high =
cpu_to_le16(priv->wl.high >> HCLGE_BUF_UNIT_S);
req->tc_wl[j].high |=
@@ -1693,9 +1754,10 @@ static int hclge_rx_priv_wl_config(struct hclge_dev *hdev)
return 0;
}
-static int hclge_common_thrd_config(struct hclge_dev *hdev)
+static int hclge_common_thrd_config(struct hclge_dev *hdev,
+ struct hclge_pkt_buf_alloc *buf_alloc)
{
- struct hclge_shared_buf *s_buf = &hdev->s_buf;
+ struct hclge_shared_buf *s_buf = &buf_alloc->s_buf;
struct hclge_rx_com_thrd *req;
struct hclge_desc desc[2];
struct hclge_tc_thrd *tc;
@@ -1739,9 +1801,10 @@ static int hclge_common_thrd_config(struct hclge_dev *hdev)
return 0;
}
-static int hclge_common_wl_config(struct hclge_dev *hdev)
+static int hclge_common_wl_config(struct hclge_dev *hdev,
+ struct hclge_pkt_buf_alloc *buf_alloc)
{
- struct hclge_shared_buf *buf = &hdev->s_buf;
+ struct hclge_shared_buf *buf = &buf_alloc->s_buf;
struct hclge_rx_com_wl *req;
struct hclge_desc desc;
int ret;
@@ -1771,63 +1834,68 @@ static int hclge_common_wl_config(struct hclge_dev *hdev)
int hclge_buffer_alloc(struct hclge_dev *hdev)
{
- u32 tx_buf_size = HCLGE_DEFAULT_TX_BUF;
+ struct hclge_pkt_buf_alloc *pkt_buf;
int ret;
- hdev->priv_buf = devm_kmalloc_array(&hdev->pdev->dev, HCLGE_MAX_TC_NUM,
- sizeof(struct hclge_priv_buf),
- GFP_KERNEL | __GFP_ZERO);
- if (!hdev->priv_buf)
+ pkt_buf = kzalloc(sizeof(*pkt_buf), GFP_KERNEL);
+ if (!pkt_buf)
return -ENOMEM;
- ret = hclge_tx_buffer_alloc(hdev, tx_buf_size);
+ ret = hclge_tx_buffer_calc(hdev, pkt_buf);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "could not calc tx buffer size for all TCs %d\n", ret);
+ goto out;
+ }
+
+ ret = hclge_tx_buffer_alloc(hdev, pkt_buf);
if (ret) {
dev_err(&hdev->pdev->dev,
"could not alloc tx buffers %d\n", ret);
- return ret;
+ goto out;
}
- ret = hclge_rx_buffer_calc(hdev, tx_buf_size);
+ ret = hclge_rx_buffer_calc(hdev, pkt_buf);
if (ret) {
dev_err(&hdev->pdev->dev,
"could not calc rx priv buffer size for all TCs %d\n",
ret);
- return ret;
+ goto out;
}
- ret = hclge_rx_priv_buf_alloc(hdev);
+ ret = hclge_rx_priv_buf_alloc(hdev, pkt_buf);
if (ret) {
dev_err(&hdev->pdev->dev, "could not alloc rx priv buffer %d\n",
ret);
- return ret;
+ goto out;
}
if (hnae3_dev_dcb_supported(hdev)) {
- ret = hclge_rx_priv_wl_config(hdev);
+ ret = hclge_rx_priv_wl_config(hdev, pkt_buf);
if (ret) {
dev_err(&hdev->pdev->dev,
"could not configure rx private waterline %d\n",
ret);
- return ret;
+ goto out;
}
- ret = hclge_common_thrd_config(hdev);
+ ret = hclge_common_thrd_config(hdev, pkt_buf);
if (ret) {
dev_err(&hdev->pdev->dev,
"could not configure common threshold %d\n",
ret);
- return ret;
+ goto out;
}
}
- ret = hclge_common_wl_config(hdev);
- if (ret) {
+ ret = hclge_common_wl_config(hdev, pkt_buf);
+ if (ret)
dev_err(&hdev->pdev->dev,
"could not configure common waterline %d\n", ret);
- return ret;
- }
- return 0;
+out:
+ kfree(pkt_buf);
+ return ret;
}
static int hclge_init_roce_base_info(struct hclge_vport *vport)
@@ -2597,7 +2665,7 @@ static int hclge_get_tc_size(struct hnae3_handle *handle)
return hdev->rss_size_max;
}
-static int hclge_rss_init_hw(struct hclge_dev *hdev)
+int hclge_rss_init_hw(struct hclge_dev *hdev)
{
const u8 hfunc = HCLGE_RSS_HASH_ALGO_TOEPLITZ;
struct hclge_vport *vport = hdev->vport;
@@ -4182,6 +4250,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
return ret;
}
+ hclge_dcb_ops_set(hdev);
+
setup_timer(&hdev->service_timer, hclge_service_timer,
(unsigned long)hdev);
INIT_WORK(&hdev->service_task, hclge_service_task);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 9fcfd9395424..7c66c00e8a3e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -421,8 +421,11 @@ struct hclge_dev {
#define HCLGE_FLAG_TC_BASE_SCH_MODE 1
#define HCLGE_FLAG_VNET_BASE_SCH_MODE 2
u8 tx_sch_mode;
+ u8 tc_max;
+ u8 pfc_max;
u8 default_up;
+ u8 dcbx_cap;
struct hclge_tm_info tm_info;
u16 num_msi;
@@ -463,8 +466,6 @@ struct hclge_dev {
u32 pkt_buf_size; /* Total pf buf size for tx/rx */
u32 mps; /* Max packet size */
- struct hclge_priv_buf *priv_buf;
- struct hclge_shared_buf s_buf;
enum hclge_mta_dmac_sel_type mta_mac_sel_type;
bool enable_mta; /* Mutilcast filter enable */
@@ -517,4 +518,7 @@ static inline int hclge_get_queue_id(struct hnae3_queue *queue)
int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex);
int hclge_set_vf_vlan_common(struct hclge_dev *vport, int vfid,
bool is_kill, u16 vlan, u8 qos, __be16 proto);
+
+int hclge_buffer_alloc(struct hclge_dev *hdev);
+int hclge_rss_init_hw(struct hclge_dev *hdev);
#endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 73a75d7cc551..359ee670d1e1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -124,6 +124,20 @@ static int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx)
return hclge_cmd_send(&hdev->hw, &desc, 1);
}
+static int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap,
+ u8 pfc_bitmap)
+{
+ struct hclge_desc desc;
+ struct hclge_pfc_en_cmd *pfc = (struct hclge_pfc_en_cmd *)&desc.data;
+
+ hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_PFC_PAUSE_EN, false);
+
+ pfc->tx_rx_en_bitmap = tx_rx_bitmap;
+ pfc->pri_en_bitmap = pfc_bitmap;
+
+ return hclge_cmd_send(&hdev->hw, &desc, 1);
+}
+
static int hclge_fill_pri_array(struct hclge_dev *hdev, u8 *pri, u8 pri_id)
{
u8 tc;
@@ -287,6 +301,34 @@ static int hclge_tm_pg_shapping_cfg(struct hclge_dev *hdev,
return hclge_cmd_send(&hdev->hw, &desc, 1);
}
+static int hclge_tm_port_shaper_cfg(struct hclge_dev *hdev)
+{
+ struct hclge_port_shapping_cmd *shap_cfg_cmd;
+ struct hclge_desc desc;
+ u32 shapping_para = 0;
+ u8 ir_u, ir_b, ir_s;
+ int ret;
+
+ ret = hclge_shaper_para_calc(HCLGE_ETHER_MAX_RATE,
+ HCLGE_SHAPER_LVL_PORT,
+ &ir_b, &ir_u, &ir_s);
+ if (ret)
+ return ret;
+
+ hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PORT_SHAPPING, false);
+ shap_cfg_cmd = (struct hclge_port_shapping_cmd *)desc.data;
+
+ hclge_tm_set_field(shapping_para, IR_B, ir_b);
+ hclge_tm_set_field(shapping_para, IR_U, ir_u);
+ hclge_tm_set_field(shapping_para, IR_S, ir_s);
+ hclge_tm_set_field(shapping_para, BS_B, HCLGE_SHAPER_BS_U_DEF);
+ hclge_tm_set_field(shapping_para, BS_S, HCLGE_SHAPER_BS_S_DEF);
+
+ shap_cfg_cmd->port_shapping_para = cpu_to_le32(shapping_para);
+
+ return hclge_cmd_send(&hdev->hw, &desc, 1);
+}
+
static int hclge_tm_pri_shapping_cfg(struct hclge_dev *hdev,
enum hclge_shap_bucket bucket, u8 pri_id,
u8 ir_b, u8 ir_u, u8 ir_s,
@@ -346,13 +388,13 @@ static int hclge_tm_pri_schd_mode_cfg(struct hclge_dev *hdev, u8 pri_id)
return hclge_cmd_send(&hdev->hw, &desc, 1);
}
-static int hclge_tm_qs_schd_mode_cfg(struct hclge_dev *hdev, u16 qs_id)
+static int hclge_tm_qs_schd_mode_cfg(struct hclge_dev *hdev, u16 qs_id, u8 mode)
{
struct hclge_desc desc;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_QS_SCH_MODE_CFG, false);
- if (hdev->tm_info.tc_info[qs_id].tc_sch_mode == HCLGE_SCH_MODE_DWRR)
+ if (mode == HCLGE_SCH_MODE_DWRR)
desc.data[1] = cpu_to_le32(HCLGE_TM_TX_SCHD_DWRR_MSK);
else
desc.data[1] = 0;
@@ -444,7 +486,11 @@ static void hclge_tm_tc_info_init(struct hclge_dev *hdev)
hdev->tm_info.prio_tc[i] =
(i >= hdev->tm_info.num_tc) ? 0 : i;
- hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
+ /* DCB is enabled if we have more than 1 TC */
+ if (hdev->tm_info.num_tc > 1)
+ hdev->flag |= HCLGE_FLAG_DCB_ENABLE;
+ else
+ hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
}
static void hclge_tm_pg_info_init(struct hclge_dev *hdev)
@@ -470,6 +516,24 @@ static void hclge_tm_pg_info_init(struct hclge_dev *hdev)
}
}
+static void hclge_pfc_info_init(struct hclge_dev *hdev)
+{
+ if (!(hdev->flag & HCLGE_FLAG_DCB_ENABLE)) {
+ if (hdev->fc_mode_last_time == HCLGE_FC_PFC)
+ dev_warn(&hdev->pdev->dev,
+ "DCB is disable, but last mode is FC_PFC\n");
+
+ hdev->tm_info.fc_mode = hdev->fc_mode_last_time;
+ } else if (hdev->tm_info.fc_mode != HCLGE_FC_PFC) {
+ /* fc_mode_last_time record the last fc_mode when
+ * DCB is enabled, so that fc_mode can be set to
+ * the correct value when DCB is disabled.
+ */
+ hdev->fc_mode_last_time = hdev->tm_info.fc_mode;
+ hdev->tm_info.fc_mode = HCLGE_FC_PFC;
+ }
+}
+
static int hclge_tm_schd_info_init(struct hclge_dev *hdev)
{
if ((hdev->tx_sch_mode != HCLGE_FLAG_TC_BASE_SCH_MODE) &&
@@ -482,8 +546,7 @@ static int hclge_tm_schd_info_init(struct hclge_dev *hdev)
hclge_tm_vport_info_update(hdev);
- hdev->tm_info.fc_mode = HCLGE_FC_NONE;
- hdev->fc_mode_last_time = hdev->tm_info.fc_mode;
+ hclge_pfc_info_init(hdev);
return 0;
}
@@ -596,17 +659,18 @@ static int hclge_tm_pri_q_qs_cfg(struct hclge_dev *hdev)
{
struct hclge_vport *vport = hdev->vport;
int ret;
- u32 i;
+ u32 i, k;
if (hdev->tx_sch_mode == HCLGE_FLAG_TC_BASE_SCH_MODE) {
/* Cfg qs -> pri mapping, one by one mapping */
- for (i = 0; i < hdev->tm_info.num_tc; i++) {
- ret = hclge_tm_qs_to_pri_map_cfg(hdev, i, i);
- if (ret)
- return ret;
- }
+ for (k = 0; k < hdev->num_alloc_vport; k++)
+ for (i = 0; i < hdev->tm_info.num_tc; i++) {
+ ret = hclge_tm_qs_to_pri_map_cfg(
+ hdev, vport[k].qs_offset + i, i);
+ if (ret)
+ return ret;
+ }
} else if (hdev->tx_sch_mode == HCLGE_FLAG_VNET_BASE_SCH_MODE) {
- int k;
/* Cfg qs -> pri mapping, qs = tc, pri = vf, 8 qs -> 1 pri */
for (k = 0; k < hdev->num_alloc_vport; k++)
for (i = 0; i < HNAE3_MAX_TC; i++) {
@@ -755,10 +819,11 @@ static int hclge_tm_pri_shaper_cfg(struct hclge_dev *hdev)
static int hclge_tm_pri_tc_base_dwrr_cfg(struct hclge_dev *hdev)
{
+ struct hclge_vport *vport = hdev->vport;
struct hclge_pg_info *pg_info;
u8 dwrr;
int ret;
- u32 i;
+ u32 i, k;
for (i = 0; i < hdev->tm_info.num_tc; i++) {
pg_info =
@@ -769,9 +834,13 @@ static int hclge_tm_pri_tc_base_dwrr_cfg(struct hclge_dev *hdev)
if (ret)
return ret;
- ret = hclge_tm_qs_weight_cfg(hdev, i, dwrr);
- if (ret)
- return ret;
+ for (k = 0; k < hdev->num_alloc_vport; k++) {
+ ret = hclge_tm_qs_weight_cfg(
+ hdev, vport[k].qs_offset + i,
+ vport[k].dwrr);
+ if (ret)
+ return ret;
+ }
}
return 0;
@@ -835,10 +904,14 @@ static int hclge_tm_pri_dwrr_cfg(struct hclge_dev *hdev)
return 0;
}
-static int hclge_tm_map_cfg(struct hclge_dev *hdev)
+int hclge_tm_map_cfg(struct hclge_dev *hdev)
{
int ret;
+ ret = hclge_up_to_tc_map(hdev);
+ if (ret)
+ return ret;
+
ret = hclge_tm_pg_to_pri_map(hdev);
if (ret)
return ret;
@@ -850,6 +923,10 @@ static int hclge_tm_shaper_cfg(struct hclge_dev *hdev)
{
int ret;
+ ret = hclge_tm_port_shaper_cfg(hdev);
+ if (ret)
+ return ret;
+
ret = hclge_tm_pg_shaper_cfg(hdev);
if (ret)
return ret;
@@ -898,7 +975,10 @@ static int hclge_tm_schd_mode_vnet_base_cfg(struct hclge_vport *vport)
return ret;
for (i = 0; i < kinfo->num_tc; i++) {
- ret = hclge_tm_qs_schd_mode_cfg(hdev, vport->qs_offset + i);
+ u8 sch_mode = hdev->tm_info.tc_info[i].tc_sch_mode;
+
+ ret = hclge_tm_qs_schd_mode_cfg(hdev, vport->qs_offset + i,
+ sch_mode);
if (ret)
return ret;
}
@@ -910,7 +990,7 @@ static int hclge_tm_lvl34_schd_mode_cfg(struct hclge_dev *hdev)
{
struct hclge_vport *vport = hdev->vport;
int ret;
- u8 i;
+ u8 i, k;
if (hdev->tx_sch_mode == HCLGE_FLAG_TC_BASE_SCH_MODE) {
for (i = 0; i < hdev->tm_info.num_tc; i++) {
@@ -918,9 +998,13 @@ static int hclge_tm_lvl34_schd_mode_cfg(struct hclge_dev *hdev)
if (ret)
return ret;
- ret = hclge_tm_qs_schd_mode_cfg(hdev, i);
- if (ret)
- return ret;
+ for (k = 0; k < hdev->num_alloc_vport; k++) {
+ ret = hclge_tm_qs_schd_mode_cfg(
+ hdev, vport[k].qs_offset + i,
+ HCLGE_SCH_MODE_DWRR);
+ if (ret)
+ return ret;
+ }
}
} else {
for (i = 0; i < hdev->num_alloc_vport; i++) {
@@ -935,7 +1019,7 @@ static int hclge_tm_lvl34_schd_mode_cfg(struct hclge_dev *hdev)
return 0;
}
-static int hclge_tm_schd_mode_hw(struct hclge_dev *hdev)
+int hclge_tm_schd_mode_hw(struct hclge_dev *hdev)
{
int ret;
@@ -969,27 +1053,109 @@ static int hclge_tm_schd_setup_hw(struct hclge_dev *hdev)
return hclge_tm_schd_mode_hw(hdev);
}
+static int hclge_pfc_setup_hw(struct hclge_dev *hdev)
+{
+ u8 enable_bitmap = 0;
+
+ if (hdev->tm_info.fc_mode == HCLGE_FC_PFC)
+ enable_bitmap = HCLGE_TX_MAC_PAUSE_EN_MSK |
+ HCLGE_RX_MAC_PAUSE_EN_MSK;
+
+ return hclge_pfc_pause_en_cfg(hdev, enable_bitmap,
+ hdev->tm_info.hw_pfc_map);
+}
+
+static int hclge_mac_pause_setup_hw(struct hclge_dev *hdev)
+{
+ bool tx_en, rx_en;
+
+ switch (hdev->tm_info.fc_mode) {
+ case HCLGE_FC_NONE:
+ tx_en = false;
+ rx_en = false;
+ break;
+ case HCLGE_FC_RX_PAUSE:
+ tx_en = false;
+ rx_en = true;
+ break;
+ case HCLGE_FC_TX_PAUSE:
+ tx_en = true;
+ rx_en = false;
+ break;
+ case HCLGE_FC_FULL:
+ tx_en = true;
+ rx_en = true;
+ break;
+ default:
+ tx_en = true;
+ rx_en = true;
+ }
+
+ return hclge_mac_pause_en_cfg(hdev, tx_en, rx_en);
+}
+
int hclge_pause_setup_hw(struct hclge_dev *hdev)
{
- bool en = hdev->tm_info.fc_mode != HCLGE_FC_PFC;
int ret;
u8 i;
- ret = hclge_mac_pause_en_cfg(hdev, en, en);
- if (ret)
- return ret;
+ if (hdev->tm_info.fc_mode != HCLGE_FC_PFC)
+ return hclge_mac_pause_setup_hw(hdev);
- /* Only DCB-supported dev supports qset back pressure setting */
+ /* Only DCB-supported dev supports qset back pressure and pfc cmd */
if (!hnae3_dev_dcb_supported(hdev))
return 0;
+ /* When MAC is GE Mode, hdev does not support pfc setting */
+ ret = hclge_pfc_setup_hw(hdev);
+ if (ret)
+ dev_warn(&hdev->pdev->dev, "set pfc pause failed:%d\n", ret);
+
for (i = 0; i < hdev->tm_info.num_tc; i++) {
ret = hclge_tm_qs_bp_cfg(hdev, i);
if (ret)
return ret;
}
- return hclge_up_to_tc_map(hdev);
+ return 0;
+}
+
+int hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc)
+{
+ struct hclge_vport *vport = hdev->vport;
+ struct hnae3_knic_private_info *kinfo;
+ u32 i, k;
+
+ for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
+ if (prio_tc[i] >= hdev->tm_info.num_tc)
+ return -EINVAL;
+ hdev->tm_info.prio_tc[i] = prio_tc[i];
+
+ for (k = 0; k < hdev->num_alloc_vport; k++) {
+ kinfo = &vport[k].nic.kinfo;
+ kinfo->prio_tc[i] = prio_tc[i];
+ }
+ }
+ return 0;
+}
+
+void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc)
+{
+ u8 i, bit_map = 0;
+
+ hdev->tm_info.num_tc = num_tc;
+
+ for (i = 0; i < hdev->tm_info.num_tc; i++)
+ bit_map |= BIT(i);
+
+ if (!bit_map) {
+ bit_map = 1;
+ hdev->tm_info.num_tc = 1;
+ }
+
+ hdev->hw_tc_map = bit_map;
+
+ hclge_tm_schd_info_init(hdev);
}
int hclge_tm_init_hw(struct hclge_dev *hdev)
@@ -1013,8 +1179,13 @@ int hclge_tm_init_hw(struct hclge_dev *hdev)
int hclge_tm_schd_init(struct hclge_dev *hdev)
{
- int ret = hclge_tm_schd_info_init(hdev);
+ int ret;
+
+ /* fc_mode is HCLGE_FC_FULL on reset */
+ hdev->tm_info.fc_mode = HCLGE_FC_FULL;
+ hdev->fc_mode_last_time = hdev->tm_info.fc_mode;
+ ret = hclge_tm_schd_info_init(hdev);
if (ret)
return ret;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index 85158b0d73fe..bf59961918ab 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -94,6 +94,15 @@ struct hclge_bp_to_qs_map_cmd {
u32 rsvd1;
};
+struct hclge_pfc_en_cmd {
+ u8 tx_rx_en_bitmap;
+ u8 pri_en_bitmap;
+};
+
+struct hclge_port_shapping_cmd {
+ __le32 port_shapping_para;
+};
+
#define hclge_tm_set_field(dest, string, val) \
hnae_set_field((dest), (HCLGE_TM_SHAP_##string##_MSK), \
(HCLGE_TM_SHAP_##string##_LSH), val)
@@ -103,4 +112,10 @@ struct hclge_bp_to_qs_map_cmd {
int hclge_tm_schd_init(struct hclge_dev *hdev);
int hclge_pause_setup_hw(struct hclge_dev *hdev);
+int hclge_tm_schd_mode_hw(struct hclge_dev *hdev);
+int hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc);
+void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc);
+int hclge_tm_dwrr_cfg(struct hclge_dev *hdev);
+int hclge_tm_map_cfg(struct hclge_dev *hdev);
+int hclge_tm_init_hw(struct hclge_dev *hdev);
#endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c
new file mode 100644
index 000000000000..9832172bfb08
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c
@@ -0,0 +1,106 @@
+/*
+ * Copyright (c) 2016-2017 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "hnae3.h"
+#include "hns3_enet.h"
+
+static
+int hns3_dcbnl_ieee_getets(struct net_device *ndev, struct ieee_ets *ets)
+{
+ struct hns3_nic_priv *priv = netdev_priv(ndev);
+ struct hnae3_handle *h = priv->ae_handle;
+
+ if (h->kinfo.dcb_ops->ieee_getets)
+ return h->kinfo.dcb_ops->ieee_getets(h, ets);
+
+ return -EOPNOTSUPP;
+}
+
+static
+int hns3_dcbnl_ieee_setets(struct net_device *ndev, struct ieee_ets *ets)
+{
+ struct hns3_nic_priv *priv = netdev_priv(ndev);
+ struct hnae3_handle *h = priv->ae_handle;
+
+ if (h->kinfo.dcb_ops->ieee_setets)
+ return h->kinfo.dcb_ops->ieee_setets(h, ets);
+
+ return -EOPNOTSUPP;
+}
+
+static
+int hns3_dcbnl_ieee_getpfc(struct net_device *ndev, struct ieee_pfc *pfc)
+{
+ struct hns3_nic_priv *priv = netdev_priv(ndev);
+ struct hnae3_handle *h = priv->ae_handle;
+
+ if (h->kinfo.dcb_ops->ieee_getpfc)
+ return h->kinfo.dcb_ops->ieee_getpfc(h, pfc);
+
+ return -EOPNOTSUPP;
+}
+
+static
+int hns3_dcbnl_ieee_setpfc(struct net_device *ndev, struct ieee_pfc *pfc)
+{
+ struct hns3_nic_priv *priv = netdev_priv(ndev);
+ struct hnae3_handle *h = priv->ae_handle;
+
+ if (h->kinfo.dcb_ops->ieee_setpfc)
+ return h->kinfo.dcb_ops->ieee_setpfc(h, pfc);
+
+ return -EOPNOTSUPP;
+}
+
+/* DCBX configuration */
+static u8 hns3_dcbnl_getdcbx(struct net_device *ndev)
+{
+ struct hns3_nic_priv *priv = netdev_priv(ndev);
+ struct hnae3_handle *h = priv->ae_handle;
+
+ if (h->kinfo.dcb_ops->getdcbx)
+ return h->kinfo.dcb_ops->getdcbx(h);
+
+ return 0;
+}
+
+/* return 0 if successful, otherwise fail */
+static u8 hns3_dcbnl_setdcbx(struct net_device *ndev, u8 mode)
+{
+ struct hns3_nic_priv *priv = netdev_priv(ndev);
+ struct hnae3_handle *h = priv->ae_handle;
+
+ if (h->kinfo.dcb_ops->setdcbx)
+ return h->kinfo.dcb_ops->setdcbx(h, mode);
+
+ return 1;
+}
+
+static const struct dcbnl_rtnl_ops hns3_dcbnl_ops = {
+ .ieee_getets = hns3_dcbnl_ieee_getets,
+ .ieee_setets = hns3_dcbnl_ieee_setets,
+ .ieee_getpfc = hns3_dcbnl_ieee_getpfc,
+ .ieee_setpfc = hns3_dcbnl_ieee_setpfc,
+ .getdcbx = hns3_dcbnl_getdcbx,
+ .setdcbx = hns3_dcbnl_setdcbx,
+};
+
+/* hclge_dcbnl_setup - DCBNL setup
+ * @handle: the corresponding vport handle
+ * Set up DCBNL
+ */
+void hns3_dcbnl_setup(struct hnae3_handle *handle)
+{
+ struct net_device *dev = handle->kinfo.netdev;
+
+ if (!handle->kinfo.dcb_ops)
+ return;
+
+ dev->dcbnl_ops = &hns3_dcbnl_ops;
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
index 35369e1c8036..c31506514e5d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
@@ -196,6 +196,32 @@ static void hns3_vector_gl_rl_init(struct hns3_enet_tqp_vector *tqp_vector)
tqp_vector->tx_group.flow_level = HNS3_FLOW_LOW;
}
+static int hns3_nic_set_real_num_queue(struct net_device *netdev)
+{
+ struct hns3_nic_priv *priv = netdev_priv(netdev);
+ struct hnae3_handle *h = priv->ae_handle;
+ struct hnae3_knic_private_info *kinfo = &h->kinfo;
+ unsigned int queue_size = kinfo->rss_size * kinfo->num_tc;
+ int ret;
+
+ ret = netif_set_real_num_tx_queues(netdev, queue_size);
+ if (ret) {
+ netdev_err(netdev,
+ "netif_set_real_num_tx_queues fail, ret=%d!\n",
+ ret);
+ return ret;
+ }
+
+ ret = netif_set_real_num_rx_queues(netdev, queue_size);
+ if (ret) {
+ netdev_err(netdev,
+ "netif_set_real_num_rx_queues fail, ret=%d!\n", ret);
+ return ret;
+ }
+
+ return 0;
+}
+
static int hns3_nic_net_up(struct net_device *netdev)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
@@ -232,26 +258,13 @@ out_start_err:
static int hns3_nic_net_open(struct net_device *netdev)
{
- struct hns3_nic_priv *priv = netdev_priv(netdev);
- struct hnae3_handle *h = priv->ae_handle;
int ret;
netif_carrier_off(netdev);
- ret = netif_set_real_num_tx_queues(netdev, h->kinfo.num_tqps);
- if (ret) {
- netdev_err(netdev,
- "netif_set_real_num_tx_queues fail, ret=%d!\n",
- ret);
+ ret = hns3_nic_set_real_num_queue(netdev);
+ if (ret)
return ret;
- }
-
- ret = netif_set_real_num_rx_queues(netdev, h->kinfo.num_tqps);
- if (ret) {
- netdev_err(netdev,
- "netif_set_real_num_rx_queues fail, ret=%d!\n", ret);
- return ret;
- }
ret = hns3_nic_net_up(netdev);
if (ret) {
@@ -2790,6 +2803,8 @@ static int hns3_client_init(struct hnae3_handle *handle)
goto out_reg_netdev_fail;
}
+ hns3_dcbnl_setup(handle);
+
/* MTU range: (ETH_MIN_MTU(kernel default) - 9706) */
netdev->max_mtu = HNS3_MAX_MTU - (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN);
@@ -2846,10 +2861,71 @@ static void hns3_link_status_change(struct hnae3_handle *handle, bool linkup)
}
}
+static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc)
+{
+ struct hnae3_knic_private_info *kinfo = &handle->kinfo;
+ struct net_device *ndev = kinfo->netdev;
+ bool if_running;
+ int ret;
+ u8 i;
+
+ if (tc > HNAE3_MAX_TC)
+ return -EINVAL;
+
+ if (!ndev)
+ return -ENODEV;
+
+ if_running = netif_running(ndev);
+
+ ret = netdev_set_num_tc(ndev, tc);
+ if (ret)
+ return ret;
+
+ if (if_running) {
+ (void)hns3_nic_net_stop(ndev);
+ msleep(100);
+ }
+
+ ret = (kinfo->dcb_ops && kinfo->dcb_ops->map_update) ?
+ kinfo->dcb_ops->map_update(handle) : -EOPNOTSUPP;
+ if (ret)
+ goto err_out;
+
+ if (tc <= 1) {
+ netdev_reset_tc(ndev);
+ goto out;
+ }
+
+ for (i = 0; i < HNAE3_MAX_TC; i++) {
+ struct hnae3_tc_info *tc_info = &kinfo->tc_info[i];
+
+ if (tc_info->enable)
+ netdev_set_tc_queue(ndev,
+ tc_info->tc,
+ tc_info->tqp_count,
+ tc_info->tqp_offset);
+ }
+
+ for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
+ netdev_set_prio_tc_map(ndev, i,
+ kinfo->prio_tc[i]);
+ }
+
+out:
+ ret = hns3_nic_set_real_num_queue(ndev);
+
+err_out:
+ if (if_running)
+ (void)hns3_nic_net_open(ndev);
+
+ return ret;
+}
+
const struct hnae3_client_ops client_ops = {
.init_instance = hns3_client_init,
.uninit_instance = hns3_client_uninit,
.link_status_change = hns3_link_status_change,
+ .setup_tc = hns3_client_setup_tc,
};
/* hns3_init_module - Driver registration routine
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h
index 7e8746189747..481eada73e2d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h
@@ -590,4 +590,11 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value)
void hns3_ethtool_set_ops(struct net_device *netdev);
int hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget);
+
+#ifdef CONFIG_HNS3_DCB
+void hns3_dcbnl_setup(struct hnae3_handle *handle);
+#else
+static inline void hns3_dcbnl_setup(struct hnae3_handle *handle) {}
+#endif
+
#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index 1d4f712b15a8..e2e5cdc7119c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -26,6 +26,7 @@
#include <linux/skbuff.h>
#include <linux/dma-mapping.h>
#include <linux/prefetch.h>
+#include <linux/cpumask.h>
#include <asm/barrier.h>
#include "hinic_common.h"
@@ -171,11 +172,10 @@ static int rx_alloc_pkts(struct hinic_rxq *rxq)
struct hinic_sge sge;
dma_addr_t dma_addr;
struct sk_buff *skb;
- int i, alloc_more;
u16 prod_idx;
+ int i;
free_wqebbs = hinic_get_rq_free_wqebbs(rxq->rq);
- alloc_more = 0;
/* Limit the allocation chunks */
if (free_wqebbs > nic_dev->rx_weight)
@@ -185,7 +185,6 @@ static int rx_alloc_pkts(struct hinic_rxq *rxq)
skb = rx_alloc_skb(rxq, &dma_addr);
if (!skb) {
netdev_err(rxq->netdev, "Failed to alloc Rx skb\n");
- alloc_more = 1;
goto skb_out;
}
@@ -195,7 +194,6 @@ static int rx_alloc_pkts(struct hinic_rxq *rxq)
&prod_idx);
if (!rq_wqe) {
rx_free_skb(rxq, skb, dma_addr);
- alloc_more = 1;
goto skb_out;
}
@@ -211,9 +209,7 @@ skb_out:
hinic_rq_update(rxq->rq, prod_idx);
}
- if (alloc_more)
- tasklet_schedule(&rxq->rx_task);
-
+ tasklet_schedule(&rxq->rx_task);
return i;
}
@@ -357,7 +353,7 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget)
}
if (pkts)
- tasklet_schedule(&rxq->rx_task); /* hinic_rx_alloc_pkts */
+ tasklet_schedule(&rxq->rx_task); /* rx_alloc_pkts */
u64_stats_update_begin(&rxq->rxq_stats.syncp);
rxq->rxq_stats.pkts += pkts;
@@ -417,6 +413,8 @@ static int rx_request_irq(struct hinic_rxq *rxq)
struct hinic_dev *nic_dev = netdev_priv(rxq->netdev);
struct hinic_hwdev *hwdev = nic_dev->hwdev;
struct hinic_rq *rq = rxq->rq;
+ struct hinic_qp *qp;
+ struct cpumask mask;
int err;
rx_add_napi(rxq);
@@ -432,7 +430,9 @@ static int rx_request_irq(struct hinic_rxq *rxq)
return err;
}
- return 0;
+ qp = container_of(rq, struct hinic_qp, rq);
+ cpumask_set_cpu(qp->q_id % num_online_cpus(), &mask);
+ return irq_set_affinity_hint(rq->irq, &mask);
}
static void rx_free_irq(struct hinic_rxq *rxq)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index abe3e38cd342..9128858479c4 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -212,10 +212,19 @@ netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
sq_wqe = hinic_sq_get_wqe(txq->sq, wqe_size, &prod_idx);
if (!sq_wqe) {
- tx_unmap_skb(nic_dev, skb, txq->sges);
-
netif_stop_subqueue(netdev, qp->q_id);
+ /* Check for the case free_tx_poll is called in another cpu
+ * and we stopped the subqueue after free_tx_poll check.
+ */
+ sq_wqe = hinic_sq_get_wqe(txq->sq, wqe_size, &prod_idx);
+ if (sq_wqe) {
+ netif_wake_subqueue(nic_dev->netdev, qp->q_id);
+ goto process_sq_wqe;
+ }
+
+ tx_unmap_skb(nic_dev, skb, txq->sges);
+
u64_stats_update_begin(&txq->txq_stats.syncp);
txq->txq_stats.tx_busy++;
u64_stats_update_end(&txq->txq_stats.syncp);
@@ -223,6 +232,7 @@ netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
goto flush_skbs;
}
+process_sq_wqe:
hinic_sq_prepare_wqe(txq->sq, prod_idx, sq_wqe, txq->sges, nr_sges);
hinic_sq_write_wqe(txq->sq, prod_idx, sq_wqe, skb, wqe_size);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index cb8182f4fdfa..4bc14a901571 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -927,6 +927,7 @@ static int ibmvnic_open(struct net_device *netdev)
}
rc = __ibmvnic_open(netdev);
+ netif_carrier_on(netdev);
mutex_unlock(&adapter->reset_lock);
return rc;
@@ -3899,6 +3900,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
if (rc)
goto ibmvnic_init_fail;
+ netif_carrier_off(netdev);
rc = register_netdev(netdev);
if (rc) {
dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc);
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 4d10270ddf8f..184f11242f56 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -1910,11 +1910,10 @@ static int e100_alloc_cbs(struct nic *nic)
nic->cb_to_use = nic->cb_to_send = nic->cb_to_clean = NULL;
nic->cbs_avail = 0;
- nic->cbs = pci_pool_alloc(nic->cbs_pool, GFP_KERNEL,
- &nic->cbs_dma_addr);
+ nic->cbs = pci_pool_zalloc(nic->cbs_pool, GFP_KERNEL,
+ &nic->cbs_dma_addr);
if (!nic->cbs)
return -ENOMEM;
- memset(nic->cbs, 0, count * sizeof(struct cb));
for (cb = nic->cbs, i = 0; i < count; cb++, i++) {
cb->next = (i + 1 < count) ? cb + 1 : nic->cbs;
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 327dfe5bedc0..8436c5f2c3e8 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -7252,13 +7252,10 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto err_eeprom;
}
- init_timer(&adapter->watchdog_timer);
- adapter->watchdog_timer.function = e1000_watchdog;
- adapter->watchdog_timer.data = (unsigned long)adapter;
-
- init_timer(&adapter->phy_info_timer);
- adapter->phy_info_timer.function = e1000_update_phy_info;
- adapter->phy_info_timer.data = (unsigned long)adapter;
+ setup_timer(&adapter->watchdog_timer, e1000_watchdog,
+ (unsigned long)adapter);
+ setup_timer(&adapter->phy_info_timer, e1000_update_phy_info,
+ (unsigned long)adapter);
INIT_WORK(&adapter->reset_task, e1000_reset_task);
INIT_WORK(&adapter->watchdog_task, e1000_watchdog_task);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h
index 689c413b7782..46973fb234c5 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k.h
@@ -248,6 +248,29 @@ struct fm10k_udp_port {
__be16 port;
};
+enum fm10k_macvlan_request_type {
+ FM10K_UC_MAC_REQUEST,
+ FM10K_MC_MAC_REQUEST,
+ FM10K_VLAN_REQUEST
+};
+
+struct fm10k_macvlan_request {
+ enum fm10k_macvlan_request_type type;
+ struct list_head list;
+ union {
+ struct fm10k_mac_request {
+ u8 addr[ETH_ALEN];
+ u16 glort;
+ u16 vid;
+ } mac;
+ struct fm10k_vlan_request {
+ u32 vid;
+ u8 vsi;
+ } vlan;
+ };
+ bool set;
+};
+
/* one work queue for entire driver */
extern struct workqueue_struct *fm10k_workqueue;
@@ -270,11 +293,15 @@ enum fm10k_flags_t {
enum fm10k_state_t {
__FM10K_RESETTING,
+ __FM10K_RESET_DETACHED,
+ __FM10K_RESET_SUSPENDED,
__FM10K_DOWN,
__FM10K_SERVICE_SCHED,
__FM10K_SERVICE_REQUEST,
__FM10K_SERVICE_DISABLE,
- __FM10K_MBX_LOCK,
+ __FM10K_MACVLAN_SCHED,
+ __FM10K_MACVLAN_REQUEST,
+ __FM10K_MACVLAN_DISABLE,
__FM10K_LINK_DOWN,
__FM10K_UPDATING_STATS,
/* This value must be last and determines the BITMAP size */
@@ -344,6 +371,8 @@ struct fm10k_intfc {
struct fm10k_hw_stats stats;
struct fm10k_hw hw;
+ /* Mailbox lock */
+ spinlock_t mbx_lock;
u32 __iomem *uc_addr;
u32 __iomem *sw_addr;
u16 msg_enable;
@@ -365,6 +394,12 @@ struct fm10k_intfc {
struct list_head vxlan_port;
struct list_head geneve_port;
+ /* MAC/VLAN update queue */
+ struct list_head macvlan_requests;
+ struct delayed_work macvlan_task;
+ /* MAC/VLAN update queue lock */
+ spinlock_t macvlan_lock;
+
#ifdef CONFIG_DEBUG_FS
struct dentry *dbg_intfc;
#endif /* CONFIG_DEBUG_FS */
@@ -384,23 +419,17 @@ struct fm10k_intfc {
static inline void fm10k_mbx_lock(struct fm10k_intfc *interface)
{
- /* busy loop if we cannot obtain the lock as some calls
- * such as ndo_set_rx_mode may be made in atomic context
- */
- while (test_and_set_bit(__FM10K_MBX_LOCK, interface->state))
- udelay(20);
+ spin_lock(&interface->mbx_lock);
}
static inline void fm10k_mbx_unlock(struct fm10k_intfc *interface)
{
- /* flush memory to make sure state is correct */
- smp_mb__before_atomic();
- clear_bit(__FM10K_MBX_LOCK, interface->state);
+ spin_unlock(&interface->mbx_lock);
}
static inline int fm10k_mbx_trylock(struct fm10k_intfc *interface)
{
- return !test_and_set_bit(__FM10K_MBX_LOCK, interface->state);
+ return spin_trylock(&interface->mbx_lock);
}
/* fm10k_test_staterr - test bits in Rx descriptor status and error fields */
@@ -490,6 +519,7 @@ void fm10k_up(struct fm10k_intfc *interface);
void fm10k_down(struct fm10k_intfc *interface);
void fm10k_update_stats(struct fm10k_intfc *interface);
void fm10k_service_event_schedule(struct fm10k_intfc *interface);
+void fm10k_macvlan_schedule(struct fm10k_intfc *interface);
void fm10k_update_rx_drop_en(struct fm10k_intfc *interface);
#ifdef CONFIG_NET_POLL_CONTROLLER
void fm10k_netpoll(struct net_device *netdev);
@@ -510,6 +540,12 @@ void fm10k_reset_rx_state(struct fm10k_intfc *);
int fm10k_setup_tc(struct net_device *dev, u8 tc);
int fm10k_open(struct net_device *netdev);
int fm10k_close(struct net_device *netdev);
+int fm10k_queue_vlan_request(struct fm10k_intfc *interface, u32 vid,
+ u8 vsi, bool set);
+int fm10k_queue_mac_request(struct fm10k_intfc *interface, u16 glort,
+ const unsigned char *addr, u16 vid, bool set);
+void fm10k_clear_macvlan_queue(struct fm10k_intfc *interface,
+ u16 glort, bool vlans);
/* Ethtool */
void fm10k_set_ethtool_ops(struct net_device *dev);
@@ -526,8 +562,8 @@ s32 fm10k_iov_update_pvid(struct fm10k_intfc *interface, u16 glort, u16 pvid);
int fm10k_ndo_set_vf_mac(struct net_device *netdev, int vf_idx, u8 *mac);
int fm10k_ndo_set_vf_vlan(struct net_device *netdev,
int vf_idx, u16 vid, u8 qos, __be16 vlan_proto);
-int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx, int rate,
- int unused);
+int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx,
+ int __always_unused min_rate, int max_rate);
int fm10k_ndo_get_vf_config(struct net_device *netdev,
int vf_idx, struct ifla_vf_info *ivi);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_common.c b/drivers/net/ethernet/intel/fm10k/fm10k_common.c
index 62a6ad9b3eed..736a9f087bc9 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_common.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_common.c
@@ -1,5 +1,5 @@
/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -517,8 +517,8 @@ s32 fm10k_get_host_state_generic(struct fm10k_hw *hw, bool *host_ready)
goto out;
}
- /* verify Mailbox is still valid */
- if (!mbx->ops.tx_ready(mbx, FM10K_VFMBX_MSG_MTU))
+ /* verify Mailbox is still open */
+ if (mbx->state != FM10K_STATE_OPEN)
goto out;
/* interface cannot receive traffic without logical ports */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c
index 5116fd043630..14df09e2d964 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c
@@ -52,9 +52,9 @@ static void fm10k_dbg_desc_seq_stop(struct seq_file __always_unused *s,
static void fm10k_dbg_desc_break(struct seq_file *s, int i)
{
while (i--)
- seq_puts(s, "-");
+ seq_putc(s, '-');
- seq_puts(s, "\n");
+ seq_putc(s, '\n');
}
static int fm10k_dbg_tx_desc_seq_show(struct seq_file *s, void *v)
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
index 5f4dac0d36ef..ea3ab24265ee 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
@@ -1,5 +1,5 @@
/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -35,10 +35,133 @@ static s32 fm10k_iov_msg_error(struct fm10k_hw *hw, u32 **results,
return fm10k_tlv_msg_error(hw, results, mbx);
}
+/**
+ * fm10k_iov_msg_queue_mac_vlan - Message handler for MAC/VLAN request from VF
+ * @hw: Pointer to hardware structure
+ * @results: Pointer array to message, results[0] is pointer to message
+ * @mbx: Pointer to mailbox information structure
+ *
+ * This function is a custom handler for MAC/VLAN requests from the VF. The
+ * assumption is that it is acceptable to directly hand off the message from
+ * the VF to the PF's switch manager. However, we use a MAC/VLAN message
+ * queue to avoid overloading the mailbox when a large number of requests
+ * come in.
+ **/
+static s32 fm10k_iov_msg_queue_mac_vlan(struct fm10k_hw *hw, u32 **results,
+ struct fm10k_mbx_info *mbx)
+{
+ struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx;
+ struct fm10k_intfc *interface = hw->back;
+ u8 mac[ETH_ALEN];
+ u32 *result;
+ int err = 0;
+ bool set;
+ u16 vlan;
+ u32 vid;
+
+ /* we shouldn't be updating rules on a disabled interface */
+ if (!FM10K_VF_FLAG_ENABLED(vf_info))
+ err = FM10K_ERR_PARAM;
+
+ if (!err && !!results[FM10K_MAC_VLAN_MSG_VLAN]) {
+ result = results[FM10K_MAC_VLAN_MSG_VLAN];
+
+ /* record VLAN id requested */
+ err = fm10k_tlv_attr_get_u32(result, &vid);
+ if (err)
+ return err;
+
+ set = !(vid & FM10K_VLAN_CLEAR);
+ vid &= ~FM10K_VLAN_CLEAR;
+
+ /* if the length field has been set, this is a multi-bit
+ * update request. For multi-bit requests, simply disallow
+ * them when the pf_vid has been set. In this case, the PF
+ * should have already cleared the VLAN_TABLE, and if we
+ * allowed them, it could allow a rogue VF to receive traffic
+ * on a VLAN it was not assigned. In the single-bit case, we
+ * need to modify requests for VLAN 0 to use the default PF or
+ * SW vid when assigned.
+ */
+
+ if (vid >> 16) {
+ /* prevent multi-bit requests when PF has
+ * administratively set the VLAN for this VF
+ */
+ if (vf_info->pf_vid)
+ return FM10K_ERR_PARAM;
+ } else {
+ err = fm10k_iov_select_vid(vf_info, (u16)vid);
+ if (err < 0)
+ return err;
+
+ vid = err;
+ }
+
+ /* update VSI info for VF in regards to VLAN table */
+ err = hw->mac.ops.update_vlan(hw, vid, vf_info->vsi, set);
+ }
+
+ if (!err && !!results[FM10K_MAC_VLAN_MSG_MAC]) {
+ result = results[FM10K_MAC_VLAN_MSG_MAC];
+
+ /* record unicast MAC address requested */
+ err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan);
+ if (err)
+ return err;
+
+ /* block attempts to set MAC for a locked device */
+ if (is_valid_ether_addr(vf_info->mac) &&
+ !ether_addr_equal(mac, vf_info->mac))
+ return FM10K_ERR_PARAM;
+
+ set = !(vlan & FM10K_VLAN_CLEAR);
+ vlan &= ~FM10K_VLAN_CLEAR;
+
+ err = fm10k_iov_select_vid(vf_info, vlan);
+ if (err < 0)
+ return err;
+
+ vlan = (u16)err;
+
+ /* Add this request to the MAC/VLAN queue */
+ err = fm10k_queue_mac_request(interface, vf_info->glort,
+ mac, vlan, set);
+ }
+
+ if (!err && !!results[FM10K_MAC_VLAN_MSG_MULTICAST]) {
+ result = results[FM10K_MAC_VLAN_MSG_MULTICAST];
+
+ /* record multicast MAC address requested */
+ err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan);
+ if (err)
+ return err;
+
+ /* verify that the VF is allowed to request multicast */
+ if (!(vf_info->vf_flags & FM10K_VF_FLAG_MULTI_ENABLED))
+ return FM10K_ERR_PARAM;
+
+ set = !(vlan & FM10K_VLAN_CLEAR);
+ vlan &= ~FM10K_VLAN_CLEAR;
+
+ err = fm10k_iov_select_vid(vf_info, vlan);
+ if (err < 0)
+ return err;
+
+ vlan = (u16)err;
+
+ /* Add this request to the MAC/VLAN queue */
+ err = fm10k_queue_mac_request(interface, vf_info->glort,
+ mac, vlan, set);
+ }
+
+ return err;
+}
+
static const struct fm10k_msg_data iov_mbx_data[] = {
FM10K_TLV_MSG_TEST_HANDLER(fm10k_tlv_msg_test),
FM10K_VF_MSG_MSIX_HANDLER(fm10k_iov_msg_msix_pf),
- FM10K_VF_MSG_MAC_VLAN_HANDLER(fm10k_iov_msg_mac_vlan_pf),
+ FM10K_VF_MSG_MAC_VLAN_HANDLER(fm10k_iov_msg_queue_mac_vlan),
FM10K_VF_MSG_LPORT_STATE_HANDLER(fm10k_iov_msg_lport_state_pf),
FM10K_TLV_MSG_ERROR_HANDLER(fm10k_iov_msg_error),
};
@@ -66,25 +189,21 @@ s32 fm10k_iov_event(struct fm10k_intfc *interface)
goto read_unlock;
/* read VFLRE to determine if any VFs have been reset */
- do {
- vflre = fm10k_read_reg(hw, FM10K_PFVFLRE(0));
- vflre <<= 32;
- vflre |= fm10k_read_reg(hw, FM10K_PFVFLRE(1));
- vflre = (vflre << 32) | (vflre >> 32);
- vflre |= fm10k_read_reg(hw, FM10K_PFVFLRE(0));
+ vflre = fm10k_read_reg(hw, FM10K_PFVFLRE(1));
+ vflre <<= 32;
+ vflre |= fm10k_read_reg(hw, FM10K_PFVFLRE(0));
- i = iov_data->num_vfs;
+ i = iov_data->num_vfs;
- for (vflre <<= 64 - i; vflre && i--; vflre += vflre) {
- struct fm10k_vf_info *vf_info = &iov_data->vf_info[i];
+ for (vflre <<= 64 - i; vflre && i--; vflre += vflre) {
+ struct fm10k_vf_info *vf_info = &iov_data->vf_info[i];
- if (vflre >= 0)
- continue;
+ if (vflre >= 0)
+ continue;
- hw->iov.ops.reset_resources(hw, vf_info);
- vf_info->mbx.ops.connect(hw, &vf_info->mbx);
- }
- } while (i != iov_data->num_vfs);
+ hw->iov.ops.reset_resources(hw, vf_info);
+ vf_info->mbx.ops.connect(hw, &vf_info->mbx);
+ }
read_unlock:
rcu_read_unlock();
@@ -126,9 +245,14 @@ process_mbx:
struct fm10k_mbx_info *mbx = &vf_info->mbx;
u16 glort = vf_info->glort;
+ /* process the SM mailbox first to drain outgoing messages */
+ hw->mbx.ops.process(hw, &hw->mbx);
+
/* verify port mapping is valid, if not reset port */
- if (vf_info->vf_flags && !fm10k_glort_valid_pf(hw, glort))
+ if (vf_info->vf_flags && !fm10k_glort_valid_pf(hw, glort)) {
hw->iov.ops.reset_lport(hw, vf_info);
+ fm10k_clear_macvlan_queue(interface, glort, false);
+ }
/* reset VFs that have mailbox timed out */
if (!mbx->timeout) {
@@ -140,6 +264,10 @@ process_mbx:
if (!hw->mbx.ops.tx_ready(&hw->mbx, FM10K_VFMBX_MSG_MTU)) {
/* keep track of how many times this occurs */
interface->hw_sm_mbx_full++;
+
+ /* make sure we try again momentarily */
+ fm10k_service_event_schedule(interface);
+
break;
}
@@ -187,6 +315,7 @@ void fm10k_iov_suspend(struct pci_dev *pdev)
hw->iov.ops.reset_resources(hw, vf_info);
hw->iov.ops.reset_lport(hw, vf_info);
+ fm10k_clear_macvlan_queue(interface, vf_info->glort, false);
}
}
@@ -411,6 +540,8 @@ static inline void fm10k_reset_vf_info(struct fm10k_intfc *interface,
/* disable LPORT for this VF which clears switch rules */
hw->iov.ops.reset_lport(hw, vf_info);
+ fm10k_clear_macvlan_queue(interface, vf_info->glort, false);
+
/* assign new MAC+VLAN for this VF */
hw->iov.ops.assign_default_mac_vlan(hw, vf_info);
@@ -482,7 +613,7 @@ int fm10k_ndo_set_vf_vlan(struct net_device *netdev, int vf_idx, u16 vid,
}
int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx,
- int __always_unused unused, int rate)
+ int __always_unused min_rate, int max_rate)
{
struct fm10k_intfc *interface = netdev_priv(netdev);
struct fm10k_iov_data *iov_data = interface->iov_data;
@@ -493,14 +624,15 @@ int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx,
return -EINVAL;
/* rate limit cannot be less than 10Mbs or greater than link speed */
- if (rate && ((rate < FM10K_VF_TC_MIN) || rate > FM10K_VF_TC_MAX))
+ if (max_rate &&
+ (max_rate < FM10K_VF_TC_MIN || max_rate > FM10K_VF_TC_MAX))
return -EINVAL;
/* store values */
- iov_data->vf_info[vf_idx].rate = rate;
+ iov_data->vf_info[vf_idx].rate = max_rate;
/* update hardware configuration */
- hw->iov.ops.configure_tc(hw, vf_idx, rate);
+ hw->iov.ops.configure_tc(hw, vf_idx, max_rate);
return 0;
}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 9dffaba85ae6..dbd69310f263 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -28,7 +28,7 @@
#include "fm10k.h"
-#define DRV_VERSION "0.21.7-k"
+#define DRV_VERSION "0.22.1-k"
#define DRV_SUMMARY "Intel(R) Ethernet Switch Host Interface Driver"
const char fm10k_driver_version[] = DRV_VERSION;
char fm10k_driver_name[] = "fm10k";
@@ -806,9 +806,10 @@ static int fm10k_tso(struct fm10k_ring *tx_ring,
tx_desc->mss = cpu_to_le16(skb_shinfo(skb)->gso_size);
return 1;
+
err_vxlan:
tx_ring->netdev->features &= ~NETIF_F_GSO_UDP_TUNNEL;
- if (!net_ratelimit())
+ if (net_ratelimit())
netdev_err(tx_ring->netdev,
"TSO requested for unsupported tunnel, disabling offload\n");
return -1;
@@ -876,6 +877,7 @@ static void fm10k_tx_csum(struct fm10k_ring *tx_ring,
case IPPROTO_GRE:
if (skb->encapsulation)
break;
+ /* fall through */
default:
if (unlikely(net_ratelimit())) {
dev_warn(tx_ring->dev,
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
index 334088a101c3..244d3ad58ca7 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
@@ -1,5 +1,5 @@
/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -1586,7 +1586,7 @@ s32 fm10k_pfvf_mbx_init(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx,
mbx->mbmem_reg = FM10K_MBMEM_VF(id, 0);
break;
}
- /* fallthough */
+ /* fall through */
default:
return FM10K_MBX_ERR_NO_MBX;
}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
index e69d49d91d67..81e4425f0529 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -643,9 +643,13 @@ int fm10k_close(struct net_device *netdev)
static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev)
{
struct fm10k_intfc *interface = netdev_priv(dev);
+ int num_tx_queues = READ_ONCE(interface->num_tx_queues);
unsigned int r_idx = skb->queue_mapping;
int err;
+ if (!num_tx_queues)
+ return NETDEV_TX_BUSY;
+
if ((skb->protocol == htons(ETH_P_8021Q)) &&
!skb_vlan_tag_present(skb)) {
/* FM10K only supports hardware tagging, any tags in frame
@@ -698,8 +702,8 @@ static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev)
__skb_put(skb, pad_len);
}
- if (r_idx >= interface->num_tx_queues)
- r_idx %= interface->num_tx_queues;
+ if (r_idx >= num_tx_queues)
+ r_idx %= num_tx_queues;
err = fm10k_xmit_frame_ring(skb, interface->tx_ring[r_idx]);
@@ -754,11 +758,132 @@ static bool fm10k_host_mbx_ready(struct fm10k_intfc *interface)
return (hw->mac.type == fm10k_mac_vf || interface->host_ready);
}
+/**
+ * fm10k_queue_vlan_request - Queue a VLAN update request
+ * @interface: the fm10k interface structure
+ * @vid: the VLAN vid
+ * @vsi: VSI index number
+ * @set: whether to set or clear
+ *
+ * This function queues up a VLAN update. For VFs, this must be sent to the
+ * managing PF over the mailbox. For PFs, we'll use the same handling so that
+ * it's similar to the VF. This avoids storming the PF<->VF mailbox with too
+ * many VLAN updates during reset.
+ */
+int fm10k_queue_vlan_request(struct fm10k_intfc *interface,
+ u32 vid, u8 vsi, bool set)
+{
+ struct fm10k_macvlan_request *request;
+ unsigned long flags;
+
+ /* This must be atomic since we may be called while the netdev
+ * addr_list_lock is held
+ */
+ request = kzalloc(sizeof(*request), GFP_ATOMIC);
+ if (!request)
+ return -ENOMEM;
+
+ request->type = FM10K_VLAN_REQUEST;
+ request->vlan.vid = vid;
+ request->vlan.vsi = vsi;
+ request->set = set;
+
+ spin_lock_irqsave(&interface->macvlan_lock, flags);
+ list_add_tail(&request->list, &interface->macvlan_requests);
+ spin_unlock_irqrestore(&interface->macvlan_lock, flags);
+
+ fm10k_macvlan_schedule(interface);
+
+ return 0;
+}
+
+/**
+ * fm10k_queue_mac_request - Queue a MAC update request
+ * @interface: the fm10k interface structure
+ * @glort: the target glort for this update
+ * @addr: the address to update
+ * @vid: the vid to update
+ * @sync: whether to add or remove
+ *
+ * This function queues up a MAC request for sending to the switch manager.
+ * A separate thread monitors the queue and sends updates to the switch
+ * manager. Return 0 on success, and negative error code on failure.
+ **/
+int fm10k_queue_mac_request(struct fm10k_intfc *interface, u16 glort,
+ const unsigned char *addr, u16 vid, bool set)
+{
+ struct fm10k_macvlan_request *request;
+ unsigned long flags;
+
+ /* This must be atomic since we may be called while the netdev
+ * addr_list_lock is held
+ */
+ request = kzalloc(sizeof(*request), GFP_ATOMIC);
+ if (!request)
+ return -ENOMEM;
+
+ if (is_multicast_ether_addr(addr))
+ request->type = FM10K_MC_MAC_REQUEST;
+ else
+ request->type = FM10K_UC_MAC_REQUEST;
+
+ ether_addr_copy(request->mac.addr, addr);
+ request->mac.glort = glort;
+ request->mac.vid = vid;
+ request->set = set;
+
+ spin_lock_irqsave(&interface->macvlan_lock, flags);
+ list_add_tail(&request->list, &interface->macvlan_requests);
+ spin_unlock_irqrestore(&interface->macvlan_lock, flags);
+
+ fm10k_macvlan_schedule(interface);
+
+ return 0;
+}
+
+/**
+ * fm10k_clear_macvlan_queue - Cancel pending updates for a given glort
+ * @interface: the fm10k interface structure
+ * @glort: the target glort to clear
+ * @vlans: true to clear VLAN messages, false to ignore them
+ *
+ * Cancel any outstanding MAC/VLAN requests for a given glort. This is
+ * expected to be called when a logical port goes down.
+ **/
+void fm10k_clear_macvlan_queue(struct fm10k_intfc *interface,
+ u16 glort, bool vlans)
+
+{
+ struct fm10k_macvlan_request *r, *tmp;
+ unsigned long flags;
+
+ spin_lock_irqsave(&interface->macvlan_lock, flags);
+
+ /* Free any outstanding MAC/VLAN requests for this interface */
+ list_for_each_entry_safe(r, tmp, &interface->macvlan_requests, list) {
+ switch (r->type) {
+ case FM10K_MC_MAC_REQUEST:
+ case FM10K_UC_MAC_REQUEST:
+ /* Don't free requests for other interfaces */
+ if (r->mac.glort != glort)
+ break;
+ /* fall through */
+ case FM10K_VLAN_REQUEST:
+ if (vlans) {
+ list_del(&r->list);
+ kfree(r);
+ }
+ break;
+ }
+ }
+
+ spin_unlock_irqrestore(&interface->macvlan_lock, flags);
+}
+
static int fm10k_uc_vlan_unsync(struct net_device *netdev,
const unsigned char *uc_addr)
{
struct fm10k_intfc *interface = netdev_priv(netdev);
- struct fm10k_hw *hw = &interface->hw;
u16 glort = interface->glort;
u16 vid = interface->vid;
bool set = !!(vid / VLAN_N_VID);
@@ -767,10 +892,7 @@ static int fm10k_uc_vlan_unsync(struct net_device *netdev,
/* drop any leading bits on the VLAN ID */
vid &= VLAN_N_VID - 1;
- if (fm10k_host_mbx_ready(interface))
- err = hw->mac.ops.update_uc_addr(hw, glort, uc_addr,
- vid, set, 0);
-
+ err = fm10k_queue_mac_request(interface, glort, uc_addr, vid, set);
if (err)
return err;
@@ -782,7 +904,6 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev,
const unsigned char *mc_addr)
{
struct fm10k_intfc *interface = netdev_priv(netdev);
- struct fm10k_hw *hw = &interface->hw;
u16 glort = interface->glort;
u16 vid = interface->vid;
bool set = !!(vid / VLAN_N_VID);
@@ -791,9 +912,7 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev,
/* drop any leading bits on the VLAN ID */
vid &= VLAN_N_VID - 1;
- if (fm10k_host_mbx_ready(interface))
- err = hw->mac.ops.update_mc_addr(hw, glort, mc_addr, vid, set);
-
+ err = fm10k_queue_mac_request(interface, glort, mc_addr, vid, set);
if (err)
return err;
@@ -851,18 +970,14 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set)
/* only need to update the VLAN if not in promiscuous mode */
if (!(netdev->flags & IFF_PROMISC)) {
- err = hw->mac.ops.update_vlan(hw, vid, 0, set);
+ err = fm10k_queue_vlan_request(interface, vid, 0, set);
if (err)
goto err_out;
}
- /* update our base MAC address if host's mailbox is ready */
- if (fm10k_host_mbx_ready(interface))
- err = hw->mac.ops.update_uc_addr(hw, interface->glort,
- hw->mac.addr, vid, set, 0);
- else
- err = -EHOSTDOWN;
-
+ /* Update our base MAC address */
+ err = fm10k_queue_mac_request(interface, interface->glort,
+ hw->mac.addr, vid, set);
if (err)
goto err_out;
@@ -906,7 +1021,6 @@ static u16 fm10k_find_next_vlan(struct fm10k_intfc *interface, u16 vid)
static void fm10k_clear_unused_vlans(struct fm10k_intfc *interface)
{
- struct fm10k_hw *hw = &interface->hw;
u32 vid, prev_vid;
/* loop through and find any gaps in the table */
@@ -918,7 +1032,7 @@ static void fm10k_clear_unused_vlans(struct fm10k_intfc *interface)
/* send request to clear multiple bits at a time */
prev_vid += (vid - prev_vid - 1) << FM10K_VLAN_LENGTH_SHIFT;
- hw->mac.ops.update_vlan(hw, prev_vid, 0, false);
+ fm10k_queue_vlan_request(interface, prev_vid, 0, false);
}
}
@@ -933,15 +1047,11 @@ static int __fm10k_uc_sync(struct net_device *dev,
if (!is_valid_ether_addr(addr))
return -EADDRNOTAVAIL;
- /* update table with current entries if host's mailbox is ready */
- if (!fm10k_host_mbx_ready(interface))
- return -EHOSTDOWN;
-
for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1;
vid < VLAN_N_VID;
vid = fm10k_find_next_vlan(interface, vid)) {
- err = hw->mac.ops.update_uc_addr(hw, glort, addr,
- vid, sync, 0);
+ err = fm10k_queue_mac_request(interface, glort,
+ addr, vid, sync);
if (err)
return err;
}
@@ -998,15 +1108,18 @@ static int __fm10k_mc_sync(struct net_device *dev,
struct fm10k_intfc *interface = netdev_priv(dev);
struct fm10k_hw *hw = &interface->hw;
u16 vid, glort = interface->glort;
+ s32 err;
- /* update table with current entries if host's mailbox is ready */
- if (!fm10k_host_mbx_ready(interface))
- return 0;
+ if (!is_multicast_ether_addr(addr))
+ return -EADDRNOTAVAIL;
for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1;
vid < VLAN_N_VID;
vid = fm10k_find_next_vlan(interface, vid)) {
- hw->mac.ops.update_mc_addr(hw, glort, addr, vid, sync);
+ err = fm10k_queue_mac_request(interface, glort,
+ addr, vid, sync);
+ if (err)
+ return err;
}
return 0;
@@ -1046,7 +1159,8 @@ static void fm10k_set_rx_mode(struct net_device *dev)
if (interface->xcast_mode != xcast_mode) {
/* update VLAN table */
if (xcast_mode == FM10K_XCAST_MODE_PROMISC)
- hw->mac.ops.update_vlan(hw, FM10K_VLAN_ALL, 0, true);
+ fm10k_queue_vlan_request(interface, FM10K_VLAN_ALL,
+ 0, true);
if (interface->xcast_mode == FM10K_XCAST_MODE_PROMISC)
fm10k_clear_unused_vlans(interface);
@@ -1094,22 +1208,20 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface)
interface->glort_count, true);
/* update VLAN table */
- hw->mac.ops.update_vlan(hw, FM10K_VLAN_ALL, 0,
- xcast_mode == FM10K_XCAST_MODE_PROMISC);
+ fm10k_queue_vlan_request(interface, FM10K_VLAN_ALL, 0,
+ xcast_mode == FM10K_XCAST_MODE_PROMISC);
/* Add filter for VLAN 0 */
- hw->mac.ops.update_vlan(hw, 0, 0, true);
+ fm10k_queue_vlan_request(interface, 0, 0, true);
/* update table with current entries */
for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1;
vid < VLAN_N_VID;
vid = fm10k_find_next_vlan(interface, vid)) {
- hw->mac.ops.update_vlan(hw, vid, 0, true);
+ fm10k_queue_vlan_request(interface, vid, 0, true);
- /* Update unicast entries if host's mailbox is ready */
- if (fm10k_host_mbx_ready(interface))
- hw->mac.ops.update_uc_addr(hw, glort, hw->mac.addr,
- vid, true, 0);
+ fm10k_queue_mac_request(interface, glort,
+ hw->mac.addr, vid, true);
}
/* update xcast mode before synchronizing addresses if host's mailbox
@@ -1136,6 +1248,13 @@ void fm10k_reset_rx_state(struct fm10k_intfc *interface)
struct net_device *netdev = interface->netdev;
struct fm10k_hw *hw = &interface->hw;
+ /* Wait for MAC/VLAN work to finish */
+ while (test_bit(__FM10K_MACVLAN_SCHED, interface->state))
+ usleep_range(1000, 2000);
+
+ /* Cancel pending MAC/VLAN requests */
+ fm10k_clear_macvlan_queue(interface, interface->glort, true);
+
fm10k_mbx_lock(interface);
/* clear the logical port state on lower device if host's mailbox is
@@ -1370,8 +1489,8 @@ static void *fm10k_dfwd_add_station(struct net_device *dev,
if (fm10k_host_mbx_ready(interface)) {
hw->mac.ops.update_xcast_mode(hw, glort,
FM10K_XCAST_MODE_MULTI);
- hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr,
- 0, true, 0);
+ fm10k_queue_mac_request(interface, glort, sdev->dev_addr,
+ 0, true);
}
fm10k_mbx_unlock(interface);
@@ -1410,8 +1529,8 @@ static void fm10k_dfwd_del_station(struct net_device *dev, void *priv)
if (fm10k_host_mbx_ready(interface)) {
hw->mac.ops.update_xcast_mode(hw, glort,
FM10K_XCAST_MODE_NONE);
- hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr,
- 0, false, 0);
+ fm10k_queue_mac_request(interface, glort, sdev->dev_addr,
+ 0, false);
}
fm10k_mbx_unlock(interface);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index 63784576ae8b..1e9ae3197b17 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -91,6 +91,76 @@ static int fm10k_hw_ready(struct fm10k_intfc *interface)
return FM10K_REMOVED(hw->hw_addr) ? -ENODEV : 0;
}
+/**
+ * fm10k_macvlan_schedule - Schedule MAC/VLAN queue task
+ * @interface: fm10k private interface structure
+ *
+ * Schedule the MAC/VLAN queue monitor task. If the MAC/VLAN task cannot be
+ * started immediately, request that it be restarted when possible.
+ */
+void fm10k_macvlan_schedule(struct fm10k_intfc *interface)
+{
+ /* Avoid processing the MAC/VLAN queue when the service task is
+ * disabled, or when we're resetting the device.
+ */
+ if (!test_bit(__FM10K_MACVLAN_DISABLE, interface->state) &&
+ !test_and_set_bit(__FM10K_MACVLAN_SCHED, interface->state)) {
+ clear_bit(__FM10K_MACVLAN_REQUEST, interface->state);
+ /* We delay the actual start of execution in order to allow
+ * multiple MAC/VLAN updates to accumulate before handling
+ * them, and to allow some time to let the mailbox drain
+ * between runs.
+ */
+ queue_delayed_work(fm10k_workqueue,
+ &interface->macvlan_task, 10);
+ } else {
+ set_bit(__FM10K_MACVLAN_REQUEST, interface->state);
+ }
+}
+
+/**
+ * fm10k_stop_macvlan_task - Stop the MAC/VLAN queue monitor
+ * @interface: fm10k private interface structure
+ *
+ * Wait until the MAC/VLAN queue task has stopped, and cancel any future
+ * requests.
+ */
+static void fm10k_stop_macvlan_task(struct fm10k_intfc *interface)
+{
+ /* Disable the MAC/VLAN work item */
+ set_bit(__FM10K_MACVLAN_DISABLE, interface->state);
+
+ /* Make sure we waited until any current invocations have stopped */
+ cancel_delayed_work_sync(&interface->macvlan_task);
+
+ /* We set the __FM10K_MACVLAN_SCHED bit when we schedule the task.
+ * However, it may not be unset of the MAC/VLAN task never actually
+ * got a chance to run. Since we've canceled the task here, and it
+ * cannot be rescheuled right now, we need to ensure the scheduled bit
+ * gets unset.
+ */
+ clear_bit(__FM10K_MACVLAN_SCHED, interface->state);
+}
+
+/**
+ * fm10k_resume_macvlan_task - Restart the MAC/VLAN queue monitor
+ * @interface: fm10k private interface structure
+ *
+ * Clear the __FM10K_MACVLAN_DISABLE bit and, if a request occurred, schedule
+ * the MAC/VLAN work monitor.
+ */
+static void fm10k_resume_macvlan_task(struct fm10k_intfc *interface)
+{
+ /* Re-enable the MAC/VLAN work item */
+ clear_bit(__FM10K_MACVLAN_DISABLE, interface->state);
+
+ /* We might have received a MAC/VLAN request while disabled. If so,
+ * kick off the queue now.
+ */
+ if (test_bit(__FM10K_MACVLAN_REQUEST, interface->state))
+ fm10k_macvlan_schedule(interface);
+}
+
void fm10k_service_event_schedule(struct fm10k_intfc *interface)
{
if (!test_bit(__FM10K_SERVICE_DISABLE, interface->state) &&
@@ -118,6 +188,27 @@ static void fm10k_service_event_complete(struct fm10k_intfc *interface)
fm10k_service_event_schedule(interface);
}
+static void fm10k_stop_service_event(struct fm10k_intfc *interface)
+{
+ set_bit(__FM10K_SERVICE_DISABLE, interface->state);
+ cancel_work_sync(&interface->service_task);
+
+ /* It's possible that cancel_work_sync stopped the service task from
+ * running before it could actually start. In this case the
+ * __FM10K_SERVICE_SCHED bit will never be cleared. Since we know that
+ * the service task cannot be running at this point, we need to clear
+ * the scheduled bit, as otherwise the service task may never be
+ * restarted.
+ */
+ clear_bit(__FM10K_SERVICE_SCHED, interface->state);
+}
+
+static void fm10k_start_service_event(struct fm10k_intfc *interface)
+{
+ clear_bit(__FM10K_SERVICE_DISABLE, interface->state);
+ fm10k_service_event_schedule(interface);
+}
+
/**
* fm10k_service_timer - Timer Call-back
* @data: pointer to interface cast into an unsigned long
@@ -132,36 +223,15 @@ static void fm10k_service_timer(unsigned long data)
fm10k_service_event_schedule(interface);
}
-static void fm10k_detach_subtask(struct fm10k_intfc *interface)
-{
- struct net_device *netdev = interface->netdev;
- u32 __iomem *hw_addr;
- u32 value;
-
- /* do nothing if device is still present or hw_addr is set */
- if (netif_device_present(netdev) || interface->hw.hw_addr)
- return;
-
- /* check the real address space to see if we've recovered */
- hw_addr = READ_ONCE(interface->uc_addr);
- value = readl(hw_addr);
- if (~value) {
- interface->hw.hw_addr = interface->uc_addr;
- netif_device_attach(netdev);
- set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
- netdev_warn(netdev, "PCIe link restored, device now attached\n");
- return;
- }
-
- rtnl_lock();
-
- if (netif_running(netdev))
- dev_close(netdev);
-
- rtnl_unlock();
-}
-
-static void fm10k_prepare_for_reset(struct fm10k_intfc *interface)
+/**
+ * fm10k_prepare_for_reset - Prepare the driver and device for a pending reset
+ * @interface: fm10k private data structure
+ *
+ * This function prepares for a device reset by shutting as much down as we
+ * can. It does nothing and returns false if __FM10K_RESETTING was already set
+ * prior to calling this function. It returns true if it actually did work.
+ */
+static bool fm10k_prepare_for_reset(struct fm10k_intfc *interface)
{
struct net_device *netdev = interface->netdev;
@@ -170,8 +240,15 @@ static void fm10k_prepare_for_reset(struct fm10k_intfc *interface)
/* put off any impending NetWatchDogTimeout */
netif_trans_update(netdev);
- while (test_and_set_bit(__FM10K_RESETTING, interface->state))
- usleep_range(1000, 2000);
+ /* Nothing to do if a reset is already in progress */
+ if (test_and_set_bit(__FM10K_RESETTING, interface->state))
+ return false;
+
+ /* As the MAC/VLAN task will be accessing registers it must not be
+ * running while we reset. Although the task will not be scheduled
+ * once we start resetting it may already be running
+ */
+ fm10k_stop_macvlan_task(interface);
rtnl_lock();
@@ -189,6 +266,8 @@ static void fm10k_prepare_for_reset(struct fm10k_intfc *interface)
interface->last_reset = jiffies + (10 * HZ);
rtnl_unlock();
+
+ return true;
}
static int fm10k_handle_reset(struct fm10k_intfc *interface)
@@ -197,6 +276,8 @@ static int fm10k_handle_reset(struct fm10k_intfc *interface)
struct fm10k_hw *hw = &interface->hw;
int err;
+ WARN_ON(!test_bit(__FM10K_RESETTING, interface->state));
+
rtnl_lock();
pci_set_master(interface->pdev);
@@ -253,6 +334,8 @@ static int fm10k_handle_reset(struct fm10k_intfc *interface)
rtnl_unlock();
+ fm10k_resume_macvlan_task(interface);
+
clear_bit(__FM10K_RESETTING, interface->state);
return err;
@@ -270,27 +353,80 @@ reinit_err:
return err;
}
-static void fm10k_reinit(struct fm10k_intfc *interface)
+static void fm10k_detach_subtask(struct fm10k_intfc *interface)
{
+ struct net_device *netdev = interface->netdev;
+ u32 __iomem *hw_addr;
+ u32 value;
int err;
- fm10k_prepare_for_reset(interface);
+ /* do nothing if netdev is still present or hw_addr is set */
+ if (netif_device_present(netdev) || interface->hw.hw_addr)
+ return;
- err = fm10k_handle_reset(interface);
- if (err)
- dev_err(&interface->pdev->dev,
- "fm10k_handle_reset failed: %d\n", err);
+ /* We've lost the PCIe register space, and can no longer access the
+ * device. Shut everything except the detach subtask down and prepare
+ * to reset the device in case we recover. If we actually prepare for
+ * reset, indicate that we're detached.
+ */
+ if (fm10k_prepare_for_reset(interface))
+ set_bit(__FM10K_RESET_DETACHED, interface->state);
+
+ /* check the real address space to see if we've recovered */
+ hw_addr = READ_ONCE(interface->uc_addr);
+ value = readl(hw_addr);
+ if (~value) {
+ /* Make sure the reset was initiated because we detached,
+ * otherwise we might race with a different reset flow.
+ */
+ if (!test_and_clear_bit(__FM10K_RESET_DETACHED,
+ interface->state))
+ return;
+
+ /* Restore the hardware address */
+ interface->hw.hw_addr = interface->uc_addr;
+
+ /* PCIe link has been restored, and the device is active
+ * again. Restore everything and reset the device.
+ */
+ err = fm10k_handle_reset(interface);
+ if (err) {
+ netdev_err(netdev, "Unable to reset device: %d\n", err);
+ interface->hw.hw_addr = NULL;
+ return;
+ }
+
+ /* Re-attach the netdev */
+ netif_device_attach(netdev);
+ netdev_warn(netdev, "PCIe link restored, device now attached\n");
+ return;
+ }
}
static void fm10k_reset_subtask(struct fm10k_intfc *interface)
{
+ int err;
+
if (!test_and_clear_bit(FM10K_FLAG_RESET_REQUESTED,
interface->flags))
return;
+ /* If another thread has already prepared to reset the device, we
+ * should not attempt to handle a reset here, since we'd race with
+ * that thread. This may happen if we suspend the device or if the
+ * PCIe link is lost. In this case, we'll just ignore the RESET
+ * request, as it will (eventually) be taken care of when the thread
+ * which actually started the reset is finished.
+ */
+ if (!fm10k_prepare_for_reset(interface))
+ return;
+
netdev_err(interface->netdev, "Reset interface\n");
- fm10k_reinit(interface);
+ err = fm10k_handle_reset(interface);
+ if (err)
+ dev_err(&interface->pdev->dev,
+ "fm10k_handle_reset failed: %d\n", err);
}
/**
@@ -360,6 +496,10 @@ static void fm10k_watchdog_update_host_state(struct fm10k_intfc *interface)
**/
static void fm10k_mbx_subtask(struct fm10k_intfc *interface)
{
+ /* If we're resetting, bail out */
+ if (test_bit(__FM10K_RESETTING, interface->state))
+ return;
+
/* process upstream mailbox and update device state */
fm10k_watchdog_update_host_state(interface);
@@ -609,9 +749,11 @@ static void fm10k_service_task(struct work_struct *work)
interface = container_of(work, struct fm10k_intfc, service_task);
+ /* Check whether we're detached first */
+ fm10k_detach_subtask(interface);
+
/* tasks run even when interface is down */
fm10k_mbx_subtask(interface);
- fm10k_detach_subtask(interface);
fm10k_reset_subtask(interface);
/* tasks only run when interface is up */
@@ -623,6 +765,112 @@ static void fm10k_service_task(struct work_struct *work)
}
/**
+ * fm10k_macvlan_task - send queued MAC/VLAN requests to switch manager
+ * @work: pointer to work_struct containing our data
+ *
+ * This work item handles sending MAC/VLAN updates to the switch manager. When
+ * the interface is up, it will attempt to queue mailbox messages to the
+ * switch manager requesting updates for MAC/VLAN pairs. If the Tx fifo of the
+ * mailbox is full, it will reschedule itself to try again in a short while.
+ * This ensures that the driver does not overload the switch mailbox with too
+ * many simultaneous requests, causing an unnecessary reset.
+ **/
+static void fm10k_macvlan_task(struct work_struct *work)
+{
+ struct fm10k_macvlan_request *item;
+ struct fm10k_intfc *interface;
+ struct delayed_work *dwork;
+ struct list_head *requests;
+ struct fm10k_hw *hw;
+ unsigned long flags;
+
+ dwork = to_delayed_work(work);
+ interface = container_of(dwork, struct fm10k_intfc, macvlan_task);
+ hw = &interface->hw;
+ requests = &interface->macvlan_requests;
+
+ do {
+ /* Pop the first item off the list */
+ spin_lock_irqsave(&interface->macvlan_lock, flags);
+ item = list_first_entry_or_null(requests,
+ struct fm10k_macvlan_request,
+ list);
+ if (item)
+ list_del_init(&item->list);
+
+ spin_unlock_irqrestore(&interface->macvlan_lock, flags);
+
+ /* We have no more items to process */
+ if (!item)
+ goto done;
+
+ fm10k_mbx_lock(interface);
+
+ /* Check that we have plenty of space to send the message. We
+ * want to ensure that the mailbox stays low enough to avoid a
+ * change in the host state, otherwise we may see spurious
+ * link up / link down notifications.
+ */
+ if (!hw->mbx.ops.tx_ready(&hw->mbx, FM10K_VFMBX_MSG_MTU + 5)) {
+ hw->mbx.ops.process(hw, &hw->mbx);
+ set_bit(__FM10K_MACVLAN_REQUEST, interface->state);
+ fm10k_mbx_unlock(interface);
+
+ /* Put the request back on the list */
+ spin_lock_irqsave(&interface->macvlan_lock, flags);
+ list_add(&item->list, requests);
+ spin_unlock_irqrestore(&interface->macvlan_lock, flags);
+ break;
+ }
+
+ switch (item->type) {
+ case FM10K_MC_MAC_REQUEST:
+ hw->mac.ops.update_mc_addr(hw,
+ item->mac.glort,
+ item->mac.addr,
+ item->mac.vid,
+ item->set);
+ break;
+ case FM10K_UC_MAC_REQUEST:
+ hw->mac.ops.update_uc_addr(hw,
+ item->mac.glort,
+ item->mac.addr,
+ item->mac.vid,
+ item->set,
+ 0);
+ break;
+ case FM10K_VLAN_REQUEST:
+ hw->mac.ops.update_vlan(hw,
+ item->vlan.vid,
+ item->vlan.vsi,
+ item->set);
+ break;
+ default:
+ break;
+ }
+
+ fm10k_mbx_unlock(interface);
+
+ /* Free the item now that we've sent the update */
+ kfree(item);
+ } while (true);
+
+done:
+ WARN_ON(!test_bit(__FM10K_MACVLAN_SCHED, interface->state));
+
+ /* flush memory to make sure state is correct */
+ smp_mb__before_atomic();
+ clear_bit(__FM10K_MACVLAN_SCHED, interface->state);
+
+ /* If a MAC/VLAN request was scheduled since we started, we should
+ * re-schedule. However, there is no reason to re-schedule if there is
+ * no work to do.
+ */
+ if (test_bit(__FM10K_MACVLAN_REQUEST, interface->state))
+ fm10k_macvlan_schedule(interface);
+}
+
+/**
* fm10k_configure_tx_ring - Configure Tx ring after Reset
* @interface: board private structure
* @ring: structure containing ring specific data
@@ -1544,7 +1792,7 @@ int fm10k_qv_request_irq(struct fm10k_intfc *interface)
struct net_device *dev = interface->netdev;
struct fm10k_hw *hw = &interface->hw;
struct msix_entry *entry;
- int ri = 0, ti = 0;
+ unsigned int ri = 0, ti = 0;
int vector, err;
entry = &interface->msix_entries[NON_Q_VECTORS(hw)];
@@ -1554,15 +1802,15 @@ int fm10k_qv_request_irq(struct fm10k_intfc *interface)
/* name the vector */
if (q_vector->tx.count && q_vector->rx.count) {
- snprintf(q_vector->name, sizeof(q_vector->name) - 1,
- "%s-TxRx-%d", dev->name, ri++);
+ snprintf(q_vector->name, sizeof(q_vector->name),
+ "%s-TxRx-%u", dev->name, ri++);
ti++;
} else if (q_vector->rx.count) {
- snprintf(q_vector->name, sizeof(q_vector->name) - 1,
- "%s-rx-%d", dev->name, ri++);
+ snprintf(q_vector->name, sizeof(q_vector->name),
+ "%s-rx-%u", dev->name, ri++);
} else if (q_vector->tx.count) {
- snprintf(q_vector->name, sizeof(q_vector->name) - 1,
- "%s-tx-%d", dev->name, ti++);
+ snprintf(q_vector->name, sizeof(q_vector->name),
+ "%s-tx-%u", dev->name, ti++);
} else {
/* skip this unused q_vector */
continue;
@@ -1800,9 +2048,6 @@ static int fm10k_sw_init(struct fm10k_intfc *interface,
netdev->vlan_features |= NETIF_F_HIGHDMA;
}
- /* delay any future reset requests */
- interface->last_reset = jiffies + (10 * HZ);
-
/* reset and initialize the hardware so it is in a known state */
err = hw->mac.ops.reset_hw(hw);
if (err) {
@@ -1857,9 +2102,16 @@ static int fm10k_sw_init(struct fm10k_intfc *interface,
INIT_LIST_HEAD(&interface->vxlan_port);
INIT_LIST_HEAD(&interface->geneve_port);
+ /* Initialize the MAC/VLAN queue */
+ INIT_LIST_HEAD(&interface->macvlan_requests);
+
netdev_rss_key_fill(rss_key, sizeof(rss_key));
memcpy(interface->rssrk, rss_key, sizeof(rss_key));
+ /* Initialize the mailbox lock */
+ spin_lock_init(&interface->mbx_lock);
+ spin_lock_init(&interface->macvlan_lock);
+
/* Start off interface as being down */
set_bit(__FM10K_DOWN, interface->state);
set_bit(__FM10K_UPDATING_STATS, interface->state);
@@ -2067,6 +2319,9 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
(unsigned long)interface);
INIT_WORK(&interface->service_task, fm10k_service_task);
+ /* Setup the MAC/VLAN queue */
+ INIT_DELAYED_WORK(&interface->macvlan_task, fm10k_macvlan_task);
+
/* kick off service timer now, even when interface is down */
mod_timer(&interface->service_timer, (HZ * 2) + jiffies);
@@ -2079,8 +2334,9 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
/* enable SR-IOV after registering netdev to enforce PF/VF ordering */
fm10k_iov_configure(pdev, 0);
- /* clear the service task disable bit to allow service task to start */
+ /* clear the service task disable bit and kick off service task */
clear_bit(__FM10K_SERVICE_DISABLE, interface->state);
+ fm10k_service_event_schedule(interface);
return 0;
@@ -2118,8 +2374,11 @@ static void fm10k_remove(struct pci_dev *pdev)
del_timer_sync(&interface->service_timer);
- set_bit(__FM10K_SERVICE_DISABLE, interface->state);
- cancel_work_sync(&interface->service_task);
+ fm10k_stop_service_event(interface);
+ fm10k_stop_macvlan_task(interface);
+
+ /* Remove all pending MAC/VLAN requests */
+ fm10k_clear_macvlan_queue(interface, interface->glort, true);
/* free netdev, this may bounce the interrupts due to setup_tc */
if (netdev->reg_state == NETREG_REGISTERED)
@@ -2156,11 +2415,14 @@ static void fm10k_prepare_suspend(struct fm10k_intfc *interface)
* a surprise remove if the PCIe device is disabled while we're
* stopped. We stop the watchdog task until after we resume software
* activity.
+ *
+ * Note that the MAC/VLAN task will be stopped as part of preparing
+ * for reset so we don't need to handle it here.
*/
- set_bit(__FM10K_SERVICE_DISABLE, interface->state);
- cancel_work_sync(&interface->service_task);
+ fm10k_stop_service_event(interface);
- fm10k_prepare_for_reset(interface);
+ if (fm10k_prepare_for_reset(interface))
+ set_bit(__FM10K_RESET_SUSPENDED, interface->state);
}
static int fm10k_handle_resume(struct fm10k_intfc *interface)
@@ -2168,6 +2430,13 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface)
struct fm10k_hw *hw = &interface->hw;
int err;
+ /* Even if we didn't properly prepare for reset in
+ * fm10k_prepare_suspend, we'll attempt to resume anyways.
+ */
+ if (!test_and_clear_bit(__FM10K_RESET_SUSPENDED, interface->state))
+ dev_warn(&interface->pdev->dev,
+ "Device was shut down as part of suspend... Attempting to recover\n");
+
/* reset statistics starting values */
hw->mac.ops.rebind_hw_stats(hw, &interface->stats);
@@ -2185,45 +2454,30 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface)
interface->link_down_event = jiffies + (HZ);
set_bit(__FM10K_LINK_DOWN, interface->state);
- /* clear the service task disable bit to allow service task to start */
- clear_bit(__FM10K_SERVICE_DISABLE, interface->state);
- fm10k_service_event_schedule(interface);
+ /* restart the service task */
+ fm10k_start_service_event(interface);
+
+ /* Restart the MAC/VLAN request queue in-case of outstanding events */
+ fm10k_macvlan_schedule(interface);
return err;
}
#ifdef CONFIG_PM
/**
- * fm10k_resume - Restore device to pre-sleep state
- * @pdev: PCI device information struct
+ * fm10k_resume - Generic PM resume hook
+ * @dev: generic device structure
*
- * fm10k_resume is called after the system has powered back up from a sleep
- * state and is ready to resume operation. This function is meant to restore
- * the device back to its pre-sleep state.
+ * Generic PM hook used when waking the device from a low power state after
+ * suspend or hibernation. This function does not need to handle lower PCIe
+ * device state as the stack takes care of that for us.
**/
-static int fm10k_resume(struct pci_dev *pdev)
+static int fm10k_resume(struct device *dev)
{
- struct fm10k_intfc *interface = pci_get_drvdata(pdev);
+ struct fm10k_intfc *interface = pci_get_drvdata(to_pci_dev(dev));
struct net_device *netdev = interface->netdev;
struct fm10k_hw *hw = &interface->hw;
- u32 err;
-
- pci_set_power_state(pdev, PCI_D0);
- pci_restore_state(pdev);
-
- /* pci_restore_state clears dev->state_saved so call
- * pci_save_state to restore it.
- */
- pci_save_state(pdev);
-
- err = pci_enable_device_mem(pdev);
- if (err) {
- dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n");
- return err;
- }
- pci_set_master(pdev);
-
- pci_wake_from_d3(pdev, false);
+ int err;
/* refresh hw_addr in case it was dropped */
hw->hw_addr = interface->uc_addr;
@@ -2238,36 +2492,27 @@ static int fm10k_resume(struct pci_dev *pdev)
}
/**
- * fm10k_suspend - Prepare the device for a system sleep state
- * @pdev: PCI device information struct
+ * fm10k_suspend - Generic PM suspend hook
+ * @dev: generic device structure
*
- * fm10k_suspend is meant to shutdown the device prior to the system entering
- * a sleep state. The fm10k hardware does not support wake on lan so the
- * driver simply needs to shut down the device so it is in a low power state.
+ * Generic PM hook used when setting the device into a low power state for
+ * system suspend or hibernation. This function does not need to handle lower
+ * PCIe device state as the stack takes care of that for us.
**/
-static int fm10k_suspend(struct pci_dev *pdev,
- pm_message_t __always_unused state)
+static int fm10k_suspend(struct device *dev)
{
- struct fm10k_intfc *interface = pci_get_drvdata(pdev);
+ struct fm10k_intfc *interface = pci_get_drvdata(to_pci_dev(dev));
struct net_device *netdev = interface->netdev;
- int err = 0;
netif_device_detach(netdev);
fm10k_prepare_suspend(interface);
- err = pci_save_state(pdev);
- if (err)
- return err;
-
- pci_disable_device(pdev);
- pci_wake_from_d3(pdev, false);
- pci_set_power_state(pdev, PCI_D3hot);
-
return 0;
}
#endif /* CONFIG_PM */
+
/**
* fm10k_io_error_detected - called when PCI error is detected
* @pdev: Pointer to PCI device
@@ -2343,11 +2588,18 @@ static void fm10k_io_resume(struct pci_dev *pdev)
if (err)
dev_warn(&pdev->dev,
- "fm10k_io_resume failed: %d\n", err);
+ "%s failed: %d\n", __func__, err);
else
netif_device_attach(netdev);
}
+/**
+ * fm10k_io_reset_prepare - called when PCI function is about to be reset
+ * @pdev: Pointer to PCI device
+ *
+ * This callback is called when the PCI function is about to be reset,
+ * allowing the device driver to prepare for it.
+ */
static void fm10k_io_reset_prepare(struct pci_dev *pdev)
{
/* warn incase we have any active VF devices */
@@ -2357,6 +2609,13 @@ static void fm10k_io_reset_prepare(struct pci_dev *pdev)
fm10k_prepare_suspend(pci_get_drvdata(pdev));
}
+/**
+ * fm10k_io_reset_done - called when PCI function has finished resetting
+ * @pdev: Pointer to PCI device
+ *
+ * This callback is called just after the PCI function is reset, such as via
+ * /sys/class/net/<enpX>/device/reset or similar.
+ */
static void fm10k_io_reset_done(struct pci_dev *pdev)
{
struct fm10k_intfc *interface = pci_get_drvdata(pdev);
@@ -2364,7 +2623,7 @@ static void fm10k_io_reset_done(struct pci_dev *pdev)
if (err) {
dev_warn(&pdev->dev,
- "fm10k_io_reset_notify failed: %d\n", err);
+ "%s failed: %d\n", __func__, err);
netif_device_detach(interface->netdev);
}
}
@@ -2377,15 +2636,18 @@ static const struct pci_error_handlers fm10k_err_handler = {
.reset_done = fm10k_io_reset_done,
};
+static SIMPLE_DEV_PM_OPS(fm10k_pm_ops, fm10k_suspend, fm10k_resume);
+
static struct pci_driver fm10k_driver = {
.name = fm10k_driver_name,
.id_table = fm10k_pci_tbl,
.probe = fm10k_probe,
.remove = fm10k_remove,
#ifdef CONFIG_PM
- .suspend = fm10k_suspend,
- .resume = fm10k_resume,
-#endif
+ .driver = {
+ .pm = &fm10k_pm_ops,
+ },
+#endif /* CONFIG_PM */
.sriov_configure = fm10k_iov_configure,
.err_handler = &fm10k_err_handler
};
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
index 40ee0242a80a..425d814aed4d 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
@@ -1,5 +1,5 @@
/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -1186,7 +1186,7 @@ s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 **results,
* Will report an error if the VLAN ID is out of range. For VID = 0, it will
* return either the pf_vid or sw_vid depending on which one is set.
*/
-static s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid)
+s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid)
{
if (!vid)
return vf_info->pf_vid ? vf_info->pf_vid : vf_info->sw_vid;
@@ -1334,19 +1334,19 @@ static u8 fm10k_iov_supported_xcast_mode_pf(struct fm10k_vf_info *vf_info,
case FM10K_XCAST_MODE_PROMISC:
if (vf_flags & FM10K_VF_FLAG_PROMISC_CAPABLE)
return FM10K_XCAST_MODE_PROMISC;
- /* fallthough */
+ /* fall through */
case FM10K_XCAST_MODE_ALLMULTI:
if (vf_flags & FM10K_VF_FLAG_ALLMULTI_CAPABLE)
return FM10K_XCAST_MODE_ALLMULTI;
- /* fallthough */
+ /* fall through */
case FM10K_XCAST_MODE_MULTI:
if (vf_flags & FM10K_VF_FLAG_MULTI_CAPABLE)
return FM10K_XCAST_MODE_MULTI;
- /* fallthough */
+ /* fall through */
case FM10K_XCAST_MODE_NONE:
if (vf_flags & FM10K_VF_FLAG_NONE_CAPABLE)
return FM10K_XCAST_MODE_NONE;
- /* fallthough */
+ /* fall through */
default:
break;
}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
index 3336d3c10760..e04d41f1a532 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
@@ -1,5 +1,5 @@
/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -114,6 +114,7 @@ extern const struct fm10k_tlv_attr fm10k_err_msg_attr[];
#define FM10K_PF_MSG_ERR_HANDLER(msg, func) \
FM10K_MSG_HANDLER(FM10K_PF_MSG_ID_##msg, fm10k_err_msg_attr, func)
+s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid);
s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *);
s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *, u32 **,
struct fm10k_mbx_info *);
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index d0c1bf5441d8..439c63cb2a0c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -77,6 +77,7 @@
#define i40e_default_queues_per_vmdq(pf) \
(((pf)->hw_features & I40E_HW_RSS_AQ_CAPABLE) ? 4 : 1)
#define I40E_DEFAULT_QUEUES_PER_VF 4
+#define I40E_MAX_VF_QUEUES 16
#define I40E_DEFAULT_QUEUES_PER_TC 1 /* should be a power of 2 */
#define i40e_pf_get_max_q_per_tc(pf) \
(((pf)->hw_features & I40E_HW_128_QP_RSS_CAPABLE) ? 128 : 64)
@@ -136,6 +137,7 @@ enum i40e_state_t {
__I40E_MDD_EVENT_PENDING,
__I40E_VFLR_EVENT_PENDING,
__I40E_RESET_RECOVERY_PENDING,
+ __I40E_MISC_IRQ_REQUESTED,
__I40E_RESET_INTR_RECEIVED,
__I40E_REINIT_REQUESTED,
__I40E_PF_RESET_REQUESTED,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index ba04988e0598..9dcb2a961197 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -607,6 +607,18 @@ i40e_status i40e_init_adminq(struct i40e_hw *hw)
&oem_lo);
hw->nvm.oem_ver = ((u32)oem_hi << 16) | oem_lo;
+ if (hw->mac.type == I40E_MAC_XL710 &&
+ hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
+ hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) {
+ hw->flags |= I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE;
+ }
+
+ /* The ability to RX (not drop) 802.1ad frames was added in API 1.7 */
+ if (hw->aq.api_maj_ver > 1 ||
+ (hw->aq.api_maj_ver == 1 &&
+ hw->aq.api_min_ver >= 7))
+ hw->flags |= I40E_HW_FLAG_802_1AD_CAPABLE;
+
if (hw->aq.api_maj_ver > I40E_FW_API_VERSION_MAJOR) {
ret_code = I40E_ERR_FIRMWARE_API_VERSION;
goto init_adminq_free_arq;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 5d5f422cbae5..4c85ea9cd89a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -34,7 +34,15 @@
*/
#define I40E_FW_API_VERSION_MAJOR 0x0001
-#define I40E_FW_API_VERSION_MINOR 0x0005
+#define I40E_FW_API_VERSION_MINOR_X722 0x0005
+#define I40E_FW_API_VERSION_MINOR_X710 0x0007
+
+#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \
+ I40E_FW_API_VERSION_MINOR_X710 : \
+ I40E_FW_API_VERSION_MINOR_X722)
+
+/* API version 1.7 implements additional link and PHY-specific APIs */
+#define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007
struct i40e_aq_desc {
__le16 flags;
@@ -236,6 +244,8 @@ enum i40e_admin_queue_opc {
i40e_aqc_opc_set_phy_debug = 0x0622,
i40e_aqc_opc_upload_ext_phy_fm = 0x0625,
i40e_aqc_opc_run_phy_activity = 0x0626,
+ i40e_aqc_opc_set_phy_register = 0x0628,
+ i40e_aqc_opc_get_phy_register = 0x0629,
/* NVM commands */
i40e_aqc_opc_nvm_read = 0x0701,
@@ -765,7 +775,22 @@ struct i40e_aqc_set_switch_config {
#define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001
#define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002
__le16 valid_flags;
- u8 reserved[12];
+ /* The ethertype in switch_tag is dropped on ingress and used
+ * internally by the switch. Set this to zero for the default
+ * of 0x88a8 (802.1ad). Should be zero for firmware API
+ * versions lower than 1.7.
+ */
+ __le16 switch_tag;
+ /* The ethertypes in first_tag and second_tag are used to
+ * match the outer and inner VLAN tags (respectively) when HW
+ * double VLAN tagging is enabled via the set port parameters
+ * AQ command. Otherwise these are both ignored. Set them to
+ * zero for their defaults of 0x8100 (802.1Q). Should be zero
+ * for firmware API versions lower than 1.7.
+ */
+ __le16 first_tag;
+ __le16 second_tag;
+ u8 reserved[6];
};
I40E_CHECK_CMD_LENGTH(i40e_aqc_set_switch_config);
@@ -1726,6 +1751,8 @@ enum i40e_aq_phy_type {
I40E_PHY_TYPE_10GBASE_CR1_CU = 0xB,
I40E_PHY_TYPE_10GBASE_AOC = 0xC,
I40E_PHY_TYPE_40GBASE_AOC = 0xD,
+ I40E_PHY_TYPE_UNRECOGNIZED = 0xE,
+ I40E_PHY_TYPE_UNSUPPORTED = 0xF,
I40E_PHY_TYPE_100BASE_TX = 0x11,
I40E_PHY_TYPE_1000BASE_T = 0x12,
I40E_PHY_TYPE_10GBASE_T = 0x13,
@@ -1744,6 +1771,8 @@ enum i40e_aq_phy_type {
I40E_PHY_TYPE_25GBASE_CR = 0x20,
I40E_PHY_TYPE_25GBASE_SR = 0x21,
I40E_PHY_TYPE_25GBASE_LR = 0x22,
+ I40E_PHY_TYPE_EMPTY = 0xFE,
+ I40E_PHY_TYPE_DEFAULT = 0xFF,
I40E_PHY_TYPE_MAX
};
@@ -1934,19 +1963,31 @@ struct i40e_aqc_get_link_status {
#define I40E_AQ_25G_SERDES_UCODE_ERR 0X04
#define I40E_AQ_25G_NIMB_UCODE_ERR 0X05
u8 loopback; /* use defines from i40e_aqc_set_lb_mode */
+/* Since firmware API 1.7 loopback field keeps power class info as well */
+#define I40E_AQ_LOOPBACK_MASK 0x07
+#define I40E_AQ_PWR_CLASS_SHIFT_LB 6
+#define I40E_AQ_PWR_CLASS_MASK_LB (0x03 << I40E_AQ_PWR_CLASS_SHIFT_LB)
__le16 max_frame_size;
u8 config;
#define I40E_AQ_CONFIG_FEC_KR_ENA 0x01
#define I40E_AQ_CONFIG_FEC_RS_ENA 0x02
#define I40E_AQ_CONFIG_CRC_ENA 0x04
#define I40E_AQ_CONFIG_PACING_MASK 0x78
- u8 power_desc;
+ union {
+ struct {
+ u8 power_desc;
#define I40E_AQ_LINK_POWER_CLASS_1 0x00
#define I40E_AQ_LINK_POWER_CLASS_2 0x01
#define I40E_AQ_LINK_POWER_CLASS_3 0x02
#define I40E_AQ_LINK_POWER_CLASS_4 0x03
#define I40E_AQ_PWR_CLASS_MASK 0x03
- u8 reserved[4];
+ u8 reserved[4];
+ };
+ struct {
+ u8 link_type[4];
+ u8 link_type_ext;
+ };
+ };
};
I40E_CHECK_CMD_LENGTH(i40e_aqc_get_link_status);
@@ -2029,6 +2070,22 @@ struct i40e_aqc_run_phy_activity {
I40E_CHECK_CMD_LENGTH(i40e_aqc_run_phy_activity);
+/* Set PHY Register command (0x0628) */
+/* Get PHY Register command (0x0629) */
+struct i40e_aqc_phy_register_access {
+ u8 phy_interface;
+#define I40E_AQ_PHY_REG_ACCESS_INTERNAL 0
+#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL 1
+#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE 2
+ u8 dev_address;
+ u8 reserved1[2];
+ __le32 reg_address;
+ __le32 reg_value;
+ u8 reserved2[4];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access);
+
/* NVM Read command (indirect 0x0701)
* NVM Erase commands (direct 0x0702)
* NVM Update commands (indirect 0x0703)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 111426ba5fbc..60542beda7ad 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1593,8 +1593,10 @@ i40e_status i40e_aq_get_phy_capabilities(struct i40e_hw *hw,
status = I40E_ERR_UNKNOWN_PHY;
if (report_init) {
- hw->phy.phy_types = le32_to_cpu(abilities->phy_type);
- hw->phy.phy_types |= ((u64)abilities->phy_type_ext << 32);
+ if (hw->mac.type == I40E_MAC_XL710 &&
+ hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
+ hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710)
+ status = i40e_aq_get_link_info(hw, true, NULL, NULL);
}
return status;
@@ -1819,7 +1821,7 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw,
hw_link_info->fec_info = resp->config & (I40E_AQ_CONFIG_FEC_KR_ENA |
I40E_AQ_CONFIG_FEC_RS_ENA);
hw_link_info->ext_info = resp->ext_info;
- hw_link_info->loopback = resp->loopback;
+ hw_link_info->loopback = resp->loopback & I40E_AQ_LOOPBACK_MASK;
hw_link_info->max_frame_size = le16_to_cpu(resp->max_frame_size);
hw_link_info->pacing = resp->config & I40E_AQ_CONFIG_PACING_MASK;
@@ -1850,6 +1852,15 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw,
hw->aq.fw_min_ver < 40)) && hw_link_info->phy_type == 0xE)
hw_link_info->phy_type = I40E_PHY_TYPE_10GBASE_SFPP_CU;
+ if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
+ hw->aq.api_min_ver >= 7) {
+ __le32 tmp;
+
+ memcpy(&tmp, resp->link_type, sizeof(tmp));
+ hw->phy.phy_types = le32_to_cpu(tmp);
+ hw->phy.phy_types |= ((u64)resp->link_type_ext << 32);
+ }
+
/* save link status information */
if (link)
*link = *hw_link_info;
@@ -2391,7 +2402,11 @@ enum i40e_status_code i40e_aq_set_switch_config(struct i40e_hw *hw,
i40e_aqc_opc_set_switch_config);
scfg->flags = cpu_to_le16(flags);
scfg->valid_flags = cpu_to_le16(valid_flags);
-
+ if (hw->flags & I40E_HW_FLAG_802_1AD_CAPABLE) {
+ scfg->switch_tag = cpu_to_le16(hw->switch_tag);
+ scfg->first_tag = cpu_to_le16(hw->first_tag);
+ scfg->second_tag = cpu_to_le16(hw->second_tag);
+ }
status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
return status;
@@ -4826,6 +4841,74 @@ phy_blinking_end:
}
/**
+ * i40e_led_get_reg - read LED register
+ * @hw: pointer to the HW structure
+ * @led_addr: LED register address
+ * @reg_val: read register value
+ **/
+static enum i40e_status_code i40e_led_get_reg(struct i40e_hw *hw, u16 led_addr,
+ u32 *reg_val)
+{
+ enum i40e_status_code status;
+ u8 phy_addr = 0;
+ u8 port_num;
+ u32 i;
+
+ *reg_val = 0;
+ if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) {
+ status =
+ i40e_aq_get_phy_register(hw,
+ I40E_AQ_PHY_REG_ACCESS_EXTERNAL,
+ I40E_PHY_COM_REG_PAGE,
+ I40E_PHY_LED_PROV_REG_1,
+ reg_val, NULL);
+ } else {
+ i = rd32(hw, I40E_PFGEN_PORTNUM);
+ port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK);
+ phy_addr = i40e_get_phy_address(hw, port_num);
+ status = i40e_read_phy_register_clause45(hw,
+ I40E_PHY_COM_REG_PAGE,
+ led_addr, phy_addr,
+ (u16 *)reg_val);
+ }
+ return status;
+}
+
+/**
+ * i40e_led_set_reg - write LED register
+ * @hw: pointer to the HW structure
+ * @led_addr: LED register address
+ * @reg_val: register value to write
+ **/
+static enum i40e_status_code i40e_led_set_reg(struct i40e_hw *hw, u16 led_addr,
+ u32 reg_val)
+{
+ enum i40e_status_code status;
+ u8 phy_addr = 0;
+ u8 port_num;
+ u32 i;
+
+ if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) {
+ status =
+ i40e_aq_set_phy_register(hw,
+ I40E_AQ_PHY_REG_ACCESS_EXTERNAL,
+ I40E_PHY_COM_REG_PAGE,
+ I40E_PHY_LED_PROV_REG_1,
+ reg_val, NULL);
+ } else {
+ i = rd32(hw, I40E_PFGEN_PORTNUM);
+ port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK);
+ phy_addr = i40e_get_phy_address(hw, port_num);
+ status = i40e_write_phy_register_clause45(hw,
+ I40E_PHY_COM_REG_PAGE,
+ led_addr, phy_addr,
+ (u16)reg_val);
+ }
+
+ return status;
+}
+
+/**
* i40e_led_get_phy - return current on/off mode
* @hw: pointer to the hw struct
* @led_addr: address of led register to use
@@ -4842,7 +4925,19 @@ i40e_status i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr,
u16 temp_addr;
u8 port_num;
u32 i;
-
+ u32 reg_val_aq;
+
+ if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) {
+ status =
+ i40e_aq_get_phy_register(hw,
+ I40E_AQ_PHY_REG_ACCESS_EXTERNAL,
+ I40E_PHY_COM_REG_PAGE,
+ I40E_PHY_LED_PROV_REG_1,
+ &reg_val_aq, NULL);
+ if (status == I40E_SUCCESS)
+ *val = (u16)reg_val_aq;
+ return status;
+ }
temp_addr = I40E_PHY_LED_PROV_REG_1;
i = rd32(hw, I40E_PFGEN_PORTNUM);
port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK);
@@ -4877,51 +4972,38 @@ i40e_status i40e_led_set_phy(struct i40e_hw *hw, bool on,
u16 led_addr, u32 mode)
{
i40e_status status = 0;
- u16 led_ctl = 0;
- u16 led_reg = 0;
- u8 phy_addr = 0;
- u8 port_num;
- u32 i;
+ u32 led_ctl = 0;
+ u32 led_reg = 0;
- i = rd32(hw, I40E_PFGEN_PORTNUM);
- port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK);
- phy_addr = i40e_get_phy_address(hw, port_num);
- status = i40e_read_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE,
- led_addr, phy_addr, &led_reg);
+ status = i40e_led_get_reg(hw, led_addr, &led_reg);
if (status)
return status;
led_ctl = led_reg;
if (led_reg & I40E_PHY_LED_LINK_MODE_MASK) {
led_reg = 0;
- status = i40e_write_phy_register_clause45(hw,
- I40E_PHY_COM_REG_PAGE,
- led_addr, phy_addr,
- led_reg);
+ status = i40e_led_set_reg(hw, led_addr, led_reg);
if (status)
return status;
}
- status = i40e_read_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE,
- led_addr, phy_addr, &led_reg);
+ status = i40e_led_get_reg(hw, led_addr, &led_reg);
if (status)
goto restore_config;
if (on)
led_reg = I40E_PHY_LED_MANUAL_ON;
else
led_reg = 0;
- status = i40e_write_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE,
- led_addr, phy_addr, led_reg);
+
+ status = i40e_led_set_reg(hw, led_addr, led_reg);
if (status)
goto restore_config;
if (mode & I40E_PHY_LED_MODE_ORIG) {
led_ctl = (mode & I40E_PHY_LED_MODE_MASK);
- status = i40e_write_phy_register_clause45(hw,
- I40E_PHY_COM_REG_PAGE,
- led_addr, phy_addr, led_ctl);
+ status = i40e_led_set_reg(hw, led_addr, led_ctl);
}
return status;
+
restore_config:
- status = i40e_write_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE,
- led_addr, phy_addr, led_ctl);
+ status = i40e_led_set_reg(hw, led_addr, led_ctl);
return status;
}
@@ -5052,6 +5134,75 @@ do_retry:
}
/**
+ * i40e_aq_set_phy_register
+ * @hw: pointer to the hw struct
+ * @phy_select: select which phy should be accessed
+ * @dev_addr: PHY device address
+ * @reg_addr: PHY register address
+ * @reg_val: new register value
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Write the external PHY register.
+ **/
+i40e_status i40e_aq_set_phy_register(struct i40e_hw *hw,
+ u8 phy_select, u8 dev_addr,
+ u32 reg_addr, u32 reg_val,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_phy_register_access *cmd =
+ (struct i40e_aqc_phy_register_access *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_set_phy_register);
+
+ cmd->phy_interface = phy_select;
+ cmd->dev_address = dev_addr;
+ cmd->reg_address = cpu_to_le32(reg_addr);
+ cmd->reg_value = cpu_to_le32(reg_val);
+
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ return status;
+}
+
+/**
+ * i40e_aq_get_phy_register
+ * @hw: pointer to the hw struct
+ * @phy_select: select which phy should be accessed
+ * @dev_addr: PHY device address
+ * @reg_addr: PHY register address
+ * @reg_val: read register value
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Read the external PHY register.
+ **/
+i40e_status i40e_aq_get_phy_register(struct i40e_hw *hw,
+ u8 phy_select, u8 dev_addr,
+ u32 reg_addr, u32 *reg_val,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_phy_register_access *cmd =
+ (struct i40e_aqc_phy_register_access *)&desc.params.raw;
+ i40e_status status;
+
+ i40e_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_get_phy_register);
+
+ cmd->phy_interface = phy_select;
+ cmd->dev_address = dev_addr;
+ cmd->reg_address = cpu_to_le32(reg_addr);
+
+ status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+ if (!status)
+ *reg_val = le32_to_cpu(cmd->reg_value);
+
+ return status;
+}
+
+/**
* i40e_aq_write_ppp - Write pipeline personalization profile (ppp)
* @hw: pointer to the hw struct
* @buff: command buffer (size in bytes = buff_size)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 05e89864f781..1136d02e2e95 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -4196,6 +4196,158 @@ flags_complete:
return 0;
}
+/**
+ * i40e_get_module_info - get (Q)SFP+ module type info
+ * @netdev: network interface device structure
+ * @modinfo: module EEPROM size and layout information structure
+ **/
+static int i40e_get_module_info(struct net_device *netdev,
+ struct ethtool_modinfo *modinfo)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ u32 sff8472_comp = 0;
+ u32 sff8472_swap = 0;
+ u32 sff8636_rev = 0;
+ i40e_status status;
+ u32 type = 0;
+
+ /* Check if firmware supports reading module EEPROM. */
+ if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE)) {
+ netdev_err(vsi->netdev, "Module EEPROM memory read not supported. Please update the NVM image.\n");
+ return -EINVAL;
+ }
+
+ status = i40e_update_link_info(hw);
+ if (status)
+ return -EIO;
+
+ if (hw->phy.link_info.phy_type == I40E_PHY_TYPE_EMPTY) {
+ netdev_err(vsi->netdev, "Cannot read module EEPROM memory. No module connected.\n");
+ return -EINVAL;
+ }
+
+ type = hw->phy.link_info.module_type[0];
+
+ switch (type) {
+ case I40E_MODULE_TYPE_SFP:
+ status = i40e_aq_get_phy_register(hw,
+ I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE,
+ I40E_I2C_EEPROM_DEV_ADDR,
+ I40E_MODULE_SFF_8472_COMP,
+ &sff8472_comp, NULL);
+ if (status)
+ return -EIO;
+
+ status = i40e_aq_get_phy_register(hw,
+ I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE,
+ I40E_I2C_EEPROM_DEV_ADDR,
+ I40E_MODULE_SFF_8472_SWAP,
+ &sff8472_swap, NULL);
+ if (status)
+ return -EIO;
+
+ /* Check if the module requires address swap to access
+ * the other EEPROM memory page.
+ */
+ if (sff8472_swap & I40E_MODULE_SFF_ADDR_MODE) {
+ netdev_warn(vsi->netdev, "Module address swap to access page 0xA2 is not supported.\n");
+ modinfo->type = ETH_MODULE_SFF_8079;
+ modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
+ } else if (sff8472_comp == 0x00) {
+ /* Module is not SFF-8472 compliant */
+ modinfo->type = ETH_MODULE_SFF_8079;
+ modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
+ } else {
+ modinfo->type = ETH_MODULE_SFF_8472;
+ modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+ }
+ break;
+ case I40E_MODULE_TYPE_QSFP_PLUS:
+ /* Read from memory page 0. */
+ status = i40e_aq_get_phy_register(hw,
+ I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE,
+ 0,
+ I40E_MODULE_REVISION_ADDR,
+ &sff8636_rev, NULL);
+ if (status)
+ return -EIO;
+ /* Determine revision compliance byte */
+ if (sff8636_rev > 0x02) {
+ /* Module is SFF-8636 compliant */
+ modinfo->type = ETH_MODULE_SFF_8636;
+ modinfo->eeprom_len = I40E_MODULE_QSFP_MAX_LEN;
+ } else {
+ modinfo->type = ETH_MODULE_SFF_8436;
+ modinfo->eeprom_len = I40E_MODULE_QSFP_MAX_LEN;
+ }
+ break;
+ case I40E_MODULE_TYPE_QSFP28:
+ modinfo->type = ETH_MODULE_SFF_8636;
+ modinfo->eeprom_len = I40E_MODULE_QSFP_MAX_LEN;
+ break;
+ default:
+ netdev_err(vsi->netdev, "Module type unrecognized\n");
+ return -EINVAL;
+ }
+ return 0;
+}
+
+/**
+ * i40e_get_module_eeprom - fills buffer with (Q)SFP+ module memory contents
+ * @netdev: network interface device structure
+ * @ee: EEPROM dump request structure
+ * @data: buffer to be filled with EEPROM contents
+ **/
+static int i40e_get_module_eeprom(struct net_device *netdev,
+ struct ethtool_eeprom *ee,
+ u8 *data)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ bool is_sfp = false;
+ i40e_status status;
+ u32 value = 0;
+ int i;
+
+ if (!ee || !ee->len || !data)
+ return -EINVAL;
+
+ if (hw->phy.link_info.module_type[0] == I40E_MODULE_TYPE_SFP)
+ is_sfp = true;
+
+ for (i = 0; i < ee->len; i++) {
+ u32 offset = i + ee->offset;
+ u32 addr = is_sfp ? I40E_I2C_EEPROM_DEV_ADDR : 0;
+
+ /* Check if we need to access the other memory page */
+ if (is_sfp) {
+ if (offset >= ETH_MODULE_SFF_8079_LEN) {
+ offset -= ETH_MODULE_SFF_8079_LEN;
+ addr = I40E_I2C_EEPROM_DEV_ADDR2;
+ }
+ } else {
+ while (offset >= ETH_MODULE_SFF_8436_LEN) {
+ /* Compute memory page number and offset. */
+ offset -= ETH_MODULE_SFF_8436_LEN / 2;
+ addr++;
+ }
+ }
+
+ status = i40e_aq_get_phy_register(hw,
+ I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE,
+ addr, offset, &value, NULL);
+ if (status)
+ return -EIO;
+ data[i] = value;
+ }
+ return 0;
+}
+
static const struct ethtool_ops i40e_ethtool_ops = {
.get_drvinfo = i40e_get_drvinfo,
.get_regs_len = i40e_get_regs_len,
@@ -4228,6 +4380,8 @@ static const struct ethtool_ops i40e_ethtool_ops = {
.set_rxfh = i40e_set_rxfh,
.get_channels = i40e_get_channels,
.set_channels = i40e_set_channels,
+ .get_module_info = i40e_get_module_info,
+ .get_module_eeprom = i40e_get_module_eeprom,
.get_ts_info = i40e_get_ts_info,
.get_priv_flags = i40e_get_priv_flags,
.set_priv_flags = i40e_set_priv_flags,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 6498da8806cb..3f9e89b054ec 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -600,6 +600,20 @@ static void i40e_stat_update32(struct i40e_hw *hw, u32 reg,
}
/**
+ * i40e_stat_update_and_clear32 - read and clear hw reg, update a 32 bit stat
+ * @hw: ptr to the hardware info
+ * @reg: the hw reg to read and clear
+ * @stat: ptr to the stat
+ **/
+static void i40e_stat_update_and_clear32(struct i40e_hw *hw, u32 reg, u64 *stat)
+{
+ u32 new_data = rd32(hw, reg);
+
+ wr32(hw, reg, 1); /* must write a nonzero value to clear register */
+ *stat += new_data;
+}
+
+/**
* i40e_update_eth_stats - Update VSI-specific ethernet statistics counters.
* @vsi: the VSI to be updated
**/
@@ -1040,18 +1054,15 @@ static void i40e_update_pf_stats(struct i40e_pf *pf)
&osd->rx_jabber, &nsd->rx_jabber);
/* FDIR stats */
- i40e_stat_update32(hw,
- I40E_GLQF_PCNT(I40E_FD_ATR_STAT_IDX(pf->hw.pf_id)),
- pf->stat_offsets_loaded,
- &osd->fd_atr_match, &nsd->fd_atr_match);
- i40e_stat_update32(hw,
- I40E_GLQF_PCNT(I40E_FD_SB_STAT_IDX(pf->hw.pf_id)),
- pf->stat_offsets_loaded,
- &osd->fd_sb_match, &nsd->fd_sb_match);
- i40e_stat_update32(hw,
- I40E_GLQF_PCNT(I40E_FD_ATR_TUNNEL_STAT_IDX(pf->hw.pf_id)),
- pf->stat_offsets_loaded,
- &osd->fd_atr_tunnel_match, &nsd->fd_atr_tunnel_match);
+ i40e_stat_update_and_clear32(hw,
+ I40E_GLQF_PCNT(I40E_FD_ATR_STAT_IDX(hw->pf_id)),
+ &nsd->fd_atr_match);
+ i40e_stat_update_and_clear32(hw,
+ I40E_GLQF_PCNT(I40E_FD_SB_STAT_IDX(hw->pf_id)),
+ &nsd->fd_sb_match);
+ i40e_stat_update_and_clear32(hw,
+ I40E_GLQF_PCNT(I40E_FD_ATR_TUNNEL_STAT_IDX(hw->pf_id)),
+ &nsd->fd_atr_tunnel_match);
val = rd32(hw, I40E_PRTPM_EEE_STAT);
nsd->tx_lpi_status =
@@ -3593,14 +3604,20 @@ static int i40e_vsi_enable_irq(struct i40e_vsi *vsi)
}
/**
- * i40e_stop_misc_vector - Stop the vector that handles non-queue events
+ * i40e_free_misc_vector - Free the vector that handles non-queue events
* @pf: board private structure
**/
-static void i40e_stop_misc_vector(struct i40e_pf *pf)
+static void i40e_free_misc_vector(struct i40e_pf *pf)
{
/* Disable ICR 0 */
wr32(&pf->hw, I40E_PFINT_ICR0_ENA, 0);
i40e_flush(&pf->hw);
+
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED && pf->msix_entries) {
+ synchronize_irq(pf->msix_entries[0].vector);
+ free_irq(pf->msix_entries[0].vector, pf);
+ clear_bit(__I40E_MISC_IRQ_REQUESTED, pf->state);
+ }
}
/**
@@ -4455,11 +4472,7 @@ static void i40e_clear_interrupt_scheme(struct i40e_pf *pf)
{
int i;
- i40e_stop_misc_vector(pf);
- if (pf->flags & I40E_FLAG_MSIX_ENABLED && pf->msix_entries) {
- synchronize_irq(pf->msix_entries[0].vector);
- free_irq(pf->msix_entries[0].vector, pf);
- }
+ i40e_free_misc_vector(pf);
i40e_put_lump(pf->irq_pile, pf->iwarp_base_vector,
I40E_IWARP_IRQ_PILE_ID);
@@ -5346,13 +5359,14 @@ out:
void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
{
enum i40e_aq_link_speed new_speed;
+ struct i40e_pf *pf = vsi->back;
char *speed = "Unknown";
char *fc = "Unknown";
char *fec = "";
char *req_fec = "";
char *an = "";
- new_speed = vsi->back->hw.phy.link_info.link_speed;
+ new_speed = pf->hw.phy.link_info.link_speed;
if ((vsi->current_isup == isup) && (vsi->current_speed == new_speed))
return;
@@ -5366,13 +5380,13 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
/* Warn user if link speed on NPAR enabled partition is not at
* least 10GB
*/
- if (vsi->back->hw.func_caps.npar_enable &&
- (vsi->back->hw.phy.link_info.link_speed == I40E_LINK_SPEED_1GB ||
- vsi->back->hw.phy.link_info.link_speed == I40E_LINK_SPEED_100MB))
+ if (pf->hw.func_caps.npar_enable &&
+ (pf->hw.phy.link_info.link_speed == I40E_LINK_SPEED_1GB ||
+ pf->hw.phy.link_info.link_speed == I40E_LINK_SPEED_100MB))
netdev_warn(vsi->netdev,
"The partition detected link speed that is less than 10Gbps\n");
- switch (vsi->back->hw.phy.link_info.link_speed) {
+ switch (pf->hw.phy.link_info.link_speed) {
case I40E_LINK_SPEED_40GB:
speed = "40 G";
break;
@@ -5395,7 +5409,7 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
break;
}
- switch (vsi->back->hw.fc.current_mode) {
+ switch (pf->hw.fc.current_mode) {
case I40E_FC_FULL:
fc = "RX/TX";
break;
@@ -5410,18 +5424,18 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
break;
}
- if (vsi->back->hw.phy.link_info.link_speed == I40E_LINK_SPEED_25GB) {
+ if (pf->hw.phy.link_info.link_speed == I40E_LINK_SPEED_25GB) {
req_fec = ", Requested FEC: None";
fec = ", FEC: None";
an = ", Autoneg: False";
- if (vsi->back->hw.phy.link_info.an_info & I40E_AQ_AN_COMPLETED)
+ if (pf->hw.phy.link_info.an_info & I40E_AQ_AN_COMPLETED)
an = ", Autoneg: True";
- if (vsi->back->hw.phy.link_info.fec_info &
+ if (pf->hw.phy.link_info.fec_info &
I40E_AQ_CONFIG_FEC_KR_ENA)
fec = ", FEC: CL74 FC-FEC/BASE-R";
- else if (vsi->back->hw.phy.link_info.fec_info &
+ else if (pf->hw.phy.link_info.fec_info &
I40E_AQ_CONFIG_FEC_RS_ENA)
fec = ", FEC: CL108 RS-FEC";
@@ -5470,15 +5484,6 @@ static int i40e_up_complete(struct i40e_vsi *vsi)
i40e_print_link_message(vsi, true);
netif_tx_start_all_queues(vsi->netdev);
netif_carrier_on(vsi->netdev);
- } else if (vsi->netdev) {
- i40e_print_link_message(vsi, false);
- /* need to check for qualified module here*/
- if ((pf->hw.phy.link_info.link_info &
- I40E_AQ_MEDIA_AVAILABLE) &&
- (!(pf->hw.phy.link_info.an_info &
- I40E_AQ_QUALIFIED_MODULE)))
- netdev_err(vsi->netdev,
- "the driver failed to link because an unqualified module was detected.");
}
/* replay FDIR SB filters */
@@ -6429,8 +6434,7 @@ static void i40e_link_event(struct i40e_pf *pf)
new_link == netif_carrier_ok(vsi->netdev)))
return;
- if (!test_bit(__I40E_VSI_DOWN, vsi->state))
- i40e_print_link_message(vsi, new_link);
+ i40e_print_link_message(vsi, new_link);
/* Notify the base of the switch tree connected to
* the link. Floating VEBs are not notified.
@@ -8350,6 +8354,57 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf)
return 0;
}
+#ifdef CONFIG_PM
+/**
+ * i40e_restore_interrupt_scheme - Restore the interrupt scheme
+ * @pf: private board data structure
+ *
+ * Restore the interrupt scheme that was cleared when we suspended the
+ * device. This should be called during resume to re-allocate the q_vectors
+ * and reacquire IRQs.
+ */
+static int i40e_restore_interrupt_scheme(struct i40e_pf *pf)
+{
+ int err, i;
+
+ /* We cleared the MSI and MSI-X flags when disabling the old interrupt
+ * scheme. We need to re-enabled them here in order to attempt to
+ * re-acquire the MSI or MSI-X vectors
+ */
+ pf->flags |= (I40E_FLAG_MSIX_ENABLED | I40E_FLAG_MSI_ENABLED);
+
+ err = i40e_init_interrupt_scheme(pf);
+ if (err)
+ return err;
+
+ /* Now that we've re-acquired IRQs, we need to remap the vectors and
+ * rings together again.
+ */
+ for (i = 0; i < pf->num_alloc_vsi; i++) {
+ if (pf->vsi[i]) {
+ err = i40e_vsi_alloc_q_vectors(pf->vsi[i]);
+ if (err)
+ goto err_unwind;
+ i40e_vsi_map_rings_to_vectors(pf->vsi[i]);
+ }
+ }
+
+ err = i40e_setup_misc_vector(pf);
+ if (err)
+ goto err_unwind;
+
+ return 0;
+
+err_unwind:
+ while (i--) {
+ if (pf->vsi[i])
+ i40e_vsi_free_q_vectors(pf->vsi[i]);
+ }
+
+ return err;
+}
+#endif /* CONFIG_PM */
+
/**
* i40e_setup_misc_vector - Setup the misc vector to handle non queue events
* @pf: board private structure
@@ -8363,13 +8418,12 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf)
struct i40e_hw *hw = &pf->hw;
int err = 0;
- /* Only request the irq if this is the first time through, and
- * not when we're rebuilding after a Reset
- */
- if (!test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) {
+ /* Only request the IRQ once, the first time through. */
+ if (!test_and_set_bit(__I40E_MISC_IRQ_REQUESTED, pf->state)) {
err = request_irq(pf->msix_entries[0].vector,
i40e_intr, 0, pf->int_name, pf);
if (err) {
+ clear_bit(__I40E_MISC_IRQ_REQUESTED, pf->state);
dev_info(&pf->pdev->dev,
"request_irq for %s failed: %d\n",
pf->int_name, err);
@@ -11039,6 +11093,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit)
static void i40e_determine_queue_usage(struct i40e_pf *pf)
{
int queues_left;
+ int q_max;
pf->num_lan_qps = 0;
@@ -11085,10 +11140,12 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
I40E_FLAG_DCB_ENABLED);
dev_info(&pf->pdev->dev, "not enough queues for DCB. DCB is disabled.\n");
}
- pf->num_lan_qps = max_t(int, pf->rss_size_max,
- num_online_cpus());
- pf->num_lan_qps = min_t(int, pf->num_lan_qps,
- pf->hw.func_caps.num_tx_qp);
+
+ /* limit lan qps to the smaller of qps, cpus or msix */
+ q_max = max_t(int, pf->rss_size_max, num_online_cpus());
+ q_max = min_t(int, q_max, pf->hw.func_caps.num_tx_qp);
+ q_max = min_t(int, q_max, pf->hw.func_caps.num_msix_vectors);
+ pf->num_lan_qps = q_max;
queues_left -= pf->num_lan_qps;
}
@@ -11304,6 +11361,13 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
hw->bus.bus_id = pdev->bus->number;
pf->instance = pfs_found;
+ /* Select something other than the 802.1ad ethertype for the
+ * switch to use internally and drop on ingress.
+ */
+ hw->switch_tag = 0xffff;
+ hw->first_tag = ETH_P_8021AD;
+ hw->second_tag = ETH_P_8021Q;
+
INIT_LIST_HEAD(&pf->l3_flex_pit_list);
INIT_LIST_HEAD(&pf->l4_flex_pit_list);
@@ -11380,11 +11444,10 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
i40e_nvm_version_str(hw));
if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
- hw->aq.api_min_ver > I40E_FW_API_VERSION_MINOR)
+ hw->aq.api_min_ver > I40E_FW_MINOR_VERSION(hw))
dev_info(&pdev->dev,
"The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n");
- else if (hw->aq.api_maj_ver < I40E_FW_API_VERSION_MAJOR ||
- hw->aq.api_min_ver < (I40E_FW_API_VERSION_MINOR - 1))
+ else if (hw->aq.api_maj_ver == 1 && hw->aq.api_min_ver < 4)
dev_info(&pdev->dev,
"The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n");
@@ -12048,18 +12111,25 @@ static void i40e_shutdown(struct pci_dev *pdev)
#ifdef CONFIG_PM
/**
- * i40e_suspend - PCI callback for moving to D3
- * @pdev: PCI device information struct
+ * i40e_suspend - PM callback for moving to D3
+ * @dev: generic device information structure
**/
-static int i40e_suspend(struct pci_dev *pdev, pm_message_t state)
+static int i40e_suspend(struct device *dev)
{
+ struct pci_dev *pdev = to_pci_dev(dev);
struct i40e_pf *pf = pci_get_drvdata(pdev);
struct i40e_hw *hw = &pf->hw;
- int retval = 0;
- set_bit(__I40E_SUSPENDED, pf->state);
+ /* If we're already suspended, then there is nothing to do */
+ if (test_and_set_bit(__I40E_SUSPENDED, pf->state))
+ return 0;
+
set_bit(__I40E_DOWN, pf->state);
+ /* Ensure service task will not be running */
+ del_timer_sync(&pf->service_timer);
+ cancel_work_sync(&pf->service_task);
+
if (pf->wol_en && (pf->hw_features & I40E_HW_WOL_MC_MAGIC_PKT_WAKE))
i40e_enable_mc_magic_wake(pf);
@@ -12068,81 +12138,72 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state)
wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0));
- i40e_stop_misc_vector(pf);
- if (pf->msix_entries) {
- synchronize_irq(pf->msix_entries[0].vector);
- free_irq(pf->msix_entries[0].vector, pf);
- }
- retval = pci_save_state(pdev);
- if (retval)
- return retval;
-
- pci_wake_from_d3(pdev, pf->wol_en);
- pci_set_power_state(pdev, PCI_D3hot);
+ /* Clear the interrupt scheme and release our IRQs so that the system
+ * can safely hibernate even when there are a large number of CPUs.
+ * Otherwise hibernation might fail when mapping all the vectors back
+ * to CPU0.
+ */
+ i40e_clear_interrupt_scheme(pf);
- return retval;
+ return 0;
}
/**
- * i40e_resume - PCI callback for waking up from D3
- * @pdev: PCI device information struct
+ * i40e_resume - PM callback for waking up from D3
+ * @dev: generic device information structure
**/
-static int i40e_resume(struct pci_dev *pdev)
+static int i40e_resume(struct device *dev)
{
+ struct pci_dev *pdev = to_pci_dev(dev);
struct i40e_pf *pf = pci_get_drvdata(pdev);
- u32 err;
+ int err;
- pci_set_power_state(pdev, PCI_D0);
- pci_restore_state(pdev);
- /* pci_restore_state() clears dev->state_saves, so
- * call pci_save_state() again to restore it.
- */
- pci_save_state(pdev);
+ /* If we're not suspended, then there is nothing to do */
+ if (!test_bit(__I40E_SUSPENDED, pf->state))
+ return 0;
- err = pci_enable_device_mem(pdev);
+ /* We cleared the interrupt scheme when we suspended, so we need to
+ * restore it now to resume device functionality.
+ */
+ err = i40e_restore_interrupt_scheme(pf);
if (err) {
- dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n");
- return err;
+ dev_err(&pdev->dev, "Cannot restore interrupt scheme: %d\n",
+ err);
}
- pci_set_master(pdev);
- /* no wakeup events while running */
- pci_wake_from_d3(pdev, false);
-
- /* handling the reset will rebuild the device state */
- if (test_and_clear_bit(__I40E_SUSPENDED, pf->state)) {
- clear_bit(__I40E_DOWN, pf->state);
- if (pf->msix_entries) {
- err = request_irq(pf->msix_entries[0].vector,
- i40e_intr, 0, pf->int_name, pf);
- if (err) {
- dev_err(&pf->pdev->dev,
- "request_irq for %s failed: %d\n",
- pf->int_name, err);
- }
- }
- i40e_reset_and_rebuild(pf, false, false);
- }
+ clear_bit(__I40E_DOWN, pf->state);
+ i40e_reset_and_rebuild(pf, false, false);
+
+ /* Clear suspended state last after everything is recovered */
+ clear_bit(__I40E_SUSPENDED, pf->state);
+
+ /* Restart the service task */
+ mod_timer(&pf->service_timer,
+ round_jiffies(jiffies + pf->service_timer_period));
return 0;
}
-#endif
+#endif /* CONFIG_PM */
+
static const struct pci_error_handlers i40e_err_handler = {
.error_detected = i40e_pci_error_detected,
.slot_reset = i40e_pci_error_slot_reset,
.resume = i40e_pci_error_resume,
};
+static SIMPLE_DEV_PM_OPS(i40e_pm_ops, i40e_suspend, i40e_resume);
+
static struct pci_driver i40e_driver = {
.name = i40e_driver_name,
.id_table = i40e_pci_tbl,
.probe = i40e_probe,
.remove = i40e_remove,
#ifdef CONFIG_PM
- .suspend = i40e_suspend,
- .resume = i40e_resume,
-#endif
+ .driver = {
+ .pm = &i40e_pm_ops,
+ },
+#endif /* CONFIG_PM */
.shutdown = i40e_shutdown,
.err_handler = &i40e_err_handler,
.sriov_configure = i40e_pci_sriov_configure,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index a39b13197891..01502561035c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -360,6 +360,15 @@ i40e_status i40e_aq_rx_ctl_write_register(struct i40e_hw *hw,
u32 reg_addr, u32 reg_val,
struct i40e_asq_cmd_details *cmd_details);
void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val);
+i40e_status i40e_aq_set_phy_register(struct i40e_hw *hw,
+ u8 phy_select, u8 dev_addr,
+ u32 reg_addr, u32 reg_val,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_get_phy_register(struct i40e_hw *hw,
+ u8 phy_select, u8 dev_addr,
+ u32 reg_addr, u32 *reg_val,
+ struct i40e_asq_cmd_details *cmd_details);
+
i40e_status i40e_read_phy_register_clause22(struct i40e_hw *hw,
u16 reg, u8 phy_addr, u16 *value);
i40e_status i40e_write_phy_register_clause22(struct i40e_hw *hw,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 1519dfb851d0..d9fdf69bbc6e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -960,14 +960,14 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
{
enum i40e_latency_range new_latency_range = rc->latency_range;
u32 new_itr = rc->itr;
- int bytes_per_int;
+ int bytes_per_usec;
unsigned int usecs, estimated_usecs;
if (rc->total_packets == 0 || !rc->itr)
return false;
usecs = (rc->itr << 1) * ITR_COUNTDOWN_START;
- bytes_per_int = rc->total_bytes / usecs;
+ bytes_per_usec = rc->total_bytes / usecs;
/* The calculations in this algorithm depend on interrupts actually
* firing at the ITR rate. This may not happen if the packet rate is
@@ -993,18 +993,18 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
*/
switch (new_latency_range) {
case I40E_LOWEST_LATENCY:
- if (bytes_per_int > 10)
+ if (bytes_per_usec > 10)
new_latency_range = I40E_LOW_LATENCY;
break;
case I40E_LOW_LATENCY:
- if (bytes_per_int > 20)
+ if (bytes_per_usec > 20)
new_latency_range = I40E_BULK_LATENCY;
- else if (bytes_per_int <= 10)
+ else if (bytes_per_usec <= 10)
new_latency_range = I40E_LOWEST_LATENCY;
break;
case I40E_BULK_LATENCY:
default:
- if (bytes_per_int <= 20)
+ if (bytes_per_usec <= 20)
new_latency_range = I40E_LOW_LATENCY;
break;
}
@@ -2107,6 +2107,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
if (!skb) {
xdp.data = page_address(rx_buffer->page) +
rx_buffer->page_offset;
+ xdp_set_data_meta_invalid(&xdp);
xdp.data_hard_start = xdp.data -
i40e_rx_offset(rx_ring);
xdp.data_end = xdp.data + size;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index fd4bbdd88b57..4b32b1d38a66 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -428,6 +428,18 @@ struct i40e_nvm_access {
u8 data[1];
};
+/* (Q)SFP module access definitions */
+#define I40E_I2C_EEPROM_DEV_ADDR 0xA0
+#define I40E_I2C_EEPROM_DEV_ADDR2 0xA2
+#define I40E_MODULE_TYPE_ADDR 0x00
+#define I40E_MODULE_REVISION_ADDR 0x01
+#define I40E_MODULE_SFF_8472_COMP 0x5E
+#define I40E_MODULE_SFF_8472_SWAP 0x5C
+#define I40E_MODULE_SFF_ADDR_MODE 0x04
+#define I40E_MODULE_TYPE_QSFP_PLUS 0x0D
+#define I40E_MODULE_TYPE_QSFP28 0x11
+#define I40E_MODULE_QSFP_MAX_LEN 640
+
/* PCI bus types */
enum i40e_bus_type {
i40e_bus_type_unknown = 0,
@@ -598,8 +610,15 @@ struct i40e_hw {
struct i40e_dcbx_config desired_dcbx_config; /* CEE Desired Cfg */
#define I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE BIT_ULL(0)
+#define I40E_HW_FLAG_802_1AD_CAPABLE BIT_ULL(1)
+#define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE BIT_ULL(2)
u64 flags;
+ /* Used in set switch config AQ command */
+ u16 switch_tag;
+ u16 first_tag;
+ u16 second_tag;
+
/* debug mask */
u32 debug_mask;
char err_str[16];
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 4d1e670f490e..04568137e029 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -154,15 +154,30 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf)
/**
* i40e_vc_disable_vf
- * @pf: pointer to the PF info
* @vf: pointer to the VF info
*
- * Disable the VF through a SW reset
+ * Disable the VF through a SW reset.
**/
-static inline void i40e_vc_disable_vf(struct i40e_pf *pf, struct i40e_vf *vf)
+static inline void i40e_vc_disable_vf(struct i40e_vf *vf)
{
+ int i;
+
i40e_vc_notify_vf_reset(vf);
- i40e_reset_vf(vf, false);
+
+ /* We want to ensure that an actual reset occurs initiated after this
+ * function was called. However, we do not want to wait forever, so
+ * we'll give a reasonable time and print a message if we failed to
+ * ensure a reset.
+ */
+ for (i = 0; i < 20; i++) {
+ if (i40e_reset_vf(vf, false))
+ return;
+ usleep_range(10000, 20000);
+ }
+
+ dev_warn(&vf->pf->pdev->dev,
+ "Failed to initiate reset for VF %d after 200 milliseconds\n",
+ vf->vf_id);
}
/**
@@ -423,6 +438,9 @@ static int i40e_config_iwarp_qvlist(struct i40e_vf *vf,
(sizeof(struct virtchnl_iwarp_qv_info) *
(qvlist_info->num_vectors - 1));
vf->qvlist_info = kzalloc(size, GFP_KERNEL);
+ if (!vf->qvlist_info)
+ return -ENOMEM;
+
vf->qvlist_info->num_vectors = qvlist_info->num_vectors;
msix_vf = pf->hw.func_caps.num_msix_vectors_vf;
@@ -815,6 +833,14 @@ static void i40e_free_vf_res(struct i40e_vf *vf)
*/
clear_bit(I40E_VF_STATE_INIT, &vf->vf_states);
+ /* It's possible the VF had requeuested more queues than the default so
+ * do the accounting here when we're about to free them.
+ */
+ if (vf->num_queue_pairs > I40E_DEFAULT_QUEUES_PER_VF) {
+ pf->queues_left += vf->num_queue_pairs -
+ I40E_DEFAULT_QUEUES_PER_VF;
+ }
+
/* free vsi & disconnect it from the parent uplink */
if (vf->lan_vsi_idx) {
i40e_vsi_release(pf->vsi[vf->lan_vsi_idx]);
@@ -853,7 +879,8 @@ static void i40e_free_vf_res(struct i40e_vf *vf)
}
/* reset some of the state variables keeping track of the resources */
vf->num_queue_pairs = 0;
- vf->vf_states = 0;
+ clear_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states);
+ clear_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states);
}
/**
@@ -868,12 +895,27 @@ static int i40e_alloc_vf_res(struct i40e_vf *vf)
int total_queue_pairs = 0;
int ret;
+ if (vf->num_req_queues &&
+ vf->num_req_queues <= pf->queues_left + I40E_DEFAULT_QUEUES_PER_VF)
+ pf->num_vf_qps = vf->num_req_queues;
+ else
+ pf->num_vf_qps = I40E_DEFAULT_QUEUES_PER_VF;
+
/* allocate hw vsi context & associated resources */
ret = i40e_alloc_vsi_res(vf, I40E_VSI_SRIOV);
if (ret)
goto error_alloc;
total_queue_pairs += pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs;
+ /* We account for each VF to get a default number of queue pairs. If
+ * the VF has now requested more, we need to account for that to make
+ * certain we never request more queues than we actually have left in
+ * HW.
+ */
+ if (total_queue_pairs > I40E_DEFAULT_QUEUES_PER_VF)
+ pf->queues_left -=
+ total_queue_pairs - I40E_DEFAULT_QUEUES_PER_VF;
+
if (vf->trusted)
set_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
else
@@ -1008,8 +1050,8 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf)
set_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states);
clear_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
/* Do not notify the client during VF init */
- if (test_and_clear_bit(I40E_VF_STATE_PRE_ENABLE,
- &vf->vf_states))
+ if (!test_and_clear_bit(I40E_VF_STATE_PRE_ENABLE,
+ &vf->vf_states))
i40e_notify_client_of_vf_reset(pf, abs_vf_id);
vf->num_vlan = 0;
}
@@ -1026,9 +1068,9 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf)
* @vf: pointer to the VF structure
* @flr: VFLR was issued or not
*
- * reset the VF
+ * Returns true if the VF is reset, false otherwise.
**/
-void i40e_reset_vf(struct i40e_vf *vf, bool flr)
+bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
{
struct i40e_pf *pf = vf->pf;
struct i40e_hw *hw = &pf->hw;
@@ -1036,9 +1078,11 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
u32 reg;
int i;
- /* If VFs have been disabled, there is no need to reset */
+ /* If the VFs have been disabled, this means something else is
+ * resetting the VF, so we shouldn't continue.
+ */
if (test_and_set_bit(__I40E_VF_DISABLE, pf->state))
- return;
+ return false;
i40e_trigger_vf_reset(vf, flr);
@@ -1075,6 +1119,8 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
i40e_flush(hw);
clear_bit(__I40E_VF_DISABLE, pf->state);
+
+ return true;
}
/**
@@ -1086,8 +1132,10 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
* VF, then do all the waiting in one chunk, and finally finish restoring each
* VF after the wait. This is useful during PF routines which need to reset
* all VFs, as otherwise it must perform these resets in a serialized fashion.
+ *
+ * Returns true if any VFs were reset, and false otherwise.
**/
-void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
+bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
{
struct i40e_hw *hw = &pf->hw;
struct i40e_vf *vf;
@@ -1096,11 +1144,11 @@ void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
/* If we don't have any VFs, then there is nothing to reset */
if (!pf->num_alloc_vfs)
- return;
+ return false;
/* If VFs have been disabled, there is no need to reset */
if (test_and_set_bit(__I40E_VF_DISABLE, pf->state))
- return;
+ return false;
/* Begin reset on all VFs at once */
for (v = 0; v < pf->num_alloc_vfs; v++)
@@ -1175,6 +1223,8 @@ void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
i40e_flush(hw);
clear_bit(__I40E_VF_DISABLE, pf->state);
+
+ return true;
}
/**
@@ -1537,6 +1587,8 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_IWARP)) {
vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_IWARP;
set_bit(I40E_VF_STATE_IWARPENA, &vf->vf_states);
+ } else {
+ clear_bit(I40E_VF_STATE_IWARPENA, &vf->vf_states);
}
if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) {
@@ -1579,6 +1631,9 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
VIRTCHNL_VF_OFFLOAD_WB_ON_ITR;
}
+ if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_REQ_QUEUES)
+ vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_REQ_QUEUES;
+
vfres->num_vsis = num_vsis;
vfres->num_queue_pairs = vf->num_queue_pairs;
vfres->max_vectors = pf->hw.func_caps.num_msix_vectors_vf;
@@ -1987,6 +2042,52 @@ error_param:
}
/**
+ * i40e_vc_request_queues_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ * @msglen: msg length
+ *
+ * VFs get a default number of queues but can use this message to request a
+ * different number. Will respond with either the number requested or the
+ * maximum we can support.
+ **/
+static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg, int msglen)
+{
+ struct virtchnl_vf_res_request *vfres =
+ (struct virtchnl_vf_res_request *)msg;
+ int req_pairs = vfres->num_queue_pairs;
+ int cur_pairs = vf->num_queue_pairs;
+ struct i40e_pf *pf = vf->pf;
+
+ if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states))
+ return -EINVAL;
+
+ if (req_pairs <= 0) {
+ dev_err(&pf->pdev->dev,
+ "VF %d tried to request %d queues. Ignoring.\n",
+ vf->vf_id, req_pairs);
+ } else if (req_pairs > I40E_MAX_VF_QUEUES) {
+ dev_err(&pf->pdev->dev,
+ "VF %d tried to request more than %d queues.\n",
+ vf->vf_id,
+ I40E_MAX_VF_QUEUES);
+ vfres->num_queue_pairs = I40E_MAX_VF_QUEUES;
+ } else if (req_pairs - cur_pairs > pf->queues_left) {
+ dev_warn(&pf->pdev->dev,
+ "VF %d requested %d more queues, but only %d left.\n",
+ vf->vf_id,
+ req_pairs - cur_pairs,
+ pf->queues_left);
+ vfres->num_queue_pairs = pf->queues_left + cur_pairs;
+ } else {
+ vf->num_req_queues = req_pairs;
+ }
+
+ return i40e_vc_send_msg_to_vf(vf, VIRTCHNL_OP_REQUEST_QUEUES, 0,
+ (u8 *)vfres, sizeof(vfres));
+}
+
+/**
* i40e_vc_get_stats_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
@@ -2708,6 +2809,9 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING:
ret = i40e_vc_disable_vlan_stripping(vf, msg, msglen);
break;
+ case VIRTCHNL_OP_REQUEST_QUEUES:
+ ret = i40e_vc_request_queues_msg(vf, msg, msglen);
+ break;
case VIRTCHNL_OP_UNKNOWN:
default:
@@ -2840,7 +2944,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
}
/* Force the VF driver stop so it has to reload with new MAC address */
- i40e_vc_disable_vf(pf, vf);
+ i40e_vc_disable_vf(vf);
dev_info(&pf->pdev->dev, "Reload the VF driver to make this change effective.\n");
error_param:
@@ -2848,6 +2952,34 @@ error_param:
}
/**
+ * i40e_vsi_has_vlans - True if VSI has configured VLANs
+ * @vsi: pointer to the vsi
+ *
+ * Check if a VSI has configured any VLANs. False if we have a port VLAN or if
+ * we have no configured VLANs. Do not call while holding the
+ * mac_filter_hash_lock.
+ */
+static bool i40e_vsi_has_vlans(struct i40e_vsi *vsi)
+{
+ bool have_vlans;
+
+ /* If we have a port VLAN, then the VSI cannot have any VLANs
+ * configured, as all MAC/VLAN filters will be assigned to the PVID.
+ */
+ if (vsi->info.pvid)
+ return false;
+
+ /* Since we don't have a PVID, we know that if the device is in VLAN
+ * mode it must be because of a VLAN filter configured on this VSI.
+ */
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
+ have_vlans = i40e_is_vsi_in_vlan(vsi);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
+
+ return have_vlans;
+}
+
+/**
* i40e_ndo_set_vf_port_vlan
* @netdev: network interface device structure
* @vf_id: VF identifier
@@ -2899,10 +3031,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
/* duplicate request, so just return success */
goto error_pvid;
- /* Locked once because multiple functions below iterate list */
- spin_lock_bh(&vsi->mac_filter_hash_lock);
-
- if (le16_to_cpu(vsi->info.pvid) == 0 && i40e_is_vsi_in_vlan(vsi)) {
+ if (i40e_vsi_has_vlans(vsi)) {
dev_err(&pf->pdev->dev,
"VF %d has already configured VLAN filters and the administrator is requesting a port VLAN override.\nPlease unload and reload the VF driver for this change to take effect.\n",
vf_id);
@@ -2910,11 +3039,14 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
* the right thing by reconfiguring his network correctly
* and then reloading the VF driver.
*/
- i40e_vc_disable_vf(pf, vf);
+ i40e_vc_disable_vf(vf);
/* During reset the VF got a new VSI, so refresh the pointer. */
vsi = pf->vsi[vf->lan_vsi_idx];
}
+ /* Locked once because multiple functions below iterate list */
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
+
/* Check for condition where there was already a port VLAN ID
* filter set and now it is being deleted by setting it to zero.
* Additionally check for the condition where there was a port
@@ -3279,14 +3411,11 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting)
vf = &pf->vf[vf_id];
- if (!vf)
- return -EINVAL;
if (setting == vf->trusted)
goto out;
vf->trusted = setting;
- i40e_vc_notify_vf_reset(vf);
- i40e_reset_vf(vf, false);
+ i40e_vc_disable_vf(vf);
dev_info(&pf->pdev->dev, "VF %u is now %strusted\n",
vf_id, setting ? "" : "un");
out:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index 1f4b0c504368..5efc4f92bb37 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -56,7 +56,6 @@ enum i40e_vf_states {
I40E_VF_STATE_INIT = 0,
I40E_VF_STATE_ACTIVE,
I40E_VF_STATE_IWARPENA,
- I40E_VF_STATE_FCOEENA,
I40E_VF_STATE_DISABLED,
I40E_VF_STATE_MC_PROMISC,
I40E_VF_STATE_UC_PROMISC,
@@ -97,6 +96,7 @@ struct i40e_vf {
u16 lan_vsi_id; /* ID as used by firmware */
u8 num_queue_pairs; /* num of qps assigned to VF vsis */
+ u8 num_req_queues; /* num of requested qps */
u64 num_mdd_events; /* num of mdd events detected */
/* num of continuous malformed or invalid msgs detected */
u64 num_invalid_msgs;
@@ -121,8 +121,8 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs);
int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
u32 v_retval, u8 *msg, u16 msglen);
int i40e_vc_process_vflr_event(struct i40e_pf *pf);
-void i40e_reset_vf(struct i40e_vf *vf, bool flr);
-void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr);
+bool i40e_reset_vf(struct i40e_vf *vf, bool flr);
+bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr);
void i40e_vc_notify_vf_reset(struct i40e_vf *vf);
/* VF configuration related iplink handlers */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
index 83e63e55c4b4..ed5602f4bbcd 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
@@ -34,7 +34,15 @@
*/
#define I40E_FW_API_VERSION_MAJOR 0x0001
-#define I40E_FW_API_VERSION_MINOR 0x0005
+#define I40E_FW_API_VERSION_MINOR_X722 0x0005
+#define I40E_FW_API_VERSION_MINOR_X710 0x0007
+
+#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \
+ I40E_FW_API_VERSION_MINOR_X710 : \
+ I40E_FW_API_VERSION_MINOR_X722)
+
+/* API version 1.7 implements additional link and PHY-specific APIs */
+#define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007
struct i40e_aq_desc {
__le16 flags;
@@ -236,6 +244,8 @@ enum i40e_admin_queue_opc {
i40e_aqc_opc_set_phy_debug = 0x0622,
i40e_aqc_opc_upload_ext_phy_fm = 0x0625,
i40e_aqc_opc_run_phy_activity = 0x0626,
+ i40e_aqc_opc_set_phy_register = 0x0628,
+ i40e_aqc_opc_get_phy_register = 0x0629,
/* NVM commands */
i40e_aqc_opc_nvm_read = 0x0701,
@@ -761,7 +771,22 @@ struct i40e_aqc_set_switch_config {
#define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001
#define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002
__le16 valid_flags;
- u8 reserved[12];
+ /* The ethertype in switch_tag is dropped on ingress and used
+ * internally by the switch. Set this to zero for the default
+ * of 0x88a8 (802.1ad). Should be zero for firmware API
+ * versions lower than 1.7.
+ */
+ __le16 switch_tag;
+ /* The ethertypes in first_tag and second_tag are used to
+ * match the outer and inner VLAN tags (respectively) when HW
+ * double VLAN tagging is enabled via the set port parameters
+ * AQ command. Otherwise these are both ignored. Set them to
+ * zero for their defaults of 0x8100 (802.1Q). Should be zero
+ * for firmware API versions lower than 1.7.
+ */
+ __le16 first_tag;
+ __le16 second_tag;
+ u8 reserved[6];
};
I40E_CHECK_CMD_LENGTH(i40e_aqc_set_switch_config);
@@ -1722,6 +1747,8 @@ enum i40e_aq_phy_type {
I40E_PHY_TYPE_10GBASE_CR1_CU = 0xB,
I40E_PHY_TYPE_10GBASE_AOC = 0xC,
I40E_PHY_TYPE_40GBASE_AOC = 0xD,
+ I40E_PHY_TYPE_UNRECOGNIZED = 0xE,
+ I40E_PHY_TYPE_UNSUPPORTED = 0xF,
I40E_PHY_TYPE_100BASE_TX = 0x11,
I40E_PHY_TYPE_1000BASE_T = 0x12,
I40E_PHY_TYPE_10GBASE_T = 0x13,
@@ -1740,6 +1767,8 @@ enum i40e_aq_phy_type {
I40E_PHY_TYPE_25GBASE_CR = 0x20,
I40E_PHY_TYPE_25GBASE_SR = 0x21,
I40E_PHY_TYPE_25GBASE_LR = 0x22,
+ I40E_PHY_TYPE_EMPTY = 0xFE,
+ I40E_PHY_TYPE_DEFAULT = 0xFF,
I40E_PHY_TYPE_MAX
};
@@ -1930,19 +1959,31 @@ struct i40e_aqc_get_link_status {
#define I40E_AQ_25G_SERDES_UCODE_ERR 0X04
#define I40E_AQ_25G_NIMB_UCODE_ERR 0X05
u8 loopback; /* use defines from i40e_aqc_set_lb_mode */
+/* Since firmware API 1.7 loopback field keeps power class info as well */
+#define I40E_AQ_LOOPBACK_MASK 0x07
+#define I40E_AQ_PWR_CLASS_SHIFT_LB 6
+#define I40E_AQ_PWR_CLASS_MASK_LB (0x03 << I40E_AQ_PWR_CLASS_SHIFT_LB)
__le16 max_frame_size;
u8 config;
#define I40E_AQ_CONFIG_FEC_KR_ENA 0x01
#define I40E_AQ_CONFIG_FEC_RS_ENA 0x02
#define I40E_AQ_CONFIG_CRC_ENA 0x04
#define I40E_AQ_CONFIG_PACING_MASK 0x78
- u8 power_desc;
+ union {
+ struct {
+ u8 power_desc;
#define I40E_AQ_LINK_POWER_CLASS_1 0x00
#define I40E_AQ_LINK_POWER_CLASS_2 0x01
#define I40E_AQ_LINK_POWER_CLASS_3 0x02
#define I40E_AQ_LINK_POWER_CLASS_4 0x03
#define I40E_AQ_PWR_CLASS_MASK 0x03
- u8 reserved[4];
+ u8 reserved[4];
+ };
+ struct {
+ u8 link_type[4];
+ u8 link_type_ext;
+ };
+ };
};
I40E_CHECK_CMD_LENGTH(i40e_aqc_get_link_status);
@@ -2022,6 +2063,22 @@ struct i40e_aqc_run_phy_activity {
I40E_CHECK_CMD_LENGTH(i40e_aqc_run_phy_activity);
+/* Set PHY Register command (0x0628) */
+/* Get PHY Register command (0x0629) */
+struct i40e_aqc_phy_register_access {
+ u8 phy_interface;
+#define I40E_AQ_PHY_REG_ACCESS_INTERNAL 0
+#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL 1
+#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE 2
+ u8 dev_address;
+ u8 reserved1[2];
+ __le32 reg_address;
+ __le32 reg_value;
+ u8 reserved2[4];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access);
+
/* NVM Read command (indirect 0x0701)
* NVM Erase commands (direct 0x0702)
* NVM Update commands (indirect 0x0703)
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c
index 8d3a2bfe186a..7d70bf69b249 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c
@@ -1042,6 +1042,75 @@ do_retry:
}
/**
+ * i40evf_aq_set_phy_register
+ * @hw: pointer to the hw struct
+ * @phy_select: select which phy should be accessed
+ * @dev_addr: PHY device address
+ * @reg_addr: PHY register address
+ * @reg_val: new register value
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Reset the external PHY.
+ **/
+i40e_status i40evf_aq_set_phy_register(struct i40e_hw *hw,
+ u8 phy_select, u8 dev_addr,
+ u32 reg_addr, u32 reg_val,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_phy_register_access *cmd =
+ (struct i40e_aqc_phy_register_access *)&desc.params.raw;
+ i40e_status status;
+
+ i40evf_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_set_phy_register);
+
+ cmd->phy_interface = phy_select;
+ cmd->dev_address = dev_addr;
+ cmd->reg_address = cpu_to_le32(reg_addr);
+ cmd->reg_value = cpu_to_le32(reg_val);
+
+ status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+ return status;
+}
+
+/**
+ * i40evf_aq_get_phy_register
+ * @hw: pointer to the hw struct
+ * @phy_select: select which phy should be accessed
+ * @dev_addr: PHY device address
+ * @reg_addr: PHY register address
+ * @reg_val: read register value
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Reset the external PHY.
+ **/
+i40e_status i40evf_aq_get_phy_register(struct i40e_hw *hw,
+ u8 phy_select, u8 dev_addr,
+ u32 reg_addr, u32 *reg_val,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_desc desc;
+ struct i40e_aqc_phy_register_access *cmd =
+ (struct i40e_aqc_phy_register_access *)&desc.params.raw;
+ i40e_status status;
+
+ i40evf_fill_default_direct_cmd_desc(&desc,
+ i40e_aqc_opc_get_phy_register);
+
+ cmd->phy_interface = phy_select;
+ cmd->dev_address = dev_addr;
+ cmd->reg_address = cpu_to_le32(reg_addr);
+
+ status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+ if (!status)
+ *reg_val = le32_to_cpu(cmd->reg_value);
+
+ return status;
+}
+
+/**
* i40e_aq_send_msg_to_pf
* @hw: pointer to the hardware structure
* @v_opcode: opcodes for VF-PF communication
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
index c9836bba487d..b624b5994075 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
@@ -111,6 +111,15 @@ i40e_status i40evf_aq_rx_ctl_write_register(struct i40e_hw *hw,
u32 reg_addr, u32 reg_val,
struct i40e_asq_cmd_details *cmd_details);
void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val);
+i40e_status i40e_aq_set_phy_register(struct i40e_hw *hw,
+ u8 phy_select, u8 dev_addr,
+ u32 reg_addr, u32 reg_val,
+ struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_get_phy_register(struct i40e_hw *hw,
+ u8 phy_select, u8 dev_addr,
+ u32 reg_addr, u32 *reg_val,
+ struct i40e_asq_cmd_details *cmd_details);
+
i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page,
u16 reg, u8 phy_addr, u16 *value);
i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page,
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index c32c62462c84..37e1de886d48 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -358,14 +358,14 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
{
enum i40e_latency_range new_latency_range = rc->latency_range;
u32 new_itr = rc->itr;
- int bytes_per_int;
+ int bytes_per_usec;
unsigned int usecs, estimated_usecs;
if (rc->total_packets == 0 || !rc->itr)
return false;
usecs = (rc->itr << 1) * ITR_COUNTDOWN_START;
- bytes_per_int = rc->total_bytes / usecs;
+ bytes_per_usec = rc->total_bytes / usecs;
/* The calculations in this algorithm depend on interrupts actually
* firing at the ITR rate. This may not happen if the packet rate is
@@ -391,18 +391,18 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
*/
switch (new_latency_range) {
case I40E_LOWEST_LATENCY:
- if (bytes_per_int > 10)
+ if (bytes_per_usec > 10)
new_latency_range = I40E_LOW_LATENCY;
break;
case I40E_LOW_LATENCY:
- if (bytes_per_int > 20)
+ if (bytes_per_usec > 20)
new_latency_range = I40E_BULK_LATENCY;
- else if (bytes_per_int <= 10)
+ else if (bytes_per_usec <= 10)
new_latency_range = I40E_LOWEST_LATENCY;
break;
case I40E_BULK_LATENCY:
default:
- if (bytes_per_int <= 20)
+ if (bytes_per_usec <= 20)
new_latency_range = I40E_LOW_LATENCY;
break;
}
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h
index 2ea919d9cdcf..9364b67fff9c 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h
@@ -401,6 +401,18 @@ struct i40e_nvm_access {
u8 data[1];
};
+/* (Q)SFP module access definitions */
+#define I40E_I2C_EEPROM_DEV_ADDR 0xA0
+#define I40E_I2C_EEPROM_DEV_ADDR2 0xA2
+#define I40E_MODULE_TYPE_ADDR 0x00
+#define I40E_MODULE_REVISION_ADDR 0x01
+#define I40E_MODULE_SFF_8472_COMP 0x5E
+#define I40E_MODULE_SFF_8472_SWAP 0x5C
+#define I40E_MODULE_SFF_ADDR_MODE 0x04
+#define I40E_MODULE_TYPE_QSFP_PLUS 0x0D
+#define I40E_MODULE_TYPE_QSFP28 0x11
+#define I40E_MODULE_QSFP_MAX_LEN 640
+
/* PCI bus types */
enum i40e_bus_type {
i40e_bus_type_unknown = 0,
@@ -556,11 +568,19 @@ struct i40e_hw {
/* LLDP/DCBX Status */
u16 dcbx_status;
+#define I40E_HW_FLAG_802_1AD_CAPABLE BIT_ULL(1)
+#define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE BIT_ULL(2)
+
/* DCBX info */
struct i40e_dcbx_config local_dcbx_config; /* Oper/Local Cfg */
struct i40e_dcbx_config remote_dcbx_config; /* Peer Cfg */
struct i40e_dcbx_config desired_dcbx_config; /* CEE Desired Cfg */
+ /* Used in set switch config AQ command */
+ u16 switch_tag;
+ u16 first_tag;
+ u16 second_tag;
+
/* debug mask */
u32 debug_mask;
char err_str[16];
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h
index 82f69031e5cd..5982362c5643 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf.h
+++ b/drivers/net/ethernet/intel/i40evf/i40evf.h
@@ -102,6 +102,7 @@ struct i40e_vsi {
#define I40E_TX_CTXTDESC(R, i) \
(&(((struct i40e_tx_context_desc *)((R)->desc))[i]))
#define MAX_QUEUES 16
+#define I40EVF_MAX_REQ_QUEUES 4
#define I40EVF_HKEY_ARRAY_SIZE ((I40E_VFQF_HKEY_MAX_INDEX + 1) * 4)
#define I40EVF_HLUT_ARRAY_SIZE ((I40E_VFQF_HLUT_MAX_INDEX + 1) * 4)
@@ -200,6 +201,7 @@ struct i40evf_adapter {
struct list_head vlan_filter_list;
char misc_vector_name[IFNAMSIZ + 9];
int num_active_queues;
+ int num_req_queues;
/* TX */
struct i40e_ring *tx_rings;
@@ -235,6 +237,7 @@ struct i40evf_adapter {
#define I40EVF_FLAG_PROMISC_ON BIT(18)
#define I40EVF_FLAG_ALLMULTI_ON BIT(19)
#define I40EVF_FLAG_LEGACY_RX BIT(20)
+#define I40EVF_FLAG_REINIT_ITR_NEEDED BIT(21)
/* duplicates for common code */
#define I40E_FLAG_DCB_ENABLED 0
#define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED
@@ -349,6 +352,7 @@ void i40evf_deconfigure_queues(struct i40evf_adapter *adapter);
void i40evf_enable_queues(struct i40evf_adapter *adapter);
void i40evf_disable_queues(struct i40evf_adapter *adapter);
void i40evf_map_queues(struct i40evf_adapter *adapter);
+int i40evf_request_queues(struct i40evf_adapter *adapter, int num);
void i40evf_add_ether_addrs(struct i40evf_adapter *adapter);
void i40evf_del_ether_addrs(struct i40evf_adapter *adapter);
void i40evf_add_vlans(struct i40evf_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
index 65874d6b3ab9..da006fa3fec1 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
@@ -669,7 +669,7 @@ static void i40evf_get_channels(struct net_device *netdev,
struct i40evf_adapter *adapter = netdev_priv(netdev);
/* Report maximum channels */
- ch->max_combined = adapter->num_active_queues;
+ ch->max_combined = I40EVF_MAX_REQ_QUEUES;
ch->max_other = NONQ_VECS;
ch->other_count = NONQ_VECS;
@@ -678,6 +678,41 @@ static void i40evf_get_channels(struct net_device *netdev,
}
/**
+ * i40evf_set_channels: set the new channel count
+ * @netdev: network interface device structure
+ * @ch: channel information structure
+ *
+ * Negotiate a new number of channels with the PF then do a reset. During
+ * reset we'll realloc queues and fix the RSS table. Returns 0 on success,
+ * negative on failure.
+ **/
+static int i40evf_set_channels(struct net_device *netdev,
+ struct ethtool_channels *ch)
+{
+ struct i40evf_adapter *adapter = netdev_priv(netdev);
+ int num_req = ch->combined_count;
+
+ if (num_req != adapter->num_active_queues &&
+ !(adapter->vf_res->vf_cap_flags &
+ VIRTCHNL_VF_OFFLOAD_REQ_QUEUES)) {
+ dev_info(&adapter->pdev->dev, "PF is not capable of queue negotiation.\n");
+ return -EINVAL;
+ }
+
+ /* All of these should have already been checked by ethtool before this
+ * even gets to us, but just to be sure.
+ */
+ if (num_req <= 0 || num_req > I40EVF_MAX_REQ_QUEUES)
+ return -EINVAL;
+
+ if (ch->rx_count || ch->tx_count || ch->other_count != NONQ_VECS)
+ return -EINVAL;
+
+ adapter->num_req_queues = num_req;
+ return i40evf_request_queues(adapter, num_req);
+}
+
+/**
* i40evf_get_rxfh_key_size - get the RSS hash key size
* @netdev: network interface device structure
*
@@ -785,6 +820,7 @@ static const struct ethtool_ops i40evf_ethtool_ops = {
.get_rxfh = i40evf_get_rxfh,
.set_rxfh = i40evf_set_rxfh,
.get_channels = i40evf_get_channels,
+ .set_channels = i40evf_set_channels,
.get_rxfh_key_size = i40evf_get_rxfh_key_size,
.get_link_ksettings = i40evf_get_link_ksettings,
};
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 1825d956bb00..f2f1e754c2ce 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -46,7 +46,7 @@ static const char i40evf_driver_string[] =
#define DRV_VERSION_MAJOR 3
#define DRV_VERSION_MINOR 0
-#define DRV_VERSION_BUILD 0
+#define DRV_VERSION_BUILD 1
#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
__stringify(DRV_VERSION_MINOR) "." \
__stringify(DRV_VERSION_BUILD) \
@@ -430,57 +430,26 @@ i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx)
* group the rings as "efficiently" as possible. You would add new
* mapping configurations in here.
**/
-static int i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter)
+static void i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter)
{
+ int rings_remaining = adapter->num_active_queues;
+ int ridx = 0, vidx = 0;
int q_vectors;
- int v_start = 0;
- int rxr_idx = 0, txr_idx = 0;
- int rxr_remaining = adapter->num_active_queues;
- int txr_remaining = adapter->num_active_queues;
- int i, j;
- int rqpv, tqpv;
- int err = 0;
q_vectors = adapter->num_msix_vectors - NONQ_VECS;
- /* The ideal configuration...
- * We have enough vectors to map one per queue.
- */
- if (q_vectors >= (rxr_remaining * 2)) {
- for (; rxr_idx < rxr_remaining; v_start++, rxr_idx++)
- i40evf_map_vector_to_rxq(adapter, v_start, rxr_idx);
-
- for (; txr_idx < txr_remaining; v_start++, txr_idx++)
- i40evf_map_vector_to_txq(adapter, v_start, txr_idx);
- goto out;
- }
+ for (; ridx < rings_remaining; ridx++) {
+ i40evf_map_vector_to_rxq(adapter, vidx, ridx);
+ i40evf_map_vector_to_txq(adapter, vidx, ridx);
- /* If we don't have enough vectors for a 1-to-1
- * mapping, we'll have to group them so there are
- * multiple queues per vector.
- * Re-adjusting *qpv takes care of the remainder.
- */
- for (i = v_start; i < q_vectors; i++) {
- rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - i);
- for (j = 0; j < rqpv; j++) {
- i40evf_map_vector_to_rxq(adapter, i, rxr_idx);
- rxr_idx++;
- rxr_remaining--;
- }
- }
- for (i = v_start; i < q_vectors; i++) {
- tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - i);
- for (j = 0; j < tqpv; j++) {
- i40evf_map_vector_to_txq(adapter, i, txr_idx);
- txr_idx++;
- txr_remaining--;
- }
+ /* In the case where we have more queues than vectors, continue
+ * round-robin on vectors until all queues are mapped.
+ */
+ if (++vidx >= q_vectors)
+ vidx = 0;
}
-out:
adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS;
-
- return err;
}
#ifdef CONFIG_NET_POLL_CONTROLLER
@@ -1217,9 +1186,18 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter)
{
int i, num_active_queues;
- num_active_queues = min_t(int,
- adapter->vsi_res->num_queue_pairs,
- (int)(num_online_cpus()));
+ /* If we're in reset reallocating queues we don't actually know yet for
+ * certain the PF gave us the number of queues we asked for but we'll
+ * assume it did. Once basic reset is finished we'll confirm once we
+ * start negotiating config with PF.
+ */
+ if (adapter->num_req_queues)
+ num_active_queues = adapter->num_req_queues;
+ else
+ num_active_queues = min_t(int,
+ adapter->vsi_res->num_queue_pairs,
+ (int)(num_online_cpus()));
+
adapter->tx_rings = kcalloc(num_active_queues,
sizeof(struct i40e_ring), GFP_KERNEL);
@@ -1568,6 +1546,46 @@ static void i40evf_free_rss(struct i40evf_adapter *adapter)
}
/**
+ * i40evf_reinit_interrupt_scheme - Reallocate queues and vectors
+ * @adapter: board private structure
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int i40evf_reinit_interrupt_scheme(struct i40evf_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ int err;
+
+ if (netif_running(netdev))
+ i40evf_free_traffic_irqs(adapter);
+ i40evf_free_misc_irq(adapter);
+ i40evf_reset_interrupt_capability(adapter);
+ i40evf_free_q_vectors(adapter);
+ i40evf_free_queues(adapter);
+
+ err = i40evf_init_interrupt_scheme(adapter);
+ if (err)
+ goto err;
+
+ netif_tx_stop_all_queues(netdev);
+
+ err = i40evf_request_misc_irq(adapter);
+ if (err)
+ goto err;
+
+ set_bit(__I40E_VSI_DOWN, adapter->vsi.state);
+
+ i40evf_map_rings_to_vectors(adapter);
+
+ if (RSS_AQ(adapter))
+ adapter->aq_required |= I40EVF_FLAG_AQ_CONFIGURE_RSS;
+ else
+ err = i40evf_init_rss(adapter);
+err:
+ return err;
+}
+
+/**
* i40evf_watchdog_timer - Periodic call-back timer
* @data: pointer to adapter disguised as unsigned long
**/
@@ -1913,8 +1931,15 @@ continue_reset:
if (err)
dev_info(&adapter->pdev->dev, "Failed to init adminq: %d\n",
err);
+ adapter->aq_required = 0;
+
+ if (adapter->flags & I40EVF_FLAG_REINIT_ITR_NEEDED) {
+ err = i40evf_reinit_interrupt_scheme(adapter);
+ if (err)
+ goto reset_err;
+ }
- adapter->aq_required = I40EVF_FLAG_AQ_GET_CONFIG;
+ adapter->aq_required |= I40EVF_FLAG_AQ_GET_CONFIG;
adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS;
/* re-add all MAC filters */
@@ -1944,6 +1969,15 @@ continue_reset:
if (err)
goto reset_err;
+ if (adapter->flags & I40EVF_FLAG_REINIT_ITR_NEEDED) {
+ err = i40evf_request_traffic_irqs(adapter,
+ netdev->name);
+ if (err)
+ goto reset_err;
+
+ adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED;
+ }
+
i40evf_configure(adapter);
i40evf_up_complete(adapter);
@@ -2459,9 +2493,9 @@ static int i40evf_check_reset_complete(struct i40e_hw *hw)
int i40evf_process_config(struct i40evf_adapter *adapter)
{
struct virtchnl_vf_resource *vfres = adapter->vf_res;
+ int i, num_req_queues = adapter->num_req_queues;
struct net_device *netdev = adapter->netdev;
struct i40e_vsi *vsi = &adapter->vsi;
- int i;
netdev_features_t hw_enc_features;
netdev_features_t hw_features;
@@ -2475,6 +2509,23 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
return -ENODEV;
}
+ if (num_req_queues &&
+ num_req_queues != adapter->vsi_res->num_queue_pairs) {
+ /* Problem. The PF gave us fewer queues than what we had
+ * negotiated in our request. Need a reset to see if we can't
+ * get back to a working state.
+ */
+ dev_err(&adapter->pdev->dev,
+ "Requested %d queues, but PF only gave us %d.\n",
+ num_req_queues,
+ adapter->vsi_res->num_queue_pairs);
+ adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED;
+ adapter->num_req_queues = adapter->vsi_res->num_queue_pairs;
+ i40evf_schedule_reset(adapter);
+ return -ENODEV;
+ }
+ adapter->num_req_queues = 0;
+
hw_enc_features = NETIF_F_SG |
NETIF_F_IP_CSUM |
NETIF_F_IPV6_CSUM |
@@ -2686,9 +2737,8 @@ static void i40evf_init_task(struct work_struct *work)
ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr);
}
- init_timer(&adapter->watchdog_timer);
- adapter->watchdog_timer.function = &i40evf_watchdog_timer;
- adapter->watchdog_timer.data = (unsigned long)adapter;
+ setup_timer(&adapter->watchdog_timer, &i40evf_watchdog_timer,
+ (unsigned long)adapter);
mod_timer(&adapter->watchdog_timer, jiffies + 1);
adapter->tx_desc_count = I40EVF_DEFAULT_TXD;
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
index 85876f4fb1fb..2bb81c39d85f 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
@@ -52,7 +52,7 @@ static int i40evf_send_pf_msg(struct i40evf_adapter *adapter,
err = i40e_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL);
if (err)
- dev_err(&adapter->pdev->dev, "Unable to send opcode %d to PF, err %s, aq_err %s\n",
+ dev_dbg(&adapter->pdev->dev, "Unable to send opcode %d to PF, err %s, aq_err %s\n",
op, i40evf_stat_str(hw, err),
i40evf_aq_str(hw, hw->aq.asq_last_status));
return err;
@@ -160,7 +160,8 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter)
VIRTCHNL_VF_OFFLOAD_WB_ON_ITR |
VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 |
VIRTCHNL_VF_OFFLOAD_ENCAP |
- VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM;
+ VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM |
+ VIRTCHNL_VF_OFFLOAD_REQ_QUEUES;
adapter->current_op = VIRTCHNL_OP_GET_VF_RESOURCES;
adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_CONFIG;
@@ -385,6 +386,32 @@ void i40evf_map_queues(struct i40evf_adapter *adapter)
}
/**
+ * i40evf_request_queues
+ * @adapter: adapter structure
+ * @num: number of requested queues
+ *
+ * We get a default number of queues from the PF. This enables us to request a
+ * different number. Returns 0 on success, negative on failure
+ **/
+int i40evf_request_queues(struct i40evf_adapter *adapter, int num)
+{
+ struct virtchnl_vf_res_request vfres;
+
+ if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
+ /* bail because we already have a command pending */
+ dev_err(&adapter->pdev->dev, "Cannot request queues, command %d pending\n",
+ adapter->current_op);
+ return -EBUSY;
+ }
+
+ vfres.num_queue_pairs = num;
+
+ adapter->current_op = VIRTCHNL_OP_REQUEST_QUEUES;
+ return i40evf_send_pf_msg(adapter, VIRTCHNL_OP_REQUEST_QUEUES,
+ (u8 *)&vfres, sizeof(vfres));
+}
+
+/**
* i40evf_add_ether_addrs
* @adapter: adapter structure
* @addrs: the MAC address filters to add (contiguous)
@@ -1068,6 +1095,21 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
"Invalid message %d from PF\n", v_opcode);
}
break;
+ case VIRTCHNL_OP_REQUEST_QUEUES: {
+ struct virtchnl_vf_res_request *vfres =
+ (struct virtchnl_vf_res_request *)msg;
+ if (vfres->num_queue_pairs == adapter->num_req_queues) {
+ adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED;
+ i40evf_schedule_reset(adapter);
+ } else {
+ dev_info(&adapter->pdev->dev,
+ "Requested %d queues, PF can support %d\n",
+ adapter->num_req_queues,
+ vfres->num_queue_pairs);
+ adapter->num_req_queues = 0;
+ }
+ }
+ break;
default:
if (adapter->current_op && (v_opcode != adapter->current_op))
dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n",
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
index 5a713199653c..1e6ec2277d54 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
@@ -508,9 +508,8 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
adapter->part_num = ixgb_get_ee_pba_number(&adapter->hw);
- init_timer(&adapter->watchdog_timer);
- adapter->watchdog_timer.function = ixgb_watchdog;
- adapter->watchdog_timer.data = (unsigned long)adapter;
+ setup_timer(&adapter->watchdog_timer, ixgb_watchdog,
+ (unsigned long)adapter);
INIT_WORK(&adapter->tx_timeout_task, ixgb_tx_timeout_task);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index d962368d08d0..3942c6208745 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2133,6 +2133,21 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring,
#if L1_CACHE_BYTES < 128
prefetch(xdp->data + L1_CACHE_BYTES);
#endif
+ /* Note, we get here by enabling legacy-rx via:
+ *
+ * ethtool --set-priv-flags <dev> legacy-rx on
+ *
+ * In this mode, we currently get 0 extra XDP headroom as
+ * opposed to having legacy-rx off, where we process XDP
+ * packets going to stack via ixgbe_build_skb(). The latter
+ * provides us currently with 192 bytes of headroom.
+ *
+ * For ixgbe_construct_skb() mode it means that the
+ * xdp->data_meta will always point to xdp->data, since
+ * the helper cannot expand the head. Should this ever
+ * change in future for legacy-rx mode on, then lets also
+ * add xdp->data_meta handling here.
+ */
/* allocate a skb to store the frags */
skb = napi_alloc_skb(&rx_ring->q_vector->napi, IXGBE_RX_HDR_SIZE);
@@ -2165,6 +2180,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
struct xdp_buff *xdp,
union ixgbe_adv_rx_desc *rx_desc)
{
+ unsigned int metasize = xdp->data - xdp->data_meta;
#if (PAGE_SIZE < 8192)
unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
#else
@@ -2174,10 +2190,14 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
#endif
struct sk_buff *skb;
- /* prefetch first cache line of first page */
- prefetch(xdp->data);
+ /* Prefetch first cache line of first page. If xdp->data_meta
+ * is unused, this points extactly as xdp->data, otherwise we
+ * likely have a consumer accessing first few bytes of meta
+ * data, and then actual data.
+ */
+ prefetch(xdp->data_meta);
#if L1_CACHE_BYTES < 128
- prefetch(xdp->data + L1_CACHE_BYTES);
+ prefetch(xdp->data_meta + L1_CACHE_BYTES);
#endif
/* build an skb to around the page buffer */
@@ -2188,6 +2208,8 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
/* update pointers within the skb to store the data */
skb_reserve(skb, xdp->data - xdp->data_hard_start);
__skb_put(skb, xdp->data_end - xdp->data);
+ if (metasize)
+ skb_metadata_set(skb, metasize);
/* record DMA address if this is the start of a chain of buffers */
if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))
@@ -2326,6 +2348,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
if (!skb) {
xdp.data = page_address(rx_buffer->page) +
rx_buffer->page_offset;
+ xdp.data_meta = xdp.data;
xdp.data_hard_start = xdp.data -
ixgbe_rx_offset(rx_ring);
xdp.data_end = xdp.data + size;
diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c
index 3c0a6451273d..7cecd9dbc111 100644
--- a/drivers/net/ethernet/korina.c
+++ b/drivers/net/ethernet/korina.c
@@ -4,6 +4,7 @@
* Copyright 2004 IDT Inc. (rischelp@idt.com)
* Copyright 2006 Felix Fietkau <nbd@openwrt.org>
* Copyright 2008 Florian Fainelli <florian@openwrt.org>
+ * Copyright 2017 Roman Yeryomin <roman@advem.lv>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
@@ -64,9 +65,9 @@
#include <asm/mach-rc32434/eth.h>
#include <asm/mach-rc32434/dma_v.h>
-#define DRV_NAME "korina"
-#define DRV_VERSION "0.10"
-#define DRV_RELDATE "04Mar2008"
+#define DRV_NAME "korina"
+#define DRV_VERSION "0.20"
+#define DRV_RELDATE "15Sep2017"
#define STATION_ADDRESS_HIGH(dev) (((dev)->dev_addr[0] << 8) | \
((dev)->dev_addr[1]))
@@ -75,7 +76,7 @@
((dev)->dev_addr[4] << 8) | \
((dev)->dev_addr[5]))
-#define MII_CLOCK 1250000 /* no more than 2.5MHz */
+#define MII_CLOCK 1250000 /* no more than 2.5MHz */
/* the following must be powers of two */
#define KORINA_NUM_RDS 64 /* number of receive descriptors */
@@ -87,15 +88,19 @@
#define KORINA_RBSIZE 1536 /* size of one resource buffer = Ether MTU */
#define KORINA_RDS_MASK (KORINA_NUM_RDS - 1)
#define KORINA_TDS_MASK (KORINA_NUM_TDS - 1)
-#define RD_RING_SIZE (KORINA_NUM_RDS * sizeof(struct dma_desc))
+#define RD_RING_SIZE (KORINA_NUM_RDS * sizeof(struct dma_desc))
#define TD_RING_SIZE (KORINA_NUM_TDS * sizeof(struct dma_desc))
-#define TX_TIMEOUT (6000 * HZ / 1000)
+#define TX_TIMEOUT (6000 * HZ / 1000)
-enum chain_status { desc_filled, desc_empty };
-#define IS_DMA_FINISHED(X) (((X) & (DMA_DESC_FINI)) != 0)
-#define IS_DMA_DONE(X) (((X) & (DMA_DESC_DONE)) != 0)
-#define RCVPKT_LENGTH(X) (((X) & ETH_RX_LEN) >> ETH_RX_LEN_BIT)
+enum chain_status {
+ desc_filled,
+ desc_empty
+};
+
+#define IS_DMA_FINISHED(X) (((X) & (DMA_DESC_FINI)) != 0)
+#define IS_DMA_DONE(X) (((X) & (DMA_DESC_DONE)) != 0)
+#define RCVPKT_LENGTH(X) (((X) & ETH_RX_LEN) >> ETH_RX_LEN_BIT)
/* Information that need to be kept for each board. */
struct korina_private {
@@ -122,10 +127,8 @@ struct korina_private {
int rx_irq;
int tx_irq;
- int ovr_irq;
- int und_irq;
- spinlock_t lock; /* NIC xmit lock */
+ spinlock_t lock; /* NIC xmit lock */
int dma_halt_cnt;
int dma_run_cnt;
@@ -148,17 +151,17 @@ static inline void korina_start_dma(struct dma_reg *ch, u32 dma_addr)
static inline void korina_abort_dma(struct net_device *dev,
struct dma_reg *ch)
{
- if (readl(&ch->dmac) & DMA_CHAN_RUN_BIT) {
- writel(0x10, &ch->dmac);
+ if (readl(&ch->dmac) & DMA_CHAN_RUN_BIT) {
+ writel(0x10, &ch->dmac);
- while (!(readl(&ch->dmas) & DMA_STAT_HALT))
- netif_trans_update(dev);
+ while (!(readl(&ch->dmas) & DMA_STAT_HALT))
+ netif_trans_update(dev);
- writel(0, &ch->dmas);
- }
+ writel(0, &ch->dmas);
+ }
- writel(0, &ch->dmadptr);
- writel(0, &ch->dmandptr);
+ writel(0, &ch->dmadptr);
+ writel(0, &ch->dmandptr);
}
static inline void korina_chain_dma(struct dma_reg *ch, u32 dma_addr)
@@ -365,59 +368,60 @@ static int korina_rx(struct net_device *dev, int limit)
if ((KORINA_RBSIZE - (u32)DMA_COUNT(rd->control)) == 0)
break;
- /* Update statistics counters */
- if (devcs & ETH_RX_CRC)
- dev->stats.rx_crc_errors++;
- if (devcs & ETH_RX_LOR)
- dev->stats.rx_length_errors++;
- if (devcs & ETH_RX_LE)
- dev->stats.rx_length_errors++;
- if (devcs & ETH_RX_OVR)
- dev->stats.rx_fifo_errors++;
- if (devcs & ETH_RX_CV)
- dev->stats.rx_frame_errors++;
- if (devcs & ETH_RX_CES)
- dev->stats.rx_length_errors++;
- if (devcs & ETH_RX_MP)
- dev->stats.multicast++;
+ /* check that this is a whole packet
+ * WARNING: DMA_FD bit incorrectly set
+ * in Rc32434 (errata ref #077) */
+ if (!(devcs & ETH_RX_LD))
+ goto next;
- if ((devcs & ETH_RX_LD) != ETH_RX_LD) {
- /* check that this is a whole packet
- * WARNING: DMA_FD bit incorrectly set
- * in Rc32434 (errata ref #077) */
+ if (!(devcs & ETH_RX_ROK)) {
+ /* Update statistics counters */
dev->stats.rx_errors++;
dev->stats.rx_dropped++;
- } else if ((devcs & ETH_RX_ROK)) {
- pkt_len = RCVPKT_LENGTH(devcs);
+ if (devcs & ETH_RX_CRC)
+ dev->stats.rx_crc_errors++;
+ if (devcs & ETH_RX_LE)
+ dev->stats.rx_length_errors++;
+ if (devcs & ETH_RX_OVR)
+ dev->stats.rx_fifo_errors++;
+ if (devcs & ETH_RX_CV)
+ dev->stats.rx_frame_errors++;
+ if (devcs & ETH_RX_CES)
+ dev->stats.rx_frame_errors++;
+
+ goto next;
+ }
- /* must be the (first and) last
- * descriptor then */
- pkt_buf = (u8 *)lp->rx_skb[lp->rx_next_done]->data;
+ pkt_len = RCVPKT_LENGTH(devcs);
- /* invalidate the cache */
- dma_cache_inv((unsigned long)pkt_buf, pkt_len - 4);
+ /* must be the (first and) last
+ * descriptor then */
+ pkt_buf = (u8 *)lp->rx_skb[lp->rx_next_done]->data;
- /* Malloc up new buffer. */
- skb_new = netdev_alloc_skb_ip_align(dev, KORINA_RBSIZE);
+ /* invalidate the cache */
+ dma_cache_inv((unsigned long)pkt_buf, pkt_len - 4);
- if (!skb_new)
- break;
- /* Do not count the CRC */
- skb_put(skb, pkt_len - 4);
- skb->protocol = eth_type_trans(skb, dev);
+ /* Malloc up new buffer. */
+ skb_new = netdev_alloc_skb_ip_align(dev, KORINA_RBSIZE);
- /* Pass the packet to upper layers */
- netif_receive_skb(skb);
- dev->stats.rx_packets++;
- dev->stats.rx_bytes += pkt_len;
+ if (!skb_new)
+ break;
+ /* Do not count the CRC */
+ skb_put(skb, pkt_len - 4);
+ skb->protocol = eth_type_trans(skb, dev);
- /* Update the mcast stats */
- if (devcs & ETH_RX_MP)
- dev->stats.multicast++;
+ /* Pass the packet to upper layers */
+ napi_gro_receive(&lp->napi, skb);
+ dev->stats.rx_packets++;
+ dev->stats.rx_bytes += pkt_len;
- lp->rx_skb[lp->rx_next_done] = skb_new;
- }
+ /* Update the mcast stats */
+ if (devcs & ETH_RX_MP)
+ dev->stats.multicast++;
+
+ lp->rx_skb[lp->rx_next_done] = skb_new;
+next:
rd->devcs = 0;
/* Restore descriptor's curr_addr */
@@ -686,7 +690,7 @@ static int korina_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
/* ethtool helpers */
static void netdev_get_drvinfo(struct net_device *dev,
- struct ethtool_drvinfo *info)
+ struct ethtool_drvinfo *info)
{
struct korina_private *lp = netdev_priv(dev);
@@ -729,10 +733,10 @@ static u32 netdev_get_link(struct net_device *dev)
}
static const struct ethtool_ops netdev_ethtool_ops = {
- .get_drvinfo = netdev_get_drvinfo,
- .get_link = netdev_get_link,
- .get_link_ksettings = netdev_get_link_ksettings,
- .set_link_ksettings = netdev_set_link_ksettings,
+ .get_drvinfo = netdev_get_drvinfo,
+ .get_link = netdev_get_link,
+ .get_link_ksettings = netdev_get_link_ksettings,
+ .set_link_ksettings = netdev_set_link_ksettings,
};
static int korina_alloc_ring(struct net_device *dev)
@@ -864,7 +868,7 @@ static int korina_init(struct net_device *dev)
/* Management Clock Prescaler Divisor
* Clock independent setting */
writel(((idt_cpu_freq) / MII_CLOCK + 1) & ~1,
- &lp->eth_regs->ethmcp);
+ &lp->eth_regs->ethmcp);
/* don't transmit until fifo contains 48b */
writel(48, &lp->eth_regs->ethfifott);
@@ -891,8 +895,6 @@ static void korina_restart_task(struct work_struct *work)
*/
disable_irq(lp->rx_irq);
disable_irq(lp->tx_irq);
- disable_irq(lp->ovr_irq);
- disable_irq(lp->und_irq);
writel(readl(&lp->tx_dma_regs->dmasm) |
DMA_STAT_FINI | DMA_STAT_ERR,
@@ -911,40 +913,10 @@ static void korina_restart_task(struct work_struct *work)
}
korina_multicast_list(dev);
- enable_irq(lp->und_irq);
- enable_irq(lp->ovr_irq);
enable_irq(lp->tx_irq);
enable_irq(lp->rx_irq);
}
-static void korina_clear_and_restart(struct net_device *dev, u32 value)
-{
- struct korina_private *lp = netdev_priv(dev);
-
- netif_stop_queue(dev);
- writel(value, &lp->eth_regs->ethintfc);
- schedule_work(&lp->restart_task);
-}
-
-/* Ethernet Tx Underflow interrupt */
-static irqreturn_t korina_und_interrupt(int irq, void *dev_id)
-{
- struct net_device *dev = dev_id;
- struct korina_private *lp = netdev_priv(dev);
- unsigned int und;
-
- spin_lock(&lp->lock);
-
- und = readl(&lp->eth_regs->ethintfc);
-
- if (und & ETH_INT_FC_UND)
- korina_clear_and_restart(dev, und & ~ETH_INT_FC_UND);
-
- spin_unlock(&lp->lock);
-
- return IRQ_HANDLED;
-}
-
static void korina_tx_timeout(struct net_device *dev)
{
struct korina_private *lp = netdev_priv(dev);
@@ -952,25 +924,6 @@ static void korina_tx_timeout(struct net_device *dev)
schedule_work(&lp->restart_task);
}
-/* Ethernet Rx Overflow interrupt */
-static irqreturn_t
-korina_ovr_interrupt(int irq, void *dev_id)
-{
- struct net_device *dev = dev_id;
- struct korina_private *lp = netdev_priv(dev);
- unsigned int ovr;
-
- spin_lock(&lp->lock);
- ovr = readl(&lp->eth_regs->ethintfc);
-
- if (ovr & ETH_INT_FC_OVR)
- korina_clear_and_restart(dev, ovr & ~ETH_INT_FC_OVR);
-
- spin_unlock(&lp->lock);
-
- return IRQ_HANDLED;
-}
-
#ifdef CONFIG_NET_POLL_CONTROLLER
static void korina_poll_controller(struct net_device *dev)
{
@@ -993,48 +946,26 @@ static int korina_open(struct net_device *dev)
}
/* Install the interrupt handler
- * that handles the Done Finished
- * Ovr and Und Events */
+ * that handles the Done Finished */
ret = request_irq(lp->rx_irq, korina_rx_dma_interrupt,
0, "Korina ethernet Rx", dev);
if (ret < 0) {
printk(KERN_ERR "%s: unable to get Rx DMA IRQ %d\n",
- dev->name, lp->rx_irq);
+ dev->name, lp->rx_irq);
goto err_release;
}
ret = request_irq(lp->tx_irq, korina_tx_dma_interrupt,
0, "Korina ethernet Tx", dev);
if (ret < 0) {
printk(KERN_ERR "%s: unable to get Tx DMA IRQ %d\n",
- dev->name, lp->tx_irq);
+ dev->name, lp->tx_irq);
goto err_free_rx_irq;
}
- /* Install handler for overrun error. */
- ret = request_irq(lp->ovr_irq, korina_ovr_interrupt,
- 0, "Ethernet Overflow", dev);
- if (ret < 0) {
- printk(KERN_ERR "%s: unable to get OVR IRQ %d\n",
- dev->name, lp->ovr_irq);
- goto err_free_tx_irq;
- }
-
- /* Install handler for underflow error. */
- ret = request_irq(lp->und_irq, korina_und_interrupt,
- 0, "Ethernet Underflow", dev);
- if (ret < 0) {
- printk(KERN_ERR "%s: unable to get UND IRQ %d\n",
- dev->name, lp->und_irq);
- goto err_free_ovr_irq;
- }
mod_timer(&lp->media_check_timer, jiffies + 1);
out:
return ret;
-err_free_ovr_irq:
- free_irq(lp->ovr_irq, dev);
-err_free_tx_irq:
- free_irq(lp->tx_irq, dev);
err_free_rx_irq:
free_irq(lp->rx_irq, dev);
err_release:
@@ -1052,8 +983,6 @@ static int korina_close(struct net_device *dev)
/* Disable interrupts */
disable_irq(lp->rx_irq);
disable_irq(lp->tx_irq);
- disable_irq(lp->ovr_irq);
- disable_irq(lp->und_irq);
korina_abort_tx(dev);
tmp = readl(&lp->tx_dma_regs->dmasm);
@@ -1073,8 +1002,6 @@ static int korina_close(struct net_device *dev)
free_irq(lp->rx_irq, dev);
free_irq(lp->tx_irq, dev);
- free_irq(lp->ovr_irq, dev);
- free_irq(lp->und_irq, dev);
return 0;
}
@@ -1113,8 +1040,6 @@ static int korina_probe(struct platform_device *pdev)
lp->rx_irq = platform_get_irq_byname(pdev, "korina_rx");
lp->tx_irq = platform_get_irq_byname(pdev, "korina_tx");
- lp->ovr_irq = platform_get_irq_byname(pdev, "korina_ovr");
- lp->und_irq = platform_get_irq_byname(pdev, "korina_und");
r = platform_get_resource_byname(pdev, IORESOURCE_MEM, "korina_regs");
dev->base_addr = r->start;
@@ -1162,7 +1087,7 @@ static int korina_probe(struct platform_device *pdev)
dev->netdev_ops = &korina_netdev_ops;
dev->ethtool_ops = &netdev_ethtool_ops;
dev->watchdog_timeo = TX_TIMEOUT;
- netif_napi_add(dev, &lp->napi, korina_poll, 64);
+ netif_napi_add(dev, &lp->napi, korina_poll, NAPI_POLL_WEIGHT);
lp->phy_addr = (((lp->rx_irq == 0x2c? 1:0) << 8) | 0x05);
lp->mii_if.dev = dev;
@@ -1226,5 +1151,6 @@ module_platform_driver(korina_driver);
MODULE_AUTHOR("Philip Rischel <rischelp@idt.com>");
MODULE_AUTHOR("Felix Fietkau <nbd@openwrt.org>");
MODULE_AUTHOR("Florian Fainelli <florian@openwrt.org>");
+MODULE_AUTHOR("Roman Yeryomin <roman@advem.lv>");
MODULE_DESCRIPTION("IDT RC32434 (Korina) Ethernet driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index 9c86cb7cb988..97efe4733661 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -6460,7 +6460,6 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev)
if (mvpp2_tx_frag_process(port, skb, aggr_txq, txq)) {
tx_desc_unmap_put(port, txq, tx_desc);
frags = 0;
- goto out;
}
}
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index 993724959a7c..91b1c154fd29 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1496,9 +1496,8 @@ static int pxa168_eth_probe(struct platform_device *pdev)
netif_napi_add(dev, &pep->napi, pxa168_rx_poll, pep->rx_ring_size);
memset(&pep->timeout, 0, sizeof(struct timer_list));
- init_timer(&pep->timeout);
- pep->timeout.function = rxq_refill_timer_wrapper;
- pep->timeout.data = (unsigned long)pep;
+ setup_timer(&pep->timeout, rxq_refill_timer_wrapper,
+ (unsigned long)pep);
pep->smi_bus = mdiobus_alloc();
if (!pep->smi_bus) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 53daa6ca5d83..de0f9e5e42ec 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -277,7 +277,7 @@ void mlx4_start_catas_poll(struct mlx4_dev *dev)
phys_addr_t addr;
INIT_LIST_HEAD(&priv->catas_err.list);
- init_timer(&priv->catas_err.timer);
+ setup_timer(&priv->catas_err.timer, poll_catas, (unsigned long)dev);
priv->catas_err.map = NULL;
if (!mlx4_is_slave(dev)) {
@@ -293,8 +293,6 @@ void mlx4_start_catas_poll(struct mlx4_dev *dev)
}
}
- priv->catas_err.timer.data = (unsigned long) dev;
- priv->catas_err.timer.function = poll_catas;
priv->catas_err.timer.expires =
round_jiffies(jiffies + MLX4_CATAS_POLL_INTERVAL);
add_timer(&priv->catas_err.timer);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index b97a55c827eb..8f9cb8abc497 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -762,6 +762,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
xdp.data_hard_start = va - frags[0].page_offset;
xdp.data = va;
+ xdp_set_data_meta_invalid(&xdp);
xdp.data_end = xdp.data + length;
orig_data = xdp.data;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index 4614ddfa91eb..6a7c8b04447e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -256,7 +256,7 @@ struct sk_buff *mlx5e_ipsec_handle_tx_skb(struct net_device *netdev,
goto drop;
}
mdata = mlx5e_ipsec_add_metadata(skb);
- if (unlikely(IS_ERR(mdata))) {
+ if (IS_ERR(mdata)) {
atomic64_inc(&priv->ipsec->sw_stats.ipsec_tx_drop_metadata);
goto drop;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 15a1687483cc..bc654aeae5d4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -797,6 +797,7 @@ static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq,
return false;
xdp.data = va + *rx_headroom;
+ xdp_set_data_meta_invalid(&xdp);
xdp.data_end = xdp.data + *len;
xdp.data_hard_start = va;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 8aea0a065e56..a89a68ce53ad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -320,15 +320,13 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev)
{
struct mlx5_core_health *health = &dev->priv.health;
- init_timer(&health->timer);
+ setup_timer(&health->timer, poll_health, (unsigned long)dev);
health->sick = 0;
clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
clear_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
health->health = &dev->iseg->health;
health->health_counter = &dev->iseg->health_counter;
- health->timer.data = (unsigned long)dev;
- health->timer.function = poll_health;
health->timer.expires = round_jiffies(jiffies + MLX5_HEALTH_POLL_INTERVAL);
add_timer(&health->timer);
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 891ff418bb5e..4816504419fc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -17,7 +17,8 @@ mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \
spectrum_kvdl.o spectrum_acl_tcam.o \
spectrum_acl.o spectrum_flower.o \
spectrum_cnt.o spectrum_fid.o \
- spectrum_ipip.o
+ spectrum_ipip.o spectrum_acl_flex_actions.o \
+ spectrum_mr.o spectrum_mr_tcam.o
mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB) += spectrum_dcb.o
mlxsw_spectrum-$(CONFIG_NET_DEVLINK) += spectrum_dpipe.o
obj-$(CONFIG_MLXSW_MINIMAL) += mlxsw_minimal.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index 5ae110172c22..6a979a09ab72 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -399,23 +399,25 @@ u32 mlxsw_afa_block_first_set_kvdl_index(struct mlxsw_afa_block *block)
}
EXPORT_SYMBOL(mlxsw_afa_block_first_set_kvdl_index);
-void mlxsw_afa_block_continue(struct mlxsw_afa_block *block)
+int mlxsw_afa_block_continue(struct mlxsw_afa_block *block)
{
- if (WARN_ON(block->finished))
- return;
+ if (block->finished)
+ return -EINVAL;
mlxsw_afa_set_goto_set(block->cur_set,
MLXSW_AFA_SET_GOTO_BINDING_CMD_NONE, 0);
block->finished = true;
+ return 0;
}
EXPORT_SYMBOL(mlxsw_afa_block_continue);
-void mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id)
+int mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id)
{
- if (WARN_ON(block->finished))
- return;
+ if (block->finished)
+ return -EINVAL;
mlxsw_afa_set_goto_set(block->cur_set,
MLXSW_AFA_SET_GOTO_BINDING_CMD_JUMP, group_id);
block->finished = true;
+ return 0;
}
EXPORT_SYMBOL(mlxsw_afa_block_jump);
@@ -674,6 +676,7 @@ enum mlxsw_afa_trapdisc_trap_action {
MLXSW_ITEM32(afa, trapdisc, trap_action, 0x00, 24, 4);
enum mlxsw_afa_trapdisc_forward_action {
+ MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD = 1,
MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD = 3,
};
@@ -712,7 +715,7 @@ int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block)
}
EXPORT_SYMBOL(mlxsw_afa_block_append_drop);
-int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block)
+int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id)
{
char *act = mlxsw_afa_block_append_action(block,
MLXSW_AFA_TRAPDISC_CODE,
@@ -722,11 +725,27 @@ int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block)
return -ENOBUFS;
mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP,
MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD,
- MLXSW_TRAP_ID_ACL0);
+ trap_id);
return 0;
}
EXPORT_SYMBOL(mlxsw_afa_block_append_trap);
+int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block,
+ u16 trap_id)
+{
+ char *act = mlxsw_afa_block_append_action(block,
+ MLXSW_AFA_TRAPDISC_CODE,
+ MLXSW_AFA_TRAPDISC_SIZE);
+
+ if (!act)
+ return -ENOBUFS;
+ mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP,
+ MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD,
+ trap_id);
+ return 0;
+}
+EXPORT_SYMBOL(mlxsw_afa_block_append_trap_and_forward);
+
/* Forwarding Action
* -----------------
* Forwarding Action can be used to implement Policy Based Switching (PBS)
@@ -891,3 +910,74 @@ int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid)
return 0;
}
EXPORT_SYMBOL(mlxsw_afa_block_append_fid_set);
+
+/* MC Routing Action
+ * -----------------
+ * The Multicast router action. Can be used by RMFT_V2 - Router Multicast
+ * Forwarding Table Version 2 Register.
+ */
+
+#define MLXSW_AFA_MCROUTER_CODE 0x10
+#define MLXSW_AFA_MCROUTER_SIZE 2
+
+enum mlxsw_afa_mcrouter_rpf_action {
+ MLXSW_AFA_MCROUTER_RPF_ACTION_NOP,
+ MLXSW_AFA_MCROUTER_RPF_ACTION_TRAP,
+ MLXSW_AFA_MCROUTER_RPF_ACTION_DISCARD_ERROR,
+};
+
+/* afa_mcrouter_rpf_action */
+MLXSW_ITEM32(afa, mcrouter, rpf_action, 0x00, 28, 3);
+
+/* afa_mcrouter_expected_irif */
+MLXSW_ITEM32(afa, mcrouter, expected_irif, 0x00, 0, 16);
+
+/* afa_mcrouter_min_mtu */
+MLXSW_ITEM32(afa, mcrouter, min_mtu, 0x08, 0, 16);
+
+enum mlxsw_afa_mrouter_vrmid {
+ MLXSW_AFA_MCROUTER_VRMID_INVALID,
+ MLXSW_AFA_MCROUTER_VRMID_VALID
+};
+
+/* afa_mcrouter_vrmid
+ * Valid RMID: rigr_rmid_index is used as RMID
+ */
+MLXSW_ITEM32(afa, mcrouter, vrmid, 0x0C, 31, 1);
+
+/* afa_mcrouter_rigr_rmid_index
+ * When the vrmid field is set to invalid, the field is used as pointer to
+ * Router Interface Group (RIGR) Table in the KVD linear.
+ * When the vrmid is set to valid, the field is used as RMID index, ranged
+ * from 0 to max_mid - 1. The index is to the Port Group Table.
+ */
+MLXSW_ITEM32(afa, mcrouter, rigr_rmid_index, 0x0C, 0, 24);
+
+static inline void
+mlxsw_afa_mcrouter_pack(char *payload,
+ enum mlxsw_afa_mcrouter_rpf_action rpf_action,
+ u16 expected_irif, u16 min_mtu,
+ enum mlxsw_afa_mrouter_vrmid vrmid, u32 rigr_rmid_index)
+
+{
+ mlxsw_afa_mcrouter_rpf_action_set(payload, rpf_action);
+ mlxsw_afa_mcrouter_expected_irif_set(payload, expected_irif);
+ mlxsw_afa_mcrouter_min_mtu_set(payload, min_mtu);
+ mlxsw_afa_mcrouter_vrmid_set(payload, vrmid);
+ mlxsw_afa_mcrouter_rigr_rmid_index_set(payload, rigr_rmid_index);
+}
+
+int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block,
+ u16 expected_irif, u16 min_mtu,
+ bool rmid_valid, u32 kvdl_index)
+{
+ char *act = mlxsw_afa_block_append_action(block,
+ MLXSW_AFA_MCROUTER_CODE,
+ MLXSW_AFA_MCROUTER_SIZE);
+ if (!act)
+ return -ENOBUFS;
+ mlxsw_afa_mcrouter_pack(act, MLXSW_AFA_MCROUTER_RPF_ACTION_TRAP,
+ expected_irif, min_mtu, rmid_valid, kvdl_index);
+ return 0;
+}
+EXPORT_SYMBOL(mlxsw_afa_block_append_mcrouter);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
index f99c341b2497..a8d3314c3a24 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
@@ -57,10 +57,12 @@ void mlxsw_afa_block_destroy(struct mlxsw_afa_block *block);
int mlxsw_afa_block_commit(struct mlxsw_afa_block *block);
char *mlxsw_afa_block_first_set(struct mlxsw_afa_block *block);
u32 mlxsw_afa_block_first_set_kvdl_index(struct mlxsw_afa_block *block);
-void mlxsw_afa_block_continue(struct mlxsw_afa_block *block);
-void mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id);
+int mlxsw_afa_block_continue(struct mlxsw_afa_block *block);
+int mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id);
int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block);
-int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block);
+int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id);
+int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block,
+ u16 trap_id);
int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block,
u8 local_port, bool in_port);
int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
@@ -68,5 +70,8 @@ int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block,
u32 counter_index);
int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid);
+int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block,
+ u16 expected_irif, u16 min_mtu,
+ bool rmid_valid, u32 kvdl_index);
#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index cc27c5de5a1d..d44e673a4c4e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2142,15 +2142,14 @@ MLXSW_REG_DEFINE(pefa, MLXSW_REG_PEFA_ID, MLXSW_REG_PEFA_LEN);
*/
MLXSW_ITEM32(reg, pefa, index, 0x00, 0, 24);
-#define MLXSW_REG_PXXX_FLEX_ACTION_SET_LEN 0xA8
+#define MLXSW_REG_FLEX_ACTION_SET_LEN 0xA8
/* reg_pefa_flex_action_set
* Action-set to perform when rule is matched.
* Must be zero padded if action set is shorter.
* Access: RW
*/
-MLXSW_ITEM_BUF(reg, pefa, flex_action_set, 0x08,
- MLXSW_REG_PXXX_FLEX_ACTION_SET_LEN);
+MLXSW_ITEM_BUF(reg, pefa, flex_action_set, 0x08, MLXSW_REG_FLEX_ACTION_SET_LEN);
static inline void mlxsw_reg_pefa_pack(char *payload, u32 index,
const char *flex_action_set)
@@ -2243,7 +2242,7 @@ MLXSW_ITEM_BUF(reg, ptce2, mask, 0x80,
* Access: RW
*/
MLXSW_ITEM_BUF(reg, ptce2, flex_action_set, 0xE0,
- MLXSW_REG_PXXX_FLEX_ACTION_SET_LEN);
+ MLXSW_REG_FLEX_ACTION_SET_LEN);
static inline void mlxsw_reg_ptce2_pack(char *payload, bool valid,
enum mlxsw_reg_ptce2_op op,
@@ -3682,12 +3681,15 @@ enum mlxsw_reg_htgt_trap_group {
MLXSW_REG_HTGT_TRAP_GROUP_SP_IGMP,
MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP,
MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF,
+ MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM,
+ MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST,
MLXSW_REG_HTGT_TRAP_GROUP_SP_ARP,
MLXSW_REG_HTGT_TRAP_GROUP_SP_HOST_MISS,
MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP,
MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE,
MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME,
MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP,
+ MLXSW_REG_HTGT_TRAP_GROUP_SP_RPF,
MLXSW_REG_HTGT_TRAP_GROUP_SP_EVENT,
MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_MLD,
MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND,
@@ -3992,6 +3994,12 @@ MLXSW_ITEM32(reg, ritr, ipv4, 0x00, 29, 1);
*/
MLXSW_ITEM32(reg, ritr, ipv6, 0x00, 28, 1);
+/* reg_ritr_ipv4_mc
+ * IPv4 multicast routing enable.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, ipv4_mc, 0x00, 27, 1);
+
enum mlxsw_reg_ritr_if_type {
/* VLAN interface. */
MLXSW_REG_RITR_VLAN_IF,
@@ -4049,6 +4057,14 @@ MLXSW_ITEM32(reg, ritr, ipv4_fe, 0x04, 29, 1);
*/
MLXSW_ITEM32(reg, ritr, ipv6_fe, 0x04, 28, 1);
+/* reg_ritr_ipv4_mc_fe
+ * IPv4 Multicast Forwarding Enable.
+ * When disabled, forwarding is blocked but local traffic (traps and IP to me)
+ * will be enabled.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, ipv4_mc_fe, 0x04, 27, 1);
+
/* reg_ritr_lb_en
* Loop-back filter enable for unicast packets.
* If the flag is set then loop-back filter for unicast packets is
@@ -4271,11 +4287,13 @@ static inline void mlxsw_reg_ritr_pack(char *payload, bool enable,
mlxsw_reg_ritr_enable_set(payload, enable);
mlxsw_reg_ritr_ipv4_set(payload, 1);
mlxsw_reg_ritr_ipv6_set(payload, 1);
+ mlxsw_reg_ritr_ipv4_mc_set(payload, 1);
mlxsw_reg_ritr_type_set(payload, type);
mlxsw_reg_ritr_op_set(payload, op);
mlxsw_reg_ritr_rif_set(payload, rif);
mlxsw_reg_ritr_ipv4_fe_set(payload, 1);
mlxsw_reg_ritr_ipv6_fe_set(payload, 1);
+ mlxsw_reg_ritr_ipv4_mc_fe_set(payload, 1);
mlxsw_reg_ritr_lb_en_set(payload, 1);
mlxsw_reg_ritr_virtual_router_set(payload, vr_id);
mlxsw_reg_ritr_mtu_set(payload, mtu);
@@ -4311,6 +4329,57 @@ mlxsw_reg_ritr_loopback_ipip4_pack(char *payload,
mlxsw_reg_ritr_loopback_ipip_usip4_set(payload, usip);
}
+/* RTAR - Router TCAM Allocation Register
+ * --------------------------------------
+ * This register is used for allocation of regions in the TCAM table.
+ */
+#define MLXSW_REG_RTAR_ID 0x8004
+#define MLXSW_REG_RTAR_LEN 0x20
+
+MLXSW_REG_DEFINE(rtar, MLXSW_REG_RTAR_ID, MLXSW_REG_RTAR_LEN);
+
+enum mlxsw_reg_rtar_op {
+ MLXSW_REG_RTAR_OP_ALLOCATE,
+ MLXSW_REG_RTAR_OP_RESIZE,
+ MLXSW_REG_RTAR_OP_DEALLOCATE,
+};
+
+/* reg_rtar_op
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, rtar, op, 0x00, 28, 4);
+
+enum mlxsw_reg_rtar_key_type {
+ MLXSW_REG_RTAR_KEY_TYPE_IPV4_MULTICAST = 1,
+ MLXSW_REG_RTAR_KEY_TYPE_IPV6_MULTICAST = 3
+};
+
+/* reg_rtar_key_type
+ * TCAM key type for the region.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, rtar, key_type, 0x00, 0, 8);
+
+/* reg_rtar_region_size
+ * TCAM region size. When allocating/resizing this is the requested
+ * size, the response is the actual size.
+ * Note: Actual size may be larger than requested.
+ * Reserved for op = Deallocate
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, rtar, region_size, 0x04, 0, 16);
+
+static inline void mlxsw_reg_rtar_pack(char *payload,
+ enum mlxsw_reg_rtar_op op,
+ enum mlxsw_reg_rtar_key_type key_type,
+ u16 region_size)
+{
+ MLXSW_REG_ZERO(rtar, payload);
+ mlxsw_reg_rtar_op_set(payload, op);
+ mlxsw_reg_rtar_key_type_set(payload, key_type);
+ mlxsw_reg_rtar_region_size_set(payload, region_size);
+}
+
/* RATR - Router Adjacency Table Register
* --------------------------------------
* The RATR register is used to configure the Router Adjacency (next-hop)
@@ -4480,6 +4549,27 @@ MLXSW_ITEM32(reg, ratr, ipip_ipv4_udip, 0x18, 0, 32);
*/
MLXSW_ITEM32(reg, ratr, ipip_ipv6_ptr, 0x1C, 0, 24);
+enum mlxsw_reg_flow_counter_set_type {
+ /* No count */
+ MLXSW_REG_FLOW_COUNTER_SET_TYPE_NO_COUNT = 0x00,
+ /* Count packets and bytes */
+ MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03,
+ /* Count only packets */
+ MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS = 0x05,
+};
+
+/* reg_ratr_counter_set_type
+ * Counter set type for flow counters
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ratr, counter_set_type, 0x28, 24, 8);
+
+/* reg_ratr_counter_index
+ * Counter index for flow counters
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ratr, counter_index, 0x28, 0, 24);
+
static inline void
mlxsw_reg_ratr_pack(char *payload,
enum mlxsw_reg_ratr_op op, bool valid,
@@ -4507,6 +4597,20 @@ static inline void mlxsw_reg_ratr_ipip4_entry_pack(char *payload, u32 ipv4_udip)
mlxsw_reg_ratr_ipip_ipv4_udip_set(payload, ipv4_udip);
}
+static inline void mlxsw_reg_ratr_counter_pack(char *payload, u64 counter_index,
+ bool counter_enable)
+{
+ enum mlxsw_reg_flow_counter_set_type set_type;
+
+ if (counter_enable)
+ set_type = MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES;
+ else
+ set_type = MLXSW_REG_FLOW_COUNTER_SET_TYPE_NO_COUNT;
+
+ mlxsw_reg_ratr_counter_index_set(payload, counter_index);
+ mlxsw_reg_ratr_counter_set_type_set(payload, set_type);
+}
+
/* RICNT - Router Interface Counter Register
* -----------------------------------------
* The RICNT register retrieves per port performance counters
@@ -4630,6 +4734,65 @@ static inline void mlxsw_reg_ricnt_pack(char *payload, u32 index,
MLXSW_REG_RICNT_COUNTER_SET_TYPE_BASIC);
}
+/* RRCR - Router Rules Copy Register Layout
+ * ----------------------------------------
+ * This register is used for moving and copying route entry rules.
+ */
+#define MLXSW_REG_RRCR_ID 0x800F
+#define MLXSW_REG_RRCR_LEN 0x24
+
+MLXSW_REG_DEFINE(rrcr, MLXSW_REG_RRCR_ID, MLXSW_REG_RRCR_LEN);
+
+enum mlxsw_reg_rrcr_op {
+ /* Move rules */
+ MLXSW_REG_RRCR_OP_MOVE,
+ /* Copy rules */
+ MLXSW_REG_RRCR_OP_COPY,
+};
+
+/* reg_rrcr_op
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, rrcr, op, 0x00, 28, 4);
+
+/* reg_rrcr_offset
+ * Offset within the region from which to copy/move.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rrcr, offset, 0x00, 0, 16);
+
+/* reg_rrcr_size
+ * The number of rules to copy/move.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, rrcr, size, 0x04, 0, 16);
+
+/* reg_rrcr_table_id
+ * Identifier of the table on which to perform the operation. Encoding is the
+ * same as in RTAR.key_type
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rrcr, table_id, 0x10, 0, 4);
+
+/* reg_rrcr_dest_offset
+ * Offset within the region to which to copy/move
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rrcr, dest_offset, 0x20, 0, 16);
+
+static inline void mlxsw_reg_rrcr_pack(char *payload, enum mlxsw_reg_rrcr_op op,
+ u16 offset, u16 size,
+ enum mlxsw_reg_rtar_key_type table_id,
+ u16 dest_offset)
+{
+ MLXSW_REG_ZERO(rrcr, payload);
+ mlxsw_reg_rrcr_op_set(payload, op);
+ mlxsw_reg_rrcr_offset_set(payload, offset);
+ mlxsw_reg_rrcr_size_set(payload, size);
+ mlxsw_reg_rrcr_table_id_set(payload, table_id);
+ mlxsw_reg_rrcr_dest_offset_set(payload, dest_offset);
+}
+
/* RALTA - Router Algorithmic LPM Tree Allocation Register
* -------------------------------------------------------
* RALTA is used to allocate the LPM trees of the SHSPM method.
@@ -5169,15 +5332,6 @@ enum mlxsw_reg_rauht_trap_id {
*/
MLXSW_ITEM32(reg, rauht, trap_id, 0x60, 0, 9);
-enum mlxsw_reg_flow_counter_set_type {
- /* No count */
- MLXSW_REG_FLOW_COUNTER_SET_TYPE_NO_COUNT = 0x00,
- /* Count packets and bytes */
- MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03,
- /* Count only packets */
- MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS = 0x05,
-};
-
/* reg_rauht_counter_set_type
* Counter set type for flow counters
* Access: RW
@@ -5596,6 +5750,229 @@ mlxsw_reg_rtdp_ipip4_pack(char *payload, u16 irif,
mlxsw_reg_rtdp_ipip_expected_gre_key_set(payload, expected_gre_key);
}
+/* RIGR-V2 - Router Interface Group Register Version 2
+ * ---------------------------------------------------
+ * The RIGR_V2 register is used to add, remove and query egress interface list
+ * of a multicast forwarding entry.
+ */
+#define MLXSW_REG_RIGR2_ID 0x8023
+#define MLXSW_REG_RIGR2_LEN 0xB0
+
+#define MLXSW_REG_RIGR2_MAX_ERIFS 32
+
+MLXSW_REG_DEFINE(rigr2, MLXSW_REG_RIGR2_ID, MLXSW_REG_RIGR2_LEN);
+
+/* reg_rigr2_rigr_index
+ * KVD Linear index.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rigr2, rigr_index, 0x04, 0, 24);
+
+/* reg_rigr2_vnext
+ * Next RIGR Index is valid.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rigr2, vnext, 0x08, 31, 1);
+
+/* reg_rigr2_next_rigr_index
+ * Next RIGR Index. The index is to the KVD linear.
+ * Reserved when vnxet = '0'.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rigr2, next_rigr_index, 0x08, 0, 24);
+
+/* reg_rigr2_vrmid
+ * RMID Index is valid.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rigr2, vrmid, 0x20, 31, 1);
+
+/* reg_rigr2_rmid_index
+ * RMID Index.
+ * Range 0 .. max_mid - 1
+ * Reserved when vrmid = '0'.
+ * The index is to the Port Group Table (PGT)
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rigr2, rmid_index, 0x20, 0, 16);
+
+/* reg_rigr2_erif_entry_v
+ * Egress Router Interface is valid.
+ * Note that low-entries must be set if high-entries are set. For
+ * example: if erif_entry[2].v is set then erif_entry[1].v and
+ * erif_entry[0].v must be set.
+ * Index can be from 0 to cap_mc_erif_list_entries-1
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, rigr2, erif_entry_v, 0x24, 31, 1, 4, 0, false);
+
+/* reg_rigr2_erif_entry_erif
+ * Egress Router Interface.
+ * Valid range is from 0 to cap_max_router_interfaces - 1
+ * Index can be from 0 to MLXSW_REG_RIGR2_MAX_ERIFS - 1
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, rigr2, erif_entry_erif, 0x24, 0, 16, 4, 0, false);
+
+static inline void mlxsw_reg_rigr2_pack(char *payload, u32 rigr_index,
+ bool vnext, u32 next_rigr_index)
+{
+ MLXSW_REG_ZERO(rigr2, payload);
+ mlxsw_reg_rigr2_rigr_index_set(payload, rigr_index);
+ mlxsw_reg_rigr2_vnext_set(payload, vnext);
+ mlxsw_reg_rigr2_next_rigr_index_set(payload, next_rigr_index);
+ mlxsw_reg_rigr2_vrmid_set(payload, 0);
+ mlxsw_reg_rigr2_rmid_index_set(payload, 0);
+}
+
+static inline void mlxsw_reg_rigr2_erif_entry_pack(char *payload, int index,
+ bool v, u16 erif)
+{
+ mlxsw_reg_rigr2_erif_entry_v_set(payload, index, v);
+ mlxsw_reg_rigr2_erif_entry_erif_set(payload, index, erif);
+}
+
+/* RMFT-V2 - Router Multicast Forwarding Table Version 2 Register
+ * --------------------------------------------------------------
+ * The RMFT_V2 register is used to configure and query the multicast table.
+ */
+#define MLXSW_REG_RMFT2_ID 0x8027
+#define MLXSW_REG_RMFT2_LEN 0x174
+
+MLXSW_REG_DEFINE(rmft2, MLXSW_REG_RMFT2_ID, MLXSW_REG_RMFT2_LEN);
+
+/* reg_rmft2_v
+ * Valid
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rmft2, v, 0x00, 31, 1);
+
+enum mlxsw_reg_rmft2_type {
+ MLXSW_REG_RMFT2_TYPE_IPV4,
+ MLXSW_REG_RMFT2_TYPE_IPV6
+};
+
+/* reg_rmft2_type
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rmft2, type, 0x00, 28, 2);
+
+enum mlxsw_sp_reg_rmft2_op {
+ /* For Write:
+ * Write operation. Used to write a new entry to the table. All RW
+ * fields are relevant for new entry. Activity bit is set for new
+ * entries - Note write with v (Valid) 0 will delete the entry.
+ * For Query:
+ * Read operation
+ */
+ MLXSW_REG_RMFT2_OP_READ_WRITE,
+};
+
+/* reg_rmft2_op
+ * Operation.
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, rmft2, op, 0x00, 20, 2);
+
+/* reg_rmft2_a
+ * Activity. Set for new entries. Set if a packet lookup has hit on the specific
+ * entry.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, rmft2, a, 0x00, 16, 1);
+
+/* reg_rmft2_offset
+ * Offset within the multicast forwarding table to write to.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rmft2, offset, 0x00, 0, 16);
+
+/* reg_rmft2_virtual_router
+ * Virtual Router ID. Range from 0..cap_max_virtual_routers-1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rmft2, virtual_router, 0x04, 0, 16);
+
+enum mlxsw_reg_rmft2_irif_mask {
+ MLXSW_REG_RMFT2_IRIF_MASK_IGNORE,
+ MLXSW_REG_RMFT2_IRIF_MASK_COMPARE
+};
+
+/* reg_rmft2_irif_mask
+ * Ingress RIF mask.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rmft2, irif_mask, 0x08, 24, 1);
+
+/* reg_rmft2_irif
+ * Ingress RIF index.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rmft2, irif, 0x08, 0, 16);
+
+/* reg_rmft2_dip4
+ * Destination IPv4 address
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rmft2, dip4, 0x1C, 0, 32);
+
+/* reg_rmft2_dip4_mask
+ * A bit that is set directs the TCAM to compare the corresponding bit in key. A
+ * bit that is clear directs the TCAM to ignore the corresponding bit in key.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rmft2, dip4_mask, 0x2C, 0, 32);
+
+/* reg_rmft2_sip4
+ * Source IPv4 address
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rmft2, sip4, 0x3C, 0, 32);
+
+/* reg_rmft2_sip4_mask
+ * A bit that is set directs the TCAM to compare the corresponding bit in key. A
+ * bit that is clear directs the TCAM to ignore the corresponding bit in key.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rmft2, sip4_mask, 0x4C, 0, 32);
+
+/* reg_rmft2_flexible_action_set
+ * ACL action set. The only supported action types in this field and in any
+ * action-set pointed from here are as follows:
+ * 00h: ACTION_NULL
+ * 01h: ACTION_MAC_TTL, only TTL configuration is supported.
+ * 03h: ACTION_TRAP
+ * 06h: ACTION_QOS
+ * 08h: ACTION_POLICING_MONITORING
+ * 10h: ACTION_ROUTER_MC
+ * Access: RW
+ */
+MLXSW_ITEM_BUF(reg, rmft2, flexible_action_set, 0x80,
+ MLXSW_REG_FLEX_ACTION_SET_LEN);
+
+static inline void
+mlxsw_reg_rmft2_ipv4_pack(char *payload, bool v, u16 offset, u16 virtual_router,
+ enum mlxsw_reg_rmft2_irif_mask irif_mask, u16 irif,
+ u32 dip4, u32 dip4_mask, u32 sip4, u32 sip4_mask,
+ const char *flexible_action_set)
+{
+ MLXSW_REG_ZERO(rmft2, payload);
+ mlxsw_reg_rmft2_v_set(payload, v);
+ mlxsw_reg_rmft2_type_set(payload, MLXSW_REG_RMFT2_TYPE_IPV4);
+ mlxsw_reg_rmft2_op_set(payload, MLXSW_REG_RMFT2_OP_READ_WRITE);
+ mlxsw_reg_rmft2_offset_set(payload, offset);
+ mlxsw_reg_rmft2_virtual_router_set(payload, virtual_router);
+ mlxsw_reg_rmft2_irif_mask_set(payload, irif_mask);
+ mlxsw_reg_rmft2_irif_set(payload, irif);
+ mlxsw_reg_rmft2_dip4_set(payload, dip4);
+ mlxsw_reg_rmft2_dip4_mask_set(payload, dip4_mask);
+ mlxsw_reg_rmft2_sip4_set(payload, sip4);
+ mlxsw_reg_rmft2_sip4_mask_set(payload, sip4_mask);
+ if (flexible_action_set)
+ mlxsw_reg_rmft2_flexible_action_set_memcpy_to(payload,
+ flexible_action_set);
+}
+
/* MFCR - Management Fan Control Register
* --------------------------------------
* This register controls the settings of the Fan Speed PWM mechanism.
@@ -6856,9 +7233,11 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
MLXSW_REG(hpkt),
MLXSW_REG(rgcr),
MLXSW_REG(ritr),
+ MLXSW_REG(rtar),
MLXSW_REG(ratr),
MLXSW_REG(rtdp),
MLXSW_REG(ricnt),
+ MLXSW_REG(rrcr),
MLXSW_REG(ralta),
MLXSW_REG(ralst),
MLXSW_REG(raltb),
@@ -6866,6 +7245,8 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
MLXSW_REG(rauht),
MLXSW_REG(raleu),
MLXSW_REG(rauhtd),
+ MLXSW_REG(rigr2),
+ MLXSW_REG(rmft2),
MLXSW_REG(mfcr),
MLXSW_REG(mfsc),
MLXSW_REG(mfsm),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h
index 9556d934714b..087aad52c195 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/resources.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h
@@ -63,6 +63,7 @@ enum mlxsw_res_id {
MLXSW_RES_ID_MAX_CPU_POLICERS,
MLXSW_RES_ID_MAX_VRS,
MLXSW_RES_ID_MAX_RIFS,
+ MLXSW_RES_ID_MC_ERIF_LIST_ENTRIES,
MLXSW_RES_ID_MAX_LPM_TREES,
/* Internal resources.
@@ -100,6 +101,7 @@ static u16 mlxsw_res_ids[] = {
[MLXSW_RES_ID_MAX_CPU_POLICERS] = 0x2A13,
[MLXSW_RES_ID_MAX_VRS] = 0x2C01,
[MLXSW_RES_ID_MAX_RIFS] = 0x2C02,
+ [MLXSW_RES_ID_MC_ERIF_LIST_ENTRIES] = 0x2C10,
[MLXSW_RES_ID_MAX_LPM_TREES] = 0x2C30,
};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 696b99e65a5a..5cd4df08ce97 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -69,6 +69,7 @@
#include "txheader.h"
#include "spectrum_cnt.h"
#include "spectrum_dpipe.h"
+#include "spectrum_acl_flex_actions.h"
#include "../mlxfw/mlxfw.h"
#define MLXSW_FWREV_MAJOR 13
@@ -3311,6 +3312,14 @@ static void mlxsw_sp_rx_listener_mark_func(struct sk_buff *skb, u8 local_port,
return mlxsw_sp_rx_listener_no_mark_func(skb, local_port, priv);
}
+static void mlxsw_sp_rx_listener_mr_mark_func(struct sk_buff *skb,
+ u8 local_port, void *priv)
+{
+ skb->offload_mr_fwd_mark = 1;
+ skb->offload_fwd_mark = 1;
+ return mlxsw_sp_rx_listener_no_mark_func(skb, local_port, priv);
+}
+
static void mlxsw_sp_rx_listener_sample_func(struct sk_buff *skb, u8 local_port,
void *priv)
{
@@ -3354,6 +3363,10 @@ out:
MLXSW_RXL(mlxsw_sp_rx_listener_mark_func, _trap_id, _action, \
_is_ctrl, SP_##_trap_group, DISCARD)
+#define MLXSW_SP_RXL_MR_MARK(_trap_id, _action, _trap_group, _is_ctrl) \
+ MLXSW_RXL(mlxsw_sp_rx_listener_mr_mark_func, _trap_id, _action, \
+ _is_ctrl, SP_##_trap_group, DISCARD)
+
#define MLXSW_SP_EVENTL(_func, _trap_id) \
MLXSW_EVENTL(_func, _trap_id, SP_EVENT)
@@ -3420,6 +3433,11 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
false, SP_IP2ME, DISCARD),
/* ACL trap */
MLXSW_SP_RXL_NO_MARK(ACL0, TRAP_TO_CPU, IP2ME, false),
+ /* Multicast Router Traps */
+ MLXSW_SP_RXL_MARK(IPV4_PIM, TRAP_TO_CPU, PIM, false),
+ MLXSW_SP_RXL_MARK(RPF, TRAP_TO_CPU, RPF, false),
+ MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false),
+ MLXSW_SP_RXL_MR_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false),
};
static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
@@ -3445,6 +3463,8 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
case MLXSW_REG_HTGT_TRAP_GROUP_SP_LACP:
case MLXSW_REG_HTGT_TRAP_GROUP_SP_LLDP:
case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF:
+ case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM:
+ case MLXSW_REG_HTGT_TRAP_GROUP_SP_RPF:
rate = 128;
burst_size = 7;
break;
@@ -3460,6 +3480,7 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP:
case MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE:
case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND:
+ case MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST:
rate = 1024;
burst_size = 7;
break;
@@ -3505,6 +3526,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
case MLXSW_REG_HTGT_TRAP_GROUP_SP_LACP:
case MLXSW_REG_HTGT_TRAP_GROUP_SP_LLDP:
case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF:
+ case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM:
priority = 5;
tc = 5;
break;
@@ -3521,12 +3543,14 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
break;
case MLXSW_REG_HTGT_TRAP_GROUP_SP_ARP:
case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND:
+ case MLXSW_REG_HTGT_TRAP_GROUP_SP_RPF:
priority = 2;
tc = 2;
break;
case MLXSW_REG_HTGT_TRAP_GROUP_SP_HOST_MISS:
case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP:
case MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE:
+ case MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST:
priority = 1;
tc = 1;
break;
@@ -3693,6 +3717,18 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
goto err_switchdev_init;
}
+ err = mlxsw_sp_counter_pool_init(mlxsw_sp);
+ if (err) {
+ dev_err(mlxsw_sp->bus_info->dev, "Failed to init counter pool\n");
+ goto err_counter_pool_init;
+ }
+
+ err = mlxsw_sp_afa_init(mlxsw_sp);
+ if (err) {
+ dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize ACL actions\n");
+ goto err_afa_init;
+ }
+
err = mlxsw_sp_router_init(mlxsw_sp);
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize router\n");
@@ -3711,12 +3747,6 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
goto err_acl_init;
}
- err = mlxsw_sp_counter_pool_init(mlxsw_sp);
- if (err) {
- dev_err(mlxsw_sp->bus_info->dev, "Failed to init counter pool\n");
- goto err_counter_pool_init;
- }
-
err = mlxsw_sp_dpipe_init(mlxsw_sp);
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Failed to init pipeline debug\n");
@@ -3734,14 +3764,16 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
err_ports_create:
mlxsw_sp_dpipe_fini(mlxsw_sp);
err_dpipe_init:
- mlxsw_sp_counter_pool_fini(mlxsw_sp);
-err_counter_pool_init:
mlxsw_sp_acl_fini(mlxsw_sp);
err_acl_init:
mlxsw_sp_span_fini(mlxsw_sp);
err_span_init:
mlxsw_sp_router_fini(mlxsw_sp);
err_router_init:
+ mlxsw_sp_afa_fini(mlxsw_sp);
+err_afa_init:
+ mlxsw_sp_counter_pool_fini(mlxsw_sp);
+err_counter_pool_init:
mlxsw_sp_switchdev_fini(mlxsw_sp);
err_switchdev_init:
mlxsw_sp_lag_fini(mlxsw_sp);
@@ -3760,10 +3792,11 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
mlxsw_sp_ports_remove(mlxsw_sp);
mlxsw_sp_dpipe_fini(mlxsw_sp);
- mlxsw_sp_counter_pool_fini(mlxsw_sp);
mlxsw_sp_acl_fini(mlxsw_sp);
mlxsw_sp_span_fini(mlxsw_sp);
mlxsw_sp_router_fini(mlxsw_sp);
+ mlxsw_sp_afa_fini(mlxsw_sp);
+ mlxsw_sp_counter_pool_fini(mlxsw_sp);
mlxsw_sp_switchdev_fini(mlxsw_sp);
mlxsw_sp_lag_fini(mlxsw_sp);
mlxsw_sp_buffers_fini(mlxsw_sp);
@@ -3986,14 +4019,21 @@ static int mlxsw_sp_lag_index_get(struct mlxsw_sp *mlxsw_sp,
static bool
mlxsw_sp_master_lag_check(struct mlxsw_sp *mlxsw_sp,
struct net_device *lag_dev,
- struct netdev_lag_upper_info *lag_upper_info)
+ struct netdev_lag_upper_info *lag_upper_info,
+ struct netlink_ext_ack *extack)
{
u16 lag_id;
- if (mlxsw_sp_lag_index_get(mlxsw_sp, lag_dev, &lag_id) != 0)
+ if (mlxsw_sp_lag_index_get(mlxsw_sp, lag_dev, &lag_id) != 0) {
+ NL_SET_ERR_MSG(extack,
+ "spectrum: Exceeded number of supported LAG devices");
return false;
- if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH)
+ }
+ if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) {
+ NL_SET_ERR_MSG(extack,
+ "spectrum: LAG device using unsupported Tx type");
return false;
+ }
return true;
}
@@ -4198,6 +4238,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
{
struct netdev_notifier_changeupper_info *info;
struct mlxsw_sp_port *mlxsw_sp_port;
+ struct netlink_ext_ack *extack;
struct net_device *upper_dev;
struct mlxsw_sp *mlxsw_sp;
int err = 0;
@@ -4205,6 +4246,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
mlxsw_sp_port = netdev_priv(dev);
mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
info = ptr;
+ extack = netdev_notifier_info_to_extack(&info->info);
switch (event) {
case NETDEV_PRECHANGEUPPER:
@@ -4212,25 +4254,43 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
if (!is_vlan_dev(upper_dev) &&
!netif_is_lag_master(upper_dev) &&
!netif_is_bridge_master(upper_dev) &&
- !netif_is_ovs_master(upper_dev))
+ !netif_is_ovs_master(upper_dev)) {
+ NL_SET_ERR_MSG(extack,
+ "spectrum: Unknown upper device type");
return -EINVAL;
+ }
if (!info->linking)
break;
- if (netdev_has_any_upper_dev(upper_dev))
+ if (netdev_has_any_upper_dev(upper_dev)) {
+ NL_SET_ERR_MSG(extack,
+ "spectrum: Enslaving a port to a device that already has an upper device is not supported");
return -EINVAL;
+ }
if (netif_is_lag_master(upper_dev) &&
!mlxsw_sp_master_lag_check(mlxsw_sp, upper_dev,
- info->upper_info))
+ info->upper_info, extack))
return -EINVAL;
- if (netif_is_lag_master(upper_dev) && vlan_uses_dev(dev))
+ if (netif_is_lag_master(upper_dev) && vlan_uses_dev(dev)) {
+ NL_SET_ERR_MSG(extack,
+ "spectrum: Master device is a LAG master and this device has a VLAN");
return -EINVAL;
+ }
if (netif_is_lag_port(dev) && is_vlan_dev(upper_dev) &&
- !netif_is_lag_master(vlan_dev_real_dev(upper_dev)))
+ !netif_is_lag_master(vlan_dev_real_dev(upper_dev))) {
+ NL_SET_ERR_MSG(extack,
+ "spectrum: Can not put a VLAN on a LAG port");
return -EINVAL;
- if (netif_is_ovs_master(upper_dev) && vlan_uses_dev(dev))
+ }
+ if (netif_is_ovs_master(upper_dev) && vlan_uses_dev(dev)) {
+ NL_SET_ERR_MSG(extack,
+ "spectrum: Master device is an OVS master and this device has a VLAN");
return -EINVAL;
- if (netif_is_ovs_port(dev) && is_vlan_dev(upper_dev))
+ }
+ if (netif_is_ovs_port(dev) && is_vlan_dev(upper_dev)) {
+ NL_SET_ERR_MSG(extack,
+ "spectrum: Can not put a VLAN on an OVS port");
return -EINVAL;
+ }
break;
case NETDEV_CHANGEUPPER:
upper_dev = info->upper_dev;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 84ce83acdc19..ae67e6046098 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -94,7 +94,8 @@ struct mlxsw_sp_mid {
unsigned char addr[ETH_ALEN];
u16 fid;
u16 mid;
- unsigned int ref_count;
+ bool in_hw;
+ unsigned long *ports_in_mid; /* bits array */
};
enum mlxsw_sp_span_type {
@@ -138,6 +139,7 @@ struct mlxsw_sp_port_mall_tc_entry {
struct mlxsw_sp_sb;
struct mlxsw_sp_bridge;
struct mlxsw_sp_router;
+struct mlxsw_sp_mr;
struct mlxsw_sp_acl;
struct mlxsw_sp_counter_pool;
struct mlxsw_sp_fid_core;
@@ -152,6 +154,8 @@ struct mlxsw_sp {
struct mlxsw_sp_sb *sb;
struct mlxsw_sp_bridge *bridge;
struct mlxsw_sp_router *router;
+ struct mlxsw_sp_mr *mr;
+ struct mlxsw_afa *afa;
struct mlxsw_sp_acl *acl;
struct mlxsw_sp_fid_core *fid_core;
struct {
@@ -466,9 +470,9 @@ void mlxsw_sp_acl_rulei_keymask_buf(struct mlxsw_sp_acl_rule_info *rulei,
enum mlxsw_afk_element element,
const char *key_value,
const char *mask_value, unsigned int len);
-void mlxsw_sp_acl_rulei_act_continue(struct mlxsw_sp_acl_rule_info *rulei);
-void mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei,
- u16 group_id);
+int mlxsw_sp_acl_rulei_act_continue(struct mlxsw_sp_acl_rule_info *rulei);
+int mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei,
+ u16 group_id);
int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei);
int mlxsw_sp_acl_rulei_act_trap(struct mlxsw_sp_acl_rule_info *rulei);
int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 4b2455e3e079..93dcd315f7d6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -52,7 +52,6 @@
struct mlxsw_sp_acl {
struct mlxsw_sp *mlxsw_sp;
struct mlxsw_afk *afk;
- struct mlxsw_afa *afa;
struct mlxsw_sp_fid *dummy_fid;
const struct mlxsw_sp_acl_ops *ops;
struct rhashtable ruleset_ht;
@@ -333,7 +332,7 @@ mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl)
rulei = kzalloc(sizeof(*rulei), GFP_KERNEL);
if (!rulei)
return NULL;
- rulei->act_block = mlxsw_afa_block_create(acl->afa);
+ rulei->act_block = mlxsw_afa_block_create(acl->mlxsw_sp->afa);
if (IS_ERR(rulei->act_block)) {
err = PTR_ERR(rulei->act_block);
goto err_afa_block_create;
@@ -379,15 +378,15 @@ void mlxsw_sp_acl_rulei_keymask_buf(struct mlxsw_sp_acl_rule_info *rulei,
key_value, mask_value, len);
}
-void mlxsw_sp_acl_rulei_act_continue(struct mlxsw_sp_acl_rule_info *rulei)
+int mlxsw_sp_acl_rulei_act_continue(struct mlxsw_sp_acl_rule_info *rulei)
{
- mlxsw_afa_block_continue(rulei->act_block);
+ return mlxsw_afa_block_continue(rulei->act_block);
}
-void mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei,
- u16 group_id)
+int mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei,
+ u16 group_id)
{
- mlxsw_afa_block_jump(rulei->act_block, group_id);
+ return mlxsw_afa_block_jump(rulei->act_block, group_id);
}
int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei)
@@ -397,7 +396,8 @@ int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei)
int mlxsw_sp_acl_rulei_act_trap(struct mlxsw_sp_acl_rule_info *rulei)
{
- return mlxsw_afa_block_append_trap(rulei->act_block);
+ return mlxsw_afa_block_append_trap(rulei->act_block,
+ MLXSW_TRAP_ID_ACL0);
}
int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
@@ -653,85 +653,6 @@ int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp,
return 0;
}
-#define MLXSW_SP_KDVL_ACT_EXT_SIZE 1
-
-static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
- char *enc_actions, bool is_first)
-{
- struct mlxsw_sp *mlxsw_sp = priv;
- char pefa_pl[MLXSW_REG_PEFA_LEN];
- u32 kvdl_index;
- int err;
-
- /* The first action set of a TCAM entry is stored directly in TCAM,
- * not KVD linear area.
- */
- if (is_first)
- return 0;
-
- err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KDVL_ACT_EXT_SIZE,
- &kvdl_index);
- if (err)
- return err;
- mlxsw_reg_pefa_pack(pefa_pl, kvdl_index, enc_actions);
- err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pefa), pefa_pl);
- if (err)
- goto err_pefa_write;
- *p_kvdl_index = kvdl_index;
- return 0;
-
-err_pefa_write:
- mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
- return err;
-}
-
-static void mlxsw_sp_act_kvdl_set_del(void *priv, u32 kvdl_index,
- bool is_first)
-{
- struct mlxsw_sp *mlxsw_sp = priv;
-
- if (is_first)
- return;
- mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
-}
-
-static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
- u8 local_port)
-{
- struct mlxsw_sp *mlxsw_sp = priv;
- char ppbs_pl[MLXSW_REG_PPBS_LEN];
- u32 kvdl_index;
- int err;
-
- err = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1, &kvdl_index);
- if (err)
- return err;
- mlxsw_reg_ppbs_pack(ppbs_pl, kvdl_index, local_port);
- err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ppbs), ppbs_pl);
- if (err)
- goto err_ppbs_write;
- *p_kvdl_index = kvdl_index;
- return 0;
-
-err_ppbs_write:
- mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
- return err;
-}
-
-static void mlxsw_sp_act_kvdl_fwd_entry_del(void *priv, u32 kvdl_index)
-{
- struct mlxsw_sp *mlxsw_sp = priv;
-
- mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
-}
-
-static const struct mlxsw_afa_ops mlxsw_sp_act_afa_ops = {
- .kvdl_set_add = mlxsw_sp_act_kvdl_set_add,
- .kvdl_set_del = mlxsw_sp_act_kvdl_set_del,
- .kvdl_fwd_entry_add = mlxsw_sp_act_kvdl_fwd_entry_add,
- .kvdl_fwd_entry_del = mlxsw_sp_act_kvdl_fwd_entry_del,
-};
-
int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
{
const struct mlxsw_sp_acl_ops *acl_ops = &mlxsw_sp_acl_tcam_ops;
@@ -753,14 +674,6 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
goto err_afk_create;
}
- acl->afa = mlxsw_afa_create(MLXSW_CORE_RES_GET(mlxsw_sp->core,
- ACL_ACTIONS_PER_SET),
- &mlxsw_sp_act_afa_ops, mlxsw_sp);
- if (IS_ERR(acl->afa)) {
- err = PTR_ERR(acl->afa);
- goto err_afa_create;
- }
-
err = rhashtable_init(&acl->ruleset_ht,
&mlxsw_sp_acl_ruleset_ht_params);
if (err)
@@ -792,8 +705,6 @@ err_acl_ops_init:
err_fid_get:
rhashtable_destroy(&acl->ruleset_ht);
err_rhashtable_init:
- mlxsw_afa_destroy(acl->afa);
-err_afa_create:
mlxsw_afk_destroy(acl->afk);
err_afk_create:
kfree(acl);
@@ -810,7 +721,6 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp)
WARN_ON(!list_empty(&acl->rules));
mlxsw_sp_fid_put(acl->dummy_fid);
rhashtable_destroy(&acl->ruleset_ht);
- mlxsw_afa_destroy(acl->afa);
mlxsw_afk_destroy(acl->afk);
kfree(acl);
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
new file mode 100644
index 000000000000..4d3340ed0291
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
@@ -0,0 +1,129 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "spectrum_acl_flex_actions.h"
+#include "core_acl_flex_actions.h"
+
+#define MLXSW_SP_KVDL_ACT_EXT_SIZE 1
+
+static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
+ char *enc_actions, bool is_first)
+{
+ struct mlxsw_sp *mlxsw_sp = priv;
+ char pefa_pl[MLXSW_REG_PEFA_LEN];
+ u32 kvdl_index;
+ int err;
+
+ /* The first action set of a TCAM entry is stored directly in TCAM,
+ * not KVD linear area.
+ */
+ if (is_first)
+ return 0;
+
+ err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ACT_EXT_SIZE,
+ &kvdl_index);
+ if (err)
+ return err;
+ mlxsw_reg_pefa_pack(pefa_pl, kvdl_index, enc_actions);
+ err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pefa), pefa_pl);
+ if (err)
+ goto err_pefa_write;
+ *p_kvdl_index = kvdl_index;
+ return 0;
+
+err_pefa_write:
+ mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+ return err;
+}
+
+static void mlxsw_sp_act_kvdl_set_del(void *priv, u32 kvdl_index,
+ bool is_first)
+{
+ struct mlxsw_sp *mlxsw_sp = priv;
+
+ if (is_first)
+ return;
+ mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+}
+
+static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
+ u8 local_port)
+{
+ struct mlxsw_sp *mlxsw_sp = priv;
+ char ppbs_pl[MLXSW_REG_PPBS_LEN];
+ u32 kvdl_index;
+ int err;
+
+ err = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1, &kvdl_index);
+ if (err)
+ return err;
+ mlxsw_reg_ppbs_pack(ppbs_pl, kvdl_index, local_port);
+ err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ppbs), ppbs_pl);
+ if (err)
+ goto err_ppbs_write;
+ *p_kvdl_index = kvdl_index;
+ return 0;
+
+err_ppbs_write:
+ mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+ return err;
+}
+
+static void mlxsw_sp_act_kvdl_fwd_entry_del(void *priv, u32 kvdl_index)
+{
+ struct mlxsw_sp *mlxsw_sp = priv;
+
+ mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+}
+
+static const struct mlxsw_afa_ops mlxsw_sp_act_afa_ops = {
+ .kvdl_set_add = mlxsw_sp_act_kvdl_set_add,
+ .kvdl_set_del = mlxsw_sp_act_kvdl_set_del,
+ .kvdl_fwd_entry_add = mlxsw_sp_act_kvdl_fwd_entry_add,
+ .kvdl_fwd_entry_del = mlxsw_sp_act_kvdl_fwd_entry_del,
+};
+
+int mlxsw_sp_afa_init(struct mlxsw_sp *mlxsw_sp)
+{
+ mlxsw_sp->afa = mlxsw_afa_create(MLXSW_CORE_RES_GET(mlxsw_sp->core,
+ ACL_ACTIONS_PER_SET),
+ &mlxsw_sp_act_afa_ops, mlxsw_sp);
+ return PTR_ERR_OR_ZERO(mlxsw_sp->afa);
+}
+
+void mlxsw_sp_afa_fini(struct mlxsw_sp *mlxsw_sp)
+{
+ mlxsw_afa_destroy(mlxsw_sp->afa);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h
new file mode 100644
index 000000000000..2726192836ad
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h
@@ -0,0 +1,44 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_SPECTRUM_ACL_FLEX_KEYS_H
+#define _MLXSW_SPECTRUM_ACL_FLEX_KEYS_H
+
+#include "spectrum.h"
+
+int mlxsw_sp_afa_init(struct mlxsw_sp *mlxsw_sp);
+void mlxsw_sp_afa_fini(struct mlxsw_sp *mlxsw_sp);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index 50b40de1fb91..7e8284b46968 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -608,7 +608,10 @@ mlxsw_sp_acl_tcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp,
goto err_rulei_create;
}
- mlxsw_sp_acl_rulei_act_continue(rulei);
+ err = mlxsw_sp_acl_rulei_act_continue(rulei);
+ if (WARN_ON(err))
+ goto err_rulei_act_continue;
+
err = mlxsw_sp_acl_rulei_commit(rulei);
if (err)
goto err_rulei_commit;
@@ -623,6 +626,7 @@ mlxsw_sp_acl_tcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp,
err_rule_insert:
err_rulei_commit:
+err_rulei_act_continue:
mlxsw_sp_acl_rulei_destroy(rulei);
err_rulei_create:
parman_item_remove(region->parman, parman_prio, parman_item);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
index 51e6846da72b..a056f23d3a0e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
@@ -43,21 +43,36 @@ enum mlxsw_sp_field_metadata_id {
MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT,
MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD,
MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP,
+ MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_INDEX,
+ MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_HASH_INDEX,
};
static struct devlink_dpipe_field mlxsw_sp_dpipe_fields_metadata[] = {
- { .name = "erif_port",
- .id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT,
- .bitwidth = 32,
- .mapping_type = DEVLINK_DPIPE_FIELD_MAPPING_TYPE_IFINDEX,
+ {
+ .name = "erif_port",
+ .id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT,
+ .bitwidth = 32,
+ .mapping_type = DEVLINK_DPIPE_FIELD_MAPPING_TYPE_IFINDEX,
},
- { .name = "l3_forward",
- .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD,
- .bitwidth = 1,
+ {
+ .name = "l3_forward",
+ .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD,
+ .bitwidth = 1,
},
- { .name = "l3_drop",
- .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP,
- .bitwidth = 1,
+ {
+ .name = "l3_drop",
+ .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP,
+ .bitwidth = 1,
+ },
+ {
+ .name = "adj_index",
+ .id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_INDEX,
+ .bitwidth = 32,
+ },
+ {
+ .name = "adj_hash_index",
+ .id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_HASH_INDEX,
+ .bitwidth = 32,
},
};
@@ -826,6 +841,359 @@ static void mlxsw_sp_dpipe_host6_table_fini(struct mlxsw_sp *mlxsw_sp)
MLXSW_SP_DPIPE_TABLE_NAME_HOST6);
}
+static int mlxsw_sp_dpipe_table_adj_matches_dump(void *priv,
+ struct sk_buff *skb)
+{
+ struct devlink_dpipe_match match = {0};
+ int err;
+
+ match.type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+ match.header = &mlxsw_sp_dpipe_header_metadata;
+ match.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_INDEX;
+
+ err = devlink_dpipe_match_put(skb, &match);
+ if (err)
+ return err;
+
+ match.type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+ match.header = &mlxsw_sp_dpipe_header_metadata;
+ match.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_HASH_INDEX;
+
+ return devlink_dpipe_match_put(skb, &match);
+}
+
+static int mlxsw_sp_dpipe_table_adj_actions_dump(void *priv,
+ struct sk_buff *skb)
+{
+ struct devlink_dpipe_action action = {0};
+ int err;
+
+ action.type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+ action.header = &devlink_dpipe_header_ethernet;
+ action.field_id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC;
+
+ err = devlink_dpipe_action_put(skb, &action);
+ if (err)
+ return err;
+
+ action.type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+ action.header = &mlxsw_sp_dpipe_header_metadata;
+ action.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT;
+
+ return devlink_dpipe_action_put(skb, &action);
+}
+
+static u64 mlxsw_sp_dpipe_table_adj_size(struct mlxsw_sp *mlxsw_sp)
+{
+ struct mlxsw_sp_nexthop *nh;
+ u64 size = 0;
+
+ mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router)
+ if (mlxsw_sp_nexthop_offload(nh) &&
+ !mlxsw_sp_nexthop_group_has_ipip(nh))
+ size++;
+ return size;
+}
+
+enum mlxsw_sp_dpipe_table_adj_match {
+ MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX,
+ MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX,
+ MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT,
+};
+
+enum mlxsw_sp_dpipe_table_adj_action {
+ MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_DST_MAC,
+ MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_ERIF_PORT,
+ MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT,
+};
+
+static void
+mlxsw_sp_dpipe_table_adj_match_action_prepare(struct devlink_dpipe_match *matches,
+ struct devlink_dpipe_action *actions)
+{
+ struct devlink_dpipe_action *action;
+ struct devlink_dpipe_match *match;
+
+ match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX];
+ match->type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+ match->header = &mlxsw_sp_dpipe_header_metadata;
+ match->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_INDEX;
+
+ match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX];
+ match->type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+ match->header = &mlxsw_sp_dpipe_header_metadata;
+ match->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_HASH_INDEX;
+
+ action = &actions[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_DST_MAC];
+ action->type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+ action->header = &devlink_dpipe_header_ethernet;
+ action->field_id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC;
+
+ action = &actions[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_ERIF_PORT];
+ action->type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+ action->header = &mlxsw_sp_dpipe_header_metadata;
+ action->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT;
+}
+
+static int
+mlxsw_sp_dpipe_table_adj_entry_prepare(struct devlink_dpipe_entry *entry,
+ struct devlink_dpipe_value *match_values,
+ struct devlink_dpipe_match *matches,
+ struct devlink_dpipe_value *action_values,
+ struct devlink_dpipe_action *actions)
+{ struct devlink_dpipe_value *action_value;
+ struct devlink_dpipe_value *match_value;
+ struct devlink_dpipe_action *action;
+ struct devlink_dpipe_match *match;
+
+ entry->match_values = match_values;
+ entry->match_values_count = MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT;
+
+ entry->action_values = action_values;
+ entry->action_values_count = MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT;
+
+ match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX];
+ match_value = &match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX];
+
+ match_value->match = match;
+ match_value->value_size = sizeof(u32);
+ match_value->value = kmalloc(match_value->value_size, GFP_KERNEL);
+ if (!match_value->value)
+ return -ENOMEM;
+
+ match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX];
+ match_value = &match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX];
+
+ match_value->match = match;
+ match_value->value_size = sizeof(u32);
+ match_value->value = kmalloc(match_value->value_size, GFP_KERNEL);
+ if (!match_value->value)
+ return -ENOMEM;
+
+ action = &actions[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_DST_MAC];
+ action_value = &action_values[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_DST_MAC];
+
+ action_value->action = action;
+ action_value->value_size = sizeof(u64);
+ action_value->value = kmalloc(action_value->value_size, GFP_KERNEL);
+ if (!action_value->value)
+ return -ENOMEM;
+
+ action = &actions[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_ERIF_PORT];
+ action_value = &action_values[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_ERIF_PORT];
+
+ action_value->action = action;
+ action_value->value_size = sizeof(u32);
+ action_value->value = kmalloc(action_value->value_size, GFP_KERNEL);
+ if (!action_value->value)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void
+__mlxsw_sp_dpipe_table_adj_entry_fill(struct devlink_dpipe_entry *entry,
+ u32 adj_index, u32 adj_hash_index,
+ unsigned char *ha,
+ struct mlxsw_sp_rif *rif)
+{
+ struct devlink_dpipe_value *value;
+ u32 *p_rif_value;
+ u32 *p_index;
+
+ value = &entry->match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX];
+ p_index = value->value;
+ *p_index = adj_index;
+
+ value = &entry->match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX];
+ p_index = value->value;
+ *p_index = adj_hash_index;
+
+ value = &entry->action_values[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_DST_MAC];
+ ether_addr_copy(value->value, ha);
+
+ value = &entry->action_values[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_ERIF_PORT];
+ p_rif_value = value->value;
+ *p_rif_value = mlxsw_sp_rif_index(rif);
+ value->mapping_value = mlxsw_sp_rif_dev_ifindex(rif);
+ value->mapping_valid = true;
+}
+
+static void mlxsw_sp_dpipe_table_adj_entry_fill(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh,
+ struct devlink_dpipe_entry *entry)
+{
+ struct mlxsw_sp_rif *rif = mlxsw_sp_nexthop_rif(nh);
+ unsigned char *ha = mlxsw_sp_nexthop_ha(nh);
+ u32 adj_hash_index = 0;
+ u32 adj_index = 0;
+ int err;
+
+ mlxsw_sp_nexthop_indexes(nh, &adj_index, &adj_hash_index);
+ __mlxsw_sp_dpipe_table_adj_entry_fill(entry, adj_index,
+ adj_hash_index, ha, rif);
+ err = mlxsw_sp_nexthop_counter_get(mlxsw_sp, nh, &entry->counter);
+ if (!err)
+ entry->counter_valid = true;
+}
+
+static int
+mlxsw_sp_dpipe_table_adj_entries_get(struct mlxsw_sp *mlxsw_sp,
+ struct devlink_dpipe_entry *entry,
+ bool counters_enabled,
+ struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+ struct mlxsw_sp_nexthop *nh;
+ int entry_index = 0;
+ int nh_count_max;
+ int nh_count = 0;
+ int nh_skip;
+ int j;
+ int err;
+
+ rtnl_lock();
+ nh_count_max = mlxsw_sp_dpipe_table_adj_size(mlxsw_sp);
+start_again:
+ err = devlink_dpipe_entry_ctx_prepare(dump_ctx);
+ if (err)
+ goto err_ctx_prepare;
+ j = 0;
+ nh_skip = nh_count;
+ mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router) {
+ if (!mlxsw_sp_nexthop_offload(nh) ||
+ mlxsw_sp_nexthop_group_has_ipip(nh))
+ continue;
+
+ if (nh_count < nh_skip)
+ goto skip;
+
+ mlxsw_sp_dpipe_table_adj_entry_fill(mlxsw_sp, nh, entry);
+ entry->index = entry_index;
+ err = devlink_dpipe_entry_ctx_append(dump_ctx, entry);
+ if (err) {
+ if (err == -EMSGSIZE) {
+ if (!j)
+ goto err_entry_append;
+ break;
+ }
+ goto err_entry_append;
+ }
+ entry_index++;
+ j++;
+skip:
+ nh_count++;
+ }
+
+ devlink_dpipe_entry_ctx_close(dump_ctx);
+ if (nh_count != nh_count_max)
+ goto start_again;
+ rtnl_unlock();
+
+ return 0;
+
+err_ctx_prepare:
+err_entry_append:
+ rtnl_unlock();
+ return err;
+}
+
+static int
+mlxsw_sp_dpipe_table_adj_entries_dump(void *priv, bool counters_enabled,
+ struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+ struct devlink_dpipe_value action_values[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT];
+ struct devlink_dpipe_value match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT];
+ struct devlink_dpipe_action actions[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT];
+ struct devlink_dpipe_match matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT];
+ struct devlink_dpipe_entry entry = {0};
+ struct mlxsw_sp *mlxsw_sp = priv;
+ int err;
+
+ memset(matches, 0, MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT *
+ sizeof(matches[0]));
+ memset(match_values, 0, MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT *
+ sizeof(match_values[0]));
+ memset(actions, 0, MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT *
+ sizeof(actions[0]));
+ memset(action_values, 0, MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT *
+ sizeof(action_values[0]));
+
+ mlxsw_sp_dpipe_table_adj_match_action_prepare(matches, actions);
+ err = mlxsw_sp_dpipe_table_adj_entry_prepare(&entry,
+ match_values, matches,
+ action_values, actions);
+ if (err)
+ goto out;
+
+ err = mlxsw_sp_dpipe_table_adj_entries_get(mlxsw_sp, &entry,
+ counters_enabled, dump_ctx);
+out:
+ devlink_dpipe_entry_clear(&entry);
+ return err;
+}
+
+static int mlxsw_sp_dpipe_table_adj_counters_update(void *priv, bool enable)
+{
+ struct mlxsw_sp *mlxsw_sp = priv;
+ struct mlxsw_sp_nexthop *nh;
+ u32 adj_hash_index = 0;
+ u32 adj_index = 0;
+
+ mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router) {
+ if (!mlxsw_sp_nexthop_offload(nh) ||
+ mlxsw_sp_nexthop_group_has_ipip(nh))
+ continue;
+
+ mlxsw_sp_nexthop_indexes(nh, &adj_index, &adj_hash_index);
+ if (enable)
+ mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh);
+ else
+ mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh);
+ mlxsw_sp_nexthop_update(mlxsw_sp,
+ adj_index + adj_hash_index, nh);
+ }
+ return 0;
+}
+
+static u64
+mlxsw_sp_dpipe_table_adj_size_get(void *priv)
+{
+ struct mlxsw_sp *mlxsw_sp = priv;
+ u64 size;
+
+ rtnl_lock();
+ size = mlxsw_sp_dpipe_table_adj_size(mlxsw_sp);
+ rtnl_unlock();
+
+ return size;
+}
+
+static struct devlink_dpipe_table_ops mlxsw_sp_dpipe_table_adj_ops = {
+ .matches_dump = mlxsw_sp_dpipe_table_adj_matches_dump,
+ .actions_dump = mlxsw_sp_dpipe_table_adj_actions_dump,
+ .entries_dump = mlxsw_sp_dpipe_table_adj_entries_dump,
+ .counters_set_update = mlxsw_sp_dpipe_table_adj_counters_update,
+ .size_get = mlxsw_sp_dpipe_table_adj_size_get,
+};
+
+static int mlxsw_sp_dpipe_adj_table_init(struct mlxsw_sp *mlxsw_sp)
+{
+ struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+
+ return devlink_dpipe_table_register(devlink,
+ MLXSW_SP_DPIPE_TABLE_NAME_ADJ,
+ &mlxsw_sp_dpipe_table_adj_ops,
+ mlxsw_sp, false);
+}
+
+static void mlxsw_sp_dpipe_adj_table_fini(struct mlxsw_sp *mlxsw_sp)
+{
+ struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+
+ devlink_dpipe_table_unregister(devlink,
+ MLXSW_SP_DPIPE_TABLE_NAME_ADJ);
+}
+
int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp)
{
struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
@@ -846,8 +1214,14 @@ int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp)
err = mlxsw_sp_dpipe_host6_table_init(mlxsw_sp);
if (err)
goto err_host6_table_init;
- return 0;
+ err = mlxsw_sp_dpipe_adj_table_init(mlxsw_sp);
+ if (err)
+ goto err_adj_table_init;
+
+ return 0;
+err_adj_table_init:
+ mlxsw_sp_dpipe_host6_table_fini(mlxsw_sp);
err_host6_table_init:
mlxsw_sp_dpipe_host4_table_fini(mlxsw_sp);
err_host4_table_init:
@@ -861,6 +1235,7 @@ void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp)
{
struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+ mlxsw_sp_dpipe_adj_table_fini(mlxsw_sp);
mlxsw_sp_dpipe_host6_table_fini(mlxsw_sp);
mlxsw_sp_dpipe_host4_table_fini(mlxsw_sp);
mlxsw_sp_dpipe_erif_table_fini(mlxsw_sp);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
index 283fde4e6783..815d543cf114 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
@@ -56,5 +56,6 @@ static inline void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp)
#define MLXSW_SP_DPIPE_TABLE_NAME_ERIF "mlxsw_erif"
#define MLXSW_SP_DPIPE_TABLE_NAME_HOST4 "mlxsw_host4"
#define MLXSW_SP_DPIPE_TABLE_NAME_HOST6 "mlxsw_host6"
+#define MLXSW_SP_DPIPE_TABLE_NAME_ADJ "mlxsw_adj"
#endif /* _MLXSW_PIPELINE_H_*/
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 8aace9a06a5d..2f0e57857ea4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -63,7 +63,11 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
tcf_exts_to_list(exts, &actions);
list_for_each_entry(a, &actions, list) {
- if (is_tcf_gact_shot(a)) {
+ if (is_tcf_gact_ok(a)) {
+ err = mlxsw_sp_acl_rulei_act_continue(rulei);
+ if (err)
+ return err;
+ } else if (is_tcf_gact_shot(a)) {
err = mlxsw_sp_acl_rulei_act_drop(rulei);
if (err)
return err;
@@ -84,7 +88,9 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
return PTR_ERR(ruleset);
group_id = mlxsw_sp_acl_ruleset_group_id(ruleset);
- mlxsw_sp_acl_rulei_act_jump(rulei, group_id);
+ err = mlxsw_sp_acl_rulei_act_jump(rulei, group_id);
+ if (err)
+ return err;
} else if (is_tcf_mirred_egress_redirect(a)) {
int ifindex = tcf_mirred_ifindex(a);
struct net_device *out_dev;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
new file mode 100644
index 000000000000..1f84bb8e9135
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
@@ -0,0 +1,1011 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/rhashtable.h>
+
+#include "spectrum_mr.h"
+#include "spectrum_router.h"
+
+struct mlxsw_sp_mr {
+ const struct mlxsw_sp_mr_ops *mr_ops;
+ void *catchall_route_priv;
+ struct delayed_work stats_update_dw;
+ struct list_head table_list;
+#define MLXSW_SP_MR_ROUTES_COUNTER_UPDATE_INTERVAL 5000 /* ms */
+ unsigned long priv[0];
+ /* priv has to be always the last item */
+};
+
+struct mlxsw_sp_mr_vif {
+ struct net_device *dev;
+ const struct mlxsw_sp_rif *rif;
+ unsigned long vif_flags;
+
+ /* A list of route_vif_entry structs that point to routes that the VIF
+ * instance is used as one of the egress VIFs
+ */
+ struct list_head route_evif_list;
+
+ /* A list of route_vif_entry structs that point to routes that the VIF
+ * instance is used as an ingress VIF
+ */
+ struct list_head route_ivif_list;
+};
+
+struct mlxsw_sp_mr_route_vif_entry {
+ struct list_head vif_node;
+ struct list_head route_node;
+ struct mlxsw_sp_mr_vif *mr_vif;
+ struct mlxsw_sp_mr_route *mr_route;
+};
+
+struct mlxsw_sp_mr_table {
+ struct list_head node;
+ enum mlxsw_sp_l3proto proto;
+ struct mlxsw_sp *mlxsw_sp;
+ u32 vr_id;
+ struct mlxsw_sp_mr_vif vifs[MAXVIFS];
+ struct list_head route_list;
+ struct rhashtable route_ht;
+ char catchall_route_priv[0];
+ /* catchall_route_priv has to be always the last item */
+};
+
+struct mlxsw_sp_mr_route {
+ struct list_head node;
+ struct rhash_head ht_node;
+ struct mlxsw_sp_mr_route_key key;
+ enum mlxsw_sp_mr_route_action route_action;
+ u16 min_mtu;
+ struct mfc_cache *mfc4;
+ void *route_priv;
+ const struct mlxsw_sp_mr_table *mr_table;
+ /* A list of route_vif_entry structs that point to the egress VIFs */
+ struct list_head evif_list;
+ /* A route_vif_entry struct that point to the ingress VIF */
+ struct mlxsw_sp_mr_route_vif_entry ivif;
+};
+
+static const struct rhashtable_params mlxsw_sp_mr_route_ht_params = {
+ .key_len = sizeof(struct mlxsw_sp_mr_route_key),
+ .key_offset = offsetof(struct mlxsw_sp_mr_route, key),
+ .head_offset = offsetof(struct mlxsw_sp_mr_route, ht_node),
+ .automatic_shrinking = true,
+};
+
+static bool mlxsw_sp_mr_vif_regular(const struct mlxsw_sp_mr_vif *vif)
+{
+ return !(vif->vif_flags & (VIFF_TUNNEL | VIFF_REGISTER));
+}
+
+static bool mlxsw_sp_mr_vif_valid(const struct mlxsw_sp_mr_vif *vif)
+{
+ return mlxsw_sp_mr_vif_regular(vif) && vif->dev && vif->rif;
+}
+
+static bool mlxsw_sp_mr_vif_exists(const struct mlxsw_sp_mr_vif *vif)
+{
+ return vif->dev;
+}
+
+static bool
+mlxsw_sp_mr_route_ivif_in_evifs(const struct mlxsw_sp_mr_route *mr_route)
+{
+ vifi_t ivif;
+
+ switch (mr_route->mr_table->proto) {
+ case MLXSW_SP_L3_PROTO_IPV4:
+ ivif = mr_route->mfc4->mfc_parent;
+ return mr_route->mfc4->mfc_un.res.ttls[ivif] != 255;
+ case MLXSW_SP_L3_PROTO_IPV6:
+ /* fall through */
+ default:
+ WARN_ON_ONCE(1);
+ }
+ return false;
+}
+
+static int
+mlxsw_sp_mr_route_valid_evifs_num(const struct mlxsw_sp_mr_route *mr_route)
+{
+ struct mlxsw_sp_mr_route_vif_entry *rve;
+ int valid_evifs;
+
+ valid_evifs = 0;
+ list_for_each_entry(rve, &mr_route->evif_list, route_node)
+ if (mlxsw_sp_mr_vif_valid(rve->mr_vif))
+ valid_evifs++;
+ return valid_evifs;
+}
+
+static bool mlxsw_sp_mr_route_starg(const struct mlxsw_sp_mr_route *mr_route)
+{
+ switch (mr_route->mr_table->proto) {
+ case MLXSW_SP_L3_PROTO_IPV4:
+ return mr_route->key.source_mask.addr4 == INADDR_ANY;
+ case MLXSW_SP_L3_PROTO_IPV6:
+ /* fall through */
+ default:
+ WARN_ON_ONCE(1);
+ }
+ return false;
+}
+
+static enum mlxsw_sp_mr_route_action
+mlxsw_sp_mr_route_action(const struct mlxsw_sp_mr_route *mr_route)
+{
+ struct mlxsw_sp_mr_route_vif_entry *rve;
+
+ /* If the ingress port is not regular and resolved, trap the route */
+ if (!mlxsw_sp_mr_vif_valid(mr_route->ivif.mr_vif))
+ return MLXSW_SP_MR_ROUTE_ACTION_TRAP;
+
+ /* The kernel does not match a (*,G) route that the ingress interface is
+ * not one of the egress interfaces, so trap these kind of routes.
+ */
+ if (mlxsw_sp_mr_route_starg(mr_route) &&
+ !mlxsw_sp_mr_route_ivif_in_evifs(mr_route))
+ return MLXSW_SP_MR_ROUTE_ACTION_TRAP;
+
+ /* If the route has no valid eVIFs, trap it. */
+ if (!mlxsw_sp_mr_route_valid_evifs_num(mr_route))
+ return MLXSW_SP_MR_ROUTE_ACTION_TRAP;
+
+ /* If one of the eVIFs has no RIF, trap-and-forward the route as there
+ * is some more routing to do in software too.
+ */
+ list_for_each_entry(rve, &mr_route->evif_list, route_node)
+ if (mlxsw_sp_mr_vif_exists(rve->mr_vif) && !rve->mr_vif->rif)
+ return MLXSW_SP_MR_ROUTE_ACTION_TRAP_AND_FORWARD;
+
+ return MLXSW_SP_MR_ROUTE_ACTION_FORWARD;
+}
+
+static enum mlxsw_sp_mr_route_prio
+mlxsw_sp_mr_route_prio(const struct mlxsw_sp_mr_route *mr_route)
+{
+ return mlxsw_sp_mr_route_starg(mr_route) ?
+ MLXSW_SP_MR_ROUTE_PRIO_STARG : MLXSW_SP_MR_ROUTE_PRIO_SG;
+}
+
+static void mlxsw_sp_mr_route4_key(struct mlxsw_sp_mr_table *mr_table,
+ struct mlxsw_sp_mr_route_key *key,
+ const struct mfc_cache *mfc)
+{
+ bool starg = (mfc->mfc_origin == INADDR_ANY);
+
+ memset(key, 0, sizeof(*key));
+ key->vrid = mr_table->vr_id;
+ key->proto = mr_table->proto;
+ key->group.addr4 = mfc->mfc_mcastgrp;
+ key->group_mask.addr4 = 0xffffffff;
+ key->source.addr4 = mfc->mfc_origin;
+ key->source_mask.addr4 = starg ? 0 : 0xffffffff;
+}
+
+static int mlxsw_sp_mr_route_evif_link(struct mlxsw_sp_mr_route *mr_route,
+ struct mlxsw_sp_mr_vif *mr_vif)
+{
+ struct mlxsw_sp_mr_route_vif_entry *rve;
+
+ rve = kzalloc(sizeof(*rve), GFP_KERNEL);
+ if (!rve)
+ return -ENOMEM;
+ rve->mr_route = mr_route;
+ rve->mr_vif = mr_vif;
+ list_add_tail(&rve->route_node, &mr_route->evif_list);
+ list_add_tail(&rve->vif_node, &mr_vif->route_evif_list);
+ return 0;
+}
+
+static void
+mlxsw_sp_mr_route_evif_unlink(struct mlxsw_sp_mr_route_vif_entry *rve)
+{
+ list_del(&rve->route_node);
+ list_del(&rve->vif_node);
+ kfree(rve);
+}
+
+static void mlxsw_sp_mr_route_ivif_link(struct mlxsw_sp_mr_route *mr_route,
+ struct mlxsw_sp_mr_vif *mr_vif)
+{
+ mr_route->ivif.mr_route = mr_route;
+ mr_route->ivif.mr_vif = mr_vif;
+ list_add_tail(&mr_route->ivif.vif_node, &mr_vif->route_ivif_list);
+}
+
+static void mlxsw_sp_mr_route_ivif_unlink(struct mlxsw_sp_mr_route *mr_route)
+{
+ list_del(&mr_route->ivif.vif_node);
+}
+
+static int
+mlxsw_sp_mr_route_info_create(struct mlxsw_sp_mr_table *mr_table,
+ struct mlxsw_sp_mr_route *mr_route,
+ struct mlxsw_sp_mr_route_info *route_info)
+{
+ struct mlxsw_sp_mr_route_vif_entry *rve;
+ u16 *erif_indices;
+ u16 irif_index;
+ u16 erif = 0;
+
+ erif_indices = kmalloc_array(MAXVIFS, sizeof(*erif_indices),
+ GFP_KERNEL);
+ if (!erif_indices)
+ return -ENOMEM;
+
+ list_for_each_entry(rve, &mr_route->evif_list, route_node) {
+ if (mlxsw_sp_mr_vif_valid(rve->mr_vif)) {
+ u16 rifi = mlxsw_sp_rif_index(rve->mr_vif->rif);
+
+ erif_indices[erif++] = rifi;
+ }
+ }
+
+ if (mlxsw_sp_mr_vif_valid(mr_route->ivif.mr_vif))
+ irif_index = mlxsw_sp_rif_index(mr_route->ivif.mr_vif->rif);
+ else
+ irif_index = 0;
+
+ route_info->irif_index = irif_index;
+ route_info->erif_indices = erif_indices;
+ route_info->min_mtu = mr_route->min_mtu;
+ route_info->route_action = mr_route->route_action;
+ route_info->erif_num = erif;
+ return 0;
+}
+
+static void
+mlxsw_sp_mr_route_info_destroy(struct mlxsw_sp_mr_route_info *route_info)
+{
+ kfree(route_info->erif_indices);
+}
+
+static int mlxsw_sp_mr_route_write(struct mlxsw_sp_mr_table *mr_table,
+ struct mlxsw_sp_mr_route *mr_route,
+ bool replace)
+{
+ struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp;
+ struct mlxsw_sp_mr_route_info route_info;
+ struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+ int err;
+
+ err = mlxsw_sp_mr_route_info_create(mr_table, mr_route, &route_info);
+ if (err)
+ return err;
+
+ if (!replace) {
+ struct mlxsw_sp_mr_route_params route_params;
+
+ mr_route->route_priv = kzalloc(mr->mr_ops->route_priv_size,
+ GFP_KERNEL);
+ if (!mr_route->route_priv) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ route_params.key = mr_route->key;
+ route_params.value = route_info;
+ route_params.prio = mlxsw_sp_mr_route_prio(mr_route);
+ err = mr->mr_ops->route_create(mlxsw_sp, mr->priv,
+ mr_route->route_priv,
+ &route_params);
+ if (err)
+ kfree(mr_route->route_priv);
+ } else {
+ err = mr->mr_ops->route_update(mlxsw_sp, mr_route->route_priv,
+ &route_info);
+ }
+out:
+ mlxsw_sp_mr_route_info_destroy(&route_info);
+ return err;
+}
+
+static void mlxsw_sp_mr_route_erase(struct mlxsw_sp_mr_table *mr_table,
+ struct mlxsw_sp_mr_route *mr_route)
+{
+ struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp;
+ struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+
+ mr->mr_ops->route_destroy(mlxsw_sp, mr->priv, mr_route->route_priv);
+ kfree(mr_route->route_priv);
+}
+
+static struct mlxsw_sp_mr_route *
+mlxsw_sp_mr_route4_create(struct mlxsw_sp_mr_table *mr_table,
+ struct mfc_cache *mfc)
+{
+ struct mlxsw_sp_mr_route_vif_entry *rve, *tmp;
+ struct mlxsw_sp_mr_route *mr_route;
+ int err = 0;
+ int i;
+
+ /* Allocate and init a new route and fill it with parameters */
+ mr_route = kzalloc(sizeof(*mr_route), GFP_KERNEL);
+ if (!mr_route)
+ return ERR_PTR(-ENOMEM);
+ INIT_LIST_HEAD(&mr_route->evif_list);
+ mlxsw_sp_mr_route4_key(mr_table, &mr_route->key, mfc);
+
+ /* Find min_mtu and link iVIF and eVIFs */
+ mr_route->min_mtu = ETH_MAX_MTU;
+ ipmr_cache_hold(mfc);
+ mr_route->mfc4 = mfc;
+ mr_route->mr_table = mr_table;
+ for (i = 0; i < MAXVIFS; i++) {
+ if (mfc->mfc_un.res.ttls[i] != 255) {
+ err = mlxsw_sp_mr_route_evif_link(mr_route,
+ &mr_table->vifs[i]);
+ if (err)
+ goto err;
+ if (mr_table->vifs[i].dev &&
+ mr_table->vifs[i].dev->mtu < mr_route->min_mtu)
+ mr_route->min_mtu = mr_table->vifs[i].dev->mtu;
+ }
+ }
+ mlxsw_sp_mr_route_ivif_link(mr_route, &mr_table->vifs[mfc->mfc_parent]);
+
+ mr_route->route_action = mlxsw_sp_mr_route_action(mr_route);
+ return mr_route;
+err:
+ ipmr_cache_put(mfc);
+ list_for_each_entry_safe(rve, tmp, &mr_route->evif_list, route_node)
+ mlxsw_sp_mr_route_evif_unlink(rve);
+ kfree(mr_route);
+ return ERR_PTR(err);
+}
+
+static void mlxsw_sp_mr_route4_destroy(struct mlxsw_sp_mr_table *mr_table,
+ struct mlxsw_sp_mr_route *mr_route)
+{
+ struct mlxsw_sp_mr_route_vif_entry *rve, *tmp;
+
+ mlxsw_sp_mr_route_ivif_unlink(mr_route);
+ ipmr_cache_put(mr_route->mfc4);
+ list_for_each_entry_safe(rve, tmp, &mr_route->evif_list, route_node)
+ mlxsw_sp_mr_route_evif_unlink(rve);
+ kfree(mr_route);
+}
+
+static void mlxsw_sp_mr_route_destroy(struct mlxsw_sp_mr_table *mr_table,
+ struct mlxsw_sp_mr_route *mr_route)
+{
+ switch (mr_table->proto) {
+ case MLXSW_SP_L3_PROTO_IPV4:
+ mlxsw_sp_mr_route4_destroy(mr_table, mr_route);
+ break;
+ case MLXSW_SP_L3_PROTO_IPV6:
+ /* fall through */
+ default:
+ WARN_ON_ONCE(1);
+ }
+}
+
+static void mlxsw_sp_mr_mfc_offload_set(struct mlxsw_sp_mr_route *mr_route,
+ bool offload)
+{
+ switch (mr_route->mr_table->proto) {
+ case MLXSW_SP_L3_PROTO_IPV4:
+ if (offload)
+ mr_route->mfc4->mfc_flags |= MFC_OFFLOAD;
+ else
+ mr_route->mfc4->mfc_flags &= ~MFC_OFFLOAD;
+ break;
+ case MLXSW_SP_L3_PROTO_IPV6:
+ /* fall through */
+ default:
+ WARN_ON_ONCE(1);
+ }
+}
+
+static void mlxsw_sp_mr_mfc_offload_update(struct mlxsw_sp_mr_route *mr_route)
+{
+ bool offload;
+
+ offload = mr_route->route_action != MLXSW_SP_MR_ROUTE_ACTION_TRAP;
+ mlxsw_sp_mr_mfc_offload_set(mr_route, offload);
+}
+
+static void __mlxsw_sp_mr_route_del(struct mlxsw_sp_mr_table *mr_table,
+ struct mlxsw_sp_mr_route *mr_route)
+{
+ mlxsw_sp_mr_mfc_offload_set(mr_route, false);
+ mlxsw_sp_mr_route_erase(mr_table, mr_route);
+ rhashtable_remove_fast(&mr_table->route_ht, &mr_route->ht_node,
+ mlxsw_sp_mr_route_ht_params);
+ list_del(&mr_route->node);
+ mlxsw_sp_mr_route_destroy(mr_table, mr_route);
+}
+
+int mlxsw_sp_mr_route4_add(struct mlxsw_sp_mr_table *mr_table,
+ struct mfc_cache *mfc, bool replace)
+{
+ struct mlxsw_sp_mr_route *mr_orig_route = NULL;
+ struct mlxsw_sp_mr_route *mr_route;
+ int err;
+
+ /* If the route is a (*,*) route, abort, as these kind of routes are
+ * used for proxy routes.
+ */
+ if (mfc->mfc_origin == INADDR_ANY && mfc->mfc_mcastgrp == INADDR_ANY) {
+ dev_warn(mr_table->mlxsw_sp->bus_info->dev,
+ "Offloading proxy routes is not supported.\n");
+ return -EINVAL;
+ }
+
+ /* Create a new route */
+ mr_route = mlxsw_sp_mr_route4_create(mr_table, mfc);
+ if (IS_ERR(mr_route))
+ return PTR_ERR(mr_route);
+
+ /* Find any route with a matching key */
+ mr_orig_route = rhashtable_lookup_fast(&mr_table->route_ht,
+ &mr_route->key,
+ mlxsw_sp_mr_route_ht_params);
+ if (replace) {
+ /* On replace case, make the route point to the new route_priv.
+ */
+ if (WARN_ON(!mr_orig_route)) {
+ err = -ENOENT;
+ goto err_no_orig_route;
+ }
+ mr_route->route_priv = mr_orig_route->route_priv;
+ } else if (mr_orig_route) {
+ /* On non replace case, if another route with the same key was
+ * found, abort, as duplicate routes are used for proxy routes.
+ */
+ dev_warn(mr_table->mlxsw_sp->bus_info->dev,
+ "Offloading proxy routes is not supported.\n");
+ err = -EINVAL;
+ goto err_duplicate_route;
+ }
+
+ /* Put it in the table data-structures */
+ list_add_tail(&mr_route->node, &mr_table->route_list);
+ err = rhashtable_insert_fast(&mr_table->route_ht,
+ &mr_route->ht_node,
+ mlxsw_sp_mr_route_ht_params);
+ if (err)
+ goto err_rhashtable_insert;
+
+ /* Write the route to the hardware */
+ err = mlxsw_sp_mr_route_write(mr_table, mr_route, replace);
+ if (err)
+ goto err_mr_route_write;
+
+ /* Destroy the original route */
+ if (replace) {
+ rhashtable_remove_fast(&mr_table->route_ht,
+ &mr_orig_route->ht_node,
+ mlxsw_sp_mr_route_ht_params);
+ list_del(&mr_orig_route->node);
+ mlxsw_sp_mr_route4_destroy(mr_table, mr_orig_route);
+ }
+
+ mlxsw_sp_mr_mfc_offload_update(mr_route);
+ return 0;
+
+err_mr_route_write:
+ rhashtable_remove_fast(&mr_table->route_ht, &mr_route->ht_node,
+ mlxsw_sp_mr_route_ht_params);
+err_rhashtable_insert:
+ list_del(&mr_route->node);
+err_no_orig_route:
+err_duplicate_route:
+ mlxsw_sp_mr_route4_destroy(mr_table, mr_route);
+ return err;
+}
+
+void mlxsw_sp_mr_route4_del(struct mlxsw_sp_mr_table *mr_table,
+ struct mfc_cache *mfc)
+{
+ struct mlxsw_sp_mr_route *mr_route;
+ struct mlxsw_sp_mr_route_key key;
+
+ mlxsw_sp_mr_route4_key(mr_table, &key, mfc);
+ mr_route = rhashtable_lookup_fast(&mr_table->route_ht, &key,
+ mlxsw_sp_mr_route_ht_params);
+ if (mr_route)
+ __mlxsw_sp_mr_route_del(mr_table, mr_route);
+}
+
+/* Should be called after the VIF struct is updated */
+static int
+mlxsw_sp_mr_route_ivif_resolve(struct mlxsw_sp_mr_table *mr_table,
+ struct mlxsw_sp_mr_route_vif_entry *rve)
+{
+ struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp;
+ enum mlxsw_sp_mr_route_action route_action;
+ struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+ u16 irif_index;
+ int err;
+
+ route_action = mlxsw_sp_mr_route_action(rve->mr_route);
+ if (route_action == MLXSW_SP_MR_ROUTE_ACTION_TRAP)
+ return 0;
+
+ /* rve->mr_vif->rif is guaranteed to be valid at this stage */
+ irif_index = mlxsw_sp_rif_index(rve->mr_vif->rif);
+ err = mr->mr_ops->route_irif_update(mlxsw_sp, rve->mr_route->route_priv,
+ irif_index);
+ if (err)
+ return err;
+
+ err = mr->mr_ops->route_action_update(mlxsw_sp,
+ rve->mr_route->route_priv,
+ route_action);
+ if (err)
+ /* No need to rollback here because the iRIF change only takes
+ * place after the action has been updated.
+ */
+ return err;
+
+ rve->mr_route->route_action = route_action;
+ mlxsw_sp_mr_mfc_offload_update(rve->mr_route);
+ return 0;
+}
+
+static void
+mlxsw_sp_mr_route_ivif_unresolve(struct mlxsw_sp_mr_table *mr_table,
+ struct mlxsw_sp_mr_route_vif_entry *rve)
+{
+ struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp;
+ struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+
+ mr->mr_ops->route_action_update(mlxsw_sp, rve->mr_route->route_priv,
+ MLXSW_SP_MR_ROUTE_ACTION_TRAP);
+ rve->mr_route->route_action = MLXSW_SP_MR_ROUTE_ACTION_TRAP;
+ mlxsw_sp_mr_mfc_offload_update(rve->mr_route);
+}
+
+/* Should be called after the RIF struct is updated */
+static int
+mlxsw_sp_mr_route_evif_resolve(struct mlxsw_sp_mr_table *mr_table,
+ struct mlxsw_sp_mr_route_vif_entry *rve)
+{
+ struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp;
+ enum mlxsw_sp_mr_route_action route_action;
+ struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+ u16 erif_index = 0;
+ int err;
+
+ /* Update the route action, as the new eVIF can be a tunnel or a pimreg
+ * device which will require updating the action.
+ */
+ route_action = mlxsw_sp_mr_route_action(rve->mr_route);
+ if (route_action != rve->mr_route->route_action) {
+ err = mr->mr_ops->route_action_update(mlxsw_sp,
+ rve->mr_route->route_priv,
+ route_action);
+ if (err)
+ return err;
+ }
+
+ /* Add the eRIF */
+ if (mlxsw_sp_mr_vif_valid(rve->mr_vif)) {
+ erif_index = mlxsw_sp_rif_index(rve->mr_vif->rif);
+ err = mr->mr_ops->route_erif_add(mlxsw_sp,
+ rve->mr_route->route_priv,
+ erif_index);
+ if (err)
+ goto err_route_erif_add;
+ }
+
+ /* Update the minimum MTU */
+ if (rve->mr_vif->dev->mtu < rve->mr_route->min_mtu) {
+ rve->mr_route->min_mtu = rve->mr_vif->dev->mtu;
+ err = mr->mr_ops->route_min_mtu_update(mlxsw_sp,
+ rve->mr_route->route_priv,
+ rve->mr_route->min_mtu);
+ if (err)
+ goto err_route_min_mtu_update;
+ }
+
+ rve->mr_route->route_action = route_action;
+ mlxsw_sp_mr_mfc_offload_update(rve->mr_route);
+ return 0;
+
+err_route_min_mtu_update:
+ if (mlxsw_sp_mr_vif_valid(rve->mr_vif))
+ mr->mr_ops->route_erif_del(mlxsw_sp, rve->mr_route->route_priv,
+ erif_index);
+err_route_erif_add:
+ if (route_action != rve->mr_route->route_action)
+ mr->mr_ops->route_action_update(mlxsw_sp,
+ rve->mr_route->route_priv,
+ rve->mr_route->route_action);
+ return err;
+}
+
+/* Should be called before the RIF struct is updated */
+static void
+mlxsw_sp_mr_route_evif_unresolve(struct mlxsw_sp_mr_table *mr_table,
+ struct mlxsw_sp_mr_route_vif_entry *rve)
+{
+ struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp;
+ enum mlxsw_sp_mr_route_action route_action;
+ struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+ u16 rifi;
+
+ /* If the unresolved RIF was not valid, no need to delete it */
+ if (!mlxsw_sp_mr_vif_valid(rve->mr_vif))
+ return;
+
+ /* Update the route action: if there is only one valid eVIF in the
+ * route, set the action to trap as the VIF deletion will lead to zero
+ * valid eVIFs. On any other case, use the mlxsw_sp_mr_route_action to
+ * determine the route action.
+ */
+ if (mlxsw_sp_mr_route_valid_evifs_num(rve->mr_route) == 1)
+ route_action = MLXSW_SP_MR_ROUTE_ACTION_TRAP;
+ else
+ route_action = mlxsw_sp_mr_route_action(rve->mr_route);
+ if (route_action != rve->mr_route->route_action)
+ mr->mr_ops->route_action_update(mlxsw_sp,
+ rve->mr_route->route_priv,
+ route_action);
+
+ /* Delete the erif from the route */
+ rifi = mlxsw_sp_rif_index(rve->mr_vif->rif);
+ mr->mr_ops->route_erif_del(mlxsw_sp, rve->mr_route->route_priv, rifi);
+ rve->mr_route->route_action = route_action;
+ mlxsw_sp_mr_mfc_offload_update(rve->mr_route);
+}
+
+static int mlxsw_sp_mr_vif_resolve(struct mlxsw_sp_mr_table *mr_table,
+ struct net_device *dev,
+ struct mlxsw_sp_mr_vif *mr_vif,
+ unsigned long vif_flags,
+ const struct mlxsw_sp_rif *rif)
+{
+ struct mlxsw_sp_mr_route_vif_entry *irve, *erve;
+ int err;
+
+ /* Update the VIF */
+ mr_vif->dev = dev;
+ mr_vif->rif = rif;
+ mr_vif->vif_flags = vif_flags;
+
+ /* Update all routes where this VIF is used as an unresolved iRIF */
+ list_for_each_entry(irve, &mr_vif->route_ivif_list, vif_node) {
+ err = mlxsw_sp_mr_route_ivif_resolve(mr_table, irve);
+ if (err)
+ goto err_irif_unresolve;
+ }
+
+ /* Update all routes where this VIF is used as an unresolved eRIF */
+ list_for_each_entry(erve, &mr_vif->route_evif_list, vif_node) {
+ err = mlxsw_sp_mr_route_evif_resolve(mr_table, erve);
+ if (err)
+ goto err_erif_unresolve;
+ }
+ return 0;
+
+err_erif_unresolve:
+ list_for_each_entry_from_reverse(erve, &mr_vif->route_evif_list,
+ vif_node)
+ mlxsw_sp_mr_route_evif_unresolve(mr_table, erve);
+err_irif_unresolve:
+ list_for_each_entry_from_reverse(irve, &mr_vif->route_ivif_list,
+ vif_node)
+ mlxsw_sp_mr_route_ivif_unresolve(mr_table, irve);
+ mr_vif->rif = NULL;
+ return err;
+}
+
+static void mlxsw_sp_mr_vif_unresolve(struct mlxsw_sp_mr_table *mr_table,
+ struct net_device *dev,
+ struct mlxsw_sp_mr_vif *mr_vif)
+{
+ struct mlxsw_sp_mr_route_vif_entry *rve;
+
+ /* Update all routes where this VIF is used as an unresolved eRIF */
+ list_for_each_entry(rve, &mr_vif->route_evif_list, vif_node)
+ mlxsw_sp_mr_route_evif_unresolve(mr_table, rve);
+
+ /* Update all routes where this VIF is used as an unresolved iRIF */
+ list_for_each_entry(rve, &mr_vif->route_ivif_list, vif_node)
+ mlxsw_sp_mr_route_ivif_unresolve(mr_table, rve);
+
+ /* Update the VIF */
+ mr_vif->dev = dev;
+ mr_vif->rif = NULL;
+}
+
+int mlxsw_sp_mr_vif_add(struct mlxsw_sp_mr_table *mr_table,
+ struct net_device *dev, vifi_t vif_index,
+ unsigned long vif_flags, const struct mlxsw_sp_rif *rif)
+{
+ struct mlxsw_sp_mr_vif *mr_vif = &mr_table->vifs[vif_index];
+
+ if (WARN_ON(vif_index >= MAXVIFS))
+ return -EINVAL;
+ if (mr_vif->dev)
+ return -EEXIST;
+ return mlxsw_sp_mr_vif_resolve(mr_table, dev, mr_vif, vif_flags, rif);
+}
+
+void mlxsw_sp_mr_vif_del(struct mlxsw_sp_mr_table *mr_table, vifi_t vif_index)
+{
+ struct mlxsw_sp_mr_vif *mr_vif = &mr_table->vifs[vif_index];
+
+ if (WARN_ON(vif_index >= MAXVIFS))
+ return;
+ if (WARN_ON(!mr_vif->dev))
+ return;
+ mlxsw_sp_mr_vif_unresolve(mr_table, NULL, mr_vif);
+}
+
+struct mlxsw_sp_mr_vif *
+mlxsw_sp_mr_dev_vif_lookup(struct mlxsw_sp_mr_table *mr_table,
+ const struct net_device *dev)
+{
+ vifi_t vif_index;
+
+ for (vif_index = 0; vif_index < MAXVIFS; vif_index++)
+ if (mr_table->vifs[vif_index].dev == dev)
+ return &mr_table->vifs[vif_index];
+ return NULL;
+}
+
+int mlxsw_sp_mr_rif_add(struct mlxsw_sp_mr_table *mr_table,
+ const struct mlxsw_sp_rif *rif)
+{
+ const struct net_device *rif_dev = mlxsw_sp_rif_dev(rif);
+ struct mlxsw_sp_mr_vif *mr_vif;
+
+ if (!rif_dev)
+ return 0;
+
+ mr_vif = mlxsw_sp_mr_dev_vif_lookup(mr_table, rif_dev);
+ if (!mr_vif)
+ return 0;
+ return mlxsw_sp_mr_vif_resolve(mr_table, mr_vif->dev, mr_vif,
+ mr_vif->vif_flags, rif);
+}
+
+void mlxsw_sp_mr_rif_del(struct mlxsw_sp_mr_table *mr_table,
+ const struct mlxsw_sp_rif *rif)
+{
+ const struct net_device *rif_dev = mlxsw_sp_rif_dev(rif);
+ struct mlxsw_sp_mr_vif *mr_vif;
+
+ if (!rif_dev)
+ return;
+
+ mr_vif = mlxsw_sp_mr_dev_vif_lookup(mr_table, rif_dev);
+ if (!mr_vif)
+ return;
+ mlxsw_sp_mr_vif_unresolve(mr_table, mr_vif->dev, mr_vif);
+}
+
+void mlxsw_sp_mr_rif_mtu_update(struct mlxsw_sp_mr_table *mr_table,
+ const struct mlxsw_sp_rif *rif, int mtu)
+{
+ const struct net_device *rif_dev = mlxsw_sp_rif_dev(rif);
+ struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp;
+ struct mlxsw_sp_mr_route_vif_entry *rve;
+ struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+ struct mlxsw_sp_mr_vif *mr_vif;
+
+ if (!rif_dev)
+ return;
+
+ /* Search for a VIF that use that RIF */
+ mr_vif = mlxsw_sp_mr_dev_vif_lookup(mr_table, rif_dev);
+ if (!mr_vif)
+ return;
+
+ /* Update all the routes that uses that VIF as eVIF */
+ list_for_each_entry(rve, &mr_vif->route_evif_list, vif_node) {
+ if (mtu < rve->mr_route->min_mtu) {
+ rve->mr_route->min_mtu = mtu;
+ mr->mr_ops->route_min_mtu_update(mlxsw_sp,
+ rve->mr_route->route_priv,
+ mtu);
+ }
+ }
+}
+
+struct mlxsw_sp_mr_table *mlxsw_sp_mr_table_create(struct mlxsw_sp *mlxsw_sp,
+ u32 vr_id,
+ enum mlxsw_sp_l3proto proto)
+{
+ struct mlxsw_sp_mr_route_params catchall_route_params = {
+ .prio = MLXSW_SP_MR_ROUTE_PRIO_CATCHALL,
+ .key = {
+ .vrid = vr_id,
+ },
+ .value = {
+ .route_action = MLXSW_SP_MR_ROUTE_ACTION_TRAP,
+ }
+ };
+ struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+ struct mlxsw_sp_mr_table *mr_table;
+ int err;
+ int i;
+
+ mr_table = kzalloc(sizeof(*mr_table) + mr->mr_ops->route_priv_size,
+ GFP_KERNEL);
+ if (!mr_table)
+ return ERR_PTR(-ENOMEM);
+
+ mr_table->vr_id = vr_id;
+ mr_table->mlxsw_sp = mlxsw_sp;
+ mr_table->proto = proto;
+ INIT_LIST_HEAD(&mr_table->route_list);
+
+ err = rhashtable_init(&mr_table->route_ht,
+ &mlxsw_sp_mr_route_ht_params);
+ if (err)
+ goto err_route_rhashtable_init;
+
+ for (i = 0; i < MAXVIFS; i++) {
+ INIT_LIST_HEAD(&mr_table->vifs[i].route_evif_list);
+ INIT_LIST_HEAD(&mr_table->vifs[i].route_ivif_list);
+ }
+
+ err = mr->mr_ops->route_create(mlxsw_sp, mr->priv,
+ mr_table->catchall_route_priv,
+ &catchall_route_params);
+ if (err)
+ goto err_ops_route_create;
+ list_add_tail(&mr_table->node, &mr->table_list);
+ return mr_table;
+
+err_ops_route_create:
+ rhashtable_destroy(&mr_table->route_ht);
+err_route_rhashtable_init:
+ kfree(mr_table);
+ return ERR_PTR(err);
+}
+
+void mlxsw_sp_mr_table_destroy(struct mlxsw_sp_mr_table *mr_table)
+{
+ struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp;
+ struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+
+ WARN_ON(!mlxsw_sp_mr_table_empty(mr_table));
+ list_del(&mr_table->node);
+ mr->mr_ops->route_destroy(mlxsw_sp, mr->priv,
+ &mr_table->catchall_route_priv);
+ rhashtable_destroy(&mr_table->route_ht);
+ kfree(mr_table);
+}
+
+void mlxsw_sp_mr_table_flush(struct mlxsw_sp_mr_table *mr_table)
+{
+ struct mlxsw_sp_mr_route *mr_route, *tmp;
+ int i;
+
+ list_for_each_entry_safe(mr_route, tmp, &mr_table->route_list, node)
+ __mlxsw_sp_mr_route_del(mr_table, mr_route);
+
+ for (i = 0; i < MAXVIFS; i++) {
+ mr_table->vifs[i].dev = NULL;
+ mr_table->vifs[i].rif = NULL;
+ }
+}
+
+bool mlxsw_sp_mr_table_empty(const struct mlxsw_sp_mr_table *mr_table)
+{
+ int i;
+
+ for (i = 0; i < MAXVIFS; i++)
+ if (mr_table->vifs[i].dev)
+ return false;
+ return list_empty(&mr_table->route_list);
+}
+
+static void mlxsw_sp_mr_route_stats_update(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_mr_route *mr_route)
+{
+ struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+ u64 packets, bytes;
+
+ if (mr_route->route_action == MLXSW_SP_MR_ROUTE_ACTION_TRAP)
+ return;
+
+ mr->mr_ops->route_stats(mlxsw_sp, mr_route->route_priv, &packets,
+ &bytes);
+
+ switch (mr_route->mr_table->proto) {
+ case MLXSW_SP_L3_PROTO_IPV4:
+ if (mr_route->mfc4->mfc_un.res.pkt != packets)
+ mr_route->mfc4->mfc_un.res.lastuse = jiffies;
+ mr_route->mfc4->mfc_un.res.pkt = packets;
+ mr_route->mfc4->mfc_un.res.bytes = bytes;
+ break;
+ case MLXSW_SP_L3_PROTO_IPV6:
+ /* fall through */
+ default:
+ WARN_ON_ONCE(1);
+ }
+}
+
+static void mlxsw_sp_mr_stats_update(struct work_struct *work)
+{
+ struct mlxsw_sp_mr *mr = container_of(work, struct mlxsw_sp_mr,
+ stats_update_dw.work);
+ struct mlxsw_sp_mr_table *mr_table;
+ struct mlxsw_sp_mr_route *mr_route;
+ unsigned long interval;
+
+ rtnl_lock();
+ list_for_each_entry(mr_table, &mr->table_list, node)
+ list_for_each_entry(mr_route, &mr_table->route_list, node)
+ mlxsw_sp_mr_route_stats_update(mr_table->mlxsw_sp,
+ mr_route);
+ rtnl_unlock();
+
+ interval = msecs_to_jiffies(MLXSW_SP_MR_ROUTES_COUNTER_UPDATE_INTERVAL);
+ mlxsw_core_schedule_dw(&mr->stats_update_dw, interval);
+}
+
+int mlxsw_sp_mr_init(struct mlxsw_sp *mlxsw_sp,
+ const struct mlxsw_sp_mr_ops *mr_ops)
+{
+ struct mlxsw_sp_mr *mr;
+ unsigned long interval;
+ int err;
+
+ mr = kzalloc(sizeof(*mr) + mr_ops->priv_size, GFP_KERNEL);
+ if (!mr)
+ return -ENOMEM;
+ mr->mr_ops = mr_ops;
+ mlxsw_sp->mr = mr;
+ INIT_LIST_HEAD(&mr->table_list);
+
+ err = mr_ops->init(mlxsw_sp, mr->priv);
+ if (err)
+ goto err;
+
+ /* Create the delayed work for counter updates */
+ INIT_DELAYED_WORK(&mr->stats_update_dw, mlxsw_sp_mr_stats_update);
+ interval = msecs_to_jiffies(MLXSW_SP_MR_ROUTES_COUNTER_UPDATE_INTERVAL);
+ mlxsw_core_schedule_dw(&mr->stats_update_dw, interval);
+ return 0;
+err:
+ kfree(mr);
+ return err;
+}
+
+void mlxsw_sp_mr_fini(struct mlxsw_sp *mlxsw_sp)
+{
+ struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
+
+ cancel_delayed_work_sync(&mr->stats_update_dw);
+ mr->mr_ops->fini(mr->priv);
+ kfree(mr);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
new file mode 100644
index 000000000000..5d26a122af49
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
@@ -0,0 +1,134 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_SPECTRUM_MCROUTER_H
+#define _MLXSW_SPECTRUM_MCROUTER_H
+
+#include <linux/mroute.h>
+#include "spectrum_router.h"
+#include "spectrum.h"
+
+enum mlxsw_sp_mr_route_action {
+ MLXSW_SP_MR_ROUTE_ACTION_FORWARD,
+ MLXSW_SP_MR_ROUTE_ACTION_TRAP,
+ MLXSW_SP_MR_ROUTE_ACTION_TRAP_AND_FORWARD,
+};
+
+enum mlxsw_sp_mr_route_prio {
+ MLXSW_SP_MR_ROUTE_PRIO_SG,
+ MLXSW_SP_MR_ROUTE_PRIO_STARG,
+ MLXSW_SP_MR_ROUTE_PRIO_CATCHALL,
+ __MLXSW_SP_MR_ROUTE_PRIO_MAX
+};
+
+#define MLXSW_SP_MR_ROUTE_PRIO_MAX (__MLXSW_SP_MR_ROUTE_PRIO_MAX - 1)
+
+struct mlxsw_sp_mr_route_key {
+ int vrid;
+ enum mlxsw_sp_l3proto proto;
+ union mlxsw_sp_l3addr group;
+ union mlxsw_sp_l3addr group_mask;
+ union mlxsw_sp_l3addr source;
+ union mlxsw_sp_l3addr source_mask;
+};
+
+struct mlxsw_sp_mr_route_info {
+ enum mlxsw_sp_mr_route_action route_action;
+ u16 irif_index;
+ u16 *erif_indices;
+ size_t erif_num;
+ u16 min_mtu;
+};
+
+struct mlxsw_sp_mr_route_params {
+ struct mlxsw_sp_mr_route_key key;
+ struct mlxsw_sp_mr_route_info value;
+ enum mlxsw_sp_mr_route_prio prio;
+};
+
+struct mlxsw_sp_mr_ops {
+ int priv_size;
+ int route_priv_size;
+ int (*init)(struct mlxsw_sp *mlxsw_sp, void *priv);
+ int (*route_create)(struct mlxsw_sp *mlxsw_sp, void *priv,
+ void *route_priv,
+ struct mlxsw_sp_mr_route_params *route_params);
+ int (*route_update)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+ struct mlxsw_sp_mr_route_info *route_info);
+ int (*route_stats)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+ u64 *packets, u64 *bytes);
+ int (*route_action_update)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+ enum mlxsw_sp_mr_route_action route_action);
+ int (*route_min_mtu_update)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+ u16 min_mtu);
+ int (*route_irif_update)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+ u16 irif_index);
+ int (*route_erif_add)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+ u16 erif_index);
+ int (*route_erif_del)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+ u16 erif_index);
+ void (*route_destroy)(struct mlxsw_sp *mlxsw_sp, void *priv,
+ void *route_priv);
+ void (*fini)(void *priv);
+};
+
+struct mlxsw_sp_mr;
+struct mlxsw_sp_mr_table;
+
+int mlxsw_sp_mr_init(struct mlxsw_sp *mlxsw_sp,
+ const struct mlxsw_sp_mr_ops *mr_ops);
+void mlxsw_sp_mr_fini(struct mlxsw_sp *mlxsw_sp);
+int mlxsw_sp_mr_route4_add(struct mlxsw_sp_mr_table *mr_table,
+ struct mfc_cache *mfc, bool replace);
+void mlxsw_sp_mr_route4_del(struct mlxsw_sp_mr_table *mr_table,
+ struct mfc_cache *mfc);
+int mlxsw_sp_mr_vif_add(struct mlxsw_sp_mr_table *mr_table,
+ struct net_device *dev, vifi_t vif_index,
+ unsigned long vif_flags,
+ const struct mlxsw_sp_rif *rif);
+void mlxsw_sp_mr_vif_del(struct mlxsw_sp_mr_table *mr_table, vifi_t vif_index);
+int mlxsw_sp_mr_rif_add(struct mlxsw_sp_mr_table *mr_table,
+ const struct mlxsw_sp_rif *rif);
+void mlxsw_sp_mr_rif_del(struct mlxsw_sp_mr_table *mr_table,
+ const struct mlxsw_sp_rif *rif);
+void mlxsw_sp_mr_rif_mtu_update(struct mlxsw_sp_mr_table *mr_table,
+ const struct mlxsw_sp_rif *rif, int mtu);
+struct mlxsw_sp_mr_table *mlxsw_sp_mr_table_create(struct mlxsw_sp *mlxsw_sp,
+ u32 tb_id,
+ enum mlxsw_sp_l3proto proto);
+void mlxsw_sp_mr_table_destroy(struct mlxsw_sp_mr_table *mr_table);
+void mlxsw_sp_mr_table_flush(struct mlxsw_sp_mr_table *mr_table);
+bool mlxsw_sp_mr_table_empty(const struct mlxsw_sp_mr_table *mr_table);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
new file mode 100644
index 000000000000..39c21c70ac32
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
@@ -0,0 +1,838 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/parman.h>
+
+#include "reg.h"
+#include "spectrum.h"
+#include "core_acl_flex_actions.h"
+#include "spectrum_mr.h"
+
+struct mlxsw_sp_mr_tcam_region {
+ struct mlxsw_sp *mlxsw_sp;
+ enum mlxsw_reg_rtar_key_type rtar_key_type;
+ struct parman *parman;
+ struct parman_prio *parman_prios;
+};
+
+struct mlxsw_sp_mr_tcam {
+ struct mlxsw_sp_mr_tcam_region ipv4_tcam_region;
+};
+
+/* This struct maps to one RIGR2 register entry */
+struct mlxsw_sp_mr_erif_sublist {
+ struct list_head list;
+ u32 rigr2_kvdl_index;
+ int num_erifs;
+ u16 erif_indices[MLXSW_REG_RIGR2_MAX_ERIFS];
+ bool synced;
+};
+
+struct mlxsw_sp_mr_tcam_erif_list {
+ struct list_head erif_sublists;
+ u32 kvdl_index;
+};
+
+static bool
+mlxsw_sp_mr_erif_sublist_full(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_mr_erif_sublist *erif_sublist)
+{
+ int erif_list_entries = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+ MC_ERIF_LIST_ENTRIES);
+
+ return erif_sublist->num_erifs == erif_list_entries;
+}
+
+static void
+mlxsw_sp_mr_erif_list_init(struct mlxsw_sp_mr_tcam_erif_list *erif_list)
+{
+ INIT_LIST_HEAD(&erif_list->erif_sublists);
+}
+
+#define MLXSW_SP_KVDL_RIGR2_SIZE 1
+
+static struct mlxsw_sp_mr_erif_sublist *
+mlxsw_sp_mr_erif_sublist_create(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_mr_tcam_erif_list *erif_list)
+{
+ struct mlxsw_sp_mr_erif_sublist *erif_sublist;
+ int err;
+
+ erif_sublist = kzalloc(sizeof(*erif_sublist), GFP_KERNEL);
+ if (!erif_sublist)
+ return ERR_PTR(-ENOMEM);
+ err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_RIGR2_SIZE,
+ &erif_sublist->rigr2_kvdl_index);
+ if (err) {
+ kfree(erif_sublist);
+ return ERR_PTR(err);
+ }
+
+ list_add_tail(&erif_sublist->list, &erif_list->erif_sublists);
+ return erif_sublist;
+}
+
+static void
+mlxsw_sp_mr_erif_sublist_destroy(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_mr_erif_sublist *erif_sublist)
+{
+ list_del(&erif_sublist->list);
+ mlxsw_sp_kvdl_free(mlxsw_sp, erif_sublist->rigr2_kvdl_index);
+ kfree(erif_sublist);
+}
+
+static int
+mlxsw_sp_mr_erif_list_add(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_mr_tcam_erif_list *erif_list,
+ u16 erif_index)
+{
+ struct mlxsw_sp_mr_erif_sublist *sublist;
+
+ /* If either there is no erif_entry or the last one is full, allocate a
+ * new one.
+ */
+ if (list_empty(&erif_list->erif_sublists)) {
+ sublist = mlxsw_sp_mr_erif_sublist_create(mlxsw_sp, erif_list);
+ if (IS_ERR(sublist))
+ return PTR_ERR(sublist);
+ erif_list->kvdl_index = sublist->rigr2_kvdl_index;
+ } else {
+ sublist = list_last_entry(&erif_list->erif_sublists,
+ struct mlxsw_sp_mr_erif_sublist,
+ list);
+ sublist->synced = false;
+ if (mlxsw_sp_mr_erif_sublist_full(mlxsw_sp, sublist)) {
+ sublist = mlxsw_sp_mr_erif_sublist_create(mlxsw_sp,
+ erif_list);
+ if (IS_ERR(sublist))
+ return PTR_ERR(sublist);
+ }
+ }
+
+ /* Add the eRIF to the last entry's last index */
+ sublist->erif_indices[sublist->num_erifs++] = erif_index;
+ return 0;
+}
+
+static void
+mlxsw_sp_mr_erif_list_flush(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_mr_tcam_erif_list *erif_list)
+{
+ struct mlxsw_sp_mr_erif_sublist *erif_sublist, *tmp;
+
+ list_for_each_entry_safe(erif_sublist, tmp, &erif_list->erif_sublists,
+ list)
+ mlxsw_sp_mr_erif_sublist_destroy(mlxsw_sp, erif_sublist);
+}
+
+static int
+mlxsw_sp_mr_erif_list_commit(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_mr_tcam_erif_list *erif_list)
+{
+ struct mlxsw_sp_mr_erif_sublist *curr_sublist;
+ char rigr2_pl[MLXSW_REG_RIGR2_LEN];
+ int err;
+ int i;
+
+ list_for_each_entry(curr_sublist, &erif_list->erif_sublists, list) {
+ if (curr_sublist->synced)
+ continue;
+
+ /* If the sublist is not the last one, pack the next index */
+ if (list_is_last(&curr_sublist->list,
+ &erif_list->erif_sublists)) {
+ mlxsw_reg_rigr2_pack(rigr2_pl,
+ curr_sublist->rigr2_kvdl_index,
+ false, 0);
+ } else {
+ struct mlxsw_sp_mr_erif_sublist *next_sublist;
+
+ next_sublist = list_next_entry(curr_sublist, list);
+ mlxsw_reg_rigr2_pack(rigr2_pl,
+ curr_sublist->rigr2_kvdl_index,
+ true,
+ next_sublist->rigr2_kvdl_index);
+ }
+
+ /* Pack all the erifs */
+ for (i = 0; i < curr_sublist->num_erifs; i++) {
+ u16 erif_index = curr_sublist->erif_indices[i];
+
+ mlxsw_reg_rigr2_erif_entry_pack(rigr2_pl, i, true,
+ erif_index);
+ }
+
+ /* Write the entry */
+ err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rigr2),
+ rigr2_pl);
+ if (err)
+ /* No need of a rollback here because this
+ * hardware entry should not be pointed yet.
+ */
+ return err;
+ curr_sublist->synced = true;
+ }
+ return 0;
+}
+
+static void mlxsw_sp_mr_erif_list_move(struct mlxsw_sp_mr_tcam_erif_list *to,
+ struct mlxsw_sp_mr_tcam_erif_list *from)
+{
+ list_splice(&from->erif_sublists, &to->erif_sublists);
+ to->kvdl_index = from->kvdl_index;
+}
+
+struct mlxsw_sp_mr_tcam_route {
+ struct mlxsw_sp_mr_tcam_erif_list erif_list;
+ struct mlxsw_afa_block *afa_block;
+ u32 counter_index;
+ struct parman_item parman_item;
+ struct parman_prio *parman_prio;
+ enum mlxsw_sp_mr_route_action action;
+ struct mlxsw_sp_mr_route_key key;
+ u16 irif_index;
+ u16 min_mtu;
+};
+
+static struct mlxsw_afa_block *
+mlxsw_sp_mr_tcam_afa_block_create(struct mlxsw_sp *mlxsw_sp,
+ enum mlxsw_sp_mr_route_action route_action,
+ u16 irif_index, u32 counter_index,
+ u16 min_mtu,
+ struct mlxsw_sp_mr_tcam_erif_list *erif_list)
+{
+ struct mlxsw_afa_block *afa_block;
+ int err;
+
+ afa_block = mlxsw_afa_block_create(mlxsw_sp->afa);
+ if (!afa_block)
+ return ERR_PTR(-ENOMEM);
+
+ err = mlxsw_afa_block_append_counter(afa_block, counter_index);
+ if (err)
+ goto err;
+
+ switch (route_action) {
+ case MLXSW_SP_MR_ROUTE_ACTION_TRAP:
+ err = mlxsw_afa_block_append_trap(afa_block,
+ MLXSW_TRAP_ID_ACL1);
+ if (err)
+ goto err;
+ break;
+ case MLXSW_SP_MR_ROUTE_ACTION_TRAP_AND_FORWARD:
+ case MLXSW_SP_MR_ROUTE_ACTION_FORWARD:
+ /* If we are about to append a multicast router action, commit
+ * the erif_list.
+ */
+ err = mlxsw_sp_mr_erif_list_commit(mlxsw_sp, erif_list);
+ if (err)
+ goto err;
+
+ err = mlxsw_afa_block_append_mcrouter(afa_block, irif_index,
+ min_mtu, false,
+ erif_list->kvdl_index);
+ if (err)
+ goto err;
+
+ if (route_action == MLXSW_SP_MR_ROUTE_ACTION_TRAP_AND_FORWARD) {
+ err = mlxsw_afa_block_append_trap_and_forward(afa_block,
+ MLXSW_TRAP_ID_ACL2);
+ if (err)
+ goto err;
+ }
+ break;
+ default:
+ err = -EINVAL;
+ goto err;
+ }
+
+ err = mlxsw_afa_block_commit(afa_block);
+ if (err)
+ goto err;
+ return afa_block;
+err:
+ mlxsw_afa_block_destroy(afa_block);
+ return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_mr_tcam_afa_block_destroy(struct mlxsw_afa_block *afa_block)
+{
+ mlxsw_afa_block_destroy(afa_block);
+}
+
+static int mlxsw_sp_mr_tcam_route_replace(struct mlxsw_sp *mlxsw_sp,
+ struct parman_item *parman_item,
+ struct mlxsw_sp_mr_route_key *key,
+ struct mlxsw_afa_block *afa_block)
+{
+ char rmft2_pl[MLXSW_REG_RMFT2_LEN];
+
+ switch (key->proto) {
+ case MLXSW_SP_L3_PROTO_IPV4:
+ mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, true, parman_item->index,
+ key->vrid,
+ MLXSW_REG_RMFT2_IRIF_MASK_IGNORE, 0,
+ ntohl(key->group.addr4),
+ ntohl(key->group_mask.addr4),
+ ntohl(key->source.addr4),
+ ntohl(key->source_mask.addr4),
+ mlxsw_afa_block_first_set(afa_block));
+ break;
+ case MLXSW_SP_L3_PROTO_IPV6:
+ default:
+ WARN_ON_ONCE(1);
+ }
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
+}
+
+static int mlxsw_sp_mr_tcam_route_remove(struct mlxsw_sp *mlxsw_sp, int vrid,
+ struct parman_item *parman_item)
+{
+ char rmft2_pl[MLXSW_REG_RMFT2_LEN];
+
+ mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, false, parman_item->index, vrid,
+ 0, 0, 0, 0, 0, 0, NULL);
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
+}
+
+static int
+mlxsw_sp_mr_tcam_erif_populate(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_mr_tcam_erif_list *erif_list,
+ struct mlxsw_sp_mr_route_info *route_info)
+{
+ int err;
+ int i;
+
+ for (i = 0; i < route_info->erif_num; i++) {
+ u16 erif_index = route_info->erif_indices[i];
+
+ err = mlxsw_sp_mr_erif_list_add(mlxsw_sp, erif_list,
+ erif_index);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
+static int
+mlxsw_sp_mr_tcam_route_parman_item_add(struct mlxsw_sp_mr_tcam *mr_tcam,
+ struct mlxsw_sp_mr_tcam_route *route,
+ enum mlxsw_sp_mr_route_prio prio)
+{
+ struct parman_prio *parman_prio = NULL;
+ int err;
+
+ switch (route->key.proto) {
+ case MLXSW_SP_L3_PROTO_IPV4:
+ parman_prio = &mr_tcam->ipv4_tcam_region.parman_prios[prio];
+ err = parman_item_add(mr_tcam->ipv4_tcam_region.parman,
+ parman_prio, &route->parman_item);
+ if (err)
+ return err;
+ break;
+ case MLXSW_SP_L3_PROTO_IPV6:
+ default:
+ WARN_ON_ONCE(1);
+ }
+ route->parman_prio = parman_prio;
+ return 0;
+}
+
+static void
+mlxsw_sp_mr_tcam_route_parman_item_remove(struct mlxsw_sp_mr_tcam *mr_tcam,
+ struct mlxsw_sp_mr_tcam_route *route)
+{
+ switch (route->key.proto) {
+ case MLXSW_SP_L3_PROTO_IPV4:
+ parman_item_remove(mr_tcam->ipv4_tcam_region.parman,
+ route->parman_prio, &route->parman_item);
+ break;
+ case MLXSW_SP_L3_PROTO_IPV6:
+ default:
+ WARN_ON_ONCE(1);
+ }
+}
+
+static int
+mlxsw_sp_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv,
+ void *route_priv,
+ struct mlxsw_sp_mr_route_params *route_params)
+{
+ struct mlxsw_sp_mr_tcam_route *route = route_priv;
+ struct mlxsw_sp_mr_tcam *mr_tcam = priv;
+ int err;
+
+ route->key = route_params->key;
+ route->irif_index = route_params->value.irif_index;
+ route->min_mtu = route_params->value.min_mtu;
+ route->action = route_params->value.route_action;
+
+ /* Create the egress RIFs list */
+ mlxsw_sp_mr_erif_list_init(&route->erif_list);
+ err = mlxsw_sp_mr_tcam_erif_populate(mlxsw_sp, &route->erif_list,
+ &route_params->value);
+ if (err)
+ goto err_erif_populate;
+
+ /* Create the flow counter */
+ err = mlxsw_sp_flow_counter_alloc(mlxsw_sp, &route->counter_index);
+ if (err)
+ goto err_counter_alloc;
+
+ /* Create the flexible action block */
+ route->afa_block = mlxsw_sp_mr_tcam_afa_block_create(mlxsw_sp,
+ route->action,
+ route->irif_index,
+ route->counter_index,
+ route->min_mtu,
+ &route->erif_list);
+ if (IS_ERR(route->afa_block)) {
+ err = PTR_ERR(route->afa_block);
+ goto err_afa_block_create;
+ }
+
+ /* Allocate place in the TCAM */
+ err = mlxsw_sp_mr_tcam_route_parman_item_add(mr_tcam, route,
+ route_params->prio);
+ if (err)
+ goto err_parman_item_add;
+
+ /* Write the route to the TCAM */
+ err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
+ &route->key, route->afa_block);
+ if (err)
+ goto err_route_replace;
+ return 0;
+
+err_route_replace:
+ mlxsw_sp_mr_tcam_route_parman_item_remove(mr_tcam, route);
+err_parman_item_add:
+ mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
+err_afa_block_create:
+ mlxsw_sp_flow_counter_free(mlxsw_sp, route->counter_index);
+err_erif_populate:
+err_counter_alloc:
+ mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &route->erif_list);
+ return err;
+}
+
+static void mlxsw_sp_mr_tcam_route_destroy(struct mlxsw_sp *mlxsw_sp,
+ void *priv, void *route_priv)
+{
+ struct mlxsw_sp_mr_tcam_route *route = route_priv;
+ struct mlxsw_sp_mr_tcam *mr_tcam = priv;
+
+ mlxsw_sp_mr_tcam_route_remove(mlxsw_sp, route->key.vrid,
+ &route->parman_item);
+ mlxsw_sp_mr_tcam_route_parman_item_remove(mr_tcam, route);
+ mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
+ mlxsw_sp_flow_counter_free(mlxsw_sp, route->counter_index);
+ mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &route->erif_list);
+}
+
+static int mlxsw_sp_mr_tcam_route_stats(struct mlxsw_sp *mlxsw_sp,
+ void *route_priv, u64 *packets,
+ u64 *bytes)
+{
+ struct mlxsw_sp_mr_tcam_route *route = route_priv;
+
+ return mlxsw_sp_flow_counter_get(mlxsw_sp, route->counter_index,
+ packets, bytes);
+}
+
+static int
+mlxsw_sp_mr_tcam_route_action_update(struct mlxsw_sp *mlxsw_sp,
+ void *route_priv,
+ enum mlxsw_sp_mr_route_action route_action)
+{
+ struct mlxsw_sp_mr_tcam_route *route = route_priv;
+ struct mlxsw_afa_block *afa_block;
+ int err;
+
+ /* Create a new flexible action block */
+ afa_block = mlxsw_sp_mr_tcam_afa_block_create(mlxsw_sp, route_action,
+ route->irif_index,
+ route->counter_index,
+ route->min_mtu,
+ &route->erif_list);
+ if (IS_ERR(afa_block))
+ return PTR_ERR(afa_block);
+
+ /* Update the TCAM route entry */
+ err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
+ &route->key, afa_block);
+ if (err)
+ goto err;
+
+ /* Delete the old one */
+ mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
+ route->afa_block = afa_block;
+ route->action = route_action;
+ return 0;
+err:
+ mlxsw_sp_mr_tcam_afa_block_destroy(afa_block);
+ return err;
+}
+
+static int mlxsw_sp_mr_tcam_route_min_mtu_update(struct mlxsw_sp *mlxsw_sp,
+ void *route_priv, u16 min_mtu)
+{
+ struct mlxsw_sp_mr_tcam_route *route = route_priv;
+ struct mlxsw_afa_block *afa_block;
+ int err;
+
+ /* Create a new flexible action block */
+ afa_block = mlxsw_sp_mr_tcam_afa_block_create(mlxsw_sp,
+ route->action,
+ route->irif_index,
+ route->counter_index,
+ min_mtu,
+ &route->erif_list);
+ if (IS_ERR(afa_block))
+ return PTR_ERR(afa_block);
+
+ /* Update the TCAM route entry */
+ err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
+ &route->key, afa_block);
+ if (err)
+ goto err;
+
+ /* Delete the old one */
+ mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
+ route->afa_block = afa_block;
+ route->min_mtu = min_mtu;
+ return 0;
+err:
+ mlxsw_sp_mr_tcam_afa_block_destroy(afa_block);
+ return err;
+}
+
+static int mlxsw_sp_mr_tcam_route_irif_update(struct mlxsw_sp *mlxsw_sp,
+ void *route_priv, u16 irif_index)
+{
+ struct mlxsw_sp_mr_tcam_route *route = route_priv;
+
+ if (route->action != MLXSW_SP_MR_ROUTE_ACTION_TRAP)
+ return -EINVAL;
+ route->irif_index = irif_index;
+ return 0;
+}
+
+static int mlxsw_sp_mr_tcam_route_erif_add(struct mlxsw_sp *mlxsw_sp,
+ void *route_priv, u16 erif_index)
+{
+ struct mlxsw_sp_mr_tcam_route *route = route_priv;
+ int err;
+
+ err = mlxsw_sp_mr_erif_list_add(mlxsw_sp, &route->erif_list,
+ erif_index);
+ if (err)
+ return err;
+
+ /* Commit the action only if the route action is not TRAP */
+ if (route->action != MLXSW_SP_MR_ROUTE_ACTION_TRAP)
+ return mlxsw_sp_mr_erif_list_commit(mlxsw_sp,
+ &route->erif_list);
+ return 0;
+}
+
+static int mlxsw_sp_mr_tcam_route_erif_del(struct mlxsw_sp *mlxsw_sp,
+ void *route_priv, u16 erif_index)
+{
+ struct mlxsw_sp_mr_tcam_route *route = route_priv;
+ struct mlxsw_sp_mr_erif_sublist *erif_sublist;
+ struct mlxsw_sp_mr_tcam_erif_list erif_list;
+ struct mlxsw_afa_block *afa_block;
+ int err;
+ int i;
+
+ /* Create a copy of the original erif_list without the deleted entry */
+ mlxsw_sp_mr_erif_list_init(&erif_list);
+ list_for_each_entry(erif_sublist, &route->erif_list.erif_sublists, list) {
+ for (i = 0; i < erif_sublist->num_erifs; i++) {
+ u16 curr_erif = erif_sublist->erif_indices[i];
+
+ if (curr_erif == erif_index)
+ continue;
+ err = mlxsw_sp_mr_erif_list_add(mlxsw_sp, &erif_list,
+ curr_erif);
+ if (err)
+ goto err_erif_list_add;
+ }
+ }
+
+ /* Create the flexible action block pointing to the new erif_list */
+ afa_block = mlxsw_sp_mr_tcam_afa_block_create(mlxsw_sp, route->action,
+ route->irif_index,
+ route->counter_index,
+ route->min_mtu,
+ &erif_list);
+ if (IS_ERR(afa_block)) {
+ err = PTR_ERR(afa_block);
+ goto err_afa_block_create;
+ }
+
+ /* Update the TCAM route entry */
+ err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
+ &route->key, afa_block);
+ if (err)
+ goto err_route_write;
+
+ mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
+ mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &route->erif_list);
+ route->afa_block = afa_block;
+ mlxsw_sp_mr_erif_list_move(&route->erif_list, &erif_list);
+ return 0;
+
+err_route_write:
+ mlxsw_sp_mr_tcam_afa_block_destroy(afa_block);
+err_afa_block_create:
+err_erif_list_add:
+ mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &erif_list);
+ return err;
+}
+
+static int
+mlxsw_sp_mr_tcam_route_update(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+ struct mlxsw_sp_mr_route_info *route_info)
+{
+ struct mlxsw_sp_mr_tcam_route *route = route_priv;
+ struct mlxsw_sp_mr_tcam_erif_list erif_list;
+ struct mlxsw_afa_block *afa_block;
+ int err;
+
+ /* Create a new erif_list */
+ mlxsw_sp_mr_erif_list_init(&erif_list);
+ err = mlxsw_sp_mr_tcam_erif_populate(mlxsw_sp, &erif_list, route_info);
+ if (err)
+ goto err_erif_populate;
+
+ /* Create the flexible action block pointing to the new erif_list */
+ afa_block = mlxsw_sp_mr_tcam_afa_block_create(mlxsw_sp,
+ route_info->route_action,
+ route_info->irif_index,
+ route->counter_index,
+ route_info->min_mtu,
+ &erif_list);
+ if (IS_ERR(afa_block)) {
+ err = PTR_ERR(afa_block);
+ goto err_afa_block_create;
+ }
+
+ /* Update the TCAM route entry */
+ err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
+ &route->key, afa_block);
+ if (err)
+ goto err_route_write;
+
+ mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
+ mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &route->erif_list);
+ route->afa_block = afa_block;
+ mlxsw_sp_mr_erif_list_move(&route->erif_list, &erif_list);
+ route->action = route_info->route_action;
+ route->irif_index = route_info->irif_index;
+ route->min_mtu = route_info->min_mtu;
+ return 0;
+
+err_route_write:
+ mlxsw_sp_mr_tcam_afa_block_destroy(afa_block);
+err_afa_block_create:
+err_erif_populate:
+ mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &erif_list);
+ return err;
+}
+
+#define MLXSW_SP_MR_TCAM_REGION_BASE_COUNT 16
+#define MLXSW_SP_MR_TCAM_REGION_RESIZE_STEP 16
+
+static int
+mlxsw_sp_mr_tcam_region_alloc(struct mlxsw_sp_mr_tcam_region *mr_tcam_region)
+{
+ struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+ char rtar_pl[MLXSW_REG_RTAR_LEN];
+
+ mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_ALLOCATE,
+ mr_tcam_region->rtar_key_type,
+ MLXSW_SP_MR_TCAM_REGION_BASE_COUNT);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
+}
+
+static void
+mlxsw_sp_mr_tcam_region_free(struct mlxsw_sp_mr_tcam_region *mr_tcam_region)
+{
+ struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+ char rtar_pl[MLXSW_REG_RTAR_LEN];
+
+ mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_DEALLOCATE,
+ mr_tcam_region->rtar_key_type, 0);
+ mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
+}
+
+static int mlxsw_sp_mr_tcam_region_parman_resize(void *priv,
+ unsigned long new_count)
+{
+ struct mlxsw_sp_mr_tcam_region *mr_tcam_region = priv;
+ struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+ char rtar_pl[MLXSW_REG_RTAR_LEN];
+ u64 max_tcam_rules;
+
+ max_tcam_rules = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_RULES);
+ if (new_count > max_tcam_rules)
+ return -EINVAL;
+ mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_RESIZE,
+ mr_tcam_region->rtar_key_type, new_count);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
+}
+
+static void mlxsw_sp_mr_tcam_region_parman_move(void *priv,
+ unsigned long from_index,
+ unsigned long to_index,
+ unsigned long count)
+{
+ struct mlxsw_sp_mr_tcam_region *mr_tcam_region = priv;
+ struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+ char rrcr_pl[MLXSW_REG_RRCR_LEN];
+
+ mlxsw_reg_rrcr_pack(rrcr_pl, MLXSW_REG_RRCR_OP_MOVE,
+ from_index, count,
+ mr_tcam_region->rtar_key_type, to_index);
+ mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rrcr), rrcr_pl);
+}
+
+static const struct parman_ops mlxsw_sp_mr_tcam_region_parman_ops = {
+ .base_count = MLXSW_SP_MR_TCAM_REGION_BASE_COUNT,
+ .resize_step = MLXSW_SP_MR_TCAM_REGION_RESIZE_STEP,
+ .resize = mlxsw_sp_mr_tcam_region_parman_resize,
+ .move = mlxsw_sp_mr_tcam_region_parman_move,
+ .algo = PARMAN_ALGO_TYPE_LSORT,
+};
+
+static int
+mlxsw_sp_mr_tcam_region_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_mr_tcam_region *mr_tcam_region,
+ enum mlxsw_reg_rtar_key_type rtar_key_type)
+{
+ struct parman_prio *parman_prios;
+ struct parman *parman;
+ int err;
+ int i;
+
+ mr_tcam_region->rtar_key_type = rtar_key_type;
+ mr_tcam_region->mlxsw_sp = mlxsw_sp;
+
+ err = mlxsw_sp_mr_tcam_region_alloc(mr_tcam_region);
+ if (err)
+ return err;
+
+ parman = parman_create(&mlxsw_sp_mr_tcam_region_parman_ops,
+ mr_tcam_region);
+ if (!parman) {
+ err = -ENOMEM;
+ goto err_parman_create;
+ }
+ mr_tcam_region->parman = parman;
+
+ parman_prios = kmalloc_array(MLXSW_SP_MR_ROUTE_PRIO_MAX + 1,
+ sizeof(*parman_prios), GFP_KERNEL);
+ if (!parman_prios) {
+ err = -ENOMEM;
+ goto err_parman_prios_alloc;
+ }
+ mr_tcam_region->parman_prios = parman_prios;
+
+ for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++)
+ parman_prio_init(mr_tcam_region->parman,
+ &mr_tcam_region->parman_prios[i], i);
+ return 0;
+
+err_parman_prios_alloc:
+ parman_destroy(parman);
+err_parman_create:
+ mlxsw_sp_mr_tcam_region_free(mr_tcam_region);
+ return err;
+}
+
+static void
+mlxsw_sp_mr_tcam_region_fini(struct mlxsw_sp_mr_tcam_region *mr_tcam_region)
+{
+ int i;
+
+ for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++)
+ parman_prio_fini(&mr_tcam_region->parman_prios[i]);
+ kfree(mr_tcam_region->parman_prios);
+ parman_destroy(mr_tcam_region->parman);
+ mlxsw_sp_mr_tcam_region_free(mr_tcam_region);
+}
+
+static int mlxsw_sp_mr_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+ struct mlxsw_sp_mr_tcam *mr_tcam = priv;
+
+ if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MC_ERIF_LIST_ENTRIES) ||
+ !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_TCAM_RULES))
+ return -EIO;
+
+ return mlxsw_sp_mr_tcam_region_init(mlxsw_sp,
+ &mr_tcam->ipv4_tcam_region,
+ MLXSW_REG_RTAR_KEY_TYPE_IPV4_MULTICAST);
+}
+
+static void mlxsw_sp_mr_tcam_fini(void *priv)
+{
+ struct mlxsw_sp_mr_tcam *mr_tcam = priv;
+
+ mlxsw_sp_mr_tcam_region_fini(&mr_tcam->ipv4_tcam_region);
+}
+
+const struct mlxsw_sp_mr_ops mlxsw_sp_mr_tcam_ops = {
+ .priv_size = sizeof(struct mlxsw_sp_mr_tcam),
+ .route_priv_size = sizeof(struct mlxsw_sp_mr_tcam_route),
+ .init = mlxsw_sp_mr_tcam_init,
+ .route_create = mlxsw_sp_mr_tcam_route_create,
+ .route_update = mlxsw_sp_mr_tcam_route_update,
+ .route_stats = mlxsw_sp_mr_tcam_route_stats,
+ .route_action_update = mlxsw_sp_mr_tcam_route_action_update,
+ .route_min_mtu_update = mlxsw_sp_mr_tcam_route_min_mtu_update,
+ .route_irif_update = mlxsw_sp_mr_tcam_route_irif_update,
+ .route_erif_add = mlxsw_sp_mr_tcam_route_erif_add,
+ .route_erif_del = mlxsw_sp_mr_tcam_route_erif_del,
+ .route_destroy = mlxsw_sp_mr_tcam_route_destroy,
+ .fini = mlxsw_sp_mr_tcam_fini,
+};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h
new file mode 100644
index 000000000000..f9b59ee25406
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h
@@ -0,0 +1,43 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_SPECTRUM_MCROUTER_TCAM_H
+#define _MLXSW_SPECTRUM_MCROUTER_TCAM_H
+
+#include "spectrum.h"
+#include "spectrum_mr.h"
+
+extern const struct mlxsw_sp_mr_ops mlxsw_sp_mr_tcam_ops;
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 032089efc1a0..e0f8ea4ed7af 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -65,6 +65,8 @@
#include "spectrum_cnt.h"
#include "spectrum_dpipe.h"
#include "spectrum_ipip.h"
+#include "spectrum_mr.h"
+#include "spectrum_mr_tcam.h"
#include "spectrum_router.h"
struct mlxsw_sp_vr;
@@ -78,6 +80,7 @@ struct mlxsw_sp_router {
struct rhashtable neigh_ht;
struct rhashtable nexthop_group_ht;
struct rhashtable nexthop_ht;
+ struct list_head nexthop_list;
struct {
struct mlxsw_sp_lpm_tree *trees;
unsigned int tree_count;
@@ -458,6 +461,7 @@ struct mlxsw_sp_vr {
unsigned int rif_count;
struct mlxsw_sp_fib *fib4;
struct mlxsw_sp_fib *fib6;
+ struct mlxsw_sp_mr_table *mr4_table;
};
static const struct rhashtable_params mlxsw_sp_fib_ht_params;
@@ -652,7 +656,7 @@ static void mlxsw_sp_lpm_fini(struct mlxsw_sp *mlxsw_sp)
static bool mlxsw_sp_vr_is_used(const struct mlxsw_sp_vr *vr)
{
- return !!vr->fib4 || !!vr->fib6;
+ return !!vr->fib4 || !!vr->fib6 || !!vr->mr4_table;
}
static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp)
@@ -692,8 +696,8 @@ static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp,
static u32 mlxsw_sp_fix_tb_id(u32 tb_id)
{
- /* For our purpose, squash main and local table into one */
- if (tb_id == RT_TABLE_LOCAL)
+ /* For our purpose, squash main, default and local tables into one */
+ if (tb_id == RT_TABLE_LOCAL || tb_id == RT_TABLE_DEFAULT)
tb_id = RT_TABLE_MAIN;
return tb_id;
}
@@ -743,9 +747,18 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp,
err = PTR_ERR(vr->fib6);
goto err_fib6_create;
}
+ vr->mr4_table = mlxsw_sp_mr_table_create(mlxsw_sp, vr->id,
+ MLXSW_SP_L3_PROTO_IPV4);
+ if (IS_ERR(vr->mr4_table)) {
+ err = PTR_ERR(vr->mr4_table);
+ goto err_mr_table_create;
+ }
vr->tb_id = tb_id;
return vr;
+err_mr_table_create:
+ mlxsw_sp_fib_destroy(vr->fib6);
+ vr->fib6 = NULL;
err_fib6_create:
mlxsw_sp_fib_destroy(vr->fib4);
vr->fib4 = NULL;
@@ -754,6 +767,8 @@ err_fib6_create:
static void mlxsw_sp_vr_destroy(struct mlxsw_sp_vr *vr)
{
+ mlxsw_sp_mr_table_destroy(vr->mr4_table);
+ vr->mr4_table = NULL;
mlxsw_sp_fib_destroy(vr->fib6);
vr->fib6 = NULL;
mlxsw_sp_fib_destroy(vr->fib4);
@@ -774,7 +789,8 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id)
static void mlxsw_sp_vr_put(struct mlxsw_sp_vr *vr)
{
if (!vr->rif_count && list_empty(&vr->fib4->node_list) &&
- list_empty(&vr->fib6->node_list))
+ list_empty(&vr->fib6->node_list) &&
+ mlxsw_sp_mr_table_empty(vr->mr4_table))
mlxsw_sp_vr_destroy(vr);
}
@@ -1316,7 +1332,7 @@ mlxsw_sp_rif_neigh_next(struct mlxsw_sp_rif *rif,
typeof(*neigh_entry),
rif_list_node);
}
- if (neigh_entry->rif_list_node.next == &rif->neigh_list)
+ if (list_is_last(&neigh_entry->rif_list_node, &rif->neigh_list))
return NULL;
return list_next_entry(neigh_entry, rif_list_node);
}
@@ -1664,7 +1680,7 @@ __mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp,
err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(rauhtd),
rauhtd_pl);
if (err) {
- dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to dump neighbour talbe\n");
+ dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to dump neighbour table\n");
break;
}
num_rec = mlxsw_reg_rauhtd_num_rec_get(rauhtd_pl);
@@ -2028,6 +2044,7 @@ struct mlxsw_sp_nexthop_key {
struct mlxsw_sp_nexthop {
struct list_head neigh_list_node; /* member of neigh entry list */
struct list_head rif_list_node;
+ struct list_head router_list_node;
struct mlxsw_sp_nexthop_group *nh_grp; /* pointer back to the group
* this belongs to
*/
@@ -2050,6 +2067,8 @@ struct mlxsw_sp_nexthop {
struct mlxsw_sp_neigh_entry *neigh_entry;
struct mlxsw_sp_ipip_entry *ipip_entry;
};
+ unsigned int counter_index;
+ bool counter_valid;
};
struct mlxsw_sp_nexthop_group {
@@ -2066,6 +2085,112 @@ struct mlxsw_sp_nexthop_group {
#define nh_rif nexthops[0].rif
};
+void mlxsw_sp_nexthop_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh)
+{
+ struct devlink *devlink;
+
+ devlink = priv_to_devlink(mlxsw_sp->core);
+ if (!devlink_dpipe_table_counter_enabled(devlink,
+ MLXSW_SP_DPIPE_TABLE_NAME_ADJ))
+ return;
+
+ if (mlxsw_sp_flow_counter_alloc(mlxsw_sp, &nh->counter_index))
+ return;
+
+ nh->counter_valid = true;
+}
+
+void mlxsw_sp_nexthop_counter_free(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh)
+{
+ if (!nh->counter_valid)
+ return;
+ mlxsw_sp_flow_counter_free(mlxsw_sp, nh->counter_index);
+ nh->counter_valid = false;
+}
+
+int mlxsw_sp_nexthop_counter_get(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh, u64 *p_counter)
+{
+ if (!nh->counter_valid)
+ return -EINVAL;
+
+ return mlxsw_sp_flow_counter_get(mlxsw_sp, nh->counter_index,
+ p_counter, NULL);
+}
+
+struct mlxsw_sp_nexthop *mlxsw_sp_nexthop_next(struct mlxsw_sp_router *router,
+ struct mlxsw_sp_nexthop *nh)
+{
+ if (!nh) {
+ if (list_empty(&router->nexthop_list))
+ return NULL;
+ else
+ return list_first_entry(&router->nexthop_list,
+ typeof(*nh), router_list_node);
+ }
+ if (list_is_last(&nh->router_list_node, &router->nexthop_list))
+ return NULL;
+ return list_next_entry(nh, router_list_node);
+}
+
+bool mlxsw_sp_nexthop_offload(struct mlxsw_sp_nexthop *nh)
+{
+ return nh->offloaded;
+}
+
+unsigned char *mlxsw_sp_nexthop_ha(struct mlxsw_sp_nexthop *nh)
+{
+ if (!nh->offloaded)
+ return NULL;
+ return nh->neigh_entry->ha;
+}
+
+int mlxsw_sp_nexthop_indexes(struct mlxsw_sp_nexthop *nh, u32 *p_adj_index,
+ u32 *p_adj_hash_index)
+{
+ struct mlxsw_sp_nexthop_group *nh_grp = nh->nh_grp;
+ u32 adj_hash_index = 0;
+ int i;
+
+ if (!nh->offloaded || !nh_grp->adj_index_valid)
+ return -EINVAL;
+
+ *p_adj_index = nh_grp->adj_index;
+
+ for (i = 0; i < nh_grp->count; i++) {
+ struct mlxsw_sp_nexthop *nh_iter = &nh_grp->nexthops[i];
+
+ if (nh_iter == nh)
+ break;
+ if (nh_iter->offloaded)
+ adj_hash_index++;
+ }
+
+ *p_adj_hash_index = adj_hash_index;
+ return 0;
+}
+
+struct mlxsw_sp_rif *mlxsw_sp_nexthop_rif(struct mlxsw_sp_nexthop *nh)
+{
+ return nh->rif;
+}
+
+bool mlxsw_sp_nexthop_group_has_ipip(struct mlxsw_sp_nexthop *nh)
+{
+ struct mlxsw_sp_nexthop_group *nh_grp = nh->nh_grp;
+ int i;
+
+ for (i = 0; i < nh_grp->count; i++) {
+ struct mlxsw_sp_nexthop *nh_iter = &nh_grp->nexthops[i];
+
+ if (nh_iter->type == MLXSW_SP_NEXTHOP_TYPE_IPIP)
+ return true;
+ }
+ return false;
+}
+
static struct fib_info *
mlxsw_sp_nexthop4_group_fi(const struct mlxsw_sp_nexthop_group *nh_grp)
{
@@ -2323,8 +2448,8 @@ static int mlxsw_sp_adj_index_mass_update(struct mlxsw_sp *mlxsw_sp,
return 0;
}
-static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
- struct mlxsw_sp_nexthop *nh)
+int mlxsw_sp_nexthop_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
+ struct mlxsw_sp_nexthop *nh)
{
struct mlxsw_sp_neigh_entry *neigh_entry = nh->neigh_entry;
char ratr_pl[MLXSW_REG_RATR_LEN];
@@ -2333,6 +2458,11 @@ static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
true, MLXSW_REG_RATR_TYPE_ETHERNET,
adj_index, neigh_entry->rif);
mlxsw_reg_ratr_eth_entry_pack(ratr_pl, neigh_entry->ha);
+ if (nh->counter_valid)
+ mlxsw_reg_ratr_counter_pack(ratr_pl, nh->counter_index, true);
+ else
+ mlxsw_reg_ratr_counter_pack(ratr_pl, 0, false);
+
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl);
}
@@ -2367,7 +2497,7 @@ mlxsw_sp_nexthop_group_update(struct mlxsw_sp *mlxsw_sp,
if (nh->update || reallocate) {
switch (nh->type) {
case MLXSW_SP_NEXTHOP_TYPE_ETH:
- err = mlxsw_sp_nexthop_mac_update
+ err = mlxsw_sp_nexthop_update
(mlxsw_sp, adj_index, nh);
break;
case MLXSW_SP_NEXTHOP_TYPE_IPIP:
@@ -2789,6 +2919,9 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp,
if (err)
return err;
+ mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh);
+ list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list);
+
if (!dev)
return 0;
@@ -2812,6 +2945,8 @@ static void mlxsw_sp_nexthop4_fini(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop *nh)
{
mlxsw_sp_nexthop4_type_fini(mlxsw_sp, nh);
+ list_del(&nh->router_list_node);
+ mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh);
mlxsw_sp_nexthop_remove(mlxsw_sp, nh);
}
@@ -3121,7 +3256,7 @@ mlxsw_sp_fib_entry_offload_refresh(struct mlxsw_sp_fib_entry *fib_entry,
return;
if (mlxsw_sp_fib_entry_should_offload(fib_entry))
mlxsw_sp_fib_entry_offload_set(fib_entry);
- else if (!mlxsw_sp_fib_entry_should_offload(fib_entry))
+ else
mlxsw_sp_fib_entry_offload_unset(fib_entry);
return;
default:
@@ -4053,6 +4188,9 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp,
nh->nh_grp = nh_grp;
memcpy(&nh->gw_addr, &rt->rt6i_gateway, sizeof(nh->gw_addr));
+ mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh);
+
+ list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list);
if (!dev)
return 0;
@@ -4065,6 +4203,8 @@ static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop *nh)
{
mlxsw_sp_nexthop6_type_fini(mlxsw_sp, nh);
+ list_del(&nh->router_list_node);
+ mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh);
}
static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp,
@@ -4615,6 +4755,75 @@ static int __mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp,
return 0;
}
+static int mlxsw_sp_router_fibmr_add(struct mlxsw_sp *mlxsw_sp,
+ struct mfc_entry_notifier_info *men_info,
+ bool replace)
+{
+ struct mlxsw_sp_vr *vr;
+
+ if (mlxsw_sp->router->aborted)
+ return 0;
+
+ vr = mlxsw_sp_vr_get(mlxsw_sp, men_info->tb_id);
+ if (IS_ERR(vr))
+ return PTR_ERR(vr);
+
+ return mlxsw_sp_mr_route4_add(vr->mr4_table, men_info->mfc, replace);
+}
+
+static void mlxsw_sp_router_fibmr_del(struct mlxsw_sp *mlxsw_sp,
+ struct mfc_entry_notifier_info *men_info)
+{
+ struct mlxsw_sp_vr *vr;
+
+ if (mlxsw_sp->router->aborted)
+ return;
+
+ vr = mlxsw_sp_vr_find(mlxsw_sp, men_info->tb_id);
+ if (WARN_ON(!vr))
+ return;
+
+ mlxsw_sp_mr_route4_del(vr->mr4_table, men_info->mfc);
+ mlxsw_sp_vr_put(vr);
+}
+
+static int
+mlxsw_sp_router_fibmr_vif_add(struct mlxsw_sp *mlxsw_sp,
+ struct vif_entry_notifier_info *ven_info)
+{
+ struct mlxsw_sp_rif *rif;
+ struct mlxsw_sp_vr *vr;
+
+ if (mlxsw_sp->router->aborted)
+ return 0;
+
+ vr = mlxsw_sp_vr_get(mlxsw_sp, ven_info->tb_id);
+ if (IS_ERR(vr))
+ return PTR_ERR(vr);
+
+ rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, ven_info->dev);
+ return mlxsw_sp_mr_vif_add(vr->mr4_table, ven_info->dev,
+ ven_info->vif_index,
+ ven_info->vif_flags, rif);
+}
+
+static void
+mlxsw_sp_router_fibmr_vif_del(struct mlxsw_sp *mlxsw_sp,
+ struct vif_entry_notifier_info *ven_info)
+{
+ struct mlxsw_sp_vr *vr;
+
+ if (mlxsw_sp->router->aborted)
+ return;
+
+ vr = mlxsw_sp_vr_find(mlxsw_sp, ven_info->tb_id);
+ if (WARN_ON(!vr))
+ return;
+
+ mlxsw_sp_mr_vif_del(vr->mr4_table, ven_info->vif_index);
+ mlxsw_sp_vr_put(vr);
+}
+
static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
{
enum mlxsw_reg_ralxx_protocol proto = MLXSW_REG_RALXX_PROTOCOL_IPV4;
@@ -4625,6 +4834,10 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
if (err)
return err;
+ /* The multicast router code does not need an abort trap as by default,
+ * packets that don't match any routes are trapped to the CPU.
+ */
+
proto = MLXSW_REG_RALXX_PROTOCOL_IPV6;
return __mlxsw_sp_router_set_abort_trap(mlxsw_sp, proto,
MLXSW_SP_LPM_TREE_MIN + 1);
@@ -4706,6 +4919,8 @@ static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp)
if (!mlxsw_sp_vr_is_used(vr))
continue;
+
+ mlxsw_sp_mr_table_flush(vr->mr4_table);
mlxsw_sp_vr_fib_flush(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV4);
/* If virtual router was only used for IPv4, then it's no
@@ -4738,6 +4953,8 @@ struct mlxsw_sp_fib_event_work {
struct fib_entry_notifier_info fen_info;
struct fib_rule_notifier_info fr_info;
struct fib_nh_notifier_info fnh_info;
+ struct mfc_entry_notifier_info men_info;
+ struct vif_entry_notifier_info ven_info;
};
struct mlxsw_sp *mlxsw_sp;
unsigned long event;
@@ -4824,6 +5041,55 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work)
kfree(fib_work);
}
+static void mlxsw_sp_router_fibmr_event_work(struct work_struct *work)
+{
+ struct mlxsw_sp_fib_event_work *fib_work =
+ container_of(work, struct mlxsw_sp_fib_event_work, work);
+ struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp;
+ struct fib_rule *rule;
+ bool replace;
+ int err;
+
+ rtnl_lock();
+ switch (fib_work->event) {
+ case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+ case FIB_EVENT_ENTRY_ADD:
+ replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE;
+
+ err = mlxsw_sp_router_fibmr_add(mlxsw_sp, &fib_work->men_info,
+ replace);
+ if (err)
+ mlxsw_sp_router_fib_abort(mlxsw_sp);
+ ipmr_cache_put(fib_work->men_info.mfc);
+ break;
+ case FIB_EVENT_ENTRY_DEL:
+ mlxsw_sp_router_fibmr_del(mlxsw_sp, &fib_work->men_info);
+ ipmr_cache_put(fib_work->men_info.mfc);
+ break;
+ case FIB_EVENT_VIF_ADD:
+ err = mlxsw_sp_router_fibmr_vif_add(mlxsw_sp,
+ &fib_work->ven_info);
+ if (err)
+ mlxsw_sp_router_fib_abort(mlxsw_sp);
+ dev_put(fib_work->ven_info.dev);
+ break;
+ case FIB_EVENT_VIF_DEL:
+ mlxsw_sp_router_fibmr_vif_del(mlxsw_sp,
+ &fib_work->ven_info);
+ dev_put(fib_work->ven_info.dev);
+ break;
+ case FIB_EVENT_RULE_ADD: /* fall through */
+ case FIB_EVENT_RULE_DEL:
+ rule = fib_work->fr_info.rule;
+ if (!ipmr_rule_default(rule) && !rule->l3mdev)
+ mlxsw_sp_router_fib_abort(mlxsw_sp);
+ fib_rule_put(rule);
+ break;
+ }
+ rtnl_unlock();
+ kfree(fib_work);
+}
+
static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event_work *fib_work,
struct fib_notifier_info *info)
{
@@ -4869,6 +5135,30 @@ static void mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work,
}
}
+static void
+mlxsw_sp_router_fibmr_event(struct mlxsw_sp_fib_event_work *fib_work,
+ struct fib_notifier_info *info)
+{
+ switch (fib_work->event) {
+ case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+ case FIB_EVENT_ENTRY_ADD: /* fall through */
+ case FIB_EVENT_ENTRY_DEL:
+ memcpy(&fib_work->men_info, info, sizeof(fib_work->men_info));
+ ipmr_cache_hold(fib_work->men_info.mfc);
+ break;
+ case FIB_EVENT_VIF_ADD: /* fall through */
+ case FIB_EVENT_VIF_DEL:
+ memcpy(&fib_work->ven_info, info, sizeof(fib_work->ven_info));
+ dev_hold(fib_work->ven_info.dev);
+ break;
+ case FIB_EVENT_RULE_ADD: /* fall through */
+ case FIB_EVENT_RULE_DEL:
+ memcpy(&fib_work->fr_info, info, sizeof(fib_work->fr_info));
+ fib_rule_get(fib_work->fr_info.rule);
+ break;
+ }
+}
+
/* Called with rcu_read_lock() */
static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
unsigned long event, void *ptr)
@@ -4878,7 +5168,8 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
struct mlxsw_sp_router *router;
if (!net_eq(info->net, &init_net) ||
- (info->family != AF_INET && info->family != AF_INET6))
+ (info->family != AF_INET && info->family != AF_INET6 &&
+ info->family != RTNL_FAMILY_IPMR))
return NOTIFY_DONE;
fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC);
@@ -4898,6 +5189,10 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
INIT_WORK(&fib_work->work, mlxsw_sp_router_fib6_event_work);
mlxsw_sp_router_fib6_event(fib_work, info);
break;
+ case RTNL_FAMILY_IPMR:
+ INIT_WORK(&fib_work->work, mlxsw_sp_router_fibmr_event_work);
+ mlxsw_sp_router_fibmr_event(fib_work, info);
+ break;
}
mlxsw_core_schedule_work(&fib_work->work);
@@ -5058,6 +5353,11 @@ int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif)
return rif->dev->ifindex;
}
+const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif)
+{
+ return rif->dev;
+}
+
static struct mlxsw_sp_rif *
mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
const struct mlxsw_sp_rif_params *params)
@@ -5107,11 +5407,17 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
if (err)
goto err_configure;
+ err = mlxsw_sp_mr_rif_add(vr->mr4_table, rif);
+ if (err)
+ goto err_mr_rif_add;
+
mlxsw_sp_rif_counters_alloc(rif);
mlxsw_sp->router->rifs[rif_index] = rif;
return rif;
+err_mr_rif_add:
+ ops->deconfigure(rif);
err_configure:
if (fid)
mlxsw_sp_fid_put(fid);
@@ -5136,6 +5442,7 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
mlxsw_sp->router->rifs[rif->rif_index] = NULL;
mlxsw_sp_rif_counters_free(rif);
+ mlxsw_sp_mr_rif_del(vr->mr4_table, rif);
ops->deconfigure(rif);
if (fid)
/* Loopback RIFs are not associated with a FID. */
@@ -5477,6 +5784,17 @@ int mlxsw_sp_netdevice_router_port_event(struct net_device *dev)
if (err)
goto err_rif_fdb_op;
+ if (rif->mtu != dev->mtu) {
+ struct mlxsw_sp_vr *vr;
+
+ /* The RIF is relevant only to its mr_table instance, as unlike
+ * unicast routing, in multicast routing a RIF cannot be shared
+ * between several multicast routing tables.
+ */
+ vr = &mlxsw_sp->router->vrs[rif->vr_id];
+ mlxsw_sp_mr_rif_mtu_update(vr->mr4_table, rif, dev->mtu);
+ }
+
ether_addr_copy(rif->addr, dev->dev_addr);
rif->mtu = dev->mtu;
@@ -5995,10 +6313,15 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
if (err)
goto err_nexthop_group_ht_init;
+ INIT_LIST_HEAD(&mlxsw_sp->router->nexthop_list);
err = mlxsw_sp_lpm_init(mlxsw_sp);
if (err)
goto err_lpm_init;
+ err = mlxsw_sp_mr_init(mlxsw_sp, &mlxsw_sp_mr_tcam_ops);
+ if (err)
+ goto err_mr_init;
+
err = mlxsw_sp_vrs_init(mlxsw_sp);
if (err)
goto err_vrs_init;
@@ -6020,6 +6343,8 @@ err_register_fib_notifier:
err_neigh_init:
mlxsw_sp_vrs_fini(mlxsw_sp);
err_vrs_init:
+ mlxsw_sp_mr_fini(mlxsw_sp);
+err_mr_init:
mlxsw_sp_lpm_fini(mlxsw_sp);
err_lpm_init:
rhashtable_destroy(&mlxsw_sp->router->nexthop_group_ht);
@@ -6041,6 +6366,7 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
unregister_fib_notifier(&mlxsw_sp->router->fib_nb);
mlxsw_sp_neigh_fini(mlxsw_sp);
mlxsw_sp_vrs_fini(mlxsw_sp);
+ mlxsw_sp_mr_fini(mlxsw_sp);
mlxsw_sp_lpm_fini(mlxsw_sp);
rhashtable_destroy(&mlxsw_sp->router->nexthop_group_ht);
rhashtable_destroy(&mlxsw_sp->router->nexthop_ht);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index 345fcc4f38e9..3d449180b035 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -62,6 +62,7 @@ enum mlxsw_sp_rif_counter_dir {
};
struct mlxsw_sp_neigh_entry;
+struct mlxsw_sp_nexthop;
struct mlxsw_sp_rif *mlxsw_sp_rif_by_index(const struct mlxsw_sp *mlxsw_sp,
u16 rif_index);
@@ -69,6 +70,7 @@ u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif);
u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *rif);
u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *rif);
int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif);
+const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif);
int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_rif *rif,
enum mlxsw_sp_rif_counter_dir dir,
@@ -107,5 +109,24 @@ union mlxsw_sp_l3addr
mlxsw_sp_ipip_netdev_daddr(enum mlxsw_sp_l3proto proto,
const struct net_device *ol_dev);
__be32 mlxsw_sp_ipip_netdev_daddr4(const struct net_device *ol_dev);
+struct mlxsw_sp_nexthop *mlxsw_sp_nexthop_next(struct mlxsw_sp_router *router,
+ struct mlxsw_sp_nexthop *nh);
+bool mlxsw_sp_nexthop_offload(struct mlxsw_sp_nexthop *nh);
+unsigned char *mlxsw_sp_nexthop_ha(struct mlxsw_sp_nexthop *nh);
+int mlxsw_sp_nexthop_indexes(struct mlxsw_sp_nexthop *nh, u32 *p_adj_index,
+ u32 *p_adj_hash_index);
+struct mlxsw_sp_rif *mlxsw_sp_nexthop_rif(struct mlxsw_sp_nexthop *nh);
+bool mlxsw_sp_nexthop_group_has_ipip(struct mlxsw_sp_nexthop *nh);
+#define mlxsw_sp_nexthop_for_each(nh, router) \
+ for (nh = mlxsw_sp_nexthop_next(router, NULL); nh; \
+ nh = mlxsw_sp_nexthop_next(router, nh))
+int mlxsw_sp_nexthop_counter_get(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh, u64 *p_counter);
+int mlxsw_sp_nexthop_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
+ struct mlxsw_sp_nexthop *nh);
+void mlxsw_sp_nexthop_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh);
+void mlxsw_sp_nexthop_counter_free(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh);
#endif /* _MLXSW_ROUTER_H_*/
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index d39ffbfcc436..0f9eac5f4ebf 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -67,7 +67,6 @@ struct mlxsw_sp_bridge {
u32 ageing_time;
bool vlan_enabled_exists;
struct list_head bridges_list;
- struct list_head mids_list;
DECLARE_BITMAP(mids_bitmap, MLXSW_SP_MID_MAX);
const struct mlxsw_sp_bridge_ops *bridge_8021q_ops;
const struct mlxsw_sp_bridge_ops *bridge_8021d_ops;
@@ -77,6 +76,7 @@ struct mlxsw_sp_bridge_device {
struct net_device *dev;
struct list_head list;
struct list_head ports_list;
+ struct list_head mids_list;
u8 vlan_enabled:1,
multicast_enabled:1;
const struct mlxsw_sp_bridge_ops *ops;
@@ -121,6 +121,20 @@ mlxsw_sp_bridge_port_fdb_flush(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_bridge_port *bridge_port,
u16 fid_index);
+static void
+mlxsw_sp_bridge_port_mdb_flush(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_bridge_port *bridge_port);
+
+static void
+mlxsw_sp_bridge_mdb_mc_enable_sync(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_bridge_device
+ *bridge_device);
+
+static void
+mlxsw_sp_port_mrouter_update_mdb(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_bridge_port *bridge_port,
+ bool add);
+
static struct mlxsw_sp_bridge_device *
mlxsw_sp_bridge_device_find(const struct mlxsw_sp_bridge *bridge,
const struct net_device *br_dev)
@@ -161,6 +175,7 @@ mlxsw_sp_bridge_device_create(struct mlxsw_sp_bridge *bridge,
} else {
bridge_device->ops = bridge->bridge_8021d_ops;
}
+ INIT_LIST_HEAD(&bridge_device->mids_list);
list_add(&bridge_device->list, &bridge->bridges_list);
return bridge_device;
@@ -174,6 +189,7 @@ mlxsw_sp_bridge_device_destroy(struct mlxsw_sp_bridge *bridge,
if (bridge_device->vlan_enabled)
bridge->vlan_enabled_exists = false;
WARN_ON(!list_empty(&bridge_device->ports_list));
+ WARN_ON(!list_empty(&bridge_device->mids_list));
kfree(bridge_device);
}
@@ -249,7 +265,8 @@ mlxsw_sp_bridge_port_create(struct mlxsw_sp_bridge_device *bridge_device,
bridge_port->dev = brport_dev;
bridge_port->bridge_device = bridge_device;
bridge_port->stp_state = BR_STATE_DISABLED;
- bridge_port->flags = BR_LEARNING | BR_FLOOD | BR_LEARNING_SYNC;
+ bridge_port->flags = BR_LEARNING | BR_FLOOD | BR_LEARNING_SYNC |
+ BR_MCAST_FLOOD;
INIT_LIST_HEAD(&bridge_port->vlans_list);
list_add(&bridge_port->list, &bridge_device->ports_list);
bridge_port->ref_count = 1;
@@ -455,7 +472,8 @@ static int mlxsw_sp_port_attr_get(struct net_device *dev,
&attr->u.brport_flags);
break;
case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT:
- attr->u.brport_flags_support = BR_LEARNING | BR_FLOOD;
+ attr->u.brport_flags_support = BR_LEARNING | BR_FLOOD |
+ BR_MCAST_FLOOD;
break;
default:
return -EOPNOTSUPP;
@@ -640,8 +658,18 @@ static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port,
if (err)
return err;
- memcpy(&bridge_port->flags, &brport_flags, sizeof(brport_flags));
+ if (bridge_port->bridge_device->multicast_enabled)
+ goto out;
+ err = mlxsw_sp_bridge_port_flood_table_set(mlxsw_sp_port, bridge_port,
+ MLXSW_SP_FLOOD_TYPE_MC,
+ brport_flags &
+ BR_MCAST_FLOOD);
+ if (err)
+ return err;
+
+out:
+ memcpy(&bridge_port->flags, &brport_flags, sizeof(brport_flags));
return 0;
}
@@ -699,10 +727,10 @@ static int mlxsw_sp_port_attr_br_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port,
return -EINVAL;
}
-static int mlxsw_sp_port_attr_mc_router_set(struct mlxsw_sp_port *mlxsw_sp_port,
- struct switchdev_trans *trans,
- struct net_device *orig_dev,
- bool is_port_mc_router)
+static int mlxsw_sp_port_attr_mrouter_set(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct switchdev_trans *trans,
+ struct net_device *orig_dev,
+ bool is_port_mrouter)
{
struct mlxsw_sp_bridge_port *bridge_port;
int err;
@@ -720,15 +748,26 @@ static int mlxsw_sp_port_attr_mc_router_set(struct mlxsw_sp_port *mlxsw_sp_port,
err = mlxsw_sp_bridge_port_flood_table_set(mlxsw_sp_port, bridge_port,
MLXSW_SP_FLOOD_TYPE_MC,
- is_port_mc_router);
+ is_port_mrouter);
if (err)
return err;
+ mlxsw_sp_port_mrouter_update_mdb(mlxsw_sp_port, bridge_port,
+ is_port_mrouter);
out:
- bridge_port->mrouter = is_port_mc_router;
+ bridge_port->mrouter = is_port_mrouter;
return 0;
}
+static bool mlxsw_sp_mc_flood(const struct mlxsw_sp_bridge_port *bridge_port)
+{
+ const struct mlxsw_sp_bridge_device *bridge_device;
+
+ bridge_device = bridge_port->bridge_device;
+ return bridge_device->multicast_enabled ? bridge_port->mrouter :
+ bridge_port->flags & BR_MCAST_FLOOD;
+}
+
static int mlxsw_sp_port_mc_disabled_set(struct mlxsw_sp_port *mlxsw_sp_port,
struct switchdev_trans *trans,
struct net_device *orig_dev,
@@ -749,9 +788,15 @@ static int mlxsw_sp_port_mc_disabled_set(struct mlxsw_sp_port *mlxsw_sp_port,
if (!bridge_device)
return 0;
+ if (bridge_device->multicast_enabled != !mc_disabled) {
+ bridge_device->multicast_enabled = !mc_disabled;
+ mlxsw_sp_bridge_mdb_mc_enable_sync(mlxsw_sp_port,
+ bridge_device);
+ }
+
list_for_each_entry(bridge_port, &bridge_device->ports_list, list) {
enum mlxsw_sp_flood_type packet_type = MLXSW_SP_FLOOD_TYPE_MC;
- bool member = mc_disabled ? true : bridge_port->mrouter;
+ bool member = mlxsw_sp_mc_flood(bridge_port);
err = mlxsw_sp_bridge_port_flood_table_set(mlxsw_sp_port,
bridge_port,
@@ -793,9 +838,9 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev,
attr->u.vlan_filtering);
break;
case SWITCHDEV_ATTR_ID_PORT_MROUTER:
- err = mlxsw_sp_port_attr_mc_router_set(mlxsw_sp_port, trans,
- attr->orig_dev,
- attr->u.mrouter);
+ err = mlxsw_sp_port_attr_mrouter_set(mlxsw_sp_port, trans,
+ attr->orig_dev,
+ attr->u.mrouter);
break;
case SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED:
err = mlxsw_sp_port_mc_disabled_set(mlxsw_sp_port, trans,
@@ -810,14 +855,6 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev,
return err;
}
-static bool mlxsw_sp_mc_flood(const struct mlxsw_sp_bridge_port *bridge_port)
-{
- const struct mlxsw_sp_bridge_device *bridge_device;
-
- bridge_device = bridge_port->bridge_device;
- return !bridge_device->multicast_enabled ? true : bridge_port->mrouter;
-}
-
static int
mlxsw_sp_port_vlan_fid_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
struct mlxsw_sp_bridge_port *bridge_port)
@@ -955,24 +992,28 @@ mlxsw_sp_port_vlan_bridge_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
struct mlxsw_sp_bridge_vlan *bridge_vlan;
struct mlxsw_sp_bridge_port *bridge_port;
u16 vid = mlxsw_sp_port_vlan->vid;
- bool last;
+ bool last_port, last_vlan;
if (WARN_ON(mlxsw_sp_fid_type(fid) != MLXSW_SP_FID_TYPE_8021Q &&
mlxsw_sp_fid_type(fid) != MLXSW_SP_FID_TYPE_8021D))
return;
bridge_port = mlxsw_sp_port_vlan->bridge_port;
+ last_vlan = list_is_singular(&bridge_port->vlans_list);
bridge_vlan = mlxsw_sp_bridge_vlan_find(bridge_port, vid);
- last = list_is_singular(&bridge_vlan->port_vlan_list);
+ last_port = list_is_singular(&bridge_vlan->port_vlan_list);
list_del(&mlxsw_sp_port_vlan->bridge_vlan_node);
mlxsw_sp_bridge_vlan_put(bridge_vlan);
mlxsw_sp_port_vid_stp_set(mlxsw_sp_port, vid, BR_STATE_DISABLED);
mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, vid, false);
- if (last)
+ if (last_port)
mlxsw_sp_bridge_port_fdb_flush(mlxsw_sp_port->mlxsw_sp,
bridge_port,
mlxsw_sp_fid_index(fid));
+ if (last_vlan)
+ mlxsw_sp_bridge_port_mdb_flush(mlxsw_sp_port, bridge_port);
+
mlxsw_sp_port_vlan_fid_leave(mlxsw_sp_port_vlan);
mlxsw_sp_bridge_port_put(mlxsw_sp_port->mlxsw_sp->bridge, bridge_port);
@@ -1182,7 +1223,7 @@ mlxsw_sp_port_fdb_set(struct mlxsw_sp_port *mlxsw_sp_port,
}
static int mlxsw_sp_port_mdb_op(struct mlxsw_sp *mlxsw_sp, const char *addr,
- u16 fid, u16 mid, bool adding)
+ u16 fid, u16 mid_idx, bool adding)
{
char *sfd_pl;
int err;
@@ -1193,16 +1234,15 @@ static int mlxsw_sp_port_mdb_op(struct mlxsw_sp *mlxsw_sp, const char *addr,
mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0);
mlxsw_reg_sfd_mc_pack(sfd_pl, 0, addr, fid,
- MLXSW_REG_SFD_REC_ACTION_NOP, mid);
+ MLXSW_REG_SFD_REC_ACTION_NOP, mid_idx);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
kfree(sfd_pl);
return err;
}
-static int mlxsw_sp_port_smid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mid,
- bool add, bool clear_all_ports)
+static int mlxsw_sp_port_smid_full_entry(struct mlxsw_sp *mlxsw_sp, u16 mid_idx,
+ long *ports_bitmap)
{
- struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
char *smid_pl;
int err, i;
@@ -1210,66 +1250,201 @@ static int mlxsw_sp_port_smid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mid,
if (!smid_pl)
return -ENOMEM;
- mlxsw_reg_smid_pack(smid_pl, mid, mlxsw_sp_port->local_port, add);
- if (clear_all_ports) {
- for (i = 1; i < mlxsw_core_max_ports(mlxsw_sp->core); i++)
- if (mlxsw_sp->ports[i])
- mlxsw_reg_smid_port_mask_set(smid_pl, i, 1);
+ mlxsw_reg_smid_pack(smid_pl, mid_idx, 0, false);
+ for (i = 1; i < mlxsw_core_max_ports(mlxsw_sp->core); i++) {
+ if (mlxsw_sp->ports[i])
+ mlxsw_reg_smid_port_mask_set(smid_pl, i, 1);
}
+
+ for_each_set_bit(i, ports_bitmap, mlxsw_core_max_ports(mlxsw_sp->core))
+ mlxsw_reg_smid_port_set(smid_pl, i, 1);
+
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(smid), smid_pl);
kfree(smid_pl);
return err;
}
-static struct mlxsw_sp_mid *__mlxsw_sp_mc_get(struct mlxsw_sp *mlxsw_sp,
- const unsigned char *addr,
- u16 fid)
+static int mlxsw_sp_port_smid_set(struct mlxsw_sp_port *mlxsw_sp_port,
+ u16 mid_idx, bool add)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ char *smid_pl;
+ int err;
+
+ smid_pl = kmalloc(MLXSW_REG_SMID_LEN, GFP_KERNEL);
+ if (!smid_pl)
+ return -ENOMEM;
+
+ mlxsw_reg_smid_pack(smid_pl, mid_idx, mlxsw_sp_port->local_port, add);
+ err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(smid), smid_pl);
+ kfree(smid_pl);
+ return err;
+}
+
+static struct
+mlxsw_sp_mid *__mlxsw_sp_mc_get(struct mlxsw_sp_bridge_device *bridge_device,
+ const unsigned char *addr,
+ u16 fid)
{
struct mlxsw_sp_mid *mid;
- list_for_each_entry(mid, &mlxsw_sp->bridge->mids_list, list) {
+ list_for_each_entry(mid, &bridge_device->mids_list, list) {
if (ether_addr_equal(mid->addr, addr) && mid->fid == fid)
return mid;
}
return NULL;
}
-static struct mlxsw_sp_mid *__mlxsw_sp_mc_alloc(struct mlxsw_sp *mlxsw_sp,
- const unsigned char *addr,
- u16 fid)
+static void
+mlxsw_sp_bridge_port_get_ports_bitmap(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_bridge_port *bridge_port,
+ unsigned long *ports_bitmap)
{
- struct mlxsw_sp_mid *mid;
+ struct mlxsw_sp_port *mlxsw_sp_port;
+ u64 max_lag_members, i;
+ int lag_id;
+
+ if (!bridge_port->lagged) {
+ set_bit(bridge_port->system_port, ports_bitmap);
+ } else {
+ max_lag_members = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+ MAX_LAG_MEMBERS);
+ lag_id = bridge_port->lag_id;
+ for (i = 0; i < max_lag_members; i++) {
+ mlxsw_sp_port = mlxsw_sp_port_lagged_get(mlxsw_sp,
+ lag_id, i);
+ if (mlxsw_sp_port)
+ set_bit(mlxsw_sp_port->local_port,
+ ports_bitmap);
+ }
+ }
+}
+
+static void
+mlxsw_sp_mc_get_mrouters_bitmap(unsigned long *flood_bitmap,
+ struct mlxsw_sp_bridge_device *bridge_device,
+ struct mlxsw_sp *mlxsw_sp)
+{
+ struct mlxsw_sp_bridge_port *bridge_port;
+
+ list_for_each_entry(bridge_port, &bridge_device->ports_list, list) {
+ if (bridge_port->mrouter) {
+ mlxsw_sp_bridge_port_get_ports_bitmap(mlxsw_sp,
+ bridge_port,
+ flood_bitmap);
+ }
+ }
+}
+
+static bool
+mlxsw_sp_mc_write_mdb_entry(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_mid *mid,
+ struct mlxsw_sp_bridge_device *bridge_device)
+{
+ long *flood_bitmap;
+ int num_of_ports;
+ int alloc_size;
u16 mid_idx;
+ int err;
mid_idx = find_first_zero_bit(mlxsw_sp->bridge->mids_bitmap,
MLXSW_SP_MID_MAX);
if (mid_idx == MLXSW_SP_MID_MAX)
- return NULL;
+ return false;
+
+ num_of_ports = mlxsw_core_max_ports(mlxsw_sp->core);
+ alloc_size = sizeof(long) * BITS_TO_LONGS(num_of_ports);
+ flood_bitmap = kzalloc(alloc_size, GFP_KERNEL);
+ if (!flood_bitmap)
+ return false;
+
+ bitmap_copy(flood_bitmap, mid->ports_in_mid, num_of_ports);
+ mlxsw_sp_mc_get_mrouters_bitmap(flood_bitmap, bridge_device, mlxsw_sp);
+
+ mid->mid = mid_idx;
+ err = mlxsw_sp_port_smid_full_entry(mlxsw_sp, mid_idx, flood_bitmap);
+ kfree(flood_bitmap);
+ if (err)
+ return false;
+
+ err = mlxsw_sp_port_mdb_op(mlxsw_sp, mid->addr, mid->fid, mid_idx,
+ true);
+ if (err)
+ return false;
+
+ set_bit(mid_idx, mlxsw_sp->bridge->mids_bitmap);
+ mid->in_hw = true;
+ return true;
+}
+
+static int mlxsw_sp_mc_remove_mdb_entry(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_mid *mid)
+{
+ if (!mid->in_hw)
+ return 0;
+
+ clear_bit(mid->mid, mlxsw_sp->bridge->mids_bitmap);
+ mid->in_hw = false;
+ return mlxsw_sp_port_mdb_op(mlxsw_sp, mid->addr, mid->fid, mid->mid,
+ false);
+}
+
+static struct
+mlxsw_sp_mid *__mlxsw_sp_mc_alloc(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_bridge_device *bridge_device,
+ const unsigned char *addr,
+ u16 fid)
+{
+ struct mlxsw_sp_mid *mid;
+ size_t alloc_size;
mid = kzalloc(sizeof(*mid), GFP_KERNEL);
if (!mid)
return NULL;
- set_bit(mid_idx, mlxsw_sp->bridge->mids_bitmap);
+ alloc_size = sizeof(unsigned long) *
+ BITS_TO_LONGS(mlxsw_core_max_ports(mlxsw_sp->core));
+
+ mid->ports_in_mid = kzalloc(alloc_size, GFP_KERNEL);
+ if (!mid->ports_in_mid)
+ goto err_ports_in_mid_alloc;
+
ether_addr_copy(mid->addr, addr);
mid->fid = fid;
- mid->mid = mid_idx;
- mid->ref_count = 0;
- list_add_tail(&mid->list, &mlxsw_sp->bridge->mids_list);
+ mid->in_hw = false;
+
+ if (!bridge_device->multicast_enabled)
+ goto out;
+
+ if (!mlxsw_sp_mc_write_mdb_entry(mlxsw_sp, mid, bridge_device))
+ goto err_write_mdb_entry;
+out:
+ list_add_tail(&mid->list, &bridge_device->mids_list);
return mid;
+
+err_write_mdb_entry:
+ kfree(mid->ports_in_mid);
+err_ports_in_mid_alloc:
+ kfree(mid);
+ return NULL;
}
-static int __mlxsw_sp_mc_dec_ref(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_mid *mid)
+static int mlxsw_sp_port_remove_from_mid(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_mid *mid)
{
- if (--mid->ref_count == 0) {
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ int err = 0;
+
+ clear_bit(mlxsw_sp_port->local_port, mid->ports_in_mid);
+ if (bitmap_empty(mid->ports_in_mid,
+ mlxsw_core_max_ports(mlxsw_sp->core))) {
+ err = mlxsw_sp_mc_remove_mdb_entry(mlxsw_sp, mid);
list_del(&mid->list);
- clear_bit(mid->mid, mlxsw_sp->bridge->mids_bitmap);
+ kfree(mid->ports_in_mid);
kfree(mid);
- return 1;
}
- return 0;
+ return err;
}
static int mlxsw_sp_port_mdb_add(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -1302,39 +1477,72 @@ static int mlxsw_sp_port_mdb_add(struct mlxsw_sp_port *mlxsw_sp_port,
fid_index = mlxsw_sp_fid_index(mlxsw_sp_port_vlan->fid);
- mid = __mlxsw_sp_mc_get(mlxsw_sp, mdb->addr, fid_index);
+ mid = __mlxsw_sp_mc_get(bridge_device, mdb->addr, fid_index);
if (!mid) {
- mid = __mlxsw_sp_mc_alloc(mlxsw_sp, mdb->addr, fid_index);
+ mid = __mlxsw_sp_mc_alloc(mlxsw_sp, bridge_device, mdb->addr,
+ fid_index);
if (!mid) {
netdev_err(dev, "Unable to allocate MC group\n");
return -ENOMEM;
}
}
- mid->ref_count++;
+ set_bit(mlxsw_sp_port->local_port, mid->ports_in_mid);
+
+ if (!bridge_device->multicast_enabled)
+ return 0;
+
+ if (bridge_port->mrouter)
+ return 0;
- err = mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid, true,
- mid->ref_count == 1);
+ err = mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid, true);
if (err) {
netdev_err(dev, "Unable to set SMID\n");
goto err_out;
}
- if (mid->ref_count == 1) {
- err = mlxsw_sp_port_mdb_op(mlxsw_sp, mdb->addr, fid_index,
- mid->mid, true);
- if (err) {
- netdev_err(dev, "Unable to set MC SFD\n");
- goto err_out;
- }
- }
-
return 0;
err_out:
- __mlxsw_sp_mc_dec_ref(mlxsw_sp, mid);
+ mlxsw_sp_port_remove_from_mid(mlxsw_sp_port, mid);
return err;
}
+static void
+mlxsw_sp_bridge_mdb_mc_enable_sync(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_bridge_device
+ *bridge_device)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ struct mlxsw_sp_mid *mid;
+ bool mc_enabled;
+
+ mc_enabled = bridge_device->multicast_enabled;
+
+ list_for_each_entry(mid, &bridge_device->mids_list, list) {
+ if (mc_enabled)
+ mlxsw_sp_mc_write_mdb_entry(mlxsw_sp, mid,
+ bridge_device);
+ else
+ mlxsw_sp_mc_remove_mdb_entry(mlxsw_sp, mid);
+ }
+}
+
+static void
+mlxsw_sp_port_mrouter_update_mdb(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_bridge_port *bridge_port,
+ bool add)
+{
+ struct mlxsw_sp_bridge_device *bridge_device;
+ struct mlxsw_sp_mid *mid;
+
+ bridge_device = bridge_port->bridge_device;
+
+ list_for_each_entry(mid, &bridge_device->mids_list, list) {
+ if (!test_bit(mlxsw_sp_port->local_port, mid->ports_in_mid))
+ mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid, add);
+ }
+}
+
static int mlxsw_sp_port_obj_add(struct net_device *dev,
const struct switchdev_obj *obj,
struct switchdev_trans *trans)
@@ -1399,6 +1607,30 @@ static int mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port,
return 0;
}
+static int
+__mlxsw_sp_port_mdb_del(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_bridge_port *bridge_port,
+ struct mlxsw_sp_mid *mid)
+{
+ struct net_device *dev = mlxsw_sp_port->dev;
+ int err;
+
+ if (bridge_port->bridge_device->multicast_enabled) {
+ if (bridge_port->bridge_device->multicast_enabled) {
+ err = mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid,
+ false);
+ if (err)
+ netdev_err(dev, "Unable to remove port from SMID\n");
+ }
+ }
+
+ err = mlxsw_sp_port_remove_from_mid(mlxsw_sp_port, mid);
+ if (err)
+ netdev_err(dev, "Unable to remove MC SFD\n");
+
+ return err;
+}
+
static int mlxsw_sp_port_mdb_del(struct mlxsw_sp_port *mlxsw_sp_port,
const struct switchdev_obj_port_mdb *mdb)
{
@@ -1410,8 +1642,6 @@ static int mlxsw_sp_port_mdb_del(struct mlxsw_sp_port *mlxsw_sp_port,
struct mlxsw_sp_bridge_port *bridge_port;
struct mlxsw_sp_mid *mid;
u16 fid_index;
- u16 mid_idx;
- int err = 0;
bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev);
if (!bridge_port)
@@ -1426,25 +1656,33 @@ static int mlxsw_sp_port_mdb_del(struct mlxsw_sp_port *mlxsw_sp_port,
fid_index = mlxsw_sp_fid_index(mlxsw_sp_port_vlan->fid);
- mid = __mlxsw_sp_mc_get(mlxsw_sp, mdb->addr, fid_index);
+ mid = __mlxsw_sp_mc_get(bridge_device, mdb->addr, fid_index);
if (!mid) {
netdev_err(dev, "Unable to remove port from MC DB\n");
return -EINVAL;
}
- err = mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid, false, false);
- if (err)
- netdev_err(dev, "Unable to remove port from SMID\n");
+ return __mlxsw_sp_port_mdb_del(mlxsw_sp_port, bridge_port, mid);
+}
- mid_idx = mid->mid;
- if (__mlxsw_sp_mc_dec_ref(mlxsw_sp, mid)) {
- err = mlxsw_sp_port_mdb_op(mlxsw_sp, mdb->addr, fid_index,
- mid_idx, false);
- if (err)
- netdev_err(dev, "Unable to remove MC SFD\n");
- }
+static void
+mlxsw_sp_bridge_port_mdb_flush(struct mlxsw_sp_port *mlxsw_sp_port,
+ struct mlxsw_sp_bridge_port *bridge_port)
+{
+ struct mlxsw_sp_bridge_device *bridge_device;
+ struct mlxsw_sp_mid *mid, *tmp;
- return err;
+ bridge_device = bridge_port->bridge_device;
+
+ list_for_each_entry_safe(mid, tmp, &bridge_device->mids_list, list) {
+ if (test_bit(mlxsw_sp_port->local_port, mid->ports_in_mid)) {
+ __mlxsw_sp_port_mdb_del(mlxsw_sp_port, bridge_port,
+ mid);
+ } else if (bridge_device->multicast_enabled &&
+ bridge_port->mrouter) {
+ mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid, false);
+ }
+ }
}
static int mlxsw_sp_port_obj_del(struct net_device *dev,
@@ -1981,17 +2219,6 @@ static void mlxsw_sp_fdb_fini(struct mlxsw_sp *mlxsw_sp)
}
-static void mlxsw_sp_mids_fini(struct mlxsw_sp *mlxsw_sp)
-{
- struct mlxsw_sp_mid *mid, *tmp;
-
- list_for_each_entry_safe(mid, tmp, &mlxsw_sp->bridge->mids_list, list) {
- list_del(&mid->list);
- clear_bit(mid->mid, mlxsw_sp->bridge->mids_bitmap);
- kfree(mid);
- }
-}
-
int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp)
{
struct mlxsw_sp_bridge *bridge;
@@ -2003,7 +2230,6 @@ int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp)
bridge->mlxsw_sp = mlxsw_sp;
INIT_LIST_HEAD(&mlxsw_sp->bridge->bridges_list);
- INIT_LIST_HEAD(&mlxsw_sp->bridge->mids_list);
bridge->bridge_8021q_ops = &mlxsw_sp_bridge_8021q_ops;
bridge->bridge_8021d_ops = &mlxsw_sp_bridge_8021d_ops;
@@ -2014,7 +2240,6 @@ int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp)
void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp)
{
mlxsw_sp_fdb_fini(mlxsw_sp);
- mlxsw_sp_mids_fini(mlxsw_sp);
WARN_ON(!list_empty(&mlxsw_sp->bridge->bridges_list));
kfree(mlxsw_sp->bridge);
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index f396a1fef633..ec6cef8267ae 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -62,6 +62,8 @@ enum {
MLXSW_TRAP_ID_TTLERROR = 0x53,
MLXSW_TRAP_ID_LBERROR = 0x54,
MLXSW_TRAP_ID_IPV4_OSPF = 0x55,
+ MLXSW_TRAP_ID_IPV4_PIM = 0x58,
+ MLXSW_TRAP_ID_RPF = 0x5C,
MLXSW_TRAP_ID_IP2ME = 0x5F,
MLXSW_TRAP_ID_IPV6_UNSPECIFIED_ADDRESS = 0x60,
MLXSW_TRAP_ID_IPV6_LINK_LOCAL_DEST = 0x61,
@@ -89,6 +91,10 @@ enum {
MLXSW_TRAP_ID_ROUTER_ALERT_IPV4 = 0xD6,
MLXSW_TRAP_ID_ROUTER_ALERT_IPV6 = 0xD7,
MLXSW_TRAP_ID_ACL0 = 0x1C0,
+ /* Multicast trap used for routes with trap action */
+ MLXSW_TRAP_ID_ACL1 = 0x1C1,
+ /* Multicast trap used for routes with trap-and-forward action */
+ MLXSW_TRAP_ID_ACL2 = 0x1C2,
MLXSW_TRAP_ID_MAX = 0x1FF
};
diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c
index 18af2a23a933..dedeacd0bbca 100644
--- a/drivers/net/ethernet/natsemi/natsemi.c
+++ b/drivers/net/ethernet/natsemi/natsemi.c
@@ -1571,10 +1571,8 @@ static int netdev_open(struct net_device *dev)
dev->name, (int)readl(ioaddr + ChipCmd));
/* Set the timer to check for link beat. */
- init_timer(&np->timer);
+ setup_timer(&np->timer, netdev_timer, (unsigned long)dev);
np->timer.expires = round_jiffies(jiffies + NATSEMI_TIMER_FREQ);
- np->timer.data = (unsigned long)dev;
- np->timer.function = netdev_timer; /* timer handler */
add_timer(&np->timer);
return 0;
diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c
index 729095db3e08..99d3c7884a4a 100644
--- a/drivers/net/ethernet/natsemi/ns83820.c
+++ b/drivers/net/ethernet/natsemi/ns83820.c
@@ -1652,9 +1652,7 @@ static int ns83820_open(struct net_device *ndev)
writel(0, dev->base + TXDP_HI);
writel(desc, dev->base + TXDP);
- init_timer(&dev->tx_watchdog);
- dev->tx_watchdog.data = (unsigned long)ndev;
- dev->tx_watchdog.function = ns83820_tx_watch;
+ setup_timer(&dev->tx_watchdog, ns83820_tx_watch, (unsigned long)ndev);
mod_timer(&dev->tx_watchdog, jiffies + 2*HZ);
netif_start_queue(ndev); /* FIXME: wait for phy to come up */
diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile
index 96e579a15cbe..becaacf1554d 100644
--- a/drivers/net/ethernet/netronome/nfp/Makefile
+++ b/drivers/net/ethernet/netronome/nfp/Makefile
@@ -37,7 +37,8 @@ nfp-objs += \
flower/main.o \
flower/match.o \
flower/metadata.o \
- flower/offload.o
+ flower/offload.o \
+ flower/tunnel_conf.o
endif
ifeq ($(CONFIG_BPF_SYSCALL),y)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index db9750695dc7..38f3835ae176 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -37,6 +37,7 @@
#include <net/tc_act/tc_gact.h>
#include <net/tc_act/tc_mirred.h>
#include <net/tc_act/tc_vlan.h>
+#include <net/tc_act/tc_tunnel_key.h>
#include "cmsg.h"
#include "main.h"
@@ -80,14 +81,27 @@ nfp_fl_push_vlan(struct nfp_fl_push_vlan *push_vlan,
push_vlan->vlan_tci = cpu_to_be16(tmp_push_vlan_tci);
}
+static bool nfp_fl_netdev_is_tunnel_type(struct net_device *out_dev,
+ enum nfp_flower_tun_type tun_type)
+{
+ if (!out_dev->rtnl_link_ops)
+ return false;
+
+ if (!strcmp(out_dev->rtnl_link_ops->kind, "vxlan"))
+ return tun_type == NFP_FL_TUNNEL_VXLAN;
+
+ return false;
+}
+
static int
nfp_fl_output(struct nfp_fl_output *output, const struct tc_action *action,
struct nfp_fl_payload *nfp_flow, bool last,
- struct net_device *in_dev)
+ struct net_device *in_dev, enum nfp_flower_tun_type tun_type,
+ int *tun_out_cnt)
{
size_t act_size = sizeof(struct nfp_fl_output);
+ u16 tmp_output_op, tmp_flags;
struct net_device *out_dev;
- u16 tmp_output_op;
int ifindex;
/* Set action opcode to output action. */
@@ -97,25 +111,114 @@ nfp_fl_output(struct nfp_fl_output *output, const struct tc_action *action,
output->a_op = cpu_to_be16(tmp_output_op);
- /* Set action output parameters. */
- output->flags = cpu_to_be16(last ? NFP_FL_OUT_FLAGS_LAST : 0);
-
ifindex = tcf_mirred_ifindex(action);
out_dev = __dev_get_by_index(dev_net(in_dev), ifindex);
if (!out_dev)
return -EOPNOTSUPP;
- /* Only offload egress ports are on the same device as the ingress
- * port.
+ tmp_flags = last ? NFP_FL_OUT_FLAGS_LAST : 0;
+
+ if (tun_type) {
+ /* Verify the egress netdev matches the tunnel type. */
+ if (!nfp_fl_netdev_is_tunnel_type(out_dev, tun_type))
+ return -EOPNOTSUPP;
+
+ if (*tun_out_cnt)
+ return -EOPNOTSUPP;
+ (*tun_out_cnt)++;
+
+ output->flags = cpu_to_be16(tmp_flags |
+ NFP_FL_OUT_FLAGS_USE_TUN);
+ output->port = cpu_to_be32(NFP_FL_PORT_TYPE_TUN | tun_type);
+ } else {
+ /* Set action output parameters. */
+ output->flags = cpu_to_be16(tmp_flags);
+
+ /* Only offload if egress ports are on the same device as the
+ * ingress port.
+ */
+ if (!switchdev_port_same_parent_id(in_dev, out_dev))
+ return -EOPNOTSUPP;
+
+ output->port = cpu_to_be32(nfp_repr_get_port_id(out_dev));
+ if (!output->port)
+ return -EOPNOTSUPP;
+ }
+ nfp_flow->meta.shortcut = output->port;
+
+ return 0;
+}
+
+static bool nfp_fl_supported_tun_port(const struct tc_action *action)
+{
+ struct ip_tunnel_info *tun = tcf_tunnel_info(action);
+
+ return tun->key.tp_dst == htons(NFP_FL_VXLAN_PORT);
+}
+
+static struct nfp_fl_pre_tunnel *nfp_fl_pre_tunnel(char *act_data, int act_len)
+{
+ size_t act_size = sizeof(struct nfp_fl_pre_tunnel);
+ struct nfp_fl_pre_tunnel *pre_tun_act;
+ u16 tmp_pre_tun_op;
+
+ /* Pre_tunnel action must be first on action list.
+ * If other actions already exist they need pushed forward.
*/
- if (!switchdev_port_same_parent_id(in_dev, out_dev))
- return -EOPNOTSUPP;
+ if (act_len)
+ memmove(act_data + act_size, act_data, act_len);
+
+ pre_tun_act = (struct nfp_fl_pre_tunnel *)act_data;
+
+ memset(pre_tun_act, 0, act_size);
+
+ tmp_pre_tun_op =
+ FIELD_PREP(NFP_FL_ACT_LEN_LW, act_size >> NFP_FL_LW_SIZ) |
+ FIELD_PREP(NFP_FL_ACT_JMP_ID, NFP_FL_ACTION_OPCODE_PRE_TUNNEL);
+
+ pre_tun_act->a_op = cpu_to_be16(tmp_pre_tun_op);
- output->port = cpu_to_be32(nfp_repr_get_port_id(out_dev));
- if (!output->port)
+ return pre_tun_act;
+}
+
+static int
+nfp_fl_set_vxlan(struct nfp_fl_set_vxlan *set_vxlan,
+ const struct tc_action *action,
+ struct nfp_fl_pre_tunnel *pre_tun)
+{
+ struct ip_tunnel_info *vxlan = tcf_tunnel_info(action);
+ size_t act_size = sizeof(struct nfp_fl_set_vxlan);
+ u32 tmp_set_vxlan_type_index = 0;
+ u16 tmp_set_vxlan_op;
+ /* Currently support one pre-tunnel so index is always 0. */
+ int pretun_idx = 0;
+
+ if (vxlan->options_len) {
+ /* Do not support options e.g. vxlan gpe. */
return -EOPNOTSUPP;
+ }
- nfp_flow->meta.shortcut = output->port;
+ tmp_set_vxlan_op =
+ FIELD_PREP(NFP_FL_ACT_LEN_LW, act_size >> NFP_FL_LW_SIZ) |
+ FIELD_PREP(NFP_FL_ACT_JMP_ID,
+ NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL);
+
+ set_vxlan->a_op = cpu_to_be16(tmp_set_vxlan_op);
+
+ /* Set tunnel type and pre-tunnel index. */
+ tmp_set_vxlan_type_index |=
+ FIELD_PREP(NFP_FL_IPV4_TUNNEL_TYPE, NFP_FL_TUNNEL_VXLAN) |
+ FIELD_PREP(NFP_FL_IPV4_PRE_TUN_INDEX, pretun_idx);
+
+ set_vxlan->tun_type_index = cpu_to_be32(tmp_set_vxlan_type_index);
+
+ set_vxlan->tun_id = vxlan->key.tun_id;
+ set_vxlan->tun_flags = vxlan->key.tun_flags;
+ set_vxlan->ipv4_ttl = vxlan->key.ttl;
+ set_vxlan->ipv4_tos = vxlan->key.tos;
+
+ /* Complete pre_tunnel action. */
+ pre_tun->ipv4_dst = vxlan->key.u.ipv4.dst;
return 0;
}
@@ -123,8 +226,11 @@ nfp_fl_output(struct nfp_fl_output *output, const struct tc_action *action,
static int
nfp_flower_loop_action(const struct tc_action *a,
struct nfp_fl_payload *nfp_fl, int *a_len,
- struct net_device *netdev)
+ struct net_device *netdev,
+ enum nfp_flower_tun_type *tun_type, int *tun_out_cnt)
{
+ struct nfp_fl_pre_tunnel *pre_tun;
+ struct nfp_fl_set_vxlan *s_vxl;
struct nfp_fl_push_vlan *psh_v;
struct nfp_fl_pop_vlan *pop_v;
struct nfp_fl_output *output;
@@ -137,7 +243,8 @@ nfp_flower_loop_action(const struct tc_action *a,
return -EOPNOTSUPP;
output = (struct nfp_fl_output *)&nfp_fl->action_data[*a_len];
- err = nfp_fl_output(output, a, nfp_fl, true, netdev);
+ err = nfp_fl_output(output, a, nfp_fl, true, netdev, *tun_type,
+ tun_out_cnt);
if (err)
return err;
@@ -147,7 +254,8 @@ nfp_flower_loop_action(const struct tc_action *a,
return -EOPNOTSUPP;
output = (struct nfp_fl_output *)&nfp_fl->action_data[*a_len];
- err = nfp_fl_output(output, a, nfp_fl, false, netdev);
+ err = nfp_fl_output(output, a, nfp_fl, false, netdev, *tun_type,
+ tun_out_cnt);
if (err)
return err;
@@ -170,6 +278,29 @@ nfp_flower_loop_action(const struct tc_action *a,
nfp_fl_push_vlan(psh_v, a);
*a_len += sizeof(struct nfp_fl_push_vlan);
+ } else if (is_tcf_tunnel_set(a) && nfp_fl_supported_tun_port(a)) {
+ /* Pre-tunnel action is required for tunnel encap.
+ * This checks for next hop entries on NFP.
+ * If none, the packet falls back before applying other actions.
+ */
+ if (*a_len + sizeof(struct nfp_fl_pre_tunnel) +
+ sizeof(struct nfp_fl_set_vxlan) > NFP_FL_MAX_A_SIZ)
+ return -EOPNOTSUPP;
+
+ *tun_type = NFP_FL_TUNNEL_VXLAN;
+ pre_tun = nfp_fl_pre_tunnel(nfp_fl->action_data, *a_len);
+ nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL);
+ *a_len += sizeof(struct nfp_fl_pre_tunnel);
+
+ s_vxl = (struct nfp_fl_set_vxlan *)&nfp_fl->action_data[*a_len];
+ err = nfp_fl_set_vxlan(s_vxl, a, pre_tun);
+ if (err)
+ return err;
+
+ *a_len += sizeof(struct nfp_fl_set_vxlan);
+ } else if (is_tcf_tunnel_release(a)) {
+ /* Tunnel decap is handled by default so accept action. */
+ return 0;
} else {
/* Currently we do not handle any other actions. */
return -EOPNOTSUPP;
@@ -182,18 +313,22 @@ int nfp_flower_compile_action(struct tc_cls_flower_offload *flow,
struct net_device *netdev,
struct nfp_fl_payload *nfp_flow)
{
- int act_len, act_cnt, err;
+ int act_len, act_cnt, err, tun_out_cnt;
+ enum nfp_flower_tun_type tun_type;
const struct tc_action *a;
LIST_HEAD(actions);
memset(nfp_flow->action_data, 0, NFP_FL_MAX_A_SIZ);
nfp_flow->meta.act_len = 0;
+ tun_type = NFP_FL_TUNNEL_NONE;
act_len = 0;
act_cnt = 0;
+ tun_out_cnt = 0;
tcf_exts_to_list(flow->exts, &actions);
list_for_each_entry(a, &actions, list) {
- err = nfp_flower_loop_action(a, nfp_flow, &act_len, netdev);
+ err = nfp_flower_loop_action(a, nfp_flow, &act_len, netdev,
+ &tun_type, &tun_out_cnt);
if (err)
return err;
act_cnt++;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
index c3ca05d10fe1..6b71c719deba 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
@@ -38,17 +38,10 @@
#include <net/dst_metadata.h>
#include "main.h"
-#include "../nfpcore/nfp_cpp.h"
#include "../nfp_net.h"
#include "../nfp_net_repr.h"
#include "./cmsg.h"
-#define nfp_flower_cmsg_warn(app, fmt, args...) \
- do { \
- if (net_ratelimit()) \
- nfp_warn((app)->cpp, fmt, ## args); \
- } while (0)
-
static struct nfp_flower_cmsg_hdr *
nfp_flower_cmsg_get_hdr(struct sk_buff *skb)
{
@@ -188,6 +181,15 @@ nfp_flower_cmsg_process_one_rx(struct nfp_app *app, struct sk_buff *skb)
case NFP_FLOWER_CMSG_TYPE_FLOW_STATS:
nfp_flower_rx_flow_stats(app, skb);
break;
+ case NFP_FLOWER_CMSG_TYPE_NO_NEIGH:
+ nfp_tunnel_request_route(app, skb);
+ break;
+ case NFP_FLOWER_CMSG_TYPE_ACTIVE_TUNS:
+ nfp_tunnel_keep_alive(app, skb);
+ break;
+ case NFP_FLOWER_CMSG_TYPE_TUN_NEIGH:
+ /* Acks from the NFP that the route is added - ignore. */
+ break;
default:
nfp_flower_cmsg_warn(app, "Cannot handle invalid repr control type %u\n",
type);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index a2ec60344236..504ddaa21701 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -39,6 +39,7 @@
#include <linux/types.h>
#include "../nfp_app.h"
+#include "../nfpcore/nfp_cpp.h"
#define NFP_FLOWER_LAYER_META BIT(0)
#define NFP_FLOWER_LAYER_PORT BIT(1)
@@ -67,10 +68,12 @@
#define NFP_FL_LW_SIZ 2
/* Action opcodes */
-#define NFP_FL_ACTION_OPCODE_OUTPUT 0
-#define NFP_FL_ACTION_OPCODE_PUSH_VLAN 1
-#define NFP_FL_ACTION_OPCODE_POP_VLAN 2
-#define NFP_FL_ACTION_OPCODE_NUM 32
+#define NFP_FL_ACTION_OPCODE_OUTPUT 0
+#define NFP_FL_ACTION_OPCODE_PUSH_VLAN 1
+#define NFP_FL_ACTION_OPCODE_POP_VLAN 2
+#define NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL 6
+#define NFP_FL_ACTION_OPCODE_PRE_TUNNEL 17
+#define NFP_FL_ACTION_OPCODE_NUM 32
#define NFP_FL_ACT_JMP_ID GENMASK(15, 8)
#define NFP_FL_ACT_LEN_LW GENMASK(7, 0)
@@ -83,6 +86,22 @@
#define NFP_FL_PUSH_VLAN_CFI BIT(12)
#define NFP_FL_PUSH_VLAN_VID GENMASK(11, 0)
+/* Tunnel ports */
+#define NFP_FL_PORT_TYPE_TUN 0x50000000
+#define NFP_FL_IPV4_TUNNEL_TYPE GENMASK(7, 4)
+#define NFP_FL_IPV4_PRE_TUN_INDEX GENMASK(2, 0)
+
+#define nfp_flower_cmsg_warn(app, fmt, args...) \
+ do { \
+ if (net_ratelimit()) \
+ nfp_warn((app)->cpp, fmt, ## args); \
+ } while (0)
+
+enum nfp_flower_tun_type {
+ NFP_FL_TUNNEL_NONE = 0,
+ NFP_FL_TUNNEL_VXLAN = 2,
+};
+
struct nfp_fl_output {
__be16 a_op;
__be16 flags;
@@ -115,6 +134,25 @@ struct nfp_flower_meta_one {
u16 reserved;
};
+struct nfp_fl_pre_tunnel {
+ __be16 a_op;
+ __be16 reserved;
+ __be32 ipv4_dst;
+ /* reserved for use with IPv6 addresses */
+ __be32 extra[3];
+};
+
+struct nfp_fl_set_vxlan {
+ __be16 a_op;
+ __be16 reserved;
+ __be64 tun_id;
+ __be32 tun_type_index;
+ __be16 tun_flags;
+ u8 ipv4_ttl;
+ u8 ipv4_tos;
+ __be32 extra[2];
+} __packed;
+
/* Metadata with L2 (1W/4B)
* ----------------------------------------------------------------
* 3 2 1
@@ -230,6 +268,36 @@ struct nfp_flower_ipv6 {
struct in6_addr ipv6_dst;
};
+/* Flow Frame VXLAN --> Tunnel details (4W/16B)
+ * -----------------------------------------------------------------
+ * 3 2 1
+ * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | ipv4_addr_src |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | ipv4_addr_dst |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | tun_flags | tos | ttl |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | gpe_flags | Reserved | Next Protocol |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | VNI | Reserved |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ */
+struct nfp_flower_vxlan {
+ __be32 ip_src;
+ __be32 ip_dst;
+ __be16 tun_flags;
+ u8 tos;
+ u8 ttl;
+ u8 gpe_flags;
+ u8 reserved[2];
+ u8 nxt_proto;
+ __be32 tun_id;
+};
+
+#define NFP_FL_TUN_VNI_OFFSET 8
+
/* The base header for a control message packet.
* Defines an 8-bit version, and an 8-bit type, padded
* to a 32-bit word. Rest of the packet is type-specific.
@@ -249,6 +317,11 @@ enum nfp_flower_cmsg_type_port {
NFP_FLOWER_CMSG_TYPE_FLOW_DEL = 2,
NFP_FLOWER_CMSG_TYPE_MAC_REPR = 7,
NFP_FLOWER_CMSG_TYPE_PORT_MOD = 8,
+ NFP_FLOWER_CMSG_TYPE_NO_NEIGH = 10,
+ NFP_FLOWER_CMSG_TYPE_TUN_MAC = 11,
+ NFP_FLOWER_CMSG_TYPE_ACTIVE_TUNS = 12,
+ NFP_FLOWER_CMSG_TYPE_TUN_NEIGH = 13,
+ NFP_FLOWER_CMSG_TYPE_TUN_IPS = 14,
NFP_FLOWER_CMSG_TYPE_FLOW_STATS = 15,
NFP_FLOWER_CMSG_TYPE_PORT_ECHO = 16,
NFP_FLOWER_CMSG_TYPE_MAX = 32,
@@ -282,6 +355,7 @@ enum nfp_flower_cmsg_port_type {
NFP_FLOWER_CMSG_PORT_TYPE_UNSPEC = 0x0,
NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT = 0x1,
NFP_FLOWER_CMSG_PORT_TYPE_PCIE_PORT = 0x2,
+ NFP_FLOWER_CMSG_PORT_TYPE_OTHER_PORT = 0x3,
};
enum nfp_flower_cmsg_port_vnic_type {
@@ -323,6 +397,11 @@ static inline void *nfp_flower_cmsg_get_data(struct sk_buff *skb)
return (unsigned char *)skb->data + NFP_FLOWER_CMSG_HLEN;
}
+static inline int nfp_flower_cmsg_get_data_len(struct sk_buff *skb)
+{
+ return skb->len - NFP_FLOWER_CMSG_HLEN;
+}
+
struct sk_buff *
nfp_flower_cmsg_mac_repr_start(struct nfp_app *app, unsigned int num_ports);
void
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index 91fe03617106..e46e7c60d491 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -436,6 +436,16 @@ static void nfp_flower_clean(struct nfp_app *app)
app->priv = NULL;
}
+static int nfp_flower_start(struct nfp_app *app)
+{
+ return nfp_tunnel_config_start(app);
+}
+
+static void nfp_flower_stop(struct nfp_app *app)
+{
+ nfp_tunnel_config_stop(app);
+}
+
const struct nfp_app_type app_flower = {
.id = NFP_APP_FLOWER_NIC,
.name = "flower",
@@ -453,6 +463,9 @@ const struct nfp_app_type app_flower = {
.repr_open = nfp_flower_repr_netdev_open,
.repr_stop = nfp_flower_repr_netdev_stop,
+ .start = nfp_flower_start,
+ .stop = nfp_flower_stop,
+
.ctrl_msg_rx = nfp_flower_cmsg_rx,
.sriov_enable = nfp_flower_sriov_enable,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index c20dd00a1cae..12c319a219d8 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -58,6 +58,8 @@ struct nfp_app;
#define NFP_FL_MASK_REUSE_TIME_NS 40000
#define NFP_FL_MASK_ID_LOCATION 1
+#define NFP_FL_VXLAN_PORT 4789
+
struct nfp_fl_mask_id {
struct circ_buf mask_id_free_list;
struct timespec64 *last_used;
@@ -82,6 +84,18 @@ struct nfp_fl_stats_id {
* @flow_table: Hash table used to store flower rules
* @cmsg_work: Workqueue for control messages processing
* @cmsg_skbs: List of skbs for control message processing
+ * @nfp_mac_off_list: List of MAC addresses to offload
+ * @nfp_mac_index_list: List of unique 8-bit indexes for non NFP netdevs
+ * @nfp_ipv4_off_list: List of IPv4 addresses to offload
+ * @nfp_neigh_off_list: List of neighbour offloads
+ * @nfp_mac_off_lock: Lock for the MAC address list
+ * @nfp_mac_index_lock: Lock for the MAC index list
+ * @nfp_ipv4_off_lock: Lock for the IPv4 address list
+ * @nfp_neigh_off_lock: Lock for the neighbour address list
+ * @nfp_mac_off_ids: IDA to manage id assignment for offloaded macs
+ * @nfp_mac_off_count: Number of MACs in address list
+ * @nfp_tun_mac_nb: Notifier to monitor link state
+ * @nfp_tun_neigh_nb: Notifier to monitor neighbour state
*/
struct nfp_flower_priv {
struct nfp_app *app;
@@ -94,6 +108,18 @@ struct nfp_flower_priv {
DECLARE_HASHTABLE(flow_table, NFP_FLOWER_HASH_BITS);
struct work_struct cmsg_work;
struct sk_buff_head cmsg_skbs;
+ struct list_head nfp_mac_off_list;
+ struct list_head nfp_mac_index_list;
+ struct list_head nfp_ipv4_off_list;
+ struct list_head nfp_neigh_off_list;
+ struct mutex nfp_mac_off_lock;
+ struct mutex nfp_mac_index_lock;
+ struct mutex nfp_ipv4_off_lock;
+ struct mutex nfp_neigh_off_lock;
+ struct ida nfp_mac_off_ids;
+ int nfp_mac_off_count;
+ struct notifier_block nfp_tun_mac_nb;
+ struct notifier_block nfp_tun_neigh_nb;
};
struct nfp_fl_key_ls {
@@ -126,6 +152,7 @@ struct nfp_fl_payload {
struct rcu_head rcu;
spinlock_t lock; /* lock stats */
struct nfp_fl_stats stats;
+ __be32 nfp_tun_ipv4_addr;
char *unmasked_data;
char *mask_data;
char *action_data;
@@ -163,4 +190,12 @@ nfp_flower_remove_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie);
void nfp_flower_rx_flow_stats(struct nfp_app *app, struct sk_buff *skb);
+int nfp_tunnel_config_start(struct nfp_app *app);
+void nfp_tunnel_config_stop(struct nfp_app *app);
+void nfp_tunnel_write_macs(struct nfp_app *app);
+void nfp_tunnel_del_ipv4_off(struct nfp_app *app, __be32 ipv4);
+void nfp_tunnel_add_ipv4_off(struct nfp_app *app, __be32 ipv4);
+void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb);
+void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb);
+
#endif
diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index d25b5038c3a2..865a815ab92a 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -77,14 +77,17 @@ nfp_flower_compile_meta(struct nfp_flower_meta_one *frame, u8 key_type)
static int
nfp_flower_compile_port(struct nfp_flower_in_port *frame, u32 cmsg_port,
- bool mask_version)
+ bool mask_version, enum nfp_flower_tun_type tun_type)
{
if (mask_version) {
frame->in_port = cpu_to_be32(~0);
return 0;
}
- frame->in_port = cpu_to_be32(cmsg_port);
+ if (tun_type)
+ frame->in_port = cpu_to_be32(NFP_FL_PORT_TYPE_TUN | tun_type);
+ else
+ frame->in_port = cpu_to_be32(cmsg_port);
return 0;
}
@@ -189,15 +192,56 @@ nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *frame,
}
}
+static void
+nfp_flower_compile_vxlan(struct nfp_flower_vxlan *frame,
+ struct tc_cls_flower_offload *flow,
+ bool mask_version, __be32 *tun_dst)
+{
+ struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
+ struct flow_dissector_key_ipv4_addrs *vxlan_ips;
+ struct flow_dissector_key_keyid *vni;
+
+ /* Wildcard TOS/TTL/GPE_FLAGS/NXT_PROTO for now. */
+ memset(frame, 0, sizeof(struct nfp_flower_vxlan));
+
+ if (dissector_uses_key(flow->dissector,
+ FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+ u32 temp_vni;
+
+ vni = skb_flow_dissector_target(flow->dissector,
+ FLOW_DISSECTOR_KEY_ENC_KEYID,
+ target);
+ temp_vni = be32_to_cpu(vni->keyid) << NFP_FL_TUN_VNI_OFFSET;
+ frame->tun_id = cpu_to_be32(temp_vni);
+ }
+
+ if (dissector_uses_key(flow->dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
+ vxlan_ips =
+ skb_flow_dissector_target(flow->dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
+ target);
+ frame->ip_src = vxlan_ips->src;
+ frame->ip_dst = vxlan_ips->dst;
+ *tun_dst = vxlan_ips->dst;
+ }
+}
+
int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
struct nfp_fl_key_ls *key_ls,
struct net_device *netdev,
struct nfp_fl_payload *nfp_flow)
{
+ enum nfp_flower_tun_type tun_type = NFP_FL_TUNNEL_NONE;
+ __be32 tun_dst, tun_dst_mask = 0;
+ struct nfp_repr *netdev_repr;
int err;
u8 *ext;
u8 *msk;
+ if (key_ls->key_layer & NFP_FLOWER_LAYER_VXLAN)
+ tun_type = NFP_FL_TUNNEL_VXLAN;
+
memset(nfp_flow->unmasked_data, 0, key_ls->key_size);
memset(nfp_flow->mask_data, 0, key_ls->key_size);
@@ -216,14 +260,14 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
/* Populate Exact Port data. */
err = nfp_flower_compile_port((struct nfp_flower_in_port *)ext,
nfp_repr_get_port_id(netdev),
- false);
+ false, tun_type);
if (err)
return err;
/* Populate Mask Port Data. */
err = nfp_flower_compile_port((struct nfp_flower_in_port *)msk,
nfp_repr_get_port_id(netdev),
- true);
+ true, tun_type);
if (err)
return err;
@@ -291,5 +335,28 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
msk += sizeof(struct nfp_flower_ipv6);
}
+ if (key_ls->key_layer & NFP_FLOWER_LAYER_VXLAN) {
+ /* Populate Exact VXLAN Data. */
+ nfp_flower_compile_vxlan((struct nfp_flower_vxlan *)ext,
+ flow, false, &tun_dst);
+ /* Populate Mask VXLAN Data. */
+ nfp_flower_compile_vxlan((struct nfp_flower_vxlan *)msk,
+ flow, true, &tun_dst_mask);
+ ext += sizeof(struct nfp_flower_vxlan);
+ msk += sizeof(struct nfp_flower_vxlan);
+
+ /* Configure tunnel end point MAC. */
+ if (nfp_netdev_is_nfp_repr(netdev)) {
+ netdev_repr = netdev_priv(netdev);
+ nfp_tunnel_write_macs(netdev_repr->app);
+
+ /* Store the tunnel destination in the rule data.
+ * This must be present and be an exact match.
+ */
+ nfp_flow->nfp_tun_ipv4_addr = tun_dst;
+ nfp_tunnel_add_ipv4_off(netdev_repr->app, tun_dst);
+ }
+ }
+
return 0;
}
diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
index 3226ddc55f99..193520ef23f0 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
@@ -140,7 +140,7 @@ exit_rcu_unlock:
void nfp_flower_rx_flow_stats(struct nfp_app *app, struct sk_buff *skb)
{
- unsigned int msg_len = skb->len - NFP_FLOWER_CMSG_HLEN;
+ unsigned int msg_len = nfp_flower_cmsg_get_data_len(skb);
struct nfp_fl_stats_frame *stats_frame;
unsigned char *msg;
int i;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index a18b4d2b1d3e..3d9537ebdea4 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -52,8 +52,25 @@
BIT(FLOW_DISSECTOR_KEY_PORTS) | \
BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | \
BIT(FLOW_DISSECTOR_KEY_VLAN) | \
+ BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | \
+ BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \
+ BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \
+ BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
+ BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | \
BIT(FLOW_DISSECTOR_KEY_IP))
+#define NFP_FLOWER_WHITELIST_TUN_DISSECTOR \
+ (BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
+ BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | \
+ BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \
+ BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \
+ BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))
+
+#define NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R \
+ (BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
+ BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \
+ BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))
+
static int
nfp_flower_xmit_flow(struct net_device *netdev,
struct nfp_fl_payload *nfp_flow, u8 mtype)
@@ -125,15 +142,58 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls,
if (flow->dissector->used_keys & ~NFP_FLOWER_WHITELIST_DISSECTOR)
return -EOPNOTSUPP;
+ /* If any tun dissector is used then the required set must be used. */
+ if (flow->dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR &&
+ (flow->dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R)
+ != NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R)
+ return -EOPNOTSUPP;
+
+ key_layer_two = 0;
+ key_layer = NFP_FLOWER_LAYER_PORT | NFP_FLOWER_LAYER_MAC;
+ key_size = sizeof(struct nfp_flower_meta_one) +
+ sizeof(struct nfp_flower_in_port) +
+ sizeof(struct nfp_flower_mac_mpls);
+
if (dissector_uses_key(flow->dissector,
FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
+ struct flow_dissector_key_ipv4_addrs *mask_ipv4 = NULL;
+ struct flow_dissector_key_ports *mask_enc_ports = NULL;
+ struct flow_dissector_key_ports *enc_ports = NULL;
struct flow_dissector_key_control *mask_enc_ctl =
skb_flow_dissector_target(flow->dissector,
FLOW_DISSECTOR_KEY_ENC_CONTROL,
flow->mask);
- /* We are expecting a tunnel. For now we ignore offloading. */
- if (mask_enc_ctl->addr_type)
+ struct flow_dissector_key_control *enc_ctl =
+ skb_flow_dissector_target(flow->dissector,
+ FLOW_DISSECTOR_KEY_ENC_CONTROL,
+ flow->key);
+ if (mask_enc_ctl->addr_type != 0xffff ||
+ enc_ctl->addr_type != FLOW_DISSECTOR_KEY_IPV4_ADDRS)
+ return -EOPNOTSUPP;
+
+ /* These fields are already verified as used. */
+ mask_ipv4 =
+ skb_flow_dissector_target(flow->dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
+ flow->mask);
+ if (mask_ipv4->dst != cpu_to_be32(~0))
+ return -EOPNOTSUPP;
+
+ mask_enc_ports =
+ skb_flow_dissector_target(flow->dissector,
+ FLOW_DISSECTOR_KEY_ENC_PORTS,
+ flow->mask);
+ enc_ports =
+ skb_flow_dissector_target(flow->dissector,
+ FLOW_DISSECTOR_KEY_ENC_PORTS,
+ flow->key);
+
+ if (mask_enc_ports->dst != cpu_to_be16(~0) ||
+ enc_ports->dst != htons(NFP_FL_VXLAN_PORT))
return -EOPNOTSUPP;
+
+ key_layer |= NFP_FLOWER_LAYER_VXLAN;
+ key_size += sizeof(struct nfp_flower_vxlan);
}
if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
@@ -151,12 +211,6 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls,
FLOW_DISSECTOR_KEY_IP,
flow->mask);
- key_layer_two = 0;
- key_layer = NFP_FLOWER_LAYER_PORT | NFP_FLOWER_LAYER_MAC;
- key_size = sizeof(struct nfp_flower_meta_one) +
- sizeof(struct nfp_flower_in_port) +
- sizeof(struct nfp_flower_mac_mpls);
-
if (mask_basic && mask_basic->n_proto) {
/* Ethernet type is present in the key. */
switch (key_basic->n_proto) {
@@ -252,6 +306,7 @@ nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer)
if (!flow_pay->action_data)
goto err_free_mask;
+ flow_pay->nfp_tun_ipv4_addr = 0;
flow_pay->meta.flags = 0;
spin_lock_init(&flow_pay->lock);
@@ -361,6 +416,9 @@ nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev,
if (err)
goto err_free_flow;
+ if (nfp_flow->nfp_tun_ipv4_addr)
+ nfp_tunnel_del_ipv4_off(app, nfp_flow->nfp_tun_ipv4_addr);
+
err = nfp_flower_xmit_flow(netdev, nfp_flow,
NFP_FLOWER_CMSG_TYPE_FLOW_DEL);
if (err)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
new file mode 100644
index 000000000000..c495f8f38506
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -0,0 +1,811 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below. You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/inetdevice.h>
+#include <net/netevent.h>
+#include <linux/idr.h>
+#include <net/dst_metadata.h>
+#include <net/arp.h>
+
+#include "cmsg.h"
+#include "main.h"
+#include "../nfp_net_repr.h"
+#include "../nfp_net.h"
+
+#define NFP_FL_MAX_ROUTES 32
+
+/**
+ * struct nfp_tun_active_tuns - periodic message of active tunnels
+ * @seq: sequence number of the message
+ * @count: number of tunnels report in message
+ * @flags: options part of the request
+ * @ipv4: dest IPv4 address of active route
+ * @egress_port: port the encapsulated packet egressed
+ * @extra: reserved for future use
+ * @tun_info: tunnels that have sent traffic in reported period
+ */
+struct nfp_tun_active_tuns {
+ __be32 seq;
+ __be32 count;
+ __be32 flags;
+ struct route_ip_info {
+ __be32 ipv4;
+ __be32 egress_port;
+ __be32 extra[2];
+ } tun_info[];
+};
+
+/**
+ * struct nfp_tun_neigh - neighbour/route entry on the NFP
+ * @dst_ipv4: destination IPv4 address
+ * @src_ipv4: source IPv4 address
+ * @dst_addr: destination MAC address
+ * @src_addr: source MAC address
+ * @port_id: NFP port to output packet on - associated with source IPv4
+ */
+struct nfp_tun_neigh {
+ __be32 dst_ipv4;
+ __be32 src_ipv4;
+ u8 dst_addr[ETH_ALEN];
+ u8 src_addr[ETH_ALEN];
+ __be32 port_id;
+};
+
+/**
+ * struct nfp_tun_req_route_ipv4 - NFP requests a route/neighbour lookup
+ * @ingress_port: ingress port of packet that signalled request
+ * @ipv4_addr: destination ipv4 address for route
+ * @reserved: reserved for future use
+ */
+struct nfp_tun_req_route_ipv4 {
+ __be32 ingress_port;
+ __be32 ipv4_addr;
+ __be32 reserved[2];
+};
+
+/**
+ * struct nfp_ipv4_route_entry - routes that are offloaded to the NFP
+ * @ipv4_addr: destination of route
+ * @list: list pointer
+ */
+struct nfp_ipv4_route_entry {
+ __be32 ipv4_addr;
+ struct list_head list;
+};
+
+#define NFP_FL_IPV4_ADDRS_MAX 32
+
+/**
+ * struct nfp_tun_ipv4_addr - set the IP address list on the NFP
+ * @count: number of IPs populated in the array
+ * @ipv4_addr: array of IPV4_ADDRS_MAX 32 bit IPv4 addresses
+ */
+struct nfp_tun_ipv4_addr {
+ __be32 count;
+ __be32 ipv4_addr[NFP_FL_IPV4_ADDRS_MAX];
+};
+
+/**
+ * struct nfp_ipv4_addr_entry - cached IPv4 addresses
+ * @ipv4_addr: IP address
+ * @ref_count: number of rules currently using this IP
+ * @list: list pointer
+ */
+struct nfp_ipv4_addr_entry {
+ __be32 ipv4_addr;
+ int ref_count;
+ struct list_head list;
+};
+
+/**
+ * struct nfp_tun_mac_addr - configure MAC address of tunnel EP on NFP
+ * @reserved: reserved for future use
+ * @count: number of MAC addresses in the message
+ * @index: index of MAC address in the lookup table
+ * @addr: interface MAC address
+ * @addresses: series of MACs to offload
+ */
+struct nfp_tun_mac_addr {
+ __be16 reserved;
+ __be16 count;
+ struct index_mac_addr {
+ __be16 index;
+ u8 addr[ETH_ALEN];
+ } addresses[];
+};
+
+/**
+ * struct nfp_tun_mac_offload_entry - list of MACs to offload
+ * @index: index of MAC address for offloading
+ * @addr: interface MAC address
+ * @list: list pointer
+ */
+struct nfp_tun_mac_offload_entry {
+ __be16 index;
+ u8 addr[ETH_ALEN];
+ struct list_head list;
+};
+
+#define NFP_MAX_MAC_INDEX 0xff
+
+/**
+ * struct nfp_tun_mac_non_nfp_idx - converts non NFP netdev ifindex to 8-bit id
+ * @ifindex: netdev ifindex of the device
+ * @index: index of netdevs mac on NFP
+ * @list: list pointer
+ */
+struct nfp_tun_mac_non_nfp_idx {
+ int ifindex;
+ u8 index;
+ struct list_head list;
+};
+
+void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb)
+{
+ struct nfp_tun_active_tuns *payload;
+ struct net_device *netdev;
+ int count, i, pay_len;
+ struct neighbour *n;
+ __be32 ipv4_addr;
+ u32 port;
+
+ payload = nfp_flower_cmsg_get_data(skb);
+ count = be32_to_cpu(payload->count);
+ if (count > NFP_FL_MAX_ROUTES) {
+ nfp_flower_cmsg_warn(app, "Tunnel keep-alive request exceeds max routes.\n");
+ return;
+ }
+
+ pay_len = nfp_flower_cmsg_get_data_len(skb);
+ if (pay_len != sizeof(struct nfp_tun_active_tuns) +
+ sizeof(struct route_ip_info) * count) {
+ nfp_flower_cmsg_warn(app, "Corruption in tunnel keep-alive message.\n");
+ return;
+ }
+
+ for (i = 0; i < count; i++) {
+ ipv4_addr = payload->tun_info[i].ipv4;
+ port = be32_to_cpu(payload->tun_info[i].egress_port);
+ netdev = nfp_app_repr_get(app, port);
+ if (!netdev)
+ continue;
+
+ n = neigh_lookup(&arp_tbl, &ipv4_addr, netdev);
+ if (!n)
+ continue;
+
+ /* Update the used timestamp of neighbour */
+ neigh_event_send(n, NULL);
+ neigh_release(n);
+ }
+}
+
+static bool nfp_tun_is_netdev_to_offload(struct net_device *netdev)
+{
+ if (!netdev->rtnl_link_ops)
+ return false;
+ if (!strcmp(netdev->rtnl_link_ops->kind, "openvswitch"))
+ return true;
+ if (!strcmp(netdev->rtnl_link_ops->kind, "vxlan"))
+ return true;
+
+ return false;
+}
+
+static int
+nfp_flower_xmit_tun_conf(struct nfp_app *app, u8 mtype, u16 plen, void *pdata)
+{
+ struct sk_buff *skb;
+ unsigned char *msg;
+
+ skb = nfp_flower_cmsg_alloc(app, plen, mtype);
+ if (!skb)
+ return -ENOMEM;
+
+ msg = nfp_flower_cmsg_get_data(skb);
+ memcpy(msg, pdata, nfp_flower_cmsg_get_data_len(skb));
+
+ nfp_ctrl_tx(app->ctrl, skb);
+ return 0;
+}
+
+static bool nfp_tun_has_route(struct nfp_app *app, __be32 ipv4_addr)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ struct nfp_ipv4_route_entry *entry;
+ struct list_head *ptr, *storage;
+
+ mutex_lock(&priv->nfp_neigh_off_lock);
+ list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) {
+ entry = list_entry(ptr, struct nfp_ipv4_route_entry, list);
+ if (entry->ipv4_addr == ipv4_addr) {
+ mutex_unlock(&priv->nfp_neigh_off_lock);
+ return true;
+ }
+ }
+ mutex_unlock(&priv->nfp_neigh_off_lock);
+ return false;
+}
+
+static void nfp_tun_add_route_to_cache(struct nfp_app *app, __be32 ipv4_addr)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ struct nfp_ipv4_route_entry *entry;
+ struct list_head *ptr, *storage;
+
+ mutex_lock(&priv->nfp_neigh_off_lock);
+ list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) {
+ entry = list_entry(ptr, struct nfp_ipv4_route_entry, list);
+ if (entry->ipv4_addr == ipv4_addr) {
+ mutex_unlock(&priv->nfp_neigh_off_lock);
+ return;
+ }
+ }
+ entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry) {
+ mutex_unlock(&priv->nfp_neigh_off_lock);
+ nfp_flower_cmsg_warn(app, "Mem error when storing new route.\n");
+ return;
+ }
+
+ entry->ipv4_addr = ipv4_addr;
+ list_add_tail(&entry->list, &priv->nfp_neigh_off_list);
+ mutex_unlock(&priv->nfp_neigh_off_lock);
+}
+
+static void nfp_tun_del_route_from_cache(struct nfp_app *app, __be32 ipv4_addr)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ struct nfp_ipv4_route_entry *entry;
+ struct list_head *ptr, *storage;
+
+ mutex_lock(&priv->nfp_neigh_off_lock);
+ list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) {
+ entry = list_entry(ptr, struct nfp_ipv4_route_entry, list);
+ if (entry->ipv4_addr == ipv4_addr) {
+ list_del(&entry->list);
+ kfree(entry);
+ break;
+ }
+ }
+ mutex_unlock(&priv->nfp_neigh_off_lock);
+}
+
+static void
+nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app,
+ struct flowi4 *flow, struct neighbour *neigh)
+{
+ struct nfp_tun_neigh payload;
+
+ /* Only offload representor IPv4s for now. */
+ if (!nfp_netdev_is_nfp_repr(netdev))
+ return;
+
+ memset(&payload, 0, sizeof(struct nfp_tun_neigh));
+ payload.dst_ipv4 = flow->daddr;
+
+ /* If entry has expired send dst IP with all other fields 0. */
+ if (!(neigh->nud_state & NUD_VALID)) {
+ nfp_tun_del_route_from_cache(app, payload.dst_ipv4);
+ /* Trigger ARP to verify invalid neighbour state. */
+ neigh_event_send(neigh, NULL);
+ goto send_msg;
+ }
+
+ /* Have a valid neighbour so populate rest of entry. */
+ payload.src_ipv4 = flow->saddr;
+ ether_addr_copy(payload.src_addr, netdev->dev_addr);
+ neigh_ha_snapshot(payload.dst_addr, neigh, netdev);
+ payload.port_id = cpu_to_be32(nfp_repr_get_port_id(netdev));
+ /* Add destination of new route to NFP cache. */
+ nfp_tun_add_route_to_cache(app, payload.dst_ipv4);
+
+send_msg:
+ nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_TUN_NEIGH,
+ sizeof(struct nfp_tun_neigh),
+ (unsigned char *)&payload);
+}
+
+static int
+nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event,
+ void *ptr)
+{
+ struct nfp_flower_priv *app_priv;
+ struct netevent_redirect *redir;
+ struct flowi4 flow = {};
+ struct neighbour *n;
+ struct nfp_app *app;
+ struct rtable *rt;
+ int err;
+
+ switch (event) {
+ case NETEVENT_REDIRECT:
+ redir = (struct netevent_redirect *)ptr;
+ n = redir->neigh;
+ break;
+ case NETEVENT_NEIGH_UPDATE:
+ n = (struct neighbour *)ptr;
+ break;
+ default:
+ return NOTIFY_DONE;
+ }
+
+ flow.daddr = *(__be32 *)n->primary_key;
+
+ /* Only concerned with route changes for representors. */
+ if (!nfp_netdev_is_nfp_repr(n->dev))
+ return NOTIFY_DONE;
+
+ app_priv = container_of(nb, struct nfp_flower_priv, nfp_tun_neigh_nb);
+ app = app_priv->app;
+
+ /* Only concerned with changes to routes already added to NFP. */
+ if (!nfp_tun_has_route(app, flow.daddr))
+ return NOTIFY_DONE;
+
+#if IS_ENABLED(CONFIG_INET)
+ /* Do a route lookup to populate flow data. */
+ rt = ip_route_output_key(dev_net(n->dev), &flow);
+ err = PTR_ERR_OR_ZERO(rt);
+ if (err)
+ return NOTIFY_DONE;
+#else
+ return NOTIFY_DONE;
+#endif
+
+ flow.flowi4_proto = IPPROTO_UDP;
+ nfp_tun_write_neigh(n->dev, app, &flow, n);
+
+ return NOTIFY_OK;
+}
+
+void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb)
+{
+ struct nfp_tun_req_route_ipv4 *payload;
+ struct net_device *netdev;
+ struct flowi4 flow = {};
+ struct neighbour *n;
+ struct rtable *rt;
+ int err;
+
+ payload = nfp_flower_cmsg_get_data(skb);
+
+ netdev = nfp_app_repr_get(app, be32_to_cpu(payload->ingress_port));
+ if (!netdev)
+ goto route_fail_warning;
+
+ flow.daddr = payload->ipv4_addr;
+ flow.flowi4_proto = IPPROTO_UDP;
+
+#if IS_ENABLED(CONFIG_INET)
+ /* Do a route lookup on same namespace as ingress port. */
+ rt = ip_route_output_key(dev_net(netdev), &flow);
+ err = PTR_ERR_OR_ZERO(rt);
+ if (err)
+ goto route_fail_warning;
+#else
+ goto route_fail_warning;
+#endif
+
+ /* Get the neighbour entry for the lookup */
+ n = dst_neigh_lookup(&rt->dst, &flow.daddr);
+ ip_rt_put(rt);
+ if (!n)
+ goto route_fail_warning;
+ nfp_tun_write_neigh(n->dev, app, &flow, n);
+ neigh_release(n);
+ return;
+
+route_fail_warning:
+ nfp_flower_cmsg_warn(app, "Requested route not found.\n");
+}
+
+static void nfp_tun_write_ipv4_list(struct nfp_app *app)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ struct nfp_ipv4_addr_entry *entry;
+ struct nfp_tun_ipv4_addr payload;
+ struct list_head *ptr, *storage;
+ int count;
+
+ memset(&payload, 0, sizeof(struct nfp_tun_ipv4_addr));
+ mutex_lock(&priv->nfp_ipv4_off_lock);
+ count = 0;
+ list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) {
+ if (count >= NFP_FL_IPV4_ADDRS_MAX) {
+ mutex_unlock(&priv->nfp_ipv4_off_lock);
+ nfp_flower_cmsg_warn(app, "IPv4 offload exceeds limit.\n");
+ return;
+ }
+ entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list);
+ payload.ipv4_addr[count++] = entry->ipv4_addr;
+ }
+ payload.count = cpu_to_be32(count);
+ mutex_unlock(&priv->nfp_ipv4_off_lock);
+
+ nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_TUN_IPS,
+ sizeof(struct nfp_tun_ipv4_addr),
+ &payload);
+}
+
+void nfp_tunnel_add_ipv4_off(struct nfp_app *app, __be32 ipv4)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ struct nfp_ipv4_addr_entry *entry;
+ struct list_head *ptr, *storage;
+
+ mutex_lock(&priv->nfp_ipv4_off_lock);
+ list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) {
+ entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list);
+ if (entry->ipv4_addr == ipv4) {
+ entry->ref_count++;
+ mutex_unlock(&priv->nfp_ipv4_off_lock);
+ return;
+ }
+ }
+
+ entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry) {
+ mutex_unlock(&priv->nfp_ipv4_off_lock);
+ nfp_flower_cmsg_warn(app, "Mem error when offloading IP address.\n");
+ return;
+ }
+ entry->ipv4_addr = ipv4;
+ entry->ref_count = 1;
+ list_add_tail(&entry->list, &priv->nfp_ipv4_off_list);
+ mutex_unlock(&priv->nfp_ipv4_off_lock);
+
+ nfp_tun_write_ipv4_list(app);
+}
+
+void nfp_tunnel_del_ipv4_off(struct nfp_app *app, __be32 ipv4)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ struct nfp_ipv4_addr_entry *entry;
+ struct list_head *ptr, *storage;
+
+ mutex_lock(&priv->nfp_ipv4_off_lock);
+ list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) {
+ entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list);
+ if (entry->ipv4_addr == ipv4) {
+ entry->ref_count--;
+ if (!entry->ref_count) {
+ list_del(&entry->list);
+ kfree(entry);
+ }
+ break;
+ }
+ }
+ mutex_unlock(&priv->nfp_ipv4_off_lock);
+
+ nfp_tun_write_ipv4_list(app);
+}
+
+void nfp_tunnel_write_macs(struct nfp_app *app)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ struct nfp_tun_mac_offload_entry *entry;
+ struct nfp_tun_mac_addr *payload;
+ struct list_head *ptr, *storage;
+ int mac_count, err, pay_size;
+
+ mutex_lock(&priv->nfp_mac_off_lock);
+ if (!priv->nfp_mac_off_count) {
+ mutex_unlock(&priv->nfp_mac_off_lock);
+ return;
+ }
+
+ pay_size = sizeof(struct nfp_tun_mac_addr) +
+ sizeof(struct index_mac_addr) * priv->nfp_mac_off_count;
+
+ payload = kzalloc(pay_size, GFP_KERNEL);
+ if (!payload) {
+ mutex_unlock(&priv->nfp_mac_off_lock);
+ return;
+ }
+
+ payload->count = cpu_to_be16(priv->nfp_mac_off_count);
+
+ mac_count = 0;
+ list_for_each_safe(ptr, storage, &priv->nfp_mac_off_list) {
+ entry = list_entry(ptr, struct nfp_tun_mac_offload_entry,
+ list);
+ payload->addresses[mac_count].index = entry->index;
+ ether_addr_copy(payload->addresses[mac_count].addr,
+ entry->addr);
+ mac_count++;
+ }
+
+ err = nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_TUN_MAC,
+ pay_size, payload);
+
+ kfree(payload);
+
+ if (err) {
+ mutex_unlock(&priv->nfp_mac_off_lock);
+ /* Write failed so retain list for future retry. */
+ return;
+ }
+
+ /* If list was successfully offloaded, flush it. */
+ list_for_each_safe(ptr, storage, &priv->nfp_mac_off_list) {
+ entry = list_entry(ptr, struct nfp_tun_mac_offload_entry,
+ list);
+ list_del(&entry->list);
+ kfree(entry);
+ }
+
+ priv->nfp_mac_off_count = 0;
+ mutex_unlock(&priv->nfp_mac_off_lock);
+}
+
+static int nfp_tun_get_mac_idx(struct nfp_app *app, int ifindex)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ struct nfp_tun_mac_non_nfp_idx *entry;
+ struct list_head *ptr, *storage;
+ int idx;
+
+ mutex_lock(&priv->nfp_mac_index_lock);
+ list_for_each_safe(ptr, storage, &priv->nfp_mac_index_list) {
+ entry = list_entry(ptr, struct nfp_tun_mac_non_nfp_idx, list);
+ if (entry->ifindex == ifindex) {
+ idx = entry->index;
+ mutex_unlock(&priv->nfp_mac_index_lock);
+ return idx;
+ }
+ }
+
+ idx = ida_simple_get(&priv->nfp_mac_off_ids, 0,
+ NFP_MAX_MAC_INDEX, GFP_KERNEL);
+ if (idx < 0) {
+ mutex_unlock(&priv->nfp_mac_index_lock);
+ return idx;
+ }
+
+ entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry) {
+ mutex_unlock(&priv->nfp_mac_index_lock);
+ return -ENOMEM;
+ }
+ entry->ifindex = ifindex;
+ entry->index = idx;
+ list_add_tail(&entry->list, &priv->nfp_mac_index_list);
+ mutex_unlock(&priv->nfp_mac_index_lock);
+
+ return idx;
+}
+
+static void nfp_tun_del_mac_idx(struct nfp_app *app, int ifindex)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ struct nfp_tun_mac_non_nfp_idx *entry;
+ struct list_head *ptr, *storage;
+
+ mutex_lock(&priv->nfp_mac_index_lock);
+ list_for_each_safe(ptr, storage, &priv->nfp_mac_index_list) {
+ entry = list_entry(ptr, struct nfp_tun_mac_non_nfp_idx, list);
+ if (entry->ifindex == ifindex) {
+ ida_simple_remove(&priv->nfp_mac_off_ids,
+ entry->index);
+ list_del(&entry->list);
+ kfree(entry);
+ break;
+ }
+ }
+ mutex_unlock(&priv->nfp_mac_index_lock);
+}
+
+static void nfp_tun_add_to_mac_offload_list(struct net_device *netdev,
+ struct nfp_app *app)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ struct nfp_tun_mac_offload_entry *entry;
+ u16 nfp_mac_idx;
+ int port = 0;
+
+ /* Check if MAC should be offloaded. */
+ if (!is_valid_ether_addr(netdev->dev_addr))
+ return;
+
+ if (nfp_netdev_is_nfp_repr(netdev))
+ port = nfp_repr_get_port_id(netdev);
+ else if (!nfp_tun_is_netdev_to_offload(netdev))
+ return;
+
+ entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry) {
+ nfp_flower_cmsg_warn(app, "Mem fail when offloading MAC.\n");
+ return;
+ }
+
+ if (FIELD_GET(NFP_FLOWER_CMSG_PORT_TYPE, port) ==
+ NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT) {
+ nfp_mac_idx = port << 8 | NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT;
+ } else if (FIELD_GET(NFP_FLOWER_CMSG_PORT_TYPE, port) ==
+ NFP_FLOWER_CMSG_PORT_TYPE_PCIE_PORT) {
+ port = FIELD_GET(NFP_FLOWER_CMSG_PORT_VNIC, port);
+ nfp_mac_idx = port << 8 | NFP_FLOWER_CMSG_PORT_TYPE_PCIE_PORT;
+ } else {
+ /* Must assign our own unique 8-bit index. */
+ int idx = nfp_tun_get_mac_idx(app, netdev->ifindex);
+
+ if (idx < 0) {
+ nfp_flower_cmsg_warn(app, "Can't assign non-repr MAC index.\n");
+ kfree(entry);
+ return;
+ }
+ nfp_mac_idx = idx << 8 | NFP_FLOWER_CMSG_PORT_TYPE_OTHER_PORT;
+ }
+
+ entry->index = cpu_to_be16(nfp_mac_idx);
+ ether_addr_copy(entry->addr, netdev->dev_addr);
+
+ mutex_lock(&priv->nfp_mac_off_lock);
+ priv->nfp_mac_off_count++;
+ list_add_tail(&entry->list, &priv->nfp_mac_off_list);
+ mutex_unlock(&priv->nfp_mac_off_lock);
+}
+
+static int nfp_tun_mac_event_handler(struct notifier_block *nb,
+ unsigned long event, void *ptr)
+{
+ struct nfp_flower_priv *app_priv;
+ struct net_device *netdev;
+ struct nfp_app *app;
+
+ if (event == NETDEV_DOWN || event == NETDEV_UNREGISTER) {
+ app_priv = container_of(nb, struct nfp_flower_priv,
+ nfp_tun_mac_nb);
+ app = app_priv->app;
+ netdev = netdev_notifier_info_to_dev(ptr);
+
+ /* If non-nfp netdev then free its offload index. */
+ if (nfp_tun_is_netdev_to_offload(netdev))
+ nfp_tun_del_mac_idx(app, netdev->ifindex);
+ } else if (event == NETDEV_UP || event == NETDEV_CHANGEADDR ||
+ event == NETDEV_REGISTER) {
+ app_priv = container_of(nb, struct nfp_flower_priv,
+ nfp_tun_mac_nb);
+ app = app_priv->app;
+ netdev = netdev_notifier_info_to_dev(ptr);
+
+ nfp_tun_add_to_mac_offload_list(netdev, app);
+
+ /* Force a list write to keep NFP up to date. */
+ nfp_tunnel_write_macs(app);
+ }
+ return NOTIFY_OK;
+}
+
+int nfp_tunnel_config_start(struct nfp_app *app)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ struct net_device *netdev;
+ int err;
+
+ /* Initialise priv data for MAC offloading. */
+ priv->nfp_mac_off_count = 0;
+ mutex_init(&priv->nfp_mac_off_lock);
+ INIT_LIST_HEAD(&priv->nfp_mac_off_list);
+ priv->nfp_tun_mac_nb.notifier_call = nfp_tun_mac_event_handler;
+ mutex_init(&priv->nfp_mac_index_lock);
+ INIT_LIST_HEAD(&priv->nfp_mac_index_list);
+ ida_init(&priv->nfp_mac_off_ids);
+
+ /* Initialise priv data for IPv4 offloading. */
+ mutex_init(&priv->nfp_ipv4_off_lock);
+ INIT_LIST_HEAD(&priv->nfp_ipv4_off_list);
+
+ /* Initialise priv data for neighbour offloading. */
+ mutex_init(&priv->nfp_neigh_off_lock);
+ INIT_LIST_HEAD(&priv->nfp_neigh_off_list);
+ priv->nfp_tun_neigh_nb.notifier_call = nfp_tun_neigh_event_handler;
+
+ err = register_netdevice_notifier(&priv->nfp_tun_mac_nb);
+ if (err)
+ goto err_free_mac_ida;
+
+ err = register_netevent_notifier(&priv->nfp_tun_neigh_nb);
+ if (err)
+ goto err_unreg_mac_nb;
+
+ /* Parse netdevs already registered for MACs that need offloaded. */
+ rtnl_lock();
+ for_each_netdev(&init_net, netdev)
+ nfp_tun_add_to_mac_offload_list(netdev, app);
+ rtnl_unlock();
+
+ return 0;
+
+err_unreg_mac_nb:
+ unregister_netdevice_notifier(&priv->nfp_tun_mac_nb);
+err_free_mac_ida:
+ ida_destroy(&priv->nfp_mac_off_ids);
+ return err;
+}
+
+void nfp_tunnel_config_stop(struct nfp_app *app)
+{
+ struct nfp_tun_mac_offload_entry *mac_entry;
+ struct nfp_flower_priv *priv = app->priv;
+ struct nfp_ipv4_route_entry *route_entry;
+ struct nfp_tun_mac_non_nfp_idx *mac_idx;
+ struct nfp_ipv4_addr_entry *ip_entry;
+ struct list_head *ptr, *storage;
+
+ unregister_netdevice_notifier(&priv->nfp_tun_mac_nb);
+ unregister_netevent_notifier(&priv->nfp_tun_neigh_nb);
+
+ /* Free any memory that may be occupied by MAC list. */
+ mutex_lock(&priv->nfp_mac_off_lock);
+ list_for_each_safe(ptr, storage, &priv->nfp_mac_off_list) {
+ mac_entry = list_entry(ptr, struct nfp_tun_mac_offload_entry,
+ list);
+ list_del(&mac_entry->list);
+ kfree(mac_entry);
+ }
+ mutex_unlock(&priv->nfp_mac_off_lock);
+
+ /* Free any memory that may be occupied by MAC index list. */
+ mutex_lock(&priv->nfp_mac_index_lock);
+ list_for_each_safe(ptr, storage, &priv->nfp_mac_index_list) {
+ mac_idx = list_entry(ptr, struct nfp_tun_mac_non_nfp_idx,
+ list);
+ list_del(&mac_idx->list);
+ kfree(mac_idx);
+ }
+ mutex_unlock(&priv->nfp_mac_index_lock);
+
+ ida_destroy(&priv->nfp_mac_off_ids);
+
+ /* Free any memory that may be occupied by ipv4 list. */
+ mutex_lock(&priv->nfp_ipv4_off_lock);
+ list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) {
+ ip_entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list);
+ list_del(&ip_entry->list);
+ kfree(ip_entry);
+ }
+ mutex_unlock(&priv->nfp_ipv4_off_lock);
+
+ /* Free any memory that may be occupied by the route list. */
+ mutex_lock(&priv->nfp_neigh_off_lock);
+ list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) {
+ route_entry = list_entry(ptr, struct nfp_ipv4_route_entry,
+ list);
+ list_del(&route_entry->list);
+ kfree(route_entry);
+ }
+ mutex_unlock(&priv->nfp_neigh_off_lock);
+}
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 1c0187f0af51..d2f73feb8497 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1574,26 +1574,6 @@ nfp_net_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring,
return true;
}
-static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, void *hard_start,
- unsigned int *off, unsigned int *len)
-{
- struct xdp_buff xdp;
- void *orig_data;
- int ret;
-
- xdp.data_hard_start = hard_start;
- xdp.data = data + *off;
- xdp.data_end = data + *off + *len;
-
- orig_data = xdp.data;
- ret = bpf_prog_run_xdp(prog, &xdp);
-
- *len -= xdp.data - orig_data;
- *off += xdp.data - orig_data;
-
- return ret;
-}
-
/**
* nfp_net_rx() - receive up to @budget packets on @rx_ring
* @rx_ring: RX ring to receive from
@@ -1629,6 +1609,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
struct nfp_meta_parsed meta;
struct net_device *netdev;
dma_addr_t new_dma_addr;
+ u32 meta_len_xdp = 0;
void *new_frag;
idx = D_IDX(rx_ring, rx_ring->rd_p);
@@ -1707,16 +1688,24 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF &&
dp->bpf_offload_xdp) && !meta.portid) {
+ void *orig_data = rxbuf->frag + pkt_off;
unsigned int dma_off;
- void *hard_start;
+ struct xdp_buff xdp;
int act;
- hard_start = rxbuf->frag + NFP_NET_RX_BUF_HEADROOM;
+ xdp.data_hard_start = rxbuf->frag + NFP_NET_RX_BUF_HEADROOM;
+ xdp.data = orig_data;
+ xdp.data_meta = orig_data;
+ xdp.data_end = orig_data + pkt_len;
+
+ act = bpf_prog_run_xdp(xdp_prog, &xdp);
+
+ pkt_len -= xdp.data - orig_data;
+ pkt_off += xdp.data - orig_data;
- act = nfp_net_run_xdp(xdp_prog, rxbuf->frag, hard_start,
- &pkt_off, &pkt_len);
switch (act) {
case XDP_PASS:
+ meta_len_xdp = xdp.data - xdp.data_meta;
break;
case XDP_TX:
dma_off = pkt_off - NFP_NET_RX_BUF_HEADROOM;
@@ -1784,6 +1773,8 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
if (rxd->rxd.flags & PCIE_DESC_RX_VLAN)
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
le16_to_cpu(rxd->rxd.vlan));
+ if (meta_len_xdp)
+ skb_metadata_set(skb, meta_len_xdp);
napi_gro_receive(&rx_ring->r_vec->napi, skb);
}
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index 994a83a1f0a5..a235e8881af9 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -1813,12 +1813,12 @@ static int nv_alloc_rx(struct net_device *dev)
struct sk_buff *skb = netdev_alloc_skb(dev, np->rx_buf_sz + NV_RX_ALLOC_PAD);
if (skb) {
np->put_rx_ctx->skb = skb;
- np->put_rx_ctx->dma = pci_map_single(np->pci_dev,
+ np->put_rx_ctx->dma = dma_map_single(&np->pci_dev->dev,
skb->data,
skb_tailroom(skb),
- PCI_DMA_FROMDEVICE);
- if (pci_dma_mapping_error(np->pci_dev,
- np->put_rx_ctx->dma)) {
+ DMA_FROM_DEVICE);
+ if (unlikely(dma_mapping_error(&np->pci_dev->dev,
+ np->put_rx_ctx->dma))) {
kfree_skb(skb);
goto packet_dropped;
}
@@ -1854,12 +1854,12 @@ static int nv_alloc_rx_optimized(struct net_device *dev)
struct sk_buff *skb = netdev_alloc_skb(dev, np->rx_buf_sz + NV_RX_ALLOC_PAD);
if (skb) {
np->put_rx_ctx->skb = skb;
- np->put_rx_ctx->dma = pci_map_single(np->pci_dev,
+ np->put_rx_ctx->dma = dma_map_single(&np->pci_dev->dev,
skb->data,
skb_tailroom(skb),
- PCI_DMA_FROMDEVICE);
- if (pci_dma_mapping_error(np->pci_dev,
- np->put_rx_ctx->dma)) {
+ DMA_FROM_DEVICE);
+ if (unlikely(dma_mapping_error(&np->pci_dev->dev,
+ np->put_rx_ctx->dma))) {
kfree_skb(skb);
goto packet_dropped;
}
@@ -1977,9 +1977,9 @@ static void nv_unmap_txskb(struct fe_priv *np, struct nv_skb_map *tx_skb)
{
if (tx_skb->dma) {
if (tx_skb->dma_single)
- pci_unmap_single(np->pci_dev, tx_skb->dma,
+ dma_unmap_single(&np->pci_dev->dev, tx_skb->dma,
tx_skb->dma_len,
- PCI_DMA_TODEVICE);
+ DMA_TO_DEVICE);
else
pci_unmap_page(np->pci_dev, tx_skb->dma,
tx_skb->dma_len,
@@ -2047,10 +2047,10 @@ static void nv_drain_rx(struct net_device *dev)
}
wmb();
if (np->rx_skb[i].skb) {
- pci_unmap_single(np->pci_dev, np->rx_skb[i].dma,
+ dma_unmap_single(&np->pci_dev->dev, np->rx_skb[i].dma,
(skb_end_pointer(np->rx_skb[i].skb) -
- np->rx_skb[i].skb->data),
- PCI_DMA_FROMDEVICE);
+ np->rx_skb[i].skb->data),
+ DMA_FROM_DEVICE);
dev_kfree_skb(np->rx_skb[i].skb);
np->rx_skb[i].skb = NULL;
}
@@ -2224,10 +2224,11 @@ static netdev_tx_t nv_start_xmit(struct sk_buff *skb, struct net_device *dev)
prev_tx = put_tx;
prev_tx_ctx = np->put_tx_ctx;
bcnt = (size > NV_TX2_TSO_MAX_SIZE) ? NV_TX2_TSO_MAX_SIZE : size;
- np->put_tx_ctx->dma = pci_map_single(np->pci_dev, skb->data + offset, bcnt,
- PCI_DMA_TODEVICE);
- if (pci_dma_mapping_error(np->pci_dev,
- np->put_tx_ctx->dma)) {
+ np->put_tx_ctx->dma = dma_map_single(&np->pci_dev->dev,
+ skb->data + offset, bcnt,
+ DMA_TO_DEVICE);
+ if (unlikely(dma_mapping_error(&np->pci_dev->dev,
+ np->put_tx_ctx->dma))) {
/* on DMA mapping error - drop the packet */
dev_kfree_skb_any(skb);
u64_stats_update_begin(&np->swstats_tx_syncp);
@@ -2267,7 +2268,8 @@ static netdev_tx_t nv_start_xmit(struct sk_buff *skb, struct net_device *dev)
frag, offset,
bcnt,
DMA_TO_DEVICE);
- if (dma_mapping_error(&np->pci_dev->dev, np->put_tx_ctx->dma)) {
+ if (unlikely(dma_mapping_error(&np->pci_dev->dev,
+ np->put_tx_ctx->dma))) {
/* Unwind the mapped fragments */
do {
@@ -2373,10 +2375,11 @@ static netdev_tx_t nv_start_xmit_optimized(struct sk_buff *skb,
prev_tx = put_tx;
prev_tx_ctx = np->put_tx_ctx;
bcnt = (size > NV_TX2_TSO_MAX_SIZE) ? NV_TX2_TSO_MAX_SIZE : size;
- np->put_tx_ctx->dma = pci_map_single(np->pci_dev, skb->data + offset, bcnt,
- PCI_DMA_TODEVICE);
- if (pci_dma_mapping_error(np->pci_dev,
- np->put_tx_ctx->dma)) {
+ np->put_tx_ctx->dma = dma_map_single(&np->pci_dev->dev,
+ skb->data + offset, bcnt,
+ DMA_TO_DEVICE);
+ if (unlikely(dma_mapping_error(&np->pci_dev->dev,
+ np->put_tx_ctx->dma))) {
/* on DMA mapping error - drop the packet */
dev_kfree_skb_any(skb);
u64_stats_update_begin(&np->swstats_tx_syncp);
@@ -2417,7 +2420,8 @@ static netdev_tx_t nv_start_xmit_optimized(struct sk_buff *skb,
bcnt,
DMA_TO_DEVICE);
- if (dma_mapping_error(&np->pci_dev->dev, np->put_tx_ctx->dma)) {
+ if (unlikely(dma_mapping_error(&np->pci_dev->dev,
+ np->put_tx_ctx->dma))) {
/* Unwind the mapped fragments */
do {
@@ -2810,9 +2814,9 @@ static int nv_rx_process(struct net_device *dev, int limit)
* TODO: check if a prefetch of the first cacheline improves
* the performance.
*/
- pci_unmap_single(np->pci_dev, np->get_rx_ctx->dma,
- np->get_rx_ctx->dma_len,
- PCI_DMA_FROMDEVICE);
+ dma_unmap_single(&np->pci_dev->dev, np->get_rx_ctx->dma,
+ np->get_rx_ctx->dma_len,
+ DMA_FROM_DEVICE);
skb = np->get_rx_ctx->skb;
np->get_rx_ctx->skb = NULL;
@@ -2916,9 +2920,9 @@ static int nv_rx_process_optimized(struct net_device *dev, int limit)
* TODO: check if a prefetch of the first cacheline improves
* the performance.
*/
- pci_unmap_single(np->pci_dev, np->get_rx_ctx->dma,
- np->get_rx_ctx->dma_len,
- PCI_DMA_FROMDEVICE);
+ dma_unmap_single(&np->pci_dev->dev, np->get_rx_ctx->dma,
+ np->get_rx_ctx->dma_len,
+ DMA_FROM_DEVICE);
skb = np->get_rx_ctx->skb;
np->get_rx_ctx->skb = NULL;
@@ -5070,11 +5074,11 @@ static int nv_loopback_test(struct net_device *dev)
ret = 0;
goto out;
}
- test_dma_addr = pci_map_single(np->pci_dev, tx_skb->data,
+ test_dma_addr = dma_map_single(&np->pci_dev->dev, tx_skb->data,
skb_tailroom(tx_skb),
- PCI_DMA_FROMDEVICE);
- if (pci_dma_mapping_error(np->pci_dev,
- test_dma_addr)) {
+ DMA_FROM_DEVICE);
+ if (unlikely(dma_mapping_error(&np->pci_dev->dev,
+ test_dma_addr))) {
dev_kfree_skb_any(tx_skb);
goto out;
}
@@ -5129,9 +5133,9 @@ static int nv_loopback_test(struct net_device *dev)
}
}
- pci_unmap_single(np->pci_dev, test_dma_addr,
- (skb_end_pointer(tx_skb) - tx_skb->data),
- PCI_DMA_TODEVICE);
+ dma_unmap_single(&np->pci_dev->dev, test_dma_addr,
+ (skb_end_pointer(tx_skb) - tx_skb->data),
+ DMA_TO_DEVICE);
dev_kfree_skb_any(tx_skb);
out:
/* stop engines */
diff --git a/drivers/net/ethernet/packetengines/hamachi.c b/drivers/net/ethernet/packetengines/hamachi.c
index 482b85e4d665..77bc7cca8980 100644
--- a/drivers/net/ethernet/packetengines/hamachi.c
+++ b/drivers/net/ethernet/packetengines/hamachi.c
@@ -979,10 +979,8 @@ static int hamachi_open(struct net_device *dev)
dev->name, readw(ioaddr + RxStatus), readw(ioaddr + TxStatus));
}
/* Set the timer to check for link beat. */
- init_timer(&hmp->timer);
+ setup_timer(&hmp->timer, hamachi_timer, (unsigned long)dev);
hmp->timer.expires = RUN_AT((24*HZ)/10); /* 2.4 sec. */
- hmp->timer.data = (unsigned long)dev;
- hmp->timer.function = hamachi_timer; /* timer handler */
add_timer(&hmp->timer);
return 0;
diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c
index fa7770da6ef8..33c241f52a71 100644
--- a/drivers/net/ethernet/packetengines/yellowfin.c
+++ b/drivers/net/ethernet/packetengines/yellowfin.c
@@ -632,10 +632,8 @@ static int yellowfin_open(struct net_device *dev)
}
/* Set the timer to check for link beat. */
- init_timer(&yp->timer);
+ setup_timer(&yp->timer, yellowfin_timer, (unsigned long)dev);
yp->timer.expires = jiffies + 3*HZ;
- yp->timer.data = (unsigned long)dev;
- yp->timer.function = yellowfin_timer; /* timer handler */
add_timer(&yp->timer);
out:
return rc;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index af106be8cc08..afd07ad91631 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -2069,6 +2069,12 @@ static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
num_srqs = min_t(u32, 32 * 1024, p_params->num_srqs);
+ if (p_hwfn->mcp_info->func_info.protocol == QED_PCI_ETH_RDMA) {
+ DP_NOTICE(p_hwfn,
+ "Current day drivers don't support RoCE & iWARP simultaneously on the same PF. Default to RoCE-only\n");
+ p_hwfn->hw_info.personality = QED_PCI_ETH_ROCE;
+ }
+
switch (p_hwfn->hw_info.personality) {
case QED_PCI_ETH_IWARP:
/* Each QP requires one connection */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index 9d989c96278c..8fc9c811f6e3 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -41,6 +41,7 @@
#include "qed_rdma.h"
#include "qed_reg_addr.h"
#include "qed_sp.h"
+#include "qed_ooo.h"
#define QED_IWARP_ORD_DEFAULT 32
#define QED_IWARP_IRD_DEFAULT 32
@@ -119,6 +120,13 @@ static void qed_iwarp_cid_cleaned(struct qed_hwfn *p_hwfn, u32 cid)
spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
}
+void qed_iwarp_init_fw_ramrod(struct qed_hwfn *p_hwfn,
+ struct iwarp_init_func_params *p_ramrod)
+{
+ p_ramrod->ll2_ooo_q_index = RESC_START(p_hwfn, QED_LL2_QUEUE) +
+ p_hwfn->p_rdma_info->iwarp.ll2_ooo_handle;
+}
+
static int qed_iwarp_alloc_cid(struct qed_hwfn *p_hwfn, u32 *cid)
{
int rc;
@@ -1725,6 +1733,14 @@ qed_iwarp_ll2_comp_syn_pkt(void *cxt, struct qed_ll2_comp_rx_data *data)
memset(&cm_info, 0, sizeof(cm_info));
ll2_syn_handle = p_hwfn->p_rdma_info->iwarp.ll2_syn_handle;
+
+ /* Check if packet was received with errors... */
+ if (data->err_flags) {
+ DP_NOTICE(p_hwfn, "Error received on SYN packet: 0x%x\n",
+ data->err_flags);
+ goto err;
+ }
+
if (GET_FIELD(data->parse_flags,
PARSING_AND_ERR_FLAGS_L4CHKSMWASCALCULATED) &&
GET_FIELD(data->parse_flags, PARSING_AND_ERR_FLAGS_L4CHKSMERROR)) {
@@ -1876,6 +1892,16 @@ static int qed_iwarp_ll2_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
iwarp_info->ll2_syn_handle = QED_IWARP_HANDLE_INVAL;
}
+ if (iwarp_info->ll2_ooo_handle != QED_IWARP_HANDLE_INVAL) {
+ rc = qed_ll2_terminate_connection(p_hwfn,
+ iwarp_info->ll2_ooo_handle);
+ if (rc)
+ DP_INFO(p_hwfn, "Failed to terminate ooo connection\n");
+
+ qed_ll2_release_connection(p_hwfn, iwarp_info->ll2_ooo_handle);
+ iwarp_info->ll2_ooo_handle = QED_IWARP_HANDLE_INVAL;
+ }
+
qed_llh_remove_mac_filter(p_hwfn,
p_ptt, p_hwfn->p_rdma_info->iwarp.mac_addr);
return rc;
@@ -1927,10 +1953,12 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
struct qed_iwarp_info *iwarp_info;
struct qed_ll2_acquire_data data;
struct qed_ll2_cbs cbs;
+ u16 n_ooo_bufs;
int rc = 0;
iwarp_info = &p_hwfn->p_rdma_info->iwarp;
iwarp_info->ll2_syn_handle = QED_IWARP_HANDLE_INVAL;
+ iwarp_info->ll2_ooo_handle = QED_IWARP_HANDLE_INVAL;
iwarp_info->max_mtu = params->max_mtu;
@@ -1978,6 +2006,29 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
if (rc)
goto err;
+ /* Start OOO connection */
+ data.input.conn_type = QED_LL2_TYPE_OOO;
+ data.input.mtu = params->max_mtu;
+
+ n_ooo_bufs = (QED_IWARP_MAX_OOO * QED_IWARP_RCV_WND_SIZE_DEF) /
+ iwarp_info->max_mtu;
+ n_ooo_bufs = min_t(u32, n_ooo_bufs, QED_IWARP_LL2_OOO_MAX_RX_SIZE);
+
+ data.input.rx_num_desc = n_ooo_bufs;
+ data.input.rx_num_ooo_buffers = n_ooo_bufs;
+
+ data.input.tx_max_bds_per_packet = 1; /* will never be fragmented */
+ data.input.tx_num_desc = QED_IWARP_LL2_OOO_DEF_TX_SIZE;
+ data.p_connection_handle = &iwarp_info->ll2_ooo_handle;
+
+ rc = qed_ll2_acquire_connection(p_hwfn, &data);
+ if (rc)
+ goto err;
+
+ rc = qed_ll2_establish_connection(p_hwfn, iwarp_info->ll2_ooo_handle);
+ if (rc)
+ goto err;
+
return rc;
err:
qed_iwarp_ll2_stop(p_hwfn, p_ptt);
@@ -2014,6 +2065,7 @@ int qed_iwarp_setup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
qed_spq_register_async_cb(p_hwfn, PROTOCOLID_IWARP,
qed_iwarp_async_event);
+ qed_ooo_setup(p_hwfn);
return qed_iwarp_ll2_start(p_hwfn, params, p_ptt);
}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
index 148ef3c33a5d..9e2bfde894df 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
@@ -47,7 +47,12 @@ enum qed_iwarp_qp_state qed_roce2iwarp_state(enum qed_roce_qp_state state);
#define QED_IWARP_LL2_SYN_TX_SIZE (128)
#define QED_IWARP_LL2_SYN_RX_SIZE (256)
#define QED_IWARP_MAX_SYN_PKT_SIZE (128)
-#define QED_IWARP_HANDLE_INVAL (0xff)
+
+#define QED_IWARP_LL2_OOO_DEF_TX_SIZE (256)
+#define QED_IWARP_MAX_OOO (16)
+#define QED_IWARP_LL2_OOO_MAX_RX_SIZE (16384)
+
+#define QED_IWARP_HANDLE_INVAL (0xff)
struct qed_iwarp_ll2_buff {
void *data;
@@ -67,6 +72,7 @@ struct qed_iwarp_info {
u8 crc_needed;
u8 tcp_flags;
u8 ll2_syn_handle;
+ u8 ll2_ooo_handle;
u8 peer2peer;
enum mpa_negotiation_mode mpa_rev;
enum mpa_rtr_type rtr_type;
@@ -147,6 +153,9 @@ int qed_iwarp_alloc(struct qed_hwfn *p_hwfn);
int qed_iwarp_setup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
struct qed_rdma_start_in_params *params);
+void qed_iwarp_init_fw_ramrod(struct qed_hwfn *p_hwfn,
+ struct iwarp_init_func_params *p_ramrod);
+
int qed_iwarp_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
void qed_iwarp_resc_free(struct qed_hwfn *p_hwfn);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index c06ad4f0758e..250afa5486cf 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -413,6 +413,7 @@ static void qed_ll2_rxq_parse_reg(struct qed_hwfn *p_hwfn,
struct qed_ll2_comp_rx_data *data)
{
data->parse_flags = le16_to_cpu(p_cqe->rx_cqe_fp.parse_flags.flags);
+ data->err_flags = le16_to_cpu(p_cqe->rx_cqe_fp.err_flags.flags);
data->length.packet_length =
le16_to_cpu(p_cqe->rx_cqe_fp.packet_length);
data->vlan = le16_to_cpu(p_cqe->rx_cqe_fp.vlan);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 376485d99357..8b99c7d26f34 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -1691,12 +1691,12 @@ qed_mcp_get_shmem_proto_mfw(struct qed_hwfn *p_hwfn,
case FW_MB_PARAM_GET_PF_RDMA_ROCE:
*p_proto = QED_PCI_ETH_ROCE;
break;
+ case FW_MB_PARAM_GET_PF_RDMA_IWARP:
+ *p_proto = QED_PCI_ETH_IWARP;
+ break;
case FW_MB_PARAM_GET_PF_RDMA_BOTH:
- DP_NOTICE(p_hwfn,
- "Current day drivers don't support RoCE & iWARP. Default to RoCE-only\n");
- *p_proto = QED_PCI_ETH_ROCE;
+ *p_proto = QED_PCI_ETH_RDMA;
break;
- case FW_MB_PARAM_GET_PF_RDMA_IWARP:
default:
DP_NOTICE(p_hwfn,
"MFW answers GET_PF_RDMA_PROTOCOL but param is %08x\n",
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index 6fb99518a61f..c8c4b3940564 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -156,7 +156,10 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
return rc;
p_hwfn->p_rdma_info = p_rdma_info;
- p_rdma_info->proto = PROTOCOLID_ROCE;
+ if (QED_IS_IWARP_PERSONALITY(p_hwfn))
+ p_rdma_info->proto = PROTOCOLID_IWARP;
+ else
+ p_rdma_info->proto = PROTOCOLID_ROCE;
num_cons = qed_cxt_get_proto_cid_count(p_hwfn, p_rdma_info->proto,
NULL);
@@ -206,11 +209,11 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
goto free_pd_map;
}
- /* Allocate bitmap for cq's. The maximum number of CQs is bounded to
- * twice the number of QPs.
+ /* Allocate bitmap for cq's. The maximum number of CQs is bound to
+ * the number of connections we support. (num_qps in iWARP or
+ * num_qps/2 in RoCE).
*/
- rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->cq_map,
- p_rdma_info->num_qps * 2, "CQ");
+ rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->cq_map, num_cons, "CQ");
if (rc) {
DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
"Failed to allocate cq bitmap, rc = %d\n", rc);
@@ -219,10 +222,10 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
/* Allocate bitmap for toggle bit for cq icids
* We toggle the bit every time we create or resize cq for a given icid.
- * The maximum number of CQs is bounded to twice the number of QPs.
+ * Size needs to equal the size of the cq bmap.
*/
rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->toggle_bits,
- p_rdma_info->num_qps * 2, "Toggle");
+ num_cons, "Toggle");
if (rc) {
DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
"Failed to allocate toogle bits, rc = %d\n", rc);
@@ -548,10 +551,13 @@ static int qed_rdma_start_fw(struct qed_hwfn *p_hwfn,
if (rc)
return rc;
- if (QED_IS_IWARP_PERSONALITY(p_hwfn))
+ if (QED_IS_IWARP_PERSONALITY(p_hwfn)) {
+ qed_iwarp_init_fw_ramrod(p_hwfn,
+ &p_ent->ramrod.iwarp_init_func.iwarp);
p_ramrod = &p_ent->ramrod.iwarp_init_func.rdma;
- else
+ } else {
p_ramrod = &p_ent->ramrod.roce_init_func.rdma;
+ }
p_params_header = &p_ramrod->params_header;
p_params_header->cnq_start_offset = (u8)RESC_START(p_hwfn,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
index 46d0c3cb83a5..a1d33f35aad3 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
@@ -377,6 +377,7 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn,
p_ramrod->personality = PERSONALITY_ISCSI;
break;
case QED_PCI_ETH_ROCE:
+ case QED_PCI_ETH_IWARP:
p_ramrod->personality = PERSONALITY_RDMA_AND_ETH;
break;
default:
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 6fc854b120b0..48ec4c56cddf 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -1004,6 +1004,7 @@ static bool qede_rx_xdp(struct qede_dev *edev,
xdp.data_hard_start = page_address(bd->data);
xdp.data = xdp.data_hard_start + *data_offset;
+ xdp_set_data_meta_invalid(&xdp);
xdp.data_end = xdp.data + *len;
/* Queues always have a full reset currently, so for the time
diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index 2991179c2fd0..05479d435469 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -3891,10 +3891,8 @@ static int ql3xxx_probe(struct pci_dev *pdev,
INIT_DELAYED_WORK(&qdev->tx_timeout_work, ql_tx_timeout_work);
INIT_DELAYED_WORK(&qdev->link_state_work, ql_link_state_machine_work);
- init_timer(&qdev->adapter_timer);
- qdev->adapter_timer.function = ql3xxx_timer;
+ setup_timer(&qdev->adapter_timer, ql3xxx_timer, (unsigned long)qdev);
qdev->adapter_timer.expires = jiffies + HZ * 2; /* two second delay */
- qdev->adapter_timer.data = (unsigned long)qdev;
if (!cards_found) {
pr_alert("%s\n", DRV_STRING);
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 1e33aea59f50..8403eea08d0e 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -175,7 +175,7 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev,
if (err)
goto err1;
- err = netdev_master_upper_dev_link(dev, real_dev, NULL, NULL);
+ err = netdev_master_upper_dev_link(dev, real_dev, NULL, NULL, extack);
if (err)
goto err2;
diff --git a/drivers/net/ethernet/realtek/atp.c b/drivers/net/ethernet/realtek/atp.c
index bed34684994f..bdc3833fab7e 100644
--- a/drivers/net/ethernet/realtek/atp.c
+++ b/drivers/net/ethernet/realtek/atp.c
@@ -438,10 +438,8 @@ static int net_open(struct net_device *dev)
hardware_init(dev);
- init_timer(&lp->timer);
+ setup_timer(&lp->timer, atp_timed_checker, (unsigned long)dev);
lp->timer.expires = jiffies + TIMED_CHECKER;
- lp->timer.data = (unsigned long)dev;
- lp->timer.function = atp_timed_checker; /* timer handler */
add_timer(&lp->timer);
netif_start_queue(dev);
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index fdf30bfa403b..a8822a756e08 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -403,8 +403,9 @@ static void ravb_emac_init(struct net_device *ndev)
/* Receive frame limit set register */
ravb_write(ndev, ndev->mtu + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN, RFLR);
- /* PAUSE prohibition */
+ /* EMAC Mode: PAUSE prohibition; Duplex; RX Checksum; TX; RX */
ravb_write(ndev, ECMR_ZPF | (priv->duplex ? ECMR_DM : 0) |
+ (ndev->features & NETIF_F_RXCSUM ? ECMR_RCSC : 0) |
ECMR_TE | ECMR_RE, ECMR);
ravb_set_rate(ndev);
@@ -520,6 +521,19 @@ static void ravb_get_tx_tstamp(struct net_device *ndev)
}
}
+static void ravb_rx_csum(struct sk_buff *skb)
+{
+ u8 *hw_csum;
+
+ /* The hardware checksum is 2 bytes appended to packet data */
+ if (unlikely(skb->len < 2))
+ return;
+ hw_csum = skb_tail_pointer(skb) - 2;
+ skb->csum = csum_unfold((__force __sum16)get_unaligned_le16(hw_csum));
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ skb_trim(skb, skb->len - 2);
+}
+
/* Packet receive function for Ethernet AVB */
static bool ravb_rx(struct net_device *ndev, int *quota, int q)
{
@@ -587,8 +601,11 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q)
ts.tv_nsec = le32_to_cpu(desc->ts_n);
shhwtstamps->hwtstamp = timespec64_to_ktime(ts);
}
+
skb_put(skb, pkt_len);
skb->protocol = eth_type_trans(skb, ndev);
+ if (ndev->features & NETIF_F_RXCSUM)
+ ravb_rx_csum(skb);
napi_gro_receive(&priv->napi[q], skb);
stats->rx_packets++;
stats->rx_bytes += pkt_len;
@@ -1842,6 +1859,38 @@ static int ravb_do_ioctl(struct net_device *ndev, struct ifreq *req, int cmd)
return phy_mii_ioctl(phydev, req, cmd);
}
+static void ravb_set_rx_csum(struct net_device *ndev, bool enable)
+{
+ struct ravb_private *priv = netdev_priv(ndev);
+ unsigned long flags;
+
+ spin_lock_irqsave(&priv->lock, flags);
+
+ /* Disable TX and RX */
+ ravb_rcv_snd_disable(ndev);
+
+ /* Modify RX Checksum setting */
+ ravb_modify(ndev, ECMR, ECMR_RCSC, enable ? ECMR_RCSC : 0);
+
+ /* Enable TX and RX */
+ ravb_rcv_snd_enable(ndev);
+
+ spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static int ravb_set_features(struct net_device *ndev,
+ netdev_features_t features)
+{
+ netdev_features_t changed = ndev->features ^ features;
+
+ if (changed & NETIF_F_RXCSUM)
+ ravb_set_rx_csum(ndev, features & NETIF_F_RXCSUM);
+
+ ndev->features = features;
+
+ return 0;
+}
+
static const struct net_device_ops ravb_netdev_ops = {
.ndo_open = ravb_open,
.ndo_stop = ravb_close,
@@ -1853,6 +1902,7 @@ static const struct net_device_ops ravb_netdev_ops = {
.ndo_do_ioctl = ravb_do_ioctl,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = eth_mac_addr,
+ .ndo_set_features = ravb_set_features,
};
/* MDIO bus init function */
@@ -2004,6 +2054,9 @@ static int ravb_probe(struct platform_device *pdev)
if (!ndev)
return -ENOMEM;
+ ndev->features = NETIF_F_RXCSUM;
+ ndev->hw_features = NETIF_F_RXCSUM;
+
pm_runtime_enable(&pdev->dev);
pm_runtime_get_sync(&pdev->dev);
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index 40bd88362e3d..cb61247b0526 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -1065,10 +1065,8 @@ sis900_open(struct net_device *net_dev)
/* Set the timer to switch to check for link beat and perhaps switch
to an alternate media type. */
- init_timer(&sis_priv->timer);
+ setup_timer(&sis_priv->timer, sis900_timer, (unsigned long)net_dev);
sis_priv->timer.expires = jiffies + HZ;
- sis_priv->timer.data = (unsigned long)net_dev;
- sis_priv->timer.function = sis900_timer;
add_timer(&sis_priv->timer);
return 0;
diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c
index 6a0e1d4b597c..2a9724898fcf 100644
--- a/drivers/net/ethernet/smsc/epic100.c
+++ b/drivers/net/ethernet/smsc/epic100.c
@@ -739,10 +739,8 @@ static int epic_open(struct net_device *dev)
/* Set the timer to switch to check for link beat and perhaps switch
to an alternate media type. */
- init_timer(&ep->timer);
+ setup_timer(&ep->timer, epic_timer, (unsigned long)dev);
ep->timer.expires = jiffies + 3*HZ;
- ep->timer.data = (unsigned long)dev;
- ep->timer.function = epic_timer; /* timer handler */
add_timer(&ep->timer);
return rc;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 1763e48c84e2..f41661a04f23 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2217,10 +2217,8 @@ static void stmmac_init_tx_coalesce(struct stmmac_priv *priv)
{
priv->tx_coal_frames = STMMAC_TX_FRAMES;
priv->tx_coal_timer = STMMAC_COAL_TX_TIMER;
- init_timer(&priv->txtimer);
+ setup_timer(&priv->txtimer, stmmac_tx_timer, (unsigned long)priv);
priv->txtimer.expires = STMMAC_COAL_TIMER(priv->tx_coal_timer);
- priv->txtimer.data = (unsigned long)priv;
- priv->txtimer.function = stmmac_tx_timer;
add_timer(&priv->txtimer);
}
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 382993c1561c..a74d78f64af9 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -5039,10 +5039,7 @@ static int cas_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
spin_lock_init(&cp->stat_lock[N_TX_RINGS]);
mutex_init(&cp->pm_mutex);
- init_timer(&cp->link_timer);
- cp->link_timer.function = cas_link_timer;
- cp->link_timer.data = (unsigned long) cp;
-
+ setup_timer(&cp->link_timer, cas_link_timer, (unsigned long)cp);
#if 1
/* Just in case the implementation of atomic operations
* change so that an explicit initialization is necessary.
diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c
index 5b56c24b6ed2..5feeaa9f0a9e 100644
--- a/drivers/net/ethernet/sun/ldmvsw.c
+++ b/drivers/net/ethernet/sun/ldmvsw.c
@@ -307,7 +307,7 @@ static int vsw_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
/* Get (or create) the vnet associated with this port */
vp = vsw_get_vnet(hp, vdev->mp, &handle);
- if (unlikely(IS_ERR(vp))) {
+ if (IS_ERR(vp)) {
err = PTR_ERR(vp);
pr_err("Failed to get vnet for vsw-port\n");
mdesc_release(hp);
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 6a4e8e1bbd90..bde19b307d0d 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -6123,10 +6123,8 @@ static int niu_open(struct net_device *dev)
err = niu_init_hw(np);
if (!err) {
- init_timer(&np->timer);
+ setup_timer(&np->timer, niu_timer, (unsigned long)np);
np->timer.expires = jiffies + HZ;
- np->timer.data = (unsigned long) np;
- np->timer.function = niu_timer;
err = niu_enable_interrupts(np, 1);
if (err)
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index fa607d062cb3..b75ab8f44968 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -2910,9 +2910,7 @@ static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
gp->msg_enable = DEFAULT_MSG;
- init_timer(&gp->link_timer);
- gp->link_timer.function = gem_link_timer;
- gp->link_timer.data = (unsigned long) gp;
+ setup_timer(&gp->link_timer, gem_link_timer, (unsigned long)gp);
INIT_WORK(&gp->reset_task, gem_reset_task);
diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index ddd43e09111e..cd1185e66133 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -859,9 +859,7 @@ void cpsw_ale_start(struct cpsw_ale *ale)
cpsw_ale_control_set(ale, 0, ALE_ENABLE, 1);
cpsw_ale_control_set(ale, 0, ALE_CLEAR, 1);
- init_timer(&ale->timer);
- ale->timer.data = (unsigned long)ale;
- ale->timer.function = cpsw_ale_timer;
+ setup_timer(&ale->timer, cpsw_ale_timer, (unsigned long)ale);
if (ale->ageout) {
ale->timer.expires = jiffies + ale->ageout;
add_timer(&ale->timer);
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 28cb38af1a34..4ad821655e51 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -3616,9 +3616,8 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
}
spin_unlock_bh(&gbe_dev->hw_stats_lock);
- init_timer(&gbe_dev->timer);
- gbe_dev->timer.data = (unsigned long)gbe_dev;
- gbe_dev->timer.function = netcp_ethss_timer;
+ setup_timer(&gbe_dev->timer, netcp_ethss_timer,
+ (unsigned long)gbe_dev);
gbe_dev->timer.expires = jiffies + GBE_TIMER_INTERVAL;
add_timer(&gbe_dev->timer);
*inst_priv = gbe_dev;
diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c
index cec9e70ab995..a913538d3213 100644
--- a/drivers/net/ethernet/toshiba/spider_net.c
+++ b/drivers/net/ethernet/toshiba/spider_net.c
@@ -2256,16 +2256,14 @@ spider_net_setup_netdev(struct spider_net_card *card)
pci_set_drvdata(card->pdev, netdev);
- init_timer(&card->tx_timer);
- card->tx_timer.function =
- (void (*)(unsigned long)) spider_net_cleanup_tx_ring;
- card->tx_timer.data = (unsigned long) card;
+ setup_timer(&card->tx_timer,
+ (void(*)(unsigned long))spider_net_cleanup_tx_ring,
+ (unsigned long)card);
netdev->irq = card->pdev->irq;
card->aneg_count = 0;
- init_timer(&card->aneg_timer);
- card->aneg_timer.function = spider_net_link_phy;
- card->aneg_timer.data = (unsigned long) card;
+ setup_timer(&card->aneg_timer, spider_net_link_phy,
+ (unsigned long)card);
netif_napi_add(netdev, &card->napi,
spider_net_poll, SPIDER_NET_NAPI_WEIGHT);
diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 021a8ec411ab..97fe8dfb602d 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -623,9 +623,7 @@ static int sixpack_open(struct tty_struct *tty)
netif_start_queue(dev);
- init_timer(&sp->tx_t);
- sp->tx_t.function = sp_xmit_on_air;
- sp->tx_t.data = (unsigned long) sp;
+ setup_timer(&sp->tx_t, sp_xmit_on_air, (unsigned long)sp);
init_timer(&sp->resync_t);
diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c
index 1503f10122f7..1e62d00732f2 100644
--- a/drivers/net/hamradio/baycom_epp.c
+++ b/drivers/net/hamradio/baycom_epp.c
@@ -840,6 +840,7 @@ static int epp_open(struct net_device *dev)
unsigned char tmp[128];
unsigned char stat;
unsigned long tstart;
+ struct pardev_cb par_cb;
if (!pp) {
printk(KERN_ERR "%s: parport at 0x%lx unknown\n", bc_drvname, dev->base_addr);
@@ -859,8 +860,21 @@ static int epp_open(struct net_device *dev)
return -EIO;
}
memset(&bc->modem, 0, sizeof(bc->modem));
- bc->pdev = parport_register_device(pp, dev->name, NULL, epp_wakeup,
- NULL, PARPORT_DEV_EXCL, dev);
+ memset(&par_cb, 0, sizeof(par_cb));
+ par_cb.wakeup = epp_wakeup;
+ par_cb.private = (void *)dev;
+ par_cb.flags = PARPORT_DEV_EXCL;
+ for (i = 0; i < NR_PORTS; i++)
+ if (baycom_device[i] == dev)
+ break;
+
+ if (i == NR_PORTS) {
+ pr_err("%s: no device found\n", bc_drvname);
+ parport_put_port(pp);
+ return -ENODEV;
+ }
+
+ bc->pdev = parport_register_dev_model(pp, dev->name, &par_cb, i);
parport_put_port(pp);
if (!bc->pdev) {
printk(KERN_ERR "%s: cannot register parport at 0x%lx\n", bc_drvname, pp->base);
@@ -1185,6 +1199,23 @@ MODULE_LICENSE("GPL");
/* --------------------------------------------------------------------- */
+static int baycom_epp_par_probe(struct pardevice *par_dev)
+{
+ struct device_driver *drv = par_dev->dev.driver;
+ int len = strlen(drv->name);
+
+ if (strncmp(par_dev->name, drv->name, len))
+ return -ENODEV;
+
+ return 0;
+}
+
+static struct parport_driver baycom_epp_par_driver = {
+ .name = "bce",
+ .probe = baycom_epp_par_probe,
+ .devmodel = true,
+};
+
static void __init baycom_epp_dev_setup(struct net_device *dev)
{
struct baycom_state *bc = netdev_priv(dev);
@@ -1204,10 +1235,15 @@ static void __init baycom_epp_dev_setup(struct net_device *dev)
static int __init init_baycomepp(void)
{
- int i, found = 0;
+ int i, found = 0, ret;
char set_hw = 1;
printk(bc_drvinfo);
+
+ ret = parport_register_driver(&baycom_epp_par_driver);
+ if (ret)
+ return ret;
+
/*
* register net devices
*/
@@ -1241,7 +1277,12 @@ static int __init init_baycomepp(void)
found++;
}
- return found ? 0 : -ENXIO;
+ if (found == 0) {
+ parport_unregister_driver(&baycom_epp_par_driver);
+ return -ENXIO;
+ }
+
+ return 0;
}
static void __exit cleanup_baycomepp(void)
@@ -1260,6 +1301,7 @@ static void __exit cleanup_baycomepp(void)
printk(paranoia_str, "cleanup_module");
}
}
+ parport_unregister_driver(&baycom_epp_par_driver);
}
module_init(init_baycomepp);
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index aec6c26563cf..54bf8e6e4a09 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -477,7 +477,8 @@ static void ax_encaps(struct net_device *dev, unsigned char *icp, int len)
cmd = 0;
}
ax->crcauto = (cmd ? 0 : 1);
- printk(KERN_INFO "mkiss: %s: crc mode %s %d\n", ax->dev->name, (len) ? "set to" : "is", cmd);
+ printk(KERN_INFO "mkiss: %s: crc mode set to %d\n",
+ ax->dev->name, cmd);
}
spin_unlock_bh(&ax->buflock);
netif_start_queue(dev);
diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c
index 71ddadbf2368..76cc140774a2 100644
--- a/drivers/net/hippi/rrunner.c
+++ b/drivers/net/hippi/rrunner.c
@@ -1229,10 +1229,8 @@ static int rr_open(struct net_device *dev)
/* Set the timer to switch to check for link beat and perhaps switch
to an alternate media type. */
- init_timer(&rrpriv->timer);
+ setup_timer(&rrpriv->timer, rr_timer, (unsigned long)dev);
rrpriv->timer.expires = RUN_AT(5*HZ); /* 5 sec. watchdog */
- rrpriv->timer.data = (unsigned long)dev;
- rrpriv->timer.function = rr_timer; /* timer handler */
add_timer(&rrpriv->timer);
netif_start_queue(dev);
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 5176be76ca7d..6f550e15a41c 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -686,6 +686,8 @@ struct netvsc_ethtool_stats {
unsigned long tx_busy;
unsigned long tx_send_full;
unsigned long rx_comp_busy;
+ unsigned long stop_queue;
+ unsigned long wake_queue;
};
struct netvsc_vf_pcpu_stats {
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 8d5077fb0492..6e5194916bbe 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -484,7 +484,7 @@ static int netvsc_connect_vsp(struct hv_device *device,
struct netvsc_device *net_device,
const struct netvsc_device_info *device_info)
{
- const u32 ver_list[] = {
+ static const u32 ver_list[] = {
NVSP_PROTOCOL_VERSION_1, NVSP_PROTOCOL_VERSION_2,
NVSP_PROTOCOL_VERSION_4, NVSP_PROTOCOL_VERSION_5
};
@@ -609,6 +609,7 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device,
{
struct sk_buff *skb = (struct sk_buff *)(unsigned long)desc->trans_id;
struct net_device *ndev = hv_get_drvdata(device);
+ struct net_device_context *ndev_ctx = netdev_priv(ndev);
struct vmbus_channel *channel = device->channel;
u16 q_idx = 0;
int queue_sends;
@@ -643,8 +644,10 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device,
if (netif_tx_queue_stopped(netdev_get_tx_queue(ndev, q_idx)) &&
(hv_ringbuf_avail_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER ||
- queue_sends < 1))
+ queue_sends < 1)) {
netif_tx_wake_queue(netdev_get_tx_queue(ndev, q_idx));
+ ndev_ctx->eth_stats.wake_queue++;
+ }
}
static void netvsc_send_completion(struct netvsc_device *net_device,
@@ -749,6 +752,7 @@ static inline int netvsc_send_pkt(
&net_device->chan_table[packet->q_idx];
struct vmbus_channel *out_channel = nvchan->channel;
struct net_device *ndev = hv_get_drvdata(device);
+ struct net_device_context *ndev_ctx = netdev_priv(ndev);
struct netdev_queue *txq = netdev_get_tx_queue(ndev, packet->q_idx);
u64 req_id;
int ret;
@@ -789,12 +793,16 @@ static inline int netvsc_send_pkt(
if (ret == 0) {
atomic_inc_return(&nvchan->queue_sends);
- if (ring_avail < RING_AVAIL_PERCENT_LOWATER)
+ if (ring_avail < RING_AVAIL_PERCENT_LOWATER) {
netif_tx_stop_queue(txq);
+ ndev_ctx->eth_stats.stop_queue++;
+ }
} else if (ret == -EAGAIN) {
netif_tx_stop_queue(txq);
+ ndev_ctx->eth_stats.stop_queue++;
if (atomic_read(&nvchan->queue_sends) < 1) {
netif_tx_wake_queue(txq);
+ ndev_ctx->eth_stats.wake_queue++;
ret = -ENOSPC;
}
} else {
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index a32ae02e1b6c..dfb986421ec6 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1126,6 +1126,8 @@ static const struct {
{ "tx_busy", offsetof(struct netvsc_ethtool_stats, tx_busy) },
{ "tx_send_full", offsetof(struct netvsc_ethtool_stats, tx_send_full) },
{ "rx_comp_busy", offsetof(struct netvsc_ethtool_stats, rx_comp_busy) },
+ { "stop_queue", offsetof(struct netvsc_ethtool_stats, stop_queue) },
+ { "wake_queue", offsetof(struct netvsc_ethtool_stats, wake_queue) },
}, vf_stats[] = {
{ "vf_rx_packets", offsetof(struct netvsc_vf_pcpu_stats, rx_packets) },
{ "vf_rx_bytes", offsetof(struct netvsc_vf_pcpu_stats, rx_bytes) },
@@ -1746,7 +1748,7 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
goto rx_handler_failed;
}
- ret = netdev_upper_dev_link(vf_netdev, ndev);
+ ret = netdev_upper_dev_link(vf_netdev, ndev, NULL);
if (ret != 0) {
netdev_err(vf_netdev,
"can not set master device %s (err = %d)\n",
@@ -1935,6 +1937,12 @@ static int netvsc_probe(struct hv_device *dev,
/* We always need headroom for rndis header */
net->needed_headroom = RNDIS_AND_PPI_SIZE;
+ /* Initialize the number of queues to be 1, we may change it if more
+ * channels are offered later.
+ */
+ netif_set_real_num_tx_queues(net, 1);
+ netif_set_real_num_rx_queues(net, 1);
+
/* Notify the netvsc driver of the new device */
memset(&device_info, 0, sizeof(device_info));
device_info.ring_size = ring_size;
diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c
index ef688518ad77..115fa3f37a86 100644
--- a/drivers/net/ieee802154/atusb.c
+++ b/drivers/net/ieee802154/atusb.c
@@ -21,6 +21,9 @@
*
* USB initialization is
* Copyright (c) 2013 Alexander Aring <alex.aring@gmail.com>
+ *
+ * Busware HUL support is
+ * Copyright (c) 2017 Josef Filzmaier <j.filzmaier@gmx.at>
*/
#include <linux/kernel.h>
@@ -42,9 +45,12 @@
#define ATUSB_ALLOC_DELAY_MS 100 /* delay after failed allocation */
#define ATUSB_TX_TIMEOUT_MS 200 /* on the air timeout */
+struct atusb_chip_data;
+
struct atusb {
struct ieee802154_hw *hw;
struct usb_device *usb_dev;
+ struct atusb_chip_data *data;
int shutdown; /* non-zero if shutting down */
int err; /* set by first error */
@@ -65,6 +71,14 @@ struct atusb {
unsigned char fw_hw_type; /* Firmware hardware type */
};
+struct atusb_chip_data {
+ u16 t_channel_switch;
+ int rssi_base_val;
+
+ int (*set_channel)(struct ieee802154_hw*, u8, u8);
+ int (*set_txpower)(struct ieee802154_hw*, s32);
+};
+
/* ----- USB commands without data ----------------------------------------- */
/* To reduce the number of error checks in the code, we record the first error
@@ -163,6 +177,18 @@ static int atusb_write_subreg(struct atusb *atusb, uint8_t reg, uint8_t mask,
return ret;
}
+static int atusb_read_subreg(struct atusb *lp,
+ unsigned int addr, unsigned int mask,
+ unsigned int shift)
+{
+ int rc;
+
+ rc = atusb_read_reg(lp, addr);
+ rc = (rc & mask) >> shift;
+
+ return rc;
+}
+
static int atusb_get_and_clear_error(struct atusb *atusb)
{
int err = atusb->err;
@@ -379,18 +405,6 @@ static int atusb_xmit(struct ieee802154_hw *hw, struct sk_buff *skb)
return ret;
}
-static int atusb_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
-{
- struct atusb *atusb = hw->priv;
- int ret;
-
- ret = atusb_write_subreg(atusb, SR_CHANNEL, channel);
- if (ret < 0)
- return ret;
- msleep(1); /* @@@ ugly synchronization */
- return 0;
-}
-
static int atusb_ed(struct ieee802154_hw *hw, u8 *level)
{
BUG_ON(!level);
@@ -475,6 +489,17 @@ static const s32 atusb_powers[ATUSB_MAX_TX_POWERS + 1] = {
};
static int
+atusb_txpower(struct ieee802154_hw *hw, s32 mbm)
+{
+ struct atusb *atusb = hw->priv;
+
+ if (atusb->data)
+ return atusb->data->set_txpower(hw, mbm);
+ else
+ return -ENOTSUPP;
+}
+
+static int
atusb_set_txpower(struct ieee802154_hw *hw, s32 mbm)
{
struct atusb *atusb = hw->priv;
@@ -488,12 +513,43 @@ atusb_set_txpower(struct ieee802154_hw *hw, s32 mbm)
return -EINVAL;
}
+static int
+hulusb_set_txpower(struct ieee802154_hw *hw, s32 mbm)
+{
+ u32 i;
+
+ for (i = 0; i < hw->phy->supported.tx_powers_size; i++) {
+ if (hw->phy->supported.tx_powers[i] == mbm)
+ return atusb_write_subreg(hw->priv, SR_TX_PWR_212, i);
+ }
+
+ return -EINVAL;
+}
+
#define ATUSB_MAX_ED_LEVELS 0xF
static const s32 atusb_ed_levels[ATUSB_MAX_ED_LEVELS + 1] = {
-9100, -8900, -8700, -8500, -8300, -8100, -7900, -7700, -7500, -7300,
-7100, -6900, -6700, -6500, -6300, -6100,
};
+#define AT86RF212_MAX_TX_POWERS 0x1F
+static const s32 at86rf212_powers[AT86RF212_MAX_TX_POWERS + 1] = {
+ 500, 400, 300, 200, 100, 0, -100, -200, -300, -400, -500, -600, -700,
+ -800, -900, -1000, -1100, -1200, -1300, -1400, -1500, -1600, -1700,
+ -1800, -1900, -2000, -2100, -2200, -2300, -2400, -2500, -2600,
+};
+
+#define AT86RF2XX_MAX_ED_LEVELS 0xF
+static const s32 at86rf212_ed_levels_100[AT86RF2XX_MAX_ED_LEVELS + 1] = {
+ -10000, -9800, -9600, -9400, -9200, -9000, -8800, -8600, -8400, -8200,
+ -8000, -7800, -7600, -7400, -7200, -7000,
+};
+
+static const s32 at86rf212_ed_levels_98[AT86RF2XX_MAX_ED_LEVELS + 1] = {
+ -9800, -9600, -9400, -9200, -9000, -8800, -8600, -8400, -8200, -8000,
+ -7800, -7600, -7400, -7200, -7000, -6800,
+};
+
static int
atusb_set_cca_mode(struct ieee802154_hw *hw, const struct wpan_phy_cca *cca)
{
@@ -527,6 +583,30 @@ atusb_set_cca_mode(struct ieee802154_hw *hw, const struct wpan_phy_cca *cca)
return atusb_write_subreg(atusb, SR_CCA_MODE, val);
}
+static int hulusb_set_cca_ed_level(struct atusb *lp, int rssi_base_val)
+{
+ unsigned int cca_ed_thres;
+
+ cca_ed_thres = atusb_read_subreg(lp, SR_CCA_ED_THRES);
+
+ switch (rssi_base_val) {
+ case -98:
+ lp->hw->phy->supported.cca_ed_levels = at86rf212_ed_levels_98;
+ lp->hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(at86rf212_ed_levels_98);
+ lp->hw->phy->cca_ed_level = at86rf212_ed_levels_98[cca_ed_thres];
+ break;
+ case -100:
+ lp->hw->phy->supported.cca_ed_levels = at86rf212_ed_levels_100;
+ lp->hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(at86rf212_ed_levels_100);
+ lp->hw->phy->cca_ed_level = at86rf212_ed_levels_100[cca_ed_thres];
+ break;
+ default:
+ WARN_ON(1);
+ }
+
+ return 0;
+}
+
static int
atusb_set_cca_ed_level(struct ieee802154_hw *hw, s32 mbm)
{
@@ -541,6 +621,92 @@ atusb_set_cca_ed_level(struct ieee802154_hw *hw, s32 mbm)
return -EINVAL;
}
+static int atusb_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
+{
+ struct atusb *atusb = hw->priv;
+ int ret = -ENOTSUPP;
+
+ if (atusb->data) {
+ ret = atusb->data->set_channel(hw, page, channel);
+ /* @@@ ugly synchronization */
+ msleep(atusb->data->t_channel_switch);
+ }
+
+ return ret;
+}
+
+static int atusb_set_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
+{
+ struct atusb *atusb = hw->priv;
+ int ret;
+
+ ret = atusb_write_subreg(atusb, SR_CHANNEL, channel);
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+
+static int hulusb_set_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
+{
+ int rc;
+ int rssi_base_val;
+
+ struct atusb *lp = hw->priv;
+
+ if (channel == 0)
+ rc = atusb_write_subreg(lp, SR_SUB_MODE, 0);
+ else
+ rc = atusb_write_subreg(lp, SR_SUB_MODE, 1);
+ if (rc < 0)
+ return rc;
+
+ if (page == 0) {
+ rc = atusb_write_subreg(lp, SR_BPSK_QPSK, 0);
+ rssi_base_val = -100;
+ } else {
+ rc = atusb_write_subreg(lp, SR_BPSK_QPSK, 1);
+ rssi_base_val = -98;
+ }
+ if (rc < 0)
+ return rc;
+
+ rc = hulusb_set_cca_ed_level(lp, rssi_base_val);
+ if (rc < 0)
+ return rc;
+
+ /* This sets the symbol_duration according frequency on the 212.
+ * TODO move this handling while set channel and page in cfg802154.
+ * We can do that, this timings are according 802.15.4 standard.
+ * If we do that in cfg802154, this is a more generic calculation.
+ *
+ * This should also protected from ifs_timer. Means cancel timer and
+ * init with a new value. For now, this is okay.
+ */
+ if (channel == 0) {
+ if (page == 0) {
+ /* SUB:0 and BPSK:0 -> BPSK-20 */
+ lp->hw->phy->symbol_duration = 50;
+ } else {
+ /* SUB:1 and BPSK:0 -> BPSK-40 */
+ lp->hw->phy->symbol_duration = 25;
+ }
+ } else {
+ if (page == 0)
+ /* SUB:0 and BPSK:1 -> OQPSK-100/200/400 */
+ lp->hw->phy->symbol_duration = 40;
+ else
+ /* SUB:1 and BPSK:1 -> OQPSK-250/500/1000 */
+ lp->hw->phy->symbol_duration = 16;
+ }
+
+ lp->hw->phy->lifs_period = IEEE802154_LIFS_PERIOD *
+ lp->hw->phy->symbol_duration;
+ lp->hw->phy->sifs_period = IEEE802154_SIFS_PERIOD *
+ lp->hw->phy->symbol_duration;
+
+ return atusb_write_subreg(lp, SR_CHANNEL, channel);
+}
+
static int
atusb_set_csma_params(struct ieee802154_hw *hw, u8 min_be, u8 max_be, u8 retries)
{
@@ -559,6 +725,14 @@ atusb_set_csma_params(struct ieee802154_hw *hw, u8 min_be, u8 max_be, u8 retries
}
static int
+hulusb_set_lbt(struct ieee802154_hw *hw, bool on)
+{
+ struct atusb *atusb = hw->priv;
+
+ return atusb_write_subreg(atusb, SR_CSMA_LBT_MODE, on);
+}
+
+static int
atusb_set_frame_retries(struct ieee802154_hw *hw, s8 retries)
{
struct atusb *atusb = hw->priv;
@@ -593,6 +767,20 @@ atusb_set_promiscuous_mode(struct ieee802154_hw *hw, const bool on)
return 0;
}
+struct atusb_chip_data atusb_chip_data = {
+ .t_channel_switch = 1,
+ .rssi_base_val = -91,
+ .set_txpower = atusb_set_txpower,
+ .set_channel = atusb_set_channel,
+};
+
+struct atusb_chip_data hulusb_chip_data = {
+ .t_channel_switch = 11,
+ .rssi_base_val = -100,
+ .set_txpower = hulusb_set_txpower,
+ .set_channel = hulusb_set_channel,
+};
+
static const struct ieee802154_ops atusb_ops = {
.owner = THIS_MODULE,
.xmit_async = atusb_xmit,
@@ -601,7 +789,8 @@ static const struct ieee802154_ops atusb_ops = {
.start = atusb_start,
.stop = atusb_stop,
.set_hw_addr_filt = atusb_set_hw_addr_filt,
- .set_txpower = atusb_set_txpower,
+ .set_txpower = atusb_txpower,
+ .set_lbt = hulusb_set_lbt,
.set_cca_mode = atusb_set_cca_mode,
.set_cca_ed_level = atusb_set_cca_ed_level,
.set_csma_params = atusb_set_csma_params,
@@ -614,6 +803,7 @@ static const struct ieee802154_ops atusb_ops = {
static int atusb_get_and_show_revision(struct atusb *atusb)
{
struct usb_device *usb_dev = atusb->usb_dev;
+ char *hw_name;
unsigned char *buffer;
int ret;
@@ -630,9 +820,31 @@ static int atusb_get_and_show_revision(struct atusb *atusb)
atusb->fw_ver_min = buffer[1];
atusb->fw_hw_type = buffer[2];
+ switch (atusb->fw_hw_type) {
+ case ATUSB_HW_TYPE_100813:
+ case ATUSB_HW_TYPE_101216:
+ case ATUSB_HW_TYPE_110131:
+ hw_name = "ATUSB";
+ atusb->data = &atusb_chip_data;
+ break;
+ case ATUSB_HW_TYPE_RZUSB:
+ hw_name = "RZUSB";
+ atusb->data = &atusb_chip_data;
+ break;
+ case ATUSB_HW_TYPE_HULUSB:
+ hw_name = "HULUSB";
+ atusb->data = &hulusb_chip_data;
+ break;
+ default:
+ hw_name = "UNKNOWN";
+ atusb->err = -ENOTSUPP;
+ ret = -ENOTSUPP;
+ break;
+ }
+
dev_info(&usb_dev->dev,
- "Firmware: major: %u, minor: %u, hardware type: %u\n",
- atusb->fw_ver_maj, atusb->fw_ver_min, atusb->fw_hw_type);
+ "Firmware: major: %u, minor: %u, hardware type: %s (%d)\n",
+ atusb->fw_ver_maj, atusb->fw_ver_min, hw_name, atusb->fw_hw_type);
}
if (atusb->fw_ver_maj == 0 && atusb->fw_ver_min < 2) {
dev_info(&usb_dev->dev,
@@ -667,11 +879,12 @@ static int atusb_get_and_show_build(struct atusb *atusb)
return ret;
}
-static int atusb_get_and_show_chip(struct atusb *atusb)
+static int atusb_get_and_conf_chip(struct atusb *atusb)
{
struct usb_device *usb_dev = atusb->usb_dev;
uint8_t man_id_0, man_id_1, part_num, version_num;
const char *chip;
+ struct ieee802154_hw *hw = atusb->hw;
man_id_0 = atusb_read_reg(atusb, RG_MAN_ID_0);
man_id_1 = atusb_read_reg(atusb, RG_MAN_ID_1);
@@ -681,6 +894,22 @@ static int atusb_get_and_show_chip(struct atusb *atusb)
if (atusb->err)
return atusb->err;
+ hw->flags = IEEE802154_HW_TX_OMIT_CKSUM | IEEE802154_HW_AFILT |
+ IEEE802154_HW_PROMISCUOUS | IEEE802154_HW_CSMA_PARAMS;
+
+ hw->phy->flags = WPAN_PHY_FLAG_TXPOWER | WPAN_PHY_FLAG_CCA_ED_LEVEL |
+ WPAN_PHY_FLAG_CCA_MODE;
+
+ hw->phy->supported.cca_modes = BIT(NL802154_CCA_ENERGY) |
+ BIT(NL802154_CCA_CARRIER) |
+ BIT(NL802154_CCA_ENERGY_CARRIER);
+ hw->phy->supported.cca_opts = BIT(NL802154_CCA_OPT_ENERGY_CARRIER_AND) |
+ BIT(NL802154_CCA_OPT_ENERGY_CARRIER_OR);
+
+ hw->phy->cca.mode = NL802154_CCA_ENERGY;
+
+ hw->phy->current_page = 0;
+
if ((man_id_1 << 8 | man_id_0) != ATUSB_JEDEC_ATMEL) {
dev_err(&usb_dev->dev,
"non-Atmel transceiver xxxx%02x%02x\n",
@@ -691,9 +920,36 @@ static int atusb_get_and_show_chip(struct atusb *atusb)
switch (part_num) {
case 2:
chip = "AT86RF230";
+ atusb->hw->phy->supported.channels[0] = 0x7FFF800;
+ atusb->hw->phy->current_channel = 11; /* reset default */
+ atusb->hw->phy->symbol_duration = 16;
+ atusb->hw->phy->supported.tx_powers = atusb_powers;
+ atusb->hw->phy->supported.tx_powers_size = ARRAY_SIZE(atusb_powers);
+ hw->phy->supported.cca_ed_levels = atusb_ed_levels;
+ hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(atusb_ed_levels);
break;
case 3:
chip = "AT86RF231";
+ atusb->hw->phy->supported.channels[0] = 0x7FFF800;
+ atusb->hw->phy->current_channel = 11; /* reset default */
+ atusb->hw->phy->symbol_duration = 16;
+ atusb->hw->phy->supported.tx_powers = atusb_powers;
+ atusb->hw->phy->supported.tx_powers_size = ARRAY_SIZE(atusb_powers);
+ hw->phy->supported.cca_ed_levels = atusb_ed_levels;
+ hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(atusb_ed_levels);
+ break;
+ case 7:
+ chip = "AT86RF212";
+ atusb->hw->flags |= IEEE802154_HW_LBT;
+ atusb->hw->phy->supported.channels[0] = 0x00007FF;
+ atusb->hw->phy->supported.channels[2] = 0x00007FF;
+ atusb->hw->phy->current_channel = 5;
+ atusb->hw->phy->symbol_duration = 25;
+ atusb->hw->phy->supported.lbt = NL802154_SUPPORTED_BOOL_BOTH;
+ atusb->hw->phy->supported.tx_powers = at86rf212_powers;
+ atusb->hw->phy->supported.tx_powers_size = ARRAY_SIZE(at86rf212_powers);
+ atusb->hw->phy->supported.cca_ed_levels = at86rf212_ed_levels_100;
+ atusb->hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(at86rf212_ed_levels_100);
break;
default:
dev_err(&usb_dev->dev,
@@ -702,6 +958,9 @@ static int atusb_get_and_show_chip(struct atusb *atusb)
goto fail;
}
+ hw->phy->transmit_power = hw->phy->supported.tx_powers[0];
+ hw->phy->cca_ed_level = hw->phy->supported.cca_ed_levels[7];
+
dev_info(&usb_dev->dev, "ATUSB: %s version %d\n", chip, version_num);
return 0;
@@ -794,32 +1053,9 @@ static int atusb_probe(struct usb_interface *interface,
goto fail;
hw->parent = &usb_dev->dev;
- hw->flags = IEEE802154_HW_TX_OMIT_CKSUM | IEEE802154_HW_AFILT |
- IEEE802154_HW_PROMISCUOUS | IEEE802154_HW_CSMA_PARAMS;
-
- hw->phy->flags = WPAN_PHY_FLAG_TXPOWER | WPAN_PHY_FLAG_CCA_ED_LEVEL |
- WPAN_PHY_FLAG_CCA_MODE;
-
- hw->phy->supported.cca_modes = BIT(NL802154_CCA_ENERGY) |
- BIT(NL802154_CCA_CARRIER) | BIT(NL802154_CCA_ENERGY_CARRIER);
- hw->phy->supported.cca_opts = BIT(NL802154_CCA_OPT_ENERGY_CARRIER_AND) |
- BIT(NL802154_CCA_OPT_ENERGY_CARRIER_OR);
-
- hw->phy->supported.cca_ed_levels = atusb_ed_levels;
- hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(atusb_ed_levels);
-
- hw->phy->cca.mode = NL802154_CCA_ENERGY;
-
- hw->phy->current_page = 0;
- hw->phy->current_channel = 11; /* reset default */
- hw->phy->supported.channels[0] = 0x7FFF800;
- hw->phy->supported.tx_powers = atusb_powers;
- hw->phy->supported.tx_powers_size = ARRAY_SIZE(atusb_powers);
- hw->phy->transmit_power = hw->phy->supported.tx_powers[0];
- hw->phy->cca_ed_level = hw->phy->supported.cca_ed_levels[7];
atusb_command(atusb, ATUSB_RF_RESET, 0);
- atusb_get_and_show_chip(atusb);
+ atusb_get_and_conf_chip(atusb);
atusb_get_and_show_revision(atusb);
atusb_get_and_show_build(atusb);
atusb_set_extended_addr(atusb);
@@ -941,5 +1177,6 @@ MODULE_AUTHOR("Alexander Aring <alex.aring@gmail.com>");
MODULE_AUTHOR("Richard Sharpe <realrichardsharpe@gmail.com>");
MODULE_AUTHOR("Stefan Schmidt <stefan@datenfreihafen.org>");
MODULE_AUTHOR("Werner Almesberger <werner@almesberger.net>");
+MODULE_AUTHOR("Josef Filzmaier <j.filzmaier@gmx.at>");
MODULE_DESCRIPTION("ATUSB IEEE 802.15.4 Driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/ieee802154/atusb.h b/drivers/net/ieee802154/atusb.h
index b22bbaa77590..555d14bf14a3 100644
--- a/drivers/net/ieee802154/atusb.h
+++ b/drivers/net/ieee802154/atusb.h
@@ -50,6 +50,14 @@ enum atusb_requests {
ATUSB_EUI64_READ,
};
+enum {
+ ATUSB_HW_TYPE_100813, /* 2010-08-13 */
+ ATUSB_HW_TYPE_101216, /* 2010-12-16 */
+ ATUSB_HW_TYPE_110131, /* 2011-01-31, ATmega32U2-based */
+ ATUSB_HW_TYPE_RZUSB, /* Atmel Raven USB dongle with at86rf230 */
+ ATUSB_HW_TYPE_HULUSB, /* Busware HUL USB dongle with at86rf212 */
+};
+
/*
* Direction bRequest wValue wIndex wLength
*
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index 8870bd2a2e8a..0008da7e9d4c 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -231,6 +231,9 @@ static void ifb_setup(struct net_device *dev)
eth_hw_addr_random(dev);
dev->needs_free_netdev = true;
dev->priv_destructor = ifb_dev_free;
+
+ dev->min_mtu = 0;
+ dev->max_mtu = 0;
}
static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev)
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index c74893c1e620..57c3856bab05 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -584,7 +584,7 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev,
if (err < 0)
goto remove_ida;
- err = netdev_upper_dev_link(phy_dev, dev);
+ err = netdev_upper_dev_link(phy_dev, dev, extack);
if (err) {
goto unregister_netdev;
}
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 98e4deaa3a6a..ccbe4eaffe4d 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -3244,7 +3244,7 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
&macsec_netdev_addr_lock_key,
macsec_get_nest_level(dev));
- err = netdev_upper_dev_link(real_dev, dev);
+ err = netdev_upper_dev_link(real_dev, dev, extack);
if (err < 0)
goto unregister;
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index d2aea961e0f4..858bd66511a2 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1231,11 +1231,14 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[],
return -EADDRNOTAVAIL;
}
- if (data && data[IFLA_MACVLAN_FLAGS] &&
+ if (!data)
+ return 0;
+
+ if (data[IFLA_MACVLAN_FLAGS] &&
nla_get_u16(data[IFLA_MACVLAN_FLAGS]) & ~MACVLAN_FLAG_NOPROMISC)
return -EINVAL;
- if (data && data[IFLA_MACVLAN_MODE]) {
+ if (data[IFLA_MACVLAN_MODE]) {
switch (nla_get_u32(data[IFLA_MACVLAN_MODE])) {
case MACVLAN_MODE_PRIVATE:
case MACVLAN_MODE_VEPA:
@@ -1248,7 +1251,7 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[],
}
}
- if (data && data[IFLA_MACVLAN_MACADDR_MODE]) {
+ if (data[IFLA_MACVLAN_MACADDR_MODE]) {
switch (nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE])) {
case MACVLAN_MACADDR_ADD:
case MACVLAN_MACADDR_DEL:
@@ -1260,7 +1263,7 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[],
}
}
- if (data && data[IFLA_MACVLAN_MACADDR]) {
+ if (data[IFLA_MACVLAN_MACADDR]) {
if (nla_len(data[IFLA_MACVLAN_MACADDR]) != ETH_ALEN)
return -EINVAL;
@@ -1268,7 +1271,7 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[],
return -EADDRNOTAVAIL;
}
- if (data && data[IFLA_MACVLAN_MACADDR_COUNT])
+ if (data[IFLA_MACVLAN_MACADDR_COUNT])
return -EINVAL;
return 0;
@@ -1341,7 +1344,8 @@ static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode,
}
int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
- struct nlattr *tb[], struct nlattr *data[])
+ struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct macvlan_port *port;
@@ -1430,7 +1434,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
goto destroy_macvlan_port;
dev->priv_flags |= IFF_MACVLAN;
- err = netdev_upper_dev_link(lowerdev, dev);
+ err = netdev_upper_dev_link(lowerdev, dev, extack);
if (err)
goto unregister_netdev;
@@ -1453,7 +1457,7 @@ static int macvlan_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
- return macvlan_common_newlink(src_net, dev, tb, data);
+ return macvlan_common_newlink(src_net, dev, tb, data, extack);
}
void macvlan_dellink(struct net_device *dev, struct list_head *head)
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index c2d0ea2fb019..f62aea2fcfa9 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -105,7 +105,7 @@ static int macvtap_newlink(struct net *src_net, struct net_device *dev,
/* Don't put anything that may fail after macvlan_common_newlink
* because we can't undo what it does.
*/
- err = macvlan_common_newlink(src_net, dev, tb, data);
+ err = macvlan_common_newlink(src_net, dev, tb, data, extack);
if (err) {
netdev_rx_handler_unregister(dev);
return err;
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 9cbe645e3d89..d4670ecdb1ba 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -22,17 +22,29 @@
#define RTL821x_INER 0x12
#define RTL821x_INER_INIT 0x6400
#define RTL821x_INSR 0x13
+#define RTL821x_PAGE_SELECT 0x1f
#define RTL8211E_INER_LINK_STATUS 0x400
#define RTL8211F_INER_LINK_STATUS 0x0010
#define RTL8211F_INSR 0x1d
-#define RTL8211F_PAGE_SELECT 0x1f
#define RTL8211F_TX_DELAY 0x100
+#define RTL8201F_ISR 0x1e
+#define RTL8201F_IER 0x13
+
MODULE_DESCRIPTION("Realtek PHY driver");
MODULE_AUTHOR("Johnson Leung");
MODULE_LICENSE("GPL");
+static int rtl8201_ack_interrupt(struct phy_device *phydev)
+{
+ int err;
+
+ err = phy_read(phydev, RTL8201F_ISR);
+
+ return (err < 0) ? err : 0;
+}
+
static int rtl821x_ack_interrupt(struct phy_device *phydev)
{
int err;
@@ -46,14 +58,33 @@ static int rtl8211f_ack_interrupt(struct phy_device *phydev)
{
int err;
- phy_write(phydev, RTL8211F_PAGE_SELECT, 0xa43);
+ phy_write(phydev, RTL821x_PAGE_SELECT, 0xa43);
err = phy_read(phydev, RTL8211F_INSR);
/* restore to default page 0 */
- phy_write(phydev, RTL8211F_PAGE_SELECT, 0x0);
+ phy_write(phydev, RTL821x_PAGE_SELECT, 0x0);
return (err < 0) ? err : 0;
}
+static int rtl8201_config_intr(struct phy_device *phydev)
+{
+ int err;
+
+ /* switch to page 7 */
+ phy_write(phydev, RTL821x_PAGE_SELECT, 0x7);
+
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ err = phy_write(phydev, RTL8201F_IER,
+ BIT(13) | BIT(12) | BIT(11));
+ else
+ err = phy_write(phydev, RTL8201F_IER, 0);
+
+ /* restore to default page 0 */
+ phy_write(phydev, RTL821x_PAGE_SELECT, 0x0);
+
+ return err;
+}
+
static int rtl8211b_config_intr(struct phy_device *phydev)
{
int err;
@@ -102,7 +133,7 @@ static int rtl8211f_config_init(struct phy_device *phydev)
if (ret < 0)
return ret;
- phy_write(phydev, RTL8211F_PAGE_SELECT, 0xd08);
+ phy_write(phydev, RTL821x_PAGE_SELECT, 0xd08);
reg = phy_read(phydev, 0x11);
/* enable TX-delay for rgmii-id and rgmii-txid, otherwise disable it */
@@ -114,7 +145,7 @@ static int rtl8211f_config_init(struct phy_device *phydev)
phy_write(phydev, 0x11, reg);
/* restore to default page 0 */
- phy_write(phydev, RTL8211F_PAGE_SELECT, 0x0);
+ phy_write(phydev, RTL821x_PAGE_SELECT, 0x0);
return 0;
}
@@ -129,6 +160,18 @@ static struct phy_driver realtek_drvs[] = {
.config_aneg = &genphy_config_aneg,
.read_status = &genphy_read_status,
}, {
+ .phy_id = 0x001cc816,
+ .name = "RTL8201F 10/100Mbps Ethernet",
+ .phy_id_mask = 0x001fffff,
+ .features = PHY_BASIC_FEATURES,
+ .flags = PHY_HAS_INTERRUPT,
+ .config_aneg = &genphy_config_aneg,
+ .read_status = &genphy_read_status,
+ .ack_interrupt = &rtl8201_ack_interrupt,
+ .config_intr = &rtl8201_config_intr,
+ .suspend = genphy_suspend,
+ .resume = genphy_resume,
+ }, {
.phy_id = 0x001cc912,
.name = "RTL8211B Gigabit Ethernet",
.phy_id_mask = 0x001fffff,
@@ -181,6 +224,7 @@ static struct phy_driver realtek_drvs[] = {
module_phy_driver(realtek_drvs);
static struct mdio_device_id __maybe_unused realtek_tbl[] = {
+ { 0x001cc816, 0x001fffff },
{ 0x001cc912, 0x001fffff },
{ 0x001cc914, 0x001fffff },
{ 0x001cc915, 0x001fffff },
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index 436dd78c396a..eb8a18991d8c 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -763,12 +763,8 @@ static struct slip *sl_alloc(dev_t line)
sl->mode = SL_MODE_DEFAULT;
#ifdef CONFIG_SLIP_SMART
/* initialize timer_list struct */
- init_timer(&sl->keepalive_timer);
- sl->keepalive_timer.data = (unsigned long)sl;
- sl->keepalive_timer.function = sl_keepalive;
- init_timer(&sl->outfill_timer);
- sl->outfill_timer.data = (unsigned long)sl;
- sl->outfill_timer.function = sl_outfill;
+ setup_timer(&sl->keepalive_timer, sl_keepalive, (unsigned long)sl);
+ setup_timer(&sl->outfill_timer, sl_outfill, (unsigned long)sl);
#endif
slip_devs[i] = dev;
return sl;
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index ae53e899259f..a468439969df 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1112,7 +1112,7 @@ static int team_upper_dev_link(struct team *team, struct team_port *port)
lag_upper_info.tx_type = team->mode->lag_tx_type;
err = netdev_master_upper_dev_link(port->dev, team->dev, NULL,
- &lag_upper_info);
+ &lag_upper_info, NULL);
if (err)
return err;
port->dev->priv_flags |= IFF_TEAM_PORT;
@@ -1914,7 +1914,8 @@ static int team_netpoll_setup(struct net_device *dev,
}
#endif
-static int team_add_slave(struct net_device *dev, struct net_device *port_dev)
+static int team_add_slave(struct net_device *dev, struct net_device *port_dev,
+ struct netlink_ext_ack *extack)
{
struct team *team = netdev_priv(dev);
int err;
diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c
index 1468ddf424cc..a5ef97010eb3 100644
--- a/drivers/net/team/team_mode_loadbalance.c
+++ b/drivers/net/team/team_mode_loadbalance.c
@@ -137,7 +137,13 @@ static struct team_port *lb_htpm_select_tx_port(struct team *team,
struct sk_buff *skb,
unsigned char hash)
{
- return rcu_dereference_bh(LB_HTPM_PORT_BY_HASH(lb_priv, hash));
+ struct team_port *port;
+
+ port = rcu_dereference_bh(LB_HTPM_PORT_BY_HASH(lb_priv, hash));
+ if (likely(port))
+ return port;
+ /* If no valid port in the table, fall back to simple hash */
+ return lb_hash_select_tx_port(team, lb_priv, skb, hash);
}
struct lb_select_tx_port {
diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt.c
new file mode 100644
index 000000000000..1a7bc0bf4598
--- /dev/null
+++ b/drivers/net/thunderbolt.c
@@ -0,0 +1,1362 @@
+/*
+ * Networking over Thunderbolt cable using Apple ThunderboltIP protocol
+ *
+ * Copyright (C) 2017, Intel Corporation
+ * Authors: Amir Levy <amir.jer.levy@intel.com>
+ * Michael Jamet <michael.jamet@intel.com>
+ * Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/atomic.h>
+#include <linux/highmem.h>
+#include <linux/if_vlan.h>
+#include <linux/jhash.h>
+#include <linux/module.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/sizes.h>
+#include <linux/thunderbolt.h>
+#include <linux/uuid.h>
+#include <linux/workqueue.h>
+
+#include <net/ip6_checksum.h>
+
+/* Protocol timeouts in ms */
+#define TBNET_LOGIN_DELAY 4500
+#define TBNET_LOGIN_TIMEOUT 500
+#define TBNET_LOGOUT_TIMEOUT 100
+
+#define TBNET_RING_SIZE 256
+#define TBNET_LOCAL_PATH 0xf
+#define TBNET_LOGIN_RETRIES 60
+#define TBNET_LOGOUT_RETRIES 5
+#define TBNET_MATCH_FRAGS_ID BIT(1)
+#define TBNET_MAX_MTU SZ_64K
+#define TBNET_FRAME_SIZE SZ_4K
+#define TBNET_MAX_PAYLOAD_SIZE \
+ (TBNET_FRAME_SIZE - sizeof(struct thunderbolt_ip_frame_header))
+/* Rx packets need to hold space for skb_shared_info */
+#define TBNET_RX_MAX_SIZE \
+ (TBNET_FRAME_SIZE + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+#define TBNET_RX_PAGE_ORDER get_order(TBNET_RX_MAX_SIZE)
+#define TBNET_RX_PAGE_SIZE (PAGE_SIZE << TBNET_RX_PAGE_ORDER)
+
+#define TBNET_L0_PORT_NUM(route) ((route) & GENMASK(5, 0))
+
+/**
+ * struct thunderbolt_ip_frame_header - Header for each Thunderbolt frame
+ * @frame_size: size of the data with the frame
+ * @frame_index: running index on the frames
+ * @frame_id: ID of the frame to match frames to specific packet
+ * @frame_count: how many frames assembles a full packet
+ *
+ * Each data frame passed to the high-speed DMA ring has this header. If
+ * the XDomain network directory announces that %TBNET_MATCH_FRAGS_ID is
+ * supported then @frame_id is filled, otherwise it stays %0.
+ */
+struct thunderbolt_ip_frame_header {
+ u32 frame_size;
+ u16 frame_index;
+ u16 frame_id;
+ u32 frame_count;
+};
+
+enum thunderbolt_ip_frame_pdf {
+ TBIP_PDF_FRAME_START = 1,
+ TBIP_PDF_FRAME_END,
+};
+
+enum thunderbolt_ip_type {
+ TBIP_LOGIN,
+ TBIP_LOGIN_RESPONSE,
+ TBIP_LOGOUT,
+ TBIP_STATUS,
+};
+
+struct thunderbolt_ip_header {
+ u32 route_hi;
+ u32 route_lo;
+ u32 length_sn;
+ uuid_t uuid;
+ uuid_t initiator_uuid;
+ uuid_t target_uuid;
+ u32 type;
+ u32 command_id;
+};
+
+#define TBIP_HDR_LENGTH_MASK GENMASK(5, 0)
+#define TBIP_HDR_SN_MASK GENMASK(28, 27)
+#define TBIP_HDR_SN_SHIFT 27
+
+struct thunderbolt_ip_login {
+ struct thunderbolt_ip_header hdr;
+ u32 proto_version;
+ u32 transmit_path;
+ u32 reserved[4];
+};
+
+#define TBIP_LOGIN_PROTO_VERSION 1
+
+struct thunderbolt_ip_login_response {
+ struct thunderbolt_ip_header hdr;
+ u32 status;
+ u32 receiver_mac[2];
+ u32 receiver_mac_len;
+ u32 reserved[4];
+};
+
+struct thunderbolt_ip_logout {
+ struct thunderbolt_ip_header hdr;
+};
+
+struct thunderbolt_ip_status {
+ struct thunderbolt_ip_header hdr;
+ u32 status;
+};
+
+struct tbnet_stats {
+ u64 tx_packets;
+ u64 rx_packets;
+ u64 tx_bytes;
+ u64 rx_bytes;
+ u64 rx_errors;
+ u64 tx_errors;
+ u64 rx_length_errors;
+ u64 rx_over_errors;
+ u64 rx_crc_errors;
+ u64 rx_missed_errors;
+};
+
+struct tbnet_frame {
+ struct net_device *dev;
+ struct page *page;
+ struct ring_frame frame;
+};
+
+struct tbnet_ring {
+ struct tbnet_frame frames[TBNET_RING_SIZE];
+ unsigned int cons;
+ unsigned int prod;
+ struct tb_ring *ring;
+};
+
+/**
+ * struct tbnet - ThunderboltIP network driver private data
+ * @svc: XDomain service the driver is bound to
+ * @xd: XDomain the service blongs to
+ * @handler: ThunderboltIP configuration protocol handler
+ * @dev: Networking device
+ * @napi: NAPI structure for Rx polling
+ * @stats: Network statistics
+ * @skb: Network packet that is currently processed on Rx path
+ * @command_id: ID used for next configuration protocol packet
+ * @login_sent: ThunderboltIP login message successfully sent
+ * @login_received: ThunderboltIP login message received from the remote
+ * host
+ * @transmit_path: HopID the other end needs to use building the
+ * opposite side path.
+ * @connection_lock: Lock serializing access to @login_sent,
+ * @login_received and @transmit_path.
+ * @login_retries: Number of login retries currently done
+ * @login_work: Worker to send ThunderboltIP login packets
+ * @connected_work: Worker that finalizes the ThunderboltIP connection
+ * setup and enables DMA paths for high speed data
+ * transfers
+ * @rx_hdr: Copy of the currently processed Rx frame. Used when a
+ * network packet consists of multiple Thunderbolt frames.
+ * In host byte order.
+ * @rx_ring: Software ring holding Rx frames
+ * @frame_id: Frame ID use for next Tx packet
+ * (if %TBNET_MATCH_FRAGS_ID is supported in both ends)
+ * @tx_ring: Software ring holding Tx frames
+ */
+struct tbnet {
+ const struct tb_service *svc;
+ struct tb_xdomain *xd;
+ struct tb_protocol_handler handler;
+ struct net_device *dev;
+ struct napi_struct napi;
+ struct tbnet_stats stats;
+ struct sk_buff *skb;
+ atomic_t command_id;
+ bool login_sent;
+ bool login_received;
+ u32 transmit_path;
+ struct mutex connection_lock;
+ int login_retries;
+ struct delayed_work login_work;
+ struct work_struct connected_work;
+ struct thunderbolt_ip_frame_header rx_hdr;
+ struct tbnet_ring rx_ring;
+ atomic_t frame_id;
+ struct tbnet_ring tx_ring;
+};
+
+/* Network property directory UUID: c66189ca-1cce-4195-bdb8-49592e5f5a4f */
+static const uuid_t tbnet_dir_uuid =
+ UUID_INIT(0xc66189ca, 0x1cce, 0x4195,
+ 0xbd, 0xb8, 0x49, 0x59, 0x2e, 0x5f, 0x5a, 0x4f);
+
+/* ThunderboltIP protocol UUID: 798f589e-3616-8a47-97c6-5664a920c8dd */
+static const uuid_t tbnet_svc_uuid =
+ UUID_INIT(0x798f589e, 0x3616, 0x8a47,
+ 0x97, 0xc6, 0x56, 0x64, 0xa9, 0x20, 0xc8, 0xdd);
+
+static struct tb_property_dir *tbnet_dir;
+
+static void tbnet_fill_header(struct thunderbolt_ip_header *hdr, u64 route,
+ u8 sequence, const uuid_t *initiator_uuid, const uuid_t *target_uuid,
+ enum thunderbolt_ip_type type, size_t size, u32 command_id)
+{
+ u32 length_sn;
+
+ /* Length does not include route_hi/lo and length_sn fields */
+ length_sn = (size - 3 * 4) / 4;
+ length_sn |= (sequence << TBIP_HDR_SN_SHIFT) & TBIP_HDR_SN_MASK;
+
+ hdr->route_hi = upper_32_bits(route);
+ hdr->route_lo = lower_32_bits(route);
+ hdr->length_sn = length_sn;
+ uuid_copy(&hdr->uuid, &tbnet_svc_uuid);
+ uuid_copy(&hdr->initiator_uuid, initiator_uuid);
+ uuid_copy(&hdr->target_uuid, target_uuid);
+ hdr->type = type;
+ hdr->command_id = command_id;
+}
+
+static int tbnet_login_response(struct tbnet *net, u64 route, u8 sequence,
+ u32 command_id)
+{
+ struct thunderbolt_ip_login_response reply;
+ struct tb_xdomain *xd = net->xd;
+
+ memset(&reply, 0, sizeof(reply));
+ tbnet_fill_header(&reply.hdr, route, sequence, xd->local_uuid,
+ xd->remote_uuid, TBIP_LOGIN_RESPONSE, sizeof(reply),
+ command_id);
+ memcpy(reply.receiver_mac, net->dev->dev_addr, ETH_ALEN);
+ reply.receiver_mac_len = ETH_ALEN;
+
+ return tb_xdomain_response(xd, &reply, sizeof(reply),
+ TB_CFG_PKG_XDOMAIN_RESP);
+}
+
+static int tbnet_login_request(struct tbnet *net, u8 sequence)
+{
+ struct thunderbolt_ip_login_response reply;
+ struct thunderbolt_ip_login request;
+ struct tb_xdomain *xd = net->xd;
+
+ memset(&request, 0, sizeof(request));
+ tbnet_fill_header(&request.hdr, xd->route, sequence, xd->local_uuid,
+ xd->remote_uuid, TBIP_LOGIN, sizeof(request),
+ atomic_inc_return(&net->command_id));
+
+ request.proto_version = TBIP_LOGIN_PROTO_VERSION;
+ request.transmit_path = TBNET_LOCAL_PATH;
+
+ return tb_xdomain_request(xd, &request, sizeof(request),
+ TB_CFG_PKG_XDOMAIN_RESP, &reply,
+ sizeof(reply), TB_CFG_PKG_XDOMAIN_RESP,
+ TBNET_LOGIN_TIMEOUT);
+}
+
+static int tbnet_logout_response(struct tbnet *net, u64 route, u8 sequence,
+ u32 command_id)
+{
+ struct thunderbolt_ip_status reply;
+ struct tb_xdomain *xd = net->xd;
+
+ memset(&reply, 0, sizeof(reply));
+ tbnet_fill_header(&reply.hdr, route, sequence, xd->local_uuid,
+ xd->remote_uuid, TBIP_STATUS, sizeof(reply),
+ atomic_inc_return(&net->command_id));
+ return tb_xdomain_response(xd, &reply, sizeof(reply),
+ TB_CFG_PKG_XDOMAIN_RESP);
+}
+
+static int tbnet_logout_request(struct tbnet *net)
+{
+ struct thunderbolt_ip_logout request;
+ struct thunderbolt_ip_status reply;
+ struct tb_xdomain *xd = net->xd;
+
+ memset(&request, 0, sizeof(request));
+ tbnet_fill_header(&request.hdr, xd->route, 0, xd->local_uuid,
+ xd->remote_uuid, TBIP_LOGOUT, sizeof(request),
+ atomic_inc_return(&net->command_id));
+
+ return tb_xdomain_request(xd, &request, sizeof(request),
+ TB_CFG_PKG_XDOMAIN_RESP, &reply,
+ sizeof(reply), TB_CFG_PKG_XDOMAIN_RESP,
+ TBNET_LOGOUT_TIMEOUT);
+}
+
+static void start_login(struct tbnet *net)
+{
+ mutex_lock(&net->connection_lock);
+ net->login_sent = false;
+ net->login_received = false;
+ mutex_unlock(&net->connection_lock);
+
+ queue_delayed_work(system_long_wq, &net->login_work,
+ msecs_to_jiffies(1000));
+}
+
+static void stop_login(struct tbnet *net)
+{
+ cancel_delayed_work_sync(&net->login_work);
+ cancel_work_sync(&net->connected_work);
+}
+
+static inline unsigned int tbnet_frame_size(const struct tbnet_frame *tf)
+{
+ return tf->frame.size ? : TBNET_FRAME_SIZE;
+}
+
+static void tbnet_free_buffers(struct tbnet_ring *ring)
+{
+ unsigned int i;
+
+ for (i = 0; i < TBNET_RING_SIZE; i++) {
+ struct device *dma_dev = tb_ring_dma_device(ring->ring);
+ struct tbnet_frame *tf = &ring->frames[i];
+ enum dma_data_direction dir;
+ unsigned int order;
+ size_t size;
+
+ if (!tf->page)
+ continue;
+
+ if (ring->ring->is_tx) {
+ dir = DMA_TO_DEVICE;
+ order = 0;
+ size = tbnet_frame_size(tf);
+ } else {
+ dir = DMA_FROM_DEVICE;
+ order = TBNET_RX_PAGE_ORDER;
+ size = TBNET_RX_PAGE_SIZE;
+ }
+
+ if (tf->frame.buffer_phy)
+ dma_unmap_page(dma_dev, tf->frame.buffer_phy, size,
+ dir);
+
+ __free_pages(tf->page, order);
+ tf->page = NULL;
+ }
+
+ ring->cons = 0;
+ ring->prod = 0;
+}
+
+static void tbnet_tear_down(struct tbnet *net, bool send_logout)
+{
+ netif_carrier_off(net->dev);
+ netif_stop_queue(net->dev);
+
+ stop_login(net);
+
+ mutex_lock(&net->connection_lock);
+
+ if (net->login_sent && net->login_received) {
+ int retries = TBNET_LOGOUT_RETRIES;
+
+ while (send_logout && retries-- > 0) {
+ int ret = tbnet_logout_request(net);
+ if (ret != -ETIMEDOUT)
+ break;
+ }
+
+ tb_ring_stop(net->rx_ring.ring);
+ tb_ring_stop(net->tx_ring.ring);
+ tbnet_free_buffers(&net->rx_ring);
+ tbnet_free_buffers(&net->tx_ring);
+
+ if (tb_xdomain_disable_paths(net->xd))
+ netdev_warn(net->dev, "failed to disable DMA paths\n");
+ }
+
+ net->login_retries = 0;
+ net->login_sent = false;
+ net->login_received = false;
+
+ mutex_unlock(&net->connection_lock);
+}
+
+static int tbnet_handle_packet(const void *buf, size_t size, void *data)
+{
+ const struct thunderbolt_ip_login *pkg = buf;
+ struct tbnet *net = data;
+ u32 command_id;
+ int ret = 0;
+ u8 sequence;
+ u64 route;
+
+ /* Make sure the packet is for us */
+ if (size < sizeof(struct thunderbolt_ip_header))
+ return 0;
+ if (!uuid_equal(&pkg->hdr.initiator_uuid, net->xd->remote_uuid))
+ return 0;
+ if (!uuid_equal(&pkg->hdr.target_uuid, net->xd->local_uuid))
+ return 0;
+
+ route = ((u64)pkg->hdr.route_hi << 32) | pkg->hdr.route_lo;
+ route &= ~BIT_ULL(63);
+ if (route != net->xd->route)
+ return 0;
+
+ sequence = pkg->hdr.length_sn & TBIP_HDR_SN_MASK;
+ sequence >>= TBIP_HDR_SN_SHIFT;
+ command_id = pkg->hdr.command_id;
+
+ switch (pkg->hdr.type) {
+ case TBIP_LOGIN:
+ if (!netif_running(net->dev))
+ break;
+
+ ret = tbnet_login_response(net, route, sequence,
+ pkg->hdr.command_id);
+ if (!ret) {
+ mutex_lock(&net->connection_lock);
+ net->login_received = true;
+ net->transmit_path = pkg->transmit_path;
+
+ /* If we reached the number of max retries or
+ * previous logout, schedule another round of
+ * login retries
+ */
+ if (net->login_retries >= TBNET_LOGIN_RETRIES ||
+ !net->login_sent) {
+ net->login_retries = 0;
+ queue_delayed_work(system_long_wq,
+ &net->login_work, 0);
+ }
+ mutex_unlock(&net->connection_lock);
+
+ queue_work(system_long_wq, &net->connected_work);
+ }
+ break;
+
+ case TBIP_LOGOUT:
+ ret = tbnet_logout_response(net, route, sequence, command_id);
+ if (!ret)
+ tbnet_tear_down(net, false);
+ break;
+
+ default:
+ return 0;
+ }
+
+ if (ret)
+ netdev_warn(net->dev, "failed to send ThunderboltIP response\n");
+
+ return 1;
+}
+
+static unsigned int tbnet_available_buffers(const struct tbnet_ring *ring)
+{
+ return ring->prod - ring->cons;
+}
+
+static int tbnet_alloc_rx_buffers(struct tbnet *net, unsigned int nbuffers)
+{
+ struct tbnet_ring *ring = &net->rx_ring;
+ int ret;
+
+ while (nbuffers--) {
+ struct device *dma_dev = tb_ring_dma_device(ring->ring);
+ unsigned int index = ring->prod & (TBNET_RING_SIZE - 1);
+ struct tbnet_frame *tf = &ring->frames[index];
+ dma_addr_t dma_addr;
+
+ if (tf->page)
+ break;
+
+ /* Allocate page (order > 0) so that it can hold maximum
+ * ThunderboltIP frame (4kB) and the additional room for
+ * SKB shared info required by build_skb().
+ */
+ tf->page = dev_alloc_pages(TBNET_RX_PAGE_ORDER);
+ if (!tf->page) {
+ ret = -ENOMEM;
+ goto err_free;
+ }
+
+ dma_addr = dma_map_page(dma_dev, tf->page, 0,
+ TBNET_RX_PAGE_SIZE, DMA_FROM_DEVICE);
+ if (dma_mapping_error(dma_dev, dma_addr)) {
+ ret = -ENOMEM;
+ goto err_free;
+ }
+
+ tf->frame.buffer_phy = dma_addr;
+ tf->dev = net->dev;
+
+ tb_ring_rx(ring->ring, &tf->frame);
+
+ ring->prod++;
+ }
+
+ return 0;
+
+err_free:
+ tbnet_free_buffers(ring);
+ return ret;
+}
+
+static struct tbnet_frame *tbnet_get_tx_buffer(struct tbnet *net)
+{
+ struct tbnet_ring *ring = &net->tx_ring;
+ struct tbnet_frame *tf;
+ unsigned int index;
+
+ if (!tbnet_available_buffers(ring))
+ return NULL;
+
+ index = ring->cons++ & (TBNET_RING_SIZE - 1);
+
+ tf = &ring->frames[index];
+ tf->frame.size = 0;
+ tf->frame.buffer_phy = 0;
+
+ return tf;
+}
+
+static void tbnet_tx_callback(struct tb_ring *ring, struct ring_frame *frame,
+ bool canceled)
+{
+ struct tbnet_frame *tf = container_of(frame, typeof(*tf), frame);
+ struct device *dma_dev = tb_ring_dma_device(ring);
+ struct tbnet *net = netdev_priv(tf->dev);
+
+ dma_unmap_page(dma_dev, tf->frame.buffer_phy, tbnet_frame_size(tf),
+ DMA_TO_DEVICE);
+
+ /* Return buffer to the ring */
+ net->tx_ring.prod++;
+
+ if (tbnet_available_buffers(&net->tx_ring) >= TBNET_RING_SIZE / 2)
+ netif_wake_queue(net->dev);
+}
+
+static int tbnet_alloc_tx_buffers(struct tbnet *net)
+{
+ struct tbnet_ring *ring = &net->tx_ring;
+ unsigned int i;
+
+ for (i = 0; i < TBNET_RING_SIZE; i++) {
+ struct tbnet_frame *tf = &ring->frames[i];
+
+ tf->page = alloc_page(GFP_KERNEL);
+ if (!tf->page) {
+ tbnet_free_buffers(ring);
+ return -ENOMEM;
+ }
+
+ tf->dev = net->dev;
+ tf->frame.callback = tbnet_tx_callback;
+ tf->frame.sof = TBIP_PDF_FRAME_START;
+ tf->frame.eof = TBIP_PDF_FRAME_END;
+ }
+
+ ring->cons = 0;
+ ring->prod = TBNET_RING_SIZE - 1;
+
+ return 0;
+}
+
+static void tbnet_connected_work(struct work_struct *work)
+{
+ struct tbnet *net = container_of(work, typeof(*net), connected_work);
+ bool connected;
+ int ret;
+
+ if (netif_carrier_ok(net->dev))
+ return;
+
+ mutex_lock(&net->connection_lock);
+ connected = net->login_sent && net->login_received;
+ mutex_unlock(&net->connection_lock);
+
+ if (!connected)
+ return;
+
+ /* Both logins successful so enable the high-speed DMA paths and
+ * start the network device queue.
+ */
+ ret = tb_xdomain_enable_paths(net->xd, TBNET_LOCAL_PATH,
+ net->rx_ring.ring->hop,
+ net->transmit_path,
+ net->tx_ring.ring->hop);
+ if (ret) {
+ netdev_err(net->dev, "failed to enable DMA paths\n");
+ return;
+ }
+
+ tb_ring_start(net->tx_ring.ring);
+ tb_ring_start(net->rx_ring.ring);
+
+ ret = tbnet_alloc_rx_buffers(net, TBNET_RING_SIZE);
+ if (ret)
+ goto err_stop_rings;
+
+ ret = tbnet_alloc_tx_buffers(net);
+ if (ret)
+ goto err_free_rx_buffers;
+
+ netif_carrier_on(net->dev);
+ netif_start_queue(net->dev);
+ return;
+
+err_free_rx_buffers:
+ tbnet_free_buffers(&net->rx_ring);
+err_stop_rings:
+ tb_ring_stop(net->rx_ring.ring);
+ tb_ring_stop(net->tx_ring.ring);
+}
+
+static void tbnet_login_work(struct work_struct *work)
+{
+ struct tbnet *net = container_of(work, typeof(*net), login_work.work);
+ unsigned long delay = msecs_to_jiffies(TBNET_LOGIN_DELAY);
+ int ret;
+
+ if (netif_carrier_ok(net->dev))
+ return;
+
+ ret = tbnet_login_request(net, net->login_retries % 4);
+ if (ret) {
+ if (net->login_retries++ < TBNET_LOGIN_RETRIES) {
+ queue_delayed_work(system_long_wq, &net->login_work,
+ delay);
+ } else {
+ netdev_info(net->dev, "ThunderboltIP login timed out\n");
+ }
+ } else {
+ net->login_retries = 0;
+
+ mutex_lock(&net->connection_lock);
+ net->login_sent = true;
+ mutex_unlock(&net->connection_lock);
+
+ queue_work(system_long_wq, &net->connected_work);
+ }
+}
+
+static bool tbnet_check_frame(struct tbnet *net, const struct tbnet_frame *tf,
+ const struct thunderbolt_ip_frame_header *hdr)
+{
+ u32 frame_id, frame_count, frame_size, frame_index;
+ unsigned int size;
+
+ if (tf->frame.flags & RING_DESC_CRC_ERROR) {
+ net->stats.rx_crc_errors++;
+ return false;
+ } else if (tf->frame.flags & RING_DESC_BUFFER_OVERRUN) {
+ net->stats.rx_over_errors++;
+ return false;
+ }
+
+ /* Should be greater than just header i.e. contains data */
+ size = tbnet_frame_size(tf);
+ if (size <= sizeof(*hdr)) {
+ net->stats.rx_length_errors++;
+ return false;
+ }
+
+ frame_count = le32_to_cpu(hdr->frame_count);
+ frame_size = le32_to_cpu(hdr->frame_size);
+ frame_index = le16_to_cpu(hdr->frame_index);
+ frame_id = le16_to_cpu(hdr->frame_id);
+
+ if ((frame_size > size - sizeof(*hdr)) || !frame_size) {
+ net->stats.rx_length_errors++;
+ return false;
+ }
+
+ /* In case we're in the middle of packet, validate the frame
+ * header based on first fragment of the packet.
+ */
+ if (net->skb && net->rx_hdr.frame_count) {
+ /* Check the frame count fits the count field */
+ if (frame_count != net->rx_hdr.frame_count) {
+ net->stats.rx_length_errors++;
+ return false;
+ }
+
+ /* Check the frame identifiers are incremented correctly,
+ * and id is matching.
+ */
+ if (frame_index != net->rx_hdr.frame_index + 1 ||
+ frame_id != net->rx_hdr.frame_id) {
+ net->stats.rx_missed_errors++;
+ return false;
+ }
+
+ if (net->skb->len + frame_size > TBNET_MAX_MTU) {
+ net->stats.rx_length_errors++;
+ return false;
+ }
+
+ return true;
+ }
+
+ /* Start of packet, validate the frame header */
+ if (frame_count == 0 || frame_count > TBNET_RING_SIZE / 4) {
+ net->stats.rx_length_errors++;
+ return false;
+ }
+ if (frame_index != 0) {
+ net->stats.rx_missed_errors++;
+ return false;
+ }
+
+ return true;
+}
+
+static int tbnet_poll(struct napi_struct *napi, int budget)
+{
+ struct tbnet *net = container_of(napi, struct tbnet, napi);
+ unsigned int cleaned_count = tbnet_available_buffers(&net->rx_ring);
+ struct device *dma_dev = tb_ring_dma_device(net->rx_ring.ring);
+ unsigned int rx_packets = 0;
+
+ while (rx_packets < budget) {
+ const struct thunderbolt_ip_frame_header *hdr;
+ unsigned int hdr_size = sizeof(*hdr);
+ struct sk_buff *skb = NULL;
+ struct ring_frame *frame;
+ struct tbnet_frame *tf;
+ struct page *page;
+ bool last = true;
+ u32 frame_size;
+
+ /* Return some buffers to hardware, one at a time is too
+ * slow so allocate MAX_SKB_FRAGS buffers at the same
+ * time.
+ */
+ if (cleaned_count >= MAX_SKB_FRAGS) {
+ tbnet_alloc_rx_buffers(net, cleaned_count);
+ cleaned_count = 0;
+ }
+
+ frame = tb_ring_poll(net->rx_ring.ring);
+ if (!frame)
+ break;
+
+ dma_unmap_page(dma_dev, frame->buffer_phy,
+ TBNET_RX_PAGE_SIZE, DMA_FROM_DEVICE);
+
+ tf = container_of(frame, typeof(*tf), frame);
+
+ page = tf->page;
+ tf->page = NULL;
+ net->rx_ring.cons++;
+ cleaned_count++;
+
+ hdr = page_address(page);
+ if (!tbnet_check_frame(net, tf, hdr)) {
+ __free_pages(page, TBNET_RX_PAGE_ORDER);
+ dev_kfree_skb_any(net->skb);
+ net->skb = NULL;
+ continue;
+ }
+
+ frame_size = le32_to_cpu(hdr->frame_size);
+
+ skb = net->skb;
+ if (!skb) {
+ skb = build_skb(page_address(page),
+ TBNET_RX_PAGE_SIZE);
+ if (!skb) {
+ __free_pages(page, TBNET_RX_PAGE_ORDER);
+ net->stats.rx_errors++;
+ break;
+ }
+
+ skb_reserve(skb, hdr_size);
+ skb_put(skb, frame_size);
+
+ net->skb = skb;
+ } else {
+ skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+ page, hdr_size, frame_size,
+ TBNET_RX_PAGE_SIZE - hdr_size);
+ }
+
+ net->rx_hdr.frame_size = frame_size;
+ net->rx_hdr.frame_count = le32_to_cpu(hdr->frame_count);
+ net->rx_hdr.frame_index = le16_to_cpu(hdr->frame_index);
+ net->rx_hdr.frame_id = le16_to_cpu(hdr->frame_id);
+ last = net->rx_hdr.frame_index == net->rx_hdr.frame_count - 1;
+
+ rx_packets++;
+ net->stats.rx_bytes += frame_size;
+
+ if (last) {
+ skb->protocol = eth_type_trans(skb, net->dev);
+ napi_gro_receive(&net->napi, skb);
+ net->skb = NULL;
+ }
+ }
+
+ net->stats.rx_packets += rx_packets;
+
+ if (cleaned_count)
+ tbnet_alloc_rx_buffers(net, cleaned_count);
+
+ if (rx_packets >= budget)
+ return budget;
+
+ napi_complete_done(napi, rx_packets);
+ /* Re-enable the ring interrupt */
+ tb_ring_poll_complete(net->rx_ring.ring);
+
+ return rx_packets;
+}
+
+static void tbnet_start_poll(void *data)
+{
+ struct tbnet *net = data;
+
+ napi_schedule(&net->napi);
+}
+
+static int tbnet_open(struct net_device *dev)
+{
+ struct tbnet *net = netdev_priv(dev);
+ struct tb_xdomain *xd = net->xd;
+ u16 sof_mask, eof_mask;
+ struct tb_ring *ring;
+
+ netif_carrier_off(dev);
+
+ ring = tb_ring_alloc_tx(xd->tb->nhi, -1, TBNET_RING_SIZE,
+ RING_FLAG_FRAME);
+ if (!ring) {
+ netdev_err(dev, "failed to allocate Tx ring\n");
+ return -ENOMEM;
+ }
+ net->tx_ring.ring = ring;
+
+ sof_mask = BIT(TBIP_PDF_FRAME_START);
+ eof_mask = BIT(TBIP_PDF_FRAME_END);
+
+ ring = tb_ring_alloc_rx(xd->tb->nhi, -1, TBNET_RING_SIZE,
+ RING_FLAG_FRAME | RING_FLAG_E2E, sof_mask,
+ eof_mask, tbnet_start_poll, net);
+ if (!ring) {
+ netdev_err(dev, "failed to allocate Rx ring\n");
+ tb_ring_free(net->tx_ring.ring);
+ net->tx_ring.ring = NULL;
+ return -ENOMEM;
+ }
+ net->rx_ring.ring = ring;
+
+ napi_enable(&net->napi);
+ start_login(net);
+
+ return 0;
+}
+
+static int tbnet_stop(struct net_device *dev)
+{
+ struct tbnet *net = netdev_priv(dev);
+
+ napi_disable(&net->napi);
+
+ tbnet_tear_down(net, true);
+
+ tb_ring_free(net->rx_ring.ring);
+ net->rx_ring.ring = NULL;
+ tb_ring_free(net->tx_ring.ring);
+ net->tx_ring.ring = NULL;
+
+ return 0;
+}
+
+static bool tbnet_xmit_map(struct device *dma_dev, struct tbnet_frame *tf)
+{
+ dma_addr_t dma_addr;
+
+ dma_addr = dma_map_page(dma_dev, tf->page, 0, tbnet_frame_size(tf),
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(dma_dev, dma_addr))
+ return false;
+
+ tf->frame.buffer_phy = dma_addr;
+ return true;
+}
+
+static bool tbnet_xmit_csum_and_map(struct tbnet *net, struct sk_buff *skb,
+ struct tbnet_frame **frames, u32 frame_count)
+{
+ struct thunderbolt_ip_frame_header *hdr = page_address(frames[0]->page);
+ struct device *dma_dev = tb_ring_dma_device(net->tx_ring.ring);
+ __wsum wsum = htonl(skb->len - skb_transport_offset(skb));
+ unsigned int i, len, offset = skb_transport_offset(skb);
+ __be16 protocol = skb->protocol;
+ void *data = skb->data;
+ void *dest = hdr + 1;
+ __sum16 *tucso;
+
+ if (skb->ip_summed != CHECKSUM_PARTIAL) {
+ /* No need to calculate checksum so we just update the
+ * total frame count and map the frames for DMA.
+ */
+ for (i = 0; i < frame_count; i++) {
+ hdr = page_address(frames[i]->page);
+ hdr->frame_count = cpu_to_le32(frame_count);
+ if (!tbnet_xmit_map(dma_dev, frames[i]))
+ goto err_unmap;
+ }
+
+ return true;
+ }
+
+ if (protocol == htons(ETH_P_8021Q)) {
+ struct vlan_hdr *vhdr, vh;
+
+ vhdr = skb_header_pointer(skb, ETH_HLEN, sizeof(vh), &vh);
+ if (!vhdr)
+ return false;
+
+ protocol = vhdr->h_vlan_encapsulated_proto;
+ }
+
+ /* Data points on the beginning of packet.
+ * Check is the checksum absolute place in the packet.
+ * ipcso will update IP checksum.
+ * tucso will update TCP/UPD checksum.
+ */
+ if (protocol == htons(ETH_P_IP)) {
+ __sum16 *ipcso = dest + ((void *)&(ip_hdr(skb)->check) - data);
+
+ *ipcso = 0;
+ *ipcso = ip_fast_csum(dest + skb_network_offset(skb),
+ ip_hdr(skb)->ihl);
+
+ if (ip_hdr(skb)->protocol == IPPROTO_TCP)
+ tucso = dest + ((void *)&(tcp_hdr(skb)->check) - data);
+ else if (ip_hdr(skb)->protocol == IPPROTO_UDP)
+ tucso = dest + ((void *)&(udp_hdr(skb)->check) - data);
+ else
+ return false;
+
+ *tucso = ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr, 0,
+ ip_hdr(skb)->protocol, 0);
+ } else if (skb_is_gso_v6(skb)) {
+ tucso = dest + ((void *)&(tcp_hdr(skb)->check) - data);
+ *tucso = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+ &ipv6_hdr(skb)->daddr, 0,
+ IPPROTO_TCP, 0);
+ return false;
+ } else if (protocol == htons(ETH_P_IPV6)) {
+ tucso = dest + skb_checksum_start_offset(skb) + skb->csum_offset;
+ *tucso = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+ &ipv6_hdr(skb)->daddr, 0,
+ ipv6_hdr(skb)->nexthdr, 0);
+ } else {
+ return false;
+ }
+
+ /* First frame was headers, rest of the frames contain data.
+ * Calculate checksum over each frame.
+ */
+ for (i = 0; i < frame_count; i++) {
+ hdr = page_address(frames[i]->page);
+ dest = (void *)(hdr + 1) + offset;
+ len = le32_to_cpu(hdr->frame_size) - offset;
+ wsum = csum_partial(dest, len, wsum);
+ hdr->frame_count = cpu_to_le32(frame_count);
+
+ offset = 0;
+ }
+
+ *tucso = csum_fold(wsum);
+
+ /* Checksum is finally calculated and we don't touch the memory
+ * anymore, so DMA map the frames now.
+ */
+ for (i = 0; i < frame_count; i++) {
+ if (!tbnet_xmit_map(dma_dev, frames[i]))
+ goto err_unmap;
+ }
+
+ return true;
+
+err_unmap:
+ while (i--)
+ dma_unmap_page(dma_dev, frames[i]->frame.buffer_phy,
+ tbnet_frame_size(frames[i]), DMA_TO_DEVICE);
+
+ return false;
+}
+
+static void *tbnet_kmap_frag(struct sk_buff *skb, unsigned int frag_num,
+ unsigned int *len)
+{
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[frag_num];
+
+ *len = skb_frag_size(frag);
+ return kmap_atomic(skb_frag_page(frag)) + frag->page_offset;
+}
+
+static netdev_tx_t tbnet_start_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ struct tbnet *net = netdev_priv(dev);
+ struct tbnet_frame *frames[MAX_SKB_FRAGS];
+ u16 frame_id = atomic_read(&net->frame_id);
+ struct thunderbolt_ip_frame_header *hdr;
+ unsigned int len = skb_headlen(skb);
+ unsigned int data_len = skb->len;
+ unsigned int nframes, i;
+ unsigned int frag = 0;
+ void *src = skb->data;
+ u32 frame_index = 0;
+ bool unmap = false;
+ void *dest;
+
+ nframes = DIV_ROUND_UP(data_len, TBNET_MAX_PAYLOAD_SIZE);
+ if (tbnet_available_buffers(&net->tx_ring) < nframes) {
+ netif_stop_queue(net->dev);
+ return NETDEV_TX_BUSY;
+ }
+
+ frames[frame_index] = tbnet_get_tx_buffer(net);
+ if (!frames[frame_index])
+ goto err_drop;
+
+ hdr = page_address(frames[frame_index]->page);
+ dest = hdr + 1;
+
+ /* If overall packet is bigger than the frame data size */
+ while (data_len > TBNET_MAX_PAYLOAD_SIZE) {
+ unsigned int size_left = TBNET_MAX_PAYLOAD_SIZE;
+
+ hdr->frame_size = cpu_to_le32(TBNET_MAX_PAYLOAD_SIZE);
+ hdr->frame_index = cpu_to_le16(frame_index);
+ hdr->frame_id = cpu_to_le16(frame_id);
+
+ do {
+ if (len > size_left) {
+ /* Copy data onto Tx buffer data with
+ * full frame size then break and go to
+ * next frame
+ */
+ memcpy(dest, src, size_left);
+ len -= size_left;
+ dest += size_left;
+ src += size_left;
+ break;
+ }
+
+ memcpy(dest, src, len);
+ size_left -= len;
+ dest += len;
+
+ if (unmap) {
+ kunmap_atomic(src);
+ unmap = false;
+ }
+
+ /* Ensure all fragments have been processed */
+ if (frag < skb_shinfo(skb)->nr_frags) {
+ /* Map and then unmap quickly */
+ src = tbnet_kmap_frag(skb, frag++, &len);
+ unmap = true;
+ } else if (unlikely(size_left > 0)) {
+ goto err_drop;
+ }
+ } while (size_left > 0);
+
+ data_len -= TBNET_MAX_PAYLOAD_SIZE;
+ frame_index++;
+
+ frames[frame_index] = tbnet_get_tx_buffer(net);
+ if (!frames[frame_index])
+ goto err_drop;
+
+ hdr = page_address(frames[frame_index]->page);
+ dest = hdr + 1;
+ }
+
+ hdr->frame_size = cpu_to_le32(data_len);
+ hdr->frame_index = cpu_to_le16(frame_index);
+ hdr->frame_id = cpu_to_le16(frame_id);
+
+ frames[frame_index]->frame.size = data_len + sizeof(*hdr);
+
+ /* In case the remaining data_len is smaller than a frame */
+ while (len < data_len) {
+ memcpy(dest, src, len);
+ data_len -= len;
+ dest += len;
+
+ if (unmap) {
+ kunmap_atomic(src);
+ unmap = false;
+ }
+
+ if (frag < skb_shinfo(skb)->nr_frags) {
+ src = tbnet_kmap_frag(skb, frag++, &len);
+ unmap = true;
+ } else if (unlikely(data_len > 0)) {
+ goto err_drop;
+ }
+ }
+
+ memcpy(dest, src, data_len);
+
+ if (unmap)
+ kunmap_atomic(src);
+
+ if (!tbnet_xmit_csum_and_map(net, skb, frames, frame_index + 1))
+ goto err_drop;
+
+ for (i = 0; i < frame_index + 1; i++)
+ tb_ring_tx(net->tx_ring.ring, &frames[i]->frame);
+
+ if (net->svc->prtcstns & TBNET_MATCH_FRAGS_ID)
+ atomic_inc(&net->frame_id);
+
+ net->stats.tx_packets++;
+ net->stats.tx_bytes += skb->len;
+
+ dev_consume_skb_any(skb);
+
+ return NETDEV_TX_OK;
+
+err_drop:
+ /* We can re-use the buffers */
+ net->tx_ring.cons -= frame_index;
+
+ dev_kfree_skb_any(skb);
+ net->stats.tx_errors++;
+
+ return NETDEV_TX_OK;
+}
+
+static void tbnet_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *stats)
+{
+ struct tbnet *net = netdev_priv(dev);
+
+ stats->tx_packets = net->stats.tx_packets;
+ stats->rx_packets = net->stats.rx_packets;
+ stats->tx_bytes = net->stats.tx_bytes;
+ stats->rx_bytes = net->stats.rx_bytes;
+ stats->rx_errors = net->stats.rx_errors + net->stats.rx_length_errors +
+ net->stats.rx_over_errors + net->stats.rx_crc_errors +
+ net->stats.rx_missed_errors;
+ stats->tx_errors = net->stats.tx_errors;
+ stats->rx_length_errors = net->stats.rx_length_errors;
+ stats->rx_over_errors = net->stats.rx_over_errors;
+ stats->rx_crc_errors = net->stats.rx_crc_errors;
+ stats->rx_missed_errors = net->stats.rx_missed_errors;
+}
+
+static const struct net_device_ops tbnet_netdev_ops = {
+ .ndo_open = tbnet_open,
+ .ndo_stop = tbnet_stop,
+ .ndo_start_xmit = tbnet_start_xmit,
+ .ndo_get_stats64 = tbnet_get_stats64,
+};
+
+static void tbnet_generate_mac(struct net_device *dev)
+{
+ const struct tbnet *net = netdev_priv(dev);
+ const struct tb_xdomain *xd = net->xd;
+ u8 phy_port;
+ u32 hash;
+
+ phy_port = tb_phy_port_from_link(TBNET_L0_PORT_NUM(xd->route));
+
+ /* Unicast and locally administered MAC */
+ dev->dev_addr[0] = phy_port << 4 | 0x02;
+ hash = jhash2((u32 *)xd->local_uuid, 4, 0);
+ memcpy(dev->dev_addr + 1, &hash, sizeof(hash));
+ hash = jhash2((u32 *)xd->local_uuid, 4, hash);
+ dev->dev_addr[5] = hash & 0xff;
+}
+
+static int tbnet_probe(struct tb_service *svc, const struct tb_service_id *id)
+{
+ struct tb_xdomain *xd = tb_service_parent(svc);
+ struct net_device *dev;
+ struct tbnet *net;
+ int ret;
+
+ dev = alloc_etherdev(sizeof(*net));
+ if (!dev)
+ return -ENOMEM;
+
+ SET_NETDEV_DEV(dev, &svc->dev);
+
+ net = netdev_priv(dev);
+ INIT_DELAYED_WORK(&net->login_work, tbnet_login_work);
+ INIT_WORK(&net->connected_work, tbnet_connected_work);
+ mutex_init(&net->connection_lock);
+ atomic_set(&net->command_id, 0);
+ atomic_set(&net->frame_id, 0);
+ net->svc = svc;
+ net->dev = dev;
+ net->xd = xd;
+
+ tbnet_generate_mac(dev);
+
+ strcpy(dev->name, "thunderbolt%d");
+ dev->netdev_ops = &tbnet_netdev_ops;
+
+ /* ThunderboltIP takes advantage of TSO packets but instead of
+ * segmenting them we just split the packet into Thunderbolt
+ * frames (maximum payload size of each frame is 4084 bytes) and
+ * calculate checksum over the whole packet here.
+ *
+ * The receiving side does the opposite if the host OS supports
+ * LRO, otherwise it needs to split the large packet into MTU
+ * sized smaller packets.
+ *
+ * In order to receive large packets from the networking stack,
+ * we need to announce support for most of the offloading
+ * features here.
+ */
+ dev->hw_features = NETIF_F_SG | NETIF_F_ALL_TSO | NETIF_F_GRO |
+ NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+ dev->features = dev->hw_features | NETIF_F_HIGHDMA;
+ dev->hard_header_len += sizeof(struct thunderbolt_ip_frame_header);
+
+ netif_napi_add(dev, &net->napi, tbnet_poll, NAPI_POLL_WEIGHT);
+
+ /* MTU range: 68 - 65522 */
+ dev->min_mtu = ETH_MIN_MTU;
+ dev->max_mtu = TBNET_MAX_MTU - ETH_HLEN;
+
+ net->handler.uuid = &tbnet_svc_uuid;
+ net->handler.callback = tbnet_handle_packet,
+ net->handler.data = net;
+ tb_register_protocol_handler(&net->handler);
+
+ tb_service_set_drvdata(svc, net);
+
+ ret = register_netdev(dev);
+ if (ret) {
+ tb_unregister_protocol_handler(&net->handler);
+ free_netdev(dev);
+ return ret;
+ }
+
+ return 0;
+}
+
+static void tbnet_remove(struct tb_service *svc)
+{
+ struct tbnet *net = tb_service_get_drvdata(svc);
+
+ unregister_netdev(net->dev);
+ tb_unregister_protocol_handler(&net->handler);
+ free_netdev(net->dev);
+}
+
+static void tbnet_shutdown(struct tb_service *svc)
+{
+ tbnet_tear_down(tb_service_get_drvdata(svc), true);
+}
+
+static int __maybe_unused tbnet_suspend(struct device *dev)
+{
+ struct tb_service *svc = tb_to_service(dev);
+ struct tbnet *net = tb_service_get_drvdata(svc);
+
+ stop_login(net);
+ if (netif_running(net->dev)) {
+ netif_device_detach(net->dev);
+ tb_ring_stop(net->rx_ring.ring);
+ tb_ring_stop(net->tx_ring.ring);
+ tbnet_free_buffers(&net->rx_ring);
+ tbnet_free_buffers(&net->tx_ring);
+ }
+
+ return 0;
+}
+
+static int __maybe_unused tbnet_resume(struct device *dev)
+{
+ struct tb_service *svc = tb_to_service(dev);
+ struct tbnet *net = tb_service_get_drvdata(svc);
+
+ netif_carrier_off(net->dev);
+ if (netif_running(net->dev)) {
+ netif_device_attach(net->dev);
+ start_login(net);
+ }
+
+ return 0;
+}
+
+static const struct dev_pm_ops tbnet_pm_ops = {
+ SET_SYSTEM_SLEEP_PM_OPS(tbnet_suspend, tbnet_resume)
+};
+
+static const struct tb_service_id tbnet_ids[] = {
+ { TB_SERVICE("network", 1) },
+ { },
+};
+MODULE_DEVICE_TABLE(tbsvc, tbnet_ids);
+
+static struct tb_service_driver tbnet_driver = {
+ .driver = {
+ .owner = THIS_MODULE,
+ .name = "thunderbolt-net",
+ .pm = &tbnet_pm_ops,
+ },
+ .probe = tbnet_probe,
+ .remove = tbnet_remove,
+ .shutdown = tbnet_shutdown,
+ .id_table = tbnet_ids,
+};
+
+static int __init tbnet_init(void)
+{
+ int ret;
+
+ tbnet_dir = tb_property_create_dir(&tbnet_dir_uuid);
+ if (!tbnet_dir)
+ return -ENOMEM;
+
+ tb_property_add_immediate(tbnet_dir, "prtcid", 1);
+ tb_property_add_immediate(tbnet_dir, "prtcvers", 1);
+ tb_property_add_immediate(tbnet_dir, "prtcrevs", 1);
+ tb_property_add_immediate(tbnet_dir, "prtcstns",
+ TBNET_MATCH_FRAGS_ID);
+
+ ret = tb_register_property_dir("network", tbnet_dir);
+ if (ret) {
+ tb_property_free_dir(tbnet_dir);
+ return ret;
+ }
+
+ return tb_register_service_driver(&tbnet_driver);
+}
+module_init(tbnet_init);
+
+static void __exit tbnet_exit(void)
+{
+ tb_unregister_service_driver(&tbnet_driver);
+ tb_unregister_property_dir("network", tbnet_dir);
+ tb_property_free_dir(tbnet_dir);
+}
+module_exit(tbnet_exit);
+
+MODULE_AUTHOR("Amir Levy <amir.jer.levy@intel.com>");
+MODULE_AUTHOR("Michael Jamet <michael.jamet@intel.com>");
+MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
+MODULE_DESCRIPTION("Thunderbolt network driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 5ce580f413b9..57e4c31fa84a 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -75,6 +75,7 @@
#include <linux/skb_array.h>
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
+#include <linux/mutex.h>
#include <linux/uaccess.h>
@@ -121,7 +122,8 @@ do { \
#define TUN_VNET_BE 0x40000000
#define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \
- IFF_MULTI_QUEUE)
+ IFF_MULTI_QUEUE | IFF_NAPI | IFF_NAPI_FRAGS)
+
#define GOODCOPY_LEN 128
#define FLT_EXACT_COUNT 8
@@ -172,6 +174,8 @@ struct tun_file {
u16 queue_index;
unsigned int ifindex;
};
+ struct napi_struct napi;
+ struct mutex napi_mutex; /* Protects access to the above napi */
struct list_head next;
struct tun_struct *detached;
struct skb_array tx_array;
@@ -229,6 +233,74 @@ struct tun_struct {
struct bpf_prog __rcu *xdp_prog;
};
+static int tun_napi_receive(struct napi_struct *napi, int budget)
+{
+ struct tun_file *tfile = container_of(napi, struct tun_file, napi);
+ struct sk_buff_head *queue = &tfile->sk.sk_write_queue;
+ struct sk_buff_head process_queue;
+ struct sk_buff *skb;
+ int received = 0;
+
+ __skb_queue_head_init(&process_queue);
+
+ spin_lock(&queue->lock);
+ skb_queue_splice_tail_init(queue, &process_queue);
+ spin_unlock(&queue->lock);
+
+ while (received < budget && (skb = __skb_dequeue(&process_queue))) {
+ napi_gro_receive(napi, skb);
+ ++received;
+ }
+
+ if (!skb_queue_empty(&process_queue)) {
+ spin_lock(&queue->lock);
+ skb_queue_splice(&process_queue, queue);
+ spin_unlock(&queue->lock);
+ }
+
+ return received;
+}
+
+static int tun_napi_poll(struct napi_struct *napi, int budget)
+{
+ unsigned int received;
+
+ received = tun_napi_receive(napi, budget);
+
+ if (received < budget)
+ napi_complete_done(napi, received);
+
+ return received;
+}
+
+static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile,
+ bool napi_en)
+{
+ if (napi_en) {
+ netif_napi_add(tun->dev, &tfile->napi, tun_napi_poll,
+ NAPI_POLL_WEIGHT);
+ napi_enable(&tfile->napi);
+ mutex_init(&tfile->napi_mutex);
+ }
+}
+
+static void tun_napi_disable(struct tun_struct *tun, struct tun_file *tfile)
+{
+ if (tun->flags & IFF_NAPI)
+ napi_disable(&tfile->napi);
+}
+
+static void tun_napi_del(struct tun_struct *tun, struct tun_file *tfile)
+{
+ if (tun->flags & IFF_NAPI)
+ netif_napi_del(&tfile->napi);
+}
+
+static bool tun_napi_frags_enabled(const struct tun_struct *tun)
+{
+ return READ_ONCE(tun->flags) & IFF_NAPI_FRAGS;
+}
+
#ifdef CONFIG_TUN_VNET_CROSS_LE
static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
{
@@ -541,6 +613,11 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
tun = rtnl_dereference(tfile->tun);
+ if (tun && clean) {
+ tun_napi_disable(tun, tfile);
+ tun_napi_del(tun, tfile);
+ }
+
if (tun && !tfile->detached) {
u16 index = tfile->queue_index;
BUG_ON(index >= tun->numqueues);
@@ -598,6 +675,7 @@ static void tun_detach_all(struct net_device *dev)
for (i = 0; i < n; i++) {
tfile = rtnl_dereference(tun->tfiles[i]);
BUG_ON(!tfile);
+ tun_napi_disable(tun, tfile);
tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
tfile->socket.sk->sk_data_ready(tfile->socket.sk);
RCU_INIT_POINTER(tfile->tun, NULL);
@@ -613,6 +691,7 @@ static void tun_detach_all(struct net_device *dev)
synchronize_net();
for (i = 0; i < n; i++) {
tfile = rtnl_dereference(tun->tfiles[i]);
+ tun_napi_del(tun, tfile);
/* Drop read queue */
tun_queue_purge(tfile);
sock_put(&tfile->sk);
@@ -631,7 +710,8 @@ static void tun_detach_all(struct net_device *dev)
module_put(THIS_MODULE);
}
-static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter)
+static int tun_attach(struct tun_struct *tun, struct file *file,
+ bool skip_filter, bool napi)
{
struct tun_file *tfile = file->private_data;
struct net_device *dev = tun->dev;
@@ -677,10 +757,12 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
tun->numqueues++;
- if (tfile->detached)
+ if (tfile->detached) {
tun_enable_queue(tfile);
- else
+ } else {
sock_hold(&tfile->sk);
+ tun_napi_init(tun, tfile, napi);
+ }
tun_set_real_num_queues(tun);
@@ -692,7 +774,7 @@ out:
return err;
}
-static struct tun_struct *__tun_get(struct tun_file *tfile)
+static struct tun_struct *tun_get(struct tun_file *tfile)
{
struct tun_struct *tun;
@@ -705,11 +787,6 @@ static struct tun_struct *__tun_get(struct tun_file *tfile)
return tun;
}
-static struct tun_struct *tun_get(struct file *file)
-{
- return __tun_get(file->private_data);
-}
-
static void tun_put(struct tun_struct *tun)
{
dev_put(tun->dev);
@@ -956,13 +1033,32 @@ static void tun_poll_controller(struct net_device *dev)
* Tun only receives frames when:
* 1) the char device endpoint gets data from user space
* 2) the tun socket gets a sendmsg call from user space
- * Since both of those are synchronous operations, we are guaranteed
- * never to have pending data when we poll for it
- * so there is nothing to do here but return.
+ * If NAPI is not enabled, since both of those are synchronous
+ * operations, we are guaranteed never to have pending data when we poll
+ * for it so there is nothing to do here but return.
* We need this though so netpoll recognizes us as an interface that
* supports polling, which enables bridge devices in virt setups to
* still use netconsole
+ * If NAPI is enabled, however, we need to schedule polling for all
+ * queues unless we are using napi_gro_frags(), which we call in
+ * process context and not in NAPI context.
*/
+ struct tun_struct *tun = netdev_priv(dev);
+
+ if (tun->flags & IFF_NAPI) {
+ struct tun_file *tfile;
+ int i;
+
+ if (tun_napi_frags_enabled(tun))
+ return;
+
+ rcu_read_lock();
+ for (i = 0; i < tun->numqueues; i++) {
+ tfile = rcu_dereference(tun->tfiles[i]);
+ napi_schedule(&tfile->napi);
+ }
+ rcu_read_unlock();
+ }
return;
}
#endif
@@ -1149,7 +1245,7 @@ static void tun_net_init(struct net_device *dev)
static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
{
struct tun_file *tfile = file->private_data;
- struct tun_struct *tun = __tun_get(tfile);
+ struct tun_struct *tun = tun_get(tfile);
struct sock *sk;
unsigned int mask = 0;
@@ -1178,6 +1274,64 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
return mask;
}
+static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile,
+ size_t len,
+ const struct iov_iter *it)
+{
+ struct sk_buff *skb;
+ size_t linear;
+ int err;
+ int i;
+
+ if (it->nr_segs > MAX_SKB_FRAGS + 1)
+ return ERR_PTR(-ENOMEM);
+
+ local_bh_disable();
+ skb = napi_get_frags(&tfile->napi);
+ local_bh_enable();
+ if (!skb)
+ return ERR_PTR(-ENOMEM);
+
+ linear = iov_iter_single_seg_count(it);
+ err = __skb_grow(skb, linear);
+ if (err)
+ goto free;
+
+ skb->len = len;
+ skb->data_len = len - linear;
+ skb->truesize += skb->data_len;
+
+ for (i = 1; i < it->nr_segs; i++) {
+ size_t fragsz = it->iov[i].iov_len;
+ unsigned long offset;
+ struct page *page;
+ void *data;
+
+ if (fragsz == 0 || fragsz > PAGE_SIZE) {
+ err = -EINVAL;
+ goto free;
+ }
+
+ local_bh_disable();
+ data = napi_alloc_frag(fragsz);
+ local_bh_enable();
+ if (!data) {
+ err = -ENOMEM;
+ goto free;
+ }
+
+ page = virt_to_head_page(data);
+ offset = data - page_address(page);
+ skb_fill_page_desc(skb, i - 1, page, offset, fragsz);
+ }
+
+ return skb;
+free:
+ /* frees skb and all frags allocated with napi_alloc_frag() */
+ napi_free_frags(&tfile->napi);
+ return ERR_PTR(err);
+}
+
/* prepad is the amount to reserve at front. len is length after that.
* linear is a hint as to how much to copy (usually headers). */
static struct sk_buff *tun_alloc_skb(struct tun_file *tfile,
@@ -1314,6 +1468,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
xdp.data_hard_start = buf;
xdp.data = buf + pad;
+ xdp_set_data_meta_invalid(&xdp);
xdp.data_end = xdp.data + len;
orig_data = xdp.data;
act = bpf_prog_run_xdp(xdp_prog, &xdp);
@@ -1390,6 +1545,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
int err;
u32 rxhash;
int skb_xdp = 1;
+ bool frags = tun_napi_frags_enabled(tun);
if (!(tun->dev->flags & IFF_UP))
return -EIO;
@@ -1447,7 +1603,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
zerocopy = true;
}
- if (tun_can_build_skb(tun, tfile, len, noblock, zerocopy)) {
+ if (!frags && tun_can_build_skb(tun, tfile, len, noblock, zerocopy)) {
/* For the packet that is not easy to be processed
* (e.g gso or jumbo packet), we will do it at after
* skb was created with generic XDP routine.
@@ -1468,10 +1624,24 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
linear = tun16_to_cpu(tun, gso.hdr_len);
}
- skb = tun_alloc_skb(tfile, align, copylen, linear, noblock);
+ if (frags) {
+ mutex_lock(&tfile->napi_mutex);
+ skb = tun_napi_alloc_frags(tfile, copylen, from);
+ /* tun_napi_alloc_frags() enforces a layout for the skb.
+ * If zerocopy is enabled, then this layout will be
+ * overwritten by zerocopy_sg_from_iter().
+ */
+ zerocopy = false;
+ } else {
+ skb = tun_alloc_skb(tfile, align, copylen, linear,
+ noblock);
+ }
+
if (IS_ERR(skb)) {
if (PTR_ERR(skb) != -EAGAIN)
this_cpu_inc(tun->pcpu_stats->rx_dropped);
+ if (frags)
+ mutex_unlock(&tfile->napi_mutex);
return PTR_ERR(skb);
}
@@ -1483,6 +1653,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
if (err) {
this_cpu_inc(tun->pcpu_stats->rx_dropped);
kfree_skb(skb);
+ if (frags) {
+ tfile->napi.skb = NULL;
+ mutex_unlock(&tfile->napi_mutex);
+ }
+
return -EFAULT;
}
}
@@ -1490,6 +1665,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
if (virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun))) {
this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
kfree_skb(skb);
+ if (frags) {
+ tfile->napi.skb = NULL;
+ mutex_unlock(&tfile->napi_mutex);
+ }
+
return -EINVAL;
}
@@ -1517,7 +1697,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
skb->dev = tun->dev;
break;
case IFF_TAP:
- skb->protocol = eth_type_trans(skb, tun->dev);
+ if (!frags)
+ skb->protocol = eth_type_trans(skb, tun->dev);
break;
}
@@ -1551,11 +1732,41 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
}
rxhash = __skb_get_hash_symmetric(skb);
-#ifndef CONFIG_4KSTACKS
- tun_rx_batched(tun, tfile, skb, more);
-#else
- netif_rx_ni(skb);
-#endif
+
+ if (frags) {
+ /* Exercise flow dissector code path. */
+ u32 headlen = eth_get_headlen(skb->data, skb_headlen(skb));
+
+ if (headlen > skb_headlen(skb) || headlen < ETH_HLEN) {
+ this_cpu_inc(tun->pcpu_stats->rx_dropped);
+ napi_free_frags(&tfile->napi);
+ mutex_unlock(&tfile->napi_mutex);
+ WARN_ON(1);
+ return -ENOMEM;
+ }
+
+ local_bh_disable();
+ napi_gro_frags(&tfile->napi);
+ local_bh_enable();
+ mutex_unlock(&tfile->napi_mutex);
+ } else if (tun->flags & IFF_NAPI) {
+ struct sk_buff_head *queue = &tfile->sk.sk_write_queue;
+ int queue_len;
+
+ spin_lock_bh(&queue->lock);
+ __skb_queue_tail(queue, skb);
+ queue_len = skb_queue_len(queue);
+ spin_unlock(&queue->lock);
+
+ if (!more || queue_len > NAPI_POLL_WEIGHT)
+ napi_schedule(&tfile->napi);
+
+ local_bh_enable();
+ } else if (!IS_ENABLED(CONFIG_4KSTACKS)) {
+ tun_rx_batched(tun, tfile, skb, more);
+ } else {
+ netif_rx_ni(skb);
+ }
stats = get_cpu_ptr(tun->pcpu_stats);
u64_stats_update_begin(&stats->syncp);
@@ -1571,8 +1782,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
- struct tun_struct *tun = tun_get(file);
struct tun_file *tfile = file->private_data;
+ struct tun_struct *tun = tun_get(tfile);
ssize_t result;
if (!tun)
@@ -1756,7 +1967,7 @@ static ssize_t tun_chr_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct tun_file *tfile = file->private_data;
- struct tun_struct *tun = __tun_get(tfile);
+ struct tun_struct *tun = tun_get(tfile);
ssize_t len = iov_iter_count(to), ret;
if (!tun)
@@ -1833,7 +2044,7 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
{
int ret;
struct tun_file *tfile = container_of(sock, struct tun_file, socket);
- struct tun_struct *tun = __tun_get(tfile);
+ struct tun_struct *tun = tun_get(tfile);
if (!tun)
return -EBADFD;
@@ -1849,7 +2060,7 @@ static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len,
int flags)
{
struct tun_file *tfile = container_of(sock, struct tun_file, socket);
- struct tun_struct *tun = __tun_get(tfile);
+ struct tun_struct *tun = tun_get(tfile);
int ret;
if (!tun)
@@ -1881,7 +2092,7 @@ static int tun_peek_len(struct socket *sock)
struct tun_struct *tun;
int ret = 0;
- tun = __tun_get(tfile);
+ tun = tun_get(tfile);
if (!tun)
return 0;
@@ -1961,6 +2172,15 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
if (tfile->detached)
return -EINVAL;
+ if ((ifr->ifr_flags & IFF_NAPI_FRAGS)) {
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (!(ifr->ifr_flags & IFF_NAPI) ||
+ (ifr->ifr_flags & TUN_TYPE_MASK) != IFF_TAP)
+ return -EINVAL;
+ }
+
dev = __dev_get_by_name(net, ifr->ifr_name);
if (dev) {
if (ifr->ifr_flags & IFF_TUN_EXCL)
@@ -1982,7 +2202,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
if (err < 0)
return err;
- err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER);
+ err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER,
+ ifr->ifr_flags & IFF_NAPI);
if (err < 0)
return err;
@@ -2068,7 +2289,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
NETIF_F_HW_VLAN_STAG_TX);
INIT_LIST_HEAD(&tun->disabled);
- err = tun_attach(tun, file, false);
+ err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI);
if (err < 0)
goto err_free_flow;
@@ -2218,7 +2439,7 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr)
ret = security_tun_dev_attach_queue(tun->security);
if (ret < 0)
goto unlock;
- ret = tun_attach(tun, file, false);
+ ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI);
} else if (ifr->ifr_flags & IFF_DETACH_QUEUE) {
tun = rtnl_dereference(tfile->tun);
if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached)
@@ -2267,7 +2488,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
ret = 0;
rtnl_lock();
- tun = __tun_get(tfile);
+ tun = tun_get(tfile);
if (cmd == TUNSETIFF) {
ret = -EEXIST;
if (tun)
@@ -2614,15 +2835,16 @@ static int tun_chr_close(struct inode *inode, struct file *file)
}
#ifdef CONFIG_PROC_FS
-static void tun_chr_show_fdinfo(struct seq_file *m, struct file *f)
+static void tun_chr_show_fdinfo(struct seq_file *m, struct file *file)
{
+ struct tun_file *tfile = file->private_data;
struct tun_struct *tun;
struct ifreq ifr;
memset(&ifr, 0, sizeof(ifr));
rtnl_lock();
- tun = tun_get(f);
+ tun = tun_get(tfile);
if (tun)
tun_get_iff(current->nsproxy->net_ns, tun, &ifr);
rtnl_unlock();
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c
index 522d2900cd1d..f4d7362eb325 100644
--- a/drivers/net/usb/asix_common.c
+++ b/drivers/net/usb/asix_common.c
@@ -245,7 +245,7 @@ struct sk_buff *asix_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
* - We are allowed to put 4 bytes at tail if skb_cloned()
* is false (and if we have 4 bytes of tailroom)
*
- * TCP packets for example are cloned, but skb_header_release()
+ * TCP packets for example are cloned, but __skb_header_release()
* was called in tcp stack, allowing us to use headroom for our needs.
*/
if (!skb_header_cloned(skb) &&
diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index dbc90313f472..aeb62e17d19d 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -805,9 +805,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
spin_lock_init(&catc->tx_lock);
spin_lock_init(&catc->ctrl_lock);
- init_timer(&catc->timer);
- catc->timer.data = (long) catc;
- catc->timer.function = catc_stats_timer;
+ setup_timer(&catc->timer, catc_stats_timer, (long)catc);
catc->ctrl_urb = usb_alloc_urb(0, GFP_KERNEL);
catc->tx_urb = usb_alloc_urb(0, GFP_KERNEL);
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 8c3733608271..db7279d5b250 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -221,7 +221,7 @@ static int qmimux_register_device(struct net_device *real_dev, u8 mux_id)
/* Account for reference in struct qmimux_priv_priv */
dev_hold(real_dev);
- err = netdev_upper_dev_link(real_dev, new_dev);
+ err = netdev_upper_dev_link(real_dev, new_dev, NULL);
if (err)
goto out_unregister_netdev;
diff --git a/drivers/net/virtio_net. b/drivers/net/virtio_net.
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/drivers/net/virtio_net.
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 511f8339fa96..fc059f193e7d 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -29,6 +29,7 @@
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/average.h>
+#include <linux/filter.h>
#include <net/route.h>
static int napi_weight = NAPI_POLL_WEIGHT;
@@ -372,9 +373,20 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
return skb;
}
-static bool virtnet_xdp_xmit(struct virtnet_info *vi,
- struct receive_queue *rq,
- struct xdp_buff *xdp)
+static void virtnet_xdp_flush(struct net_device *dev)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ struct send_queue *sq;
+ unsigned int qp;
+
+ qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id();
+ sq = &vi->sq[qp];
+
+ virtqueue_kick(sq->vq);
+}
+
+static bool __virtnet_xdp_xmit(struct virtnet_info *vi,
+ struct xdp_buff *xdp)
{
struct virtio_net_hdr_mrg_rxbuf *hdr;
unsigned int len;
@@ -408,10 +420,19 @@ static bool virtnet_xdp_xmit(struct virtnet_info *vi,
return false;
}
- virtqueue_kick(sq->vq);
return true;
}
+static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ bool sent = __virtnet_xdp_xmit(vi, xdp);
+
+ if (!sent)
+ return -ENOSPC;
+ return 0;
+}
+
static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
{
return vi->xdp_queue_pairs ? VIRTIO_XDP_HEADROOM : 0;
@@ -484,7 +505,8 @@ static struct sk_buff *receive_small(struct net_device *dev,
struct virtnet_info *vi,
struct receive_queue *rq,
void *buf, void *ctx,
- unsigned int len)
+ unsigned int len,
+ bool *xdp_xmit)
{
struct sk_buff *skb;
struct bpf_prog *xdp_prog;
@@ -494,7 +516,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
unsigned int buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
struct page *page = virt_to_head_page(buf);
- unsigned int delta = 0;
+ unsigned int delta = 0, err;
struct page *xdp_page;
len -= vi->hdr_len;
@@ -532,6 +554,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
xdp.data_hard_start = buf + VIRTNET_RX_PAD + vi->hdr_len;
xdp.data = xdp.data_hard_start + xdp_headroom;
+ xdp_set_data_meta_invalid(&xdp);
xdp.data_end = xdp.data + len;
orig_data = xdp.data;
act = bpf_prog_run_xdp(xdp_prog, &xdp);
@@ -542,8 +565,16 @@ static struct sk_buff *receive_small(struct net_device *dev,
delta = orig_data - xdp.data;
break;
case XDP_TX:
- if (unlikely(!virtnet_xdp_xmit(vi, rq, &xdp)))
+ if (unlikely(!__virtnet_xdp_xmit(vi, &xdp)))
trace_xdp_exception(vi->dev, xdp_prog, act);
+ else
+ *xdp_xmit = true;
+ rcu_read_unlock();
+ goto xdp_xmit;
+ case XDP_REDIRECT:
+ err = xdp_do_redirect(dev, &xdp, xdp_prog);
+ if (!err)
+ *xdp_xmit = true;
rcu_read_unlock();
goto xdp_xmit;
default:
@@ -604,7 +635,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
struct receive_queue *rq,
void *buf,
void *ctx,
- unsigned int len)
+ unsigned int len,
+ bool *xdp_xmit)
{
struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
@@ -614,6 +646,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
struct bpf_prog *xdp_prog;
unsigned int truesize;
unsigned int headroom = mergeable_ctx_to_headroom(ctx);
+ int err;
head_skb = NULL;
@@ -654,9 +687,13 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
data = page_address(xdp_page) + offset;
xdp.data_hard_start = data - VIRTIO_XDP_HEADROOM + vi->hdr_len;
xdp.data = data + vi->hdr_len;
+ xdp_set_data_meta_invalid(&xdp);
xdp.data_end = xdp.data + (len - vi->hdr_len);
act = bpf_prog_run_xdp(xdp_prog, &xdp);
+ if (act != XDP_PASS)
+ ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
+
switch (act) {
case XDP_PASS:
/* recalculate offset to account for any header
@@ -672,18 +709,24 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
put_page(page);
head_skb = page_to_skb(vi, rq, xdp_page,
offset, len, PAGE_SIZE);
- ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
return head_skb;
}
break;
case XDP_TX:
- if (unlikely(!virtnet_xdp_xmit(vi, rq, &xdp)))
+ if (unlikely(!__virtnet_xdp_xmit(vi, &xdp)))
trace_xdp_exception(vi->dev, xdp_prog, act);
- ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
+ else
+ *xdp_xmit = true;
if (unlikely(xdp_page != page))
goto err_xdp;
rcu_read_unlock();
goto xdp_xmit;
+ case XDP_REDIRECT:
+ err = xdp_do_redirect(dev, &xdp, xdp_prog);
+ if (!err)
+ *xdp_xmit = true;
+ rcu_read_unlock();
+ goto xdp_xmit;
default:
bpf_warn_invalid_xdp_action(act);
case XDP_ABORTED:
@@ -691,7 +734,6 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
case XDP_DROP:
if (unlikely(xdp_page != page))
__free_pages(xdp_page, 0);
- ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
goto err_xdp;
}
}
@@ -789,7 +831,7 @@ xdp_xmit:
}
static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
- void *buf, unsigned int len, void **ctx)
+ void *buf, unsigned int len, void **ctx, bool *xdp_xmit)
{
struct net_device *dev = vi->dev;
struct sk_buff *skb;
@@ -810,11 +852,11 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
}
if (vi->mergeable_rx_bufs)
- skb = receive_mergeable(dev, vi, rq, buf, ctx, len);
+ skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit);
else if (vi->big_packets)
skb = receive_big(dev, vi, rq, buf, len);
else
- skb = receive_small(dev, vi, rq, buf, ctx, len);
+ skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit);
if (unlikely(!skb))
return 0;
@@ -1072,7 +1114,7 @@ static void refill_work(struct work_struct *work)
}
}
-static int virtnet_receive(struct receive_queue *rq, int budget)
+static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit)
{
struct virtnet_info *vi = rq->vq->vdev->priv;
unsigned int len, received = 0, bytes = 0;
@@ -1084,13 +1126,13 @@ static int virtnet_receive(struct receive_queue *rq, int budget)
while (received < budget &&
(buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
- bytes += receive_buf(vi, rq, buf, len, ctx);
+ bytes += receive_buf(vi, rq, buf, len, ctx, xdp_xmit);
received++;
}
} else {
while (received < budget &&
(buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
- bytes += receive_buf(vi, rq, buf, len, NULL);
+ bytes += receive_buf(vi, rq, buf, len, NULL, xdp_xmit);
received++;
}
}
@@ -1162,15 +1204,19 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
struct receive_queue *rq =
container_of(napi, struct receive_queue, napi);
unsigned int received;
+ bool xdp_xmit = false;
virtnet_poll_cleantx(rq);
- received = virtnet_receive(rq, budget);
+ received = virtnet_receive(rq, budget, &xdp_xmit);
/* Out of packets? */
if (received < budget)
virtqueue_napi_complete(napi, rq->vq, received);
+ if (xdp_xmit)
+ xdp_do_flush_map();
+
return received;
}
@@ -2070,6 +2116,8 @@ static const struct net_device_ops virtnet_netdev = {
.ndo_poll_controller = virtnet_netpoll,
#endif
.ndo_xdp = virtnet_xdp,
+ .ndo_xdp_xmit = virtnet_xdp_xmit,
+ .ndo_xdp_flush = virtnet_xdp_flush,
.ndo_features_check = passthru_features_check,
};
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 9b243e6f3008..0b54f553228e 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -132,7 +132,6 @@ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev,
skb_orphan(skb);
skb_dst_set(skb, dst);
- skb_dst_force(skb);
/* set pkt_type to avoid skb hitting packet taps twice -
* once on Tx and again in Rx processing
@@ -765,18 +764,22 @@ static void cycle_netdev(struct net_device *dev)
}
}
-static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
+static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev,
+ struct netlink_ext_ack *extack)
{
int ret;
/* do not allow loopback device to be enslaved to a VRF.
* The vrf device acts as the loopback for the vrf.
*/
- if (port_dev == dev_net(dev)->loopback_dev)
+ if (port_dev == dev_net(dev)->loopback_dev) {
+ NL_SET_ERR_MSG(extack,
+ "Can not enslave loopback device to a VRF");
return -EOPNOTSUPP;
+ }
port_dev->priv_flags |= IFF_L3MDEV_SLAVE;
- ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL);
+ ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL, extack);
if (ret < 0)
goto err;
@@ -789,12 +792,19 @@ err:
return ret;
}
-static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
+static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev,
+ struct netlink_ext_ack *extack)
{
- if (netif_is_l3_master(port_dev) || netif_is_l3_slave(port_dev))
+ if (netif_is_l3_master(port_dev)) {
+ NL_SET_ERR_MSG(extack,
+ "Can not enslave an L3 master device to a VRF");
+ return -EINVAL;
+ }
+
+ if (netif_is_l3_slave(port_dev))
return -EINVAL;
- return do_vrf_add_slave(dev, port_dev);
+ return do_vrf_add_slave(dev, port_dev, extack);
}
/* inverse of do_vrf_add_slave */
diff --git a/drivers/net/wan/dscc4.c b/drivers/net/wan/dscc4.c
index a043fb1367bd..64f176496da4 100644
--- a/drivers/net/wan/dscc4.c
+++ b/drivers/net/wan/dscc4.c
@@ -1127,10 +1127,8 @@ static int dscc4_open(struct net_device *dev)
done:
netif_start_queue(dev);
- init_timer(&dpriv->timer);
+ setup_timer(&dpriv->timer, dscc4_timer, (unsigned long)dev);
dpriv->timer.expires = jiffies + 10*HZ;
- dpriv->timer.data = (unsigned long)dev;
- dpriv->timer.function = dscc4_timer;
add_timer(&dpriv->timer);
netif_carrier_on(dev);
diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c
index a408abc25512..c696d42f4502 100644
--- a/drivers/net/wan/hdlc_cisco.c
+++ b/drivers/net/wan/hdlc_cisco.c
@@ -293,10 +293,8 @@ static void cisco_start(struct net_device *dev)
st->up = st->txseq = st->rxseq = 0;
spin_unlock_irqrestore(&st->lock, flags);
- init_timer(&st->timer);
+ setup_timer(&st->timer, cisco_timer, (unsigned long)dev);
st->timer.expires = jiffies + HZ; /* First poll after 1 s */
- st->timer.function = cisco_timer;
- st->timer.data = (unsigned long)dev;
add_timer(&st->timer);
}
diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c
index 78596e42a3f3..425a47ffed25 100644
--- a/drivers/net/wan/hdlc_fr.c
+++ b/drivers/net/wan/hdlc_fr.c
@@ -1003,11 +1003,10 @@ static void fr_start(struct net_device *dev)
state(hdlc)->n391cnt = 0;
state(hdlc)->txseq = state(hdlc)->rxseq = 0;
- init_timer(&state(hdlc)->timer);
+ setup_timer(&state(hdlc)->timer, fr_timer,
+ (unsigned long)dev);
/* First poll after 1 s */
state(hdlc)->timer.expires = jiffies + HZ;
- state(hdlc)->timer.function = fr_timer;
- state(hdlc)->timer.data = (unsigned long)dev;
add_timer(&state(hdlc)->timer);
} else
fr_set_link_state(1, dev);
diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c
index 0d2e00ece804..c7721c729541 100644
--- a/drivers/net/wan/hdlc_ppp.c
+++ b/drivers/net/wan/hdlc_ppp.c
@@ -610,9 +610,7 @@ static void ppp_start(struct net_device *dev)
for (i = 0; i < IDX_COUNT; i++) {
struct proto *proto = &ppp->protos[i];
proto->dev = dev;
- init_timer(&proto->timer);
- proto->timer.function = ppp_timer;
- proto->timer.data = (unsigned long)proto;
+ setup_timer(&proto->timer, ppp_timer, (unsigned long)proto);
proto->state = CLOSED;
}
ppp->protos[IDX_LCP].pid = PID_LCP;
diff --git a/drivers/net/wan/lmc/lmc_main.c b/drivers/net/wan/lmc/lmc_main.c
index 4698450c77d1..ae69d65158e6 100644
--- a/drivers/net/wan/lmc/lmc_main.c
+++ b/drivers/net/wan/lmc/lmc_main.c
@@ -1084,10 +1084,8 @@ static int lmc_open(struct net_device *dev)
* Setup a timer for the watchdog on probe, and start it running.
* Since lmc_ok == 0, it will be a NOP for now.
*/
- init_timer (&sc->timer);
+ setup_timer(&sc->timer, lmc_watchdog, (unsigned long)dev);
sc->timer.expires = jiffies + HZ;
- sc->timer.data = (unsigned long) dev;
- sc->timer.function = lmc_watchdog;
add_timer (&sc->timer);
lmc_trace(dev, "lmc_open out");
diff --git a/drivers/net/wan/sdla.c b/drivers/net/wan/sdla.c
index 236c62538036..0cc48902dbb9 100644
--- a/drivers/net/wan/sdla.c
+++ b/drivers/net/wan/sdla.c
@@ -1617,10 +1617,8 @@ static void setup_sdla(struct net_device *dev)
flp->deassoc = sdla_deassoc;
flp->dlci_conf = sdla_dlci_conf;
- init_timer(&flp->timer);
+ setup_timer(&flp->timer, sdla_poll, (unsigned long)dev);
flp->timer.expires = 1;
- flp->timer.data = (unsigned long) dev;
- flp->timer.function = sdla_poll;
}
static struct net_device *sdla;
diff --git a/drivers/net/wireless/ath/ath6kl/txrx.c b/drivers/net/wireless/ath/ath6kl/txrx.c
index e6b2517e6334..4e5cc2b7045a 100644
--- a/drivers/net/wireless/ath/ath6kl/txrx.c
+++ b/drivers/net/wireless/ath/ath6kl/txrx.c
@@ -1753,9 +1753,7 @@ void aggr_conn_init(struct ath6kl_vif *vif, struct aggr_info *aggr_info,
aggr_conn->aggr_sz = AGGR_SZ_DEFAULT;
aggr_conn->dev = vif->ndev;
- init_timer(&aggr_conn->timer);
- aggr_conn->timer.function = aggr_timeout;
- aggr_conn->timer.data = (unsigned long) aggr_conn;
+ setup_timer(&aggr_conn->timer, aggr_timeout, (unsigned long)aggr_conn);
aggr_conn->aggr_info = aggr_info;
aggr_conn->timer_scheduled = false;
diff --git a/drivers/net/wireless/atmel/atmel.c b/drivers/net/wireless/atmel/atmel.c
index b68436b23a63..e816d53c2c05 100644
--- a/drivers/net/wireless/atmel/atmel.c
+++ b/drivers/net/wireless/atmel/atmel.c
@@ -1579,11 +1579,10 @@ struct net_device *init_atmel_card(unsigned short irq, unsigned long port,
priv->default_beacon_period = priv->beacon_period = 100;
priv->listen_interval = 1;
- init_timer(&priv->management_timer);
+ setup_timer(&priv->management_timer, atmel_management_timer,
+ (unsigned long)dev);
spin_lock_init(&priv->irqlock);
spin_lock_init(&priv->timerlock);
- priv->management_timer.function = atmel_management_timer;
- priv->management_timer.data = (unsigned long) dev;
dev->netdev_ops = &atmel_netdev_ops;
dev->wireless_handlers = &atmel_handler_def;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 4157c90ad973..4bfd43a80273 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -3261,9 +3261,8 @@ static void brcmf_init_escan(struct brcmf_cfg80211_info *cfg)
brcmf_cfg80211_escan_handler);
cfg->escan_info.escan_state = WL_ESCAN_STATE_IDLE;
/* Init scan_timeout timer */
- init_timer(&cfg->escan_timeout);
- cfg->escan_timeout.data = (unsigned long) cfg;
- cfg->escan_timeout.function = brcmf_escan_timeout;
+ setup_timer(&cfg->escan_timeout, brcmf_escan_timeout,
+ (unsigned long)cfg);
INIT_WORK(&cfg->escan_timeout_work,
brcmf_cfg80211_escan_timeout_worker);
}
diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c
index 070dfd68bb83..7ad286d6e9a7 100644
--- a/drivers/net/wireless/rsi/rsi_91x_hal.c
+++ b/drivers/net/wireless/rsi/rsi_91x_hal.c
@@ -411,9 +411,8 @@ static void bl_cmd_timeout(unsigned long priv)
static int bl_start_cmd_timer(struct rsi_hw *adapter, u32 timeout)
{
- init_timer(&adapter->bl_cmd_timer);
- adapter->bl_cmd_timer.data = (unsigned long)adapter;
- adapter->bl_cmd_timer.function = (void *)&bl_cmd_timeout;
+ setup_timer(&adapter->bl_cmd_timer, (void *)&bl_cmd_timeout,
+ (unsigned long)adapter);
adapter->bl_cmd_timer.expires = (msecs_to_jiffies(timeout) + jiffies);
adapter->blcmd_timer_expired = false;
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index ee8ed9da00ad..dcfcb153918c 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -520,8 +520,7 @@ int xenvif_init_queue(struct xenvif_queue *queue)
queue->credit_bytes = queue->remaining_credit = ~0UL;
queue->credit_usec = 0UL;
- init_timer(&queue->credit_timeout);
- queue->credit_timeout.function = xenvif_tx_credit_callback;
+ setup_timer(&queue->credit_timeout, xenvif_tx_credit_callback, 0UL);
queue->credit_window_start = get_jiffies_64();
queue->rx_queue_max = XENVIF_RX_QUEUE_BYTES;