From 11380a4b2d86fae9a6bce75c9373668cc323fe57 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 19 Jan 2010 13:46:10 -0800 Subject: net: Unexport napi_gro_flush(). Nothing outside of net/core/dev.c uses it. Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a3fccc85b1a0..468a11dea58c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1527,7 +1527,6 @@ extern int netif_rx(struct sk_buff *skb); extern int netif_rx_ni(struct sk_buff *skb); #define HAVE_NETIF_RECEIVE_SKB 1 extern int netif_receive_skb(struct sk_buff *skb); -extern void napi_gro_flush(struct napi_struct *napi); extern gro_result_t dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb); extern gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb); -- cgit v1.2.3 From a271623f871dda970319ca15dfad3a8c8c36249f Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 22 Jan 2010 10:13:10 +0000 Subject: netdev: remove certain HAVE_ macros After netdev_ops compat code HAVE_* macros aren't needed, in fact they _will_ result in compile breakage for out of tree drivers. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 468a11dea58c..b5fb51d0b8b1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -621,30 +621,21 @@ struct net_device_ops { struct net_device *dev); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb); -#define HAVE_CHANGE_RX_FLAGS void (*ndo_change_rx_flags)(struct net_device *dev, int flags); -#define HAVE_SET_RX_MODE void (*ndo_set_rx_mode)(struct net_device *dev); -#define HAVE_MULTICAST void (*ndo_set_multicast_list)(struct net_device *dev); -#define HAVE_SET_MAC_ADDR int (*ndo_set_mac_address)(struct net_device *dev, void *addr); -#define HAVE_VALIDATE_ADDR int (*ndo_validate_addr)(struct net_device *dev); -#define HAVE_PRIVATE_IOCTL int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); -#define HAVE_SET_CONFIG int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); -#define HAVE_CHANGE_MTU int (*ndo_change_mtu)(struct net_device *dev, int new_mtu); int (*ndo_neigh_setup)(struct net_device *dev, struct neigh_parms *); -#define HAVE_TX_TIMEOUT void (*ndo_tx_timeout) (struct net_device *dev); struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); @@ -656,7 +647,6 @@ struct net_device_ops { void (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid); #ifdef CONFIG_NET_POLL_CONTROLLER -#define HAVE_NETDEV_POLL void (*ndo_poll_controller)(struct net_device *dev); #endif #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) -- cgit v1.2.3 From 32e7bfc41110bc8f29ec0f293c3bcee6645fef34 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 25 Jan 2010 13:36:10 -0800 Subject: net: use helpers to access uc list V2 This patch introduces three macros to work with uc list from net drivers. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/bnx2.c | 5 ++--- drivers/net/e1000/e1000_main.c | 4 ++-- drivers/net/igb/igb_main.c | 7 ++++--- drivers/net/ixgbe/ixgbe_common.c | 7 +++---- drivers/net/ixgbe/ixgbe_common.h | 2 +- drivers/net/ixgbe/ixgbe_main.c | 2 +- drivers/net/ixgbe/ixgbe_type.h | 4 ++-- drivers/net/mv643xx_eth.c | 3 +-- drivers/net/niu.c | 4 ++-- drivers/net/stmmac/dwmac1000_core.c | 10 +++++----- drivers/net/virtio_net.c | 12 +++++++----- drivers/s390/net/qeth_l2_main.c | 2 +- include/linux/netdevice.h | 5 +++++ net/core/dev.c | 4 ++-- 14 files changed, 38 insertions(+), 33 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c index d83512d3e02f..a7b6b12c1c05 100644 --- a/drivers/net/bnx2.c +++ b/drivers/net/bnx2.c @@ -48,7 +48,6 @@ #include #include #include -#include #if defined(CONFIG_CNIC) || defined(CONFIG_CNIC_MODULE) #define BCM_CNIC 1 @@ -3579,14 +3578,14 @@ bnx2_set_rx_mode(struct net_device *dev) sort_mode |= BNX2_RPM_SORT_USER0_MC_HSH_EN; } - if (dev->uc.count > BNX2_MAX_UNICAST_ADDRESSES) { + if (netdev_uc_count(dev) > BNX2_MAX_UNICAST_ADDRESSES) { rx_mode |= BNX2_EMAC_RX_MODE_PROMISCUOUS; sort_mode |= BNX2_RPM_SORT_USER0_PROM_EN | BNX2_RPM_SORT_USER0_PROM_VLAN; } else if (!(dev->flags & IFF_PROMISC)) { /* Add all entries into to the match filter list */ i = 0; - list_for_each_entry(ha, &dev->uc.list, list) { + netdev_for_each_uc_addr(ha, dev) { bnx2_set_mac_addr(bp, ha->addr, i + BNX2_START_UNICAST_ADDRESS_INDEX); sort_mode |= (1 << diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c index 87f575ca427d..2ce88c5f75c5 100644 --- a/drivers/net/e1000/e1000_main.c +++ b/drivers/net/e1000/e1000_main.c @@ -2139,7 +2139,7 @@ static void e1000_set_rx_mode(struct net_device *netdev) rctl |= E1000_RCTL_VFE; } - if (netdev->uc.count > rar_entries - 1) { + if (netdev_uc_count(netdev) > rar_entries - 1) { rctl |= E1000_RCTL_UPE; } else if (!(netdev->flags & IFF_PROMISC)) { rctl &= ~E1000_RCTL_UPE; @@ -2162,7 +2162,7 @@ static void e1000_set_rx_mode(struct net_device *netdev) */ i = 1; if (use_uc) - list_for_each_entry(ha, &netdev->uc.list, list) { + netdev_for_each_uc_addr(ha, netdev) { if (i == rar_entries) break; e1000_rar_set(hw, ha->addr, i++); diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c index d9679493c635..01cc29483e2f 100644 --- a/drivers/net/igb/igb_main.c +++ b/drivers/net/igb/igb_main.c @@ -2905,12 +2905,13 @@ static int igb_write_uc_addr_list(struct net_device *netdev) int count = 0; /* return ENOMEM indicating insufficient memory for addresses */ - if (netdev->uc.count > rar_entries) + if (netdev_uc_count(netdev) > rar_entries) return -ENOMEM; - if (netdev->uc.count && rar_entries) { + if (!netdev_uc_empty(netdev) && rar_entries) { struct netdev_hw_addr *ha; - list_for_each_entry(ha, &netdev->uc.list, list) { + + netdev_for_each_uc_addr(ha, netdev) { if (!rar_entries) break; igb_rar_set_qsel(adapter, ha->addr, diff --git a/drivers/net/ixgbe/ixgbe_common.c b/drivers/net/ixgbe/ixgbe_common.c index 276c2aaa800b..eb49020903c1 100644 --- a/drivers/net/ixgbe/ixgbe_common.c +++ b/drivers/net/ixgbe/ixgbe_common.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include "ixgbe.h" @@ -1347,7 +1346,7 @@ static void ixgbe_add_uc_addr(struct ixgbe_hw *hw, u8 *addr, u32 vmdq) /** * ixgbe_update_uc_addr_list_generic - Updates MAC list of secondary addresses * @hw: pointer to hardware structure - * @uc_list: the list of new addresses + * @netdev: pointer to net device structure * * The given list replaces any existing list. Clears the secondary addrs from * receive address registers. Uses unused receive address registers for the @@ -1357,7 +1356,7 @@ static void ixgbe_add_uc_addr(struct ixgbe_hw *hw, u8 *addr, u32 vmdq) * manually putting the device into promiscuous mode. **/ s32 ixgbe_update_uc_addr_list_generic(struct ixgbe_hw *hw, - struct list_head *uc_list) + struct net_device *netdev) { u32 i; u32 old_promisc_setting = hw->addr_ctrl.overflow_promisc; @@ -1381,7 +1380,7 @@ s32 ixgbe_update_uc_addr_list_generic(struct ixgbe_hw *hw, } /* Add the new addresses */ - list_for_each_entry(ha, uc_list, list) { + netdev_for_each_uc_addr(ha, netdev) { hw_dbg(hw, " Adding the secondary addresses:\n"); ixgbe_add_uc_addr(hw, ha->addr, 0); } diff --git a/drivers/net/ixgbe/ixgbe_common.h b/drivers/net/ixgbe/ixgbe_common.h index dfff0ffaa502..13606d4809c9 100644 --- a/drivers/net/ixgbe/ixgbe_common.h +++ b/drivers/net/ixgbe/ixgbe_common.h @@ -60,7 +60,7 @@ s32 ixgbe_update_mc_addr_list_generic(struct ixgbe_hw *hw, u8 *mc_addr_list, u32 mc_addr_count, ixgbe_mc_addr_itr func); s32 ixgbe_update_uc_addr_list_generic(struct ixgbe_hw *hw, - struct list_head *uc_list); + struct net_device *netdev); s32 ixgbe_enable_mc_generic(struct ixgbe_hw *hw); s32 ixgbe_disable_mc_generic(struct ixgbe_hw *hw); s32 ixgbe_enable_rx_dma_generic(struct ixgbe_hw *hw, u32 regval); diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index ee41d331a35f..439645d2aeef 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -2568,7 +2568,7 @@ void ixgbe_set_rx_mode(struct net_device *netdev) IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); /* reprogram secondary unicast list */ - hw->mac.ops.update_uc_addr_list(hw, &netdev->uc.list); + hw->mac.ops.update_uc_addr_list(hw, netdev); /* reprogram multicast list */ addr_count = netdev->mc_count; diff --git a/drivers/net/ixgbe/ixgbe_type.h b/drivers/net/ixgbe/ixgbe_type.h index b4caa7011a2b..0db67c19b2c4 100644 --- a/drivers/net/ixgbe/ixgbe_type.h +++ b/drivers/net/ixgbe/ixgbe_type.h @@ -30,7 +30,7 @@ #include #include -#include +#include /* Vendor ID */ #define IXGBE_INTEL_VENDOR_ID 0x8086 @@ -2405,7 +2405,7 @@ struct ixgbe_mac_operations { s32 (*set_vmdq)(struct ixgbe_hw *, u32, u32); s32 (*clear_vmdq)(struct ixgbe_hw *, u32, u32); s32 (*init_rx_addrs)(struct ixgbe_hw *); - s32 (*update_uc_addr_list)(struct ixgbe_hw *, struct list_head *); + s32 (*update_uc_addr_list)(struct ixgbe_hw *, struct net_device *); s32 (*update_mc_addr_list)(struct ixgbe_hw *, u8 *, u32, ixgbe_mc_addr_itr); s32 (*enable_mc)(struct ixgbe_hw *); diff --git a/drivers/net/mv643xx_eth.c b/drivers/net/mv643xx_eth.c index af67af55efe7..e24072a9a979 100644 --- a/drivers/net/mv643xx_eth.c +++ b/drivers/net/mv643xx_eth.c @@ -55,7 +55,6 @@ #include #include #include -#include static char mv643xx_eth_driver_name[] = "mv643xx_eth"; static char mv643xx_eth_driver_version[] = "1.4"; @@ -1697,7 +1696,7 @@ static u32 uc_addr_filter_mask(struct net_device *dev) return 0; nibbles = 1 << (dev->dev_addr[5] & 0x0f); - list_for_each_entry(ha, &dev->uc.list, list) { + netdev_for_each_uc_addr(ha, dev) { if (memcmp(dev->dev_addr, ha->addr, 5)) return 0; if ((dev->dev_addr[5] ^ ha->addr[5]) & 0xf0) diff --git a/drivers/net/niu.c b/drivers/net/niu.c index 0e260cfbff7b..af9a8647c7e8 100644 --- a/drivers/net/niu.c +++ b/drivers/net/niu.c @@ -6372,7 +6372,7 @@ static void niu_set_rx_mode(struct net_device *dev) if ((dev->flags & IFF_ALLMULTI) || (dev->mc_count > 0)) np->flags |= NIU_FLAGS_MCAST; - alt_cnt = dev->uc.count; + alt_cnt = netdev_uc_count(dev); if (alt_cnt > niu_num_alt_addr(np)) { alt_cnt = 0; np->flags |= NIU_FLAGS_PROMISC; @@ -6381,7 +6381,7 @@ static void niu_set_rx_mode(struct net_device *dev) if (alt_cnt) { int index = 0; - list_for_each_entry(ha, &dev->uc.list, list) { + netdev_for_each_uc_addr(ha, dev) { err = niu_set_alt_mac(np, index, ha->addr); if (err) printk(KERN_WARNING PFX "%s: Error %d " diff --git a/drivers/net/stmmac/dwmac1000_core.c b/drivers/net/stmmac/dwmac1000_core.c index 928eac05b912..d812e9cdb3db 100644 --- a/drivers/net/stmmac/dwmac1000_core.c +++ b/drivers/net/stmmac/dwmac1000_core.c @@ -83,7 +83,7 @@ static void dwmac1000_set_filter(struct net_device *dev) unsigned int value = 0; DBG(KERN_INFO "%s: # mcasts %d, # unicast %d\n", - __func__, dev->mc_count, dev->uc.count); + __func__, dev->mc_count, netdev_uc_count(dev)); if (dev->flags & IFF_PROMISC) value = GMAC_FRAME_FILTER_PR; @@ -117,7 +117,7 @@ static void dwmac1000_set_filter(struct net_device *dev) } /* Handle multiple unicast addresses (perfect filtering)*/ - if (dev->uc.count > GMAC_MAX_UNICAST_ADDRESSES) + if (netdev_uc_count(dev) > GMAC_MAX_UNICAST_ADDRESSES) /* Switch to promiscuous mode is more than 16 addrs are required */ value |= GMAC_FRAME_FILTER_PR; @@ -125,9 +125,9 @@ static void dwmac1000_set_filter(struct net_device *dev) int reg = 1; struct netdev_hw_addr *ha; - list_for_each_entry(ha, &dev->uc.list, list) { - dwmac1000_set_umac_addr(ioaddr, ha->addr, reg); - reg++; + netdev_for_each_uc_addr(ha, dev) { + dwmac1000_set_umac_addr(ioaddr, ha->addr, reg); + reg++; } } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index c708ecc3cb2e..088332a943f7 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -675,6 +675,7 @@ static void virtnet_set_rx_mode(struct net_device *dev) struct virtio_net_ctrl_mac *mac_data; struct dev_addr_list *addr; struct netdev_hw_addr *ha; + int uc_count; void *buf; int i; @@ -701,8 +702,9 @@ static void virtnet_set_rx_mode(struct net_device *dev) dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n", allmulti ? "en" : "dis"); + uc_count = netdev_uc_count(dev); /* MAC filter - use one buffer for both lists */ - mac_data = buf = kzalloc(((dev->uc.count + dev->mc_count) * ETH_ALEN) + + mac_data = buf = kzalloc(((uc_count + dev->mc_count) * ETH_ALEN) + (2 * sizeof(mac_data->entries)), GFP_ATOMIC); if (!buf) { dev_warn(&dev->dev, "No memory for MAC address buffer\n"); @@ -712,16 +714,16 @@ static void virtnet_set_rx_mode(struct net_device *dev) sg_init_table(sg, 2); /* Store the unicast list and count in the front of the buffer */ - mac_data->entries = dev->uc.count; + mac_data->entries = uc_count; i = 0; - list_for_each_entry(ha, &dev->uc.list, list) + netdev_for_each_uc_addr(ha, dev) memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN); sg_set_buf(&sg[0], mac_data, - sizeof(mac_data->entries) + (dev->uc.count * ETH_ALEN)); + sizeof(mac_data->entries) + (uc_count * ETH_ALEN)); /* multicast list and count fill the end */ - mac_data = (void *)&mac_data->macs[dev->uc.count][0]; + mac_data = (void *)&mac_data->macs[uc_count][0]; mac_data->entries = dev->mc_count; addr = dev->mc_list; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index c3258b0dd649..51fde6f2e0b8 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -622,7 +622,7 @@ static void qeth_l2_set_multicast_list(struct net_device *dev) for (dm = dev->mc_list; dm; dm = dm->next) qeth_l2_add_mc(card, dm->da_addr, 0); - list_for_each_entry(ha, &dev->uc.list, list) + netdev_for_each_uc_addr(ha, dev) qeth_l2_add_mc(card, ha->addr, 1); spin_unlock_bh(&card->mclock); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b5fb51d0b8b1..93a32a5ca74f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -263,6 +263,11 @@ struct netdev_hw_addr_list { int count; }; +#define netdev_uc_count(dev) ((dev)->uc.count) +#define netdev_uc_empty(dev) ((dev)->uc.count == 0) +#define netdev_for_each_uc_addr(ha, dev) \ + list_for_each_entry(ha, &dev->uc.list, list) + struct hh_cache { struct hh_cache *hh_next; /* Next entry */ atomic_t hh_refcnt; /* number of users */ diff --git a/net/core/dev.c b/net/core/dev.c index 4fad9db417b1..2cba5c521e56 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3665,10 +3665,10 @@ void __dev_set_rx_mode(struct net_device *dev) /* Unicast addresses changes may only happen under the rtnl, * therefore calling __dev_set_promiscuity here is safe. */ - if (dev->uc.count > 0 && !dev->uc_promisc) { + if (!netdev_uc_empty(dev) && !dev->uc_promisc) { __dev_set_promiscuity(dev, 1); dev->uc_promisc = 1; - } else if (dev->uc.count == 0 && dev->uc_promisc) { + } else if (netdev_uc_empty(dev) && dev->uc_promisc) { __dev_set_promiscuity(dev, -1); dev->uc_promisc = 0; } -- cgit v1.2.3 From 8a83a00b0735190384a348156837918271034144 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 30 Jan 2010 12:23:03 +0000 Subject: net: maintain namespace isolation between vlan and real device In the vlan and macvlan drivers, the start_xmit function forwards data to the dev_queue_xmit function for another device, which may potentially belong to a different namespace. To make sure that classification stays within a single namespace, this resets the potentially critical fields. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 2 +- include/linux/netdevice.h | 9 +++++++++ net/8021q/vlan_dev.c | 2 +- net/core/dev.c | 35 +++++++++++++++++++++++++++++++---- 4 files changed, 42 insertions(+), 6 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index fa0dc514dbaf..d32e0bdfc5e9 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -269,7 +269,7 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) } xmit_world: - skb->dev = vlan->lowerdev; + skb_set_dev(skb, vlan->lowerdev); return dev_queue_xmit(skb); } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 93a32a5ca74f..622ba5aa93c4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1004,6 +1004,15 @@ static inline bool netdev_uses_dsa_tags(struct net_device *dev) return 0; } +#ifndef CONFIG_NET_NS +static inline void skb_set_dev(struct sk_buff *skb, struct net_device *dev) +{ + skb->dev = dev; +} +#else /* CONFIG_NET_NS */ +void skb_set_dev(struct sk_buff *skb, struct net_device *dev); +#endif + static inline bool netdev_uses_trailer_tags(struct net_device *dev) { #ifdef CONFIG_NET_DSA_TAG_TRAILER diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index a9e1f1785614..9e83272fc5b0 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -322,7 +322,7 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, } - skb->dev = vlan_dev_info(dev)->real_dev; + skb_set_dev(skb, vlan_dev_info(dev)->real_dev); len = skb->len; ret = dev_queue_xmit(skb); diff --git a/net/core/dev.c b/net/core/dev.c index 2cba5c521e56..94c1eeed25e5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1448,13 +1448,10 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) if (skb->len > (dev->mtu + dev->hard_header_len)) return NET_RX_DROP; - skb_dst_drop(skb); + skb_set_dev(skb, dev); skb->tstamp.tv64 = 0; skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, dev); - skb->mark = 0; - secpath_reset(skb); - nf_reset(skb); return netif_rx(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb); @@ -1614,6 +1611,36 @@ static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb) return false; } +/** + * skb_dev_set -- assign a new device to a buffer + * @skb: buffer for the new device + * @dev: network device + * + * If an skb is owned by a device already, we have to reset + * all data private to the namespace a device belongs to + * before assigning it a new device. + */ +#ifdef CONFIG_NET_NS +void skb_set_dev(struct sk_buff *skb, struct net_device *dev) +{ + skb_dst_drop(skb); + if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) { + secpath_reset(skb); + nf_reset(skb); + skb_init_secmark(skb); + skb->mark = 0; + skb->priority = 0; + skb->nf_trace = 0; + skb->ipvs_property = 0; +#ifdef CONFIG_NET_SCHED + skb->tc_index = 0; +#endif + } + skb->dev = dev; +} +EXPORT_SYMBOL(skb_set_dev); +#endif /* CONFIG_NET_NS */ + /* * Invalidate hardware checksum when packet is to be mangled, and * complete checksum manually on outgoing path. -- cgit v1.2.3 From 6683ece36e3531fc8c75f69e7165c5f20930be88 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 4 Feb 2010 10:22:25 -0800 Subject: net: use helpers to access mc list V2 This patch introduces the similar helpers as those already done for uc list. However multicast lists are no list_head lists but "mademanually". The three macros added by this patch will make the transition of mc_list to list_head smooth in two steps: 1) convert all drivers to use these macros (with the original iterator of type "struct dev_mc_list") 2) once all drivers are converted, convert list type and iterators to "struct netdev_hw_addr" in one patch. >From now on, drivers can (and should) use "netdev_for_each_mc_addr" to iterate over the addresses with iterator of type "struct netdev_hw_addr". Also macros "netdev_mc_count" and "netdev_mc_empty" to read list's length. This is the state which should be reached in all drivers. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 622ba5aa93c4..e535700a3b72 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -268,6 +268,12 @@ struct netdev_hw_addr_list { #define netdev_for_each_uc_addr(ha, dev) \ list_for_each_entry(ha, &dev->uc.list, list) +#define netdev_mc_count(dev) ((dev)->mc_count) +#define netdev_mc_empty(dev) (netdev_mc_count(dev) == 0) + +#define netdev_for_each_mc_addr(mclist, dev) \ + for (mclist = dev->mc_list; mclist; mclist = mclist->next) + struct hh_cache { struct hh_cache *hh_next; /* Next entry */ atomic_t hh_refcnt; /* number of users */ -- cgit v1.2.3 From 15682bc488d4af8c9bb998844a94281025e0a333 Mon Sep 17 00:00:00 2001 From: Peter P Waskiewicz Jr Date: Wed, 10 Feb 2010 20:03:05 -0800 Subject: ethtool: Introduce n-tuple filter programming support This patchset enables the ethtool layer to program n-tuple filters to an underlying device. The idea is to allow capable hardware to have static rules applied that can assist steering flows into appropriate queues. Hardware that is known to support these types of filters today are ixgbe and niu. Signed-off-by: Peter P Waskiewicz Jr Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/ethtool.h | 50 +++++++ include/linux/netdevice.h | 3 + net/core/dev.c | 5 + net/core/ethtool.c | 329 +++++++++++++++++++++++++++++++++++++++++++++- 4 files changed, 386 insertions(+), 1 deletion(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index ef4a2d84d922..a3cac53a0766 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -14,6 +14,7 @@ #define _LINUX_ETHTOOL_H #include +#include /* This should work for both 32 and 64 bit userland. */ struct ethtool_cmd { @@ -242,6 +243,7 @@ enum ethtool_stringset { ETH_SS_TEST = 0, ETH_SS_STATS, ETH_SS_PRIV_FLAGS, + ETH_SS_NTUPLE_FILTERS, }; /* for passing string sets for data tagging */ @@ -290,6 +292,7 @@ struct ethtool_perm_addr { */ enum ethtool_flags { ETH_FLAG_LRO = (1 << 15), /* LRO is enabled */ + ETH_FLAG_NTUPLE = (1 << 27), /* N-tuple filters enabled */ }; /* The following structures are for supporting RX network flow @@ -363,6 +366,35 @@ struct ethtool_rxnfc { __u32 rule_locs[0]; }; +struct ethtool_rx_ntuple_flow_spec { + __u32 flow_type; + union { + struct ethtool_tcpip4_spec tcp_ip4_spec; + struct ethtool_tcpip4_spec udp_ip4_spec; + struct ethtool_tcpip4_spec sctp_ip4_spec; + struct ethtool_ah_espip4_spec ah_ip4_spec; + struct ethtool_ah_espip4_spec esp_ip4_spec; + struct ethtool_rawip4_spec raw_ip4_spec; + struct ethtool_ether_spec ether_spec; + struct ethtool_usrip4_spec usr_ip4_spec; + __u8 hdata[64]; + } h_u, m_u; /* entry, mask */ + + __u16 vlan_tag; + __u16 vlan_tag_mask; + __u64 data; /* user-defined flow spec data */ + __u64 data_mask; /* user-defined flow spec mask */ + + /* signed to distinguish between queue and actions (DROP) */ + __s32 action; +#define ETHTOOL_RXNTUPLE_ACTION_DROP -1 +}; + +struct ethtool_rx_ntuple { + __u32 cmd; + struct ethtool_rx_ntuple_flow_spec fs; +}; + #define ETHTOOL_FLASH_MAX_FILENAME 128 enum ethtool_flash_op_type { ETHTOOL_FLASH_ALL_REGIONS = 0, @@ -377,6 +409,18 @@ struct ethtool_flash { #ifdef __KERNEL__ +struct ethtool_rx_ntuple_flow_spec_container { + struct ethtool_rx_ntuple_flow_spec fs; + struct list_head list; +}; + +struct ethtool_rx_ntuple_list { +#define ETHTOOL_MAX_NTUPLE_LIST_ENTRY 1024 +#define ETHTOOL_MAX_NTUPLE_STRING_PER_ENTRY 14 + struct list_head list; + unsigned int count; +}; + struct net_device; /* Some generic methods drivers may use in their ethtool_ops */ @@ -394,6 +438,7 @@ u32 ethtool_op_get_ufo(struct net_device *dev); int ethtool_op_set_ufo(struct net_device *dev, u32 data); u32 ethtool_op_get_flags(struct net_device *dev); int ethtool_op_set_flags(struct net_device *dev, u32 data); +void ethtool_ntuple_flush(struct net_device *dev); /** * ðtool_ops - Alter and report network device settings @@ -500,6 +545,8 @@ struct ethtool_ops { int (*set_rxnfc)(struct net_device *, struct ethtool_rxnfc *); int (*flash_device)(struct net_device *, struct ethtool_flash *); int (*reset)(struct net_device *, u32 *); + int (*set_rx_ntuple)(struct net_device *, struct ethtool_rx_ntuple *); + int (*get_rx_ntuple)(struct net_device *, u32 stringset, void *); }; #endif /* __KERNEL__ */ @@ -559,6 +606,9 @@ struct ethtool_ops { #define ETHTOOL_FLASHDEV 0x00000033 /* Flash firmware to device */ #define ETHTOOL_RESET 0x00000034 /* Reset hardware */ +#define ETHTOOL_SRXNTUPLE 0x00000035 /* Add an n-tuple filter to device */ +#define ETHTOOL_GRXNTUPLE 0x00000036 /* Get n-tuple filters from device */ + /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET #define SPARC_ETH_SSET ETHTOOL_SSET diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e535700a3b72..cdf53a8d9ff5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -746,6 +746,7 @@ struct net_device { #define NETIF_F_FCOE_CRC (1 << 24) /* FCoE CRC32 */ #define NETIF_F_SCTP_CSUM (1 << 25) /* SCTP checksum offload */ #define NETIF_F_FCOE_MTU (1 << 26) /* Supports max FCoE MTU, 2158 bytes*/ +#define NETIF_F_NTUPLE (1 << 27) /* N-tuple filters supported */ /* Segmentation offload features */ #define NETIF_F_GSO_SHIFT 16 @@ -954,6 +955,8 @@ struct net_device { /* max exchange id for FCoE LRO by ddp */ unsigned int fcoe_ddp_xid; #endif + /* n-tuple filter list attached to this device */ + struct ethtool_rx_ntuple_list ethtool_ntuple_list; }; #define to_net_dev(d) container_of(d, struct net_device, dev) diff --git a/net/core/dev.c b/net/core/dev.c index 94c1eeed25e5..ae75f25ac0a5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5419,6 +5419,8 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, netdev_init_queues(dev); + INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list); + dev->ethtool_ntuple_list.count = 0; INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); INIT_LIST_HEAD(&dev->link_watch_list); @@ -5455,6 +5457,9 @@ void free_netdev(struct net_device *dev) /* Flush device addresses */ dev_addr_flush(dev); + /* Clear ethtool n-tuple list */ + ethtool_ntuple_flush(dev); + list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index d8aee584e8d1..6ec73d3983a3 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -120,7 +120,7 @@ int ethtool_op_set_ufo(struct net_device *dev, u32 data) * NETIF_F_xxx values in include/linux/netdevice.h */ static const u32 flags_dup_features = - ETH_FLAG_LRO; + (ETH_FLAG_LRO | ETH_FLAG_NTUPLE); u32 ethtool_op_get_flags(struct net_device *dev) { @@ -139,9 +139,26 @@ int ethtool_op_set_flags(struct net_device *dev, u32 data) else dev->features &= ~NETIF_F_LRO; + if (data & ETH_FLAG_NTUPLE) + dev->features |= NETIF_F_NTUPLE; + else + dev->features &= ~NETIF_F_NTUPLE; + return 0; } +void ethtool_ntuple_flush(struct net_device *dev) +{ + struct ethtool_rx_ntuple_flow_spec_container *fsc, *f; + + list_for_each_entry_safe(fsc, f, &dev->ethtool_ntuple_list.list, list) { + list_del(&fsc->list); + kfree(fsc); + } + dev->ethtool_ntuple_list.count = 0; +} +EXPORT_SYMBOL(ethtool_ntuple_flush); + /* Handlers for each ethtool command */ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) @@ -266,6 +283,307 @@ err_out: return ret; } +static int __rx_ntuple_filter_add(struct ethtool_rx_ntuple_list *list, + struct ethtool_rx_ntuple_flow_spec *spec) +{ + struct ethtool_rx_ntuple_flow_spec_container *fsc; + + /* don't add filters forever */ + if (list->count >= ETHTOOL_MAX_NTUPLE_LIST_ENTRY) + return 0; + + fsc = kmalloc(sizeof(*fsc), GFP_ATOMIC); + if (!fsc) + return -ENOMEM; + + /* Copy the whole filter over */ + fsc->fs.flow_type = spec->flow_type; + memcpy(&fsc->fs.h_u, &spec->h_u, sizeof(spec->h_u)); + memcpy(&fsc->fs.m_u, &spec->m_u, sizeof(spec->m_u)); + + fsc->fs.vlan_tag = spec->vlan_tag; + fsc->fs.vlan_tag_mask = spec->vlan_tag_mask; + fsc->fs.data = spec->data; + fsc->fs.data_mask = spec->data_mask; + fsc->fs.action = spec->action; + + /* add to the list */ + list_add_tail_rcu(&fsc->list, &list->list); + list->count++; + + return 0; +} + +static int ethtool_set_rx_ntuple(struct net_device *dev, void __user *useraddr) +{ + struct ethtool_rx_ntuple cmd; + const struct ethtool_ops *ops = dev->ethtool_ops; + int ret; + + if (!ops->set_rx_ntuple) + return -EOPNOTSUPP; + + if (!(dev->features & NETIF_F_NTUPLE)) + return -EINVAL; + + if (copy_from_user(&cmd, useraddr, sizeof(cmd))) + return -EFAULT; + + ret = ops->set_rx_ntuple(dev, &cmd); + + /* + * Cache filter in dev struct for GET operation only if + * the underlying driver doesn't have its own GET operation, and + * only if the filter was added successfully. + */ + if (!ops->get_rx_ntuple && !ret) + if (__rx_ntuple_filter_add(&dev->ethtool_ntuple_list, &cmd.fs)) + return -ENOMEM; + + return ret; +} + +static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr) +{ + struct ethtool_gstrings gstrings; + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_rx_ntuple_flow_spec_container *fsc; + u8 *data; + char *p; + int ret, i, num_strings = 0; + + if (!ops->get_sset_count) + return -EOPNOTSUPP; + + if (copy_from_user(&gstrings, useraddr, sizeof(gstrings))) + return -EFAULT; + + ret = ops->get_sset_count(dev, gstrings.string_set); + if (ret < 0) + return ret; + + gstrings.len = ret; + + data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); + if (!data) + return -ENOMEM; + + if (ops->get_rx_ntuple) { + /* driver-specific filter grab */ + ret = ops->get_rx_ntuple(dev, gstrings.string_set, data); + goto copy; + } + + /* default ethtool filter grab */ + i = 0; + p = (char *)data; + list_for_each_entry(fsc, &dev->ethtool_ntuple_list.list, list) { + sprintf(p, "Filter %d:\n", i); + p += ETH_GSTRING_LEN; + num_strings++; + + switch (fsc->fs.flow_type) { + case TCP_V4_FLOW: + sprintf(p, "\tFlow Type: TCP\n"); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case UDP_V4_FLOW: + sprintf(p, "\tFlow Type: UDP\n"); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case SCTP_V4_FLOW: + sprintf(p, "\tFlow Type: SCTP\n"); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case AH_ESP_V4_FLOW: + sprintf(p, "\tFlow Type: AH ESP\n"); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case ESP_V4_FLOW: + sprintf(p, "\tFlow Type: ESP\n"); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case IP_USER_FLOW: + sprintf(p, "\tFlow Type: Raw IP\n"); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case IPV4_FLOW: + sprintf(p, "\tFlow Type: IPv4\n"); + p += ETH_GSTRING_LEN; + num_strings++; + break; + default: + sprintf(p, "\tFlow Type: Unknown\n"); + p += ETH_GSTRING_LEN; + num_strings++; + goto unknown_filter; + }; + + /* now the rest of the filters */ + switch (fsc->fs.flow_type) { + case TCP_V4_FLOW: + case UDP_V4_FLOW: + case SCTP_V4_FLOW: + sprintf(p, "\tSrc IP addr: 0x%x\n", + fsc->fs.h_u.tcp_ip4_spec.ip4src); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tSrc IP mask: 0x%x\n", + fsc->fs.m_u.tcp_ip4_spec.ip4src); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tDest IP addr: 0x%x\n", + fsc->fs.h_u.tcp_ip4_spec.ip4dst); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tDest IP mask: 0x%x\n", + fsc->fs.m_u.tcp_ip4_spec.ip4dst); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tSrc Port: %d, mask: 0x%x\n", + fsc->fs.h_u.tcp_ip4_spec.psrc, + fsc->fs.m_u.tcp_ip4_spec.psrc); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tDest Port: %d, mask: 0x%x\n", + fsc->fs.h_u.tcp_ip4_spec.pdst, + fsc->fs.m_u.tcp_ip4_spec.pdst); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tTOS: %d, mask: 0x%x\n", + fsc->fs.h_u.tcp_ip4_spec.tos, + fsc->fs.m_u.tcp_ip4_spec.tos); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case AH_ESP_V4_FLOW: + case ESP_V4_FLOW: + sprintf(p, "\tSrc IP addr: 0x%x\n", + fsc->fs.h_u.ah_ip4_spec.ip4src); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tSrc IP mask: 0x%x\n", + fsc->fs.m_u.ah_ip4_spec.ip4src); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tDest IP addr: 0x%x\n", + fsc->fs.h_u.ah_ip4_spec.ip4dst); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tDest IP mask: 0x%x\n", + fsc->fs.m_u.ah_ip4_spec.ip4dst); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tSPI: %d, mask: 0x%x\n", + fsc->fs.h_u.ah_ip4_spec.spi, + fsc->fs.m_u.ah_ip4_spec.spi); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tTOS: %d, mask: 0x%x\n", + fsc->fs.h_u.ah_ip4_spec.tos, + fsc->fs.m_u.ah_ip4_spec.tos); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case IP_USER_FLOW: + sprintf(p, "\tSrc IP addr: 0x%x\n", + fsc->fs.h_u.raw_ip4_spec.ip4src); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tSrc IP mask: 0x%x\n", + fsc->fs.m_u.raw_ip4_spec.ip4src); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tDest IP addr: 0x%x\n", + fsc->fs.h_u.raw_ip4_spec.ip4dst); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tDest IP mask: 0x%x\n", + fsc->fs.m_u.raw_ip4_spec.ip4dst); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case IPV4_FLOW: + sprintf(p, "\tSrc IP addr: 0x%x\n", + fsc->fs.h_u.usr_ip4_spec.ip4src); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tSrc IP mask: 0x%x\n", + fsc->fs.m_u.usr_ip4_spec.ip4src); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tDest IP addr: 0x%x\n", + fsc->fs.h_u.usr_ip4_spec.ip4dst); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tDest IP mask: 0x%x\n", + fsc->fs.m_u.usr_ip4_spec.ip4dst); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tL4 bytes: 0x%x, mask: 0x%x\n", + fsc->fs.h_u.usr_ip4_spec.l4_4_bytes, + fsc->fs.m_u.usr_ip4_spec.l4_4_bytes); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tTOS: %d, mask: 0x%x\n", + fsc->fs.h_u.usr_ip4_spec.tos, + fsc->fs.m_u.usr_ip4_spec.tos); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tIP Version: %d, mask: 0x%x\n", + fsc->fs.h_u.usr_ip4_spec.ip_ver, + fsc->fs.m_u.usr_ip4_spec.ip_ver); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tProtocol: %d, mask: 0x%x\n", + fsc->fs.h_u.usr_ip4_spec.proto, + fsc->fs.m_u.usr_ip4_spec.proto); + p += ETH_GSTRING_LEN; + num_strings++; + break; + }; + sprintf(p, "\tVLAN: %d, mask: 0x%x\n", + fsc->fs.vlan_tag, fsc->fs.vlan_tag_mask); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tUser-defined: 0x%Lx\n", fsc->fs.data); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tUser-defined mask: 0x%Lx\n", fsc->fs.data_mask); + p += ETH_GSTRING_LEN; + num_strings++; + if (fsc->fs.action == ETHTOOL_RXNTUPLE_ACTION_DROP) + sprintf(p, "\tAction: Drop\n"); + else + sprintf(p, "\tAction: Direct to queue %d\n", + fsc->fs.action); + p += ETH_GSTRING_LEN; + num_strings++; +unknown_filter: + i++; + } +copy: + /* indicate to userspace how many strings we actually have */ + gstrings.len = num_strings; + ret = -EFAULT; + if (copy_to_user(useraddr, &gstrings, sizeof(gstrings))) + goto out; + useraddr += sizeof(gstrings); + if (copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN)) + goto out; + ret = 0; + +out: + kfree(data); + return ret; +} + static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) { struct ethtool_regs regs; @@ -313,6 +631,9 @@ static int ethtool_reset(struct net_device *dev, char __user *useraddr) if (copy_from_user(&reset, useraddr, sizeof(reset))) return -EFAULT; + /* Clear ethtool n-tuple list */ + ethtool_ntuple_flush(dev); + ret = dev->ethtool_ops->reset(dev, &reset.data); if (ret) return ret; @@ -1112,6 +1433,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_RESET: rc = ethtool_reset(dev, useraddr); break; + case ETHTOOL_SRXNTUPLE: + rc = ethtool_set_rx_ntuple(dev, useraddr); + break; + case ETHTOOL_GRXNTUPLE: + rc = ethtool_get_rx_ntuple(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } -- cgit v1.2.3 From 571ba42303813106d533bf6bda929d8e289f51bf Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 9 Feb 2010 11:49:47 +0000 Subject: netdevice.h: Add netdev_printk helpers like dev_printk These netdev_printk routines take a struct net_device * and emit dev_printk logging messages adding "%s: " ... netdev->dev.parent to the dev_printk format and arguments. This can create some uniformity in the output message log. These helpers should not be used until a successful alloc_netdev. Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/netdevice.h | 71 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 71 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cdf53a8d9ff5..a51228ac9331 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2095,6 +2095,77 @@ static inline u32 dev_ethtool_get_flags(struct net_device *dev) return 0; return dev->ethtool_ops->get_flags(dev); } + +/* Logging, debugging and troubleshooting/diagnostic helpers. */ + +/* netdev_printk helpers, similar to dev_printk */ + +static inline const char *netdev_name(const struct net_device *dev) +{ + if (dev->reg_state != NETREG_REGISTERED) + return "(unregistered net_device)"; + return dev->name; +} + +#define netdev_printk(level, netdev, format, args...) \ + dev_printk(level, (netdev)->dev.parent, \ + "%s: " format, \ + netdev_name(netdev), ##args) + +#define netdev_emerg(dev, format, args...) \ + netdev_printk(KERN_EMERG, dev, format, ##args) +#define netdev_alert(dev, format, args...) \ + netdev_printk(KERN_ALERT, dev, format, ##args) +#define netdev_crit(dev, format, args...) \ + netdev_printk(KERN_CRIT, dev, format, ##args) +#define netdev_err(dev, format, args...) \ + netdev_printk(KERN_ERR, dev, format, ##args) +#define netdev_warn(dev, format, args...) \ + netdev_printk(KERN_WARNING, dev, format, ##args) +#define netdev_notice(dev, format, args...) \ + netdev_printk(KERN_NOTICE, dev, format, ##args) +#define netdev_info(dev, format, args...) \ + netdev_printk(KERN_INFO, dev, format, ##args) + +#if defined(DEBUG) +#define netdev_dbg(__dev, format, args...) \ + netdev_printk(KERN_DEBUG, __dev, format, ##args) +#elif defined(CONFIG_DYNAMIC_DEBUG) +#define netdev_dbg(__dev, format, args...) \ +do { \ + dynamic_dev_dbg((__dev)->dev.parent, "%s: " format, \ + netdev_name(__dev), ##args); \ +} while (0) +#else +#define netdev_dbg(__dev, format, args...) \ +({ \ + if (0) \ + netdev_printk(KERN_DEBUG, __dev, format, ##args); \ + 0; \ +}) +#endif + +#if defined(VERBOSE_DEBUG) +#define netdev_vdbg netdev_dbg +#else + +#define netdev_vdbg(dev, format, args...) \ +({ \ + if (0) \ + netdev_printk(KERN_DEBUG, dev, format, ##args); \ + 0; \ +}) +#endif + +/* + * netdev_WARN() acts like dev_printk(), but with the key difference + * of using a WARN/WARN_ON to get the message out, including the + * file/line information and a backtrace. + */ +#define netdev_WARN(dev, format, args...) \ + WARN(1, "netdevice: %s\n" format, netdev_name(dev), ##args); + + #endif /* __KERNEL__ */ #endif /* _LINUX_NETDEVICE_H */ -- cgit v1.2.3 From b3d95c5c93d4b57eaea0ad3f582b08a6b5fb3eb1 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 9 Feb 2010 11:49:49 +0000 Subject: include/linux/netdevice.h: Add netif_printk helpers Add macros to test a private structure for msg_enable bits and the netif_msg_##bit to test and call netdev_printk if set Simplifies logic in callers and adds message logging consistency Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/netdevice.h | 53 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a51228ac9331..1412dde16d00 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2165,6 +2165,59 @@ do { \ #define netdev_WARN(dev, format, args...) \ WARN(1, "netdevice: %s\n" format, netdev_name(dev), ##args); +/* netif printk helpers, similar to netdev_printk */ + +#define netif_printk(priv, type, level, dev, fmt, args...) \ +do { \ + if (netif_msg_##type(priv)) \ + netdev_printk(level, (dev), fmt, ##args); \ +} while (0) + +#define netif_emerg(priv, type, dev, fmt, args...) \ + netif_printk(priv, type, KERN_EMERG, dev, fmt, ##args) +#define netif_alert(priv, type, dev, fmt, args...) \ + netif_printk(priv, type, KERN_ALERT, dev, fmt, ##args) +#define netif_crit(priv, type, dev, fmt, args...) \ + netif_printk(priv, type, KERN_CRIT, dev, fmt, ##args) +#define netif_err(priv, type, dev, fmt, args...) \ + netif_printk(priv, type, KERN_ERR, dev, fmt, ##args) +#define netif_warn(priv, type, dev, fmt, args...) \ + netif_printk(priv, type, KERN_WARNING, dev, fmt, ##args) +#define netif_notice(priv, type, dev, fmt, args...) \ + netif_printk(priv, type, KERN_NOTICE, dev, fmt, ##args) +#define netif_info(priv, type, dev, fmt, args...) \ + netif_printk(priv, type, KERN_INFO, (dev), fmt, ##args) + +#if defined(DEBUG) +#define netif_dbg(priv, type, dev, format, args...) \ + netif_printk(priv, type, KERN_DEBUG, dev, format, ##args) +#elif defined(CONFIG_DYNAMIC_DEBUG) +#define netif_dbg(priv, type, netdev, format, args...) \ +do { \ + if (netif_msg_##type(priv)) \ + dynamic_dev_dbg((netdev)->dev.parent, \ + "%s: " format, \ + netdev_name(netdev), ##args); \ +} while (0) +#else +#define netif_dbg(priv, type, dev, format, args...) \ +({ \ + if (0) \ + netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ + 0; \ +}) +#endif + +#if defined(VERBOSE_DEBUG) +#define netif_vdbg netdev_dbg +#else +#define netif_vdbg(priv, type, dev, format, args...) \ +({ \ + if (0) \ + netif_printk(KERN_DEBUG, dev, format, ##args); \ + 0; \ +}) +#endif #endif /* __KERNEL__ */ -- cgit v1.2.3 From 95c26df829ba4a25f40595cadb4c9433883cbe28 Mon Sep 17 00:00:00 2001 From: "Williams, Mitch A" Date: Wed, 10 Feb 2010 01:43:46 +0000 Subject: net: Add netdev ops for SR-IOV configuration Add netdev ops for configuring SR-IOV VF devices through the PF driver. Signed-off-by: Mitch Williams Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/netdevice.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1412dde16d00..682d02521bbc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -28,6 +28,7 @@ #include #include #include +#include #ifdef __KERNEL__ #include @@ -621,6 +622,13 @@ struct netdev_queue { * this function is called when a VLAN id is unregistered. * * void (*ndo_poll_controller)(struct net_device *dev); + * + * SR-IOV management functions. + * int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac); + * int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, u8 qos); + * int (*ndo_set_vf_tx_rate)(struct net_device *dev, int vf, int rate); + * int (*ndo_get_vf_config)(struct net_device *dev, + * int vf, struct ifla_vf_info *ivf); */ #define HAVE_NET_DEVICE_OPS struct net_device_ops { @@ -660,6 +668,15 @@ struct net_device_ops { #ifdef CONFIG_NET_POLL_CONTROLLER void (*ndo_poll_controller)(struct net_device *dev); #endif + int (*ndo_set_vf_mac)(struct net_device *dev, + int queue, u8 *mac); + int (*ndo_set_vf_vlan)(struct net_device *dev, + int queue, u16 vlan, u8 qos); + int (*ndo_set_vf_tx_rate)(struct net_device *dev, + int vf, int rate); + int (*ndo_get_vf_config)(struct net_device *dev, + int vf, + struct ifla_vf_info *ivf); #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); -- cgit v1.2.3 From caf66e581172dc5032bb84841a91bc7b77ad9876 Mon Sep 17 00:00:00 2001 From: "John W. Linville" Date: Thu, 25 Feb 2010 12:02:45 -0500 Subject: netdevice.h: check for CONFIG_WLAN instead of CONFIG_WLAN_80211 In "wireless: remove WLAN_80211 and WLAN_PRE80211 from Kconfig" I inadvertantly missed a line in include/linux/netdevice.h. I thereby effectively reverted "net: Set LL_MAX_HEADER properly for wireless." by accident. :-( Now we should check there for CONFIG_WLAN instead. Signed-off-by: John W. Linville Reported-by: Christoph Egger Cc: stable@kernel.org --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a3fccc85b1a0..99914e6fa3fd 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -136,7 +136,7 @@ static inline bool dev_xmit_complete(int rc) * used. */ -#if defined(CONFIG_WLAN_80211) || defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE) +#if defined(CONFIG_WLAN) || defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE) # if defined(CONFIG_MAC80211_MESH) # define LL_MAX_HEADER 128 # else -- cgit v1.2.3 From a2835763e130c343ace5320c20d33c281e7097b7 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 26 Feb 2010 06:34:51 +0000 Subject: rtnetlink: handle rtnl_link netlink notifications manually In order to support specifying device flags during device creation, we must be able to roll back device registration in case setting the flags fails without sending any notifications related to the device to userspace. This patch changes rollback_registered_many() and register_netdevice() to manually send netlink notifications for devices not handled by rtnl_link and allows to defer notifications for devices handled by rtnl_link until setup is complete. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 ++++++- net/core/dev.c | 8 +++++++- net/core/rtnetlink.c | 4 +--- 3 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7a2aea56f195..1bfda90c2625 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -924,7 +924,12 @@ struct net_device { NETREG_UNREGISTERED, /* completed unregister todo */ NETREG_RELEASED, /* called free_netdev */ NETREG_DUMMY, /* dummy device for NAPI poll */ - } reg_state; + } reg_state:16; + + enum { + RTNL_LINK_INITIALIZED, + RTNL_LINK_INITIALIZING, + } rtnl_link_state:16; /* Called from unregister, can be used to call free_netdev */ void (*destructor)(struct net_device *dev); diff --git a/net/core/dev.c b/net/core/dev.c index eb7f1a4fefc6..75332b089529 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4865,6 +4865,10 @@ static void rollback_registered_many(struct list_head *head) */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + rtmsg_ifinfo(RTM_DELLINK, dev, ~0U); + /* * Flush the unicast and multicast chains */ @@ -5091,7 +5095,9 @@ int register_netdevice(struct net_device *dev) * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); out: return ret; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b7c7dfd86507..020e43bfef5f 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1425,9 +1425,6 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi struct net_device *dev = ptr; switch (event) { - case NETDEV_UNREGISTER: - rtmsg_ifinfo(RTM_DELLINK, dev, ~0U); - break; case NETDEV_UP: case NETDEV_DOWN: rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); @@ -1437,6 +1434,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_REGISTER: case NETDEV_CHANGE: case NETDEV_GOING_DOWN: + case NETDEV_UNREGISTER: case NETDEV_UNREGISTER_BATCH: break; default: -- cgit v1.2.3 From bd38081160bb3d036db98472e537b6a7dd4da51a Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 26 Feb 2010 06:34:53 +0000 Subject: dev: support deferring device flag change notifications Split dev_change_flags() into two functions: __dev_change_flags() to perform the actual changes and __dev_notify_flags() to invoke netdevice notifiers. This will be used by rtnl_link to defer netlink notifications until the device has been fully configured. This changes ordering of some operations, in particular: - netlink notifications are sent after all changes have been performed. As a side effect this surpresses one unnecessary netlink message when the IFF_UP and other flags are changed simultaneously. - The NETDEV_UP/NETDEV_DOWN and NETDEV_CHANGE notifiers are invoked after all changes have been performed. Their relative is unchanged. - net_dmaengine_put() is invoked before the NETDEV_DOWN notifier instead of afterwards. This should not make any difference since both RX and TX are already shut down at this point. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 + net/core/dev.c | 163 +++++++++++++++++++++++++++++----------------- net/core/rtnetlink.c | 2 - 3 files changed, 106 insertions(+), 61 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1bfda90c2625..c79a88be7c33 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1587,7 +1587,9 @@ extern int dev_valid_name(const char *name); extern int dev_ioctl(struct net *net, unsigned int cmd, void __user *); extern int dev_ethtool(struct net *net, struct ifreq *); extern unsigned dev_get_flags(const struct net_device *); +extern int __dev_change_flags(struct net_device *, unsigned int flags); extern int dev_change_flags(struct net_device *, unsigned); +extern void __dev_notify_flags(struct net_device *, unsigned int old_flags); extern int dev_change_name(struct net_device *, const char *); extern int dev_set_alias(struct net_device *, const char *, size_t); extern int dev_change_net_namespace(struct net_device *, diff --git a/net/core/dev.c b/net/core/dev.c index 75332b089529..e5972f7f7e1b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1113,32 +1113,13 @@ void dev_load(struct net *net, const char *name) } EXPORT_SYMBOL(dev_load); -/** - * dev_open - prepare an interface for use. - * @dev: device to open - * - * Takes a device from down to up state. The device's private open - * function is invoked and then the multicast lists are loaded. Finally - * the device is moved into the up state and a %NETDEV_UP message is - * sent to the netdev notifier chain. - * - * Calling this function on an active interface is a nop. On a failure - * a negative errno code is returned. - */ -int dev_open(struct net_device *dev) +static int __dev_open(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; int ret; ASSERT_RTNL(); - /* - * Is it already up? - */ - - if (dev->flags & IFF_UP) - return 0; - /* * Is it even present? */ @@ -1187,36 +1168,57 @@ int dev_open(struct net_device *dev) * Wakeup transmit queue engine */ dev_activate(dev); - - /* - * ... and announce new interface. - */ - call_netdevice_notifiers(NETDEV_UP, dev); } return ret; } -EXPORT_SYMBOL(dev_open); /** - * dev_close - shutdown an interface. - * @dev: device to shutdown + * dev_open - prepare an interface for use. + * @dev: device to open * - * This function moves an active device into down state. A - * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device - * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier - * chain. + * Takes a device from down to up state. The device's private open + * function is invoked and then the multicast lists are loaded. Finally + * the device is moved into the up state and a %NETDEV_UP message is + * sent to the netdev notifier chain. + * + * Calling this function on an active interface is a nop. On a failure + * a negative errno code is returned. */ -int dev_close(struct net_device *dev) +int dev_open(struct net_device *dev) +{ + int ret; + + /* + * Is it already up? + */ + if (dev->flags & IFF_UP) + return 0; + + /* + * Open device + */ + ret = __dev_open(dev); + if (ret < 0) + return ret; + + /* + * ... and announce new interface. + */ + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); + call_netdevice_notifiers(NETDEV_UP, dev); + + return ret; +} +EXPORT_SYMBOL(dev_open); + +static int __dev_close(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; - ASSERT_RTNL(); + ASSERT_RTNL(); might_sleep(); - if (!(dev->flags & IFF_UP)) - return 0; - /* * Tell people we are going down, so that they can * prepare to death, when device is still operating. @@ -1252,14 +1254,34 @@ int dev_close(struct net_device *dev) dev->flags &= ~IFF_UP; /* - * Tell people we are down + * Shutdown NET_DMA */ - call_netdevice_notifiers(NETDEV_DOWN, dev); + net_dmaengine_put(); + + return 0; +} + +/** + * dev_close - shutdown an interface. + * @dev: device to shutdown + * + * This function moves an active device into down state. A + * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device + * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier + * chain. + */ +int dev_close(struct net_device *dev) +{ + if (!(dev->flags & IFF_UP)) + return 0; + + __dev_close(dev); /* - * Shutdown NET_DMA + * Tell people we are down */ - net_dmaengine_put(); + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); + call_netdevice_notifiers(NETDEV_DOWN, dev); return 0; } @@ -4299,18 +4321,10 @@ unsigned dev_get_flags(const struct net_device *dev) } EXPORT_SYMBOL(dev_get_flags); -/** - * dev_change_flags - change device settings - * @dev: device - * @flags: device state flags - * - * Change settings on device based state flags. The flags are - * in the userspace exported format. - */ -int dev_change_flags(struct net_device *dev, unsigned flags) +int __dev_change_flags(struct net_device *dev, unsigned int flags) { - int ret, changes; int old_flags = dev->flags; + int ret; ASSERT_RTNL(); @@ -4341,17 +4355,12 @@ int dev_change_flags(struct net_device *dev, unsigned flags) ret = 0; if ((old_flags ^ flags) & IFF_UP) { /* Bit is different ? */ - ret = ((old_flags & IFF_UP) ? dev_close : dev_open)(dev); + ret = ((old_flags & IFF_UP) ? __dev_close : __dev_open)(dev); if (!ret) dev_set_rx_mode(dev); } - if (dev->flags & IFF_UP && - ((old_flags ^ dev->flags) & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | - IFF_VOLATILE))) - call_netdevice_notifiers(NETDEV_CHANGE, dev); - if ((flags ^ dev->gflags) & IFF_PROMISC) { int inc = (flags & IFF_PROMISC) ? 1 : -1; @@ -4370,11 +4379,47 @@ int dev_change_flags(struct net_device *dev, unsigned flags) dev_set_allmulti(dev, inc); } - /* Exclude state transition flags, already notified */ - changes = (old_flags ^ dev->flags) & ~(IFF_UP | IFF_RUNNING); + return ret; +} + +void __dev_notify_flags(struct net_device *dev, unsigned int old_flags) +{ + unsigned int changes = dev->flags ^ old_flags; + + if (changes & IFF_UP) { + if (dev->flags & IFF_UP) + call_netdevice_notifiers(NETDEV_UP, dev); + else + call_netdevice_notifiers(NETDEV_DOWN, dev); + } + + if (dev->flags & IFF_UP && + (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) + call_netdevice_notifiers(NETDEV_CHANGE, dev); +} + +/** + * dev_change_flags - change device settings + * @dev: device + * @flags: device state flags + * + * Change settings on device based state flags. The flags are + * in the userspace exported format. + */ +int dev_change_flags(struct net_device *dev, unsigned flags) +{ + int ret, changes; + int old_flags = dev->flags; + + ret = __dev_change_flags(dev, flags); + if (ret < 0) + return ret; + + changes = old_flags ^ dev->flags; if (changes) rtmsg_ifinfo(RTM_NEWLINK, dev, changes); + __dev_notify_flags(dev, old_flags); return ret; } EXPORT_SYMBOL(dev_change_flags); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 020e43bfef5f..c21ec4236dd0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1427,8 +1427,6 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi switch (event) { case NETDEV_UP: case NETDEV_DOWN: - rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); - break; case NETDEV_PRE_UP: case NETDEV_POST_INIT: case NETDEV_REGISTER: -- cgit v1.2.3