diff options
Diffstat (limited to 'include')
43 files changed, 560 insertions, 317 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index fa517ae604ad..8c92c974bd12 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -194,6 +194,17 @@ struct bpf_map { struct work_struct work; struct mutex freeze_mutex; atomic64_t writecnt; + /* 'Ownership' of program-containing map is claimed by the first program + * that is going to use this map or by the first program which FD is + * stored in the map to make sure that all callers and callees have the + * same prog type, JITed flag and xdp_has_frags flag. + */ + struct { + spinlock_t lock; + enum bpf_prog_type type; + bool jited; + bool xdp_has_frags; + } owner; }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -578,7 +589,6 @@ struct bpf_verifier_ops { const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); - bool (*check_kfunc_call)(u32 kfunc_btf_id, struct module *owner); }; struct bpf_prog_offload_ops { @@ -939,6 +949,7 @@ struct bpf_prog_aux { bool func_proto_unreliable; bool sleepable; bool tail_call_reachable; + bool xdp_has_frags; struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; @@ -999,16 +1010,6 @@ struct bpf_prog_aux { }; struct bpf_array_aux { - /* 'Ownership' of prog array is claimed by the first program that - * is going to use this map or by the first program which FD is - * stored in the map to make sure that all callers and callees have - * the same prog type and JITed flag. - */ - struct { - spinlock_t lock; - enum bpf_prog_type type; - bool jited; - } owner; /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; struct bpf_map *map; @@ -1183,7 +1184,14 @@ struct bpf_event_entry { struct rcu_head rcu; }; -bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); +static inline bool map_type_contains_progs(struct bpf_map *map) +{ + return map->map_type == BPF_MAP_TYPE_PROG_ARRAY || + map->map_type == BPF_MAP_TYPE_DEVMAP || + map->map_type == BPF_MAP_TYPE_CPUMAP; +} + +bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); @@ -1251,6 +1259,7 @@ struct bpf_run_ctx {}; struct bpf_cg_run_ctx { struct bpf_run_ctx run_ctx; const struct bpf_prog_array_item *prog_item; + int retval; }; struct bpf_trace_run_ctx { @@ -1283,19 +1292,19 @@ static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); -static __always_inline u32 +static __always_inline int BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, const void *ctx, bpf_prog_run_fn run_prog, - u32 *ret_flags) + int retval, u32 *ret_flags) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; - u32 ret = 1; u32 func_ret; + run_ctx.retval = retval; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); @@ -1304,27 +1313,29 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; func_ret = run_prog(prog, ctx); - ret &= (func_ret & 1); + if (!(func_ret & 1) && !IS_ERR_VALUE((long)run_ctx.retval)) + run_ctx.retval = -EPERM; *(ret_flags) |= (func_ret >> 1); item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); - return ret; + return run_ctx.retval; } -static __always_inline u32 +static __always_inline int BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, - const void *ctx, bpf_prog_run_fn run_prog) + const void *ctx, bpf_prog_run_fn run_prog, + int retval) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; - u32 ret = 1; + run_ctx.retval = retval; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); @@ -1332,13 +1343,14 @@ BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; - ret &= run_prog(prog, ctx); + if (!run_prog(prog, ctx) && !IS_ERR_VALUE((long)run_ctx.retval)) + run_ctx.retval = -EPERM; item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); - return ret; + return run_ctx.retval; } static __always_inline u32 @@ -1391,19 +1403,21 @@ out: * 0: NET_XMIT_SUCCESS skb should be transmitted * 1: NET_XMIT_DROP skb should be dropped and cn * 2: NET_XMIT_CN skb should be transmitted and cn - * 3: -EPERM skb should be dropped + * 3: -err skb should be dropped */ #define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ ({ \ u32 _flags = 0; \ bool _cn; \ u32 _ret; \ - _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, &_flags); \ + _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, 0, &_flags); \ _cn = _flags & BPF_RET_SET_CN; \ - if (_ret) \ + if (_ret && !IS_ERR_VALUE((long)_ret)) \ + _ret = -EFAULT; \ + if (!_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ else \ - _ret = (_cn ? NET_XMIT_DROP : -EPERM); \ + _ret = (_cn ? NET_XMIT_DROP : _ret); \ _ret; \ }) @@ -1724,7 +1738,6 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); -bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); @@ -1976,12 +1989,6 @@ static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, return -ENOTSUPP; } -static inline bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, - struct module *owner) -{ - return false; -} - static inline void bpf_map_put(struct bpf_map *map) { } @@ -2076,6 +2083,9 @@ int bpf_prog_test_run_syscall(struct bpf_prog *prog, int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); +int sock_map_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); + void sock_map_unhash(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else @@ -2129,6 +2139,12 @@ static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void { return -EOPNOTSUPP; } + +static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EINVAL; +} #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e9993172f892..7a7be8c057f2 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -521,6 +521,8 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); int check_ptr_off_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno); +int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size); @@ -564,4 +566,9 @@ static inline u32 type_flag(u32 type) return type & ~BPF_BASE_TYPE_MASK; } +static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) +{ + return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type; +} + #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/btf.h b/include/linux/btf.h index 0c74348cbc9d..b12cfe3b12bb 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -12,11 +12,33 @@ #define BTF_TYPE_EMIT(type) ((void)(type *)0) #define BTF_TYPE_EMIT_ENUM(enum_val) ((void)enum_val) +enum btf_kfunc_type { + BTF_KFUNC_TYPE_CHECK, + BTF_KFUNC_TYPE_ACQUIRE, + BTF_KFUNC_TYPE_RELEASE, + BTF_KFUNC_TYPE_RET_NULL, + BTF_KFUNC_TYPE_MAX, +}; + struct btf; struct btf_member; struct btf_type; union bpf_attr; struct btf_show; +struct btf_id_set; + +struct btf_kfunc_id_set { + struct module *owner; + union { + struct { + struct btf_id_set *check_set; + struct btf_id_set *acquire_set; + struct btf_id_set *release_set; + struct btf_id_set *ret_null_set; + }; + struct btf_id_set *sets[BTF_KFUNC_TYPE_MAX]; + }; +}; extern const struct file_operations btf_fops; @@ -307,6 +329,11 @@ 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); struct btf *btf_parse_vmlinux(void); struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); +bool btf_kfunc_id_set_contains(const struct btf *btf, + enum bpf_prog_type prog_type, + enum btf_kfunc_type type, u32 kfunc_btf_id); +int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *s); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -318,50 +345,18 @@ static inline const char *btf_name_by_offset(const struct btf *btf, { return NULL; } -#endif - -struct kfunc_btf_id_set { - struct list_head list; - struct btf_id_set *set; - struct module *owner; -}; - -struct kfunc_btf_id_list { - struct list_head list; - struct mutex mutex; -}; - -#ifdef CONFIG_DEBUG_INFO_BTF_MODULES -void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s); -void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s); -bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, - struct module *owner); - -extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list; -extern struct kfunc_btf_id_list prog_test_kfunc_list; -#else -static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) -{ -} -static inline void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) +static inline bool btf_kfunc_id_set_contains(const struct btf *btf, + enum bpf_prog_type prog_type, + enum btf_kfunc_type type, + u32 kfunc_btf_id) { + return false; } -static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, - u32 kfunc_id, struct module *owner) +static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *s) { - return false; + return 0; } - -static struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list __maybe_unused; -static struct kfunc_btf_id_list prog_test_kfunc_list __maybe_unused; #endif -#define DEFINE_KFUNC_BTF_ID_SET(set, name) \ - struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set), \ - THIS_MODULE } - #endif diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 919c0fde1c51..bc5d9cc34e4c 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -11,6 +11,7 @@ struct btf_id_set { #ifdef CONFIG_DEBUG_INFO_BTF #include <linux/compiler.h> /* for __PASTE */ +#include <linux/compiler_attributes.h> /* for __maybe_unused */ /* * Following macros help to define lists of BTF IDs placed @@ -146,14 +147,14 @@ extern struct btf_id_set name; #else -#define BTF_ID_LIST(name) static u32 name[5]; +#define BTF_ID_LIST(name) static u32 __maybe_unused name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED -#define BTF_ID_LIST_GLOBAL(name, n) u32 name[n]; -#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1]; -#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 name[1]; -#define BTF_SET_START(name) static struct btf_id_set name = { 0 }; -#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 }; +#define BTF_ID_LIST_GLOBAL(name, n) u32 __maybe_unused name[n]; +#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 __maybe_unused name[1]; +#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 __maybe_unused name[1]; +#define BTF_SET_START(name) static struct btf_id_set __maybe_unused name = { 0 }; +#define BTF_SET_START_GLOBAL(name) static struct btf_id_set __maybe_unused name = { 0 }; #define BTF_SET_END(name) #endif /* CONFIG_DEBUG_INFO_BTF */ diff --git a/include/linux/dsa/tag_qca.h b/include/linux/dsa/tag_qca.h new file mode 100644 index 000000000000..4359fb0221cf --- /dev/null +++ b/include/linux/dsa/tag_qca.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __TAG_QCA_H +#define __TAG_QCA_H + +#define QCA_HDR_LEN 2 +#define QCA_HDR_VERSION 0x2 + +#define QCA_HDR_RECV_VERSION GENMASK(15, 14) +#define QCA_HDR_RECV_PRIORITY GENMASK(13, 11) +#define QCA_HDR_RECV_TYPE GENMASK(10, 6) +#define QCA_HDR_RECV_FRAME_IS_TAGGED BIT(3) +#define QCA_HDR_RECV_SOURCE_PORT GENMASK(2, 0) + +/* Packet type for recv */ +#define QCA_HDR_RECV_TYPE_NORMAL 0x0 +#define QCA_HDR_RECV_TYPE_MIB 0x1 +#define QCA_HDR_RECV_TYPE_RW_REG_ACK 0x2 + +#define QCA_HDR_XMIT_VERSION GENMASK(15, 14) +#define QCA_HDR_XMIT_PRIORITY GENMASK(13, 11) +#define QCA_HDR_XMIT_CONTROL GENMASK(10, 8) +#define QCA_HDR_XMIT_FROM_CPU BIT(7) +#define QCA_HDR_XMIT_DP_BIT GENMASK(6, 0) + +/* Packet type for xmit */ +#define QCA_HDR_XMIT_TYPE_NORMAL 0x0 +#define QCA_HDR_XMIT_TYPE_RW_REG 0x1 + +/* Check code for a valid mgmt packet. Switch will ignore the packet + * with this wrong. + */ +#define QCA_HDR_MGMT_CHECK_CODE_VAL 0x5 + +/* Specific define for in-band MDIO read/write with Ethernet packet */ +#define QCA_HDR_MGMT_SEQ_LEN 4 /* 4 byte for the seq */ +#define QCA_HDR_MGMT_COMMAND_LEN 4 /* 4 byte for the command */ +#define QCA_HDR_MGMT_DATA1_LEN 4 /* First 4 byte for the mdio data */ +#define QCA_HDR_MGMT_HEADER_LEN (QCA_HDR_MGMT_SEQ_LEN + \ + QCA_HDR_MGMT_COMMAND_LEN + \ + QCA_HDR_MGMT_DATA1_LEN) + +#define QCA_HDR_MGMT_DATA2_LEN 12 /* Other 12 byte for the mdio data */ +#define QCA_HDR_MGMT_PADDING_LEN 34 /* Padding to reach the min Ethernet packet */ + +#define QCA_HDR_MGMT_PKT_LEN (QCA_HDR_MGMT_HEADER_LEN + \ + QCA_HDR_LEN + \ + QCA_HDR_MGMT_DATA2_LEN + \ + QCA_HDR_MGMT_PADDING_LEN) + +#define QCA_HDR_MGMT_SEQ_NUM GENMASK(31, 0) /* 63, 32 */ +#define QCA_HDR_MGMT_CHECK_CODE GENMASK(31, 29) /* 31, 29 */ +#define QCA_HDR_MGMT_CMD BIT(28) /* 28 */ +#define QCA_HDR_MGMT_LENGTH GENMASK(23, 20) /* 23, 20 */ +#define QCA_HDR_MGMT_ADDR GENMASK(18, 0) /* 18, 0 */ + +/* Special struct emulating a Ethernet header */ +struct qca_mgmt_ethhdr { + u32 command; /* command bit 31:0 */ + u32 seq; /* seq 63:32 */ + u32 mdio_data; /* first 4byte mdio */ + __be16 hdr; /* qca hdr */ +} __packed; + +enum mdio_cmd { + MDIO_WRITE = 0x0, + MDIO_READ +}; + +struct mib_ethhdr { + u32 data[3]; /* first 3 mib counter */ + __be16 hdr; /* qca hdr */ +} __packed; + +struct qca_tagger_data { + void (*rw_reg_ack_handler)(struct dsa_switch *ds, + struct sk_buff *skb); + void (*mib_autocast_handler)(struct dsa_switch *ds, + struct sk_buff *skb); +}; + +#endif /* __TAG_QCA_H */ diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 11efc45de66a..e0853f48b75e 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -70,9 +70,11 @@ enum { /** * struct kernel_ethtool_ringparam - RX/TX ring configuration * @rx_buf_len: Current length of buffers on the rx ring. + * @tcp_data_split: Scatter packet headers and data to separate buffers */ struct kernel_ethtool_ringparam { u32 rx_buf_len; + u8 tcp_data_split; }; /** diff --git a/include/linux/filter.h b/include/linux/filter.h index 71fa57b88bfc..d23e999dc032 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1356,7 +1356,10 @@ struct bpf_sockopt_kern { s32 level; s32 optname; s32 optlen; - s32 retval; + /* for retval in struct bpf_cg_run_ctx */ + struct task_struct *current_task; + /* Temporary "register" for indirect stores to ppos. */ + u64 tmp_reg; }; int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index a59d25f19385..1e0f8a31f3de 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -371,19 +371,12 @@ static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) return NULL; } -static inline struct inet6_request_sock * - inet6_rsk(const struct request_sock *rsk) -{ - return NULL; -} - static inline struct raw6_sock *raw6_sk(const struct sock *sk) { return NULL; } #define inet6_rcv_saddr(__sk) NULL -#define tcp_twsk_ipv6only(__sk) 0 #define inet_v6_ipv6only(__sk) 0 #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _IPV6_H */ diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index f8397f300fcd..15e0e0209da4 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -66,11 +66,6 @@ static inline void linkmode_mod_bit(int nr, volatile unsigned long *addr, linkmode_clear_bit(nr, addr); } -static inline void linkmode_change_bit(int nr, volatile unsigned long *addr) -{ - __change_bit(nr, addr); -} - static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr) { return test_bit(nr, addr); diff --git a/include/linux/mii.h b/include/linux/mii.h index 12ea29e04293..5ee13083cec7 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -355,56 +355,6 @@ static inline u32 mii_adv_to_ethtool_adv_x(u32 adv) } /** - * mii_lpa_mod_linkmode_adv_sgmii - * @lp_advertising: pointer to destination link mode. - * @lpa: value of the MII_LPA register - * - * A small helper function that translates MII_LPA bits to - * linkmode advertisement settings for SGMII. - * Leaves other bits unchanged. - */ -static inline void -mii_lpa_mod_linkmode_lpa_sgmii(unsigned long *lp_advertising, u32 lpa) -{ - u32 speed_duplex = lpa & LPA_SGMII_DPX_SPD_MASK; - - linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_1000HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_1000FULL); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_100HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_100FULL); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_10HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_10FULL); -} - -/** - * mii_lpa_to_linkmode_adv_sgmii - * @advertising: pointer to destination link mode. - * @lpa: value of the MII_LPA register - * - * A small helper function that translates MII_ADVERTISE bits - * to linkmode advertisement settings when in SGMII mode. - * Clears the old value of advertising. - */ -static inline void mii_lpa_to_linkmode_lpa_sgmii(unsigned long *lp_advertising, - u32 lpa) -{ - linkmode_zero(lp_advertising); - - mii_lpa_mod_linkmode_lpa_sgmii(lp_advertising, lpa); -} - -/** * mii_adv_mod_linkmode_adv_t * @advertising:pointer to destination link mode. * @adv: value of the MII_ADVERTISE register diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 598ac3bcc901..27145c4d6820 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -64,13 +64,6 @@ enum { }; enum { - MLX5_MODIFY_TIR_BITMASK_LRO = 0x0, - MLX5_MODIFY_TIR_BITMASK_INDIRECT_TABLE = 0x1, - MLX5_MODIFY_TIR_BITMASK_HASH = 0x2, - MLX5_MODIFY_TIR_BITMASK_TUNNELED_OFFLOAD_EN = 0x3 -}; - -enum { MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE = 0x0, MLX5_SET_HCA_CAP_OP_MOD_ODP = 0x2, MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3, diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 1ec631838af9..bda1c385cffb 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -135,15 +135,6 @@ static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack, extack->cookie_len = sizeof(cookie); } -static inline void nl_set_extack_cookie_u32(struct netlink_ext_ack *extack, - u32 cookie) -{ - if (!extack) - return; - memcpy(extack->cookie, &cookie, sizeof(cookie)); - extack->cookie_len = sizeof(cookie); -} - void netlink_kernel_release(struct sock *sk); int __netlink_change_ngroups(struct sock *sk, unsigned int groups); int netlink_change_ngroups(struct sock *sk, unsigned int groups); diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index add077a81b21..266eb26fb029 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -31,8 +31,7 @@ void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex); int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, unsigned int mode); -void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, - struct phylink_link_state *state); +void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable); struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, diff --git a/include/linux/phy.h b/include/linux/phy.h index 6de8d7a90d78..cd08cf1a8b0d 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1661,7 +1661,7 @@ int phy_disable_interrupts(struct phy_device *phydev); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); -int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); +void phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_advertise_supported(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 8a636e678902..a27bcc4f7e9a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -557,6 +557,7 @@ struct skb_shared_info { * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; + unsigned int xdp_frags_size; /* Intermediate layers must ensure that destructor_arg * remains valid until skb destructor */ @@ -3898,11 +3899,6 @@ static inline ktime_t net_timedelta(ktime_t t) return ktime_sub(ktime_get_real(), t); } -static inline ktime_t net_invalid_timestamp(void) -{ - return 0; -} - static inline u8 skb_metadata_len(const struct sk_buff *skb) { return skb_shinfo(skb)->meta_len; diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 571f605bc91e..382af90320ac 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -88,6 +88,7 @@ struct svc_xprt { struct list_head xpt_users; /* callbacks on free */ struct net *xpt_net; + netns_tracker ns_tracker; const struct cred *xpt_cred; struct rpc_xprt *xpt_bc_xprt; /* NFSv4.1 backchannel */ struct rpc_xprt_switch *xpt_bc_xps; /* NFSv4.1 backchannel */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 955ea4d7af0b..3cdc8d878d81 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -284,6 +284,7 @@ struct rpc_xprt { } stat; struct net *xprt_net; + netns_tracker ns_tracker; const char *servername; const char *address_strings[RPC_DISPLAY_MAX]; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) diff --git a/include/linux/udp.h b/include/linux/udp.h index ae66dadd8543..254a2654400f 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -23,11 +23,6 @@ static inline struct udphdr *udp_hdr(const struct sk_buff *skb) return (struct udphdr *)skb_transport_header(skb); } -static inline struct udphdr *inner_udp_hdr(const struct sk_buff *skb) -{ - return (struct udphdr *)skb_inner_transport_header(skb); -} - #define UDP_HTABLE_SIZE_MIN (CONFIG_BASE_SMALL ? 128 : 256) static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) diff --git a/include/net/ax25.h b/include/net/ax25.h index 8221af1811df..0f9790c455bb 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -187,18 +187,12 @@ typedef struct { typedef struct ax25_route { struct ax25_route *next; - refcount_t refcount; ax25_address callsign; struct net_device *dev; ax25_digi *digipeat; char ip_mode; } ax25_route; -static inline void ax25_hold_route(ax25_route *ax25_rt) -{ - refcount_inc(&ax25_rt->refcount); -} - void __ax25_put_route(ax25_route *ax25_rt); extern rwlock_t ax25_route_lock; @@ -213,12 +207,6 @@ static inline void ax25_route_lock_unuse(void) read_unlock(&ax25_route_lock); } -static inline void ax25_put_route(ax25_route *ax25_rt) -{ - if (refcount_dec_and_test(&ax25_rt->refcount)) - __ax25_put_route(ax25_rt); -} - typedef struct { char slave; /* slave_mode? */ struct timer_list slave_timer; /* timeout timer */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 586f69d084a2..f5caff1ddb29 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -258,6 +258,15 @@ struct adv_info { #define HCI_ADV_TX_POWER_NO_PREFERENCE 0x7F +struct monitored_device { + struct list_head list; + + bdaddr_t bdaddr; + __u8 addr_type; + __u16 handle; + bool notified; +}; + struct adv_pattern { struct list_head list; __u8 ad_type; @@ -294,6 +303,9 @@ struct adv_monitor { #define HCI_MAX_SHORT_NAME_LENGTH 10 +#define HCI_CONN_HANDLE_UNSET 0xffff +#define HCI_CONN_HANDLE_MAX 0x0eff + /* Min encryption key size to match with SMP */ #define HCI_MIN_ENC_KEY_SIZE 7 @@ -591,6 +603,9 @@ struct hci_dev { struct delayed_work interleave_scan; + struct list_head monitored_devices; + bool advmon_pend_notify; + #if IS_ENABLED(CONFIG_BT_LEDS) struct led_trigger *power_led; #endif @@ -1847,6 +1862,8 @@ void mgmt_adv_monitor_removed(struct hci_dev *hdev, u16 handle); int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip); int mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, u8 status); int mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, u8 status); +void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle, + bdaddr_t *bdaddr, u8 addr_type); u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 107b25deae68..99266f7aebdc 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -1104,3 +1104,19 @@ struct mgmt_ev_controller_resume { #define MGMT_WAKE_REASON_NON_BT_WAKE 0x0 #define MGMT_WAKE_REASON_UNEXPECTED 0x1 #define MGMT_WAKE_REASON_REMOTE_WAKE 0x2 + +#define MGMT_EV_ADV_MONITOR_DEVICE_FOUND 0x002f +struct mgmt_ev_adv_monitor_device_found { + __le16 monitor_handle; + struct mgmt_addr_info addr; + __s8 rssi; + __le32 flags; + __le16 eir_len; + __u8 eir[0]; +} __packed; + +#define MGMT_EV_ADV_MONITOR_DEVICE_LOST 0x0030 +struct mgmt_ev_adv_monitor_device_lost { + __le16 monitor_handle; + struct mgmt_addr_info addr; +} __packed; diff --git a/include/net/bonding.h b/include/net/bonding.h index 83cfd2d70247..7dead855a72d 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -699,20 +699,6 @@ static inline struct slave *bond_slave_has_mac(struct bonding *bond, } /* Caller must hold rcu_read_lock() for read */ -static inline struct slave *bond_slave_has_mac_rcu(struct bonding *bond, - const u8 *mac) -{ - struct list_head *iter; - struct slave *tmp; - - bond_for_each_slave_rcu(bond, tmp, iter) - if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) - return tmp; - - return NULL; -} - -/* Caller must hold rcu_read_lock() for read */ static inline bool bond_slave_has_mac_rx(struct bonding *bond, const u8 *mac) { struct list_head *iter; diff --git a/include/net/dsa.h b/include/net/dsa.h index 57b3e4e7413b..ca8c14b547b4 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -278,6 +278,10 @@ struct dsa_port { u8 devlink_port_setup:1; + /* Master state bits, valid only on CPU ports */ + u8 master_admin_up:1; + u8 master_oper_up:1; + u8 setup:1; struct device_node *dn; @@ -478,6 +482,12 @@ static inline bool dsa_port_is_unused(struct dsa_port *dp) return dp->type == DSA_PORT_TYPE_UNUSED; } +static inline bool dsa_port_master_is_operational(struct dsa_port *dp) +{ + return dsa_port_is_cpu(dp) && dp->master_admin_up && + dp->master_oper_up; +} + static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; @@ -581,6 +591,24 @@ static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port) return port == dsa_upstream_port(ds, port); } +/* Return true if this is a DSA port leading away from the CPU */ +static inline bool dsa_is_downstream_port(struct dsa_switch *ds, int port) +{ + return dsa_is_dsa_port(ds, port) && !dsa_is_upstream_port(ds, port); +} + +/* Return the local port used to reach the CPU port */ +static inline unsigned int dsa_switch_upstream_port(struct dsa_switch *ds) +{ + struct dsa_port *dp; + + dsa_switch_for_each_available_port(dp, ds) { + return dsa_upstream_port(ds, dp->index); + } + + return ds->num_ports; +} + /* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning * that the routing port from @downstream_ds to @upstream_ds is also the port * which @downstream_ds uses to reach its dedicated CPU. @@ -1036,6 +1064,13 @@ struct dsa_switch_ops { int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); + + /* + * DSA master tracking operations + */ + void (*master_state_change)(struct dsa_switch *ds, + const struct net_device *master, + bool operational); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 4ad47d9f9d27..3908296d103f 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -285,6 +285,14 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req); +static inline unsigned long +reqsk_timeout(struct request_sock *req, unsigned long max_timeout) +{ + u64 timeout = (u64)req->timeout << req->num_timeout; + + return (unsigned long)min_t(u64, timeout, max_timeout); +} + static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk) { /* The below has to be done to allow calling inet_csk_destroy_sock */ diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index dfd919b3119e..463ae5d33eb0 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -65,13 +65,13 @@ struct inet_timewait_sock { /* these three are in inet_sock */ __be16 tw_sport; /* And these are ours. */ - unsigned int tw_kill : 1, - tw_transparent : 1, + unsigned int tw_transparent : 1, tw_flowlabel : 20, - tw_pad : 2, /* 2 bits hole */ + tw_pad : 3, /* 3 bits hole */ tw_tos : 8; u32 tw_txhash; u32 tw_priority; + u32 tw_bslot; /* bind bucket slot */ struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; }; @@ -110,8 +110,6 @@ static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo void inet_twsk_deschedule_put(struct inet_timewait_sock *tw); -void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family); - static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) { diff --git a/include/net/ip.h b/include/net/ip.h index b51bae43b0dd..3984f2c39c4b 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -517,7 +517,6 @@ void ip_dst_metrics_put(struct dst_entry *dst) kfree(p); } -u32 ip_idents_reserve(u32 hash, int segs); void __ip_select_ident(struct net *net, struct iphdr *iph, int segs); static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb, @@ -712,7 +711,7 @@ int ip_forward(struct sk_buff *skb); */ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, - __be32 daddr, struct rtable *rt, int is_frag); + __be32 daddr, struct rtable *rt); int __ip_options_echo(struct net *net, struct ip_options *dopt, struct sk_buff *skb, const struct ip_options *sopt); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 3afcb128e064..082f30256f59 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -437,8 +437,16 @@ struct ipv6_txoptions *ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, int newtype, struct ipv6_opt_hdr *newopt); -struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, - struct ipv6_txoptions *opt); +struct ipv6_txoptions *__ipv6_fixup_options(struct ipv6_txoptions *opt_space, + struct ipv6_txoptions *opt); + +static inline struct ipv6_txoptions * +ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt) +{ + if (!opt) + return NULL; + return __ipv6_fixup_options(opt_space, opt); +} bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, const struct inet6_skb_parm *opt); @@ -1020,7 +1028,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, - struct ipcm6_cookie *ipc6, struct flowi6 *fl6, + struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork); diff --git a/include/net/netfilter/nf_conntrack_bpf.h b/include/net/netfilter/nf_conntrack_bpf.h new file mode 100644 index 000000000000..a473b56842c5 --- /dev/null +++ b/include/net/netfilter/nf_conntrack_bpf.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _NF_CONNTRACK_BPF_H +#define _NF_CONNTRACK_BPF_H + +#include <linux/btf.h> +#include <linux/kconfig.h> + +#if (IS_BUILTIN(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ + (IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) + +extern int register_nf_conntrack_bpf(void); + +#else + +static inline int register_nf_conntrack_bpf(void) +{ + return 0; +} + +#endif + +#endif /* _NF_CONNTRACK_BPF_H */ diff --git a/include/net/netns/core.h b/include/net/netns/core.h index 552bc25b1933..388244e315e7 100644 --- a/include/net/netns/core.h +++ b/include/net/netns/core.h @@ -10,6 +10,7 @@ struct netns_core { struct ctl_table_header *sysctl_hdr; int sysctl_somaxconn; + u8 sysctl_txrehash; #ifdef CONFIG_PROC_FS struct prot_inuse __percpu *prot_inuse; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 78557643526e..f0687867b5cd 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -31,18 +31,16 @@ struct ping_group_range { struct inet_hashinfo; struct inet_timewait_death_row { - atomic_t tw_count; - char tw_pad[L1_CACHE_BYTES - sizeof(atomic_t)]; + refcount_t tw_refcount; - struct inet_hashinfo *hashinfo; + struct inet_hashinfo *hashinfo ____cacheline_aligned_in_smp; int sysctl_max_tw_buckets; }; struct tcp_fastopen_context; struct netns_ipv4 { - /* Please keep tcp_death_row at first field in netns_ipv4 */ - struct inet_timewait_death_row tcp_death_row ____cacheline_aligned_in_smp; + struct inet_timewait_death_row *tcp_death_row; #ifdef CONFIG_SYSCTL struct ctl_table_header *forw_hdr; @@ -70,11 +68,9 @@ struct netns_ipv4 { struct hlist_head *fib_table_hash; struct sock *fibnl; - struct sock * __percpu *icmp_sk; struct sock *mc_autojoin_sk; struct inet_peer_base *peers; - struct sock * __percpu *tcp_sk; struct fqdir *fqdir; u8 sysctl_icmp_echo_ignore_all; @@ -87,6 +83,7 @@ struct netns_ipv4 { u32 ip_rt_min_pmtu; int ip_rt_mtu_expires; + int ip_rt_min_advmss; struct local_ports ip_local_ports; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index a4b550380316..30cdfc4e1615 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -88,7 +88,6 @@ struct netns_ipv6 { struct fib6_table *fib6_local_tbl; struct fib_rules_ops *fib6_rules_ops; #endif - struct sock * __percpu *icmp_sk; struct sock *ndisc_sk; struct sock *tcp_sk; struct sock *igmp_sk; diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 79a805542d0f..97c3c19872ff 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -201,21 +201,67 @@ static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data, } #endif -void page_pool_put_page(struct page_pool *pool, struct page *page, - unsigned int dma_sync_size, bool allow_direct); +void page_pool_put_defragged_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, + bool allow_direct); -/* Same as above but will try to sync the entire area pool->max_len */ -static inline void page_pool_put_full_page(struct page_pool *pool, - struct page *page, bool allow_direct) +static inline void page_pool_fragment_page(struct page *page, long nr) +{ + atomic_long_set(&page->pp_frag_count, nr); +} + +static inline long page_pool_defrag_page(struct page *page, long nr) +{ + long ret; + + /* If nr == pp_frag_count then we have cleared all remaining + * references to the page. No need to actually overwrite it, instead + * we can leave this to be overwritten by the calling function. + * + * The main advantage to doing this is that an atomic_read is + * generally a much cheaper operation than an atomic update, + * especially when dealing with a page that may be partitioned + * into only 2 or 3 pieces. + */ + if (atomic_long_read(&page->pp_frag_count) == nr) + return 0; + + ret = atomic_long_sub_return(nr, &page->pp_frag_count); + WARN_ON(ret < 0); + return ret; +} + +static inline bool page_pool_is_last_frag(struct page_pool *pool, + struct page *page) +{ + /* If fragments aren't enabled or count is 0 we were the last user */ + return !(pool->p.flags & PP_FLAG_PAGE_FRAG) || + (page_pool_defrag_page(page, 1) == 0); +} + +static inline void page_pool_put_page(struct page_pool *pool, + struct page *page, + unsigned int dma_sync_size, + bool allow_direct) { /* When page_pool isn't compiled-in, net/core/xdp.c doesn't * allow registering MEM_TYPE_PAGE_POOL, but shield linker. */ #ifdef CONFIG_PAGE_POOL - page_pool_put_page(pool, page, -1, allow_direct); + if (!page_pool_is_last_frag(pool, page)) + return; + + page_pool_put_defragged_page(pool, page, dma_sync_size, allow_direct); #endif } +/* Same as above but will try to sync the entire area pool->max_len */ +static inline void page_pool_put_full_page(struct page_pool *pool, + struct page *page, bool allow_direct) +{ + page_pool_put_page(pool, page, -1, allow_direct); +} + /* Same as above but the caller must guarantee safe context. e.g NAPI */ static inline void page_pool_recycle_direct(struct page_pool *pool, struct page *page) @@ -243,30 +289,6 @@ static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) page->dma_addr_upper = upper_32_bits(addr); } -static inline void page_pool_set_frag_count(struct page *page, long nr) -{ - atomic_long_set(&page->pp_frag_count, nr); -} - -static inline long page_pool_atomic_sub_frag_count_return(struct page *page, - long nr) -{ - long ret; - - /* As suggested by Alexander, atomic_long_read() may cover up the - * reference count errors, so avoid calling atomic_long_read() in - * the cases of freeing or draining the page_frags, where we would - * not expect it to match or that are slowpath anyway. - */ - if (__builtin_constant_p(nr) && - atomic_long_read(&page->pp_frag_count) == nr) - return 0; - - ret = atomic_long_sub_return(nr, &page->pp_frag_count); - WARN_ON(ret < 0); - return ret; -} - static inline bool is_page_pool_compiled_in(void) { #ifdef CONFIG_PAGE_POOL diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 9e7b21c0b3a6..44a35531952e 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -63,12 +63,6 @@ static inline psched_time_t psched_get_time(void) return PSCHED_NS2TICKS(ktime_get_ns()); } -static inline psched_tdiff_t -psched_tdiff_bounded(psched_time_t tv1, psched_time_t tv2, psched_time_t bound) -{ - return min(tv1 - tv2, bound); -} - struct qdisc_watchdog { u64 last_expires; struct hrtimer timer; diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 29e41ff3ec93..144c39db9898 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -70,6 +70,7 @@ struct request_sock { struct saved_syn *saved_syn; u32 secid; u32 peer_secid; + u32 timeout; }; static inline struct request_sock *inet_reqsk(const struct sock *sk) @@ -104,6 +105,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, sk_node_init(&req_to_sk(req)->sk_node); sk_tx_queue_clear(req_to_sk(req)); req->saved_syn = NULL; + req->timeout = 0; req->num_timeout = 0; req->num_retrans = 0; req->sk = NULL; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 472843eedbae..9bab396c1f3b 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -518,11 +518,6 @@ static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) BUILD_BUG_ON(sizeof(qcb->data) < sz); } -static inline int qdisc_qlen_cpu(const struct Qdisc *q) -{ - return this_cpu_ptr(q->cpu_qstats)->qlen; -} - static inline int qdisc_qlen(const struct Qdisc *q) { return q->q.qlen; diff --git a/include/net/sock.h b/include/net/sock.h index ff9b508d9c5f..d6c13f0fba40 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -316,6 +316,7 @@ struct sk_filter; * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting * @sk_txhash: computed flow hash for use on transmit + * @sk_txrehash: enable TX hash rethink * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer * @sk_stamp: time stamp of last packet received @@ -491,6 +492,7 @@ struct sock { u32 sk_ack_backlog; u32 sk_max_ack_backlog; kuid_t sk_uid; + u8 sk_txrehash; #ifdef CONFIG_NET_RX_BUSY_POLL u8 sk_prefer_busy_poll; u16 sk_busy_poll_budget; @@ -587,6 +589,18 @@ static inline bool sk_user_data_is_nocopy(const struct sock *sk) __tmp | SK_USER_DATA_NOCOPY); \ }) +static inline +struct net *sock_net(const struct sock *sk) +{ + return read_pnet(&sk->sk_net); +} + +static inline +void sock_net_set(struct sock *sk, struct net *net) +{ + write_pnet(&sk->sk_net, net); +} + /* * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK * or not whether his port will be reused by someone else. SK_FORCE_REUSE @@ -2054,7 +2068,7 @@ static inline void sk_set_txhash(struct sock *sk) static inline bool sk_rethink_txhash(struct sock *sk) { - if (sk->sk_txhash) { + if (sk->sk_txhash && sk->sk_txrehash == SOCK_TXREHASH_ENABLED) { sk_set_txhash(sk); return true; } @@ -2704,18 +2718,6 @@ static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) __kfree_skb(skb); } -static inline -struct net *sock_net(const struct sock *sk) -{ - return read_pnet(&sk->sk_net); -} - -static inline -void sock_net_set(struct sock *sk, struct net *net) -{ - write_pnet(&sk->sk_net, net); -} - static inline bool skb_sk_is_prefetched(struct sk_buff *skb) { diff --git a/include/net/tcp.h b/include/net/tcp.h index b9fc978fb2ca..eff2487d972d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2358,7 +2358,7 @@ static inline u32 tcp_timeout_init(struct sock *sk) if (timeout <= 0) timeout = TCP_TIMEOUT_INIT; - return timeout; + return min_t(int, timeout, TCP_RTO_MAX); } static inline u32 tcp_rwnd_init_bpf(struct sock *sk) diff --git a/include/net/udplite.h b/include/net/udplite.h index 9185e45b997f..a3c53110d30b 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -70,49 +70,6 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh) return 0; } -/* Slow-path computation of checksum. Socket is locked. */ -static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb) -{ - const struct udp_sock *up = udp_sk(skb->sk); - int cscov = up->len; - __wsum csum = 0; - - if (up->pcflag & UDPLITE_SEND_CC) { - /* - * Sender has set `partial coverage' option on UDP-Lite socket. - * The special case "up->pcslen == 0" signifies full coverage. - */ - if (up->pcslen < up->len) { - if (0 < up->pcslen) - cscov = up->pcslen; - udp_hdr(skb)->len = htons(up->pcslen); - } - /* - * NOTE: Causes for the error case `up->pcslen > up->len': - * (i) Application error (will not be penalized). - * (ii) Payload too big for send buffer: data is split - * into several packets, each with its own header. - * In this case (e.g. last segment), coverage may - * exceed packet length. - * Since packets with coverage length > packet length are - * illegal, we fall back to the defaults here. - */ - } - - skb->ip_summed = CHECKSUM_NONE; /* no HW support for checksumming */ - - skb_queue_walk(&sk->sk_write_queue, skb) { - const int off = skb_transport_offset(skb); - const int len = skb->len - off; - - csum = skb_checksum(skb, off, (cscov > len)? len : cscov, csum); - - if ((cscov -= len) <= 0) - break; - } - return csum; -} - /* Fast-path computation of checksum. Socket may not be locked. */ static inline __wsum udplite_csum(struct sk_buff *skb) { diff --git a/include/net/xdp.h b/include/net/xdp.h index 8f0812e4996d..b7721c3e4d1f 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -60,12 +60,20 @@ struct xdp_rxq_info { u32 reg_state; struct xdp_mem_info mem; unsigned int napi_id; + u32 frag_size; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ struct xdp_txq_info { struct net_device *dev; }; +enum xdp_buff_flags { + XDP_FLAGS_HAS_FRAGS = BIT(0), /* non-linear xdp buff */ + XDP_FLAGS_FRAGS_PF_MEMALLOC = BIT(1), /* xdp paged memory is under + * pressure + */ +}; + struct xdp_buff { void *data; void *data_end; @@ -74,13 +82,40 @@ struct xdp_buff { struct xdp_rxq_info *rxq; struct xdp_txq_info *txq; u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/ + u32 flags; /* supported values defined in xdp_buff_flags */ }; +static __always_inline bool xdp_buff_has_frags(struct xdp_buff *xdp) +{ + return !!(xdp->flags & XDP_FLAGS_HAS_FRAGS); +} + +static __always_inline void xdp_buff_set_frags_flag(struct xdp_buff *xdp) +{ + xdp->flags |= XDP_FLAGS_HAS_FRAGS; +} + +static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp) +{ + xdp->flags &= ~XDP_FLAGS_HAS_FRAGS; +} + +static __always_inline bool xdp_buff_is_frag_pfmemalloc(struct xdp_buff *xdp) +{ + return !!(xdp->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); +} + +static __always_inline void xdp_buff_set_frag_pfmemalloc(struct xdp_buff *xdp) +{ + xdp->flags |= XDP_FLAGS_FRAGS_PF_MEMALLOC; +} + static __always_inline void xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq) { xdp->frame_sz = frame_sz; xdp->rxq = rxq; + xdp->flags = 0; } static __always_inline void @@ -111,6 +146,20 @@ xdp_get_shared_info_from_buff(struct xdp_buff *xdp) return (struct skb_shared_info *)xdp_data_hard_end(xdp); } +static __always_inline unsigned int xdp_get_buff_len(struct xdp_buff *xdp) +{ + unsigned int len = xdp->data_end - xdp->data; + struct skb_shared_info *sinfo; + + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + + sinfo = xdp_get_shared_info_from_buff(xdp); + len += sinfo->xdp_frags_size; +out: + return len; +} + struct xdp_frame { void *data; u16 len; @@ -122,8 +171,19 @@ struct xdp_frame { */ struct xdp_mem_info mem; struct net_device *dev_rx; /* used by cpumap */ + u32 flags; /* supported values defined in xdp_buff_flags */ }; +static __always_inline bool xdp_frame_has_frags(struct xdp_frame *frame) +{ + return !!(frame->flags & XDP_FLAGS_HAS_FRAGS); +} + +static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame) +{ + return !!(frame->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); +} + #define XDP_BULK_QUEUE_SIZE 16 struct xdp_frame_bulk { int count; @@ -159,6 +219,19 @@ static inline void xdp_scrub_frame(struct xdp_frame *frame) frame->dev_rx = NULL; } +static inline void +xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags, + unsigned int size, unsigned int truesize, + bool pfmemalloc) +{ + skb_shinfo(skb)->nr_frags = nr_frags; + + skb->len += size; + skb->data_len += size; + skb->truesize += truesize; + skb->pfmemalloc |= pfmemalloc; +} + /* Avoids inlining WARN macro in fast-path */ void xdp_warn(const char *msg, const char *func, const int line); #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) @@ -180,6 +253,7 @@ void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) xdp->data_end = frame->data + frame->len; xdp->data_meta = frame->data - frame->metasize; xdp->frame_sz = frame->frame_sz; + xdp->flags = frame->flags; } static inline @@ -206,6 +280,7 @@ int xdp_update_frame_from_buff(struct xdp_buff *xdp, xdp_frame->headroom = headroom - sizeof(*xdp_frame); xdp_frame->metasize = metasize; xdp_frame->frame_sz = xdp->frame_sz; + xdp_frame->flags = xdp->flags; return 0; } @@ -230,6 +305,8 @@ struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) return xdp_frame; } +void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, + struct xdp_buff *xdp); void xdp_return_frame(struct xdp_frame *xdpf); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); @@ -246,14 +323,37 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem); static inline void xdp_release_frame(struct xdp_frame *xdpf) { struct xdp_mem_info *mem = &xdpf->mem; + struct skb_shared_info *sinfo; + int i; /* Curr only page_pool needs this */ - if (mem->type == MEM_TYPE_PAGE_POOL) - __xdp_release_frame(xdpf->data, mem); + if (mem->type != MEM_TYPE_PAGE_POOL) + return; + + if (likely(!xdp_frame_has_frags(xdpf))) + goto out; + + sinfo = xdp_get_shared_info_from_frame(xdpf); + for (i = 0; i < sinfo->nr_frags; i++) { + struct page *page = skb_frag_page(&sinfo->frags[i]); + + __xdp_release_frame(page_address(page), mem); + } +out: + __xdp_release_frame(xdpf->data, mem); +} + +int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, + struct net_device *dev, u32 queue_index, + unsigned int napi_id, u32 frag_size); +static inline int +xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, + struct net_device *dev, u32 queue_index, + unsigned int napi_id) +{ + return __xdp_rxq_info_reg(xdp_rxq, dev, queue_index, napi_id, 0); } -int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, - struct net_device *dev, u32 queue_index, unsigned int napi_id); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index c77a1313b3b0..467ca2f28760 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -128,6 +128,8 @@ #define SO_RESERVE_MEM 73 +#define SO_TXREHASH 74 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b0383d371b9a..16a7574292a5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -330,6 +330,8 @@ union bpf_iter_link_info { * *ctx_out*, *data_in* and *data_out* must be NULL. * *repeat* must be zero. * + * BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN. + * * Return * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. @@ -1111,6 +1113,11 @@ enum bpf_link_type { */ #define BPF_F_SLEEPABLE (1U << 4) +/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program + * fully support xdp frags. + */ +#define BPF_F_XDP_HAS_FRAGS (1U << 5) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * @@ -1775,6 +1782,8 @@ union bpf_attr { * 0 on success, or a negative error in case of failure. * * u64 bpf_get_current_pid_tgid(void) + * Description + * Get the current pid and tgid. * Return * A 64-bit integer containing the current tgid and pid, and * created as such: @@ -1782,6 +1791,8 @@ union bpf_attr { * *current_task*\ **->pid**. * * u64 bpf_get_current_uid_gid(void) + * Description + * Get the current uid and gid. * Return * A 64-bit integer containing the current GID and UID, and * created as such: *current_gid* **<< 32 \|** *current_uid*. @@ -2256,6 +2267,8 @@ union bpf_attr { * The 32-bit hash. * * u64 bpf_get_current_task(void) + * Description + * Get the current task. * Return * A pointer to the current task struct. * @@ -2369,6 +2382,8 @@ union bpf_attr { * indicate that the hash is outdated and to trigger a * recalculation the next time the kernel tries to access this * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * Return + * void. * * long bpf_get_numa_node_id(void) * Description @@ -2466,6 +2481,8 @@ union bpf_attr { * A 8-byte long unique number or 0 if *sk* is NULL. * * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Description + * Get the owner UID of the socked associated to *skb*. * Return * The owner UID of the socket associated to *skb*. If the socket * is **NULL**, or if it is not a full socket (i.e. if it is a @@ -3240,6 +3257,9 @@ union bpf_attr { * The id is returned or 0 in case the id could not be retrieved. * * u64 bpf_get_current_cgroup_id(void) + * Description + * Get the current cgroup id based on the cgroup within which + * the current task is running. * Return * A 64-bit integer containing the current cgroup id based * on the cgroup within which the current task is running. @@ -5018,6 +5038,44 @@ union bpf_attr { * * Return * The number of arguments of the traced function. + * + * int bpf_get_retval(void) + * Description + * Get the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * The syscall's return value. + * + * int bpf_set_retval(int retval) + * Description + * Set the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md) + * Description + * Get the total size of a given xdp buff (linear and paged area) + * Return + * The total size of a given xdp buffer. + * + * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * This helper is provided as an easy way to load data from a + * xdp buffer. It can be used to load *len* bytes from *offset* from + * the frame associated to *xdp_md*, into the buffer pointed by + * *buf*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * Store *len* bytes from buffer *buf* into the frame + * associated to *xdp_md*, at *offset*. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5206,6 +5264,11 @@ union bpf_attr { FN(get_func_arg), \ FN(get_func_ret), \ FN(get_func_arg_cnt), \ + FN(get_retval), \ + FN(set_retval), \ + FN(xdp_get_buff_len), \ + FN(xdp_load_bytes), \ + FN(xdp_store_bytes), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index cca6e474a085..417d4280d7b5 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -319,6 +319,12 @@ enum { /* RINGS */ enum { + ETHTOOL_TCP_DATA_SPLIT_UNKNOWN = 0, + ETHTOOL_TCP_DATA_SPLIT_DISABLED, + ETHTOOL_TCP_DATA_SPLIT_ENABLED, +}; + +enum { ETHTOOL_A_RINGS_UNSPEC, ETHTOOL_A_RINGS_HEADER, /* nest - _A_HEADER_* */ ETHTOOL_A_RINGS_RX_MAX, /* u32 */ @@ -330,6 +336,7 @@ enum { ETHTOOL_A_RINGS_RX_JUMBO, /* u32 */ ETHTOOL_A_RINGS_TX, /* u32 */ ETHTOOL_A_RINGS_RX_BUF_LEN, /* u32 */ + ETHTOOL_A_RINGS_TCP_DATA_SPLIT, /* u8 */ /* add new constants above here */ __ETHTOOL_A_RINGS_CNT, diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h index eb0a9a5b6e71..51d6bb2f6765 100644 --- a/include/uapi/linux/socket.h +++ b/include/uapi/linux/socket.h @@ -31,4 +31,8 @@ struct __kernel_sockaddr_storage { #define SOCK_BUF_LOCK_MASK (SOCK_SNDBUF_LOCK | SOCK_RCVBUF_LOCK) +#define SOCK_TXREHASH_DEFAULT ((u8)-1) +#define SOCK_TXREHASH_DISABLED 0 +#define SOCK_TXREHASH_ENABLED 1 + #endif /* _UAPI_LINUX_SOCKET_H */ |