From 56f36acd215cf7c28372b2fdb4f33f6900e97e05 Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Wed, 15 Mar 2017 10:39:25 -0700 Subject: mqprio: Modify mqprio to pass user parameters via ndo_setup_tc. The configurable priority to traffic class mapping and the user specified queue ranges are used to configure the traffic class, overriding the hardware defaults when the 'hw' option is set to 0. However, when the 'hw' option is non-zero, the hardware QOS defaults are used. This patch makes it so that we can pass the data the user provided to ndo_setup_tc. This allows us to pull in the queue configuration if the user requested it as well as any additional hardware offload type requested by using a value other than 1 for the hw value. Finally it also provides a means for the device driver to return the level supported for the offload type via the qopt->hw value. Previously we were just always assuming the value to be 1, in the future values beyond just 1 may be supported. Signed-off-by: Amritha Nambiar Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- 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 97456b2539e4..b7365b587818 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -786,11 +786,11 @@ struct tc_cls_u32_offload; struct tc_to_netdev { unsigned int type; union { - u8 tc; struct tc_cls_u32_offload *cls_u32; struct tc_cls_flower_offload *cls_flower; struct tc_cls_matchall_offload *cls_mall; struct tc_cls_bpf_offload *cls_bpf; + struct tc_mqprio_qopt *mqprio; }; bool egress_dev; }; -- cgit v1.2.3 From c6e970a04bdceb7ef1fdbac6be3bd4cd0a0a02bd Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 28 Mar 2017 23:45:06 +0200 Subject: net: break include loop netdevice.h, dsa.h, devlink.h There is an include loop between netdevice.h, dsa.h, devlink.h because of NETDEV_ALIGN, making it impossible to use devlink structures in dsa.h. Break this loop by taking dsa.h out of netdevice.h, add a forward declaration of dsa_switch_tree and netdev_set_default_ethtool_ops() function, which is what netdevice.h requires. No longer having dsa.h in netdevice.h means the includes in dsa.h no longer get included. This breaks a few other files which depend on these includes. Add these directly in the affected file. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/bcm_sf2_cfp.c | 3 ++- drivers/net/dsa/mv88e6xxx/mv88e6xxx.h | 1 + drivers/net/ethernet/broadcom/bcmsysport.c | 1 + drivers/net/ethernet/freescale/fman/fman_memac.h | 1 + drivers/net/ethernet/hisilicon/hns/hnae.c | 2 +- drivers/net/ieee802154/mrf24j40.c | 1 + drivers/net/phy/smsc.c | 1 + drivers/net/usb/lan78xx.c | 1 + fs/cifs/cifsfs.c | 1 + fs/cifs/connect.c | 1 + fs/cifs/smb2pdu.c | 1 + include/linux/netdevice.h | 12 ++---------- include/net/dsa.h | 9 +++++++++ net/bridge/br_if.c | 1 + net/core/netprio_cgroup.c | 1 + net/dsa/dsa.c | 3 ++- net/dsa/dsa2.c | 3 ++- net/dsa/slave.c | 1 + net/dsa/tag_brcm.c | 1 + net/dsa/tag_dsa.c | 1 + net/dsa/tag_edsa.c | 1 + net/dsa/tag_qca.c | 1 + net/dsa/tag_trailer.c | 1 + net/ipv4/ipconfig.c | 1 + 24 files changed, 36 insertions(+), 14 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c index 346dd9a1232d..2fb32d67065f 100644 --- a/drivers/net/dsa/bcm_sf2_cfp.c +++ b/drivers/net/dsa/bcm_sf2_cfp.c @@ -10,10 +10,11 @@ */ #include -#include #include #include #include +#include +#include #include #include "bcm_sf2.h" diff --git a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h index 75be2c339a49..55367d05374e 100644 --- a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h @@ -16,6 +16,7 @@ #include #include #include +#include #ifndef UINT64_MAX #define UINT64_MAX (u64)(~((u64)0)) diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 61e26c6b26ab..099b374c1b17 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.h b/drivers/net/ethernet/freescale/fman/fman_memac.h index 173d8e0fd716..c4a66469a907 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.h +++ b/drivers/net/ethernet/freescale/fman/fman_memac.h @@ -36,6 +36,7 @@ #include "fman_mac.h" #include +#include struct fman_mac *memac_config(struct fman_mac_params *params); int memac_set_promiscuous(struct fman_mac *memac, bool new_val); diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index b6ed818f78ff..120427a40883 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -9,9 +9,9 @@ #include #include +#include #include #include - #include "hnae.h" #define cls_to_ae_dev(dev) container_of(dev, struct hnae_ae_dev, cls_dev) diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c index 7b131f8e4093..bd63289c55e8 100644 --- a/drivers/net/ieee802154/mrf24j40.c +++ b/drivers/net/ieee802154/mrf24j40.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index fb32eaf2255d..cef6967b0396 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index d885e0325422..a17e32bf5f92 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 15e1db8738ae..8c91f37ac0eb 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include "cifsfs.h" diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 9ae695ae3ed7..858698dcde3c 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 7446496850a3..fb75fe908225 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include "smb2pdu.h" diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b7365b587818..cc07c3be2705 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -41,7 +41,6 @@ #include #include -#include #ifdef CONFIG_DCB #include #endif @@ -57,6 +56,8 @@ struct netpoll_info; struct device; struct phy_device; +struct dsa_switch_tree; + /* 802.11 specific */ struct wireless_dev; /* 802.15.4 specific */ @@ -2004,15 +2005,6 @@ void dev_net_set(struct net_device *dev, struct net *net) write_pnet(&dev->nd_net, net); } -static inline bool netdev_uses_dsa(struct net_device *dev) -{ -#if IS_ENABLED(CONFIG_NET_DSA) - if (dev->dsa_ptr != NULL) - return dsa_uses_tagged_protocol(dev->dsa_ptr); -#endif - return false; -} - /** * netdev_priv - access network device private data * @dev: network device diff --git a/include/net/dsa.h b/include/net/dsa.h index e42897fd7a96..f80e81912b83 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -468,6 +468,15 @@ static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst) return dst->rcv != NULL; } +static inline bool netdev_uses_dsa(struct net_device *dev) +{ +#if IS_ENABLED(CONFIG_NET_DSA) + if (dev->dsa_ptr != NULL) + return dsa_uses_tagged_protocol(dev->dsa_ptr); +#endif + return false; +} + struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n); void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds, struct device *dev); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 8ac1770aa222..6eb52d422dd9 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 0f9275ee5595..1c4810919a0a 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -11,6 +11,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index b6d4f6a23f06..95d1a756202c 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -14,15 +14,16 @@ #include #include #include -#include #include #include #include #include #include +#include #include #include #include +#include #include "dsa_priv.h" static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb, diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 737be6470c7f..d039c8d7adfd 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -13,11 +13,12 @@ #include #include #include +#include #include #include -#include #include #include +#include #include "dsa_priv.h" static LIST_HEAD(dsa_switch_trees); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 78128acfbf63..7693182df81e 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 5d925b6b2bb1..e2ed6cf68261 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -12,6 +12,7 @@ #include #include #include +#include #include "dsa_priv.h" /* This tag length is 4 bytes, older ones were 6 bytes, we do not diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 72579ceea381..e42ba906100c 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "dsa_priv.h" #define DSA_HLEN 4 diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index 648c051817a1..6a9b7a9e4e15 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "dsa_priv.h" #define DSA_HLEN 4 diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 30240f343aea..4e0dad759d04 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -12,6 +12,7 @@ */ #include +#include #include "dsa_priv.h" #define QCA_HDR_LEN 2 diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 26f977176978..74c948512550 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "dsa_priv.h" static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index fd9f34bbd740..9def8ed31c76 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -57,6 +57,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 5b3dc2f37d7daf76a679cd204492ec5dff06bb8a Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 10 Apr 2017 11:11:17 +0300 Subject: net: neigh: make ->hh_len 32-bit Using 16-bit ->hh_len doesn't save any memory, save some .text instead: add/remove: 0/0 grow/shrink: 1/6 up/down: 2/-19 (-17) function old new delta neigh_update 2312 2314 +2 fwnet_header_cache 199 197 -2 eth_header_cache 101 99 -2 ip6_finish_output2 2371 2368 -3 vrf_finish_output6 1522 1518 -4 vrf_finish_output 1413 1409 -4 ip_finish_output2 1627 1623 -4 Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +-- include/net/neighbour.h | 4 ++-- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cc07c3be2705..8ea8a8b70755 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -237,8 +237,7 @@ struct netdev_hw_addr_list { netdev_hw_addr_list_for_each(ha, &(dev)->mc) struct hh_cache { - u16 hh_len; - u16 __pad; + unsigned int hh_len; seqlock_t hh_lock; /* cached hardware header; allow for machine alignment needs. */ diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 9496179c7b4e..e4dd3a214034 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -450,7 +450,7 @@ static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb) static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb) { unsigned int seq; - int hh_len; + unsigned int hh_len; do { seq = read_seqbegin(&hh->hh_lock); @@ -459,7 +459,7 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb /* this is inlined by gcc */ memcpy(skb->data - HH_DATA_MOD, hh->hh_data, HH_DATA_MOD); } else { - int hh_alen = HH_DATA_ALIGN(hh_len); + unsigned int hh_alen = HH_DATA_ALIGN(hh_len); memcpy(skb->data - hh_alen, hh->hh_data, hh_alen); } -- cgit v1.2.3 From d92be7a41ef15463eb816a4a2d42bf094b56dfce Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 10 Apr 2017 11:25:26 +0300 Subject: net: make struct net_device::min_header_len 8-bit This field is never big enough to warrant 16-bitness. 8-bit accesses enjoy shorted encoding on i386/x86_64 than 16-bit accesses: add/remove: 0/0 grow/shrink: 0/2 up/down: 0/-10 (-10) function old new delta loopback_setup 169 164 -5 ether_setup 148 143 -5 Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- 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 8ea8a8b70755..b0aa089ce67f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1715,7 +1715,7 @@ struct net_device { unsigned int max_mtu; unsigned short type; unsigned short hard_header_len; - unsigned short min_header_len; + unsigned char min_header_len; unsigned short needed_headroom; unsigned short needed_tailroom; -- cgit v1.2.3 From c7ef8f0c020ac43c8a692bf989017c06ab1fdf0f Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Fri, 14 Apr 2017 10:05:36 +0200 Subject: net: Add ESP offload features This patch adds netdev features to configure IPsec offloads. Signed-off-by: Steffen Klassert --- include/linux/netdev_features.h | 8 +++++++- include/linux/netdevice.h | 1 + include/linux/skbuff.h | 2 ++ net/core/ethtool.c | 3 +++ 4 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 9a0419594e84..1d4737cffc71 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -54,8 +54,9 @@ enum { */ NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */ NETIF_F_GSO_SCTP_BIT, /* ... SCTP fragmentation */ + NETIF_F_GSO_ESP_BIT, /* ... ESP with TSO */ /**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */ - NETIF_F_GSO_SCTP_BIT, + NETIF_F_GSO_ESP_BIT, NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */ @@ -73,6 +74,8 @@ enum { NETIF_F_HW_L2FW_DOFFLOAD_BIT, /* Allow L2 Forwarding in Hardware */ NETIF_F_HW_TC_BIT, /* Offload TC infrastructure */ + NETIF_F_HW_ESP_BIT, /* Hardware ESP transformation offload */ + NETIF_F_HW_ESP_TX_CSUM_BIT, /* ESP with TX checksum offload */ /* * Add your fresh new feature above and remember to update @@ -129,11 +132,14 @@ enum { #define NETIF_F_GSO_PARTIAL __NETIF_F(GSO_PARTIAL) #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM) #define NETIF_F_GSO_SCTP __NETIF_F(GSO_SCTP) +#define NETIF_F_GSO_ESP __NETIF_F(GSO_ESP) #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER) #define NETIF_F_HW_VLAN_STAG_RX __NETIF_F(HW_VLAN_STAG_RX) #define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX) #define NETIF_F_HW_L2FW_DOFFLOAD __NETIF_F(HW_L2FW_DOFFLOAD) #define NETIF_F_HW_TC __NETIF_F(HW_TC) +#define NETIF_F_HW_ESP __NETIF_F(HW_ESP) +#define NETIF_F_HW_ESP_TX_CSUM __NETIF_F(HW_ESP_TX_CSUM) #define for_each_netdev_feature(mask_addr, bit) \ for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cc07c3be2705..5bb03d181848 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4070,6 +4070,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_SCTP != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 741d75cfc686..81ef53f06534 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -492,6 +492,8 @@ enum { SKB_GSO_TUNNEL_REMCSUM = 1 << 14, SKB_GSO_SCTP = 1 << 15, + + SKB_GSO_ESP = 1 << 16, }; #if BITS_PER_LONG > 32 diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 905a88ad28e0..03111a2d6653 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -90,6 +90,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation", [NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial", [NETIF_F_GSO_SCTP_BIT] = "tx-sctp-segmentation", + [NETIF_F_GSO_ESP_BIT] = "tx-esp-segmentation", [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", [NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp", @@ -103,6 +104,8 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_RXALL_BIT] = "rx-all", [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", [NETIF_F_HW_TC_BIT] = "hw-tc-offload", + [NETIF_F_HW_ESP_BIT] = "esp-hw-offload", + [NETIF_F_HW_ESP_TX_CSUM_BIT] = "esp-tx-csum-hw-offload", }; static const char -- cgit v1.2.3 From d77e38e612a017480157fe6d2c1422f42cb5b7e3 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Fri, 14 Apr 2017 10:06:10 +0200 Subject: xfrm: Add an IPsec hardware offloading API This patch adds all the bits that are needed to do IPsec hardware offload for IPsec states and ESP packets. We add xfrmdev_ops to the net_device. xfrmdev_ops has function pointers that are needed to manage the xfrm states in the hardware and to do a per packet offloading decision. Joint work with: Ilan Tayari Guy Shapiro Yossi Kuperman Signed-off-by: Guy Shapiro Signed-off-by: Ilan Tayari Signed-off-by: Yossi Kuperman Signed-off-by: Steffen Klassert --- include/linux/netdevice.h | 14 +++++ include/net/xfrm.h | 65 +++++++++++++++++++++- include/uapi/linux/xfrm.h | 8 +++ net/ipv4/esp4.c | 7 +-- net/ipv4/xfrm4_output.c | 3 +- net/ipv6/esp6.c | 4 +- net/ipv6/xfrm6_output.c | 9 ++- net/xfrm/Makefile | 3 +- net/xfrm/xfrm_device.c | 138 +++++++++++++++++++++++++++++++++++++++++++++- net/xfrm/xfrm_input.c | 41 +++++++++++++- net/xfrm/xfrm_output.c | 44 +++++++++++++-- net/xfrm/xfrm_policy.c | 10 ++-- net/xfrm/xfrm_state.c | 74 +++++++++++++++++++++++++ net/xfrm/xfrm_user.c | 28 ++++++++++ 14 files changed, 424 insertions(+), 24 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5bb03d181848..b3eb83db0223 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -824,6 +824,16 @@ struct netdev_xdp { }; }; +#ifdef CONFIG_XFRM_OFFLOAD +struct xfrmdev_ops { + int (*xdo_dev_state_add) (struct xfrm_state *x); + void (*xdo_dev_state_delete) (struct xfrm_state *x); + void (*xdo_dev_state_free) (struct xfrm_state *x); + bool (*xdo_dev_offload_ok) (struct sk_buff *skb, + struct xfrm_state *x); +}; +#endif + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1697,6 +1707,10 @@ struct net_device { const struct ndisc_ops *ndisc_ops; #endif +#ifdef CONFIG_XFRM + const struct xfrmdev_ops *xfrmdev_ops; +#endif + const struct header_ops *header_ops; unsigned int flags; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 54515d989365..17603bf190c1 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -120,6 +120,13 @@ struct xfrm_state_walk { struct xfrm_address_filter *filter; }; +struct xfrm_state_offload { + struct net_device *dev; + unsigned long offload_handle; + unsigned int num_exthdrs; + u8 flags; +}; + /* Full description of state of transformer. */ struct xfrm_state { possible_net_t xs_net; @@ -207,6 +214,8 @@ struct xfrm_state { struct xfrm_lifetime_cur curlft; struct tasklet_hrtimer mtimer; + struct xfrm_state_offload xso; + /* used to fix curlft->add_time when changing date */ long saved_tmo; @@ -1453,7 +1462,6 @@ struct xfrm6_tunnel { void xfrm_init(void); void xfrm4_init(void); int xfrm_state_init(struct net *net); -void xfrm_dev_init(void); void xfrm_state_fini(struct net *net); void xfrm4_state_init(void); void xfrm4_protocol_init(void); @@ -1559,6 +1567,7 @@ struct xfrmk_spdinfo { struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq); int xfrm_state_delete(struct xfrm_state *x); int xfrm_state_flush(struct net *net, u8 proto, bool task_valid); +int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq); @@ -1641,6 +1650,11 @@ static inline int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) } #endif +struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, + const xfrm_address_t *saddr, + const xfrm_address_t *daddr, + int family); + struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp); void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type); @@ -1846,6 +1860,55 @@ static inline struct xfrm_offload *xfrm_offload(struct sk_buff *skb) } #endif +#ifdef CONFIG_XFRM_OFFLOAD +void __net_init xfrm_dev_init(void); +int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, + struct xfrm_user_offload *xuo); +bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x); + +static inline void xfrm_dev_state_delete(struct xfrm_state *x) +{ + struct xfrm_state_offload *xso = &x->xso; + + if (xso->dev) + xso->dev->xfrmdev_ops->xdo_dev_state_delete(x); +} + +static inline void xfrm_dev_state_free(struct xfrm_state *x) +{ + struct xfrm_state_offload *xso = &x->xso; + struct net_device *dev = xso->dev; + + if (dev && dev->xfrmdev_ops) { + dev->xfrmdev_ops->xdo_dev_state_free(x); + xso->dev = NULL; + dev_put(dev); + } +} +#else +static inline void __net_init xfrm_dev_init(void) +{ +} + +static inline int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo) +{ + return 0; +} + +static inline void xfrm_dev_state_delete(struct xfrm_state *x) +{ +} + +static inline void xfrm_dev_state_free(struct xfrm_state *x) +{ +} + +static inline bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) +{ + return false; +} +#endif + static inline int xfrm_mark_get(struct nlattr **attrs, struct xfrm_mark *m) { if (attrs[XFRMA_MARK]) diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 1fc62b239f1b..2b384ff09fa0 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -303,6 +303,7 @@ enum xfrm_attr_type_t { XFRMA_PROTO, /* __u8 */ XFRMA_ADDRESS_FILTER, /* struct xfrm_address_filter */ XFRMA_PAD, + XFRMA_OFFLOAD_DEV, /* struct xfrm_state_offload */ __XFRMA_MAX #define XFRMA_MAX (__XFRMA_MAX - 1) @@ -494,6 +495,13 @@ struct xfrm_address_filter { __u8 dplen; }; +struct xfrm_user_offload { + int ifindex; + __u8 flags; +}; +#define XFRM_OFFLOAD_IPV6 1 +#define XFRM_OFFLOAD_INBOUND 2 + #ifndef __KERNEL__ /* backwards compatibility for userspace */ #define XFRMGRP_ACQUIRE 1 diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index b1e24446e297..c6aba234b6e9 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -435,9 +435,6 @@ skip_cow2: aead_request_set_crypt(req, sg, dsg, ivlen + clen, iv); aead_request_set_ad(req, assoclen); - seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low + - ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32)); - memset(iv, 0, ivlen); memcpy(iv + ivlen - min(ivlen, 8), (u8 *)&seqno + 8 - min(ivlen, 8), min(ivlen, 8)); @@ -470,6 +467,7 @@ static int esp_input_done2(struct sk_buff *skb, int err) { const struct iphdr *iph; struct xfrm_state *x = xfrm_input_state(skb); + struct xfrm_offload *xo = xfrm_offload(skb); struct crypto_aead *aead = x->data; int alen = crypto_aead_authsize(aead); int hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead); @@ -478,7 +476,8 @@ static int esp_input_done2(struct sk_buff *skb, int err) u8 nexthdr[2]; int padlen; - kfree(ESP_SKB_CB(skb)->tmp); + if (!xo || (xo && !(xo->flags & CRYPTO_DONE))) + kfree(ESP_SKB_CB(skb)->tmp); if (unlikely(err)) goto out; diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 7ee6518afa86..94b8702603bc 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -29,7 +29,8 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) goto out; mtu = dst_mtu(skb_dst(skb)); - if (skb->len > mtu) { + if ((!skb_is_gso(skb) && skb->len > mtu) || + (skb_is_gso(skb) && skb_gso_network_seglen(skb) > ip_skb_dst_mtu(skb->sk, skb))) { skb->protocol = htons(ETH_P_IP); if (skb->sk) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index ff54faa75631..3d3757d20d0a 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -450,6 +450,7 @@ error: static int esp_input_done2(struct sk_buff *skb, int err) { struct xfrm_state *x = xfrm_input_state(skb); + struct xfrm_offload *xo = xfrm_offload(skb); struct crypto_aead *aead = x->data; int alen = crypto_aead_authsize(aead); int hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead); @@ -458,7 +459,8 @@ static int esp_input_done2(struct sk_buff *skb, int err) int padlen; u8 nexthdr[2]; - kfree(ESP_SKB_CB(skb)->tmp); + if (!xo || (xo && !(xo->flags & CRYPTO_DONE))) + kfree(ESP_SKB_CB(skb)->tmp); if (unlikely(err)) goto out; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 4d09ce6fa90e..8ae87d4ec5ff 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -73,11 +73,16 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) int mtu, ret = 0; struct dst_entry *dst = skb_dst(skb); + if (skb->ignore_df) + goto out; + mtu = dst_mtu(dst); if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if (!skb->ignore_df && skb->len > mtu) { + if ((!skb_is_gso(skb) && skb->len > mtu) || + (skb_is_gso(skb) && + skb_gso_network_seglen(skb) > ip6_skb_dst_mtu(skb))) { skb->dev = dst->dev; skb->protocol = htons(ETH_P_IPV6); @@ -89,7 +94,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ret = -EMSGSIZE; } - +out: return ret; } diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index 55b2ac300995..abf81b329dc1 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -4,7 +4,8 @@ obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \ xfrm_input.o xfrm_output.o \ - xfrm_sysctl.o xfrm_replay.o xfrm_device.o + xfrm_sysctl.o xfrm_replay.o +obj-$(CONFIG_XFRM_OFFLOAD) += xfrm_device.o obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o obj-$(CONFIG_XFRM_USER) += xfrm_user.o diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 34a260a61be9..9bac2ba9052c 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -22,13 +22,149 @@ #include #include +int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, + struct xfrm_user_offload *xuo) +{ + int err; + struct dst_entry *dst; + struct net_device *dev; + struct xfrm_state_offload *xso = &x->xso; + xfrm_address_t *saddr; + xfrm_address_t *daddr; + + if (!x->type_offload) + return 0; + + /* We don't yet support UDP encapsulation, TFC padding and ESN. */ + if (x->encap || x->tfcpad || (x->props.flags & XFRM_STATE_ESN)) + return 0; + + dev = dev_get_by_index(net, xuo->ifindex); + if (!dev) { + if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) { + saddr = &x->props.saddr; + daddr = &x->id.daddr; + } else { + saddr = &x->id.daddr; + daddr = &x->props.saddr; + } + + dst = __xfrm_dst_lookup(net, 0, 0, saddr, daddr, x->props.family); + if (IS_ERR(dst)) + return 0; + + dev = dst->dev; + + dev_hold(dev); + dst_release(dst); + } + + if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_state_add) { + dev_put(dev); + return 0; + } + + xso->dev = dev; + xso->num_exthdrs = 1; + xso->flags = xuo->flags; + + err = dev->xfrmdev_ops->xdo_dev_state_add(x); + if (err) { + dev_put(dev); + return err; + } + + return 0; +} +EXPORT_SYMBOL_GPL(xfrm_dev_state_add); + +bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) +{ + int mtu; + struct dst_entry *dst = skb_dst(skb); + struct xfrm_dst *xdst = (struct xfrm_dst *)dst; + struct net_device *dev = x->xso.dev; + + if (!x->type_offload || x->encap) + return false; + + if ((x->xso.offload_handle && (dev == dst->path->dev)) && + !dst->child->xfrm && x->type->get_mtu) { + mtu = x->type->get_mtu(x, xdst->child_mtu_cached); + + if (skb->len <= mtu) + goto ok; + + if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + goto ok; + } + + return false; + +ok: + if (dev && dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_offload_ok) + return x->xso.dev->xfrmdev_ops->xdo_dev_offload_ok(skb, x); + + return true; +} +EXPORT_SYMBOL_GPL(xfrm_dev_offload_ok); + +int xfrm_dev_register(struct net_device *dev) +{ + if ((dev->features & NETIF_F_HW_ESP) && !dev->xfrmdev_ops) + return NOTIFY_BAD; + if ((dev->features & NETIF_F_HW_ESP_TX_CSUM) && + !(dev->features & NETIF_F_HW_ESP)) + return NOTIFY_BAD; + + return NOTIFY_DONE; +} + +static int xfrm_dev_unregister(struct net_device *dev) +{ + return NOTIFY_DONE; +} + +static int xfrm_dev_feat_change(struct net_device *dev) +{ + if ((dev->features & NETIF_F_HW_ESP) && !dev->xfrmdev_ops) + return NOTIFY_BAD; + else if (!(dev->features & NETIF_F_HW_ESP)) + dev->xfrmdev_ops = NULL; + + if ((dev->features & NETIF_F_HW_ESP_TX_CSUM) && + !(dev->features & NETIF_F_HW_ESP)) + return NOTIFY_BAD; + + return NOTIFY_DONE; +} + +static int xfrm_dev_down(struct net_device *dev) +{ + if (dev->hw_features & NETIF_F_HW_ESP) + xfrm_dev_state_flush(dev_net(dev), dev, true); + + xfrm_garbage_collect(dev_net(dev)); + + return NOTIFY_DONE; +} + static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { + case NETDEV_REGISTER: + return xfrm_dev_register(dev); + + case NETDEV_UNREGISTER: + return xfrm_dev_unregister(dev); + + case NETDEV_FEAT_CHANGE: + return xfrm_dev_feat_change(dev); + case NETDEV_DOWN: - xfrm_garbage_collect(dev_net(dev)); + return xfrm_dev_down(dev); } return NOTIFY_DONE; } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 46bdb4fbed0b..362d655eac27 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -107,6 +107,8 @@ struct sec_path *secpath_dup(struct sec_path *src) sp->len = 0; sp->olen = 0; + memset(sp->ovec, 0, sizeof(sp->ovec[XFRM_MAX_OFFLOAD_DEPTH])); + if (src) { int i; @@ -207,8 +209,9 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) unsigned int family; int decaps = 0; int async = 0; - struct xfrm_offload *xo; bool xfrm_gro = false; + bool crypto_done = false; + struct xfrm_offload *xo = xfrm_offload(skb); if (encap_type < 0) { x = xfrm_input_state(skb); @@ -226,6 +229,37 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) goto lock; } + if (xo && (xo->flags & CRYPTO_DONE)) { + crypto_done = true; + x = xfrm_input_state(skb); + family = XFRM_SPI_SKB_CB(skb)->family; + + if (!(xo->status & CRYPTO_SUCCESS)) { + if (xo->status & + (CRYPTO_TRANSPORT_AH_AUTH_FAILED | + CRYPTO_TRANSPORT_ESP_AUTH_FAILED | + CRYPTO_TUNNEL_AH_AUTH_FAILED | + CRYPTO_TUNNEL_ESP_AUTH_FAILED)) { + + xfrm_audit_state_icvfail(x, skb, + x->type->proto); + x->stats.integrity_failed++; + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR); + goto drop; + } + + XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); + goto drop; + } + + if ((err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); + goto drop; + } + + goto lock; + } + daddr = (xfrm_address_t *)(skb_network_header(skb) + XFRM_SPI_SKB_CB(skb)->daddroff); family = XFRM_SPI_SKB_CB(skb)->family; @@ -311,7 +345,10 @@ lock: skb_dst_force(skb); dev_hold(skb->dev); - nexthdr = x->type->input(x, skb); + if (crypto_done) + nexthdr = x->type_offload->input_tail(x, skb); + else + nexthdr = x->type->input(x, skb); if (nexthdr == -EINPROGRESS) return 0; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 8ba29fe58352..a15088613a6c 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -99,12 +99,13 @@ static int xfrm_output_one(struct sk_buff *skb, int err) skb_dst_force(skb); - /* Inner headers are invalid now. */ - skb->encapsulation = 0; - - err = x->type->output(x, skb); - if (err == -EINPROGRESS) - goto out; + if (xfrm_offload(skb)) { + x->type_offload->encap(x, skb); + } else { + err = x->type->output(x, skb); + if (err == -EINPROGRESS) + goto out; + } resume: if (err) { @@ -200,8 +201,38 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb int xfrm_output(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); + struct xfrm_state *x = skb_dst(skb)->xfrm; int err; + secpath_reset(skb); + + if (xfrm_dev_offload_ok(skb, x)) { + struct sec_path *sp; + + sp = secpath_dup(skb->sp); + if (!sp) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); + kfree_skb(skb); + return -ENOMEM; + } + if (skb->sp) + secpath_put(skb->sp); + skb->sp = sp; + + sp->olen++; + sp->xvec[skb->sp->len++] = x; + xfrm_state_hold(x); + + if (skb_is_gso(skb)) { + skb_shinfo(skb)->gso_type |= SKB_GSO_ESP; + + return xfrm_output2(net, sk, skb); + } + + if (x->xso.dev && x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM) + goto out; + } + if (skb_is_gso(skb)) return xfrm_output_gso(net, sk, skb); @@ -214,6 +245,7 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) } } +out: return xfrm_output2(net, sk, skb); } EXPORT_SYMBOL_GPL(xfrm_output); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 7befca2a0773..dd44ddc1aea5 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -116,11 +116,10 @@ static const struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short fa return afinfo; } -static inline struct dst_entry *__xfrm_dst_lookup(struct net *net, - int tos, int oif, - const xfrm_address_t *saddr, - const xfrm_address_t *daddr, - int family) +struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, + const xfrm_address_t *saddr, + const xfrm_address_t *daddr, + int family) { const struct xfrm_policy_afinfo *afinfo; struct dst_entry *dst; @@ -135,6 +134,7 @@ static inline struct dst_entry *__xfrm_dst_lookup(struct net *net, return dst; } +EXPORT_SYMBOL(__xfrm_dst_lookup); static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, int tos, int oif, diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 47fefe97d1e3..fc3c5aa38754 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -440,6 +440,7 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) x->type->destructor(x); xfrm_put_type(x->type); } + xfrm_dev_state_free(x); security_xfrm_state_free(x); kfree(x); } @@ -609,6 +610,8 @@ int __xfrm_state_delete(struct xfrm_state *x) net->xfrm.state_num--; spin_unlock(&net->xfrm.xfrm_state_lock); + xfrm_dev_state_delete(x); + /* All xfrm_state objects are created by xfrm_state_alloc. * The xfrm_state_alloc call gives a reference, and that * is what we are dropping here. @@ -653,12 +656,41 @@ xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid) return err; } + +static inline int +xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid) +{ + int i, err = 0; + + for (i = 0; i <= net->xfrm.state_hmask; i++) { + struct xfrm_state *x; + struct xfrm_state_offload *xso; + + hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { + xso = &x->xso; + + if (xso->dev == dev && + (err = security_xfrm_state_delete(x)) != 0) { + xfrm_audit_state_delete(x, 0, task_valid); + return err; + } + } + } + + return err; +} #else static inline int xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid) { return 0; } + +static inline int +xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid) +{ + return 0; +} #endif int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) @@ -701,6 +733,48 @@ out: } EXPORT_SYMBOL(xfrm_state_flush); +int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid) +{ + int i, err = 0, cnt = 0; + + spin_lock_bh(&net->xfrm.xfrm_state_lock); + err = xfrm_dev_state_flush_secctx_check(net, dev, task_valid); + if (err) + goto out; + + err = -ESRCH; + for (i = 0; i <= net->xfrm.state_hmask; i++) { + struct xfrm_state *x; + struct xfrm_state_offload *xso; +restart: + hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { + xso = &x->xso; + + if (!xfrm_state_kern(x) && xso->dev == dev) { + xfrm_state_hold(x); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); + + err = xfrm_state_delete(x); + xfrm_audit_state_delete(x, err ? 0 : 1, + task_valid); + xfrm_state_put(x); + if (!err) + cnt++; + + spin_lock_bh(&net->xfrm.xfrm_state_lock); + goto restart; + } + } + } + if (cnt) + err = 0; + +out: + spin_unlock_bh(&net->xfrm.xfrm_state_lock); + return err; +} +EXPORT_SYMBOL(xfrm_dev_state_flush); + void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) { spin_lock_bh(&net->xfrm.xfrm_state_lock); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 4f7e62ddc17e..de3332e3f9e2 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -595,6 +595,10 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, goto error; } + if (attrs[XFRMA_OFFLOAD_DEV] && + xfrm_dev_state_add(net, x, nla_data(attrs[XFRMA_OFFLOAD_DEV]))) + goto error; + if ((err = xfrm_alloc_replay_state_esn(&x->replay_esn, &x->preplay_esn, attrs[XFRMA_REPLAY_ESN_VAL]))) goto error; @@ -779,6 +783,23 @@ static int copy_sec_ctx(struct xfrm_sec_ctx *s, struct sk_buff *skb) return 0; } +static int copy_user_offload(struct xfrm_state_offload *xso, struct sk_buff *skb) +{ + struct xfrm_user_offload *xuo; + struct nlattr *attr; + + attr = nla_reserve(skb, XFRMA_OFFLOAD_DEV, sizeof(*xuo)); + if (attr == NULL) + return -EMSGSIZE; + + xuo = nla_data(attr); + + xuo->ifindex = xso->dev->ifindex; + xuo->flags = xso->flags; + + return 0; +} + static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb) { struct xfrm_algo *algo; @@ -869,6 +890,10 @@ static int copy_to_user_state_extra(struct xfrm_state *x, &x->replay); if (ret) goto out; + if(x->xso.dev) + ret = copy_user_offload(&x->xso, skb); + if (ret) + goto out; if (x->security) ret = copy_sec_ctx(x->security, skb); out: @@ -2406,6 +2431,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_SA_EXTRA_FLAGS] = { .type = NLA_U32 }, [XFRMA_PROTO] = { .type = NLA_U8 }, [XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) }, + [XFRMA_OFFLOAD_DEV] = { .len = sizeof(struct xfrm_user_offload) }, }; static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = { @@ -2622,6 +2648,8 @@ static inline size_t xfrm_sa_len(struct xfrm_state *x) l += nla_total_size(sizeof(*x->coaddr)); if (x->props.extra_flags) l += nla_total_size(sizeof(x->props.extra_flags)); + if (x->xso.dev) + l += nla_total_size(sizeof(x->xso)); /* Must count x->lastused as it may become non-zero behind our back. */ l += nla_total_size_64bit(sizeof(u64)); -- cgit v1.2.3 From 5be661412762bbef45a55eaf1e6847258d69b3a4 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 18 Apr 2017 16:55:36 +0200 Subject: net: add netif_is_ovs_port helper To find out if a netdev is an OVS port. Signed-off-by: Jiri Pirko Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b0aa089ce67f..0f3c38ce5417 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4171,6 +4171,11 @@ static inline bool netif_is_ovs_master(const struct net_device *dev) return dev->priv_flags & IFF_OPENVSWITCH; } +static inline bool netif_is_ovs_port(const struct net_device *dev) +{ + return dev->priv_flags & IFF_OVS_DATAPATH; +} + static inline bool netif_is_team_master(const struct net_device *dev) { return dev->priv_flags & IFF_TEAM; -- cgit v1.2.3 From 7acf8a1e8a28b3d7407a8d8061a7d0766cfac2f4 Mon Sep 17 00:00:00 2001 From: Matthew Whitehead Date: Wed, 19 Apr 2017 12:37:10 -0400 Subject: Replace 2 jiffies with sysctl netdev_budget_usecs to enable softirq tuning Constants used for tuning are generally a bad idea, especially as hardware changes over time. Replace the constant 2 jiffies with sysctl variable netdev_budget_usecs to enable sysadmins to tune the softirq processing. Also document the variable. For example, a very fast machine might tune this to 1000 microseconds, while my regression testing 486DX-25 needs it to be 4000 microseconds on a nearly idle network to prevent time_squeeze from being incremented. Version 2: changed jiffies to microseconds for predictable units. Signed-off-by: Matthew Whitehead Signed-off-by: David S. Miller --- Documentation/sysctl/net.txt | 11 ++++++++++- include/linux/netdevice.h | 1 + include/uapi/linux/sysctl.h | 1 + kernel/sysctl_binary.c | 1 + net/core/dev.c | 4 +++- net/core/sysctl_net_core.c | 8 ++++++++ 6 files changed, 24 insertions(+), 2 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index 2ebabc93014a..14db18c970b1 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -188,7 +188,16 @@ netdev_budget Maximum number of packets taken from all interfaces in one polling cycle (NAPI poll). In one polling cycle interfaces which are registered to polling are -probed in a round-robin manner. +probed in a round-robin manner. Also, a polling cycle may not exceed +netdev_budget_usecs microseconds, even if netdev_budget has not been +exhausted. + +netdev_budget_usecs +--------------------- + +Maximum number of microseconds in one NAPI polling cycle. Polling +will exit when either netdev_budget_usecs have elapsed during the +poll cycle or the number of packets processed reaches netdev_budget. netdev_max_backlog ------------------ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0f3c38ce5417..c49cf21f2b31 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3296,6 +3296,7 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev, void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); extern int netdev_budget; +extern unsigned int netdev_budget_usecs; /* Called by rtnetlink.c:rtnl_unlock() */ void netdev_run_todo(void); diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index e13d48058b8d..177f5f139b36 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -274,6 +274,7 @@ enum NET_CORE_AEVENT_ETIME=20, NET_CORE_AEVENT_RSEQTH=21, NET_CORE_WARNINGS=22, + NET_CORE_BUDGET_USECS=23, }; /* /proc/sys/net/ethernet */ diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index ece4b177052b..4ee3e49530d2 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -197,6 +197,7 @@ static const struct bin_table bin_net_core_table[] = { { CTL_INT, NET_CORE_AEVENT_ETIME, "xfrm_aevent_etime" }, { CTL_INT, NET_CORE_AEVENT_RSEQTH, "xfrm_aevent_rseqth" }, { CTL_INT, NET_CORE_WARNINGS, "warnings" }, + { CTL_INT, NET_CORE_BUDGET_USECS, "netdev_budget_usecs" }, {}, }; diff --git a/net/core/dev.c b/net/core/dev.c index 5d33e2baab2b..1c53c055b197 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3441,6 +3441,7 @@ EXPORT_SYMBOL(netdev_max_backlog); int netdev_tstamp_prequeue __read_mostly = 1; int netdev_budget __read_mostly = 300; +unsigned int __read_mostly netdev_budget_usecs = 2000; int weight_p __read_mostly = 64; /* old backlog weight */ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ @@ -5307,7 +5308,8 @@ out_unlock: static __latent_entropy void net_rx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); - unsigned long time_limit = jiffies + 2; + unsigned long time_limit = jiffies + + usecs_to_jiffies(netdev_budget_usecs); int budget = netdev_budget; LIST_HEAD(list); LIST_HEAD(repoll); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 7f9cc400eca0..ea23254b2457 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -452,6 +452,14 @@ static struct ctl_table net_core_table[] = { .extra1 = &one, .extra2 = &max_skb_frags, }, + { + .procname = "netdev_budget_usecs", + .data = &netdev_budget_usecs, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + }, { } }; -- cgit v1.2.3 From b5cdae3291f7be7a34e75affe4c0ec1f7f328b64 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 18 Apr 2017 15:36:58 -0400 Subject: net: Generic XDP This provides a generic SKB based non-optimized XDP path which is used if either the driver lacks a specific XDP implementation, or the user requests it via a new IFLA_XDP_FLAGS value named XDP_FLAGS_SKB_MODE. It is arguable that perhaps I should have required something like this as part of the initial XDP feature merge. I believe this is critical for two reasons: 1) Accessibility. More people can play with XDP with less dependencies. Yes I know we have XDP support in virtio_net, but that just creates another depedency for learning how to use this facility. I wrote this to make life easier for the XDP newbies. 2) As a model for what the expected semantics are. If there is a pure generic core implementation, it serves as a semantic example for driver folks adding XDP support. One thing I have not tried to address here is the issue of XDP_PACKET_HEADROOM, thanks to Daniel for spotting that. It seems incredibly expensive to do a skb_cow(skb, XDP_PACKET_HEADROOM) or whatever even if the XDP program doesn't try to push headers at all. I think we really need the verifier to somehow propagate whether certain XDP helpers are used or not. v5: - Handle both negative and positive offset after running prog - Fix mac length in XDP_TX case (Alexei) - Use rcu_dereference_protected() in free_netdev (kbuild test robot) v4: - Fix MAC header adjustmnet before calling prog (David Ahern) - Disable LRO when generic XDP is installed (Michael Chan) - Bypass qdisc et al. on XDP_TX and record the event (Alexei) - Do not perform generic XDP on reinjected packets (DaveM) v3: - Make sure XDP program sees packet at MAC header, push back MAC header if we do XDP_TX. (Alexei) - Elide GRO when generic XDP is in use. (Alexei) - Add XDP_FLAG_SKB_MODE flag which the user can use to request generic XDP even if the driver has an XDP implementation. (Alexei) - Report whether SKB mode is in use in rtnl_xdp_fill() via XDP_FLAGS attribute. (Daniel) v2: - Add some "fall through" comments in switch statements based upon feedback from Andrew Lunn - Use RCU for generic xdp_prog, thanks to Johannes Berg. Tested-by: Andy Gospodarek Tested-by: Jesper Dangaard Brouer Tested-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 +++ include/uapi/linux/if_link.h | 4 +- net/core/dev.c | 155 +++++++++++++++++++++++++++++++++++++++++-- net/core/gro_cells.c | 2 +- net/core/rtnetlink.c | 40 ++++++----- 5 files changed, 187 insertions(+), 22 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5d5267febd56..46d220c2bf92 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1905,9 +1905,17 @@ struct net_device { struct lock_class_key *qdisc_tx_busylock; struct lock_class_key *qdisc_running_key; bool proto_down; + struct bpf_prog __rcu *xdp_prog; }; #define to_net_dev(d) container_of(d, struct net_device, dev) +static inline bool netif_elide_gro(const struct net_device *dev) +{ + if (!(dev->features & NETIF_F_GRO) || dev->xdp_prog) + return true; + return false; +} + #define NETDEV_ALIGN 32 static inline diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 8b405afb2376..633aa0276d32 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -887,7 +887,9 @@ enum { /* XDP section */ #define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0) -#define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST) +#define XDP_FLAGS_SKB_MODE (2U << 0) +#define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \ + XDP_FLAGS_SKB_MODE) enum { IFLA_XDP_UNSPEC, diff --git a/net/core/dev.c b/net/core/dev.c index db6e31564d06..1b3317c026c6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -95,6 +95,7 @@ #include #include #include +#include #include #include #include @@ -4251,6 +4252,125 @@ static int __netif_receive_skb(struct sk_buff *skb) return ret; } +static struct static_key generic_xdp_needed __read_mostly; + +static int generic_xdp_install(struct net_device *dev, struct netdev_xdp *xdp) +{ + struct bpf_prog *new = xdp->prog; + int ret = 0; + + switch (xdp->command) { + case XDP_SETUP_PROG: { + struct bpf_prog *old = rtnl_dereference(dev->xdp_prog); + + rcu_assign_pointer(dev->xdp_prog, new); + if (old) + bpf_prog_put(old); + + if (old && !new) { + static_key_slow_dec(&generic_xdp_needed); + } else if (new && !old) { + static_key_slow_inc(&generic_xdp_needed); + dev_disable_lro(dev); + } + break; + } + + case XDP_QUERY_PROG: + xdp->prog_attached = !!rcu_access_pointer(dev->xdp_prog); + break; + + default: + ret = -EINVAL; + break; + } + + return ret; +} + +static u32 netif_receive_generic_xdp(struct sk_buff *skb, + struct bpf_prog *xdp_prog) +{ + struct xdp_buff xdp; + u32 act = XDP_DROP; + void *orig_data; + int hlen, off; + u32 mac_len; + + /* Reinjected packets coming from act_mirred or similar should + * not get XDP generic processing. + */ + if (skb_cloned(skb)) + return XDP_PASS; + + if (skb_linearize(skb)) + goto do_drop; + + /* The XDP program wants to see the packet starting at the MAC + * header. + */ + mac_len = skb->data - skb_mac_header(skb); + hlen = skb_headlen(skb) + mac_len; + xdp.data = skb->data - mac_len; + xdp.data_end = xdp.data + hlen; + xdp.data_hard_start = skb->data - skb_headroom(skb); + orig_data = xdp.data; + + act = bpf_prog_run_xdp(xdp_prog, &xdp); + + off = xdp.data - orig_data; + if (off > 0) + __skb_pull(skb, off); + else if (off < 0) + __skb_push(skb, -off); + + switch (act) { + case XDP_TX: + __skb_push(skb, mac_len); + /* fall through */ + case XDP_PASS: + break; + + default: + bpf_warn_invalid_xdp_action(act); + /* fall through */ + case XDP_ABORTED: + trace_xdp_exception(skb->dev, xdp_prog, act); + /* fall through */ + case XDP_DROP: + do_drop: + kfree_skb(skb); + break; + } + + return act; +} + +/* When doing generic XDP we have to bypass the qdisc layer and the + * network taps in order to match in-driver-XDP behavior. + */ +static void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) +{ + struct net_device *dev = skb->dev; + struct netdev_queue *txq; + bool free_skb = true; + int cpu, rc; + + txq = netdev_pick_tx(dev, skb, NULL); + cpu = smp_processor_id(); + HARD_TX_LOCK(dev, txq, cpu); + if (!netif_xmit_stopped(txq)) { + rc = netdev_start_xmit(skb, dev, txq, 0); + if (dev_xmit_complete(rc)) + free_skb = false; + } + HARD_TX_UNLOCK(dev, txq); + if (free_skb) { + trace_xdp_exception(dev, xdp_prog, XDP_TX); + kfree_skb(skb); + } +} + static int netif_receive_skb_internal(struct sk_buff *skb) { int ret; @@ -4262,6 +4382,21 @@ static int netif_receive_skb_internal(struct sk_buff *skb) rcu_read_lock(); + if (static_key_false(&generic_xdp_needed)) { + struct bpf_prog *xdp_prog = rcu_dereference(skb->dev->xdp_prog); + + if (xdp_prog) { + u32 act = netif_receive_generic_xdp(skb, xdp_prog); + + if (act != XDP_PASS) { + rcu_read_unlock(); + if (act == XDP_TX) + generic_xdp_tx(skb, xdp_prog); + return NET_RX_DROP; + } + } + } + #ifdef CONFIG_RPS if (static_key_false(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; @@ -4494,7 +4629,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff enum gro_result ret; int grow; - if (!(skb->dev->features & NETIF_F_GRO)) + if (netif_elide_gro(skb->dev)) goto normal; if (skb->csum_bad) @@ -6723,6 +6858,7 @@ EXPORT_SYMBOL(dev_change_proto_down); */ int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags) { + int (*xdp_op)(struct net_device *dev, struct netdev_xdp *xdp); const struct net_device_ops *ops = dev->netdev_ops; struct bpf_prog *prog = NULL; struct netdev_xdp xdp; @@ -6730,14 +6866,16 @@ int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags) ASSERT_RTNL(); - if (!ops->ndo_xdp) - return -EOPNOTSUPP; + xdp_op = ops->ndo_xdp; + if (!xdp_op || (flags & XDP_FLAGS_SKB_MODE)) + xdp_op = generic_xdp_install; + if (fd >= 0) { if (flags & XDP_FLAGS_UPDATE_IF_NOEXIST) { memset(&xdp, 0, sizeof(xdp)); xdp.command = XDP_QUERY_PROG; - err = ops->ndo_xdp(dev, &xdp); + err = xdp_op(dev, &xdp); if (err < 0) return err; if (xdp.prog_attached) @@ -6753,7 +6891,7 @@ int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags) xdp.command = XDP_SETUP_PROG; xdp.prog = prog; - err = ops->ndo_xdp(dev, &xdp); + err = xdp_op(dev, &xdp); if (err < 0 && prog) bpf_prog_put(prog); @@ -7793,6 +7931,7 @@ EXPORT_SYMBOL(alloc_netdev_mqs); void free_netdev(struct net_device *dev) { struct napi_struct *p, *n; + struct bpf_prog *prog; might_sleep(); netif_free_tx_queues(dev); @@ -7811,6 +7950,12 @@ void free_netdev(struct net_device *dev) free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL; + prog = rcu_dereference_protected(dev->xdp_prog, 1); + if (prog) { + bpf_prog_put(prog); + static_key_slow_dec(&generic_xdp_needed); + } + /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED) { netdev_freemem(dev); diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index c98bbfbd26b8..814e58a3ce8b 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -13,7 +13,7 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) struct net_device *dev = skb->dev; struct gro_cell *cell; - if (!gcells->cells || skb_cloned(skb) || !(dev->features & NETIF_F_GRO)) + if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) return netif_rx(skb); cell = this_cpu_ptr(gcells->cells); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 088f9c8b4196..9031a6c8bfa7 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -896,15 +896,13 @@ static size_t rtnl_port_size(const struct net_device *dev, return port_self_size; } -static size_t rtnl_xdp_size(const struct net_device *dev) +static size_t rtnl_xdp_size(void) { size_t xdp_size = nla_total_size(0) + /* nest IFLA_XDP */ - nla_total_size(1); /* XDP_ATTACHED */ + nla_total_size(1) + /* XDP_ATTACHED */ + nla_total_size(4); /* XDP_FLAGS */ - if (!dev->netdev_ops->ndo_xdp) - return 0; - else - return xdp_size; + return xdp_size; } static noinline size_t if_nlmsg_size(const struct net_device *dev, @@ -943,7 +941,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */ + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */ - + rtnl_xdp_size(dev) /* IFLA_XDP */ + + rtnl_xdp_size() /* IFLA_XDP */ + nla_total_size(1); /* IFLA_PROTO_DOWN */ } @@ -1251,23 +1249,35 @@ static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev) static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev) { - struct netdev_xdp xdp_op = {}; struct nlattr *xdp; + u32 xdp_flags = 0; + u8 val = 0; int err; - if (!dev->netdev_ops->ndo_xdp) - return 0; xdp = nla_nest_start(skb, IFLA_XDP); if (!xdp) return -EMSGSIZE; - xdp_op.command = XDP_QUERY_PROG; - err = dev->netdev_ops->ndo_xdp(dev, &xdp_op); - if (err) - goto err_cancel; - err = nla_put_u8(skb, IFLA_XDP_ATTACHED, xdp_op.prog_attached); + if (rcu_access_pointer(dev->xdp_prog)) { + xdp_flags = XDP_FLAGS_SKB_MODE; + val = 1; + } else if (dev->netdev_ops->ndo_xdp) { + struct netdev_xdp xdp_op = {}; + + xdp_op.command = XDP_QUERY_PROG; + err = dev->netdev_ops->ndo_xdp(dev, &xdp_op); + if (err) + goto err_cancel; + val = xdp_op.prog_attached; + } + err = nla_put_u8(skb, IFLA_XDP_ATTACHED, val); if (err) goto err_cancel; + if (xdp_flags) { + err = nla_put_u32(skb, IFLA_XDP_FLAGS, xdp_flags); + if (err) + goto err_cancel; + } nla_nest_end(skb, xdp); return 0; -- cgit v1.2.3 From 7acedaf5c4355f812cfef883ac28bf15f7d9205e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 25 Apr 2017 11:36:52 -0700 Subject: net: move xdp_prog field in RX cache lines (struct net_device, xdp_prog) field should be moved in RX cache lines, reducing latencies when a single packet is received on idle host, since netif_elide_gro() needs it. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- 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 46d220c2bf92..8c5c8cdc7b97 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1790,6 +1790,7 @@ struct net_device { unsigned int real_num_rx_queues; #endif + struct bpf_prog __rcu *xdp_prog; unsigned long gro_flush_timeout; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; @@ -1905,7 +1906,6 @@ struct net_device { struct lock_class_key *qdisc_tx_busylock; struct lock_class_key *qdisc_running_key; bool proto_down; - struct bpf_prog __rcu *xdp_prog; }; #define to_net_dev(d) container_of(d, struct net_device, dev) -- cgit v1.2.3 From 8ecbc40ada116f2f7d6b61cd646802c87b7c5c7d Mon Sep 17 00:00:00 2001 From: Zhang Shengju Date: Wed, 26 Apr 2017 11:05:12 +0800 Subject: net: update comment for netif_dormant() function This patch updates the comment for netif_dormant() function to reflect the intended usage. Signed-off-by: Zhang Shengju Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8c5c8cdc7b97..6847714a5ae3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3408,10 +3408,10 @@ static inline void netif_dormant_off(struct net_device *dev) } /** - * netif_dormant - test if carrier present + * netif_dormant - test if device is dormant * @dev: network device * - * Check if carrier is present on device + * Check if device is dormant. */ static inline bool netif_dormant(const struct net_device *dev) { -- cgit v1.2.3 From ddf9f970764f4390aba767e77fddaaced4a6760d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 30 Apr 2017 21:46:46 -0700 Subject: xdp: propagate extended ack to XDP setup Drivers usually have a number of restrictions for running XDP - most common being buffer sizes, LRO and number of rings. Even though some drivers try to be helpful and print error messages experience shows that users don't often consult kernel logs on netlink errors. Try to use the new extended ack mechanism to carry the message back to user space. Signed-off-by: Jakub Kicinski Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++++++++-- net/core/dev.c | 5 ++++- net/core/rtnetlink.c | 13 ++++++++----- 3 files changed, 20 insertions(+), 8 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6847714a5ae3..9c23bd2efb56 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -813,11 +813,16 @@ enum xdp_netdev_command { XDP_QUERY_PROG, }; +struct netlink_ext_ack; + struct netdev_xdp { enum xdp_netdev_command command; union { /* XDP_SETUP_PROG */ - struct bpf_prog *prog; + struct { + struct bpf_prog *prog; + struct netlink_ext_ack *extack; + }; /* XDP_QUERY_PROG */ bool prog_attached; }; @@ -3291,7 +3296,8 @@ int dev_get_phys_port_id(struct net_device *dev, int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); int dev_change_proto_down(struct net_device *dev, bool proto_down); -int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags); +int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, + int fd, u32 flags); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); diff --git a/net/core/dev.c b/net/core/dev.c index 8371a01eee87..35a06cebb282 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6854,12 +6854,14 @@ EXPORT_SYMBOL(dev_change_proto_down); /** * dev_change_xdp_fd - set or clear a bpf program for a device rx path * @dev: device + * @extact: netlink extended ack * @fd: new program fd or negative value to clear * @flags: xdp-related flags * * Set or clear a bpf program for a device */ -int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags) +int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, + int fd, u32 flags) { int (*xdp_op)(struct net_device *dev, struct netdev_xdp *xdp); const struct net_device_ops *ops = dev->netdev_ops; @@ -6892,6 +6894,7 @@ int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags) memset(&xdp, 0, sizeof(xdp)); xdp.command = XDP_SETUP_PROG; + xdp.extack = extack; xdp.prog = prog; err = xdp_op(dev, &xdp); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 9031a6c8bfa7..6e67315ec368 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1919,6 +1919,7 @@ static int do_set_master(struct net_device *dev, int ifindex) #define DO_SETLINK_NOTIFY 0x03 static int do_setlink(const struct sk_buff *skb, struct net_device *dev, struct ifinfomsg *ifm, + struct netlink_ext_ack *extack, struct nlattr **tb, char *ifname, int status) { const struct net_device_ops *ops = dev->netdev_ops; @@ -2201,7 +2202,7 @@ static int do_setlink(const struct sk_buff *skb, } if (xdp[IFLA_XDP_FD]) { - err = dev_change_xdp_fd(dev, + err = dev_change_xdp_fd(dev, extack, nla_get_s32(xdp[IFLA_XDP_FD]), xdp_flags); if (err) @@ -2261,7 +2262,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) goto errout; - err = do_setlink(skb, dev, ifm, tb, ifname, 0); + err = do_setlink(skb, dev, ifm, extack, tb, ifname, 0); errout: return err; } @@ -2423,6 +2424,7 @@ EXPORT_SYMBOL(rtnl_create_link); static int rtnl_group_changelink(const struct sk_buff *skb, struct net *net, int group, struct ifinfomsg *ifm, + struct netlink_ext_ack *extack, struct nlattr **tb) { struct net_device *dev, *aux; @@ -2430,7 +2432,7 @@ static int rtnl_group_changelink(const struct sk_buff *skb, for_each_netdev_safe(net, dev, aux) { if (dev->group == group) { - err = do_setlink(skb, dev, ifm, tb, NULL, 0); + err = do_setlink(skb, dev, ifm, extack, tb, NULL, 0); if (err < 0) return err; } @@ -2576,14 +2578,15 @@ replay: status |= DO_SETLINK_NOTIFY; } - return do_setlink(skb, dev, ifm, tb, ifname, status); + return do_setlink(skb, dev, ifm, extack, tb, ifname, + status); } if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { if (ifm->ifi_index == 0 && tb[IFLA_GROUP]) return rtnl_group_changelink(skb, net, nla_get_u32(tb[IFLA_GROUP]), - ifm, tb); + ifm, extack, tb); return -ENODEV; } -- cgit v1.2.3