diff options
Diffstat (limited to 'include')
79 files changed, 1483 insertions, 278 deletions
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index b2488055fd1d..7605b5919c3a 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -171,7 +171,7 @@ struct virtchnl_msg { VIRTCHNL_CHECK_STRUCT_LEN(20, virtchnl_msg); -/* Message descriptions and data structures.*/ +/* Message descriptions and data structures. */ /* VIRTCHNL_OP_VERSION * VF posts its version number to the PF. PF responds with its version number @@ -342,6 +342,8 @@ struct virtchnl_vsi_queue_config_info { struct virtchnl_queue_pair_info qpair[1]; }; +VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info); + /* VIRTCHNL_OP_REQUEST_QUEUES * VF sends this message to request the PF to allocate additional queues to * this VF. Each VF gets a guaranteed number of queues on init but asking for @@ -357,8 +359,6 @@ struct virtchnl_vf_res_request { u16 num_queue_pairs; }; -VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info); - /* VIRTCHNL_OP_CONFIG_IRQ_MAP * VF uses this message to map vectors to queues. * The rxq_map and txq_map fields are bitmaps used to indicate which queues @@ -819,8 +819,8 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, if (msglen >= valid_len) { struct virtchnl_tc_info *vti = (struct virtchnl_tc_info *)msg; - valid_len += vti->num_tc * - sizeof(struct virtchnl_channel_info); + valid_len += (vti->num_tc - 1) * + sizeof(struct virtchnl_channel_info); if (vti->num_tc == 0) err_msg_format = true; } diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 33014ae73103..e82b7039fc66 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -268,15 +268,18 @@ struct bpf_prog_offload_ops { int (*insn_hook)(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int (*finalize)(struct bpf_verifier_env *env); + int (*prepare)(struct bpf_prog *prog); + int (*translate)(struct bpf_prog *prog); + void (*destroy)(struct bpf_prog *prog); }; struct bpf_prog_offload { struct bpf_prog *prog; struct net_device *netdev; + struct bpf_offload_dev *offdev; void *dev_priv; struct list_head offloads; bool dev_state; - const struct bpf_prog_offload_ops *dev_ops; void *jited_image; u32 jited_len; }; @@ -293,9 +296,11 @@ struct bpf_prog_aux { atomic_t refcnt; u32 used_map_cnt; u32 max_ctx_offset; + u32 max_pkt_offset; u32 stack_depth; u32 id; - u32 func_cnt; + u32 func_cnt; /* used by non-func prog as the number of func progs */ + u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ bool offload_requested; struct bpf_prog **func; void *jit_data; /* JIT specific data. arch dependent */ @@ -312,6 +317,9 @@ struct bpf_prog_aux { void *security; #endif struct bpf_prog_offload *offload; + struct btf *btf; + struct bpf_func_info *func_info; + u32 func_info_cnt; union { struct work_struct work; struct rcu_head rcu; @@ -523,7 +531,8 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) } /* verify correctness of eBPF program */ -int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); +int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, + union bpf_attr __user *uattr); void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); /* Map specifics */ @@ -691,7 +700,8 @@ int bpf_map_offload_get_next_key(struct bpf_map *map, bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map); -struct bpf_offload_dev *bpf_offload_dev_create(void); +struct bpf_offload_dev * +bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops); void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev); int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, struct net_device *netdev); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index d93e89761a8b..11f5df1092d9 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -245,7 +245,7 @@ static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) return cur_func(env)->regs; } -int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env); +int bpf_prog_offload_verifier_prep(struct bpf_prog *prog); int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int bpf_prog_offload_finalize(struct bpf_verifier_env *env); diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 949e9af8d9d6..9cd00a37b8d3 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -28,6 +28,7 @@ #define PHY_ID_BCM89610 0x03625cd0 #define PHY_ID_BCM7250 0xae025280 +#define PHY_ID_BCM7255 0xae025120 #define PHY_ID_BCM7260 0xae025190 #define PHY_ID_BCM7268 0xae025090 #define PHY_ID_BCM7271 0xae0253b0 diff --git a/include/linux/btf.h b/include/linux/btf.h index e076c4697049..8c2199b5d250 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -47,4 +47,20 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, int btf_get_fd_by_id(u32 id); u32 btf_id(const struct btf *btf); +#ifdef CONFIG_BPF_SYSCALL +const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); +const char *btf_name_by_offset(const struct btf *btf, u32 offset); +#else +static inline const struct btf_type *btf_type_by_id(const struct btf *btf, + u32 type_id) +{ + return NULL; +} +static inline const char *btf_name_by_offset(const struct btf *btf, + u32 offset) +{ + return NULL; +} +#endif + #endif diff --git a/include/linux/cordic.h b/include/linux/cordic.h index cf68ca4a508c..3d656f54d64f 100644 --- a/include/linux/cordic.h +++ b/include/linux/cordic.h @@ -18,6 +18,15 @@ #include <linux/types.h> +#define CORDIC_ANGLE_GEN 39797 +#define CORDIC_PRECISION_SHIFT 16 +#define CORDIC_NUM_ITER (CORDIC_PRECISION_SHIFT + 2) + +#define CORDIC_FIXED(X) ((s32)((X) << CORDIC_PRECISION_SHIFT)) +#define CORDIC_FLOAT(X) (((X) >= 0) \ + ? ((((X) >> (CORDIC_PRECISION_SHIFT - 1)) + 1) >> 1) \ + : -((((-(X)) >> (CORDIC_PRECISION_SHIFT - 1)) + 1) >> 1)) + /** * struct cordic_iq - i/q coordinate. * diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 572e11bb8696..2c0af7b00715 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -32,6 +32,7 @@ struct device; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); unsigned char *arch_get_platform_mac_address(void); +int nvmem_get_mac_address(struct device *dev, void *addrbuf); u32 eth_get_headlen(void *data, unsigned int max_len); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); extern const struct header_ops eth_header_ops; diff --git a/include/linux/filter.h b/include/linux/filter.h index 795ff0b869bb..5a26a7caa98f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -675,24 +675,10 @@ static inline u32 bpf_ctx_off_adjust_machine(u32 size) return size; } -static inline bool bpf_ctx_narrow_align_ok(u32 off, u32 size_access, - u32 size_default) -{ - size_default = bpf_ctx_off_adjust_machine(size_default); - size_access = bpf_ctx_off_adjust_machine(size_access); - -#ifdef __LITTLE_ENDIAN - return (off & (size_default - 1)) == 0; -#else - return (off & (size_default - 1)) + size_access == size_default; -#endif -} - static inline bool bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) { - return bpf_ctx_narrow_align_ok(off, size, size_default) && - size <= size_default && (size & (size - 1)) == 0; + return size <= size_default && (size & (size - 1)) == 0; } #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index c20c7e197d07..627b788ba0ff 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -119,6 +119,8 @@ static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, struct net_device *br_fdb_find_port(const struct net_device *br_dev, const unsigned char *addr, __u16 vid); +void br_fdb_clear_offload(const struct net_device *dev, u16 vid); +bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag); #else static inline struct net_device * br_fdb_find_port(const struct net_device *br_dev, @@ -127,6 +129,16 @@ br_fdb_find_port(const struct net_device *br_dev, { return NULL; } + +static inline void br_fdb_clear_offload(const struct net_device *dev, u16 vid) +{ +} + +static inline bool +br_port_flag_is_set(const struct net_device *dev, unsigned long flag) +{ + return false; +} #endif #endif diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 83ea4df6ab81..4cca4da7a6de 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -65,8 +65,7 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb) #define VLAN_PRIO_MASK 0xe000 /* Priority Code Point */ #define VLAN_PRIO_SHIFT 13 -#define VLAN_CFI_MASK 0x1000 /* Canonical Format Indicator */ -#define VLAN_TAG_PRESENT VLAN_CFI_MASK +#define VLAN_CFI_MASK 0x1000 /* Canonical Format Indicator / Drop Eligible Indicator */ #define VLAN_VID_MASK 0x0fff /* VLAN Identifier */ #define VLAN_N_VID 4096 @@ -78,10 +77,11 @@ static inline bool is_vlan_dev(const struct net_device *dev) return dev->priv_flags & IFF_802_1Q_VLAN; } -#define skb_vlan_tag_present(__skb) ((__skb)->vlan_tci & VLAN_TAG_PRESENT) -#define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci & ~VLAN_TAG_PRESENT) +#define skb_vlan_tag_present(__skb) ((__skb)->vlan_present) +#define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci) #define skb_vlan_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK) -#define skb_vlan_tag_get_prio(__skb) ((__skb)->vlan_tci & VLAN_PRIO_MASK) +#define skb_vlan_tag_get_cfi(__skb) (!!((__skb)->vlan_tci & VLAN_CFI_MASK)) +#define skb_vlan_tag_get_prio(__skb) (((__skb)->vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT) static inline int vlan_get_rx_ctag_filter_info(struct net_device *dev) { @@ -133,6 +133,9 @@ struct vlan_pcpu_stats { extern struct net_device *__vlan_find_dev_deep_rcu(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id); +extern int vlan_for_each(struct net_device *dev, + int (*action)(struct net_device *dev, int vid, + void *arg), void *arg); extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); extern __be16 vlan_dev_vlan_proto(const struct net_device *dev); @@ -236,6 +239,14 @@ __vlan_find_dev_deep_rcu(struct net_device *real_dev, return NULL; } +static inline int +vlan_for_each(struct net_device *dev, + int (*action)(struct net_device *dev, int vid, void *arg), + void *arg) +{ + return 0; +} + static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev) { BUG(); @@ -461,6 +472,31 @@ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb, return skb; } +/** + * __vlan_hwaccel_clear_tag - clear hardware accelerated VLAN info + * @skb: skbuff to clear + * + * Clears the VLAN information from @skb + */ +static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) +{ + skb->vlan_present = 0; +} + +/** + * __vlan_hwaccel_copy_tag - copy hardware accelerated VLAN info from another skb + * @dst: skbuff to copy to + * @src: skbuff to copy from + * + * Copies VLAN information from @src to @dst (for branchless code) + */ +static inline void __vlan_hwaccel_copy_tag(struct sk_buff *dst, const struct sk_buff *src) +{ + dst->vlan_present = src->vlan_present; + dst->vlan_proto = src->vlan_proto; + dst->vlan_tci = src->vlan_tci; +} + /* * __vlan_hwaccel_push_inside - pushes vlan tag to the payload * @skb: skbuff to tag @@ -475,7 +511,7 @@ static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb) skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (likely(skb)) - skb->vlan_tci = 0; + __vlan_hwaccel_clear_tag(skb); return skb; } @@ -491,7 +527,8 @@ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { skb->vlan_proto = vlan_proto; - skb->vlan_tci = VLAN_TAG_PRESENT | vlan_tci; + skb->vlan_tci = vlan_tci; + skb->vlan_present = 1; } /** @@ -531,8 +568,6 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, } } -#define HAVE_VLAN_GET_TAG - /** * vlan_get_tag - get the VLAN ID from the skb * @skb: skbuff to query diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index 22443d7fb5cd..a99c58866860 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -57,6 +57,15 @@ 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 void linkmode_change_bit(int nr, volatile unsigned long *addr) { __change_bit(nr, addr); diff --git a/include/linux/mii.h b/include/linux/mii.h index 2da85b02e1c0..6fee8b1a4400 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -209,7 +209,7 @@ static inline u32 ethtool_adv_to_mii_ctrl1000_t(u32 ethadv) /** * linkmode_adv_to_mii_ctrl1000_t - * advertising: the linkmode advertisement settings + * @advertising: the linkmode advertisement settings * * A small helper function that translates linkmode advertisement * settings to phy autonegotiation advertisements for the @@ -288,6 +288,25 @@ static inline u32 mii_stat1000_to_ethtool_lpa_t(u32 lpa) } /** + * mii_stat1000_mod_linkmode_lpa_t + * @advertising: target the linkmode advertisement settings + * @adv: value of the MII_STAT1000 register + * + * A small helper function that translates MII_STAT1000 bits, when in + * 1000Base-T mode, to linkmode advertisement settings. Other bits in + * advertising are not changes. + */ +static inline void mii_stat1000_mod_linkmode_lpa_t(unsigned long *advertising, + u32 lpa) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, + advertising, lpa & LPA_1000HALF); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + advertising, lpa & LPA_1000FULL); +} + +/** * ethtool_adv_to_mii_adv_x * @ethadv: the ethtool advertisement settings * @@ -354,50 +373,104 @@ static inline u32 mii_lpa_to_ethtool_lpa_x(u32 lpa) } /** + * mii_adv_mod_linkmode_adv_t + * @advertising:pointer to destination link mode. + * @adv: value of the MII_ADVERTISE register + * + * A small helper function that translates MII_ADVERTISE bits to + * linkmode advertisement settings. Leaves other bits unchanged. + */ +static inline void mii_adv_mod_linkmode_adv_t(unsigned long *advertising, + u32 adv) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, + advertising, adv & ADVERTISE_10HALF); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, + advertising, adv & ADVERTISE_10FULL); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, + advertising, adv & ADVERTISE_100HALF); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + advertising, adv & ADVERTISE_100FULL); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising, + adv & ADVERTISE_PAUSE_CAP); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + advertising, adv & ADVERTISE_PAUSE_ASYM); +} + +/** * mii_adv_to_linkmode_adv_t * @advertising:pointer to destination link mode. * @adv: value of the MII_ADVERTISE register * * A small helper function that translates MII_ADVERTISE bits - * to linkmode advertisement settings. + * to linkmode advertisement settings. Clears the old value + * of advertising. */ static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising, u32 adv) { linkmode_zero(advertising); - if (adv & ADVERTISE_10HALF) - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, - advertising); - if (adv & ADVERTISE_10FULL) - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, - advertising); - if (adv & ADVERTISE_100HALF) - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, - advertising); - if (adv & ADVERTISE_100FULL) - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, - advertising); - if (adv & ADVERTISE_PAUSE_CAP) - linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising); - if (adv & ADVERTISE_PAUSE_ASYM) - linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising); + mii_adv_mod_linkmode_adv_t(advertising, adv); +} + +/** + * mii_lpa_to_linkmode_lpa_t + * @adv: value of the MII_LPA register + * + * A small helper function that translates MII_LPA bits, when in + * 1000Base-T mode, to linkmode LP advertisement settings. Clears the + * old value of advertising + */ +static inline void mii_lpa_to_linkmode_lpa_t(unsigned long *lp_advertising, + u32 lpa) +{ + mii_adv_to_linkmode_adv_t(lp_advertising, lpa); + + if (lpa & LPA_LPACK) + linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + lp_advertising); + +} + +/** + * mii_lpa_mod_linkmode_lpa_t + * @adv: value of the MII_LPA register + * + * A small helper function that translates MII_LPA bits, when in + * 1000Base-T mode, to linkmode LP advertisement settings. Leaves + * other bits unchanged. + */ +static inline void mii_lpa_mod_linkmode_lpa_t(unsigned long *lp_advertising, + u32 lpa) +{ + mii_adv_mod_linkmode_adv_t(lp_advertising, lpa); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + lp_advertising, lpa & LPA_LPACK); } /** - * ethtool_adv_to_lcl_adv_t - * @advertising:pointer to ethtool advertising + * linkmode_adv_to_lcl_adv_t + * @advertising:pointer to linkmode advertising * - * A small helper function that translates ethtool advertising to LVL + * A small helper function that translates linkmode advertising to LVL * pause capabilities. */ -static inline u32 ethtool_adv_to_lcl_adv_t(u32 advertising) +static inline u32 linkmode_adv_to_lcl_adv_t(unsigned long *advertising) { u32 lcl_adv = 0; - if (advertising & ADVERTISED_Pause) + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, + advertising)) lcl_adv |= ADVERTISE_PAUSE_CAP; - if (advertising & ADVERTISED_Asym_Pause) + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, + advertising)) lcl_adv |= ADVERTISE_PAUSE_ASYM; return lcl_adv; diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index dca6ab4eaa99..36e412c3d657 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -226,6 +226,7 @@ enum { MLX4_DEV_CAP_FLAG2_SL_TO_VL_CHANGE_EVENT = 1ULL << 37, MLX4_DEV_CAP_FLAG2_USER_MAC_EN = 1ULL << 38, MLX4_DEV_CAP_FLAG2_DRIVER_VERSION_TO_FW = 1ULL << 39, + MLX4_DEV_CAP_FLAG2_SW_CQ_INIT = 1ULL << 40, }; enum { @@ -1136,7 +1137,8 @@ void mlx4_free_hwq_res(struct mlx4_dev *mdev, struct mlx4_hwq_resources *wqres, int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt, struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq, - unsigned vector, int collapsed, int timestamp_en); + unsigned int vector, int collapsed, int timestamp_en, + void *buf_addr, bool user_cq); void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq); int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base, u8 flags, u8 usage); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 857f8abf7b91..fc6ba71513be 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -845,6 +845,8 @@ enum tc_setup_type { TC_SETUP_QDISC_PRIO, TC_SETUP_QDISC_MQ, TC_SETUP_QDISC_ETF, + TC_SETUP_ROOT_QDISC, + TC_SETUP_QDISC_GRED, }; /* These structures hold the attributes of bpf state that are being passed @@ -863,9 +865,6 @@ enum bpf_netdev_command { XDP_QUERY_PROG, XDP_QUERY_PROG_HW, /* BPF program for offload callbacks, invoked at program load time. */ - BPF_OFFLOAD_VERIFIER_PREP, - BPF_OFFLOAD_TRANSLATE, - BPF_OFFLOAD_DESTROY, BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, XDP_QUERY_XSK_UMEM, @@ -891,15 +890,6 @@ struct netdev_bpf { /* flags with which program was installed */ u32 prog_flags; }; - /* BPF_OFFLOAD_VERIFIER_PREP */ - struct { - struct bpf_prog *prog; - const struct bpf_prog_offload_ops *ops; /* callee set */ - } verifier; - /* BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY */ - struct { - struct bpf_prog *prog; - } offload; /* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */ struct { struct bpf_offloaded_map *offmap; @@ -2388,13 +2378,13 @@ struct pcpu_sw_netstats { u64 tx_packets; u64 tx_bytes; struct u64_stats_sync syncp; -}; +} __aligned(4 * sizeof(u64)); struct pcpu_lstats { u64 packets; u64 bytes; struct u64_stats_sync syncp; -}; +} __aligned(2 * sizeof(u64)); #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ @@ -2615,7 +2605,7 @@ struct net_device *dev_get_by_name(struct net *net, const char *name); struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); struct net_device *__dev_get_by_name(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); -int dev_open(struct net_device *dev); +int dev_open(struct net_device *dev, struct netlink_ext_ack *extack); void dev_close(struct net_device *dev); void dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); @@ -3224,6 +3214,14 @@ static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes) netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes); } +static inline bool __netdev_sent_queue(struct net_device *dev, + unsigned int bytes, + bool xmit_more) +{ + return __netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes, + xmit_more); +} + static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, unsigned int pkts, unsigned int bytes) { @@ -3613,8 +3611,10 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, int dev_ifconf(struct net *net, struct ifconf *, int); int dev_ethtool(struct net *net, struct ifreq *); unsigned int dev_get_flags(const struct net_device *); -int __dev_change_flags(struct net_device *, unsigned int flags); -int dev_change_flags(struct net_device *, unsigned int); +int __dev_change_flags(struct net_device *dev, unsigned int flags, + struct netlink_ext_ack *extack); +int dev_change_flags(struct net_device *dev, unsigned int flags, + struct netlink_ext_ack *extack); void __dev_notify_flags(struct net_device *, unsigned int old_flags, unsigned int gchanges); int dev_change_name(struct net_device *, const char *); @@ -4068,6 +4068,16 @@ int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *)); +int __hw_addr_ref_sync_dev(struct netdev_hw_addr_list *list, + struct net_device *dev, + int (*sync)(struct net_device *, + const unsigned char *, int), + int (*unsync)(struct net_device *, + const unsigned char *, int)); +void __hw_addr_ref_unsync_dev(struct netdev_hw_addr_list *list, + struct net_device *dev, + int (*unsync)(struct net_device *, + const unsigned char *, int)); void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, @@ -4332,9 +4342,10 @@ static inline bool can_checksum_protocol(netdev_features_t features, } #ifdef CONFIG_BUG -void netdev_rx_csum_fault(struct net_device *dev); +void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb); #else -static inline void netdev_rx_csum_fault(struct net_device *dev) +static inline void netdev_rx_csum_fault(struct net_device *dev, + struct sk_buff *skb) { } #endif @@ -4360,7 +4371,7 @@ static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_devi struct netdev_queue *txq, bool more) { const struct net_device_ops *ops = dev->netdev_ops; - int rc; + netdev_tx_t rc; rc = __netdev_start_xmit(ops, skb, dev, more); if (rc == NETDEV_TX_OK) diff --git a/include/linux/objagg.h b/include/linux/objagg.h new file mode 100644 index 000000000000..34f38c186ea0 --- /dev/null +++ b/include/linux/objagg.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ +/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */ + +#ifndef _OBJAGG_H +#define _OBJAGG_H + +struct objagg_ops { + size_t obj_size; + void * (*delta_create)(void *priv, void *parent_obj, void *obj); + void (*delta_destroy)(void *priv, void *delta_priv); + void * (*root_create)(void *priv, void *obj); + void (*root_destroy)(void *priv, void *root_priv); +}; + +struct objagg; +struct objagg_obj; + +const void *objagg_obj_root_priv(const struct objagg_obj *objagg_obj); +const void *objagg_obj_delta_priv(const struct objagg_obj *objagg_obj); +const void *objagg_obj_raw(const struct objagg_obj *objagg_obj); + +struct objagg_obj *objagg_obj_get(struct objagg *objagg, void *obj); +void objagg_obj_put(struct objagg *objagg, struct objagg_obj *objagg_obj); +struct objagg *objagg_create(const struct objagg_ops *ops, void *priv); +void objagg_destroy(struct objagg *objagg); + +struct objagg_obj_stats { + unsigned int user_count; + unsigned int delta_user_count; /* includes delta object users */ +}; + +struct objagg_obj_stats_info { + struct objagg_obj_stats stats; + struct objagg_obj *objagg_obj; /* associated object */ + bool is_root; +}; + +struct objagg_stats { + unsigned int stats_info_count; + struct objagg_obj_stats_info stats_info[]; +}; + +const struct objagg_stats *objagg_stats_get(struct objagg *objagg); +void objagg_stats_put(const struct objagg_stats *objagg_stats); + +#endif diff --git a/include/linux/of_net.h b/include/linux/of_net.h index 90d81ee9e6a0..9cd72aab76fe 100644 --- a/include/linux/of_net.h +++ b/include/linux/of_net.h @@ -13,7 +13,6 @@ struct net_device; extern int of_get_phy_mode(struct device_node *np); extern const void *of_get_mac_address(struct device_node *np); -extern int of_get_nvmem_mac_address(struct device_node *np, void *addr); extern struct net_device *of_find_net_device_by_node(struct device_node *np); #else static inline int of_get_phy_mode(struct device_node *np) @@ -26,11 +25,6 @@ static inline const void *of_get_mac_address(struct device_node *np) return NULL; } -static inline int of_get_nvmem_mac_address(struct device_node *np, void *addr) -{ - return -ENODEV; -} - static inline struct net_device *of_find_net_device_by_node(struct device_node *np) { return NULL; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 69f0abe1ba1a..144de2e89531 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2359,6 +2359,8 @@ #define PCI_VENDOR_ID_SYNOPSYS 0x16c3 +#define PCI_VENDOR_ID_USR 0x16ec + #define PCI_VENDOR_ID_VITESSE 0x1725 #define PCI_DEVICE_ID_VITESSE_VSC7174 0x7174 diff --git a/include/linux/phy.h b/include/linux/phy.h index 3ea87f774a76..8f927246acdb 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -58,6 +58,11 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_ini #define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features) #define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features) +extern const int phy_10_100_features_array[4]; +extern const int phy_basic_t1_features_array[2]; +extern const int phy_gbit_features_array[2]; +extern const int phy_10gbit_features_array[1]; + /* * Set phydev->irq to PHY_POLL if interrupts are not supported, * or not desired for this PHY. Set to PHY_IGNORE_INTERRUPT if @@ -66,9 +71,8 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_ini #define PHY_POLL -1 #define PHY_IGNORE_INTERRUPT -2 -#define PHY_HAS_INTERRUPT 0x00000001 -#define PHY_IS_INTERNAL 0x00000002 -#define PHY_RST_AFTER_CLK_EN 0x00000004 +#define PHY_IS_INTERNAL 0x00000001 +#define PHY_RST_AFTER_CLK_EN 0x00000002 #define MDIO_DEVICE_IS_PHY 0x80000000 /* Interface Mode definitions */ @@ -178,7 +182,6 @@ static inline const char *phy_modes(phy_interface_t interface) #define PHY_INIT_TIMEOUT 100000 #define PHY_STATE_TIME 1 #define PHY_FORCE_TIMEOUT 10 -#define PHY_AN_TIMEOUT 10 #define PHY_MAX_ADDR 32 @@ -264,57 +267,27 @@ static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) void devm_mdiobus_free(struct device *dev, struct mii_bus *bus); struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); -#define PHY_INTERRUPT_DISABLED 0x0 -#define PHY_INTERRUPT_ENABLED 0x80000000 +#define PHY_INTERRUPT_DISABLED false +#define PHY_INTERRUPT_ENABLED true /* PHY state machine states: * * DOWN: PHY device and driver are not ready for anything. probe * should be called if and only if the PHY is in this state, * given that the PHY device exists. - * - PHY driver probe function will, depending on the PHY, set - * the state to STARTING or READY - * - * STARTING: PHY device is coming up, and the ethernet driver is - * not ready. PHY drivers may set this in the probe function. - * If they do, they are responsible for making sure the state is - * eventually set to indicate whether the PHY is UP or READY, - * depending on the state when the PHY is done starting up. - * - PHY driver will set the state to READY - * - start will set the state to PENDING + * - PHY driver probe function will set the state to READY * * READY: PHY is ready to send and receive packets, but the * controller is not. By default, PHYs which do not implement - * probe will be set to this state by phy_probe(). If the PHY - * driver knows the PHY is ready, and the PHY state is STARTING, - * then it sets this STATE. + * probe will be set to this state by phy_probe(). * - start will set the state to UP * - * PENDING: PHY device is coming up, but the ethernet driver is - * ready. phy_start will set this state if the PHY state is - * STARTING. - * - PHY driver will set the state to UP when the PHY is ready - * * UP: The PHY and attached device are ready to do work. * Interrupts should be started here. - * - timer moves to AN - * - * AN: The PHY is currently negotiating the link state. Link is - * therefore down for now. phy_timer will set this state when it - * detects the state is UP. config_aneg will set this state - * whenever called with phydev->autoneg set to AUTONEG_ENABLE. - * - If autonegotiation finishes, but there's no link, it sets - * the state to NOLINK. - * - If aneg finishes with link, it sets the state to RUNNING, - * and calls adjust_link - * - If autonegotiation did not finish after an arbitrary amount - * of time, autonegotiation should be tried again if the PHY - * supports "magic" autonegotiation (back to AN) - * - If it didn't finish, and no magic_aneg, move to FORCING. + * - timer moves to NOLINK or RUNNING * * NOLINK: PHY is up, but not currently plugged in. - * - If the timer notes that the link comes back, we move to RUNNING - * - config_aneg moves to AN + * - irq or timer will set RUNNING if link comes back * - phy_stop moves to HALTED * * FORCING: PHY is being configured with forced settings @@ -325,11 +298,7 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); * * RUNNING: PHY is currently up, running, and possibly sending * and/or receiving packets - * - timer will set CHANGELINK if we're polling (this ensures the - * link state is polled every other cycle of this state machine, - * which makes it every other second) - * - irq will set CHANGELINK - * - config_aneg will set AN + * - irq or timer will set NOLINK if link goes down * - phy_stop moves to HALTED * * CHANGELINK: PHY experienced a change in link state @@ -349,11 +318,8 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); */ enum phy_state { PHY_DOWN = 0, - PHY_STARTING, PHY_READY, - PHY_PENDING, PHY_UP, - PHY_AN, PHY_RUNNING, PHY_NOLINK, PHY_FORCING, @@ -390,7 +356,6 @@ struct phy_c45_device_ids { * giving up on the current attempt at acquiring a link * irq: IRQ number of the PHY's interrupt (-1 if none) * phy_timer: The timer for handling the state machine - * phy_queue: A work_queue for the phy_mac_interrupt * attached_dev: The attached enet driver's device instance ptr * adjust_link: Callback for the enet controller to respond to * changes in the link state. @@ -427,6 +392,9 @@ struct phy_device { /* The most recently read link state */ unsigned link:1; + /* Interrupts are enabled */ + unsigned interrupts:1; + enum phy_state state; u32 dev_flags; @@ -442,14 +410,11 @@ struct phy_device { int pause; int asym_pause; - /* Enabled Interrupts */ - u32 interrupts; - - /* Union of PHY and Attached devices' supported modes */ - /* See mii.h for more info */ - u32 supported; - u32 advertising; - u32 lp_advertising; + /* Union of PHY and Attached devices' supported link modes */ + /* See ethtool.h for more info */ + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); + __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); /* Energy efficient ethernet modes which should be prohibited */ u32 eee_broken_modes; @@ -475,7 +440,6 @@ struct phy_device { void *priv; /* Interrupt and Polling infrastructure */ - struct work_struct phy_queue; struct delayed_work state_queue; struct mutex lock; @@ -674,6 +638,10 @@ struct phy_driver { #define PHY_ANY_ID "MATCH ANY PHY" #define PHY_ANY_UID 0xffffffff +#define PHY_ID_MATCH_EXACT(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 0) +#define PHY_ID_MATCH_MODEL(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 4) +#define PHY_ID_MATCH_VENDOR(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 10) + /* A Structure for boards to register fixups with the PHY Lib */ struct phy_fixup { struct list_head list; @@ -697,9 +665,9 @@ struct phy_setting { const struct phy_setting * phy_lookup_setting(int speed, int duplex, const unsigned long *mask, - size_t maxbit, bool exact); + bool exact); size_t phy_speeds(unsigned int *speeds, size_t size, - unsigned long *mask, size_t maxbit); + unsigned long *mask); void phy_resolve_aneg_linkmode(struct phy_device *phydev); @@ -1050,11 +1018,9 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner); int phy_drivers_register(struct phy_driver *new_driver, int n, struct module *owner); void phy_state_machine(struct work_struct *work); -void phy_change_work(struct work_struct *work); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); -void phy_trigger_machine(struct phy_device *phydev); int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); void phy_ethtool_ksettings_get(struct phy_device *phydev, struct ethtool_link_ksettings *cmd); diff --git a/include/linux/phy_led_triggers.h b/include/linux/phy_led_triggers.h index b37b05bfd1a6..4587ce362535 100644 --- a/include/linux/phy_led_triggers.h +++ b/include/linux/phy_led_triggers.h @@ -20,7 +20,7 @@ struct phy_device; #include <linux/leds.h> #include <linux/phy.h> -#define PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE 10 +#define PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE 11 #define PHY_LINK_LED_TRIGGER_NAME_SIZE (MII_BUS_ID_SIZE + \ FIELD_SIZEOF(struct mdio_device, addr)+\ diff --git a/include/linux/platform_data/mdio-gpio.h b/include/linux/platform_data/mdio-gpio.h new file mode 100644 index 000000000000..13874fa6e767 --- /dev/null +++ b/include/linux/platform_data/mdio-gpio.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * MDIO-GPIO bus platform data structure + */ + +#ifndef __LINUX_MDIO_GPIO_PDATA_H +#define __LINUX_MDIO_GPIO_PDATA_H + +struct mdio_gpio_platform_data { + u32 phy_mask; + u32 phy_ignore_ta_mask; +}; + +#endif /* __LINUX_MDIO_GPIO_PDATA_H */ diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 51349d124ee5..7121bbe76979 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -39,6 +39,15 @@ struct ptp_clock_request { }; struct system_device_crosststamp; + +/** + * struct ptp_system_timestamp - system time corresponding to a PHC timestamp + */ +struct ptp_system_timestamp { + struct timespec64 pre_ts; + struct timespec64 post_ts; +}; + /** * struct ptp_clock_info - decribes a PTP hardware clock * @@ -73,8 +82,18 @@ struct system_device_crosststamp; * parameter delta: Desired change in nanoseconds. * * @gettime64: Reads the current time from the hardware clock. + * This method is deprecated. New drivers should implement + * the @gettimex64 method instead. * parameter ts: Holds the result. * + * @gettimex64: Reads the current time from the hardware clock and optionally + * also the system clock. + * parameter ts: Holds the PHC timestamp. + * parameter sts: If not NULL, it holds a pair of timestamps from + * the system clock. The first reading is made right before + * reading the lowest bits of the PHC timestamp and the second + * reading immediately follows that. + * * @getcrosststamp: Reads the current time from the hardware clock and * system clock simultaneously. * parameter cts: Contains timestamp (device,system) pair, @@ -124,6 +143,8 @@ struct ptp_clock_info { int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta); int (*adjtime)(struct ptp_clock_info *ptp, s64 delta); int (*gettime64)(struct ptp_clock_info *ptp, struct timespec64 *ts); + int (*gettimex64)(struct ptp_clock_info *ptp, struct timespec64 *ts, + struct ptp_system_timestamp *sts); int (*getcrosststamp)(struct ptp_clock_info *ptp, struct system_device_crosststamp *cts); int (*settime64)(struct ptp_clock_info *p, const struct timespec64 *ts); @@ -247,4 +268,16 @@ static inline int ptp_schedule_worker(struct ptp_clock *ptp, #endif +static inline void ptp_read_system_prets(struct ptp_system_timestamp *sts) +{ + if (sts) + ktime_get_real_ts64(&sts->pre_ts); +} + +static inline void ptp_read_system_postts(struct ptp_system_timestamp *sts) +{ + if (sts) + ktime_get_real_ts64(&sts->post_ts); +} + #endif diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index a47321a0d572..91c536a01b56 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -47,6 +47,7 @@ #include <linux/slab.h> #include <linux/qed/common_hsi.h> #include <linux/qed/qed_chain.h> +#include <linux/io-64-nonatomic-lo-hi.h> enum dcbx_protocol_type { DCBX_PROTOCOL_ISCSI, @@ -448,11 +449,24 @@ struct qed_mfw_tlv_iscsi { bool tx_bytes_set; }; +enum qed_db_rec_width { + DB_REC_WIDTH_32B, + DB_REC_WIDTH_64B, +}; + +enum qed_db_rec_space { + DB_REC_KERNEL, + DB_REC_USER, +}; + #define DIRECT_REG_WR(reg_addr, val) writel((u32)val, \ (void __iomem *)(reg_addr)) #define DIRECT_REG_RD(reg_addr) readl((void __iomem *)(reg_addr)) +#define DIRECT_REG_WR64(reg_addr, val) writeq((u32)val, \ + (void __iomem *)(reg_addr)) + #define QED_COALESCE_MAX 0x1FF #define QED_DEFAULT_RX_USECS 12 #define QED_DEFAULT_TX_USECS 48 @@ -1015,6 +1029,33 @@ struct qed_common_ops { */ int (*set_led)(struct qed_dev *cdev, enum qed_led_mode mode); +/** + * @brief db_recovery_add - add doorbell information to the doorbell + * recovery mechanism. + * + * @param cdev + * @param db_addr - doorbell address + * @param db_data - address of where db_data is stored + * @param db_is_32b - doorbell is 32b pr 64b + * @param db_is_user - doorbell recovery addresses are user or kernel space + */ + int (*db_recovery_add)(struct qed_dev *cdev, + void __iomem *db_addr, + void *db_data, + enum qed_db_rec_width db_width, + enum qed_db_rec_space db_space); + +/** + * @brief db_recovery_del - remove doorbell information from the doorbell + * recovery mechanism. db_data serves as key (db_addr is not unique). + * + * @param cdev + * @param db_addr - doorbell address + * @param db_data - address where db_data is stored. Serves as key for the + * entry to delete. + */ + int (*db_recovery_del)(struct qed_dev *cdev, + void __iomem *db_addr, void *db_data); /** * @brief update_drv_state - API to inform the change in the driver state. diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index eb7111039247..20f9c6af7473 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -75,8 +75,19 @@ struct bucket_table { struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; +/* + * NULLS_MARKER() expects a hash value with the low + * bits mostly likely to be significant, and it discards + * the msb. + * We git it an address, in which the bottom 2 bits are + * always 0, and the msb might be significant. + * So we shift the address down one bit to align with + * expectations and avoid losing a significant bit. + */ +#define RHT_NULLS_MARKER(ptr) \ + ((void *)NULLS_MARKER(((unsigned long) (ptr)) >> 1)) #define INIT_RHT_NULLS_HEAD(ptr) \ - ((ptr) = (typeof(ptr)) NULLS_MARKER(0)) + ((ptr) = RHT_NULLS_MARKER(&(ptr))) static inline bool rht_is_a_nulls(const struct rhash_head *ptr) { @@ -471,6 +482,7 @@ static inline struct rhash_head *__rhashtable_lookup( .ht = ht, .key = key, }; + struct rhash_head __rcu * const *head; struct bucket_table *tbl; struct rhash_head *he; unsigned int hash; @@ -478,13 +490,19 @@ static inline struct rhash_head *__rhashtable_lookup( tbl = rht_dereference_rcu(ht->tbl, ht); restart: hash = rht_key_hashfn(ht, tbl, key, params); - rht_for_each_rcu(he, tbl, hash) { - if (params.obj_cmpfn ? - params.obj_cmpfn(&arg, rht_obj(ht, he)) : - rhashtable_compare(&arg, rht_obj(ht, he))) - continue; - return he; - } + head = rht_bucket(tbl, hash); + do { + rht_for_each_rcu_continue(he, *head, tbl, hash) { + if (params.obj_cmpfn ? + params.obj_cmpfn(&arg, rht_obj(ht, he)) : + rhashtable_compare(&arg, rht_obj(ht, he))) + continue; + return he; + } + /* An object might have been moved to a different hash chain, + * while we walk along it - better check and retry. + */ + } while (he != RHT_NULLS_MARKER(head)); /* Ensure we see any new tables. */ smp_rmb(); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0d1b2c3f127b..b1831a5ca173 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -481,10 +481,11 @@ static inline void sock_zerocopy_get(struct ubuf_info *uarg) } void sock_zerocopy_put(struct ubuf_info *uarg); -void sock_zerocopy_put_abort(struct ubuf_info *uarg); +void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); void sock_zerocopy_callback(struct ubuf_info *uarg, bool success); +int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len); int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg); @@ -615,6 +616,8 @@ typedef unsigned char *sk_buff_data_t; * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs + * @offload_fwd_mark: Packet was L2-forwarded in hardware + * @offload_l3_fwd_mark: Packet was L3-forwarded in hardware * @tc_skip_classify: do not classify packet. set by IFB device * @tc_at_ingress: used within tc_classify to distinguish in/egress * @tc_redirected: packet was redirected by a tc action @@ -777,6 +780,14 @@ struct sk_buff { __u8 encap_hdr_csum:1; __u8 csum_valid:1; +#ifdef __BIG_ENDIAN_BITFIELD +#define PKT_VLAN_PRESENT_BIT 7 +#else +#define PKT_VLAN_PRESENT_BIT 0 +#endif +#define PKT_VLAN_PRESENT_OFFSET() offsetof(struct sk_buff, __pkt_vlan_present_offset) + __u8 __pkt_vlan_present_offset[0]; + __u8 vlan_present:1; __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 csum_not_inet:1; @@ -784,13 +795,13 @@ struct sk_buff { #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif - __u8 ipvs_property:1; + __u8 ipvs_property:1; __u8 inner_protocol_type:1; __u8 remcsum_offload:1; #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; - __u8 offload_mr_fwd_mark:1; + __u8 offload_l3_fwd_mark:1; #endif #ifdef CONFIG_NET_CLS_ACT __u8 tc_skip_classify:1; @@ -1317,10 +1328,14 @@ static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) return is_zcopy ? skb_uarg(skb) : NULL; } -static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg) +static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, + bool *have_ref) { if (skb && uarg && !skb_zcopy(skb)) { - sock_zerocopy_get(uarg); + if (unlikely(have_ref && *have_ref)) + *have_ref = false; + else + sock_zerocopy_get(uarg); skb_shinfo(skb)->destructor_arg = uarg; skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; } @@ -1365,7 +1380,7 @@ static inline void skb_zcopy_abort(struct sk_buff *skb) struct ubuf_info *uarg = skb_zcopy(skb); if (uarg) { - sock_zerocopy_put_abort(uarg); + sock_zerocopy_put_abort(uarg, false); skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; } } @@ -1741,8 +1756,6 @@ static inline void skb_queue_head_init_class(struct sk_buff_head *list, * The "__skb_xxxx()" functions are the non-atomic ones that * can only be called with interrupts disabled. */ -void skb_insert(struct sk_buff *old, struct sk_buff *newsk, - struct sk_buff_head *list); static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) @@ -2524,10 +2537,8 @@ int ___pskb_trim(struct sk_buff *skb, unsigned int len); static inline void __skb_set_length(struct sk_buff *skb, unsigned int len) { - if (unlikely(skb_is_nonlinear(skb))) { - WARN_ON(1); + if (WARN_ON(skb_is_nonlinear(skb))) return; - } skb->len = len; skb_set_tail_pointer(skb, len); } @@ -3345,7 +3356,6 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, unsigned int flags); int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len); -int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, diff --git a/include/linux/udp.h b/include/linux/udp.h index 320d49d85484..2725c83395bf 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -49,7 +49,13 @@ struct udp_sock { unsigned int corkflag; /* Cork is required */ __u8 encap_type; /* Is this an Encapsulation socket? */ unsigned char no_check6_tx:1,/* Send zero UDP6 checksums on TX? */ - no_check6_rx:1;/* Allow zero UDP6 checksums on RX? */ + no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */ + encap_enabled:1, /* This socket enabled encap + * processing; UDP tunnels and + * different encapsulation layer set + * this + */ + gro_enabled:1; /* Can accept GRO packets */ /* * Following member retains the information to create a UDP header * when the socket is uncorked. @@ -71,6 +77,7 @@ struct udp_sock { * For encapsulation sockets. */ int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); + int (*encap_err_lookup)(struct sock *sk, struct sk_buff *skb); void (*encap_destroy)(struct sock *sk); /* GRO functions for UDP socket */ @@ -115,6 +122,23 @@ static inline bool udp_get_no_check6_rx(struct sock *sk) return udp_sk(sk)->no_check6_rx; } +static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) +{ + int gso_size; + + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) { + gso_size = skb_shinfo(skb)->gso_size; + put_cmsg(msg, SOL_UDP, UDP_GRO, sizeof(gso_size), &gso_size); + } +} + +static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) +{ + return !udp_sk(sk)->gro_enabled && skb_is_gso(skb) && + skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4; +} + #define udp_portaddr_for_each_entry(__sk, list) \ hlist_for_each_entry(__sk, list, __sk_common.skc_portaddr_node) diff --git a/include/net/devlink.h b/include/net/devlink.h index 45db0c79462d..67f4293bc970 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -365,6 +365,7 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_IGNORE_ARI, DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, + DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, @@ -392,6 +393,9 @@ enum devlink_param_generic_id { #define DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_NAME "msix_vec_per_pf_min" #define DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_TYPE DEVLINK_PARAM_TYPE_U32 +#define DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_NAME "fw_load_policy" +#define DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_TYPE DEVLINK_PARAM_TYPE_U8 + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ diff --git a/include/net/dsa.h b/include/net/dsa.h index 23690c44e167..6ee2e24e0a6e 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -113,6 +113,7 @@ struct dsa_device_ops { struct packet_type *pt); int (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); + unsigned int overhead; }; struct dsa_switch_tree { diff --git a/include/net/flow.h b/include/net/flow.h index 8ce21793094e..93f2c9a0f098 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -38,8 +38,8 @@ struct flowi_common { #define FLOWI_FLAG_KNOWN_NH 0x02 #define FLOWI_FLAG_SKIP_NH_OIF 0x04 __u32 flowic_secid; - struct flowi_tunnel flowic_tun_key; kuid_t flowic_uid; + struct flowi_tunnel flowic_tun_key; }; union flowi_uli { diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 6a4586dcdede..2b26979efb48 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -209,8 +209,8 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_ETH_ADDRS, /* struct flow_dissector_key_eth_addrs */ FLOW_DISSECTOR_KEY_TIPC, /* struct flow_dissector_key_tipc */ FLOW_DISSECTOR_KEY_ARP, /* struct flow_dissector_key_arp */ - FLOW_DISSECTOR_KEY_VLAN, /* struct flow_dissector_key_flow_vlan */ - FLOW_DISSECTOR_KEY_FLOW_LABEL, /* struct flow_dissector_key_flow_tags */ + FLOW_DISSECTOR_KEY_VLAN, /* struct flow_dissector_key_vlan */ + FLOW_DISSECTOR_KEY_FLOW_LABEL, /* struct flow_dissector_key_tags */ FLOW_DISSECTOR_KEY_GRE_KEYID, /* struct flow_dissector_key_keyid */ FLOW_DISSECTOR_KEY_MPLS_ENTROPY, /* struct flow_dissector_key_keyid */ FLOW_DISSECTOR_KEY_ENC_KEYID, /* struct flow_dissector_key_keyid */ @@ -221,7 +221,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_MPLS, /* struct flow_dissector_key_mpls */ FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */ FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */ - FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_flow_vlan */ + FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_vlan */ FLOW_DISSECTOR_KEY_ENC_IP, /* struct flow_dissector_key_ip */ FLOW_DISSECTOR_KEY_ENC_OPTS, /* struct flow_dissector_key_enc_opts */ diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 946bd53a9f81..ca23860adbb9 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -10,7 +10,7 @@ struct gnet_stats_basic_cpu { struct gnet_stats_basic_packed bstats; struct u64_stats_sync syncp; -}; +} __aligned(2 * sizeof(u64)); struct net_rate_estimator; diff --git a/include/net/geneve.h b/include/net/geneve.h index a7600ed55ea3..fc6a7e0a874a 100644 --- a/include/net/geneve.h +++ b/include/net/geneve.h @@ -60,6 +60,12 @@ struct genevehdr { struct geneve_opt options[]; }; +static inline bool netif_is_geneve(const struct net_device *dev) +{ + return dev->rtnl_link_ops && + !strcmp(dev->rtnl_link_ops->kind, "geneve"); +} + #ifdef CONFIG_INET struct net_device *geneve_dev_create_fb(struct net *net, const char *name, u8 name_assign_type, u16 dst_port); diff --git a/include/net/icmp.h b/include/net/icmp.h index 3ef2743a8eec..6ac3a5bd0117 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -41,7 +41,7 @@ struct net; void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info); int icmp_rcv(struct sk_buff *skb); -void icmp_err(struct sk_buff *skb, u32 info); +int icmp_err(struct sk_buff *skb, u32 info); int icmp_init(void); void icmp_out_count(struct net *net, unsigned char type); diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 6e91e38a31da..9db98af46985 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -115,9 +115,8 @@ int inet6_hash(struct sock *sk); ((__sk)->sk_family == AF_INET6) && \ ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr)) && \ ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr)) && \ - (!(__sk)->sk_bound_dev_if || \ - ((__sk)->sk_bound_dev_if == (__dif)) || \ - ((__sk)->sk_bound_dev_if == (__sdif))) && \ + (((__sk)->sk_bound_dev_if == (__dif)) || \ + ((__sk)->sk_bound_dev_if == (__sdif))) && \ net_eq(sock_net(__sk), (__net))) #endif /* _INET6_HASHTABLES_H */ diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 9141e95529e7..0ce460e93dc4 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -79,6 +79,7 @@ struct inet_ehash_bucket { struct inet_bind_bucket { possible_net_t ib_net; + int l3mdev; unsigned short port; signed char fastreuse; signed char fastreuseport; @@ -188,10 +189,21 @@ static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo) hashinfo->ehash_locks = NULL; } +static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if, + int dif, int sdif) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + return inet_bound_dev_eq(!!net->ipv4.sysctl_tcp_l3mdev_accept, + bound_dev_if, dif, sdif); +#else + return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); +#endif +} + struct inet_bind_bucket * inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net, struct inet_bind_hashbucket *head, - const unsigned short snum); + const unsigned short snum, int l3mdev); void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb); @@ -282,9 +294,8 @@ static inline struct sock *inet_lookup_listener(struct net *net, #define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \ (((__sk)->sk_portpair == (__ports)) && \ ((__sk)->sk_addrpair == (__cookie)) && \ - (!(__sk)->sk_bound_dev_if || \ - ((__sk)->sk_bound_dev_if == (__dif)) || \ - ((__sk)->sk_bound_dev_if == (__sdif))) && \ + (((__sk)->sk_bound_dev_if == (__dif)) || \ + ((__sk)->sk_bound_dev_if == (__sdif))) && \ net_eq(sock_net(__sk), (__net))) #else /* 32-bit arch */ #define INET_ADDR_COOKIE(__name, __saddr, __daddr) \ @@ -294,9 +305,8 @@ static inline struct sock *inet_lookup_listener(struct net *net, (((__sk)->sk_portpair == (__ports)) && \ ((__sk)->sk_daddr == (__saddr)) && \ ((__sk)->sk_rcv_saddr == (__daddr)) && \ - (!(__sk)->sk_bound_dev_if || \ - ((__sk)->sk_bound_dev_if == (__dif)) || \ - ((__sk)->sk_bound_dev_if == (__sdif))) && \ + (((__sk)->sk_bound_dev_if == (__dif)) || \ + ((__sk)->sk_bound_dev_if == (__sdif))) && \ net_eq(sock_net(__sk), (__net))) #endif /* 64-bit arch */ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index a80fd0ac4563..e8eef85006aa 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -130,6 +130,27 @@ static inline int inet_request_bound_dev_if(const struct sock *sk, return sk->sk_bound_dev_if; } +static inline int inet_sk_bound_l3mdev(const struct sock *sk) +{ +#ifdef CONFIG_NET_L3_MASTER_DEV + struct net *net = sock_net(sk); + + if (!net->ipv4.sysctl_tcp_l3mdev_accept) + return l3mdev_master_ifindex_by_index(net, + sk->sk_bound_dev_if); +#endif + + return 0; +} + +static inline bool inet_bound_dev_eq(bool l3mdev_accept, int bound_dev_if, + int dif, int sdif) +{ + if (!bound_dev_if) + return !sdif || l3mdev_accept; + return bound_dev_if == dif || bound_dev_if == sdif; +} + struct inet_cork { unsigned int flags; __be32 addr; diff --git a/include/net/ip.h b/include/net/ip.h index 72593e171d14..8866bfce6121 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -155,6 +155,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, void ip_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *orig_dev); int ip_local_deliver(struct sk_buff *skb); +void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int proto); int ip_mr_input(struct sk_buff *skb); int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb); @@ -421,7 +422,8 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk, } struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx, - int fc_mx_len); + int fc_mx_len, + struct netlink_ext_ack *extack); static inline void ip_fib_metrics_put(struct dst_metrics *fib_metrics) { if (fib_metrics != &dst_default_metrics && diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 236e40ba06bf..69b4bcf880c9 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -69,6 +69,8 @@ struct ip6_tnl_encap_ops { size_t (*encap_hlen)(struct ip_tunnel_encap *e); int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, struct flowi6 *fl6); + int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info); }; #ifdef CONFIG_INET diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index b0d022ff6ea1..db6b2218a2ad 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -311,6 +311,7 @@ struct ip_tunnel_encap_ops { size_t (*encap_hlen)(struct ip_tunnel_encap *e); int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, struct flowi4 *fl4); + int (*err_handler)(struct sk_buff *skb, u32 info); }; #define MAX_IPTUN_ENCAP_OPS 8 diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 829650540780..daf80863d3a5 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -975,6 +975,8 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); +void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr, + bool have_final); int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 3832099289c5..78fa0ac4613c 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -101,6 +101,17 @@ struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev) return master; } +int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex); +static inline +int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex) +{ + rcu_read_lock(); + ifindex = l3mdev_master_upper_ifindex_by_index_rcu(net, ifindex); + rcu_read_unlock(); + + return ifindex; +} + u32 l3mdev_fib_table_rcu(const struct net_device *dev); u32 l3mdev_fib_table_by_index(struct net *net, int ifindex); static inline u32 l3mdev_fib_table(const struct net_device *dev) @@ -208,6 +219,17 @@ static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) } static inline +int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) +{ + return 0; +} +static inline +int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex) +{ + return 0; +} + +static inline struct net_device *l3mdev_master_dev_rcu(const struct net_device *dev) { return NULL; diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 665990c7dec8..f886b58956a6 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -154,6 +154,7 @@ struct neighbour { struct hh_cache hh; int (*output)(struct neighbour *, struct sk_buff *); const struct neigh_ops *ops; + struct list_head gc_list; struct rcu_head rcu; struct net_device *dev; u8 primary_key[0]; @@ -214,6 +215,8 @@ struct neigh_table { struct timer_list proxy_timer; struct sk_buff_head proxy_queue; atomic_t entries; + atomic_t gc_entries; + struct list_head gc_list; rwlock_t lock; unsigned long last_rand; struct neigh_statistics __percpu *stats; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index e47503b4e4d1..104a6669e344 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -103,6 +103,9 @@ struct netns_ipv4 { /* Shall we try to damage output packets if routing dev changes? */ int sysctl_ip_dynaddr; int sysctl_ip_early_demux; +#ifdef CONFIG_NET_L3_MASTER_DEV + int sysctl_raw_l3mdev_accept; +#endif int sysctl_tcp_early_demux; int sysctl_udp_early_demux; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 72ffb3120ced..ea191d8cfcc9 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -81,6 +81,14 @@ void __tcf_block_cb_unregister(struct tcf_block *block, struct tcf_block_cb *block_cb); void tcf_block_cb_unregister(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident); +int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, + tc_indr_block_bind_cb_t *cb, void *cb_ident); +int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, + tc_indr_block_bind_cb_t *cb, void *cb_ident); +void __tc_indr_block_cb_unregister(struct net_device *dev, + tc_indr_block_bind_cb_t *cb, void *cb_ident); +void tc_indr_block_cb_unregister(struct net_device *dev, + tc_indr_block_bind_cb_t *cb, void *cb_ident); int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode); @@ -183,6 +191,32 @@ void tcf_block_cb_unregister(struct tcf_block *block, { } +static inline +int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, + tc_indr_block_bind_cb_t *cb, void *cb_ident) +{ + return 0; +} + +static inline +int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, + tc_indr_block_bind_cb_t *cb, void *cb_ident) +{ + return 0; +} + +static inline +void __tc_indr_block_cb_unregister(struct net_device *dev, + tc_indr_block_bind_cb_t *cb, void *cb_ident) +{ +} + +static inline +void tc_indr_block_cb_unregister(struct net_device *dev, + tc_indr_block_bind_cb_t *cb, void *cb_ident) +{ +} + static inline int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode) { @@ -609,6 +643,7 @@ struct tc_cls_common_offload { struct tc_cls_u32_knode { struct tcf_exts *exts; + struct tcf_result *res; struct tc_u32_sel *sel; u32 handle; u32 val; @@ -787,12 +822,21 @@ enum tc_mq_command { TC_MQ_CREATE, TC_MQ_DESTROY, TC_MQ_STATS, + TC_MQ_GRAFT, +}; + +struct tc_mq_opt_offload_graft_params { + unsigned long queue; + u32 child_handle; }; struct tc_mq_qopt_offload { enum tc_mq_command command; u32 handle; - struct tc_qopt_offload_stats stats; + union { + struct tc_qopt_offload_stats stats; + struct tc_mq_opt_offload_graft_params graft_params; + }; }; enum tc_red_command { @@ -800,13 +844,16 @@ enum tc_red_command { TC_RED_DESTROY, TC_RED_STATS, TC_RED_XSTATS, + TC_RED_GRAFT, }; struct tc_red_qopt_offload_params { u32 min; u32 max; u32 probability; + u32 limit; bool is_ecn; + bool is_harddrop; struct gnet_stats_queue *qstats; }; @@ -818,6 +865,51 @@ struct tc_red_qopt_offload { struct tc_red_qopt_offload_params set; struct tc_qopt_offload_stats stats; struct red_stats *xstats; + u32 child_handle; + }; +}; + +enum tc_gred_command { + TC_GRED_REPLACE, + TC_GRED_DESTROY, + TC_GRED_STATS, +}; + +struct tc_gred_vq_qopt_offload_params { + bool present; + u32 limit; + u32 prio; + u32 min; + u32 max; + bool is_ecn; + bool is_harddrop; + u32 probability; + /* Only need backlog, see struct tc_prio_qopt_offload_params */ + u32 *backlog; +}; + +struct tc_gred_qopt_offload_params { + bool grio_on; + bool wred_on; + unsigned int dp_cnt; + unsigned int dp_def; + struct gnet_stats_queue *qstats; + struct tc_gred_vq_qopt_offload_params tab[MAX_DPs]; +}; + +struct tc_gred_qopt_offload_stats { + struct gnet_stats_basic_packed bstats[MAX_DPs]; + struct gnet_stats_queue qstats[MAX_DPs]; + struct red_stats *xstats[MAX_DPs]; +}; + +struct tc_gred_qopt_offload { + enum tc_gred_command command; + u32 handle; + u32 parent; + union { + struct tc_gred_qopt_offload_params set; + struct tc_gred_qopt_offload_stats stats; }; }; @@ -854,4 +946,14 @@ struct tc_prio_qopt_offload { }; }; +enum tc_root_command { + TC_ROOT_GRAFT, +}; + +struct tc_root_qopt_offload { + enum tc_root_command command; + u32 handle; + bool ingress; +}; + #endif diff --git a/include/net/protocol.h b/include/net/protocol.h index 4fc75f7ae23b..92b3eaad6088 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -42,7 +42,10 @@ struct net_protocol { int (*early_demux)(struct sk_buff *skb); int (*early_demux_handler)(struct sk_buff *skb); int (*handler)(struct sk_buff *skb); - void (*err_handler)(struct sk_buff *skb, u32 info); + + /* This returns an error if we weren't able to handle the error. */ + int (*err_handler)(struct sk_buff *skb, u32 info); + unsigned int no_policy:1, netns_ok:1, /* does the protocol do more stringent @@ -58,10 +61,12 @@ struct inet6_protocol { void (*early_demux_handler)(struct sk_buff *skb); int (*handler)(struct sk_buff *skb); - void (*err_handler)(struct sk_buff *skb, + /* This returns an error if we weren't able to handle the error. */ + int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info); + unsigned int flags; /* INET6_PROTO_xxx */ }; diff --git a/include/net/raw.h b/include/net/raw.h index 9c9fa98a91a4..821ff4887f77 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -17,7 +17,7 @@ #ifndef _RAW_H #define _RAW_H - +#include <net/inet_sock.h> #include <net/protocol.h> #include <linux/icmp.h> @@ -61,6 +61,7 @@ void raw_seq_stop(struct seq_file *seq, void *v); int raw_hash_sk(struct sock *sk); void raw_unhash_sk(struct sock *sk); +void raw_init(void); struct raw_sock { /* inet_sock has to be the first member */ @@ -74,4 +75,15 @@ static inline struct raw_sock *raw_sk(const struct sock *sk) return (struct raw_sock *)sk; } +static inline bool raw_sk_bound_dev_eq(struct net *net, int bound_dev_if, + int dif, int sdif) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + return inet_bound_dev_eq(!!net->ipv4.sysctl_raw_l3mdev_accept, + bound_dev_if, dif, sdif); +#else + return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); +#endif +} + #endif /* _RAW_H */ diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index cf26e5aacac4..e2091bb2b3a8 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -159,7 +159,8 @@ struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]); struct net_device *rtnl_create_link(struct net *net, const char *ifname, unsigned char name_assign_type, const struct rtnl_link_ops *ops, - struct nlattr *tb[]); + struct nlattr *tb[], + struct netlink_ext_ack *extack); int rtnl_delete_link(struct net_device *dev); int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 4d736427a4cb..9481f2c142e2 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -24,6 +24,9 @@ struct bpf_flow_keys; typedef int tc_setup_cb_t(enum tc_setup_type type, void *type_data, void *cb_priv); +typedef int tc_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv, + enum tc_setup_type type, void *type_data); + struct qdisc_rate_table { struct tc_ratespec rate; u32 data[256]; @@ -579,6 +582,30 @@ void qdisc_put(struct Qdisc *qdisc); void qdisc_put_unlocked(struct Qdisc *qdisc); void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n, unsigned int len); +#ifdef CONFIG_NET_SCHED +int qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type, + void *type_data); +void qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch, + struct Qdisc *new, struct Qdisc *old, + enum tc_setup_type type, void *type_data, + struct netlink_ext_ack *extack); +#else +static inline int +qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type, + void *type_data) +{ + q->flags &= ~TCQ_F_OFFLOADED; + return 0; +} + +static inline void +qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch, + struct Qdisc *new, struct Qdisc *old, + enum tc_setup_type type, void *type_data, + struct netlink_ext_ack *extack) +{ +} +#endif struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack); diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 8dadc74c22e7..4588bdc2b8f0 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -71,7 +71,7 @@ enum { SCTP_DEFAULT_INSTREAMS = SCTP_MAX_STREAM }; SCTP_NUM_AUTH_CHUNK_TYPES) /* These are the different flavours of event. */ -enum sctp_event { +enum sctp_event_type { SCTP_EVENT_T_CHUNK = 1, SCTP_EVENT_T_TIMEOUT, SCTP_EVENT_T_OTHER, diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 2abbc15824af..1d13ec3f2707 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -151,8 +151,8 @@ int sctp_primitive_RECONF(struct net *net, struct sctp_association *asoc, * sctp/input.c */ int sctp_rcv(struct sk_buff *skb); -void sctp_v4_err(struct sk_buff *skb, u32 info); -void sctp_hash_endpoint(struct sctp_endpoint *); +int sctp_v4_err(struct sk_buff *skb, u32 info); +int sctp_hash_endpoint(struct sctp_endpoint *ep); void sctp_unhash_endpoint(struct sctp_endpoint *); struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *, struct sctphdr *, struct sctp_association **, diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 9e3d32746430..24825a81829e 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -173,7 +173,7 @@ sctp_state_fn_t sctp_sf_autoclose_timer_expire; __u8 sctp_get_chunk_type(struct sctp_chunk *chunk); const struct sctp_sm_table_entry *sctp_sm_lookup_event( struct net *net, - enum sctp_event event_type, + enum sctp_event_type event_type, enum sctp_state state, union sctp_subtype event_subtype); int sctp_chunk_iif(const struct sctp_chunk *); @@ -313,7 +313,7 @@ struct sctp_chunk *sctp_process_strreset_resp( /* Prototypes for statetable processing. */ -int sctp_do_sm(struct net *net, enum sctp_event event_type, +int sctp_do_sm(struct net *net, enum sctp_event_type event_type, union sctp_subtype subtype, enum sctp_state state, struct sctp_endpoint *ep, struct sctp_association *asoc, void *event_arg, gfp_t gfp); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index feada358d872..003020eb6e66 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -96,7 +96,9 @@ struct sctp_stream; struct sctp_bind_bucket { unsigned short port; - unsigned short fastreuse; + signed char fastreuse; + signed char fastreuseport; + kuid_t fastuid; struct hlist_node node; struct hlist_head owner; struct net *net; @@ -215,7 +217,7 @@ struct sctp_sock { * These two structures must be grouped together for the usercopy * whitelist region. */ - struct sctp_event_subscribe subscribe; + __u16 subscribe; struct sctp_initmsg initmsg; int user_frag; @@ -1190,6 +1192,8 @@ int sctp_bind_addr_conflict(struct sctp_bind_addr *, const union sctp_addr *, struct sctp_sock *, struct sctp_sock *); int sctp_bind_addr_state(const struct sctp_bind_addr *bp, const union sctp_addr *addr); +int sctp_bind_addrs_check(struct sctp_sock *sp, + struct sctp_sock *sp2, int cnt2); union sctp_addr *sctp_find_unmatch_addr(struct sctp_bind_addr *bp, const union sctp_addr *addrs, int addrcnt, @@ -2073,6 +2077,8 @@ struct sctp_association { int sent_cnt_removable; + __u16 subscribe; + __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1]; __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1]; diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h index 51b4e0626c34..bd922a0fe914 100644 --- a/include/net/sctp/ulpevent.h +++ b/include/net/sctp/ulpevent.h @@ -164,30 +164,39 @@ void sctp_ulpevent_read_nxtinfo(const struct sctp_ulpevent *event, __u16 sctp_ulpevent_get_notification_type(const struct sctp_ulpevent *event); +static inline void sctp_ulpevent_type_set(__u16 *subscribe, + __u16 sn_type, __u8 on) +{ + if (sn_type > SCTP_SN_TYPE_MAX) + return; + + if (on) + *subscribe |= (1 << (sn_type - SCTP_SN_TYPE_BASE)); + else + *subscribe &= ~(1 << (sn_type - SCTP_SN_TYPE_BASE)); +} + /* Is this event type enabled? */ -static inline int sctp_ulpevent_type_enabled(__u16 sn_type, - struct sctp_event_subscribe *mask) +static inline bool sctp_ulpevent_type_enabled(__u16 subscribe, __u16 sn_type) { - int offset = sn_type - SCTP_SN_TYPE_BASE; - char *amask = (char *) mask; + if (sn_type > SCTP_SN_TYPE_MAX) + return false; - if (offset >= sizeof(struct sctp_event_subscribe)) - return 0; - return amask[offset]; + return subscribe & (1 << (sn_type - SCTP_SN_TYPE_BASE)); } /* Given an event subscription, is this event enabled? */ -static inline int sctp_ulpevent_is_enabled(const struct sctp_ulpevent *event, - struct sctp_event_subscribe *mask) +static inline bool sctp_ulpevent_is_enabled(const struct sctp_ulpevent *event, + __u16 subscribe) { __u16 sn_type; - int enabled = 1; - if (sctp_ulpevent_is_notification(event)) { - sn_type = sctp_ulpevent_get_notification_type(event); - enabled = sctp_ulpevent_type_enabled(sn_type, mask); - } - return enabled; + if (!sctp_ulpevent_is_notification(event)) + return true; + + sn_type = sctp_ulpevent_get_notification_type(event); + + return sctp_ulpevent_type_enabled(subscribe, sn_type); } #endif /* __sctp_ulpevent_h__ */ diff --git a/include/net/sock.h b/include/net/sock.h index f665d74ae509..df390a3e23fe 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1110,7 +1110,7 @@ struct proto { unsigned int inuse_idx; #endif - bool (*stream_memory_free)(const struct sock *sk); + bool (*stream_memory_free)(const struct sock *sk, int wake); bool (*stream_memory_read)(const struct sock *sk); /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); @@ -1192,19 +1192,29 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ -static inline bool sk_stream_memory_free(const struct sock *sk) +static inline bool __sk_stream_memory_free(const struct sock *sk, int wake) { if (sk->sk_wmem_queued >= sk->sk_sndbuf) return false; return sk->sk_prot->stream_memory_free ? - sk->sk_prot->stream_memory_free(sk) : true; + sk->sk_prot->stream_memory_free(sk, wake) : true; } -static inline bool sk_stream_is_writeable(const struct sock *sk) +static inline bool sk_stream_memory_free(const struct sock *sk) +{ + return __sk_stream_memory_free(sk, 0); +} + +static inline bool __sk_stream_is_writeable(const struct sock *sk, int wake) { return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && - sk_stream_memory_free(sk); + __sk_stream_memory_free(sk, wake); +} + +static inline bool sk_stream_is_writeable(const struct sock *sk) +{ + return __sk_stream_is_writeable(sk, 0); } static inline int sk_under_cgroup_hierarchy(struct sock *sk, diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 881ecb1555bf..866b6d148b77 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -95,8 +95,8 @@ struct switchdev_obj_port_vlan { u16 vid_end; }; -#define SWITCHDEV_OBJ_PORT_VLAN(obj) \ - container_of(obj, struct switchdev_obj_port_vlan, obj) +#define SWITCHDEV_OBJ_PORT_VLAN(OBJ) \ + container_of((OBJ), struct switchdev_obj_port_vlan, obj) /* SWITCHDEV_OBJ_ID_PORT_MDB */ struct switchdev_obj_port_mdb { @@ -105,8 +105,8 @@ struct switchdev_obj_port_mdb { u16 vid; }; -#define SWITCHDEV_OBJ_PORT_MDB(obj) \ - container_of(obj, struct switchdev_obj_port_mdb, obj) +#define SWITCHDEV_OBJ_PORT_MDB(OBJ) \ + container_of((OBJ), struct switchdev_obj_port_mdb, obj) void switchdev_trans_item_enqueue(struct switchdev_trans *trans, void *data, void (*destructor)(void const *), @@ -121,10 +121,6 @@ typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj); * @switchdev_port_attr_get: Get a port attribute (see switchdev_attr). * * @switchdev_port_attr_set: Set a port attribute (see switchdev_attr). - * - * @switchdev_port_obj_add: Add an object to port (see switchdev_obj_*). - * - * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj_*). */ struct switchdev_ops { int (*switchdev_port_attr_get)(struct net_device *dev, @@ -132,11 +128,6 @@ struct switchdev_ops { int (*switchdev_port_attr_set)(struct net_device *dev, const struct switchdev_attr *attr, struct switchdev_trans *trans); - int (*switchdev_port_obj_add)(struct net_device *dev, - const struct switchdev_obj *obj, - struct switchdev_trans *trans); - int (*switchdev_port_obj_del)(struct net_device *dev, - const struct switchdev_obj *obj); }; enum switchdev_notifier_type { @@ -146,6 +137,11 @@ enum switchdev_notifier_type { SWITCHDEV_FDB_DEL_TO_DEVICE, SWITCHDEV_FDB_OFFLOADED, + SWITCHDEV_PORT_OBJ_ADD, /* Blocking. */ + SWITCHDEV_PORT_OBJ_DEL, /* Blocking. */ + + SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE, + SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE, SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE, SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE, SWITCHDEV_VXLAN_FDB_OFFLOADED, @@ -163,6 +159,13 @@ struct switchdev_notifier_fdb_info { offloaded:1; }; +struct switchdev_notifier_port_obj_info { + struct switchdev_notifier_info info; /* must be first */ + const struct switchdev_obj *obj; + struct switchdev_trans *trans; + bool handled; +}; + static inline struct net_device * switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info) { @@ -180,10 +183,17 @@ int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj); int switchdev_port_obj_del(struct net_device *dev, const struct switchdev_obj *obj); + int register_switchdev_notifier(struct notifier_block *nb); int unregister_switchdev_notifier(struct notifier_block *nb); int call_switchdev_notifiers(unsigned long val, struct net_device *dev, struct switchdev_notifier_info *info); + +int register_switchdev_blocking_notifier(struct notifier_block *nb); +int unregister_switchdev_blocking_notifier(struct notifier_block *nb); +int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev, + struct switchdev_notifier_info *info); + void switchdev_port_fwd_mark_set(struct net_device *dev, struct net_device *group_dev, bool joining); @@ -191,6 +201,18 @@ void switchdev_port_fwd_mark_set(struct net_device *dev, bool switchdev_port_same_parent_id(struct net_device *a, struct net_device *b); +int switchdev_handle_port_obj_add(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + int (*add_cb)(struct net_device *dev, + const struct switchdev_obj *obj, + struct switchdev_trans *trans)); +int switchdev_handle_port_obj_del(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + int (*del_cb)(struct net_device *dev, + const struct switchdev_obj *obj)); + #define SWITCHDEV_SET_OPS(netdev, ops) ((netdev)->switchdev_ops = (ops)) #else @@ -239,12 +261,53 @@ static inline int call_switchdev_notifiers(unsigned long val, return NOTIFY_DONE; } +static inline int +register_switchdev_blocking_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline int +unregister_switchdev_blocking_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline int +call_switchdev_blocking_notifiers(unsigned long val, + struct net_device *dev, + struct switchdev_notifier_info *info) +{ + return NOTIFY_DONE; +} + static inline bool switchdev_port_same_parent_id(struct net_device *a, struct net_device *b) { return false; } +static inline int +switchdev_handle_port_obj_add(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + int (*add_cb)(struct net_device *dev, + const struct switchdev_obj *obj, + struct switchdev_trans *trans)) +{ + return 0; +} + +static inline int +switchdev_handle_port_obj_del(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + int (*del_cb)(struct net_device *dev, + const struct switchdev_obj *obj)) +{ + return 0; +} + #define SWITCHDEV_SET_OPS(netdev, ops) do {} while (0) #endif diff --git a/include/net/tcp.h b/include/net/tcp.h index a18914d20486..e0a65c067662 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -313,7 +313,7 @@ extern struct proto tcp_prot; void tcp_tasklet_init(void); -void tcp_v4_err(struct sk_buff *skb, u32); +int tcp_v4_err(struct sk_buff *skb, u32); void tcp_shutdown(struct sock *sk, int how); @@ -1124,7 +1124,7 @@ void tcp_rate_check_app_limited(struct sock *sk); */ static inline int tcp_is_sack(const struct tcp_sock *tp) { - return tp->rx_opt.sack_ok; + return likely(tp->rx_opt.sack_ok); } static inline bool tcp_is_reno(const struct tcp_sock *tp) @@ -1315,33 +1315,16 @@ static inline __sum16 tcp_v4_check(int len, __be32 saddr, return csum_tcpudp_magic(saddr,daddr,len,IPPROTO_TCP,base); } -static inline __sum16 __tcp_checksum_complete(struct sk_buff *skb) -{ - return __skb_checksum_complete(skb); -} - static inline bool tcp_checksum_complete(struct sk_buff *skb) { return !skb_csum_unnecessary(skb) && - __tcp_checksum_complete(skb); + __skb_checksum_complete(skb); } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb); int tcp_filter(struct sock *sk, struct sk_buff *skb); - -#undef STATE_TRACE - -#ifdef STATE_TRACE -static const char *statename[]={ - "Unused","Established","Syn Sent","Syn Recv", - "Fin Wait 1","Fin Wait 2","Time Wait", "Close", - "Close Wait","Last ACK","Listen","Closing" -}; -#endif void tcp_set_state(struct sock *sk, int state); - void tcp_done(struct sock *sk); - int tcp_abort(struct sock *sk, int err); static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) @@ -1385,7 +1368,7 @@ static inline int tcp_win_from_space(const struct sock *sk, int space) /* Note: caller must be prepared to deal with negative returns */ static inline int tcp_space(const struct sock *sk) { - return tcp_win_from_space(sk, sk->sk_rcvbuf - + return tcp_win_from_space(sk, sk->sk_rcvbuf - sk->sk_backlog.len - atomic_read(&sk->sk_rmem_alloc)); } @@ -1572,9 +1555,21 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG -struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, - const union tcp_md5_addr *addr, - int family); +#include <linux/jump_label.h> +extern struct static_key tcp_md5_needed; +struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, + const union tcp_md5_addr *addr, + int family); +static inline struct tcp_md5sig_key * +tcp_md5_do_lookup(const struct sock *sk, + const union tcp_md5_addr *addr, + int family) +{ + if (!static_key_false(&tcp_md5_needed)) + return NULL; + return __tcp_md5_do_lookup(sk, addr, family); +} + #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) #else static inline struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, @@ -1875,12 +1870,16 @@ static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat; } -static inline bool tcp_stream_memory_free(const struct sock *sk) +/* @wake is one when sk_stream_write_space() calls us. + * This sends EPOLLOUT only if notsent_bytes is half the limit. + * This mimics the strategy used in sock_def_write_space(). + */ +static inline bool tcp_stream_memory_free(const struct sock *sk, int wake) { const struct tcp_sock *tp = tcp_sk(sk); u32 notsent_bytes = tp->write_seq - tp->snd_nxt; - return notsent_bytes < tcp_notsent_lowat(tp); + return (notsent_bytes << wake) < tcp_notsent_lowat(tp); } #ifdef CONFIG_PROC_FS diff --git a/include/net/udp.h b/include/net/udp.h index 9e82cb391dea..fd6d948755c8 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -252,6 +252,17 @@ static inline int udp_rqueue_get(struct sock *sk) return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit); } +static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if, + int dif, int sdif) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + return inet_bound_dev_eq(!!net->ipv4.sysctl_udp_l3mdev_accept, + bound_dev_if, dif, sdif); +#else + return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); +#endif +} + /* net/ipv4/udp.c */ void udp_destruct_sock(struct sock *sk); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); @@ -272,7 +283,7 @@ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst); int udp_get_port(struct sock *sk, unsigned short snum, int (*saddr_cmp)(const struct sock *, const struct sock *)); -void udp_err(struct sk_buff *, u32); +int udp_err(struct sk_buff *, u32); int udp_abort(struct sock *sk, int err); int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); int udp_push_pending_frames(struct sock *sk); @@ -406,17 +417,24 @@ static inline int copy_linear_skb(struct sk_buff *skb, int len, int off, } while(0) #if IS_ENABLED(CONFIG_IPV6) -#define __UDPX_INC_STATS(sk, field) \ -do { \ - if ((sk)->sk_family == AF_INET) \ - __UDP_INC_STATS(sock_net(sk), field, 0); \ - else \ - __UDP6_INC_STATS(sock_net(sk), field, 0); \ -} while (0) +#define __UDPX_MIB(sk, ipv4) \ +({ \ + ipv4 ? (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \ + sock_net(sk)->mib.udp_statistics) : \ + (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_stats_in6 : \ + sock_net(sk)->mib.udp_stats_in6); \ +}) #else -#define __UDPX_INC_STATS(sk, field) __UDP_INC_STATS(sock_net(sk), field, 0) +#define __UDPX_MIB(sk, ipv4) \ +({ \ + IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \ + sock_net(sk)->mib.udp_statistics; \ +}) #endif +#define __UDPX_INC_STATS(sk, field) \ + __SNMP_INC_STATS(__UDPX_MIB(sk, (sk)->sk_family == AF_INET), field) + #ifdef CONFIG_PROC_FS struct udp_seq_afinfo { sa_family_t family; @@ -450,4 +468,26 @@ DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void); #endif +static inline struct sk_buff *udp_rcv_segment(struct sock *sk, + struct sk_buff *skb, bool ipv4) +{ + struct sk_buff *segs; + + /* the GSO CB lays after the UDP one, no need to save and restore any + * CB fragment + */ + segs = __skb_gso_segment(skb, NETIF_F_SG, false); + if (unlikely(IS_ERR_OR_NULL(segs))) { + int segs_nr = skb_shinfo(skb)->gso_segs; + + atomic_add(segs_nr, &sk->sk_drops); + SNMP_ADD_STATS(__UDPX_MIB(sk, ipv4), UDP_MIB_INERRORS, segs_nr); + kfree_skb(skb); + return NULL; + } + + consume_skb(skb); + return segs; +} + #endif /* _UDP_H */ diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index fe680ab6b15a..b8137953fea3 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -30,6 +30,7 @@ struct udp_port_cfg { __be16 local_udp_port; __be16 peer_udp_port; + int bind_ifindex; unsigned int use_udp_checksums:1, use_udp6_tx_checksums:1, use_udp6_rx_checksums:1, @@ -64,6 +65,8 @@ static inline int udp_sock_create(struct net *net, } typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb); +typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk, + struct sk_buff *skb); typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk); typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk, struct list_head *head, @@ -76,6 +79,7 @@ struct udp_tunnel_sock_cfg { /* Used for setting up udp_sock fields, see udp.h for details */ __u8 encap_type; udp_tunnel_encap_rcv_t encap_rcv; + udp_tunnel_encap_err_lookup_t encap_err_lookup; udp_tunnel_encap_destroy_t encap_destroy; udp_tunnel_gro_receive_t gro_receive; udp_tunnel_gro_complete_t gro_complete; @@ -165,6 +169,12 @@ static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) static inline void udp_tunnel_encap_enable(struct socket *sock) { + struct udp_sock *up = udp_sk(sock->sk); + + if (up->encap_enabled) + return; + + up->encap_enabled = 1; #if IS_ENABLED(CONFIG_IPV6) if (sock->sk->sk_family == PF_INET6) ipv6_stub->udpv6_encap_enable(); diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 03431c148e16..236403eb5ba6 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -216,6 +216,7 @@ struct vxlan_config { unsigned long age_interval; unsigned int addrmax; bool no_share; + enum ifla_vxlan_df df; }; struct vxlan_dev_node { @@ -420,11 +421,16 @@ struct switchdev_notifier_vxlan_fdb_info { u8 eth_addr[ETH_ALEN]; __be32 vni; bool offloaded; + bool added_by_user; }; #if IS_ENABLED(CONFIG_VXLAN) int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, struct switchdev_notifier_vxlan_fdb_info *fdb_info); +int vxlan_fdb_replay(const struct net_device *dev, __be32 vni, + struct notifier_block *nb); +void vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni); + #else static inline int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, @@ -432,6 +438,17 @@ vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, { return -ENOENT; } + +static inline int vxlan_fdb_replay(const struct net_device *dev, __be32 vni, + struct notifier_block *nb) +{ + return -EOPNOTSUPP; +} + +static inline void +vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni) +{ +} #endif #endif diff --git a/include/soc/fsl/qman.h b/include/soc/fsl/qman.h index 56877660d5ba..5cc7af06c1ba 100644 --- a/include/soc/fsl/qman.h +++ b/include/soc/fsl/qman.h @@ -1205,8 +1205,10 @@ void qman_dqrr_get_ithresh(struct qman_portal *portal, u8 *ithresh); * qman_dqrr_set_ithresh - Set coalesce interrupt threshold * @portal: portal to set the new value on * @ithresh: new threshold value + * + * Returns 0 on success, or a negative error code. */ -void qman_dqrr_set_ithresh(struct qman_portal *portal, u8 ithresh); +int qman_dqrr_set_ithresh(struct qman_portal *portal, u8 ithresh); /** * qman_dqrr_get_iperiod - Get coalesce interrupt period @@ -1219,7 +1221,9 @@ void qman_portal_get_iperiod(struct qman_portal *portal, u32 *iperiod); * qman_dqrr_set_iperiod - Set coalesce interrupt period * @portal: portal to set the new value on * @ithresh: new period value + * + * Returns 0 on success, or a negative error code. */ -void qman_portal_set_iperiod(struct qman_portal *portal, u32 iperiod); +int qman_portal_set_iperiod(struct qman_portal *portal, u32 iperiod); #endif /* __FSL_QMAN_H */ diff --git a/include/trace/events/net.h b/include/trace/events/net.h index 00aa72ce0e7c..1efd7d9b25fe 100644 --- a/include/trace/events/net.h +++ b/include/trace/events/net.h @@ -244,6 +244,65 @@ DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_ni_entry, TP_ARGS(skb) ); +DECLARE_EVENT_CLASS(net_dev_rx_exit_template, + + TP_PROTO(int ret), + + TP_ARGS(ret), + + TP_STRUCT__entry( + __field(int, ret) + ), + + TP_fast_assign( + __entry->ret = ret; + ), + + TP_printk("ret=%d", __entry->ret) +); + +DEFINE_EVENT(net_dev_rx_exit_template, napi_gro_frags_exit, + + TP_PROTO(int ret), + + TP_ARGS(ret) +); + +DEFINE_EVENT(net_dev_rx_exit_template, napi_gro_receive_exit, + + TP_PROTO(int ret), + + TP_ARGS(ret) +); + +DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_exit, + + TP_PROTO(int ret), + + TP_ARGS(ret) +); + +DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_exit, + + TP_PROTO(int ret), + + TP_ARGS(ret) +); + +DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_ni_exit, + + TP_PROTO(int ret), + + TP_ARGS(ret) +); + +DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_list_exit, + + TP_PROTO(int ret), + + TP_ARGS(ret) +); + #endif /* _TRACE_NET_H */ /* This part must be outside protection */ diff --git a/include/trace/events/objagg.h b/include/trace/events/objagg.h new file mode 100644 index 000000000000..fcec0fc9eb0c --- /dev/null +++ b/include/trace/events/objagg.h @@ -0,0 +1,228 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ +/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM objagg + +#if !defined(__TRACE_OBJAGG_H) || defined(TRACE_HEADER_MULTI_READ) +#define __TRACE_OBJAGG_H + +#include <linux/tracepoint.h> + +struct objagg; +struct objagg_obj; + +TRACE_EVENT(objagg_create, + TP_PROTO(const struct objagg *objagg), + + TP_ARGS(objagg), + + TP_STRUCT__entry( + __field(const void *, objagg) + ), + + TP_fast_assign( + __entry->objagg = objagg; + ), + + TP_printk("objagg %p", __entry->objagg) +); + +TRACE_EVENT(objagg_destroy, + TP_PROTO(const struct objagg *objagg), + + TP_ARGS(objagg), + + TP_STRUCT__entry( + __field(const void *, objagg) + ), + + TP_fast_assign( + __entry->objagg = objagg; + ), + + TP_printk("objagg %p", __entry->objagg) +); + +TRACE_EVENT(objagg_obj_create, + TP_PROTO(const struct objagg *objagg, + const struct objagg_obj *obj), + + TP_ARGS(objagg, obj), + + TP_STRUCT__entry( + __field(const void *, objagg) + __field(const void *, obj) + ), + + TP_fast_assign( + __entry->objagg = objagg; + __entry->obj = obj; + ), + + TP_printk("objagg %p, obj %p", __entry->objagg, __entry->obj) +); + +TRACE_EVENT(objagg_obj_destroy, + TP_PROTO(const struct objagg *objagg, + const struct objagg_obj *obj), + + TP_ARGS(objagg, obj), + + TP_STRUCT__entry( + __field(const void *, objagg) + __field(const void *, obj) + ), + + TP_fast_assign( + __entry->objagg = objagg; + __entry->obj = obj; + ), + + TP_printk("objagg %p, obj %p", __entry->objagg, __entry->obj) +); + +TRACE_EVENT(objagg_obj_get, + TP_PROTO(const struct objagg *objagg, + const struct objagg_obj *obj, + unsigned int refcount), + + TP_ARGS(objagg, obj, refcount), + + TP_STRUCT__entry( + __field(const void *, objagg) + __field(const void *, obj) + __field(unsigned int, refcount) + ), + + TP_fast_assign( + __entry->objagg = objagg; + __entry->obj = obj; + __entry->refcount = refcount; + ), + + TP_printk("objagg %p, obj %p, refcount %u", + __entry->objagg, __entry->obj, __entry->refcount) +); + +TRACE_EVENT(objagg_obj_put, + TP_PROTO(const struct objagg *objagg, + const struct objagg_obj *obj, + unsigned int refcount), + + TP_ARGS(objagg, obj, refcount), + + TP_STRUCT__entry( + __field(const void *, objagg) + __field(const void *, obj) + __field(unsigned int, refcount) + ), + + TP_fast_assign( + __entry->objagg = objagg; + __entry->obj = obj; + __entry->refcount = refcount; + ), + + TP_printk("objagg %p, obj %p, refcount %u", + __entry->objagg, __entry->obj, __entry->refcount) +); + +TRACE_EVENT(objagg_obj_parent_assign, + TP_PROTO(const struct objagg *objagg, + const struct objagg_obj *obj, + const struct objagg_obj *parent, + unsigned int parent_refcount), + + TP_ARGS(objagg, obj, parent, parent_refcount), + + TP_STRUCT__entry( + __field(const void *, objagg) + __field(const void *, obj) + __field(const void *, parent) + __field(unsigned int, parent_refcount) + ), + + TP_fast_assign( + __entry->objagg = objagg; + __entry->obj = obj; + __entry->parent = parent; + __entry->parent_refcount = parent_refcount; + ), + + TP_printk("objagg %p, obj %p, parent %p, parent_refcount %u", + __entry->objagg, __entry->obj, + __entry->parent, __entry->parent_refcount) +); + +TRACE_EVENT(objagg_obj_parent_unassign, + TP_PROTO(const struct objagg *objagg, + const struct objagg_obj *obj, + const struct objagg_obj *parent, + unsigned int parent_refcount), + + TP_ARGS(objagg, obj, parent, parent_refcount), + + TP_STRUCT__entry( + __field(const void *, objagg) + __field(const void *, obj) + __field(const void *, parent) + __field(unsigned int, parent_refcount) + ), + + TP_fast_assign( + __entry->objagg = objagg; + __entry->obj = obj; + __entry->parent = parent; + __entry->parent_refcount = parent_refcount; + ), + + TP_printk("objagg %p, obj %p, parent %p, parent_refcount %u", + __entry->objagg, __entry->obj, + __entry->parent, __entry->parent_refcount) +); + +TRACE_EVENT(objagg_obj_root_create, + TP_PROTO(const struct objagg *objagg, + const struct objagg_obj *obj), + + TP_ARGS(objagg, obj), + + TP_STRUCT__entry( + __field(const void *, objagg) + __field(const void *, obj) + ), + + TP_fast_assign( + __entry->objagg = objagg; + __entry->obj = obj; + ), + + TP_printk("objagg %p, obj %p", + __entry->objagg, __entry->obj) +); + +TRACE_EVENT(objagg_obj_root_destroy, + TP_PROTO(const struct objagg *objagg, + const struct objagg_obj *obj), + + TP_ARGS(objagg, obj), + + TP_STRUCT__entry( + __field(const void *, objagg) + __field(const void *, obj) + ), + + TP_fast_assign( + __entry->objagg = objagg; + __entry->obj = obj; + ), + + TP_printk("objagg %p, obj %p", + __entry->objagg, __entry->obj) +); + +#endif /* __TRACE_OBJAGG_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 72c453a8bf50..ec8b40ff386e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -257,9 +257,6 @@ enum bpf_attach_type { /* Specify numa node during map creation */ #define BPF_F_NUMA_NODE (1U << 2) -/* flags for BPF_PROG_QUERY */ -#define BPF_F_QUERY_EFFECTIVE (1U << 0) - #define BPF_OBJ_NAME_LEN 16U /* Flags for accessing BPF object */ @@ -269,6 +266,12 @@ enum bpf_attach_type { /* Flag for stack_map, store build_id+offset instead of pointer */ #define BPF_F_STACK_BUILD_ID (1U << 5) +/* Zero-initialize hash function seed. This should only be used for testing. */ +#define BPF_F_ZERO_SEED (1U << 6) + +/* flags for BPF_PROG_QUERY */ +#define BPF_F_QUERY_EFFECTIVE (1U << 0) + enum bpf_stack_build_id_status { /* user space need an empty entry to identify end of a trace */ BPF_STACK_BUILD_ID_EMPTY = 0, @@ -335,6 +338,10 @@ union bpf_attr { * (context accesses, allowed helpers, etc). */ __u32 expected_attach_type; + __u32 prog_btf_fd; /* fd pointing to BTF type data */ + __u32 func_info_rec_size; /* userspace bpf_func_info size */ + __aligned_u64 func_info; /* func info */ + __u32 func_info_cnt; /* number of bpf_func_info records */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -2265,6 +2272,19 @@ union bpf_attr { * * Return * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 pop, u64 flags) + * Description + * Will remove *pop* bytes from a *msg* starting at byte *start*. + * This may result in **ENOMEM** errors under certain situations if + * an allocation and copy are required due to a full ring buffer. + * However, the helper will try to avoid doing the allocation + * if possible. Other errors can occur if input parameters are + * invalid either due to *start* byte not being valid part of msg + * payload and/or *pop* value being to large. + * + * Return + * 0 on success, or a negative erro in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2357,7 +2377,8 @@ union bpf_attr { FN(map_push_elem), \ FN(map_pop_elem), \ FN(map_peek_elem), \ - FN(msg_push_data), + FN(msg_push_data), \ + FN(msg_pop_data), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2474,6 +2495,7 @@ struct __sk_buff { __u32 data_meta; __bpf_md_ptr(struct bpf_flow_keys *, flow_keys); + __u64 tstamp; }; struct bpf_tunnel_key { @@ -2649,6 +2671,10 @@ struct bpf_prog_info { __u32 nr_jited_func_lens; __aligned_u64 jited_ksyms; __aligned_u64 jited_func_lens; + __u32 btf_id; + __u32 func_info_rec_size; + __aligned_u64 func_info; + __u32 func_info_cnt; } __attribute__((aligned(8))); struct bpf_map_info { @@ -2960,4 +2986,9 @@ struct bpf_flow_keys { }; }; +struct bpf_func_info { + __u32 insn_offset; + __u32 type_id; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index 972265f32871..14f66948fc95 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -40,7 +40,8 @@ struct btf_type { /* "size" is used by INT, ENUM, STRUCT and UNION. * "size" tells the size of the type it is describing. * - * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT. + * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, + * FUNC and FUNC_PROTO. * "type" is a type_id referring to another type. */ union { @@ -64,8 +65,10 @@ struct btf_type { #define BTF_KIND_VOLATILE 9 /* Volatile */ #define BTF_KIND_CONST 10 /* Const */ #define BTF_KIND_RESTRICT 11 /* Restrict */ -#define BTF_KIND_MAX 11 -#define NR_BTF_KINDS 12 +#define BTF_KIND_FUNC 12 /* Function */ +#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ +#define BTF_KIND_MAX 13 +#define NR_BTF_KINDS 14 /* For some specific BTF_KIND, "struct btf_type" is immediately * followed by extra data. @@ -110,4 +113,13 @@ struct btf_member { __u32 offset; /* offset in bits */ }; +/* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param". + * The exact number of btf_param is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_param { + __u32 name_off; + __u32 type; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 79407bbd296d..6e52d3660654 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -163,6 +163,11 @@ enum devlink_param_cmode { DEVLINK_PARAM_CMODE_MAX = __DEVLINK_PARAM_CMODE_MAX - 1 }; +enum devlink_param_fw_load_policy_value { + DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DRIVER, + DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_FLASH, +}; + enum devlink_attr { /* don't change the order or add anything between, this is ABI! */ DEVLINK_ATTR_UNSPEC, diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index c8f8e2455bf3..17be76aeb468 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -882,7 +882,7 @@ struct ethtool_rx_flow_spec { __u32 location; }; -/* How rings are layed out when accessing virtual functions or +/* How rings are laid out when accessing virtual functions or * offloaded queues is device specific. To allow users to do flow * steering and specify these queues the ring cookie is partitioned * into a 32bit queue index with an 8 bit virtual function id. @@ -891,7 +891,7 @@ struct ethtool_rx_flow_spec { * devices start supporting PCIe w/ARI. However at the moment I * do not know of any devices that support this so I do not reserve * space for this at this time. If a future patch consumes the next - * byte it should be aware of this possiblity. + * byte it should be aware of this possibility. */ #define ETHTOOL_RX_FLOW_SPEC_RING 0x00000000FFFFFFFFLL #define ETHTOOL_RX_FLOW_SPEC_RING_VF 0x000000FF00000000LL diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index e41eda3c71f1..773e476a8e54 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -292,4 +292,25 @@ struct br_mcast_stats { __u64 mcast_bytes[BR_MCAST_DIR_SIZE]; __u64 mcast_packets[BR_MCAST_DIR_SIZE]; }; + +/* bridge boolean options + * BR_BOOLOPT_NO_LL_LEARN - disable learning from link-local packets + * + * IMPORTANT: if adding a new option do not forget to handle + * it in br_boolopt_toggle/get and bridge sysfs + */ +enum br_boolopt_id { + BR_BOOLOPT_NO_LL_LEARN, + BR_BOOLOPT_MAX +}; + +/* struct br_boolopt_multi - change multiple bridge boolean options + * + * @optval: new option values (bit per option) + * @optmask: options to change (bit per option) + */ +struct br_boolopt_multi { + __u32 optval; + __u32 optmask; +}; #endif /* _UAPI_LINUX_IF_BRIDGE_H */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 1debfa42cba1..d6533828123a 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -288,6 +288,7 @@ enum { IFLA_BR_MCAST_IGMP_VERSION, IFLA_BR_MCAST_MLD_VERSION, IFLA_BR_VLAN_STATS_PER_PORT, + IFLA_BR_MULTI_BOOLOPT, __IFLA_BR_MAX, }; @@ -533,6 +534,7 @@ enum { IFLA_VXLAN_LABEL, IFLA_VXLAN_GPE, IFLA_VXLAN_TTL_INHERIT, + IFLA_VXLAN_DF, __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) @@ -542,6 +544,14 @@ struct ifla_vxlan_port_range { __be16 high; }; +enum ifla_vxlan_df { + VXLAN_DF_UNSET = 0, + VXLAN_DF_SET, + VXLAN_DF_INHERIT, + __VXLAN_DF_END, + VXLAN_DF_MAX = __VXLAN_DF_END - 1, +}; + /* GENEVE section */ enum { IFLA_GENEVE_UNSPEC, @@ -557,10 +567,19 @@ enum { IFLA_GENEVE_UDP_ZERO_CSUM6_RX, IFLA_GENEVE_LABEL, IFLA_GENEVE_TTL_INHERIT, + IFLA_GENEVE_DF, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) +enum ifla_geneve_df { + GENEVE_DF_UNSET = 0, + GENEVE_DF_SET, + GENEVE_DF_INHERIT, + __GENEVE_DF_END, + GENEVE_DF_MAX = __GENEVE_DF_END - 1, +}; + /* PPP section */ enum { IFLA_PPP_UNSPEC, diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index ee432cd3018c..23a6753b37df 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -59,6 +59,7 @@ #define TUNGETVNETBE _IOR('T', 223, int) #define TUNSETSTEERINGEBPF _IOR('T', 224, int) #define TUNSETFILTEREBPF _IOR('T', 225, int) +#define TUNSETCARRIER _IOW('T', 226, int) /* TUNSETIFF ifr flags */ #define IFF_TUN 0x0001 diff --git a/include/uapi/linux/ncsi.h b/include/uapi/linux/ncsi.h index 0a26a5576645..a3f87c54fdb3 100644 --- a/include/uapi/linux/ncsi.h +++ b/include/uapi/linux/ncsi.h @@ -26,6 +26,12 @@ * @NCSI_CMD_SEND_CMD: send NC-SI command to network card. * Requires NCSI_ATTR_IFINDEX, NCSI_ATTR_PACKAGE_ID * and NCSI_ATTR_CHANNEL_ID. + * @NCSI_CMD_SET_PACKAGE_MASK: set a whitelist of allowed packages. + * Requires NCSI_ATTR_IFINDEX and NCSI_ATTR_PACKAGE_MASK. + * @NCSI_CMD_SET_CHANNEL_MASK: set a whitelist of allowed channels. + * Requires NCSI_ATTR_IFINDEX, NCSI_ATTR_PACKAGE_ID, and + * NCSI_ATTR_CHANNEL_MASK. If NCSI_ATTR_CHANNEL_ID is present it sets + * the primary channel. * @NCSI_CMD_MAX: highest command number */ enum ncsi_nl_commands { @@ -34,6 +40,8 @@ enum ncsi_nl_commands { NCSI_CMD_SET_INTERFACE, NCSI_CMD_CLEAR_INTERFACE, NCSI_CMD_SEND_CMD, + NCSI_CMD_SET_PACKAGE_MASK, + NCSI_CMD_SET_CHANNEL_MASK, __NCSI_CMD_AFTER_LAST, NCSI_CMD_MAX = __NCSI_CMD_AFTER_LAST - 1 @@ -48,6 +56,10 @@ enum ncsi_nl_commands { * @NCSI_ATTR_PACKAGE_ID: package ID * @NCSI_ATTR_CHANNEL_ID: channel ID * @NCSI_ATTR_DATA: command payload + * @NCSI_ATTR_MULTI_FLAG: flag to signal that multi-mode should be enabled with + * NCSI_CMD_SET_PACKAGE_MASK or NCSI_CMD_SET_CHANNEL_MASK. + * @NCSI_ATTR_PACKAGE_MASK: 32-bit mask of allowed packages. + * @NCSI_ATTR_CHANNEL_MASK: 32-bit mask of allowed channels. * @NCSI_ATTR_MAX: highest attribute number */ enum ncsi_nl_attrs { @@ -57,6 +69,9 @@ enum ncsi_nl_attrs { NCSI_ATTR_PACKAGE_ID, NCSI_ATTR_CHANNEL_ID, NCSI_ATTR_DATA, + NCSI_ATTR_MULTI_FLAG, + NCSI_ATTR_PACKAGE_MASK, + NCSI_ATTR_CHANNEL_MASK, __NCSI_ATTR_AFTER_LAST, NCSI_ATTR_MAX = __NCSI_ATTR_AFTER_LAST - 1 diff --git a/include/uapi/linux/net_namespace.h b/include/uapi/linux/net_namespace.h index 0187c74d8889..9f9956809565 100644 --- a/include/uapi/linux/net_namespace.h +++ b/include/uapi/linux/net_namespace.h @@ -16,6 +16,8 @@ enum { NETNSA_NSID, NETNSA_PID, NETNSA_FD, + NETNSA_TARGET_NSID, + NETNSA_CURRENT_NSID, __NETNSA_MAX, }; diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 401d0c1e612d..95d0db2a8350 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -485,6 +485,11 @@ enum { TCA_FLOWER_IN_HW_COUNT, + TCA_FLOWER_KEY_PORT_SRC_MIN, /* be16 */ + TCA_FLOWER_KEY_PORT_SRC_MAX, /* be16 */ + TCA_FLOWER_KEY_PORT_DST_MIN, /* be16 */ + TCA_FLOWER_KEY_PORT_DST_MAX, /* be16 */ + __TCA_FLOWER_MAX, }; @@ -518,6 +523,8 @@ enum { TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1), }; +#define TCA_FLOWER_MASK_FLAGS_RANGE (1 << 0) /* Range-based match */ + /* Match-all classifier */ enum { diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 89ee47c2f17d..0d18b1d1fbbc 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -291,11 +291,38 @@ enum { TCA_GRED_DPS, TCA_GRED_MAX_P, TCA_GRED_LIMIT, + TCA_GRED_VQ_LIST, /* nested TCA_GRED_VQ_ENTRY */ __TCA_GRED_MAX, }; #define TCA_GRED_MAX (__TCA_GRED_MAX - 1) +enum { + TCA_GRED_VQ_ENTRY_UNSPEC, + TCA_GRED_VQ_ENTRY, /* nested TCA_GRED_VQ_* */ + __TCA_GRED_VQ_ENTRY_MAX, +}; +#define TCA_GRED_VQ_ENTRY_MAX (__TCA_GRED_VQ_ENTRY_MAX - 1) + +enum { + TCA_GRED_VQ_UNSPEC, + TCA_GRED_VQ_PAD, + TCA_GRED_VQ_DP, /* u32 */ + TCA_GRED_VQ_STAT_BYTES, /* u64 */ + TCA_GRED_VQ_STAT_PACKETS, /* u32 */ + TCA_GRED_VQ_STAT_BACKLOG, /* u32 */ + TCA_GRED_VQ_STAT_PROB_DROP, /* u32 */ + TCA_GRED_VQ_STAT_PROB_MARK, /* u32 */ + TCA_GRED_VQ_STAT_FORCED_DROP, /* u32 */ + TCA_GRED_VQ_STAT_FORCED_MARK, /* u32 */ + TCA_GRED_VQ_STAT_PDROP, /* u32 */ + TCA_GRED_VQ_STAT_OTHER, /* u32 */ + TCA_GRED_VQ_FLAGS, /* u32 */ + __TCA_GRED_VQ_MAX +}; + +#define TCA_GRED_VQ_MAX (__TCA_GRED_VQ_MAX - 1) + struct tc_gred_qopt { __u32 limit; /* HARD maximal queue length (bytes) */ __u32 qth_min; /* Min average length threshold (bytes) */ @@ -864,6 +891,8 @@ enum { TCA_FQ_LOW_RATE_THRESHOLD, /* per packet delay under this rate */ + TCA_FQ_CE_THRESHOLD, /* DCTCP-like CE-marking threshold */ + __TCA_FQ_MAX }; @@ -882,6 +911,7 @@ struct tc_fq_qd_stats { __u32 inactive_flows; __u32 throttled_flows; __u32 unthrottle_latency_ns; + __u64 ce_mark; /* packets above ce_threshold */ }; /* Heavy-Hitter Filter */ diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h index 3039bf6a742e..d73d83950265 100644 --- a/include/uapi/linux/ptp_clock.h +++ b/include/uapi/linux/ptp_clock.h @@ -84,6 +84,16 @@ struct ptp_sys_offset { struct ptp_clock_time ts[2 * PTP_MAX_SAMPLES + 1]; }; +struct ptp_sys_offset_extended { + unsigned int n_samples; /* Desired number of measurements. */ + unsigned int rsv[3]; /* Reserved for future use. */ + /* + * Array of [system, phc, system] time stamps. The kernel will provide + * 3*n_samples time stamps. + */ + struct ptp_clock_time ts[PTP_MAX_SAMPLES][3]; +}; + struct ptp_sys_offset_precise { struct ptp_clock_time device; struct ptp_clock_time sys_realtime; @@ -136,6 +146,8 @@ struct ptp_pin_desc { #define PTP_PIN_SETFUNC _IOW(PTP_CLK_MAGIC, 7, struct ptp_pin_desc) #define PTP_SYS_OFFSET_PRECISE \ _IOWR(PTP_CLK_MAGIC, 8, struct ptp_sys_offset_precise) +#define PTP_SYS_OFFSET_EXTENDED \ + _IOW(PTP_CLK_MAGIC, 9, struct ptp_sys_offset_extended) struct ptp_extts_event { struct ptp_clock_time t; /* Time event occured. */ diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index c81feb373d3e..d584073532b8 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -129,6 +129,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_STREAM_SCHEDULER_VALUE 124 #define SCTP_INTERLEAVING_SUPPORTED 125 #define SCTP_SENDMSG_CONNECT 126 +#define SCTP_EVENT 127 /* PR-SCTP policies */ #define SCTP_PR_SCTP_NONE 0x0000 @@ -632,7 +633,9 @@ union sctp_notification { */ enum sctp_sn_type { - SCTP_SN_TYPE_BASE = (1<<15), + SCTP_SN_TYPE_BASE = (1<<15), + SCTP_DATA_IO_EVENT = SCTP_SN_TYPE_BASE, +#define SCTP_DATA_IO_EVENT SCTP_DATA_IO_EVENT SCTP_ASSOC_CHANGE, #define SCTP_ASSOC_CHANGE SCTP_ASSOC_CHANGE SCTP_PEER_ADDR_CHANGE, @@ -657,6 +660,8 @@ enum sctp_sn_type { #define SCTP_ASSOC_RESET_EVENT SCTP_ASSOC_RESET_EVENT SCTP_STREAM_CHANGE_EVENT, #define SCTP_STREAM_CHANGE_EVENT SCTP_STREAM_CHANGE_EVENT + SCTP_SN_TYPE_MAX = SCTP_STREAM_CHANGE_EVENT, +#define SCTP_SN_TYPE_MAX SCTP_SN_TYPE_MAX }; /* Notification error codes used to fill up the error fields in some @@ -1150,6 +1155,12 @@ struct sctp_add_streams { uint16_t sas_outstrms; }; +struct sctp_event { + sctp_assoc_t se_assoc_id; + uint16_t se_type; + uint8_t se_on; +}; + /* SCTP Stream schedulers */ enum sctp_sched_type { SCTP_SS_FCFS, diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index f80135e5feaa..86dc24a96c90 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -243,6 +243,7 @@ enum LINUX_MIB_TCPREQQFULLDROP, /* TCPReqQFullDrop */ LINUX_MIB_TCPRETRANSFAIL, /* TCPRetransFail */ LINUX_MIB_TCPRCVCOALESCE, /* TCPRcvCoalesce */ + LINUX_MIB_TCPBACKLOGCOALESCE, /* TCPBacklogCoalesce */ LINUX_MIB_TCPOFOQUEUE, /* TCPOFOQueue */ LINUX_MIB_TCPOFODROP, /* TCPOFODrop */ LINUX_MIB_TCPOFOMERGE, /* TCPOFOMerge */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index e02d31986ff9..8bb6cc5f3235 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -266,6 +266,7 @@ enum { TCP_NLA_BYTES_RETRANS, /* Data bytes retransmitted */ TCP_NLA_DSACK_DUPS, /* DSACK blocks received */ TCP_NLA_REORD_SEEN, /* reordering events seen */ + TCP_NLA_SRTT, /* smoothed RTT in usecs */ }; /* for TCP_MD5SIG socket option */ diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h index 09502de447f5..30baccb6c9c4 100644 --- a/include/uapi/linux/udp.h +++ b/include/uapi/linux/udp.h @@ -33,6 +33,7 @@ struct udphdr { #define UDP_NO_CHECK6_TX 101 /* Disable sending checksum for UDP6X */ #define UDP_NO_CHECK6_RX 102 /* Disable accpeting checksum for UDP6 */ #define UDP_SEGMENT 103 /* Set GSO segmentation size */ +#define UDP_GRO 104 /* This socket can receive UDP GRO packets */ /* UDP encapsulation types */ #define UDP_ENCAP_ESPINUDP_NON_IKE 1 /* draft-ietf-ipsec-nat-t-ike-00/01 */ diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h index 449132c76b1c..1196e1c1d4f6 100644 --- a/include/uapi/linux/virtio_config.h +++ b/include/uapi/linux/virtio_config.h @@ -75,6 +75,9 @@ */ #define VIRTIO_F_IOMMU_PLATFORM 33 +/* This feature indicates support for the packed virtqueue layout. */ +#define VIRTIO_F_RING_PACKED 34 + /* * Does the device support Single Root I/O Virtualization? */ diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h index 6d5d5faa989b..2414f8af26b3 100644 --- a/include/uapi/linux/virtio_ring.h +++ b/include/uapi/linux/virtio_ring.h @@ -44,6 +44,13 @@ /* This means the buffer contains a list of buffer descriptors. */ #define VRING_DESC_F_INDIRECT 4 +/* + * Mark a descriptor as available or used in packed ring. + * Notice: they are defined as shifts instead of shifted values. + */ +#define VRING_PACKED_DESC_F_AVAIL 7 +#define VRING_PACKED_DESC_F_USED 15 + /* The Host uses this in used->flags to advise the Guest: don't kick me when * you add a buffer. It's unreliable, so it's simply an optimization. Guest * will still kick if it's out of buffers. */ @@ -53,6 +60,23 @@ * optimization. */ #define VRING_AVAIL_F_NO_INTERRUPT 1 +/* Enable events in packed ring. */ +#define VRING_PACKED_EVENT_FLAG_ENABLE 0x0 +/* Disable events in packed ring. */ +#define VRING_PACKED_EVENT_FLAG_DISABLE 0x1 +/* + * Enable events for a specific descriptor in packed ring. + * (as specified by Descriptor Ring Change Event Offset/Wrap Counter). + * Only valid if VIRTIO_RING_F_EVENT_IDX has been negotiated. + */ +#define VRING_PACKED_EVENT_FLAG_DESC 0x2 + +/* + * Wrap counter bit shift in event suppression structure + * of packed ring. + */ +#define VRING_PACKED_EVENT_F_WRAP_CTR 15 + /* We support indirect buffer descriptors */ #define VIRTIO_RING_F_INDIRECT_DESC 28 @@ -171,4 +195,32 @@ static inline int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old) return (__u16)(new_idx - event_idx - 1) < (__u16)(new_idx - old); } +struct vring_packed_desc_event { + /* Descriptor Ring Change Event Offset/Wrap Counter. */ + __le16 off_wrap; + /* Descriptor Ring Change Event Flags. */ + __le16 flags; +}; + +struct vring_packed_desc { + /* Buffer Address. */ + __le64 addr; + /* Buffer Length. */ + __le32 len; + /* Buffer ID. */ + __le16 id; + /* The flags depending on descriptor type. */ + __le16 flags; +}; + +struct vring_packed { + unsigned int num; + + struct vring_packed_desc *desc; + + struct vring_packed_desc_event *driver; + + struct vring_packed_desc_event *device; +}; + #endif /* _UAPI_LINUX_VIRTIO_RING_H */ |