diff options
146 files changed, 3618 insertions, 953 deletions
diff --git a/Documentation/devicetree/bindings/net/airoha,en8811h.yaml b/Documentation/devicetree/bindings/net/airoha,en8811h.yaml new file mode 100644 index 000000000000..ecb5149ec6b0 --- /dev/null +++ b/Documentation/devicetree/bindings/net/airoha,en8811h.yaml @@ -0,0 +1,56 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/airoha,en8811h.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Airoha EN8811H PHY + +maintainers: + - Eric Woudstra <ericwouds@gmail.com> + +description: + The Airoha EN8811H PHY has the ability to reverse polarity + on the lines to and/or from the MAC. It is reversed by + the booleans in the devicetree node of the phy. + +allOf: + - $ref: ethernet-phy.yaml# + +properties: + compatible: + enum: + - ethernet-phy-id03a2.a411 + + reg: + maxItems: 1 + + airoha,pnswap-rx: + type: boolean + description: + Reverse rx polarity of the SERDES. This is the receiving + side of the lines from the MAC towards the EN881H. + + airoha,pnswap-tx: + type: boolean + description: + Reverse tx polarity of SERDES. This is the transmitting + side of the lines from EN8811H towards the MAC. + +required: + - reg + +unevaluatedProperties: false + +examples: + - | + mdio { + #address-cells = <1>; + #size-cells = <0>; + + ethernet-phy@1 { + compatible = "ethernet-phy-id03a2.a411"; + reg = <1>; + airoha,pnswap-rx; + }; + }; diff --git a/Documentation/devicetree/bindings/net/stm32-dwmac.yaml b/Documentation/devicetree/bindings/net/stm32-dwmac.yaml index fc8c96b08d7d..857d58949b02 100644 --- a/Documentation/devicetree/bindings/net/stm32-dwmac.yaml +++ b/Documentation/devicetree/bindings/net/stm32-dwmac.yaml @@ -82,6 +82,13 @@ properties: Should be phandle/offset pair. The phandle to the syscon node which encompases the glue register, and the offset of the control register + st,ext-phyclk: + description: + set this property in RMII mode when you have PHY without crystal 50MHz and want to + select RCC clock instead of ETH_REF_CLK. OR in RGMII mode when you want to select + RCC clock instead of ETH_CLK125. + type: boolean + st,eth-clk-sel: description: set this property in RGMII PHY when you want to select RCC clock instead of ETH_CLK125. diff --git a/Documentation/netlink/specs/tc.yaml b/Documentation/netlink/specs/tc.yaml index 324fa182cd14..6068c105c5ee 100644 --- a/Documentation/netlink/specs/tc.yaml +++ b/Documentation/netlink/specs/tc.yaml @@ -1100,6 +1100,19 @@ definitions: name: offmask type: s32 - + name: tc-u32-mark + type: struct + members: + - + name: val + type: u32 + - + name: mask + type: u32 + - + name: success + type: u32 + - name: tc-u32-sel type: struct members: @@ -1775,6 +1788,44 @@ attribute-sets: name: key-ex type: binary - + name: tc-act-police-attrs + attributes: + - + name: tbf + type: binary + struct: tc-police + - + name: rate + type: binary # TODO + - + name: peakrate + type: binary # TODO + - + name: avrate + type: u32 + - + name: result + type: u32 + - + name: tm + type: binary + struct: tcf-t + - + name: pad + type: pad + - + name: rate64 + type: u64 + - + name: peakrate64 + type: u64 + - + name: pktrate64 + type: u64 + - + name: pktburst64 + type: u64 + - name: tc-act-simple-attrs attributes: - diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 68cc9290cabe..5bc6d0fa7498 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -847,7 +847,7 @@ void af_alg_wmem_wakeup(struct sock *sk) wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLRDNORM | EPOLLRDBAND); - sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); + sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(af_alg_wmem_wakeup); @@ -914,7 +914,7 @@ static void af_alg_data_wakeup(struct sock *sk) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | EPOLLRDNORM | EPOLLRDBAND); - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); rcu_read_unlock(); } diff --git a/drivers/md/dm-clone-metadata.c b/drivers/md/dm-clone-metadata.c index c43d55672bce..47c1fa7aad8b 100644 --- a/drivers/md/dm-clone-metadata.c +++ b/drivers/md/dm-clone-metadata.c @@ -465,11 +465,6 @@ static void __destroy_persistent_data_structures(struct dm_clone_metadata *cmd) /*---------------------------------------------------------------------------*/ -static size_t bitmap_size(unsigned long nr_bits) -{ - return BITS_TO_LONGS(nr_bits) * sizeof(long); -} - static int __dirty_map_init(struct dirty_map *dmap, unsigned long nr_words, unsigned long nr_regions) { diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 8ca0bc223b30..172d84e39129 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -290,6 +290,19 @@ config GTP To compile this drivers as a module, choose M here: the module will be called gtp. +config PFCP + tristate "Packet Forwarding Control Protocol (PFCP)" + depends on INET + select NET_UDP_TUNNEL + help + This allows one to create PFCP virtual interfaces that allows to + set up software and hardware offload of PFCP packets. + Note that this module does not support PFCP protocol in the kernel space. + There is no support for parsing any PFCP messages. + + To compile this drivers as a module, choose M here: the module + will be called pfcp. + config AMT tristate "Automatic Multicast Tunneling (AMT)" depends on INET && IP_MULTICAST diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 7cab36f94782..9c053673d6b2 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -38,6 +38,7 @@ obj-$(CONFIG_GENEVE) += geneve.o obj-$(CONFIG_BAREUDP) += bareudp.o obj-$(CONFIG_GTP) += gtp.o obj-$(CONFIG_NLMON) += nlmon.o +obj-$(CONFIG_PFCP) += pfcp.o obj-$(CONFIG_NET_VRF) += vrf.o obj-$(CONFIG_VSOCKMON) += vsockmon.o obj-$(CONFIG_MHI_NET) += mhi_net.o diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index 339db6e4a1d5..d5c56ca91b77 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -61,6 +61,7 @@ struct bareudp_dev { static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct metadata_dst *tun_dst = NULL; + IP_TUNNEL_DECLARE_FLAGS(key) = { }; struct bareudp_dev *bareudp; unsigned short family; unsigned int len; @@ -137,7 +138,10 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) bareudp->dev->stats.rx_dropped++; goto drop; } - tun_dst = udp_tun_rx_dst(skb, family, TUNNEL_KEY, 0, 0); + + __set_bit(IP_TUNNEL_KEY_BIT, key); + + tun_dst = udp_tun_rx_dst(skb, family, key, 0, 0); if (!tun_dst) { bareudp->dev->stats.rx_dropped++; goto drop; @@ -285,10 +289,10 @@ static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct bareudp_dev *bareudp, const struct ip_tunnel_info *info) { + bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev)); bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct socket *sock = rcu_dereference(bareudp->sock); - bool udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); const struct ip_tunnel_key *key = &info->key; struct rtable *rt; __be16 sport, df; @@ -316,7 +320,8 @@ static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev, tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; - df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; + df = test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) ? + htons(IP_DF) : 0; skb_scrub_packet(skb, xnet); err = -ENOSPC; @@ -338,7 +343,8 @@ static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev, udp_tunnel_xmit_skb(rt, sock->sk, skb, saddr, info->key.u.ipv4.dst, tos, ttl, df, sport, bareudp->port, !net_eq(bareudp->net, dev_net(bareudp->dev)), - !(info->key.tun_flags & TUNNEL_CSUM)); + !test_bit(IP_TUNNEL_CSUM_BIT, + info->key.tun_flags)); return 0; free_dst: @@ -350,10 +356,10 @@ static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct bareudp_dev *bareudp, const struct ip_tunnel_info *info) { + bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev)); bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct socket *sock = rcu_dereference(bareudp->sock); - bool udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); const struct ip_tunnel_key *key = &info->key; struct dst_entry *dst = NULL; struct in6_addr saddr, daddr; @@ -402,7 +408,8 @@ static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev, udp_tunnel6_xmit_skb(dst, sock->sk, skb, dev, &saddr, &daddr, prio, ttl, info->key.label, sport, bareudp->port, - !(info->key.tun_flags & TUNNEL_CSUM)); + !test_bit(IP_TUNNEL_CSUM_BIT, + info->key.tun_flags)); return 0; free_dst: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 388e80bf91f5..b4db4b1aaffb 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -14581,12 +14581,9 @@ static int bnxt_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, if (!br_spec) return -EINVAL; - nla_for_each_nested(attr, br_spec, rem) { + nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) { u16 mode; - if (nla_type(attr) != IFLA_BRIDGE_MODE) - continue; - mode = nla_get_u16(attr); if (mode == bp->br_mode) break; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index ad862ed7888a..a8596ebcdfd6 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4982,10 +4982,7 @@ static int be_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, if (!br_spec) return -EINVAL; - nla_for_each_nested(attr, br_spec, rem) { - if (nla_type(attr) != IFLA_BRIDGE_MODE) - continue; - + nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) { mode = nla_get_u16(attr); if (BE3_chip(adapter) && mode == BRIDGE_MODE_VEPA) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 9f07f4947b63..5c45f42232d3 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -2769,7 +2769,7 @@ static int enetc_setup_xdp_prog(struct net_device *ndev, struct bpf_prog *prog, if (priv->min_num_stack_tx_queues + num_xdp_tx_queues > priv->num_tx_rings) { NL_SET_ERR_MSG_FMT_MOD(extack, - "Reserving %d XDP TXQs does not leave a minimum of %d for stack (total %d)", + "Reserving %d XDP TXQs leaves under %d for stack (total %d)", num_xdp_tx_queues, priv->min_num_stack_tx_queues, priv->num_tx_rings); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b297f44d635f..3c7d6ea84491 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -13108,13 +13108,9 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev, if (!br_spec) return -EINVAL; - nla_for_each_nested(attr, br_spec, rem) { - __u16 mode; + nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) { + __u16 mode = nla_get_u16(attr); - if (nla_type(attr) != IFLA_BRIDGE_MODE) - continue; - - mode = nla_get_u16(attr); if ((mode != BRIDGE_MODE_VEPA) && (mode != BRIDGE_MODE_VEB)) return -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index fc91c4d41186..2ffa11fa2df1 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -721,6 +721,12 @@ static bool ice_is_gtp_c_profile(u16 prof_idx) } } +static bool ice_is_pfcp_profile(u16 prof_idx) +{ + return prof_idx >= ICE_PROFID_IPV4_PFCP_NODE && + prof_idx <= ICE_PROFID_IPV6_PFCP_SESSION; +} + /** * ice_get_sw_prof_type - determine switch profile type * @hw: pointer to the HW structure @@ -738,6 +744,9 @@ static enum ice_prof_type ice_get_sw_prof_type(struct ice_hw *hw, if (ice_is_gtp_u_profile(prof_idx)) return ICE_PROF_TUN_GTPU; + if (ice_is_pfcp_profile(prof_idx)) + return ICE_PROF_TUN_PFCP; + for (i = 0; i < hw->blk[ICE_BLK_SW].es.fvw; i++) { /* UDP tunnel will have UDP_OF protocol ID and VNI offset */ if (fv->ew[i].prot_id == (u8)ICE_PROT_UDP_OF && diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h index d427a79d001a..817beca591e0 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_type.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h @@ -93,6 +93,7 @@ enum ice_tunnel_type { TNL_GRETAP, TNL_GTPC, TNL_GTPU, + TNL_PFCP, __TNL_TYPE_CNT, TNL_LAST = 0xFF, TNL_ALL = 0xFF, @@ -358,7 +359,8 @@ enum ice_prof_type { ICE_PROF_TUN_GRE = 0x4, ICE_PROF_TUN_GTPU = 0x8, ICE_PROF_TUN_GTPC = 0x10, - ICE_PROF_TUN_ALL = 0x1E, + ICE_PROF_TUN_PFCP = 0x20, + ICE_PROF_TUN_ALL = 0x3E, ICE_PROF_ALL = 0xFF, }; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 3dea0d4c767c..1c7055148264 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -7989,12 +7989,9 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, if (!br_spec) return -EINVAL; - nla_for_each_nested(attr, br_spec, rem) { - __u16 mode; + nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) { + __u16 mode = nla_get_u16(attr); - if (nla_type(attr) != IFLA_BRIDGE_MODE) - continue; - mode = nla_get_u16(attr); if (mode != BRIDGE_MODE_VEPA && mode != BRIDGE_MODE_VEB) return -EINVAL; /* Continue if bridge mode is not being flipped */ diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h index f6f27361c3cf..755a9c55267c 100644 --- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h +++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h @@ -43,6 +43,7 @@ enum ice_protocol_type { ICE_NVGRE, ICE_GTP, ICE_GTP_NO_PAY, + ICE_PFCP, ICE_PPPOE, ICE_L2TPV3, ICE_VLAN_EX, @@ -61,6 +62,7 @@ enum ice_sw_tunnel_type { ICE_SW_TUN_NVGRE, ICE_SW_TUN_GTPU, ICE_SW_TUN_GTPC, + ICE_SW_TUN_PFCP, ICE_ALL_TUNNELS /* All tunnel types including NVGRE */ }; @@ -202,6 +204,15 @@ struct ice_udp_gtp_hdr { u8 rsvrd; }; +struct ice_pfcp_hdr { + u8 flags; + u8 msg_type; + __be16 length; + __be64 seid; + __be32 seq; + u8 spare; +} __packed __aligned(__alignof__(u16)); + struct ice_pppoe_hdr { u8 rsrvd_ver_type; u8 rsrvd_code; @@ -418,6 +429,7 @@ union ice_prot_hdr { struct ice_udp_tnl_hdr tnl_hdr; struct ice_nvgre_hdr nvgre_hdr; struct ice_udp_gtp_hdr gtp_hdr; + struct ice_pfcp_hdr pfcp_hdr; struct ice_pppoe_hdr pppoe_hdr; struct ice_l2tpv3_sess_hdr l2tpv3_sess_hdr; struct ice_hw_metadata metadata; diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index f1f9d6b7b5c1..606c2419182a 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -42,6 +42,7 @@ enum { ICE_PKT_KMALLOC = BIT(9), ICE_PKT_PPPOE = BIT(10), ICE_PKT_L2TPV3 = BIT(11), + ICE_PKT_PFCP = BIT(12), }; struct ice_dummy_pkt_offsets { @@ -1110,6 +1111,77 @@ ICE_DECLARE_PKT_TEMPLATE(ipv6_gtp) = { 0x00, 0x00, }; +ICE_DECLARE_PKT_OFFSETS(pfcp_session_ipv4) = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_UDP_ILOS, 34 }, + { ICE_PFCP, 42 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(pfcp_session_ipv4) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x08, 0x00, /* ICE_ETYPE_OL 12 */ + + 0x45, 0x00, 0x00, 0x2c, /* ICE_IPV4_OFOS 14 */ + 0x00, 0x01, 0x00, 0x00, + 0x00, 0x11, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x22, 0x65, /* ICE_UDP_ILOS 34 */ + 0x00, 0x18, 0x00, 0x00, + + 0x21, 0x01, 0x00, 0x0c, /* ICE_PFCP 42 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +ICE_DECLARE_PKT_OFFSETS(pfcp_session_ipv6) = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV6_OFOS, 14 }, + { ICE_UDP_ILOS, 54 }, + { ICE_PFCP, 62 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(pfcp_session_ipv6) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x86, 0xdd, /* ICE_ETYPE_OL 12 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 14 */ + 0x00, 0x10, 0x11, 0x00, /* Next header UDP */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x22, 0x65, /* ICE_UDP_ILOS 54 */ + 0x00, 0x18, 0x00, 0x00, + + 0x21, 0x01, 0x00, 0x0c, /* ICE_PFCP 62 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + ICE_DECLARE_PKT_OFFSETS(pppoe_ipv4_tcp) = { { ICE_MAC_OFOS, 0 }, { ICE_ETYPE_OL, 12 }, @@ -1343,6 +1415,8 @@ static const struct ice_dummy_pkt_profile ice_dummy_pkt_profiles[] = { ICE_PKT_PROFILE(ipv4_gtpu_ipv4_tcp, ICE_PKT_TUN_GTPU), ICE_PKT_PROFILE(ipv6_gtp, ICE_PKT_TUN_GTPC | ICE_PKT_OUTER_IPV6), ICE_PKT_PROFILE(ipv4_gtpu_ipv4, ICE_PKT_TUN_GTPC), + ICE_PKT_PROFILE(pfcp_session_ipv6, ICE_PKT_PFCP | ICE_PKT_OUTER_IPV6), + ICE_PKT_PROFILE(pfcp_session_ipv4, ICE_PKT_PFCP), ICE_PKT_PROFILE(pppoe_ipv6_udp, ICE_PKT_PPPOE | ICE_PKT_OUTER_IPV6 | ICE_PKT_INNER_UDP), ICE_PKT_PROFILE(pppoe_ipv6_tcp, ICE_PKT_PPPOE | ICE_PKT_OUTER_IPV6), @@ -4532,6 +4606,7 @@ static const struct ice_prot_ext_tbl_entry ice_prot_ext[ICE_PROTOCOL_LAST] = { ICE_PROTOCOL_ENTRY(ICE_NVGRE, 0, 2, 4, 6), ICE_PROTOCOL_ENTRY(ICE_GTP, 8, 10, 12, 14, 16, 18, 20, 22), ICE_PROTOCOL_ENTRY(ICE_GTP_NO_PAY, 8, 10, 12, 14), + ICE_PROTOCOL_ENTRY(ICE_PFCP, 8, 10, 12, 14, 16, 18, 20, 22), ICE_PROTOCOL_ENTRY(ICE_PPPOE, 0, 2, 4, 6), ICE_PROTOCOL_ENTRY(ICE_L2TPV3, 0, 2, 4, 6, 8, 10), ICE_PROTOCOL_ENTRY(ICE_VLAN_EX, 2, 0), @@ -4565,6 +4640,7 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { { ICE_NVGRE, ICE_GRE_OF_HW }, { ICE_GTP, ICE_UDP_OF_HW }, { ICE_GTP_NO_PAY, ICE_UDP_ILOS_HW }, + { ICE_PFCP, ICE_UDP_ILOS_HW }, { ICE_PPPOE, ICE_PPPOE_HW }, { ICE_L2TPV3, ICE_L2TPV3_HW }, { ICE_VLAN_EX, ICE_VLAN_OF_HW }, @@ -5272,6 +5348,9 @@ ice_get_compat_fv_bitmap(struct ice_hw *hw, struct ice_adv_rule_info *rinfo, case ICE_SW_TUN_GTPC: prof_type = ICE_PROF_TUN_GTPC; break; + case ICE_SW_TUN_PFCP: + prof_type = ICE_PROF_TUN_PFCP; + break; case ICE_SW_TUN_AND_NON_TUN: default: prof_type = ICE_PROF_ALL; @@ -5556,6 +5635,9 @@ ice_find_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, case ICE_SW_TUN_VXLAN: match |= ICE_PKT_TUN_UDP; break; + case ICE_SW_TUN_PFCP: + match |= ICE_PKT_PFCP; + break; default: break; } @@ -5696,6 +5778,9 @@ ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, case ICE_GTP: len = sizeof(struct ice_udp_gtp_hdr); break; + case ICE_PFCP: + len = sizeof(struct ice_pfcp_hdr); + break; case ICE_PPPOE: len = sizeof(struct ice_pppoe_hdr); break; diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index 89e6b18975ef..322ef81d3913 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -22,6 +22,8 @@ #define ICE_PROFID_IPV6_GTPC_NO_TEID 45 #define ICE_PROFID_IPV6_GTPU_TEID 46 #define ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER 70 +#define ICE_PROFID_IPV4_PFCP_NODE 79 +#define ICE_PROFID_IPV6_PFCP_SESSION 82 #define ICE_SW_RULE_VSI_LIST_SIZE(s, n) struct_size((s), vsi, (n)) #define ICE_SW_RULE_RX_TX_HDR_SIZE(s, l) struct_size((s), hdr_data, (l)) diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index b890410a2bc0..2f2fce285ecd 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -35,7 +35,10 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, if (flags & ICE_TC_FLWR_FIELD_ENC_DST_MAC) lkups_cnt++; - if (flags & ICE_TC_FLWR_FIELD_ENC_OPTS) + if (flags & ICE_TC_FLWR_FIELD_GTP_OPTS) + lkups_cnt++; + + if (flags & ICE_TC_FLWR_FIELD_PFCP_OPTS) lkups_cnt++; if (flags & (ICE_TC_FLWR_FIELD_ENC_SRC_IPV4 | @@ -138,6 +141,8 @@ ice_proto_type_from_tunnel(enum ice_tunnel_type type) return ICE_GTP; case TNL_GTPC: return ICE_GTP_NO_PAY; + case TNL_PFCP: + return ICE_PFCP; default: return 0; } @@ -157,6 +162,8 @@ ice_sw_type_from_tunnel(enum ice_tunnel_type type) return ICE_SW_TUN_GTPU; case TNL_GTPC: return ICE_SW_TUN_GTPC; + case TNL_PFCP: + return ICE_SW_TUN_PFCP; default: return ICE_NON_TUN; } @@ -219,8 +226,7 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, i++; } - if (flags & ICE_TC_FLWR_FIELD_ENC_OPTS && - (fltr->tunnel_type == TNL_GTPU || fltr->tunnel_type == TNL_GTPC)) { + if (flags & ICE_TC_FLWR_FIELD_GTP_OPTS) { list[i].type = ice_proto_type_from_tunnel(fltr->tunnel_type); if (fltr->gtp_pdu_info_masks.pdu_type) { @@ -237,6 +243,22 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, i++; } + if (flags & ICE_TC_FLWR_FIELD_PFCP_OPTS) { + struct ice_pfcp_hdr *hdr_h, *hdr_m; + + hdr_h = &list[i].h_u.pfcp_hdr; + hdr_m = &list[i].m_u.pfcp_hdr; + list[i].type = ICE_PFCP; + + hdr_h->flags = fltr->pfcp_meta_keys.type; + hdr_m->flags = fltr->pfcp_meta_masks.type & 0x01; + + hdr_h->seid = fltr->pfcp_meta_keys.seid; + hdr_m->seid = fltr->pfcp_meta_masks.seid; + + i++; + } + if (flags & (ICE_TC_FLWR_FIELD_ENC_SRC_IPV4 | ICE_TC_FLWR_FIELD_ENC_DEST_IPV4)) { list[i].type = ice_proto_type_from_ipv4(false); @@ -367,8 +389,11 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, if (tc_fltr->tunnel_type != TNL_LAST) { i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list, i); - headers = &tc_fltr->inner_headers; - inner = true; + /* PFCP is considered non-tunneled - don't swap headers. */ + if (tc_fltr->tunnel_type != TNL_PFCP) { + headers = &tc_fltr->inner_headers; + inner = true; + } } if (flags & ICE_TC_FLWR_FIELD_ETH_TYPE_ID) { @@ -622,6 +647,8 @@ static int ice_tc_tun_get_type(struct net_device *tunnel_dev) */ if (netif_is_gtp(tunnel_dev)) return TNL_GTPU; + if (netif_is_pfcp(tunnel_dev)) + return TNL_PFCP; return TNL_LAST; } @@ -1401,7 +1428,8 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, } } - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS) && + (fltr->tunnel_type == TNL_GTPU || fltr->tunnel_type == TNL_GTPC)) { struct flow_match_enc_opts match; flow_rule_match_enc_opts(rule, &match); @@ -1412,7 +1440,21 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, memcpy(&fltr->gtp_pdu_info_masks, &match.mask->data[0], sizeof(struct gtp_pdu_session_info)); - fltr->flags |= ICE_TC_FLWR_FIELD_ENC_OPTS; + fltr->flags |= ICE_TC_FLWR_FIELD_GTP_OPTS; + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS) && + fltr->tunnel_type == TNL_PFCP) { + struct flow_match_enc_opts match; + + flow_rule_match_enc_opts(rule, &match); + + memcpy(&fltr->pfcp_meta_keys, match.key->data, + sizeof(struct pfcp_metadata)); + memcpy(&fltr->pfcp_meta_masks, match.mask->data, + sizeof(struct pfcp_metadata)); + + fltr->flags |= ICE_TC_FLWR_FIELD_PFCP_OPTS; } return 0; @@ -1473,10 +1515,14 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, return err; } - /* header pointers should point to the inner headers, outer - * header were already set by ice_parse_tunnel_attr - */ - headers = &fltr->inner_headers; + /* PFCP is considered non-tunneled - don't swap headers. */ + if (fltr->tunnel_type != TNL_PFCP) { + /* Header pointers should point to the inner headers, + * outer header were already set by + * ice_parse_tunnel_attr(). + */ + headers = &fltr->inner_headers; + } } else if (dissector->used_keys & (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h index 65d387163a46..d84f153517ec 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h @@ -4,6 +4,9 @@ #ifndef _ICE_TC_LIB_H_ #define _ICE_TC_LIB_H_ +#include <linux/bits.h> +#include <net/pfcp.h> + #define ICE_TC_FLWR_FIELD_DST_MAC BIT(0) #define ICE_TC_FLWR_FIELD_SRC_MAC BIT(1) #define ICE_TC_FLWR_FIELD_VLAN BIT(2) @@ -22,7 +25,7 @@ #define ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT BIT(15) #define ICE_TC_FLWR_FIELD_ENC_DST_MAC BIT(16) #define ICE_TC_FLWR_FIELD_ETH_TYPE_ID BIT(17) -#define ICE_TC_FLWR_FIELD_ENC_OPTS BIT(18) +#define ICE_TC_FLWR_FIELD_GTP_OPTS BIT(18) #define ICE_TC_FLWR_FIELD_CVLAN BIT(19) #define ICE_TC_FLWR_FIELD_PPPOE_SESSID BIT(20) #define ICE_TC_FLWR_FIELD_PPP_PROTO BIT(21) @@ -34,6 +37,7 @@ #define ICE_TC_FLWR_FIELD_VLAN_PRIO BIT(27) #define ICE_TC_FLWR_FIELD_CVLAN_PRIO BIT(28) #define ICE_TC_FLWR_FIELD_VLAN_TPID BIT(29) +#define ICE_TC_FLWR_FIELD_PFCP_OPTS BIT(30) #define ICE_TC_FLOWER_MASK_32 0xFFFFFFFF @@ -161,6 +165,8 @@ struct ice_tc_flower_fltr { __be32 tenant_id; struct gtp_pdu_session_info gtp_pdu_info_keys; struct gtp_pdu_session_info gtp_pdu_info_masks; + struct pfcp_metadata pfcp_meta_keys; + struct pfcp_metadata pfcp_meta_masks; u32 flags; u8 tunnel_type; struct ice_tc_flower_action action; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 987dd9c7206d..43e7e75ae18c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -10061,15 +10061,10 @@ static int ixgbe_ndo_bridge_setlink(struct net_device *dev, if (!br_spec) return -EINVAL; - nla_for_each_nested(attr, br_spec, rem) { - int status; - __u16 mode; + nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) { + __u16 mode = nla_get_u16(attr); + int status = ixgbe_configure_bridge_mode(adapter, mode); - if (nla_type(attr) != IFLA_BRIDGE_MODE) - continue; - - mode = nla_get_u16(attr); - status = ixgbe_configure_bridge_mode(adapter, mode); if (status) return status; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index eb2a20b5a0d0..3d801a1a4f70 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -1213,10 +1213,8 @@ struct nix_bp_cfg_req { /* bpid_per_chan = 1 assigns separate bp id for each channel */ }; -/* PF can be mapped to either CGX or LBK interface, - * so maximum 64 channels are possible. - */ -#define NIX_MAX_BPID_CHAN 64 +/* Maximum channels any single NIX interface can have */ +#define NIX_MAX_BPID_CHAN 256 struct nix_bp_cfg_rsp { struct mbox_msghdr hdr; u16 chan_bpid[NIX_MAX_BPID_CHAN]; /* Channel and bpid mapping */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index b40bd0e46751..5d8359b54098 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -450,7 +450,6 @@ static void otx2_pfvf_mbox_handler(struct work_struct *work) struct mbox_msghdr *msg = NULL; int offset, vf_idx, id, err; struct otx2_mbox_dev *mdev; - struct mbox_hdr *req_hdr; struct otx2_mbox *mbox; struct mbox *vf_mbox; struct otx2_nic *pf; @@ -461,9 +460,8 @@ static void otx2_pfvf_mbox_handler(struct work_struct *work) mbox = &pf->mbox_pfvf[0].mbox; mdev = &mbox->dev[vf_idx]; - req_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); - offset = ALIGN(sizeof(*req_hdr), MBOX_MSG_ALIGN); + offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN); for (id = 0; id < vf_mbox->num_msgs; id++) { msg = (struct mbox_msghdr *)(mdev->mbase + mbox->rx_start + @@ -494,7 +492,6 @@ static void otx2_pfvf_mbox_up_handler(struct work_struct *work) struct otx2_nic *pf = vf_mbox->pfvf; struct otx2_mbox_dev *mdev; int offset, id, vf_idx = 0; - struct mbox_hdr *rsp_hdr; struct mbox_msghdr *msg; struct otx2_mbox *mbox; @@ -502,8 +499,7 @@ static void otx2_pfvf_mbox_up_handler(struct work_struct *work) mbox = &pf->mbox_pfvf[0].mbox_up; mdev = &mbox->dev[vf_idx]; - rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); - offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN); + offset = mbox->rx_start + ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN); for (id = 0; id < vf_mbox->up_num_msgs; id++) { msg = mdev->mbase + offset; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h index 92065568bb19..6873c1201803 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h @@ -117,7 +117,7 @@ bool mlx5e_tc_tun_encap_info_equal_generic(struct mlx5e_encap_key *a, bool mlx5e_tc_tun_encap_info_equal_options(struct mlx5e_encap_key *a, struct mlx5e_encap_key *b, - __be16 tun_flags); + u32 tun_type); #endif /* CONFIG_MLX5_ESWITCH */ #endif //__MLX5_EN_TC_TUNNEL_H__ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index f1d1e1542e81..878cbdbf5ec8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -587,7 +587,7 @@ bool mlx5e_tc_tun_encap_info_equal_generic(struct mlx5e_encap_key *a, bool mlx5e_tc_tun_encap_info_equal_options(struct mlx5e_encap_key *a, struct mlx5e_encap_key *b, - __be16 tun_flags) + u32 tun_type) { struct ip_tunnel_info *a_info; struct ip_tunnel_info *b_info; @@ -596,8 +596,8 @@ bool mlx5e_tc_tun_encap_info_equal_options(struct mlx5e_encap_key *a, if (!mlx5e_tc_tun_encap_info_equal_generic(a, b)) return false; - a_has_opts = !!(a->ip_tun_key->tun_flags & tun_flags); - b_has_opts = !!(b->ip_tun_key->tun_flags & tun_flags); + a_has_opts = test_bit(tun_type, a->ip_tun_key->tun_flags); + b_has_opts = test_bit(tun_type, b->ip_tun_key->tun_flags); /* keys are equal when both don't have any options attached */ if (!a_has_opts && !b_has_opts) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c index 2bcd10b6d653..bf969212cc77 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c @@ -106,12 +106,13 @@ static int mlx5e_gen_ip_tunnel_header_geneve(char buf[], memset(geneveh, 0, sizeof(*geneveh)); geneveh->ver = MLX5E_GENEVE_VER; geneveh->opt_len = tun_info->options_len / 4; - geneveh->oam = !!(tun_info->key.tun_flags & TUNNEL_OAM); - geneveh->critical = !!(tun_info->key.tun_flags & TUNNEL_CRIT_OPT); + geneveh->oam = test_bit(IP_TUNNEL_OAM_BIT, tun_info->key.tun_flags); + geneveh->critical = test_bit(IP_TUNNEL_CRIT_OPT_BIT, + tun_info->key.tun_flags); mlx5e_tunnel_id_to_vni(tun_info->key.tun_id, geneveh->vni); geneveh->proto_type = htons(ETH_P_TEB); - if (tun_info->key.tun_flags & TUNNEL_GENEVE_OPT) { + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_info->key.tun_flags)) { if (!geneveh->opt_len) return -EOPNOTSUPP; ip_tunnel_info_opts_get(geneveh->options, tun_info); @@ -188,7 +189,7 @@ static int mlx5e_tc_tun_parse_geneve_options(struct mlx5e_priv *priv, /* make sure that we're talking about GENEVE options */ - if (enc_opts.key->dst_opt_type != TUNNEL_GENEVE_OPT) { + if (enc_opts.key->dst_opt_type != IP_TUNNEL_GENEVE_OPT_BIT) { NL_SET_ERR_MSG_MOD(extack, "Matching on GENEVE options: option type is not GENEVE"); netdev_warn(priv->netdev, @@ -337,7 +338,8 @@ static int mlx5e_tc_tun_parse_geneve(struct mlx5e_priv *priv, static bool mlx5e_tc_tun_encap_info_equal_geneve(struct mlx5e_encap_key *a, struct mlx5e_encap_key *b) { - return mlx5e_tc_tun_encap_info_equal_options(a, b, TUNNEL_GENEVE_OPT); + return mlx5e_tc_tun_encap_info_equal_options(a, b, + IP_TUNNEL_GENEVE_OPT_BIT); } struct mlx5e_tc_tunnel geneve_tunnel = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c index ada14f0574dc..579eda89fc76 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c @@ -31,12 +31,16 @@ static int mlx5e_gen_ip_tunnel_header_gretap(char buf[], const struct ip_tunnel_key *tun_key = &e->tun_info->key; struct gre_base_hdr *greh = (struct gre_base_hdr *)(buf); __be32 tun_id = tunnel_id_to_key32(tun_key->tun_id); + IP_TUNNEL_DECLARE_FLAGS(unsupp) = { }; int hdr_len; *ip_proto = IPPROTO_GRE; /* the HW does not calculate GRE csum or sequences */ - if (tun_key->tun_flags & (TUNNEL_CSUM | TUNNEL_SEQ)) + __set_bit(IP_TUNNEL_CSUM_BIT, unsupp); + __set_bit(IP_TUNNEL_SEQ_BIT, unsupp); + + if (ip_tunnel_flags_intersect(tun_key->tun_flags, unsupp)) return -EOPNOTSUPP; greh->protocol = htons(ETH_P_TEB); @@ -44,7 +48,7 @@ static int mlx5e_gen_ip_tunnel_header_gretap(char buf[], /* GRE key */ hdr_len = mlx5e_tc_tun_calc_hlen_gretap(e); greh->flags = gre_tnl_flags_to_gre_flags(tun_key->tun_flags); - if (tun_key->tun_flags & TUNNEL_KEY) { + if (test_bit(IP_TUNNEL_KEY_BIT, tun_key->tun_flags)) { __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); *ptr = tun_id; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c index a184d739d5f8..e4e487c8431b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c @@ -90,7 +90,7 @@ static int mlx5e_gen_ip_tunnel_header_vxlan(char buf[], const struct vxlan_metadata *md; struct vxlanhdr *vxh; - if ((tun_key->tun_flags & TUNNEL_VXLAN_OPT) && + if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_key->tun_flags) && e->tun_info->options_len != sizeof(*md)) return -EOPNOTSUPP; vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr)); @@ -99,7 +99,7 @@ static int mlx5e_gen_ip_tunnel_header_vxlan(char buf[], udp->dest = tun_key->tp_dst; vxh->vx_flags = VXLAN_HF_VNI; vxh->vx_vni = vxlan_vni_field(tun_id); - if (tun_key->tun_flags & TUNNEL_VXLAN_OPT) { + if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_key->tun_flags)) { md = ip_tunnel_info_opts(e->tun_info); vxlan_build_gbp_hdr(vxh, md); } @@ -125,7 +125,7 @@ static int mlx5e_tc_tun_parse_vxlan_gbp_option(struct mlx5e_priv *priv, return -EOPNOTSUPP; } - if (enc_opts.key->dst_opt_type != TUNNEL_VXLAN_OPT) { + if (enc_opts.key->dst_opt_type != IP_TUNNEL_VXLAN_OPT_BIT) { NL_SET_ERR_MSG_MOD(extack, "Wrong VxLAN option type: not GBP"); return -EOPNOTSUPP; } @@ -208,7 +208,8 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv, static bool mlx5e_tc_tun_encap_info_equal_vxlan(struct mlx5e_encap_key *a, struct mlx5e_encap_key *b) { - return mlx5e_tc_tun_encap_info_equal_options(a, b, TUNNEL_VXLAN_OPT); + return mlx5e_tc_tun_encap_info_equal_options(a, b, + IP_TUNNEL_VXLAN_OPT_BIT); } static int mlx5e_tc_tun_get_remote_ifindex(struct net_device *mirred_dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index 06592b9f0424..9240cfe25d10 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -28,8 +28,10 @@ bool mlx5e_validate_xsk_param(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, struct mlx5_core_dev *mdev) { - /* AF_XDP doesn't support frames larger than PAGE_SIZE. */ - if (xsk->chunk_size > PAGE_SIZE || xsk->chunk_size < MLX5E_MIN_XSK_CHUNK_SIZE) { + /* AF_XDP doesn't support frames larger than PAGE_SIZE, + * and xsk->chunk_size is limited to 65535 bytes. + */ + if ((size_t)xsk->chunk_size > PAGE_SIZE || xsk->chunk_size < MLX5E_MIN_XSK_CHUNK_SIZE) { mlx5_core_err(mdev, "XSK chunk size %u out of bounds [%u, %lu]\n", xsk->chunk_size, MLX5E_MIN_XSK_CHUNK_SIZE, PAGE_SIZE); return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 91848eae4565..81e1c1e401f9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4950,10 +4950,7 @@ static int mlx5e_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, if (!br_spec) return -EINVAL; - nla_for_each_nested(attr, br_spec, rem) { - if (nla_type(attr) != IFLA_BRIDGE_MODE) - continue; - + nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) { mode = nla_get_u16(attr); if (mode > BRIDGE_MODE_VEPA) return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 31ed26cac9bf..f2f19fa37d91 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -5464,6 +5464,7 @@ static bool mlx5e_tc_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct tunnel_match_enc_opts enc_opts = {}; struct mlx5_rep_uplink_priv *uplink_priv; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct mlx5e_rep_priv *uplink_rpriv; struct metadata_dst *tun_dst; struct tunnel_match_key key; @@ -5471,6 +5472,8 @@ static bool mlx5e_tc_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb struct net_device *dev; int err; + __set_bit(IP_TUNNEL_KEY_BIT, flags); + enc_opts_id = tunnel_id & ENC_OPTS_BITS_MASK; tun_id = tunnel_id >> ENC_OPTS_BITS; @@ -5503,14 +5506,14 @@ static bool mlx5e_tc_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb case FLOW_DISSECTOR_KEY_IPV4_ADDRS: tun_dst = __ip_tun_set_dst(key.enc_ipv4.src, key.enc_ipv4.dst, key.enc_ip.tos, key.enc_ip.ttl, - key.enc_tp.dst, TUNNEL_KEY, + key.enc_tp.dst, flags, key32_to_tunnel_id(key.enc_key_id.keyid), enc_opts.key.len); break; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: tun_dst = __ipv6_tun_set_dst(&key.enc_ipv6.src, &key.enc_ipv6.dst, key.enc_ip.tos, key.enc_ip.ttl, - key.enc_tp.dst, 0, TUNNEL_KEY, + key.enc_tp.dst, 0, flags, key32_to_tunnel_id(key.enc_key_id.keyid), enc_opts.key.len); break; @@ -5528,11 +5531,16 @@ static bool mlx5e_tc_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb tun_dst->u.tun_info.key.tp_src = key.enc_tp.src; - if (enc_opts.key.len) + if (enc_opts.key.len) { + ip_tunnel_flags_zero(flags); + if (enc_opts.key.dst_opt_type) + __set_bit(enc_opts.key.dst_opt_type, flags); + ip_tunnel_info_opts_set(&tun_dst->u.tun_info, enc_opts.key.data, enc_opts.key.len, - enc_opts.key.dst_opt_type); + flags); + } skb_dst_set(skb, (struct dst_entry *)tun_dst); dev = dev_get_by_index(&init_net, key.filter_ifindex); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index 1b9bc32efd6f..c5ea1d1d2b03 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -1874,7 +1874,7 @@ int mlx5_esw_bridge_port_mdb_add(struct net_device *dev, u16 vport_num, u16 esw_ "Failed to lookup bridge port vlan metadata to create MDB (MAC=%pM,vid=%u,vport=%u)\n", addr, vid, vport_num); NL_SET_ERR_MSG_FMT_MOD(extack, - "Failed to lookup bridge port vlan metadata to create MDB (MAC=%pM,vid=%u,vport=%u)\n", + "Failed to lookup vlan metadata for MDB (MAC=%pM,vid=%u,vport=%u)\n", addr, vid, vport_num); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c index 3340b4a694c3..d761a1235994 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c @@ -8,7 +8,7 @@ #include "spectrum_ipip.h" #include "reg.h" -struct ip_tunnel_parm +struct ip_tunnel_parm_kern mlxsw_sp_ipip_netdev_parms4(const struct net_device *ol_dev) { struct ip_tunnel *tun = netdev_priv(ol_dev); @@ -24,27 +24,29 @@ mlxsw_sp_ipip_netdev_parms6(const struct net_device *ol_dev) return tun->parms; } -static bool mlxsw_sp_ipip_parms4_has_ikey(const struct ip_tunnel_parm *parms) +static bool +mlxsw_sp_ipip_parms4_has_ikey(const struct ip_tunnel_parm_kern *parms) { - return !!(parms->i_flags & TUNNEL_KEY); + return test_bit(IP_TUNNEL_KEY_BIT, parms->i_flags); } static bool mlxsw_sp_ipip_parms6_has_ikey(const struct __ip6_tnl_parm *parms) { - return !!(parms->i_flags & TUNNEL_KEY); + return test_bit(IP_TUNNEL_KEY_BIT, parms->i_flags); } -static bool mlxsw_sp_ipip_parms4_has_okey(const struct ip_tunnel_parm *parms) +static bool +mlxsw_sp_ipip_parms4_has_okey(const struct ip_tunnel_parm_kern *parms) { - return !!(parms->o_flags & TUNNEL_KEY); + return test_bit(IP_TUNNEL_KEY_BIT, parms->o_flags); } static bool mlxsw_sp_ipip_parms6_has_okey(const struct __ip6_tnl_parm *parms) { - return !!(parms->o_flags & TUNNEL_KEY); + return test_bit(IP_TUNNEL_KEY_BIT, parms->o_flags); } -static u32 mlxsw_sp_ipip_parms4_ikey(const struct ip_tunnel_parm *parms) +static u32 mlxsw_sp_ipip_parms4_ikey(const struct ip_tunnel_parm_kern *parms) { return mlxsw_sp_ipip_parms4_has_ikey(parms) ? be32_to_cpu(parms->i_key) : 0; @@ -56,7 +58,7 @@ static u32 mlxsw_sp_ipip_parms6_ikey(const struct __ip6_tnl_parm *parms) be32_to_cpu(parms->i_key) : 0; } -static u32 mlxsw_sp_ipip_parms4_okey(const struct ip_tunnel_parm *parms) +static u32 mlxsw_sp_ipip_parms4_okey(const struct ip_tunnel_parm_kern *parms) { return mlxsw_sp_ipip_parms4_has_okey(parms) ? be32_to_cpu(parms->o_key) : 0; @@ -69,7 +71,7 @@ static u32 mlxsw_sp_ipip_parms6_okey(const struct __ip6_tnl_parm *parms) } static union mlxsw_sp_l3addr -mlxsw_sp_ipip_parms4_saddr(const struct ip_tunnel_parm *parms) +mlxsw_sp_ipip_parms4_saddr(const struct ip_tunnel_parm_kern *parms) { return (union mlxsw_sp_l3addr) { .addr4 = parms->iph.saddr }; } @@ -81,7 +83,7 @@ mlxsw_sp_ipip_parms6_saddr(const struct __ip6_tnl_parm *parms) } static union mlxsw_sp_l3addr -mlxsw_sp_ipip_parms4_daddr(const struct ip_tunnel_parm *parms) +mlxsw_sp_ipip_parms4_daddr(const struct ip_tunnel_parm_kern *parms) { return (union mlxsw_sp_l3addr) { .addr4 = parms->iph.daddr }; } @@ -96,7 +98,7 @@ union mlxsw_sp_l3addr mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto, const struct net_device *ol_dev) { - struct ip_tunnel_parm parms4; + struct ip_tunnel_parm_kern parms4; struct __ip6_tnl_parm parms6; switch (proto) { @@ -115,7 +117,9 @@ mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto, static __be32 mlxsw_sp_ipip_netdev_daddr4(const struct net_device *ol_dev) { - struct ip_tunnel_parm parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); + struct ip_tunnel_parm_kern parms4; + + parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); return mlxsw_sp_ipip_parms4_daddr(&parms4).addr4; } @@ -124,7 +128,7 @@ static union mlxsw_sp_l3addr mlxsw_sp_ipip_netdev_daddr(enum mlxsw_sp_l3proto proto, const struct net_device *ol_dev) { - struct ip_tunnel_parm parms4; + struct ip_tunnel_parm_kern parms4; struct __ip6_tnl_parm parms6; switch (proto) { @@ -150,7 +154,7 @@ bool mlxsw_sp_l3addr_is_zero(union mlxsw_sp_l3addr addr) static struct mlxsw_sp_ipip_parms mlxsw_sp_ipip_netdev_parms_init_gre4(const struct net_device *ol_dev) { - struct ip_tunnel_parm parms = mlxsw_sp_ipip_netdev_parms4(ol_dev); + struct ip_tunnel_parm_kern parms = mlxsw_sp_ipip_netdev_parms4(ol_dev); return (struct mlxsw_sp_ipip_parms) { .proto = MLXSW_SP_L3_PROTO_IPV4, @@ -187,8 +191,8 @@ mlxsw_sp_ipip_decap_config_gre4(struct mlxsw_sp *mlxsw_sp, { u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb); u16 ul_rif_id = mlxsw_sp_ipip_lb_ul_rif_id(ipip_entry->ol_lb); + struct ip_tunnel_parm_kern parms; char rtdp_pl[MLXSW_REG_RTDP_LEN]; - struct ip_tunnel_parm parms; unsigned int type_check; bool has_ikey; u32 daddr4; @@ -238,12 +242,15 @@ static bool mlxsw_sp_ipip_can_offload_gre4(const struct mlxsw_sp *mlxsw_sp, const struct net_device *ol_dev) { struct ip_tunnel *tunnel = netdev_priv(ol_dev); - __be16 okflags = TUNNEL_KEY; /* We can't offload any other features. */ bool inherit_ttl = tunnel->parms.iph.ttl == 0; bool inherit_tos = tunnel->parms.iph.tos & 0x1; + IP_TUNNEL_DECLARE_FLAGS(okflags) = { }; + + /* We can't offload any other features. */ + __set_bit(IP_TUNNEL_KEY_BIT, okflags); - return (tunnel->parms.i_flags & ~okflags) == 0 && - (tunnel->parms.o_flags & ~okflags) == 0 && + return ip_tunnel_flags_subset(tunnel->parms.i_flags, okflags) && + ip_tunnel_flags_subset(tunnel->parms.o_flags, okflags) && inherit_ttl && inherit_tos && mlxsw_sp_ipip_tunnel_complete(MLXSW_SP_L3_PROTO_IPV4, ol_dev); } @@ -252,7 +259,7 @@ static struct mlxsw_sp_rif_ipip_lb_config mlxsw_sp_ipip_ol_loopback_config_gre4(struct mlxsw_sp *mlxsw_sp, const struct net_device *ol_dev) { - struct ip_tunnel_parm parms = mlxsw_sp_ipip_netdev_parms4(ol_dev); + struct ip_tunnel_parm_kern parms = mlxsw_sp_ipip_netdev_parms4(ol_dev); enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt; lb_ipipt = mlxsw_sp_ipip_parms4_has_okey(&parms) ? @@ -439,10 +446,13 @@ static bool mlxsw_sp_ipip_can_offload_gre6(const struct mlxsw_sp *mlxsw_sp, struct __ip6_tnl_parm tparm = mlxsw_sp_ipip_netdev_parms6(ol_dev); bool inherit_tos = tparm.flags & IP6_TNL_F_USE_ORIG_TCLASS; bool inherit_ttl = tparm.hop_limit == 0; - __be16 okflags = TUNNEL_KEY; /* We can't offload any other features. */ + IP_TUNNEL_DECLARE_FLAGS(okflags) = { }; + + /* We can't offload any other features. */ + __set_bit(IP_TUNNEL_KEY_BIT, okflags); - return (tparm.i_flags & ~okflags) == 0 && - (tparm.o_flags & ~okflags) == 0 && + return ip_tunnel_flags_subset(tparm.i_flags, okflags) && + ip_tunnel_flags_subset(tparm.o_flags, okflags) && inherit_ttl && inherit_tos && mlxsw_sp_ipip_tunnel_complete(MLXSW_SP_L3_PROTO_IPV6, ol_dev); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h index a35f009da561..a66173779641 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h @@ -9,7 +9,7 @@ #include <linux/if_tunnel.h> #include <net/ip6_tunnel.h> -struct ip_tunnel_parm +struct ip_tunnel_parm_kern mlxsw_sp_ipip_netdev_parms4(const struct net_device *ol_dev); struct __ip6_tnl_parm mlxsw_sp_ipip_netdev_parms6(const struct net_device *ol_dev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index af50ff9e5f26..3de69b2eb5c4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -413,8 +413,8 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev, __be32 *saddrp, __be32 *daddrp) { struct ip_tunnel *tun = netdev_priv(to_dev); + struct ip_tunnel_parm_kern parms; struct net_device *dev = NULL; - struct ip_tunnel_parm parms; struct rtable *rt = NULL; struct flowi4 fl4; @@ -451,7 +451,7 @@ mlxsw_sp_span_entry_gretap4_parms(struct mlxsw_sp *mlxsw_sp, const struct net_device *to_dev, struct mlxsw_sp_span_parms *sparmsp) { - struct ip_tunnel_parm tparm = mlxsw_sp_ipip_netdev_parms4(to_dev); + struct ip_tunnel_parm_kern tparm = mlxsw_sp_ipip_netdev_parms4(to_dev); union mlxsw_sp_l3addr saddr = { .addr4 = tparm.iph.saddr }; union mlxsw_sp_l3addr daddr = { .addr4 = tparm.iph.daddr }; bool inherit_tos = tparm.iph.tos & 0x1; @@ -461,7 +461,8 @@ mlxsw_sp_span_entry_gretap4_parms(struct mlxsw_sp *mlxsw_sp, if (!(to_dev->flags & IFF_UP) || /* Reject tunnels with GRE keys, checksums, etc. */ - tparm.i_flags || tparm.o_flags || + !ip_tunnel_flags_empty(tparm.i_flags) || + !ip_tunnel_flags_empty(tparm.o_flags) || /* Require a fixed TTL and a TOS copied from the mirrored packet. */ inherit_ttl || !inherit_tos || /* A destination address may not be "any". */ @@ -565,7 +566,8 @@ mlxsw_sp_span_entry_gretap6_parms(struct mlxsw_sp *mlxsw_sp, if (!(to_dev->flags & IFF_UP) || /* Reject tunnels with GRE keys, checksums, etc. */ - tparm.i_flags || tparm.o_flags || + !ip_tunnel_flags_empty(tparm.i_flags) || + !ip_tunnel_flags_empty(tparm.o_flags) || /* Require a fixed TTL and a TOS copied from the mirrored packet. */ inherit_ttl || !inherit_tos || /* A destination address may not be "any". */ diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c index d7c8aa77ec75..cdc2872ace1b 100644 --- a/drivers/net/ethernet/microchip/encx24j600.c +++ b/drivers/net/ethernet/microchip/encx24j600.c @@ -1112,7 +1112,6 @@ MODULE_DEVICE_TABLE(spi, encx24j600_spi_id_table); static struct spi_driver encx24j600_spi_net_driver = { .driver = { .name = DRV_NAME, - .owner = THIS_MODULE, .bus = &spi_bus_type, }, .probe = encx24j600_spi_probe, diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 2c3f62907958..aca2a7417af3 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -396,6 +396,17 @@ nfp_fl_push_geneve_options(struct nfp_fl_payload *nfp_fl, int *list_len, return 0; } +#define NFP_FL_CHECK(flag) ({ \ + IP_TUNNEL_DECLARE_FLAGS(__check) = { }; \ + __be16 __res; \ + \ + __set_bit(IP_TUNNEL_##flag##_BIT, __check); \ + __res = ip_tunnel_flags_to_be16(__check); \ + \ + BUILD_BUG_ON(__builtin_constant_p(__res) && \ + NFP_FL_TUNNEL_##flag != __res); \ +}) + static int nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun, const struct flow_action_entry *act, @@ -410,6 +421,7 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun, u32 tmp_set_ip_tun_type_index = 0; /* Currently support one pre-tunnel so index is always 0. */ int pretun_idx = 0; + __be16 tun_flags; if (!IS_ENABLED(CONFIG_IPV6) && ipv6) return -EOPNOTSUPP; @@ -417,9 +429,10 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun, if (ipv6 && !(priv->flower_ext_feats & NFP_FL_FEATS_IPV6_TUN)) return -EOPNOTSUPP; - BUILD_BUG_ON(NFP_FL_TUNNEL_CSUM != TUNNEL_CSUM || - NFP_FL_TUNNEL_KEY != TUNNEL_KEY || - NFP_FL_TUNNEL_GENEVE_OPT != TUNNEL_GENEVE_OPT); + NFP_FL_CHECK(CSUM); + NFP_FL_CHECK(KEY); + NFP_FL_CHECK(GENEVE_OPT); + if (ip_tun->options_len && (tun_type != NFP_FL_TUNNEL_GENEVE || !(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE_OPT))) { @@ -427,7 +440,9 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun, return -EOPNOTSUPP; } - if (ip_tun->key.tun_flags & ~NFP_FL_SUPPORTED_UDP_TUN_FLAGS) { + tun_flags = ip_tunnel_flags_to_be16(ip_tun->key.tun_flags); + if (!ip_tunnel_flags_is_be16_compat(ip_tun->key.tun_flags) || + (tun_flags & ~NFP_FL_SUPPORTED_UDP_TUN_FLAGS)) { NL_SET_ERR_MSG_MOD(extack, "unsupported offload: loaded firmware does not support tunnel flag offload"); return -EOPNOTSUPP; @@ -442,7 +457,7 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun, FIELD_PREP(NFP_FL_PRE_TUN_INDEX, pretun_idx); set_tun->tun_type_index = cpu_to_be32(tmp_set_ip_tun_type_index); - if (ip_tun->key.tun_flags & NFP_FL_TUNNEL_KEY) + if (tun_flags & NFP_FL_TUNNEL_KEY) set_tun->tun_id = ip_tun->key.tun_id; if (ip_tun->key.ttl) { @@ -486,7 +501,7 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun, } set_tun->tos = ip_tun->key.tos; - set_tun->tun_flags = ip_tun->key.tun_flags; + set_tun->tun_flags = tun_flags; if (tun_type == NFP_FL_TUNNEL_GENEVE) { set_tun->tun_proto = htons(ETH_P_TEB); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index f28e769e6fda..997cc4fcffdb 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -2289,10 +2289,7 @@ static int nfp_net_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, if (!br_spec) return -EINVAL; - nla_for_each_nested(attr, br_spec, rem) { - if (nla_type(attr) != IFLA_BRIDGE_MODE) - continue; - + nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) { new_ctrl = nn->dp.ctrl; mode = nla_get_u16(attr); if (mode == BRIDGE_MODE_VEPA) diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 408da4312e01..17f284e9f06d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -1205,7 +1205,6 @@ out: static int qed_slowpath_wq_start(struct qed_dev *cdev) { struct qed_hwfn *hwfn; - char name[NAME_SIZE]; int i; if (IS_VF(cdev)) @@ -1214,11 +1213,11 @@ static int qed_slowpath_wq_start(struct qed_dev *cdev) for_each_hwfn(cdev, i) { hwfn = &cdev->hwfns[i]; - snprintf(name, NAME_SIZE, "slowpath-%02x:%02x.%02x", - cdev->pdev->bus->number, - PCI_SLOT(cdev->pdev->devfn), hwfn->abs_pf_id); + hwfn->slowpath_wq = alloc_workqueue("slowpath-%02x:%02x.%02x", + 0, 0, cdev->pdev->bus->number, + PCI_SLOT(cdev->pdev->devfn), + hwfn->abs_pf_id); - hwfn->slowpath_wq = alloc_workqueue(name, 0, 0); if (!hwfn->slowpath_wq) { DP_NOTICE(hwfn, "Cannot create slowpath workqueue\n"); return -ENOMEM; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index 807ead678551..fa5500decc96 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -359,6 +359,7 @@ * @app2: MM2S/S2MM User Application Field 2. * @app3: MM2S/S2MM User Application Field 3. * @app4: MM2S/S2MM User Application Field 4. + * @skb: Pointer to SKB transferred using DMA */ struct axidma_bd { u32 next; /* Physical address of next buffer descriptor */ @@ -399,7 +400,6 @@ struct skbuf_dma_descriptor { * struct axienet_local - axienet private per device data * @ndev: Pointer for net_device to which it will be attached. * @dev: Pointer to device structure - * @phy_node: Pointer to device node structure * @phylink: Pointer to phylink instance * @phylink_config: phylink configuration settings * @pcs_phy: Reference to PCS/PMA PHY if used @@ -537,7 +537,7 @@ struct axienet_local { }; /** - * struct axiethernet_option - Used to set axi ethernet hardware options + * struct axienet_option - Used to set axi ethernet hardware options * @opt: Option to be set. * @reg: Register offset to be written for setting the option * @m_or: Mask to be ORed for setting the option in the register diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c index 2f07fde361aa..9ca2643c921e 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c @@ -20,7 +20,14 @@ #define DEFAULT_MDIO_FREQ 2500000 /* 2.5 MHz */ #define DEFAULT_HOST_CLOCK 150000000 /* 150 MHz */ -/* Wait till MDIO interface is ready to accept a new transaction.*/ +/** + * axienet_mdio_wait_until_ready - MDIO wait function + * @lp: Pointer to axienet local data structure. + * + * Return : 0 on success, Negative value on errors + * + * Wait till MDIO interface is ready to accept a new transaction. + */ static int axienet_mdio_wait_until_ready(struct axienet_local *lp) { u32 val; @@ -30,14 +37,24 @@ static int axienet_mdio_wait_until_ready(struct axienet_local *lp) 1, 20000); } -/* Enable the MDIO MDC. Called prior to a read/write operation */ +/** + * axienet_mdio_mdc_enable - MDIO MDC enable function + * @lp: Pointer to axienet local data structure. + * + * Enable the MDIO MDC. Called prior to a read/write operation + */ static void axienet_mdio_mdc_enable(struct axienet_local *lp) { axienet_iow(lp, XAE_MDIO_MC_OFFSET, ((u32)lp->mii_clk_div | XAE_MDIO_MC_MDIOEN_MASK)); } -/* Disable the MDIO MDC. Called after a read/write operation*/ +/** + * axienet_mdio_mdc_disable - MDIO MDC disable function + * @lp: Pointer to axienet local data structure. + * + * Disable the MDIO MDC. Called after a read/write operation + */ static void axienet_mdio_mdc_disable(struct axienet_local *lp) { u32 mc_reg; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 2f6739fe78af..163f94a5a58f 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -225,10 +225,11 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, void *oiph; if (ip_tunnel_collect_metadata() || gs->collect_md) { - __be16 flags; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; - flags = TUNNEL_KEY | (gnvh->oam ? TUNNEL_OAM : 0) | - (gnvh->critical ? TUNNEL_CRIT_OPT : 0); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + __assign_bit(IP_TUNNEL_OAM_BIT, flags, gnvh->oam); + __assign_bit(IP_TUNNEL_CRIT_OPT_BIT, flags, gnvh->critical); tun_dst = udp_tun_rx_dst(skb, geneve_get_sk_family(gs), flags, vni_to_tunnel_id(gnvh->vni), @@ -238,9 +239,11 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, goto drop; } /* Update tunnel dst according to Geneve options. */ + ip_tunnel_flags_zero(flags); + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, flags); ip_tunnel_info_opts_set(&tun_dst->u.tun_info, gnvh->options, gnvh->opt_len * 4, - TUNNEL_GENEVE_OPT); + flags); } else { /* Drop packets w/ critical options, * since we don't support any... @@ -745,14 +748,15 @@ static void geneve_build_header(struct genevehdr *geneveh, { geneveh->ver = GENEVE_VER; geneveh->opt_len = info->options_len / 4; - geneveh->oam = !!(info->key.tun_flags & TUNNEL_OAM); - geneveh->critical = !!(info->key.tun_flags & TUNNEL_CRIT_OPT); + geneveh->oam = test_bit(IP_TUNNEL_OAM_BIT, info->key.tun_flags); + geneveh->critical = test_bit(IP_TUNNEL_CRIT_OPT_BIT, + info->key.tun_flags); geneveh->rsvd1 = 0; tunnel_id_to_vni(info->key.tun_id, geneveh->vni); geneveh->proto_type = inner_proto; geneveh->rsvd2 = 0; - if (info->key.tun_flags & TUNNEL_GENEVE_OPT) + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) ip_tunnel_info_opts_get(geneveh->options, info); } @@ -761,7 +765,7 @@ static int geneve_build_skb(struct dst_entry *dst, struct sk_buff *skb, bool xnet, int ip_hdr_len, bool inner_proto_inherit) { - bool udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); + bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); struct genevehdr *gnvh; __be16 inner_proto; int min_headroom; @@ -878,7 +882,8 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (geneve->cfg.collect_md) { ttl = key->ttl; - df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; + df = test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) ? + htons(IP_DF) : 0; } else { if (geneve->cfg.ttl_inherit) ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); @@ -910,7 +915,8 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, udp_tunnel_xmit_skb(rt, gs4->sock->sk, skb, saddr, info->key.u.ipv4.dst, tos, ttl, df, sport, geneve->cfg.info.key.tp_dst, !net_eq(geneve->net, dev_net(geneve->dev)), - !(info->key.tun_flags & TUNNEL_CSUM)); + !test_bit(IP_TUNNEL_CSUM_BIT, + info->key.tun_flags)); return 0; } @@ -998,7 +1004,8 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, udp_tunnel6_xmit_skb(dst, gs6->sock->sk, skb, dev, &saddr, &key->u.ipv6.dst, prio, ttl, info->key.label, sport, geneve->cfg.info.key.tp_dst, - !(info->key.tun_flags & TUNNEL_CSUM)); + !test_bit(IP_TUNNEL_CSUM_BIT, + info->key.tun_flags)); return 0; } #endif @@ -1297,7 +1304,8 @@ static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, static bool is_tnl_info_zero(const struct ip_tunnel_info *info) { - return !(info->key.tun_id || info->key.tun_flags || info->key.tos || + return !(info->key.tun_id || info->key.tos || + !ip_tunnel_flags_empty(info->key.tun_flags) || info->key.ttl || info->key.label || info->key.tp_src || memchr_inv(&info->key.u, 0, sizeof(info->key.u))); } @@ -1435,7 +1443,7 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], "Remote IPv6 address cannot be Multicast"); return -EINVAL; } - info->key.tun_flags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); cfg->use_udp6_rx_checksums = true; #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], @@ -1510,7 +1518,7 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_CSUM])) - info->key.tun_flags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); } if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX]) { @@ -1520,7 +1528,7 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX])) - info->key.tun_flags &= ~TUNNEL_CSUM; + __clear_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX], "IPv6 support not enabled in the kernel"); @@ -1753,7 +1761,8 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) info->key.u.ipv4.dst)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_UDP_CSUM, - !!(info->key.tun_flags & TUNNEL_CSUM))) + test_bit(IP_TUNNEL_CSUM_BIT, + info->key.tun_flags))) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) @@ -1762,7 +1771,8 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) &info->key.u.ipv6.dst)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_TX, - !(info->key.tun_flags & TUNNEL_CSUM))) + !test_bit(IP_TUNNEL_CSUM_BIT, + info->key.tun_flags))) goto nla_put_failure; #endif } diff --git a/drivers/net/pfcp.c b/drivers/net/pfcp.c new file mode 100644 index 000000000000..cc5b28c5f99f --- /dev/null +++ b/drivers/net/pfcp.c @@ -0,0 +1,302 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * PFCP according to 3GPP TS 29.244 + * + * Copyright (C) 2022, Intel Corporation. + */ + +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/rculist.h> +#include <linux/skbuff.h> +#include <linux/types.h> + +#include <net/udp.h> +#include <net/udp_tunnel.h> +#include <net/pfcp.h> + +struct pfcp_dev { + struct list_head list; + + struct socket *sock; + struct net_device *dev; + struct net *net; + + struct gro_cells gro_cells; +}; + +static unsigned int pfcp_net_id __read_mostly; + +struct pfcp_net { + struct list_head pfcp_dev_list; +}; + +static void +pfcp_session_recv(struct pfcp_dev *pfcp, struct sk_buff *skb, + struct pfcp_metadata *md) +{ + struct pfcphdr_session *unparsed = pfcp_hdr_session(skb); + + md->seid = unparsed->seid; + md->type = PFCP_TYPE_SESSION; +} + +static void +pfcp_node_recv(struct pfcp_dev *pfcp, struct sk_buff *skb, + struct pfcp_metadata *md) +{ + md->type = PFCP_TYPE_NODE; +} + +static int pfcp_encap_recv(struct sock *sk, struct sk_buff *skb) +{ + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; + struct metadata_dst *tun_dst; + struct pfcp_metadata *md; + struct pfcphdr *unparsed; + struct pfcp_dev *pfcp; + + if (unlikely(!pskb_may_pull(skb, PFCP_HLEN))) + goto drop; + + pfcp = rcu_dereference_sk_user_data(sk); + if (unlikely(!pfcp)) + goto drop; + + unparsed = pfcp_hdr(skb); + + ip_tunnel_flags_zero(flags); + tun_dst = udp_tun_rx_dst(skb, sk->sk_family, flags, 0, + sizeof(*md)); + if (unlikely(!tun_dst)) + goto drop; + + md = ip_tunnel_info_opts(&tun_dst->u.tun_info); + if (unlikely(!md)) + goto drop; + + if (unparsed->flags & PFCP_SEID_FLAG) + pfcp_session_recv(pfcp, skb, md); + else + pfcp_node_recv(pfcp, skb, md); + + __set_bit(IP_TUNNEL_PFCP_OPT_BIT, flags); + ip_tunnel_info_opts_set(&tun_dst->u.tun_info, md, sizeof(*md), + flags); + + if (unlikely(iptunnel_pull_header(skb, PFCP_HLEN, skb->protocol, + !net_eq(sock_net(sk), + dev_net(pfcp->dev))))) + goto drop; + + skb_dst_set(skb, (struct dst_entry *)tun_dst); + + skb_reset_network_header(skb); + skb_reset_mac_header(skb); + skb->dev = pfcp->dev; + + gro_cells_receive(&pfcp->gro_cells, skb); + + return 0; +drop: + kfree_skb(skb); + return 0; +} + +static void pfcp_del_sock(struct pfcp_dev *pfcp) +{ + udp_tunnel_sock_release(pfcp->sock); + pfcp->sock = NULL; +} + +static void pfcp_dev_uninit(struct net_device *dev) +{ + struct pfcp_dev *pfcp = netdev_priv(dev); + + gro_cells_destroy(&pfcp->gro_cells); + pfcp_del_sock(pfcp); +} + +static int pfcp_dev_init(struct net_device *dev) +{ + struct pfcp_dev *pfcp = netdev_priv(dev); + + pfcp->dev = dev; + + return gro_cells_init(&pfcp->gro_cells, dev); +} + +static const struct net_device_ops pfcp_netdev_ops = { + .ndo_init = pfcp_dev_init, + .ndo_uninit = pfcp_dev_uninit, + .ndo_get_stats64 = dev_get_tstats64, +}; + +static const struct device_type pfcp_type = { + .name = "pfcp", +}; + +static void pfcp_link_setup(struct net_device *dev) +{ + dev->netdev_ops = &pfcp_netdev_ops; + dev->needs_free_netdev = true; + SET_NETDEV_DEVTYPE(dev, &pfcp_type); + + dev->hard_header_len = 0; + dev->addr_len = 0; + + dev->type = ARPHRD_NONE; + dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; + dev->priv_flags |= IFF_NO_QUEUE; + + netif_keep_dst(dev); +} + +static struct socket *pfcp_create_sock(struct pfcp_dev *pfcp) +{ + struct udp_tunnel_sock_cfg tuncfg = {}; + struct udp_port_cfg udp_conf = { + .local_ip.s_addr = htonl(INADDR_ANY), + .family = AF_INET, + }; + struct net *net = pfcp->net; + struct socket *sock; + int err; + + udp_conf.local_udp_port = htons(PFCP_PORT); + + err = udp_sock_create(net, &udp_conf, &sock); + if (err) + return ERR_PTR(err); + + tuncfg.sk_user_data = pfcp; + tuncfg.encap_rcv = pfcp_encap_recv; + tuncfg.encap_type = 1; + + setup_udp_tunnel_sock(net, sock, &tuncfg); + + return sock; +} + +static int pfcp_add_sock(struct pfcp_dev *pfcp) +{ + pfcp->sock = pfcp_create_sock(pfcp); + + return PTR_ERR_OR_ZERO(pfcp->sock); +} + +static int pfcp_newlink(struct net *net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct pfcp_dev *pfcp = netdev_priv(dev); + struct pfcp_net *pn; + int err; + + pfcp->net = net; + + err = pfcp_add_sock(pfcp); + if (err) { + netdev_dbg(dev, "failed to add pfcp socket %d\n", err); + goto exit_err; + } + + err = register_netdevice(dev); + if (err) { + netdev_dbg(dev, "failed to register pfcp netdev %d\n", err); + goto exit_del_pfcp_sock; + } + + pn = net_generic(dev_net(dev), pfcp_net_id); + list_add_rcu(&pfcp->list, &pn->pfcp_dev_list); + + netdev_dbg(dev, "registered new PFCP interface\n"); + + return 0; + +exit_del_pfcp_sock: + pfcp_del_sock(pfcp); +exit_err: + pfcp->net = NULL; + return err; +} + +static void pfcp_dellink(struct net_device *dev, struct list_head *head) +{ + struct pfcp_dev *pfcp = netdev_priv(dev); + + list_del_rcu(&pfcp->list); + unregister_netdevice_queue(dev, head); +} + +static struct rtnl_link_ops pfcp_link_ops __read_mostly = { + .kind = "pfcp", + .priv_size = sizeof(struct pfcp_dev), + .setup = pfcp_link_setup, + .newlink = pfcp_newlink, + .dellink = pfcp_dellink, +}; + +static int __net_init pfcp_net_init(struct net *net) +{ + struct pfcp_net *pn = net_generic(net, pfcp_net_id); + + INIT_LIST_HEAD(&pn->pfcp_dev_list); + return 0; +} + +static void __net_exit pfcp_net_exit(struct net *net) +{ + struct pfcp_net *pn = net_generic(net, pfcp_net_id); + struct pfcp_dev *pfcp; + LIST_HEAD(list); + + rtnl_lock(); + list_for_each_entry(pfcp, &pn->pfcp_dev_list, list) + pfcp_dellink(pfcp->dev, &list); + + unregister_netdevice_many(&list); + rtnl_unlock(); +} + +static struct pernet_operations pfcp_net_ops = { + .init = pfcp_net_init, + .exit = pfcp_net_exit, + .id = &pfcp_net_id, + .size = sizeof(struct pfcp_net), +}; + +static int __init pfcp_init(void) +{ + int err; + + err = register_pernet_subsys(&pfcp_net_ops); + if (err) + goto exit_err; + + err = rtnl_link_register(&pfcp_link_ops); + if (err) + goto exit_unregister_subsys; + return 0; + +exit_unregister_subsys: + unregister_pernet_subsys(&pfcp_net_ops); +exit_err: + pr_err("loading PFCP module failed: err %d\n", err); + return err; +} +late_initcall(pfcp_init); + +static void __exit pfcp_exit(void) +{ + rtnl_link_unregister(&pfcp_link_ops); + unregister_pernet_subsys(&pfcp_net_ops); + + pr_info("PFCP module unloaded\n"); +} +module_exit(pfcp_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Wojciech Drewek <wojciech.drewek@intel.com>"); +MODULE_DESCRIPTION("Interface driver for PFCP encapsulated traffic"); +MODULE_ALIAS_RTNL_LINK("pfcp"); diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 1df0595c5ba9..7fddc8306d82 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -76,6 +76,11 @@ config SFP comment "MII PHY device drivers" +config AIR_EN8811H_PHY + tristate "Airoha EN8811H 2.5 Gigabit PHY" + help + Currently supports the Airoha EN8811H PHY. + config AMD_PHY tristate "AMD and Altima PHYs" help diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 197acfa0b412..202ed7f450da 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -34,6 +34,7 @@ obj-y += $(sfp-obj-y) $(sfp-obj-m) obj-$(CONFIG_ADIN_PHY) += adin.o obj-$(CONFIG_ADIN1100_PHY) += adin1100.o +obj-$(CONFIG_AIR_EN8811H_PHY) += air_en8811h.o obj-$(CONFIG_AMD_PHY) += amd.o obj-$(CONFIG_AQUANTIA_PHY) += aquantia/ ifdef CONFIG_AX88796B_RUST_PHY diff --git a/drivers/net/phy/air_en8811h.c b/drivers/net/phy/air_en8811h.c new file mode 100644 index 000000000000..720542a4fd82 --- /dev/null +++ b/drivers/net/phy/air_en8811h.c @@ -0,0 +1,1086 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Driver for the Airoha EN8811H 2.5 Gigabit PHY. + * + * Limitations of the EN8811H: + * - Only full duplex supported + * - Forced speed (AN off) is not supported by hardware (100Mbps) + * + * Source originated from airoha's en8811h.c and en8811h.h v1.2.1 + * + * Copyright (C) 2023 Airoha Technology Corp. + */ + +#include <linux/phy.h> +#include <linux/firmware.h> +#include <linux/property.h> +#include <linux/wordpart.h> +#include <asm/unaligned.h> + +#define EN8811H_PHY_ID 0x03a2a411 + +#define EN8811H_MD32_DM "airoha/EthMD32.dm.bin" +#define EN8811H_MD32_DSP "airoha/EthMD32.DSP.bin" + +#define AIR_FW_ADDR_DM 0x00000000 +#define AIR_FW_ADDR_DSP 0x00100000 + +/* MII Registers */ +#define AIR_AUX_CTRL_STATUS 0x1d +#define AIR_AUX_CTRL_STATUS_SPEED_MASK GENMASK(4, 2) +#define AIR_AUX_CTRL_STATUS_SPEED_100 0x4 +#define AIR_AUX_CTRL_STATUS_SPEED_1000 0x8 +#define AIR_AUX_CTRL_STATUS_SPEED_2500 0xc + +#define AIR_EXT_PAGE_ACCESS 0x1f +#define AIR_PHY_PAGE_STANDARD 0x0000 +#define AIR_PHY_PAGE_EXTENDED_4 0x0004 + +/* MII Registers Page 4*/ +#define AIR_BPBUS_MODE 0x10 +#define AIR_BPBUS_MODE_ADDR_FIXED 0x0000 +#define AIR_BPBUS_MODE_ADDR_INCR BIT(15) +#define AIR_BPBUS_WR_ADDR_HIGH 0x11 +#define AIR_BPBUS_WR_ADDR_LOW 0x12 +#define AIR_BPBUS_WR_DATA_HIGH 0x13 +#define AIR_BPBUS_WR_DATA_LOW 0x14 +#define AIR_BPBUS_RD_ADDR_HIGH 0x15 +#define AIR_BPBUS_RD_ADDR_LOW 0x16 +#define AIR_BPBUS_RD_DATA_HIGH 0x17 +#define AIR_BPBUS_RD_DATA_LOW 0x18 + +/* Registers on MDIO_MMD_VEND1 */ +#define EN8811H_PHY_FW_STATUS 0x8009 +#define EN8811H_PHY_READY 0x02 + +#define AIR_PHY_MCU_CMD_1 0x800c +#define AIR_PHY_MCU_CMD_1_MODE1 0x0 +#define AIR_PHY_MCU_CMD_2 0x800d +#define AIR_PHY_MCU_CMD_2_MODE1 0x0 +#define AIR_PHY_MCU_CMD_3 0x800e +#define AIR_PHY_MCU_CMD_3_MODE1 0x1101 +#define AIR_PHY_MCU_CMD_3_DOCMD 0x1100 +#define AIR_PHY_MCU_CMD_4 0x800f +#define AIR_PHY_MCU_CMD_4_MODE1 0x0002 +#define AIR_PHY_MCU_CMD_4_INTCLR 0x00e4 + +/* Registers on MDIO_MMD_VEND2 */ +#define AIR_PHY_LED_BCR 0x021 +#define AIR_PHY_LED_BCR_MODE_MASK GENMASK(1, 0) +#define AIR_PHY_LED_BCR_TIME_TEST BIT(2) +#define AIR_PHY_LED_BCR_CLK_EN BIT(3) +#define AIR_PHY_LED_BCR_EXT_CTRL BIT(15) + +#define AIR_PHY_LED_DUR_ON 0x022 + +#define AIR_PHY_LED_DUR_BLINK 0x023 + +#define AIR_PHY_LED_ON(i) (0x024 + ((i) * 2)) +#define AIR_PHY_LED_ON_MASK (GENMASK(6, 0) | BIT(8)) +#define AIR_PHY_LED_ON_LINK1000 BIT(0) +#define AIR_PHY_LED_ON_LINK100 BIT(1) +#define AIR_PHY_LED_ON_LINK10 BIT(2) +#define AIR_PHY_LED_ON_LINKDOWN BIT(3) +#define AIR_PHY_LED_ON_FDX BIT(4) /* Full duplex */ +#define AIR_PHY_LED_ON_HDX BIT(5) /* Half duplex */ +#define AIR_PHY_LED_ON_FORCE_ON BIT(6) +#define AIR_PHY_LED_ON_LINK2500 BIT(8) +#define AIR_PHY_LED_ON_POLARITY BIT(14) +#define AIR_PHY_LED_ON_ENABLE BIT(15) + +#define AIR_PHY_LED_BLINK(i) (0x025 + ((i) * 2)) +#define AIR_PHY_LED_BLINK_1000TX BIT(0) +#define AIR_PHY_LED_BLINK_1000RX BIT(1) +#define AIR_PHY_LED_BLINK_100TX BIT(2) +#define AIR_PHY_LED_BLINK_100RX BIT(3) +#define AIR_PHY_LED_BLINK_10TX BIT(4) +#define AIR_PHY_LED_BLINK_10RX BIT(5) +#define AIR_PHY_LED_BLINK_COLLISION BIT(6) +#define AIR_PHY_LED_BLINK_RX_CRC_ERR BIT(7) +#define AIR_PHY_LED_BLINK_RX_IDLE_ERR BIT(8) +#define AIR_PHY_LED_BLINK_FORCE_BLINK BIT(9) +#define AIR_PHY_LED_BLINK_2500TX BIT(10) +#define AIR_PHY_LED_BLINK_2500RX BIT(11) + +/* Registers on BUCKPBUS */ +#define EN8811H_2P5G_LPA 0x3b30 +#define EN8811H_2P5G_LPA_2P5G BIT(0) + +#define EN8811H_FW_VERSION 0x3b3c + +#define EN8811H_POLARITY 0xca0f8 +#define EN8811H_POLARITY_TX_NORMAL BIT(0) +#define EN8811H_POLARITY_RX_REVERSE BIT(1) + +#define EN8811H_GPIO_OUTPUT 0xcf8b8 +#define EN8811H_GPIO_OUTPUT_345 (BIT(3) | BIT(4) | BIT(5)) + +#define EN8811H_FW_CTRL_1 0x0f0018 +#define EN8811H_FW_CTRL_1_START 0x0 +#define EN8811H_FW_CTRL_1_FINISH 0x1 +#define EN8811H_FW_CTRL_2 0x800000 +#define EN8811H_FW_CTRL_2_LOADING BIT(11) + +/* Led definitions */ +#define EN8811H_LED_COUNT 3 + +/* Default LED setup: + * GPIO5 <-> LED0 On: Link detected, blink Rx/Tx + * GPIO4 <-> LED1 On: Link detected at 2500 or 1000 Mbps + * GPIO3 <-> LED2 On: Link detected at 2500 or 100 Mbps + */ +#define AIR_DEFAULT_TRIGGER_LED0 (BIT(TRIGGER_NETDEV_LINK) | \ + BIT(TRIGGER_NETDEV_RX) | \ + BIT(TRIGGER_NETDEV_TX)) +#define AIR_DEFAULT_TRIGGER_LED1 (BIT(TRIGGER_NETDEV_LINK_2500) | \ + BIT(TRIGGER_NETDEV_LINK_1000)) +#define AIR_DEFAULT_TRIGGER_LED2 (BIT(TRIGGER_NETDEV_LINK_2500) | \ + BIT(TRIGGER_NETDEV_LINK_100)) + +struct led { + unsigned long rules; + unsigned long state; +}; + +struct en8811h_priv { + u32 firmware_version; + bool mcu_needs_restart; + struct led led[EN8811H_LED_COUNT]; +}; + +enum { + AIR_PHY_LED_STATE_FORCE_ON, + AIR_PHY_LED_STATE_FORCE_BLINK, +}; + +enum { + AIR_PHY_LED_DUR_BLINK_32MS, + AIR_PHY_LED_DUR_BLINK_64MS, + AIR_PHY_LED_DUR_BLINK_128MS, + AIR_PHY_LED_DUR_BLINK_256MS, + AIR_PHY_LED_DUR_BLINK_512MS, + AIR_PHY_LED_DUR_BLINK_1024MS, +}; + +enum { + AIR_LED_DISABLE, + AIR_LED_ENABLE, +}; + +enum { + AIR_ACTIVE_LOW, + AIR_ACTIVE_HIGH, +}; + +enum { + AIR_LED_MODE_DISABLE, + AIR_LED_MODE_USER_DEFINE, +}; + +#define AIR_PHY_LED_DUR_UNIT 1024 +#define AIR_PHY_LED_DUR (AIR_PHY_LED_DUR_UNIT << AIR_PHY_LED_DUR_BLINK_64MS) + +static const unsigned long en8811h_led_trig = BIT(TRIGGER_NETDEV_FULL_DUPLEX) | + BIT(TRIGGER_NETDEV_LINK) | + BIT(TRIGGER_NETDEV_LINK_10) | + BIT(TRIGGER_NETDEV_LINK_100) | + BIT(TRIGGER_NETDEV_LINK_1000) | + BIT(TRIGGER_NETDEV_LINK_2500) | + BIT(TRIGGER_NETDEV_RX) | + BIT(TRIGGER_NETDEV_TX); + +static int air_phy_read_page(struct phy_device *phydev) +{ + return __phy_read(phydev, AIR_EXT_PAGE_ACCESS); +} + +static int air_phy_write_page(struct phy_device *phydev, int page) +{ + return __phy_write(phydev, AIR_EXT_PAGE_ACCESS, page); +} + +static int __air_buckpbus_reg_write(struct phy_device *phydev, + u32 pbus_address, u32 pbus_data) +{ + int ret; + + ret = __phy_write(phydev, AIR_BPBUS_MODE, AIR_BPBUS_MODE_ADDR_FIXED); + if (ret < 0) + return ret; + + ret = __phy_write(phydev, AIR_BPBUS_WR_ADDR_HIGH, + upper_16_bits(pbus_address)); + if (ret < 0) + return ret; + + ret = __phy_write(phydev, AIR_BPBUS_WR_ADDR_LOW, + lower_16_bits(pbus_address)); + if (ret < 0) + return ret; + + ret = __phy_write(phydev, AIR_BPBUS_WR_DATA_HIGH, + upper_16_bits(pbus_data)); + if (ret < 0) + return ret; + + ret = __phy_write(phydev, AIR_BPBUS_WR_DATA_LOW, + lower_16_bits(pbus_data)); + if (ret < 0) + return ret; + + return 0; +} + +static int air_buckpbus_reg_write(struct phy_device *phydev, + u32 pbus_address, u32 pbus_data) +{ + int saved_page; + int ret = 0; + + saved_page = phy_select_page(phydev, AIR_PHY_PAGE_EXTENDED_4); + + if (saved_page >= 0) { + ret = __air_buckpbus_reg_write(phydev, pbus_address, + pbus_data); + if (ret < 0) + phydev_err(phydev, "%s 0x%08x failed: %d\n", __func__, + pbus_address, ret); + } + + return phy_restore_page(phydev, saved_page, ret); +} + +static int __air_buckpbus_reg_read(struct phy_device *phydev, + u32 pbus_address, u32 *pbus_data) +{ + int pbus_data_low, pbus_data_high; + int ret; + + ret = __phy_write(phydev, AIR_BPBUS_MODE, AIR_BPBUS_MODE_ADDR_FIXED); + if (ret < 0) + return ret; + + ret = __phy_write(phydev, AIR_BPBUS_RD_ADDR_HIGH, + upper_16_bits(pbus_address)); + if (ret < 0) + return ret; + + ret = __phy_write(phydev, AIR_BPBUS_RD_ADDR_LOW, + lower_16_bits(pbus_address)); + if (ret < 0) + return ret; + + pbus_data_high = __phy_read(phydev, AIR_BPBUS_RD_DATA_HIGH); + if (pbus_data_high < 0) + return ret; + + pbus_data_low = __phy_read(phydev, AIR_BPBUS_RD_DATA_LOW); + if (pbus_data_low < 0) + return ret; + + *pbus_data = pbus_data_low | (pbus_data_high << 16); + return 0; +} + +static int air_buckpbus_reg_read(struct phy_device *phydev, + u32 pbus_address, u32 *pbus_data) +{ + int saved_page; + int ret = 0; + + saved_page = phy_select_page(phydev, AIR_PHY_PAGE_EXTENDED_4); + + if (saved_page >= 0) { + ret = __air_buckpbus_reg_read(phydev, pbus_address, pbus_data); + if (ret < 0) + phydev_err(phydev, "%s 0x%08x failed: %d\n", __func__, + pbus_address, ret); + } + + return phy_restore_page(phydev, saved_page, ret); +} + +static int __air_buckpbus_reg_modify(struct phy_device *phydev, + u32 pbus_address, u32 mask, u32 set) +{ + int pbus_data_low, pbus_data_high; + u32 pbus_data_old, pbus_data_new; + int ret; + + ret = __phy_write(phydev, AIR_BPBUS_MODE, AIR_BPBUS_MODE_ADDR_FIXED); + if (ret < 0) + return ret; + + ret = __phy_write(phydev, AIR_BPBUS_RD_ADDR_HIGH, + upper_16_bits(pbus_address)); + if (ret < 0) + return ret; + + ret = __phy_write(phydev, AIR_BPBUS_RD_ADDR_LOW, + lower_16_bits(pbus_address)); + if (ret < 0) + return ret; + + pbus_data_high = __phy_read(phydev, AIR_BPBUS_RD_DATA_HIGH); + if (pbus_data_high < 0) + return ret; + + pbus_data_low = __phy_read(phydev, AIR_BPBUS_RD_DATA_LOW); + if (pbus_data_low < 0) + return ret; + + pbus_data_old = pbus_data_low | (pbus_data_high << 16); + pbus_data_new = (pbus_data_old & ~mask) | set; + if (pbus_data_new == pbus_data_old) + return 0; + + ret = __phy_write(phydev, AIR_BPBUS_WR_ADDR_HIGH, + upper_16_bits(pbus_address)); + if (ret < 0) + return ret; + + ret = __phy_write(phydev, AIR_BPBUS_WR_ADDR_LOW, + lower_16_bits(pbus_address)); + if (ret < 0) + return ret; + + ret = __phy_write(phydev, AIR_BPBUS_WR_DATA_HIGH, + upper_16_bits(pbus_data_new)); + if (ret < 0) + return ret; + + ret = __phy_write(phydev, AIR_BPBUS_WR_DATA_LOW, + lower_16_bits(pbus_data_new)); + if (ret < 0) + return ret; + + return 0; +} + +static int air_buckpbus_reg_modify(struct phy_device *phydev, + u32 pbus_address, u32 mask, u32 set) +{ + int saved_page; + int ret = 0; + + saved_page = phy_select_page(phydev, AIR_PHY_PAGE_EXTENDED_4); + + if (saved_page >= 0) { + ret = __air_buckpbus_reg_modify(phydev, pbus_address, mask, + set); + if (ret < 0) + phydev_err(phydev, "%s 0x%08x failed: %d\n", __func__, + pbus_address, ret); + } + + return phy_restore_page(phydev, saved_page, ret); +} + +static int __air_write_buf(struct phy_device *phydev, u32 address, + const struct firmware *fw) +{ + unsigned int offset; + int ret; + u16 val; + + ret = __phy_write(phydev, AIR_BPBUS_MODE, AIR_BPBUS_MODE_ADDR_INCR); + if (ret < 0) + return ret; + + ret = __phy_write(phydev, AIR_BPBUS_WR_ADDR_HIGH, + upper_16_bits(address)); + if (ret < 0) + return ret; + + ret = __phy_write(phydev, AIR_BPBUS_WR_ADDR_LOW, + lower_16_bits(address)); + if (ret < 0) + return ret; + + for (offset = 0; offset < fw->size; offset += 4) { + val = get_unaligned_le16(&fw->data[offset + 2]); + ret = __phy_write(phydev, AIR_BPBUS_WR_DATA_HIGH, val); + if (ret < 0) + return ret; + + val = get_unaligned_le16(&fw->data[offset]); + ret = __phy_write(phydev, AIR_BPBUS_WR_DATA_LOW, val); + if (ret < 0) + return ret; + } + + return 0; +} + +static int air_write_buf(struct phy_device *phydev, u32 address, + const struct firmware *fw) +{ + int saved_page; + int ret = 0; + + saved_page = phy_select_page(phydev, AIR_PHY_PAGE_EXTENDED_4); + + if (saved_page >= 0) { + ret = __air_write_buf(phydev, address, fw); + if (ret < 0) + phydev_err(phydev, "%s 0x%08x failed: %d\n", __func__, + address, ret); + } + + return phy_restore_page(phydev, saved_page, ret); +} + +static int en8811h_wait_mcu_ready(struct phy_device *phydev) +{ + int ret, reg_value; + + /* Because of mdio-lock, may have to wait for multiple loads */ + ret = phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1, + EN8811H_PHY_FW_STATUS, reg_value, + reg_value == EN8811H_PHY_READY, + 20000, 7500000, true); + if (ret) { + phydev_err(phydev, "MCU not ready: 0x%x\n", reg_value); + return -ENODEV; + } + + return 0; +} + +static int en8811h_load_firmware(struct phy_device *phydev) +{ + struct en8811h_priv *priv = phydev->priv; + struct device *dev = &phydev->mdio.dev; + const struct firmware *fw1, *fw2; + int ret; + + ret = request_firmware_direct(&fw1, EN8811H_MD32_DM, dev); + if (ret < 0) + return ret; + + ret = request_firmware_direct(&fw2, EN8811H_MD32_DSP, dev); + if (ret < 0) + goto en8811h_load_firmware_rel1; + + ret = air_buckpbus_reg_write(phydev, EN8811H_FW_CTRL_1, + EN8811H_FW_CTRL_1_START); + if (ret < 0) + goto en8811h_load_firmware_out; + + ret = air_buckpbus_reg_modify(phydev, EN8811H_FW_CTRL_2, + EN8811H_FW_CTRL_2_LOADING, + EN8811H_FW_CTRL_2_LOADING); + if (ret < 0) + goto en8811h_load_firmware_out; + + ret = air_write_buf(phydev, AIR_FW_ADDR_DM, fw1); + if (ret < 0) + goto en8811h_load_firmware_out; + + ret = air_write_buf(phydev, AIR_FW_ADDR_DSP, fw2); + if (ret < 0) + goto en8811h_load_firmware_out; + + ret = air_buckpbus_reg_modify(phydev, EN8811H_FW_CTRL_2, + EN8811H_FW_CTRL_2_LOADING, 0); + if (ret < 0) + goto en8811h_load_firmware_out; + + ret = air_buckpbus_reg_write(phydev, EN8811H_FW_CTRL_1, + EN8811H_FW_CTRL_1_FINISH); + if (ret < 0) + goto en8811h_load_firmware_out; + + ret = en8811h_wait_mcu_ready(phydev); + + air_buckpbus_reg_read(phydev, EN8811H_FW_VERSION, + &priv->firmware_version); + phydev_info(phydev, "MD32 firmware version: %08x\n", + priv->firmware_version); + +en8811h_load_firmware_out: + release_firmware(fw2); + +en8811h_load_firmware_rel1: + release_firmware(fw1); + + if (ret < 0) + phydev_err(phydev, "Load firmware failed: %d\n", ret); + + return ret; +} + +static int en8811h_restart_mcu(struct phy_device *phydev) +{ + int ret; + + ret = air_buckpbus_reg_write(phydev, EN8811H_FW_CTRL_1, + EN8811H_FW_CTRL_1_START); + if (ret < 0) + return ret; + + ret = air_buckpbus_reg_write(phydev, EN8811H_FW_CTRL_1, + EN8811H_FW_CTRL_1_FINISH); + if (ret < 0) + return ret; + + return en8811h_wait_mcu_ready(phydev); +} + +static int air_hw_led_on_set(struct phy_device *phydev, u8 index, bool on) +{ + struct en8811h_priv *priv = phydev->priv; + bool changed; + + if (index >= EN8811H_LED_COUNT) + return -EINVAL; + + if (on) + changed = !test_and_set_bit(AIR_PHY_LED_STATE_FORCE_ON, + &priv->led[index].state); + else + changed = !!test_and_clear_bit(AIR_PHY_LED_STATE_FORCE_ON, + &priv->led[index].state); + + changed |= (priv->led[index].rules != 0); + + if (changed) + return phy_modify_mmd(phydev, MDIO_MMD_VEND2, + AIR_PHY_LED_ON(index), + AIR_PHY_LED_ON_MASK, + on ? AIR_PHY_LED_ON_FORCE_ON : 0); + + return 0; +} + +static int air_hw_led_blink_set(struct phy_device *phydev, u8 index, + bool blinking) +{ + struct en8811h_priv *priv = phydev->priv; + bool changed; + + if (index >= EN8811H_LED_COUNT) + return -EINVAL; + + if (blinking) + changed = !test_and_set_bit(AIR_PHY_LED_STATE_FORCE_BLINK, + &priv->led[index].state); + else + changed = !!test_and_clear_bit(AIR_PHY_LED_STATE_FORCE_BLINK, + &priv->led[index].state); + + changed |= (priv->led[index].rules != 0); + + if (changed) + return phy_write_mmd(phydev, MDIO_MMD_VEND2, + AIR_PHY_LED_BLINK(index), + blinking ? + AIR_PHY_LED_BLINK_FORCE_BLINK : 0); + else + return 0; +} + +static int air_led_blink_set(struct phy_device *phydev, u8 index, + unsigned long *delay_on, + unsigned long *delay_off) +{ + struct en8811h_priv *priv = phydev->priv; + bool blinking = false; + int err; + + if (index >= EN8811H_LED_COUNT) + return -EINVAL; + + if (delay_on && delay_off && (*delay_on > 0) && (*delay_off > 0)) { + blinking = true; + *delay_on = 50; + *delay_off = 50; + } + + err = air_hw_led_blink_set(phydev, index, blinking); + if (err) + return err; + + /* led-blink set, so switch led-on off */ + err = air_hw_led_on_set(phydev, index, false); + if (err) + return err; + + /* hw-control is off*/ + if (!!test_bit(AIR_PHY_LED_STATE_FORCE_BLINK, &priv->led[index].state)) + priv->led[index].rules = 0; + + return 0; +} + +static int air_led_brightness_set(struct phy_device *phydev, u8 index, + enum led_brightness value) +{ + struct en8811h_priv *priv = phydev->priv; + int err; + + if (index >= EN8811H_LED_COUNT) + return -EINVAL; + + /* led-on set, so switch led-blink off */ + err = air_hw_led_blink_set(phydev, index, false); + if (err) + return err; + + err = air_hw_led_on_set(phydev, index, (value != LED_OFF)); + if (err) + return err; + + /* hw-control is off */ + if (!!test_bit(AIR_PHY_LED_STATE_FORCE_ON, &priv->led[index].state)) + priv->led[index].rules = 0; + + return 0; +} + +static int air_led_hw_control_get(struct phy_device *phydev, u8 index, + unsigned long *rules) +{ + struct en8811h_priv *priv = phydev->priv; + + if (index >= EN8811H_LED_COUNT) + return -EINVAL; + + *rules = priv->led[index].rules; + + return 0; +}; + +static int air_led_hw_control_set(struct phy_device *phydev, u8 index, + unsigned long rules) +{ + struct en8811h_priv *priv = phydev->priv; + u16 on = 0, blink = 0; + int ret; + + if (index >= EN8811H_LED_COUNT) + return -EINVAL; + + priv->led[index].rules = rules; + + if (rules & BIT(TRIGGER_NETDEV_FULL_DUPLEX)) + on |= AIR_PHY_LED_ON_FDX; + + if (rules & (BIT(TRIGGER_NETDEV_LINK_10) | BIT(TRIGGER_NETDEV_LINK))) + on |= AIR_PHY_LED_ON_LINK10; + + if (rules & (BIT(TRIGGER_NETDEV_LINK_100) | BIT(TRIGGER_NETDEV_LINK))) + on |= AIR_PHY_LED_ON_LINK100; + + if (rules & (BIT(TRIGGER_NETDEV_LINK_1000) | BIT(TRIGGER_NETDEV_LINK))) + on |= AIR_PHY_LED_ON_LINK1000; + + if (rules & (BIT(TRIGGER_NETDEV_LINK_2500) | BIT(TRIGGER_NETDEV_LINK))) + on |= AIR_PHY_LED_ON_LINK2500; + + if (rules & BIT(TRIGGER_NETDEV_RX)) { + blink |= AIR_PHY_LED_BLINK_10RX | + AIR_PHY_LED_BLINK_100RX | + AIR_PHY_LED_BLINK_1000RX | + AIR_PHY_LED_BLINK_2500RX; + } + + if (rules & BIT(TRIGGER_NETDEV_TX)) { + blink |= AIR_PHY_LED_BLINK_10TX | + AIR_PHY_LED_BLINK_100TX | + AIR_PHY_LED_BLINK_1000TX | + AIR_PHY_LED_BLINK_2500TX; + } + + if (blink || on) { + /* switch hw-control on, so led-on and led-blink are off */ + clear_bit(AIR_PHY_LED_STATE_FORCE_ON, + &priv->led[index].state); + clear_bit(AIR_PHY_LED_STATE_FORCE_BLINK, + &priv->led[index].state); + } else { + priv->led[index].rules = 0; + } + + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, AIR_PHY_LED_ON(index), + AIR_PHY_LED_ON_MASK, on); + + if (ret < 0) + return ret; + + return phy_write_mmd(phydev, MDIO_MMD_VEND2, AIR_PHY_LED_BLINK(index), + blink); +}; + +static int air_led_init(struct phy_device *phydev, u8 index, u8 state, u8 pol) +{ + int val = 0; + int err; + + if (index >= EN8811H_LED_COUNT) + return -EINVAL; + + if (state == AIR_LED_ENABLE) + val |= AIR_PHY_LED_ON_ENABLE; + else + val &= ~AIR_PHY_LED_ON_ENABLE; + + if (pol == AIR_ACTIVE_HIGH) + val |= AIR_PHY_LED_ON_POLARITY; + else + val &= ~AIR_PHY_LED_ON_POLARITY; + + err = phy_modify_mmd(phydev, MDIO_MMD_VEND2, AIR_PHY_LED_ON(index), + AIR_PHY_LED_ON_ENABLE | + AIR_PHY_LED_ON_POLARITY, val); + + if (err < 0) + return err; + + return 0; +} + +static int air_leds_init(struct phy_device *phydev, int num, int dur, int mode) +{ + struct en8811h_priv *priv = phydev->priv; + int ret, i; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, AIR_PHY_LED_DUR_BLINK, + dur); + if (ret < 0) + return ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, AIR_PHY_LED_DUR_ON, + dur >> 1); + if (ret < 0) + return ret; + + switch (mode) { + case AIR_LED_MODE_DISABLE: + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, AIR_PHY_LED_BCR, + AIR_PHY_LED_BCR_EXT_CTRL | + AIR_PHY_LED_BCR_MODE_MASK, 0); + if (ret < 0) + return ret; + break; + case AIR_LED_MODE_USER_DEFINE: + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, AIR_PHY_LED_BCR, + AIR_PHY_LED_BCR_EXT_CTRL | + AIR_PHY_LED_BCR_CLK_EN, + AIR_PHY_LED_BCR_EXT_CTRL | + AIR_PHY_LED_BCR_CLK_EN); + if (ret < 0) + return ret; + break; + default: + phydev_err(phydev, "LED mode %d is not supported\n", mode); + return -EINVAL; + } + + for (i = 0; i < num; ++i) { + ret = air_led_init(phydev, i, AIR_LED_ENABLE, AIR_ACTIVE_HIGH); + if (ret < 0) { + phydev_err(phydev, "LED%d init failed: %d\n", i, ret); + return ret; + } + air_led_hw_control_set(phydev, i, priv->led[i].rules); + } + + return 0; +} + +static int en8811h_led_hw_is_supported(struct phy_device *phydev, u8 index, + unsigned long rules) +{ + if (index >= EN8811H_LED_COUNT) + return -EINVAL; + + /* All combinations of the supported triggers are allowed */ + if (rules & ~en8811h_led_trig) + return -EOPNOTSUPP; + + return 0; +}; + +static int en8811h_probe(struct phy_device *phydev) +{ + struct en8811h_priv *priv; + int ret; + + priv = devm_kzalloc(&phydev->mdio.dev, sizeof(struct en8811h_priv), + GFP_KERNEL); + if (!priv) + return -ENOMEM; + phydev->priv = priv; + + ret = en8811h_load_firmware(phydev); + if (ret < 0) + return ret; + + /* mcu has just restarted after firmware load */ + priv->mcu_needs_restart = false; + + priv->led[0].rules = AIR_DEFAULT_TRIGGER_LED0; + priv->led[1].rules = AIR_DEFAULT_TRIGGER_LED1; + priv->led[2].rules = AIR_DEFAULT_TRIGGER_LED2; + + /* MDIO_DEVS1/2 empty, so set mmds_present bits here */ + phydev->c45_ids.mmds_present |= MDIO_DEVS_PMAPMD | MDIO_DEVS_AN; + + ret = air_leds_init(phydev, EN8811H_LED_COUNT, AIR_PHY_LED_DUR, + AIR_LED_MODE_DISABLE); + if (ret < 0) { + phydev_err(phydev, "Failed to disable leds: %d\n", ret); + return ret; + } + + /* Configure led gpio pins as output */ + ret = air_buckpbus_reg_modify(phydev, EN8811H_GPIO_OUTPUT, + EN8811H_GPIO_OUTPUT_345, + EN8811H_GPIO_OUTPUT_345); + if (ret < 0) + return ret; + + return 0; +} + +static int en8811h_config_init(struct phy_device *phydev) +{ + struct en8811h_priv *priv = phydev->priv; + struct device *dev = &phydev->mdio.dev; + u32 pbus_value; + int ret; + + /* If restart happened in .probe(), no need to restart now */ + if (priv->mcu_needs_restart) { + ret = en8811h_restart_mcu(phydev); + if (ret < 0) + return ret; + } else { + /* Next calls to .config_init() mcu needs to restart */ + priv->mcu_needs_restart = true; + } + + /* Select mode 1, the only mode supported. + * Configures the SerDes for 2500Base-X with rate adaptation + */ + ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, AIR_PHY_MCU_CMD_1, + AIR_PHY_MCU_CMD_1_MODE1); + if (ret < 0) + return ret; + ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, AIR_PHY_MCU_CMD_2, + AIR_PHY_MCU_CMD_2_MODE1); + if (ret < 0) + return ret; + ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, AIR_PHY_MCU_CMD_3, + AIR_PHY_MCU_CMD_3_MODE1); + if (ret < 0) + return ret; + ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, AIR_PHY_MCU_CMD_4, + AIR_PHY_MCU_CMD_4_MODE1); + if (ret < 0) + return ret; + + /* Serdes polarity */ + pbus_value = 0; + if (device_property_read_bool(dev, "airoha,pnswap-rx")) + pbus_value |= EN8811H_POLARITY_RX_REVERSE; + else + pbus_value &= ~EN8811H_POLARITY_RX_REVERSE; + if (device_property_read_bool(dev, "airoha,pnswap-tx")) + pbus_value &= ~EN8811H_POLARITY_TX_NORMAL; + else + pbus_value |= EN8811H_POLARITY_TX_NORMAL; + ret = air_buckpbus_reg_modify(phydev, EN8811H_POLARITY, + EN8811H_POLARITY_RX_REVERSE | + EN8811H_POLARITY_TX_NORMAL, pbus_value); + if (ret < 0) + return ret; + + ret = air_leds_init(phydev, EN8811H_LED_COUNT, AIR_PHY_LED_DUR, + AIR_LED_MODE_USER_DEFINE); + if (ret < 0) { + phydev_err(phydev, "Failed to initialize leds: %d\n", ret); + return ret; + } + + return 0; +} + +static int en8811h_get_features(struct phy_device *phydev) +{ + linkmode_set_bit_array(phy_basic_ports_array, + ARRAY_SIZE(phy_basic_ports_array), + phydev->supported); + + return genphy_c45_pma_read_abilities(phydev); +} + +static int en8811h_get_rate_matching(struct phy_device *phydev, + phy_interface_t iface) +{ + return RATE_MATCH_PAUSE; +} + +static int en8811h_config_aneg(struct phy_device *phydev) +{ + bool changed = false; + int ret; + u32 adv; + + if (phydev->autoneg == AUTONEG_DISABLE) { + phydev_warn(phydev, "Disabling autoneg is not supported\n"); + return -EINVAL; + } + + adv = linkmode_adv_to_mii_10gbt_adv_t(phydev->advertising); + + ret = phy_modify_mmd_changed(phydev, MDIO_MMD_AN, MDIO_AN_10GBT_CTRL, + MDIO_AN_10GBT_CTRL_ADV2_5G, adv); + if (ret < 0) + return ret; + if (ret > 0) + changed = true; + + return __genphy_config_aneg(phydev, changed); +} + +static int en8811h_read_status(struct phy_device *phydev) +{ + struct en8811h_priv *priv = phydev->priv; + u32 pbus_value; + int ret, val; + + ret = genphy_update_link(phydev); + if (ret) + return ret; + + phydev->master_slave_get = MASTER_SLAVE_CFG_UNSUPPORTED; + phydev->master_slave_state = MASTER_SLAVE_STATE_UNSUPPORTED; + phydev->speed = SPEED_UNKNOWN; + phydev->duplex = DUPLEX_UNKNOWN; + phydev->pause = 0; + phydev->asym_pause = 0; + phydev->rate_matching = RATE_MATCH_PAUSE; + + ret = genphy_read_master_slave(phydev); + if (ret < 0) + return ret; + + ret = genphy_read_lpa(phydev); + if (ret < 0) + return ret; + + /* Get link partner 2.5GBASE-T ability from vendor register */ + ret = air_buckpbus_reg_read(phydev, EN8811H_2P5G_LPA, &pbus_value); + if (ret < 0) + return ret; + linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + phydev->lp_advertising, + pbus_value & EN8811H_2P5G_LPA_2P5G); + + if (phydev->autoneg_complete) + phy_resolve_aneg_pause(phydev); + + if (!phydev->link) + return 0; + + /* Get real speed from vendor register */ + val = phy_read(phydev, AIR_AUX_CTRL_STATUS); + if (val < 0) + return val; + switch (val & AIR_AUX_CTRL_STATUS_SPEED_MASK) { + case AIR_AUX_CTRL_STATUS_SPEED_2500: + phydev->speed = SPEED_2500; + break; + case AIR_AUX_CTRL_STATUS_SPEED_1000: + phydev->speed = SPEED_1000; + break; + case AIR_AUX_CTRL_STATUS_SPEED_100: + phydev->speed = SPEED_100; + break; + } + + /* Firmware before version 24011202 has no vendor register 2P5G_LPA. + * Assume link partner advertised it if connected at 2500Mbps. + */ + if (priv->firmware_version < 0x24011202) { + linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + phydev->lp_advertising, + phydev->speed == SPEED_2500); + } + + /* Only supports full duplex */ + phydev->duplex = DUPLEX_FULL; + + return 0; +} + +static int en8811h_clear_intr(struct phy_device *phydev) +{ + int ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, AIR_PHY_MCU_CMD_3, + AIR_PHY_MCU_CMD_3_DOCMD); + if (ret < 0) + return ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, AIR_PHY_MCU_CMD_4, + AIR_PHY_MCU_CMD_4_INTCLR); + if (ret < 0) + return ret; + + return 0; +} + +static irqreturn_t en8811h_handle_interrupt(struct phy_device *phydev) +{ + int ret; + + ret = en8811h_clear_intr(phydev); + if (ret < 0) { + phy_error(phydev); + return IRQ_NONE; + } + + phy_trigger_machine(phydev); + + return IRQ_HANDLED; +} + +static struct phy_driver en8811h_driver[] = { +{ + PHY_ID_MATCH_MODEL(EN8811H_PHY_ID), + .name = "Airoha EN8811H", + .probe = en8811h_probe, + .get_features = en8811h_get_features, + .config_init = en8811h_config_init, + .get_rate_matching = en8811h_get_rate_matching, + .config_aneg = en8811h_config_aneg, + .read_status = en8811h_read_status, + .config_intr = en8811h_clear_intr, + .handle_interrupt = en8811h_handle_interrupt, + .led_hw_is_supported = en8811h_led_hw_is_supported, + .read_page = air_phy_read_page, + .write_page = air_phy_write_page, + .led_blink_set = air_led_blink_set, + .led_brightness_set = air_led_brightness_set, + .led_hw_control_set = air_led_hw_control_set, + .led_hw_control_get = air_led_hw_control_get, +} }; + +module_phy_driver(en8811h_driver); + +static struct mdio_device_id __maybe_unused en8811h_tbl[] = { + { PHY_ID_MATCH_MODEL(EN8811H_PHY_ID) }, + { } +}; + +MODULE_DEVICE_TABLE(mdio, en8811h_tbl); +MODULE_FIRMWARE(EN8811H_MD32_DM); +MODULE_FIRMWARE(EN8811H_MD32_DSP); + +MODULE_DESCRIPTION("Airoha EN8811H PHY drivers"); +MODULE_AUTHOR("Airoha"); +MODULE_AUTHOR("Eric Woudstra <ericwouds@gmail.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 3495591a5c29..72ecf6cf809c 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -1584,7 +1584,8 @@ static void vxlan_parse_gbp_hdr(struct vxlanhdr *unparsed, tun_dst = (struct metadata_dst *)skb_dst(skb); if (tun_dst) { - tun_dst->u.tun_info.key.tun_flags |= TUNNEL_VXLAN_OPT; + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, + tun_dst->u.tun_info.key.tun_flags); tun_dst->u.tun_info.options_len = sizeof(*md); } if (gbp->dont_learn) @@ -1716,9 +1717,11 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) goto drop; if (vxlan_collect_metadata(vs)) { + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tun_dst; - tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), TUNNEL_KEY, + __set_bit(IP_TUNNEL_KEY_BIT, flags); + tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), flags, key32_to_tunnel_id(vni), sizeof(*md)); if (!tun_dst) @@ -2403,14 +2406,14 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, vni = tunnel_id_to_key32(info->key.tun_id); ifindex = 0; dst_cache = &info->dst_cache; - if (info->key.tun_flags & TUNNEL_VXLAN_OPT) { + if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { if (info->options_len < sizeof(*md)) goto drop; md = ip_tunnel_info_opts(info); } ttl = info->key.ttl; tos = info->key.tos; - udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); + udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); } src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); @@ -2451,7 +2454,8 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, old_iph->frag_off & htons(IP_DF))) df = htons(IP_DF); } - } else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) { + } else if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, + info->key.tun_flags)) { df = htons(IP_DF); } diff --git a/drivers/net/wwan/mhi_wwan_mbim.c b/drivers/net/wwan/mhi_wwan_mbim.c index 3f72ae943b29..f2aef84fc08d 100644 --- a/drivers/net/wwan/mhi_wwan_mbim.c +++ b/drivers/net/wwan/mhi_wwan_mbim.c @@ -648,7 +648,6 @@ static struct mhi_driver mhi_mbim_driver = { .id_table = mhi_mbim_id_table, .driver = { .name = "mhi_wwan_mbim", - .owner = THIS_MODULE, }, }; diff --git a/drivers/nfc/nfcmrvl/spi.c b/drivers/nfc/nfcmrvl/spi.c index ad3359a4942c..9c8cde1250fb 100644 --- a/drivers/nfc/nfcmrvl/spi.c +++ b/drivers/nfc/nfcmrvl/spi.c @@ -199,7 +199,6 @@ static struct spi_driver nfcmrvl_spi_driver = { .id_table = nfcmrvl_spi_id_table, .driver = { .name = "nfcmrvl_spi", - .owner = THIS_MODULE, .of_match_table = of_match_ptr(of_nfcmrvl_spi_match), }, }; diff --git a/drivers/nfc/st95hf/core.c b/drivers/nfc/st95hf/core.c index ed704bb77226..ffe5b4eab457 100644 --- a/drivers/nfc/st95hf/core.c +++ b/drivers/nfc/st95hf/core.c @@ -7,14 +7,13 @@ */ #include <linux/err.h> -#include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/nfc.h> -#include <linux/of_gpio.h> #include <linux/of.h> #include <linux/property.h> #include <linux/regulator/consumer.h> @@ -196,7 +195,7 @@ struct st95_digital_cmd_complete_arg { * for spi communication between st95hf and host. * @ddev: nfc digital device object. * @nfcdev: nfc device object. - * @enable_gpio: gpio used to enable st95hf transceiver. + * @enable_gpiod: gpio used to enable st95hf transceiver. * @complete_cb_arg: structure to store various context information * that is passed from nfc requesting thread to the threaded ISR. * @st95hf_supply: regulator "consumer" for NFC device. @@ -219,7 +218,7 @@ struct st95hf_context { struct st95hf_spi_context spicontext; struct nfc_digital_dev *ddev; struct nfc_dev *nfcdev; - unsigned int enable_gpio; + struct gpio_desc *enable_gpiod; struct st95_digital_cmd_complete_arg complete_cb_arg; struct regulator *st95hf_supply; unsigned char sendrcv_trflag; @@ -451,19 +450,19 @@ static int st95hf_select_protocol(struct st95hf_context *stcontext, int type) static void st95hf_send_st95enable_negativepulse(struct st95hf_context *st95con) { /* First make irq_in pin high */ - gpio_set_value(st95con->enable_gpio, HIGH); + gpiod_set_value(st95con->enable_gpiod, HIGH); /* wait for 1 milisecond */ usleep_range(1000, 2000); /* Make irq_in pin low */ - gpio_set_value(st95con->enable_gpio, LOW); + gpiod_set_value(st95con->enable_gpiod, LOW); /* wait for minimum interrupt pulse to make st95 active */ usleep_range(1000, 2000); /* At end make it high */ - gpio_set_value(st95con->enable_gpio, HIGH); + gpiod_set_value(st95con->enable_gpiod, HIGH); } /* @@ -1063,6 +1062,7 @@ MODULE_DEVICE_TABLE(of, st95hf_spi_of_match); static int st95hf_probe(struct spi_device *nfc_spi_dev) { + struct device *dev = &nfc_spi_dev->dev; int ret; struct st95hf_context *st95context; @@ -1108,19 +1108,14 @@ static int st95hf_probe(struct spi_device *nfc_spi_dev) */ dev_set_drvdata(&nfc_spi_dev->dev, spicontext); - st95context->enable_gpio = - of_get_named_gpio(nfc_spi_dev->dev.of_node, - "enable-gpio", - 0); - if (!gpio_is_valid(st95context->enable_gpio)) { + st95context->enable_gpiod = devm_gpiod_get(dev, "enable", GPIOD_OUT_HIGH); + if (IS_ERR(st95context->enable_gpiod)) { + ret = PTR_ERR(st95context->enable_gpiod); dev_err(&nfc_spi_dev->dev, "No valid enable gpio\n"); - ret = st95context->enable_gpio; goto err_disable_regulator; } - ret = devm_gpio_request_one(&nfc_spi_dev->dev, st95context->enable_gpio, - GPIOF_DIR_OUT | GPIOF_INIT_HIGH, - "enable_gpio"); + ret = gpiod_set_consumer_name(st95context->enable_gpiod, "enable_gpio"); if (ret) goto err_disable_regulator; @@ -1242,7 +1237,6 @@ static void st95hf_remove(struct spi_device *nfc_spi_dev) static struct spi_driver st95hf_driver = { .driver = { .name = "st95hf", - .owner = THIS_MODULE, .of_match_table = of_match_ptr(st95hf_spi_of_match), }, .id_table = st95hf_id, diff --git a/drivers/s390/cio/idset.c b/drivers/s390/cio/idset.c index 45f9c0736be4..e5f28370a903 100644 --- a/drivers/s390/cio/idset.c +++ b/drivers/s390/cio/idset.c @@ -16,20 +16,21 @@ struct idset { unsigned long bitmap[]; }; -static inline unsigned long bitmap_size(int num_ssid, int num_id) +static inline unsigned long idset_bitmap_size(int num_ssid, int num_id) { - return BITS_TO_LONGS(num_ssid * num_id) * sizeof(unsigned long); + return bitmap_size(size_mul(num_ssid, num_id)); } static struct idset *idset_new(int num_ssid, int num_id) { struct idset *set; - set = vmalloc(sizeof(struct idset) + bitmap_size(num_ssid, num_id)); + set = vmalloc(sizeof(struct idset) + + idset_bitmap_size(num_ssid, num_id)); if (set) { set->num_ssid = num_ssid; set->num_id = num_id; - memset(set->bitmap, 0, bitmap_size(num_ssid, num_id)); + memset(set->bitmap, 0, idset_bitmap_size(num_ssid, num_id)); } return set; } @@ -41,7 +42,8 @@ void idset_free(struct idset *set) void idset_fill(struct idset *set) { - memset(set->bitmap, 0xff, bitmap_size(set->num_ssid, set->num_id)); + memset(set->bitmap, 0xff, + idset_bitmap_size(set->num_ssid, set->num_id)); } static inline void idset_add(struct idset *set, int ssid, int id) diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index c8a05d5eb9cb..3ab8dea5036b 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1911,9 +1911,9 @@ static inline void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, ctl->free_space -= bytes; } -static void bitmap_set_bits(struct btrfs_free_space_ctl *ctl, - struct btrfs_free_space *info, u64 offset, - u64 bytes) +static void btrfs_bitmap_set_bits(struct btrfs_free_space_ctl *ctl, + struct btrfs_free_space *info, u64 offset, + u64 bytes) { unsigned long start, count, end; int extent_delta = 1; @@ -2249,7 +2249,7 @@ static u64 add_bytes_to_bitmap(struct btrfs_free_space_ctl *ctl, bytes_to_set = min(end - offset, bytes); - bitmap_set_bits(ctl, info, offset, bytes_to_set); + btrfs_bitmap_set_bits(ctl, info, offset, bytes_to_set); return bytes_to_set; diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c index 845f9b22deef..c9eb01ccee51 100644 --- a/fs/ntfs3/bitmap.c +++ b/fs/ntfs3/bitmap.c @@ -654,7 +654,7 @@ int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nbits) wnd->total_zeroes = nbits; wnd->extent_max = MINUS_ONE_T; wnd->zone_bit = wnd->zone_end = 0; - wnd->nwnd = bytes_to_block(sb, bitmap_size(nbits)); + wnd->nwnd = bytes_to_block(sb, ntfs3_bitmap_size(nbits)); wnd->bits_last = nbits & (wbits - 1); if (!wnd->bits_last) wnd->bits_last = wbits; @@ -1347,7 +1347,7 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits) return -EINVAL; /* Align to 8 byte boundary. */ - new_wnd = bytes_to_block(sb, bitmap_size(new_bits)); + new_wnd = bytes_to_block(sb, ntfs3_bitmap_size(new_bits)); new_last = new_bits & (wbits - 1); if (!new_last) new_last = wbits; diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index ae2ef5c11868..626d3f2c7e2d 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -522,7 +522,7 @@ static int ntfs_extend_mft(struct ntfs_sb_info *sbi) ni->mi.dirty = true; /* Step 2: Resize $MFT::BITMAP. */ - new_bitmap_bytes = bitmap_size(new_mft_total); + new_bitmap_bytes = ntfs3_bitmap_size(new_mft_total); err = attr_set_size(ni, ATTR_BITMAP, NULL, 0, &sbi->mft.bitmap.run, new_bitmap_bytes, &new_bitmap_bytes, true, NULL); diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index daabaad63aaf..43796aaa3d97 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -1456,8 +1456,8 @@ static int indx_create_allocate(struct ntfs_index *indx, struct ntfs_inode *ni, alloc->nres.valid_size = alloc->nres.data_size = cpu_to_le64(data_size); - err = ni_insert_resident(ni, bitmap_size(1), ATTR_BITMAP, in->name, - in->name_len, &bitmap, NULL, NULL); + err = ni_insert_resident(ni, ntfs3_bitmap_size(1), ATTR_BITMAP, + in->name, in->name_len, &bitmap, NULL, NULL); if (err) goto out2; @@ -1518,8 +1518,9 @@ static int indx_add_allocate(struct ntfs_index *indx, struct ntfs_inode *ni, if (bmp) { /* Increase bitmap. */ err = attr_set_size(ni, ATTR_BITMAP, in->name, in->name_len, - &indx->bitmap_run, bitmap_size(bit + 1), - NULL, true, NULL); + &indx->bitmap_run, + ntfs3_bitmap_size(bit + 1), NULL, true, + NULL); if (err) goto out1; } @@ -2092,7 +2093,7 @@ static int indx_shrink(struct ntfs_index *indx, struct ntfs_inode *ni, if (in->name == I30_NAME) i_size_write(&ni->vfs_inode, new_data); - bpb = bitmap_size(bit); + bpb = ntfs3_bitmap_size(bit); if (bpb * 8 == nbits) return 0; diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 79356fd29a14..ea5b5e814e63 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -966,9 +966,9 @@ static inline bool run_is_empty(struct runs_tree *run) } /* NTFS uses quad aligned bitmaps. */ -static inline size_t bitmap_size(size_t bits) +static inline size_t ntfs3_bitmap_size(size_t bits) { - return ALIGN((bits + 7) >> 3, 8); + return BITS_TO_U64(bits) * sizeof(u64); } #define _100ns2seconds 10000000 diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 9df7c20d066f..71dfeb0c4323 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -1341,7 +1341,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) /* Check bitmap boundary. */ tt = sbi->used.bitmap.nbits; - if (inode->i_size < bitmap_size(tt)) { + if (inode->i_size < ntfs3_bitmap_size(tt)) { ntfs_err(sb, "$Bitmap is corrupted."); err = -EINVAL; goto put_inode_out; diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index aa4096126553..8c4768c44a01 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -83,6 +83,10 @@ struct device; * bitmap_to_arr64(buf, src, nbits) Copy nbits from buf to u64[] dst * bitmap_get_value8(map, start) Get 8bit value from map at start * bitmap_set_value8(map, value, start) Set 8bit value to map at start + * bitmap_read(map, start, nbits) Read an nbits-sized value from + * map at start + * bitmap_write(map, value, start, nbits) Write an nbits-sized value to + * map at start * * Note, bitmap_zero() and bitmap_fill() operate over the region of * unsigned longs, that is, bits behind bitmap till the unsigned long @@ -222,9 +226,11 @@ void bitmap_fold(unsigned long *dst, const unsigned long *orig, #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) +#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) + static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = 0; @@ -234,7 +240,7 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = ~0UL; @@ -245,7 +251,7 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = *src; @@ -722,38 +728,83 @@ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) } /** - * bitmap_get_value8 - get an 8-bit value within a memory region + * bitmap_read - read a value of n-bits from the memory region * @map: address to the bitmap memory region - * @start: bit offset of the 8-bit value; must be a multiple of 8 + * @start: bit offset of the n-bit value + * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG * - * Returns the 8-bit value located at the @start bit offset within the @src - * memory region. + * Returns: value of @nbits bits located at the @start bit offset within the + * @map memory region. For @nbits = 0 and @nbits > BITS_PER_LONG the return + * value is undefined. */ -static inline unsigned long bitmap_get_value8(const unsigned long *map, - unsigned long start) +static inline unsigned long bitmap_read(const unsigned long *map, + unsigned long start, + unsigned long nbits) { - const size_t index = BIT_WORD(start); - const unsigned long offset = start % BITS_PER_LONG; + size_t index = BIT_WORD(start); + unsigned long offset = start % BITS_PER_LONG; + unsigned long space = BITS_PER_LONG - offset; + unsigned long value_low, value_high; + + if (unlikely(!nbits || nbits > BITS_PER_LONG)) + return 0; + + if (space >= nbits) + return (map[index] >> offset) & BITMAP_LAST_WORD_MASK(nbits); - return (map[index] >> offset) & 0xFF; + value_low = map[index] & BITMAP_FIRST_WORD_MASK(start); + value_high = map[index + 1] & BITMAP_LAST_WORD_MASK(start + nbits); + return (value_low >> offset) | (value_high << space); } /** - * bitmap_set_value8 - set an 8-bit value within a memory region + * bitmap_write - write n-bit value within a memory region * @map: address to the bitmap memory region - * @value: the 8-bit value; values wider than 8 bits may clobber bitmap - * @start: bit offset of the 8-bit value; must be a multiple of 8 + * @value: value to write, clamped to nbits + * @start: bit offset of the n-bit value + * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG. + * + * bitmap_write() behaves as-if implemented as @nbits calls of __assign_bit(), + * i.e. bits beyond @nbits are ignored: + * + * for (bit = 0; bit < nbits; bit++) + * __assign_bit(start + bit, bitmap, val & BIT(bit)); + * + * For @nbits == 0 and @nbits > BITS_PER_LONG no writes are performed. */ -static inline void bitmap_set_value8(unsigned long *map, unsigned long value, - unsigned long start) -{ - const size_t index = BIT_WORD(start); - const unsigned long offset = start % BITS_PER_LONG; - - map[index] &= ~(0xFFUL << offset); +static inline void bitmap_write(unsigned long *map, unsigned long value, + unsigned long start, unsigned long nbits) +{ + size_t index; + unsigned long offset; + unsigned long space; + unsigned long mask; + bool fit; + + if (unlikely(!nbits || nbits > BITS_PER_LONG)) + return; + + mask = BITMAP_LAST_WORD_MASK(nbits); + value &= mask; + offset = start % BITS_PER_LONG; + space = BITS_PER_LONG - offset; + fit = space >= nbits; + index = BIT_WORD(start); + + map[index] &= (fit ? (~(mask << offset)) : ~BITMAP_FIRST_WORD_MASK(start)); map[index] |= value << offset; + if (fit) + return; + + map[index + 1] &= BITMAP_FIRST_WORD_MASK(start + nbits); + map[index + 1] |= (value >> space); } +#define bitmap_get_value8(map, start) \ + bitmap_read(map, start, BITS_PER_BYTE) +#define bitmap_set_value8(map, value, start) \ + bitmap_write(map, value, start, BITS_PER_BYTE) + #endif /* __ASSEMBLY__ */ #endif /* __LINUX_BITMAP_H */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 2ba557e067fe..b25dc8742124 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -21,6 +21,8 @@ #define BITS_TO_U32(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u32)) #define BITS_TO_BYTES(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) +#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_BYTE) + extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); extern unsigned int __sw_hweight32(unsigned int w); @@ -80,6 +82,7 @@ __check_bitop_pr(__test_and_set_bit); __check_bitop_pr(__test_and_clear_bit); __check_bitop_pr(__test_and_change_bit); __check_bitop_pr(test_bit); +__check_bitop_pr(test_bit_acquire); #undef __check_bitop_pr @@ -272,23 +275,11 @@ static inline unsigned long fns(unsigned long word, unsigned int n) * @addr: the address to start counting from * @value: the value to assign */ -static __always_inline void assign_bit(long nr, volatile unsigned long *addr, - bool value) -{ - if (value) - set_bit(nr, addr); - else - clear_bit(nr, addr); -} +#define assign_bit(nr, addr, value) \ + ((value) ? set_bit((nr), (addr)) : clear_bit((nr), (addr))) -static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, - bool value) -{ - if (value) - __set_bit(nr, addr); - else - __clear_bit(nr, addr); -} +#define __assign_bit(nr, addr, value) \ + ((value) ? __set_bit((nr), (addr)) : __clear_bit((nr), (addr))) /** * __ptr_set_bit - Set bit in a pointer's value diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 1c29947db848..6519f9c77709 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -853,7 +853,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) */ static inline unsigned int cpumask_size(void) { - return BITS_TO_LONGS(large_cpumask_bits) * sizeof(long); + return bitmap_size(large_cpumask_bits); } /* diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index 287f590ed56b..d94bfd9ac8cc 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -43,29 +43,10 @@ static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1, return bitmap_andnot(dst, src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) -{ - __set_bit(nr, addr); -} - -static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr) -{ - __clear_bit(nr, addr); -} - -static inline void linkmode_mod_bit(int nr, volatile unsigned long *addr, - int set) -{ - if (set) - linkmode_set_bit(nr, addr); - else - linkmode_clear_bit(nr, addr); -} - -static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr) -{ - return test_bit(nr, addr); -} +#define linkmode_test_bit test_bit +#define linkmode_set_bit __set_bit +#define linkmode_clear_bit __clear_bit +#define linkmode_mod_bit __assign_bit static inline void linkmode_set_bit_array(const int *array, int array_size, unsigned long *addr) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e41d30ebaca6..7d12b5a9380f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -59,7 +59,7 @@ struct ethtool_ops; struct kernel_hwtstamp_config; struct phy_device; struct dsa_port; -struct ip_tunnel_parm; +struct ip_tunnel_parm_kern; struct macsec_context; struct macsec_ops; struct netdev_name_node; @@ -1327,7 +1327,7 @@ struct netdev_net_notifier { * queue id bound to an AF_XDP socket. The flags field specifies if * only RX, only Tx, or both should be woken up using the flags * XDP_WAKEUP_RX and XDP_WAKEUP_TX. - * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, + * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm_kern *p, * int cmd); * Add, change, delete or get information on an IPv4 tunnel. * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev); @@ -1583,7 +1583,8 @@ struct net_device_ops { int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); int (*ndo_tunnel_ctl)(struct net_device *dev, - struct ip_tunnel_parm *p, int cmd); + struct ip_tunnel_parm_kern *p, + int cmd); struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); @@ -3203,6 +3204,7 @@ struct softnet_data { struct softnet_data *rps_ipi_list; #endif + unsigned int received_rps; bool in_net_rx_action; bool in_napi_threaded_poll; @@ -3235,11 +3237,11 @@ struct softnet_data { unsigned int cpu; unsigned int input_queue_tail; #endif - unsigned int received_rps; - unsigned int dropped; struct sk_buff_head input_pkt_queue; struct napi_struct backlog; + atomic_t dropped ____cacheline_aligned_in_smp; + /* Another possibly contended cache line */ spinlock_t defer_lock ____cacheline_aligned_in_smp; int defer_count; @@ -3248,21 +3250,6 @@ struct softnet_data { call_single_data_t defer_csd; }; -static inline void input_queue_head_incr(struct softnet_data *sd) -{ -#ifdef CONFIG_RPS - sd->input_queue_head++; -#endif -} - -static inline void input_queue_tail_incr_save(struct softnet_data *sd, - unsigned int *qtail) -{ -#ifdef CONFIG_RPS - *qtail = ++sd->input_queue_tail; -#endif -} - DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); static inline int dev_recursion_level(void) @@ -3270,24 +3257,6 @@ static inline int dev_recursion_level(void) return this_cpu_read(softnet_data.xmit.recursion); } -#define XMIT_RECURSION_LIMIT 8 -static inline bool dev_xmit_recursion(void) -{ - return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > - XMIT_RECURSION_LIMIT); -} - -static inline void dev_xmit_recursion_inc(void) -{ - __this_cpu_inc(softnet_data.xmit.recursion); -} - -static inline void dev_xmit_recursion_dec(void) -{ - __this_cpu_dec(softnet_data.xmit.recursion); -} - -void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu); void __netif_schedule(struct Qdisc *q); void netif_schedule_queue(struct netdev_queue *txq); diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 1b7fae4c6b24..4160731dcb6e 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -198,7 +198,7 @@ static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr, __be32 daddr, __u8 tos, __u8 ttl, __be16 tp_dst, - __be16 flags, + const unsigned long *flags, __be64 tunnel_id, int md_size) { @@ -215,7 +215,7 @@ static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr, } static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, - __be16 flags, + const unsigned long *flags, __be64 tunnel_id, int md_size) { @@ -230,7 +230,7 @@ static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *sad __u8 tos, __u8 ttl, __be16 tp_dst, __be32 label, - __be16 flags, + const unsigned long *flags, __be64 tunnel_id, int md_size) { @@ -243,7 +243,7 @@ static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *sad info = &tun_dst->u.tun_info; info->mode = IP_TUNNEL_INFO_IPV6; - info->key.tun_flags = flags; + ip_tunnel_flags_copy(info->key.tun_flags, flags); info->key.tun_id = tunnel_id; info->key.tp_src = 0; info->key.tp_dst = tp_dst; @@ -259,7 +259,7 @@ static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *sad } static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb, - __be16 flags, + const unsigned long *flags, __be64 tunnel_id, int md_size) { diff --git a/include/net/espintcp.h b/include/net/espintcp.h index 0335bbd76552..c70efd704b6d 100644 --- a/include/net/espintcp.h +++ b/include/net/espintcp.h @@ -32,7 +32,7 @@ struct espintcp_ctx { static inline struct espintcp_ctx *espintcp_getctx(const struct sock *sk) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); /* RCU is only needed for diag */ return (__force void *)icsk->icsk_ulp_data; diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 1a7131d6cb0e..9ab376d1a677 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -97,7 +97,7 @@ struct flow_dissector_key_enc_opts { * here but seems difficult to #include */ u8 len; - __be16 dst_opt_type; + u32 dst_opt_type; }; struct flow_dissector_key_keyid { diff --git a/include/net/gre.h b/include/net/gre.h index 4e209708b754..ccd293203284 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -49,67 +49,61 @@ static inline bool netif_is_ip6gretap(const struct net_device *dev) !strcmp(dev->rtnl_link_ops->kind, "ip6gretap"); } -static inline int gre_calc_hlen(__be16 o_flags) +static inline int gre_calc_hlen(const unsigned long *o_flags) { int addend = 4; - if (o_flags & TUNNEL_CSUM) + if (test_bit(IP_TUNNEL_CSUM_BIT, o_flags)) addend += 4; - if (o_flags & TUNNEL_KEY) + if (test_bit(IP_TUNNEL_KEY_BIT, o_flags)) addend += 4; - if (o_flags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, o_flags)) addend += 4; return addend; } -static inline __be16 gre_flags_to_tnl_flags(__be16 flags) +static inline void gre_flags_to_tnl_flags(unsigned long *dst, __be16 flags) { - __be16 tflags = 0; - - if (flags & GRE_CSUM) - tflags |= TUNNEL_CSUM; - if (flags & GRE_ROUTING) - tflags |= TUNNEL_ROUTING; - if (flags & GRE_KEY) - tflags |= TUNNEL_KEY; - if (flags & GRE_SEQ) - tflags |= TUNNEL_SEQ; - if (flags & GRE_STRICT) - tflags |= TUNNEL_STRICT; - if (flags & GRE_REC) - tflags |= TUNNEL_REC; - if (flags & GRE_VERSION) - tflags |= TUNNEL_VERSION; - - return tflags; + IP_TUNNEL_DECLARE_FLAGS(res) = { }; + + __assign_bit(IP_TUNNEL_CSUM_BIT, res, flags & GRE_CSUM); + __assign_bit(IP_TUNNEL_ROUTING_BIT, res, flags & GRE_ROUTING); + __assign_bit(IP_TUNNEL_KEY_BIT, res, flags & GRE_KEY); + __assign_bit(IP_TUNNEL_SEQ_BIT, res, flags & GRE_SEQ); + __assign_bit(IP_TUNNEL_STRICT_BIT, res, flags & GRE_STRICT); + __assign_bit(IP_TUNNEL_REC_BIT, res, flags & GRE_REC); + __assign_bit(IP_TUNNEL_VERSION_BIT, res, flags & GRE_VERSION); + + ip_tunnel_flags_copy(dst, res); } -static inline __be16 gre_tnl_flags_to_gre_flags(__be16 tflags) +static inline __be16 gre_tnl_flags_to_gre_flags(const unsigned long *tflags) { __be16 flags = 0; - if (tflags & TUNNEL_CSUM) + if (test_bit(IP_TUNNEL_CSUM_BIT, tflags)) flags |= GRE_CSUM; - if (tflags & TUNNEL_ROUTING) + if (test_bit(IP_TUNNEL_ROUTING_BIT, tflags)) flags |= GRE_ROUTING; - if (tflags & TUNNEL_KEY) + if (test_bit(IP_TUNNEL_KEY_BIT, tflags)) flags |= GRE_KEY; - if (tflags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, tflags)) flags |= GRE_SEQ; - if (tflags & TUNNEL_STRICT) + if (test_bit(IP_TUNNEL_STRICT_BIT, tflags)) flags |= GRE_STRICT; - if (tflags & TUNNEL_REC) + if (test_bit(IP_TUNNEL_REC_BIT, tflags)) flags |= GRE_REC; - if (tflags & TUNNEL_VERSION) + if (test_bit(IP_TUNNEL_VERSION_BIT, tflags)) flags |= GRE_VERSION; return flags; } static inline void gre_build_header(struct sk_buff *skb, int hdr_len, - __be16 flags, __be16 proto, + const unsigned long *flags, __be16 proto, __be32 key, __be32 seq) { + IP_TUNNEL_DECLARE_FLAGS(cond) = { }; struct gre_base_hdr *greh; skb_push(skb, hdr_len); @@ -120,18 +114,22 @@ static inline void gre_build_header(struct sk_buff *skb, int hdr_len, greh->flags = gre_tnl_flags_to_gre_flags(flags); greh->protocol = proto; - if (flags & (TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_SEQ)) { + __set_bit(IP_TUNNEL_KEY_BIT, cond); + __set_bit(IP_TUNNEL_CSUM_BIT, cond); + __set_bit(IP_TUNNEL_SEQ_BIT, cond); + + if (ip_tunnel_flags_intersect(flags, cond)) { __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); - if (flags & TUNNEL_SEQ) { + if (test_bit(IP_TUNNEL_SEQ_BIT, flags)) { *ptr = seq; ptr--; } - if (flags & TUNNEL_KEY) { + if (test_bit(IP_TUNNEL_KEY_BIT, flags)) { *ptr = key; ptr--; } - if (flags & TUNNEL_CSUM && + if (test_bit(IP_TUNNEL_CSUM_BIT, flags) && !(skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) { *ptr = 0; diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index ccf171f7eb60..d96c871b0d58 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -147,10 +147,7 @@ struct inet_connection_sock { #define ICSK_TIME_LOSS_PROBE 5 /* Tail loss probe timer */ #define ICSK_TIME_REO_TIMEOUT 6 /* Reordering timer */ -static inline struct inet_connection_sock *inet_csk(const struct sock *sk) -{ - return (struct inet_connection_sock *)sk; -} +#define inet_csk(ptr) container_of_const(ptr, struct inet_connection_sock, icsk_inet.sk) static inline void *inet_csk_ca(const struct sock *sk) { diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index f28da08a37b4..2a536eea9424 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -111,7 +111,7 @@ static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo void inet_twsk_deschedule_put(struct inet_timewait_sock *tw); -void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family); +void inet_twsk_purge(struct inet_hashinfo *hashinfo); static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 74b369bddf49..399592405c72 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -30,8 +30,8 @@ struct __ip6_tnl_parm { struct in6_addr laddr; /* local tunnel end-point address */ struct in6_addr raddr; /* remote tunnel end-point address */ - __be16 i_flags; - __be16 o_flags; + IP_TUNNEL_DECLARE_FLAGS(i_flags); + IP_TUNNEL_DECLARE_FLAGS(o_flags); __be32 i_key; __be32 o_key; diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 5cd64bb2104d..d8f574fbb11e 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -36,6 +36,24 @@ (sizeof_field(struct ip_tunnel_key, u) - \ sizeof_field(struct ip_tunnel_key, u.ipv4)) +#define __ipt_flag_op(op, ...) \ + op(__VA_ARGS__, __IP_TUNNEL_FLAG_NUM) + +#define IP_TUNNEL_DECLARE_FLAGS(...) \ + __ipt_flag_op(DECLARE_BITMAP, __VA_ARGS__) + +#define ip_tunnel_flags_zero(...) __ipt_flag_op(bitmap_zero, __VA_ARGS__) +#define ip_tunnel_flags_copy(...) __ipt_flag_op(bitmap_copy, __VA_ARGS__) +#define ip_tunnel_flags_and(...) __ipt_flag_op(bitmap_and, __VA_ARGS__) +#define ip_tunnel_flags_or(...) __ipt_flag_op(bitmap_or, __VA_ARGS__) + +#define ip_tunnel_flags_empty(...) \ + __ipt_flag_op(bitmap_empty, __VA_ARGS__) +#define ip_tunnel_flags_intersect(...) \ + __ipt_flag_op(bitmap_intersects, __VA_ARGS__) +#define ip_tunnel_flags_subset(...) \ + __ipt_flag_op(bitmap_subset, __VA_ARGS__) + struct ip_tunnel_key { __be64 tun_id; union { @@ -48,11 +66,11 @@ struct ip_tunnel_key { struct in6_addr dst; } ipv6; } u; - __be16 tun_flags; - u8 tos; /* TOS for IPv4, TC for IPv6 */ - u8 ttl; /* TTL for IPv4, HL for IPv6 */ + IP_TUNNEL_DECLARE_FLAGS(tun_flags); __be32 label; /* Flow Label for IPv6 */ u32 nhid; + u8 tos; /* TOS for IPv4, TC for IPv6 */ + u8 ttl; /* TTL for IPv4, HL for IPv6 */ __be16 tp_src; __be16 tp_dst; __u8 flow_flags; @@ -110,6 +128,17 @@ struct ip_tunnel_prl_entry { struct metadata_dst; +/* Kernel-side variant of ip_tunnel_parm */ +struct ip_tunnel_parm_kern { + char name[IFNAMSIZ]; + IP_TUNNEL_DECLARE_FLAGS(i_flags); + IP_TUNNEL_DECLARE_FLAGS(o_flags); + __be32 i_key; + __be32 o_key; + int link; + struct iphdr iph; +}; + struct ip_tunnel { struct ip_tunnel __rcu *next; struct hlist_node hash_node; @@ -136,7 +165,7 @@ struct ip_tunnel { struct dst_cache dst_cache; - struct ip_tunnel_parm parms; + struct ip_tunnel_parm_kern parms; int mlink; int encap_hlen; /* Encap header length (FOU,GUE) */ @@ -157,7 +186,7 @@ struct ip_tunnel { }; struct tnl_ptk_info { - __be16 flags; + IP_TUNNEL_DECLARE_FLAGS(flags); __be16 proto; __be32 key; __be32 seq; @@ -179,11 +208,80 @@ struct ip_tunnel_net { int type; }; +static inline void ip_tunnel_set_options_present(unsigned long *flags) +{ + IP_TUNNEL_DECLARE_FLAGS(present) = { }; + + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present); + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_GTP_OPT_BIT, present); + __set_bit(IP_TUNNEL_PFCP_OPT_BIT, present); + + ip_tunnel_flags_or(flags, flags, present); +} + +static inline void ip_tunnel_clear_options_present(unsigned long *flags) +{ + IP_TUNNEL_DECLARE_FLAGS(present) = { }; + + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present); + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_GTP_OPT_BIT, present); + __set_bit(IP_TUNNEL_PFCP_OPT_BIT, present); + + __ipt_flag_op(bitmap_andnot, flags, flags, present); +} + +static inline bool ip_tunnel_is_options_present(const unsigned long *flags) +{ + IP_TUNNEL_DECLARE_FLAGS(present) = { }; + + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present); + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present); + __set_bit(IP_TUNNEL_GTP_OPT_BIT, present); + __set_bit(IP_TUNNEL_PFCP_OPT_BIT, present); + + return ip_tunnel_flags_intersect(flags, present); +} + +static inline bool ip_tunnel_flags_is_be16_compat(const unsigned long *flags) +{ + IP_TUNNEL_DECLARE_FLAGS(supp) = { }; + + bitmap_set(supp, 0, BITS_PER_TYPE(__be16)); + __set_bit(IP_TUNNEL_VTI_BIT, supp); + + return ip_tunnel_flags_subset(flags, supp); +} + +static inline void ip_tunnel_flags_from_be16(unsigned long *dst, __be16 flags) +{ + ip_tunnel_flags_zero(dst); + + bitmap_write(dst, be16_to_cpu(flags), 0, BITS_PER_TYPE(__be16)); + __assign_bit(IP_TUNNEL_VTI_BIT, dst, flags & VTI_ISVTI); +} + +static inline __be16 ip_tunnel_flags_to_be16(const unsigned long *flags) +{ + __be16 ret; + + ret = cpu_to_be16(bitmap_read(flags, 0, BITS_PER_TYPE(__be16))); + if (test_bit(IP_TUNNEL_VTI_BIT, flags)) + ret |= VTI_ISVTI; + + return ret; +} + static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, __be32 saddr, __be32 daddr, u8 tos, u8 ttl, __be32 label, __be16 tp_src, __be16 tp_dst, - __be64 tun_id, __be16 tun_flags) + __be64 tun_id, + const unsigned long *tun_flags) { key->tun_id = tun_id; key->u.ipv4.src = saddr; @@ -193,7 +291,7 @@ static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, key->tos = tos; key->ttl = ttl; key->label = label; - key->tun_flags = tun_flags; + ip_tunnel_flags_copy(key->tun_flags, tun_flags); /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of * the upper tunnel are used. @@ -214,12 +312,8 @@ ip_tunnel_dst_cache_usable(const struct sk_buff *skb, { if (skb->mark) return false; - if (!info) - return true; - if (info->key.tun_flags & TUNNEL_NOCACHE) - return false; - return true; + return !info || !test_bit(IP_TUNNEL_NOCACHE_BIT, info->key.tun_flags); } static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info @@ -291,14 +385,18 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, const u8 protocol); void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const u8 proto, int tunnel_hlen); -int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); +int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, + int cmd); +bool ip_tunnel_parm_from_user(struct ip_tunnel_parm_kern *kp, + const void __user *data); +bool ip_tunnel_parm_to_user(void __user *data, struct ip_tunnel_parm_kern *kp); int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, - int link, __be16 flags, + int link, const unsigned long *flags, __be32 remote, __be32 local, __be32 key); @@ -307,16 +405,16 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_error); int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], - struct ip_tunnel_parm *p, __u32 fwmark); + struct ip_tunnel_parm_kern *p, __u32 fwmark); int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], - struct ip_tunnel_parm *p, __u32 fwmark); + struct ip_tunnel_parm_kern *p, __u32 fwmark); void ip_tunnel_setup(struct net_device *dev, unsigned int net_id); bool ip_tunnel_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *encap); void ip_tunnel_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms); + struct ip_tunnel_parm_kern *parms); extern const struct header_ops ip_tunnel_header_ops; __be16 ip_tunnel_parse_protocol(const struct sk_buff *skb); @@ -514,12 +612,13 @@ static inline void ip_tunnel_info_opts_get(void *to, static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, - __be16 flags) + const unsigned long *flags) { info->options_len = len; if (len > 0) { memcpy(ip_tunnel_info_opts(info), from, len); - info->key.tun_flags |= flags; + ip_tunnel_flags_or(info->key.tun_flags, info->key.tun_flags, + flags); } } @@ -563,7 +662,7 @@ static inline void ip_tunnel_info_opts_get(void *to, static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, - __be16 flags) + const unsigned long *flags) { info->options_len = 0; } diff --git a/include/net/netlink.h b/include/net/netlink.h index c19ff921b661..1d2bbcc50212 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -157,7 +157,11 @@ * nla_parse() parse and validate stream of attrs * nla_parse_nested() parse nested attributes * nla_for_each_attr() loop over all attributes + * nla_for_each_attr_type() loop over all attributes with the + * given type * nla_for_each_nested() loop over the nested attributes + * nla_for_each_nested_type() loop over the nested attributes with + * the given type *========================================================================= */ @@ -2071,6 +2075,18 @@ static inline int nla_total_size_64bit(int payload) pos = nla_next(pos, &(rem))) /** + * nla_for_each_attr_type - iterate over a stream of attributes + * @pos: loop counter, set to current attribute + * @type: required attribute type for @pos + * @head: head of attribute stream + * @len: length of attribute stream + * @rem: initialized to len, holds bytes currently remaining in stream + */ +#define nla_for_each_attr_type(pos, type, head, len, rem) \ + nla_for_each_attr(pos, head, len, rem) \ + if (nla_type(pos) == type) + +/** * nla_for_each_nested - iterate over nested attributes * @pos: loop counter, set to current attribute * @nla: attribute containing the nested attributes @@ -2080,6 +2096,17 @@ static inline int nla_total_size_64bit(int payload) nla_for_each_attr(pos, nla_data(nla), nla_len(nla), rem) /** + * nla_for_each_nested_type - iterate over nested attributes + * @pos: loop counter, set to current attribute + * @type: required attribute type for @pos + * @nla: attribute containing the nested attributes + * @rem: initialized to len, holds bytes currently remaining in stream + */ +#define nla_for_each_nested_type(pos, type, nla, rem) \ + nla_for_each_nested(pos, nla, rem) \ + if (nla_type(pos) == type) + +/** * nla_is_last - Test if attribute is last in stream * @nla: attribute to test * @rem: bytes remaining in stream diff --git a/include/net/pfcp.h b/include/net/pfcp.h new file mode 100644 index 000000000000..af14f970b80e --- /dev/null +++ b/include/net/pfcp.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _PFCP_H_ +#define _PFCP_H_ + +#include <uapi/linux/if_ether.h> +#include <net/dst_metadata.h> +#include <linux/netdevice.h> +#include <uapi/linux/ipv6.h> +#include <net/udp_tunnel.h> +#include <uapi/linux/udp.h> +#include <uapi/linux/ip.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/bits.h> + +#define PFCP_PORT 8805 + +/* PFCP protocol header */ +struct pfcphdr { + u8 flags; + u8 message_type; + __be16 message_length; +}; + +/* PFCP header flags */ +#define PFCP_SEID_FLAG BIT(0) +#define PFCP_MP_FLAG BIT(1) + +#define PFCP_VERSION_MASK GENMASK(4, 0) + +#define PFCP_HLEN (sizeof(struct udphdr) + sizeof(struct pfcphdr)) + +/* PFCP node related messages */ +struct pfcphdr_node { + u8 seq_number[3]; + u8 reserved; +}; + +/* PFCP session related messages */ +struct pfcphdr_session { + __be64 seid; + u8 seq_number[3]; +#ifdef __LITTLE_ENDIAN_BITFIELD + u8 message_priority:4, + reserved:4; +#elif defined(__BIG_ENDIAN_BITFIELD) + u8 reserved:4, + message_priprity:4; +#else +#error "Please fix <asm/byteorder>" +#endif +}; + +struct pfcp_metadata { + u8 type; + __be64 seid; +} __packed; + +enum { + PFCP_TYPE_NODE = 0, + PFCP_TYPE_SESSION = 1, +}; + +#define PFCP_HEADROOM (sizeof(struct iphdr) + sizeof(struct udphdr) + \ + sizeof(struct pfcphdr) + sizeof(struct ethhdr)) +#define PFCP6_HEADROOM (sizeof(struct ipv6hdr) + sizeof(struct udphdr) + \ + sizeof(struct pfcphdr) + sizeof(struct ethhdr)) + +static inline struct pfcphdr *pfcp_hdr(struct sk_buff *skb) +{ + return (struct pfcphdr *)(udp_hdr(skb) + 1); +} + +static inline struct pfcphdr_node *pfcp_hdr_node(struct sk_buff *skb) +{ + return (struct pfcphdr_node *)(pfcp_hdr(skb) + 1); +} + +static inline struct pfcphdr_session *pfcp_hdr_session(struct sk_buff *skb) +{ + return (struct pfcphdr_session *)(pfcp_hdr(skb) + 1); +} + +static inline bool netif_is_pfcp(const struct net_device *dev) +{ + return dev->rtnl_link_ops && + !strcmp(dev->rtnl_link_ops->kind, "pfcp"); +} + +#endif diff --git a/include/net/rps.h b/include/net/rps.h index 7660243e905b..a93401d23d66 100644 --- a/include/net/rps.h +++ b/include/net/rps.h @@ -122,4 +122,32 @@ static inline void sock_rps_record_flow(const struct sock *sk) #endif } +static inline u32 rps_input_queue_tail_incr(struct softnet_data *sd) +{ +#ifdef CONFIG_RPS + return ++sd->input_queue_tail; +#else + return 0; +#endif +} + +static inline void rps_input_queue_tail_save(u32 *dest, u32 tail) +{ +#ifdef CONFIG_RPS + WRITE_ONCE(*dest, tail); +#endif +} + +static inline void rps_input_queue_head_add(struct softnet_data *sd, int val) +{ +#ifdef CONFIG_RPS + WRITE_ONCE(sd->input_queue_head, sd->input_queue_head + val); +#endif +} + +static inline void rps_input_queue_head_incr(struct softnet_data *sd) +{ + rps_input_queue_head_add(sd, 1); +} + #endif /* _NET_RPS_H */ diff --git a/include/net/sock.h b/include/net/sock.h index f57bfd8a2ad2..2253eefe2848 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2513,6 +2513,12 @@ static inline void sk_wake_async(const struct sock *sk, int how, int band) } } +static inline void sk_wake_async_rcu(const struct sock *sk, int how, int band) +{ + if (unlikely(sock_flag(sk, SOCK_FASYNC))) + sock_wake_async(rcu_dereference(sk->sk_wq), how, band); +} + /* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might * need sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak. * Note: for send buffers, TCP works better if we can build two skbs at diff --git a/include/net/tcp.h b/include/net/tcp.h index 6ae35199d3b3..9ab5b37e9d53 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -353,7 +353,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb); void tcp_rcv_space_adjust(struct sock *sk); int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); void tcp_twsk_destructor(struct sock *sk); -void tcp_twsk_purge(struct list_head *net_exit_list, int family); +void tcp_twsk_purge(struct list_head *net_exit_list); ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); @@ -742,7 +742,7 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu); int tcp_mss_to_mtu(struct sock *sk, int mss); void tcp_mtup_init(struct sock *sk); -static inline void tcp_bound_rto(const struct sock *sk) +static inline void tcp_bound_rto(struct sock *sk) { if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX) inet_csk(sk)->icsk_rto = TCP_RTO_MAX; diff --git a/include/net/tls.h b/include/net/tls.h index 340ad43971e4..400f4857dc11 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -361,7 +361,7 @@ static inline bool tls_is_skb_tx_device_offloaded(const struct sk_buff *skb) static inline struct tls_context *tls_get_ctx(const struct sock *sk) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); /* Use RCU on icsk_ulp_data only for sock diag code, * TLS data path doesn't need rcu_dereference(). diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index d716214fe03d..a93dc51f6323 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -179,8 +179,8 @@ struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, struct dst_cache *dst_cache); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, - __be16 flags, __be64 tunnel_id, - int md_size); + const unsigned long *flags, + __be64 tunnel_id, int md_size); #ifdef CONFIG_INET static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) diff --git a/include/trace/events/net_probe_common.h b/include/trace/events/net_probe_common.h index b1f9a4d3ee13..5e33f91bdea3 100644 --- a/include/trace/events/net_probe_common.h +++ b/include/trace/events/net_probe_common.h @@ -70,4 +70,44 @@ TP_STORE_V4MAPPED(__entry, saddr, daddr) #endif +#define TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb, protoh) \ + do { \ + struct sockaddr_in *v4 = (void *)__entry->saddr; \ + \ + v4->sin_family = AF_INET; \ + v4->sin_port = protoh->source; \ + v4->sin_addr.s_addr = ip_hdr(skb)->saddr; \ + v4 = (void *)__entry->daddr; \ + v4->sin_family = AF_INET; \ + v4->sin_port = protoh->dest; \ + v4->sin_addr.s_addr = ip_hdr(skb)->daddr; \ + } while (0) + +#if IS_ENABLED(CONFIG_IPV6) + +#define TP_STORE_ADDR_PORTS_SKB(__entry, skb, protoh) \ + do { \ + const struct iphdr *iph = ip_hdr(skb); \ + \ + if (iph->version == 6) { \ + struct sockaddr_in6 *v6 = (void *)__entry->saddr; \ + \ + v6->sin6_family = AF_INET6; \ + v6->sin6_port = protoh->source; \ + v6->sin6_addr = ipv6_hdr(skb)->saddr; \ + v6 = (void *)__entry->daddr; \ + v6->sin6_family = AF_INET6; \ + v6->sin6_port = protoh->dest; \ + v6->sin6_addr = ipv6_hdr(skb)->daddr; \ + } else \ + TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb, protoh); \ + } while (0) + +#else + +#define TP_STORE_ADDR_PORTS_SKB(__entry, skb, protoh) \ + TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb, protoh) + +#endif + #endif diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 3c08a0846c47..1db95175c1e5 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -273,48 +273,6 @@ TRACE_EVENT(tcp_probe, __entry->skbaddr, __entry->skaddr) ); -#define TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb) \ - do { \ - const struct tcphdr *th = (const struct tcphdr *)skb->data; \ - struct sockaddr_in *v4 = (void *)__entry->saddr; \ - \ - v4->sin_family = AF_INET; \ - v4->sin_port = th->source; \ - v4->sin_addr.s_addr = ip_hdr(skb)->saddr; \ - v4 = (void *)__entry->daddr; \ - v4->sin_family = AF_INET; \ - v4->sin_port = th->dest; \ - v4->sin_addr.s_addr = ip_hdr(skb)->daddr; \ - } while (0) - -#if IS_ENABLED(CONFIG_IPV6) - -#define TP_STORE_ADDR_PORTS_SKB(__entry, skb) \ - do { \ - const struct iphdr *iph = ip_hdr(skb); \ - \ - if (iph->version == 6) { \ - const struct tcphdr *th = (const struct tcphdr *)skb->data; \ - struct sockaddr_in6 *v6 = (void *)__entry->saddr; \ - \ - v6->sin6_family = AF_INET6; \ - v6->sin6_port = th->source; \ - v6->sin6_addr = ipv6_hdr(skb)->saddr; \ - v6 = (void *)__entry->daddr; \ - v6->sin6_family = AF_INET6; \ - v6->sin6_port = th->dest; \ - v6->sin6_addr = ipv6_hdr(skb)->daddr; \ - } else \ - TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb); \ - } while (0) - -#else - -#define TP_STORE_ADDR_PORTS_SKB(__entry, skb) \ - TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb) - -#endif - /* * tcp event with only skb */ @@ -331,12 +289,13 @@ DECLARE_EVENT_CLASS(tcp_event_skb, ), TP_fast_assign( + const struct tcphdr *th = (const struct tcphdr *)skb->data; __entry->skbaddr = skb; memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); - TP_STORE_ADDR_PORTS_SKB(__entry, skb); + TP_STORE_ADDR_PORTS_SKB(__entry, skb, th); ), TP_printk("skbaddr=%p src=%pISpc dest=%pISpc", diff --git a/include/trace/events/udp.h b/include/trace/events/udp.h index 336fe272889f..62bebe2a6ece 100644 --- a/include/trace/events/udp.h +++ b/include/trace/events/udp.h @@ -7,24 +7,43 @@ #include <linux/udp.h> #include <linux/tracepoint.h> +#include <trace/events/net_probe_common.h> TRACE_EVENT(udp_fail_queue_rcv_skb, - TP_PROTO(int rc, struct sock *sk), + TP_PROTO(int rc, struct sock *sk, struct sk_buff *skb), - TP_ARGS(rc, sk), + TP_ARGS(rc, sk, skb), TP_STRUCT__entry( __field(int, rc) - __field(__u16, lport) + + __field(__u16, sport) + __field(__u16, dport) + __field(__u16, family) + __array(__u8, saddr, sizeof(struct sockaddr_in6)) + __array(__u8, daddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( + const struct udphdr *uh = (const struct udphdr *)udp_hdr(skb); + __entry->rc = rc; - __entry->lport = inet_sk(sk)->inet_num; + + /* for filtering use */ + __entry->sport = ntohs(uh->source); + __entry->dport = ntohs(uh->dest); + __entry->family = sk->sk_family; + + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); + + TP_STORE_ADDR_PORTS_SKB(__entry, skb, uh); ), - TP_printk("rc=%d port=%hu", __entry->rc, __entry->lport) + TP_printk("rc=%d family=%s src=%pISpc dest=%pISpc", __entry->rc, + show_family_name(__entry->family), + __entry->saddr, __entry->daddr) ); #endif /* _TRACE_UDP_H */ diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 102119628ff5..e1a246dd8c62 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -161,6 +161,14 @@ enum { #define IFLA_VTI_MAX (__IFLA_VTI_MAX - 1) +#ifndef __KERNEL__ +/* Historically, tunnel flags have been defined as __be16 and now there are + * no free bits left. It is strongly advised to switch the already existing + * userspace code to the new *_BIT definitions from down below, as __be16 + * can't be simply cast to a wider type on LE systems. All new flags and + * code must use *_BIT only. + */ + #define TUNNEL_CSUM __cpu_to_be16(0x01) #define TUNNEL_ROUTING __cpu_to_be16(0x02) #define TUNNEL_KEY __cpu_to_be16(0x04) @@ -181,5 +189,33 @@ enum { #define TUNNEL_OPTIONS_PRESENT \ (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT | \ TUNNEL_GTP_OPT) +#endif + +enum { + IP_TUNNEL_CSUM_BIT = 0U, + IP_TUNNEL_ROUTING_BIT, + IP_TUNNEL_KEY_BIT, + IP_TUNNEL_SEQ_BIT, + IP_TUNNEL_STRICT_BIT, + IP_TUNNEL_REC_BIT, + IP_TUNNEL_VERSION_BIT, + IP_TUNNEL_NO_KEY_BIT, + IP_TUNNEL_DONT_FRAGMENT_BIT, + IP_TUNNEL_OAM_BIT, + IP_TUNNEL_CRIT_OPT_BIT, + IP_TUNNEL_GENEVE_OPT_BIT, /* OPTIONS_PRESENT */ + IP_TUNNEL_VXLAN_OPT_BIT, /* OPTIONS_PRESENT */ + IP_TUNNEL_NOCACHE_BIT, + IP_TUNNEL_ERSPAN_OPT_BIT, /* OPTIONS_PRESENT */ + IP_TUNNEL_GTP_OPT_BIT, /* OPTIONS_PRESENT */ + + IP_TUNNEL_VTI_BIT, + IP_TUNNEL_SIT_ISATAP_BIT = IP_TUNNEL_VTI_BIT, + + /* Flags starting from here are not available via the old UAPI */ + IP_TUNNEL_PFCP_OPT_BIT, /* OPTIONS_PRESENT */ + + __IP_TUNNEL_FLAG_NUM, +}; #endif /* _UAPI_IF_TUNNEL_H_ */ diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index ea277039f89d..229fc925ec3a 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -587,6 +587,10 @@ enum { * TCA_FLOWER_KEY_ENC_OPT_GTP_ * attributes */ + TCA_FLOWER_KEY_ENC_OPTS_PFCP, /* Nested + * TCA_FLOWER_KEY_ENC_IPT_PFCP + * attributes + */ __TCA_FLOWER_KEY_ENC_OPTS_MAX, }; @@ -637,6 +641,16 @@ enum { (__TCA_FLOWER_KEY_ENC_OPT_GTP_MAX - 1) enum { + TCA_FLOWER_KEY_ENC_OPT_PFCP_UNSPEC, + TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE, /* u8 */ + TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID, /* be64 */ + __TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX, +}; + +#define TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX \ + (__TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX - 1) + +enum { TCA_FLOWER_KEY_MPLS_OPTS_UNSPEC, TCA_FLOWER_KEY_MPLS_OPTS_LSE, __TCA_FLOWER_KEY_MPLS_OPTS_MAX, diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index dfe3ee6035ec..87337a0c8e03 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -1180,8 +1180,6 @@ parse_probe_arg(char *arg, const struct fetch_type *type, return ret; } -#define BYTES_TO_BITS(nb) ((BITS_PER_LONG * (nb)) / sizeof(long)) - /* Bitfield type needs to be parsed into a fetch function */ static int __parse_bitfield_probe_arg(const char *bf, const struct fetch_type *t, diff --git a/lib/math/prime_numbers.c b/lib/math/prime_numbers.c index d42cebf7407f..d3b64b10da1c 100644 --- a/lib/math/prime_numbers.c +++ b/lib/math/prime_numbers.c @@ -6,8 +6,6 @@ #include <linux/prime_numbers.h> #include <linux/slab.h> -#define bitmap_size(nbits) (BITS_TO_LONGS(nbits) * sizeof(unsigned long)) - struct primes { struct rcu_head rcu; unsigned long last, sz; diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 6b2b33579f56..83019beabce4 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -60,18 +60,17 @@ static const unsigned long exp3_1_0[] __initconst = { }; static bool __init -__check_eq_uint(const char *srcfile, unsigned int line, - const unsigned int exp_uint, unsigned int x) +__check_eq_ulong(const char *srcfile, unsigned int line, + const unsigned long exp_ulong, unsigned long x) { - if (exp_uint != x) { - pr_err("[%s:%u] expected %u, got %u\n", - srcfile, line, exp_uint, x); + if (exp_ulong != x) { + pr_err("[%s:%u] expected %lu, got %lu\n", + srcfile, line, exp_ulong, x); return false; } return true; } - static bool __init __check_eq_bitmap(const char *srcfile, unsigned int line, const unsigned long *exp_bmap, const unsigned long *bmap, @@ -185,7 +184,8 @@ __check_eq_str(const char *srcfile, unsigned int line, result; \ }) -#define expect_eq_uint(...) __expect_eq(uint, ##__VA_ARGS__) +#define expect_eq_ulong(...) __expect_eq(ulong, ##__VA_ARGS__) +#define expect_eq_uint(x, y) expect_eq_ulong((unsigned int)(x), (unsigned int)(y)) #define expect_eq_bitmap(...) __expect_eq(bitmap, ##__VA_ARGS__) #define expect_eq_pbl(...) __expect_eq(pbl, ##__VA_ARGS__) #define expect_eq_u32_array(...) __expect_eq(u32_array, ##__VA_ARGS__) @@ -548,7 +548,7 @@ static void __init test_bitmap_parselist(void) } if (ptest.flags & PARSE_TIME) - pr_err("parselist: %d: input is '%s' OK, Time: %llu\n", + pr_info("parselist: %d: input is '%s' OK, Time: %llu\n", i, ptest.in, time); #undef ptest @@ -587,7 +587,7 @@ static void __init test_bitmap_printlist(void) goto out; } - pr_err("bitmap_print_to_pagebuf: input is '%s', Time: %llu\n", buf, time); + pr_info("bitmap_print_to_pagebuf: input is '%s', Time: %llu\n", buf, time); out: kfree(buf); kfree(bmap); @@ -665,7 +665,7 @@ static void __init test_bitmap_parse(void) } if (test.flags & PARSE_TIME) - pr_err("parse: %d: input is '%s' OK, Time: %llu\n", + pr_info("parse: %d: input is '%s' OK, Time: %llu\n", i, test.in, time); } } @@ -1245,14 +1245,7 @@ static void __init test_bitmap_const_eval(void) * in runtime. */ - /* - * Equals to `unsigned long bitmap[1] = { GENMASK(6, 5), }`. - * Clang on s390 optimizes bitops at compile-time as intended, but at - * the same time stops treating @bitmap and @bitopvar as compile-time - * constants after regular test_bit() is executed, thus triggering the - * build bugs below. So, call const_test_bit() there directly until - * the compiler is fixed. - */ + /* Equals to `unsigned long bitmap[1] = { GENMASK(6, 5), }` */ bitmap_clear(bitmap, 0, BITS_PER_LONG); if (!test_bit(7, bitmap)) bitmap_set(bitmap, 5, 2); @@ -1284,8 +1277,179 @@ static void __init test_bitmap_const_eval(void) /* ~BIT(25) */ BUILD_BUG_ON(!__builtin_constant_p(~var)); BUILD_BUG_ON(~var != ~BIT(25)); + + /* ~BIT(25) | BIT(25) == ~0UL */ + bitmap_complement(&var, &var, BITS_PER_LONG); + __assign_bit(25, &var, true); + + /* !(~(~0UL)) == 1 */ + res = bitmap_full(&var, BITS_PER_LONG); + BUILD_BUG_ON(!__builtin_constant_p(res)); + BUILD_BUG_ON(!res); +} + +/* + * Test bitmap should be big enough to include the cases when start is not in + * the first word, and start+nbits lands in the following word. + */ +#define TEST_BIT_LEN (1000) + +/* + * Helper function to test bitmap_write() overwriting the chosen byte pattern. + */ +static void __init test_bitmap_write_helper(const char *pattern) +{ + DECLARE_BITMAP(bitmap, TEST_BIT_LEN); + DECLARE_BITMAP(exp_bitmap, TEST_BIT_LEN); + DECLARE_BITMAP(pat_bitmap, TEST_BIT_LEN); + unsigned long w, r, bit; + int i, n, nbits; + + /* + * Only parse the pattern once and store the result in the intermediate + * bitmap. + */ + bitmap_parselist(pattern, pat_bitmap, TEST_BIT_LEN); + + /* + * Check that writing a single bit does not accidentally touch the + * adjacent bits. + */ + for (i = 0; i < TEST_BIT_LEN; i++) { + bitmap_copy(bitmap, pat_bitmap, TEST_BIT_LEN); + bitmap_copy(exp_bitmap, pat_bitmap, TEST_BIT_LEN); + for (bit = 0; bit <= 1; bit++) { + bitmap_write(bitmap, bit, i, 1); + __assign_bit(i, exp_bitmap, bit); + expect_eq_bitmap(exp_bitmap, bitmap, + TEST_BIT_LEN); + } + } + + /* Ensure writing 0 bits does not change anything. */ + bitmap_copy(bitmap, pat_bitmap, TEST_BIT_LEN); + bitmap_copy(exp_bitmap, pat_bitmap, TEST_BIT_LEN); + for (i = 0; i < TEST_BIT_LEN; i++) { + bitmap_write(bitmap, ~0UL, i, 0); + expect_eq_bitmap(exp_bitmap, bitmap, TEST_BIT_LEN); + } + + for (nbits = BITS_PER_LONG; nbits >= 1; nbits--) { + w = IS_ENABLED(CONFIG_64BIT) ? 0xdeadbeefdeadbeefUL + : 0xdeadbeefUL; + w >>= (BITS_PER_LONG - nbits); + for (i = 0; i <= TEST_BIT_LEN - nbits; i++) { + bitmap_copy(bitmap, pat_bitmap, TEST_BIT_LEN); + bitmap_copy(exp_bitmap, pat_bitmap, TEST_BIT_LEN); + for (n = 0; n < nbits; n++) + __assign_bit(i + n, exp_bitmap, w & BIT(n)); + bitmap_write(bitmap, w, i, nbits); + expect_eq_bitmap(exp_bitmap, bitmap, TEST_BIT_LEN); + r = bitmap_read(bitmap, i, nbits); + expect_eq_ulong(r, w); + } + } +} + +static void __init test_bitmap_read_write(void) +{ + unsigned char *pattern[3] = {"", "all:1/2", "all"}; + DECLARE_BITMAP(bitmap, TEST_BIT_LEN); + unsigned long zero_bits = 0, bits_per_long = BITS_PER_LONG; + unsigned long val; + int i, pi; + + /* + * Reading/writing zero bits should not crash the kernel. + * READ_ONCE() prevents constant folding. + */ + bitmap_write(NULL, 0, 0, READ_ONCE(zero_bits)); + /* Return value of bitmap_read() is undefined here. */ + bitmap_read(NULL, 0, READ_ONCE(zero_bits)); + + /* + * Reading/writing more than BITS_PER_LONG bits should not crash the + * kernel. READ_ONCE() prevents constant folding. + */ + bitmap_write(NULL, 0, 0, READ_ONCE(bits_per_long) + 1); + /* Return value of bitmap_read() is undefined here. */ + bitmap_read(NULL, 0, READ_ONCE(bits_per_long) + 1); + + /* + * Ensure that bitmap_read() reads the same value that was previously + * written, and two consequent values are correctly merged. + * The resulting bit pattern is asymmetric to rule out possible issues + * with bit numeration order. + */ + for (i = 0; i < TEST_BIT_LEN - 7; i++) { + bitmap_zero(bitmap, TEST_BIT_LEN); + + bitmap_write(bitmap, 0b10101UL, i, 5); + val = bitmap_read(bitmap, i, 5); + expect_eq_ulong(0b10101UL, val); + + bitmap_write(bitmap, 0b101UL, i + 5, 3); + val = bitmap_read(bitmap, i + 5, 3); + expect_eq_ulong(0b101UL, val); + + val = bitmap_read(bitmap, i, 8); + expect_eq_ulong(0b10110101UL, val); + } + + for (pi = 0; pi < ARRAY_SIZE(pattern); pi++) + test_bitmap_write_helper(pattern[pi]); } +static void __init test_bitmap_read_perf(void) +{ + DECLARE_BITMAP(bitmap, TEST_BIT_LEN); + unsigned int cnt, nbits, i; + unsigned long val; + ktime_t time; + + bitmap_fill(bitmap, TEST_BIT_LEN); + time = ktime_get(); + for (cnt = 0; cnt < 5; cnt++) { + for (nbits = 1; nbits <= BITS_PER_LONG; nbits++) { + for (i = 0; i < TEST_BIT_LEN; i++) { + if (i + nbits > TEST_BIT_LEN) + break; + /* + * Prevent the compiler from optimizing away the + * bitmap_read() by using its value. + */ + WRITE_ONCE(val, bitmap_read(bitmap, i, nbits)); + } + } + } + time = ktime_get() - time; + pr_info("Time spent in %s:\t%llu\n", __func__, time); +} + +static void __init test_bitmap_write_perf(void) +{ + DECLARE_BITMAP(bitmap, TEST_BIT_LEN); + unsigned int cnt, nbits, i; + unsigned long val = 0xfeedface; + ktime_t time; + + bitmap_zero(bitmap, TEST_BIT_LEN); + time = ktime_get(); + for (cnt = 0; cnt < 5; cnt++) { + for (nbits = 1; nbits <= BITS_PER_LONG; nbits++) { + for (i = 0; i < TEST_BIT_LEN; i++) { + if (i + nbits > TEST_BIT_LEN) + break; + bitmap_write(bitmap, val, i, nbits); + } + } + } + time = ktime_get() - time; + pr_info("Time spent in %s:\t%llu\n", __func__, time); +} + +#undef TEST_BIT_LEN + static void __init selftest(void) { test_zero_clear(); @@ -1303,6 +1467,9 @@ static void __init selftest(void) test_bitmap_cut(); test_bitmap_print_buf(); test_bitmap_const_eval(); + test_bitmap_read_write(); + test_bitmap_read_perf(); + test_bitmap_write_perf(); test_find_nth_bit(); test_for_each_set_bit(); diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index a3b68243fd4b..cf5219df7903 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -117,17 +117,15 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[], return err; } if (data[IFLA_VLAN_INGRESS_QOS]) { - nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) { - if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING) - continue; + nla_for_each_nested_type(attr, IFLA_VLAN_QOS_MAPPING, + data[IFLA_VLAN_INGRESS_QOS], rem) { m = nla_data(attr); vlan_dev_set_ingress_priority(dev, m->to, m->from); } } if (data[IFLA_VLAN_EGRESS_QOS]) { - nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) { - if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING) - continue; + nla_for_each_nested_type(attr, IFLA_VLAN_QOS_MAPPING, + data[IFLA_VLAN_EGRESS_QOS], rem) { m = nla_data(attr); err = vlan_dev_set_egress_priority(dev, m->from, m->to); if (err) diff --git a/net/atm/common.c b/net/atm/common.c index 2a1ec014e901..9b75699992ff 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -116,7 +116,7 @@ static void vcc_write_space(struct sock *sk) if (skwq_has_sleeper(wq)) wake_up_interruptible(&wq->wait); - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c index 81833ca7a2c7..a966a6ec8263 100644 --- a/net/bridge/br_vlan_tunnel.c +++ b/net/bridge/br_vlan_tunnel.c @@ -65,13 +65,14 @@ static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, { struct metadata_dst *metadata = rtnl_dereference(vlan->tinfo.tunnel_dst); __be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id)); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; int err; if (metadata) return -EEXIST; - metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY, - key, 0); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, flags, key, 0); if (!metadata) return -EINVAL; @@ -185,6 +186,7 @@ void br_handle_ingress_vlan_tunnel(struct sk_buff *skb, int br_handle_egress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan *vlan) { + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tunnel_dst; __be64 tunnel_id; int err; @@ -202,7 +204,8 @@ int br_handle_egress_vlan_tunnel(struct sk_buff *skb, return err; if (BR_INPUT_SKB_CB(skb)->backup_nhid) { - tunnel_dst = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY, + __set_bit(IP_TUNNEL_KEY_BIT, flags); + tunnel_dst = __ip_tun_set_dst(0, 0, 0, 0, 0, flags, tunnel_id, 0); if (!tunnel_dst) return -ENOMEM; diff --git a/net/core/Makefile b/net/core/Makefile index 6e6548011fae..21d6fbc7e884 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -41,4 +41,4 @@ obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o obj-$(CONFIG_BPF_SYSCALL) += sock_map.o obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o obj-$(CONFIG_OF) += of_net.o -obj-$(CONFIG_NET_TEST) += gso_test.o +obj-$(CONFIG_NET_TEST) += net_test.o diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 6c4d90b24d46..bc01b3aa6b0f 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -496,27 +496,22 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) if (!bpf_capable()) return ERR_PTR(-EPERM); - nla_for_each_nested(nla, nla_stgs, rem) { - if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) { - if (nla_len(nla) != sizeof(u32)) - return ERR_PTR(-EINVAL); - nr_maps++; - } + nla_for_each_nested_type(nla, SK_DIAG_BPF_STORAGE_REQ_MAP_FD, + nla_stgs, rem) { + if (nla_len(nla) != sizeof(u32)) + return ERR_PTR(-EINVAL); + nr_maps++; } diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL); if (!diag) return ERR_PTR(-ENOMEM); - nla_for_each_nested(nla, nla_stgs, rem) { - struct bpf_map *map; - int map_fd; - - if (nla_type(nla) != SK_DIAG_BPF_STORAGE_REQ_MAP_FD) - continue; + nla_for_each_nested_type(nla, SK_DIAG_BPF_STORAGE_REQ_MAP_FD, + nla_stgs, rem) { + int map_fd = nla_get_u32(nla); + struct bpf_map *map = bpf_map_get(map_fd); - map_fd = nla_get_u32(nla); - map = bpf_map_get(map_fd); if (IS_ERR(map)) { err = PTR_ERR(map); goto err_free; diff --git a/net/core/dev.c b/net/core/dev.c index c136e80dea61..818699dea9d7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4528,7 +4528,7 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb, out: #endif rflow->last_qtail = - per_cpu(softnet_data, next_cpu).input_queue_head; + READ_ONCE(per_cpu(softnet_data, next_cpu).input_queue_head); } rflow->cpu = next_cpu; @@ -4610,8 +4610,8 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, */ if (unlikely(tcpu != next_cpu) && (tcpu >= nr_cpu_ids || !cpu_online(tcpu) || - ((int)(per_cpu(softnet_data, tcpu).input_queue_head - - rflow->last_qtail)) >= 0)) { + ((int)(READ_ONCE(per_cpu(softnet_data, tcpu).input_queue_head) - + READ_ONCE(rflow->last_qtail))) >= 0)) { tcpu = next_cpu; rflow = set_rps_cpu(dev, skb, rflow, next_cpu); } @@ -4665,8 +4665,8 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, rflow = &flow_table->flows[flow_id]; cpu = READ_ONCE(rflow->cpu); if (rflow->filter == filter_id && cpu < nr_cpu_ids && - ((int)(per_cpu(softnet_data, cpu).input_queue_head - - rflow->last_qtail) < + ((int)(READ_ONCE(per_cpu(softnet_data, cpu).input_queue_head) - + READ_ONCE(rflow->last_qtail)) < (int)(10 * flow_table->mask))) expire = false; } @@ -4800,37 +4800,45 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, struct softnet_data *sd; unsigned long flags; unsigned int qlen; + int max_backlog; + u32 tail; - reason = SKB_DROP_REASON_NOT_SPECIFIED; + reason = SKB_DROP_REASON_DEV_READY; + if (!netif_running(skb->dev)) + goto bad_dev; + + reason = SKB_DROP_REASON_CPU_BACKLOG; sd = &per_cpu(softnet_data, cpu); + qlen = skb_queue_len_lockless(&sd->input_pkt_queue); + max_backlog = READ_ONCE(net_hotdata.max_backlog); + if (unlikely(qlen > max_backlog)) + goto cpu_backlog_drop; backlog_lock_irq_save(sd, &flags); - if (!netif_running(skb->dev)) - goto drop; qlen = skb_queue_len(&sd->input_pkt_queue); - if (qlen <= READ_ONCE(net_hotdata.max_backlog) && - !skb_flow_limit(skb, qlen)) { - if (qlen) { -enqueue: - __skb_queue_tail(&sd->input_pkt_queue, skb); - input_queue_tail_incr_save(sd, qtail); - backlog_unlock_irq_restore(sd, &flags); - return NET_RX_SUCCESS; + if (qlen <= max_backlog && !skb_flow_limit(skb, qlen)) { + if (!qlen) { + /* Schedule NAPI for backlog device. We can use + * non atomic operation as we own the queue lock. + */ + if (!__test_and_set_bit(NAPI_STATE_SCHED, + &sd->backlog.state)) + napi_schedule_rps(sd); } + __skb_queue_tail(&sd->input_pkt_queue, skb); + tail = rps_input_queue_tail_incr(sd); + backlog_unlock_irq_restore(sd, &flags); - /* Schedule NAPI for backlog device - * We can use non atomic operation since we own the queue lock - */ - if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) - napi_schedule_rps(sd); - goto enqueue; + /* save the tail outside of the critical section */ + rps_input_queue_tail_save(qtail, tail); + return NET_RX_SUCCESS; } - reason = SKB_DROP_REASON_CPU_BACKLOG; -drop: - sd->dropped++; backlog_unlock_irq_restore(sd, &flags); +cpu_backlog_drop: + atomic_inc(&sd->dropped); +bad_dev: dev_core_stats_rx_dropped_inc(skb->dev); kfree_skb_reason(skb, reason); return NET_RX_DROP; @@ -5900,7 +5908,7 @@ static void flush_backlog(struct work_struct *work) if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); dev_kfree_skb_irq(skb); - input_queue_head_incr(sd); + rps_input_queue_head_incr(sd); } } backlog_unlock_irq_enable(sd); @@ -5909,7 +5917,7 @@ static void flush_backlog(struct work_struct *work) if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->process_queue); kfree_skb(skb); - input_queue_head_incr(sd); + rps_input_queue_head_incr(sd); } } local_bh_enable(); @@ -6037,9 +6045,10 @@ static int process_backlog(struct napi_struct *napi, int quota) rcu_read_lock(); __netif_receive_skb(skb); rcu_read_unlock(); - input_queue_head_incr(sd); - if (++work >= quota) + if (++work >= quota) { + rps_input_queue_head_add(sd, work); return work; + } } @@ -6062,6 +6071,8 @@ static int process_backlog(struct napi_struct *napi, int quota) backlog_unlock_irq_enable(sd); } + if (work) + rps_input_queue_head_add(sd, work); return work; } @@ -11451,11 +11462,11 @@ static int dev_cpu_dead(unsigned int oldcpu) /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { netif_rx(skb); - input_queue_head_incr(oldsd); + rps_input_queue_head_incr(oldsd); } while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx(skb); - input_queue_head_incr(oldsd); + rps_input_queue_head_incr(oldsd); } return 0; diff --git a/net/core/dev.h b/net/core/dev.h index 2bcaf8eee50c..8572d2c8dc4a 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -4,11 +4,9 @@ #include <linux/types.h> #include <linux/rwsem.h> +#include <linux/netdevice.h> struct net; -struct net_device; -struct netdev_bpf; -struct netdev_phys_item_id; struct netlink_ext_ack; struct cpumask; @@ -150,4 +148,23 @@ static inline void xdp_do_check_flushed(struct napi_struct *napi) { } #endif struct napi_struct *napi_by_id(unsigned int napi_id); +void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu); + +#define XMIT_RECURSION_LIMIT 8 +static inline bool dev_xmit_recursion(void) +{ + return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > + XMIT_RECURSION_LIMIT); +} + +static inline void dev_xmit_recursion_inc(void) +{ + __this_cpu_inc(softnet_data.xmit.recursion); +} + +static inline void dev_xmit_recursion_dec(void) +{ + __this_cpu_dec(softnet_data.xmit.recursion); +} + #endif diff --git a/net/core/filter.c b/net/core/filter.c index 0c66e4a3fc5b..294670d3850d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4662,7 +4662,7 @@ set_compat: to->tunnel_tos = info->key.tos; to->tunnel_ttl = info->key.ttl; if (flags & BPF_F_TUNINFO_FLAGS) - to->tunnel_flags = info->key.tun_flags; + to->tunnel_flags = ip_tunnel_flags_to_be16(info->key.tun_flags); else to->tunnel_ext = 0; @@ -4705,7 +4705,7 @@ BPF_CALL_3(bpf_skb_get_tunnel_opt, struct sk_buff *, skb, u8 *, to, u32, size) int err; if (unlikely(!info || - !(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT))) { + !ip_tunnel_is_options_present(info->key.tun_flags))) { err = -ENOENT; goto err_clear; } @@ -4775,15 +4775,15 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, memset(info, 0, sizeof(*info)); info->mode = IP_TUNNEL_INFO_TX; - info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE; - if (flags & BPF_F_DONT_FRAGMENT) - info->key.tun_flags |= TUNNEL_DONT_FRAGMENT; - if (flags & BPF_F_ZERO_CSUM_TX) - info->key.tun_flags &= ~TUNNEL_CSUM; - if (flags & BPF_F_SEQ_NUMBER) - info->key.tun_flags |= TUNNEL_SEQ; - if (flags & BPF_F_NO_TUNNEL_KEY) - info->key.tun_flags &= ~TUNNEL_KEY; + __set_bit(IP_TUNNEL_NOCACHE_BIT, info->key.tun_flags); + __assign_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, info->key.tun_flags, + flags & BPF_F_DONT_FRAGMENT); + __assign_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags, + !(flags & BPF_F_ZERO_CSUM_TX)); + __assign_bit(IP_TUNNEL_SEQ_BIT, info->key.tun_flags, + flags & BPF_F_SEQ_NUMBER); + __assign_bit(IP_TUNNEL_KEY_BIT, info->key.tun_flags, + !(flags & BPF_F_NO_TUNNEL_KEY)); info->key.tun_id = cpu_to_be64(from->tunnel_id); info->key.tos = from->tunnel_tos; @@ -4821,13 +4821,15 @@ BPF_CALL_3(bpf_skb_set_tunnel_opt, struct sk_buff *, skb, { struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct metadata_dst *md = this_cpu_ptr(md_dst); + IP_TUNNEL_DECLARE_FLAGS(present) = { }; if (unlikely(info != &md->u.tun_info || (size & (sizeof(u32) - 1)))) return -EINVAL; if (unlikely(size > IP_TUNNEL_OPTS_MAX)) return -ENOMEM; - ip_tunnel_info_opts_set(info, from, size, TUNNEL_OPTIONS_PRESENT); + ip_tunnel_set_options_present(present); + ip_tunnel_info_opts_set(info, from, size, present); return 0; } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 272f09251343..f82e9a7d3b37 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -455,17 +455,25 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb, if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) { struct flow_dissector_key_enc_opts *enc_opt; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; + u32 val; enc_opt = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS, target_container); - if (info->options_len) { - enc_opt->len = info->options_len; - ip_tunnel_info_opts_get(enc_opt->data, info); - enc_opt->dst_opt_type = info->key.tun_flags & - TUNNEL_OPTIONS_PRESENT; - } + if (!info->options_len) + return; + + enc_opt->len = info->options_len; + ip_tunnel_info_opts_get(enc_opt->data, info); + + ip_tunnel_set_options_present(flags); + ip_tunnel_flags_and(flags, info->key.tun_flags, flags); + + val = find_next_bit(flags, __IP_TUNNEL_FLAG_NUM, + IP_TUNNEL_GENEVE_OPT_BIT); + enc_opt->dst_opt_type = val < __IP_TUNNEL_FLAG_NUM ? val : 0; } } EXPORT_SYMBOL(skb_flow_dissect_tunnel_info); diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index a97eceb84e61..fa6d3969734a 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -144,7 +144,8 @@ static int softnet_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x " "%08x %08x\n", - sd->processed, sd->dropped, sd->time_squeeze, 0, + sd->processed, atomic_read(&sd->dropped), + sd->time_squeeze, 0, 0, 0, 0, 0, /* was fastroute */ 0, /* was cpu_collision */ sd->received_rps, flow_limit_count, diff --git a/net/core/gso_test.c b/net/core/net_test.c index 358c44680d91..9c3a590865d2 100644 --- a/net/core/gso_test.c +++ b/net/core/net_test.c @@ -1,6 +1,9 @@ // SPDX-License-Identifier: GPL-2.0-or-later #include <kunit/test.h> + +/* GSO */ + #include <linux/skbuff.h> static const char hdr[] = "abcdefgh"; @@ -258,17 +261,127 @@ free_gso_skb: consume_skb(skb); } -static struct kunit_case gso_test_cases[] = { - KUNIT_CASE_PARAM(gso_test_func, gso_test_gen_params), - {} +/* IP tunnel flags */ + +#include <net/ip_tunnels.h> + +struct ip_tunnel_flags_test { + const char *name; + + const u16 *src_bits; + const u16 *exp_bits; + u8 src_num; + u8 exp_num; + + __be16 exp_val; + bool exp_comp; +}; + +#define IP_TUNNEL_FLAGS_TEST(n, src, comp, eval, exp) { \ + .name = (n), \ + .src_bits = (src), \ + .src_num = ARRAY_SIZE(src), \ + .exp_comp = (comp), \ + .exp_val = (eval), \ + .exp_bits = (exp), \ + .exp_num = ARRAY_SIZE(exp), \ +} + +/* These are __be16-compatible and can be compared as is */ +static const u16 ip_tunnel_flags_1[] = { + IP_TUNNEL_KEY_BIT, + IP_TUNNEL_STRICT_BIT, + IP_TUNNEL_ERSPAN_OPT_BIT, +}; + +/* Due to the previous flags design limitation, setting either + * ``IP_TUNNEL_CSUM_BIT`` (on Big Endian) or ``IP_TUNNEL_DONT_FRAGMENT_BIT`` + * (on Little) also sets VTI/ISATAP bit. In the bitmap implementation, they + * correspond to ``BIT(16)``, which is bigger than ``U16_MAX``, but still is + * backward-compatible. + */ +#ifdef __LITTLE_ENDIAN +#define IP_TUNNEL_CONFLICT_BIT IP_TUNNEL_DONT_FRAGMENT_BIT +#else +#define IP_TUNNEL_CONFLICT_BIT IP_TUNNEL_CSUM_BIT +#endif + +static const u16 ip_tunnel_flags_2_src[] = { + IP_TUNNEL_CONFLICT_BIT, +}; + +static const u16 ip_tunnel_flags_2_exp[] = { + IP_TUNNEL_CONFLICT_BIT, + IP_TUNNEL_SIT_ISATAP_BIT, }; -static struct kunit_suite gso_test_suite = { - .name = "net_core_gso", - .test_cases = gso_test_cases, +/* Bits 17 and higher are not compatible with __be16 flags */ +static const u16 ip_tunnel_flags_3_src[] = { + IP_TUNNEL_VXLAN_OPT_BIT, + 17, + 18, + 20, }; -kunit_test_suite(gso_test_suite); +static const u16 ip_tunnel_flags_3_exp[] = { + IP_TUNNEL_VXLAN_OPT_BIT, +}; + +static const struct ip_tunnel_flags_test ip_tunnel_flags_test[] = { + IP_TUNNEL_FLAGS_TEST("compat", ip_tunnel_flags_1, true, + cpu_to_be16(BIT(IP_TUNNEL_KEY_BIT) | + BIT(IP_TUNNEL_STRICT_BIT) | + BIT(IP_TUNNEL_ERSPAN_OPT_BIT)), + ip_tunnel_flags_1), + IP_TUNNEL_FLAGS_TEST("conflict", ip_tunnel_flags_2_src, true, + VTI_ISVTI, ip_tunnel_flags_2_exp), + IP_TUNNEL_FLAGS_TEST("new", ip_tunnel_flags_3_src, false, + cpu_to_be16(BIT(IP_TUNNEL_VXLAN_OPT_BIT)), + ip_tunnel_flags_3_exp), +}; + +static void +ip_tunnel_flags_test_case_to_desc(const struct ip_tunnel_flags_test *t, + char *desc) +{ + strscpy(desc, t->name, KUNIT_PARAM_DESC_SIZE); +} +KUNIT_ARRAY_PARAM(ip_tunnel_flags_test, ip_tunnel_flags_test, + ip_tunnel_flags_test_case_to_desc); + +static void ip_tunnel_flags_test_run(struct kunit *test) +{ + const struct ip_tunnel_flags_test *t = test->param_value; + IP_TUNNEL_DECLARE_FLAGS(src) = { }; + IP_TUNNEL_DECLARE_FLAGS(exp) = { }; + IP_TUNNEL_DECLARE_FLAGS(out); + + for (u32 j = 0; j < t->src_num; j++) + __set_bit(t->src_bits[j], src); + for (u32 j = 0; j < t->exp_num; j++) + __set_bit(t->exp_bits[j], exp); + + KUNIT_ASSERT_EQ(test, t->exp_comp, + ip_tunnel_flags_is_be16_compat(src)); + KUNIT_ASSERT_EQ(test, (__force u16)t->exp_val, + (__force u16)ip_tunnel_flags_to_be16(src)); + + ip_tunnel_flags_from_be16(out, t->exp_val); + KUNIT_ASSERT_TRUE(test, __ipt_flag_op(bitmap_equal, exp, out)); +} + +static struct kunit_case net_test_cases[] = { + KUNIT_CASE_PARAM(gso_test_func, gso_test_gen_params), + KUNIT_CASE_PARAM(ip_tunnel_flags_test_run, + ip_tunnel_flags_test_gen_params), + { }, +}; + +static struct kunit_suite net_test_suite = { + .name = "net_core", + .test_cases = net_test_cases, +}; +kunit_test_suite(net_test_suite); +MODULE_DESCRIPTION("KUnit tests for networking core"); MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("KUnit tests for segmentation offload"); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a3d7847ce69d..283e42f48af6 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -5245,15 +5245,14 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (br_spec) { - nla_for_each_nested(attr, br_spec, rem) { - if (nla_type(attr) == IFLA_BRIDGE_FLAGS) { - if (nla_len(attr) < sizeof(flags)) - return -EINVAL; + nla_for_each_nested_type(attr, IFLA_BRIDGE_FLAGS, br_spec, + rem) { + if (nla_len(attr) < sizeof(flags)) + return -EINVAL; - have_flags = true; - flags = nla_get_u16(attr); - break; - } + have_flags = true; + flags = nla_get_u16(attr); + break; } } diff --git a/net/core/sock.c b/net/core/sock.c index 0963689a5950..5ed411231fc7 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3338,7 +3338,7 @@ static void sock_def_error_report(struct sock *sk) wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_poll(&wq->wait, EPOLLERR); - sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR); + sk_wake_async_rcu(sk, SOCK_WAKE_IO, POLL_ERR); rcu_read_unlock(); } @@ -3353,7 +3353,7 @@ void sock_def_readable(struct sock *sk) if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI | EPOLLRDNORM | EPOLLRDBAND); - sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); + sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); } @@ -3373,7 +3373,7 @@ static void sock_def_write_space(struct sock *sk) EPOLLWRNORM | EPOLLWRBAND); /* Should agree with poll, otherwise some programs break */ - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); @@ -3398,7 +3398,7 @@ static void sock_def_write_space_wfree(struct sock *sk) EPOLLWRNORM | EPOLLWRBAND); /* Should agree with poll, otherwise some programs break */ - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 44b033fe1ef6..9fc9cea4c251 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -1039,7 +1039,7 @@ static void __net_exit dccp_v4_exit_net(struct net *net) static void __net_exit dccp_v4_exit_batch(struct list_head *net_exit_list) { - inet_twsk_purge(&dccp_hashinfo, AF_INET); + inet_twsk_purge(&dccp_hashinfo); } static struct pernet_operations dccp_v4_ops = { diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index ded07e09f813..c8ca703dc331 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1119,15 +1119,9 @@ static void __net_exit dccp_v6_exit_net(struct net *net) inet_ctl_sock_destroy(pn->v6_ctl_sk); } -static void __net_exit dccp_v6_exit_batch(struct list_head *net_exit_list) -{ - inet_twsk_purge(&dccp_hashinfo, AF_INET6); -} - static struct pernet_operations dccp_v6_ops = { .init = dccp_v6_init_net, .exit = dccp_v6_exit_net, - .exit_batch = dccp_v6_exit_batch, .id = &dccp_v6_pernet_id, .size = sizeof(struct dccp_v6_pernet), }; diff --git a/net/dccp/output.c b/net/dccp/output.c index fd2eb148d24d..5c2e24f3c39b 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -204,7 +204,7 @@ void dccp_write_space(struct sock *sk) wake_up_interruptible(&wq->wait); /* Should agree with poll, otherwise some programs break */ if (sock_writeable(sk)) - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); rcu_read_unlock(); } diff --git a/net/devlink/core.c b/net/devlink/core.c index 7f0b093208d7..f49cd83f1955 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -314,7 +314,7 @@ static void devlink_release(struct work_struct *work) mutex_destroy(&devlink->lock); lockdep_unregister_key(&devlink->lock_key); put_device(devlink->dev); - kfree(devlink); + kvfree(devlink); } void devlink_put(struct devlink *devlink) @@ -420,7 +420,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, if (!devlink_reload_actions_valid(ops)) return NULL; - devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL); + devlink = kvzalloc(struct_size(devlink, priv, priv_size), GFP_KERNEL); if (!devlink) return NULL; @@ -455,7 +455,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, return devlink; err_xa_alloc: - kfree(devlink); + kvfree(devlink); return NULL; } EXPORT_SYMBOL_GPL(devlink_alloc_ns); diff --git a/net/devlink/dev.c b/net/devlink/dev.c index 19dbf540748a..c609deb42e88 100644 --- a/net/devlink/dev.c +++ b/net/devlink/dev.c @@ -1202,17 +1202,13 @@ static void __devlink_compat_running_version(struct devlink *devlink, if (err) goto free_msg; - nla_for_each_attr(nlattr, (void *)msg->data, msg->len, rem) { + nla_for_each_attr_type(nlattr, DEVLINK_ATTR_INFO_VERSION_RUNNING, + (void *)msg->data, msg->len, rem) { const struct nlattr *kv; int rem_kv; - if (nla_type(nlattr) != DEVLINK_ATTR_INFO_VERSION_RUNNING) - continue; - - nla_for_each_nested(kv, nlattr, rem_kv) { - if (nla_type(kv) != DEVLINK_ATTR_INFO_VERSION_VALUE) - continue; - + nla_for_each_nested_type(kv, DEVLINK_ATTR_INFO_VERSION_VALUE, + nlattr, rem_kv) { strlcat(buf, nla_data(kv), len); strlcat(buf, " ", len); } diff --git a/net/ipv4/fou_bpf.c b/net/ipv4/fou_bpf.c index 06e5572f296f..54984f3170a8 100644 --- a/net/ipv4/fou_bpf.c +++ b/net/ipv4/fou_bpf.c @@ -64,7 +64,7 @@ __bpf_kfunc int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx, info->encap.type = TUNNEL_ENCAP_NONE; } - if (info->key.tun_flags & TUNNEL_CSUM) + if (test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)) info->encap.flags |= TUNNEL_ENCAP_FLAG_CSUM; info->encap.sport = encap->sport; diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 3757fd93523f..6701a98d9a9f 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -73,7 +73,7 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; - tpi->flags = gre_flags_to_tnl_flags(greh->flags); + gre_flags_to_tnl_flags(tpi->flags, greh->flags); hdr_len = gre_calc_hlen(tpi->flags); if (!pskb_may_pull(skb, nhs + hdr_len)) diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index b0cc07d9a568..e28075f0006e 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -264,7 +264,7 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) EXPORT_SYMBOL_GPL(__inet_twsk_schedule); /* Remove all non full sockets (TIME_WAIT and NEW_SYN_RECV) for dead netns */ -void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) +void inet_twsk_purge(struct inet_hashinfo *hashinfo) { struct inet_ehash_bucket *head = &hashinfo->ehash[0]; unsigned int ehash_mask = hashinfo->ehash_mask; @@ -273,7 +273,6 @@ void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) struct sock *sk; for (slot = 0; slot <= ehash_mask; slot++, head++) { - if (hlist_nulls_empty(&head->chain)) continue; @@ -288,15 +287,13 @@ restart: TCPF_NEW_SYN_RECV)) continue; - if (sk->sk_family != family || - refcount_read(&sock_net(sk)->ns.count)) + if (refcount_read(&sock_net(sk)->ns.count)) continue; if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) continue; - if (unlikely(sk->sk_family != family || - refcount_read(&sock_net(sk)->ns.count))) { + if (refcount_read(&sock_net(sk)->ns.count)) { sock_gen_put(sk); goto restart; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 7b16c211b904..3c46a7fef8db 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -265,6 +265,7 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, struct net *net = dev_net(skb->dev); struct metadata_dst *tun_dst = NULL; struct erspan_base_hdr *ershdr; + IP_TUNNEL_DECLARE_FLAGS(flags); struct ip_tunnel_net *itn; struct ip_tunnel *tunnel; const struct iphdr *iph; @@ -272,18 +273,20 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, int ver; int len; + ip_tunnel_flags_copy(flags, tpi->flags); + itn = net_generic(net, erspan_net_id); iph = ip_hdr(skb); if (is_erspan_type1(gre_hdr_len)) { ver = 0; - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, - tpi->flags | TUNNEL_NO_KEY, + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, 0); } else { ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, - tpi->flags | TUNNEL_KEY, + __set_bit(IP_TUNNEL_KEY_BIT, flags); + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, tpi->key); } @@ -307,10 +310,9 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, struct ip_tunnel_info *info; unsigned char *gh; __be64 tun_id; - __be16 flags; - tpi->flags |= TUNNEL_KEY; - flags = tpi->flags; + __set_bit(IP_TUNNEL_KEY_BIT, tpi->flags); + ip_tunnel_flags_copy(flags, tpi->flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, @@ -333,7 +335,8 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, ERSPAN_V2_MDSIZE); info = &tun_dst->u.tun_info; - info->key.tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + info->key.tun_flags); info->options_len = sizeof(*md); } @@ -376,10 +379,13 @@ static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, tnl_params = &tunnel->parms.iph; if (tunnel->collect_md || tnl_params->daddr == 0) { - __be16 flags; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __be64 tun_id; - flags = tpi->flags & (TUNNEL_CSUM | TUNNEL_KEY); + __set_bit(IP_TUNNEL_CSUM_BIT, flags); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + ip_tunnel_flags_and(flags, tpi->flags, flags); + tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0); if (!tun_dst) @@ -459,12 +465,15 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); - __be16 flags = tunnel->parms.o_flags; + IP_TUNNEL_DECLARE_FLAGS(flags); + + ip_tunnel_flags_copy(flags, tunnel->parms.o_flags); /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, flags, proto, tunnel->parms.o_key, - (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); + test_bit(IP_TUNNEL_SEQ_BIT, flags) ? + htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } @@ -478,10 +487,10 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; int tunnel_hlen; - __be16 flags; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || @@ -495,14 +504,19 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, goto err_free_skb; /* Push Tunnel header. */ - if (gre_handle_offloads(skb, !!(tun_info->key.tun_flags & TUNNEL_CSUM))) + if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + tunnel->parms.o_flags))) goto err_free_skb; - flags = tun_info->key.tun_flags & - (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); + __set_bit(IP_TUNNEL_CSUM_BIT, flags); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + __set_bit(IP_TUNNEL_SEQ_BIT, flags); + ip_tunnel_flags_and(flags, tun_info->key.tun_flags, flags); + gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); + test_bit(IP_TUNNEL_SEQ_BIT, flags) ? + htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -516,6 +530,7 @@ err_free_skb: static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; struct erspan_metadata *md; @@ -531,7 +546,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; key = &tun_info->key; - if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) + if (!test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_info->key.tun_flags)) goto err_free_skb; if (tun_info->options_len < sizeof(*md)) goto err_free_skb; @@ -584,8 +599,9 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; } - gre_build_header(skb, 8, TUNNEL_SEQ, - proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); + __set_bit(IP_TUNNEL_SEQ_BIT, flags); + gre_build_header(skb, 8, flags, proto, 0, + htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -659,7 +675,8 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, tnl_params = &tunnel->parms.iph; } - if (gre_handle_offloads(skb, !!(tunnel->parms.o_flags & TUNNEL_CSUM))) + if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + tunnel->parms.o_flags))) goto free_skb; __gre_xmit(skb, dev, tnl_params, skb->protocol); @@ -701,7 +718,7 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, /* Push ERSPAN header */ if (tunnel->erspan_ver == 0) { proto = htons(ETH_P_ERSPAN); - tunnel->parms.o_flags &= ~TUNNEL_SEQ; + __clear_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags); } else if (tunnel->erspan_ver == 1) { erspan_build_header(skb, ntohl(tunnel->parms.o_key), tunnel->index, @@ -716,7 +733,7 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, goto free_skb; } - tunnel->parms.o_flags &= ~TUNNEL_KEY; + __clear_bit(IP_TUNNEL_KEY_BIT, tunnel->parms.o_flags); __gre_xmit(skb, dev, &tunnel->parms.iph, proto); return NETDEV_TX_OK; @@ -739,7 +756,8 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } - if (gre_handle_offloads(skb, !!(tunnel->parms.o_flags & TUNNEL_CSUM))) + if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + tunnel->parms.o_flags))) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) @@ -757,7 +775,6 @@ free_skb: static void ipgre_link_update(struct net_device *dev, bool set_mtu) { struct ip_tunnel *tunnel = netdev_priv(dev); - __be16 flags; int len; len = tunnel->tun_hlen; @@ -773,10 +790,9 @@ static void ipgre_link_update(struct net_device *dev, bool set_mtu) if (set_mtu) dev->mtu = max_t(int, dev->mtu - len, 68); - flags = tunnel->parms.o_flags; - - if (flags & TUNNEL_SEQ || - (flags & TUNNEL_CSUM && tunnel->encap.type != TUNNEL_ENCAP_NONE)) { + if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags) || + (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && + tunnel->encap.type != TUNNEL_ENCAP_NONE)) { dev->features &= ~NETIF_F_GSO_SOFTWARE; dev->hw_features &= ~NETIF_F_GSO_SOFTWARE; } else { @@ -785,20 +801,29 @@ static void ipgre_link_update(struct net_device *dev, bool set_mtu) } } -static int ipgre_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, +static int ipgre_tunnel_ctl(struct net_device *dev, + struct ip_tunnel_parm_kern *p, int cmd) { + __be16 i_flags, o_flags; int err; + if (!ip_tunnel_flags_is_be16_compat(p->i_flags) || + !ip_tunnel_flags_is_be16_compat(p->o_flags)) + return -EOVERFLOW; + + i_flags = ip_tunnel_flags_to_be16(p->i_flags); + o_flags = ip_tunnel_flags_to_be16(p->o_flags); + if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || p->iph.protocol != IPPROTO_GRE || p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF)) || - ((p->i_flags | p->o_flags) & (GRE_VERSION | GRE_ROUTING))) + ((i_flags | o_flags) & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; } - p->i_flags = gre_flags_to_tnl_flags(p->i_flags); - p->o_flags = gre_flags_to_tnl_flags(p->o_flags); + gre_flags_to_tnl_flags(p->i_flags, i_flags); + gre_flags_to_tnl_flags(p->o_flags, o_flags); err = ip_tunnel_ctl(dev, p, cmd); if (err) @@ -807,15 +832,18 @@ static int ipgre_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, if (cmd == SIOCCHGTUNNEL) { struct ip_tunnel *t = netdev_priv(dev); - t->parms.i_flags = p->i_flags; - t->parms.o_flags = p->o_flags; + ip_tunnel_flags_copy(t->parms.i_flags, p->i_flags); + ip_tunnel_flags_copy(t->parms.o_flags, p->o_flags); if (strcmp(dev->rtnl_link_ops->kind, "erspan")) ipgre_link_update(dev, true); } - p->i_flags = gre_tnl_flags_to_gre_flags(p->i_flags); - p->o_flags = gre_tnl_flags_to_gre_flags(p->o_flags); + i_flags = gre_tnl_flags_to_gre_flags(p->i_flags); + ip_tunnel_flags_from_be16(p->i_flags, i_flags); + o_flags = gre_tnl_flags_to_gre_flags(p->o_flags); + ip_tunnel_flags_from_be16(p->o_flags, o_flags); + return 0; } @@ -955,7 +983,6 @@ static void ipgre_tunnel_setup(struct net_device *dev) static void __gre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel; - __be16 flags; tunnel = netdev_priv(dev); tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); @@ -967,14 +994,13 @@ static void __gre_tunnel_init(struct net_device *dev) dev->features |= GRE_FEATURES | NETIF_F_LLTX; dev->hw_features |= GRE_FEATURES; - flags = tunnel->parms.o_flags; - /* TCP offload with GRE SEQ is not supported, nor can we support 2 * levels of outer headers requiring an update. */ - if (flags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags)) return; - if (flags & TUNNEL_CSUM && tunnel->encap.type != TUNNEL_ENCAP_NONE) + if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && + tunnel->encap.type != TUNNEL_ENCAP_NONE) return; dev->features |= NETIF_F_GSO_SOFTWARE; @@ -1131,7 +1157,7 @@ static int erspan_validate(struct nlattr *tb[], struct nlattr *data[], static int ipgre_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], - struct ip_tunnel_parm *parms, + struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); @@ -1147,10 +1173,12 @@ static int ipgre_netlink_parms(struct net_device *dev, parms->link = nla_get_u32(data[IFLA_GRE_LINK]); if (data[IFLA_GRE_IFLAGS]) - parms->i_flags = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_IFLAGS])); + gre_flags_to_tnl_flags(parms->i_flags, + nla_get_be16(data[IFLA_GRE_IFLAGS])); if (data[IFLA_GRE_OFLAGS]) - parms->o_flags = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_OFLAGS])); + gre_flags_to_tnl_flags(parms->o_flags, + nla_get_be16(data[IFLA_GRE_OFLAGS])); if (data[IFLA_GRE_IKEY]) parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]); @@ -1198,7 +1226,7 @@ static int ipgre_netlink_parms(struct net_device *dev, static int erspan_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], - struct ip_tunnel_parm *parms, + struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); @@ -1357,7 +1385,7 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - struct ip_tunnel_parm p; + struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; @@ -1375,7 +1403,7 @@ static int erspan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - struct ip_tunnel_parm p; + struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; @@ -1394,8 +1422,8 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); + struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; - struct ip_tunnel_parm p; int err; err = ipgre_newlink_encap_setup(dev, data); @@ -1410,8 +1438,8 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], if (err < 0) return err; - t->parms.i_flags = p.i_flags; - t->parms.o_flags = p.o_flags; + ip_tunnel_flags_copy(t->parms.i_flags, p.i_flags); + ip_tunnel_flags_copy(t->parms.o_flags, p.o_flags); ipgre_link_update(dev, !tb[IFLA_MTU]); @@ -1423,8 +1451,8 @@ static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); + struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; - struct ip_tunnel_parm p; int err; err = ipgre_newlink_encap_setup(dev, data); @@ -1439,8 +1467,8 @@ static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], if (err < 0) return err; - t->parms.i_flags = p.i_flags; - t->parms.o_flags = p.o_flags; + ip_tunnel_flags_copy(t->parms.i_flags, p.i_flags); + ip_tunnel_flags_copy(t->parms.o_flags, p.o_flags); return 0; } @@ -1496,8 +1524,10 @@ static size_t ipgre_get_size(const struct net_device *dev) static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_parm *p = &t->parms; - __be16 o_flags = p->o_flags; + struct ip_tunnel_parm_kern *p = &t->parms; + IP_TUNNEL_DECLARE_FLAGS(o_flags); + + ip_tunnel_flags_copy(o_flags, p->o_flags); if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, @@ -1545,7 +1575,7 @@ static int erspan_fill_info(struct sk_buff *skb, const struct net_device *dev) if (t->erspan_ver <= 2) { if (t->erspan_ver != 0 && !t->collect_md) - t->parms.o_flags |= TUNNEL_KEY; + __set_bit(IP_TUNNEL_KEY_BIT, t->parms.o_flags); if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) goto nla_put_failure; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 1b8d8ff9a237..f65170a28106 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -56,17 +56,13 @@ static unsigned int ip_tunnel_hash(__be32 key, __be32 remote) IP_TNL_HASH_BITS); } -static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p, - __be16 flags, __be32 key) +static bool ip_tunnel_key_match(const struct ip_tunnel_parm_kern *p, + const unsigned long *flags, __be32 key) { - if (p->i_flags & TUNNEL_KEY) { - if (flags & TUNNEL_KEY) - return key == p->i_key; - else - /* key expected, none present */ - return false; - } else - return !(flags & TUNNEL_KEY); + if (!test_bit(IP_TUNNEL_KEY_BIT, flags)) + return !test_bit(IP_TUNNEL_KEY_BIT, p->i_flags); + + return test_bit(IP_TUNNEL_KEY_BIT, p->i_flags) && p->i_key == key; } /* Fallback tunnel: no source, no destination, no key, no options @@ -81,7 +77,7 @@ static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p, Given src, dst and key, find appropriate for input tunnel. */ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, - int link, __be16 flags, + int link, const unsigned long *flags, __be32 remote, __be32 local, __be32 key) { @@ -143,7 +139,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, } hlist_for_each_entry_rcu(t, head, hash_node) { - if ((!(flags & TUNNEL_NO_KEY) && t->parms.i_key != key) || + if ((!test_bit(IP_TUNNEL_NO_KEY_BIT, flags) && + t->parms.i_key != key) || t->parms.iph.saddr != 0 || t->parms.iph.daddr != 0 || !(t->dev->flags & IFF_UP)) @@ -171,7 +168,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, EXPORT_SYMBOL_GPL(ip_tunnel_lookup); static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn, - struct ip_tunnel_parm *parms) + struct ip_tunnel_parm_kern *parms) { unsigned int h; __be32 remote; @@ -182,7 +179,8 @@ static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn, else remote = 0; - if (!(parms->i_flags & TUNNEL_KEY) && (parms->i_flags & VTI_ISVTI)) + if (!test_bit(IP_TUNNEL_KEY_BIT, parms->i_flags) && + test_bit(IP_TUNNEL_VTI_BIT, parms->i_flags)) i_key = 0; h = ip_tunnel_hash(i_key, remote); @@ -206,17 +204,19 @@ static void ip_tunnel_del(struct ip_tunnel_net *itn, struct ip_tunnel *t) } static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, - struct ip_tunnel_parm *parms, + struct ip_tunnel_parm_kern *parms, int type) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; + IP_TUNNEL_DECLARE_FLAGS(flags); __be32 key = parms->i_key; - __be16 flags = parms->i_flags; int link = parms->link; struct ip_tunnel *t = NULL; struct hlist_head *head = ip_bucket(itn, parms); + ip_tunnel_flags_copy(flags, parms->i_flags); + hlist_for_each_entry_rcu(t, head, hash_node) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && @@ -230,7 +230,7 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, static struct net_device *__ip_tunnel_create(struct net *net, const struct rtnl_link_ops *ops, - struct ip_tunnel_parm *parms) + struct ip_tunnel_parm_kern *parms) { int err; struct ip_tunnel *tunnel; @@ -326,7 +326,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) static struct ip_tunnel *ip_tunnel_create(struct net *net, struct ip_tunnel_net *itn, - struct ip_tunnel_parm *parms) + struct ip_tunnel_parm_kern *parms) { struct ip_tunnel *nt; struct net_device *dev; @@ -386,15 +386,15 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, } #endif - if ((!(tpi->flags&TUNNEL_CSUM) && (tunnel->parms.i_flags&TUNNEL_CSUM)) || - ((tpi->flags&TUNNEL_CSUM) && !(tunnel->parms.i_flags&TUNNEL_CSUM))) { + if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.i_flags) != + test_bit(IP_TUNNEL_CSUM_BIT, tpi->flags)) { DEV_STATS_INC(tunnel->dev, rx_crc_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } - if (tunnel->parms.i_flags&TUNNEL_SEQ) { - if (!(tpi->flags&TUNNEL_SEQ) || + if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.i_flags)) { + if (!test_bit(IP_TUNNEL_SEQ_BIT, tpi->flags) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { DEV_STATS_INC(tunnel->dev, rx_fifo_errors); DEV_STATS_INC(tunnel->dev, rx_errors); @@ -638,7 +638,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } - if (key->tun_flags & TUNNEL_DONT_FRAGMENT) + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags)) df = htons(IP_DF); if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, tunnel_hlen, key->u.ipv4.dst, true)) { @@ -871,7 +871,7 @@ EXPORT_SYMBOL_GPL(ip_tunnel_xmit); static void ip_tunnel_update(struct ip_tunnel_net *itn, struct ip_tunnel *t, struct net_device *dev, - struct ip_tunnel_parm *p, + struct ip_tunnel_parm_kern *p, bool set_mtu, __u32 fwmark) { @@ -903,7 +903,8 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, netdev_state_change(dev); } -int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) +int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, + int cmd) { int err = 0; struct ip_tunnel *t = netdev_priv(dev); @@ -927,10 +928,10 @@ int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) goto done; if (p->iph.ttl) p->iph.frag_off |= htons(IP_DF); - if (!(p->i_flags & VTI_ISVTI)) { - if (!(p->i_flags & TUNNEL_KEY)) + if (!test_bit(IP_TUNNEL_VTI_BIT, p->i_flags)) { + if (!test_bit(IP_TUNNEL_KEY_BIT, p->i_flags)) p->i_key = 0; - if (!(p->o_flags & TUNNEL_KEY)) + if (!test_bit(IP_TUNNEL_KEY_BIT, p->o_flags)) p->o_key = 0; } @@ -1005,16 +1006,56 @@ done: } EXPORT_SYMBOL_GPL(ip_tunnel_ctl); +bool ip_tunnel_parm_from_user(struct ip_tunnel_parm_kern *kp, + const void __user *data) +{ + struct ip_tunnel_parm p; + + if (copy_from_user(&p, data, sizeof(p))) + return false; + + strscpy(kp->name, p.name); + kp->link = p.link; + ip_tunnel_flags_from_be16(kp->i_flags, p.i_flags); + ip_tunnel_flags_from_be16(kp->o_flags, p.o_flags); + kp->i_key = p.i_key; + kp->o_key = p.o_key; + memcpy(&kp->iph, &p.iph, min(sizeof(kp->iph), sizeof(p.iph))); + + return true; +} +EXPORT_SYMBOL_GPL(ip_tunnel_parm_from_user); + +bool ip_tunnel_parm_to_user(void __user *data, struct ip_tunnel_parm_kern *kp) +{ + struct ip_tunnel_parm p; + + if (!ip_tunnel_flags_is_be16_compat(kp->i_flags) || + !ip_tunnel_flags_is_be16_compat(kp->o_flags)) + return false; + + strscpy(p.name, kp->name); + p.link = kp->link; + p.i_flags = ip_tunnel_flags_to_be16(kp->i_flags); + p.o_flags = ip_tunnel_flags_to_be16(kp->o_flags); + p.i_key = kp->i_key; + p.o_key = kp->o_key; + memcpy(&p.iph, &kp->iph, min(sizeof(p.iph), sizeof(kp->iph))); + + return !copy_to_user(data, &p, sizeof(p)); +} +EXPORT_SYMBOL_GPL(ip_tunnel_parm_to_user); + int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { - struct ip_tunnel_parm p; + struct ip_tunnel_parm_kern p; int err; - if (copy_from_user(&p, data, sizeof(p))) + if (!ip_tunnel_parm_from_user(&p, data)) return -EFAULT; err = dev->netdev_ops->ndo_tunnel_ctl(dev, &p, cmd); - if (!err && copy_to_user(data, &p, sizeof(p))) + if (!err && !ip_tunnel_parm_to_user(data, &p)) return -EFAULT; return err; } @@ -1093,7 +1134,7 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, struct rtnl_link_ops *ops, char *devname) { struct ip_tunnel_net *itn = net_generic(net, ip_tnl_net_id); - struct ip_tunnel_parm parms; + struct ip_tunnel_parm_kern parms; unsigned int i; itn->rtnl_link_ops = ops; @@ -1171,7 +1212,7 @@ void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id, EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets); int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], - struct ip_tunnel_parm *p, __u32 fwmark) + struct ip_tunnel_parm_kern *p, __u32 fwmark) { struct ip_tunnel *nt; struct net *net = dev_net(dev); @@ -1225,7 +1266,7 @@ err_register_netdevice: EXPORT_SYMBOL_GPL(ip_tunnel_newlink); int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], - struct ip_tunnel_parm *p, __u32 fwmark) + struct ip_tunnel_parm_kern *p, __u32 fwmark) { struct ip_tunnel *t; struct ip_tunnel *tunnel = netdev_priv(dev); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 80ccd6661aa3..a3676155be78 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -125,6 +125,7 @@ EXPORT_SYMBOL_GPL(__iptunnel_pull_header); struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags) { + IP_TUNNEL_DECLARE_FLAGS(tun_flags) = { }; struct metadata_dst *res; struct ip_tunnel_info *dst, *src; @@ -144,10 +145,10 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, sizeof(struct in6_addr)); else dst->key.u.ipv4.dst = src->key.u.ipv4.src; - dst->key.tun_flags = src->key.tun_flags; + ip_tunnel_flags_copy(dst->key.tun_flags, src->key.tun_flags); dst->mode = src->mode | IP_TUNNEL_INFO_TX; ip_tunnel_info_opts_set(dst, ip_tunnel_info_opts(src), - src->options_len, 0); + src->options_len, tun_flags); return res; } @@ -497,7 +498,7 @@ static int ip_tun_parse_opts_geneve(struct nlattr *attr, opt->opt_class = nla_get_be16(attr); attr = tb[LWTUNNEL_IP_OPT_GENEVE_TYPE]; opt->type = nla_get_u8(attr); - info->key.tun_flags |= TUNNEL_GENEVE_OPT; + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags); } return sizeof(struct geneve_opt) + data_len; @@ -525,7 +526,7 @@ static int ip_tun_parse_opts_vxlan(struct nlattr *attr, attr = tb[LWTUNNEL_IP_OPT_VXLAN_GBP]; md->gbp = nla_get_u32(attr); md->gbp &= VXLAN_GBP_MASK; - info->key.tun_flags |= TUNNEL_VXLAN_OPT; + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags); } return sizeof(struct vxlan_metadata); @@ -574,7 +575,7 @@ static int ip_tun_parse_opts_erspan(struct nlattr *attr, set_hwid(&md->u.md2, nla_get_u8(attr)); } - info->key.tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); } return sizeof(struct erspan_metadata); @@ -585,7 +586,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, { int err, rem, opt_len, opts_len = 0; struct nlattr *nla; - __be16 type = 0; + u32 type = 0; if (!attr) return 0; @@ -598,7 +599,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, nla_for_each_attr(nla, nla_data(attr), nla_len(attr), rem) { switch (nla_type(nla)) { case LWTUNNEL_IP_OPTS_GENEVE: - if (type && type != TUNNEL_GENEVE_OPT) + if (type && type != IP_TUNNEL_GENEVE_OPT_BIT) return -EINVAL; opt_len = ip_tun_parse_opts_geneve(nla, info, opts_len, extack); @@ -607,7 +608,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, opts_len += opt_len; if (opts_len > IP_TUNNEL_OPTS_MAX) return -EINVAL; - type = TUNNEL_GENEVE_OPT; + type = IP_TUNNEL_GENEVE_OPT_BIT; break; case LWTUNNEL_IP_OPTS_VXLAN: if (type) @@ -617,7 +618,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, if (opt_len < 0) return opt_len; opts_len += opt_len; - type = TUNNEL_VXLAN_OPT; + type = IP_TUNNEL_VXLAN_OPT_BIT; break; case LWTUNNEL_IP_OPTS_ERSPAN: if (type) @@ -627,7 +628,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, if (opt_len < 0) return opt_len; opts_len += opt_len; - type = TUNNEL_ERSPAN_OPT; + type = IP_TUNNEL_ERSPAN_OPT_BIT; break; default: return -EINVAL; @@ -705,10 +706,16 @@ static int ip_tun_build_state(struct net *net, struct nlattr *attr, if (tb[LWTUNNEL_IP_TOS]) tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]); - if (tb[LWTUNNEL_IP_FLAGS]) - tun_info->key.tun_flags |= - (nla_get_be16(tb[LWTUNNEL_IP_FLAGS]) & - ~TUNNEL_OPTIONS_PRESENT); + if (tb[LWTUNNEL_IP_FLAGS]) { + IP_TUNNEL_DECLARE_FLAGS(flags); + + ip_tunnel_flags_from_be16(flags, + nla_get_be16(tb[LWTUNNEL_IP_FLAGS])); + ip_tunnel_clear_options_present(flags); + + ip_tunnel_flags_or(tun_info->key.tun_flags, + tun_info->key.tun_flags, flags); + } tun_info->mode = IP_TUNNEL_INFO_TX; tun_info->options_len = opt_len; @@ -812,18 +819,18 @@ static int ip_tun_fill_encap_opts(struct sk_buff *skb, int type, struct nlattr *nest; int err = 0; - if (!(tun_info->key.tun_flags & TUNNEL_OPTIONS_PRESENT)) + if (!ip_tunnel_is_options_present(tun_info->key.tun_flags)) return 0; nest = nla_nest_start_noflag(skb, type); if (!nest) return -ENOMEM; - if (tun_info->key.tun_flags & TUNNEL_GENEVE_OPT) + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_info->key.tun_flags)) err = ip_tun_fill_encap_opts_geneve(skb, tun_info); - else if (tun_info->key.tun_flags & TUNNEL_VXLAN_OPT) + else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_info->key.tun_flags)) err = ip_tun_fill_encap_opts_vxlan(skb, tun_info); - else if (tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT) + else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_info->key.tun_flags)) err = ip_tun_fill_encap_opts_erspan(skb, tun_info); if (err) { @@ -846,7 +853,8 @@ static int ip_tun_fill_encap_info(struct sk_buff *skb, nla_put_in_addr(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) || nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) || - nla_put_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags) || + nla_put_be16(skb, LWTUNNEL_IP_FLAGS, + ip_tunnel_flags_to_be16(tun_info->key.tun_flags)) || ip_tun_fill_encap_opts(skb, LWTUNNEL_IP_OPTS, tun_info)) return -ENOMEM; @@ -857,11 +865,11 @@ static int ip_tun_opts_nlsize(struct ip_tunnel_info *info) { int opt_len; - if (!(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT)) + if (!ip_tunnel_is_options_present(info->key.tun_flags)) return 0; opt_len = nla_total_size(0); /* LWTUNNEL_IP_OPTS */ - if (info->key.tun_flags & TUNNEL_GENEVE_OPT) { + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) { struct geneve_opt *opt; int offset = 0; @@ -874,10 +882,10 @@ static int ip_tun_opts_nlsize(struct ip_tunnel_info *info) /* OPT_GENEVE_DATA */ offset += sizeof(*opt) + opt->length * 4; } - } else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) { + } else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { opt_len += nla_total_size(0) /* LWTUNNEL_IP_OPTS_VXLAN */ + nla_total_size(4); /* OPT_VXLAN_GBP */ - } else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) { + } else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags)) { struct erspan_metadata *md = ip_tunnel_info_opts(info); opt_len += nla_total_size(0) /* LWTUNNEL_IP_OPTS_ERSPAN */ @@ -984,10 +992,17 @@ static int ip6_tun_build_state(struct net *net, struct nlattr *attr, if (tb[LWTUNNEL_IP6_TC]) tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]); - if (tb[LWTUNNEL_IP6_FLAGS]) - tun_info->key.tun_flags |= - (nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]) & - ~TUNNEL_OPTIONS_PRESENT); + if (tb[LWTUNNEL_IP6_FLAGS]) { + IP_TUNNEL_DECLARE_FLAGS(flags); + __be16 data; + + data = nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]); + ip_tunnel_flags_from_be16(flags, data); + ip_tunnel_clear_options_present(flags); + + ip_tunnel_flags_or(tun_info->key.tun_flags, + tun_info->key.tun_flags, flags); + } tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6; tun_info->options_len = opt_len; @@ -1008,7 +1023,8 @@ static int ip6_tun_fill_encap_info(struct sk_buff *skb, nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) || nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) || - nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags) || + nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, + ip_tunnel_flags_to_be16(tun_info->key.tun_flags)) || ip_tun_fill_encap_opts(skb, LWTUNNEL_IP6_OPTS, tun_info)) return -ENOMEM; @@ -1116,7 +1132,7 @@ bool ip_tunnel_netlink_encap_parms(struct nlattr *data[], EXPORT_SYMBOL_GPL(ip_tunnel_netlink_encap_parms); void ip_tunnel_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms) + struct ip_tunnel_parm_kern *parms) { if (data[IFLA_IPTUN_LINK]) parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); @@ -1139,8 +1155,12 @@ void ip_tunnel_netlink_parms(struct nlattr *data[], if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) parms->iph.frag_off = htons(IP_DF); - if (data[IFLA_IPTUN_FLAGS]) - parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); + if (data[IFLA_IPTUN_FLAGS]) { + __be16 flags; + + flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); + ip_tunnel_flags_from_be16(parms->i_flags, flags); + } if (data[IFLA_IPTUN_PROTO]) parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index ee587adb169f..14536da9f5dc 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -51,8 +51,11 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, const struct iphdr *iph = ip_hdr(skb); struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); + + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, 0); if (tunnel) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) @@ -167,7 +170,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct ip_tunnel_parm *parms = &tunnel->parms; + struct ip_tunnel_parm_kern *parms = &tunnel->parms; struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; /* Device to other host */ int pkt_len = skb->len; @@ -322,8 +325,11 @@ static int vti4_err(struct sk_buff *skb, u32 info) const struct iphdr *iph = (const struct iphdr *)skb->data; int protocol = iph->protocol; struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; + + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->daddr, iph->saddr, 0); if (!tunnel) return -1; @@ -373,8 +379,9 @@ static int vti4_err(struct sk_buff *skb, u32 info) } static int -vti_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) +vti_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; int err = 0; if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { @@ -383,20 +390,26 @@ vti_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) return -EINVAL; } - if (!(p->i_flags & GRE_KEY)) + if (!ip_tunnel_flags_is_be16_compat(p->i_flags) || + !ip_tunnel_flags_is_be16_compat(p->o_flags)) + return -EOVERFLOW; + + if (!(ip_tunnel_flags_to_be16(p->i_flags) & GRE_KEY)) p->i_key = 0; - if (!(p->o_flags & GRE_KEY)) + if (!(ip_tunnel_flags_to_be16(p->o_flags) & GRE_KEY)) p->o_key = 0; - p->i_flags = VTI_ISVTI; + __set_bit(IP_TUNNEL_VTI_BIT, flags); + ip_tunnel_flags_copy(p->i_flags, flags); err = ip_tunnel_ctl(dev, p, cmd); if (err) return err; if (cmd != SIOCDELTUNNEL) { - p->i_flags |= GRE_KEY; - p->o_flags |= GRE_KEY; + ip_tunnel_flags_from_be16(flags, GRE_KEY); + ip_tunnel_flags_or(p->i_flags, p->i_flags, flags); + ip_tunnel_flags_or(p->o_flags, p->o_flags, flags); } return 0; } @@ -531,7 +544,7 @@ static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], } static void vti_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms, + struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); @@ -541,7 +554,7 @@ static void vti_netlink_parms(struct nlattr *data[], if (!data) return; - parms->i_flags = VTI_ISVTI; + __set_bit(IP_TUNNEL_VTI_BIT, parms->i_flags); if (data[IFLA_VTI_LINK]) parms->link = nla_get_u32(data[IFLA_VTI_LINK]); @@ -566,7 +579,7 @@ static int vti_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - struct ip_tunnel_parm parms; + struct ip_tunnel_parm_kern parms; __u32 fwmark = 0; vti_netlink_parms(data, &parms, &fwmark); @@ -578,8 +591,8 @@ static int vti_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); + struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; - struct ip_tunnel_parm p; vti_netlink_parms(data, &p, &fwmark); return ip_tunnel_changelink(dev, tb, &p, fwmark); @@ -606,7 +619,7 @@ static size_t vti_get_size(const struct net_device *dev) static int vti_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_parm *p = &t->parms; + struct ip_tunnel_parm_kern *p = &t->parms; if (nla_put_u32(skb, IFLA_VTI_LINK, p->link) || nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key) || diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index f2696eaadbe6..923a2ef68c2f 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -130,13 +130,16 @@ static int ipip_err(struct sk_buff *skb, u32 info) struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); const struct iphdr *iph = (const struct iphdr *)skb->data; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct ip_tunnel *t; int err = 0; - t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, - iph->daddr, iph->saddr, 0); + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); + + t = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->daddr, + iph->saddr, 0); if (!t) { err = -ENOENT; goto out; @@ -213,13 +216,16 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) { struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tun_dst = NULL; struct ip_tunnel *tunnel; const struct iphdr *iph; + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); + iph = ip_hdr(skb); - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, - iph->saddr, iph->daddr, 0); + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, + iph->daddr, 0); if (tunnel) { const struct tnl_ptk_info *tpi; @@ -238,7 +244,9 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; if (tunnel->collect_md) { - tun_dst = ip_tun_rx_dst(skb, 0, 0, 0); + ip_tunnel_flags_zero(flags); + + tun_dst = ip_tun_rx_dst(skb, flags, 0, 0); if (!tun_dst) return 0; ip_tunnel_md_udp_encap(skb, &tun_dst->u.tun_info); @@ -330,7 +338,7 @@ static bool ipip_tunnel_ioctl_verify_protocol(u8 ipproto) } static int -ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) +ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || @@ -340,7 +348,8 @@ ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) } p->i_key = p->o_key = 0; - p->i_flags = p->o_flags = 0; + ip_tunnel_flags_zero(p->i_flags); + ip_tunnel_flags_zero(p->o_flags); return ip_tunnel_ctl(dev, p, cmd); } @@ -405,8 +414,8 @@ static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], } static void ipip_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms, bool *collect_md, - __u32 *fwmark) + struct ip_tunnel_parm_kern *parms, + bool *collect_md, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); @@ -432,8 +441,8 @@ static int ipip_newlink(struct net *src_net, struct net_device *dev, struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; + struct ip_tunnel_parm_kern p; __u32 fwmark = 0; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { @@ -452,8 +461,8 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; + struct ip_tunnel_parm_kern p; bool collect_md; __u32 fwmark = t->fwmark; @@ -510,7 +519,7 @@ static size_t ipip_get_size(const struct net_device *dev) static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct ip_tunnel_parm *parm = &tunnel->parms; + struct ip_tunnel_parm_kern *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index fd5c01c8489f..6c750bd13dd8 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -441,7 +441,7 @@ static bool ipmr_init_vif_indev(const struct net_device *dev) static struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) { struct net_device *tunnel_dev, *new_dev; - struct ip_tunnel_parm p = { }; + struct ip_tunnel_parm_kern p = { }; int err; tunnel_dev = __dev_get_by_name(net, "tunl0"); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5d874817a78d..1b6cd3840012 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6999,7 +6999,7 @@ EXPORT_SYMBOL(inet_reqsk_alloc); /* * Return true if a syncookie should be sent */ -static bool tcp_syn_flood_action(const struct sock *sk, const char *proto) +static bool tcp_syn_flood_action(struct sock *sk, const char *proto) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; const char *msg = "Dropping request"; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a22ee5838751..1e0a9762f92e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3501,7 +3501,7 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; - tcp_twsk_purge(net_exit_list, AF_INET); + tcp_twsk_purge(net_exit_list); list_for_each_entry(net, net_exit_list, exit_list) { inet_pernet_hashinfo_free(net->ipv4.tcp_death_row.hashinfo); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f0761f060a83..5b21a07ddf9a 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -388,7 +388,7 @@ void tcp_twsk_destructor(struct sock *sk) } EXPORT_SYMBOL_GPL(tcp_twsk_destructor); -void tcp_twsk_purge(struct list_head *net_exit_list, int family) +void tcp_twsk_purge(struct list_head *net_exit_list) { bool purged_once = false; struct net *net; @@ -396,9 +396,9 @@ void tcp_twsk_purge(struct list_head *net_exit_list, int family) list_for_each_entry(net, net_exit_list, exit_list) { if (net->ipv4.tcp_death_row.hashinfo->pernet) { /* Even if tw_refcount == 1, we must clean up kernel reqsk */ - inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo, family); + inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo); } else if (!purged_once) { - inet_twsk_purge(&tcp_hashinfo, family); + inet_twsk_purge(&tcp_hashinfo); purged_once = true; } } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index d1ad20ce1c8c..976db57b95d4 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -25,7 +25,7 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); u32 elapsed, user_timeout; s32 remaining; @@ -47,7 +47,7 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); u32 remaining, user_timeout; s32 elapsed; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 661d0e0d273f..11460d751e73 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1492,13 +1492,15 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) struct sk_buff_head *list = &sk->sk_receive_queue; int rmem, err = -ENOMEM; spinlock_t *busy = NULL; - int size; + bool becomes_readable; + int size, rcvbuf; - /* try to avoid the costly atomic add/sub pair when the receive - * queue is full; always allow at least a packet + /* Immediately drop when the receive queue is full. + * Always allow at least one packet. */ rmem = atomic_read(&sk->sk_rmem_alloc); - if (rmem > sk->sk_rcvbuf) + rcvbuf = READ_ONCE(sk->sk_rcvbuf); + if (rmem > rcvbuf) goto drop; /* Under mem pressure, it might be helpful to help udp_recvmsg() @@ -1507,7 +1509,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) * - Less cache line misses at copyout() time * - Less work at consume_skb() (less alien page frag freeing) */ - if (rmem > (sk->sk_rcvbuf >> 1)) { + if (rmem > (rcvbuf >> 1)) { skb_condense(skb); busy = busylock_acquire(sk); @@ -1515,12 +1517,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) size = skb->truesize; udp_set_dev_scratch(skb); - /* we drop only if the receive buf is full and the receive - * queue contains some other skb - */ - rmem = atomic_add_return(size, &sk->sk_rmem_alloc); - if (rmem > (size + (unsigned int)sk->sk_rcvbuf)) - goto uncharge_drop; + atomic_add(size, &sk->sk_rmem_alloc); spin_lock(&list->lock); err = udp_rmem_schedule(sk, size); @@ -1536,12 +1533,19 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) */ sock_skb_set_dropcount(sk, skb); + becomes_readable = skb_queue_empty(list); __skb_queue_tail(list, skb); spin_unlock(&list->lock); - if (!sock_flag(sk, SOCK_DEAD)) - INDIRECT_CALL_1(sk->sk_data_ready, sock_def_readable, sk); - + if (!sock_flag(sk, SOCK_DEAD)) { + if (becomes_readable || + sk->sk_data_ready != sock_def_readable || + READ_ONCE(sk->sk_peek_off) >= 0) + INDIRECT_CALL_1(sk->sk_data_ready, + sock_def_readable, sk); + else + sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); + } busylock_release(busy); return 0; @@ -2049,8 +2053,8 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) drop_reason = SKB_DROP_REASON_PROTO_MEM; } UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + trace_udp_fail_queue_rcv_skb(rc, sk, skb); kfree_skb_reason(skb, drop_reason); - trace_udp_fail_queue_rcv_skb(rc, sk); return -1; } diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 860aff5f8599..e4e0fa869fa4 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -183,7 +183,8 @@ void udp_tunnel_sock_release(struct socket *sock) EXPORT_SYMBOL_GPL(udp_tunnel_sock_release); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, - __be16 flags, __be64 tunnel_id, int md_size) + const unsigned long *flags, + __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; struct ip_tunnel_info *info; @@ -199,7 +200,7 @@ struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, info->key.tp_src = udp_hdr(skb)->source; info->key.tp_dst = udp_hdr(skb)->dest; if (udp_hdr(skb)->check) - info->key.tun_flags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); return tun_dst; } EXPORT_SYMBOL_GPL(udp_tun_rx_dst); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 92db9b474f2b..82ad6b8fa007 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -63,6 +63,7 @@ #include <linux/string.h> #include <linux/hash.h> +#include <net/ip_tunnels.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/snmp.h> @@ -2917,7 +2918,7 @@ put: static int addrconf_set_sit_dstaddr(struct net *net, struct net_device *dev, struct in6_ifreq *ireq) { - struct ip_tunnel_parm p = { }; + struct ip_tunnel_parm_kern p = { }; int err; if (!(ipv6_addr_type(&ireq->ifr6_addr) & IPV6_ADDR_COMPATv4)) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index ca7e77e84283..2146cf69d8e2 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -496,11 +496,11 @@ static int ip6gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) tpi->proto); if (tunnel) { if (tunnel->parms.collect_md) { + IP_TUNNEL_DECLARE_FLAGS(flags); struct metadata_dst *tun_dst; __be64 tun_id; - __be16 flags; - flags = tpi->flags; + ip_tunnel_flags_copy(flags, tpi->flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ipv6_tun_rx_dst(skb, flags, tun_id, 0); @@ -548,14 +548,14 @@ static int ip6erspan_rcv(struct sk_buff *skb, if (tunnel->parms.collect_md) { struct erspan_metadata *pkt_md, *md; + IP_TUNNEL_DECLARE_FLAGS(flags); struct metadata_dst *tun_dst; struct ip_tunnel_info *info; unsigned char *gh; __be64 tun_id; - __be16 flags; - tpi->flags |= TUNNEL_KEY; - flags = tpi->flags; + __set_bit(IP_TUNNEL_KEY_BIT, tpi->flags); + ip_tunnel_flags_copy(flags, tpi->flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ipv6_tun_rx_dst(skb, flags, tun_id, @@ -577,7 +577,8 @@ static int ip6erspan_rcv(struct sk_buff *skb, md2 = &md->u.md2; memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); - info->key.tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + info->key.tun_flags); info->options_len = sizeof(*md); ip6_tnl_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); @@ -745,8 +746,8 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, __u32 *pmtu, __be16 proto) { struct ip6_tnl *tunnel = netdev_priv(dev); + IP_TUNNEL_DECLARE_FLAGS(flags); __be16 protocol; - __be16 flags; if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; @@ -778,8 +779,11 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, fl6->fl6_gre_key = tunnel_id_to_key32(key->tun_id); dsfield = key->tos; - flags = key->tun_flags & - (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); + ip_tunnel_flags_zero(flags); + __set_bit(IP_TUNNEL_CSUM_BIT, flags); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + __set_bit(IP_TUNNEL_SEQ_BIT, flags); + ip_tunnel_flags_and(flags, flags, key->tun_flags); tun_hlen = gre_calc_hlen(flags); if (skb_cow_head(skb, dev->needed_headroom ?: tun_hlen + tunnel->encap_hlen)) @@ -788,19 +792,21 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, gre_build_header(skb, tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) - : 0); + test_bit(IP_TUNNEL_SEQ_BIT, flags) ? + htonl(atomic_fetch_inc(&tunnel->o_seqno)) : + 0); } else { if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) return -ENOMEM; - flags = tunnel->parms.o_flags; + ip_tunnel_flags_copy(flags, tunnel->parms.o_flags); gre_build_header(skb, tunnel->tun_hlen, flags, protocol, tunnel->parms.o_key, - (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) - : 0); + test_bit(IP_TUNNEL_SEQ_BIT, flags) ? + htonl(atomic_fetch_inc(&tunnel->o_seqno)) : + 0); } return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, @@ -822,7 +828,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) prepare_ip6gre_xmit_ipv4(skb, dev, &fl6, &dsfield, &encap_limit); - err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM)); + err = gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + t->parms.o_flags)); if (err) return -1; @@ -856,7 +863,8 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) prepare_ip6gre_xmit_ipv6(skb, dev, &fl6, &dsfield, &encap_limit)) return -1; - if (gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM))) + if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + t->parms.o_flags))) return -1; err = __gre6_xmit(skb, dev, dsfield, &fl6, encap_limit, @@ -883,7 +891,8 @@ static int ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev) prepare_ip6gre_xmit_other(skb, dev, &fl6, &dsfield, &encap_limit)) return -1; - err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM)); + err = gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + t->parms.o_flags)); if (err) return err; err = __gre6_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, skb->protocol); @@ -936,6 +945,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, struct ip_tunnel_info *tun_info = NULL; struct ip6_tnl *t = netdev_priv(dev); struct dst_entry *dst = skb_dst(skb); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; bool truncate = false; int encap_limit = -1; __u8 dsfield = false; @@ -979,7 +989,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen)) goto tx_err; - t->parms.o_flags &= ~TUNNEL_KEY; + __clear_bit(IP_TUNNEL_KEY_BIT, t->parms.o_flags); IPCB(skb)->flags = 0; /* For collect_md mode, derive fl6 from the tunnel key, @@ -1004,7 +1014,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, fl6.fl6_gre_key = tunnel_id_to_key32(key->tun_id); dsfield = key->tos; - if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) + if (!test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + tun_info->key.tun_flags)) goto tx_err; if (tun_info->options_len < sizeof(*md)) goto tx_err; @@ -1065,7 +1076,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, } /* Push GRE header. */ - gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); + __set_bit(IP_TUNNEL_SEQ_BIT, flags); + gre_build_header(skb, 8, flags, proto, 0, + htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) @@ -1208,8 +1221,8 @@ static void ip6gre_tnl_copy_tnl_parm(struct ip6_tnl *t, t->parms.proto = p->proto; t->parms.i_key = p->i_key; t->parms.o_key = p->o_key; - t->parms.i_flags = p->i_flags; - t->parms.o_flags = p->o_flags; + ip_tunnel_flags_copy(t->parms.i_flags, p->i_flags); + ip_tunnel_flags_copy(t->parms.o_flags, p->o_flags); t->parms.fwmark = p->fwmark; t->parms.erspan_ver = p->erspan_ver; t->parms.index = p->index; @@ -1238,8 +1251,8 @@ static void ip6gre_tnl_parm_from_user(struct __ip6_tnl_parm *p, p->link = u->link; p->i_key = u->i_key; p->o_key = u->o_key; - p->i_flags = gre_flags_to_tnl_flags(u->i_flags); - p->o_flags = gre_flags_to_tnl_flags(u->o_flags); + gre_flags_to_tnl_flags(p->i_flags, u->i_flags); + gre_flags_to_tnl_flags(p->o_flags, u->o_flags); memcpy(p->name, u->name, sizeof(u->name)); } @@ -1391,7 +1404,7 @@ static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, ipv6h->daddr = t->parms.raddr; p = (__be16 *)(ipv6h + 1); - p[0] = t->parms.o_flags; + p[0] = ip_tunnel_flags_to_be16(t->parms.o_flags); p[1] = htons(type); /* @@ -1455,19 +1468,17 @@ static void ip6gre_tunnel_setup(struct net_device *dev) static void ip6gre_tnl_init_features(struct net_device *dev) { struct ip6_tnl *nt = netdev_priv(dev); - __be16 flags; dev->features |= GRE6_FEATURES | NETIF_F_LLTX; dev->hw_features |= GRE6_FEATURES; - flags = nt->parms.o_flags; - /* TCP offload with GRE SEQ is not supported, nor can we support 2 * levels of outer headers requiring an update. */ - if (flags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, nt->parms.o_flags)) return; - if (flags & TUNNEL_CSUM && nt->encap.type != TUNNEL_ENCAP_NONE) + if (test_bit(IP_TUNNEL_CSUM_BIT, nt->parms.o_flags) && + nt->encap.type != TUNNEL_ENCAP_NONE) return; dev->features |= NETIF_F_GSO_SOFTWARE; @@ -1792,12 +1803,12 @@ static void ip6gre_netlink_parms(struct nlattr *data[], parms->link = nla_get_u32(data[IFLA_GRE_LINK]); if (data[IFLA_GRE_IFLAGS]) - parms->i_flags = gre_flags_to_tnl_flags( - nla_get_be16(data[IFLA_GRE_IFLAGS])); + gre_flags_to_tnl_flags(parms->i_flags, + nla_get_be16(data[IFLA_GRE_IFLAGS])); if (data[IFLA_GRE_OFLAGS]) - parms->o_flags = gre_flags_to_tnl_flags( - nla_get_be16(data[IFLA_GRE_OFLAGS])); + gre_flags_to_tnl_flags(parms->o_flags, + nla_get_be16(data[IFLA_GRE_OFLAGS])); if (data[IFLA_GRE_IKEY]) parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]); @@ -2144,11 +2155,13 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm *p = &t->parms; - __be16 o_flags = p->o_flags; + IP_TUNNEL_DECLARE_FLAGS(o_flags); + + ip_tunnel_flags_copy(o_flags, p->o_flags); if (p->erspan_ver == 1 || p->erspan_ver == 2) { if (!p->collect_md) - o_flags |= TUNNEL_KEY; + __set_bit(IP_TUNNEL_KEY_BIT, o_flags); if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver)) goto nla_put_failure; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index e9cc315832cb..57bb3b3ea0c5 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -798,17 +798,15 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, const struct ipv6hdr *ipv6h; int nh, err; - if ((!(tpi->flags & TUNNEL_CSUM) && - (tunnel->parms.i_flags & TUNNEL_CSUM)) || - ((tpi->flags & TUNNEL_CSUM) && - !(tunnel->parms.i_flags & TUNNEL_CSUM))) { + if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.i_flags) != + test_bit(IP_TUNNEL_CSUM_BIT, tpi->flags)) { DEV_STATS_INC(tunnel->dev, rx_crc_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } - if (tunnel->parms.i_flags & TUNNEL_SEQ) { - if (!(tpi->flags & TUNNEL_SEQ) || + if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.i_flags)) { + if (!test_bit(IP_TUNNEL_SEQ_BIT, tpi->flags) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { DEV_STATS_INC(tunnel->dev, rx_fifo_errors); @@ -946,7 +944,9 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto, if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; if (t->parms.collect_md) { - tun_dst = ipv6_tun_rx_dst(skb, 0, 0, 0); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; + + tun_dst = ipv6_tun_rx_dst(skb, flags, 0, 0); if (!tun_dst) goto drop; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 655c9b1a19b8..83b195f09561 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -132,8 +132,8 @@ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, return NULL; } -static struct ip_tunnel __rcu **__ipip6_bucket(struct sit_net *sitn, - struct ip_tunnel_parm *parms) +static struct ip_tunnel __rcu ** +__ipip6_bucket(struct sit_net *sitn, struct ip_tunnel_parm_kern *parms) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; @@ -207,7 +207,7 @@ static int ipip6_tunnel_create(struct net_device *dev) __dev_addr_set(dev, &t->parms.iph.saddr, 4); memcpy(dev->broadcast, &t->parms.iph.daddr, 4); - if ((__force u16)t->parms.i_flags & SIT_ISATAP) + if (test_bit(IP_TUNNEL_SIT_ISATAP_BIT, t->parms.i_flags)) dev->priv_flags |= IFF_ISATAP; dev->rtnl_link_ops = &sit_link_ops; @@ -226,7 +226,8 @@ out: } static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, - struct ip_tunnel_parm *parms, int create) + struct ip_tunnel_parm_kern *parms, + int create) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; @@ -1135,7 +1136,8 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) dev->needed_headroom = t_hlen + hlen; } -static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p, +static void ipip6_tunnel_update(struct ip_tunnel *t, + struct ip_tunnel_parm_kern *p, __u32 fwmark) { struct net *net = t->net; @@ -1196,11 +1198,11 @@ static int ipip6_tunnel_get6rd(struct net_device *dev, struct ip_tunnel_parm __user *data) { struct ip_tunnel *t = netdev_priv(dev); + struct ip_tunnel_parm_kern p; struct ip_tunnel_6rd ip6rd; - struct ip_tunnel_parm p; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) { - if (copy_from_user(&p, data, sizeof(p))) + if (!ip_tunnel_parm_from_user(&p, data)) return -EFAULT; t = ipip6_tunnel_locate(t->net, &p, 0); } @@ -1251,7 +1253,7 @@ static bool ipip6_valid_ip_proto(u8 ipproto) } static int -__ipip6_tunnel_ioctl_validate(struct net *net, struct ip_tunnel_parm *p) +__ipip6_tunnel_ioctl_validate(struct net *net, struct ip_tunnel_parm_kern *p) { if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; @@ -1268,7 +1270,7 @@ __ipip6_tunnel_ioctl_validate(struct net *net, struct ip_tunnel_parm *p) } static int -ipip6_tunnel_get(struct net_device *dev, struct ip_tunnel_parm *p) +ipip6_tunnel_get(struct net_device *dev, struct ip_tunnel_parm_kern *p) { struct ip_tunnel *t = netdev_priv(dev); @@ -1281,7 +1283,7 @@ ipip6_tunnel_get(struct net_device *dev, struct ip_tunnel_parm *p) } static int -ipip6_tunnel_add(struct net_device *dev, struct ip_tunnel_parm *p) +ipip6_tunnel_add(struct net_device *dev, struct ip_tunnel_parm_kern *p) { struct ip_tunnel *t = netdev_priv(dev); int err; @@ -1297,7 +1299,7 @@ ipip6_tunnel_add(struct net_device *dev, struct ip_tunnel_parm *p) } static int -ipip6_tunnel_change(struct net_device *dev, struct ip_tunnel_parm *p) +ipip6_tunnel_change(struct net_device *dev, struct ip_tunnel_parm_kern *p) { struct ip_tunnel *t = netdev_priv(dev); int err; @@ -1328,7 +1330,7 @@ ipip6_tunnel_change(struct net_device *dev, struct ip_tunnel_parm *p) } static int -ipip6_tunnel_del(struct net_device *dev, struct ip_tunnel_parm *p) +ipip6_tunnel_del(struct net_device *dev, struct ip_tunnel_parm_kern *p) { struct ip_tunnel *t = netdev_priv(dev); @@ -1348,7 +1350,8 @@ ipip6_tunnel_del(struct net_device *dev, struct ip_tunnel_parm *p) } static int -ipip6_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) +ipip6_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, + int cmd) { switch (cmd) { case SIOCGETTUNNEL: @@ -1490,7 +1493,7 @@ static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[], } static void ipip6_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms, + struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); @@ -1599,8 +1602,8 @@ static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; + struct ip_tunnel_parm_kern p; struct net *net = t->net; struct sit_net *sitn = net_generic(net, sit_net_id); #ifdef CONFIG_IPV6_SIT_6RD @@ -1687,7 +1690,7 @@ static size_t ipip6_get_size(const struct net_device *dev) static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct ip_tunnel_parm *parm = &tunnel->parms; + struct ip_tunnel_parm_kern *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || @@ -1697,7 +1700,8 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, !!(parm->iph.frag_off & htons(IP_DF))) || nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) || - nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags) || + nla_put_be16(skb, IFLA_IPTUN_FLAGS, + ip_tunnel_flags_to_be16(parm->i_flags)) || nla_put_u32(skb, IFLA_IPTUN_FWMARK, tunnel->fwmark)) goto nla_put_failure; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 3f4cba49e9ee..5ae74f661d25 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2389,15 +2389,9 @@ static void __net_exit tcpv6_net_exit(struct net *net) inet_ctl_sock_destroy(net->ipv6.tcp_sk); } -static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list) -{ - tcp_twsk_purge(net_exit_list, AF_INET6); -} - static struct pernet_operations tcpv6_net_ops = { .init = tcpv6_net_init, .exit = tcpv6_net_exit, - .exit_batch = tcpv6_net_exit_batch, }; int __init tcpv6_init(void) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 7c1e6469d091..2e4dc5e6137b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -34,6 +34,7 @@ #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/indirect_call_wrapper.h> +#include <trace/events/udp.h> #include <net/addrconf.h> #include <net/ndisc.h> @@ -658,8 +659,8 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) drop_reason = SKB_DROP_REASON_PROTO_MEM; } UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + trace_udp_fail_queue_rcv_skb(rc, sk, skb); kfree_skb_reason(skb, drop_reason); - trace_udp_fail_queue_rcv_skb(rc, sk); return -1; } diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 7c8c3adcac6e..c951bb9cc2e0 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -184,7 +184,7 @@ static void iucv_sock_wake_msglim(struct sock *sk) wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_all(&wq->wait); - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); rcu_read_unlock(); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index a10ebf3ee10a..46f4655b7123 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -558,7 +558,7 @@ struct mptcp_subflow_context { static inline struct mptcp_subflow_context * mptcp_subflow_ctx(const struct sock *sk) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); /* Use RCU on icsk_ulp_data only for sock diag code */ return (__force struct mptcp_subflow_context *)icsk->icsk_ulp_data; diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index a2c16b501087..c7a8a08b7308 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1550,6 +1550,7 @@ static int ipvs_gre_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, if (!dest) goto unk; if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { + IP_TUNNEL_DECLARE_FLAGS(flags); __be16 type; /* Only support version 0 and C (csum) */ @@ -1560,7 +1561,10 @@ static int ipvs_gre_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, if (type != htons(ETH_P_IP)) goto unk; *proto = IPPROTO_IPIP; - return gre_calc_hlen(gre_flags_to_tnl_flags(greh->flags)); + + gre_flags_to_tnl_flags(flags, greh->flags); + + return gre_calc_hlen(flags); } unk: diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 65e0259178da..39b5fd6bbf65 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -390,10 +390,10 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, skb->ip_summed == CHECKSUM_PARTIAL) mtu -= GUE_PLEN_REMCSUM + GUE_LEN_PRIV; } else if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { - __be16 tflags = 0; + IP_TUNNEL_DECLARE_FLAGS(tflags) = { }; if (dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) - tflags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tflags); mtu -= gre_calc_hlen(tflags); } if (mtu < 68) { @@ -553,10 +553,10 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, skb->ip_summed == CHECKSUM_PARTIAL) mtu -= GUE_PLEN_REMCSUM + GUE_LEN_PRIV; } else if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { - __be16 tflags = 0; + IP_TUNNEL_DECLARE_FLAGS(tflags) = { }; if (dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) - tflags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tflags); mtu -= gre_calc_hlen(tflags); } if (mtu < IPV6_MIN_MTU) { @@ -1082,11 +1082,11 @@ ipvs_gre_encap(struct net *net, struct sk_buff *skb, { __be16 proto = *next_protocol == IPPROTO_IPIP ? htons(ETH_P_IP) : htons(ETH_P_IPV6); - __be16 tflags = 0; + IP_TUNNEL_DECLARE_FLAGS(tflags) = { }; size_t hdrlen; if (cp->dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) - tflags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tflags); hdrlen = gre_calc_hlen(tflags); gre_build_header(skb, hdrlen, tflags, proto, 0, 0); @@ -1165,11 +1165,11 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, max_headroom += sizeof(struct udphdr) + gue_hdrlen; } else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { + IP_TUNNEL_DECLARE_FLAGS(tflags) = { }; size_t gre_hdrlen; - __be16 tflags = 0; if (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) - tflags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tflags); gre_hdrlen = gre_calc_hlen(tflags); max_headroom += gre_hdrlen; @@ -1310,11 +1310,11 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, max_headroom += sizeof(struct udphdr) + gue_hdrlen; } else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { + IP_TUNNEL_DECLARE_FLAGS(tflags) = { }; size_t gre_hdrlen; - __be16 tflags = 0; if (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) - tflags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tflags); gre_hdrlen = gre_calc_hlen(tflags); max_headroom += gre_hdrlen; diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index f735d79d8be5..60a76e6e348e 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -174,8 +174,8 @@ struct nft_tunnel_opts { struct erspan_metadata erspan; u8 data[IP_TUNNEL_OPTS_MAX]; } u; + IP_TUNNEL_DECLARE_FLAGS(flags); u32 len; - __be16 flags; }; struct nft_tunnel_obj { @@ -271,7 +271,8 @@ static int nft_tunnel_obj_vxlan_init(const struct nlattr *attr, opts->u.vxlan.gbp = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_VXLAN_GBP])); opts->len = sizeof(struct vxlan_metadata); - opts->flags = TUNNEL_VXLAN_OPT; + ip_tunnel_flags_zero(opts->flags); + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, opts->flags); return 0; } @@ -325,7 +326,8 @@ static int nft_tunnel_obj_erspan_init(const struct nlattr *attr, opts->u.erspan.version = version; opts->len = sizeof(struct erspan_metadata); - opts->flags = TUNNEL_ERSPAN_OPT; + ip_tunnel_flags_zero(opts->flags); + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, opts->flags); return 0; } @@ -366,7 +368,8 @@ static int nft_tunnel_obj_geneve_init(const struct nlattr *attr, opt->length = data_len / 4; opt->opt_class = nla_get_be16(tb[NFTA_TUNNEL_KEY_GENEVE_CLASS]); opt->type = nla_get_u8(tb[NFTA_TUNNEL_KEY_GENEVE_TYPE]); - opts->flags = TUNNEL_GENEVE_OPT; + ip_tunnel_flags_zero(opts->flags); + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, opts->flags); return 0; } @@ -385,8 +388,8 @@ static int nft_tunnel_obj_opts_init(const struct nft_ctx *ctx, struct nft_tunnel_opts *opts) { struct nlattr *nla; - __be16 type = 0; int err, rem; + u32 type = 0; err = nla_validate_nested_deprecated(attr, NFTA_TUNNEL_KEY_OPTS_MAX, nft_tunnel_opts_policy, NULL); @@ -401,7 +404,7 @@ static int nft_tunnel_obj_opts_init(const struct nft_ctx *ctx, err = nft_tunnel_obj_vxlan_init(nla, opts); if (err) return err; - type = TUNNEL_VXLAN_OPT; + type = IP_TUNNEL_VXLAN_OPT_BIT; break; case NFTA_TUNNEL_KEY_OPTS_ERSPAN: if (type) @@ -409,15 +412,15 @@ static int nft_tunnel_obj_opts_init(const struct nft_ctx *ctx, err = nft_tunnel_obj_erspan_init(nla, opts); if (err) return err; - type = TUNNEL_ERSPAN_OPT; + type = IP_TUNNEL_ERSPAN_OPT_BIT; break; case NFTA_TUNNEL_KEY_OPTS_GENEVE: - if (type && type != TUNNEL_GENEVE_OPT) + if (type && type != IP_TUNNEL_GENEVE_OPT_BIT) return -EINVAL; err = nft_tunnel_obj_geneve_init(nla, opts); if (err) return err; - type = TUNNEL_GENEVE_OPT; + type = IP_TUNNEL_GENEVE_OPT_BIT; break; default: return -EOPNOTSUPP; @@ -454,7 +457,9 @@ static int nft_tunnel_obj_init(const struct nft_ctx *ctx, memset(&info, 0, sizeof(info)); info.mode = IP_TUNNEL_INFO_TX; info.key.tun_id = key32_to_tunnel_id(nla_get_be32(tb[NFTA_TUNNEL_KEY_ID])); - info.key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE; + __set_bit(IP_TUNNEL_KEY_BIT, info.key.tun_flags); + __set_bit(IP_TUNNEL_CSUM_BIT, info.key.tun_flags); + __set_bit(IP_TUNNEL_NOCACHE_BIT, info.key.tun_flags); if (tb[NFTA_TUNNEL_KEY_IP]) { err = nft_tunnel_obj_ip_init(ctx, tb[NFTA_TUNNEL_KEY_IP], &info); @@ -483,11 +488,12 @@ static int nft_tunnel_obj_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; if (tun_flags & NFT_TUNNEL_F_ZERO_CSUM_TX) - info.key.tun_flags &= ~TUNNEL_CSUM; + __clear_bit(IP_TUNNEL_CSUM_BIT, info.key.tun_flags); if (tun_flags & NFT_TUNNEL_F_DONT_FRAGMENT) - info.key.tun_flags |= TUNNEL_DONT_FRAGMENT; + __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, + info.key.tun_flags); if (tun_flags & NFT_TUNNEL_F_SEQ_NUMBER) - info.key.tun_flags |= TUNNEL_SEQ; + __set_bit(IP_TUNNEL_SEQ_BIT, info.key.tun_flags); } if (tb[NFTA_TUNNEL_KEY_TOS]) info.key.tos = nla_get_u8(tb[NFTA_TUNNEL_KEY_TOS]); @@ -583,7 +589,7 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, if (!nest) return -1; - if (opts->flags & TUNNEL_VXLAN_OPT) { + if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, opts->flags)) { inner = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS_VXLAN); if (!inner) goto failure; @@ -591,7 +597,7 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, htonl(opts->u.vxlan.gbp))) goto inner_failure; nla_nest_end(skb, inner); - } else if (opts->flags & TUNNEL_ERSPAN_OPT) { + } else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, opts->flags)) { inner = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS_ERSPAN); if (!inner) goto failure; @@ -613,7 +619,7 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, break; } nla_nest_end(skb, inner); - } else if (opts->flags & TUNNEL_GENEVE_OPT) { + } else if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, opts->flags)) { struct geneve_opt *opt; int offset = 0; @@ -658,11 +664,11 @@ static int nft_tunnel_flags_dump(struct sk_buff *skb, { u32 flags = 0; - if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, info->key.tun_flags)) flags |= NFT_TUNNEL_F_DONT_FRAGMENT; - if (!(info->key.tun_flags & TUNNEL_CSUM)) + if (!test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)) flags |= NFT_TUNNEL_F_ZERO_CSUM_TX; - if (info->key.tun_flags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, info->key.tun_flags)) flags |= NFT_TUNNEL_F_SEQ_NUMBER; if (nla_put_be32(skb, NFTA_TUNNEL_KEY_FLAGS, htonl(flags)) < 0) diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index ebc5728aab4e..f224d9bcea5e 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -152,6 +152,13 @@ static void update_range(struct sw_flow_match *match, sizeof((match)->key->field)); \ } while (0) +#define SW_FLOW_KEY_BITMAP_COPY(match, field, value_p, nbits, is_mask) ({ \ + update_range(match, offsetof(struct sw_flow_key, field), \ + bitmap_size(nbits), is_mask); \ + bitmap_copy(is_mask ? (match)->mask->key.field : (match)->key->field, \ + value_p, nbits); \ +}) + static bool match_validate(const struct sw_flow_match *match, u64 key_attrs, u64 mask_attrs, bool log) { @@ -670,8 +677,8 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, bool log) { bool ttl = false, ipv4 = false, ipv6 = false; + IP_TUNNEL_DECLARE_FLAGS(tun_flags) = { }; bool info_bridge_mode = false; - __be16 tun_flags = 0; int opts_type = 0; struct nlattr *a; int rem; @@ -697,7 +704,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, case OVS_TUNNEL_KEY_ATTR_ID: SW_FLOW_KEY_PUT(match, tun_key.tun_id, nla_get_be64(a), is_mask); - tun_flags |= TUNNEL_KEY; + __set_bit(IP_TUNNEL_KEY_BIT, tun_flags); break; case OVS_TUNNEL_KEY_ATTR_IPV4_SRC: SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.src, @@ -729,10 +736,10 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, ttl = true; break; case OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT: - tun_flags |= TUNNEL_DONT_FRAGMENT; + __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, tun_flags); break; case OVS_TUNNEL_KEY_ATTR_CSUM: - tun_flags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tun_flags); break; case OVS_TUNNEL_KEY_ATTR_TP_SRC: SW_FLOW_KEY_PUT(match, tun_key.tp_src, @@ -743,7 +750,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, nla_get_be16(a), is_mask); break; case OVS_TUNNEL_KEY_ATTR_OAM: - tun_flags |= TUNNEL_OAM; + __set_bit(IP_TUNNEL_OAM_BIT, tun_flags); break; case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS: if (opts_type) { @@ -755,7 +762,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, if (err) return err; - tun_flags |= TUNNEL_GENEVE_OPT; + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_flags); opts_type = type; break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: @@ -768,7 +775,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, if (err) return err; - tun_flags |= TUNNEL_VXLAN_OPT; + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_flags); opts_type = type; break; case OVS_TUNNEL_KEY_ATTR_PAD: @@ -784,7 +791,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, if (err) return err; - tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_flags); opts_type = type; break; case OVS_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE: @@ -798,7 +805,8 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, } } - SW_FLOW_KEY_PUT(match, tun_key.tun_flags, tun_flags, is_mask); + SW_FLOW_KEY_BITMAP_COPY(match, tun_key.tun_flags, tun_flags, + __IP_TUNNEL_FLAG_NUM, is_mask); if (is_mask) SW_FLOW_KEY_MEMSET_FIELD(match, tun_proto, 0xff, true); else @@ -823,13 +831,15 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, } if (ipv4) { if (info_bridge_mode) { + __clear_bit(IP_TUNNEL_KEY_BIT, tun_flags); + if (match->key->tun_key.u.ipv4.src || match->key->tun_key.u.ipv4.dst || match->key->tun_key.tp_src || match->key->tun_key.tp_dst || match->key->tun_key.ttl || match->key->tun_key.tos || - tun_flags & ~TUNNEL_KEY) { + !ip_tunnel_flags_empty(tun_flags)) { OVS_NLERR(log, "IPv4 tun info is not correct"); return -EINVAL; } @@ -874,7 +884,7 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, const void *tun_opts, int swkey_tun_opts_len, unsigned short tun_proto, u8 mode) { - if (output->tun_flags & TUNNEL_KEY && + if (test_bit(IP_TUNNEL_KEY_BIT, output->tun_flags) && nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id, OVS_TUNNEL_KEY_ATTR_PAD)) return -EMSGSIZE; @@ -910,10 +920,10 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, return -EMSGSIZE; if (nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TTL, output->ttl)) return -EMSGSIZE; - if ((output->tun_flags & TUNNEL_DONT_FRAGMENT) && + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, output->tun_flags) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT)) return -EMSGSIZE; - if ((output->tun_flags & TUNNEL_CSUM) && + if (test_bit(IP_TUNNEL_CSUM_BIT, output->tun_flags) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM)) return -EMSGSIZE; if (output->tp_src && @@ -922,18 +932,20 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, if (output->tp_dst && nla_put_be16(skb, OVS_TUNNEL_KEY_ATTR_TP_DST, output->tp_dst)) return -EMSGSIZE; - if ((output->tun_flags & TUNNEL_OAM) && + if (test_bit(IP_TUNNEL_OAM_BIT, output->tun_flags) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM)) return -EMSGSIZE; if (swkey_tun_opts_len) { - if (output->tun_flags & TUNNEL_GENEVE_OPT && + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, output->tun_flags) && nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS, swkey_tun_opts_len, tun_opts)) return -EMSGSIZE; - else if (output->tun_flags & TUNNEL_VXLAN_OPT && + else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, + output->tun_flags) && vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len)) return -EMSGSIZE; - else if (output->tun_flags & TUNNEL_ERSPAN_OPT && + else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + output->tun_flags) && nla_put(skb, OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, swkey_tun_opts_len, tun_opts)) return -EMSGSIZE; @@ -2029,7 +2041,7 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, if ((swkey->tun_proto || is_mask)) { const void *opts = NULL; - if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT) + if (ip_tunnel_is_options_present(output->tun_key.tun_flags)) opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len); if (ip_tun_to_nlattr(skb, &output->tun_key, opts, @@ -2752,7 +2764,8 @@ static int validate_geneve_opts(struct sw_flow_key *key) opts_len -= len; } - key->tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0; + if (crit_opt) + __set_bit(IP_TUNNEL_CRIT_OPT_BIT, key->tun_key.tun_flags); return 0; } @@ -2760,6 +2773,7 @@ static int validate_geneve_opts(struct sw_flow_key *key) static int validate_and_copy_set_tun(const struct nlattr *attr, struct sw_flow_actions **sfa, bool log) { + IP_TUNNEL_DECLARE_FLAGS(dst_opt_type) = { }; struct sw_flow_match match; struct sw_flow_key key; struct metadata_dst *tun_dst; @@ -2767,9 +2781,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, struct ovs_tunnel_info *ovs_tun; struct nlattr *a; int err = 0, start, opts_type; - __be16 dst_opt_type; - dst_opt_type = 0; ovs_match_init(&match, &key, true, NULL); opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log); if (opts_type < 0) @@ -2781,13 +2793,14 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, err = validate_geneve_opts(&key); if (err < 0) return err; - dst_opt_type = TUNNEL_GENEVE_OPT; + + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, dst_opt_type); break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: - dst_opt_type = TUNNEL_VXLAN_OPT; + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, dst_opt_type); break; case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: - dst_opt_type = TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, dst_opt_type); break; } } diff --git a/net/psample/psample.c b/net/psample/psample.c index ddd211a151d0..a5d9b8446f77 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -221,7 +221,7 @@ static int __psample_ip_tun_to_nlattr(struct sk_buff *skb, const struct ip_tunnel_key *tun_key = &tun_info->key; int tun_opts_len = tun_info->options_len; - if (tun_key->tun_flags & TUNNEL_KEY && + if (test_bit(IP_TUNNEL_KEY_BIT, tun_key->tun_flags) && nla_put_be64(skb, PSAMPLE_TUNNEL_KEY_ATTR_ID, tun_key->tun_id, PSAMPLE_TUNNEL_KEY_ATTR_PAD)) return -EMSGSIZE; @@ -257,10 +257,10 @@ static int __psample_ip_tun_to_nlattr(struct sk_buff *skb, return -EMSGSIZE; if (nla_put_u8(skb, PSAMPLE_TUNNEL_KEY_ATTR_TTL, tun_key->ttl)) return -EMSGSIZE; - if ((tun_key->tun_flags & TUNNEL_DONT_FRAGMENT) && + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, tun_key->tun_flags) && nla_put_flag(skb, PSAMPLE_TUNNEL_KEY_ATTR_DONT_FRAGMENT)) return -EMSGSIZE; - if ((tun_key->tun_flags & TUNNEL_CSUM) && + if (test_bit(IP_TUNNEL_CSUM_BIT, tun_key->tun_flags) && nla_put_flag(skb, PSAMPLE_TUNNEL_KEY_ATTR_CSUM)) return -EMSGSIZE; if (tun_key->tp_src && @@ -269,15 +269,16 @@ static int __psample_ip_tun_to_nlattr(struct sk_buff *skb, if (tun_key->tp_dst && nla_put_be16(skb, PSAMPLE_TUNNEL_KEY_ATTR_TP_DST, tun_key->tp_dst)) return -EMSGSIZE; - if ((tun_key->tun_flags & TUNNEL_OAM) && + if (test_bit(IP_TUNNEL_OAM_BIT, tun_key->tun_flags) && nla_put_flag(skb, PSAMPLE_TUNNEL_KEY_ATTR_OAM)) return -EMSGSIZE; if (tun_opts_len) { - if (tun_key->tun_flags & TUNNEL_GENEVE_OPT && + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_key->tun_flags) && nla_put(skb, PSAMPLE_TUNNEL_KEY_ATTR_GENEVE_OPTS, tun_opts_len, tun_opts)) return -EMSGSIZE; - else if (tun_key->tun_flags & TUNNEL_ERSPAN_OPT && + else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + tun_key->tun_flags) && nla_put(skb, PSAMPLE_TUNNEL_KEY_ATTR_ERSPAN_OPTS, tun_opts_len, tun_opts)) return -EMSGSIZE; @@ -314,7 +315,7 @@ static int psample_tunnel_meta_len(struct ip_tunnel_info *tun_info) int tun_opts_len = tun_info->options_len; int sum = nla_total_size(0); /* PSAMPLE_ATTR_TUNNEL */ - if (tun_key->tun_flags & TUNNEL_KEY) + if (test_bit(IP_TUNNEL_KEY_BIT, tun_key->tun_flags)) sum += nla_total_size_64bit(sizeof(u64)); if (tun_info->mode & IP_TUNNEL_INFO_BRIDGE) @@ -337,20 +338,21 @@ static int psample_tunnel_meta_len(struct ip_tunnel_info *tun_info) if (tun_key->tos) sum += nla_total_size(sizeof(u8)); sum += nla_total_size(sizeof(u8)); /* TTL */ - if (tun_key->tun_flags & TUNNEL_DONT_FRAGMENT) + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, tun_key->tun_flags)) sum += nla_total_size(0); - if (tun_key->tun_flags & TUNNEL_CSUM) + if (test_bit(IP_TUNNEL_CSUM_BIT, tun_key->tun_flags)) sum += nla_total_size(0); if (tun_key->tp_src) sum += nla_total_size(sizeof(u16)); if (tun_key->tp_dst) sum += nla_total_size(sizeof(u16)); - if (tun_key->tun_flags & TUNNEL_OAM) + if (test_bit(IP_TUNNEL_OAM_BIT, tun_key->tun_flags)) sum += nla_total_size(0); if (tun_opts_len) { - if (tun_key->tun_flags & TUNNEL_GENEVE_OPT) + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_key->tun_flags)) sum += nla_total_size(tun_opts_len); - else if (tun_key->tun_flags & TUNNEL_ERSPAN_OPT) + else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + tun_key->tun_flags)) sum += nla_total_size(tun_opts_len); } diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 5222bc97d192..f4844683e120 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -65,7 +65,7 @@ static void rxrpc_write_space(struct sock *sk) if (skwq_has_sleeper(wq)) wake_up_interruptible(&wq->wait); - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); } diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 1536f8b16f1b..af7c99845948 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -230,7 +230,7 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, nla_for_each_attr(attr, head, len, rem) { switch (nla_type(attr)) { case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: - if (type && type != TUNNEL_GENEVE_OPT) { + if (type && type != IP_TUNNEL_GENEVE_OPT_BIT) { NL_SET_ERR_MSG(extack, "Duplicate type for geneve options"); return -EINVAL; } @@ -247,7 +247,7 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, dst_len -= opt_len; dst += opt_len; } - type = TUNNEL_GENEVE_OPT; + type = IP_TUNNEL_GENEVE_OPT_BIT; break; case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN: if (type) { @@ -259,7 +259,7 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, if (opt_len < 0) return opt_len; opts_len += opt_len; - type = TUNNEL_VXLAN_OPT; + type = IP_TUNNEL_VXLAN_OPT_BIT; break; case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN: if (type) { @@ -271,7 +271,7 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, if (opt_len < 0) return opt_len; opts_len += opt_len; - type = TUNNEL_ERSPAN_OPT; + type = IP_TUNNEL_ERSPAN_OPT_BIT; break; } } @@ -302,7 +302,7 @@ static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info, switch (nla_type(nla_data(nla))) { case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: #if IS_ENABLED(CONFIG_INET) - info->key.tun_flags |= TUNNEL_GENEVE_OPT; + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags); return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), opts_len, extack); #else @@ -310,7 +310,7 @@ static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info, #endif case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN: #if IS_ENABLED(CONFIG_INET) - info->key.tun_flags |= TUNNEL_VXLAN_OPT; + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags); return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), opts_len, extack); #else @@ -318,7 +318,7 @@ static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info, #endif case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN: #if IS_ENABLED(CONFIG_INET) - info->key.tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), opts_len, extack); #else @@ -363,6 +363,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, bool bind = act_flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1]; struct tcf_tunnel_key_params *params_new; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *metadata = NULL; struct tcf_chain *goto_ch = NULL; struct tc_tunnel_key *parm; @@ -371,7 +372,6 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, __be16 dst_port = 0; __be64 key_id = 0; int opts_len = 0; - __be16 flags = 0; u8 tos, ttl; int ret = 0; u32 index; @@ -412,16 +412,16 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, key32 = nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID]); key_id = key32_to_tunnel_id(key32); - flags = TUNNEL_KEY; + __set_bit(IP_TUNNEL_KEY_BIT, flags); } - flags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, flags); if (tb[TCA_TUNNEL_KEY_NO_CSUM] && nla_get_u8(tb[TCA_TUNNEL_KEY_NO_CSUM])) - flags &= ~TUNNEL_CSUM; + __clear_bit(IP_TUNNEL_CSUM_BIT, flags); if (nla_get_flag(tb[TCA_TUNNEL_KEY_NO_FRAG])) - flags |= TUNNEL_DONT_FRAGMENT; + __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, flags); if (tb[TCA_TUNNEL_KEY_ENC_DST_PORT]) dst_port = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_DST_PORT]); @@ -663,15 +663,15 @@ static int tunnel_key_opts_dump(struct sk_buff *skb, if (!start) return -EMSGSIZE; - if (info->key.tun_flags & TUNNEL_GENEVE_OPT) { + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) { err = tunnel_key_geneve_opts_dump(skb, info); if (err) goto err_out; - } else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) { + } else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { err = tunnel_key_vxlan_opts_dump(skb, info); if (err) goto err_out; - } else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) { + } else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags)) { err = tunnel_key_erspan_opts_dump(skb, info); if (err) goto err_out; @@ -741,7 +741,7 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, struct ip_tunnel_key *key = &info->key; __be32 key_id = tunnel_id_to_key32(key->tun_id); - if (((key->tun_flags & TUNNEL_KEY) && + if ((test_bit(IP_TUNNEL_KEY_BIT, key->tun_flags) && nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id)) || tunnel_key_dump_addresses(skb, ¶ms->tcft_enc_metadata->u.tun_info) || @@ -749,8 +749,8 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst)) || nla_put_u8(skb, TCA_TUNNEL_KEY_NO_CSUM, - !(key->tun_flags & TUNNEL_CSUM)) || - ((key->tun_flags & TUNNEL_DONT_FRAGMENT) && + !test_bit(IP_TUNNEL_CSUM_BIT, key->tun_flags)) || + (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) && nla_put_flag(skb, TCA_TUNNEL_KEY_NO_FRAG)) || tunnel_key_opts_dump(skb, info)) goto nla_put_failure; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index e1314674b4a9..fd9a6f20b60b 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -28,6 +28,7 @@ #include <net/vxlan.h> #include <net/erspan.h> #include <net/gtp.h> +#include <net/pfcp.h> #include <net/tc_wrapper.h> #include <net/dst.h> @@ -741,6 +742,7 @@ enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = { [TCA_FLOWER_KEY_ENC_OPTS_VXLAN] = { .type = NLA_NESTED }, [TCA_FLOWER_KEY_ENC_OPTS_ERSPAN] = { .type = NLA_NESTED }, [TCA_FLOWER_KEY_ENC_OPTS_GTP] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_OPTS_PFCP] = { .type = NLA_NESTED }, }; static const struct nla_policy @@ -771,6 +773,12 @@ gtp_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GTP_MAX + 1] = { }; static const struct nla_policy +pfcp_opt_policy[TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX + 1] = { + [TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID] = { .type = NLA_U64 }, +}; + +static const struct nla_policy mpls_stack_entry_policy[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1] = { [TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL] = { .type = NLA_U8 }, @@ -1419,6 +1427,44 @@ static int fl_set_gtp_opt(const struct nlattr *nla, struct fl_flow_key *key, return sizeof(*sinfo); } +static int fl_set_pfcp_opt(const struct nlattr *nla, struct fl_flow_key *key, + int depth, int option_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX + 1]; + struct pfcp_metadata *md; + int err; + + md = (struct pfcp_metadata *)&key->enc_opts.data[key->enc_opts.len]; + memset(md, 0xff, sizeof(*md)); + + if (!depth) + return sizeof(*md); + + if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_PFCP) { + NL_SET_ERR_MSG_MOD(extack, "Non-pfcp option type for mask"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX, nla, + pfcp_opt_policy, extack); + if (err < 0) + return err; + + if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing tunnel key pfcp option type"); + return -EINVAL; + } + + if (tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE]) + md->type = nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE]); + + if (tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID]) + md->seid = nla_get_be64(tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID]); + + return sizeof(*md); +} + static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask, struct netlink_ext_ack *extack) @@ -1454,12 +1500,13 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, switch (nla_type(nla_opt_key)) { case TCA_FLOWER_KEY_ENC_OPTS_GENEVE: if (key->enc_opts.dst_opt_type && - key->enc_opts.dst_opt_type != TUNNEL_GENEVE_OPT) { + key->enc_opts.dst_opt_type != + IP_TUNNEL_GENEVE_OPT_BIT) { NL_SET_ERR_MSG(extack, "Duplicate type for geneve options"); return -EINVAL; } option_len = 0; - key->enc_opts.dst_opt_type = TUNNEL_GENEVE_OPT; + key->enc_opts.dst_opt_type = IP_TUNNEL_GENEVE_OPT_BIT; option_len = fl_set_geneve_opt(nla_opt_key, key, key_depth, option_len, extack); @@ -1470,7 +1517,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, /* At the same time we need to parse through the mask * in order to verify exact and mask attribute lengths. */ - mask->enc_opts.dst_opt_type = TUNNEL_GENEVE_OPT; + mask->enc_opts.dst_opt_type = IP_TUNNEL_GENEVE_OPT_BIT; option_len = fl_set_geneve_opt(nla_opt_msk, mask, msk_depth, option_len, extack); @@ -1489,7 +1536,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } option_len = 0; - key->enc_opts.dst_opt_type = TUNNEL_VXLAN_OPT; + key->enc_opts.dst_opt_type = IP_TUNNEL_VXLAN_OPT_BIT; option_len = fl_set_vxlan_opt(nla_opt_key, key, key_depth, option_len, extack); @@ -1500,7 +1547,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, /* At the same time we need to parse through the mask * in order to verify exact and mask attribute lengths. */ - mask->enc_opts.dst_opt_type = TUNNEL_VXLAN_OPT; + mask->enc_opts.dst_opt_type = IP_TUNNEL_VXLAN_OPT_BIT; option_len = fl_set_vxlan_opt(nla_opt_msk, mask, msk_depth, option_len, extack); @@ -1519,7 +1566,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } option_len = 0; - key->enc_opts.dst_opt_type = TUNNEL_ERSPAN_OPT; + key->enc_opts.dst_opt_type = IP_TUNNEL_ERSPAN_OPT_BIT; option_len = fl_set_erspan_opt(nla_opt_key, key, key_depth, option_len, extack); @@ -1530,7 +1577,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, /* At the same time we need to parse through the mask * in order to verify exact and mask attribute lengths. */ - mask->enc_opts.dst_opt_type = TUNNEL_ERSPAN_OPT; + mask->enc_opts.dst_opt_type = IP_TUNNEL_ERSPAN_OPT_BIT; option_len = fl_set_erspan_opt(nla_opt_msk, mask, msk_depth, option_len, extack); @@ -1550,7 +1597,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } option_len = 0; - key->enc_opts.dst_opt_type = TUNNEL_GTP_OPT; + key->enc_opts.dst_opt_type = IP_TUNNEL_GTP_OPT_BIT; option_len = fl_set_gtp_opt(nla_opt_key, key, key_depth, option_len, extack); @@ -1561,7 +1608,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, /* At the same time we need to parse through the mask * in order to verify exact and mask attribute lengths. */ - mask->enc_opts.dst_opt_type = TUNNEL_GTP_OPT; + mask->enc_opts.dst_opt_type = IP_TUNNEL_GTP_OPT_BIT; option_len = fl_set_gtp_opt(nla_opt_msk, mask, msk_depth, option_len, extack); @@ -1575,6 +1622,36 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } break; + case TCA_FLOWER_KEY_ENC_OPTS_PFCP: + if (key->enc_opts.dst_opt_type) { + NL_SET_ERR_MSG_MOD(extack, "Duplicate type for pfcp options"); + return -EINVAL; + } + option_len = 0; + key->enc_opts.dst_opt_type = IP_TUNNEL_PFCP_OPT_BIT; + option_len = fl_set_pfcp_opt(nla_opt_key, key, + key_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + key->enc_opts.len += option_len; + /* At the same time we need to parse through the mask + * in order to verify exact and mask attribute lengths. + */ + mask->enc_opts.dst_opt_type = IP_TUNNEL_PFCP_OPT_BIT; + option_len = fl_set_pfcp_opt(nla_opt_msk, mask, + msk_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + mask->enc_opts.len += option_len; + if (key->enc_opts.len != mask->enc_opts.len) { + NL_SET_ERR_MSG_MOD(extack, "Key and mask miss aligned"); + return -EINVAL; + } + break; default: NL_SET_ERR_MSG(extack, "Unknown tunnel option type"); return -EINVAL; @@ -3117,6 +3194,32 @@ nla_put_failure: return -EMSGSIZE; } +static int fl_dump_key_pfcp_opt(struct sk_buff *skb, + struct flow_dissector_key_enc_opts *enc_opts) +{ + struct pfcp_metadata *md; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_PFCP); + if (!nest) + goto nla_put_failure; + + md = (struct pfcp_metadata *)&enc_opts->data[0]; + if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE, md->type)) + goto nla_put_failure; + + if (nla_put_be64(skb, TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID, + md->seid, 0)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + static int fl_dump_key_ct(struct sk_buff *skb, struct flow_dissector_key_ct *key, struct flow_dissector_key_ct *mask) @@ -3202,26 +3305,31 @@ static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type, goto nla_put_failure; switch (enc_opts->dst_opt_type) { - case TUNNEL_GENEVE_OPT: + case IP_TUNNEL_GENEVE_OPT_BIT: err = fl_dump_key_geneve_opt(skb, enc_opts); if (err) goto nla_put_failure; break; - case TUNNEL_VXLAN_OPT: + case IP_TUNNEL_VXLAN_OPT_BIT: err = fl_dump_key_vxlan_opt(skb, enc_opts); if (err) goto nla_put_failure; break; - case TUNNEL_ERSPAN_OPT: + case IP_TUNNEL_ERSPAN_OPT_BIT: err = fl_dump_key_erspan_opt(skb, enc_opts); if (err) goto nla_put_failure; break; - case TUNNEL_GTP_OPT: + case IP_TUNNEL_GTP_OPT_BIT: err = fl_dump_key_gtp_opt(skb, enc_opts); if (err) goto nla_put_failure; break; + case IP_TUNNEL_PFCP_OPT_BIT: + err = fl_dump_key_pfcp_opt(skb, enc_opts); + if (err) + goto nla_put_failure; + break; default: goto nla_put_failure; } diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 225353fbb3f1..51d4013b6121 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -215,10 +215,8 @@ static int mqprio_parse_tc_entries(struct Qdisc *sch, struct nlattr *nlattr_opt, for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) fp[tc] = priv->fp[tc]; - nla_for_each_attr(n, nlattr_opt, nlattr_opt_len, rem) { - if (nla_type(n) != TCA_MQPRIO_TC_ENTRY) - continue; - + nla_for_each_attr_type(n, TCA_MQPRIO_TC_ENTRY, nlattr_opt, + nlattr_opt_len, rem) { err = mqprio_parse_tc_entry(fp, n, &seen_tcs, extack); if (err) goto out; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index a0d54b422186..1ab17e8a7260 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1752,10 +1752,7 @@ static int taprio_parse_tc_entries(struct Qdisc *sch, fp[tc] = q->fp[tc]; } - nla_for_each_nested(n, opt, rem) { - if (nla_type(n) != TCA_TAPRIO_ATTR_TC_ENTRY) - continue; - + nla_for_each_nested_type(n, TCA_TAPRIO_ATTR_TC_ENTRY, opt, rem) { err = taprio_parse_tc_entry(sch, n, max_sdu, fp, &seen_tcs, extack); if (err) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c67679a41044..e416b6d3d270 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -9276,7 +9276,7 @@ void sctp_data_ready(struct sock *sk) if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLRDNORM | EPOLLRDBAND); - sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); + sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); } diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index 9a2f3638d161..f0cbe77a80b4 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -42,10 +42,10 @@ static void smc_rx_wake_up(struct sock *sk) if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI | EPOLLRDNORM | EPOLLRDBAND); - sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); + sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); if ((sk->sk_shutdown == SHUTDOWN_MASK) || (sk->sk_state == SMC_CLOSED)) - sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP); + sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_HUP); rcu_read_unlock(); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 27ca50ab1cd1..533fb682c954 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -546,7 +546,7 @@ static void unix_write_space(struct sock *sk) if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); } diff --git a/tools/include/linux/align.h b/tools/include/linux/align.h new file mode 100644 index 000000000000..14e34ace80dd --- /dev/null +++ b/tools/include/linux/align.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _TOOLS_LINUX_ALIGN_H +#define _TOOLS_LINUX_ALIGN_H + +#include <uapi/linux/const.h> + +#define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) +#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) +#define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) + +#endif /* _TOOLS_LINUX_ALIGN_H */ diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index f3566ea0f932..210c13b1b857 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -3,6 +3,7 @@ #define _TOOLS_LINUX_BITMAP_H #include <string.h> +#include <linux/align.h> #include <linux/bitops.h> #include <linux/find.h> #include <stdlib.h> @@ -25,13 +26,14 @@ bool __bitmap_intersects(const unsigned long *bitmap1, #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) +#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) + static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = 0UL; else { - int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memset(dst, 0, len); + memset(dst, 0, bitmap_size(nbits)); } } @@ -83,7 +85,7 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, */ static inline unsigned long *bitmap_zalloc(int nbits) { - return calloc(1, BITS_TO_LONGS(nbits) * sizeof(unsigned long)); + return calloc(1, bitmap_size(nbits)); } /* @@ -126,7 +128,6 @@ static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1, #define BITMAP_MEM_ALIGNMENT (8 * sizeof(unsigned long)) #endif #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) -#define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) static inline bool bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h index 7319f6ced108..272f15d0e434 100644 --- a/tools/include/linux/bitops.h +++ b/tools/include/linux/bitops.h @@ -20,6 +20,8 @@ #define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(u32)) #define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) +#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_BYTE) + extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); extern unsigned int __sw_hweight32(unsigned int w); diff --git a/tools/include/linux/mm.h b/tools/include/linux/mm.h index f3c82ab5b14c..7a6b98f4e579 100644 --- a/tools/include/linux/mm.h +++ b/tools/include/linux/mm.h @@ -2,8 +2,8 @@ #ifndef _TOOLS_LINUX_MM_H #define _TOOLS_LINUX_MM_H +#include <linux/align.h> #include <linux/mmzone.h> -#include <uapi/linux/const.h> #define PAGE_SHIFT 12 #define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT) @@ -11,9 +11,6 @@ #define PHYS_ADDR_MAX (~(phys_addr_t)0) -#define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) -#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) - #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) #define __va(x) ((void *)((unsigned long)(x))) diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index e73b027c5624..82d3c98067aa 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause from collections import namedtuple +from enum import Enum import functools import os import random @@ -76,6 +77,25 @@ class Netlink: NLMSGERR_ATTR_MISS_TYPE = 5 NLMSGERR_ATTR_MISS_NEST = 6 + # Policy types + NL_POLICY_TYPE_ATTR_TYPE = 1 + NL_POLICY_TYPE_ATTR_MIN_VALUE_S = 2 + NL_POLICY_TYPE_ATTR_MAX_VALUE_S = 3 + NL_POLICY_TYPE_ATTR_MIN_VALUE_U = 4 + NL_POLICY_TYPE_ATTR_MAX_VALUE_U = 5 + NL_POLICY_TYPE_ATTR_MIN_LENGTH = 6 + NL_POLICY_TYPE_ATTR_MAX_LENGTH = 7 + NL_POLICY_TYPE_ATTR_POLICY_IDX = 8 + NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE = 9 + NL_POLICY_TYPE_ATTR_BITFIELD32_MASK = 10 + NL_POLICY_TYPE_ATTR_PAD = 11 + NL_POLICY_TYPE_ATTR_MASK = 12 + + AttrType = Enum('AttrType', ['flag', 'u8', 'u16', 'u32', 'u64', + 's8', 's16', 's32', 's64', + 'binary', 'string', 'nul-string', + 'nested', 'nested-array', + 'bitfield32', 'sint', 'uint']) class NlError(Exception): def __init__(self, nl_msg): @@ -198,6 +218,8 @@ class NlMsg: self.extack['miss-nest'] = extack.as_scalar('u32') elif extack.type == Netlink.NLMSGERR_ATTR_OFFS: self.extack['bad-attr-offs'] = extack.as_scalar('u32') + elif extack.type == Netlink.NLMSGERR_ATTR_POLICY: + self.extack['policy'] = self._decode_policy(extack.raw) else: if 'unknown' not in self.extack: self.extack['unknown'] = [] @@ -214,6 +236,30 @@ class NlMsg: desc += f" ({spec['doc']})" self.extack['miss-type'] = desc + def _decode_policy(self, raw): + policy = {} + for attr in NlAttrs(raw): + if attr.type == Netlink.NL_POLICY_TYPE_ATTR_TYPE: + type = attr.as_scalar('u32') + policy['type'] = Netlink.AttrType(type).name + elif attr.type == Netlink.NL_POLICY_TYPE_ATTR_MIN_VALUE_S: + policy['min-value'] = attr.as_scalar('s64') + elif attr.type == Netlink.NL_POLICY_TYPE_ATTR_MAX_VALUE_S: + policy['max-value'] = attr.as_scalar('s64') + elif attr.type == Netlink.NL_POLICY_TYPE_ATTR_MIN_VALUE_U: + policy['min-value'] = attr.as_scalar('u64') + elif attr.type == Netlink.NL_POLICY_TYPE_ATTR_MAX_VALUE_U: + policy['max-value'] = attr.as_scalar('u64') + elif attr.type == Netlink.NL_POLICY_TYPE_ATTR_MIN_LENGTH: + policy['min-length'] = attr.as_scalar('u32') + elif attr.type == Netlink.NL_POLICY_TYPE_ATTR_MAX_LENGTH: + policy['max-length'] = attr.as_scalar('u32') + elif attr.type == Netlink.NL_POLICY_TYPE_ATTR_BITFIELD32_MASK: + policy['bitfield32-mask'] = attr.as_scalar('u32') + elif attr.type == Netlink.NL_POLICY_TYPE_ATTR_MASK: + policy['mask'] = attr.as_scalar('u64') + return policy + def cmd(self): return self.nl_type diff --git a/tools/net/ynl/ynl-gen-rst.py b/tools/net/ynl/ynl-gen-rst.py index 927407b3efb3..657e881d2ea4 100755 --- a/tools/net/ynl/ynl-gen-rst.py +++ b/tools/net/ynl/ynl-gen-rst.py @@ -82,9 +82,9 @@ def rst_subsubsection(title: str) -> str: return f"{title}\n" + "~" * len(title) -def rst_section(title: str) -> str: +def rst_section(namespace: str, prefix: str, title: str) -> str: """Add a section to the document""" - return f"\n{title}\n" + "=" * len(title) + return f".. _{namespace}-{prefix}-{title}:\n\n{title}\n" + "=" * len(title) def rst_subtitle(title: str) -> str: @@ -102,6 +102,17 @@ def rst_list_inline(list_: List[str], level: int = 0) -> str: return headroom(level) + "[" + ", ".join(inline(i) for i in list_) + "]" +def rst_ref(namespace: str, prefix: str, name: str) -> str: + """Add a hyperlink to the document""" + mappings = {'enum': 'definition', + 'fixed-header': 'definition', + 'nested-attributes': 'attribute-set', + 'struct': 'definition'} + if prefix in mappings: + prefix = mappings[prefix] + return f":ref:`{namespace}-{prefix}-{name}`" + + def rst_header() -> str: """The headers for all the auto generated RST files""" lines = [] @@ -159,20 +170,24 @@ def parse_do_attributes(attrs: Dict[str, Any], level: int = 0) -> str: return "\n".join(lines) -def parse_operations(operations: List[Dict[str, Any]]) -> str: +def parse_operations(operations: List[Dict[str, Any]], namespace: str) -> str: """Parse operations block""" preprocessed = ["name", "doc", "title", "do", "dump"] + linkable = ["fixed-header", "attribute-set"] lines = [] for operation in operations: - lines.append(rst_section(operation["name"])) + lines.append(rst_section(namespace, 'operation', operation["name"])) lines.append(rst_paragraph(sanitize(operation["doc"])) + "\n") for key in operation.keys(): if key in preprocessed: # Skip the special fields continue - lines.append(rst_fields(key, operation[key], 0)) + value = operation[key] + if key in linkable: + value = rst_ref(namespace, key, value) + lines.append(rst_fields(key, value, 0)) if "do" in operation: lines.append(rst_paragraph(":do:", 0)) @@ -212,14 +227,14 @@ def parse_entries(entries: List[Dict[str, Any]], level: int) -> str: return "\n".join(lines) -def parse_definitions(defs: Dict[str, Any]) -> str: +def parse_definitions(defs: Dict[str, Any], namespace: str) -> str: """Parse definitions section""" preprocessed = ["name", "entries", "members"] ignored = ["render-max"] # This is not printed lines = [] for definition in defs: - lines.append(rst_section(definition["name"])) + lines.append(rst_section(namespace, 'definition', definition["name"])) for k in definition.keys(): if k in preprocessed + ignored: continue @@ -237,14 +252,15 @@ def parse_definitions(defs: Dict[str, Any]) -> str: return "\n".join(lines) -def parse_attr_sets(entries: List[Dict[str, Any]]) -> str: +def parse_attr_sets(entries: List[Dict[str, Any]], namespace: str) -> str: """Parse attribute from attribute-set""" preprocessed = ["name", "type"] + linkable = ["enum", "nested-attributes", "struct", "sub-message"] ignored = ["checks"] lines = [] for entry in entries: - lines.append(rst_section(entry["name"])) + lines.append(rst_section(namespace, 'attribute-set', entry["name"])) for attr in entry["attributes"]: type_ = attr.get("type") attr_line = attr["name"] @@ -257,25 +273,31 @@ def parse_attr_sets(entries: List[Dict[str, Any]]) -> str: for k in attr.keys(): if k in preprocessed + ignored: continue - lines.append(rst_fields(k, sanitize(attr[k]), 0)) + if k in linkable: + value = rst_ref(namespace, k, attr[k]) + else: + value = sanitize(attr[k]) + lines.append(rst_fields(k, value, 0)) lines.append("\n") return "\n".join(lines) -def parse_sub_messages(entries: List[Dict[str, Any]]) -> str: +def parse_sub_messages(entries: List[Dict[str, Any]], namespace: str) -> str: """Parse sub-message definitions""" lines = [] for entry in entries: - lines.append(rst_section(entry["name"])) + lines.append(rst_section(namespace, 'sub-message', entry["name"])) for fmt in entry["formats"]: value = fmt["value"] lines.append(rst_bullet(bold(value))) for attr in ['fixed-header', 'attribute-set']: if attr in fmt: - lines.append(rst_fields(attr, fmt[attr], 1)) + lines.append(rst_fields(attr, + rst_ref(namespace, attr, fmt[attr]), + 1)) lines.append("\n") return "\n".join(lines) @@ -289,9 +311,11 @@ def parse_yaml(obj: Dict[str, Any]) -> str: lines.append(rst_header()) - title = f"Family ``{obj['name']}`` netlink specification" + family = obj['name'] + + title = f"Family ``{family}`` netlink specification" lines.append(rst_title(title)) - lines.append(rst_paragraph(".. contents::\n")) + lines.append(rst_paragraph(".. contents:: :depth: 3\n")) if "doc" in obj: lines.append(rst_subtitle("Summary")) @@ -300,7 +324,7 @@ def parse_yaml(obj: Dict[str, Any]) -> str: # Operations if "operations" in obj: lines.append(rst_subtitle("Operations")) - lines.append(parse_operations(obj["operations"]["list"])) + lines.append(parse_operations(obj["operations"]["list"], family)) # Multicast groups if "mcast-groups" in obj: @@ -310,17 +334,17 @@ def parse_yaml(obj: Dict[str, Any]) -> str: # Definitions if "definitions" in obj: lines.append(rst_subtitle("Definitions")) - lines.append(parse_definitions(obj["definitions"])) + lines.append(parse_definitions(obj["definitions"], family)) # Attributes set if "attribute-sets" in obj: lines.append(rst_subtitle("Attribute sets")) - lines.append(parse_attr_sets(obj["attribute-sets"])) + lines.append(parse_attr_sets(obj["attribute-sets"], family)) # Sub-messages if "sub-messages" in obj: lines.append(rst_subtitle("Sub-messages")) - lines.append(parse_sub_messages(obj["sub-messages"])) + lines.append(parse_sub_messages(obj["sub-messages"], family)) return "\n".join(lines) diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index c8923375e30d..630e16c54ed5 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -186,8 +186,6 @@ static_var: return ret2; } -#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_LONG / sizeof(long)) - static int convert_variable_type(Dwarf_Die *vr_die, struct probe_trace_arg *tvar, const char *cast, bool user_access) @@ -217,7 +215,7 @@ static int convert_variable_type(Dwarf_Die *vr_die, total = dwarf_bytesize(vr_die); if (boffs < 0 || total < 0) return -ENOENT; - ret = snprintf(buf, 16, "b%d@%d/%zd", bsize, boffs, + ret = snprintf(buf, 16, "b%d@%d/%d", bsize, boffs, BYTES_TO_BITS(total)); goto formatted; } |