diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-07-11 10:55:49 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-07-11 10:55:49 -0700 |
| commit | 237f83dfbe668443b5e31c3c7576125871cca674 (patch) | |
| tree | 11848a8d0aa414a1d3ce2024e181071b1d9dea08 /include | |
| parent | 8f6ccf6159aed1f04c6d179f61f6fb2691261e84 (diff) | |
| parent | 1ff2f0fa450ea4e4f87793d9ed513098ec6e12be (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Some highlights from this development cycle:
1) Big refactoring of ipv6 route and neigh handling to support
nexthop objects configurable as units from userspace. From David
Ahern.
2) Convert explored_states in BPF verifier into a hash table,
significantly decreased state held for programs with bpf2bpf
calls, from Alexei Starovoitov.
3) Implement bpf_send_signal() helper, from Yonghong Song.
4) Various classifier enhancements to mvpp2 driver, from Maxime
Chevallier.
5) Add aRFS support to hns3 driver, from Jian Shen.
6) Fix use after free in inet frags by allocating fqdirs dynamically
and reworking how rhashtable dismantle occurs, from Eric Dumazet.
7) Add act_ctinfo packet classifier action, from Kevin
Darbyshire-Bryant.
8) Add TFO key backup infrastructure, from Jason Baron.
9) Remove several old and unused ISDN drivers, from Arnd Bergmann.
10) Add devlink notifications for flash update status to mlxsw driver,
from Jiri Pirko.
11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.
12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.
13) Various enhancements to ipv6 flow label handling, from Eric
Dumazet and Willem de Bruijn.
14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
der Merwe, and others.
15) Various improvements to axienet driver including converting it to
phylink, from Robert Hancock.
16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.
17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
Radulescu.
18) Add devlink health reporting to mlx5, from Moshe Shemesh.
19) Convert stmmac over to phylink, from Jose Abreu.
20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
Shalom Toledo.
21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.
22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.
23) Track spill/fill of constants in BPF verifier, from Alexei
Starovoitov.
24) Support bounded loops in BPF, from Alexei Starovoitov.
25) Various page_pool API fixes and improvements, from Jesper Dangaard
Brouer.
26) Just like ipv4, support ref-countless ipv6 route handling. From
Wei Wang.
27) Support VLAN offloading in aquantia driver, from Igor Russkikh.
28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.
29) Add flower GRE encap/decap support to nfp driver, from Pieter
Jansen van Vuuren.
30) Protect against stack overflow when using act_mirred, from John
Hurley.
31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.
32) Use page_pool API in netsec driver, Ilias Apalodimas.
33) Add Google gve network driver, from Catherine Sullivan.
34) More indirect call avoidance, from Paolo Abeni.
35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.
36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.
37) Add MPLS manipulation actions to TC, from John Hurley.
38) Add sending a packet to connection tracking from TC actions, and
then allow flower classifier matching on conntrack state. From
Paul Blakey.
39) Netfilter hw offload support, from Pablo Neira Ayuso"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
net/mlx5e: Return in default case statement in tx_post_resync_params
mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
net: dsa: add support for BRIDGE_MROUTER attribute
pkt_sched: Include const.h
net: netsec: remove static declaration for netsec_set_tx_de()
net: netsec: remove superfluous if statement
netfilter: nf_tables: add hardware offload support
net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
net: flow_offload: add flow_block_cb_is_busy() and use it
net: sched: remove tcf block API
drivers: net: use flow block API
net: sched: use flow block API
net: flow_offload: add flow_block_cb_{priv, incref, decref}()
net: flow_offload: add list handling functions
net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
net: flow_offload: add flow_block_cb_setup_simple()
net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
...
Diffstat (limited to 'include')
160 files changed, 3940 insertions, 2762 deletions
diff --git a/include/dt-bindings/net/ti-dp83867.h b/include/dt-bindings/net/ti-dp83867.h index 3b48847cd83b..6fc4b445d3a1 100644 --- a/include/dt-bindings/net/ti-dp83867.h +++ b/include/dt-bindings/net/ti-dp83867.h @@ -48,4 +48,6 @@ #define DP83867_CLK_O_SEL_CHN_C_TCLK 0xA #define DP83867_CLK_O_SEL_CHN_D_TCLK 0xB #define DP83867_CLK_O_SEL_REF_CLK 0xC +/* Special flag to indicate clock should be off */ +#define DP83867_CLK_O_SEL_OFF 0xFFFFFFFF #endif diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 191621ff7594..ca956b672ac0 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -61,12 +61,14 @@ enum virtchnl_status_code { #define VIRTCHNL_ERR_PARAM VIRTCHNL_STATUS_ERR_PARAM #define VIRTCHNL_STATUS_NOT_SUPPORTED VIRTCHNL_STATUS_ERR_NOT_SUPPORTED +#define VIRTCHNL_LINK_SPEED_2_5GB_SHIFT 0x0 #define VIRTCHNL_LINK_SPEED_100MB_SHIFT 0x1 #define VIRTCHNL_LINK_SPEED_1000MB_SHIFT 0x2 #define VIRTCHNL_LINK_SPEED_10GB_SHIFT 0x3 #define VIRTCHNL_LINK_SPEED_40GB_SHIFT 0x4 #define VIRTCHNL_LINK_SPEED_20GB_SHIFT 0x5 #define VIRTCHNL_LINK_SPEED_25GB_SHIFT 0x6 +#define VIRTCHNL_LINK_SPEED_5GB_SHIFT 0x7 enum virtchnl_link_speed { VIRTCHNL_LINK_SPEED_UNKNOWN = 0, @@ -76,6 +78,8 @@ enum virtchnl_link_speed { VIRTCHNL_LINK_SPEED_40GB = BIT(VIRTCHNL_LINK_SPEED_40GB_SHIFT), VIRTCHNL_LINK_SPEED_20GB = BIT(VIRTCHNL_LINK_SPEED_20GB_SHIFT), VIRTCHNL_LINK_SPEED_25GB = BIT(VIRTCHNL_LINK_SPEED_25GB_SHIFT), + VIRTCHNL_LINK_SPEED_2_5GB = BIT(VIRTCHNL_LINK_SPEED_2_5GB_SHIFT), + VIRTCHNL_LINK_SPEED_5GB = BIT(VIRTCHNL_LINK_SPEED_5GB_SHIFT), }; /* for hsplit_0 field of Rx HMC context */ diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index a7f7a98ec39d..169fd25f6bc2 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -6,6 +6,7 @@ #include <linux/errno.h> #include <linux/jump_label.h> #include <linux/percpu.h> +#include <linux/percpu-refcount.h> #include <linux/rbtree.h> #include <uapi/linux/bpf.h> @@ -71,11 +72,17 @@ struct cgroup_bpf { u32 flags[MAX_BPF_ATTACH_TYPE]; /* temp storage for effective prog array used by prog_attach/detach */ - struct bpf_prog_array __rcu *inactive; + struct bpf_prog_array *inactive; + + /* reference counter used to detach bpf programs after cgroup removal */ + struct percpu_ref refcnt; + + /* cgroup_bpf is released using a work queue */ + struct work_struct release_work; }; -void cgroup_bpf_put(struct cgroup *cgrp); int cgroup_bpf_inherit(struct cgroup *cgrp); +void cgroup_bpf_offline(struct cgroup *cgrp); int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); @@ -117,6 +124,14 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, loff_t *ppos, void **new_buf, enum bpf_attach_type type); +int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level, + int *optname, char __user *optval, + int *optlen, char **kernel_optval); +int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, + int optname, char __user *optval, + int __user *optlen, int max_optlen, + int retval); + static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { @@ -279,6 +294,38 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, __ret; \ }) +#define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \ + kernel_optval) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_setsockopt(sock, level, \ + optname, optval, \ + optlen, \ + kernel_optval); \ + __ret; \ +}) + +#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + get_user(__ret, optlen); \ + __ret; \ +}) + +#define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen, \ + max_optlen, retval) \ +({ \ + int __ret = retval; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_getsockopt(sock, level, \ + optname, optval, \ + optlen, max_optlen, \ + retval); \ + __ret; \ +}) + int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, struct bpf_prog *prog); int cgroup_bpf_prog_detach(const union bpf_attr *attr, @@ -289,8 +336,8 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, struct bpf_prog; struct cgroup_bpf {}; -static inline void cgroup_bpf_put(struct cgroup *cgrp) {} static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } +static inline void cgroup_bpf_offline(struct cgroup *cgrp) {} static inline int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, @@ -350,6 +397,11 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; }) +#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ + optlen, max_optlen, retval) ({ retval; }) +#define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \ + kernel_optval) ({ 0; }) #define for_each_cgroup_storage_type(stype) for (; false; ) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b92ef9f73e42..18f4cc2c6acd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -63,6 +63,11 @@ struct bpf_map_ops { u64 imm, u32 *off); }; +struct bpf_map_memory { + u32 pages; + struct user_struct *user; +}; + struct bpf_map { /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). @@ -83,7 +88,7 @@ struct bpf_map { u32 btf_key_type_id; u32 btf_value_type_id; struct btf *btf; - u32 pages; + struct bpf_map_memory memory; bool unpriv_array; bool frozen; /* write-once */ /* 48 bytes hole */ @@ -91,8 +96,7 @@ struct bpf_map { /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ - struct user_struct *user ____cacheline_aligned; - atomic_t refcnt; + atomic_t refcnt ____cacheline_aligned; atomic_t usercnt; struct work_struct work; char name[BPF_OBJ_NAME_LEN]; @@ -273,6 +277,7 @@ enum bpf_reg_type { PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */ PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ + PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ }; /* The information passed from prog-specific *_is_valid_access @@ -367,6 +372,7 @@ struct bpf_prog_aux { u32 id; 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 verifier_zext; /* Zero extensions has been inserted by verifier. */ bool offload_requested; struct bpf_prog **func; void *jit_data; /* JIT specific data. arch dependent */ @@ -510,17 +516,18 @@ struct bpf_prog_array { }; struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); -void bpf_prog_array_free(struct bpf_prog_array __rcu *progs); -int bpf_prog_array_length(struct bpf_prog_array __rcu *progs); -int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, +void bpf_prog_array_free(struct bpf_prog_array *progs); +int bpf_prog_array_length(struct bpf_prog_array *progs); +bool bpf_prog_array_is_empty(struct bpf_prog_array *array); +int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs, __u32 __user *prog_ids, u32 cnt); -void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs, +void bpf_prog_array_delete_safe(struct bpf_prog_array *progs, struct bpf_prog *old_prog); -int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array, +int bpf_prog_array_copy_info(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt); -int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, +int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, struct bpf_prog_array **new_array); @@ -548,6 +555,56 @@ _out: \ _ret; \ }) +/* To be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs + * so BPF programs can request cwr for TCP packets. + * + * Current cgroup skb programs can only return 0 or 1 (0 to drop the + * packet. This macro changes the behavior so the low order bit + * indicates whether the packet should be dropped (0) or not (1) + * and the next bit is a congestion notification bit. This could be + * used by TCP to call tcp_enter_cwr() + * + * Hence, new allowed return values of CGROUP EGRESS BPF programs are: + * 0: drop packet + * 1: keep packet + * 2: drop packet and cn + * 3: keep packet and cn + * + * This macro then converts it to one of the NET_XMIT or an error + * code that is then interpreted as drop packet (and no cn): + * 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 + */ +#define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ + ({ \ + struct bpf_prog_array_item *_item; \ + struct bpf_prog *_prog; \ + struct bpf_prog_array *_array; \ + u32 ret; \ + u32 _ret = 1; \ + u32 _cn = 0; \ + preempt_disable(); \ + rcu_read_lock(); \ + _array = rcu_dereference(array); \ + _item = &_array->items[0]; \ + while ((_prog = READ_ONCE(_item->prog))) { \ + bpf_cgroup_storage_set(_item->cgroup_storage); \ + ret = func(_prog, ctx); \ + _ret &= (ret & 1); \ + _cn |= (ret & 2); \ + _item++; \ + } \ + rcu_read_unlock(); \ + preempt_enable(); \ + if (_ret) \ + _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ + else \ + _ret = (_cn ? NET_XMIT_DROP : -EPERM); \ + _ret; \ + }) + #define BPF_PROG_RUN_ARRAY(array, ctx, func) \ __BPF_PROG_RUN_ARRAY(array, ctx, func, false) @@ -592,9 +649,12 @@ struct bpf_map *__bpf_map_get(struct fd f); struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); -int bpf_map_precharge_memlock(u32 pages); int bpf_map_charge_memlock(struct bpf_map *map, u32 pages); void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages); +int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size); +void bpf_map_charge_finish(struct bpf_map_memory *mem); +void bpf_map_charge_move(struct bpf_map_memory *dst, + struct bpf_map_memory *src); void *bpf_map_area_alloc(size_t size, int numa_node); void bpf_map_area_free(void *base); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); @@ -992,6 +1052,7 @@ extern const struct bpf_func_proto bpf_spin_unlock_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto; extern const struct bpf_func_proto bpf_strtol_proto; extern const struct bpf_func_proto bpf_strtoul_proto; +extern const struct bpf_func_proto bpf_tcp_sock_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); @@ -1040,6 +1101,15 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); + +bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info); + +u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size); #else static inline bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, @@ -1056,6 +1126,21 @@ static inline u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, { return 0; } +static inline bool bpf_xdp_sock_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + return false; +} + +static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size) +{ + return 0; +} #endif /* CONFIG_INET */ #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 5a9975678d6f..eec5aeeeaf92 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -30,6 +30,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable) #ifdef CONFIG_CGROUP_BPF BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt) #endif #ifdef CONFIG_BPF_LIRC_MODE2 BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 519aafabc40c..5fe99f322b1c 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -33,9 +33,11 @@ */ enum bpf_reg_liveness { REG_LIVE_NONE = 0, /* reg hasn't been read or written this branch */ - REG_LIVE_READ, /* reg was read, so we're sensitive to initial value */ - REG_LIVE_WRITTEN, /* reg was written first, screening off later reads */ - REG_LIVE_DONE = 4, /* liveness won't be updating this register anymore */ + REG_LIVE_READ32 = 0x1, /* reg was read, so we're sensitive to initial value */ + REG_LIVE_READ64 = 0x2, /* likewise, but full 64-bit content matters */ + REG_LIVE_READ = REG_LIVE_READ32 | REG_LIVE_READ64, + REG_LIVE_WRITTEN = 0x4, /* reg was written first, screening off later reads */ + REG_LIVE_DONE = 0x8, /* liveness won't be updating this register anymore */ }; struct bpf_reg_state { @@ -128,7 +130,14 @@ struct bpf_reg_state { * pointing to bpf_func_state. */ u32 frameno; + /* Tracks subreg definition. The stored value is the insn_idx of the + * writing insn. This is safe because subreg_def is used before any insn + * patching which only happens after main verification finished. + */ + s32 subreg_def; enum bpf_reg_liveness live; + /* if (!precise && SCALAR_VALUE) min/max/tnum don't affect safety */ + bool precise; }; enum bpf_stack_slot_type { @@ -180,13 +189,77 @@ struct bpf_func_state { struct bpf_stack_state *stack; }; +struct bpf_idx_pair { + u32 prev_idx; + u32 idx; +}; + #define MAX_CALL_FRAMES 8 struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; + struct bpf_verifier_state *parent; + /* + * 'branches' field is the number of branches left to explore: + * 0 - all possible paths from this state reached bpf_exit or + * were safely pruned + * 1 - at least one path is being explored. + * This state hasn't reached bpf_exit + * 2 - at least two paths are being explored. + * This state is an immediate parent of two children. + * One is fallthrough branch with branches==1 and another + * state is pushed into stack (to be explored later) also with + * branches==1. The parent of this state has branches==1. + * The verifier state tree connected via 'parent' pointer looks like: + * 1 + * 1 + * 2 -> 1 (first 'if' pushed into stack) + * 1 + * 2 -> 1 (second 'if' pushed into stack) + * 1 + * 1 + * 1 bpf_exit. + * + * Once do_check() reaches bpf_exit, it calls update_branch_counts() + * and the verifier state tree will look: + * 1 + * 1 + * 2 -> 1 (first 'if' pushed into stack) + * 1 + * 1 -> 1 (second 'if' pushed into stack) + * 0 + * 0 + * 0 bpf_exit. + * After pop_stack() the do_check() will resume at second 'if'. + * + * If is_state_visited() sees a state with branches > 0 it means + * there is a loop. If such state is exactly equal to the current state + * it's an infinite loop. Note states_equal() checks for states + * equvalency, so two states being 'states_equal' does not mean + * infinite loop. The exact comparison is provided by + * states_maybe_looping() function. It's a stronger pre-check and + * much faster than states_equal(). + * + * This algorithm may not find all possible infinite loops or + * loop iteration count may be too high. + * In such cases BPF_COMPLEXITY_LIMIT_INSNS limit kicks in. + */ + u32 branches; + u32 insn_idx; u32 curframe; u32 active_spin_lock; bool speculative; + + /* first and last insn idx of this verifier state */ + u32 first_insn_idx; + u32 last_insn_idx; + /* jmp history recorded from first to last. + * backtracking is using it to go from last to first. + * For most states jmp_history_cnt is [0-3]. + * For loops can go up to ~40. + */ + struct bpf_idx_pair *jmp_history; + u32 jmp_history_cnt; }; #define bpf_get_spilled_reg(slot, frame) \ @@ -229,7 +302,9 @@ struct bpf_insn_aux_data { int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ int sanitize_stack_off; /* stack slot to be cleared */ bool seen; /* this insn was processed by the verifier */ + bool zext_dst; /* this insn zero extends dst reg */ u8 alu_state; /* used in combination with alu_limit */ + bool prune_point; unsigned int orig_idx; /* original instruction index */ }; @@ -299,7 +374,9 @@ struct bpf_verifier_env { } cfg; u32 subprog_cnt; /* number of instructions analyzed by the verifier */ - u32 insn_processed; + u32 prev_insn_processed, insn_processed; + /* number of jmps, calls, exits analyzed so far */ + u32 prev_jmps_processed, jmps_processed; /* total verification time */ u64 verification_time; /* maximum number of verifier states kept in 'branching' instructions */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 3745ecdad925..2af9b1b419f1 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -936,4 +936,22 @@ static inline bool cgroup_task_frozen(struct task_struct *task) #endif /* !CONFIG_CGROUPS */ +#ifdef CONFIG_CGROUP_BPF +static inline void cgroup_bpf_get(struct cgroup *cgrp) +{ + percpu_ref_get(&cgrp->bpf.refcnt); +} + +static inline void cgroup_bpf_put(struct cgroup *cgrp) +{ + percpu_ref_put(&cgrp->bpf.refcnt); +} + +#else /* CONFIG_CGROUP_BPF */ + +static inline void cgroup_bpf_get(struct cgroup *cgrp) {} +static inline void cgroup_bpf_put(struct cgroup *cgrp) {} + +#endif /* CONFIG_CGROUP_BPF */ + #endif /* _LINUX_CGROUP_H */ diff --git a/include/linux/concap.h b/include/linux/concap.h deleted file mode 100644 index 977acb3d1fb2..000000000000 --- a/include/linux/concap.h +++ /dev/null @@ -1,112 +0,0 @@ -/* $Id: concap.h,v 1.3.2.2 2004/01/12 23:08:35 keil Exp $ - * - * Copyright 1997 by Henner Eisen <eis@baty.hanse.de> - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - */ - -#ifndef _LINUX_CONCAP_H -#define _LINUX_CONCAP_H - -#include <linux/skbuff.h> -#include <linux/netdevice.h> - -/* Stuff to support encapsulation protocols genericly. The encapsulation - protocol is processed at the uppermost layer of the network interface. - - Based on a ideas developed in a 'synchronous device' thread in the - linux-x25 mailing list contributed by Alan Cox, Thomasz Motylewski - and Jonathan Naylor. - - For more documetation on this refer to Documentation/isdn/README.concap -*/ - -struct concap_proto_ops; -struct concap_device_ops; - -/* this manages all data needed by the encapsulation protocol - */ -struct concap_proto{ - struct net_device *net_dev; /* net device using our service */ - struct concap_device_ops *dops; /* callbacks provided by device */ - struct concap_proto_ops *pops; /* callbacks provided by us */ - spinlock_t lock; - int flags; - void *proto_data; /* protocol specific private data, to - be accessed via *pops methods only*/ - /* - : - whatever - : - */ -}; - -/* Operations to be supported by the net device. Called by the encapsulation - * protocol entity. No receive method is offered because the encapsulation - * protocol directly calls netif_rx(). - */ -struct concap_device_ops{ - - /* to request data is submitted by device*/ - int (*data_req)(struct concap_proto *, struct sk_buff *); - - /* Control methods must be set to NULL by devices which do not - support connection control.*/ - /* to request a connection is set up */ - int (*connect_req)(struct concap_proto *); - - /* to request a connection is released */ - int (*disconn_req)(struct concap_proto *); -}; - -/* Operations to be supported by the encapsulation protocol. Called by - * device driver. - */ -struct concap_proto_ops{ - - /* create a new encapsulation protocol instance of same type */ - struct concap_proto * (*proto_new) (void); - - /* delete encapsulation protocol instance and free all its resources. - cprot may no loger be referenced after calling this */ - void (*proto_del)(struct concap_proto *cprot); - - /* initialize the protocol's data. To be called at interface startup - or when the device driver resets the interface. All services of the - encapsulation protocol may be used after this*/ - int (*restart)(struct concap_proto *cprot, - struct net_device *ndev, - struct concap_device_ops *dops); - - /* inactivate an encapsulation protocol instance. The encapsulation - protocol may not call any *dops methods after this. */ - int (*close)(struct concap_proto *cprot); - - /* process a frame handed down to us by upper layer */ - int (*encap_and_xmit)(struct concap_proto *cprot, struct sk_buff *skb); - - /* to be called for each data entity received from lower layer*/ - int (*data_ind)(struct concap_proto *cprot, struct sk_buff *skb); - - /* to be called when a connection was set up/down. - Protocols that don't process these primitives might fill in - dummy methods here */ - int (*connect_ind)(struct concap_proto *cprot); - int (*disconn_ind)(struct concap_proto *cprot); - /* - Some network device support functions, like net_header(), rebuild_header(), - and others, that depend solely on the encapsulation protocol, might - be provided here, too. The net device would just fill them in its - corresponding fields when it is opened. - */ -}; - -/* dummy restart/close/connect/reset/disconn methods - */ -extern int concap_nop(struct concap_proto *cprot); - -/* dummy submit method - */ -extern int concap_drop_skb(struct concap_proto *cprot, struct sk_buff *skb); -#endif diff --git a/include/linux/dim.h b/include/linux/dim.h new file mode 100644 index 000000000000..aa9bdd47a648 --- /dev/null +++ b/include/linux/dim.h @@ -0,0 +1,366 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef DIM_H +#define DIM_H + +#include <linux/module.h> + +/** + * Number of events between DIM iterations. + * Causes a moderation of the algorithm run. + */ +#define DIM_NEVENTS 64 + +/** + * Is a difference between values justifies taking an action. + * We consider 10% difference as significant. + */ +#define IS_SIGNIFICANT_DIFF(val, ref) \ + (((100UL * abs((val) - (ref))) / (ref)) > 10) + +/** + * Calculate the gap between two values. + * Take wrap-around and variable size into consideration. + */ +#define BIT_GAP(bits, end, start) ((((end) - (start)) + BIT_ULL(bits)) \ + & (BIT_ULL(bits) - 1)) + +/** + * Structure for CQ moderation values. + * Used for communications between DIM and its consumer. + * + * @usec: CQ timer suggestion (by DIM) + * @pkts: CQ packet counter suggestion (by DIM) + * @cq_period_mode: CQ priod count mode (from CQE/EQE) + */ +struct dim_cq_moder { + u16 usec; + u16 pkts; + u16 comps; + u8 cq_period_mode; +}; + +/** + * Structure for DIM sample data. + * Used for communications between DIM and its consumer. + * + * @time: Sample timestamp + * @pkt_ctr: Number of packets + * @byte_ctr: Number of bytes + * @event_ctr: Number of events + */ +struct dim_sample { + ktime_t time; + u32 pkt_ctr; + u32 byte_ctr; + u16 event_ctr; + u32 comp_ctr; +}; + +/** + * Structure for DIM stats. + * Used for holding current measured rates. + * + * @ppms: Packets per msec + * @bpms: Bytes per msec + * @epms: Events per msec + */ +struct dim_stats { + int ppms; /* packets per msec */ + int bpms; /* bytes per msec */ + int epms; /* events per msec */ + int cpms; /* completions per msec */ + int cpe_ratio; /* ratio of completions to events */ +}; + +/** + * Main structure for dynamic interrupt moderation (DIM). + * Used for holding all information about a specific DIM instance. + * + * @state: Algorithm state (see below) + * @prev_stats: Measured rates from previous iteration (for comparison) + * @start_sample: Sampled data at start of current iteration + * @work: Work to perform on action required + * @profile_ix: Current moderation profile + * @mode: CQ period count mode + * @tune_state: Algorithm tuning state (see below) + * @steps_right: Number of steps taken towards higher moderation + * @steps_left: Number of steps taken towards lower moderation + * @tired: Parking depth counter + */ +struct dim { + u8 state; + struct dim_stats prev_stats; + struct dim_sample start_sample; + struct dim_sample measuring_sample; + struct work_struct work; + u8 profile_ix; + u8 mode; + u8 tune_state; + u8 steps_right; + u8 steps_left; + u8 tired; +}; + +/** + * enum dim_cq_period_mode + * + * These are the modes for CQ period count. + * + * @DIM_CQ_PERIOD_MODE_START_FROM_EQE: Start counting from EQE + * @DIM_CQ_PERIOD_MODE_START_FROM_CQE: Start counting from CQE (implies timer reset) + * @DIM_CQ_PERIOD_NUM_MODES: Number of modes + */ +enum { + DIM_CQ_PERIOD_MODE_START_FROM_EQE = 0x0, + DIM_CQ_PERIOD_MODE_START_FROM_CQE = 0x1, + DIM_CQ_PERIOD_NUM_MODES +}; + +/** + * enum dim_state + * + * These are the DIM algorithm states. + * These will determine if the algorithm is in a valid state to start an iteration. + * + * @DIM_START_MEASURE: This is the first iteration (also after applying a new profile) + * @DIM_MEASURE_IN_PROGRESS: Algorithm is already in progress - check if + * need to perform an action + * @DIM_APPLY_NEW_PROFILE: DIM consumer is currently applying a profile - no need to measure + */ +enum { + DIM_START_MEASURE, + DIM_MEASURE_IN_PROGRESS, + DIM_APPLY_NEW_PROFILE, +}; + +/** + * enum dim_tune_state + * + * These are the DIM algorithm tune states. + * These will determine which action the algorithm should perform. + * + * @DIM_PARKING_ON_TOP: Algorithm found a local top point - exit on significant difference + * @DIM_PARKING_TIRED: Algorithm found a deep top point - don't exit if tired > 0 + * @DIM_GOING_RIGHT: Algorithm is currently trying higher moderation levels + * @DIM_GOING_LEFT: Algorithm is currently trying lower moderation levels + */ +enum { + DIM_PARKING_ON_TOP, + DIM_PARKING_TIRED, + DIM_GOING_RIGHT, + DIM_GOING_LEFT, +}; + +/** + * enum dim_stats_state + * + * These are the DIM algorithm statistics states. + * These will determine the verdict of current iteration. + * + * @DIM_STATS_WORSE: Current iteration shows worse performance than before + * @DIM_STATS_WORSE: Current iteration shows same performance than before + * @DIM_STATS_WORSE: Current iteration shows better performance than before + */ +enum { + DIM_STATS_WORSE, + DIM_STATS_SAME, + DIM_STATS_BETTER, +}; + +/** + * enum dim_step_result + * + * These are the DIM algorithm step results. + * These describe the result of a step. + * + * @DIM_STEPPED: Performed a regular step + * @DIM_TOO_TIRED: Same kind of step was done multiple times - should go to + * tired parking + * @DIM_ON_EDGE: Stepped to the most left/right profile + */ +enum { + DIM_STEPPED, + DIM_TOO_TIRED, + DIM_ON_EDGE, +}; + +/** + * dim_on_top - check if current state is a good place to stop (top location) + * @dim: DIM context + * + * Check if current profile is a good place to park at. + * This will result in reducing the DIM checks frequency as we assume we + * shouldn't probably change profiles, unless traffic pattern wasn't changed. + */ +bool dim_on_top(struct dim *dim); + +/** + * dim_turn - change profile alterning direction + * @dim: DIM context + * + * Go left if we were going right and vice-versa. + * Do nothing if currently parking. + */ +void dim_turn(struct dim *dim); + +/** + * dim_park_on_top - enter a parking state on a top location + * @dim: DIM context + * + * Enter parking state. + * Clear all movement history. + */ +void dim_park_on_top(struct dim *dim); + +/** + * dim_park_tired - enter a tired parking state + * @dim: DIM context + * + * Enter parking state. + * Clear all movement history and cause DIM checks frequency to reduce. + */ +void dim_park_tired(struct dim *dim); + +/** + * dim_calc_stats - calculate the difference between two samples + * @start: start sample + * @end: end sample + * @curr_stats: delta between samples + * + * Calculate the delta between two samples (in data rates). + * Takes into consideration counter wrap-around. + */ +void dim_calc_stats(struct dim_sample *start, struct dim_sample *end, + struct dim_stats *curr_stats); + +/** + * dim_update_sample - set a sample's fields with give values + * @event_ctr: number of events to set + * @packets: number of packets to set + * @bytes: number of bytes to set + * @s: DIM sample + */ +static inline void +dim_update_sample(u16 event_ctr, u64 packets, u64 bytes, struct dim_sample *s) +{ + s->time = ktime_get(); + s->pkt_ctr = packets; + s->byte_ctr = bytes; + s->event_ctr = event_ctr; +} + +/** + * dim_update_sample_with_comps - set a sample's fields with given + * values including the completion parameter + * @event_ctr: number of events to set + * @packets: number of packets to set + * @bytes: number of bytes to set + * @comps: number of completions to set + * @s: DIM sample + */ +static inline void +dim_update_sample_with_comps(u16 event_ctr, u64 packets, u64 bytes, u64 comps, + struct dim_sample *s) +{ + dim_update_sample(event_ctr, packets, bytes, s); + s->comp_ctr = comps; +} + +/* Net DIM */ + +/* + * Net DIM profiles: + * There are different set of profiles for each CQ period mode. + * There are different set of profiles for RX/TX CQs. + * Each profile size must be of NET_DIM_PARAMS_NUM_PROFILES + */ +#define NET_DIM_PARAMS_NUM_PROFILES 5 +#define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256 +#define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128 +#define NET_DIM_DEF_PROFILE_CQE 1 +#define NET_DIM_DEF_PROFILE_EQE 1 + +#define NET_DIM_RX_EQE_PROFILES { \ + {1, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {8, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {64, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {128, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {256, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ +} + +#define NET_DIM_RX_CQE_PROFILES { \ + {2, 256}, \ + {8, 128}, \ + {16, 64}, \ + {32, 64}, \ + {64, 64} \ +} + +#define NET_DIM_TX_EQE_PROFILES { \ + {1, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {8, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {32, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {64, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {128, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE} \ +} + +#define NET_DIM_TX_CQE_PROFILES { \ + {5, 128}, \ + {8, 64}, \ + {16, 32}, \ + {32, 32}, \ + {64, 32} \ +} + +static const struct dim_cq_moder +rx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { + NET_DIM_RX_EQE_PROFILES, + NET_DIM_RX_CQE_PROFILES, +}; + +static const struct dim_cq_moder +tx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { + NET_DIM_TX_EQE_PROFILES, + NET_DIM_TX_CQE_PROFILES, +}; + +/** + * net_dim_get_rx_moderation - provide a CQ moderation object for the given RX profile + * @cq_period_mode: CQ period mode + * @ix: Profile index + */ +struct dim_cq_moder net_dim_get_rx_moderation(u8 cq_period_mode, int ix); + +/** + * net_dim_get_def_rx_moderation - provide the default RX moderation + * @cq_period_mode: CQ period mode + */ +struct dim_cq_moder net_dim_get_def_rx_moderation(u8 cq_period_mode); + +/** + * net_dim_get_tx_moderation - provide a CQ moderation object for the given TX profile + * @cq_period_mode: CQ period mode + * @ix: Profile index + */ +struct dim_cq_moder net_dim_get_tx_moderation(u8 cq_period_mode, int ix); + +/** + * net_dim_get_def_tx_moderation - provide the default TX moderation + * @cq_period_mode: CQ period mode + */ +struct dim_cq_moder net_dim_get_def_tx_moderation(u8 cq_period_mode); + +/** + * net_dim - main DIM algorithm entry point + * @dim: DIM instance information + * @end_sample: Current data measurement + * + * Called by the consumer. + * This is the main logic of the algorithm, where data is processed in order to decide on next + * required action. + */ +void net_dim(struct dim *dim, struct dim_sample end_sample); + +#endif /* DIM_H */ diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 3911e0586478..0aa803c451a3 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -20,9 +20,6 @@ int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); -struct sk_buff *dsa_8021q_rcv(struct sk_buff *skb, struct net_device *netdev, - struct packet_type *pt, u16 *tpid, u16 *tci); - u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); @@ -31,6 +28,8 @@ int dsa_8021q_rx_switch_id(u16 vid); int dsa_8021q_rx_source_port(u16 vid); +struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb); + #else int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, @@ -45,12 +44,6 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, return NULL; } -struct sk_buff *dsa_8021q_rcv(struct sk_buff *skb, struct net_device *netdev, - struct packet_type *pt, u16 *tpid, u16 *tci) -{ - return NULL; -} - u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port) { return 0; @@ -71,6 +64,11 @@ int dsa_8021q_rx_source_port(u16 vid) return 0; } +struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb) +{ + return NULL; +} + #endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */ #endif /* _NET_DSA_8021Q_H */ diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index e46e18c47d41..79435cfc20eb 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -12,6 +12,7 @@ #include <net/dsa.h> #define ETH_P_SJA1105 ETH_P_DSA_8021Q +#define ETH_P_SJA1105_META 0x0008 /* IEEE 802.3 Annex 57A: Slow Protocols PDUs (01:80:C2:xx:xx:xx) */ #define SJA1105_LINKLOCAL_FILTER_A 0x0180C2000000ull @@ -20,8 +21,41 @@ #define SJA1105_LINKLOCAL_FILTER_B 0x011B19000000ull #define SJA1105_LINKLOCAL_FILTER_B_MASK 0xFFFFFF000000ull +/* Source and Destination MAC of follow-up meta frames. + * Whereas the choice of SMAC only affects the unique identification of the + * switch as sender of meta frames, the DMAC must be an address that is present + * in the DSA master port's multicast MAC filter. + * 01-80-C2-00-00-0E is a good choice for this, as all profiles of IEEE 1588 + * over L2 use this address for some purpose already. + */ +#define SJA1105_META_SMAC 0x222222222222ull +#define SJA1105_META_DMAC 0x0180C200000Eull + +/* Global tagger data: each struct sja1105_port has a reference to + * the structure defined in struct sja1105_private. + */ +struct sja1105_tagger_data { + struct sk_buff_head skb_rxtstamp_queue; + struct work_struct rxtstamp_work; + struct sk_buff *stampable_skb; + /* Protects concurrent access to the meta state machine + * from taggers running on multiple ports on SMP systems + */ + spinlock_t meta_lock; + bool hwts_rx_en; +}; + +struct sja1105_skb_cb { + u32 meta_tstamp; +}; + +#define SJA1105_SKB_CB(skb) \ + ((struct sja1105_skb_cb *)DSA_SKB_CB_PRIV(skb)) + struct sja1105_port { + struct sja1105_tagger_data *data; struct dsa_port *dp; + bool hwts_tx_en; int mgmt_slot; }; diff --git a/include/linux/filter.h b/include/linux/filter.h index 7148bab96943..6d944369ca87 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -160,6 +160,20 @@ struct ctl_table_header; .off = 0, \ .imm = IMM }) +/* Special form of mov32, used for doing explicit zero extension on dst. */ +#define BPF_ZEXT_REG(DST) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = DST, \ + .off = 0, \ + .imm = 1 }) + +static inline bool insn_is_zext(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU | BPF_MOV | BPF_X) && insn->imm == 1; +} + /* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */ #define BPF_LD_IMM64(DST, IMM) \ BPF_LD_IMM64_RAW(DST, 0, IMM) @@ -512,7 +526,8 @@ struct bpf_prog { blinded:1, /* Was blinded */ is_func:1, /* program is a bpf function */ kprobe_override:1, /* Do we override a kprobe? */ - has_callchain_buf:1; /* callchain buffer allocated? */ + has_callchain_buf:1, /* callchain buffer allocated? */ + enforce_expected_attach_type:1; /* Enforce expected_attach_type checking at attach time */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ @@ -563,8 +578,9 @@ struct bpf_skb_data_end { }; struct bpf_redirect_info { - u32 ifindex; u32 flags; + u32 tgt_index; + void *tgt_value; struct bpf_map *map; struct bpf_map *map_to_flush; u32 kern_flags; @@ -731,6 +747,12 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) return size <= size_default && (size & (size - 1)) == 0; } +#define bpf_ctx_wide_store_ok(off, size, type, field) \ + (size == sizeof(__u64) && \ + off >= offsetof(type, field) && \ + off + sizeof(__u64) <= offsetofend(type, field) && \ + off % sizeof(__u64) == 0) + #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) static inline void bpf_prog_lock_ro(struct bpf_prog *fp) @@ -811,6 +833,7 @@ u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); +bool bpf_jit_needs_zext(void); bool bpf_helper_changes_pkt_data(void *func); static inline bool bpf_dump_raw_ok(void) @@ -1183,4 +1206,14 @@ struct bpf_sysctl_kern { u64 tmp_reg; }; +struct bpf_sockopt_kern { + struct sock *sk; + u8 *optval; + u8 *optval_end; + s32 level; + s32 optname; + s32 optlen; + s32 retval; +}; + #endif /* __LINUX_FILTER_H__ */ diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 1308126fc384..e982b8913b73 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -14,6 +14,7 @@ #ifndef _LINUX_I2C_H #define _LINUX_I2C_H +#include <linux/acpi.h> /* for acpi_handle */ #include <linux/mod_devicetable.h> #include <linux/device.h> /* for struct device */ #include <linux/sched.h> /* for completion */ @@ -981,6 +982,7 @@ bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, u32 i2c_acpi_find_bus_speed(struct device *dev); struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, struct i2c_board_info *info); +struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle); #else static inline bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c) @@ -996,6 +998,10 @@ static inline struct i2c_client *i2c_acpi_new_device(struct device *dev, { return NULL; } +static inline struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle) +{ + return NULL; +} #endif /* CONFIG_ACPI */ #endif /* _LINUX_I2C_H */ diff --git a/include/linux/idr.h b/include/linux/idr.h index ee7abae143d3..4ec8986e5dfb 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -191,14 +191,17 @@ static inline void idr_preload_end(void) * idr_for_each_entry_ul() - Iterate over an IDR's elements of a given type. * @idr: IDR handle. * @entry: The type * to use as cursor. + * @tmp: A temporary placeholder for ID. * @id: Entry ID. * * @entry and @id do not need to be initialized before the loop, and * after normal termination @entry is left with the value NULL. This * is convenient for a "not found" value. */ -#define idr_for_each_entry_ul(idr, entry, id) \ - for (id = 0; ((entry) = idr_get_next_ul(idr, &(id))) != NULL; ++id) +#define idr_for_each_entry_ul(idr, entry, tmp, id) \ + for (tmp = 0, id = 0; \ + tmp <= id && ((entry) = idr_get_next_ul(idr, &(id))) != NULL; \ + tmp = id, ++id) /** * idr_for_each_entry_continue() - Continue iteration over an IDR's elements of a given type @@ -213,6 +216,20 @@ static inline void idr_preload_end(void) entry; \ ++id, (entry) = idr_get_next((idr), &(id))) +/** + * idr_for_each_entry_continue_ul() - Continue iteration over an IDR's elements of a given type + * @idr: IDR handle. + * @entry: The type * to use as a cursor. + * @tmp: A temporary placeholder for ID. + * @id: Entry ID. + * + * Continue to iterate over entries, continuing after the current position. + */ +#define idr_for_each_entry_continue_ul(idr, entry, tmp, id) \ + for (tmp = id; \ + tmp <= id && ((entry) = idr_get_next_ul(idr, &(id))) != NULL; \ + tmp = id, ++id) + /* * IDA - ID Allocator, use when translation from id to pointer isn't necessary. */ diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 42690007d612..8511fadc0935 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2609,6 +2609,7 @@ enum ieee80211_key_len { #define FILS_ERP_MAX_RRK_LEN 64 #define PMK_MAX_LEN 64 +#define SAE_PASSWORD_MAX_LEN 128 /* Public action codes (IEEE Std 802.11-2016, 9.6.8.1, Table 9-307) */ enum ieee80211_pub_actioncode { @@ -2709,6 +2710,13 @@ enum ieee80211_tdls_actioncode { #define WLAN_EXT_CAPA10_TWT_REQUESTER_SUPPORT BIT(5) #define WLAN_EXT_CAPA10_TWT_RESPONDER_SUPPORT BIT(6) +/* + * When set, indicates that the AP is able to tolerate 26-tone RU UL + * OFDMA transmissions using HE TB PPDU from OBSS (not falsely classify the + * 26-tone RU UL OFDMA transmissions as radar pulses). + */ +#define WLAN_EXT_CAPA10_OBSS_NARROW_BW_RU_TOLERANCE_SUPPORT BIT(7) + /* Defines support for enhanced multi-bssid advertisement*/ #define WLAN_EXT_CAPA11_EMA_SUPPORT BIT(1) diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index f3fab5d0ea97..9e57c4411734 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -88,6 +88,8 @@ static inline bool br_multicast_router(const struct net_device *dev) #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING) bool br_vlan_enabled(const struct net_device *dev); int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid); +int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid); +int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto); int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); #else @@ -101,6 +103,16 @@ static inline int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) return -EINVAL; } +static inline int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto) +{ + return -EINVAL; +} + +static inline int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid) +{ + return -EINVAL; +} + static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo) { diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h new file mode 100644 index 000000000000..b4f5403383fc --- /dev/null +++ b/include/linux/if_rmnet.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * Copyright (c) 2013-2019, The Linux Foundation. All rights reserved. + */ + +#ifndef _LINUX_IF_RMNET_H_ +#define _LINUX_IF_RMNET_H_ + +struct rmnet_map_header { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u8 pad_len:6; + u8 reserved_bit:1; + u8 cd_bit:1; +#elif defined (__BIG_ENDIAN_BITFIELD) + u8 cd_bit:1; + u8 reserved_bit:1; + u8 pad_len:6; +#else +#error "Please fix <asm/byteorder.h>" +#endif + u8 mux_id; + __be16 pkt_len; +} __aligned(1); + +struct rmnet_map_dl_csum_trailer { + u8 reserved1; +#if defined(__LITTLE_ENDIAN_BITFIELD) + u8 valid:1; + u8 reserved2:7; +#elif defined (__BIG_ENDIAN_BITFIELD) + u8 reserved2:7; + u8 valid:1; +#else +#error "Please fix <asm/byteorder.h>" +#endif + u16 csum_start_offset; + u16 csum_length; + __be16 csum_value; +} __aligned(1); + +struct rmnet_map_ul_csum_header { + __be16 csum_start_offset; +#if defined(__LITTLE_ENDIAN_BITFIELD) + u16 csum_insert_offset:14; + u16 udp_ip4_ind:1; + u16 csum_enabled:1; +#elif defined (__BIG_ENDIAN_BITFIELD) + u16 csum_enabled:1; + u16 udp_ip4_ind:1; + u16 csum_insert_offset:14; +#else +#error "Please fix <asm/byteorder.h>" +#endif +} __aligned(1); + +#endif /* !(_LINUX_IF_RMNET_H_) */ diff --git a/include/linux/if_tap.h b/include/linux/if_tap.h index 8e66866c11be..915a187cfabd 100644 --- a/include/linux/if_tap.h +++ b/include/linux/if_tap.h @@ -62,7 +62,6 @@ struct tap_dev { struct tap_queue { struct sock sk; struct socket sock; - struct socket_wq wq; int vnet_hdr_sz; struct tap_dev __rcu *tap; struct file *file; diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 9cbbd1baaf85..463047d0190b 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -60,8 +60,8 @@ struct ip_mc_socklist { struct ip_sf_list { struct ip_sf_list *sf_next; - __be32 sf_inaddr; unsigned long sf_count[2]; /* include/exclude counts */ + __be32 sf_inaddr; unsigned char sf_gsresp; /* include in g & s response? */ unsigned char sf_oldin; /* change state */ unsigned char sf_crcount; /* retrans. left to send */ diff --git a/include/linux/in.h b/include/linux/in.h index 4d2fedfb753a..1873ef642605 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -63,7 +63,7 @@ static inline bool ipv4_is_all_snoopers(__be32 addr) static inline bool ipv4_is_zeronet(__be32 addr) { - return (addr & htonl(0xff000000)) == htonl(0x00000000); + return (addr == 0); } /* Special-Use IPv4 Addresses (RFC3330) */ diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 367dc2a0f84a..3515ca64e638 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -26,7 +26,7 @@ struct in_device { struct net_device *dev; refcount_t refcnt; int dead; - struct in_ifaddr *ifa_list; /* IP ifaddr chain */ + struct in_ifaddr __rcu *ifa_list;/* IP ifaddr chain */ struct ip_mc_list __rcu *mc_list; /* IP multicast filter chain */ struct ip_mc_list __rcu * __rcu *mc_hash; @@ -136,7 +136,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) struct in_ifaddr { struct hlist_node hash; - struct in_ifaddr *ifa_next; + struct in_ifaddr __rcu *ifa_next; struct in_device *ifa_dev; struct rcu_head rcu_head; __be32 ifa_local; @@ -186,7 +186,7 @@ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr); -static __inline__ bool inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) +static inline bool inet_ifa_match(__be32 addr, const struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); } @@ -206,14 +206,13 @@ static __inline__ bool bad_mask(__be32 mask, __be32 addr) return false; } -#define for_primary_ifa(in_dev) { struct in_ifaddr *ifa; \ - for (ifa = (in_dev)->ifa_list; ifa && !(ifa->ifa_flags&IFA_F_SECONDARY); ifa = ifa->ifa_next) +#define in_dev_for_each_ifa_rtnl(ifa, in_dev) \ + for (ifa = rtnl_dereference((in_dev)->ifa_list); ifa; \ + ifa = rtnl_dereference(ifa->ifa_next)) -#define for_ifa(in_dev) { struct in_ifaddr *ifa; \ - for (ifa = (in_dev)->ifa_list; ifa; ifa = ifa->ifa_next) - - -#define endfor_ifa(in_dev) } +#define in_dev_for_each_ifa_rcu(ifa, in_dev) \ + for (ifa = rcu_dereference((in_dev)->ifa_list); ifa; \ + ifa = rcu_dereference(ifa->ifa_next)) static inline struct in_device *__in_dev_get_rcu(const struct net_device *dev) { diff --git a/include/linux/isdn.h b/include/linux/isdn.h deleted file mode 100644 index df97c8444f5d..000000000000 --- a/include/linux/isdn.h +++ /dev/null @@ -1,473 +0,0 @@ -/* $Id: isdn.h,v 1.125.2.3 2004/02/10 01:07:14 keil Exp $ - * - * Main header for the Linux ISDN subsystem (linklevel). - * - * Copyright 1994,95,96 by Fritz Elfert (fritz@isdn4linux.de) - * Copyright 1995,96 by Thinking Objects Software GmbH Wuerzburg - * Copyright 1995,96 by Michael Hipp (Michael.Hipp@student.uni-tuebingen.de) - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ -#ifndef __ISDN_H__ -#define __ISDN_H__ - - -#include <linux/errno.h> -#include <linux/fs.h> -#include <linux/major.h> -#include <asm/io.h> -#include <linux/kernel.h> -#include <linux/signal.h> -#include <linux/slab.h> -#include <linux/timer.h> -#include <linux/wait.h> -#include <linux/tty.h> -#include <linux/tty_flip.h> -#include <linux/serial_reg.h> -#include <linux/fcntl.h> -#include <linux/types.h> -#include <linux/interrupt.h> -#include <linux/ip.h> -#include <linux/in.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/skbuff.h> -#include <linux/tcp.h> -#include <linux/mutex.h> -#include <uapi/linux/isdn.h> - -#define ISDN_TTY_MAJOR 43 -#define ISDN_TTYAUX_MAJOR 44 -#define ISDN_MAJOR 45 - -/* The minor-devicenumbers for Channel 0 and 1 are used as arguments for - * physical Channel-Mapping, so they MUST NOT be changed without changing - * the correspondent code in isdn.c - */ - -#define ISDN_MINOR_B 0 -#define ISDN_MINOR_BMAX (ISDN_MAX_CHANNELS-1) -#define ISDN_MINOR_CTRL 64 -#define ISDN_MINOR_CTRLMAX (64 + (ISDN_MAX_CHANNELS-1)) -#define ISDN_MINOR_PPP 128 -#define ISDN_MINOR_PPPMAX (128 + (ISDN_MAX_CHANNELS-1)) -#define ISDN_MINOR_STATUS 255 - -#ifdef CONFIG_ISDN_PPP - -#ifdef CONFIG_ISDN_PPP_VJ -# include <net/slhc_vj.h> -#endif - -#include <linux/ppp_defs.h> -#include <linux/ppp-ioctl.h> - -#include <linux/isdn_ppp.h> -#endif - -#ifdef CONFIG_ISDN_X25 -# include <linux/concap.h> -#endif - -#include <linux/isdnif.h> - -#define ISDN_DRVIOCTL_MASK 0x7f /* Mask for Device-ioctl */ - -/* Until now unused */ -#define ISDN_SERVICE_VOICE 1 -#define ISDN_SERVICE_AB 1<<1 -#define ISDN_SERVICE_X21 1<<2 -#define ISDN_SERVICE_G4 1<<3 -#define ISDN_SERVICE_BTX 1<<4 -#define ISDN_SERVICE_DFUE 1<<5 -#define ISDN_SERVICE_X25 1<<6 -#define ISDN_SERVICE_TTX 1<<7 -#define ISDN_SERVICE_MIXED 1<<8 -#define ISDN_SERVICE_FW 1<<9 -#define ISDN_SERVICE_GTEL 1<<10 -#define ISDN_SERVICE_BTXN 1<<11 -#define ISDN_SERVICE_BTEL 1<<12 - -/* Macros checking plain usage */ -#define USG_NONE(x) ((x & ISDN_USAGE_MASK)==ISDN_USAGE_NONE) -#define USG_RAW(x) ((x & ISDN_USAGE_MASK)==ISDN_USAGE_RAW) -#define USG_MODEM(x) ((x & ISDN_USAGE_MASK)==ISDN_USAGE_MODEM) -#define USG_VOICE(x) ((x & ISDN_USAGE_MASK)==ISDN_USAGE_VOICE) -#define USG_NET(x) ((x & ISDN_USAGE_MASK)==ISDN_USAGE_NET) -#define USG_FAX(x) ((x & ISDN_USAGE_MASK)==ISDN_USAGE_FAX) -#define USG_OUTGOING(x) ((x & ISDN_USAGE_OUTGOING)==ISDN_USAGE_OUTGOING) -#define USG_MODEMORVOICE(x) (((x & ISDN_USAGE_MASK)==ISDN_USAGE_MODEM) || \ - ((x & ISDN_USAGE_MASK)==ISDN_USAGE_VOICE) ) - -/* Timer-delays and scheduling-flags */ -#define ISDN_TIMER_RES 4 /* Main Timer-Resolution */ -#define ISDN_TIMER_02SEC (HZ/ISDN_TIMER_RES/5) /* Slow-Timer1 .2 sec */ -#define ISDN_TIMER_1SEC (HZ/ISDN_TIMER_RES) /* Slow-Timer2 1 sec */ -#define ISDN_TIMER_RINGING 5 /* tty RINGs = ISDN_TIMER_1SEC * this factor */ -#define ISDN_TIMER_KEEPINT 10 /* Cisco-Keepalive = ISDN_TIMER_1SEC * this factor */ -#define ISDN_TIMER_MODEMREAD 1 -#define ISDN_TIMER_MODEMPLUS 2 -#define ISDN_TIMER_MODEMRING 4 -#define ISDN_TIMER_MODEMXMIT 8 -#define ISDN_TIMER_NETDIAL 16 -#define ISDN_TIMER_NETHANGUP 32 -#define ISDN_TIMER_CARRIER 256 /* Wait for Carrier */ -#define ISDN_TIMER_FAST (ISDN_TIMER_MODEMREAD | ISDN_TIMER_MODEMPLUS | \ - ISDN_TIMER_MODEMXMIT) -#define ISDN_TIMER_SLOW (ISDN_TIMER_MODEMRING | ISDN_TIMER_NETHANGUP | \ - ISDN_TIMER_NETDIAL | ISDN_TIMER_CARRIER) - -/* Timeout-Values for isdn_net_dial() */ -#define ISDN_TIMER_DTIMEOUT10 (10*HZ/(ISDN_TIMER_02SEC*(ISDN_TIMER_RES+1))) -#define ISDN_TIMER_DTIMEOUT15 (15*HZ/(ISDN_TIMER_02SEC*(ISDN_TIMER_RES+1))) -#define ISDN_TIMER_DTIMEOUT60 (60*HZ/(ISDN_TIMER_02SEC*(ISDN_TIMER_RES+1))) - -/* GLOBAL_FLAGS */ -#define ISDN_GLOBAL_STOPPED 1 - -/*=================== Start of ip-over-ISDN stuff =========================*/ - -/* Feature- and status-flags for a net-interface */ -#define ISDN_NET_CONNECTED 0x01 /* Bound to ISDN-Channel */ -#define ISDN_NET_SECURE 0x02 /* Accept calls from phonelist only */ -#define ISDN_NET_CALLBACK 0x04 /* activate callback */ -#define ISDN_NET_CBHUP 0x08 /* hangup before callback */ -#define ISDN_NET_CBOUT 0x10 /* remote machine does callback */ - -#define ISDN_NET_MAGIC 0x49344C02 /* for paranoia-checking */ - -/* Phone-list-element */ -typedef struct { - void *next; - char num[ISDN_MSNLEN]; -} isdn_net_phone; - -/* - Principles when extending structures for generic encapsulation protocol - ("concap") support: - - Stuff which is hardware specific (here i4l-specific) goes in - the netdev -> local structure (here: isdn_net_local) - - Stuff which is encapsulation protocol specific goes in the structure - which holds the linux device structure (here: isdn_net_device) -*/ - -/* Local interface-data */ -typedef struct isdn_net_local_s { - ulong magic; - struct net_device_stats stats; /* Ethernet Statistics */ - int isdn_device; /* Index to isdn-device */ - int isdn_channel; /* Index to isdn-channel */ - int ppp_slot; /* PPPD device slot number */ - int pre_device; /* Preselected isdn-device */ - int pre_channel; /* Preselected isdn-channel */ - int exclusive; /* If non-zero idx to reserved chan.*/ - int flags; /* Connection-flags */ - int dialretry; /* Counter for Dialout-retries */ - int dialmax; /* Max. Number of Dial-retries */ - int cbdelay; /* Delay before Callback starts */ - int dtimer; /* Timeout-counter for dialing */ - char msn[ISDN_MSNLEN]; /* MSNs/EAZs for this interface */ - u_char cbhup; /* Flag: Reject Call before Callback*/ - u_char dialstate; /* State for dialing */ - u_char p_encap; /* Packet encapsulation */ - /* 0 = Ethernet over ISDN */ - /* 1 = RAW-IP */ - /* 2 = IP with type field */ - u_char l2_proto; /* Layer-2-protocol */ - /* See ISDN_PROTO_L2..-constants in */ - /* isdnif.h */ - /* 0 = X75/LAPB with I-Frames */ - /* 1 = X75/LAPB with UI-Frames */ - /* 2 = X75/LAPB with BUI-Frames */ - /* 3 = HDLC */ - u_char l3_proto; /* Layer-3-protocol */ - /* See ISDN_PROTO_L3..-constants in */ - /* isdnif.h */ - /* 0 = Transparent */ - int huptimer; /* Timeout-counter for auto-hangup */ - int charge; /* Counter for charging units */ - ulong chargetime; /* Timer for Charging info */ - int hupflags; /* Flags for charge-unit-hangup: */ - /* bit0: chargeint is invalid */ - /* bit1: Getting charge-interval */ - /* bit2: Do charge-unit-hangup */ - /* bit3: Do hangup even on incoming */ - int outgoing; /* Flag: outgoing call */ - int onhtime; /* Time to keep link up */ - int chargeint; /* Interval between charge-infos */ - int onum; /* Flag: at least 1 outgoing number */ - int cps; /* current speed of this interface */ - int transcount; /* byte-counter for cps-calculation */ - int sqfull; /* Flag: netdev-queue overloaded */ - ulong sqfull_stamp; /* Start-Time of overload */ - ulong slavedelay; /* Dynamic bundling delaytime */ - int triggercps; /* BogoCPS needed for trigger slave */ - isdn_net_phone *phone[2]; /* List of remote-phonenumbers */ - /* phone[0] = Incoming Numbers */ - /* phone[1] = Outgoing Numbers */ - isdn_net_phone *dial; /* Pointer to dialed number */ - struct net_device *master; /* Ptr to Master device for slaves */ - struct net_device *slave; /* Ptr to Slave device for masters */ - struct isdn_net_local_s *next; /* Ptr to next link in bundle */ - struct isdn_net_local_s *last; /* Ptr to last link in bundle */ - struct isdn_net_dev_s *netdev; /* Ptr to netdev */ - struct sk_buff_head super_tx_queue; /* List of supervisory frames to */ - /* be transmitted asap */ - atomic_t frame_cnt; /* number of frames currently */ - /* queued in HL driver */ - /* Ptr to orig. hard_header_cache */ - spinlock_t xmit_lock; /* used to protect the xmit path of */ - /* a particular channel (including */ - /* the frame_cnt */ - - int pppbind; /* ippp device for bindings */ - int dialtimeout; /* How long shall we try on dialing? (jiffies) */ - int dialwait; /* How long shall we wait after failed attempt? (jiffies) */ - ulong dialstarted; /* jiffies of first dialing-attempt */ - ulong dialwait_timer; /* jiffies of earliest next dialing-attempt */ - int huptimeout; /* How long will the connection be up? (seconds) */ -#ifdef CONFIG_ISDN_X25 - struct concap_device_ops *dops; /* callbacks used by encapsulator */ -#endif - /* use an own struct for that in later versions */ - ulong cisco_myseq; /* Local keepalive seq. for Cisco */ - ulong cisco_mineseen; /* returned keepalive seq. from remote */ - ulong cisco_yourseq; /* Remote keepalive seq. for Cisco */ - int cisco_keepalive_period; /* keepalive period */ - ulong cisco_last_slarp_in; /* jiffie of last keepalive packet we received */ - char cisco_line_state; /* state of line according to keepalive packets */ - char cisco_debserint; /* debugging flag of cisco hdlc with slarp */ - struct timer_list cisco_timer; - struct work_struct tqueue; -} isdn_net_local; - -/* the interface itself */ -typedef struct isdn_net_dev_s { - isdn_net_local *local; - isdn_net_local *queue; /* circular list of all bundled - channels, which are currently - online */ - spinlock_t queue_lock; /* lock to protect queue */ - void *next; /* Pointer to next isdn-interface */ - struct net_device *dev; /* interface to upper levels */ -#ifdef CONFIG_ISDN_PPP - ippp_bundle * pb; /* pointer to the common bundle structure - * with the per-bundle data */ -#endif -#ifdef CONFIG_ISDN_X25 - struct concap_proto *cprot; /* connection oriented encapsulation protocol */ -#endif - -} isdn_net_dev; - -/*===================== End of ip-over-ISDN stuff ===========================*/ - -/*======================= Start of ISDN-tty stuff ===========================*/ - -#define ISDN_ASYNC_MAGIC 0x49344C01 /* for paranoia-checking */ -#define ISDN_SERIAL_XMIT_SIZE 1024 /* Default bufsize for write */ -#define ISDN_SERIAL_XMIT_MAX 4000 /* Maximum bufsize for write */ - -#ifdef CONFIG_ISDN_AUDIO -/* For using sk_buffs with audio we need some private variables - * within each sk_buff. For this purpose, we declare a struct here, - * and put it always at the private skb->cb data array. A few macros help - * accessing the variables. - */ -typedef struct _isdn_audio_data { - unsigned short dle_count; - unsigned char lock; -} isdn_audio_data_t; - -#define ISDN_AUDIO_SKB_DLECOUNT(skb) (((isdn_audio_data_t *)&skb->cb[0])->dle_count) -#define ISDN_AUDIO_SKB_LOCK(skb) (((isdn_audio_data_t *)&skb->cb[0])->lock) -#endif - -/* Private data of AT-command-interpreter */ -typedef struct atemu { - u_char profile[ISDN_MODEM_NUMREG]; /* Modem-Regs. Profile 0 */ - u_char mdmreg[ISDN_MODEM_NUMREG]; /* Modem-Registers */ - char pmsn[ISDN_MSNLEN]; /* EAZ/MSNs Profile 0 */ - char msn[ISDN_MSNLEN]; /* EAZ/MSN */ - char plmsn[ISDN_LMSNLEN]; /* Listening MSNs Profile 0 */ - char lmsn[ISDN_LMSNLEN]; /* Listening MSNs */ - char cpn[ISDN_MSNLEN]; /* CalledPartyNumber on incoming call */ - char connmsg[ISDN_CMSGLEN]; /* CONNECT-Msg from HL-Driver */ -#ifdef CONFIG_ISDN_AUDIO - u_char vpar[10]; /* Voice-parameters */ - int lastDLE; /* Flag for voice-coding: DLE seen */ -#endif - int mdmcmdl; /* Length of Modem-Commandbuffer */ - int pluscount; /* Counter for +++ sequence */ - u_long lastplus; /* Timestamp of last + */ - int carrierwait; /* Seconds of carrier waiting */ - char mdmcmd[255]; /* Modem-Commandbuffer */ - unsigned int charge; /* Charge units of current connection */ -} atemu; - -/* Private data (similar to async_struct in <linux/serial.h>) */ -typedef struct modem_info { - int magic; - struct tty_port port; - int x_char; /* xon/xoff character */ - int mcr; /* Modem control register */ - int msr; /* Modem status register */ - int lsr; /* Line status register */ - int line; - int online; /* 1 = B-Channel is up, drop data */ - /* 2 = B-Channel is up, deliver d.*/ - int dialing; /* Dial in progress or ATA */ - int closing; - int rcvsched; /* Receive needs schedule */ - int isdn_driver; /* Index to isdn-driver */ - int isdn_channel; /* Index to isdn-channel */ - int drv_index; /* Index to dev->usage */ - int ncarrier; /* Flag: schedule NO CARRIER */ - unsigned char last_cause[8]; /* Last cause message */ - unsigned char last_num[ISDN_MSNLEN]; - /* Last phone-number */ - unsigned char last_l2; /* Last layer-2 protocol */ - unsigned char last_si; /* Last service */ - unsigned char last_lhup; /* Last hangup local? */ - unsigned char last_dir; /* Last direction (in or out) */ - struct timer_list nc_timer; /* Timer for delayed NO CARRIER */ - int send_outstanding;/* # of outstanding send-requests */ - int xmit_size; /* max. # of chars in xmit_buf */ - int xmit_count; /* # of chars in xmit_buf */ - struct sk_buff_head xmit_queue; /* transmit queue */ - atomic_t xmit_lock; /* Semaphore for isdn_tty_write */ -#ifdef CONFIG_ISDN_AUDIO - int vonline; /* Voice-channel status */ - /* Bit 0 = recording */ - /* Bit 1 = playback */ - /* Bit 2 = playback, DLE-ETX seen */ - struct sk_buff_head dtmf_queue; /* queue for dtmf results */ - void *adpcms; /* state for adpcm decompression */ - void *adpcmr; /* state for adpcm compression */ - void *dtmf_state; /* state for dtmf decoder */ - void *silence_state; /* state for silence detection */ -#endif -#ifdef CONFIG_ISDN_TTY_FAX - struct T30_s *fax; /* T30 Fax Group 3 data/interface */ - int faxonline; /* Fax-channel status */ -#endif - atemu emu; /* AT-emulator data */ - spinlock_t readlock; -} modem_info; - -#define ISDN_MODEM_WINSIZE 8 - -/* Description of one ISDN-tty */ -typedef struct _isdn_modem { - int refcount; /* Number of opens */ - struct tty_driver *tty_modem; /* tty-device */ - struct tty_struct *modem_table[ISDN_MAX_CHANNELS]; /* ?? copied from Orig */ - struct ktermios *modem_termios[ISDN_MAX_CHANNELS]; - struct ktermios *modem_termios_locked[ISDN_MAX_CHANNELS]; - modem_info info[ISDN_MAX_CHANNELS]; /* Private data */ -} isdn_modem_t; - -/*======================= End of ISDN-tty stuff ============================*/ - -/*======================== Start of V.110 stuff ============================*/ -#define V110_BUFSIZE 1024 - -typedef struct { - int nbytes; /* 1 Matrixbyte -> nbytes in stream */ - int nbits; /* Number of used bits in streambyte */ - unsigned char key; /* Bitmask in stream eg. 11 (nbits=2) */ - int decodelen; /* Amount of data in decodebuf */ - int SyncInit; /* Number of sync frames to send */ - unsigned char *OnlineFrame; /* Precalculated V110 idle frame */ - unsigned char *OfflineFrame; /* Precalculated V110 sync Frame */ - int framelen; /* Length of frames */ - int skbuser; /* Number of unacked userdata skbs */ - int skbidle; /* Number of unacked idle/sync skbs */ - int introducer; /* Local vars for decoder */ - int dbit; - unsigned char b; - int skbres; /* space to reserve in outgoing skb */ - int maxsize; /* maxbufsize of lowlevel driver */ - unsigned char *encodebuf; /* temporary buffer for encoding */ - unsigned char decodebuf[V110_BUFSIZE]; /* incomplete V110 matrices */ -} isdn_v110_stream; - -/*========================= End of V.110 stuff =============================*/ - -/*======================= Start of general stuff ===========================*/ - -typedef struct { - char *next; - char *private; -} infostruct; - -#define DRV_FLAG_RUNNING 1 -#define DRV_FLAG_REJBUS 2 -#define DRV_FLAG_LOADED 4 - -/* Description of hardware-level-driver */ -typedef struct _isdn_driver { - ulong online; /* Channel-Online flags */ - ulong flags; /* Misc driver Flags */ - int locks; /* Number of locks for this driver */ - int channels; /* Number of channels */ - wait_queue_head_t st_waitq; /* Wait-Queue for status-read's */ - int maxbufsize; /* Maximum Buffersize supported */ - unsigned long pktcount; /* Until now: unused */ - int stavail; /* Chars avail on Status-device */ - isdn_if *interface; /* Interface to driver */ - int *rcverr; /* Error-counters for B-Ch.-receive */ - int *rcvcount; /* Byte-counters for B-Ch.-receive */ -#ifdef CONFIG_ISDN_AUDIO - unsigned long DLEflag; /* Flags: Insert DLE at next read */ -#endif - struct sk_buff_head *rpqueue; /* Pointers to start of Rcv-Queue */ - wait_queue_head_t *rcv_waitq; /* Wait-Queues for B-Channel-Reads */ - wait_queue_head_t *snd_waitq; /* Wait-Queue for B-Channel-Send's */ - char msn2eaz[10][ISDN_MSNLEN]; /* Mapping-Table MSN->EAZ */ -} isdn_driver_t; - -/* Main driver-data */ -typedef struct isdn_devt { - struct module *owner; - spinlock_t lock; - unsigned short flags; /* Bitmapped Flags: */ - int drivers; /* Current number of drivers */ - int channels; /* Current number of channels */ - int net_verbose; /* Verbose-Flag */ - int modempoll; /* Flag: tty-read active */ - spinlock_t timerlock; - int tflags; /* Timer-Flags: */ - /* see ISDN_TIMER_..defines */ - int global_flags; - infostruct *infochain; /* List of open info-devs. */ - wait_queue_head_t info_waitq; /* Wait-Queue for isdninfo */ - struct timer_list timer; /* Misc.-function Timer */ - int chanmap[ISDN_MAX_CHANNELS]; /* Map minor->device-channel */ - int drvmap[ISDN_MAX_CHANNELS]; /* Map minor->driver-index */ - int usage[ISDN_MAX_CHANNELS]; /* Used by tty/ip/voice */ - char num[ISDN_MAX_CHANNELS][ISDN_MSNLEN]; - /* Remote number of active ch.*/ - int m_idx[ISDN_MAX_CHANNELS]; /* Index for mdm.... */ - isdn_driver_t *drv[ISDN_MAX_DRIVERS]; /* Array of drivers */ - isdn_net_dev *netdev; /* Linked list of net-if's */ - char drvid[ISDN_MAX_DRIVERS][20];/* Driver-ID */ - struct task_struct *profd; /* For iprofd */ - isdn_modem_t mdm; /* tty-driver-data */ - isdn_net_dev *rx_netdev[ISDN_MAX_CHANNELS]; /* rx netdev-pointers */ - isdn_net_dev *st_netdev[ISDN_MAX_CHANNELS]; /* stat netdev-pointers */ - ulong ibytes[ISDN_MAX_CHANNELS]; /* Statistics incoming bytes */ - ulong obytes[ISDN_MAX_CHANNELS]; /* Statistics outgoing bytes */ - int v110emu[ISDN_MAX_CHANNELS]; /* V.110 emulator-mode 0=none */ - atomic_t v110use[ISDN_MAX_CHANNELS]; /* Usage-Semaphore for stream */ - isdn_v110_stream *v110[ISDN_MAX_CHANNELS]; /* V.110 private data */ - struct mutex mtx; /* serialize list access*/ - unsigned long global_features; -} isdn_dev; - -extern isdn_dev *dev; - - -#endif /* __ISDN_H__ */ diff --git a/include/linux/isdn/hdlc.h b/include/linux/isdn/hdlc.h deleted file mode 100644 index fe2c1279c139..000000000000 --- a/include/linux/isdn/hdlc.h +++ /dev/null @@ -1,69 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * hdlc.h -- General purpose ISDN HDLC decoder. - * - * Implementation of a HDLC decoder/encoder in software. - * Necessary because some ISDN devices don't have HDLC - * controllers. - * - * Copyright (C) - * 2009 Karsten Keil <keil@b1-systems.de> - * 2002 Wolfgang Mües <wolfgang@iksw-muees.de> - * 2001 Frode Isaksen <fisaksen@bewan.com> - * 2001 Kai Germaschewski <kai.germaschewski@gmx.de> - */ - -#ifndef __ISDNHDLC_H__ -#define __ISDNHDLC_H__ - -struct isdnhdlc_vars { - int bit_shift; - int hdlc_bits1; - int data_bits; - int ffbit_shift; /* encoding only */ - int state; - int dstpos; - - u16 crc; - - u8 cbin; - u8 shift_reg; - u8 ffvalue; - - /* set if transferring data */ - u32 data_received:1; - /* set if D channel (send idle instead of flags) */ - u32 dchannel:1; - /* set if 56K adaptation */ - u32 do_adapt56:1; - /* set if in closing phase (need to send CRC + flag) */ - u32 do_closing:1; - /* set if data is bitreverse */ - u32 do_bitreverse:1; -}; - -/* Feature Flags */ -#define HDLC_56KBIT 0x01 -#define HDLC_DCHANNEL 0x02 -#define HDLC_BITREVERSE 0x04 - -/* - The return value from isdnhdlc_decode is - the frame length, 0 if no complete frame was decoded, - or a negative error number -*/ -#define HDLC_FRAMING_ERROR 1 -#define HDLC_CRC_ERROR 2 -#define HDLC_LENGTH_ERROR 3 - -extern void isdnhdlc_rcv_init(struct isdnhdlc_vars *hdlc, u32 features); - -extern int isdnhdlc_decode(struct isdnhdlc_vars *hdlc, const u8 *src, - int slen, int *count, u8 *dst, int dsize); - -extern void isdnhdlc_out_init(struct isdnhdlc_vars *hdlc, u32 features); - -extern int isdnhdlc_encode(struct isdnhdlc_vars *hdlc, const u8 *src, - u16 slen, int *count, u8 *dst, int dsize); - -#endif /* __ISDNHDLC_H__ */ diff --git a/include/linux/isdn_divertif.h b/include/linux/isdn_divertif.h deleted file mode 100644 index 19ab361f9f07..000000000000 --- a/include/linux/isdn_divertif.h +++ /dev/null @@ -1,35 +0,0 @@ -/* $Id: isdn_divertif.h,v 1.4.6.1 2001/09/23 22:25:05 kai Exp $ - * - * Header for the diversion supplementary interface for i4l. - * - * Author Werner Cornelius (werner@titro.de) - * Copyright by Werner Cornelius (werner@titro.de) - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ -#ifndef _LINUX_ISDN_DIVERTIF_H -#define _LINUX_ISDN_DIVERTIF_H - -#include <linux/isdnif.h> -#include <linux/types.h> -#include <uapi/linux/isdn_divertif.h> - -/***************************************************************/ -/* structure exchanging data between isdn hl and divert module */ -/***************************************************************/ -typedef struct - { ulong if_magic; /* magic info and version */ - int cmd; /* command */ - int (*stat_callback)(isdn_ctrl *); /* supplied by divert module when calling */ - int (*ll_cmd)(isdn_ctrl *); /* supplied by hl on return */ - char * (*drv_to_name)(int); /* map a driver id to name, supplied by hl */ - int (*name_to_drv)(char *); /* map a driver id to name, supplied by hl */ - } isdn_divert_if; - -/*********************/ -/* function register */ -/*********************/ -extern int DIVERT_REG_NAME(isdn_divert_if *); -#endif /* _LINUX_ISDN_DIVERTIF_H */ diff --git a/include/linux/isdn_ppp.h b/include/linux/isdn_ppp.h deleted file mode 100644 index a0070c6dfaf8..000000000000 --- a/include/linux/isdn_ppp.h +++ /dev/null @@ -1,194 +0,0 @@ -/* Linux ISDN subsystem, sync PPP, interface to ipppd - * - * Copyright 1994-1999 by Fritz Elfert (fritz@isdn4linux.de) - * Copyright 1995,96 Thinking Objects Software GmbH Wuerzburg - * Copyright 1995,96 by Michael Hipp (Michael.Hipp@student.uni-tuebingen.de) - * Copyright 2000-2002 by Kai Germaschewski (kai@germaschewski.name) - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ -#ifndef _LINUX_ISDN_PPP_H -#define _LINUX_ISDN_PPP_H - - - - -#ifdef CONFIG_IPPP_FILTER -#include <linux/filter.h> -#endif -#include <uapi/linux/isdn_ppp.h> - -#define DECOMP_ERR_NOMEM (-10) - -#define MP_END_FRAG 0x40 -#define MP_BEGIN_FRAG 0x80 - -#define MP_MAX_QUEUE_LEN 16 - -/* - * We need a way for the decompressor to influence the generation of CCP - * Reset-Requests in a variety of ways. The decompressor is already returning - * a lot of information (generated skb length, error conditions) so we use - * another parameter. This parameter is a pointer to a structure which is - * to be marked valid by the decompressor and only in this case is ever used. - * Furthermore, the only case where this data is used is when the decom- - * pressor returns DECOMP_ERROR. - * - * We use this same struct for the reset entry of the compressor to commu- - * nicate to its caller how to deal with sending of a Reset Ack. In this - * case, expra is not used, but other options still apply (suppressing - * sending with rsend, appending arbitrary data, etc). - */ - -#define IPPP_RESET_MAXDATABYTES 32 - -struct isdn_ppp_resetparams { - unsigned char valid:1; /* rw Is this structure filled at all ? */ - unsigned char rsend:1; /* rw Should we send one at all ? */ - unsigned char idval:1; /* rw Is the id field valid ? */ - unsigned char dtval:1; /* rw Is the data field valid ? */ - unsigned char expra:1; /* rw Is an Ack expected for this Req ? */ - unsigned char id; /* wo Send CCP ResetReq with this id */ - unsigned short maxdlen; /* ro Max bytes to be stored in data field */ - unsigned short dlen; /* rw Bytes stored in data field */ - unsigned char *data; /* wo Data for ResetReq info field */ -}; - -/* - * this is an 'old friend' from ppp-comp.h under a new name - * check the original include for more information - */ -struct isdn_ppp_compressor { - struct isdn_ppp_compressor *next, *prev; - struct module *owner; - int num; /* CCP compression protocol number */ - - void *(*alloc) (struct isdn_ppp_comp_data *); - void (*free) (void *state); - int (*init) (void *state, struct isdn_ppp_comp_data *, - int unit,int debug); - - /* The reset entry needs to get more exact information about the - ResetReq or ResetAck it was called with. The parameters are - obvious. If reset is called without a Req or Ack frame which - could be handed into it, code MUST be set to 0. Using rsparm, - the reset entry can control if and how a ResetAck is returned. */ - - void (*reset) (void *state, unsigned char code, unsigned char id, - unsigned char *data, unsigned len, - struct isdn_ppp_resetparams *rsparm); - - int (*compress) (void *state, struct sk_buff *in, - struct sk_buff *skb_out, int proto); - - int (*decompress) (void *state,struct sk_buff *in, - struct sk_buff *skb_out, - struct isdn_ppp_resetparams *rsparm); - - void (*incomp) (void *state, struct sk_buff *in,int proto); - void (*stat) (void *state, struct compstat *stats); -}; - -extern int isdn_ppp_register_compressor(struct isdn_ppp_compressor *); -extern int isdn_ppp_unregister_compressor(struct isdn_ppp_compressor *); -extern int isdn_ppp_dial_slave(char *); -extern int isdn_ppp_hangup_slave(char *); - -typedef struct { - unsigned long seqerrs; - unsigned long frame_drops; - unsigned long overflows; - unsigned long max_queue_len; -} isdn_mppp_stats; - -typedef struct { - int mp_mrru; /* unused */ - struct sk_buff * frags; /* fragments sl list -- use skb->next */ - long frames; /* number of frames in the frame list */ - unsigned int seq; /* last processed packet seq #: any packets - * with smaller seq # will be dropped - * unconditionally */ - spinlock_t lock; - int ref_ct; - /* statistics */ - isdn_mppp_stats stats; -} ippp_bundle; - -#define NUM_RCV_BUFFS 64 - -struct ippp_buf_queue { - struct ippp_buf_queue *next; - struct ippp_buf_queue *last; - char *buf; /* NULL here indicates end of queue */ - int len; -}; - -/* The data structure for one CCP reset transaction */ -enum ippp_ccp_reset_states { - CCPResetIdle, - CCPResetSentReq, - CCPResetRcvdReq, - CCPResetSentAck, - CCPResetRcvdAck -}; - -struct ippp_ccp_reset_state { - enum ippp_ccp_reset_states state; /* State of this transaction */ - struct ippp_struct *is; /* Backlink to device stuff */ - unsigned char id; /* Backlink id index */ - unsigned char ta:1; /* The timer is active (flag) */ - unsigned char expra:1; /* We expect a ResetAck at all */ - int dlen; /* Databytes stored in data */ - struct timer_list timer; /* For timeouts/retries */ - /* This is a hack but seems sufficient for the moment. We do not want - to have this be yet another allocation for some bytes, it is more - memory management overhead than the whole mess is worth. */ - unsigned char data[IPPP_RESET_MAXDATABYTES]; -}; - -/* The data structure keeping track of the currently outstanding CCP Reset - transactions. */ -struct ippp_ccp_reset { - struct ippp_ccp_reset_state *rs[256]; /* One per possible id */ - unsigned char lastid; /* Last id allocated by the engine */ -}; - -struct ippp_struct { - struct ippp_struct *next_link; - int state; - spinlock_t buflock; - struct ippp_buf_queue rq[NUM_RCV_BUFFS]; /* packet queue for isdn_ppp_read() */ - struct ippp_buf_queue *first; /* pointer to (current) first packet */ - struct ippp_buf_queue *last; /* pointer to (current) last used packet in queue */ - wait_queue_head_t wq; - struct task_struct *tk; - unsigned int mpppcfg; - unsigned int pppcfg; - unsigned int mru; - unsigned int mpmru; - unsigned int mpmtu; - unsigned int maxcid; - struct isdn_net_local_s *lp; - int unit; - int minor; - unsigned int last_link_seqno; - long mp_seqno; -#ifdef CONFIG_ISDN_PPP_VJ - unsigned char *cbuf; - struct slcompress *slcomp; -#endif -#ifdef CONFIG_IPPP_FILTER - struct bpf_prog *pass_filter; /* filter for packets to pass */ - struct bpf_prog *active_filter; /* filter for pkts to reset idle */ -#endif - unsigned long debug; - struct isdn_ppp_compressor *compressor,*decompressor; - struct isdn_ppp_compressor *link_compressor,*link_decompressor; - void *decomp_stat,*comp_stat,*link_decomp_stat,*link_comp_stat; - struct ippp_ccp_reset *reset; /* Allocated on demand, may never be needed */ - unsigned long compflags; -}; - -#endif /* _LINUX_ISDN_PPP_H */ diff --git a/include/linux/isdnif.h b/include/linux/isdnif.h deleted file mode 100644 index 8d80fdc68647..000000000000 --- a/include/linux/isdnif.h +++ /dev/null @@ -1,505 +0,0 @@ -/* $Id: isdnif.h,v 1.43.2.2 2004/01/12 23:08:35 keil Exp $ - * - * Linux ISDN subsystem - * Definition of the interface between the subsystem and its low-level drivers. - * - * Copyright 1994,95,96 by Fritz Elfert (fritz@isdn4linux.de) - * Copyright 1995,96 Thinking Objects Software GmbH Wuerzburg - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ -#ifndef __ISDNIF_H__ -#define __ISDNIF_H__ - - -#include <linux/skbuff.h> -#include <uapi/linux/isdnif.h> - -/***************************************************************************/ -/* Extensions made by Werner Cornelius (werner@ikt.de) */ -/* */ -/* The proceed command holds a incoming call in a state to leave processes */ -/* enough time to check whether ist should be accepted. */ -/* The PROT_IO Command extends the interface to make protocol dependent */ -/* features available (call diversion, call waiting...). */ -/* */ -/* The PROT_IO Command is executed with the desired driver id and the arg */ -/* parameter coded as follows: */ -/* The lower 8 bits of arg contain the desired protocol from ISDN_PTYPE */ -/* definitions. The upper 24 bits represent the protocol specific cmd/stat.*/ -/* Any additional data is protocol and command specific. */ -/* This mechanism also applies to the statcallb callback STAT_PROT. */ -/* */ -/* This suggested extension permits an easy expansion of protocol specific */ -/* handling. Extensions may be added at any time without changing the HL */ -/* driver code and not getting conflicts without certifications. */ -/* The well known CAPI 2.0 interface handles such extensions in a similar */ -/* way. Perhaps a protocol specific module may be added and separately */ -/* loaded and linked to the basic isdn module for handling. */ -/***************************************************************************/ - -/*****************/ -/* DSS1 commands */ -/*****************/ -#define DSS1_CMD_INVOKE ((0x00 << 8) | ISDN_PTYPE_EURO) /* invoke a supplementary service */ -#define DSS1_CMD_INVOKE_ABORT ((0x01 << 8) | ISDN_PTYPE_EURO) /* abort a invoke cmd */ - -/*******************************/ -/* DSS1 Status callback values */ -/*******************************/ -#define DSS1_STAT_INVOKE_RES ((0x80 << 8) | ISDN_PTYPE_EURO) /* Result for invocation */ -#define DSS1_STAT_INVOKE_ERR ((0x81 << 8) | ISDN_PTYPE_EURO) /* Error Return for invocation */ -#define DSS1_STAT_INVOKE_BRD ((0x82 << 8) | ISDN_PTYPE_EURO) /* Deliver invoke broadcast info */ - - -/*********************************************************************/ -/* structures for DSS1 commands and callback */ -/* */ -/* An action is invoked by sending a DSS1_CMD_INVOKE. The ll_id, proc*/ -/* timeout, datalen and data fields must be set before calling. */ -/* */ -/* The return value is a positive hl_id value also delivered in the */ -/* hl_id field. A value of zero signals no more left hl_id capacitys.*/ -/* A negative return value signals errors in LL. So if the return */ -/* value is <= 0 no action in LL will be taken -> request ignored */ -/* */ -/* The timeout field must be filled with a positive value specifying */ -/* the amount of time the INVOKED process waits for a reaction from */ -/* the network. */ -/* If a response (either error or result) is received during this */ -/* intervall, a reporting callback is initiated and the process will */ -/* be deleted, the hl identifier will be freed. */ -/* If no response is received during the specified intervall, a error*/ -/* callback is initiated with timeout set to -1 and a datalen set */ -/* to 0. */ -/* If timeout is set to a value <= 0 during INVOCATION the process is*/ -/* immediately deleted after sending the data. No callback occurs ! */ -/* */ -/* A currently waiting process may be aborted with INVOKE_ABORT. No */ -/* callback will occur when a process has been aborted. */ -/* */ -/* Broadcast invoke frames from the network are reported via the */ -/* STAT_INVOKE_BRD callback. The ll_id is set to 0, the other fields */ -/* are supplied by the network and not by the HL. */ -/*********************************************************************/ - -/*****************/ -/* NI1 commands */ -/*****************/ -#define NI1_CMD_INVOKE ((0x00 << 8) | ISDN_PTYPE_NI1) /* invoke a supplementary service */ -#define NI1_CMD_INVOKE_ABORT ((0x01 << 8) | ISDN_PTYPE_NI1) /* abort a invoke cmd */ - -/*******************************/ -/* NI1 Status callback values */ -/*******************************/ -#define NI1_STAT_INVOKE_RES ((0x80 << 8) | ISDN_PTYPE_NI1) /* Result for invocation */ -#define NI1_STAT_INVOKE_ERR ((0x81 << 8) | ISDN_PTYPE_NI1) /* Error Return for invocation */ -#define NI1_STAT_INVOKE_BRD ((0x82 << 8) | ISDN_PTYPE_NI1) /* Deliver invoke broadcast info */ - -typedef struct - { ulong ll_id; /* ID supplied by LL when executing */ - /* a command and returned by HL for */ - /* INVOKE_RES and INVOKE_ERR */ - int hl_id; /* ID supplied by HL when called */ - /* for executing a cmd and delivered */ - /* for results and errors */ - /* must be supplied by LL when aborting*/ - int proc; /* invoke procedure used by CMD_INVOKE */ - /* returned by callback and broadcast */ - int timeout; /* timeout for INVOKE CMD in ms */ - /* -1 in stat callback when timed out */ - /* error value when error callback */ - int datalen; /* length of cmd or stat data */ - u_char *data;/* pointer to data delivered or send */ - } isdn_cmd_stat; - -/* - * Commands from linklevel to lowlevel - * - */ -#define ISDN_CMD_IOCTL 0 /* Perform ioctl */ -#define ISDN_CMD_DIAL 1 /* Dial out */ -#define ISDN_CMD_ACCEPTD 2 /* Accept an incoming call on D-Chan. */ -#define ISDN_CMD_ACCEPTB 3 /* Request B-Channel connect. */ -#define ISDN_CMD_HANGUP 4 /* Hangup */ -#define ISDN_CMD_CLREAZ 5 /* Clear EAZ(s) of channel */ -#define ISDN_CMD_SETEAZ 6 /* Set EAZ(s) of channel */ -#define ISDN_CMD_GETEAZ 7 /* Get EAZ(s) of channel */ -#define ISDN_CMD_SETSIL 8 /* Set Service-Indicator-List of channel */ -#define ISDN_CMD_GETSIL 9 /* Get Service-Indicator-List of channel */ -#define ISDN_CMD_SETL2 10 /* Set B-Chan. Layer2-Parameter */ -#define ISDN_CMD_GETL2 11 /* Get B-Chan. Layer2-Parameter */ -#define ISDN_CMD_SETL3 12 /* Set B-Chan. Layer3-Parameter */ -#define ISDN_CMD_GETL3 13 /* Get B-Chan. Layer3-Parameter */ -// #define ISDN_CMD_LOCK 14 /* Signal usage by upper levels */ -// #define ISDN_CMD_UNLOCK 15 /* Release usage-lock */ -#define ISDN_CMD_SUSPEND 16 /* Suspend connection */ -#define ISDN_CMD_RESUME 17 /* Resume connection */ -#define ISDN_CMD_PROCEED 18 /* Proceed with call establishment */ -#define ISDN_CMD_ALERT 19 /* Alert after Proceeding */ -#define ISDN_CMD_REDIR 20 /* Redir a incoming call */ -#define ISDN_CMD_PROT_IO 21 /* Protocol specific commands */ -#define CAPI_PUT_MESSAGE 22 /* CAPI message send down or up */ -#define ISDN_CMD_FAXCMD 23 /* FAX commands to HL-driver */ -#define ISDN_CMD_AUDIO 24 /* DSP, DTMF, ... settings */ - -/* - * Status-Values delivered from lowlevel to linklevel via - * statcallb(). - * - */ -#define ISDN_STAT_STAVAIL 256 /* Raw status-data available */ -#define ISDN_STAT_ICALL 257 /* Incoming call detected */ -#define ISDN_STAT_RUN 258 /* Signal protocol-code is running */ -#define ISDN_STAT_STOP 259 /* Signal halt of protocol-code */ -#define ISDN_STAT_DCONN 260 /* Signal D-Channel connect */ -#define ISDN_STAT_BCONN 261 /* Signal B-Channel connect */ -#define ISDN_STAT_DHUP 262 /* Signal D-Channel disconnect */ -#define ISDN_STAT_BHUP 263 /* Signal B-Channel disconnect */ -#define ISDN_STAT_CINF 264 /* Charge-Info */ -#define ISDN_STAT_LOAD 265 /* Signal new lowlevel-driver is loaded */ -#define ISDN_STAT_UNLOAD 266 /* Signal unload of lowlevel-driver */ -#define ISDN_STAT_BSENT 267 /* Signal packet sent */ -#define ISDN_STAT_NODCH 268 /* Signal no D-Channel */ -#define ISDN_STAT_ADDCH 269 /* Add more Channels */ -#define ISDN_STAT_CAUSE 270 /* Cause-Message */ -#define ISDN_STAT_ICALLW 271 /* Incoming call without B-chan waiting */ -#define ISDN_STAT_REDIR 272 /* Redir result */ -#define ISDN_STAT_PROT 273 /* protocol IO specific callback */ -#define ISDN_STAT_DISPLAY 274 /* deliver a received display message */ -#define ISDN_STAT_L1ERR 275 /* Signal Layer-1 Error */ -#define ISDN_STAT_FAXIND 276 /* FAX indications from HL-driver */ -#define ISDN_STAT_AUDIO 277 /* DTMF, DSP indications */ -#define ISDN_STAT_DISCH 278 /* Disable/Enable channel usage */ - -/* - * Audio commands - */ -#define ISDN_AUDIO_SETDD 0 /* Set DTMF detection */ -#define ISDN_AUDIO_DTMF 1 /* Rx/Tx DTMF */ - -/* - * Values for errcode field - */ -#define ISDN_STAT_L1ERR_SEND 1 -#define ISDN_STAT_L1ERR_RECV 2 - -/* - * Values for feature-field of interface-struct. - */ -/* Layer 2 */ -#define ISDN_FEATURE_L2_X75I (0x0001 << ISDN_PROTO_L2_X75I) -#define ISDN_FEATURE_L2_X75UI (0x0001 << ISDN_PROTO_L2_X75UI) -#define ISDN_FEATURE_L2_X75BUI (0x0001 << ISDN_PROTO_L2_X75BUI) -#define ISDN_FEATURE_L2_HDLC (0x0001 << ISDN_PROTO_L2_HDLC) -#define ISDN_FEATURE_L2_TRANS (0x0001 << ISDN_PROTO_L2_TRANS) -#define ISDN_FEATURE_L2_X25DTE (0x0001 << ISDN_PROTO_L2_X25DTE) -#define ISDN_FEATURE_L2_X25DCE (0x0001 << ISDN_PROTO_L2_X25DCE) -#define ISDN_FEATURE_L2_V11096 (0x0001 << ISDN_PROTO_L2_V11096) -#define ISDN_FEATURE_L2_V11019 (0x0001 << ISDN_PROTO_L2_V11019) -#define ISDN_FEATURE_L2_V11038 (0x0001 << ISDN_PROTO_L2_V11038) -#define ISDN_FEATURE_L2_MODEM (0x0001 << ISDN_PROTO_L2_MODEM) -#define ISDN_FEATURE_L2_FAX (0x0001 << ISDN_PROTO_L2_FAX) -#define ISDN_FEATURE_L2_HDLC_56K (0x0001 << ISDN_PROTO_L2_HDLC_56K) - -#define ISDN_FEATURE_L2_MASK (0x0FFFF) /* Max. 16 protocols */ -#define ISDN_FEATURE_L2_SHIFT (0) - -/* Layer 3 */ -#define ISDN_FEATURE_L3_TRANS (0x10000 << ISDN_PROTO_L3_TRANS) -#define ISDN_FEATURE_L3_TRANSDSP (0x10000 << ISDN_PROTO_L3_TRANSDSP) -#define ISDN_FEATURE_L3_FCLASS2 (0x10000 << ISDN_PROTO_L3_FCLASS2) -#define ISDN_FEATURE_L3_FCLASS1 (0x10000 << ISDN_PROTO_L3_FCLASS1) - -#define ISDN_FEATURE_L3_MASK (0x0FF0000) /* Max. 8 Protocols */ -#define ISDN_FEATURE_L3_SHIFT (16) - -/* Signaling */ -#define ISDN_FEATURE_P_UNKNOWN (0x1000000 << ISDN_PTYPE_UNKNOWN) -#define ISDN_FEATURE_P_1TR6 (0x1000000 << ISDN_PTYPE_1TR6) -#define ISDN_FEATURE_P_EURO (0x1000000 << ISDN_PTYPE_EURO) -#define ISDN_FEATURE_P_NI1 (0x1000000 << ISDN_PTYPE_NI1) - -#define ISDN_FEATURE_P_MASK (0x0FF000000) /* Max. 8 Protocols */ -#define ISDN_FEATURE_P_SHIFT (24) - -typedef struct setup_parm { - unsigned char phone[32]; /* Remote Phone-Number */ - unsigned char eazmsn[32]; /* Local EAZ or MSN */ - unsigned char si1; /* Service Indicator 1 */ - unsigned char si2; /* Service Indicator 2 */ - unsigned char plan; /* Numbering plan */ - unsigned char screen; /* Screening info */ -} setup_parm; - - -#ifdef CONFIG_ISDN_TTY_FAX -/* T.30 Fax G3 */ - -#define FAXIDLEN 21 - -typedef struct T30_s { - /* session parameters */ - __u8 resolution; - __u8 rate; - __u8 width; - __u8 length; - __u8 compression; - __u8 ecm; - __u8 binary; - __u8 scantime; - __u8 id[FAXIDLEN]; - /* additional parameters */ - __u8 phase; - __u8 direction; - __u8 code; - __u8 badlin; - __u8 badmul; - __u8 bor; - __u8 fet; - __u8 pollid[FAXIDLEN]; - __u8 cq; - __u8 cr; - __u8 ctcrty; - __u8 minsp; - __u8 phcto; - __u8 rel; - __u8 nbc; - /* remote station parameters */ - __u8 r_resolution; - __u8 r_rate; - __u8 r_width; - __u8 r_length; - __u8 r_compression; - __u8 r_ecm; - __u8 r_binary; - __u8 r_scantime; - __u8 r_id[FAXIDLEN]; - __u8 r_code; -} __packed T30_s; - -#define ISDN_TTY_FAX_CONN_IN 0 -#define ISDN_TTY_FAX_CONN_OUT 1 - -#define ISDN_TTY_FAX_FCON 0 -#define ISDN_TTY_FAX_DIS 1 -#define ISDN_TTY_FAX_FTT 2 -#define ISDN_TTY_FAX_MCF 3 -#define ISDN_TTY_FAX_DCS 4 -#define ISDN_TTY_FAX_TRAIN_OK 5 -#define ISDN_TTY_FAX_EOP 6 -#define ISDN_TTY_FAX_EOM 7 -#define ISDN_TTY_FAX_MPS 8 -#define ISDN_TTY_FAX_DTC 9 -#define ISDN_TTY_FAX_RID 10 -#define ISDN_TTY_FAX_HNG 11 -#define ISDN_TTY_FAX_DT 12 -#define ISDN_TTY_FAX_FCON_I 13 -#define ISDN_TTY_FAX_DR 14 -#define ISDN_TTY_FAX_ET 15 -#define ISDN_TTY_FAX_CFR 16 -#define ISDN_TTY_FAX_PTS 17 -#define ISDN_TTY_FAX_SENT 18 - -#define ISDN_FAX_PHASE_IDLE 0 -#define ISDN_FAX_PHASE_A 1 -#define ISDN_FAX_PHASE_B 2 -#define ISDN_FAX_PHASE_C 3 -#define ISDN_FAX_PHASE_D 4 -#define ISDN_FAX_PHASE_E 5 - -#endif /* TTY_FAX */ - -#define ISDN_FAX_CLASS1_FAE 0 -#define ISDN_FAX_CLASS1_FTS 1 -#define ISDN_FAX_CLASS1_FRS 2 -#define ISDN_FAX_CLASS1_FTM 3 -#define ISDN_FAX_CLASS1_FRM 4 -#define ISDN_FAX_CLASS1_FTH 5 -#define ISDN_FAX_CLASS1_FRH 6 -#define ISDN_FAX_CLASS1_CTRL 7 - -#define ISDN_FAX_CLASS1_OK 0 -#define ISDN_FAX_CLASS1_CONNECT 1 -#define ISDN_FAX_CLASS1_NOCARR 2 -#define ISDN_FAX_CLASS1_ERROR 3 -#define ISDN_FAX_CLASS1_FCERROR 4 -#define ISDN_FAX_CLASS1_QUERY 5 - -typedef struct { - __u8 cmd; - __u8 subcmd; - __u8 para[50]; -} aux_s; - -#define AT_COMMAND 0 -#define AT_EQ_VALUE 1 -#define AT_QUERY 2 -#define AT_EQ_QUERY 3 - -/* CAPI structs */ - -/* this is compatible to the old union size */ -#define MAX_CAPI_PARA_LEN 50 - -typedef struct { - /* Header */ - __u16 Length; - __u16 ApplId; - __u8 Command; - __u8 Subcommand; - __u16 Messagenumber; - - /* Parameter */ - union { - __u32 Controller; - __u32 PLCI; - __u32 NCCI; - } adr; - __u8 para[MAX_CAPI_PARA_LEN]; -} capi_msg; - -/* - * Structure for exchanging above infos - * - */ -typedef struct { - int driver; /* Lowlevel-Driver-ID */ - int command; /* Command or Status (see above) */ - ulong arg; /* Additional Data */ - union { - ulong errcode; /* Type of error with STAT_L1ERR */ - int length; /* Amount of bytes sent with STAT_BSENT */ - u_char num[50]; /* Additional Data */ - setup_parm setup;/* For SETUP msg */ - capi_msg cmsg; /* For CAPI like messages */ - char display[85];/* display message data */ - isdn_cmd_stat isdn_io; /* ISDN IO-parameter/result */ - aux_s aux; /* for modem commands/indications */ -#ifdef CONFIG_ISDN_TTY_FAX - T30_s *fax; /* Pointer to ttys fax struct */ -#endif - ulong userdata; /* User Data */ - } parm; -} isdn_ctrl; - -#define dss1_io isdn_io -#define ni1_io isdn_io - -/* - * The interface-struct itself (initialized at load-time of lowlevel-driver) - * - * See Documentation/isdn/INTERFACE for a description, how the communication - * between the ISDN subsystem and its drivers is done. - * - */ -typedef struct { - struct module *owner; - - /* Number of channels supported by this driver - */ - int channels; - - /* - * Maximum Size of transmit/receive-buffer this driver supports. - */ - int maxbufsize; - - /* Feature-Flags for this driver. - * See defines ISDN_FEATURE_... for Values - */ - unsigned long features; - - /* - * Needed for calculating - * dev->hard_header_len = linklayer header + hl_hdrlen; - * Drivers, not supporting sk_buff's should set this to 0. - */ - unsigned short hl_hdrlen; - - /* - * Receive-Callback using sk_buff's - * Parameters: - * int Driver-ID - * int local channel-number (0 ...) - * struct sk_buff *skb received Data - */ - void (*rcvcallb_skb)(int, int, struct sk_buff *); - - /* Status-Callback - * Parameters: - * isdn_ctrl* - * driver = Driver ID. - * command = One of above ISDN_STAT_... constants. - * arg = depending on status-type. - * num = depending on status-type. - */ - int (*statcallb)(isdn_ctrl*); - - /* Send command - * Parameters: - * isdn_ctrl* - * driver = Driver ID. - * command = One of above ISDN_CMD_... constants. - * arg = depending on command. - * num = depending on command. - */ - int (*command)(isdn_ctrl*); - - /* - * Send data using sk_buff's - * Parameters: - * int driverId - * int local channel-number (0...) - * int Flag: Need ACK for this packet. - * struct sk_buff *skb Data to send - */ - int (*writebuf_skb) (int, int, int, struct sk_buff *); - - /* Send raw D-Channel-Commands - * Parameters: - * u_char pointer data - * int length of data - * int driverId - * int local channel-number (0 ...) - */ - int (*writecmd)(const u_char __user *, int, int, int); - - /* Read raw Status replies - * u_char pointer data (volatile) - * int length of buffer - * int driverId - * int local channel-number (0 ...) - */ - int (*readstat)(u_char __user *, int, int, int); - - char id[20]; -} isdn_if; - -/* - * Function which must be called by lowlevel-driver at loadtime with - * the following fields of above struct set: - * - * channels Number of channels that will be supported. - * hl_hdrlen Space to preserve in sk_buff's when sending. Drivers, not - * supporting sk_buff's should set this to 0. - * command Address of Command-Handler. - * features Bitwise coded Features of this driver. (use ISDN_FEATURE_...) - * writebuf_skb Address of Skbuff-Send-Handler. - * writecmd " " D-Channel " which accepts raw D-Ch-Commands. - * readstat " " D-Channel " which delivers raw Status-Data. - * - * The linklevel-driver fills the following fields: - * - * channels Driver-ID assigned to this driver. (Must be used on all - * subsequent callbacks. - * rcvcallb_skb Address of handler for received Skbuff's. - * statcallb " " " for status-changes. - * - */ -extern int register_isdn(isdn_if*); -#include <linux/uaccess.h> - -#endif /* __ISDNIF_H__ */ diff --git a/include/linux/jhash.h b/include/linux/jhash.h index 8037850f3104..ba2f6a9776b6 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -17,7 +17,7 @@ * if SELF_TEST is defined. You can use this free for any purpose. It's in * the public domain. It has no warranty. * - * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@blackhole.kfki.hu) + * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@netfilter.org) * * I've modified Bob's hash to be useful in the Linux kernel, and * any bugs present are my fault. diff --git a/include/linux/jump_label_ratelimit.h b/include/linux/jump_label_ratelimit.h index 42710d5949ba..8c3ee291b2d8 100644 --- a/include/linux/jump_label_ratelimit.h +++ b/include/linux/jump_label_ratelimit.h @@ -60,8 +60,6 @@ extern void jump_label_update_timeout(struct work_struct *work); 0), \ } -#define static_branch_deferred_inc(x) static_branch_inc(&(x)->key) - #else /* !CONFIG_JUMP_LABEL */ struct static_key_deferred { struct static_key key; @@ -95,4 +93,7 @@ jump_label_rate_limit(struct static_key_deferred *key, STATIC_KEY_CHECK_USE(key); } #endif /* CONFIG_JUMP_LABEL */ + +#define static_branch_deferred_inc(x) static_branch_inc(&(x)->key) + #endif /* _LINUX_JUMP_LABEL_RATELIMIT_H */ diff --git a/include/linux/list.h b/include/linux/list.h index e951228db4b2..85c92555e31f 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -106,6 +106,20 @@ static inline void __list_del(struct list_head * prev, struct list_head * next) WRITE_ONCE(prev->next, next); } +/* + * Delete a list entry and clear the 'prev' pointer. + * + * This is a special-purpose list clearing method used in the networking code + * for lists allocated as per-cpu, where we don't want to incur the extra + * WRITE_ONCE() overhead of a regular list_del_init(). The code that uses this + * needs to check the node 'prev' pointer instead of calling list_empty(). + */ +static inline void __list_del_clearprev(struct list_head *entry) +{ + __list_del(entry->prev, entry->next); + entry->prev = NULL; +} + /** * list_del - deletes entry from list. * @entry: the element to delete from the list. diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index 70e7e5673ce9..5613e677a5f9 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -114,7 +114,7 @@ enum mlx5_accel_ipsec_cap { MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN = 1 << 7, }; -#ifdef CONFIG_MLX5_ACCEL +#ifdef CONFIG_MLX5_FPGA_IPSEC u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev); diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 769326ea1d9b..40748fc1b11b 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -47,7 +47,7 @@ struct mlx5_core_cq { struct completion free; unsigned vector; unsigned int irqn; - void (*comp) (struct mlx5_core_cq *); + void (*comp)(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe); void (*event) (struct mlx5_core_cq *, enum mlx5_event); u32 cons_index; unsigned arm_sn; @@ -55,7 +55,7 @@ struct mlx5_core_cq { int pid; struct { struct list_head list; - void (*comp)(struct mlx5_core_cq *); + void (*comp)(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe); void *priv; } tasklet_ctx; int reset_notify_added; @@ -185,7 +185,7 @@ static inline void mlx5_cq_put(struct mlx5_core_cq *cq) } int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, - u32 *in, int inlen); + u32 *in, int inlen, u32 *out, int outlen); int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); int mlx5_core_query_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *out, int outlen); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index fc2b6e807f06..ce9839c8bc1a 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -342,7 +342,7 @@ enum mlx5_event { MLX5_EVENT_TYPE_PAGE_FAULT = 0xc, MLX5_EVENT_TYPE_NIC_VPORT_CHANGE = 0xd, - MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE = 0xe, + MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED = 0xe, MLX5_EVENT_TYPE_DCT_DRAINED = 0x1c, @@ -351,7 +351,7 @@ enum mlx5_event { MLX5_EVENT_TYPE_DEVICE_TRACER = 0x26, - MLX5_EVENT_TYPE_MAX = MLX5_EVENT_TYPE_DEVICE_TRACER + 1, + MLX5_EVENT_TYPE_MAX = 0x100, }; enum { @@ -437,6 +437,7 @@ enum { MLX5_OPCODE_SET_PSV = 0x20, MLX5_OPCODE_GET_PSV = 0x21, MLX5_OPCODE_CHECK_PSV = 0x22, + MLX5_OPCODE_DUMP = 0x23, MLX5_OPCODE_RGET_PSV = 0x26, MLX5_OPCODE_RCHECK_PSV = 0x27, @@ -445,6 +446,14 @@ enum { }; enum { + MLX5_OPC_MOD_TLS_TIS_STATIC_PARAMS = 0x20, +}; + +enum { + MLX5_OPC_MOD_TLS_TIS_PROGRESS_PARAMS = 0x20, +}; + +enum { MLX5_SET_PORT_RESET_QKEY = 0, MLX5_SET_PORT_GUID0 = 16, MLX5_SET_PORT_NODE_GUID = 17, @@ -510,6 +519,10 @@ struct mlx5_cmd_layout { u8 status_own; }; +enum mlx5_fatal_assert_bit_offsets { + MLX5_RFR_OFFSET = 31, +}; + struct health_buffer { __be32 assert_var[5]; __be32 rsvd0[3]; @@ -518,12 +531,16 @@ struct health_buffer { __be32 rsvd1[2]; __be32 fw_ver; __be32 hw_id; - __be32 rsvd2; + __be32 rfr; u8 irisc_index; u8 synd; __be16 ext_synd; }; +enum mlx5_initializing_bit_offsets { + MLX5_FW_RESET_SUPPORTED_OFFSET = 30, +}; + enum mlx5_cmd_addr_l_sz_offset { MLX5_NIC_IFC_OFFSET = 8, }; @@ -1077,6 +1094,9 @@ enum mlx5_cap_type { MLX5_CAP_DEBUG, MLX5_CAP_RESERVED_14, MLX5_CAP_DEV_MEM, + MLX5_CAP_RESERVED_16, + MLX5_CAP_TLS, + MLX5_CAP_DEV_EVENT = 0x14, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1255,6 +1275,12 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP64_DEV_MEM(mdev, cap)\ MLX5_GET64(device_mem_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_MEM], cap) +#define MLX5_CAP_TLS(mdev, cap) \ + MLX5_GET(tls_cap, (mdev)->caps.hca_cur[MLX5_CAP_TLS], cap) + +#define MLX5_CAP_DEV_EVENT(mdev, cap)\ + MLX5_ADDR_OF(device_event_cap, (mdev)->caps.hca_cur[MLX5_CAP_DEV_EVENT], cap) + enum { MLX5_CMD_STAT_OK = 0x0, MLX5_CMD_STAT_INT_ERR = 0x1, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5a27246db883..0e6da1840c7d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -41,7 +41,7 @@ #include <linux/semaphore.h> #include <linux/slab.h> #include <linux/vmalloc.h> -#include <linux/radix-tree.h> +#include <linux/xarray.h> #include <linux/workqueue.h> #include <linux/mempool.h> #include <linux/interrupt.h> @@ -53,6 +53,7 @@ #include <linux/mlx5/eq.h> #include <linux/timecounter.h> #include <linux/ptp_clock_kernel.h> +#include <net/devlink.h> enum { MLX5_BOARD_ID_LEN = 64, @@ -107,6 +108,7 @@ enum { MLX5_REG_FPGA_CAP = 0x4022, MLX5_REG_FPGA_CTRL = 0x4023, MLX5_REG_FPGA_ACCESS_REG = 0x4024, + MLX5_REG_CORE_DUMP = 0x402e, MLX5_REG_PCAP = 0x5001, MLX5_REG_PMTU = 0x5003, MLX5_REG_PTYS = 0x5004, @@ -137,6 +139,7 @@ enum { MLX5_REG_MTPPS = 0x9053, MLX5_REG_MTPPSE = 0x9054, MLX5_REG_MPEGC = 0x9056, + MLX5_REG_MCQS = 0x9060, MLX5_REG_MCQI = 0x9061, MLX5_REG_MCC = 0x9062, MLX5_REG_MCDA = 0x9063, @@ -180,6 +183,11 @@ enum port_state_policy { MLX5_POLICY_INVALID = 0xffffffff }; +enum mlx5_coredev_type { + MLX5_COREDEV_PF, + MLX5_COREDEV_VF +}; + struct mlx5_field_desc { struct dentry *dent; int i; @@ -433,13 +441,18 @@ struct mlx5_core_health { struct timer_list timer; u32 prev; int miss_counter; - bool sick; + u8 synd; + u32 fatal_error; + u32 crdump_size; /* wq spinlock to synchronize draining */ spinlock_t wq_lock; struct workqueue_struct *wq; unsigned long flags; - struct work_struct work; + struct work_struct fatal_report_work; + struct work_struct report_work; struct delayed_work recover_work; + struct devlink_health_reporter *fw_reporter; + struct devlink_health_reporter *fw_fatal_reporter; }; struct mlx5_qp_table { @@ -451,13 +464,6 @@ struct mlx5_qp_table { struct radix_tree_root tree; }; -struct mlx5_mkey_table { - /* protect radix tree - */ - rwlock_t lock; - struct radix_tree_root tree; -}; - struct mlx5_vf_context { int enabled; u64 port_guid; @@ -468,7 +474,7 @@ struct mlx5_vf_context { struct mlx5_core_sriov { struct mlx5_vf_context *vfs_ctx; int num_vfs; - int enabled_vfs; + u16 max_vfs; }; struct mlx5_fc_stats { @@ -490,6 +496,7 @@ struct mlx5_eswitch; struct mlx5_lag; struct mlx5_devcom; struct mlx5_eq_table; +struct mlx5_irq_table; struct mlx5_rate_limit { u32 rate; @@ -519,6 +526,8 @@ struct mlx5_core_roce { }; struct mlx5_priv { + /* IRQ table valid only for real pci devices PF or VF */ + struct mlx5_irq_table *irq_table; struct mlx5_eq_table *eq_table; /* pages stuff */ @@ -541,9 +550,7 @@ struct mlx5_priv { struct dentry *cmdif_debugfs; /* end: qp staff */ - /* start: mkey staff */ - struct mlx5_mkey_table mkey_table; - /* end: mkey staff */ + struct xarray mkey_table; /* start: alloc staff */ /* protect buffer alocation according to numa node */ @@ -570,7 +577,6 @@ struct mlx5_priv { struct mlx5_core_sriov sriov; struct mlx5_lag *lag; struct mlx5_devcom *devcom; - unsigned long pci_dev_data; struct mlx5_core_roce roce; struct mlx5_fc_stats fc_stats; struct mlx5_rl_table rl_table; @@ -580,6 +586,7 @@ struct mlx5_priv { }; enum mlx5_device_state { + MLX5_DEVICE_STATE_UNINITIALIZED, MLX5_DEVICE_STATE_UP, MLX5_DEVICE_STATE_INTERNAL_ERROR, }; @@ -646,9 +653,11 @@ struct mlx5_clock { struct mlx5_fw_tracer; struct mlx5_vxlan; +struct mlx5_geneve; struct mlx5_core_dev { struct device *device; + enum mlx5_coredev_type coredev_type; struct pci_dev *pdev; /* sync pci state */ struct mutex pci_status_mutex; @@ -680,6 +689,7 @@ struct mlx5_core_dev { u32 issi; struct mlx5e_resources mlx5e_res; struct mlx5_vxlan *vxlan; + struct mlx5_geneve *geneve; struct { struct mlx5_rsvd_gids reserved_gids; u32 roce_en; @@ -690,6 +700,7 @@ struct mlx5_core_dev { struct mlx5_clock clock; struct mlx5_ib_clock_info *clock_info; struct mlx5_fw_tracer *tracer; + u32 vsc_addr; }; struct mlx5_db { @@ -901,7 +912,6 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); void mlx5_trigger_health_work(struct mlx5_core_dev *dev); -void mlx5_drain_health_recovery(struct mlx5_core_dev *dev); int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size, struct mlx5_frag_buf *buf, int node); int mlx5_buf_alloc(struct mlx5_core_dev *dev, @@ -1042,6 +1052,8 @@ int mlx5_register_interface(struct mlx5_interface *intf); void mlx5_unregister_interface(struct mlx5_interface *intf); int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb); int mlx5_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb); +int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb); +int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb); int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id); @@ -1082,9 +1094,9 @@ enum { MLX5_PCI_DEV_IS_VF = 1 << 0, }; -static inline int mlx5_core_is_pf(struct mlx5_core_dev *dev) +static inline bool mlx5_core_is_pf(const struct mlx5_core_dev *dev) { - return !(dev->priv.pci_dev_data & MLX5_PCI_DEV_IS_VF); + return dev->coredev_type == MLX5_COREDEV_PF; } static inline bool mlx5_core_is_ecpf(struct mlx5_core_dev *dev) @@ -1092,23 +1104,20 @@ static inline bool mlx5_core_is_ecpf(struct mlx5_core_dev *dev) return dev->caps.embedded_cpu; } -static inline bool mlx5_core_is_ecpf_esw_manager(struct mlx5_core_dev *dev) +static inline bool +mlx5_core_is_ecpf_esw_manager(const struct mlx5_core_dev *dev) { return dev->caps.embedded_cpu && MLX5_CAP_GEN(dev, eswitch_manager); } -static inline bool mlx5_ecpf_vport_exists(struct mlx5_core_dev *dev) +static inline bool mlx5_ecpf_vport_exists(const struct mlx5_core_dev *dev) { return mlx5_core_is_pf(dev) && MLX5_CAP_ESW(dev, ecpf_vport_exists); } -#define MLX5_HOST_PF_MAX_VFS (127u) -static inline u16 mlx5_core_max_vfs(struct mlx5_core_dev *dev) +static inline u16 mlx5_core_max_vfs(const struct mlx5_core_dev *dev) { - if (mlx5_core_is_ecpf_esw_manager(dev)) - return MLX5_HOST_PF_MAX_VFS; - else - return pci_sriov_get_totalvfs(dev->pdev); + return dev->priv.sriov.max_vfs; } static inline int mlx5_get_gid_table_len(u16 param) diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index 00045cc4ea11..e49d8c0d4f26 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -4,17 +4,7 @@ #ifndef MLX5_CORE_EQ_H #define MLX5_CORE_EQ_H -enum { - MLX5_EQ_PAGEREQ_IDX = 0, - MLX5_EQ_CMD_IDX = 1, - MLX5_EQ_ASYNC_IDX = 2, - /* reserved to be used by mlx5_core ulps (mlx5e/mlx5_ib) */ - MLX5_EQ_PFAULT_IDX = 3, - MLX5_EQ_MAX_ASYNC_EQS, - /* completion eqs vector indices start here */ - MLX5_EQ_VEC_COMP_BASE = MLX5_EQ_MAX_ASYNC_EQS, -}; - +#define MLX5_IRQ_VEC_COMP_BASE 1 #define MLX5_NUM_CMD_EQE (32) #define MLX5_NUM_ASYNC_EQE (0x1000) #define MLX5_NUM_SPARE_EQE (0x80) @@ -23,18 +13,19 @@ struct mlx5_eq; struct mlx5_core_dev; struct mlx5_eq_param { - u8 index; + u8 irq_index; int nent; - u64 mask; - void *context; - irq_handler_t handler; + u64 mask[4]; }; struct mlx5_eq * -mlx5_eq_create_generic(struct mlx5_core_dev *dev, const char *name, - struct mlx5_eq_param *param); +mlx5_eq_create_generic(struct mlx5_core_dev *dev, struct mlx5_eq_param *param); int mlx5_eq_destroy_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq); +int mlx5_eq_enable(struct mlx5_core_dev *dev, struct mlx5_eq *eq, + struct notifier_block *nb); +void mlx5_eq_disable(struct mlx5_core_dev *dev, struct mlx5_eq *eq, + struct notifier_block *nb); struct mlx5_eqe *mlx5_eq_get_eqe(struct mlx5_eq *eq, u32 cc); void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm); diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index cf226c190329..46b5ba029802 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -7,13 +7,14 @@ #define _MLX5_ESWITCH_ #include <linux/mlx5/driver.h> +#include <net/devlink.h> #define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager) enum { - SRIOV_NONE, - SRIOV_LEGACY, - SRIOV_OFFLOADS + MLX5_ESWITCH_NONE, + MLX5_ESWITCH_LEGACY, + MLX5_ESWITCH_OFFLOADS }; enum { @@ -29,25 +30,29 @@ enum { }; struct mlx5_eswitch_rep; -struct mlx5_eswitch_rep_if { - int (*load)(struct mlx5_core_dev *dev, - struct mlx5_eswitch_rep *rep); - void (*unload)(struct mlx5_eswitch_rep *rep); - void *(*get_proto_dev)(struct mlx5_eswitch_rep *rep); - void *priv; - atomic_t state; +struct mlx5_eswitch_rep_ops { + int (*load)(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep); + void (*unload)(struct mlx5_eswitch_rep *rep); + void *(*get_proto_dev)(struct mlx5_eswitch_rep *rep); +}; + +struct mlx5_eswitch_rep_data { + void *priv; + atomic_t state; }; struct mlx5_eswitch_rep { - struct mlx5_eswitch_rep_if rep_if[NUM_REP_TYPES]; + struct mlx5_eswitch_rep_data rep_data[NUM_REP_TYPES]; u16 vport; u8 hw_id[ETH_ALEN]; u16 vlan; + /* Only IB rep is using vport_index */ + u16 vport_index; u32 vlan_refcount; }; void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw, - struct mlx5_eswitch_rep_if *rep_if, + const struct mlx5_eswitch_rep_ops *ops, u8 rep_type); void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type); void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw, @@ -60,4 +65,35 @@ u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw); struct mlx5_flow_handle * mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, u16 vport_num, u32 sqn); + +u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev); + +#ifdef CONFIG_MLX5_ESWITCH +enum devlink_eswitch_encap_mode +mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev); + +bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw); +u32 mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw, + u16 vport_num); +#else /* CONFIG_MLX5_ESWITCH */ +static inline enum devlink_eswitch_encap_mode +mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev) +{ + return DEVLINK_ESWITCH_ENCAP_MODE_NONE; +} + +static inline bool +mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw) +{ + return false; +}; + +static inline u32 +mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw, + int vport_num) +{ + return 0; +}; +#endif /* CONFIG_MLX5_ESWITCH */ + #endif diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index e690ba0f965c..04a569568eac 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -47,6 +47,7 @@ enum { enum { MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT = BIT(0), MLX5_FLOW_TABLE_TUNNEL_EN_DECAP = BIT(1), + MLX5_FLOW_TABLE_TERMINATION = BIT(2), }; #define LEFTOVERS_RULE_NUM 2 @@ -87,10 +88,21 @@ struct mlx5_flow_group; struct mlx5_flow_namespace; struct mlx5_flow_handle; +enum { + FLOW_CONTEXT_HAS_TAG = BIT(0), +}; + +struct mlx5_flow_context { + u32 flags; + u32 flow_tag; + u32 flow_source; +}; + struct mlx5_flow_spec { u8 match_criteria_enable; u32 match_criteria[MLX5_ST_SZ_DW(fte_match_param)]; u32 match_value[MLX5_ST_SZ_DW(fte_match_param)]; + struct mlx5_flow_context flow_context; }; enum { @@ -172,13 +184,11 @@ struct mlx5_fs_vlan { #define MLX5_FS_VLAN_DEPTH 2 enum { - FLOW_ACT_HAS_TAG = BIT(0), - FLOW_ACT_NO_APPEND = BIT(1), + FLOW_ACT_NO_APPEND = BIT(0), }; struct mlx5_flow_act { u32 action; - u32 flow_tag; u32 reformat_id; u32 modify_id; uintptr_t esp_id; @@ -189,7 +199,6 @@ struct mlx5_flow_act { #define MLX5_DECLARE_FLOW_ACT(name) \ struct mlx5_flow_act name = { .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\ - .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG, \ .reformat_id = 0, \ .modify_id = 0, \ .flags = 0, } @@ -199,7 +208,7 @@ struct mlx5_flow_act { */ struct mlx5_flow_handle * mlx5_add_flow_rules(struct mlx5_flow_table *ft, - struct mlx5_flow_spec *spec, + const struct mlx5_flow_spec *spec, struct mlx5_flow_act *flow_act, struct mlx5_flow_destination *dest, int num_dest); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 5e74305e2e57..06881b79167e 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -91,6 +91,20 @@ enum { enum { MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b, + MLX5_OBJ_TYPE_MKEY = 0xff01, + MLX5_OBJ_TYPE_QP = 0xff02, + MLX5_OBJ_TYPE_PSV = 0xff03, + MLX5_OBJ_TYPE_RMP = 0xff04, + MLX5_OBJ_TYPE_XRC_SRQ = 0xff05, + MLX5_OBJ_TYPE_RQ = 0xff06, + MLX5_OBJ_TYPE_SQ = 0xff07, + MLX5_OBJ_TYPE_TIR = 0xff08, + MLX5_OBJ_TYPE_TIS = 0xff09, + MLX5_OBJ_TYPE_DCT = 0xff0a, + MLX5_OBJ_TYPE_XRQ = 0xff0b, + MLX5_OBJ_TYPE_RQT = 0xff0e, + MLX5_OBJ_TYPE_FLOW_COUNTER = 0xff0f, + MLX5_OBJ_TYPE_CQ = 0xff10, }; enum { @@ -106,6 +120,9 @@ enum { MLX5_CMD_OP_QUERY_ISSI = 0x10a, MLX5_CMD_OP_SET_ISSI = 0x10b, MLX5_CMD_OP_SET_DRIVER_VERSION = 0x10d, + MLX5_CMD_OP_QUERY_SF_PARTITION = 0x111, + MLX5_CMD_OP_ALLOC_SF = 0x113, + MLX5_CMD_OP_DEALLOC_SF = 0x114, MLX5_CMD_OP_CREATE_MKEY = 0x200, MLX5_CMD_OP_QUERY_MKEY = 0x201, MLX5_CMD_OP_DESTROY_MKEY = 0x202, @@ -155,7 +172,7 @@ enum { MLX5_CMD_OP_QUERY_XRQ_DC_PARAMS_ENTRY = 0x725, MLX5_CMD_OP_SET_XRQ_DC_PARAMS_ENTRY = 0x726, MLX5_CMD_OP_QUERY_XRQ_ERROR_PARAMS = 0x727, - MLX5_CMD_OP_QUERY_HOST_PARAMS = 0x740, + MLX5_CMD_OP_QUERY_ESW_FUNCTIONS = 0x740, MLX5_CMD_OP_QUERY_VPORT_STATE = 0x750, MLX5_CMD_OP_MODIFY_VPORT_STATE = 0x751, MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT = 0x752, @@ -382,7 +399,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reformat_and_modify_action[0x1]; u8 reserved_at_15[0x2]; u8 table_miss_action_domain[0x1]; - u8 reserved_at_18[0x8]; + u8 termination_table[0x1]; + u8 reserved_at_19[0x7]; u8 reserved_at_20[0x2]; u8 log_max_ft_size[0x6]; u8 log_max_modify_header_context[0x8]; @@ -527,7 +545,21 @@ struct mlx5_ifc_fte_match_set_misc2_bits { struct mlx5_ifc_fte_match_mpls_bits outer_first_mpls_over_udp; - u8 reserved_at_80[0x100]; + u8 metadata_reg_c_7[0x20]; + + u8 metadata_reg_c_6[0x20]; + + u8 metadata_reg_c_5[0x20]; + + u8 metadata_reg_c_4[0x20]; + + u8 metadata_reg_c_3[0x20]; + + u8 metadata_reg_c_2[0x20]; + + u8 metadata_reg_c_1[0x20]; + + u8 metadata_reg_c_0[0x20]; u8 metadata_reg_a[0x20]; @@ -635,8 +667,22 @@ struct mlx5_ifc_flow_table_nic_cap_bits { u8 reserved_at_e00[0x7200]; }; +enum { + MLX5_FDB_TO_VPORT_REG_C_0 = 0x01, + MLX5_FDB_TO_VPORT_REG_C_1 = 0x02, + MLX5_FDB_TO_VPORT_REG_C_2 = 0x04, + MLX5_FDB_TO_VPORT_REG_C_3 = 0x08, + MLX5_FDB_TO_VPORT_REG_C_4 = 0x10, + MLX5_FDB_TO_VPORT_REG_C_5 = 0x20, + MLX5_FDB_TO_VPORT_REG_C_6 = 0x40, + MLX5_FDB_TO_VPORT_REG_C_7 = 0x80, +}; + struct mlx5_ifc_flow_table_eswitch_cap_bits { - u8 reserved_at_0[0x1a]; + u8 fdb_to_vport_reg_c_id[0x8]; + u8 reserved_at_8[0xf]; + u8 flow_source[0x1]; + u8 reserved_at_18[0x2]; u8 multi_fdb_encap[0x1]; u8 reserved_at_1b[0x1]; u8 fdb_multi_path_to_table[0x1]; @@ -664,7 +710,11 @@ struct mlx5_ifc_e_switch_cap_bits { u8 vport_svlan_insert[0x1]; u8 vport_cvlan_insert_if_not_exist[0x1]; u8 vport_cvlan_insert_overwrite[0x1]; - u8 reserved_at_5[0x16]; + u8 reserved_at_5[0x3]; + u8 esw_uplink_ingress_acl[0x1]; + u8 reserved_at_9[0x10]; + u8 esw_functions_changed[0x1]; + u8 reserved_at_1a[0x1]; u8 ecpf_vport_exists[0x1]; u8 counter_eswitch_affinity[0x1]; u8 merged_eswitch[0x1]; @@ -680,7 +730,11 @@ struct mlx5_ifc_e_switch_cap_bits { u8 reserved_2b[0x6]; u8 max_encap_header_size[0xa]; - u8 reserved_40[0x7c0]; + u8 reserved_at_40[0xb]; + u8 log_max_esw_sf[0x5]; + u8 esw_sf_base_id[0x10]; + + u8 reserved_at_60[0x7a0]; }; @@ -715,7 +769,9 @@ struct mlx5_ifc_qos_cap_bits { }; struct mlx5_ifc_debug_cap_bits { - u8 reserved_at_0[0x20]; + u8 core_dump_general[0x1]; + u8 core_dump_qp[0x1]; + u8 reserved_at_2[0x1e]; u8 reserved_at_20[0x2]; u8 stall_detect[0x1]; @@ -818,6 +874,12 @@ struct mlx5_ifc_device_mem_cap_bits { u8 reserved_at_180[0x680]; }; +struct mlx5_ifc_device_event_cap_bits { + u8 user_affiliated_events[4][0x40]; + + u8 user_unaffiliated_events[4][0x40]; +}; + enum { MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_1_BYTE = 0x0, MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_2_BYTES = 0x2, @@ -911,6 +973,16 @@ struct mlx5_ifc_vector_calc_cap_bits { u8 reserved_at_c0[0x720]; }; +struct mlx5_ifc_tls_cap_bits { + u8 tls_1_2_aes_gcm_128[0x1]; + u8 tls_1_3_aes_gcm_128[0x1]; + u8 tls_1_2_aes_gcm_256[0x1]; + u8 tls_1_3_aes_gcm_256[0x1]; + u8 reserved_at_4[0x1c]; + + u8 reserved_at_20[0x7e0]; +}; + enum { MLX5_WQ_TYPE_LINKED_LIST = 0x0, MLX5_WQ_TYPE_CYCLIC = 0x1, @@ -975,7 +1047,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_srq_sz[0x8]; u8 log_max_qp_sz[0x8]; - u8 reserved_at_90[0x8]; + u8 event_cap[0x1]; + u8 reserved_at_91[0x7]; u8 prio_tag_required[0x1]; u8 reserved_at_99[0x2]; u8 log_max_qp[0x5]; @@ -1023,7 +1096,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 cc_modify_allowed[0x1]; u8 start_pad[0x1]; u8 cache_line_128byte[0x1]; - u8 reserved_at_165[0xa]; + u8 reserved_at_165[0x4]; + u8 rts2rts_qp_counters_set_id[0x1]; + u8 reserved_at_16a[0x5]; u8 qcam_reg[0x1]; u8 gid_table_size[0x10]; @@ -1240,7 +1315,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_440[0x20]; - u8 reserved_at_460[0x3]; + u8 tls[0x1]; + u8 reserved_at_461[0x2]; u8 log_max_uctx[0x5]; u8 reserved_at_468[0x3]; u8 log_max_umem[0x5]; @@ -1265,7 +1341,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 max_geneve_tlv_option_data_len[0x5]; u8 reserved_at_570[0x10]; - u8 reserved_at_580[0x3c]; + u8 reserved_at_580[0x33]; + u8 log_max_dek[0x5]; + u8 reserved_at_5b8[0x4]; u8 mini_cqe_resp_stride_index[0x1]; u8 cqe_128_always[0x1]; u8 cqe_compression_128[0x1]; @@ -1295,13 +1373,24 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_640[0x10]; u8 num_q_monitor_counters[0x10]; - u8 reserved_at_660[0x40]; + u8 reserved_at_660[0x20]; + + u8 sf[0x1]; + u8 sf_set_partition[0x1]; + u8 reserved_at_682[0x1]; + u8 log_max_sf[0x5]; + u8 reserved_at_688[0x8]; + u8 log_min_sf_size[0x8]; + u8 max_num_sf_partitions[0x8]; u8 uctx_cap[0x20]; u8 reserved_at_6c0[0x4]; u8 flex_parser_id_geneve_tlv_option_0[0x4]; - u8 reserved_at_6c8[0x138]; + u8 reserved_at_6c8[0x28]; + u8 sf_base_id[0x10]; + + u8 reserved_at_700[0x100]; }; enum mlx5_flow_destination_type { @@ -2531,7 +2620,9 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_e_switch_cap_bits e_switch_cap; struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap; struct mlx5_ifc_qos_cap_bits qos_cap; + struct mlx5_ifc_debug_cap_bits debug_cap; struct mlx5_ifc_fpga_cap_bits fpga_cap; + struct mlx5_ifc_tls_cap_bits tls_cap; u8 reserved_at_0[0x8000]; }; @@ -2549,6 +2640,12 @@ enum { MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2 = 0x800, }; +enum { + MLX5_FLOW_CONTEXT_FLOW_SOURCE_ANY_VPORT = 0x0, + MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK = 0x1, + MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT = 0x2, +}; + struct mlx5_ifc_vlan_bits { u8 ethtype[0x10]; u8 prio[0x3]; @@ -2568,7 +2665,9 @@ struct mlx5_ifc_flow_context_bits { u8 action[0x10]; u8 extended_destination[0x1]; - u8 reserved_at_80[0x7]; + u8 reserved_at_81[0x1]; + u8 flow_source[0x2]; + u8 reserved_at_84[0x4]; u8 destination_list_size[0x18]; u8 reserved_at_a0[0x8]; @@ -2663,7 +2762,8 @@ struct mlx5_ifc_traffic_counter_bits { struct mlx5_ifc_tisc_bits { u8 strict_lag_tx_port_affinity[0x1]; - u8 reserved_at_1[0x3]; + u8 tls_en[0x1]; + u8 reserved_at_1[0x2]; u8 lag_tx_port_affinity[0x04]; u8 reserved_at_8[0x4]; @@ -2677,7 +2777,11 @@ struct mlx5_ifc_tisc_bits { u8 reserved_at_140[0x8]; u8 underlay_qpn[0x18]; - u8 reserved_at_160[0x3a0]; + + u8 reserved_at_160[0x8]; + u8 pd[0x18]; + + u8 reserved_at_180[0x380]; }; enum { @@ -3093,12 +3197,14 @@ struct mlx5_ifc_hca_vport_context_bits { }; struct mlx5_ifc_esw_vport_context_bits { - u8 reserved_at_0[0x3]; + u8 fdb_to_vport_reg_c[0x1]; + u8 reserved_at_1[0x2]; u8 vport_svlan_strip[0x1]; u8 vport_cvlan_strip[0x1]; u8 vport_svlan_insert[0x1]; u8 vport_cvlan_insert[0x2]; - u8 reserved_at_8[0x18]; + u8 fdb_to_vport_reg_c_id[0x8]; + u8 reserved_at_10[0x10]; u8 reserved_at_20[0x20]; @@ -4979,7 +5085,8 @@ struct mlx5_ifc_modify_esw_vport_context_out_bits { }; struct mlx5_ifc_esw_vport_context_fields_select_bits { - u8 reserved_at_0[0x1c]; + u8 reserved_at_0[0x1b]; + u8 fdb_to_vport_reg_c_id[0x1]; u8 vport_cvlan_insert[0x1]; u8 vport_svlan_insert[0x1]; u8 vport_cvlan_strip[0x1]; @@ -5176,6 +5283,7 @@ enum { MLX5_ACTION_IN_FIELD_OUT_DIPV4 = 0x16, MLX5_ACTION_IN_FIELD_OUT_FIRST_VID = 0x17, MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT = 0x47, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_0 = 0x51, }; struct mlx5_ifc_alloc_modify_header_context_out_bits { @@ -7236,7 +7344,8 @@ struct mlx5_ifc_create_flow_table_out_bits { struct mlx5_ifc_flow_table_context_bits { u8 reformat_en[0x1]; u8 decap_en[0x1]; - u8 reserved_at_2[0x2]; + u8 reserved_at_2[0x1]; + u8 termination_table[0x1]; u8 table_miss_action[0x4]; u8 level[0x8]; u8 reserved_at_10[0x8]; @@ -7355,9 +7464,9 @@ struct mlx5_ifc_create_eq_in_bits { u8 reserved_at_280[0x40]; - u8 event_bitmask[0x40]; + u8 event_bitmask[4][0x40]; - u8 reserved_at_300[0x580]; + u8 reserved_at_3c0[0x4c0]; u8 pas[0][0x40]; }; @@ -8475,7 +8584,7 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 mcda[0x1]; u8 mcc[0x1]; u8 mcqi[0x1]; - u8 reserved_at_1f[0x1]; + u8 mcqs[0x1]; u8 regs_95_to_87[0x9]; u8 mpegc[0x1]; @@ -8546,6 +8655,18 @@ struct mlx5_ifc_qcam_reg_bits { u8 reserved_at_1c0[0x80]; }; +struct mlx5_ifc_core_dump_reg_bits { + u8 reserved_at_0[0x18]; + u8 core_dump_type[0x8]; + + u8 reserved_at_20[0x30]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x8]; + u8 qpn[0x18]; + u8 reserved_at_80[0x180]; +}; + struct mlx5_ifc_pcap_reg_bits { u8 reserved_at_0[0x8]; u8 local_port[0x8]; @@ -8955,6 +9076,24 @@ struct mlx5_ifc_mtppse_reg_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_mcqs_reg_bits { + u8 last_index_flag[0x1]; + u8 reserved_at_1[0x7]; + u8 fw_device[0x8]; + u8 component_index[0x10]; + + u8 reserved_at_20[0x10]; + u8 identifier[0x10]; + + u8 reserved_at_40[0x17]; + u8 component_status[0x5]; + u8 component_update_state[0x4]; + + u8 last_update_state_changer_type[0x4]; + u8 last_update_state_changer_host_id[0x4]; + u8 reserved_at_68[0x18]; +}; + struct mlx5_ifc_mcqi_cap_bits { u8 supported_info_bitmask[0x20]; @@ -8975,6 +9114,43 @@ struct mlx5_ifc_mcqi_cap_bits { u8 reserved_at_86[0x1a]; }; +struct mlx5_ifc_mcqi_version_bits { + u8 reserved_at_0[0x2]; + u8 build_time_valid[0x1]; + u8 user_defined_time_valid[0x1]; + u8 reserved_at_4[0x14]; + u8 version_string_length[0x8]; + + u8 version[0x20]; + + u8 build_time[0x40]; + + u8 user_defined_time[0x40]; + + u8 build_tool_version[0x20]; + + u8 reserved_at_e0[0x20]; + + u8 version_string[92][0x8]; +}; + +struct mlx5_ifc_mcqi_activation_method_bits { + u8 pending_server_ac_power_cycle[0x1]; + u8 pending_server_dc_power_cycle[0x1]; + u8 pending_server_reboot[0x1]; + u8 pending_fw_reset[0x1]; + u8 auto_activate[0x1]; + u8 all_hosts_sync[0x1]; + u8 device_hw_reset[0x1]; + u8 reserved_at_7[0x19]; +}; + +union mlx5_ifc_mcqi_reg_data_bits { + struct mlx5_ifc_mcqi_cap_bits mcqi_caps; + struct mlx5_ifc_mcqi_version_bits mcqi_version; + struct mlx5_ifc_mcqi_activation_method_bits mcqi_activation_mathod; +}; + struct mlx5_ifc_mcqi_reg_bits { u8 read_pending_component[0x1]; u8 reserved_at_1[0xf]; @@ -8992,7 +9168,7 @@ struct mlx5_ifc_mcqi_reg_bits { u8 reserved_at_a0[0x10]; u8 data_size[0x10]; - u8 data[0][0x20]; + union mlx5_ifc_mcqi_reg_data_bits data[0]; }; struct mlx5_ifc_mcc_reg_bits { @@ -9689,10 +9865,11 @@ struct mlx5_ifc_mtrc_ctrl_bits { struct mlx5_ifc_host_params_context_bits { u8 host_number[0x8]; - u8 reserved_at_8[0x8]; + u8 reserved_at_8[0x7]; + u8 host_pf_disabled[0x1]; u8 host_num_of_vfs[0x10]; - u8 reserved_at_20[0x10]; + u8 host_total_vfs[0x10]; u8 host_pci_bus[0x10]; u8 reserved_at_40[0x10]; @@ -9704,7 +9881,7 @@ struct mlx5_ifc_host_params_context_bits { u8 reserved_at_80[0x180]; }; -struct mlx5_ifc_query_host_params_in_bits { +struct mlx5_ifc_query_esw_functions_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; @@ -9714,7 +9891,7 @@ struct mlx5_ifc_query_host_params_in_bits { u8 reserved_at_40[0x40]; }; -struct mlx5_ifc_query_host_params_out_bits { +struct mlx5_ifc_query_esw_functions_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -9725,6 +9902,165 @@ struct mlx5_ifc_query_host_params_out_bits { struct mlx5_ifc_host_params_context_bits host_params_context; u8 reserved_at_280[0x180]; + u8 host_sf_enable[0][0x40]; +}; + +struct mlx5_ifc_sf_partition_bits { + u8 reserved_at_0[0x10]; + u8 log_num_sf[0x8]; + u8 log_sf_bar_size[0x8]; +}; + +struct mlx5_ifc_query_sf_partitions_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x18]; + u8 num_sf_partitions[0x8]; + + u8 reserved_at_60[0x20]; + + struct mlx5_ifc_sf_partition_bits sf_partition[0]; +}; + +struct mlx5_ifc_query_sf_partitions_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_dealloc_sf_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_dealloc_sf_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 function_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_alloc_sf_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_alloc_sf_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 function_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_affiliated_event_header_bits { + u8 reserved_at_0[0x10]; + u8 obj_type[0x10]; + + u8 obj_id[0x20]; +}; + +enum { + MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = BIT(0xc), +}; + +enum { + MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc, +}; + +struct mlx5_ifc_encryption_key_obj_bits { + u8 modify_field_select[0x40]; + + u8 reserved_at_40[0x14]; + u8 key_size[0x4]; + u8 reserved_at_58[0x4]; + u8 key_type[0x4]; + + u8 reserved_at_60[0x8]; + u8 pd[0x18]; + + u8 reserved_at_80[0x180]; + u8 key[8][0x20]; + + u8 reserved_at_300[0x500]; +}; + +struct mlx5_ifc_create_encryption_key_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + struct mlx5_ifc_encryption_key_obj_bits encryption_key_object; +}; + +enum { + MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_128 = 0x0, + MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_256 = 0x1, +}; + +enum { + MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_DEK = 0x1, +}; + +struct mlx5_ifc_tls_static_params_bits { + u8 const_2[0x2]; + u8 tls_version[0x4]; + u8 const_1[0x2]; + u8 reserved_at_8[0x14]; + u8 encryption_standard[0x4]; + + u8 reserved_at_20[0x20]; + + u8 initial_record_number[0x40]; + + u8 resync_tcp_sn[0x20]; + + u8 gcm_iv[0x20]; + + u8 implicit_iv[0x40]; + + u8 reserved_at_100[0x8]; + u8 dek_index[0x18]; + + u8 reserved_at_120[0xe0]; +}; + +struct mlx5_ifc_tls_progress_params_bits { + u8 valid[0x1]; + u8 reserved_at_1[0x7]; + u8 pd[0x18]; + + u8 next_record_tcp_sn[0x20]; + + u8 hw_resync_tcp_sn[0x20]; + + u8 record_tracker_state[0x2]; + u8 auth_state[0x2]; + u8 reserved_at_64[0x4]; + u8 hw_offset_record_number[0x18]; }; #endif /* MLX5_IFC_H */ diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 3ba4edbd17a6..127d224443e3 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -202,7 +202,12 @@ struct mlx5_wqe_ctrl_seg { u8 signature; u8 rsvd[2]; u8 fm_ce_se; - __be32 imm; + union { + __be32 general_id; + __be32 imm; + __be32 umr_mkey; + __be32 tisn; + }; }; #define MLX5_WQE_CTRL_DS_MASK 0x3f @@ -551,11 +556,6 @@ static inline struct mlx5_core_qp *__mlx5_qp_lookup(struct mlx5_core_dev *dev, u return radix_tree_lookup(&dev->priv.qp_table.tree, qpn); } -static inline struct mlx5_core_mkey *__mlx5_mr_lookup(struct mlx5_core_dev *dev, u32 key) -{ - return radix_tree_lookup(&dev->priv.mkey_table.tree, key); -} - int mlx5_core_create_dct(struct mlx5_core_dev *dev, struct mlx5_core_dct *qp, u32 *in, int inlen, diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 3d1c6cdbbba7..16060fb9b5e5 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -44,9 +44,6 @@ MLX5_VPORT_UPLINK_PLACEHOLDER + \ MLX5_VPORT_ECPF_PLACEHOLDER(mdev)) -#define MLX5_TOTAL_VPORTS(mdev) (MLX5_SPECIAL_VPORTS(mdev) + \ - mlx5_core_max_vfs(mdev)) - #define MLX5_VPORT_MANAGER(mdev) \ (MLX5_CAP_GEN(mdev, vport_group_manager) && \ (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && \ @@ -58,6 +55,7 @@ enum { MLX5_CAP_INLINE_MODE_NOT_REQUIRED, }; +/* Vport number for each function must keep unchanged */ enum { MLX5_VPORT_PF = 0x0, MLX5_VPORT_FIRST_VF = 0x1, @@ -69,7 +67,8 @@ u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport); int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport, u8 other_vport, u8 state); int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, - u16 vport, u8 *addr); + u16 vport, bool other, u8 *addr); +int mlx5_query_mac_address(struct mlx5_core_dev *mdev, u8 *addr); int mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev, u16 vport, u8 *min_inline); void mlx5_query_min_inline(struct mlx5_core_dev *mdev, u8 *min_inline); diff --git a/include/linux/net.h b/include/linux/net.h index f7d672cf25b5..9cafb5f353a9 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -116,11 +116,11 @@ struct socket { unsigned long flags; - struct socket_wq *wq; - struct file *file; struct sock *sk; const struct proto_ops *ops; + + struct socket_wq wq; }; struct vm_area_struct; diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h deleted file mode 100644 index fd458389f7d1..000000000000 --- a/include/linux/net_dim.h +++ /dev/null @@ -1,418 +0,0 @@ -/* - * Copyright (c) 2016, Mellanox Technologies. All rights reserved. - * Copyright (c) 2017-2018, Broadcom Limited. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#ifndef NET_DIM_H -#define NET_DIM_H - -#include <linux/module.h> - -struct net_dim_cq_moder { - u16 usec; - u16 pkts; - u8 cq_period_mode; -}; - -struct net_dim_sample { - ktime_t time; - u32 pkt_ctr; - u32 byte_ctr; - u16 event_ctr; -}; - -struct net_dim_stats { - int ppms; /* packets per msec */ - int bpms; /* bytes per msec */ - int epms; /* events per msec */ -}; - -struct net_dim { /* Adaptive Moderation */ - u8 state; - struct net_dim_stats prev_stats; - struct net_dim_sample start_sample; - struct work_struct work; - u8 profile_ix; - u8 mode; - u8 tune_state; - u8 steps_right; - u8 steps_left; - u8 tired; -}; - -enum { - NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE = 0x0, - NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE = 0x1, - NET_DIM_CQ_PERIOD_NUM_MODES -}; - -/* Adaptive moderation logic */ -enum { - NET_DIM_START_MEASURE, - NET_DIM_MEASURE_IN_PROGRESS, - NET_DIM_APPLY_NEW_PROFILE, -}; - -enum { - NET_DIM_PARKING_ON_TOP, - NET_DIM_PARKING_TIRED, - NET_DIM_GOING_RIGHT, - NET_DIM_GOING_LEFT, -}; - -enum { - NET_DIM_STATS_WORSE, - NET_DIM_STATS_SAME, - NET_DIM_STATS_BETTER, -}; - -enum { - NET_DIM_STEPPED, - NET_DIM_TOO_TIRED, - NET_DIM_ON_EDGE, -}; - -#define NET_DIM_PARAMS_NUM_PROFILES 5 -/* Adaptive moderation profiles */ -#define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256 -#define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128 -#define NET_DIM_DEF_PROFILE_CQE 1 -#define NET_DIM_DEF_PROFILE_EQE 1 - -/* All profiles sizes must be NET_PARAMS_DIM_NUM_PROFILES */ -#define NET_DIM_RX_EQE_PROFILES { \ - {1, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {8, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {64, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {128, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {256, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ -} - -#define NET_DIM_RX_CQE_PROFILES { \ - {2, 256}, \ - {8, 128}, \ - {16, 64}, \ - {32, 64}, \ - {64, 64} \ -} - -#define NET_DIM_TX_EQE_PROFILES { \ - {1, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {8, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {32, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {64, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {128, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE} \ -} - -#define NET_DIM_TX_CQE_PROFILES { \ - {5, 128}, \ - {8, 64}, \ - {16, 32}, \ - {32, 32}, \ - {64, 32} \ -} - -static const struct net_dim_cq_moder -rx_profile[NET_DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { - NET_DIM_RX_EQE_PROFILES, - NET_DIM_RX_CQE_PROFILES, -}; - -static const struct net_dim_cq_moder -tx_profile[NET_DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { - NET_DIM_TX_EQE_PROFILES, - NET_DIM_TX_CQE_PROFILES, -}; - -static inline struct net_dim_cq_moder -net_dim_get_rx_moderation(u8 cq_period_mode, int ix) -{ - struct net_dim_cq_moder cq_moder = rx_profile[cq_period_mode][ix]; - - cq_moder.cq_period_mode = cq_period_mode; - return cq_moder; -} - -static inline struct net_dim_cq_moder -net_dim_get_def_rx_moderation(u8 cq_period_mode) -{ - u8 profile_ix = cq_period_mode == NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE ? - NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE; - - return net_dim_get_rx_moderation(cq_period_mode, profile_ix); -} - -static inline struct net_dim_cq_moder -net_dim_get_tx_moderation(u8 cq_period_mode, int ix) -{ - struct net_dim_cq_moder cq_moder = tx_profile[cq_period_mode][ix]; - - cq_moder.cq_period_mode = cq_period_mode; - return cq_moder; -} - -static inline struct net_dim_cq_moder -net_dim_get_def_tx_moderation(u8 cq_period_mode) -{ - u8 profile_ix = cq_period_mode == NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE ? - NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE; - - return net_dim_get_tx_moderation(cq_period_mode, profile_ix); -} - -static inline bool net_dim_on_top(struct net_dim *dim) -{ - switch (dim->tune_state) { - case NET_DIM_PARKING_ON_TOP: - case NET_DIM_PARKING_TIRED: - return true; - case NET_DIM_GOING_RIGHT: - return (dim->steps_left > 1) && (dim->steps_right == 1); - default: /* NET_DIM_GOING_LEFT */ - return (dim->steps_right > 1) && (dim->steps_left == 1); - } -} - -static inline void net_dim_turn(struct net_dim *dim) -{ - switch (dim->tune_state) { - case NET_DIM_PARKING_ON_TOP: - case NET_DIM_PARKING_TIRED: - break; - case NET_DIM_GOING_RIGHT: - dim->tune_state = NET_DIM_GOING_LEFT; - dim->steps_left = 0; - break; - case NET_DIM_GOING_LEFT: - dim->tune_state = NET_DIM_GOING_RIGHT; - dim->steps_right = 0; - break; - } -} - -static inline int net_dim_step(struct net_dim *dim) -{ - if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2)) - return NET_DIM_TOO_TIRED; - - switch (dim->tune_state) { - case NET_DIM_PARKING_ON_TOP: - case NET_DIM_PARKING_TIRED: - break; - case NET_DIM_GOING_RIGHT: - if (dim->profile_ix == (NET_DIM_PARAMS_NUM_PROFILES - 1)) - return NET_DIM_ON_EDGE; - dim->profile_ix++; - dim->steps_right++; - break; - case NET_DIM_GOING_LEFT: - if (dim->profile_ix == 0) - return NET_DIM_ON_EDGE; - dim->profile_ix--; - dim->steps_left++; - break; - } - - dim->tired++; - return NET_DIM_STEPPED; -} - -static inline void net_dim_park_on_top(struct net_dim *dim) -{ - dim->steps_right = 0; - dim->steps_left = 0; - dim->tired = 0; - dim->tune_state = NET_DIM_PARKING_ON_TOP; -} - -static inline void net_dim_park_tired(struct net_dim *dim) -{ - dim->steps_right = 0; - dim->steps_left = 0; - dim->tune_state = NET_DIM_PARKING_TIRED; -} - -static inline void net_dim_exit_parking(struct net_dim *dim) -{ - dim->tune_state = dim->profile_ix ? NET_DIM_GOING_LEFT : - NET_DIM_GOING_RIGHT; - net_dim_step(dim); -} - -#define IS_SIGNIFICANT_DIFF(val, ref) \ - (((100UL * abs((val) - (ref))) / (ref)) > 10) /* more than 10% difference */ - -static inline int net_dim_stats_compare(struct net_dim_stats *curr, - struct net_dim_stats *prev) -{ - if (!prev->bpms) - return curr->bpms ? NET_DIM_STATS_BETTER : - NET_DIM_STATS_SAME; - - if (IS_SIGNIFICANT_DIFF(curr->bpms, prev->bpms)) - return (curr->bpms > prev->bpms) ? NET_DIM_STATS_BETTER : - NET_DIM_STATS_WORSE; - - if (!prev->ppms) - return curr->ppms ? NET_DIM_STATS_BETTER : - NET_DIM_STATS_SAME; - - if (IS_SIGNIFICANT_DIFF(curr->ppms, prev->ppms)) - return (curr->ppms > prev->ppms) ? NET_DIM_STATS_BETTER : - NET_DIM_STATS_WORSE; - - if (!prev->epms) - return NET_DIM_STATS_SAME; - - if (IS_SIGNIFICANT_DIFF(curr->epms, prev->epms)) - return (curr->epms < prev->epms) ? NET_DIM_STATS_BETTER : - NET_DIM_STATS_WORSE; - - return NET_DIM_STATS_SAME; -} - -static inline bool net_dim_decision(struct net_dim_stats *curr_stats, - struct net_dim *dim) -{ - int prev_state = dim->tune_state; - int prev_ix = dim->profile_ix; - int stats_res; - int step_res; - - switch (dim->tune_state) { - case NET_DIM_PARKING_ON_TOP: - stats_res = net_dim_stats_compare(curr_stats, &dim->prev_stats); - if (stats_res != NET_DIM_STATS_SAME) - net_dim_exit_parking(dim); - break; - - case NET_DIM_PARKING_TIRED: - dim->tired--; - if (!dim->tired) - net_dim_exit_parking(dim); - break; - - case NET_DIM_GOING_RIGHT: - case NET_DIM_GOING_LEFT: - stats_res = net_dim_stats_compare(curr_stats, &dim->prev_stats); - if (stats_res != NET_DIM_STATS_BETTER) - net_dim_turn(dim); - - if (net_dim_on_top(dim)) { - net_dim_park_on_top(dim); - break; - } - - step_res = net_dim_step(dim); - switch (step_res) { - case NET_DIM_ON_EDGE: - net_dim_park_on_top(dim); - break; - case NET_DIM_TOO_TIRED: - net_dim_park_tired(dim); - break; - } - - break; - } - - if ((prev_state != NET_DIM_PARKING_ON_TOP) || - (dim->tune_state != NET_DIM_PARKING_ON_TOP)) - dim->prev_stats = *curr_stats; - - return dim->profile_ix != prev_ix; -} - -static inline void net_dim_sample(u16 event_ctr, - u64 packets, - u64 bytes, - struct net_dim_sample *s) -{ - s->time = ktime_get(); - s->pkt_ctr = packets; - s->byte_ctr = bytes; - s->event_ctr = event_ctr; -} - -#define NET_DIM_NEVENTS 64 -#define BIT_GAP(bits, end, start) ((((end) - (start)) + BIT_ULL(bits)) & (BIT_ULL(bits) - 1)) - -static inline void net_dim_calc_stats(struct net_dim_sample *start, - struct net_dim_sample *end, - struct net_dim_stats *curr_stats) -{ - /* u32 holds up to 71 minutes, should be enough */ - u32 delta_us = ktime_us_delta(end->time, start->time); - u32 npkts = BIT_GAP(BITS_PER_TYPE(u32), end->pkt_ctr, start->pkt_ctr); - u32 nbytes = BIT_GAP(BITS_PER_TYPE(u32), end->byte_ctr, - start->byte_ctr); - - if (!delta_us) - return; - - curr_stats->ppms = DIV_ROUND_UP(npkts * USEC_PER_MSEC, delta_us); - curr_stats->bpms = DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us); - curr_stats->epms = DIV_ROUND_UP(NET_DIM_NEVENTS * USEC_PER_MSEC, - delta_us); -} - -static inline void net_dim(struct net_dim *dim, - struct net_dim_sample end_sample) -{ - struct net_dim_stats curr_stats; - u16 nevents; - - switch (dim->state) { - case NET_DIM_MEASURE_IN_PROGRESS: - nevents = BIT_GAP(BITS_PER_TYPE(u16), - end_sample.event_ctr, - dim->start_sample.event_ctr); - if (nevents < NET_DIM_NEVENTS) - break; - net_dim_calc_stats(&dim->start_sample, &end_sample, - &curr_stats); - if (net_dim_decision(&curr_stats, dim)) { - dim->state = NET_DIM_APPLY_NEW_PROFILE; - schedule_work(&dim->work); - break; - } - /* fall through */ - case NET_DIM_START_MEASURE: - net_dim_sample(end_sample.event_ctr, end_sample.pkt_ctr, end_sample.byte_ctr, - &dim->start_sample); - dim->state = NET_DIM_MEASURE_IN_PROGRESS; - break; - case NET_DIM_APPLY_NEW_PROFILE: - break; - } -} - -#endif /* NET_DIM_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index eeacebd7debb..88292953aa6f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4870,4 +4870,6 @@ do { \ #define PTYPE_HASH_SIZE (16) #define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1) +extern struct net_device *blackhole_netdev; + #endif /* _LINUX_NETDEVICE_H */ diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 996bc247ef6e..049aeb40fa35 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -336,11 +336,6 @@ int compat_nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); #endif -/* Call this before modifying an existing packet: ensures it is - modifiable and linear to the point you care about (writable_len). - Returns true or false. */ -int skb_make_writable(struct sk_buff *skb, unsigned int writable_len); - struct flowi; struct nf_queue_entry; diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index f5e03809cdb2..12ad9b1853b4 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -2,7 +2,7 @@ /* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu> * Patrick Schaaf <bof@bof.de> * Martin Josefsson <gandalf@wlug.westbo.se> - * Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ #ifndef _IP_SET_H #define _IP_SET_H diff --git a/include/linux/netfilter/ipset/ip_set_counter.h b/include/linux/netfilter/ipset/ip_set_counter.h index 5477492c8374..3400958c07be 100644 --- a/include/linux/netfilter/ipset/ip_set_counter.h +++ b/include/linux/netfilter/ipset/ip_set_counter.h @@ -2,8 +2,7 @@ #ifndef _IP_SET_COUNTER_H #define _IP_SET_COUNTER_H -/* Copyright (C) 2015 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> - */ +/* Copyright (C) 2015 Jozsef Kadlecsik <kadlec@netfilter.org> */ #ifdef __KERNEL__ diff --git a/include/linux/netfilter/ipset/ip_set_skbinfo.h b/include/linux/netfilter/ipset/ip_set_skbinfo.h index aae081e085c6..3a2df02dbd55 100644 --- a/include/linux/netfilter/ipset/ip_set_skbinfo.h +++ b/include/linux/netfilter/ipset/ip_set_skbinfo.h @@ -2,8 +2,7 @@ #ifndef _IP_SET_SKBINFO_H #define _IP_SET_SKBINFO_H -/* Copyright (C) 2015 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> - */ +/* Copyright (C) 2015 Jozsef Kadlecsik <kadlec@netfilter.org> */ #ifdef __KERNEL__ diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h index 88926b4c75f0..2be60e379ecf 100644 --- a/include/linux/netfilter/ipset/ip_set_timeout.h +++ b/include/linux/netfilter/ipset/ip_set_timeout.h @@ -2,8 +2,7 @@ #ifndef _IP_SET_TIMEOUT_H #define _IP_SET_TIMEOUT_H -/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> - */ +/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ #ifdef __KERNEL__ diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 12113e502656..7beb681e1ce5 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -8,6 +8,7 @@ #define __LINUX_IP6_NETFILTER_H #include <uapi/linux/netfilter_ipv6.h> +#include <net/tcp.h> /* Extra routing may needed on local out, as the QUEUE target never returns * control to the table. @@ -19,6 +20,7 @@ struct ip6_rt_info { }; struct nf_queue_entry; +struct nf_ct_bridge_frag_data; /* * Hook functions for ipv6 to allow xt_* modules to be built-in even @@ -34,11 +36,24 @@ struct nf_ipv6_ops { struct in6_addr *saddr); int (*route)(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict); + u32 (*cookie_init_sequence)(const struct ipv6hdr *iph, + const struct tcphdr *th, u16 *mssp); + int (*cookie_v6_check)(const struct ipv6hdr *iph, + const struct tcphdr *th, __u32 cookie); #endif void (*route_input)(struct sk_buff *skb); int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry); +#if IS_MODULE(CONFIG_IPV6) + int (*br_defrag)(struct net *net, struct sk_buff *skb, u32 user); + int (*br_fragment)(struct net *net, struct sock *sk, + struct sk_buff *skb, + struct nf_ct_bridge_frag_data *data, + int (*output)(struct net *, struct sock *sk, + const struct nf_ct_bridge_frag_data *data, + struct sk_buff *)); +#endif }; #ifdef CONFIG_NETFILTER @@ -60,8 +75,10 @@ static inline int nf_ipv6_chk_addr(struct net *net, const struct in6_addr *addr, return 1; return v6_ops->chk_addr(net, addr, dev, strict); -#else +#elif IS_BUILTIN(CONFIG_IPV6) return ipv6_chk_addr(net, addr, dev, strict); +#else + return 1; #endif } @@ -86,6 +103,52 @@ static inline int nf_ip6_route(struct net *net, struct dst_entry **dst, #endif } +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> + +static inline int nf_ipv6_br_defrag(struct net *net, struct sk_buff *skb, + u32 user) +{ +#if IS_MODULE(CONFIG_IPV6) + const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); + + if (!v6_ops) + return 1; + + return v6_ops->br_defrag(net, skb, user); +#elif IS_BUILTIN(CONFIG_IPV6) + return nf_ct_frag6_gather(net, skb, user); +#else + return 1; +#endif +} + +int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + struct nf_ct_bridge_frag_data *data, + int (*output)(struct net *, struct sock *sk, + const struct nf_ct_bridge_frag_data *data, + struct sk_buff *)); + +static inline int nf_br_ip6_fragment(struct net *net, struct sock *sk, + struct sk_buff *skb, + struct nf_ct_bridge_frag_data *data, + int (*output)(struct net *, struct sock *sk, + const struct nf_ct_bridge_frag_data *data, + struct sk_buff *)) +{ +#if IS_MODULE(CONFIG_IPV6) + const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); + + if (!v6_ops) + return 1; + + return v6_ops->br_fragment(net, sk, skb, data, output); +#elif IS_BUILTIN(CONFIG_IPV6) + return br_ip6_fragment(net, sk, skb, data, output); +#else + return 1; +#endif +} + int ip6_route_me_harder(struct net *net, struct sk_buff *skb); static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb) @@ -97,9 +160,44 @@ static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb) return -EHOSTUNREACH; return v6_ops->route_me_harder(net, skb); -#else +#elif IS_BUILTIN(CONFIG_IPV6) return ip6_route_me_harder(net, skb); +#else + return -EHOSTUNREACH; +#endif +} + +static inline u32 nf_ipv6_cookie_init_sequence(const struct ipv6hdr *iph, + const struct tcphdr *th, + u16 *mssp) +{ +#if IS_ENABLED(CONFIG_SYN_COOKIES) +#if IS_MODULE(CONFIG_IPV6) + const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); + + if (v6_ops) + return v6_ops->cookie_init_sequence(iph, th, mssp); +#elif IS_BUILTIN(CONFIG_IPV6) + return __cookie_v6_init_sequence(iph, th, mssp); +#endif +#endif + return 0; +} + +static inline int nf_cookie_v6_check(const struct ipv6hdr *iph, + const struct tcphdr *th, __u32 cookie) +{ +#if IS_ENABLED(CONFIG_SYN_COOKIES) +#if IS_MODULE(CONFIG_IPV6) + const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); + + if (v6_ops) + return v6_ops->cookie_v6_check(iph, th, cookie); +#elif IS_BUILTIN(CONFIG_IPV6) + return __cookie_v6_check(iph, th, cookie); +#endif #endif + return 0; } __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 593d1b9c33a8..205fa7b1f07a 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -192,7 +192,14 @@ struct netlink_callback { bool strict_check; u16 answer_flags; unsigned int prev_seq, seq; - long args[6]; + union { + u8 ctx[48]; + + /* args is deprecated. Cast a struct over ctx instead + * for proper type safety. + */ + long args[6]; + }; }; struct netlink_notify { diff --git a/include/linux/pci-aspm.h b/include/linux/pci-aspm.h index df28af5cef21..67064145d76e 100644 --- a/include/linux/pci-aspm.h +++ b/include/linux/pci-aspm.h @@ -24,11 +24,12 @@ #define PCIE_LINK_STATE_CLKPM 4 #ifdef CONFIG_PCIEASPM -void pci_disable_link_state(struct pci_dev *pdev, int state); -void pci_disable_link_state_locked(struct pci_dev *pdev, int state); +int pci_disable_link_state(struct pci_dev *pdev, int state); +int pci_disable_link_state_locked(struct pci_dev *pdev, int state); void pcie_no_aspm(void); #else -static inline void pci_disable_link_state(struct pci_dev *pdev, int state) { } +static inline int pci_disable_link_state(struct pci_dev *pdev, int state) +{ return 0; } static inline void pcie_no_aspm(void) { } #endif diff --git a/include/linux/phy.h b/include/linux/phy.h index 6424586fe2d6..1739c6dc470e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -98,6 +98,7 @@ typedef enum { PHY_INTERFACE_MODE_XAUI, /* 10GBASE-KR, XFI, SFI - single lane 10G Serdes */ PHY_INTERFACE_MODE_10GKR, + PHY_INTERFACE_MODE_USXGMII, PHY_INTERFACE_MODE_MAX, } phy_interface_t; @@ -173,6 +174,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "xaui"; case PHY_INTERFACE_MODE_10GKR: return "10gbase-kr"; + case PHY_INTERFACE_MODE_USXGMII: + return "usxgmii"; default: return "unknown"; } @@ -180,7 +183,6 @@ 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_MAX_ADDR 32 @@ -193,6 +195,8 @@ static inline const char *phy_modes(phy_interface_t interface) /* Or MII_ADDR_C45 into regnum for read/write on mii_bus to enable the 21 bit IEEE 802.3ae clause 45 addressing mode used by 10GIGE phy chips. */ #define MII_ADDR_C45 (1<<30) +#define MII_DEVADDR_C45_SHIFT 16 +#define MII_REGADDR_C45_MASK GENMASK(15, 0) struct device; struct phylink; @@ -290,12 +294,6 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); * - irq or timer will set RUNNING if link comes back * - phy_stop moves to HALTED * - * FORCING: PHY is being configured with forced settings - * - if link is up, move to RUNNING - * - If link is down, we drop to the next highest setting, and - * retry (FORCING) after a timeout - * - phy_stop moves to HALTED - * * RUNNING: PHY is currently up, running, and possibly sending * and/or receiving packets * - irq or timer will set NOLINK if link goes down @@ -312,7 +310,6 @@ enum phy_state { PHY_UP, PHY_RUNNING, PHY_NOLINK, - PHY_FORCING, }; /** @@ -340,8 +337,6 @@ struct phy_c45_device_ids { * loopback_enabled: Set true if this phy has been loopbacked successfully. * state: state of the PHY for management purposes * dev_flags: Device-specific flags used by the PHY driver. - * link_timeout: The number of timer firings to wait before the - * 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 * attached_dev: The attached enet driver's device instance ptr @@ -409,8 +404,6 @@ struct phy_device { /* Energy efficient ethernet modes which should be prohibited */ u32 eee_broken_modes; - int link_timeout; - #ifdef CONFIG_LED_TRIGGER_PHY struct phy_led_trigger *phy_led_triggers; unsigned int phy_num_led_triggers; @@ -529,6 +522,9 @@ struct phy_driver { */ int (*did_interrupt)(struct phy_device *phydev); + /* Override default interrupt handling */ + int (*handle_interrupt)(struct phy_device *phydev); + /* Clears up any memory if needed */ void (*remove)(struct phy_device *phydev); @@ -1129,6 +1125,7 @@ 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_queue_state_machine(struct phy_device *phydev, unsigned long jiffies); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); @@ -1139,6 +1136,7 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev, const struct ethtool_link_ksettings *cmd); int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); 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_remove_link_mode(struct phy_device *phydev, u32 link_mode); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 2d2e55dfea94..300ecdb6790a 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -54,6 +54,21 @@ struct phylink_link_state { unsigned int an_complete:1; }; +enum phylink_op_type { + PHYLINK_NETDEV = 0, + PHYLINK_DEV, +}; + +/** + * struct phylink_config - PHYLINK configuration structure + * @dev: a pointer to a struct device associated with the MAC + * @type: operation type of PHYLINK instance + */ +struct phylink_config { + struct device *dev; + enum phylink_op_type type; +}; + /** * struct phylink_mac_ops - MAC operations structure. * @validate: Validate and update the link configuration. @@ -66,16 +81,17 @@ struct phylink_link_state { * The individual methods are described more fully below. */ struct phylink_mac_ops { - void (*validate)(struct net_device *ndev, unsigned long *supported, + void (*validate)(struct phylink_config *config, + unsigned long *supported, struct phylink_link_state *state); - int (*mac_link_state)(struct net_device *ndev, + int (*mac_link_state)(struct phylink_config *config, struct phylink_link_state *state); - void (*mac_config)(struct net_device *ndev, unsigned int mode, + void (*mac_config)(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state); - void (*mac_an_restart)(struct net_device *ndev); - void (*mac_link_down)(struct net_device *ndev, unsigned int mode, + void (*mac_an_restart)(struct phylink_config *config); + void (*mac_link_down)(struct phylink_config *config, unsigned int mode, phy_interface_t interface); - void (*mac_link_up)(struct net_device *ndev, unsigned int mode, + void (*mac_link_up)(struct phylink_config *config, unsigned int mode, phy_interface_t interface, struct phy_device *phy); }; @@ -83,7 +99,7 @@ struct phylink_mac_ops { #if 0 /* For kernel-doc purposes only. */ /** * validate - Validate and update the link configuration - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. * @supported: ethtool bitmask for supported link modes. * @state: a pointer to a &struct phylink_link_state. * @@ -93,19 +109,26 @@ struct phylink_mac_ops { * Note that the PHY may be able to transform from one connection * technology to another, so, eg, don't clear 1000BaseX just * because the MAC is unable to BaseX mode. This is more about - * clearing unsupported speeds and duplex settings. + * clearing unsupported speeds and duplex settings. The port modes + * should not be cleared; phylink_set_port_modes() will help with this. * * If the @state->interface mode is %PHY_INTERFACE_MODE_1000BASEX * or %PHY_INTERFACE_MODE_2500BASEX, select the appropriate mode * based on @state->advertising and/or @state->speed and update - * @state->interface accordingly. + * @state->interface accordingly. See phylink_helper_basex_speed(). + * + * When @state->interface is %PHY_INTERFACE_MODE_NA, phylink expects the + * MAC driver to return all supported link modes. + * + * If the @state->interface mode is not supported, then the @supported + * mask must be cleared. */ -void validate(struct net_device *ndev, unsigned long *supported, +void validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); /** * mac_link_state() - Read the current link state from the hardware - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. * @state: a pointer to a &struct phylink_link_state. * * Read the current link state from the MAC, reporting the current @@ -114,12 +137,12 @@ void validate(struct net_device *ndev, unsigned long *supported, * negotiation completion state in @state->an_complete, and link * up state in @state->link. */ -int mac_link_state(struct net_device *ndev, +int mac_link_state(struct phylink_config *config, struct phylink_link_state *state); /** * mac_config() - configure the MAC for the selected mode and state - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND. * @state: a pointer to a &struct phylink_link_state. * @@ -168,18 +191,18 @@ int mac_link_state(struct net_device *ndev, * down. This "update" behaviour is critical to avoid bouncing the * link up status. */ -void mac_config(struct net_device *ndev, unsigned int mode, +void mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state); /** * mac_an_restart() - restart 802.3z BaseX autonegotiation - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. */ -void mac_an_restart(struct net_device *ndev); +void mac_an_restart(struct phylink_config *config); /** * mac_link_down() - take the link down - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. * @mode: link autonegotiation mode * @interface: link &typedef phy_interface_t mode * @@ -188,12 +211,12 @@ void mac_an_restart(struct net_device *ndev); * Energy Efficient Ethernet MAC configuration. Interface type * selection must be done in mac_config(). */ -void mac_link_down(struct net_device *ndev, unsigned int mode, +void mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface); /** * mac_link_up() - allow the link to come up - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. * @mode: link autonegotiation mode * @interface: link &typedef phy_interface_t mode * @phy: any attached phy @@ -204,13 +227,14 @@ void mac_link_down(struct net_device *ndev, unsigned int mode, * phy_init_eee() and perform appropriate MAC configuration for EEE. * Interface type selection must be done in mac_config(). */ -void mac_link_up(struct net_device *ndev, unsigned int mode, +void mac_link_up(struct phylink_config *config, unsigned int mode, phy_interface_t interface, struct phy_device *phy); #endif -struct phylink *phylink_create(struct net_device *, struct fwnode_handle *, - phy_interface_t iface, const struct phylink_mac_ops *ops); +struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, + phy_interface_t iface, + const struct phylink_mac_ops *ops); void phylink_destroy(struct phylink *); int phylink_connect_phy(struct phylink *, struct phy_device *); diff --git a/include/linux/platform_data/xilinx-ll-temac.h b/include/linux/platform_data/xilinx-ll-temac.h index 368530f98176..f4a68136afa6 100644 --- a/include/linux/platform_data/xilinx-ll-temac.h +++ b/include/linux/platform_data/xilinx-ll-temac.h @@ -4,6 +4,7 @@ #include <linux/if_ether.h> #include <linux/phy.h> +#include <linux/spinlock.h> struct ll_temac_platform_data { bool txcsum; /* Enable/disable TX checksum */ @@ -21,7 +22,7 @@ struct ll_temac_platform_data { * TEMAC IP block, the same mutex should be passed here, as * they share the same DCR bus bridge. */ - struct mutex *indirect_mutex; + spinlock_t *indirect_lock; /* DMA channel control setup */ u8 tx_irq_timeout; /* TX Interrupt Delay Time-out */ u8 tx_irq_count; /* TX Interrupt Coalescing Threshold Count */ diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 28eb9c792522..93cc4f1d444a 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -213,6 +213,14 @@ extern void ptp_clock_event(struct ptp_clock *ptp, extern int ptp_clock_index(struct ptp_clock *ptp); /** + * scaled_ppm_to_ppb() - convert scaled ppm to ppb + * + * @ppm: Parts per million, but with a 16 bit binary fractional field + */ + +extern s32 scaled_ppm_to_ppb(long ppm); + +/** * ptp_find_pin() - obtain the pin index of a given auxiliary function * * @ptp: The clock obtained from ptp_clock_register(). diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 48841e5dab90..eef02e64b422 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -907,7 +907,8 @@ struct qed_common_ops { u32 (*sb_release)(struct qed_dev *cdev, struct qed_sb_info *sb_info, - u16 sb_id); + u16 sb_id, + enum qed_sb_type type); void (*simd_handler_config)(struct qed_dev *cdev, void *token, @@ -1123,6 +1124,13 @@ struct qed_common_ops { */ int (*read_module_eeprom)(struct qed_dev *cdev, char *buf, u8 dev_addr, u32 offset, u32 len); + +/** + * @brief get_affin_hwfn_idx + * + * @param cdev + */ + u8 (*get_affin_hwfn_idx)(struct qed_dev *cdev); }; #define MASK_FIELD(_name, _value) \ diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index d15f8e4815e3..898f595ea3d6 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -670,6 +670,8 @@ struct qed_rdma_ops { int (*ll2_set_mac_filter)(struct qed_dev *cdev, u8 *old_mac_address, u8 *new_mac_address); + int (*iwarp_set_engine_affin)(struct qed_dev *cdev, bool b_reset); + int (*iwarp_connect)(void *rdma_cxt, struct qed_iwarp_connect_in *iparams, struct qed_iwarp_connect_out *oparams); diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 9f8bc06d4136..beb9a9da1699 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -352,37 +352,38 @@ static inline void rht_unlock(struct bucket_table *tbl, static inline struct rhash_head __rcu *__rht_ptr( struct rhash_lock_head *const *bkt) { - return (struct rhash_head __rcu *)((unsigned long)*bkt & ~BIT(0)); + return (struct rhash_head __rcu *) + ((unsigned long)*bkt & ~BIT(0) ?: + (unsigned long)RHT_NULLS_MARKER(bkt)); } /* * Where 'bkt' is a bucket and might be locked: - * rht_ptr() dereferences that pointer and clears the lock bit. + * rht_ptr_rcu() dereferences that pointer and clears the lock bit. + * rht_ptr() dereferences in a context where the bucket is locked. * rht_ptr_exclusive() dereferences in a context where exclusive * access is guaranteed, such as when destroying the table. */ +static inline struct rhash_head *rht_ptr_rcu( + struct rhash_lock_head *const *bkt) +{ + struct rhash_head __rcu *p = __rht_ptr(bkt); + + return rcu_dereference(p); +} + static inline struct rhash_head *rht_ptr( struct rhash_lock_head *const *bkt, struct bucket_table *tbl, unsigned int hash) { - struct rhash_head __rcu *p = __rht_ptr(bkt); - - if (!p) - return RHT_NULLS_MARKER(bkt); - - return rht_dereference_bucket_rcu(p, tbl, hash); + return rht_dereference_bucket(__rht_ptr(bkt), tbl, hash); } static inline struct rhash_head *rht_ptr_exclusive( struct rhash_lock_head *const *bkt) { - struct rhash_head __rcu *p = __rht_ptr(bkt); - - if (!p) - return RHT_NULLS_MARKER(bkt); - - return rcu_dereference_protected(p, 1); + return rcu_dereference_protected(__rht_ptr(bkt), 1); } static inline void rht_assign_locked(struct rhash_lock_head **bkt, @@ -509,7 +510,7 @@ static inline void rht_assign_unlock(struct bucket_table *tbl, */ #define rht_for_each_rcu(pos, tbl, hash) \ for (({barrier(); }), \ - pos = rht_ptr(rht_bucket(tbl, hash), tbl, hash); \ + pos = rht_ptr_rcu(rht_bucket(tbl, hash)); \ !rht_is_a_nulls(pos); \ pos = rcu_dereference_raw(pos->next)) @@ -546,8 +547,7 @@ static inline void rht_assign_unlock(struct bucket_table *tbl, */ #define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member) \ rht_for_each_entry_rcu_from(tpos, pos, \ - rht_ptr(rht_bucket(tbl, hash), \ - tbl, hash), \ + rht_ptr_rcu(rht_bucket(tbl, hash)), \ tbl, hash, member) /** @@ -603,7 +603,7 @@ restart: hash = rht_key_hashfn(ht, tbl, key, params); bkt = rht_bucket(tbl, hash); do { - rht_for_each_rcu_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) { + rht_for_each_rcu_from(he, rht_ptr_rcu(bkt), tbl, hash) { if (params.obj_cmpfn ? params.obj_cmpfn(&arg, rht_obj(ht, he)) : rhashtable_compare(&arg, rht_obj(ht, he))) diff --git a/include/linux/sfp.h b/include/linux/sfp.h index d9d9de3fcf8e..1c35428e98bc 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -464,11 +464,14 @@ enum { struct fwnode_handle; struct ethtool_eeprom; struct ethtool_modinfo; -struct net_device; struct sfp_bus; /** * struct sfp_upstream_ops - upstream operations structure + * @attach: called when the sfp socket driver is bound to the upstream + * (mandatory). + * @detach: called when the sfp socket driver is unbound from the upstream + * (mandatory). * @module_insert: called after a module has been detected to determine * whether the module is supported for the upstream device. * @module_remove: called after the module has been removed. @@ -481,6 +484,8 @@ struct sfp_bus; * been removed. */ struct sfp_upstream_ops { + void (*attach)(void *priv, struct sfp_bus *bus); + void (*detach)(void *priv, struct sfp_bus *bus); int (*module_insert)(void *priv, const struct sfp_eeprom_id *id); void (*module_remove)(void *priv); void (*link_down)(void *priv); @@ -504,7 +509,7 @@ int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee, void sfp_upstream_start(struct sfp_bus *bus); void sfp_upstream_stop(struct sfp_bus *bus); struct sfp_bus *sfp_register_upstream(struct fwnode_handle *fwnode, - struct net_device *ndev, void *upstream, + void *upstream, const struct sfp_upstream_ops *ops); void sfp_unregister_upstream(struct sfp_bus *bus); #else @@ -549,8 +554,7 @@ static inline void sfp_upstream_stop(struct sfp_bus *bus) } static inline struct sfp_bus *sfp_register_upstream( - struct fwnode_handle *fwnode, - struct net_device *ndev, void *upstream, + struct fwnode_handle *fwnode, void *upstream, const struct sfp_upstream_ops *ops) { return (struct sfp_bus *)-1; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 056f557d5194..d8af86d995d6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1024,6 +1024,7 @@ static inline bool skb_unref(struct sk_buff *skb) void skb_release_head_state(struct sk_buff *skb); void kfree_skb(struct sk_buff *skb); void kfree_skb_list(struct sk_buff *segs); +void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); void consume_skb(struct sk_buff *skb); void __consume_stateless_skb(struct sk_buff *skb); @@ -1059,6 +1060,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, int max_page_order, int *errcode, gfp_t gfp_mask); +struct sk_buff *alloc_skb_for_msg(struct sk_buff *first); /* Layout of fast clones : [skb1][skb2][fclone_ref] */ struct sk_buff_fclones { @@ -1319,6 +1321,20 @@ skb_flow_dissect_flow_keys_basic(const struct net *net, data, proto, nhoff, hlen, flags); } +void skb_flow_dissect_meta(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container); + +/* Gets a skb connection tracking info, ctinfo map should be a + * a map of mapsize to translate enum ip_conntrack_info states + * to user states. + */ +void +skb_flow_dissect_ct(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, + u16 *ctinfo_map, + size_t mapsize); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, @@ -3441,6 +3457,10 @@ int skb_ensure_writable(struct sk_buff *skb, int write_len); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); +int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto); +int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto); +int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); +int skb_mpls_dec_ttl(struct sk_buff *skb); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp); @@ -3914,18 +3934,16 @@ static inline bool __skb_checksum_convert_check(struct sk_buff *skb) return (skb->ip_summed == CHECKSUM_NONE && skb->csum_valid); } -static inline void __skb_checksum_convert(struct sk_buff *skb, - __sum16 check, __wsum pseudo) +static inline void __skb_checksum_convert(struct sk_buff *skb, __wsum pseudo) { skb->csum = ~pseudo; skb->ip_summed = CHECKSUM_COMPLETE; } -#define skb_checksum_try_convert(skb, proto, check, compute_pseudo) \ +#define skb_checksum_try_convert(skb, proto, compute_pseudo) \ do { \ if (__skb_checksum_convert_check(skb)) \ - __skb_checksum_convert(skb, check, \ - compute_pseudo(skb, proto)); \ + __skb_checksum_convert(skb, compute_pseudo(skb, proto)); \ } while (0) static inline void skb_remcsum_adjust_partial(struct sk_buff *skb, void *ptr, diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 1a0bb622cf10..7d06241582dd 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -78,14 +78,9 @@ /* Platfrom data for platform device structure's platform_data field */ struct stmmac_mdio_bus_data { - int (*phy_reset)(void *priv); unsigned int phy_mask; int *irqs; int probed_phy_irq; -#ifdef CONFIG_OF - int reset_gpio, active_low; - u32 delays[3]; -#endif }; struct stmmac_dma_cfg { @@ -137,6 +132,7 @@ struct plat_stmmacenet_data { int interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; + struct device_node *phylink_node; struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; int clk_csr; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 9a478a0cd3a2..f3a85a7fb4b1 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -58,12 +58,7 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb) /* TCP Fast Open Cookie as stored in memory */ struct tcp_fastopen_cookie { - union { - u8 val[TCP_FASTOPEN_COOKIE_MAX]; -#if IS_ENABLED(CONFIG_IPV6) - struct in6_addr addr; -#endif - }; + __le64 val[DIV_ROUND_UP(TCP_FASTOPEN_COOKIE_MAX, sizeof(u64))]; s8 len; bool exp; /* In RFC6994 experimental option format */ }; @@ -245,6 +240,7 @@ struct tcp_sock { syn_smc:1; /* SYN includes SMC */ u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ + u32 tcp_tx_delay; /* delay (in usec) added to TX packets */ u64 tcp_wstamp_ns; /* departure time for next sent data packet */ u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ @@ -436,6 +432,7 @@ struct tcp_timewait_sock { u32 tw_last_oow_ack_time; int tw_ts_recent_stamp; + u32 tw_tx_delay; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *tw_md5_key; #endif diff --git a/include/linux/wanrouter.h b/include/linux/wanrouter.h deleted file mode 100644 index f6358558f9f5..000000000000 --- a/include/linux/wanrouter.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * wanrouter.h Legacy declarations kept around until X25 is removed - */ - -#ifndef _ROUTER_H -#define _ROUTER_H - -#include <uapi/linux/wanrouter.h> - -#endif /* _ROUTER_H */ diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 9a5330eed794..5bc1e30dedde 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1143,6 +1143,26 @@ struct hci_cp_write_sc_support { __u8 support; } __packed; +#define HCI_OP_READ_AUTH_PAYLOAD_TO 0x0c7b +struct hci_cp_read_auth_payload_to { + __le16 handle; +} __packed; +struct hci_rp_read_auth_payload_to { + __u8 status; + __le16 handle; + __le16 timeout; +} __packed; + +#define HCI_OP_WRITE_AUTH_PAYLOAD_TO 0x0c7c +struct hci_cp_write_auth_payload_to { + __le16 handle; + __le16 timeout; +} __packed; +struct hci_rp_write_auth_payload_to { + __u8 status; + __le16 handle; +} __packed; + #define HCI_OP_READ_LOCAL_OOB_EXT_DATA 0x0c7d struct hci_rp_read_local_oob_ext_data { __u8 status; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 05b1b96f4d9e..ded574b32c20 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -199,6 +199,8 @@ struct adv_info { /* Default min/max age of connection information (1s/3s) */ #define DEFAULT_CONN_INFO_MIN_AGE 1000 #define DEFAULT_CONN_INFO_MAX_AGE 3000 +/* Default authenticated payload timeout 30s */ +#define DEFAULT_AUTH_PAYLOAD_TIMEOUT 0x0bb8 struct amp_assoc { __u16 len; @@ -275,6 +277,7 @@ struct hci_dev { __u16 discov_interleaved_timeout; __u16 conn_info_min_age; __u16 conn_info_max_age; + __u16 auth_payload_timeout; __u8 ssp_debug_mode; __u8 hw_error_code; __u32 clock; @@ -481,6 +484,7 @@ struct hci_conn { __u16 disc_timeout; __u16 conn_timeout; __u16 setting; + __u16 auth_payload_timeout; __u16 le_conn_min_interval; __u16 le_conn_max_interval; __u16 le_conn_interval; diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 2a05cc349018..9d382f2f0bc5 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -63,6 +63,7 @@ enum { BOND_OPT_AD_ACTOR_SYSTEM, BOND_OPT_AD_USER_PORT_KEY, BOND_OPT_NUM_PEER_NOTIF_ALIAS, + BOND_OPT_PEER_NOTIF_DELAY, BOND_OPT_LAST }; diff --git a/include/net/bonding.h b/include/net/bonding.h index b46d68acf701..f7fe45689142 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -38,6 +38,15 @@ #define __long_aligned __attribute__((aligned((sizeof(long))))) #endif +#define slave_info(bond_dev, slave_dev, fmt, ...) \ + netdev_info(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) +#define slave_warn(bond_dev, slave_dev, fmt, ...) \ + netdev_warn(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) +#define slave_dbg(bond_dev, slave_dev, fmt, ...) \ + netdev_dbg(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) +#define slave_err(bond_dev, slave_dev, fmt, ...) \ + netdev_err(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) + #define BOND_MODE(bond) ((bond)->params.mode) /* slave list primitives */ @@ -114,6 +123,7 @@ struct bond_params { int fail_over_mac; int updelay; int downdelay; + int peer_notif_delay; int lacp_fast; unsigned int min_links; int ad_select; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1fce25b1d87f..88c27153a4bc 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -379,16 +379,18 @@ ieee80211_get_sband_iftype_data(const struct ieee80211_supported_band *sband, } /** - * ieee80211_get_he_sta_cap - return HE capabilities for an sband's STA - * @sband: the sband to search for the STA on + * ieee80211_get_he_iftype_cap - return HE capabilities for an sband's iftype + * @sband: the sband to search for the iftype on + * @iftype: enum nl80211_iftype * * Return: pointer to the struct ieee80211_sta_he_cap, or NULL is none found */ static inline const struct ieee80211_sta_he_cap * -ieee80211_get_he_sta_cap(const struct ieee80211_supported_band *sband) +ieee80211_get_he_iftype_cap(const struct ieee80211_supported_band *sband, + u8 iftype) { const struct ieee80211_sband_iftype_data *data = - ieee80211_get_sband_iftype_data(sband, NL80211_IFTYPE_STATION); + ieee80211_get_sband_iftype_data(sband, iftype); if (data && data->he_cap.has_he) return &data->he_cap; @@ -397,6 +399,18 @@ ieee80211_get_he_sta_cap(const struct ieee80211_supported_band *sband) } /** + * ieee80211_get_he_sta_cap - return HE capabilities for an sband's STA + * @sband: the sband to search for the STA on + * + * Return: pointer to the struct ieee80211_sta_he_cap, or NULL is none found + */ +static inline const struct ieee80211_sta_he_cap * +ieee80211_get_he_sta_cap(const struct ieee80211_supported_band *sband) +{ + return ieee80211_get_he_iftype_cap(sband, NL80211_IFTYPE_STATION); +} + +/** * wiphy_read_of_freq_limits - read frequency limits from device tree * * @wiphy: the wireless device to get extra limits for @@ -739,6 +753,9 @@ struct survey_info { * CFG80211_MAX_WEP_KEYS WEP keys * @wep_tx_key: key index (0..3) of the default TX static WEP key * @psk: PSK (for devices supporting 4-way-handshake offload) + * @sae_pwd: password for SAE authentication (for devices supporting SAE + * offload) + * @sae_pwd_len: length of SAE password (for devices supporting SAE offload) */ struct cfg80211_crypto_settings { u32 wpa_versions; @@ -754,6 +771,8 @@ struct cfg80211_crypto_settings { struct key_params *wep_keys; int wep_tx_key; const u8 *psk; + const u8 *sae_pwd; + u8 sae_pwd_len; }; /** @@ -875,6 +894,7 @@ enum cfg80211_ap_settings_flags { * @he_cap: HE capabilities (or %NULL if HE isn't enabled) * @ht_required: stations must support HT * @vht_required: stations must support VHT + * @twt_responder: Enable Target Wait Time * @flags: flags, as defined in enum cfg80211_ap_settings_flags */ struct cfg80211_ap_settings { @@ -901,6 +921,7 @@ struct cfg80211_ap_settings { const struct ieee80211_vht_cap *vht_cap; const struct ieee80211_he_cap_elem *he_cap; bool ht_required, vht_required; + bool twt_responder; u32 flags; }; @@ -4149,6 +4170,8 @@ struct sta_opmode_info { u8 rx_nss; }; +#define VENDOR_CMD_RAW_DATA ((const struct nla_policy *)ERR_PTR(-ENODATA)) + /** * struct wiphy_vendor_command - vendor command definition * @info: vendor command identifying information, as used in nl80211 @@ -4159,6 +4182,10 @@ struct sta_opmode_info { * @dumpit: dump callback, for transferring bigger/multiple items. The * @storage points to cb->args[5], ie. is preserved over the multiple * dumpit calls. + * @policy: policy pointer for attributes within %NL80211_ATTR_VENDOR_DATA. + * Set this to %VENDOR_CMD_RAW_DATA if no policy can be given and the + * attribute is just raw data (e.g. a firmware command). + * @maxattr: highest attribute number in policy * It's recommended to not have the same sub command with both @doit and * @dumpit, so that userspace can assume certain ones are get and others * are used with dump requests. @@ -4171,6 +4198,8 @@ struct wiphy_vendor_command { int (*dumpit)(struct wiphy *wiphy, struct wireless_dev *wdev, struct sk_buff *skb, const void *data, int data_len, unsigned long *storage); + const struct nla_policy *policy; + unsigned int maxattr; }; /** @@ -5719,6 +5748,26 @@ void cfg80211_put_bss(struct wiphy *wiphy, struct cfg80211_bss *bss); */ void cfg80211_unlink_bss(struct wiphy *wiphy, struct cfg80211_bss *bss); +/** + * cfg80211_bss_iter - iterate all BSS entries + * + * This function iterates over the BSS entries associated with the given wiphy + * and calls the callback for the iterated BSS. The iterator function is not + * allowed to call functions that might modify the internal state of the BSS DB. + * + * @wiphy: the wiphy + * @chandef: if given, the iterator function will be called only if the channel + * of the currently iterated BSS is a subset of the given channel. + * @iter: the iterator function to call + * @iter_data: an argument to the iterator function + */ +void cfg80211_bss_iter(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef, + void (*iter)(struct wiphy *wiphy, + struct cfg80211_bss *bss, + void *data), + void *iter_data); + static inline enum nl80211_bss_scan_width cfg80211_chandef_to_scan_width(const struct cfg80211_chan_def *chandef) { @@ -6229,8 +6278,11 @@ struct cfg80211_fils_resp_params { * case. * @bssid: The BSSID of the AP (may be %NULL) * @bss: Entry of bss to which STA got connected to, can be obtained through - * cfg80211_get_bss() (may be %NULL). Only one parameter among @bssid and - * @bss needs to be specified. + * cfg80211_get_bss() (may be %NULL). But it is recommended to store the + * bss from the connect_request and hold a reference to it and return + * through this param to avoid a warning if the bss is expired during the + * connection, esp. for those drivers implementing connect op. + * Only one parameter among @bssid and @bss needs to be specified. * @req_ie: Association request IEs (may be %NULL) * @req_ie_len: Association request IEs length * @resp_ie: Association response IEs (may be %NULL) @@ -6278,8 +6330,12 @@ void cfg80211_connect_done(struct net_device *dev, * * @dev: network device * @bssid: the BSSID of the AP - * @bss: entry of bss to which STA got connected to, can be obtained - * through cfg80211_get_bss (may be %NULL) + * @bss: Entry of bss to which STA got connected to, can be obtained through + * cfg80211_get_bss() (may be %NULL). But it is recommended to store the + * bss from the connect_request and hold a reference to it and return + * through this param to avoid a warning if the bss is expired during the + * connection, esp. for those drivers implementing connect op. + * Only one parameter among @bssid and @bss needs to be specified. * @req_ie: association request IEs (maybe be %NULL) * @req_ie_len: association request IEs length * @resp_ie: association response IEs (may be %NULL) @@ -6490,6 +6546,16 @@ void cfg80211_remain_on_channel_expired(struct wireless_dev *wdev, u64 cookie, gfp_t gfp); /** + * cfg80211_tx_mgmt_expired - tx_mgmt duration expired + * @wdev: wireless device + * @cookie: the requested cookie + * @chan: The current channel (from tx_mgmt request) + * @gfp: allocation flags + */ +void cfg80211_tx_mgmt_expired(struct wireless_dev *wdev, u64 cookie, + struct ieee80211_channel *chan, gfp_t gfp); + +/** * cfg80211_sinfo_alloc_tid_stats - allocate per-tid statistics. * * @sinfo: the station information diff --git a/include/net/devlink.h b/include/net/devlink.h index c9fbeb5b701f..bc36f942a7d5 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -13,6 +13,7 @@ #include <linux/list.h> #include <linux/netdevice.h> #include <linux/spinlock.h> +#include <linux/workqueue.h> #include <net/net_namespace.h> #include <uapi/linux/devlink.h> @@ -37,14 +38,34 @@ struct devlink { char priv[0] __aligned(NETDEV_ALIGN); }; +struct devlink_port_phys_attrs { + u32 port_number; /* Same value as "split group". + * A physical port which is visible to the user + * for a given port flavour. + */ + u32 split_subport_number; +}; + +struct devlink_port_pci_pf_attrs { + u16 pf; /* Associated PCI PF for this port. */ +}; + +struct devlink_port_pci_vf_attrs { + u16 pf; /* Associated PCI PF for this port. */ + u16 vf; /* Associated PCI VF for of the PCI PF for this port. */ +}; + struct devlink_port_attrs { u8 set:1, split:1, switch_port:1; enum devlink_port_flavour flavour; - u32 port_number; /* same value as "split group" */ - u32 split_subport_number; struct netdev_phys_item_id switch_id; + union { + struct devlink_port_phys_attrs phys; + struct devlink_port_pci_pf_attrs pci_pf; + struct devlink_port_pci_vf_attrs pci_vf; + }; }; struct devlink_port { @@ -60,6 +81,7 @@ struct devlink_port { enum devlink_port_type desired_type; void *type_dev; struct devlink_port_attrs attrs; + struct delayed_work type_warn_dw; }; struct devlink_sb_pool_info { @@ -526,8 +548,10 @@ struct devlink_ops { int (*eswitch_inline_mode_get)(struct devlink *devlink, u8 *p_inline_mode); int (*eswitch_inline_mode_set)(struct devlink *devlink, u8 inline_mode, struct netlink_ext_ack *extack); - int (*eswitch_encap_mode_get)(struct devlink *devlink, u8 *p_encap_mode); - int (*eswitch_encap_mode_set)(struct devlink *devlink, u8 encap_mode, + int (*eswitch_encap_mode_get)(struct devlink *devlink, + enum devlink_eswitch_encap_mode *p_encap_mode); + int (*eswitch_encap_mode_set)(struct devlink *devlink, + enum devlink_eswitch_encap_mode encap_mode, struct netlink_ext_ack *extack); int (*info_get)(struct devlink *devlink, struct devlink_info_req *req, struct netlink_ext_ack *extack); @@ -586,6 +610,13 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port, u32 split_subport_number, const unsigned char *switch_id, unsigned char switch_id_len); +void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, + const unsigned char *switch_id, + unsigned char switch_id_len, u16 pf); +void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, + const unsigned char *switch_id, + unsigned char switch_id_len, + u16 pf, u16 vf); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, @@ -735,6 +766,14 @@ void devlink_health_reporter_state_update(struct devlink_health_reporter *reporter, enum devlink_health_reporter_state state); +void devlink_flash_update_begin_notify(struct devlink *devlink); +void devlink_flash_update_end_notify(struct devlink *devlink); +void devlink_flash_update_status_notify(struct devlink *devlink, + const char *status_msg, + const char *component, + unsigned long done, + unsigned long total); + #if IS_ENABLED(CONFIG_NET_DEVLINK) void devlink_compat_running_version(struct net_device *dev, diff --git a/include/net/dsa.h b/include/net/dsa.h index ba6dfff98196..1e8650fa8acc 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -18,6 +18,7 @@ #include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/platform_data/dsa.h> +#include <linux/phylink.h> #include <net/devlink.h> #include <net/switchdev.h> @@ -180,7 +181,7 @@ struct dsa_port { struct dsa_switch *ds; unsigned int index; const char *name; - const struct dsa_port *cpu_dp; + struct dsa_port *cpu_dp; const char *mac; struct device_node *dn; unsigned int ageing_time; @@ -189,6 +190,7 @@ struct dsa_port { struct net_device *bridge_dev; struct devlink_port devlink_port; struct phylink *pl; + struct phylink_config pl_config; struct work_struct xmit_work; struct sk_buff_head xmit_queue; @@ -355,6 +357,7 @@ struct dsa_switch_ops { int port); int (*setup)(struct dsa_switch *ds); + void (*teardown)(struct dsa_switch *ds); u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* diff --git a/include/net/dst.h b/include/net/dst.h index 12b31c602cb0..fe62fe2eb781 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -183,7 +183,7 @@ static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) } /* Kernel-internal feature bits that are unallocated in user space. */ -#define DST_FEATURE_ECN_CA (1 << 31) +#define DST_FEATURE_ECN_CA (1U << 31) #define DST_FEATURE_MASK (DST_FEATURE_ECN_CA) #define DST_FEATURE_ECN_MASK (DST_FEATURE_ECN_CA | RTAX_FEATURE_ECN) @@ -302,8 +302,9 @@ static inline bool dst_hold_safe(struct dst_entry *dst) * @skb: buffer * * If dst is not yet refcounted and not destroyed, grab a ref on it. + * Returns true if dst is refcounted. */ -static inline void skb_dst_force(struct sk_buff *skb) +static inline bool skb_dst_force(struct sk_buff *skb) { if (skb_dst_is_noref(skb)) { struct dst_entry *dst = skb_dst(skb); @@ -314,6 +315,8 @@ static inline void skb_dst_force(struct sk_buff *skb) skb->_skb_refdst = (unsigned long)dst; } + + return skb->_skb_refdst != 0UL; } diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index b473df5b9512..eba8465e1d86 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -103,6 +103,7 @@ struct fib_rule_notifier_info { }; #define FRA_GENERIC_POLICY \ + [FRA_UNSPEC] = { .strict_start_type = FRA_DPORT_RANGE + 1 }, \ [FRA_IIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ [FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ [FRA_PRIORITY] = { .type = NLA_U32 }, \ diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index dfabc0503446..90bd210be060 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -200,6 +200,28 @@ struct flow_dissector_key_ip { __u8 ttl; }; +/** + * struct flow_dissector_key_meta: + * @ingress_ifindex: ingress ifindex + */ +struct flow_dissector_key_meta { + int ingress_ifindex; +}; + +/** + * struct flow_dissector_key_ct: + * @ct_state: conntrack state after converting with map + * @ct_mark: conttrack mark + * @ct_zone: conntrack zone + * @ct_labels: conntrack labels + */ +struct flow_dissector_key_ct { + u16 ct_state; + u16 ct_zone; + u32 ct_mark; + u32 ct_labels[4]; +}; + enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */ @@ -225,14 +247,15 @@ enum flow_dissector_key_id { 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 */ + FLOW_DISSECTOR_KEY_META, /* struct flow_dissector_key_meta */ + FLOW_DISSECTOR_KEY_CT, /* struct flow_dissector_key_ct */ FLOW_DISSECTOR_KEY_MAX, }; #define FLOW_DISSECTOR_F_PARSE_1ST_FRAG BIT(0) -#define FLOW_DISSECTOR_F_STOP_AT_L3 BIT(1) -#define FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL BIT(2) -#define FLOW_DISSECTOR_F_STOP_AT_ENCAP BIT(3) +#define FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL BIT(1) +#define FLOW_DISSECTOR_F_STOP_AT_ENCAP BIT(2) struct flow_dissector_key { enum flow_dissector_key_id key_id; diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index a2df99f9b196..db337299e81e 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -1,7 +1,9 @@ #ifndef _NET_FLOW_OFFLOAD_H #define _NET_FLOW_OFFLOAD_H +#include <linux/kernel.h> #include <net/flow_dissector.h> +#include <net/sch_generic.h> struct flow_match { struct flow_dissector *dissector; @@ -9,6 +11,10 @@ struct flow_match { void *key; }; +struct flow_match_meta { + struct flow_dissector_key_meta *key, *mask; +}; + struct flow_match_basic { struct flow_dissector_key_basic *key, *mask; }; @@ -63,6 +69,8 @@ struct flow_match_enc_opts { struct flow_rule; +void flow_rule_match_meta(const struct flow_rule *rule, + struct flow_match_meta *out); void flow_rule_match_basic(const struct flow_rule *rule, struct flow_match_basic *out); void flow_rule_match_control(const struct flow_rule *rule, @@ -122,6 +130,7 @@ enum flow_action_id { FLOW_ACTION_QUEUE, FLOW_ACTION_SAMPLE, FLOW_ACTION_POLICE, + FLOW_ACTION_CT, }; /* This is mirroring enum pedit_header_type definition for easy mapping between @@ -171,6 +180,10 @@ struct flow_action_entry { s64 burst; u64 rate_bytes_ps; } police; + struct { /* FLOW_ACTION_CT */ + int action; + u16 zone; + } ct; }; }; @@ -225,4 +238,99 @@ static inline void flow_stats_update(struct flow_stats *flow_stats, flow_stats->lastused = max_t(u64, flow_stats->lastused, lastused); } +enum flow_block_command { + FLOW_BLOCK_BIND, + FLOW_BLOCK_UNBIND, +}; + +enum flow_block_binder_type { + FLOW_BLOCK_BINDER_TYPE_UNSPEC, + FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS, + FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS, +}; + +struct netlink_ext_ack; + +struct flow_block_offload { + enum flow_block_command command; + enum flow_block_binder_type binder_type; + bool block_shared; + struct net *net; + struct list_head cb_list; + struct list_head *driver_block_list; + struct netlink_ext_ack *extack; +}; + +struct flow_block_cb { + struct list_head driver_list; + struct list_head list; + struct net *net; + tc_setup_cb_t *cb; + void *cb_ident; + void *cb_priv; + void (*release)(void *cb_priv); + unsigned int refcnt; +}; + +struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb, + void *cb_ident, void *cb_priv, + void (*release)(void *cb_priv)); +void flow_block_cb_free(struct flow_block_cb *block_cb); + +struct flow_block_cb *flow_block_cb_lookup(struct flow_block_offload *offload, + tc_setup_cb_t *cb, void *cb_ident); + +void *flow_block_cb_priv(struct flow_block_cb *block_cb); +void flow_block_cb_incref(struct flow_block_cb *block_cb); +unsigned int flow_block_cb_decref(struct flow_block_cb *block_cb); + +static inline void flow_block_cb_add(struct flow_block_cb *block_cb, + struct flow_block_offload *offload) +{ + list_add_tail(&block_cb->list, &offload->cb_list); +} + +static inline void flow_block_cb_remove(struct flow_block_cb *block_cb, + struct flow_block_offload *offload) +{ + list_move(&block_cb->list, &offload->cb_list); +} + +bool flow_block_cb_is_busy(tc_setup_cb_t *cb, void *cb_ident, + struct list_head *driver_block_list); + +int flow_block_cb_setup_simple(struct flow_block_offload *f, + struct list_head *driver_list, tc_setup_cb_t *cb, + void *cb_ident, void *cb_priv, bool ingress_only); + +enum flow_cls_command { + FLOW_CLS_REPLACE, + FLOW_CLS_DESTROY, + FLOW_CLS_STATS, + FLOW_CLS_TMPLT_CREATE, + FLOW_CLS_TMPLT_DESTROY, +}; + +struct flow_cls_common_offload { + u32 chain_index; + __be16 protocol; + u32 prio; + struct netlink_ext_ack *extack; +}; + +struct flow_cls_offload { + struct flow_cls_common_offload common; + enum flow_cls_command command; + unsigned long cookie; + struct flow_rule *rule; + struct flow_stats stats; + u32 classid; +}; + +static inline struct flow_rule * +flow_cls_offload_flow_rule(struct flow_cls_offload *flow_cmd) +{ + return flow_cmd->rule; +} + #endif /* _NET_FLOW_OFFLOAD_H */ diff --git a/include/net/gue.h b/include/net/gue.h index fdad41469b65..3a6595bfa641 100644 --- a/include/net/gue.h +++ b/include/net/gue.h @@ -60,7 +60,7 @@ struct guehdr { /* Private flags in the private option extension */ -#define GUE_PFLAG_REMCSUM htonl(1 << 31) +#define GUE_PFLAG_REMCSUM htonl(1U << 31) #define GUE_PLEN_REMCSUM 4 #define GUE_PFLAGS_ALL (GUE_PFLAG_REMCSUM) diff --git a/include/net/hwbm.h b/include/net/hwbm.h index 89085e2e2da5..81643cf8a1c4 100644 --- a/include/net/hwbm.h +++ b/include/net/hwbm.h @@ -12,18 +12,18 @@ struct hwbm_pool { /* constructor called during alocation */ int (*construct)(struct hwbm_pool *bm_pool, void *buf); /* protect acces to the buffer counter*/ - spinlock_t lock; + struct mutex buf_lock; /* private data */ void *priv; }; #ifdef CONFIG_HWBM void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf); int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp); -int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp); +int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num); #else void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf) {} int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp) { return 0; } -int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp) +int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num) { return 0; } #endif /* CONFIG_HWBM */ #endif /* _HWBM_H */ diff --git a/include/net/inet_common.h b/include/net/inet_common.h index 975901a95c0f..ae2ba897675c 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -25,6 +25,7 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags); int inet_accept(struct socket *sock, struct socket *newsock, int flags, bool kern); +int inet_send_prepare(struct sock *sk); int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 378904ee9129..010f26b31c89 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -3,19 +3,24 @@ #define __NET_FRAG_H__ #include <linux/rhashtable-types.h> +#include <linux/completion.h> -struct netns_frags { +/* Per netns frag queues directory */ +struct fqdir { /* sysctls */ long high_thresh; long low_thresh; int timeout; int max_dist; struct inet_frags *f; + struct net *net; + bool dead; struct rhashtable rhashtable ____cacheline_aligned_in_smp; /* Keep atomic mem on separate cachelines in structs that include it */ atomic_long_t mem ____cacheline_aligned_in_smp; + struct work_struct destroy_work; }; /** @@ -24,11 +29,13 @@ struct netns_frags { * @INET_FRAG_FIRST_IN: first fragment has arrived * @INET_FRAG_LAST_IN: final fragment has arrived * @INET_FRAG_COMPLETE: frag queue has been processed and is due for destruction + * @INET_FRAG_HASH_DEAD: inet_frag_kill() has not removed fq from rhashtable */ enum { INET_FRAG_FIRST_IN = BIT(0), INET_FRAG_LAST_IN = BIT(1), INET_FRAG_COMPLETE = BIT(2), + INET_FRAG_HASH_DEAD = BIT(3), }; struct frag_v4_compare_key { @@ -64,7 +71,7 @@ struct frag_v6_compare_key { * @meat: length of received fragments so far * @flags: fragment queue flags * @max_size: maximum received fragment size - * @net: namespace that this frag belongs to + * @fqdir: pointer to struct fqdir * @rcu: rcu head for freeing deferall */ struct inet_frag_queue { @@ -84,7 +91,7 @@ struct inet_frag_queue { int meat; __u8 flags; u16 max_size; - struct netns_frags *net; + struct fqdir *fqdir; struct rcu_head rcu; }; @@ -98,21 +105,25 @@ struct inet_frags { struct kmem_cache *frags_cachep; const char *frags_cache_name; struct rhashtable_params rhash_params; + refcount_t refcnt; + struct completion completion; }; int inet_frags_init(struct inet_frags *); void inet_frags_fini(struct inet_frags *); -static inline int inet_frags_init_net(struct netns_frags *nf) +int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net); + +static inline void fqdir_pre_exit(struct fqdir *fqdir) { - atomic_long_set(&nf->mem, 0); - return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params); + fqdir->high_thresh = 0; /* prevent creation of new frags */ + fqdir->dead = true; } -void inet_frags_exit_net(struct netns_frags *nf); +void fqdir_exit(struct fqdir *fqdir); void inet_frag_kill(struct inet_frag_queue *q); void inet_frag_destroy(struct inet_frag_queue *q); -struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key); +struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key); /* Free all skbs in the queue; return the sum of their truesizes. */ unsigned int inet_frag_rbtree_purge(struct rb_root *root); @@ -125,19 +136,19 @@ static inline void inet_frag_put(struct inet_frag_queue *q) /* Memory Tracking Functions. */ -static inline long frag_mem_limit(const struct netns_frags *nf) +static inline long frag_mem_limit(const struct fqdir *fqdir) { - return atomic_long_read(&nf->mem); + return atomic_long_read(&fqdir->mem); } -static inline void sub_frag_mem_limit(struct netns_frags *nf, long val) +static inline void sub_frag_mem_limit(struct fqdir *fqdir, long val) { - atomic_long_sub(val, &nf->mem); + atomic_long_sub(val, &fqdir->mem); } -static inline void add_frag_mem_limit(struct netns_frags *nf, long val) +static inline void add_frag_mem_limit(struct fqdir *fqdir, long val) { - atomic_long_add(val, &nf->mem); + atomic_long_add(val, &fqdir->mem); } /* RFC 3168 support : diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index c2f756aedc54..aef38c140014 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -70,6 +70,7 @@ struct inet_timewait_sock { tw_flowlabel : 20, tw_pad : 2, /* 2 bits hole */ tw_tos : 8; + u32 tw_txhash; struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; }; diff --git a/include/net/ip.h b/include/net/ip.h index 49c672c8cdae..29d89de39822 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -161,6 +161,44 @@ 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); int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); + +struct ip_fraglist_iter { + struct sk_buff *frag; + struct iphdr *iph; + int offset; + unsigned int hlen; +}; + +void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph, + unsigned int hlen, struct ip_fraglist_iter *iter); +void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter); + +static inline struct sk_buff *ip_fraglist_next(struct ip_fraglist_iter *iter) +{ + struct sk_buff *skb = iter->frag; + + iter->frag = skb->next; + skb_mark_not_on_list(skb); + + return skb; +} + +struct ip_frag_state { + struct iphdr *iph; + unsigned int hlen; + unsigned int ll_rs; + unsigned int mtu; + unsigned int left; + int offset; + int ptr; + __be16 not_last_frag; +}; + +void ip_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int ll_rs, + unsigned int mtu, struct ip_frag_state *state); +struct sk_buff *ip_frag_next(struct sk_buff *skb, + struct ip_frag_state *state); + void ip_send_check(struct iphdr *ip); int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); @@ -241,7 +279,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, - unsigned int len); + unsigned int len, u64 transmit_time); #define IP_INC_STATS(net, field) SNMP_INC_STATS64((net)->mib.ip_statistics, field) #define __IP_INC_STATS(net, field) __SNMP_INC_STATS64((net)->mib.ip_statistics, field) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 855b352b660f..4b5656c71abc 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -49,6 +49,7 @@ struct fib6_config { u16 fc_delete_all_nh : 1, fc_ignore_dev_down:1, __unused : 14; + u32 fc_nh_id; struct in6_addr fc_dst; struct in6_addr fc_src; @@ -127,6 +128,9 @@ struct fib6_nh { #ifdef CONFIG_IPV6_ROUTER_PREF unsigned long last_probe; #endif + + struct rt6_info * __percpu *rt6i_pcpu; + struct rt6_exception_bucket __rcu *rt6i_exception_bucket; }; struct fib6_info { @@ -139,7 +143,10 @@ struct fib6_info { * destination, but not the same gateway. nsiblings is just a cache * to speed up lookup. */ - struct list_head fib6_siblings; + union { + struct list_head fib6_siblings; + struct list_head nh_list; + }; unsigned int fib6_nsiblings; refcount_t fib6_ref; @@ -152,22 +159,19 @@ struct fib6_info { struct rt6key fib6_src; struct rt6key fib6_prefsrc; - struct rt6_info * __percpu *rt6i_pcpu; - struct rt6_exception_bucket __rcu *rt6i_exception_bucket; - u32 fib6_metric; u8 fib6_protocol; u8 fib6_type; - u8 exception_bucket_flushed:1, - should_flush:1, + u8 should_flush:1, dst_nocount:1, dst_nopolicy:1, dst_host:1, fib6_destroying:1, - unused:2; + unused:3; - struct fib6_nh fib6_nh; struct rcu_head rcu; + struct nexthop *nh; + struct fib6_nh fib6_nh[0]; }; struct rt6_info { @@ -276,7 +280,7 @@ static inline void ip6_rt_put(struct rt6_info *rt) dst_release(&rt->dst); } -struct fib6_info *fib6_info_alloc(gfp_t gfp_flags); +struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh); void fib6_info_destroy_rcu(struct rcu_head *head); static inline void fib6_info_hold(struct fib6_info *f6i) @@ -312,6 +316,7 @@ struct fib6_walker { enum fib6_walk_state state; unsigned int skip; unsigned int count; + unsigned int skip_in_node; int (*func)(struct fib6_walker *); void *args; }; @@ -373,6 +378,7 @@ typedef struct rt6_info *(*pol_lookup_t)(struct net *, struct fib6_entry_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib6_info *rt; + unsigned int nsiblings; }; /* @@ -437,16 +443,22 @@ void rt6_get_prefsrc(const struct rt6_info *rt, struct in6_addr *addr) rcu_read_unlock(); } -static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i) -{ - return f6i->fib6_nh.fib_nh_dev; -} - int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void fib6_nh_release(struct fib6_nh *fib6_nh); +int call_fib6_entry_notifiers(struct net *net, + enum fib_event_type event_type, + struct fib6_info *rt, + struct netlink_ext_ack *extack); +int call_fib6_multipath_entry_notifiers(struct net *net, + enum fib_event_type event_type, + struct fib6_info *rt, + unsigned int nsiblings, + struct netlink_ext_ack *extack); +void fib6_rt_update(struct net *net, struct fib6_info *rt, + struct nl_info *info); void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int flags); @@ -480,6 +492,7 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb); void fib6_update_sernum(struct net *net, struct fib6_info *rt); void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt); +void fib6_update_sernum_stub(struct net *net, struct fib6_info *f6i); void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val); static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric) diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index ee7405e759ba..b69c16cbbf71 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -27,6 +27,7 @@ struct route_info { #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/route.h> +#include <net/nexthop.h> #define RT6_LOOKUP_F_IFACE 0x00000001 #define RT6_LOOKUP_F_REACHABLE 0x00000002 @@ -35,6 +36,7 @@ struct route_info { #define RT6_LOOKUP_F_SRCPREF_PUBLIC 0x00000010 #define RT6_LOOKUP_F_SRCPREF_COA 0x00000020 #define RT6_LOOKUP_F_IGNORE_LINKSTATE 0x00000040 +#define RT6_LOOKUP_F_DST_NOREF 0x00000080 /* We do not (yet ?) support IPv6 jumbograms (RFC 2675) * Unlike IPv4, hdr->seg_len doesn't include the IPv6 header @@ -66,11 +68,14 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr) (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } +/* fib entries using a nexthop object can not be coalesced into + * a multipath route + */ static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i) { /* the RTF_ADDRCONF flag filters out RA's */ - return !(f6i->fib6_flags & RTF_ADDRCONF) && - f6i->fib6_nh.fib_nh_gw_family; + return !(f6i->fib6_flags & RTF_ADDRCONF) && !f6i->nh && + f6i->fib6_nh->fib_nh_gw_family; } void ip6_route_input(struct sk_buff *skb); @@ -79,6 +84,10 @@ struct dst_entry *ip6_route_input_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags); +struct dst_entry *ip6_route_output_flags_noref(struct net *net, + const struct sock *sk, + struct flowi6 *fl6, int flags); + struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags); @@ -89,6 +98,16 @@ static inline struct dst_entry *ip6_route_output(struct net *net, return ip6_route_output_flags(net, sk, fl6, 0); } +/* Only conditionally release dst if flags indicates + * !RT6_LOOKUP_F_DST_NOREF or dst is in uncached_list. + */ +static inline void ip6_rt_put_flags(struct rt6_info *rt, int flags) +{ + if (!(flags & RT6_LOOKUP_F_DST_NOREF) || + !list_empty(&rt->rt6i_uncached)) + ip6_rt_put(rt); +} + struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags); struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, @@ -178,7 +197,7 @@ struct rt6_rtnl_dump_arg { struct fib_dump_filter filter; }; -int rt6_dump_route(struct fib6_info *f6i, void *p_arg); +int rt6_dump_route(struct fib6_info *f6i, void *p_arg, unsigned int skip); void rt6_mtu_change(struct net_device *dev, unsigned int mtu); void rt6_remove_prefsrc(struct inet6_ifaddr *ifp); void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); @@ -275,8 +294,13 @@ static inline const struct in6_addr *rt6_nexthop(const struct rt6_info *rt, static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info *b) { - struct fib6_nh *nha = &a->fib6_nh, *nhb = &b->fib6_nh; + struct fib6_nh *nha, *nhb; + + if (a->nh || b->nh) + return nexthop_cmp(a->nh, b->nh); + nha = a->fib6_nh; + nhb = b->fib6_nh; return nha->fib_nh_dev == nhb->fib_nh_dev && ipv6_addr_equal(&nha->fib_nh_gw6, &nhb->fib_nh_gw6) && !lwtunnel_cmp_encap(nha->fib_nh_lws, nhb->fib_nh_lws); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index bbeff32fb6cb..4c81846ccce8 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -40,6 +40,7 @@ struct fib_config { u32 fc_flags; u32 fc_priority; __be32 fc_prefsrc; + u32 fc_nh_id; struct nlattr *fc_mx; struct rtnexthop *fc_mp; int fc_mx_len; @@ -125,9 +126,12 @@ struct fib_nh { * This structure contains data shared by many of routes. */ +struct nexthop; + struct fib_info { struct hlist_node fib_hash; struct hlist_node fib_lhash; + struct list_head nh_list; struct net *fib_net; int fib_treeref; refcount_t fib_clntref; @@ -146,9 +150,10 @@ struct fib_info { #define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1] int fib_nhs; bool fib_nh_is_v6; + bool nh_updated; + struct nexthop *nh; struct rcu_head rcu; struct fib_nh fib_nh[0]; -#define fib_dev fib_nh[0].fib_nh_dev }; @@ -185,18 +190,14 @@ struct fib_result_nl { int err; }; -static inline struct fib_nh_common *fib_info_nhc(struct fib_info *fi, int nhsel) -{ - return &fi->fib_nh[nhsel].nh_common; -} - #ifdef CONFIG_IP_MULTIPLE_TABLES #define FIB_TABLE_HASHSZ 256 #else #define FIB_TABLE_HASHSZ 2 #endif -__be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh); +__be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, + unsigned char scope); __be32 fib_result_prefsrc(struct net *net, struct fib_result *res); #define FIB_RES_NHC(res) ((res).nhc) @@ -227,6 +228,7 @@ int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, int __net_init fib4_notifier_init(struct net *net); void __net_exit fib4_notifier_exit(struct net *net); +void fib_info_notify_update(struct net *net, struct nl_info *info); void fib_notify(struct net *net, struct notifier_block *nb); struct fib_table { @@ -243,6 +245,8 @@ struct fib_dump_filter { /* filter_set is an optimization that an entry is set */ bool filter_set; bool dump_all_families; + bool dump_routes; + bool dump_exceptions; unsigned char protocol; unsigned char rt_type; unsigned int flags; @@ -425,11 +429,14 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force); int fib_sync_down_addr(struct net_device *dev, __be32 local); int fib_sync_up(struct net_device *dev, unsigned char nh_flags); void fib_sync_mtu(struct net_device *dev, u32 orig_mtu); +void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig); #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys); #endif +int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope, + struct netlink_ext_ack *extack); void fib_select_multipath(struct fib_result *res, int hash); void fib_select_path(struct net *net, struct fib_result *res, struct flowi4 *fl4, const struct sk_buff *skb); @@ -451,11 +458,18 @@ static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) { #ifdef CONFIG_IP_ROUTE_CLASSID struct fib_nh_common *nhc = res->nhc; - struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common); #ifdef CONFIG_IP_MULTIPLE_TABLES u32 rtag; #endif - *itag = nh->nh_tclassid << 16; + if (nhc->nhc_family == AF_INET) { + struct fib_nh *nh; + + nh = container_of(nhc, struct fib_nh, nh_common); + *itag = nh->nh_tclassid << 16; + } else { + *itag = 0; + } + #ifdef CONFIG_IP_MULTIPLE_TABLES rtag = res->tclassid; if (*itag == 0) @@ -465,6 +479,7 @@ static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) #endif } +void fib_flush(struct net *net); void free_fib_info(struct fib_info *fi); static inline void fib_info_hold(struct fib_info *fi) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 2ac40135b576..3759167f91f5 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -603,6 +603,7 @@ struct ip_vs_dest_user_kern { u16 tun_type; /* tunnel type */ __be16 tun_port; /* tunnel port */ + u16 tun_flags; /* tunnel flags */ }; @@ -665,6 +666,7 @@ struct ip_vs_dest { atomic_t last_weight; /* server latest weight */ __u16 tun_type; /* tunnel type */ __be16 tun_port; /* tunnel port */ + __u16 tun_flags; /* tunnel flags */ refcount_t refcnt; /* reference counter */ struct ip_vs_stats stats; /* statistics */ @@ -808,11 +810,12 @@ struct ipvs_master_sync_state { struct ip_vs_sync_buff *sync_buff; unsigned long sync_queue_len; unsigned int sync_queue_delay; - struct task_struct *master_thread; struct delayed_work master_wakeup_work; struct netns_ipvs *ipvs; }; +struct ip_vs_sync_thread_data; + /* How much time to keep dests in trash */ #define IP_VS_DEST_TRASH_PERIOD (120 * HZ) @@ -943,7 +946,8 @@ struct netns_ipvs { spinlock_t sync_lock; struct ipvs_master_sync_state *ms; spinlock_t sync_buff_lock; - struct task_struct **backup_threads; + struct ip_vs_sync_thread_data *master_tinfo; + struct ip_vs_sync_thread_data *backup_tinfo; int threads_mask; volatile int sync_state; struct mutex sync_mutex; @@ -1404,6 +1408,9 @@ bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol, struct ip_vs_dest * ip_vs_find_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport); +struct ip_vs_dest *ip_vs_find_tunnel(struct netns_ipvs *ipvs, int af, + const union nf_inet_addr *daddr, + __be16 tun_port); int ip_vs_use_count_inc(void); void ip_vs_use_count_dec(void); @@ -1497,6 +1504,9 @@ static inline int ip_vs_todrop(struct netns_ipvs *ipvs) static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { return 0; } #endif +#define IP_VS_DFWD_METHOD(dest) (atomic_read(&(dest)->conn_flags) & \ + IP_VS_CONN_F_FWD_MASK) + /* ip_vs_fwd_tag returns the forwarding tag of the connection */ #define IP_VS_FWD_METHOD(cp) (cp->flags & IP_VS_CONN_F_FWD_MASK) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 60d9480bc4d1..8dfc65639aa4 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -13,6 +13,7 @@ #include <linux/hardirq.h> #include <linux/jhash.h> #include <linux/refcount.h> +#include <linux/jump_label_ratelimit.h> #include <net/if_inet6.h> #include <net/ndisc.h> #include <net/flow.h> @@ -150,6 +151,49 @@ struct frag_hdr { #define IP6_MF 0x0001 #define IP6_OFFSET 0xFFF8 +struct ip6_fraglist_iter { + struct ipv6hdr *tmp_hdr; + struct sk_buff *frag; + int offset; + unsigned int hlen; + __be32 frag_id; + u8 nexthdr; +}; + +int ip6_fraglist_init(struct sk_buff *skb, unsigned int hlen, u8 *prevhdr, + u8 nexthdr, __be32 frag_id, + struct ip6_fraglist_iter *iter); +void ip6_fraglist_prepare(struct sk_buff *skb, struct ip6_fraglist_iter *iter); + +static inline struct sk_buff *ip6_fraglist_next(struct ip6_fraglist_iter *iter) +{ + struct sk_buff *skb = iter->frag; + + iter->frag = skb->next; + skb_mark_not_on_list(skb); + + return skb; +} + +struct ip6_frag_state { + u8 *prevhdr; + unsigned int hlen; + unsigned int mtu; + unsigned int left; + int offset; + int ptr; + int hroom; + int troom; + __be32 frag_id; + u8 nexthdr; +}; + +void ip6_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int mtu, + unsigned short needed_tailroom, int hdr_room, u8 *prevhdr, + u8 nexthdr, __be32 frag_id, struct ip6_frag_state *state); +struct sk_buff *ip6_frag_next(struct sk_buff *skb, + struct ip6_frag_state *state); + #define IP6_REPLY_MARK(net, mark) \ ((net)->ipv6.sysctl.fwmark_reflect ? (mark) : 0) @@ -258,6 +302,13 @@ struct ipv6_txoptions { /* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */ }; +/* flowlabel_reflect sysctl values */ +enum flowlabel_reflect { + FLOWLABEL_REFLECT_ESTABLISHED = 1, + FLOWLABEL_REFLECT_TCP_RESET = 2, + FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES = 4, +}; + struct ip6_flowlabel { struct ip6_flowlabel __rcu *next; __be32 label; @@ -339,7 +390,18 @@ static inline void txopt_put(struct ipv6_txoptions *opt) kfree_rcu(opt, rcu); } -struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label); +struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label); + +extern struct static_key_false_deferred ipv6_flowlabel_exclusive; +static inline struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, + __be32 label) +{ + if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key)) + return __fl6_sock_lookup(sk, label) ? : ERR_PTR(-ENOENT); + + return NULL; +} + struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, struct ip6_flowlabel *fl, struct ipv6_txoptions *fopt); diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index 1f77fb4dc79d..a21e8b1381a1 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -67,6 +67,8 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) struct sk_buff *head; rcu_read_lock(); + if (fq->q.fqdir->dead) + goto out_rcu_unlock; spin_lock(&fq->q.lock); if (fq->q.flags & INET_FRAG_COMPLETE) diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 6c0c4fde16f8..5c93e942c50b 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -45,6 +45,11 @@ struct ipv6_stub { struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void (*fib6_nh_release)(struct fib6_nh *fib6_nh); + void (*fib6_update_sernum)(struct net *net, struct fib6_info *rt); + int (*ip6_del_rt)(struct net *net, struct fib6_info *rt); + void (*fib6_rt_update)(struct net *net, struct fib6_info *rt, + struct nl_info *info); + void (*udpv6_encap_enable)(void); void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 456f2edf78dc..d26da013f7c0 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -314,6 +314,7 @@ struct ieee80211_vif_chanctx_switch { * @BSS_CHANGED_MCAST_RATE: Multicast Rate setting changed for this interface * @BSS_CHANGED_FTM_RESPONDER: fime timing reasurement request responder * functionality changed for this BSS (AP mode). + * @BSS_CHANGED_TWT: TWT status changed * */ enum ieee80211_bss_change { @@ -344,6 +345,7 @@ enum ieee80211_bss_change { BSS_CHANGED_KEEP_ALIVE = 1<<24, BSS_CHANGED_MCAST_RATE = 1<<25, BSS_CHANGED_FTM_RESPONDER = 1<<26, + BSS_CHANGED_TWT = 1<<27, /* when adding here, make sure to change ieee80211_reconfig */ }; @@ -501,6 +503,8 @@ struct ieee80211_ftm_responder_params { * @he_support: does this BSS support HE * @twt_requester: does this BSS support TWT requester (relevant for managed * mode only, set if the AP advertises TWT responder role) + * @twt_responder: does this BSS support TWT requester (relevant for managed + * mode only, set if the AP advertises TWT responder role) * @assoc: association status * @ibss_joined: indicates whether this station is part of an IBSS * or not @@ -608,6 +612,7 @@ struct ieee80211_bss_conf { u16 frame_time_rts_th; bool he_support; bool twt_requester; + bool twt_responder; /* association related data */ bool assoc, ibss_joined; bool ibss_creator; @@ -2266,6 +2271,9 @@ struct ieee80211_txq { * @IEEE80211_HW_EXT_KEY_ID_NATIVE: Driver and hardware are supporting Extended * Key ID and can handle two unicast keys per station for Rx and Tx. * + * @IEEE80211_HW_NO_AMPDU_KEYBORDER_SUPPORT: The card/driver can't handle + * active Tx A-MPDU sessions with Extended Key IDs during rekey. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2318,6 +2326,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_MULTI_BSSID, IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID, IEEE80211_HW_EXT_KEY_ID_NATIVE, + IEEE80211_HW_NO_AMPDU_KEYBORDER_SUPPORT, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -5948,29 +5957,6 @@ static inline int rate_supported(struct ieee80211_sta *sta, return (sta == NULL || sta->supp_rates[band] & BIT(index)); } -/** - * rate_control_send_low - helper for drivers for management/no-ack frames - * - * Rate control algorithms that agree to use the lowest rate to - * send management frames and NO_ACK data with the respective hw - * retries should use this in the beginning of their mac80211 get_rate - * callback. If true is returned the rate control can simply return. - * If false is returned we guarantee that sta and sta and priv_sta is - * not null. - * - * Rate control algorithms wishing to do more intelligent selection of - * rate for multicast/broadcast frames may choose to not use this. - * - * @sta: &struct ieee80211_sta pointer to the target destination. Note - * that this may be null. - * @priv_sta: private rate control structure. This may be null. - * @txrc: rate control information we sholud populate for mac80211. - */ -bool rate_control_send_low(struct ieee80211_sta *sta, - void *priv_sta, - struct ieee80211_tx_rate_control *txrc); - - static inline s8 rate_lowest_index(struct ieee80211_supported_band *sband, struct ieee80211_sta *sta) diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index a56bf7fc7c2b..4a9da951a794 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -19,6 +19,7 @@ #include <net/netns/packet.h> #include <net/netns/ipv4.h> #include <net/netns/ipv6.h> +#include <net/netns/nexthop.h> #include <net/netns/ieee802154_6lowpan.h> #include <net/netns/sctp.h> #include <net/netns/dccp.h> @@ -111,6 +112,7 @@ struct net { struct netns_mib mib; struct netns_packet packet; struct netns_unix unx; + struct netns_nexthop nexthop; struct netns_ipv4 ipv4; #if IS_ENABLED(CONFIG_IPV6) struct netns_ipv6 ipv6; @@ -356,8 +358,13 @@ struct pernet_operations { * synchronize_rcu() related to these pernet_operations, * instead of separate synchronize_rcu() for every net. * Please, avoid synchronize_rcu() at all, where it's possible. + * + * Note that a combination of pre_exit() and exit() can + * be used, since a synchronize_rcu() is guaranteed between + * the calls. */ int (*init)(struct net *net); + void (*pre_exit)(struct net *net); void (*exit)(struct net *net); void (*exit_batch)(struct list_head *net_exit_list); unsigned int *id; diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index 89808ce293c4..302fcd3aade2 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -42,7 +42,8 @@ static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) return port ? &port->br->fake_rtable : NULL; } -struct net_device *setup_pre_routing(struct sk_buff *skb); +struct net_device *setup_pre_routing(struct sk_buff *skb, + const struct net *net); #if IS_ENABLED(CONFIG_IPV6) int br_validate_ipv6(struct net *net, struct sk_buff *skb); diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index d2bc733a2ef1..c86657d99630 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -49,6 +49,7 @@ union nf_conntrack_expect_proto { struct nf_conntrack_net { unsigned int users4; unsigned int users6; + unsigned int users_bridge; }; #include <linux/types.h> @@ -69,7 +70,8 @@ struct nf_conn { struct nf_conntrack ct_general; spinlock_t lock; - u16 cpu; + /* jiffies32 when this ct is considered dead */ + u32 timeout; #ifdef CONFIG_NF_CONNTRACK_ZONES struct nf_conntrack_zone zone; @@ -81,9 +83,7 @@ struct nf_conn { /* Have we seen traffic both ways yet? (bitset) */ unsigned long status; - /* jiffies32 when this ct is considered dead */ - u32 timeout; - + u16 cpu; possible_net_t ct_net; #if IS_ENABLED(CONFIG_NF_NAT) diff --git a/include/net/netfilter/nf_conntrack_bridge.h b/include/net/netfilter/nf_conntrack_bridge.h new file mode 100644 index 000000000000..9a5514d5bc51 --- /dev/null +++ b/include/net/netfilter/nf_conntrack_bridge.h @@ -0,0 +1,20 @@ +#ifndef NF_CONNTRACK_BRIDGE_ +#define NF_CONNTRACK_BRIDGE_ + +struct nf_ct_bridge_info { + struct nf_hook_ops *ops; + unsigned int ops_size; + struct module *me; +}; + +void nf_ct_bridge_register(struct nf_ct_bridge_info *info); +void nf_ct_bridge_unregister(struct nf_ct_bridge_info *info); + +struct nf_ct_bridge_frag_data { + char mac[ETH_HLEN]; + bool vlan_present; + u16 vlan_tci; + __be16 vlan_proto; +}; + +#endif diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index ae41e92251dd..de10faf2ce91 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -64,6 +64,9 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb) return ret; } +unsigned int nf_confirm(struct sk_buff *skb, unsigned int protoff, + struct nf_conn *ct, enum ip_conntrack_info ctinfo); + void print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l4proto *proto); diff --git a/include/net/netfilter/nf_conntrack_synproxy.h b/include/net/netfilter/nf_conntrack_synproxy.h index 2c7559a54092..8f00125b06f4 100644 --- a/include/net/netfilter/nf_conntrack_synproxy.h +++ b/include/net/netfilter/nf_conntrack_synproxy.h @@ -2,6 +2,7 @@ #ifndef _NF_CONNTRACK_SYNPROXY_H #define _NF_CONNTRACK_SYNPROXY_H +#include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netns/generic.h> struct nf_conn_synproxy { @@ -72,21 +73,12 @@ struct synproxy_options { }; struct tcphdr; -struct xt_synproxy_info; +struct nf_synproxy_info; bool synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, const struct tcphdr *th, struct synproxy_options *opts); -unsigned int synproxy_options_size(const struct synproxy_options *opts); -void synproxy_build_options(struct tcphdr *th, - const struct synproxy_options *opts); -void synproxy_init_timestamp_cookie(const struct xt_synproxy_info *info, +void synproxy_init_timestamp_cookie(const struct nf_synproxy_info *info, struct synproxy_options *opts); -void synproxy_check_timestamp_cookie(struct synproxy_options *opts); - -unsigned int synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff, - struct tcphdr *th, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - const struct nf_conn_synproxy *synproxy); #endif /* _NF_CONNTRACK_SYNPROXY_H */ diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 3e370cb36263..d8c187936bec 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -53,8 +53,6 @@ struct flow_offload_tuple { u8 l4proto; u8 dir; - int oifidx; - u16 mtu; struct dst_entry *dst_cache; diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 7239105d9d2e..3cb6dcf53a4e 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -120,6 +120,5 @@ nfqueue_hash(const struct sk_buff *skb, u16 queue, u16 queues_total, u8 family, } int nf_queue(struct sk_buff *skb, struct nf_hook_state *state, - const struct nf_hook_entries *entries, unsigned int index, - unsigned int verdict); + unsigned int index, unsigned int verdict); #endif /* _NF_QUEUE_H */ diff --git a/include/net/netfilter/nf_synproxy.h b/include/net/netfilter/nf_synproxy.h new file mode 100644 index 000000000000..87d73fb5279d --- /dev/null +++ b/include/net/netfilter/nf_synproxy.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NF_SYNPROXY_SHARED_H +#define _NF_SYNPROXY_SHARED_H + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <net/ip6_checksum.h> +#include <net/ip6_route.h> +#include <net/tcp.h> + +#include <net/netfilter/nf_conntrack_seqadj.h> +#include <net/netfilter/nf_conntrack_synproxy.h> + +void synproxy_send_client_synack(struct net *net, const struct sk_buff *skb, + const struct tcphdr *th, + const struct synproxy_options *opts); + +bool synproxy_recv_client_ack(struct net *net, + const struct sk_buff *skb, + const struct tcphdr *th, + struct synproxy_options *opts, u32 recv_seq); + +unsigned int ipv4_synproxy_hook(void *priv, struct sk_buff *skb, + const struct nf_hook_state *nhs); +int nf_synproxy_ipv4_init(struct synproxy_net *snet, struct net *net); +void nf_synproxy_ipv4_fini(struct synproxy_net *snet, struct net *net); + +#if IS_ENABLED(CONFIG_IPV6) +void synproxy_send_client_synack_ipv6(struct net *net, + const struct sk_buff *skb, + const struct tcphdr *th, + const struct synproxy_options *opts); + +bool synproxy_recv_client_ack_ipv6(struct net *net, const struct sk_buff *skb, + const struct tcphdr *th, + struct synproxy_options *opts, u32 recv_seq); + +unsigned int ipv6_synproxy_hook(void *priv, struct sk_buff *skb, + const struct nf_hook_state *nhs); +int nf_synproxy_ipv6_init(struct synproxy_net *snet, struct net *net); +void nf_synproxy_ipv6_fini(struct synproxy_net *snet, struct net *net); +#else +static inline int +nf_synproxy_ipv6_init(struct synproxy_net *snet, struct net *net) { return 0; } +static inline void +nf_synproxy_ipv6_fini(struct synproxy_net *snet, struct net *net) {}; +#endif /* CONFIG_IPV6 */ + +#endif /* _NF_SYNPROXY_SHARED_H */ diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 5b8624ae4a27..35dfdd9f69b3 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -161,6 +161,7 @@ struct nft_ctx { const struct nlattr * const *nla; u32 portid; u32 seq; + u16 flags; u8 family; u8 level; bool report; @@ -636,7 +637,7 @@ static inline struct nft_object **nft_set_ext_obj(const struct nft_set_ext *ext) void *nft_set_elem_init(const struct nft_set *set, const struct nft_set_ext_tmpl *tmpl, const u32 *key, const u32 *data, - u64 timeout, gfp_t gfp); + u64 timeout, u64 expiration, gfp_t gfp); void nft_set_elem_destroy(const struct nft_set *set, void *elem, bool destroy_expr); @@ -735,6 +736,9 @@ enum nft_trans_phase { NFT_TRANS_RELEASE }; +struct nft_flow_rule; +struct nft_offload_ctx; + /** * struct nft_expr_ops - nf_tables expression operations * @@ -777,6 +781,10 @@ struct nft_expr_ops { const struct nft_data **data); bool (*gc)(struct net *net, const struct nft_expr *expr); + int (*offload)(struct nft_offload_ctx *ctx, + struct nft_flow_rule *flow, + const struct nft_expr *expr); + u32 offload_flags; const struct nft_expr_type *type; void *data; }; @@ -859,6 +867,7 @@ static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) enum nft_chain_flags { NFT_BASE_CHAIN = 0x1, + NFT_CHAIN_HW_OFFLOAD = 0x2, }; /** @@ -942,6 +951,7 @@ struct nft_stats { * @stats: per-cpu chain stats * @chain: the chain * @dev_name: device name that this base chain is attached to (if any) + * @cb_list: list of flow block callbacks (for hardware offload) */ struct nft_base_chain { struct nf_hook_ops ops; @@ -951,6 +961,7 @@ struct nft_base_chain { struct nft_stats __percpu *stats; struct nft_chain chain; char dev_name[IFNAMSIZ]; + struct list_head cb_list; }; static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chain) @@ -1322,11 +1333,14 @@ struct nft_trans { struct nft_trans_rule { struct nft_rule *rule; + struct nft_flow_rule *flow; u32 rule_id; }; #define nft_trans_rule(trans) \ (((struct nft_trans_rule *)trans->data)->rule) +#define nft_trans_flow_rule(trans) \ + (((struct nft_trans_rule *)trans->data)->flow) #define nft_trans_rule_id(trans) \ (((struct nft_trans_rule *)trans->data)->rule_id) diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h new file mode 100644 index 000000000000..3196663a10e3 --- /dev/null +++ b/include/net/netfilter/nf_tables_offload.h @@ -0,0 +1,76 @@ +#ifndef _NET_NF_TABLES_OFFLOAD_H +#define _NET_NF_TABLES_OFFLOAD_H + +#include <net/flow_offload.h> +#include <net/netfilter/nf_tables.h> + +struct nft_offload_reg { + u32 key; + u32 len; + u32 base_offset; + u32 offset; + struct nft_data mask; +}; + +enum nft_offload_dep_type { + NFT_OFFLOAD_DEP_UNSPEC = 0, + NFT_OFFLOAD_DEP_NETWORK, + NFT_OFFLOAD_DEP_TRANSPORT, +}; + +struct nft_offload_ctx { + struct { + enum nft_offload_dep_type type; + __be16 l3num; + u8 protonum; + } dep; + unsigned int num_actions; + struct nft_offload_reg regs[NFT_REG32_15 + 1]; +}; + +void nft_offload_set_dependency(struct nft_offload_ctx *ctx, + enum nft_offload_dep_type type); +void nft_offload_update_dependency(struct nft_offload_ctx *ctx, + const void *data, u32 len); + +struct nft_flow_key { + struct flow_dissector_key_basic basic; + union { + struct flow_dissector_key_ipv4_addrs ipv4; + struct flow_dissector_key_ipv6_addrs ipv6; + }; + struct flow_dissector_key_ports tp; + struct flow_dissector_key_ip ip; + struct flow_dissector_key_vlan vlan; + struct flow_dissector_key_eth_addrs eth_addrs; +} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ + +struct nft_flow_match { + struct flow_dissector dissector; + struct nft_flow_key key; + struct nft_flow_key mask; +}; + +struct nft_flow_rule { + __be16 proto; + struct nft_flow_match match; + struct flow_rule *rule; +}; + +#define NFT_OFFLOAD_F_ACTION (1 << 0) + +struct nft_rule; +struct nft_flow_rule *nft_flow_rule_create(const struct nft_rule *rule); +void nft_flow_rule_destroy(struct nft_flow_rule *flow); +int nft_flow_rule_offload_commit(struct net *net); + +#define NFT_OFFLOAD_MATCH(__key, __base, __field, __len, __reg) \ + (__reg)->base_offset = \ + offsetof(struct nft_flow_key, __base); \ + (__reg)->offset = \ + offsetof(struct nft_flow_key, __base.__field); \ + (__reg)->len = __len; \ + (__reg)->key = __key; \ + memset(&(__reg)->mask, 0xff, (__reg)->len); + +#endif diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h new file mode 100644 index 000000000000..5c69e9b09388 --- /dev/null +++ b/include/net/netfilter/nft_meta.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NFT_META_H_ +#define _NFT_META_H_ + +struct nft_meta { + enum nft_meta_keys key:8; + union { + enum nft_registers dreg:8; + enum nft_registers sreg:8; + }; +}; + +extern const struct nla_policy nft_meta_policy[]; + +int nft_meta_get_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]); + +int nft_meta_set_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]); + +int nft_meta_get_dump(struct sk_buff *skb, + const struct nft_expr *expr); + +int nft_meta_set_dump(struct sk_buff *skb, + const struct nft_expr *expr); + +void nft_meta_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt); + +void nft_meta_set_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt); + +void nft_meta_set_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr); + +int nft_meta_set_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data); + +#endif diff --git a/include/net/netlink.h b/include/net/netlink.h index 395b4406f4b0..e4650e5b64a1 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -378,13 +378,17 @@ struct nla_policy { /** * struct nl_info - netlink source information * @nlh: Netlink message header of original request + * @nl_net: Network namespace * @portid: Netlink PORTID of requesting application + * @skip_notify: Skip netlink notifications to user space + * @skip_notify_kernel: Skip selected in-kernel notifications */ struct nl_info { struct nlmsghdr *nlh; struct net *nl_net; u32 portid; - bool skip_notify; + u8 skip_notify:1, + skip_notify_kernel:1; }; /** @@ -1755,6 +1759,15 @@ static inline int __nla_validate_nested(const struct nlattr *start, int maxtype, } static inline int +nl80211_validate_nested(const struct nlattr *start, int maxtype, + const struct nla_policy *policy, + struct netlink_ext_ack *extack) +{ + return __nla_validate_nested(start, maxtype, policy, + NL_VALIDATE_STRICT, extack); +} + +static inline int nla_validate_nested_deprecated(const struct nlattr *start, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) diff --git a/include/net/netns/ieee802154_6lowpan.h b/include/net/netns/ieee802154_6lowpan.h index 736aeac52f56..95406e1342cb 100644 --- a/include/net/netns/ieee802154_6lowpan.h +++ b/include/net/netns/ieee802154_6lowpan.h @@ -16,7 +16,7 @@ struct netns_sysctl_lowpan { struct netns_ieee802154_lowpan { struct netns_sysctl_lowpan sysctl; - struct netns_frags frags; + struct fqdir *fqdir; }; #endif diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 623cfbb7b8dc..bc24a8ec1ce5 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -72,7 +72,7 @@ struct netns_ipv4 { struct inet_peer_base *peers; struct sock * __percpu *tcp_sk; - struct netns_frags frags; + struct fqdir *fqdir; #ifdef CONFIG_NETFILTER struct xt_table *iptable_filter; struct xt_table *iptable_mangle; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 5e61b5a8635d..022a0fd1a5a4 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -58,7 +58,7 @@ struct netns_ipv6 { struct ipv6_devconf *devconf_all; struct ipv6_devconf *devconf_dflt; struct inet_peer_base *peers; - struct netns_frags frags; + struct fqdir *fqdir; #ifdef CONFIG_NETFILTER struct xt_table *ip6table_filter; struct xt_table *ip6table_mangle; @@ -116,7 +116,7 @@ struct netns_ipv6 { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) struct netns_nf_frag { - struct netns_frags frags; + struct fqdir *fqdir; }; #endif diff --git a/include/net/netns/nexthop.h b/include/net/netns/nexthop.h new file mode 100644 index 000000000000..c712ee5eebd9 --- /dev/null +++ b/include/net/netns/nexthop.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * nexthops in net namespaces + */ + +#ifndef __NETNS_NEXTHOP_H__ +#define __NETNS_NEXTHOP_H__ + +#include <linux/rbtree.h> + +struct netns_nexthop { + struct rb_root rb_root; /* tree of nexthops by id */ + struct hlist_head *devhash; /* nexthops by device */ + + unsigned int seq; /* protected by rtnl_mutex */ + u32 last_id_allocated; +}; +#endif diff --git a/include/net/nexthop.h b/include/net/nexthop.h new file mode 100644 index 000000000000..25f1f9a8419b --- /dev/null +++ b/include/net/nexthop.h @@ -0,0 +1,312 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Generic nexthop implementation + * + * Copyright (c) 2017-19 Cumulus Networks + * Copyright (c) 2017-19 David Ahern <dsa@cumulusnetworks.com> + */ + +#ifndef __LINUX_NEXTHOP_H +#define __LINUX_NEXTHOP_H + +#include <linux/netdevice.h> +#include <linux/route.h> +#include <linux/types.h> +#include <net/ip_fib.h> +#include <net/ip6_fib.h> +#include <net/netlink.h> + +#define NEXTHOP_VALID_USER_FLAGS RTNH_F_ONLINK + +struct nexthop; + +struct nh_config { + u32 nh_id; + + u8 nh_family; + u8 nh_protocol; + u8 nh_blackhole; + u32 nh_flags; + + int nh_ifindex; + struct net_device *dev; + + union { + __be32 ipv4; + struct in6_addr ipv6; + } gw; + + struct nlattr *nh_grp; + u16 nh_grp_type; + + struct nlattr *nh_encap; + u16 nh_encap_type; + + u32 nlflags; + struct nl_info nlinfo; +}; + +struct nh_info { + struct hlist_node dev_hash; /* entry on netns devhash */ + struct nexthop *nh_parent; + + u8 family; + bool reject_nh; + + union { + struct fib_nh_common fib_nhc; + struct fib_nh fib_nh; + struct fib6_nh fib6_nh; + }; +}; + +struct nh_grp_entry { + struct nexthop *nh; + u8 weight; + atomic_t upper_bound; + + struct list_head nh_list; + struct nexthop *nh_parent; /* nexthop of group with this entry */ +}; + +struct nh_group { + u16 num_nh; + bool mpath; + bool has_v4; + struct nh_grp_entry nh_entries[0]; +}; + +struct nexthop { + struct rb_node rb_node; /* entry on netns rbtree */ + struct list_head fi_list; /* v4 entries using nh */ + struct list_head f6i_list; /* v6 entries using nh */ + struct list_head grp_list; /* nh group entries using this nh */ + struct net *net; + + u32 id; + + u8 protocol; /* app managing this nh */ + u8 nh_flags; + bool is_group; + + refcount_t refcnt; + struct rcu_head rcu; + + union { + struct nh_info __rcu *nh_info; + struct nh_group __rcu *nh_grp; + }; +}; + +/* caller is holding rcu or rtnl; no reference taken to nexthop */ +struct nexthop *nexthop_find_by_id(struct net *net, u32 id); +void nexthop_free_rcu(struct rcu_head *head); + +static inline bool nexthop_get(struct nexthop *nh) +{ + return refcount_inc_not_zero(&nh->refcnt); +} + +static inline void nexthop_put(struct nexthop *nh) +{ + if (refcount_dec_and_test(&nh->refcnt)) + call_rcu(&nh->rcu, nexthop_free_rcu); +} + +static inline bool nexthop_cmp(const struct nexthop *nh1, + const struct nexthop *nh2) +{ + return nh1 == nh2; +} + +static inline bool nexthop_is_multipath(const struct nexthop *nh) +{ + if (nh->is_group) { + struct nh_group *nh_grp; + + nh_grp = rcu_dereference_rtnl(nh->nh_grp); + return nh_grp->mpath; + } + return false; +} + +struct nexthop *nexthop_select_path(struct nexthop *nh, int hash); + +static inline unsigned int nexthop_num_path(const struct nexthop *nh) +{ + unsigned int rc = 1; + + if (nexthop_is_multipath(nh)) { + struct nh_group *nh_grp; + + nh_grp = rcu_dereference_rtnl(nh->nh_grp); + rc = nh_grp->num_nh; + } else { + const struct nh_info *nhi; + + nhi = rcu_dereference_rtnl(nh->nh_info); + if (nhi->reject_nh) + rc = 0; + } + + return rc; +} + +static inline +struct nexthop *nexthop_mpath_select(const struct nexthop *nh, int nhsel) +{ + const struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp); + + /* for_nexthops macros in fib_semantics.c grabs a pointer to + * the nexthop before checking nhsel + */ + if (nhsel >= nhg->num_nh) + return NULL; + + return nhg->nh_entries[nhsel].nh; +} + +static inline +int nexthop_mpath_fill_node(struct sk_buff *skb, struct nexthop *nh) +{ + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + int i; + + for (i = 0; i < nhg->num_nh; i++) { + struct nexthop *nhe = nhg->nh_entries[i].nh; + struct nh_info *nhi = rcu_dereference_rtnl(nhe->nh_info); + struct fib_nh_common *nhc = &nhi->fib_nhc; + int weight = nhg->nh_entries[i].weight; + + if (fib_add_nexthop(skb, nhc, weight) < 0) + return -EMSGSIZE; + } + + return 0; +} + +/* called with rcu lock */ +static inline bool nexthop_is_blackhole(const struct nexthop *nh) +{ + const struct nh_info *nhi; + + if (nexthop_is_multipath(nh)) { + if (nexthop_num_path(nh) > 1) + return false; + nh = nexthop_mpath_select(nh, 0); + if (!nh) + return false; + } + + nhi = rcu_dereference_rtnl(nh->nh_info); + return nhi->reject_nh; +} + +static inline void nexthop_path_fib_result(struct fib_result *res, int hash) +{ + struct nh_info *nhi; + struct nexthop *nh; + + nh = nexthop_select_path(res->fi->nh, hash); + nhi = rcu_dereference(nh->nh_info); + res->nhc = &nhi->fib_nhc; +} + +/* called with rcu read lock or rtnl held */ +static inline +struct fib_nh_common *nexthop_fib_nhc(struct nexthop *nh, int nhsel) +{ + struct nh_info *nhi; + + BUILD_BUG_ON(offsetof(struct fib_nh, nh_common) != 0); + BUILD_BUG_ON(offsetof(struct fib6_nh, nh_common) != 0); + + if (nexthop_is_multipath(nh)) { + nh = nexthop_mpath_select(nh, nhsel); + if (!nh) + return NULL; + } + + nhi = rcu_dereference_rtnl(nh->nh_info); + return &nhi->fib_nhc; +} + +static inline unsigned int fib_info_num_path(const struct fib_info *fi) +{ + if (unlikely(fi->nh)) + return nexthop_num_path(fi->nh); + + return fi->fib_nhs; +} + +int fib_check_nexthop(struct nexthop *nh, u8 scope, + struct netlink_ext_ack *extack); + +static inline struct fib_nh_common *fib_info_nhc(struct fib_info *fi, int nhsel) +{ + if (unlikely(fi->nh)) + return nexthop_fib_nhc(fi->nh, nhsel); + + return &fi->fib_nh[nhsel].nh_common; +} + +/* only used when fib_nh is built into fib_info */ +static inline struct fib_nh *fib_info_nh(struct fib_info *fi, int nhsel) +{ + WARN_ON(fi->nh); + + return &fi->fib_nh[nhsel]; +} + +/* + * IPv6 variants + */ +int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, + struct netlink_ext_ack *extack); + +static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) +{ + struct nh_info *nhi; + + if (nexthop_is_multipath(nh)) { + nh = nexthop_mpath_select(nh, 0); + if (!nh) + return NULL; + } + + nhi = rcu_dereference_rtnl(nh->nh_info); + if (nhi->family == AF_INET6) + return &nhi->fib6_nh; + + return NULL; +} + +static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i) +{ + struct fib6_nh *fib6_nh; + + fib6_nh = f6i->nh ? nexthop_fib6_nh(f6i->nh) : f6i->fib6_nh; + return fib6_nh->fib_nh_dev; +} + +static inline void nexthop_path_fib6_result(struct fib6_result *res, int hash) +{ + struct nexthop *nh = res->f6i->nh; + struct nh_info *nhi; + + nh = nexthop_select_path(nh, hash); + + nhi = rcu_dereference_rtnl(nh->nh_info); + if (nhi->reject_nh) { + res->fib6_type = RTN_BLACKHOLE; + res->fib6_flags |= RTF_REJECT; + res->nh = nexthop_fib6_nh(nh); + } else { + res->nh = &nhi->fib6_nh; + } +} + +int nexthop_for_each_fib6_nh(struct nexthop *nh, + int (*cb)(struct fib6_nh *nh, void *arg), + void *arg); +#endif diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 694d055e01ef..2cbcdbdec254 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -16,14 +16,16 @@ * page_pool_alloc_pages() call. Drivers should likely use * page_pool_dev_alloc_pages() replacing dev_alloc_pages(). * - * If page_pool handles DMA mapping (use page->private), then API user - * is responsible for invoking page_pool_put_page() once. In-case of - * elevated refcnt, the DMA state is released, assuming other users of - * the page will eventually call put_page(). + * API keeps track of in-flight pages, in-order to let API user know + * when it is safe to dealloactor page_pool object. Thus, API users + * must make sure to call page_pool_release_page() when a page is + * "leaving" the page_pool. Or call page_pool_put_page() where + * appropiate. For maintaining correct accounting. * - * If no DMA mapping is done, then it can act as shim-layer that - * fall-through to alloc_page. As no state is kept on the page, the - * regular put_page() call is sufficient. + * API user must only call page_pool_put_page() once on a page, as it + * will either recycle the page, or in case of elevated refcnt, it + * will release the DMA mapping and in-flight state accounting. We + * hope to lift this requirement in the future. */ #ifndef _NET_PAGE_POOL_H #define _NET_PAGE_POOL_H @@ -66,9 +68,10 @@ struct page_pool_params { }; struct page_pool { - struct rcu_head rcu; struct page_pool_params p; + u32 pages_state_hold_cnt; + /* * Data structure for allocation side * @@ -96,6 +99,14 @@ struct page_pool { * TODO: Implement bulk return pages into this structure. */ struct ptr_ring ring; + + atomic_t pages_state_release_cnt; + + /* A page_pool is strictly tied to a single RX-queue being + * protected by NAPI, due to above pp_alloc_cache. This + * refcnt serves purpose is to simplify drivers error handling. + */ + refcount_t user_cnt; }; struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp); @@ -107,9 +118,36 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) return page_pool_alloc_pages(pool, gfp); } +/* get the stored dma direction. A driver might decide to treat this locally and + * avoid the extra cache line from page_pool to determine the direction + */ +static +inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool) +{ + return pool->p.dma_dir; +} + struct page_pool *page_pool_create(const struct page_pool_params *params); -void page_pool_destroy(struct page_pool *pool); +void __page_pool_free(struct page_pool *pool); +static inline void page_pool_free(struct page_pool *pool) +{ + /* 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_free(pool); +#endif +} + +/* Drivers use this instead of page_pool_free */ +static inline void page_pool_destroy(struct page_pool *pool) +{ + if (!pool) + return; + + page_pool_free(pool); +} /* Never call this directly, use helpers below */ void __page_pool_put_page(struct page_pool *pool, @@ -132,6 +170,43 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, __page_pool_put_page(pool, page, true); } +/* API user MUST have disconnected alloc-side (not allowed to call + * page_pool_alloc_pages()) before calling this. The free-side can + * still run concurrently, to handle in-flight packet-pages. + * + * A request to shutdown can fail (with false) if there are still + * in-flight packet-pages. + */ +bool __page_pool_request_shutdown(struct page_pool *pool); +static inline bool page_pool_request_shutdown(struct page_pool *pool) +{ + bool safe_to_remove = false; + +#ifdef CONFIG_PAGE_POOL + safe_to_remove = __page_pool_request_shutdown(pool); +#endif + return safe_to_remove; +} + +/* Disconnects a page (from a page_pool). API users can have a need + * to disconnect a page (from a page_pool), to allow it to be used as + * a regular page (that will eventually be returned to the normal + * page-allocator via put_page). + */ +void page_pool_unmap_page(struct page_pool *pool, struct page *page); +static inline void page_pool_release_page(struct page_pool *pool, + struct page *page) +{ +#ifdef CONFIG_PAGE_POOL + page_pool_unmap_page(pool, page); +#endif +} + +static inline dma_addr_t page_pool_get_dma_addr(struct page *page) +{ + return page->dma_addr; +} + static inline bool is_page_pool_compiled_in(void) { #ifdef CONFIG_PAGE_POOL @@ -141,4 +216,14 @@ static inline bool is_page_pool_compiled_in(void) #endif } +static inline void page_pool_get(struct page_pool *pool) +{ + refcount_inc(&pool->user_cnt); +} + +static inline bool page_pool_put(struct page_pool *pool) +{ + return refcount_dec_and_test(&pool->user_cnt); +} + #endif /* _NET_PAGE_POOL_H */ diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 514e3c80ecc1..b03d466182db 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -7,9 +7,10 @@ #include <net/sch_generic.h> #include <net/act_api.h> #include <net/flow_offload.h> +#include <net/net_namespace.h> /* TC action not accessible from user space */ -#define TC_ACT_REINSERT (TC_ACT_VALUE_MAX + 1) +#define TC_ACT_CONSUMED (TC_ACT_VALUE_MAX + 1) /* Basic packet classifier frontend definitions. */ @@ -25,14 +26,8 @@ struct tcf_walker { int register_tcf_proto_ops(struct tcf_proto_ops *ops); int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); -enum tcf_block_binder_type { - TCF_BLOCK_BINDER_TYPE_UNSPEC, - TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS, - TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS, -}; - struct tcf_block_ext_info { - enum tcf_block_binder_type binder_type; + enum flow_block_binder_type binder_type; tcf_chain_head_change_t *chain_head_change; void *chain_head_change_priv; u32 block_index; @@ -71,22 +66,6 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block) return block->q; } -void *tcf_block_cb_priv(struct tcf_block_cb *block_cb); -struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident); -void tcf_block_cb_incref(struct tcf_block_cb *block_cb); -unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb); -struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv, - struct netlink_ext_ack *extack); -int tcf_block_cb_register(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv, struct netlink_ext_ack *extack); -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, @@ -150,59 +129,6 @@ void tc_setup_cb_block_unregister(struct tcf_block *block, tc_setup_cb_t *cb, } static inline -void *tcf_block_cb_priv(struct tcf_block_cb *block_cb) -{ - return NULL; -} - -static inline -struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident) -{ - return NULL; -} - -static inline -void tcf_block_cb_incref(struct tcf_block_cb *block_cb) -{ -} - -static inline -unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb) -{ - return 0; -} - -static inline -struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv, - struct netlink_ext_ack *extack) -{ - return NULL; -} - -static inline -int tcf_block_cb_register(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv, struct netlink_ext_ack *extack) -{ - return 0; -} - -static inline -void __tcf_block_cb_unregister(struct tcf_block *block, - struct tcf_block_cb *block_cb) -{ -} - -static inline -void tcf_block_cb_unregister(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident) -{ -} - -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) { @@ -576,9 +502,6 @@ static inline int tcf_valid_offset(const struct sk_buff *skb, (ptr <= (ptr + len))); } -#ifdef CONFIG_NET_CLS_IND -#include <net/net_namespace.h> - static inline int tcf_change_indev(struct net *net, struct nlattr *indev_tlv, struct netlink_ext_ack *extack) @@ -605,7 +528,6 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) return false; return ifindex == skb->skb_iif; } -#endif /* CONFIG_NET_CLS_IND */ int tc_setup_flow_action(struct flow_action *flow_action, const struct tcf_exts *exts); @@ -613,25 +535,6 @@ int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, void *type_data, bool err_stop); unsigned int tcf_exts_num_actions(struct tcf_exts *exts); -enum tc_block_command { - TC_BLOCK_BIND, - TC_BLOCK_UNBIND, -}; - -struct tc_block_offload { - enum tc_block_command command; - enum tcf_block_binder_type binder_type; - struct tcf_block *block; - struct netlink_ext_ack *extack; -}; - -struct tc_cls_common_offload { - u32 chain_index; - __be16 protocol; - u32 prio; - struct netlink_ext_ack *extack; -}; - struct tc_cls_u32_knode { struct tcf_exts *exts; struct tcf_result *res; @@ -659,7 +562,7 @@ enum tc_clsu32_command { }; struct tc_cls_u32_offload { - struct tc_cls_common_offload common; + struct flow_cls_common_offload common; /* knode values */ enum tc_clsu32_command command; union { @@ -686,7 +589,7 @@ static inline bool tc_can_offload_extack(const struct net_device *dev, static inline bool tc_cls_can_offload_and_chain0(const struct net_device *dev, - struct tc_cls_common_offload *common) + struct flow_cls_common_offload *common) { if (!tc_can_offload_extack(dev, common->extack)) return false; @@ -728,7 +631,7 @@ static inline bool tc_in_hw(u32 flags) } static inline void -tc_cls_common_offload_init(struct tc_cls_common_offload *cls_common, +tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common, const struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { @@ -739,29 +642,6 @@ tc_cls_common_offload_init(struct tc_cls_common_offload *cls_common, cls_common->extack = extack; } -enum tc_fl_command { - TC_CLSFLOWER_REPLACE, - TC_CLSFLOWER_DESTROY, - TC_CLSFLOWER_STATS, - TC_CLSFLOWER_TMPLT_CREATE, - TC_CLSFLOWER_TMPLT_DESTROY, -}; - -struct tc_cls_flower_offload { - struct tc_cls_common_offload common; - enum tc_fl_command command; - unsigned long cookie; - struct flow_rule *rule; - struct flow_stats stats; - u32 classid; -}; - -static inline struct flow_rule * -tc_cls_flower_offload_flow_rule(struct tc_cls_flower_offload *tc_flow_cmd) -{ - return tc_flow_cmd->rule; -} - enum tc_matchall_command { TC_CLSMATCHALL_REPLACE, TC_CLSMATCHALL_DESTROY, @@ -769,7 +649,7 @@ enum tc_matchall_command { }; struct tc_cls_matchall_offload { - struct tc_cls_common_offload common; + struct flow_cls_common_offload common; enum tc_matchall_command command; struct flow_rule *rule; struct flow_stats stats; @@ -782,7 +662,7 @@ enum tc_clsbpf_command { }; struct tc_cls_bpf_offload { - struct tc_cls_common_offload common; + struct flow_cls_common_offload common; enum tc_clsbpf_command command; struct tcf_exts *exts; struct bpf_prog *prog; diff --git a/include/net/route.h b/include/net/route.h index 55ff71ffb796..630a0493f1f3 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -231,6 +231,10 @@ void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric); void rt_add_uncached_list(struct rtable *rt); void rt_del_uncached_list(struct rtable *rt); +int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, + u32 table_id, struct fib_info *fi, + int *fa_index, int fa_start); + static inline void ip_rt_put(struct rtable *rt) { /* dst_release() accepts a NULL parameter. diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 21f434f3ac9e..855167bbc372 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -279,7 +279,7 @@ struct tcf_result { }; const struct tcf_proto *goto_tp; - /* used by the TC_ACT_REINSERT action */ + /* used in the skb_tc_reinsert function */ struct { bool ingress; struct gnet_stats_queue *qstats; diff --git a/include/net/sctp/checksum.h b/include/net/sctp/checksum.h index 314699333bec..5a9bb09f32b6 100644 --- a/include/net/sctp/checksum.h +++ b/include/net/sctp/checksum.h @@ -43,19 +43,21 @@ static inline __wsum sctp_csum_combine(__wsum csum, __wsum csum2, (__force __u32)csum2, len); } +static const struct skb_checksum_ops sctp_csum_ops = { + .update = sctp_csum_update, + .combine = sctp_csum_combine, +}; + static inline __le32 sctp_compute_cksum(const struct sk_buff *skb, unsigned int offset) { struct sctphdr *sh = (struct sctphdr *)(skb->data + offset); - const struct skb_checksum_ops ops = { - .update = sctp_csum_update, - .combine = sctp_csum_combine, - }; __le32 old = sh->checksum; __wsum new; sh->checksum = 0; - new = ~__skb_checksum(skb, offset, skb->len - offset, ~(__wsum)0, &ops); + new = ~__skb_checksum(skb, offset, skb->len - offset, ~(__wsum)0, + &sctp_csum_ops); sh->checksum = old; return cpu_to_le32((__force __u32)new); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 0767701ef362..ba5c4f6eede5 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -219,7 +219,6 @@ struct sctp_sock { disable_fragments:1, v4mapped:1, frag_interleave:1, - strm_interleave:1, recvrcvinfo:1, recvnxtinfo:1, data_ready_signalled:1; @@ -1324,6 +1323,7 @@ struct sctp_endpoint { struct list_head endpoint_shared_keys; __u16 active_key_id; __u8 auth_enable:1, + intl_enable:1, prsctp_enable:1, reconf_enable:1; @@ -1679,28 +1679,30 @@ struct sctp_association { __be16 addip_disabled_mask; /* These are capabilities which our peer advertised. */ - __u8 ecn_capable:1, /* Can peer do ECN? */ + __u16 ecn_capable:1, /* Can peer do ECN? */ ipv4_address:1, /* Peer understands IPv4 addresses? */ ipv6_address:1, /* Peer understands IPv6 addresses? */ hostname_address:1, /* Peer understands DNS addresses? */ asconf_capable:1, /* Does peer support ADDIP? */ prsctp_capable:1, /* Can peer do PR-SCTP? */ reconf_capable:1, /* Can peer do RE-CONFIG? */ - auth_capable:1; /* Is peer doing SCTP-AUTH? */ - - /* sack_needed : This flag indicates if the next received - * : packet is to be responded to with a - * : SACK. This is initialized to 0. When a packet - * : is received sack_cnt is incremented. If this value - * : reaches 2 or more, a SACK is sent and the - * : value is reset to 0. Note: This is used only - * : when no DATA chunks are received out of - * : order. When DATA chunks are out of order, - * : SACK's are not delayed (see Section 6). - */ - __u8 sack_needed:1, /* Do we need to sack the peer? */ + intl_capable:1, /* Can peer do INTERLEAVE */ + auth_capable:1, /* Is peer doing SCTP-AUTH? */ + /* sack_needed: + * This flag indicates if the next received + * packet is to be responded to with a + * SACK. This is initialized to 0. When a packet + * is received sack_cnt is incremented. If this value + * reaches 2 or more, a SACK is sent and the + * value is reset to 0. Note: This is used only + * when no DATA chunks are received out of + * order. When DATA chunks are out of order, + * SACK's are not delayed (see Section 6). + */ + sack_needed:1, /* Do we need to sack the peer? */ sack_generation:1, zero_window_announced:1; + __u32 sack_cnt; __u32 adaptation_ind; /* Adaptation Code point. */ @@ -2049,10 +2051,7 @@ struct sctp_association { __u8 need_ecne:1, /* Need to send an ECNE Chunk? */ temp:1, /* Is it a temporary association? */ - force_delay:1, - intl_enable:1, - prsctp_enable:1, - reconf_enable:1; + force_delay:1; __u8 strreset_enable; __u8 strreset_outstanding; /* request param count on the fly */ diff --git a/include/net/sock.h b/include/net/sock.h index 6cbc16136357..228db3998e46 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1822,7 +1822,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) { WARN_ON(parent->sk); write_lock_bh(&sk->sk_callback_lock); - rcu_assign_pointer(sk->sk_wq, parent->wq); + rcu_assign_pointer(sk->sk_wq, &parent->wq); parent->sk = sk; sk_set_socket(sk, parent); sk->sk_uid = SOCK_INODE(parent)->i_uid; @@ -2100,7 +2100,7 @@ static inline void sock_poll_wait(struct file *filp, struct socket *sock, poll_table *p) { if (!poll_does_not_wait(p)) { - poll_wait(filp, &sock->wq->wait, p); + poll_wait(filp, &sock->wq.wait, p); /* We need to be sure we are in sync with the * socket flags modification. * diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 8a5f70c7cdf2..d9112de85261 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -35,6 +35,8 @@ extern struct sock *reuseport_select_sock(struct sock *sk, struct sk_buff *skb, int hdr_len); extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog); +extern int reuseport_detach_prog(struct sock *sk); + int reuseport_get_id(struct sock_reuseport *reuse); #endif /* _SOCK_REUSEPORT_H */ diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h new file mode 100644 index 000000000000..bdc20ab3b88d --- /dev/null +++ b/include/net/tc_act/tc_ct.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NET_TC_CT_H +#define __NET_TC_CT_H + +#include <net/act_api.h> +#include <uapi/linux/tc_act/tc_ct.h> + +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_conntrack_labels.h> + +struct tcf_ct_params { + struct nf_conn *tmpl; + u16 zone; + + u32 mark; + u32 mark_mask; + + u32 labels[NF_CT_LABELS_MAX_SIZE / sizeof(u32)]; + u32 labels_mask[NF_CT_LABELS_MAX_SIZE / sizeof(u32)]; + + struct nf_nat_range2 range; + bool ipv4_range; + + u16 ct_action; + + struct rcu_head rcu; +}; + +struct tcf_ct { + struct tc_action common; + struct tcf_ct_params __rcu *params; +}; + +#define to_ct(a) ((struct tcf_ct *)a) +#define to_ct_params(a) ((struct tcf_ct_params *) \ + rtnl_dereference((to_ct(a)->params))) + +static inline uint16_t tcf_ct_zone(const struct tc_action *a) +{ + return to_ct_params(a)->zone; +} + +static inline int tcf_ct_action(const struct tc_action *a) +{ + return to_ct_params(a)->ct_action; +} + +#else +static inline uint16_t tcf_ct_zone(const struct tc_action *a) { return 0; } +static inline int tcf_ct_action(const struct tc_action *a) { return 0; } +#endif /* CONFIG_NF_CONNTRACK */ + +static inline bool is_tcf_ct(const struct tc_action *a) +{ +#if defined(CONFIG_NET_CLS_ACT) && IS_ENABLED(CONFIG_NF_CONNTRACK) + if (a->ops && a->ops->id == TCA_ID_CT) + return true; +#endif + return false; +} + +#endif /* __NET_TC_CT_H */ diff --git a/include/net/tc_act/tc_ctinfo.h b/include/net/tc_act/tc_ctinfo.h new file mode 100644 index 000000000000..f071c1d70a25 --- /dev/null +++ b/include/net/tc_act/tc_ctinfo.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NET_TC_CTINFO_H +#define __NET_TC_CTINFO_H + +#include <net/act_api.h> + +struct tcf_ctinfo_params { + struct rcu_head rcu; + struct net *net; + u32 dscpmask; + u32 dscpstatemask; + u32 cpmarkmask; + u16 zone; + u8 mode; + u8 dscpmaskshift; +}; + +struct tcf_ctinfo { + struct tc_action common; + struct tcf_ctinfo_params __rcu *params; + u64 stats_dscp_set; + u64 stats_dscp_error; + u64 stats_cpmark_set; +}; + +enum { + CTINFO_MODE_DSCP = BIT(0), + CTINFO_MODE_CPMARK = BIT(1) +}; + +#define to_ctinfo(a) ((struct tcf_ctinfo *)a) + +#endif /* __NET_TC_CTINFO_H */ diff --git a/include/net/tc_act/tc_mpls.h b/include/net/tc_act/tc_mpls.h new file mode 100644 index 000000000000..4bc3d9250ef0 --- /dev/null +++ b/include/net/tc_act/tc_mpls.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (C) 2019 Netronome Systems, Inc. */ + +#ifndef __NET_TC_MPLS_H +#define __NET_TC_MPLS_H + +#include <linux/tc_act/tc_mpls.h> +#include <net/act_api.h> + +struct tcf_mpls_params { + int tcfm_action; + u32 tcfm_label; + u8 tcfm_tc; + u8 tcfm_ttl; + u8 tcfm_bos; + __be16 tcfm_proto; + struct rcu_head rcu; +}; + +#define ACT_MPLS_TC_NOT_SET 0xff +#define ACT_MPLS_BOS_NOT_SET 0xff +#define ACT_MPLS_LABEL_NOT_SET 0xffffffff + +struct tcf_mpls { + struct tc_action common; + struct tcf_mpls_params __rcu *mpls_p; +}; +#define to_mpls(a) ((struct tcf_mpls *)a) + +#endif /* __NET_TC_MPLS_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 582c0caa9811..cca3c59b98bf 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -43,6 +43,7 @@ #include <linux/seq_file.h> #include <linux/memcontrol.h> #include <linux/bpf-cgroup.h> +#include <linux/siphash.h> extern struct inet_hashinfo tcp_hashinfo; @@ -1612,7 +1613,7 @@ void tcp_free_fastopen_req(struct tcp_sock *tp); void tcp_fastopen_destroy_cipher(struct sock *sk); void tcp_fastopen_ctx_destroy(struct net *net); int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, - void *key, unsigned int len); + void *primary_key, void *backup_key); void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, @@ -1622,13 +1623,16 @@ void tcp_fastopen_init_key_once(struct net *net); bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); bool tcp_fastopen_defer_connect(struct sock *sk, int *err); -#define TCP_FASTOPEN_KEY_LENGTH 16 +#define TCP_FASTOPEN_KEY_LENGTH sizeof(siphash_key_t) +#define TCP_FASTOPEN_KEY_MAX 2 +#define TCP_FASTOPEN_KEY_BUF_LENGTH \ + (TCP_FASTOPEN_KEY_LENGTH * TCP_FASTOPEN_KEY_MAX) /* Fastopen key context */ struct tcp_fastopen_context { - struct crypto_cipher *tfm; - __u8 key[TCP_FASTOPEN_KEY_LENGTH]; - struct rcu_head rcu; + siphash_key_t key[TCP_FASTOPEN_KEY_MAX]; + int num; + struct rcu_head rcu; }; extern unsigned int sysctl_tcp_fastopen_blackhole_timeout; @@ -1637,6 +1641,35 @@ bool tcp_fastopen_active_should_disable(struct sock *sk); void tcp_fastopen_active_disable_ofo_check(struct sock *sk); void tcp_fastopen_active_detect_blackhole(struct sock *sk, bool expired); +/* Caller needs to wrap with rcu_read_(un)lock() */ +static inline +struct tcp_fastopen_context *tcp_fastopen_get_ctx(const struct sock *sk) +{ + struct tcp_fastopen_context *ctx; + + ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx); + if (!ctx) + ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx); + return ctx; +} + +static inline +bool tcp_fastopen_cookie_match(const struct tcp_fastopen_cookie *foc, + const struct tcp_fastopen_cookie *orig) +{ + if (orig->len == TCP_FASTOPEN_COOKIE_SIZE && + orig->len == foc->len && + !memcmp(orig->val, foc->val, foc->len)) + return true; + return false; +} + +static inline +int tcp_fastopen_context_len(const struct tcp_fastopen_context *ctx) +{ + return ctx->num; +} + /* Latencies incurred by various limits for a sender. They are * chronograph-like stats that are mutually exclusive. */ @@ -2188,6 +2221,12 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1); } +static inline void tcp_bpf_rtt(struct sock *sk) +{ + if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG)) + tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL); +} + #if IS_ENABLED(CONFIG_SMC) extern struct static_key_false tcp_have_smc; #endif @@ -2199,4 +2238,26 @@ void clean_acked_data_disable(struct inet_connection_sock *icsk); void clean_acked_data_flush(void); #endif +DECLARE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); +static inline void tcp_add_tx_delay(struct sk_buff *skb, + const struct tcp_sock *tp) +{ + if (static_branch_unlikely(&tcp_tx_delay_enabled)) + skb->skb_mstamp_ns += (u64)tp->tcp_tx_delay * NSEC_PER_USEC; +} + +/* Compute Earliest Departure Time for some control packets + * like ACK or RST for TIME_WAIT or non ESTABLISHED sockets. + */ +static inline u64 tcp_transmit_time(const struct sock *sk) +{ + if (static_branch_unlikely(&tcp_tx_delay_enabled)) { + u32 delay = (sk->sk_state == TCP_TIME_WAIT) ? + tcp_twsk(sk)->tw_tx_delay : tcp_sk(sk)->tcp_tx_delay; + + return tcp_clock_ns() + (u64)delay * NSEC_PER_USEC; + } + return 0; +} + #endif /* _TCP_H */ diff --git a/include/net/tls.h b/include/net/tls.h index 53d96bca220d..584609174fe0 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -40,6 +40,7 @@ #include <linux/socket.h> #include <linux/tcp.h> #include <linux/skmsg.h> +#include <linux/netdevice.h> #include <net/tcp.h> #include <net/strparser.h> @@ -61,6 +62,7 @@ #define TLS_DEVICE_NAME_MAX 32 #define MAX_IV_SIZE 16 +#define TLS_MAX_REC_SEQ_SIZE 8 /* For AES-CCM, the full 16-bytes of IV is made of '4' fields of given sizes. * @@ -197,20 +199,24 @@ struct tls_offload_context_tx { struct scatterlist sg_tx_data[MAX_SKB_FRAGS]; void (*sk_destruct)(struct sock *sk); - u8 driver_state[]; + u8 driver_state[] __aligned(8); /* The TLS layer reserves room for driver specific state * Currently the belief is that there is not enough * driver specific state to justify another layer of indirection */ -#define TLS_DRIVER_STATE_SIZE (max_t(size_t, 8, sizeof(void *))) +#define TLS_DRIVER_STATE_SIZE_TX 16 }; #define TLS_OFFLOAD_CONTEXT_SIZE_TX \ - (ALIGN(sizeof(struct tls_offload_context_tx), sizeof(void *)) + \ - TLS_DRIVER_STATE_SIZE) + (sizeof(struct tls_offload_context_tx) + TLS_DRIVER_STATE_SIZE_TX) enum tls_context_flags { TLS_RX_SYNC_RUNNING = 0, + /* Unlike RX where resync is driven entirely by the core in TX only + * the driver knows when things went out of sync, so we need the flag + * to be atomic. + */ + TLS_TX_SYNC_SCHED = 1, }; struct cipher_context { @@ -240,34 +246,32 @@ struct tls_prot_info { }; struct tls_context { + /* read-only cache line */ struct tls_prot_info prot_info; - union tls_crypto_context crypto_send; - union tls_crypto_context crypto_recv; + u8 tx_conf:3; + u8 rx_conf:3; - struct list_head list; - struct net_device *netdev; - refcount_t refcount; + int (*push_pending_record)(struct sock *sk, int flags); + void (*sk_write_space)(struct sock *sk); void *priv_ctx_tx; void *priv_ctx_rx; - u8 tx_conf:3; - u8 rx_conf:3; + struct net_device *netdev; + /* rw cache line */ struct cipher_context tx; struct cipher_context rx; struct scatterlist *partially_sent_record; u16 partially_sent_offset; - unsigned long flags; bool in_tcp_sendpages; bool pending_open_record_frags; + unsigned long flags; - int (*push_pending_record)(struct sock *sk, int flags); - - void (*sk_write_space)(struct sock *sk); + /* cache cold stuff */ void (*sk_destruct)(struct sock *sk); void (*sk_proto_close)(struct sock *sk, long timeout); @@ -279,6 +283,12 @@ struct tls_context { int __user *optlen); int (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); + + union tls_crypto_context crypto_send; + union tls_crypto_context crypto_recv; + + struct list_head list; + refcount_t refcount; }; enum tls_offload_ctx_dir { @@ -294,25 +304,50 @@ struct tlsdev_ops { void (*tls_dev_del)(struct net_device *netdev, struct tls_context *ctx, enum tls_offload_ctx_dir direction); - void (*tls_dev_resync_rx)(struct net_device *netdev, - struct sock *sk, u32 seq, u64 rcd_sn); + int (*tls_dev_resync)(struct net_device *netdev, + struct sock *sk, u32 seq, u8 *rcd_sn, + enum tls_offload_ctx_dir direction); }; +enum tls_offload_sync_type { + TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ = 0, + TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT = 1, +}; + +#define TLS_DEVICE_RESYNC_NH_START_IVAL 2 +#define TLS_DEVICE_RESYNC_NH_MAX_IVAL 128 + struct tls_offload_context_rx { /* sw must be the first member of tls_offload_context_rx */ struct tls_sw_context_rx sw; - atomic64_t resync_req; - u8 driver_state[]; + enum tls_offload_sync_type resync_type; + /* this member is set regardless of resync_type, to avoid branches */ + u8 resync_nh_reset:1; + /* CORE_NEXT_HINT-only member, but use the hole here */ + u8 resync_nh_do_now:1; + union { + /* TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ */ + struct { + atomic64_t resync_req; + }; + /* TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT */ + struct { + u32 decrypted_failed; + u32 decrypted_tgt; + } resync_nh; + }; + u8 driver_state[] __aligned(8); /* The TLS layer reserves room for driver specific state * Currently the belief is that there is not enough * driver specific state to justify another layer of indirection */ +#define TLS_DRIVER_STATE_SIZE_RX 8 }; #define TLS_OFFLOAD_CONTEXT_SIZE_RX \ - (ALIGN(sizeof(struct tls_offload_context_rx), sizeof(void *)) + \ - TLS_DRIVER_STATE_SIZE) + (sizeof(struct tls_offload_context_rx) + TLS_DRIVER_STATE_SIZE_RX) +void tls_ctx_free(struct tls_context *ctx); int wait_on_pending_writer(struct sock *sk, long *timeo); int tls_sk_query(struct sock *sk, int optname, char __user *optval, int __user *optlen); @@ -431,19 +466,15 @@ static inline struct tls_context *tls_get_ctx(const struct sock *sk) } static inline void tls_advance_record_sn(struct sock *sk, - struct cipher_context *ctx, - int version) + struct tls_prot_info *prot, + struct cipher_context *ctx) { - struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_prot_info *prot = &tls_ctx->prot_info; - if (tls_bigint_increment(ctx->rec_seq, prot->rec_seq_size)) tls_err_abort(sk, EBADMSG); - if (version != TLS_1_3_VERSION) { + if (prot->version != TLS_1_3_VERSION) tls_bigint_increment(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, prot->iv_size); - } } static inline void tls_fill_prepend(struct tls_context *ctx, @@ -545,6 +576,23 @@ tls_offload_ctx_rx(const struct tls_context *tls_ctx) return (struct tls_offload_context_rx *)tls_ctx->priv_ctx_rx; } +#if IS_ENABLED(CONFIG_TLS_DEVICE) +static inline void *__tls_driver_ctx(struct tls_context *tls_ctx, + enum tls_offload_ctx_dir direction) +{ + if (direction == TLS_OFFLOAD_CTX_DIR_TX) + return tls_offload_ctx_tx(tls_ctx)->driver_state; + else + return tls_offload_ctx_rx(tls_ctx)->driver_state; +} + +static inline void * +tls_driver_ctx(const struct sock *sk, enum tls_offload_ctx_dir direction) +{ + return __tls_driver_ctx(tls_get_ctx(sk), direction); +} +#endif + /* The TLS context is valid until sk_destruct is called */ static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq) { @@ -554,6 +602,31 @@ static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq) atomic64_set(&rx_ctx->resync_req, ((u64)ntohl(seq) << 32) | 1); } +static inline void +tls_offload_rx_resync_set_type(struct sock *sk, enum tls_offload_sync_type type) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + + tls_offload_ctx_rx(tls_ctx)->resync_type = type; +} + +static inline void tls_offload_tx_resync_request(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + + WARN_ON(test_and_set_bit(TLS_TX_SYNC_SCHED, &tls_ctx->flags)); +} + +/* Driver's seq tracking has to be disabled until resync succeeded */ +static inline bool tls_offload_tx_resync_pending(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + bool ret; + + ret = test_bit(TLS_TX_SYNC_SCHED, &tls_ctx->flags); + smp_mb__after_atomic(); + return ret; +} int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, unsigned char *record_type); @@ -562,6 +635,7 @@ void tls_unregister_device(struct tls_device *device); int tls_device_decrypted(struct sock *sk, struct sk_buff *skb); int decrypt_skb(struct sock *sk, struct sk_buff *skb, struct scatterlist *sgout); +struct sk_buff *tls_encrypt_skb(struct sk_buff *skb); struct sk_buff *tls_validate_xmit_skb(struct sock *sk, struct net_device *dev, @@ -574,6 +648,6 @@ int tls_sw_fallback_init(struct sock *sk, int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx); void tls_device_offload_cleanup_rx(struct sock *sk); -void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn); +void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq); #endif /* _TLS_OFFLOAD_H */ diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 83b5999a2587..dc1583a1fb8a 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -242,7 +242,7 @@ struct vxlan_dev { struct vxlan_rdst default_dst; /* default destination */ struct timer_list age_timer; - spinlock_t hash_lock; + spinlock_t hash_lock[FDB_HASH_SIZE]; unsigned int addrcnt; struct gro_cells gro_cells; diff --git a/include/net/xdp.h b/include/net/xdp.h index 8e0deddef35c..40c6d3398458 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -129,6 +129,21 @@ 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); +/* When sending xdp_frame into the network stack, then there is no + * return point callback, which is needed to release e.g. DMA-mapping + * resources with page_pool. Thus, have explicit function to release + * frame resources. + */ +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; + + /* Curr only page_pool needs this */ + if (mem->type == MEM_TYPE_PAGE_POOL) + __xdp_release_frame(xdpf->data, mem); +} + int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); diff --git a/include/net/xdp_priv.h b/include/net/xdp_priv.h new file mode 100644 index 000000000000..6a8cba6ea79a --- /dev/null +++ b/include/net/xdp_priv.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_NET_XDP_PRIV_H__ +#define __LINUX_NET_XDP_PRIV_H__ + +#include <linux/rhashtable.h> + +/* Private to net/core/xdp.c, but used by trace/events/xdp.h */ +struct xdp_mem_allocator { + struct xdp_mem_info mem; + union { + void *allocator; + struct page_pool *page_pool; + struct zero_copy_allocator *zc_alloc; + }; + int disconnect_cnt; + unsigned long defer_start; + struct rhash_head node; + struct rcu_head rcu; + struct delayed_work defer_wq; + unsigned long defer_warn; +}; + +#endif /* __LINUX_NET_XDP_PRIV_H__ */ diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index d074b6d60f8a..69796d264f06 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -58,15 +58,22 @@ struct xdp_sock { struct xdp_umem *umem; struct list_head flush_node; u16 queue_id; - struct xsk_queue *tx ____cacheline_aligned_in_smp; - struct list_head list; bool zc; + enum { + XSK_READY = 0, + XSK_BOUND, + XSK_UNBOUND, + } state; /* Protects multiple processes in the control path */ struct mutex mutex; + struct xsk_queue *tx ____cacheline_aligned_in_smp; + struct list_head list; /* Mutual exclusion of NAPI TX thread and sendmsg error paths * in the SKB destructor callback. */ spinlock_t tx_completion_lock; + /* Protects generic receive. */ + spinlock_t rx_lock; u64 rx_dropped; }; @@ -77,10 +84,11 @@ int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); void xsk_flush(struct xdp_sock *xs); bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs); /* Used from netdev driver */ +bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt); u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr); void xsk_umem_discard_addr(struct xdp_umem *umem); void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); -bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len); +bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc); void xsk_umem_consume_tx_done(struct xdp_umem *umem); struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries); struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem, @@ -99,6 +107,16 @@ static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) } /* Reuse-queue aware version of FILL queue helpers */ +static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt) +{ + struct xdp_umem_fq_reuse *rq = umem->fq_reuse; + + if (rq->length >= cnt) + return true; + + return xsk_umem_has_addrs(umem, cnt - rq->length); +} + static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr) { struct xdp_umem_fq_reuse *rq = umem->fq_reuse; @@ -146,6 +164,11 @@ static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) return false; } +static inline bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt) +{ + return false; +} + static inline u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr) { return NULL; @@ -159,8 +182,8 @@ static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) { } -static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, - u32 *len) +static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, + struct xdp_desc *desc) { return false; } @@ -200,6 +223,11 @@ static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) return 0; } +static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt) +{ + return false; +} + static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr) { return NULL; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index a2907873ed56..b22db30c3d88 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -346,22 +346,19 @@ void km_state_expired(struct xfrm_state *x, int hard, u32 portid); int __xfrm_state_delete(struct xfrm_state *x); struct xfrm_state_afinfo { - unsigned int family; - unsigned int proto; - __be16 eth_proto; - struct module *owner; - const struct xfrm_type *type_map[IPPROTO_MAX]; - const struct xfrm_type_offload *type_offload_map[IPPROTO_MAX]; - - int (*init_flags)(struct xfrm_state *x); - void (*init_tempsel)(struct xfrm_selector *sel, - const struct flowi *fl); - void (*init_temprop)(struct xfrm_state *x, - const struct xfrm_tmpl *tmpl, - const xfrm_address_t *daddr, - const xfrm_address_t *saddr); - int (*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n); - int (*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n); + u8 family; + u8 proto; + + const struct xfrm_type_offload *type_offload_esp; + + const struct xfrm_type *type_esp; + const struct xfrm_type *type_ipip; + const struct xfrm_type *type_ipip6; + const struct xfrm_type *type_comp; + const struct xfrm_type *type_ah; + const struct xfrm_type *type_routing; + const struct xfrm_type *type_dstopts; + int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*output_finish)(struct sock *sk, struct sk_buff *skb); int (*extract_input)(struct xfrm_state *x, @@ -407,12 +404,10 @@ struct xfrm_type { int (*reject)(struct xfrm_state *, struct sk_buff *, const struct flowi *); int (*hdr_offset)(struct xfrm_state *, struct sk_buff *, u8 **); - /* Estimate maximal size of result of transformation of a dgram */ - u32 (*get_mtu)(struct xfrm_state *, int size); }; int xfrm_register_type(const struct xfrm_type *type, unsigned short family); -int xfrm_unregister_type(const struct xfrm_type *type, unsigned short family); +void xfrm_unregister_type(const struct xfrm_type *type, unsigned short family); struct xfrm_type_offload { char *description; @@ -424,7 +419,7 @@ struct xfrm_type_offload { }; int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family); -int xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family); +void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family); static inline int xfrm_af2proto(unsigned int family) { @@ -1508,21 +1503,19 @@ struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark, u8 proto, unsigned short family); #ifdef CONFIG_XFRM_SUB_POLICY -int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, - unsigned short family, struct net *net); -int xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, +void xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, unsigned short family); +void xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, + unsigned short family); #else -static inline int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, - int n, unsigned short family, struct net *net) +static inline void xfrm_tmpl_sort(struct xfrm_tmpl **d, struct xfrm_tmpl **s, + int n, unsigned short family) { - return -ENOSYS; } -static inline int xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, - int n, unsigned short family) +static inline void xfrm_state_sort(struct xfrm_state **d, struct xfrm_state **s, + int n, unsigned short family) { - return -ENOSYS; } #endif @@ -1551,7 +1544,7 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq); int xfrm_init_replay(struct xfrm_state *x); -int xfrm_state_mtu(struct xfrm_state *x, int mtu); +u32 xfrm_state_mtu(struct xfrm_state *x, int mtu); int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload); int xfrm_init_state(struct xfrm_state *x); int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); diff --git a/include/trace/events/neigh.h b/include/trace/events/neigh.h index 0bdb08557763..62bb17516713 100644 --- a/include/trace/events/neigh.h +++ b/include/trace/events/neigh.h @@ -20,6 +20,55 @@ { NUD_NOARP, "noarp" }, \ { NUD_PERMANENT, "permanent"}) +TRACE_EVENT(neigh_create, + + TP_PROTO(struct neigh_table *tbl, struct net_device *dev, + const void *pkey, const struct neighbour *n, + bool exempt_from_gc), + + TP_ARGS(tbl, dev, pkey, n, exempt_from_gc), + + TP_STRUCT__entry( + __field(u32, family) + __dynamic_array(char, dev, IFNAMSIZ ) + __field(int, entries) + __field(u8, created) + __field(u8, gc_exempt) + __array(u8, primary_key4, 4) + __array(u8, primary_key6, 16) + ), + + TP_fast_assign( + struct in6_addr *pin6; + __be32 *p32; + + __entry->family = tbl->family; + __assign_str(dev, (dev ? dev->name : "NULL")); + __entry->entries = atomic_read(&tbl->gc_entries); + __entry->created = n != NULL; + __entry->gc_exempt = exempt_from_gc; + pin6 = (struct in6_addr *)__entry->primary_key6; + p32 = (__be32 *)__entry->primary_key4; + + if (tbl->family == AF_INET) + *p32 = *(__be32 *)pkey; + else + *p32 = 0; + +#if IS_ENABLED(CONFIG_IPV6) + if (tbl->family == AF_INET6) { + pin6 = (struct in6_addr *)__entry->primary_key6; + *pin6 = *(struct in6_addr *)pkey; + } +#endif + ), + + TP_printk("family %d dev %s entries %d primary_key4 %pI4 primary_key6 %pI6c created %d gc_exempt %d", + __entry->family, __get_str(dev), __entry->entries, + __entry->primary_key4, __entry->primary_key6, + __entry->created, __entry->gc_exempt) +); + TRACE_EVENT(neigh_update, TP_PROTO(struct neighbour *n, const u8 *lladdr, u8 new, diff --git a/include/trace/events/page_pool.h b/include/trace/events/page_pool.h new file mode 100644 index 000000000000..47b5ee880aa9 --- /dev/null +++ b/include/trace/events/page_pool.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM page_pool + +#if !defined(_TRACE_PAGE_POOL_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_PAGE_POOL_H + +#include <linux/types.h> +#include <linux/tracepoint.h> + +#include <net/page_pool.h> + +TRACE_EVENT(page_pool_inflight, + + TP_PROTO(const struct page_pool *pool, + s32 inflight, u32 hold, u32 release), + + TP_ARGS(pool, inflight, hold, release), + + TP_STRUCT__entry( + __field(const struct page_pool *, pool) + __field(s32, inflight) + __field(u32, hold) + __field(u32, release) + ), + + TP_fast_assign( + __entry->pool = pool; + __entry->inflight = inflight; + __entry->hold = hold; + __entry->release = release; + ), + + TP_printk("page_pool=%p inflight=%d hold=%u release=%u", + __entry->pool, __entry->inflight, __entry->hold, __entry->release) +); + +TRACE_EVENT(page_pool_state_release, + + TP_PROTO(const struct page_pool *pool, + const struct page *page, u32 release), + + TP_ARGS(pool, page, release), + + TP_STRUCT__entry( + __field(const struct page_pool *, pool) + __field(const struct page *, page) + __field(u32, release) + ), + + TP_fast_assign( + __entry->pool = pool; + __entry->page = page; + __entry->release = release; + ), + + TP_printk("page_pool=%p page=%p release=%u", + __entry->pool, __entry->page, __entry->release) +); + +TRACE_EVENT(page_pool_state_hold, + + TP_PROTO(const struct page_pool *pool, + const struct page *page, u32 hold), + + TP_ARGS(pool, page, hold), + + TP_STRUCT__entry( + __field(const struct page_pool *, pool) + __field(const struct page *, page) + __field(u32, hold) + ), + + TP_fast_assign( + __entry->pool = pool; + __entry->page = page; + __entry->hold = hold; + ), + + TP_printk("page_pool=%p page=%p hold=%u", + __entry->pool, __entry->page, __entry->hold) +); + +#endif /* _TRACE_PAGE_POOL_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index d85816878a52..cc1d060cbf13 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -1379,7 +1379,7 @@ TRACE_EVENT(rxrpc_rx_eproto, ), TP_fast_assign( - __entry->call = call->debug_id; + __entry->call = call ? call->debug_id : 0; __entry->serial = serial; __entry->why = why; ), diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index e95cb86b65cf..68899fdc985b 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -50,6 +50,35 @@ TRACE_EVENT(xdp_exception, __entry->ifindex) ); +TRACE_EVENT(xdp_bulk_tx, + + TP_PROTO(const struct net_device *dev, + int sent, int drops, int err), + + TP_ARGS(dev, sent, drops, err), + + TP_STRUCT__entry( + __field(int, ifindex) + __field(u32, act) + __field(int, drops) + __field(int, sent) + __field(int, err) + ), + + TP_fast_assign( + __entry->ifindex = dev->ifindex; + __entry->act = XDP_TX; + __entry->drops = drops; + __entry->sent = sent; + __entry->err = err; + ), + + TP_printk("ifindex=%d action=%s sent=%d drops=%d err=%d", + __entry->ifindex, + __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), + __entry->sent, __entry->drops, __entry->err) +); + DECLARE_EVENT_CLASS(xdp_redirect_template, TP_PROTO(const struct net_device *dev, @@ -146,9 +175,8 @@ struct _bpf_dtab_netdev { #endif /* __DEVMAP_OBJ_TYPE */ #define devmap_ifindex(fwd, map) \ - (!fwd ? 0 : \ - ((map->map_type == BPF_MAP_TYPE_DEVMAP) ? \ - ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0)) + ((map->map_type == BPF_MAP_TYPE_DEVMAP) ? \ + ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0) #define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \ trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map), \ @@ -269,6 +297,121 @@ TRACE_EVENT(xdp_devmap_xmit, __entry->from_ifindex, __entry->to_ifindex, __entry->err) ); +/* Expect users already include <net/xdp.h>, but not xdp_priv.h */ +#include <net/xdp_priv.h> + +#define __MEM_TYPE_MAP(FN) \ + FN(PAGE_SHARED) \ + FN(PAGE_ORDER0) \ + FN(PAGE_POOL) \ + FN(ZERO_COPY) + +#define __MEM_TYPE_TP_FN(x) \ + TRACE_DEFINE_ENUM(MEM_TYPE_##x); +#define __MEM_TYPE_SYM_FN(x) \ + { MEM_TYPE_##x, #x }, +#define __MEM_TYPE_SYM_TAB \ + __MEM_TYPE_MAP(__MEM_TYPE_SYM_FN) { -1, 0 } +__MEM_TYPE_MAP(__MEM_TYPE_TP_FN) + +TRACE_EVENT(mem_disconnect, + + TP_PROTO(const struct xdp_mem_allocator *xa, + bool safe_to_remove, bool force), + + TP_ARGS(xa, safe_to_remove, force), + + TP_STRUCT__entry( + __field(const struct xdp_mem_allocator *, xa) + __field(u32, mem_id) + __field(u32, mem_type) + __field(const void *, allocator) + __field(bool, safe_to_remove) + __field(bool, force) + __field(int, disconnect_cnt) + ), + + TP_fast_assign( + __entry->xa = xa; + __entry->mem_id = xa->mem.id; + __entry->mem_type = xa->mem.type; + __entry->allocator = xa->allocator; + __entry->safe_to_remove = safe_to_remove; + __entry->force = force; + __entry->disconnect_cnt = xa->disconnect_cnt; + ), + + TP_printk("mem_id=%d mem_type=%s allocator=%p" + " safe_to_remove=%s force=%s disconnect_cnt=%d", + __entry->mem_id, + __print_symbolic(__entry->mem_type, __MEM_TYPE_SYM_TAB), + __entry->allocator, + __entry->safe_to_remove ? "true" : "false", + __entry->force ? "true" : "false", + __entry->disconnect_cnt + ) +); + +TRACE_EVENT(mem_connect, + + TP_PROTO(const struct xdp_mem_allocator *xa, + const struct xdp_rxq_info *rxq), + + TP_ARGS(xa, rxq), + + TP_STRUCT__entry( + __field(const struct xdp_mem_allocator *, xa) + __field(u32, mem_id) + __field(u32, mem_type) + __field(const void *, allocator) + __field(const struct xdp_rxq_info *, rxq) + __field(int, ifindex) + ), + + TP_fast_assign( + __entry->xa = xa; + __entry->mem_id = xa->mem.id; + __entry->mem_type = xa->mem.type; + __entry->allocator = xa->allocator; + __entry->rxq = rxq; + __entry->ifindex = rxq->dev->ifindex; + ), + + TP_printk("mem_id=%d mem_type=%s allocator=%p" + " ifindex=%d", + __entry->mem_id, + __print_symbolic(__entry->mem_type, __MEM_TYPE_SYM_TAB), + __entry->allocator, + __entry->ifindex + ) +); + +TRACE_EVENT(mem_return_failed, + + TP_PROTO(const struct xdp_mem_info *mem, + const struct page *page), + + TP_ARGS(mem, page), + + TP_STRUCT__entry( + __field(const struct page *, page) + __field(u32, mem_id) + __field(u32, mem_type) + ), + + TP_fast_assign( + __entry->page = page; + __entry->mem_id = mem->id; + __entry->mem_type = mem->type; + ), + + TP_printk("mem_id=%d mem_type=%s page=%p", + __entry->mem_id, + __print_symbolic(__entry->mem_type, __MEM_TYPE_SYM_TAB), + __entry->page + ) +); + #endif /* _TRACE_XDP_H */ #include <trace/define_trace.h> diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 8c1391c89171..77f7c1638eb1 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -117,6 +117,8 @@ #define SO_RCVTIMEO_NEW 66 #define SO_SNDTIMEO_NEW 67 +#define SO_DETACH_REUSEPORT_BPF 68 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h index 4ebc2135e950..2a15f01c2243 100644 --- a/include/uapi/linux/batadv_packet.h +++ b/include/uapi/linux/batadv_packet.h @@ -107,12 +107,20 @@ enum batadv_icmp_packettype { * @BATADV_MCAST_WANT_ALL_UNSNOOPABLES: we want all packets destined for * 224.0.0.0/24 or ff02::1 * @BATADV_MCAST_WANT_ALL_IPV4: we want all IPv4 multicast packets + * (both link-local and routable ones) * @BATADV_MCAST_WANT_ALL_IPV6: we want all IPv6 multicast packets + * (both link-local and routable ones) + * @BATADV_MCAST_WANT_NO_RTR4: we have no IPv4 multicast router and therefore + * only need routable IPv4 multicast packets we signed up for explicitly + * @BATADV_MCAST_WANT_NO_RTR6: we have no IPv6 multicast router and therefore + * only need routable IPv6 multicast packets we signed up for explicitly */ enum batadv_mcast_flags { BATADV_MCAST_WANT_ALL_UNSNOOPABLES = 1UL << 0, BATADV_MCAST_WANT_ALL_IPV4 = 1UL << 1, BATADV_MCAST_WANT_ALL_IPV6 = 1UL << 2, + BATADV_MCAST_WANT_NO_RTR4 = 1UL << 3, + BATADV_MCAST_WANT_NO_RTR6 = 1UL << 4, }; /* tt data subtypes */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 489e118b69d2..6f68438aa4ed 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -170,6 +170,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + BPF_PROG_TYPE_CGROUP_SOCKOPT, }; enum bpf_attach_type { @@ -194,6 +195,8 @@ enum bpf_attach_type { BPF_CGROUP_SYSCTL, BPF_CGROUP_UDP4_RECVMSG, BPF_CGROUP_UDP6_RECVMSG, + BPF_CGROUP_GETSOCKOPT, + BPF_CGROUP_SETSOCKOPT, __MAX_BPF_ATTACH_TYPE }; @@ -262,6 +265,24 @@ enum bpf_attach_type { */ #define BPF_F_ANY_ALIGNMENT (1U << 1) +/* BPF_F_TEST_RND_HI32 is used in BPF_PROG_LOAD command for testing purpose. + * Verifier does sub-register def/use analysis and identifies instructions whose + * def only matters for low 32-bit, high 32-bit is never referenced later + * through implicit zero extension. Therefore verifier notifies JIT back-ends + * that it is safe to ignore clearing high 32-bit for these instructions. This + * saves some back-ends a lot of code-gen. However such optimization is not + * necessary on some arches, for example x86_64, arm64 etc, whose JIT back-ends + * hence hasn't used verifier's analysis result. But, we really want to have a + * way to be able to verify the correctness of the described optimization on + * x86_64 on which testsuites are frequently exercised. + * + * So, this flag is introduced. Once it is set, verifier will randomize high + * 32-bit for those instructions who has been identified as safe to ignore them. + * Then, if verifier is not doing correct analysis, such randomization will + * regress tests to expose bugs. + */ +#define BPF_F_TEST_RND_HI32 (1U << 2) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * two extensions: * @@ -1550,8 +1571,11 @@ union bpf_attr { * but this is only implemented for native XDP (with driver * support) as of this writing). * - * All values for *flags* are reserved for future usage, and must - * be left at zero. + * The lower two bits of *flags* are used as the return code if + * the map lookup fails. This is so that the return value can be + * one of the XDP program return codes up to XDP_TX, as chosen by + * the caller. Any higher bits in the *flags* argument must be + * unset. * * When used to redirect packets to net devices, this helper * provides a high performance increase over **bpf_redirect**\ (). @@ -1746,6 +1770,7 @@ union bpf_attr { * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) + * * **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT) * * Therefore, this function can be used to clear a callback flag by * setting the appropriate bit to zero. e.g. to disable the RTO @@ -2674,6 +2699,20 @@ union bpf_attr { * 0 on success. * * **-ENOENT** if the bpf-local-storage cannot be found. + * + * int bpf_send_signal(u32 sig) + * Description + * Send signal *sig* to the current task. + * Return + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2784,7 +2823,8 @@ union bpf_attr { FN(strtol), \ FN(strtoul), \ FN(sk_storage_get), \ - FN(sk_storage_delete), + FN(sk_storage_delete), \ + FN(send_signal), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3033,6 +3073,12 @@ struct bpf_tcp_sock { * sum(delta(snd_una)), or how many bytes * were acked. */ + __u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups + * total number of DSACK blocks received + */ + __u32 delivered; /* Total data packets delivered incl. rexmits */ + __u32 delivered_ce; /* Like the above but only ECE marked packets */ + __u32 icsk_retransmits; /* Number of unrecovered [RTO] timeouts */ }; struct bpf_sock_tuple { @@ -3052,6 +3098,10 @@ struct bpf_sock_tuple { }; }; +struct bpf_xdp_sock { + __u32 queue_id; +}; + #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. @@ -3143,6 +3193,7 @@ struct bpf_prog_info { char name[BPF_OBJ_NAME_LEN]; __u32 ifindex; __u32 gpl_compatible:1; + __u32 :31; /* alignment pad */ __u64 netns_dev; __u64 netns_ino; __u32 nr_jited_ksyms; @@ -3197,7 +3248,7 @@ struct bpf_sock_addr { __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order. */ - __u32 user_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. + __u32 user_ip6[4]; /* Allows 1,2,4-byte read and 4,8-byte write. * Stored in network byte order. */ __u32 user_port; /* Allows 4-byte read and write. @@ -3206,12 +3257,13 @@ struct bpf_sock_addr { __u32 family; /* Allows 4-byte read, but no write */ __u32 type; /* Allows 4-byte read, but no write */ __u32 protocol; /* Allows 4-byte read, but no write */ - __u32 msg_src_ip4; /* Allows 1,2,4-byte read an 4-byte write. + __u32 msg_src_ip4; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order. */ - __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. + __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read and 4,8-byte write. * Stored in network byte order. */ + __bpf_md_ptr(struct bpf_sock *, sk); }; /* User bpf_sock_ops struct to access socket values and specify request ops @@ -3263,13 +3315,15 @@ struct bpf_sock_ops { __u32 sk_txhash; __u64 bytes_received; __u64 bytes_acked; + __bpf_md_ptr(struct bpf_sock *, sk); }; /* Definitions for bpf_sock_ops_cb_flags */ #define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0) #define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1) #define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2) -#define BPF_SOCK_OPS_ALL_CB_FLAGS 0x7 /* Mask of all currently +#define BPF_SOCK_OPS_RTT_CB_FLAG (1<<3) +#define BPF_SOCK_OPS_ALL_CB_FLAGS 0xF /* Mask of all currently * supported cb flags */ @@ -3324,6 +3378,8 @@ enum { BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after * socket transition to LISTEN state. */ + BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect @@ -3502,4 +3558,15 @@ struct bpf_sysctl { */ }; +struct bpf_sockopt { + __bpf_md_ptr(struct bpf_sock *, sk); + __bpf_md_ptr(void *, optval); + __bpf_md_ptr(void *, optval_end); + + __s32 level; + __s32 optname; + __s32 optlen; + __s32 retval; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 5bb4ea67d84f..ffc993256527 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -104,6 +104,8 @@ enum devlink_command { DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, DEVLINK_CMD_FLASH_UPDATE, + DEVLINK_CMD_FLASH_UPDATE_END, /* notification only */ + DEVLINK_CMD_FLASH_UPDATE_STATUS, /* notification only */ /* add new commands above here */ __DEVLINK_CMD_MAX, @@ -167,6 +169,14 @@ enum devlink_port_flavour { DEVLINK_PORT_FLAVOUR_DSA, /* Distributed switch architecture * interconnect port. */ + DEVLINK_PORT_FLAVOUR_PCI_PF, /* Represents eswitch port for + * the PCI PF. It is an internal + * port that faces the PCI PF. + */ + DEVLINK_PORT_FLAVOUR_PCI_VF, /* Represents eswitch port + * for the PCI VF. It is an internal + * port that faces the PCI VF. + */ }; enum devlink_param_cmode { @@ -331,6 +341,12 @@ enum devlink_attr { DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME, /* string */ DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, /* string */ + DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG, /* string */ + DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, /* u64 */ + DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, /* u64 */ + + DEVLINK_ATTR_PORT_PCI_PF_NUMBER, /* u16 */ + DEVLINK_ATTR_PORT_PCI_VF_NUMBER, /* u16 */ /* add new attributes above here, update the policy in devlink.c */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 3534ce157ae9..dd06302aa93e 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1483,6 +1483,8 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT = 64, ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT = 65, ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT = 66, + ETHTOOL_LINK_MODE_100baseT1_Full_BIT = 67, + ETHTOOL_LINK_MODE_1000baseT1_Full_BIT = 68, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 3158ba672b72..f6ceb2e63d1e 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -91,6 +91,7 @@ #define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */ #define ETH_P_PREAUTH 0x88C7 /* 802.11 Preauthentication */ #define ETH_P_TIPC 0x88CA /* TIPC */ +#define ETH_P_LLDP 0x88CC /* Link Layer Discovery Protocol */ #define ETH_P_MACSEC 0x88E5 /* 802.1ae MACsec */ #define ETH_P_8021AH 0x88E7 /* 802.1ah Backbone Service Tag */ #define ETH_P_MVRP 0x88F5 /* 802.1Q MVRP */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 5b225ff63b48..4a8c02cafa9a 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -636,6 +636,7 @@ enum { IFLA_BOND_AD_USER_PORT_KEY, IFLA_BOND_AD_ACTOR_SYSTEM, IFLA_BOND_TLB_DYNAMIC_LB, + IFLA_BOND_PEER_NOTIF_DELAY, __IFLA_BOND_MAX, }; @@ -694,6 +695,7 @@ enum { IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */ IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */ IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */ + IFLA_VF_BROADCAST, /* VF broadcast */ __IFLA_VF_MAX, }; @@ -704,6 +706,10 @@ struct ifla_vf_mac { __u8 mac[32]; /* MAX_ADDR_LEN */ }; +struct ifla_vf_broadcast { + __u8 broadcast[32]; +}; + struct ifla_vf_vlan { __u32 vf; __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index 467b654bd4c7..3d884d68eb30 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -123,7 +123,7 @@ struct tpacket_auxdata { /* Rx and Tx ring - header status */ #define TP_STATUS_TS_SOFTWARE (1 << 29) #define TP_STATUS_TS_SYS_HARDWARE (1 << 30) /* deprecated, never set */ -#define TP_STATUS_TS_RAW_HARDWARE (1 << 31) +#define TP_STATUS_TS_RAW_HARDWARE (1U << 31) /* Rx ring - feature request bits */ #define TP_FT_REQ_FILL_RXHASH 0x1 diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h index caed8b1614ff..faaa5ca2a117 100644 --- a/include/uapi/linux/if_xdp.h +++ b/include/uapi/linux/if_xdp.h @@ -46,6 +46,7 @@ struct xdp_mmap_offsets { #define XDP_UMEM_FILL_RING 5 #define XDP_UMEM_COMPLETION_RING 6 #define XDP_STATISTICS 7 +#define XDP_OPTIONS 8 struct xdp_umem_reg { __u64 addr; /* Start of packet data area */ @@ -60,6 +61,13 @@ struct xdp_statistics { __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */ }; +struct xdp_options { + __u32 flags; +}; + +/* Flags for the flags field of struct xdp_options */ +#define XDP_OPTIONS_ZEROCOPY (1 << 0) + /* Pgoff for mmaping the rings */ #define XDP_PGOFF_RX_RING 0 #define XDP_PGOFF_TX_RING 0x80000000 diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h index e34f436fc79d..4102ddcb4e14 100644 --- a/include/uapi/linux/ip_vs.h +++ b/include/uapi/linux/ip_vs.h @@ -128,9 +128,15 @@ enum { IP_VS_CONN_F_TUNNEL_TYPE_IPIP = 0, /* IPIP */ IP_VS_CONN_F_TUNNEL_TYPE_GUE, /* GUE */ + IP_VS_CONN_F_TUNNEL_TYPE_GRE, /* GRE */ IP_VS_CONN_F_TUNNEL_TYPE_MAX, }; +/* Tunnel encapsulation flags */ +#define IP_VS_TUNNEL_ENCAP_FLAG_NOCSUM (0) +#define IP_VS_TUNNEL_ENCAP_FLAG_CSUM (1 << 0) +#define IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM (1 << 1) + /* * The struct ip_vs_service_user and struct ip_vs_dest_user are * used to set IPVS rules through setsockopt. @@ -403,6 +409,8 @@ enum { IPVS_DEST_ATTR_TUN_PORT, /* tunnel port */ + IPVS_DEST_ATTR_TUN_FLAGS, /* tunnel flags */ + __IPVS_DEST_ATTR_MAX, }; diff --git a/include/uapi/linux/isdn.h b/include/uapi/linux/isdn.h deleted file mode 100644 index f371fd52ed75..000000000000 --- a/include/uapi/linux/isdn.h +++ /dev/null @@ -1,144 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* $Id: isdn.h,v 1.125.2.3 2004/02/10 01:07:14 keil Exp $ - * - * Main header for the Linux ISDN subsystem (linklevel). - * - * Copyright 1994,95,96 by Fritz Elfert (fritz@isdn4linux.de) - * Copyright 1995,96 by Thinking Objects Software GmbH Wuerzburg - * Copyright 1995,96 by Michael Hipp (Michael.Hipp@student.uni-tuebingen.de) - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ - -#ifndef _UAPI__ISDN_H__ -#define _UAPI__ISDN_H__ - -#include <linux/ioctl.h> -#include <linux/tty.h> - -#define ISDN_MAX_DRIVERS 32 -#define ISDN_MAX_CHANNELS 64 - -/* New ioctl-codes */ -#define IIOCNETAIF _IO('I',1) -#define IIOCNETDIF _IO('I',2) -#define IIOCNETSCF _IO('I',3) -#define IIOCNETGCF _IO('I',4) -#define IIOCNETANM _IO('I',5) -#define IIOCNETDNM _IO('I',6) -#define IIOCNETGNM _IO('I',7) -#define IIOCGETSET _IO('I',8) /* no longer supported */ -#define IIOCSETSET _IO('I',9) /* no longer supported */ -#define IIOCSETVER _IO('I',10) -#define IIOCNETHUP _IO('I',11) -#define IIOCSETGST _IO('I',12) -#define IIOCSETBRJ _IO('I',13) -#define IIOCSIGPRF _IO('I',14) -#define IIOCGETPRF _IO('I',15) -#define IIOCSETPRF _IO('I',16) -#define IIOCGETMAP _IO('I',17) -#define IIOCSETMAP _IO('I',18) -#define IIOCNETASL _IO('I',19) -#define IIOCNETDIL _IO('I',20) -#define IIOCGETCPS _IO('I',21) -#define IIOCGETDVR _IO('I',22) -#define IIOCNETLCR _IO('I',23) /* dwabc ioctl for LCR from isdnlog */ -#define IIOCNETDWRSET _IO('I',24) /* dwabc ioctl to reset abc-values to default on a net-interface */ - -#define IIOCNETALN _IO('I',32) -#define IIOCNETDLN _IO('I',33) - -#define IIOCNETGPN _IO('I',34) - -#define IIOCDBGVAR _IO('I',127) - -#define IIOCDRVCTL _IO('I',128) - -/* cisco hdlck device private ioctls */ -#define SIOCGKEEPPERIOD (SIOCDEVPRIVATE + 0) -#define SIOCSKEEPPERIOD (SIOCDEVPRIVATE + 1) -#define SIOCGDEBSERINT (SIOCDEVPRIVATE + 2) -#define SIOCSDEBSERINT (SIOCDEVPRIVATE + 3) - -/* Packet encapsulations for net-interfaces */ -#define ISDN_NET_ENCAP_ETHER 0 -#define ISDN_NET_ENCAP_RAWIP 1 -#define ISDN_NET_ENCAP_IPTYP 2 -#define ISDN_NET_ENCAP_CISCOHDLC 3 /* Without SLARP and keepalive */ -#define ISDN_NET_ENCAP_SYNCPPP 4 -#define ISDN_NET_ENCAP_UIHDLC 5 -#define ISDN_NET_ENCAP_CISCOHDLCK 6 /* With SLARP and keepalive */ -#define ISDN_NET_ENCAP_X25IFACE 7 /* Documentation/networking/x25-iface.txt */ -#define ISDN_NET_ENCAP_MAX_ENCAP ISDN_NET_ENCAP_X25IFACE - -/* Facility which currently uses an ISDN-channel */ -#define ISDN_USAGE_NONE 0 -#define ISDN_USAGE_RAW 1 -#define ISDN_USAGE_MODEM 2 -#define ISDN_USAGE_NET 3 -#define ISDN_USAGE_VOICE 4 -#define ISDN_USAGE_FAX 5 -#define ISDN_USAGE_MASK 7 /* Mask to get plain usage */ -#define ISDN_USAGE_DISABLED 32 /* This bit is set, if channel is disabled */ -#define ISDN_USAGE_EXCLUSIVE 64 /* This bit is set, if channel is exclusive */ -#define ISDN_USAGE_OUTGOING 128 /* This bit is set, if channel is outgoing */ - -#define ISDN_MODEM_NUMREG 24 /* Number of Modem-Registers */ -#define ISDN_LMSNLEN 255 /* Length of tty's Listen-MSN string */ -#define ISDN_CMSGLEN 50 /* Length of CONNECT-Message to add for Modem */ - -#define ISDN_MSNLEN 32 -#define NET_DV 0x06 /* Data version for isdn_net_ioctl_cfg */ -#define TTY_DV 0x06 /* Data version for iprofd etc. */ - -#define INF_DV 0x01 /* Data version for /dev/isdninfo */ - -typedef struct { - char drvid[25]; - unsigned long arg; -} isdn_ioctl_struct; - -typedef struct { - char name[10]; - char phone[ISDN_MSNLEN]; - int outgoing; -} isdn_net_ioctl_phone; - -typedef struct { - char name[10]; /* Name of interface */ - char master[10]; /* Name of Master for Bundling */ - char slave[10]; /* Name of Slave for Bundling */ - char eaz[256]; /* EAZ/MSN */ - char drvid[25]; /* DriverId for Bindings */ - int onhtime; /* Hangup-Timeout */ - int charge; /* Charge-Units */ - int l2_proto; /* Layer-2 protocol */ - int l3_proto; /* Layer-3 protocol */ - int p_encap; /* Encapsulation */ - int exclusive; /* Channel, if bound exclusive */ - int dialmax; /* Dial Retry-Counter */ - int slavedelay; /* Delay until slave starts up */ - int cbdelay; /* Delay before Callback */ - int chargehup; /* Flag: Charge-Hangup */ - int ihup; /* Flag: Hangup-Timeout on incoming line */ - int secure; /* Flag: Secure */ - int callback; /* Flag: Callback */ - int cbhup; /* Flag: Reject Call before Callback */ - int pppbind; /* ippp device for bindings */ - int chargeint; /* Use fixed charge interval length */ - int triggercps; /* BogoCPS needed for triggering slave */ - int dialtimeout; /* Dial-Timeout */ - int dialwait; /* Time to wait after failed dial */ - int dialmode; /* Flag: off / on / auto */ -} isdn_net_ioctl_cfg; - -#define ISDN_NET_DIALMODE_MASK 0xC0 /* bits for status */ -#define ISDN_NET_DM_OFF 0x00 /* this interface is stopped */ -#define ISDN_NET_DM_MANUAL 0x40 /* this interface is on (manual) */ -#define ISDN_NET_DM_AUTO 0x80 /* this interface is autodial */ -#define ISDN_NET_DIALMODE(x) ((&(x))->flags & ISDN_NET_DIALMODE_MASK) - - -#endif /* _UAPI__ISDN_H__ */ diff --git a/include/uapi/linux/isdn_divertif.h b/include/uapi/linux/isdn_divertif.h deleted file mode 100644 index 0a17bb1bcb1b..000000000000 --- a/include/uapi/linux/isdn_divertif.h +++ /dev/null @@ -1,31 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* $Id: isdn_divertif.h,v 1.4.6.1 2001/09/23 22:25:05 kai Exp $ - * - * Header for the diversion supplementary interface for i4l. - * - * Author Werner Cornelius (werner@titro.de) - * Copyright by Werner Cornelius (werner@titro.de) - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ - -#ifndef _UAPI_LINUX_ISDN_DIVERTIF_H -#define _UAPI_LINUX_ISDN_DIVERTIF_H - -/***********************************************************/ -/* magic value is also used to control version information */ -/***********************************************************/ -#define DIVERT_IF_MAGIC 0x25873401 -#define DIVERT_CMD_REG 0x00 /* register command */ -#define DIVERT_CMD_REL 0x01 /* release command */ -#define DIVERT_NO_ERR 0x00 /* return value no error */ -#define DIVERT_CMD_ERR 0x01 /* invalid cmd */ -#define DIVERT_VER_ERR 0x02 /* magic/version invalid */ -#define DIVERT_REG_ERR 0x03 /* module already registered */ -#define DIVERT_REL_ERR 0x04 /* module not registered */ -#define DIVERT_REG_NAME isdn_register_divert - - -#endif /* _UAPI_LINUX_ISDN_DIVERTIF_H */ diff --git a/include/uapi/linux/isdn_ppp.h b/include/uapi/linux/isdn_ppp.h deleted file mode 100644 index 0bdc4efaacb2..000000000000 --- a/include/uapi/linux/isdn_ppp.h +++ /dev/null @@ -1,68 +0,0 @@ -/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ -/* Linux ISDN subsystem, sync PPP, interface to ipppd - * - * Copyright 1994-1999 by Fritz Elfert (fritz@isdn4linux.de) - * Copyright 1995,96 Thinking Objects Software GmbH Wuerzburg - * Copyright 1995,96 by Michael Hipp (Michael.Hipp@student.uni-tuebingen.de) - * Copyright 2000-2002 by Kai Germaschewski (kai@germaschewski.name) - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ - -#ifndef _UAPI_LINUX_ISDN_PPP_H -#define _UAPI_LINUX_ISDN_PPP_H - -#define CALLTYPE_INCOMING 0x1 -#define CALLTYPE_OUTGOING 0x2 -#define CALLTYPE_CALLBACK 0x4 - -#define IPPP_VERSION "2.2.0" - -struct pppcallinfo -{ - int calltype; - unsigned char local_num[64]; - unsigned char remote_num[64]; - int charge_units; -}; - -#define PPPIOCGCALLINFO _IOWR('t',128,struct pppcallinfo) -#define PPPIOCBUNDLE _IOW('t',129,int) -#define PPPIOCGMPFLAGS _IOR('t',130,int) -#define PPPIOCSMPFLAGS _IOW('t',131,int) -#define PPPIOCSMPMTU _IOW('t',132,int) -#define PPPIOCSMPMRU _IOW('t',133,int) -#define PPPIOCGCOMPRESSORS _IOR('t',134,unsigned long [8]) -#define PPPIOCSCOMPRESSOR _IOW('t',135,int) -#define PPPIOCGIFNAME _IOR('t',136, char [IFNAMSIZ] ) - - -#define SC_MP_PROT 0x00000200 -#define SC_REJ_MP_PROT 0x00000400 -#define SC_OUT_SHORT_SEQ 0x00000800 -#define SC_IN_SHORT_SEQ 0x00004000 - -#define SC_DECOMP_ON 0x01 -#define SC_COMP_ON 0x02 -#define SC_DECOMP_DISCARD 0x04 -#define SC_COMP_DISCARD 0x08 -#define SC_LINK_DECOMP_ON 0x10 -#define SC_LINK_COMP_ON 0x20 -#define SC_LINK_DECOMP_DISCARD 0x40 -#define SC_LINK_COMP_DISCARD 0x80 - -#define ISDN_PPP_COMP_MAX_OPTIONS 16 - -#define IPPP_COMP_FLAG_XMIT 0x1 -#define IPPP_COMP_FLAG_LINK 0x2 - -struct isdn_ppp_comp_data { - int num; - unsigned char options[ISDN_PPP_COMP_MAX_OPTIONS]; - int optlen; - int flags; -}; - -#endif /* _UAPI_LINUX_ISDN_PPP_H */ diff --git a/include/uapi/linux/isdnif.h b/include/uapi/linux/isdnif.h deleted file mode 100644 index 611a69196738..000000000000 --- a/include/uapi/linux/isdnif.h +++ /dev/null @@ -1,57 +0,0 @@ -/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ -/* $Id: isdnif.h,v 1.43.2.2 2004/01/12 23:08:35 keil Exp $ - * - * Linux ISDN subsystem - * Definition of the interface between the subsystem and its low-level drivers. - * - * Copyright 1994,95,96 by Fritz Elfert (fritz@isdn4linux.de) - * Copyright 1995,96 Thinking Objects Software GmbH Wuerzburg - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ - -#ifndef _UAPI__ISDNIF_H__ -#define _UAPI__ISDNIF_H__ - - -/* - * Values for general protocol-selection - */ -#define ISDN_PTYPE_UNKNOWN 0 /* Protocol undefined */ -#define ISDN_PTYPE_1TR6 1 /* german 1TR6-protocol */ -#define ISDN_PTYPE_EURO 2 /* EDSS1-protocol */ -#define ISDN_PTYPE_LEASED 3 /* for leased lines */ -#define ISDN_PTYPE_NI1 4 /* US NI-1 protocol */ -#define ISDN_PTYPE_MAX 7 /* Max. 8 Protocols */ - -/* - * Values for Layer-2-protocol-selection - */ -#define ISDN_PROTO_L2_X75I 0 /* X75/LAPB with I-Frames */ -#define ISDN_PROTO_L2_X75UI 1 /* X75/LAPB with UI-Frames */ -#define ISDN_PROTO_L2_X75BUI 2 /* X75/LAPB with UI-Frames */ -#define ISDN_PROTO_L2_HDLC 3 /* HDLC */ -#define ISDN_PROTO_L2_TRANS 4 /* Transparent (Voice) */ -#define ISDN_PROTO_L2_X25DTE 5 /* X25/LAPB DTE mode */ -#define ISDN_PROTO_L2_X25DCE 6 /* X25/LAPB DCE mode */ -#define ISDN_PROTO_L2_V11096 7 /* V.110 bitrate adaption 9600 Baud */ -#define ISDN_PROTO_L2_V11019 8 /* V.110 bitrate adaption 19200 Baud */ -#define ISDN_PROTO_L2_V11038 9 /* V.110 bitrate adaption 38400 Baud */ -#define ISDN_PROTO_L2_MODEM 10 /* Analog Modem on Board */ -#define ISDN_PROTO_L2_FAX 11 /* Fax Group 2/3 */ -#define ISDN_PROTO_L2_HDLC_56K 12 /* HDLC 56k */ -#define ISDN_PROTO_L2_MAX 15 /* Max. 16 Protocols */ - -/* - * Values for Layer-3-protocol-selection - */ -#define ISDN_PROTO_L3_TRANS 0 /* Transparent */ -#define ISDN_PROTO_L3_TRANSDSP 1 /* Transparent with DSP */ -#define ISDN_PROTO_L3_FCLASS2 2 /* Fax Group 2/3 CLASS 2 */ -#define ISDN_PROTO_L3_FCLASS1 3 /* Fax Group 2/3 CLASS 1 */ -#define ISDN_PROTO_L3_MAX 7 /* Max. 8 Protocols */ - - -#endif /* _UAPI__ISDNIF_H__ */ diff --git a/include/uapi/linux/mii.h b/include/uapi/linux/mii.h index a506216591d6..51b48e4be1f2 100644 --- a/include/uapi/linux/mii.h +++ b/include/uapi/linux/mii.h @@ -121,6 +121,8 @@ #define EXPANSION_MFAULTS 0x0010 /* Multiple faults detected */ #define EXPANSION_RESV 0xffe0 /* Unused... */ +#define ESTATUS_1000_XFULL 0x8000 /* Can do 1000BaseX Full */ +#define ESTATUS_1000_XHALF 0x4000 /* Can do 1000BaseX Half */ #define ESTATUS_1000_TFULL 0x2000 /* Can do 1000BT Full */ #define ESTATUS_1000_THALF 0x1000 /* Can do 1000BT Half */ diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h index ea69ca21ff23..eea166c52c36 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set.h +++ b/include/uapi/linux/netfilter/ipset/ip_set.h @@ -2,7 +2,7 @@ /* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu> * Patrick Schaaf <bof@bof.de> * Martin Josefsson <gandalf@wlug.westbo.se> - * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@netfilter.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as diff --git a/include/uapi/linux/netfilter/nf_synproxy.h b/include/uapi/linux/netfilter/nf_synproxy.h new file mode 100644 index 000000000000..6f3791c8946f --- /dev/null +++ b/include/uapi/linux/netfilter/nf_synproxy.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NF_SYNPROXY_H +#define _NF_SYNPROXY_H + +#include <linux/types.h> + +#define NF_SYNPROXY_OPT_MSS 0x01 +#define NF_SYNPROXY_OPT_WSCALE 0x02 +#define NF_SYNPROXY_OPT_SACK_PERM 0x04 +#define NF_SYNPROXY_OPT_TIMESTAMP 0x08 +#define NF_SYNPROXY_OPT_ECN 0x10 +#define NF_SYNPROXY_OPT_MASK (NF_SYNPROXY_OPT_MSS | \ + NF_SYNPROXY_OPT_WSCALE | \ + NF_SYNPROXY_OPT_SACK_PERM | \ + NF_SYNPROXY_OPT_TIMESTAMP) + +struct nf_synproxy_info { + __u8 options; + __u8 wscale; + __u16 mss; +}; + +#endif /* _NF_SYNPROXY_H */ diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 505393c6e959..82abaa183fc3 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -192,6 +192,7 @@ enum nft_table_attributes { * @NFTA_CHAIN_USE: number of references to this chain (NLA_U32) * @NFTA_CHAIN_TYPE: type name of the string (NLA_NUL_STRING) * @NFTA_CHAIN_COUNTERS: counter specification of the chain (NLA_NESTED: nft_counter_attributes) + * @NFTA_CHAIN_FLAGS: chain flags */ enum nft_chain_attributes { NFTA_CHAIN_UNSPEC, @@ -204,6 +205,7 @@ enum nft_chain_attributes { NFTA_CHAIN_TYPE, NFTA_CHAIN_COUNTERS, NFTA_CHAIN_PAD, + NFTA_CHAIN_FLAGS, __NFTA_CHAIN_MAX }; #define NFTA_CHAIN_MAX (__NFTA_CHAIN_MAX - 1) @@ -730,10 +732,12 @@ enum nft_exthdr_flags { * * @NFT_EXTHDR_OP_IPV6: match against ipv6 extension headers * @NFT_EXTHDR_OP_TCP: match against tcp options + * @NFT_EXTHDR_OP_IPV4: match against ipv4 options */ enum nft_exthdr_op { NFT_EXTHDR_OP_IPV6, NFT_EXTHDR_OP_TCPOPT, + NFT_EXTHDR_OP_IPV4, __NFT_EXTHDR_OP_MAX }; #define NFT_EXTHDR_OP_MAX (__NFT_EXTHDR_OP_MAX - 1) @@ -793,6 +797,8 @@ enum nft_exthdr_attributes { * @NFT_META_SECPATH: boolean, secpath_exists (!!skb->sp) * @NFT_META_IIFKIND: packet input interface kind name (dev->rtnl_link_ops->kind) * @NFT_META_OIFKIND: packet output interface kind name (dev->rtnl_link_ops->kind) + * @NFT_META_BRI_IIFPVID: packet input bridge port pvid + * @NFT_META_BRI_IIFVPROTO: packet input bridge vlan proto */ enum nft_meta_keys { NFT_META_LEN, @@ -823,6 +829,8 @@ enum nft_meta_keys { NFT_META_SECPATH, NFT_META_IIFKIND, NFT_META_OIFKIND, + NFT_META_BRI_IIFPVID, + NFT_META_BRI_IIFVPROTO, }; /** @@ -1445,6 +1453,17 @@ enum nft_ct_timeout_timeout_attributes { }; #define NFTA_CT_TIMEOUT_MAX (__NFTA_CT_TIMEOUT_MAX - 1) +enum nft_ct_expectation_attributes { + NFTA_CT_EXPECT_UNSPEC, + NFTA_CT_EXPECT_L3PROTO, + NFTA_CT_EXPECT_L4PROTO, + NFTA_CT_EXPECT_DPORT, + NFTA_CT_EXPECT_TIMEOUT, + NFTA_CT_EXPECT_SIZE, + __NFTA_CT_EXPECT_MAX, +}; +#define NFTA_CT_EXPECT_MAX (__NFTA_CT_EXPECT_MAX - 1) + #define NFT_OBJECT_UNSPEC 0 #define NFT_OBJECT_COUNTER 1 #define NFT_OBJECT_QUOTA 2 @@ -1454,7 +1473,8 @@ enum nft_ct_timeout_timeout_attributes { #define NFT_OBJECT_TUNNEL 6 #define NFT_OBJECT_CT_TIMEOUT 7 #define NFT_OBJECT_SECMARK 8 -#define __NFT_OBJECT_MAX 9 +#define NFT_OBJECT_CT_EXPECT 9 +#define __NFT_OBJECT_MAX 10 #define NFT_OBJECT_MAX (__NFT_OBJECT_MAX - 1) /** @@ -1538,6 +1558,22 @@ enum nft_osf_flags { }; /** + * enum nft_synproxy_attributes - nf_tables synproxy expression netlink attributes + * + * @NFTA_SYNPROXY_MSS: mss value sent to the backend (NLA_U16) + * @NFTA_SYNPROXY_WSCALE: wscale value sent to the backend (NLA_U8) + * @NFTA_SYNPROXY_FLAGS: flags (NLA_U32) + */ +enum nft_synproxy_attributes { + NFTA_SYNPROXY_UNSPEC, + NFTA_SYNPROXY_MSS, + NFTA_SYNPROXY_WSCALE, + NFTA_SYNPROXY_FLAGS, + __NFTA_SYNPROXY_MAX, +}; +#define NFTA_SYNPROXY_MAX (__NFTA_SYNPROXY_MAX - 1) + +/** * enum nft_device_attributes - nf_tables device netlink attributes * * @NFTA_DEVICE_NAME: name of this device (NLA_STRING) diff --git a/include/uapi/linux/netfilter/xt_SYNPROXY.h b/include/uapi/linux/netfilter/xt_SYNPROXY.h index ea5eba15d4c1..19c04ed86172 100644 --- a/include/uapi/linux/netfilter/xt_SYNPROXY.h +++ b/include/uapi/linux/netfilter/xt_SYNPROXY.h @@ -2,18 +2,14 @@ #ifndef _XT_SYNPROXY_H #define _XT_SYNPROXY_H -#include <linux/types.h> +#include <linux/netfilter/nf_synproxy.h> -#define XT_SYNPROXY_OPT_MSS 0x01 -#define XT_SYNPROXY_OPT_WSCALE 0x02 -#define XT_SYNPROXY_OPT_SACK_PERM 0x04 -#define XT_SYNPROXY_OPT_TIMESTAMP 0x08 -#define XT_SYNPROXY_OPT_ECN 0x10 +#define XT_SYNPROXY_OPT_MSS NF_SYNPROXY_OPT_MSS +#define XT_SYNPROXY_OPT_WSCALE NF_SYNPROXY_OPT_WSCALE +#define XT_SYNPROXY_OPT_SACK_PERM NF_SYNPROXY_OPT_SACK_PERM +#define XT_SYNPROXY_OPT_TIMESTAMP NF_SYNPROXY_OPT_TIMESTAMP +#define XT_SYNPROXY_OPT_ECN NF_SYNPROXY_OPT_ECN -struct xt_synproxy_info { - __u8 options; - __u8 wscale; - __u16 mss; -}; +#define xt_synproxy_info nf_synproxy_info #endif /* _XT_SYNPROXY_H */ diff --git a/include/uapi/linux/netfilter/xt_owner.h b/include/uapi/linux/netfilter/xt_owner.h index fa3ad84957d5..5108df4d0313 100644 --- a/include/uapi/linux/netfilter/xt_owner.h +++ b/include/uapi/linux/netfilter/xt_owner.h @@ -5,11 +5,17 @@ #include <linux/types.h> enum { - XT_OWNER_UID = 1 << 0, - XT_OWNER_GID = 1 << 1, - XT_OWNER_SOCKET = 1 << 2, + XT_OWNER_UID = 1 << 0, + XT_OWNER_GID = 1 << 1, + XT_OWNER_SOCKET = 1 << 2, + XT_OWNER_SUPPL_GROUPS = 1 << 3, }; +#define XT_OWNER_MASK (XT_OWNER_UID | \ + XT_OWNER_GID | \ + XT_OWNER_SOCKET | \ + XT_OWNER_SUPPL_GROUPS) + struct xt_owner_match_info { __u32 uid_min, uid_max; __u32 gid_min, gid_max; diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h new file mode 100644 index 000000000000..7b61867e9848 --- /dev/null +++ b/include/uapi/linux/nexthop.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_NEXTHOP_H +#define _UAPI_LINUX_NEXTHOP_H + +#include <linux/types.h> + +struct nhmsg { + unsigned char nh_family; + unsigned char nh_scope; /* return only */ + unsigned char nh_protocol; /* Routing protocol that installed nh */ + unsigned char resvd; + unsigned int nh_flags; /* RTNH_F flags */ +}; + +/* entry in a nexthop group */ +struct nexthop_grp { + __u32 id; /* nexthop id - must exist */ + __u8 weight; /* weight of this nexthop */ + __u8 resvd1; + __u16 resvd2; +}; + +enum { + NEXTHOP_GRP_TYPE_MPATH, /* default type if not specified */ + __NEXTHOP_GRP_TYPE_MAX, +}; + +#define NEXTHOP_GRP_TYPE_MAX (__NEXTHOP_GRP_TYPE_MAX - 1) + +enum { + NHA_UNSPEC, + NHA_ID, /* u32; id for nexthop. id == 0 means auto-assign */ + + NHA_GROUP, /* array of nexthop_grp */ + NHA_GROUP_TYPE, /* u16 one of NEXTHOP_GRP_TYPE */ + /* if NHA_GROUP attribute is added, no other attributes can be set */ + + NHA_BLACKHOLE, /* flag; nexthop used to blackhole packets */ + /* if NHA_BLACKHOLE is added, OIF, GATEWAY, ENCAP can not be set */ + + NHA_OIF, /* u32; nexthop device */ + NHA_GATEWAY, /* be32 (IPv4) or in6_addr (IPv6) gw address */ + NHA_ENCAP_TYPE, /* u16; lwt encap type */ + NHA_ENCAP, /* lwt encap data */ + + /* NHA_OIF can be appended to dump request to return only + * nexthops using given device + */ + NHA_GROUPS, /* flag; only return nexthop groups in dump */ + NHA_MASTER, /* u32; only return nexthops with given master dev */ + + __NHA_MAX, +}; + +#define NHA_MAX (__NHA_MAX - 1) +#endif diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 6f09d1500960..75758ec26c8b 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -235,6 +235,15 @@ */ /** + * DOC: SAE authentication offload + * + * By setting @NL80211_EXT_FEATURE_SAE_OFFLOAD flag drivers can indicate they + * support offloading SAE authentication for WPA3-Personal networks. In + * %NL80211_CMD_CONNECT the password for SAE should be specified using + * %NL80211_ATTR_SAE_PASSWORD. + */ + +/** * enum nl80211_commands - supported nl80211 commands * * @NL80211_CMD_UNSPEC: unspecified command to catch errors @@ -2341,6 +2350,12 @@ enum nl80211_commands { * should be picking up the lowest tx power, either tx power per-interface * or per-station. * + * @NL80211_ATTR_SAE_PASSWORD: attribute for passing SAE password material. It + * is used with %NL80211_CMD_CONNECT to provide password for offloading + * SAE authentication for WPA3-Personal networks. + * + * @NL80211_ATTR_TWT_RESPONDER: Enable target wait time responder support. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2794,6 +2809,10 @@ enum nl80211_attrs { NL80211_ATTR_STA_TX_POWER_SETTING, NL80211_ATTR_STA_TX_POWER, + NL80211_ATTR_SAE_PASSWORD, + + NL80211_ATTR_TWT_RESPONDER, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -4406,6 +4425,7 @@ enum nl80211_mfp { enum nl80211_wpa_versions { NL80211_WPA_VERSION_1 = 1 << 0, NL80211_WPA_VERSION_2 = 1 << 1, + NL80211_WPA_VERSION_3 = 1 << 2, }; /** @@ -5314,7 +5334,7 @@ enum nl80211_feature_flags { NL80211_FEATURE_TDLS_CHANNEL_SWITCH = 1 << 28, NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR = 1 << 29, NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR = 1 << 30, - NL80211_FEATURE_ND_RANDOM_MAC_ADDR = 1 << 31, + NL80211_FEATURE_ND_RANDOM_MAC_ADDR = 1U << 31, }; /** @@ -5422,6 +5442,9 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_STA_TX_PWR: This driver supports controlling tx power * to a station. * + * @NL80211_EXT_FEATURE_SAE_OFFLOAD: Device wants to do SAE authentication in + * station mode (SAE password is passed as part of the connect command). + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5466,6 +5489,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD, NL80211_EXT_FEATURE_EXT_KEY_ID, NL80211_EXT_FEATURE_STA_TX_PWR, + NL80211_EXT_FEATURE_SAE_OFFLOAD, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 51a0496f78ea..b057aeeb6338 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -104,6 +104,9 @@ enum tca_id { TCA_ID_SIMP = TCA_ACT_SIMP, TCA_ID_IFE = TCA_ACT_IFE, TCA_ID_SAMPLE = TCA_ACT_SAMPLE, + TCA_ID_CTINFO, + TCA_ID_MPLS, + TCA_ID_CT, /* other actions go here */ __TCA_ID_MAX = 255 }; @@ -294,7 +297,7 @@ enum { TCA_FW_UNSPEC, TCA_FW_CLASSID, TCA_FW_POLICE, - TCA_FW_INDEV, /* used by CONFIG_NET_CLS_IND */ + TCA_FW_INDEV, TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */ TCA_FW_MASK, __TCA_FW_MAX @@ -534,12 +537,28 @@ enum { TCA_FLOWER_KEY_PORT_DST_MIN, /* be16 */ TCA_FLOWER_KEY_PORT_DST_MAX, /* be16 */ + TCA_FLOWER_KEY_CT_STATE, /* u16 */ + TCA_FLOWER_KEY_CT_STATE_MASK, /* u16 */ + TCA_FLOWER_KEY_CT_ZONE, /* u16 */ + TCA_FLOWER_KEY_CT_ZONE_MASK, /* u16 */ + TCA_FLOWER_KEY_CT_MARK, /* u32 */ + TCA_FLOWER_KEY_CT_MARK_MASK, /* u32 */ + TCA_FLOWER_KEY_CT_LABELS, /* u128 */ + TCA_FLOWER_KEY_CT_LABELS_MASK, /* u128 */ + __TCA_FLOWER_MAX, }; #define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1) enum { + TCA_FLOWER_KEY_CT_FLAGS_NEW = 1 << 0, /* Beginning of a new connection. */ + TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED = 1 << 1, /* Part of an existing connection. */ + TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */ + TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */ +}; + +enum { TCA_FLOWER_KEY_ENC_OPTS_UNSPEC, TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested * TCA_FLOWER_KEY_ENC_OPT_GENEVE_ diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 8b2f993cbb77..1f623252abe8 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -2,6 +2,7 @@ #ifndef __LINUX_PKT_SCHED_H #define __LINUX_PKT_SCHED_H +#include <linux/const.h> #include <linux/types.h> /* Logical priority bands not depending on specific packet scheduler. @@ -988,8 +989,9 @@ struct tc_etf_qopt { __s32 delta; __s32 clockid; __u32 flags; -#define TC_ETF_DEADLINE_MODE_ON BIT(0) -#define TC_ETF_OFFLOAD_ON BIT(1) +#define TC_ETF_DEADLINE_MODE_ON _BITUL(0) +#define TC_ETF_OFFLOAD_ON _BITUL(1) +#define TC_ETF_SKIP_SOCK_CHECK _BITUL(2) }; enum { @@ -1158,6 +1160,8 @@ enum { * [TCA_TAPRIO_ATTR_SCHED_ENTRY_INTERVAL] */ +#define TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST 0x1 + enum { TCA_TAPRIO_ATTR_UNSPEC, TCA_TAPRIO_ATTR_PRIOMAP, /* struct tc_mqprio_qopt */ @@ -1169,6 +1173,8 @@ enum { TCA_TAPRIO_ATTR_ADMIN_SCHED, /* The admin sched, only used in dump */ TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME, /* s64 */ TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION, /* s64 */ + TCA_TAPRIO_ATTR_FLAGS, /* u32 */ + TCA_TAPRIO_ATTR_TXTIME_DELAY, /* s32 */ __TCA_TAPRIO_ATTR_MAX, }; diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h index 5d0f76c780e5..fd6b5f66e2c5 100644 --- a/include/uapi/linux/rds.h +++ b/include/uapi/linux/rds.h @@ -250,6 +250,7 @@ struct rds_info_rdma_connection { __u32 rdma_mr_max; __u32 rdma_mr_size; __u8 tos; + __u32 cache_allocs; }; struct rds6_info_rdma_connection { @@ -264,6 +265,7 @@ struct rds6_info_rdma_connection { __u32 rdma_mr_max; __u32 rdma_mr_size; __u8 tos; + __u32 cache_allocs; }; /* RDS message Receive Path Latency points */ diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 46399367627f..ce2a623abb75 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -157,6 +157,13 @@ enum { RTM_GETCHAIN, #define RTM_GETCHAIN RTM_GETCHAIN + RTM_NEWNEXTHOP = 104, +#define RTM_NEWNEXTHOP RTM_NEWNEXTHOP + RTM_DELNEXTHOP, +#define RTM_DELNEXTHOP RTM_DELNEXTHOP + RTM_GETNEXTHOP, +#define RTM_GETNEXTHOP RTM_GETNEXTHOP + __RTM_MAX, #define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1) }; @@ -342,6 +349,7 @@ enum rtattr_type_t { RTA_IP_PROTO, RTA_SPORT, RTA_DPORT, + RTA_NH_ID, __RTA_MAX }; @@ -704,6 +712,8 @@ enum rtnetlink_groups { #define RTNLGRP_IPV4_MROUTE_R RTNLGRP_IPV4_MROUTE_R RTNLGRP_IPV6_MROUTE_R, #define RTNLGRP_IPV6_MROUTE_R RTNLGRP_IPV6_MROUTE_R + RTNLGRP_NEXTHOP, +#define RTNLGRP_NEXTHOP RTNLGRP_NEXTHOP __RTNLGRP_MAX }; #define RTNLGRP_MAX (__RTNLGRP_MAX - 1) diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index fd42c1316d3d..549a31c29f7d 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -284,6 +284,7 @@ enum LINUX_MIB_TCPZEROWINDOWDROP, /* TCPZeroWindowDrop */ LINUX_MIB_TCPRCVQDROP, /* TCPRcvQDrop */ LINUX_MIB_TCPWQUEUETOOBIG, /* TCPWqueueTooBig */ + LINUX_MIB_TCPFASTOPENPASSIVEALTKEY, /* TCPFastOpenPassiveAltKey */ __LINUX_MIB_MAX }; diff --git a/include/uapi/linux/tc_act/tc_ct.h b/include/uapi/linux/tc_act/tc_ct.h new file mode 100644 index 000000000000..5fb1d7ac1027 --- /dev/null +++ b/include/uapi/linux/tc_act/tc_ct.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __UAPI_TC_CT_H +#define __UAPI_TC_CT_H + +#include <linux/types.h> +#include <linux/pkt_cls.h> + +enum { + TCA_CT_UNSPEC, + TCA_CT_PARMS, + TCA_CT_TM, + TCA_CT_ACTION, /* u16 */ + TCA_CT_ZONE, /* u16 */ + TCA_CT_MARK, /* u32 */ + TCA_CT_MARK_MASK, /* u32 */ + TCA_CT_LABELS, /* u128 */ + TCA_CT_LABELS_MASK, /* u128 */ + TCA_CT_NAT_IPV4_MIN, /* be32 */ + TCA_CT_NAT_IPV4_MAX, /* be32 */ + TCA_CT_NAT_IPV6_MIN, /* struct in6_addr */ + TCA_CT_NAT_IPV6_MAX, /* struct in6_addr */ + TCA_CT_NAT_PORT_MIN, /* be16 */ + TCA_CT_NAT_PORT_MAX, /* be16 */ + TCA_CT_PAD, + __TCA_CT_MAX +}; + +#define TCA_CT_MAX (__TCA_CT_MAX - 1) + +#define TCA_CT_ACT_COMMIT (1 << 0) +#define TCA_CT_ACT_FORCE (1 << 1) +#define TCA_CT_ACT_CLEAR (1 << 2) +#define TCA_CT_ACT_NAT (1 << 3) +#define TCA_CT_ACT_NAT_SRC (1 << 4) +#define TCA_CT_ACT_NAT_DST (1 << 5) + +struct tc_ct { + tc_gen; +}; + +#endif /* __UAPI_TC_CT_H */ diff --git a/include/uapi/linux/tc_act/tc_ctinfo.h b/include/uapi/linux/tc_act/tc_ctinfo.h new file mode 100644 index 000000000000..f5f26d95d0e7 --- /dev/null +++ b/include/uapi/linux/tc_act/tc_ctinfo.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __UAPI_TC_CTINFO_H +#define __UAPI_TC_CTINFO_H + +#include <linux/types.h> +#include <linux/pkt_cls.h> + +struct tc_ctinfo { + tc_gen; +}; + +enum { + TCA_CTINFO_UNSPEC, + TCA_CTINFO_PAD, + TCA_CTINFO_TM, + TCA_CTINFO_ACT, + TCA_CTINFO_ZONE, + TCA_CTINFO_PARMS_DSCP_MASK, + TCA_CTINFO_PARMS_DSCP_STATEMASK, + TCA_CTINFO_PARMS_CPMARK_MASK, + TCA_CTINFO_STATS_DSCP_SET, + TCA_CTINFO_STATS_DSCP_ERROR, + TCA_CTINFO_STATS_CPMARK_SET, + __TCA_CTINFO_MAX +}; + +#define TCA_CTINFO_MAX (__TCA_CTINFO_MAX - 1) + +#endif diff --git a/include/uapi/linux/tc_act/tc_mpls.h b/include/uapi/linux/tc_act/tc_mpls.h new file mode 100644 index 000000000000..9360e95273c7 --- /dev/null +++ b/include/uapi/linux/tc_act/tc_mpls.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (C) 2019 Netronome Systems, Inc. */ + +#ifndef __LINUX_TC_MPLS_H +#define __LINUX_TC_MPLS_H + +#include <linux/pkt_cls.h> + +#define TCA_MPLS_ACT_POP 1 +#define TCA_MPLS_ACT_PUSH 2 +#define TCA_MPLS_ACT_MODIFY 3 +#define TCA_MPLS_ACT_DEC_TTL 4 + +struct tc_mpls { + tc_gen; /* generic TC action fields. */ + int m_action; /* action of type TCA_MPLS_ACT_*. */ +}; + +enum { + TCA_MPLS_UNSPEC, + TCA_MPLS_TM, /* struct tcf_t; time values associated with action. */ + TCA_MPLS_PARMS, /* struct tc_mpls; action type and general TC fields. */ + TCA_MPLS_PAD, + TCA_MPLS_PROTO, /* be16; eth_type of pushed or next (for pop) header. */ + TCA_MPLS_LABEL, /* u32; MPLS label. Lower 20 bits are used. */ + TCA_MPLS_TC, /* u8; MPLS TC field. Lower 3 bits are used. */ + TCA_MPLS_TTL, /* u8; MPLS TTL field. Must not be 0. */ + TCA_MPLS_BOS, /* u8; MPLS BOS field. Either 1 or 0. */ + __TCA_MPLS_MAX, +}; +#define TCA_MPLS_MAX (__TCA_MPLS_MAX - 1) + +#endif diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index b521464ea962..b3564f85a762 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -127,6 +127,9 @@ enum { #define TCP_CM_INQ TCP_INQ +#define TCP_TX_DELAY 37 /* delay outgoing packets by XX usec */ + + #define TCP_REPAIR_ON 1 #define TCP_REPAIR_OFF 0 #define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */ diff --git a/include/uapi/linux/unix_diag.h b/include/uapi/linux/unix_diag.h index 5c502fdf7a42..a1988576fa8a 100644 --- a/include/uapi/linux/unix_diag.h +++ b/include/uapi/linux/unix_diag.h @@ -20,6 +20,7 @@ struct unix_diag_req { #define UDIAG_SHOW_ICONS 0x00000008 /* show pending connections */ #define UDIAG_SHOW_RQLEN 0x00000010 /* show skb receive queue len */ #define UDIAG_SHOW_MEMINFO 0x00000020 /* show memory info of a socket */ +#define UDIAG_SHOW_UID 0x00000040 /* show socket's UID */ struct unix_diag_msg { __u8 udiag_family; @@ -40,6 +41,7 @@ enum { UNIX_DIAG_RQLEN, UNIX_DIAG_MEMINFO, UNIX_DIAG_SHUTDOWN, + UNIX_DIAG_UID, __UNIX_DIAG_MAX, }; diff --git a/include/uapi/linux/wanrouter.h b/include/uapi/linux/wanrouter.h deleted file mode 100644 index 2f1216d00caa..000000000000 --- a/include/uapi/linux/wanrouter.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * wanrouter.h Legacy declarations kept around until X25 is removed - */ - -#ifndef _UAPI_ROUTER_H -#define _UAPI_ROUTER_H - -/* 'state' defines */ -enum wan_states -{ - WAN_UNCONFIGURED, /* link/channel is not configured */ - WAN_DISCONNECTED, /* link/channel is disconnected */ - WAN_CONNECTING, /* connection is in progress */ - WAN_CONNECTED /* link/channel is operational */ -}; - -#endif /* _UAPI_ROUTER_H */ |