From e40fbbf0572c5e41dc87ad79001748ed399ce32d Mon Sep 17 00:00:00 2001 From: Usama Arif Date: Wed, 19 Jan 2022 11:44:40 +0000 Subject: uapi/bpf: Add missing description and returns for helper documentation Both description and returns section will become mandatory for helpers and syscalls in a later commit to generate man pages. This commit also adds in the documentation that BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN for anyone searching for the syscall in the generated man pages. Signed-off-by: Usama Arif Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220119114442.1452088-1-usama.arif@bytedance.com --- include/uapi/linux/bpf.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b0383d371b9a..a9c96c21330a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -330,6 +330,8 @@ union bpf_iter_link_info { * *ctx_out*, *data_in* and *data_out* must be NULL. * *repeat* must be zero. * + * BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN. + * * Return * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. @@ -1775,6 +1777,8 @@ union bpf_attr { * 0 on success, or a negative error in case of failure. * * u64 bpf_get_current_pid_tgid(void) + * Description + * Get the current pid and tgid. * Return * A 64-bit integer containing the current tgid and pid, and * created as such: @@ -1782,6 +1786,8 @@ union bpf_attr { * *current_task*\ **->pid**. * * u64 bpf_get_current_uid_gid(void) + * Description + * Get the current uid and gid. * Return * A 64-bit integer containing the current GID and UID, and * created as such: *current_gid* **<< 32 \|** *current_uid*. @@ -2256,6 +2262,8 @@ union bpf_attr { * The 32-bit hash. * * u64 bpf_get_current_task(void) + * Description + * Get the current task. * Return * A pointer to the current task struct. * @@ -2369,6 +2377,8 @@ union bpf_attr { * indicate that the hash is outdated and to trigger a * recalculation the next time the kernel tries to access this * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * Return + * void. * * long bpf_get_numa_node_id(void) * Description @@ -2466,6 +2476,8 @@ union bpf_attr { * A 8-byte long unique number or 0 if *sk* is NULL. * * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Description + * Get the owner UID of the socked associated to *skb*. * Return * The owner UID of the socket associated to *skb*. If the socket * is **NULL**, or if it is not a full socket (i.e. if it is a @@ -3240,6 +3252,9 @@ union bpf_attr { * The id is returned or 0 in case the id could not be retrieved. * * u64 bpf_get_current_cgroup_id(void) + * Description + * Get the current cgroup id based on the cgroup within which + * the current task is running. * Return * A 64-bit integer containing the current cgroup id based * on the cgroup within which the current task is running. -- cgit v1.2.3 From b44123b4a3dcad4664d3a0f72c011ffd4c9c4d93 Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Thu, 16 Dec 2021 02:04:27 +0000 Subject: bpf: Add cgroup helpers bpf_{get,set}_retval to get/set syscall return value The helpers continue to use int for retval because all the hooks are int-returning rather than long-returning. The return value of bpf_set_retval is int for future-proofing, in case in the future there may be errors trying to set the retval. After the previous patch, if a program rejects a syscall by returning 0, an -EPERM will be generated no matter if the retval is already set to -err. This patch change it being forced only if retval is not -err. This is because we want to support, for example, invoking bpf_set_retval(-EINVAL) and return 0, and have the syscall return value be -EINVAL not -EPERM. For BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY, the prior behavior is that, if the return value is NET_XMIT_DROP, the packet is silently dropped. We preserve this behavior for backward compatibility reasons, so even if an errno is set, the errno does not return to caller. However, setting a non-err to retval cannot propagate so this is not allowed and we return a -EFAULT in that case. Signed-off-by: YiFei Zhu Reviewed-by: Stanislav Fomichev Link: https://lore.kernel.org/r/b4013fd5d16bed0b01977c1fafdeae12e1de61fb.1639619851.git.zhuyifei@google.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 10 ++++++---- include/uapi/linux/bpf.h | 18 ++++++++++++++++++ kernel/bpf/cgroup.c | 38 +++++++++++++++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 18 ++++++++++++++++++ 4 files changed, 79 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7b0c11f414d0..dce54eb0aae8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1299,7 +1299,7 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; func_ret = run_prog(prog, ctx); - if (!(func_ret & 1)) + if (!(func_ret & 1) && !IS_ERR_VALUE((long)run_ctx.retval)) run_ctx.retval = -EPERM; *(ret_flags) |= (func_ret >> 1); item++; @@ -1329,7 +1329,7 @@ BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; - if (!run_prog(prog, ctx)) + if (!run_prog(prog, ctx) && !IS_ERR_VALUE((long)run_ctx.retval)) run_ctx.retval = -EPERM; item++; } @@ -1389,7 +1389,7 @@ out: * 0: NET_XMIT_SUCCESS skb should be transmitted * 1: NET_XMIT_DROP skb should be dropped and cn * 2: NET_XMIT_CN skb should be transmitted and cn - * 3: -EPERM skb should be dropped + * 3: -err skb should be dropped */ #define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ ({ \ @@ -1398,10 +1398,12 @@ out: u32 _ret; \ _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, 0, &_flags); \ _cn = _flags & BPF_RET_SET_CN; \ + if (_ret && !IS_ERR_VALUE((long)_ret)) \ + _ret = -EFAULT; \ if (!_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ else \ - _ret = (_cn ? NET_XMIT_DROP : -EPERM); \ + _ret = (_cn ? NET_XMIT_DROP : _ret); \ _ret; \ }) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a9c96c21330a..fe2272defcd9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5033,6 +5033,22 @@ union bpf_attr { * * Return * The number of arguments of the traced function. + * + * int bpf_get_retval(void) + * Description + * Get the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * The syscall's return value. + * + * int bpf_set_retval(int retval) + * Description + * Set the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5221,6 +5237,8 @@ union bpf_attr { FN(get_func_arg), \ FN(get_func_ret), \ FN(get_func_arg_cnt), \ + FN(get_retval), \ + FN(set_retval), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index b6fad0bbf5a7..279ebbed75a5 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1044,7 +1044,7 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, * NET_XMIT_DROP (1) - drop packet and notify TCP to call cwr * NET_XMIT_CN (2) - continue with packet output and notify TCP * to call cwr - * -EPERM - drop packet + * -err - drop packet * * For ingress packets, this function will return -EPERM if any * attached program was found and if it returned != 1 during execution. @@ -1080,6 +1080,8 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, } else { ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], skb, __bpf_prog_run_save_cb, 0); + if (ret && !IS_ERR_VALUE((long)ret)) + ret = -EFAULT; } bpf_restore_data_end(skb, saved_data_end); __skb_pull(skb, offset); @@ -1205,6 +1207,36 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, return ret; } +BPF_CALL_0(bpf_get_retval) +{ + struct bpf_cg_run_ctx *ctx = + container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); + + return ctx->retval; +} + +static const struct bpf_func_proto bpf_get_retval_proto = { + .func = bpf_get_retval, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + +BPF_CALL_1(bpf_set_retval, int, retval) +{ + struct bpf_cg_run_ctx *ctx = + container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); + + ctx->retval = retval; + return 0; +} + +static const struct bpf_func_proto bpf_set_retval_proto = { + .func = bpf_set_retval, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1217,6 +1249,10 @@ cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_current_cgroup_id_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; + case BPF_FUNC_get_retval: + return &bpf_get_retval_proto; + case BPF_FUNC_set_retval: + return &bpf_set_retval_proto; default: return bpf_base_func_proto(func_id); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a9c96c21330a..fe2272defcd9 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5033,6 +5033,22 @@ union bpf_attr { * * Return * The number of arguments of the traced function. + * + * int bpf_get_retval(void) + * Description + * Get the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * The syscall's return value. + * + * int bpf_set_retval(int retval) + * Description + * Set the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5221,6 +5237,8 @@ union bpf_attr { FN(get_func_arg), \ FN(get_func_ret), \ FN(get_func_arg_cnt), \ + FN(get_retval), \ + FN(set_retval), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From c2f2cdbeffda7b153c19e0f3d73149c41026c0db Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:09:52 +0100 Subject: bpf: introduce BPF_F_XDP_HAS_FRAGS flag in prog_flags loading the ebpf program Introduce BPF_F_XDP_HAS_FRAGS and the related field in bpf_prog_aux in order to notify the driver the loaded program support xdp frags. Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/db2e8075b7032a356003f407d1b0deb99adaa0ed.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 5 +++++ kernel/bpf/syscall.c | 4 +++- tools/include/uapi/linux/bpf.h | 5 +++++ 4 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 80e3387ea3af..e93ed028a030 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -933,6 +933,7 @@ struct bpf_prog_aux { bool func_proto_unreliable; bool sleepable; bool tail_call_reachable; + bool xdp_has_frags; struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index fe2272defcd9..945649c67e03 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1113,6 +1113,11 @@ enum bpf_link_type { */ #define BPF_F_SLEEPABLE (1U << 4) +/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program + * fully support xdp frags. + */ +#define BPF_F_XDP_HAS_FRAGS (1U << 5) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 9e0631f091a6..f29090643c6e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2217,7 +2217,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) BPF_F_ANY_ALIGNMENT | BPF_F_TEST_STATE_FREQ | BPF_F_SLEEPABLE | - BPF_F_TEST_RND_HI32)) + BPF_F_TEST_RND_HI32 | + BPF_F_XDP_HAS_FRAGS)) return -EINVAL; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && @@ -2303,6 +2304,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) prog->aux->dst_prog = dst_prog; prog->aux->offload_requested = !!attr->prog_ifindex; prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; + prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; err = security_bpf_prog_alloc(prog->aux); if (err) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index fe2272defcd9..945649c67e03 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1113,6 +1113,11 @@ enum bpf_link_type { */ #define BPF_F_SLEEPABLE (1U << 4) +/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program + * fully support xdp frags. + */ +#define BPF_F_XDP_HAS_FRAGS (1U << 5) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * -- cgit v1.2.3 From 0165cc817075cf701e4289838f1d925ff1911b3e Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:09:54 +0100 Subject: bpf: introduce bpf_xdp_get_buff_len helper Introduce bpf_xdp_get_buff_len helper in order to return the xdp buffer total size (linear and paged area) Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/aac9ac3504c84026cf66a3c71b7c5ae89bc991be.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 14 ++++++++++++++ include/uapi/linux/bpf.h | 7 +++++++ net/core/filter.c | 15 +++++++++++++++ tools/include/uapi/linux/bpf.h | 7 +++++++ 4 files changed, 43 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/xdp.h b/include/net/xdp.h index 8463dea8b4db..52b593321956 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -145,6 +145,20 @@ xdp_get_shared_info_from_buff(struct xdp_buff *xdp) return (struct skb_shared_info *)xdp_data_hard_end(xdp); } +static __always_inline unsigned int xdp_get_buff_len(struct xdp_buff *xdp) +{ + unsigned int len = xdp->data_end - xdp->data; + struct skb_shared_info *sinfo; + + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + + sinfo = xdp_get_shared_info_from_buff(xdp); + len += sinfo->xdp_frags_size; +out: + return len; +} + struct xdp_frame { void *data; u16 len; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 945649c67e03..5a28772063f6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5054,6 +5054,12 @@ union bpf_attr { * This helper is currently supported by cgroup programs only. * Return * 0 on success, or a negative error in case of failure. + * + * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md) + * Description + * Get the total size of a given xdp buff (linear and paged area) + * Return + * The total size of a given xdp buffer. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5244,6 +5250,7 @@ union bpf_attr { FN(get_func_arg_cnt), \ FN(get_retval), \ FN(set_retval), \ + FN(xdp_get_buff_len), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/net/core/filter.c b/net/core/filter.c index f73a84c75970..a7f03bbca465 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3783,6 +3783,19 @@ static const struct bpf_func_proto sk_skb_change_head_proto = { .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; + +BPF_CALL_1(bpf_xdp_get_buff_len, struct xdp_buff*, xdp) +{ + return xdp_get_buff_len(xdp); +} + +static const struct bpf_func_proto bpf_xdp_get_buff_len_proto = { + .func = bpf_xdp_get_buff_len, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) { return xdp_data_meta_unsupported(xdp) ? 0 : @@ -7533,6 +7546,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_xdp_redirect_map_proto; case BPF_FUNC_xdp_adjust_tail: return &bpf_xdp_adjust_tail_proto; + case BPF_FUNC_xdp_get_buff_len: + return &bpf_xdp_get_buff_len_proto; case BPF_FUNC_fib_lookup: return &bpf_xdp_fib_lookup_proto; case BPF_FUNC_check_mtu: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 945649c67e03..5a28772063f6 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5054,6 +5054,12 @@ union bpf_attr { * This helper is currently supported by cgroup programs only. * Return * 0 on success, or a negative error in case of failure. + * + * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md) + * Description + * Get the total size of a given xdp buff (linear and paged area) + * Return + * The total size of a given xdp buffer. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5244,6 +5250,7 @@ union bpf_attr { FN(get_func_arg_cnt), \ FN(get_retval), \ FN(set_retval), \ + FN(xdp_get_buff_len), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 3f364222d032eea6b245780e845ad213dab28cdd Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:10:03 +0100 Subject: net: xdp: introduce bpf_xdp_pointer utility routine Similar to skb_header_pointer, introduce bpf_xdp_pointer utility routine to return a pointer to a given position in the xdp_buff if the requested area (offset + len) is contained in a contiguous memory area otherwise it will be copied in a bounce buffer provided by the caller. Similar to the tc counterpart, introduce the two following xdp helpers: - bpf_xdp_load_bytes - bpf_xdp_store_bytes Reviewed-by: Eelco Chaudron Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Acked-by: Jakub Kicinski Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/ab285c1efdd5b7a9d361348b1e7d3ef49f6382b3.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 18 +++++ net/core/filter.c | 176 ++++++++++++++++++++++++++++++++--------- tools/include/uapi/linux/bpf.h | 18 +++++ 3 files changed, 174 insertions(+), 38 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 5a28772063f6..16a7574292a5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5060,6 +5060,22 @@ union bpf_attr { * Get the total size of a given xdp buff (linear and paged area) * Return * The total size of a given xdp buffer. + * + * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * This helper is provided as an easy way to load data from a + * xdp buffer. It can be used to load *len* bytes from *offset* from + * the frame associated to *xdp_md*, into the buffer pointed by + * *buf*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * Store *len* bytes from buffer *buf* into the frame + * associated to *xdp_md*, at *offset*. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5251,6 +5267,8 @@ union bpf_attr { FN(get_retval), \ FN(set_retval), \ FN(xdp_get_buff_len), \ + FN(xdp_load_bytes), \ + FN(xdp_store_bytes), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/net/core/filter.c b/net/core/filter.c index e4ce138bf925..945ccaaab3cb 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3839,6 +3839,138 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .arg2_type = ARG_ANYTHING, }; +static void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, + void *buf, unsigned long len, bool flush) +{ + unsigned long ptr_len, ptr_off = 0; + skb_frag_t *next_frag, *end_frag; + struct skb_shared_info *sinfo; + void *src, *dst; + u8 *ptr_buf; + + if (likely(xdp->data_end - xdp->data >= off + len)) { + src = flush ? buf : xdp->data + off; + dst = flush ? xdp->data + off : buf; + memcpy(dst, src, len); + return; + } + + sinfo = xdp_get_shared_info_from_buff(xdp); + end_frag = &sinfo->frags[sinfo->nr_frags]; + next_frag = &sinfo->frags[0]; + + ptr_len = xdp->data_end - xdp->data; + ptr_buf = xdp->data; + + while (true) { + if (off < ptr_off + ptr_len) { + unsigned long copy_off = off - ptr_off; + unsigned long copy_len = min(len, ptr_len - copy_off); + + src = flush ? buf : ptr_buf + copy_off; + dst = flush ? ptr_buf + copy_off : buf; + memcpy(dst, src, copy_len); + + off += copy_len; + len -= copy_len; + buf += copy_len; + } + + if (!len || next_frag == end_frag) + break; + + ptr_off += ptr_len; + ptr_buf = skb_frag_address(next_frag); + ptr_len = skb_frag_size(next_frag); + next_frag++; + } +} + +static void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + u32 size = xdp->data_end - xdp->data; + void *addr = xdp->data; + int i; + + if (unlikely(offset > 0xffff || len > 0xffff)) + return ERR_PTR(-EFAULT); + + if (offset + len > xdp_get_buff_len(xdp)) + return ERR_PTR(-EINVAL); + + if (offset < size) /* linear area */ + goto out; + + offset -= size; + for (i = 0; i < sinfo->nr_frags; i++) { /* paged area */ + u32 frag_size = skb_frag_size(&sinfo->frags[i]); + + if (offset < frag_size) { + addr = skb_frag_address(&sinfo->frags[i]); + size = frag_size; + break; + } + offset -= frag_size; + } +out: + return offset + len < size ? addr + offset : NULL; +} + +BPF_CALL_4(bpf_xdp_load_bytes, struct xdp_buff *, xdp, u32, offset, + void *, buf, u32, len) +{ + void *ptr; + + ptr = bpf_xdp_pointer(xdp, offset, len); + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + + if (!ptr) + bpf_xdp_copy_buf(xdp, offset, buf, len, false); + else + memcpy(buf, ptr, len); + + return 0; +} + +static const struct bpf_func_proto bpf_xdp_load_bytes_proto = { + .func = bpf_xdp_load_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; + +BPF_CALL_4(bpf_xdp_store_bytes, struct xdp_buff *, xdp, u32, offset, + void *, buf, u32, len) +{ + void *ptr; + + ptr = bpf_xdp_pointer(xdp, offset, len); + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + + if (!ptr) + bpf_xdp_copy_buf(xdp, offset, buf, len, true); + else + memcpy(ptr, buf, len); + + return 0; +} + +static const struct bpf_func_proto bpf_xdp_store_bytes_proto = { + .func = bpf_xdp_store_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; + static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); @@ -4677,48 +4809,12 @@ static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = { }; #endif -static unsigned long bpf_xdp_copy(void *dst_buff, const void *ctx, +static unsigned long bpf_xdp_copy(void *dst, const void *ctx, unsigned long off, unsigned long len) { struct xdp_buff *xdp = (struct xdp_buff *)ctx; - unsigned long ptr_len, ptr_off = 0; - skb_frag_t *next_frag, *end_frag; - struct skb_shared_info *sinfo; - u8 *ptr_buf; - - if (likely(xdp->data_end - xdp->data >= off + len)) { - memcpy(dst_buff, xdp->data + off, len); - return 0; - } - - sinfo = xdp_get_shared_info_from_buff(xdp); - end_frag = &sinfo->frags[sinfo->nr_frags]; - next_frag = &sinfo->frags[0]; - - ptr_len = xdp->data_end - xdp->data; - ptr_buf = xdp->data; - - while (true) { - if (off < ptr_off + ptr_len) { - unsigned long copy_off = off - ptr_off; - unsigned long copy_len = min(len, ptr_len - copy_off); - - memcpy(dst_buff, ptr_buf + copy_off, copy_len); - - off += copy_len; - len -= copy_len; - dst_buff += copy_len; - } - - if (!len || next_frag == end_frag) - break; - - ptr_off += ptr_len; - ptr_buf = skb_frag_address(next_frag); - ptr_len = skb_frag_size(next_frag); - next_frag++; - } + bpf_xdp_copy_buf(xdp, off, dst, len, false); return 0; } @@ -7660,6 +7756,10 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_xdp_adjust_tail_proto; case BPF_FUNC_xdp_get_buff_len: return &bpf_xdp_get_buff_len_proto; + case BPF_FUNC_xdp_load_bytes: + return &bpf_xdp_load_bytes_proto; + case BPF_FUNC_xdp_store_bytes: + return &bpf_xdp_store_bytes_proto; case BPF_FUNC_fib_lookup: return &bpf_xdp_fib_lookup_proto; case BPF_FUNC_check_mtu: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 5a28772063f6..16a7574292a5 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5060,6 +5060,22 @@ union bpf_attr { * Get the total size of a given xdp buff (linear and paged area) * Return * The total size of a given xdp buffer. + * + * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * This helper is provided as an easy way to load data from a + * xdp buffer. It can be used to load *len* bytes from *offset* from + * the frame associated to *xdp_md*, into the buffer pointed by + * *buf*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * Store *len* bytes from buffer *buf* into the frame + * associated to *xdp_md*, at *offset*. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5251,6 +5267,8 @@ union bpf_attr { FN(get_retval), \ FN(set_retval), \ FN(xdp_get_buff_len), \ + FN(xdp_load_bytes), \ + FN(xdp_store_bytes), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 376040e47334c6dc6a939a32197acceb00fe4acf Mon Sep 17 00:00:00 2001 From: Kenny Yu Date: Mon, 24 Jan 2022 10:54:01 -0800 Subject: bpf: Add bpf_copy_from_user_task() helper This adds a helper for bpf programs to read the memory of other tasks. As an example use case at Meta, we are using a bpf task iterator program and this new helper to print C++ async stack traces for all threads of a given process. Signed-off-by: Kenny Yu Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20220124185403.468466-3-kennyyu@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 11 +++++++++++ kernel/bpf/helpers.c | 34 ++++++++++++++++++++++++++++++++++ kernel/trace/bpf_trace.c | 2 ++ tools/include/uapi/linux/bpf.h | 11 +++++++++++ 5 files changed, 59 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8c92c974bd12..394305a5e02f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2243,6 +2243,7 @@ extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; extern const struct bpf_func_proto bpf_find_vma_proto; extern const struct bpf_func_proto bpf_loop_proto; extern const struct bpf_func_proto bpf_strncmp_proto; +extern const struct bpf_func_proto bpf_copy_from_user_task_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 16a7574292a5..4a2f7041ebae 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5076,6 +5076,16 @@ union bpf_attr { * associated to *xdp_md*, at *offset*. * Return * 0 on success, or a negative error in case of failure. + * + * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags) + * Description + * Read *size* bytes from user space address *user_ptr* in *tsk*'s + * address space, and stores the data in *dst*. *flags* is not + * used yet and is provided for future extensibility. This helper + * can only be used by sleepable programs. + * Return + * 0 on success, or a negative error in case of failure. On error + * *dst* buffer is zeroed out. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5269,6 +5279,7 @@ union bpf_attr { FN(xdp_get_buff_len), \ FN(xdp_load_bytes), \ FN(xdp_store_bytes), \ + FN(copy_from_user_task), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 01cfdf40c838..ed2780b76cc1 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "../../lib/kstrtox.h" @@ -671,6 +672,39 @@ const struct bpf_func_proto bpf_copy_from_user_proto = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_5(bpf_copy_from_user_task, void *, dst, u32, size, + const void __user *, user_ptr, struct task_struct *, tsk, u64, flags) +{ + int ret; + + /* flags is not used yet */ + if (unlikely(flags)) + return -EINVAL; + + if (unlikely(!size)) + return 0; + + ret = access_process_vm(tsk, (unsigned long)user_ptr, dst, size, 0); + if (ret == size) + return 0; + + memset(dst, 0, size); + /* Return -EFAULT for partial read */ + return ret < 0 ? ret : -EFAULT; +} + +const struct bpf_func_proto bpf_copy_from_user_task_proto = { + .func = bpf_copy_from_user_task, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_BTF_ID, + .arg4_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], + .arg5_type = ARG_ANYTHING +}; + BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu) { if (cpu >= nr_cpu_ids) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 06a9e220069e..a2024ba32a20 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1235,6 +1235,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_task_stack_proto; case BPF_FUNC_copy_from_user: return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL; + case BPF_FUNC_copy_from_user_task: + return prog->aux->sleepable ? &bpf_copy_from_user_task_proto : NULL; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; case BPF_FUNC_per_cpu_ptr: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 16a7574292a5..4a2f7041ebae 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5076,6 +5076,16 @@ union bpf_attr { * associated to *xdp_md*, at *offset*. * Return * 0 on success, or a negative error in case of failure. + * + * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags) + * Description + * Read *size* bytes from user space address *user_ptr* in *tsk*'s + * address space, and stores the data in *dst*. *flags* is not + * used yet and is provided for future extensibility. This helper + * can only be used by sleepable programs. + * Return + * 0 on success, or a negative error in case of failure. On error + * *dst* buffer is zeroed out. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5269,6 +5279,7 @@ union bpf_attr { FN(xdp_get_buff_len), \ FN(xdp_load_bytes), \ FN(xdp_store_bytes), \ + FN(copy_from_user_task), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 9690ae60429020f38e4aa2540c306f27eb021bc0 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 27 Jan 2022 10:42:59 -0800 Subject: ethtool: add header/data split indication For applications running on a mix of platforms it's useful to have a clear indication whether host's NIC supports the geometry requirements of TCP zero-copy. TCP zero-copy Rx requires data to be neatly placed into memory pages. Most NICs can't do that. This patch is adding GET support only, since the NICs I work with either always have the feature enabled or enable it whenever MTU is set to jumbo. In other words I don't need SET. But adding set should be trivial. (The only note on SET is that we will likely want the setting to be "sticky" and use 0 / `unknown` to reset it back to driver default.) Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 8 ++++++++ include/linux/ethtool.h | 2 ++ include/uapi/linux/ethtool_netlink.h | 7 +++++++ net/ethtool/rings.c | 15 ++++++++++----- 4 files changed, 27 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 9d98e0511249..cae28af7a476 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -860,8 +860,16 @@ Kernel response contents: ``ETHTOOL_A_RINGS_RX_JUMBO`` u32 size of RX jumbo ring ``ETHTOOL_A_RINGS_TX`` u32 size of TX ring ``ETHTOOL_A_RINGS_RX_BUF_LEN`` u32 size of buffers on the ring + ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` u8 TCP header / data split ==================================== ====== =========================== +``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` indicates whether the device is usable with +page-flipping TCP zero-copy receive (``getsockopt(TCP_ZEROCOPY_RECEIVE)``). +If enabled the device is configured to place frame headers and data into +separate buffers. The device configuration must make it possible to receive +full memory pages of data, for example because MTU is high enough or through +HW-GRO. + RINGS_SET ========= diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 11efc45de66a..e0853f48b75e 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -70,9 +70,11 @@ enum { /** * struct kernel_ethtool_ringparam - RX/TX ring configuration * @rx_buf_len: Current length of buffers on the rx ring. + * @tcp_data_split: Scatter packet headers and data to separate buffers */ struct kernel_ethtool_ringparam { u32 rx_buf_len; + u8 tcp_data_split; }; /** diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index cca6e474a085..417d4280d7b5 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -318,6 +318,12 @@ enum { /* RINGS */ +enum { + ETHTOOL_TCP_DATA_SPLIT_UNKNOWN = 0, + ETHTOOL_TCP_DATA_SPLIT_DISABLED, + ETHTOOL_TCP_DATA_SPLIT_ENABLED, +}; + enum { ETHTOOL_A_RINGS_UNSPEC, ETHTOOL_A_RINGS_HEADER, /* nest - _A_HEADER_* */ @@ -330,6 +336,7 @@ enum { ETHTOOL_A_RINGS_RX_JUMBO, /* u32 */ ETHTOOL_A_RINGS_TX, /* u32 */ ETHTOOL_A_RINGS_RX_BUF_LEN, /* u32 */ + ETHTOOL_A_RINGS_TCP_DATA_SPLIT, /* u8 */ /* add new constants above here */ __ETHTOOL_A_RINGS_CNT, diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c index c1d5f5e0fdc9..18a5035d3bee 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -53,7 +53,8 @@ static int rings_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u32)) + /* _RINGS_RX_MINI */ nla_total_size(sizeof(u32)) + /* _RINGS_RX_JUMBO */ nla_total_size(sizeof(u32)) + /* _RINGS_TX */ - nla_total_size(sizeof(u32)); /* _RINGS_RX_BUF_LEN */ + nla_total_size(sizeof(u32)) + /* _RINGS_RX_BUF_LEN */ + nla_total_size(sizeof(u8)); /* _RINGS_TCP_DATA_SPLIT */ } static int rings_fill_reply(struct sk_buff *skb, @@ -61,9 +62,11 @@ static int rings_fill_reply(struct sk_buff *skb, const struct ethnl_reply_data *reply_base) { const struct rings_reply_data *data = RINGS_REPDATA(reply_base); - const struct kernel_ethtool_ringparam *kernel_ringparam = &data->kernel_ringparam; + const struct kernel_ethtool_ringparam *kr = &data->kernel_ringparam; const struct ethtool_ringparam *ringparam = &data->ringparam; + WARN_ON(kr->tcp_data_split > ETHTOOL_TCP_DATA_SPLIT_ENABLED); + if ((ringparam->rx_max_pending && (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_MAX, ringparam->rx_max_pending) || @@ -84,9 +87,11 @@ static int rings_fill_reply(struct sk_buff *skb, ringparam->tx_max_pending) || nla_put_u32(skb, ETHTOOL_A_RINGS_TX, ringparam->tx_pending))) || - (kernel_ringparam->rx_buf_len && - (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_BUF_LEN, - kernel_ringparam->rx_buf_len)))) + (kr->rx_buf_len && + (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_BUF_LEN, kr->rx_buf_len))) || + (kr->tcp_data_split && + (nla_put_u8(skb, ETHTOOL_A_RINGS_TCP_DATA_SPLIT, + kr->tcp_data_split)))) return -EMSGSIZE; return 0; -- cgit v1.2.3 From e187013abeb4c2a7ec8a4bb978844c7e92a1a6ec Mon Sep 17 00:00:00 2001 From: Akhmat Karakotov Date: Mon, 31 Jan 2022 16:31:21 +0300 Subject: txhash: Make rethinking txhash behavior configurable via sysctl Add a per ns sysctl that controls the txhash rethink behavior: net.core.txrehash. When enabled, the same behavior is retained, when disabled, rethink is not performed. Sysctl is enabled by default. Signed-off-by: Akhmat Karakotov Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/netns/core.h | 1 + include/net/sock.h | 34 +++++++++++++++++++++------------- include/uapi/linux/socket.h | 3 +++ net/core/net_namespace.c | 2 ++ net/core/sysctl_net_core.c | 14 ++++++++++++-- 5 files changed, 39 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/netns/core.h b/include/net/netns/core.h index 552bc25b1933..388244e315e7 100644 --- a/include/net/netns/core.h +++ b/include/net/netns/core.h @@ -10,6 +10,7 @@ struct netns_core { struct ctl_table_header *sysctl_hdr; int sysctl_somaxconn; + u8 sysctl_txrehash; #ifdef CONFIG_PROC_FS struct prot_inuse __percpu *prot_inuse; diff --git a/include/net/sock.h b/include/net/sock.h index ff9b508d9c5f..0540e1b2aeb0 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -587,6 +587,18 @@ static inline bool sk_user_data_is_nocopy(const struct sock *sk) __tmp | SK_USER_DATA_NOCOPY); \ }) +static inline +struct net *sock_net(const struct sock *sk) +{ + return read_pnet(&sk->sk_net); +} + +static inline +void sock_net_set(struct sock *sk, struct net *net) +{ + write_pnet(&sk->sk_net, net); +} + /* * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK * or not whether his port will be reused by someone else. SK_FORCE_REUSE @@ -2054,10 +2066,18 @@ static inline void sk_set_txhash(struct sock *sk) static inline bool sk_rethink_txhash(struct sock *sk) { - if (sk->sk_txhash) { + u8 rehash; + + if (!sk->sk_txhash) + return false; + + rehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); + + if (rehash) { sk_set_txhash(sk); return true; } + return false; } @@ -2704,18 +2724,6 @@ static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) __kfree_skb(skb); } -static inline -struct net *sock_net(const struct sock *sk) -{ - return read_pnet(&sk->sk_net); -} - -static inline -void sock_net_set(struct sock *sk, struct net *net) -{ - write_pnet(&sk->sk_net, net); -} - static inline bool skb_sk_is_prefetched(struct sk_buff *skb) { diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h index eb0a9a5b6e71..0accd6102ece 100644 --- a/include/uapi/linux/socket.h +++ b/include/uapi/linux/socket.h @@ -31,4 +31,7 @@ struct __kernel_sockaddr_storage { #define SOCK_BUF_LOCK_MASK (SOCK_SNDBUF_LOCK | SOCK_RCVBUF_LOCK) +#define SOCK_TXREHASH_DISABLED 0 +#define SOCK_TXREHASH_ENABLED 1 + #endif /* _UAPI_LINUX_SOCKET_H */ diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index c53d9aab38ab..8711350085d6 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -364,6 +364,8 @@ out_undo: static int __net_init net_defaults_init_net(struct net *net) { net->core.sysctl_somaxconn = SOMAXCONN; + net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED; + return 0; } diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 7b4d485aac7a..dbeb8ecbcd98 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -593,6 +593,15 @@ static struct ctl_table netns_core_table[] = { .extra1 = SYSCTL_ZERO, .proc_handler = proc_dointvec_minmax }, + { + .procname = "txrehash", + .data = &init_net.core.sysctl_txrehash, + .maxlen = sizeof(u8), + .mode = 0644, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + .proc_handler = proc_dou8vec_minmax, + }, { } }; @@ -611,7 +620,7 @@ __setup("fb_tunnels=", fb_tunnels_only_for_init_net_sysctl_setup); static __net_init int sysctl_core_net_init(struct net *net) { - struct ctl_table *tbl; + struct ctl_table *tbl, *tmp; tbl = netns_core_table; if (!net_eq(net, &init_net)) { @@ -619,7 +628,8 @@ static __net_init int sysctl_core_net_init(struct net *net) if (tbl == NULL) goto err_dup; - tbl[0].data = &net->core.sysctl_somaxconn; + for (tmp = tbl; tmp->procname; tmp++) + tmp->data += (char *)net - (char *)&init_net; /* Don't export any sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) { -- cgit v1.2.3 From 26859240e4ee701e0379f08634957adaff67e43a Mon Sep 17 00:00:00 2001 From: Akhmat Karakotov Date: Mon, 31 Jan 2022 16:31:22 +0300 Subject: txhash: Add socket option to control TX hash rethink behavior Add the SO_TXREHASH socket option to control hash rethink behavior per socket. When default mode is set, sockets disable rehash at initialization and use sysctl option when entering listen state. setsockopt() overrides default behavior. Signed-off-by: Akhmat Karakotov Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- arch/alpha/include/uapi/asm/socket.h | 2 ++ arch/mips/include/uapi/asm/socket.h | 2 ++ arch/parisc/include/uapi/asm/socket.h | 2 ++ arch/sparc/include/uapi/asm/socket.h | 2 ++ include/net/sock.h | 12 +++--------- include/uapi/asm-generic/socket.h | 2 ++ include/uapi/linux/socket.h | 1 + net/core/sock.c | 13 +++++++++++++ net/ipv4/inet_connection_sock.c | 3 +++ 9 files changed, 30 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 284d28755b8d..7d81535893af 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -133,6 +133,8 @@ #define SO_RESERVE_MEM 73 +#define SO_TXREHASH 74 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 24e0efb360f6..1d55e57b8466 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -144,6 +144,8 @@ #define SO_RESERVE_MEM 73 +#define SO_TXREHASH 74 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 845ddc63c882..654061e0964e 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -125,6 +125,8 @@ #define SO_RESERVE_MEM 0x4047 +#define SO_TXREHASH 0x4048 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 2672dd03faf3..666f81e617ea 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -126,6 +126,8 @@ #define SO_RESERVE_MEM 0x0052 +#define SO_TXREHASH 0x0053 + #if !defined(__KERNEL__) diff --git a/include/net/sock.h b/include/net/sock.h index 0540e1b2aeb0..d6c13f0fba40 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -316,6 +316,7 @@ struct sk_filter; * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting * @sk_txhash: computed flow hash for use on transmit + * @sk_txrehash: enable TX hash rethink * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer * @sk_stamp: time stamp of last packet received @@ -491,6 +492,7 @@ struct sock { u32 sk_ack_backlog; u32 sk_max_ack_backlog; kuid_t sk_uid; + u8 sk_txrehash; #ifdef CONFIG_NET_RX_BUSY_POLL u8 sk_prefer_busy_poll; u16 sk_busy_poll_budget; @@ -2066,18 +2068,10 @@ static inline void sk_set_txhash(struct sock *sk) static inline bool sk_rethink_txhash(struct sock *sk) { - u8 rehash; - - if (!sk->sk_txhash) - return false; - - rehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); - - if (rehash) { + if (sk->sk_txhash && sk->sk_txrehash == SOCK_TXREHASH_ENABLED) { sk_set_txhash(sk); return true; } - return false; } diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index c77a1313b3b0..467ca2f28760 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -128,6 +128,8 @@ #define SO_RESERVE_MEM 73 +#define SO_TXREHASH 74 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h index 0accd6102ece..51d6bb2f6765 100644 --- a/include/uapi/linux/socket.h +++ b/include/uapi/linux/socket.h @@ -31,6 +31,7 @@ struct __kernel_sockaddr_storage { #define SOCK_BUF_LOCK_MASK (SOCK_SNDBUF_LOCK | SOCK_RCVBUF_LOCK) +#define SOCK_TXREHASH_DEFAULT ((u8)-1) #define SOCK_TXREHASH_DISABLED 0 #define SOCK_TXREHASH_ENABLED 1 diff --git a/net/core/sock.c b/net/core/sock.c index cccf21f3618d..5e711b42898f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1447,6 +1447,14 @@ set_sndbuf: break; } + case SO_TXREHASH: + if (val < -1 || val > 1) { + ret = -EINVAL; + break; + } + sk->sk_txrehash = (u8)val; + break; + default: ret = -ENOPROTOOPT; break; @@ -1834,6 +1842,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_reserved_mem; break; + case SO_TXREHASH: + v.val = sk->sk_txrehash; + break; + default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). @@ -3279,6 +3291,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_pacing_rate = ~0UL; WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; + sk->sk_txrehash = SOCK_TXREHASH_DEFAULT; sk_rx_queue_clear(sk); /* diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index fc2a985f6064..b81fb13fc5f4 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1046,6 +1046,9 @@ int inet_csk_listen_start(struct sock *sk) sk->sk_ack_backlog = 0; inet_csk_delack_init(sk); + if (sk->sk_txrehash == SOCK_TXREHASH_DEFAULT) + sk->sk_txrehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); + /* There is race window here: we announce ourselves listening, * but this transition is still not validated by get_port(). * It is OK, because this socket enters to hash table only -- cgit v1.2.3 From 4421a582718ab81608d8486734c18083b822390d Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Sun, 30 Jan 2022 12:55:17 +0100 Subject: bpf: Make dst_port field in struct bpf_sock 16-bit wide Menglong Dong reports that the documentation for the dst_port field in struct bpf_sock is inaccurate and confusing. From the BPF program PoV, the field is a zero-padded 16-bit integer in network byte order. The value appears to the BPF user as if laid out in memory as so: offsetof(struct bpf_sock, dst_port) + 0 + 8 +16 0x00 +24 0x00 32-, 16-, and 8-bit wide loads from the field are all allowed, but only if the offset into the field is 0. 32-bit wide loads from dst_port are especially confusing. The loaded value, after converting to host byte order with bpf_ntohl(dst_port), contains the port number in the upper 16-bits. Remove the confusion by splitting the field into two 16-bit fields. For backward compatibility, allow 32-bit wide loads from offsetof(struct bpf_sock, dst_port). While at it, allow loads 8-bit loads at offset [0] and [1] from dst_port. Reported-by: Menglong Dong Signed-off-by: Jakub Sitnicki Link: https://lore.kernel.org/r/20220130115518.213259-2-jakub@cloudflare.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 3 ++- net/core/filter.c | 10 +++++++++- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4a2f7041ebae..a7f0ddedac1f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5574,7 +5574,8 @@ struct bpf_sock { __u32 src_ip4; __u32 src_ip6[4]; __u32 src_port; /* host byte order */ - __u32 dst_port; /* network byte order */ + __be16 dst_port; /* network byte order */ + __u16 :16; /* zero padding */ __u32 dst_ip4; __u32 dst_ip6[4]; __u32 state; diff --git a/net/core/filter.c b/net/core/filter.c index a06931c27eeb..99a05199a806 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8265,6 +8265,7 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); + int field_size; if (off < 0 || off >= sizeof(struct bpf_sock)) return false; @@ -8276,7 +8277,6 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, case offsetof(struct bpf_sock, family): case offsetof(struct bpf_sock, type): case offsetof(struct bpf_sock, protocol): - case offsetof(struct bpf_sock, dst_port): case offsetof(struct bpf_sock, src_port): case offsetof(struct bpf_sock, rx_queue_mapping): case bpf_ctx_range(struct bpf_sock, src_ip4): @@ -8285,6 +8285,14 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); + case bpf_ctx_range(struct bpf_sock, dst_port): + field_size = size == size_default ? + size_default : sizeof_field(struct bpf_sock, dst_port); + bpf_ctx_record_field_size(info, field_size); + return bpf_ctx_narrow_access_ok(off, size, field_size); + case offsetofend(struct bpf_sock, dst_port) ... + offsetof(struct bpf_sock, dst_ip4) - 1: + return false; } return size == size_default; -- cgit v1.2.3 From 8b5413647262dda8d8d0e07e14ea1de9ac7cf0b2 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Mon, 17 Jan 2022 21:56:13 +0100 Subject: netfilter: nfqueue: enable to get skb->priority This info could be useful to improve traffic analysis. Signed-off-by: Nicolas Dichtel Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nfnetlink_queue.h | 1 + net/netfilter/nfnetlink_queue.c | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nfnetlink_queue.h b/include/uapi/linux/netfilter/nfnetlink_queue.h index aed90c4df0c8..ef7c97f21a15 100644 --- a/include/uapi/linux/netfilter/nfnetlink_queue.h +++ b/include/uapi/linux/netfilter/nfnetlink_queue.h @@ -61,6 +61,7 @@ enum nfqnl_attr_type { NFQA_SECCTX, /* security context string */ NFQA_VLAN, /* nested attribute: packet vlan info */ NFQA_L2HDR, /* full L2 header */ + NFQA_PRIORITY, /* skb->priority */ __NFQA_MAX }; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index ea2d9c2a44cf..48d7a59c6482 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -402,6 +402,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, + nla_total_size(sizeof(u_int32_t)) /* ifindex */ #endif + nla_total_size(sizeof(u_int32_t)) /* mark */ + + nla_total_size(sizeof(u_int32_t)) /* priority */ + nla_total_size(sizeof(struct nfqnl_msg_packet_hw)) + nla_total_size(sizeof(u_int32_t)) /* skbinfo */ + nla_total_size(sizeof(u_int32_t)); /* cap_len */ @@ -559,6 +560,10 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, nla_put_be32(skb, NFQA_MARK, htonl(entskb->mark))) goto nla_put_failure; + if (entskb->priority && + nla_put_be32(skb, NFQA_PRIORITY, htonl(entskb->priority))) + goto nla_put_failure; + if (indev && entskb->dev && skb_mac_header_was_set(entskb) && skb_mac_header_len(entskb) != 0) { -- cgit v1.2.3 From be847673cfffce8bb6e9ed6ae186081280c58831 Mon Sep 17 00:00:00 2001 From: Justin Iurman Date: Wed, 2 Feb 2022 15:25:53 +0100 Subject: uapi: ioam: Insertion frequency Add the insertion frequency uapi for IOAM lwtunnels. Signed-off-by: Justin Iurman Signed-off-by: Jakub Kicinski --- include/uapi/linux/ioam6_iptunnel.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ioam6_iptunnel.h b/include/uapi/linux/ioam6_iptunnel.h index 829ffdfcacca..38f6a8fdfd34 100644 --- a/include/uapi/linux/ioam6_iptunnel.h +++ b/include/uapi/linux/ioam6_iptunnel.h @@ -41,6 +41,15 @@ enum { /* IOAM Trace Header */ IOAM6_IPTUNNEL_TRACE, /* struct ioam6_trace_hdr */ + /* Insertion frequency: + * "k over n" packets (0 < k <= n) + * [0.0001% ... 100%] + */ +#define IOAM6_IPTUNNEL_FREQ_MIN 1 +#define IOAM6_IPTUNNEL_FREQ_MAX 1000000 + IOAM6_IPTUNNEL_FREQ_K, /* u32 */ + IOAM6_IPTUNNEL_FREQ_N, /* u32 */ + __IOAM6_IPTUNNEL_MAX, }; -- cgit v1.2.3 From 63ed1aab3d40aa61aaa66819bdce9377ac7f40fa Mon Sep 17 00:00:00 2001 From: Matt Johnston Date: Wed, 9 Feb 2022 12:05:57 +0800 Subject: mctp: Add SIOCMCTP{ALLOC,DROP}TAG ioctls for tag control This change adds a couple of new ioctls for mctp sockets: SIOCMCTPALLOCTAG and SIOCMCTPDROPTAG. These ioctls provide facilities for explicit allocation / release of tags, overriding the automatic allocate-on-send/release-on-reply and timeout behaviours. This allows userspace more control over messages that may not fit a simple request/response model. In order to indicate a pre-allocated tag to the sendmsg() syscall, we introduce a new flag to the struct sockaddr_mctp.smctp_tag value: MCTP_TAG_PREALLOC. Additional changes from Jeremy Kerr . Contains a fix that was: Reported-by: kernel test robot Signed-off-by: Matt Johnston Signed-off-by: Jeremy Kerr Signed-off-by: David S. Miller --- Documentation/networking/mctp.rst | 48 ++++++++++ include/net/mctp.h | 11 ++- include/trace/events/mctp.h | 5 +- include/uapi/linux/mctp.h | 18 ++++ net/mctp/af_mctp.c | 189 ++++++++++++++++++++++++++++++++------ net/mctp/route.c | 114 +++++++++++++++++------ 6 files changed, 329 insertions(+), 56 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/mctp.rst b/Documentation/networking/mctp.rst index 46f74bffce0f..c628cb5406d2 100644 --- a/Documentation/networking/mctp.rst +++ b/Documentation/networking/mctp.rst @@ -212,6 +212,54 @@ remote address is already known, or the message does not require a reply. Like the send calls, sockets will only receive responses to requests they have sent (TO=1) and may only respond (TO=0) to requests they have received. +``ioctl(SIOCMCTPALLOCTAG)`` and ``ioctl(SIOCMCTPDROPTAG)`` +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +These tags give applications more control over MCTP message tags, by allocating +(and dropping) tag values explicitly, rather than the kernel automatically +allocating a per-message tag at ``sendmsg()`` time. + +In general, you will only need to use these ioctls if your MCTP protocol does +not fit the usual request/response model. For example, if you need to persist +tags across multiple requests, or a request may generate more than one response. +In these cases, the ioctls allow you to decouple the tag allocation (and +release) from individual message send and receive operations. + +Both ioctls are passed a pointer to a ``struct mctp_ioc_tag_ctl``: + +.. code-block:: C + + struct mctp_ioc_tag_ctl { + mctp_eid_t peer_addr; + __u8 tag; + __u16 flags; + }; + +``SIOCMCTPALLOCTAG`` allocates a tag for a specific peer, which an application +can use in future ``sendmsg()`` calls. The application populates the +``peer_addr`` member with the remote EID. Other fields must be zero. + +On return, the ``tag`` member will be populated with the allocated tag value. +The allocated tag will have the following tag bits set: + + - ``MCTP_TAG_OWNER``: it only makes sense to allocate tags if you're the tag + owner + + - ``MCTP_TAG_PREALLOC``: to indicate to ``sendmsg()`` that this is a + preallocated tag. + + - ... and the actual tag value, within the least-significant three bits + (``MCTP_TAG_MASK``). Note that zero is a valid tag value. + +The tag value should be used as-is for the ``smctp_tag`` member of ``struct +sockaddr_mctp``. + +``SIOCMCTPDROPTAG`` releases a tag that has been previously allocated by a +``SIOCMCTPALLOCTAG`` ioctl. The ``peer_addr`` must be the same as used for the +allocation, and the ``tag`` value must match exactly the tag returned from the +allocation (including the ``MCTP_TAG_OWNER`` and ``MCTP_TAG_PREALLOC`` bits). +The ``flags`` field must be zero. + Kernel internals ================ diff --git a/include/net/mctp.h b/include/net/mctp.h index 706d329dd8e8..e80a4baf8379 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -126,7 +126,7 @@ struct mctp_sock { */ struct mctp_sk_key { mctp_eid_t peer_addr; - mctp_eid_t local_addr; + mctp_eid_t local_addr; /* MCTP_ADDR_ANY for local owned tags */ __u8 tag; /* incoming tag match; invert TO for local */ /* we hold a ref to sk when set */ @@ -163,6 +163,12 @@ struct mctp_sk_key { */ unsigned long dev_flow_state; struct mctp_dev *dev; + + /* a tag allocated with SIOCMCTPALLOCTAG ioctl will not expire + * automatically on timeout or response, instead SIOCMCTPDROPTAG + * is used. + */ + bool manual_alloc; }; struct mctp_skb_cb { @@ -239,6 +245,9 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag); void mctp_key_unref(struct mctp_sk_key *key); +struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, + mctp_eid_t daddr, mctp_eid_t saddr, + bool manual, u8 *tagp); /* routing <--> device interface */ unsigned int mctp_default_net(struct net *net); diff --git a/include/trace/events/mctp.h b/include/trace/events/mctp.h index 175b057c507f..165cf25f77a7 100644 --- a/include/trace/events/mctp.h +++ b/include/trace/events/mctp.h @@ -15,6 +15,7 @@ enum { MCTP_TRACE_KEY_REPLIED, MCTP_TRACE_KEY_INVALIDATED, MCTP_TRACE_KEY_CLOSED, + MCTP_TRACE_KEY_DROPPED, }; #endif /* __TRACE_MCTP_ENUMS */ @@ -22,6 +23,7 @@ TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_TIMEOUT); TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_REPLIED); TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_INVALIDATED); TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_CLOSED); +TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_DROPPED); TRACE_EVENT(mctp_key_acquire, TP_PROTO(const struct mctp_sk_key *key), @@ -66,7 +68,8 @@ TRACE_EVENT(mctp_key_release, { MCTP_TRACE_KEY_TIMEOUT, "timeout" }, { MCTP_TRACE_KEY_REPLIED, "replied" }, { MCTP_TRACE_KEY_INVALIDATED, "invalidated" }, - { MCTP_TRACE_KEY_CLOSED, "closed" }) + { MCTP_TRACE_KEY_CLOSED, "closed" }, + { MCTP_TRACE_KEY_DROPPED, "dropped" }) ) ); diff --git a/include/uapi/linux/mctp.h b/include/uapi/linux/mctp.h index 07b0318716fc..154ab56651f1 100644 --- a/include/uapi/linux/mctp.h +++ b/include/uapi/linux/mctp.h @@ -44,7 +44,25 @@ struct sockaddr_mctp_ext { #define MCTP_TAG_MASK 0x07 #define MCTP_TAG_OWNER 0x08 +#define MCTP_TAG_PREALLOC 0x10 #define MCTP_OPT_ADDR_EXT 1 +#define SIOCMCTPALLOCTAG (SIOCPROTOPRIVATE + 0) +#define SIOCMCTPDROPTAG (SIOCPROTOPRIVATE + 1) + +struct mctp_ioc_tag_ctl { + mctp_eid_t peer_addr; + + /* For SIOCMCTPALLOCTAG: must be passed as zero, kernel will + * populate with the allocated tag value. Returned tag value will + * always have TO and PREALLOC set. + * + * For SIOCMCTPDROPTAG: userspace provides tag value to drop, from + * a prior SIOCMCTPALLOCTAG call (and so must have TO and PREALLOC set). + */ + __u8 tag; + __u16 flags; +}; + #endif /* __UAPI_MCTP_H */ diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index c921de63b494..f0702d920d8d 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -6,6 +6,7 @@ * Copyright (c) 2021 Google */ +#include #include #include #include @@ -21,6 +22,8 @@ /* socket implementation */ +static void mctp_sk_expire_keys(struct timer_list *timer); + static int mctp_release(struct socket *sock) { struct sock *sk = sock->sk; @@ -99,13 +102,20 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) struct sk_buff *skb; if (addr) { + const u8 tagbits = MCTP_TAG_MASK | MCTP_TAG_OWNER | + MCTP_TAG_PREALLOC; + if (addrlen < sizeof(struct sockaddr_mctp)) return -EINVAL; if (addr->smctp_family != AF_MCTP) return -EINVAL; if (!mctp_sockaddr_is_ok(addr)) return -EINVAL; - if (addr->smctp_tag & ~(MCTP_TAG_MASK | MCTP_TAG_OWNER)) + if (addr->smctp_tag & ~tagbits) + return -EINVAL; + /* can't preallocate a non-owned tag */ + if (addr->smctp_tag & MCTP_TAG_PREALLOC && + !(addr->smctp_tag & MCTP_TAG_OWNER)) return -EINVAL; } else { @@ -248,6 +258,32 @@ out_free: return rc; } +/* We're done with the key; invalidate, stop reassembly, and remove from lists. + */ +static void __mctp_key_remove(struct mctp_sk_key *key, struct net *net, + unsigned long flags, unsigned long reason) +__releases(&key->lock) +__must_hold(&net->mctp.keys_lock) +{ + struct sk_buff *skb; + + trace_mctp_key_release(key, reason); + skb = key->reasm_head; + key->reasm_head = NULL; + key->reasm_dead = true; + key->valid = false; + mctp_dev_release_key(key->dev, key); + spin_unlock_irqrestore(&key->lock, flags); + + hlist_del(&key->hlist); + hlist_del(&key->sklist); + + /* unref for the lists */ + mctp_key_unref(key); + + kfree_skb(skb); +} + static int mctp_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { @@ -293,6 +329,115 @@ static int mctp_getsockopt(struct socket *sock, int level, int optname, return -EINVAL; } +static int mctp_ioctl_alloctag(struct mctp_sock *msk, unsigned long arg) +{ + struct net *net = sock_net(&msk->sk); + struct mctp_sk_key *key = NULL; + struct mctp_ioc_tag_ctl ctl; + unsigned long flags; + u8 tag; + + if (copy_from_user(&ctl, (void __user *)arg, sizeof(ctl))) + return -EFAULT; + + if (ctl.tag) + return -EINVAL; + + if (ctl.flags) + return -EINVAL; + + key = mctp_alloc_local_tag(msk, ctl.peer_addr, MCTP_ADDR_ANY, + true, &tag); + if (IS_ERR(key)) + return PTR_ERR(key); + + ctl.tag = tag | MCTP_TAG_OWNER | MCTP_TAG_PREALLOC; + if (copy_to_user((void __user *)arg, &ctl, sizeof(ctl))) { + spin_lock_irqsave(&key->lock, flags); + __mctp_key_remove(key, net, flags, MCTP_TRACE_KEY_DROPPED); + mctp_key_unref(key); + return -EFAULT; + } + + mctp_key_unref(key); + return 0; +} + +static int mctp_ioctl_droptag(struct mctp_sock *msk, unsigned long arg) +{ + struct net *net = sock_net(&msk->sk); + struct mctp_ioc_tag_ctl ctl; + unsigned long flags, fl2; + struct mctp_sk_key *key; + struct hlist_node *tmp; + int rc; + u8 tag; + + if (copy_from_user(&ctl, (void __user *)arg, sizeof(ctl))) + return -EFAULT; + + if (ctl.flags) + return -EINVAL; + + /* Must be a local tag, TO set, preallocated */ + if ((ctl.tag & ~MCTP_TAG_MASK) != (MCTP_TAG_OWNER | MCTP_TAG_PREALLOC)) + return -EINVAL; + + tag = ctl.tag & MCTP_TAG_MASK; + rc = -EINVAL; + + spin_lock_irqsave(&net->mctp.keys_lock, flags); + hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) { + /* we do an irqsave here, even though we know the irq state, + * so we have the flags to pass to __mctp_key_remove + */ + spin_lock_irqsave(&key->lock, fl2); + if (key->manual_alloc && + ctl.peer_addr == key->peer_addr && + tag == key->tag) { + __mctp_key_remove(key, net, fl2, + MCTP_TRACE_KEY_DROPPED); + rc = 0; + } else { + spin_unlock_irqrestore(&key->lock, fl2); + } + } + spin_unlock_irqrestore(&net->mctp.keys_lock, flags); + + return rc; +} + +static int mctp_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk); + + switch (cmd) { + case SIOCMCTPALLOCTAG: + return mctp_ioctl_alloctag(msk, arg); + case SIOCMCTPDROPTAG: + return mctp_ioctl_droptag(msk, arg); + } + + return -EINVAL; +} + +#ifdef CONFIG_COMPAT +static int mctp_compat_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg) +{ + void __user *argp = compat_ptr(arg); + + switch (cmd) { + /* These have compatible ptr layouts */ + case SIOCMCTPALLOCTAG: + case SIOCMCTPDROPTAG: + return mctp_ioctl(sock, cmd, (unsigned long)argp); + } + + return -ENOIOCTLCMD; +} +#endif + static const struct proto_ops mctp_dgram_ops = { .family = PF_MCTP, .release = mctp_release, @@ -302,7 +447,7 @@ static const struct proto_ops mctp_dgram_ops = { .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, - .ioctl = sock_no_ioctl, + .ioctl = mctp_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, @@ -312,6 +457,9 @@ static const struct proto_ops mctp_dgram_ops = { .recvmsg = mctp_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, +#ifdef CONFIG_COMPAT + .compat_ioctl = mctp_compat_ioctl, +#endif }; static void mctp_sk_expire_keys(struct timer_list *timer) @@ -319,7 +467,7 @@ static void mctp_sk_expire_keys(struct timer_list *timer) struct mctp_sock *msk = container_of(timer, struct mctp_sock, key_expiry); struct net *net = sock_net(&msk->sk); - unsigned long next_expiry, flags; + unsigned long next_expiry, flags, fl2; struct mctp_sk_key *key; struct hlist_node *tmp; bool next_expiry_valid = false; @@ -327,15 +475,16 @@ static void mctp_sk_expire_keys(struct timer_list *timer) spin_lock_irqsave(&net->mctp.keys_lock, flags); hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) { - spin_lock(&key->lock); + /* don't expire. manual_alloc is immutable, no locking + * required. + */ + if (key->manual_alloc) + continue; + spin_lock_irqsave(&key->lock, fl2); if (!time_after_eq(key->expiry, jiffies)) { - trace_mctp_key_release(key, MCTP_TRACE_KEY_TIMEOUT); - key->valid = false; - hlist_del_rcu(&key->hlist); - hlist_del_rcu(&key->sklist); - spin_unlock(&key->lock); - mctp_key_unref(key); + __mctp_key_remove(key, net, fl2, + MCTP_TRACE_KEY_TIMEOUT); continue; } @@ -346,7 +495,7 @@ static void mctp_sk_expire_keys(struct timer_list *timer) next_expiry = key->expiry; next_expiry_valid = true; } - spin_unlock(&key->lock); + spin_unlock_irqrestore(&key->lock, fl2); } spin_unlock_irqrestore(&net->mctp.keys_lock, flags); @@ -387,9 +536,9 @@ static void mctp_sk_unhash(struct sock *sk) { struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct net *net = sock_net(sk); + unsigned long flags, fl2; struct mctp_sk_key *key; struct hlist_node *tmp; - unsigned long flags; /* remove from any type-based binds */ mutex_lock(&net->mctp.bind_lock); @@ -399,20 +548,8 @@ static void mctp_sk_unhash(struct sock *sk) /* remove tag allocations */ spin_lock_irqsave(&net->mctp.keys_lock, flags); hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) { - hlist_del(&key->sklist); - hlist_del(&key->hlist); - - trace_mctp_key_release(key, MCTP_TRACE_KEY_CLOSED); - - spin_lock(&key->lock); - kfree_skb(key->reasm_head); - key->reasm_head = NULL; - key->reasm_dead = true; - key->valid = false; - spin_unlock(&key->lock); - - /* key is no longer on the lookup lists, unref */ - mctp_key_unref(key); + spin_lock_irqsave(&key->lock, fl2); + __mctp_key_remove(key, net, fl2, MCTP_TRACE_KEY_CLOSED); } spin_unlock_irqrestore(&net->mctp.keys_lock, flags); } diff --git a/net/mctp/route.c b/net/mctp/route.c index 35f72e99e188..17e3482aa770 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -203,29 +203,38 @@ static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk) return rc; } -/* We're done with the key; unset valid and remove from lists. There may still - * be outstanding refs on the key though... +/* Helper for mctp_route_input(). + * We're done with the key; unlock and unref the key. + * For the usual case of automatic expiry we remove the key from lists. + * In the case that manual allocation is set on a key we release the lock + * and local ref, reset reassembly, but don't remove from lists. */ -static void __mctp_key_unlock_drop(struct mctp_sk_key *key, struct net *net, - unsigned long flags) - __releases(&key->lock) +static void __mctp_key_done_in(struct mctp_sk_key *key, struct net *net, + unsigned long flags, unsigned long reason) +__releases(&key->lock) { struct sk_buff *skb; + trace_mctp_key_release(key, reason); skb = key->reasm_head; key->reasm_head = NULL; - key->reasm_dead = true; - key->valid = false; - mctp_dev_release_key(key->dev, key); + + if (!key->manual_alloc) { + key->reasm_dead = true; + key->valid = false; + mctp_dev_release_key(key->dev, key); + } spin_unlock_irqrestore(&key->lock, flags); - spin_lock_irqsave(&net->mctp.keys_lock, flags); - hlist_del(&key->hlist); - hlist_del(&key->sklist); - spin_unlock_irqrestore(&net->mctp.keys_lock, flags); + if (!key->manual_alloc) { + spin_lock_irqsave(&net->mctp.keys_lock, flags); + hlist_del(&key->hlist); + hlist_del(&key->sklist); + spin_unlock_irqrestore(&net->mctp.keys_lock, flags); - /* one unref for the lists */ - mctp_key_unref(key); + /* unref for the lists */ + mctp_key_unref(key); + } /* and one for the local reference */ mctp_key_unref(key); @@ -379,9 +388,8 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) /* we've hit a pending reassembly; not much we * can do but drop it */ - trace_mctp_key_release(key, - MCTP_TRACE_KEY_REPLIED); - __mctp_key_unlock_drop(key, net, f); + __mctp_key_done_in(key, net, f, + MCTP_TRACE_KEY_REPLIED); key = NULL; } rc = 0; @@ -423,9 +431,8 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) } else { if (key->reasm_head || key->reasm_dead) { /* duplicate start? drop everything */ - trace_mctp_key_release(key, - MCTP_TRACE_KEY_INVALIDATED); - __mctp_key_unlock_drop(key, net, f); + __mctp_key_done_in(key, net, f, + MCTP_TRACE_KEY_INVALIDATED); rc = -EEXIST; key = NULL; } else { @@ -448,10 +455,10 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * the reassembly/response key */ if (!rc && flags & MCTP_HDR_FLAG_EOM) { + msk = container_of(key->sk, struct mctp_sock, sk); sock_queue_rcv_skb(key->sk, key->reasm_head); key->reasm_head = NULL; - trace_mctp_key_release(key, MCTP_TRACE_KEY_REPLIED); - __mctp_key_unlock_drop(key, net, f); + __mctp_key_done_in(key, net, f, MCTP_TRACE_KEY_REPLIED); key = NULL; } @@ -579,9 +586,9 @@ static void mctp_reserve_tag(struct net *net, struct mctp_sk_key *key, /* Allocate a locally-owned tag value for (saddr, daddr), and reserve * it for the socket msk */ -static struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, - mctp_eid_t saddr, - mctp_eid_t daddr, u8 *tagp) +struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, + mctp_eid_t daddr, mctp_eid_t saddr, + bool manual, u8 *tagp) { struct net *net = sock_net(&msk->sk); struct netns_mctp *mns = &net->mctp; @@ -636,6 +643,7 @@ static struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, mctp_reserve_tag(net, key, msk); trace_mctp_key_acquire(key); + key->manual_alloc = manual; *tagp = key->tag; } @@ -649,6 +657,50 @@ static struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, return key; } +static struct mctp_sk_key *mctp_lookup_prealloc_tag(struct mctp_sock *msk, + mctp_eid_t daddr, + u8 req_tag, u8 *tagp) +{ + struct net *net = sock_net(&msk->sk); + struct netns_mctp *mns = &net->mctp; + struct mctp_sk_key *key, *tmp; + unsigned long flags; + + req_tag &= ~(MCTP_TAG_PREALLOC | MCTP_TAG_OWNER); + key = NULL; + + spin_lock_irqsave(&mns->keys_lock, flags); + + hlist_for_each_entry(tmp, &mns->keys, hlist) { + if (tmp->tag != req_tag) + continue; + + if (!mctp_address_matches(tmp->peer_addr, daddr)) + continue; + + if (!tmp->manual_alloc) + continue; + + spin_lock(&tmp->lock); + if (tmp->valid) { + key = tmp; + refcount_inc(&key->refs); + spin_unlock(&tmp->lock); + break; + } + spin_unlock(&tmp->lock); + } + spin_unlock_irqrestore(&mns->keys_lock, flags); + + if (!key) + return ERR_PTR(-ENOENT); + + if (tagp) + *tagp = key->tag; + + return key; +} + /* routing lookups */ static bool mctp_rt_match_eid(struct mctp_route *rt, unsigned int net, mctp_eid_t eid) @@ -843,8 +895,14 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, if (rc) goto out_release; - if (req_tag & MCTP_HDR_FLAG_TO) { - key = mctp_alloc_local_tag(msk, saddr, daddr, &tag); + if (req_tag & MCTP_TAG_OWNER) { + if (req_tag & MCTP_TAG_PREALLOC) + key = mctp_lookup_prealloc_tag(msk, daddr, + req_tag, &tag); + else + key = mctp_alloc_local_tag(msk, daddr, saddr, + false, &tag); + if (IS_ERR(key)) { rc = PTR_ERR(key); goto out_release; @@ -855,7 +913,7 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, tag |= MCTP_HDR_FLAG_TO; } else { key = NULL; - tag = req_tag; + tag = req_tag & MCTP_TAG_MASK; } skb->protocol = htons(ETH_P_MCTP); -- cgit v1.2.3 From 9a69e2b385f443f244a7e8b8bcafe5ccfb0866b4 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Wed, 9 Feb 2022 19:43:32 +0100 Subject: bpf: Make remote_port field in struct bpf_sk_lookup 16-bit wide remote_port is another case of a BPF context field documented as a 32-bit value in network byte order for which the BPF context access converter generates a load of a zero-padded 16-bit integer in network byte order. First such case was dst_port in bpf_sock which got addressed in commit 4421a582718a ("bpf: Make dst_port field in struct bpf_sock 16-bit wide"). Loading 4-bytes from the remote_port offset and converting the value with bpf_ntohl() leads to surprising results, as the expected value is shifted by 16 bits. Reduce the confusion by splitting the field in two - a 16-bit field holding a big-endian integer, and a 16-bit zero-padding anonymous field that follows it. Suggested-by: Alexei Starovoitov Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220209184333.654927-2-jakub@cloudflare.com --- include/uapi/linux/bpf.h | 3 ++- net/bpf/test_run.c | 4 ++-- net/core/filter.c | 3 ++- 3 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a7f0ddedac1f..afe3d0d7f5f2 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6453,7 +6453,8 @@ struct bpf_sk_lookup { __u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */ __u32 remote_ip4; /* Network byte order */ __u32 remote_ip6[4]; /* Network byte order */ - __u32 remote_port; /* Network byte order */ + __be16 remote_port; /* Network byte order */ + __u16 :16; /* Zero padding */ __u32 local_ip4; /* Network byte order */ __u32 local_ip6[4]; /* Network byte order */ __u32 local_port; /* Host byte order */ diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index cb150f756f3d..f08034500813 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -1147,7 +1147,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat if (!range_is_zero(user_ctx, offsetofend(typeof(*user_ctx), local_port), sizeof(*user_ctx))) goto out; - if (user_ctx->local_port > U16_MAX || user_ctx->remote_port > U16_MAX) { + if (user_ctx->local_port > U16_MAX) { ret = -ERANGE; goto out; } @@ -1155,7 +1155,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat ctx.family = (u16)user_ctx->family; ctx.protocol = (u16)user_ctx->protocol; ctx.dport = (u16)user_ctx->local_port; - ctx.sport = (__force __be16)user_ctx->remote_port; + ctx.sport = user_ctx->remote_port; switch (ctx.family) { case AF_INET: diff --git a/net/core/filter.c b/net/core/filter.c index 99a05199a806..83f06d3b2c52 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -10843,7 +10843,8 @@ static bool sk_lookup_is_valid_access(int off, int size, case bpf_ctx_range(struct bpf_sk_lookup, local_ip4): case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]): - case bpf_ctx_range(struct bpf_sk_lookup, remote_port): + case offsetof(struct bpf_sk_lookup, remote_port) ... + offsetof(struct bpf_sk_lookup, local_ip4) - 1: case bpf_ctx_range(struct bpf_sk_lookup, local_port): case bpf_ctx_range(struct bpf_sk_lookup, ingress_ifindex): bpf_ctx_record_field_size(info, sizeof(__u32)); -- cgit v1.2.3 From 5cad527d5ffa9a1c4731bb9c97d2ee93f8960d50 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 9 Feb 2022 14:08:38 +0800 Subject: net: drop_monitor: support drop reason In the commit c504e5c2f964 ("net: skb: introduce kfree_skb_reason()") drop reason is introduced to the tracepoint of kfree_skb. Therefore, drop_monitor is able to report the drop reason to users by netlink. The drop reasons are reported as string to users, which is exactly the same as what we do when reporting it to ftrace. Signed-off-by: Menglong Dong Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20220209060838.55513-1-imagedong@tencent.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/net_dropmon.h | 1 + net/core/drop_monitor.c | 41 ++++++++++++++++++++++++++++++++++------ 2 files changed, 36 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h index 66048cc5d7b3..1bbea8f0681e 100644 --- a/include/uapi/linux/net_dropmon.h +++ b/include/uapi/linux/net_dropmon.h @@ -93,6 +93,7 @@ enum net_dm_attr { NET_DM_ATTR_SW_DROPS, /* flag */ NET_DM_ATTR_HW_DROPS, /* flag */ NET_DM_ATTR_FLOW_ACTION_COOKIE, /* binary */ + NET_DM_ATTR_REASON, /* string */ __NET_DM_ATTR_MAX, NET_DM_ATTR_MAX = __NET_DM_ATTR_MAX - 1 diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 7b288a121a41..4641126b8a20 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -48,6 +48,19 @@ static int trace_state = TRACE_OFF; static bool monitor_hw; +#undef EM +#undef EMe + +#define EM(a, b) [a] = #b, +#define EMe(a, b) [a] = #b + +/* drop_reasons is used to translate 'enum skb_drop_reason' to string, + * which is reported to user space. + */ +static const char * const drop_reasons[] = { + TRACE_SKB_DROP_REASON +}; + /* net_dm_mutex * * An overall lock guarding every operation coming from userspace. @@ -126,6 +139,7 @@ struct net_dm_skb_cb { struct devlink_trap_metadata *hw_metadata; void *pc; }; + enum skb_drop_reason reason; }; #define NET_DM_SKB_CB(__skb) ((struct net_dm_skb_cb *)&((__skb)->cb[0])) @@ -498,6 +512,7 @@ static void net_dm_packet_trace_kfree_skb_hit(void *ignore, { ktime_t tstamp = ktime_get_real(); struct per_cpu_dm_data *data; + struct net_dm_skb_cb *cb; struct sk_buff *nskb; unsigned long flags; @@ -508,7 +523,11 @@ static void net_dm_packet_trace_kfree_skb_hit(void *ignore, if (!nskb) return; - NET_DM_SKB_CB(nskb)->pc = location; + if ((unsigned int)reason >= SKB_DROP_REASON_MAX) + reason = SKB_DROP_REASON_NOT_SPECIFIED; + cb = NET_DM_SKB_CB(nskb); + cb->reason = reason; + cb->pc = location; /* Override the timestamp because we care about the time when the * packet was dropped. */ @@ -553,7 +572,8 @@ static size_t net_dm_in_port_size(void) #define NET_DM_MAX_SYMBOL_LEN 40 -static size_t net_dm_packet_report_size(size_t payload_len) +static size_t net_dm_packet_report_size(size_t payload_len, + enum skb_drop_reason reason) { size_t size; @@ -574,6 +594,8 @@ static size_t net_dm_packet_report_size(size_t payload_len) nla_total_size(sizeof(u32)) + /* NET_DM_ATTR_PROTO */ nla_total_size(sizeof(u16)) + + /* NET_DM_ATTR_REASON */ + nla_total_size(strlen(drop_reasons[reason]) + 1) + /* NET_DM_ATTR_PAYLOAD */ nla_total_size(payload_len); } @@ -606,7 +628,7 @@ nla_put_failure: static int net_dm_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, size_t payload_len) { - u64 pc = (u64)(uintptr_t) NET_DM_SKB_CB(skb)->pc; + struct net_dm_skb_cb *cb = NET_DM_SKB_CB(skb); char buf[NET_DM_MAX_SYMBOL_LEN]; struct nlattr *attr; void *hdr; @@ -620,10 +642,15 @@ static int net_dm_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, if (nla_put_u16(msg, NET_DM_ATTR_ORIGIN, NET_DM_ORIGIN_SW)) goto nla_put_failure; - if (nla_put_u64_64bit(msg, NET_DM_ATTR_PC, pc, NET_DM_ATTR_PAD)) + if (nla_put_u64_64bit(msg, NET_DM_ATTR_PC, (u64)(uintptr_t)cb->pc, + NET_DM_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_string(msg, NET_DM_ATTR_REASON, + drop_reasons[cb->reason])) goto nla_put_failure; - snprintf(buf, sizeof(buf), "%pS", NET_DM_SKB_CB(skb)->pc); + snprintf(buf, sizeof(buf), "%pS", cb->pc); if (nla_put_string(msg, NET_DM_ATTR_SYMBOL, buf)) goto nla_put_failure; @@ -679,7 +706,9 @@ static void net_dm_packet_report(struct sk_buff *skb) if (net_dm_trunc_len) payload_len = min_t(size_t, net_dm_trunc_len, payload_len); - msg = nlmsg_new(net_dm_packet_report_size(payload_len), GFP_KERNEL); + msg = nlmsg_new(net_dm_packet_report_size(payload_len, + NET_DM_SKB_CB(skb)->reason), + GFP_KERNEL); if (!msg) goto out; -- cgit v1.2.3 From a6a6fe27bab48f0d09a64b051e7bde432fcae081 Mon Sep 17 00:00:00 2001 From: "D. Wythe" Date: Thu, 10 Feb 2022 17:11:37 +0800 Subject: net/smc: Dynamic control handshake limitation by socket options This patch aims to add dynamic control for SMC handshake limitation for every smc sockets, in production environment, it is possible for the same applications to handle different service types, and may have different opinion on SMC handshake limitation. This patch try socket options to complete it, since we don't have socket option level for SMC yet, which requires us to implement it at the same time. This patch does the following: - add new socket option level: SOL_SMC. - add new SMC socket option: SMC_LIMIT_HS. - provide getter/setter for SMC socket options. Link: https://lore.kernel.org/all/20f504f961e1a803f85d64229ad84260434203bd.1644323503.git.alibuda@linux.alibaba.com/ Signed-off-by: D. Wythe Signed-off-by: David S. Miller --- include/linux/socket.h | 1 + include/uapi/linux/smc.h | 4 +++ net/smc/af_smc.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++- net/smc/smc.h | 1 + 4 files changed, 74 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 8ef26d89ef49..6f85f5d957ef 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -366,6 +366,7 @@ struct ucred { #define SOL_XDP 283 #define SOL_MPTCP 284 #define SOL_MCTP 285 +#define SOL_SMC 286 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 6c2874fd2c00..343e7450c3a3 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -284,4 +284,8 @@ enum { __SMC_NLA_SEID_TABLE_MAX, SMC_NLA_SEID_TABLE_MAX = __SMC_NLA_SEID_TABLE_MAX - 1 }; + +/* SMC socket options */ +#define SMC_LIMIT_HS 1 /* constraint on smc handshake */ + #endif /* _UAPI_LINUX_SMC_H */ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index a05ffb268c3e..97dcdc0a2107 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2326,7 +2326,8 @@ static int smc_listen(struct socket *sock, int backlog) inet_csk(smc->clcsock->sk)->icsk_af_ops = &smc->af_ops; - tcp_sk(smc->clcsock->sk)->smc_hs_congested = smc_hs_congested; + if (smc->limit_smc_hs) + tcp_sk(smc->clcsock->sk)->smc_hs_congested = smc_hs_congested; rc = kernel_listen(smc->clcsock, backlog); if (rc) { @@ -2621,6 +2622,67 @@ out: return rc ? rc : rc1; } +static int __smc_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct smc_sock *smc; + int val, len; + + smc = smc_sk(sock->sk); + + if (get_user(len, optlen)) + return -EFAULT; + + len = min_t(int, len, sizeof(int)); + + if (len < 0) + return -EINVAL; + + switch (optname) { + case SMC_LIMIT_HS: + val = smc->limit_smc_hs; + break; + default: + return -EOPNOTSUPP; + } + + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &val, len)) + return -EFAULT; + + return 0; +} + +static int __smc_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen) +{ + struct sock *sk = sock->sk; + struct smc_sock *smc; + int val, rc; + + smc = smc_sk(sk); + + lock_sock(sk); + switch (optname) { + case SMC_LIMIT_HS: + if (optlen < sizeof(int)) + return -EINVAL; + if (copy_from_sockptr(&val, optval, sizeof(int))) + return -EFAULT; + + smc->limit_smc_hs = !!val; + rc = 0; + break; + default: + rc = -EOPNOTSUPP; + break; + } + release_sock(sk); + + return rc; +} + static int smc_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { @@ -2630,6 +2692,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, if (level == SOL_TCP && optname == TCP_ULP) return -EOPNOTSUPP; + else if (level == SOL_SMC) + return __smc_setsockopt(sock, level, optname, optval, optlen); smc = smc_sk(sk); @@ -2712,6 +2776,9 @@ static int smc_getsockopt(struct socket *sock, int level, int optname, struct smc_sock *smc; int rc; + if (level == SOL_SMC) + return __smc_getsockopt(sock, level, optname, optval, optlen); + smc = smc_sk(sock->sk); mutex_lock(&smc->clcsock_release_lock); if (!smc->clcsock) { diff --git a/net/smc/smc.h b/net/smc/smc.h index e91e40040d07..7e2693832a1b 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -249,6 +249,7 @@ struct smc_sock { /* smc sock container */ struct work_struct smc_listen_work;/* prepare new accept socket */ struct list_head accept_q; /* sockets to be accepted */ spinlock_t accept_q_lock; /* protects accept_q */ + bool limit_smc_hs; /* put constraint on handshake */ bool use_fallback; /* fallback to tcp */ int fallback_rsn; /* reason for fallback */ u32 peer_diagnosis; /* decline reason from peer */ -- cgit v1.2.3 From f9496b7c1b48ce02cd17a3ee88b1e049c689a222 Mon Sep 17 00:00:00 2001 From: "D. Wythe" Date: Thu, 10 Feb 2022 17:11:38 +0800 Subject: net/smc: Add global configure for handshake limitation by netlink Although we can control SMC handshake limitation through socket options, which means that applications who need it must modify their code. It's quite troublesome for many existing applications. This patch modifies the global default value of SMC handshake limitation through netlink, providing a way to put constraint on handshake without modifies any code for applications. Suggested-by: Tony Lu Signed-off-by: D. Wythe Reviewed-by: Tony Lu Signed-off-by: David S. Miller --- include/net/netns/smc.h | 2 ++ include/uapi/linux/smc.h | 11 +++++++++++ net/smc/af_smc.c | 42 ++++++++++++++++++++++++++++++++++++++++++ net/smc/smc.h | 6 ++++++ net/smc/smc_netlink.c | 15 +++++++++++++++ net/smc/smc_pnet.c | 3 +++ 6 files changed, 79 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h index ea8a9cf2619b..47b166684fd8 100644 --- a/include/net/netns/smc.h +++ b/include/net/netns/smc.h @@ -12,5 +12,7 @@ struct netns_smc { /* protect fback_rsn */ struct mutex mutex_fback_rsn; struct smc_stats_rsn *fback_rsn; + + bool limit_smc_hs; /* constraint on handshake */ }; #endif diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 343e7450c3a3..693f549f6966 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -59,6 +59,9 @@ enum { SMC_NETLINK_DUMP_SEID, SMC_NETLINK_ENABLE_SEID, SMC_NETLINK_DISABLE_SEID, + SMC_NETLINK_DUMP_HS_LIMITATION, + SMC_NETLINK_ENABLE_HS_LIMITATION, + SMC_NETLINK_DISABLE_HS_LIMITATION, }; /* SMC_GENL_FAMILY top level attributes */ @@ -285,6 +288,14 @@ enum { SMC_NLA_SEID_TABLE_MAX = __SMC_NLA_SEID_TABLE_MAX - 1 }; +/* SMC_NETLINK_HS_LIMITATION attributes */ +enum { + SMC_NLA_HS_LIMITATION_UNSPEC, + SMC_NLA_HS_LIMITATION_ENABLED, /* u8 */ + __SMC_NLA_HS_LIMITATION_MAX, + SMC_NLA_HS_LIMITATION_MAX = __SMC_NLA_HS_LIMITATION_MAX - 1 +}; + /* SMC socket options */ #define SMC_LIMIT_HS 1 /* constraint on smc handshake */ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 97dcdc0a2107..246c874de629 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -66,6 +66,45 @@ struct workqueue_struct *smc_close_wq; /* wq for close work */ static void smc_tcp_listen_work(struct work_struct *); static void smc_connect_work(struct work_struct *); +int smc_nl_dump_hs_limitation(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + void *hdr; + + if (cb_ctx->pos[0]) + goto out; + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_DUMP_HS_LIMITATION); + if (!hdr) + return -ENOMEM; + + if (nla_put_u8(skb, SMC_NLA_HS_LIMITATION_ENABLED, + sock_net(skb->sk)->smc.limit_smc_hs)) + goto err; + + genlmsg_end(skb, hdr); + cb_ctx->pos[0] = 1; +out: + return skb->len; +err: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +int smc_nl_enable_hs_limitation(struct sk_buff *skb, struct genl_info *info) +{ + sock_net(skb->sk)->smc.limit_smc_hs = true; + return 0; +} + +int smc_nl_disable_hs_limitation(struct sk_buff *skb, struct genl_info *info) +{ + sock_net(skb->sk)->smc.limit_smc_hs = false; + return 0; +} + static void smc_set_keepalive(struct sock *sk, int val) { struct smc_sock *smc = smc_sk(sk); @@ -3007,6 +3046,9 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol, smc->use_fallback = false; /* assume rdma capability first */ smc->fallback_rsn = 0; + /* default behavior from limit_smc_hs in every net namespace */ + smc->limit_smc_hs = net->smc.limit_smc_hs; + rc = 0; if (!clcsock) { rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, diff --git a/net/smc/smc.h b/net/smc/smc.h index 7e2693832a1b..a096d8af21a0 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -14,6 +14,7 @@ #include #include #include /* __aligned */ +#include #include #include "smc_ib.h" @@ -336,4 +337,9 @@ void smc_fill_gid_list(struct smc_link_group *lgr, struct smc_gidlist *gidlist, struct smc_ib_device *known_dev, u8 *known_gid); +/* smc handshake limitation interface for netlink */ +int smc_nl_dump_hs_limitation(struct sk_buff *skb, struct netlink_callback *cb); +int smc_nl_enable_hs_limitation(struct sk_buff *skb, struct genl_info *info); +int smc_nl_disable_hs_limitation(struct sk_buff *skb, struct genl_info *info); + #endif /* __SMC_H */ diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index f13ab0661ed5..c5a62f6f52ba 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -111,6 +111,21 @@ static const struct genl_ops smc_gen_nl_ops[] = { .flags = GENL_ADMIN_PERM, .doit = smc_nl_disable_seid, }, + { + .cmd = SMC_NETLINK_DUMP_HS_LIMITATION, + /* can be retrieved by unprivileged users */ + .dumpit = smc_nl_dump_hs_limitation, + }, + { + .cmd = SMC_NETLINK_ENABLE_HS_LIMITATION, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_enable_hs_limitation, + }, + { + .cmd = SMC_NETLINK_DISABLE_HS_LIMITATION, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_disable_hs_limitation, + }, }; static const struct nla_policy smc_gen_nl_policy[2] = { diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 0599246c0376..ff61b7b95875 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -870,6 +870,9 @@ int smc_pnet_net_init(struct net *net) smc_pnet_create_pnetids_list(net); + /* disable handshake limitation by default */ + net->smc.limit_smc_hs = 0; + return 0; } -- cgit v1.2.3 From 5cd5a8a3e2fb11b1c8a09f062c44c1e228ef987a Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Mon, 14 Feb 2022 17:29:53 +0100 Subject: cfg80211: Add data structures to capture EHT capabilities And advertise EHT capabilities to user space when supported. Signed-off-by: Ilan Peer Link: https://lore.kernel.org/r/20220214173004.6fb70658529f.I2413a37c8f7d2d6d638038a3d95360a3fce0114d@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 63 ++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/nl80211.h | 12 +++++++++ net/wireless/nl80211.c | 27 +++++++++++++++++++ 3 files changed, 102 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f6db085ff3df..7bec15f605be 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -360,6 +360,48 @@ struct ieee80211_sta_he_cap { u8 ppe_thres[IEEE80211_HE_PPE_THRES_MAX_LEN]; }; +/** + * struct ieee80211_eht_mcs_nss_supp - EHT max supported NSS per MCS + * + * See P802.11be_D1.3 Table 9-401k - "Subfields of the Supported EHT-MCS + * and NSS Set field" + * + * @only_20mhz: MCS/NSS support for 20 MHz-only STA. + * @bw._80: MCS/NSS support for BW <= 80 MHz + * @bw._160: MCS/NSS support for BW = 160 MHz + * @bw._320: MCS/NSS support for BW = 320 MHz + */ +struct ieee80211_eht_mcs_nss_supp { + union { + struct ieee80211_eht_mcs_nss_supp_20mhz_only only_20mhz; + struct { + struct ieee80211_eht_mcs_nss_supp_bw _80; + struct ieee80211_eht_mcs_nss_supp_bw _160; + struct ieee80211_eht_mcs_nss_supp_bw _320; + } __packed bw; + } __packed; +} __packed; + +#define IEEE80211_EHT_PPE_THRES_MAX_LEN 32 + +/** + * struct ieee80211_sta_eht_cap - STA's EHT capabilities + * + * This structure describes most essential parameters needed + * to describe 802.11be EHT capabilities for a STA. + * + * @has_eht: true iff EHT data is valid. + * @eht_cap_elem: Fixed portion of the eht capabilities element. + * @eht_mcs_nss_supp: The supported NSS/MCS combinations. + * @eht_ppe_thres: Holds the PPE Thresholds data. + */ +struct ieee80211_sta_eht_cap { + bool has_eht; + struct ieee80211_eht_cap_elem_fixed eht_cap_elem; + struct ieee80211_eht_mcs_nss_supp eht_mcs_nss_supp; + u8 eht_ppe_thres[IEEE80211_EHT_PPE_THRES_MAX_LEN]; +}; + /** * struct ieee80211_sband_iftype_data - sband data per interface type * @@ -379,6 +421,7 @@ struct ieee80211_sband_iftype_data { u16 types_mask; struct ieee80211_sta_he_cap he_cap; struct ieee80211_he_6ghz_capa he_6ghz_capa; + struct ieee80211_sta_eht_cap eht_cap; struct { const u8 *data; unsigned int len; @@ -561,6 +604,26 @@ ieee80211_get_he_6ghz_capa(const struct ieee80211_supported_band *sband, return data->he_6ghz_capa.capa; } +/** + * ieee80211_get_eht_iftype_cap - return ETH 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_eht_cap, or NULL is none found + */ +static inline const struct ieee80211_sta_eht_cap * +ieee80211_get_eht_iftype_cap(const struct ieee80211_supported_band *sband, + enum nl80211_iftype iftype) +{ + const struct ieee80211_sband_iftype_data *data = + ieee80211_get_sband_iftype_data(sband, iftype); + + if (data && data->eht_cap.has_eht) + return &data->eht_cap; + + return NULL; +} + /** * wiphy_read_of_freq_limits - read frequency limits from device tree * diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 195a238a322e..d305a8b8c536 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3766,6 +3766,14 @@ enum nl80211_mpath_info { * given for all 6 GHz band channels * @NL80211_BAND_IFTYPE_ATTR_VENDOR_ELEMS: vendor element capabilities that are * advertised on this band/for this iftype (binary) + * @NL80211_BAND_IFTYPE_ATTR_EHT_CAP_MAC: EHT MAC capabilities as in EHT + * capabilities element + * @NL80211_BAND_IFTYPE_ATTR_EHT_CAP_PHY: EHT PHY capabilities as in EHT + * capabilities element + * @NL80211_BAND_IFTYPE_ATTR_EHT_CAP_MCS_SET: EHT supported NSS/MCS as in EHT + * capabilities element + * @NL80211_BAND_IFTYPE_ATTR_EHT_CAP_PPE: EHT PPE thresholds information as + * defined in EHT capabilities element * @__NL80211_BAND_IFTYPE_ATTR_AFTER_LAST: internal use * @NL80211_BAND_IFTYPE_ATTR_MAX: highest band attribute currently defined */ @@ -3779,6 +3787,10 @@ enum nl80211_band_iftype_attr { NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE, NL80211_BAND_IFTYPE_ATTR_HE_6GHZ_CAPA, NL80211_BAND_IFTYPE_ATTR_VENDOR_ELEMS, + NL80211_BAND_IFTYPE_ATTR_EHT_CAP_MAC, + NL80211_BAND_IFTYPE_ATTR_EHT_CAP_PHY, + NL80211_BAND_IFTYPE_ATTR_EHT_CAP_MCS_SET, + NL80211_BAND_IFTYPE_ATTR_EHT_CAP_PPE, /* keep last */ __NL80211_BAND_IFTYPE_ATTR_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5c49d7c4bcae..2dfd45f35486 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1737,6 +1737,7 @@ nl80211_send_iftype_data(struct sk_buff *msg, const struct ieee80211_sband_iftype_data *iftdata) { const struct ieee80211_sta_he_cap *he_cap = &iftdata->he_cap; + const struct ieee80211_sta_eht_cap *eht_cap = &iftdata->eht_cap; if (nl80211_put_iftypes(msg, NL80211_BAND_IFTYPE_ATTR_IFTYPES, iftdata->types_mask)) @@ -1757,6 +1758,32 @@ nl80211_send_iftype_data(struct sk_buff *msg, return -ENOBUFS; } + if (eht_cap->has_eht && he_cap->has_he) { + u8 mcs_nss_size, ppe_thresh_size; + u16 ppe_thres_hdr; + + mcs_nss_size = + ieee80211_eht_mcs_nss_size(&he_cap->he_cap_elem, + &eht_cap->eht_cap_elem); + + ppe_thres_hdr = get_unaligned_le16(&eht_cap->eht_ppe_thres[0]); + ppe_thresh_size = + ieee80211_eht_ppe_size(ppe_thres_hdr, + eht_cap->eht_cap_elem.phy_cap_info); + + if (nla_put(msg, NL80211_BAND_IFTYPE_ATTR_EHT_CAP_MAC, + sizeof(eht_cap->eht_cap_elem.mac_cap_info), + eht_cap->eht_cap_elem.mac_cap_info) || + nla_put(msg, NL80211_BAND_IFTYPE_ATTR_EHT_CAP_PHY, + sizeof(eht_cap->eht_cap_elem.phy_cap_info), + eht_cap->eht_cap_elem.phy_cap_info) || + nla_put(msg, NL80211_BAND_IFTYPE_ATTR_EHT_CAP_MCS_SET, + mcs_nss_size, &eht_cap->eht_mcs_nss_supp) || + nla_put(msg, NL80211_BAND_IFTYPE_ATTR_EHT_CAP_PPE, + ppe_thresh_size, eht_cap->eht_ppe_thres)) + return -ENOBUFS; + } + if (sband->band == NL80211_BAND_6GHZ && nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_6GHZ_CAPA, sizeof(iftdata->he_6ghz_capa), -- cgit v1.2.3 From 3743bec6120ae0748cb3fda6ff80a690117ef1f3 Mon Sep 17 00:00:00 2001 From: Jia Ding Date: Mon, 14 Feb 2022 17:29:54 +0100 Subject: cfg80211: Add support for EHT 320 MHz channel width Add 320 MHz support in the channel def and center frequency validation with compatible check. Signed-off-by: Jia Ding Co-authored-by: Karthikeyan Periyasamy Signed-off-by: Karthikeyan Periyasamy Co-authored-by: Muna Sinada Signed-off-by: Muna Sinada Co-authored-by: Veerendranath Jakkam Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/1640163883-12696-5-git-send-email-quic_vjakkam@quicinc.com Link: https://lore.kernel.org/r/20220214163009.175289-1-johannes@sipsolutions.net Signed-off-by: Johannes Berg --- drivers/net/wireless/mac80211_hwsim.c | 2 + include/net/cfg80211.h | 7 ++- include/uapi/linux/nl80211.h | 3 ++ net/wireless/chan.c | 91 ++++++++++++++++++++++++++++++++--- net/wireless/nl80211.c | 2 + 5 files changed, 97 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index defb7e36c1f2..0054c234fb9a 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -836,6 +836,8 @@ static int hwsim_get_chanwidth(enum nl80211_chan_width bw) case NL80211_CHAN_WIDTH_80P80: case NL80211_CHAN_WIDTH_160: return 160; + case NL80211_CHAN_WIDTH_320: + return 320; case NL80211_CHAN_WIDTH_5: return 5; case NL80211_CHAN_WIDTH_10: diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7bec15f605be..a27f2d699dac 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -109,7 +109,11 @@ struct wiphy; * on this channel. * @IEEE80211_CHAN_16MHZ: 16 MHz bandwidth is permitted * on this channel. - * + * @IEEE80211_CHAN_NO_320MHZ: If the driver supports 320 MHz on the band, + * this flag indicates that a 320 MHz channel cannot use this + * channel as the control or any of the secondary channels. + * This may be due to the driver or due to regulatory bandwidth + * restrictions. */ enum ieee80211_channel_flags { IEEE80211_CHAN_DISABLED = 1<<0, @@ -131,6 +135,7 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_4MHZ = 1<<16, IEEE80211_CHAN_8MHZ = 1<<17, IEEE80211_CHAN_16MHZ = 1<<18, + IEEE80211_CHAN_NO_320MHZ = 1<<19, }; #define IEEE80211_CHAN_NO_HT40 \ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index d305a8b8c536..9e05973f3f56 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4684,6 +4684,8 @@ enum nl80211_key_mode { * @NL80211_CHAN_WIDTH_4: 4 MHz OFDM channel * @NL80211_CHAN_WIDTH_8: 8 MHz OFDM channel * @NL80211_CHAN_WIDTH_16: 16 MHz OFDM channel + * @NL80211_CHAN_WIDTH_320: 320 MHz channel, the %NL80211_ATTR_CENTER_FREQ1 + * attribute must be provided as well */ enum nl80211_chan_width { NL80211_CHAN_WIDTH_20_NOHT, @@ -4699,6 +4701,7 @@ enum nl80211_chan_width { NL80211_CHAN_WIDTH_4, NL80211_CHAN_WIDTH_8, NL80211_CHAN_WIDTH_16, + NL80211_CHAN_WIDTH_320, }; /** diff --git a/net/wireless/chan.c b/net/wireless/chan.c index eb822052d344..8b7fb4a9e07b 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -181,6 +181,9 @@ static int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width) case NL80211_CHAN_WIDTH_160: mhz = 160; break; + case NL80211_CHAN_WIDTH_320: + mhz = 320; + break; default: WARN_ON_ONCE(1); return -1; @@ -271,6 +274,17 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef) case NL80211_CHAN_WIDTH_16: /* all checked above */ break; + case NL80211_CHAN_WIDTH_320: + if (chandef->center_freq1 == control_freq + 150 || + chandef->center_freq1 == control_freq + 130 || + chandef->center_freq1 == control_freq + 110 || + chandef->center_freq1 == control_freq + 90 || + chandef->center_freq1 == control_freq - 90 || + chandef->center_freq1 == control_freq - 110 || + chandef->center_freq1 == control_freq - 130 || + chandef->center_freq1 == control_freq - 150) + break; + fallthrough; case NL80211_CHAN_WIDTH_160: if (chandef->center_freq1 == control_freq + 70 || chandef->center_freq1 == control_freq + 50 || @@ -307,7 +321,7 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef) EXPORT_SYMBOL(cfg80211_chandef_valid); static void chandef_primary_freqs(const struct cfg80211_chan_def *c, - u32 *pri40, u32 *pri80) + u32 *pri40, u32 *pri80, u32 *pri160) { int tmp; @@ -315,9 +329,11 @@ static void chandef_primary_freqs(const struct cfg80211_chan_def *c, case NL80211_CHAN_WIDTH_40: *pri40 = c->center_freq1; *pri80 = 0; + *pri160 = 0; break; case NL80211_CHAN_WIDTH_80: case NL80211_CHAN_WIDTH_80P80: + *pri160 = 0; *pri80 = c->center_freq1; /* n_P20 */ tmp = (30 + c->chan->center_freq - c->center_freq1)/20; @@ -327,6 +343,7 @@ static void chandef_primary_freqs(const struct cfg80211_chan_def *c, *pri40 = c->center_freq1 - 20 + 40 * tmp; break; case NL80211_CHAN_WIDTH_160: + *pri160 = c->center_freq1; /* n_P20 */ tmp = (70 + c->chan->center_freq - c->center_freq1)/20; /* n_P40 */ @@ -337,6 +354,20 @@ static void chandef_primary_freqs(const struct cfg80211_chan_def *c, tmp /= 2; *pri80 = c->center_freq1 - 40 + 80 * tmp; break; + case NL80211_CHAN_WIDTH_320: + /* n_P20 */ + tmp = (150 + c->chan->center_freq - c->center_freq1) / 20; + /* n_P40 */ + tmp /= 2; + /* freq_P40 */ + *pri40 = c->center_freq1 - 140 + 40 * tmp; + /* n_P80 */ + tmp /= 2; + *pri80 = c->center_freq1 - 120 + 80 * tmp; + /* n_P160 */ + tmp /= 2; + *pri160 = c->center_freq1 - 80 + 160 * tmp; + break; default: WARN_ON_ONCE(1); } @@ -346,7 +377,7 @@ const struct cfg80211_chan_def * cfg80211_chandef_compatible(const struct cfg80211_chan_def *c1, const struct cfg80211_chan_def *c2) { - u32 c1_pri40, c1_pri80, c2_pri40, c2_pri80; + u32 c1_pri40, c1_pri80, c2_pri40, c2_pri80, c1_pri160, c2_pri160; /* If they are identical, return */ if (cfg80211_chandef_identical(c1, c2)) @@ -381,14 +412,31 @@ cfg80211_chandef_compatible(const struct cfg80211_chan_def *c1, c2->width == NL80211_CHAN_WIDTH_20) return c1; - chandef_primary_freqs(c1, &c1_pri40, &c1_pri80); - chandef_primary_freqs(c2, &c2_pri40, &c2_pri80); + chandef_primary_freqs(c1, &c1_pri40, &c1_pri80, &c1_pri160); + chandef_primary_freqs(c2, &c2_pri40, &c2_pri80, &c2_pri160); if (c1_pri40 != c2_pri40) return NULL; - WARN_ON(!c1_pri80 && !c2_pri80); - if (c1_pri80 && c2_pri80 && c1_pri80 != c2_pri80) + if (c1->width == NL80211_CHAN_WIDTH_40) + return c2; + + if (c2->width == NL80211_CHAN_WIDTH_40) + return c1; + + if (c1_pri80 != c2_pri80) + return NULL; + + if (c1->width == NL80211_CHAN_WIDTH_80 && + c2->width > NL80211_CHAN_WIDTH_80) + return c2; + + if (c2->width == NL80211_CHAN_WIDTH_80 && + c1->width > NL80211_CHAN_WIDTH_80) + return c1; + + WARN_ON(!c1_pri160 && !c2_pri160); + if (c1_pri160 && c2_pri160 && c1_pri160 != c2_pri160) return NULL; if (c1->width > c2->width) @@ -960,7 +1008,10 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, struct ieee80211_sta_vht_cap *vht_cap; struct ieee80211_edmg *edmg_cap; u32 width, control_freq, cap; - bool ext_nss_cap, support_80_80 = false; + bool ext_nss_cap, support_80_80 = false, support_320 = false; + const struct ieee80211_sband_iftype_data *iftd; + struct ieee80211_supported_band *sband; + int i; if (WARN_ON(!cfg80211_chandef_valid(chandef))) return false; @@ -1062,6 +1113,32 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, (vht_cap->cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK))) return false; break; + case NL80211_CHAN_WIDTH_320: + prohibited_flags |= IEEE80211_CHAN_NO_320MHZ; + width = 320; + + if (chandef->chan->band != NL80211_BAND_6GHZ) + return false; + + sband = wiphy->bands[NL80211_BAND_6GHZ]; + if (!sband) + return false; + + for (i = 0; i < sband->n_iftype_data; i++) { + iftd = &sband->iftype_data[i]; + if (!iftd->eht_cap.has_eht) + continue; + + if (iftd->eht_cap.eht_cap_elem.phy_cap_info[0] & + IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ) { + support_320 = true; + break; + } + } + + if (!support_320) + return false; + break; default: WARN_ON_ONCE(1); return false; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 2dfd45f35486..f93b9686fb41 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -10589,6 +10589,8 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) NL80211_EXT_FEATURE_VHT_IBSS)) return -EINVAL; break; + case NL80211_CHAN_WIDTH_320: + return -EINVAL; default: return -EINVAL; } -- cgit v1.2.3 From cfb14110acf87b4db62e07ba08a80429f1749f40 Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Mon, 14 Feb 2022 17:29:55 +0100 Subject: nl80211: add EHT MCS support Add support for reporting and calculating EHT bitrates. Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/1640163883-12696-7-git-send-email-quic_vjakkam@quicinc.com Link: https://lore.kernel.org/r/20220214163009.175289-2-johannes@sipsolutions.net Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 11 ++++ include/uapi/linux/nl80211.h | 62 ++++++++++++++++++++ net/wireless/nl80211.c | 19 +++++++ net/wireless/util.c | 131 +++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 223 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index a27f2d699dac..f35ffd81d213 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1595,6 +1595,7 @@ int cfg80211_check_station_change(struct wiphy *wiphy, * @RATE_INFO_FLAGS_HE_MCS: HE MCS information * @RATE_INFO_FLAGS_EDMG: 60GHz MCS in EDMG mode * @RATE_INFO_FLAGS_EXTENDED_SC_DMG: 60GHz extended SC MCS + * @RATE_INFO_FLAGS_EHT_MCS: EHT MCS information */ enum rate_info_flags { RATE_INFO_FLAGS_MCS = BIT(0), @@ -1604,6 +1605,7 @@ enum rate_info_flags { RATE_INFO_FLAGS_HE_MCS = BIT(4), RATE_INFO_FLAGS_EDMG = BIT(5), RATE_INFO_FLAGS_EXTENDED_SC_DMG = BIT(6), + RATE_INFO_FLAGS_EHT_MCS = BIT(7), }; /** @@ -1618,6 +1620,8 @@ enum rate_info_flags { * @RATE_INFO_BW_80: 80 MHz bandwidth * @RATE_INFO_BW_160: 160 MHz bandwidth * @RATE_INFO_BW_HE_RU: bandwidth determined by HE RU allocation + * @RATE_INFO_BW_320: 320 MHz bandwidth + * @RATE_INFO_BW_EHT_RU: bandwidth determined by EHT RU allocation */ enum rate_info_bw { RATE_INFO_BW_20 = 0, @@ -1627,6 +1631,8 @@ enum rate_info_bw { RATE_INFO_BW_80, RATE_INFO_BW_160, RATE_INFO_BW_HE_RU, + RATE_INFO_BW_320, + RATE_INFO_BW_EHT_RU, }; /** @@ -1644,6 +1650,9 @@ enum rate_info_bw { * @he_ru_alloc: HE RU allocation (from &enum nl80211_he_ru_alloc, * only valid if bw is %RATE_INFO_BW_HE_RU) * @n_bonded_ch: In case of EDMG the number of bonded channels (1-4) + * @eht_gi: EHT guard interval (from &enum nl80211_eht_gi) + * @eht_ru_alloc: EHT RU allocation (from &enum nl80211_eht_ru_alloc, + * only valid if bw is %RATE_INFO_BW_EHT_RU) */ struct rate_info { u8 flags; @@ -1655,6 +1664,8 @@ struct rate_info { u8 he_dcm; u8 he_ru_alloc; u8 n_bonded_ch; + u8 eht_gi; + u8 eht_ru_alloc; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 9e05973f3f56..d0ba70ea5d04 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3392,6 +3392,56 @@ enum nl80211_he_ru_alloc { NL80211_RATE_INFO_HE_RU_ALLOC_2x996, }; +/** + * enum nl80211_eht_gi - EHT guard interval + * @NL80211_RATE_INFO_EHT_GI_0_8: 0.8 usec + * @NL80211_RATE_INFO_EHT_GI_1_6: 1.6 usec + * @NL80211_RATE_INFO_EHT_GI_3_2: 3.2 usec + */ +enum nl80211_eht_gi { + NL80211_RATE_INFO_EHT_GI_0_8, + NL80211_RATE_INFO_EHT_GI_1_6, + NL80211_RATE_INFO_EHT_GI_3_2, +}; + +/** + * enum nl80211_eht_ru_alloc - EHT RU allocation values + * @NL80211_RATE_INFO_EHT_RU_ALLOC_26: 26-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_52: 52-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_52P26: 52+26-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_106: 106-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_106P26: 106+26 tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_242: 242-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_484: 484-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_484P242: 484+242 tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_996: 996-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_996P484: 996+484 tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_996P484P242: 996+484+242 tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_2x996: 2x996-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_2x996P484: 2x996+484 tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_3x996: 3x996-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_3x996P484: 3x996+484 tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_4x996: 4x996-tone RU allocation + */ +enum nl80211_eht_ru_alloc { + NL80211_RATE_INFO_EHT_RU_ALLOC_26, + NL80211_RATE_INFO_EHT_RU_ALLOC_52, + NL80211_RATE_INFO_EHT_RU_ALLOC_52P26, + NL80211_RATE_INFO_EHT_RU_ALLOC_106, + NL80211_RATE_INFO_EHT_RU_ALLOC_106P26, + NL80211_RATE_INFO_EHT_RU_ALLOC_242, + NL80211_RATE_INFO_EHT_RU_ALLOC_484, + NL80211_RATE_INFO_EHT_RU_ALLOC_484P242, + NL80211_RATE_INFO_EHT_RU_ALLOC_996, + NL80211_RATE_INFO_EHT_RU_ALLOC_996P484, + NL80211_RATE_INFO_EHT_RU_ALLOC_996P484P242, + NL80211_RATE_INFO_EHT_RU_ALLOC_2x996, + NL80211_RATE_INFO_EHT_RU_ALLOC_2x996P484, + NL80211_RATE_INFO_EHT_RU_ALLOC_3x996, + NL80211_RATE_INFO_EHT_RU_ALLOC_3x996P484, + NL80211_RATE_INFO_EHT_RU_ALLOC_4x996, +}; + /** * enum nl80211_rate_info - bitrate information * @@ -3431,6 +3481,13 @@ enum nl80211_he_ru_alloc { * @NL80211_RATE_INFO_HE_DCM: HE DCM value (u8, 0/1) * @NL80211_RATE_INFO_RU_ALLOC: HE RU allocation, if not present then * non-OFDMA was used (u8, see &enum nl80211_he_ru_alloc) + * @NL80211_RATE_INFO_320_MHZ_WIDTH: 320 MHz bitrate + * @NL80211_RATE_INFO_EHT_MCS: EHT MCS index (u8, 0-15) + * @NL80211_RATE_INFO_EHT_NSS: EHT NSS value (u8, 1-8) + * @NL80211_RATE_INFO_EHT_GI: EHT guard interval identifier + * (u8, see &enum nl80211_eht_gi) + * @NL80211_RATE_INFO_EHT_RU_ALLOC: EHT RU allocation, if not present then + * non-OFDMA was used (u8, see &enum nl80211_eht_ru_alloc) * @__NL80211_RATE_INFO_AFTER_LAST: internal use */ enum nl80211_rate_info { @@ -3452,6 +3509,11 @@ enum nl80211_rate_info { NL80211_RATE_INFO_HE_GI, NL80211_RATE_INFO_HE_DCM, NL80211_RATE_INFO_HE_RU_ALLOC, + NL80211_RATE_INFO_320_MHZ_WIDTH, + NL80211_RATE_INFO_EHT_MCS, + NL80211_RATE_INFO_EHT_NSS, + NL80211_RATE_INFO_EHT_GI, + NL80211_RATE_INFO_EHT_RU_ALLOC, /* keep last */ __NL80211_RATE_INFO_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index f93b9686fb41..a267e838f79c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5954,6 +5954,14 @@ bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, int attr) case RATE_INFO_BW_HE_RU: rate_flg = 0; WARN_ON(!(info->flags & RATE_INFO_FLAGS_HE_MCS)); + break; + case RATE_INFO_BW_320: + rate_flg = NL80211_RATE_INFO_320_MHZ_WIDTH; + break; + case RATE_INFO_BW_EHT_RU: + rate_flg = 0; + WARN_ON(!(info->flags & RATE_INFO_FLAGS_EHT_MCS)); + break; } if (rate_flg && nla_put_flag(msg, rate_flg)) @@ -5986,6 +5994,17 @@ bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, int attr) nla_put_u8(msg, NL80211_RATE_INFO_HE_RU_ALLOC, info->he_ru_alloc)) return false; + } else if (info->flags & RATE_INFO_FLAGS_EHT_MCS) { + if (nla_put_u8(msg, NL80211_RATE_INFO_EHT_MCS, info->mcs)) + return false; + if (nla_put_u8(msg, NL80211_RATE_INFO_EHT_NSS, info->nss)) + return false; + if (nla_put_u8(msg, NL80211_RATE_INFO_EHT_GI, info->eht_gi)) + return false; + if (info->bw == RATE_INFO_BW_EHT_RU && + nla_put_u8(msg, NL80211_RATE_INFO_EHT_RU_ALLOC, + info->eht_ru_alloc)) + return false; } nla_nest_end(msg, rate); diff --git a/net/wireless/util.c b/net/wireless/util.c index e02f1702806e..2eda097aee7f 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1430,6 +1430,135 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) return result / 10000; } +static u32 cfg80211_calculate_bitrate_eht(struct rate_info *rate) +{ +#define SCALE 6144 + static const u32 mcs_divisors[16] = { + 102399, /* 16.666666... */ + 51201, /* 8.333333... */ + 34134, /* 5.555555... */ + 25599, /* 4.166666... */ + 17067, /* 2.777777... */ + 12801, /* 2.083333... */ + 11769, /* 1.851851... */ + 10239, /* 1.666666... */ + 8532, /* 1.388888... */ + 7680, /* 1.250000... */ + 6828, /* 1.111111... */ + 6144, /* 1.000000... */ + 5690, /* 0.926106... */ + 5120, /* 0.833333... */ + 409600, /* 66.666666... */ + 204800, /* 33.333333... */ + }; + static const u32 rates_996[3] = { 480388888, 453700000, 408333333 }; + static const u32 rates_484[3] = { 229411111, 216666666, 195000000 }; + static const u32 rates_242[3] = { 114711111, 108333333, 97500000 }; + static const u32 rates_106[3] = { 40000000, 37777777, 34000000 }; + static const u32 rates_52[3] = { 18820000, 17777777, 16000000 }; + static const u32 rates_26[3] = { 9411111, 8888888, 8000000 }; + u64 tmp; + u32 result; + + if (WARN_ON_ONCE(rate->mcs > 15)) + return 0; + if (WARN_ON_ONCE(rate->eht_gi > NL80211_RATE_INFO_EHT_GI_3_2)) + return 0; + if (WARN_ON_ONCE(rate->eht_ru_alloc > + NL80211_RATE_INFO_EHT_RU_ALLOC_4x996)) + return 0; + if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8)) + return 0; + + /* Bandwidth checks for MCS 14 */ + if (rate->mcs == 14) { + if ((rate->bw != RATE_INFO_BW_EHT_RU && + rate->bw != RATE_INFO_BW_80 && + rate->bw != RATE_INFO_BW_160 && + rate->bw != RATE_INFO_BW_320) || + (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc != NL80211_RATE_INFO_EHT_RU_ALLOC_996 && + rate->eht_ru_alloc != NL80211_RATE_INFO_EHT_RU_ALLOC_2x996 && + rate->eht_ru_alloc != NL80211_RATE_INFO_EHT_RU_ALLOC_4x996)) { + WARN(1, "invalid EHT BW for MCS 14: bw:%d, ru:%d\n", + rate->bw, rate->eht_ru_alloc); + return 0; + } + } + + if (rate->bw == RATE_INFO_BW_320 || + (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_4x996)) + result = 4 * rates_996[rate->eht_gi]; + else if (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_3x996P484) + result = 3 * rates_996[rate->eht_gi] + rates_484[rate->eht_gi]; + else if (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_3x996) + result = 3 * rates_996[rate->eht_gi]; + else if (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_2x996P484) + result = 2 * rates_996[rate->eht_gi] + rates_484[rate->eht_gi]; + else if (rate->bw == RATE_INFO_BW_160 || + (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_2x996)) + result = 2 * rates_996[rate->eht_gi]; + else if (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc == + NL80211_RATE_INFO_EHT_RU_ALLOC_996P484P242) + result = rates_996[rate->eht_gi] + rates_484[rate->eht_gi] + + rates_242[rate->eht_gi]; + else if (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_996P484) + result = rates_996[rate->eht_gi] + rates_484[rate->eht_gi]; + else if (rate->bw == RATE_INFO_BW_80 || + (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_996)) + result = rates_996[rate->eht_gi]; + else if (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_484P242) + result = rates_484[rate->eht_gi] + rates_242[rate->eht_gi]; + else if (rate->bw == RATE_INFO_BW_40 || + (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_484)) + result = rates_484[rate->eht_gi]; + else if (rate->bw == RATE_INFO_BW_20 || + (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_242)) + result = rates_242[rate->eht_gi]; + else if (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_106P26) + result = rates_106[rate->eht_gi] + rates_26[rate->eht_gi]; + else if (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_106) + result = rates_106[rate->eht_gi]; + else if (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_52P26) + result = rates_52[rate->eht_gi] + rates_26[rate->eht_gi]; + else if (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_52) + result = rates_52[rate->eht_gi]; + else if (rate->bw == RATE_INFO_BW_EHT_RU && + rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_26) + result = rates_26[rate->eht_gi]; + else { + WARN(1, "invalid EHT MCS: bw:%d, ru:%d\n", + rate->bw, rate->eht_ru_alloc); + return 0; + } + + /* now scale to the appropriate MCS */ + tmp = result; + tmp *= SCALE; + do_div(tmp, mcs_divisors[rate->mcs]); + result = tmp; + + /* and take NSS */ + result = (result * rate->nss) / 8; + + return result / 10000; +} + u32 cfg80211_calculate_bitrate(struct rate_info *rate) { if (rate->flags & RATE_INFO_FLAGS_MCS) @@ -1444,6 +1573,8 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate) return cfg80211_calculate_bitrate_vht(rate); if (rate->flags & RATE_INFO_FLAGS_HE_MCS) return cfg80211_calculate_bitrate_he(rate); + if (rate->flags & RATE_INFO_FLAGS_EHT_MCS) + return cfg80211_calculate_bitrate_eht(rate); return rate->legacy; } -- cgit v1.2.3 From c2b3d7699fb0ce66538b829af43970acc2f89060 Mon Sep 17 00:00:00 2001 From: Sriram R Date: Mon, 14 Feb 2022 17:29:56 +0100 Subject: nl80211: add support for 320MHz channel limitation Add support to advertise drivers or regulatory limitations on 320 MHz channels to userspace. Signed-off-by: Sriram R Co-authored-by: Karthikeyan Periyasamy Signed-off-by: Karthikeyan Periyasamy Co-authored-by: Veerendranath Jakkam Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/1640163883-12696-6-git-send-email-quic_vjakkam@quicinc.com Link: https://lore.kernel.org/r/20220214163009.175289-3-johannes@sipsolutions.net Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 5 +++++ net/wireless/nl80211.c | 3 +++ net/wireless/reg.c | 6 ++++++ 3 files changed, 14 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index d0ba70ea5d04..6a338dafcd07 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3997,6 +3997,8 @@ enum nl80211_wmm_rule { * on this channel in current regulatory domain. * @NL80211_FREQUENCY_ATTR_16MHZ: 16 MHz operation is allowed * on this channel in current regulatory domain. + * @NL80211_FREQUENCY_ATTR_NO_320MHZ: any 320 MHz channel using this channel + * as the primary or any of the secondary channels isn't possible * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use @@ -4033,6 +4035,7 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_4MHZ, NL80211_FREQUENCY_ATTR_8MHZ, NL80211_FREQUENCY_ATTR_16MHZ, + NL80211_FREQUENCY_ATTR_NO_320MHZ, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, @@ -4231,6 +4234,7 @@ enum nl80211_sched_scan_match_attr { * @NL80211_RRF_NO_80MHZ: 80MHz operation not allowed * @NL80211_RRF_NO_160MHZ: 160MHz operation not allowed * @NL80211_RRF_NO_HE: HE operation not allowed + * @NL80211_RRF_NO_320MHZ: 320MHz operation not allowed */ enum nl80211_reg_rule_flags { NL80211_RRF_NO_OFDM = 1<<0, @@ -4249,6 +4253,7 @@ enum nl80211_reg_rule_flags { NL80211_RRF_NO_80MHZ = 1<<15, NL80211_RRF_NO_160MHZ = 1<<16, NL80211_RRF_NO_HE = 1<<17, + NL80211_RRF_NO_320MHZ = 1<<18, }; #define NL80211_RRF_PASSIVE_SCAN NL80211_RRF_NO_IR diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index a267e838f79c..7edf0bb4e90e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1156,6 +1156,9 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if ((chan->flags & IEEE80211_CHAN_16MHZ) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_16MHZ)) goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_NO_320MHZ) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_320MHZ)) + goto nla_put_failure; } if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index ec25924a1c26..c76cd973f06e 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1238,6 +1238,8 @@ unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd, { unsigned int bw = reg_get_max_bandwidth_from_range(rd, rule); + if (rule->flags & NL80211_RRF_NO_320MHZ) + bw = min_t(unsigned int, bw, MHZ_TO_KHZ(160)); if (rule->flags & NL80211_RRF_NO_160MHZ) bw = min_t(unsigned int, bw, MHZ_TO_KHZ(80)); if (rule->flags & NL80211_RRF_NO_80MHZ) @@ -1611,6 +1613,8 @@ static u32 map_regdom_flags(u32 rd_flags) channel_flags |= IEEE80211_CHAN_NO_160MHZ; if (rd_flags & NL80211_RRF_NO_HE) channel_flags |= IEEE80211_CHAN_NO_HE; + if (rd_flags & NL80211_RRF_NO_320MHZ) + channel_flags |= IEEE80211_CHAN_NO_320MHZ; return channel_flags; } @@ -1773,6 +1777,8 @@ static uint32_t reg_rule_to_chan_bw_flags(const struct ieee80211_regdomain *regd bw_flags |= IEEE80211_CHAN_NO_80MHZ; if (max_bandwidth_khz < MHZ_TO_KHZ(160)) bw_flags |= IEEE80211_CHAN_NO_160MHZ; + if (max_bandwidth_khz < MHZ_TO_KHZ(320)) + bw_flags |= IEEE80211_CHAN_NO_320MHZ; } return bw_flags; } -- cgit v1.2.3 From 31846b657857e6a73d982604f36a34710d98902c Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Mon, 14 Feb 2022 17:29:57 +0100 Subject: cfg80211: add NO-EHT flag to regulatory This may be necessary in some cases, add a flag and propagate it, just like the NO-HE that already exists. Signed-off-by: Ilan Peer [split off from a combined 320/no-EHT patch] Link: https://lore.kernel.org/r/20220214173004.dbb85a7b86bb.Ifc1e2daac51c1cc5f895ccfb79faf5eaec3950ec@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ include/uapi/linux/nl80211.h | 3 +++ net/wireless/nl80211.c | 3 +++ 3 files changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f35ffd81d213..5cfc483dece1 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -114,6 +114,7 @@ struct wiphy; * channel as the control or any of the secondary channels. * This may be due to the driver or due to regulatory bandwidth * restrictions. + * @IEEE80211_CHAN_NO_EHT: EHT operation is not permitted on this channel. */ enum ieee80211_channel_flags { IEEE80211_CHAN_DISABLED = 1<<0, @@ -136,6 +137,7 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_8MHZ = 1<<17, IEEE80211_CHAN_16MHZ = 1<<18, IEEE80211_CHAN_NO_320MHZ = 1<<19, + IEEE80211_CHAN_NO_EHT = 1<<20, }; #define IEEE80211_CHAN_NO_HT40 \ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 6a338dafcd07..baf6433c0119 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3999,6 +3999,8 @@ enum nl80211_wmm_rule { * on this channel in current regulatory domain. * @NL80211_FREQUENCY_ATTR_NO_320MHZ: any 320 MHz channel using this channel * as the primary or any of the secondary channels isn't possible + * @NL80211_FREQUENCY_ATTR_NO_EHT: EHT operation is not allowed on this channel + * in current regulatory domain. * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use @@ -4036,6 +4038,7 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_8MHZ, NL80211_FREQUENCY_ATTR_16MHZ, NL80211_FREQUENCY_ATTR_NO_320MHZ, + NL80211_FREQUENCY_ATTR_NO_EHT, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 7edf0bb4e90e..3e6809f24220 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1159,6 +1159,9 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if ((chan->flags & IEEE80211_CHAN_NO_320MHZ) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_320MHZ)) goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_NO_EHT) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_EHT)) + goto nla_put_failure; } if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER, -- cgit v1.2.3 From ea05fd3581d32a0f1098657005c7a9b763798fe8 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Mon, 14 Feb 2022 17:29:58 +0100 Subject: cfg80211: Support configuration of station EHT capabilities Add attributes and some code bits to support userspace passing in EHT capabilities of stations. Signed-off-by: Ilan Peer Link: https://lore.kernel.org/r/20220214173004.ecf0b3ff9627.Icb4a5f2ec7b41d9008ac4cfc16c59baeb84793d3@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 ++++ include/uapi/linux/nl80211.h | 10 +++++++++- net/wireless/nl80211.c | 37 +++++++++++++++++++++++++++++++++---- 3 files changed, 46 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5cfc483dece1..68713388b617 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1487,6 +1487,8 @@ struct sta_txpwr { * @airtime_weight: airtime scheduler weight for this station * @txpwr: transmit power for an associated station * @he_6ghz_capa: HE 6 GHz Band capabilities of station + * @eht_capa: EHT capabilities of station + * @eht_capa_len: the length of the EHT capabilities */ struct station_parameters { const u8 *supported_rates; @@ -1520,6 +1522,8 @@ struct station_parameters { u16 airtime_weight; struct sta_txpwr txpwr; const struct ieee80211_he_6ghz_capa *he_6ghz_capa; + const struct ieee80211_eht_cap_elem *eht_capa; + u8 eht_capa_len; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index baf6433c0119..98ed52663d6b 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -11,7 +11,7 @@ * Copyright 2008 Jouni Malinen * Copyright 2008 Colin McCabe * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2021 Intel Corporation + * Copyright (C) 2018-2022 Intel Corporation * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -2659,6 +2659,10 @@ enum nl80211_commands { * enumerated in &enum nl80211_ap_settings_flags. This attribute shall be * used with %NL80211_CMD_START_AP request. * + * @NL80211_ATTR_EHT_CAPABILITY: EHT Capability information element (from + * association request when used with NL80211_CMD_NEW_STATION). Can be set + * only if %NL80211_STA_FLAG_WME is set. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3169,6 +3173,8 @@ enum nl80211_attrs { NL80211_ATTR_AP_SETTINGS_FLAGS, + NL80211_ATTR_EHT_CAPABILITY, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3224,6 +3230,8 @@ enum nl80211_attrs { #define NL80211_HE_MAX_CAPABILITY_LEN 54 #define NL80211_MAX_NR_CIPHER_SUITES 5 #define NL80211_MAX_NR_AKM_SUITES 2 +#define NL80211_EHT_MIN_CAPABILITY_LEN 13 +#define NL80211_EHT_MAX_CAPABILITY_LEN 51 #define NL80211_MIN_REMAIN_ON_CHANNEL_TIME 10 diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 3e6809f24220..7543c73a3f1d 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5,7 +5,7 @@ * Copyright 2006-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2021 Intel Corporation + * Copyright (C) 2018-2022 Intel Corporation */ #include @@ -786,6 +786,10 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MBSSID_ELEMS] = { .type = NLA_NESTED }, [NL80211_ATTR_RADAR_BACKGROUND] = { .type = NLA_FLAG }, [NL80211_ATTR_AP_SETTINGS_FLAGS] = { .type = NLA_U32 }, + [NL80211_ATTR_EHT_CAPABILITY] = + NLA_POLICY_RANGE(NLA_BINARY, + NL80211_EHT_MIN_CAPABILITY_LEN, + NL80211_EHT_MAX_CAPABILITY_LEN), }; /* policy for the key attributes */ @@ -6425,7 +6429,7 @@ int cfg80211_check_station_change(struct wiphy *wiphy, if (params->supported_rates) return -EINVAL; if (params->ext_capab || params->ht_capa || params->vht_capa || - params->he_capa) + params->he_capa || params->eht_capa) return -EINVAL; } @@ -6628,6 +6632,18 @@ static int nl80211_set_station_tdls(struct genl_info *info, nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); params->he_capa_len = nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + + if (info->attrs[NL80211_ATTR_EHT_CAPABILITY]) { + params->eht_capa = + nla_data(info->attrs[NL80211_ATTR_EHT_CAPABILITY]); + params->eht_capa_len = + nla_len(info->attrs[NL80211_ATTR_EHT_CAPABILITY]); + + if (!ieee80211_eht_capa_size_ok((const u8 *)params->he_capa, + (const u8 *)params->eht_capa, + params->eht_capa_len)) + return -EINVAL; + } } err = nl80211_parse_sta_channel_info(info, params); @@ -6885,6 +6901,18 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); params.he_capa_len = nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + + if (info->attrs[NL80211_ATTR_EHT_CAPABILITY]) { + params.eht_capa = + nla_data(info->attrs[NL80211_ATTR_EHT_CAPABILITY]); + params.eht_capa_len = + nla_len(info->attrs[NL80211_ATTR_EHT_CAPABILITY]); + + if (!ieee80211_eht_capa_size_ok((const u8 *)params.he_capa, + (const u8 *)params.eht_capa, + params.eht_capa_len)) + return -EINVAL; + } } if (info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]) @@ -6934,8 +6962,9 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) params.ht_capa = NULL; params.vht_capa = NULL; - /* HE requires WME */ - if (params.he_capa_len || params.he_6ghz_capa) + /* HE and EHT require WME */ + if (params.he_capa_len || params.he_6ghz_capa || + params.eht_capa_len) return -EINVAL; } -- cgit v1.2.3 From 47f0bd5032106469827cf56c8b45bb9101112105 Mon Sep 17 00:00:00 2001 From: Jacques de Laval Date: Thu, 17 Feb 2022 16:02:02 +0100 Subject: net: Add new protocol attribute to IP addresses This patch adds a new protocol attribute to IPv4 and IPv6 addresses. Inspiration was taken from the protocol attribute of routes. User space applications like iproute2 can set/get the protocol with the Netlink API. The attribute is stored as an 8-bit unsigned integer. The protocol attribute is set by kernel for these categories: - IPv4 and IPv6 loopback addresses - IPv6 addresses generated from router announcements - IPv6 link local addresses User space may pass custom protocols, not defined by the kernel. Grouping addresses on their origin is useful in scenarios where you want to distinguish between addresses based on who added them, e.g. kernel vs. user space. Tagging addresses with a string label is an existing feature that could be used as a solution. Unfortunately the max length of a label is 15 characters, and for compatibility reasons the label must be prefixed with the name of the device followed by a colon. Since device names also have a max length of 15 characters, only -1 characters is guaranteed to be available for any origin tag, which is not that much. A reference implementation of user space setting and getting protocols is available for iproute2: https://github.com/westermo/iproute2/commit/9a6ea18bd79f47f293e5edc7780f315ea42ff540 Signed-off-by: Jacques de Laval Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20220217150202.80802-1-Jacques.De.Laval@westermo.com Signed-off-by: Jakub Kicinski --- include/linux/inetdevice.h | 1 + include/net/addrconf.h | 2 ++ include/net/if_inet6.h | 2 ++ include/uapi/linux/if_addr.h | 9 ++++++++- net/ipv4/devinet.c | 7 +++++++ net/ipv6/addrconf.c | 27 +++++++++++++++++++++------ 6 files changed, 41 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 674aeead6260..ead323243e7b 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -150,6 +150,7 @@ struct in_ifaddr { __be32 ifa_broadcast; unsigned char ifa_scope; unsigned char ifa_prefixlen; + unsigned char ifa_proto; __u32 ifa_flags; char ifa_label[IFNAMSIZ]; diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 59940e230b78..f7506f08e505 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -64,6 +64,8 @@ struct ifa6_config { const struct in6_addr *pfx; unsigned int plen; + u8 ifa_proto; + const struct in6_addr *peer_pfx; u32 rt_priority; diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index f026cf08a8e8..4cfdef6ca4f6 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -71,6 +71,8 @@ struct inet6_ifaddr { bool tokenized; + u8 ifa_proto; + struct rcu_head rcu; struct in6_addr peer_addr; }; diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h index dfcf3ce0097f..1c392dd95a5e 100644 --- a/include/uapi/linux/if_addr.h +++ b/include/uapi/linux/if_addr.h @@ -33,8 +33,9 @@ enum { IFA_CACHEINFO, IFA_MULTICAST, IFA_FLAGS, - IFA_RT_PRIORITY, /* u32, priority/metric for prefix route */ + IFA_RT_PRIORITY, /* u32, priority/metric for prefix route */ IFA_TARGET_NETNSID, + IFA_PROTO, /* u8, address protocol */ __IFA_MAX, }; @@ -69,4 +70,10 @@ struct ifa_cacheinfo { #define IFA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifaddrmsg)) #endif +/* ifa_proto */ +#define IFAPROT_UNSPEC 0 +#define IFAPROT_KERNEL_LO 1 /* loopback */ +#define IFAPROT_KERNEL_RA 2 /* set by kernel from router announcement */ +#define IFAPROT_KERNEL_LL 3 /* link-local set by kernel */ + #endif diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index fba2bffd65f7..53a6b14dc50a 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -104,6 +104,7 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_FLAGS] = { .type = NLA_U32 }, [IFA_RT_PRIORITY] = { .type = NLA_U32 }, [IFA_TARGET_NETNSID] = { .type = NLA_S32 }, + [IFA_PROTO] = { .type = NLA_U8 }, }; struct inet_fill_args { @@ -889,6 +890,9 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, if (tb[IFA_RT_PRIORITY]) ifa->ifa_rt_priority = nla_get_u32(tb[IFA_RT_PRIORITY]); + if (tb[IFA_PROTO]) + ifa->ifa_proto = nla_get_u8(tb[IFA_PROTO]); + if (tb[IFA_CACHEINFO]) { struct ifa_cacheinfo *ci; @@ -1625,6 +1629,7 @@ static size_t inet_nlmsg_size(void) + nla_total_size(4) /* IFA_BROADCAST */ + nla_total_size(IFNAMSIZ) /* IFA_LABEL */ + nla_total_size(4) /* IFA_FLAGS */ + + nla_total_size(1) /* IFA_PROTO */ + nla_total_size(4) /* IFA_RT_PRIORITY */ + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */ } @@ -1699,6 +1704,8 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, nla_put_in_addr(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || (ifa->ifa_label[0] && nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || + (ifa->ifa_proto && + nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) || nla_put_u32(skb, IFA_FLAGS, ifa->ifa_flags) || (ifa->ifa_rt_priority && nla_put_u32(skb, IFA_RT_PRIORITY, ifa->ifa_rt_priority)) || diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2f307da17f21..85bab3a35709 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1115,6 +1115,7 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg, ifa->prefix_len = cfg->plen; ifa->rt_priority = cfg->rt_priority; ifa->flags = cfg->ifa_flags; + ifa->ifa_proto = cfg->ifa_proto; /* No need to add the TENTATIVE flag for addresses with NODAD */ if (!(cfg->ifa_flags & IFA_F_NODAD)) ifa->flags |= IFA_F_TENTATIVE; @@ -2593,6 +2594,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, .valid_lft = valid_lft, .preferred_lft = prefered_lft, .scope = addr_type & IPV6_ADDR_SCOPE_MASK, + .ifa_proto = IFAPROT_KERNEL_RA }; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD @@ -3077,7 +3079,7 @@ int addrconf_del_ifaddr(struct net *net, void __user *arg) } static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, - int plen, int scope) + int plen, int scope, u8 proto) { struct inet6_ifaddr *ifp; struct ifa6_config cfg = { @@ -3086,7 +3088,8 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, .ifa_flags = IFA_F_PERMANENT, .valid_lft = INFINITY_LIFE_TIME, .preferred_lft = INFINITY_LIFE_TIME, - .scope = scope + .scope = scope, + .ifa_proto = proto }; ifp = ipv6_add_addr(idev, &cfg, true, NULL); @@ -3131,7 +3134,7 @@ static void add_v4_addrs(struct inet6_dev *idev) } if (addr.s6_addr32[3]) { - add_addr(idev, &addr, plen, scope); + add_addr(idev, &addr, plen, scope, IFAPROT_UNSPEC); addrconf_prefix_route(&addr, plen, 0, idev->dev, 0, pflags, GFP_KERNEL); return; @@ -3154,7 +3157,8 @@ static void add_v4_addrs(struct inet6_dev *idev) flag |= IFA_HOST; } - add_addr(idev, &addr, plen, flag); + add_addr(idev, &addr, plen, flag, + IFAPROT_UNSPEC); addrconf_prefix_route(&addr, plen, 0, idev->dev, 0, pflags, GFP_KERNEL); } @@ -3177,7 +3181,7 @@ static void init_loopback(struct net_device *dev) return; } - add_addr(idev, &in6addr_loopback, 128, IFA_HOST); + add_addr(idev, &in6addr_loopback, 128, IFA_HOST, IFAPROT_KERNEL_LO); } void addrconf_add_linklocal(struct inet6_dev *idev, @@ -3189,7 +3193,8 @@ void addrconf_add_linklocal(struct inet6_dev *idev, .ifa_flags = flags | IFA_F_PERMANENT, .valid_lft = INFINITY_LIFE_TIME, .preferred_lft = INFINITY_LIFE_TIME, - .scope = IFA_LINK + .scope = IFA_LINK, + .ifa_proto = IFAPROT_KERNEL_LL }; struct inet6_ifaddr *ifp; @@ -4627,6 +4632,7 @@ static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = { [IFA_FLAGS] = { .len = sizeof(u32) }, [IFA_RT_PRIORITY] = { .len = sizeof(u32) }, [IFA_TARGET_NETNSID] = { .type = NLA_S32 }, + [IFA_PROTO] = { .type = NLA_U8 }, }; static int @@ -4752,6 +4758,7 @@ static int inet6_addr_modify(struct net *net, struct inet6_ifaddr *ifp, ifp->tstamp = jiffies; ifp->valid_lft = cfg->valid_lft; ifp->prefered_lft = cfg->preferred_lft; + ifp->ifa_proto = cfg->ifa_proto; if (cfg->rt_priority && cfg->rt_priority != ifp->rt_priority) ifp->rt_priority = cfg->rt_priority; @@ -4845,6 +4852,9 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[IFA_RT_PRIORITY]) cfg.rt_priority = nla_get_u32(tb[IFA_RT_PRIORITY]); + if (tb[IFA_PROTO]) + cfg.ifa_proto = nla_get_u8(tb[IFA_PROTO]); + cfg.valid_lft = INFINITY_LIFE_TIME; cfg.preferred_lft = INFINITY_LIFE_TIME; @@ -4948,6 +4958,7 @@ static inline int inet6_ifaddr_msgsize(void) + nla_total_size(16) /* IFA_ADDRESS */ + nla_total_size(sizeof(struct ifa_cacheinfo)) + nla_total_size(4) /* IFA_FLAGS */ + + nla_total_size(1) /* IFA_PROTO */ + nla_total_size(4) /* IFA_RT_PRIORITY */; } @@ -5025,6 +5036,10 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, if (nla_put_u32(skb, IFA_FLAGS, ifa->flags) < 0) goto error; + if (ifa->ifa_proto && + nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) + goto error; + nlmsg_end(skb, nlh); return 0; -- cgit v1.2.3 From 4b340a5a726dafba15b366c4009aa0a8f77631ac Mon Sep 17 00:00:00 2001 From: Mobashshera Rasool Date: Thu, 17 Feb 2022 07:46:40 +0000 Subject: net: ip6mr: add support for passing full packet on wrong mif This patch adds support for MRT6MSG_WRMIFWHOLE which is used to pass full packet and real vif id when the incoming interface is wrong. While the RP and FHR are setting up state we need to be sending the registers encapsulated with all the data inside otherwise we lose it. The RP then decapsulates it and forwards it to the interested parties. Currently with WRONGMIF we can only be sending empty register packets and will lose that data. This behaviour can be enabled by using MRT_PIM with val == MRT6MSG_WRMIFWHOLE. This doesn't prevent MRT6MSG_WRONGMIF from happening, it happens in addition to it, also it is controlled by the same throttling parameters as WRONGMIF (i.e. 1 packet per 3 seconds currently). Both messages are generated to keep backwards compatibily and avoid breaking someone who was enabling MRT_PIM with val == 4, since any positive val is accepted and treated the same. Signed-off-by: Mobashshera Rasool Signed-off-by: David S. Miller --- include/uapi/linux/mroute6.h | 1 + net/ipv6/ip6mr.c | 18 ++++++++++++++---- 2 files changed, 15 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mroute6.h b/include/uapi/linux/mroute6.h index a1fd6173e2db..1d90c21a6251 100644 --- a/include/uapi/linux/mroute6.h +++ b/include/uapi/linux/mroute6.h @@ -134,6 +134,7 @@ struct mrt6msg { #define MRT6MSG_NOCACHE 1 #define MRT6MSG_WRONGMIF 2 #define MRT6MSG_WHOLEPKT 3 /* used for use level encap */ +#define MRT6MSG_WRMIFWHOLE 4 /* For PIM Register and assert processing */ __u8 im6_mbz; /* must be zero */ __u8 im6_msgtype; /* what type of message */ __u16 im6_mif; /* mif rec'd on */ diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 0ebaaec3faf9..a9775c830194 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1040,7 +1040,7 @@ static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, int ret; #ifdef CONFIG_IPV6_PIMSM_V2 - if (assert == MRT6MSG_WHOLEPKT) + if (assert == MRT6MSG_WHOLEPKT || assert == MRT6MSG_WRMIFWHOLE) skb = skb_realloc_headroom(pkt, -skb_network_offset(pkt) +sizeof(*msg)); else @@ -1056,7 +1056,7 @@ static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, skb->ip_summed = CHECKSUM_UNNECESSARY; #ifdef CONFIG_IPV6_PIMSM_V2 - if (assert == MRT6MSG_WHOLEPKT) { + if (assert == MRT6MSG_WHOLEPKT || assert == MRT6MSG_WRMIFWHOLE) { /* Ugly, but we have no choice with this interface. Duplicate old header, fix length etc. And all this only to mangle msg->im6_msgtype and @@ -1068,8 +1068,11 @@ static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, skb_reset_transport_header(skb); msg = (struct mrt6msg *)skb_transport_header(skb); msg->im6_mbz = 0; - msg->im6_msgtype = MRT6MSG_WHOLEPKT; - msg->im6_mif = mrt->mroute_reg_vif_num; + msg->im6_msgtype = assert; + if (assert == MRT6MSG_WRMIFWHOLE) + msg->im6_mif = mifi; + else + msg->im6_mif = mrt->mroute_reg_vif_num; msg->im6_pad = 0; msg->im6_src = ipv6_hdr(pkt)->saddr; msg->im6_dst = ipv6_hdr(pkt)->daddr; @@ -1650,6 +1653,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, mifi_t mifi; struct net *net = sock_net(sk); struct mr_table *mrt; + bool do_wrmifwhole; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) @@ -1763,12 +1767,15 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, return -EINVAL; if (copy_from_sockptr(&v, optval, sizeof(v))) return -EFAULT; + + do_wrmifwhole = (v == MRT6MSG_WRMIFWHOLE); v = !!v; rtnl_lock(); ret = 0; if (v != mrt->mroute_do_pim) { mrt->mroute_do_pim = v; mrt->mroute_do_assert = v; + mrt->mroute_do_wrvifwhole = do_wrmifwhole; } rtnl_unlock(); return ret; @@ -2144,6 +2151,9 @@ static void ip6_mr_forward(struct net *net, struct mr_table *mrt, MFC_ASSERT_THRESH)) { c->_c.mfc_un.res.last_assert = jiffies; ip6mr_cache_report(mrt, skb, true_vifi, MRT6MSG_WRONGMIF); + if (mrt->mroute_do_wrvifwhole) + ip6mr_cache_report(mrt, skb, true_vifi, + MRT6MSG_WRMIFWHOLE); } goto dont_forward; } -- cgit v1.2.3 From 129e3c1bab24d27d0fa6e505a472345a92d7a2b0 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Mon, 21 Feb 2022 13:54:57 +0800 Subject: bonding: add new option ns_ip6_target This patch add a new bonding option ns_ip6_target, which correspond to the arp_ip_target. With this we set IPv6 targets and send IPv6 NS request to determine the health of the link. For other related options like the validation, we still use arp_validate, and will change to ns_validate later. Note: the sysfs configuration support was removed based on https://lore.kernel.org/netdev/8863.1645071997@famine Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- Documentation/networking/bonding.rst | 11 ++++++ drivers/net/bonding/bond_netlink.c | 59 +++++++++++++++++++++++++++++ drivers/net/bonding/bond_options.c | 72 ++++++++++++++++++++++++++++++++++++ include/net/bond_options.h | 4 ++ include/net/bonding.h | 7 ++++ include/uapi/linux/if_link.h | 1 + tools/include/uapi/linux/if_link.h | 1 + 7 files changed, 155 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst index ab98373535ea..525e6842dd33 100644 --- a/Documentation/networking/bonding.rst +++ b/Documentation/networking/bonding.rst @@ -313,6 +313,17 @@ arp_ip_target maximum number of targets that can be specified is 16. The default value is no IP addresses. +ns_ip6_target + + Specifies the IPv6 addresses to use as IPv6 monitoring peers when + arp_interval is > 0. These are the targets of the NS request + sent to determine the health of the link to the targets. + Specify these values in ffff:ffff::ffff:ffff format. Multiple IPv6 + addresses must be separated by a comma. At least one IPv6 + address must be given for NS/NA monitoring to function. The + maximum number of targets that can be specified is 16. The + default value is no IPv6 addresses. + arp_validate Specifies whether or not ARP probes and replies should be diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 1007bf6d385d..f427fa1737c7 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -14,6 +14,7 @@ #include #include #include +#include static size_t bond_get_slave_size(const struct net_device *bond_dev, const struct net_device *slave_dev) @@ -111,6 +112,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { [IFLA_BOND_TLB_DYNAMIC_LB] = { .type = NLA_U8 }, [IFLA_BOND_PEER_NOTIF_DELAY] = { .type = NLA_U32 }, [IFLA_BOND_MISSED_MAX] = { .type = NLA_U8 }, + [IFLA_BOND_NS_IP6_TARGET] = { .type = NLA_NESTED }, }; static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = { @@ -272,6 +274,40 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], if (err) return err; } +#if IS_ENABLED(CONFIG_IPV6) + if (data[IFLA_BOND_NS_IP6_TARGET]) { + struct nlattr *attr; + int i = 0, rem; + + bond_option_ns_ip6_targets_clear(bond); + nla_for_each_nested(attr, data[IFLA_BOND_NS_IP6_TARGET], rem) { + struct in6_addr addr6; + + if (nla_len(attr) < sizeof(addr6)) { + NL_SET_ERR_MSG(extack, "Invalid IPv6 address"); + return -EINVAL; + } + + addr6 = nla_get_in6_addr(attr); + + if (ipv6_addr_type(&addr6) & IPV6_ADDR_LINKLOCAL) { + NL_SET_ERR_MSG(extack, "Invalid IPv6 addr6"); + return -EINVAL; + } + + bond_opt_initextra(&newval, &addr6, sizeof(addr6)); + err = __bond_opt_set(bond, BOND_OPT_NS_TARGETS, + &newval); + if (err) + break; + i++; + } + if (i == 0 && bond->params.arp_interval) + netdev_warn(bond->dev, "Removing last ns target with arp_interval on\n"); + if (err) + return err; + } +#endif if (data[IFLA_BOND_ARP_VALIDATE]) { int arp_validate = nla_get_u32(data[IFLA_BOND_ARP_VALIDATE]); @@ -526,6 +562,9 @@ static size_t bond_get_size(const struct net_device *bond_dev) nla_total_size(sizeof(u8)) + /* IFLA_BOND_TLB_DYNAMIC_LB */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_PEER_NOTIF_DELAY */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_MISSED_MAX */ + /* IFLA_BOND_NS_IP6_TARGET */ + nla_total_size(sizeof(struct nlattr)) + + nla_total_size(sizeof(struct in6_addr)) * BOND_MAX_NS_TARGETS + 0; } @@ -603,6 +642,26 @@ static int bond_fill_info(struct sk_buff *skb, bond->params.arp_all_targets)) goto nla_put_failure; +#if IS_ENABLED(CONFIG_IPV6) + targets = nla_nest_start(skb, IFLA_BOND_NS_IP6_TARGET); + if (!targets) + goto nla_put_failure; + + targets_added = 0; + for (i = 0; i < BOND_MAX_NS_TARGETS; i++) { + if (!ipv6_addr_any(&bond->params.ns_targets[i])) { + if (nla_put_in6_addr(skb, i, &bond->params.ns_targets[i])) + goto nla_put_failure; + targets_added = 1; + } + } + + if (targets_added) + nla_nest_end(skb, targets); + else + nla_nest_cancel(skb, targets); +#endif + primary = rtnl_dereference(bond->primary_slave); if (primary && nla_put_u32(skb, IFLA_BOND_PRIMARY, primary->dev->ifindex)) diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index ab575135b626..64f7db2627ce 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -34,6 +34,10 @@ static int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target); static int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target); static int bond_option_arp_ip_targets_set(struct bonding *bond, const struct bond_opt_value *newval); +#if IS_ENABLED(CONFIG_IPV6) +static int bond_option_ns_ip6_targets_set(struct bonding *bond, + const struct bond_opt_value *newval); +#endif static int bond_option_arp_validate_set(struct bonding *bond, const struct bond_opt_value *newval); static int bond_option_arp_all_targets_set(struct bonding *bond, @@ -295,6 +299,15 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = { .flags = BOND_OPTFLAG_RAWVAL, .set = bond_option_arp_ip_targets_set }, +#if IS_ENABLED(CONFIG_IPV6) + [BOND_OPT_NS_TARGETS] = { + .id = BOND_OPT_NS_TARGETS, + .name = "ns_ip6_target", + .desc = "NS targets in ffff:ffff::ffff:ffff form", + .flags = BOND_OPTFLAG_RAWVAL, + .set = bond_option_ns_ip6_targets_set + }, +#endif [BOND_OPT_DOWNDELAY] = { .id = BOND_OPT_DOWNDELAY, .name = "downdelay", @@ -1184,6 +1197,65 @@ static int bond_option_arp_ip_targets_set(struct bonding *bond, return ret; } +#if IS_ENABLED(CONFIG_IPV6) +static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot, + struct in6_addr *target, + unsigned long last_rx) +{ + struct in6_addr *targets = bond->params.ns_targets; + struct list_head *iter; + struct slave *slave; + + if (slot >= 0 && slot < BOND_MAX_NS_TARGETS) { + bond_for_each_slave(bond, slave, iter) + slave->target_last_arp_rx[slot] = last_rx; + targets[slot] = *target; + } +} + +void bond_option_ns_ip6_targets_clear(struct bonding *bond) +{ + struct in6_addr addr_any = in6addr_any; + int i; + + for (i = 0; i < BOND_MAX_NS_TARGETS; i++) + _bond_options_ns_ip6_target_set(bond, i, &addr_any, 0); +} + +static int bond_option_ns_ip6_targets_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + struct in6_addr *target = (struct in6_addr *)newval->extra; + struct in6_addr *targets = bond->params.ns_targets; + struct in6_addr addr_any = in6addr_any; + int index; + + if (!bond_is_ip6_target_ok(target)) { + netdev_err(bond->dev, "invalid NS target %pI6c specified for addition\n", + target); + return -EINVAL; + } + + if (bond_get_targets_ip6(targets, target) != -1) { /* dup */ + netdev_err(bond->dev, "NS target %pI6c is already present\n", + target); + return -EINVAL; + } + + index = bond_get_targets_ip6(targets, &addr_any); /* first free slot */ + if (index == -1) { + netdev_err(bond->dev, "NS target table is full!\n"); + return -EINVAL; + } + + netdev_dbg(bond->dev, "Adding NS target %pI6c\n", target); + + _bond_options_ns_ip6_target_set(bond, index, target, jiffies); + + return 0; +} +#endif + static int bond_option_arp_validate_set(struct bonding *bond, const struct bond_opt_value *newval) { diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 286b29c6c451..61b49063791c 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -66,6 +66,7 @@ enum { BOND_OPT_PEER_NOTIF_DELAY, BOND_OPT_LACP_ACTIVE, BOND_OPT_MISSED_MAX, + BOND_OPT_NS_TARGETS, BOND_OPT_LAST }; @@ -140,5 +141,8 @@ static inline void __bond_opt_init(struct bond_opt_value *optval, __bond_opt_init(optval, NULL, ULLONG_MAX, extra, extra_len) void bond_option_arp_ip_targets_clear(struct bonding *bond); +#if IS_ENABLED(CONFIG_IPV6) +void bond_option_ns_ip6_targets_clear(struct bonding *bond); +#endif #endif /* _NET_BOND_OPTIONS_H */ diff --git a/include/net/bonding.h b/include/net/bonding.h index f3b986f6b6e4..d0dfe727e0b1 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -503,6 +503,13 @@ static inline int bond_is_ip_target_ok(__be32 addr) return !ipv4_is_lbcast(addr) && !ipv4_is_zeronet(addr); } +static inline int bond_is_ip6_target_ok(struct in6_addr *addr) +{ + return !ipv6_addr_any(addr) && + !ipv6_addr_loopback(addr) && + !ipv6_addr_is_multicast(addr); +} + /* Get the oldest arp which we've received on this slave for bond's * arp_targets. */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 6218f93f5c1a..e1ba2d51b717 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -860,6 +860,7 @@ enum { IFLA_BOND_PEER_NOTIF_DELAY, IFLA_BOND_AD_LACP_ACTIVE, IFLA_BOND_MISSED_MAX, + IFLA_BOND_NS_IP6_TARGET, __IFLA_BOND_MAX, }; diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 6218f93f5c1a..e1ba2d51b717 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -860,6 +860,7 @@ enum { IFLA_BOND_PEER_NOTIF_DELAY, IFLA_BOND_AD_LACP_ACTIVE, IFLA_BOND_MISSED_MAX, + IFLA_BOND_NS_IP6_TARGET, __IFLA_BOND_MAX, }; -- cgit v1.2.3 From a21d9a670d81103db7f788de1a4a4a6e4b891a0b Mon Sep 17 00:00:00 2001 From: Hans Schultz Date: Wed, 23 Feb 2022 11:16:46 +0100 Subject: net: bridge: Add support for bridge port in locked mode In a 802.1X scenario, clients connected to a bridge port shall not be allowed to have traffic forwarded until fully authenticated. A static fdb entry of the clients MAC address for the bridge port unlocks the client and allows bidirectional communication. This scenario is facilitated with setting the bridge port in locked mode, which is also supported by various switchcore chipsets. Signed-off-by: Hans Schultz Acked-by: Nikolay Aleksandrov Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 1 + include/uapi/linux/if_link.h | 1 + net/bridge/br_input.c | 11 ++++++++++- net/bridge/br_netlink.c | 6 +++++- 4 files changed, 17 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 509e18c7e740..3aae023a9353 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -58,6 +58,7 @@ struct br_ip_list { #define BR_MRP_LOST_CONT BIT(18) #define BR_MRP_LOST_IN_CONT BIT(19) #define BR_TX_FWD_OFFLOAD BIT(20) +#define BR_PORT_LOCKED BIT(21) #define BR_DEFAULT_AGEING_TIME (300 * HZ) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index e1ba2d51b717..be09d2ad4b5d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -537,6 +537,7 @@ enum { IFLA_BRPORT_MRP_IN_OPEN, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, + IFLA_BRPORT_LOCKED, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index b50382f957c1..e0c13fcc50ed 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -81,6 +81,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if (!p || p->state == BR_STATE_DISABLED) goto drop; + br = p->br; brmctx = &p->br->multicast_ctx; pmctx = &p->multicast_ctx; state = p->state; @@ -88,10 +89,18 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb &state, &vlan)) goto out; + if (p->flags & BR_PORT_LOCKED) { + struct net_bridge_fdb_entry *fdb_src = + br_fdb_find_rcu(br, eth_hdr(skb)->h_source, vid); + + if (!fdb_src || READ_ONCE(fdb_src->dst) != p || + test_bit(BR_FDB_LOCAL, &fdb_src->flags)) + goto drop; + } + nbp_switchdev_frame_mark(p, skb); /* insert into forwarding database after filtering to avoid spoofing */ - br = p->br; if (p->flags & BR_LEARNING) br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, 0); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 2ff83d84230d..7d4432ca9a20 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -184,6 +184,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */ + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */ + nla_total_size(1) /* IFLA_BRPORT_ISOLATED */ + + nla_total_size(1) /* IFLA_BRPORT_LOCKED */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ @@ -269,7 +270,8 @@ static int br_port_fill_attrs(struct sk_buff *skb, BR_MRP_LOST_CONT)) || nla_put_u8(skb, IFLA_BRPORT_MRP_IN_OPEN, !!(p->flags & BR_MRP_LOST_IN_CONT)) || - nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(p->flags & BR_ISOLATED))) + nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(p->flags & BR_ISOLATED)) || + nla_put_u8(skb, IFLA_BRPORT_LOCKED, !!(p->flags & BR_PORT_LOCKED))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); @@ -827,6 +829,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 }, [IFLA_BRPORT_ISOLATED] = { .type = NLA_U8 }, + [IFLA_BRPORT_LOCKED] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, }; @@ -893,6 +896,7 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], br_set_port_flag(p, tb, IFLA_BRPORT_VLAN_TUNNEL, BR_VLAN_TUNNEL); br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, BR_NEIGH_SUPPRESS); br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED); + br_set_port_flag(p, tb, IFLA_BRPORT_LOCKED, BR_PORT_LOCKED); changed_mask = old_flags ^ p->flags; -- cgit v1.2.3 From 1241e329ce2e1f5b1039fd356b75867b29721ad2 Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Wed, 23 Feb 2022 00:09:12 +0530 Subject: ethtool: add support to set/get completion queue event size Add support to set completion queue event size via ethtool -G parameter and get it via ethtool -g parameter. ~ # ./ethtool -G eth0 cqe-size 512 ~ # ./ethtool -g eth0 Ring parameters for eth0: Pre-set maximums: RX: 1048576 RX Mini: n/a RX Jumbo: n/a TX: 1048576 Current hardware settings: RX: 256 RX Mini: n/a RX Jumbo: n/a TX: 4096 RX Buf Len: 2048 CQE Size: 128 Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Goutham Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 11 +++++++++++ include/linux/ethtool.h | 4 ++++ include/uapi/linux/ethtool_netlink.h | 1 + net/ethtool/netlink.h | 2 +- net/ethtool/rings.c | 19 +++++++++++++++++-- 5 files changed, 34 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index cae28af7a476..24d9be69065d 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -861,6 +861,7 @@ Kernel response contents: ``ETHTOOL_A_RINGS_TX`` u32 size of TX ring ``ETHTOOL_A_RINGS_RX_BUF_LEN`` u32 size of buffers on the ring ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` u8 TCP header / data split + ``ETHTOOL_A_RINGS_CQE_SIZE`` u32 Size of TX/RX CQE ==================================== ====== =========================== ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` indicates whether the device is usable with @@ -885,6 +886,7 @@ Request contents: ``ETHTOOL_A_RINGS_RX_JUMBO`` u32 size of RX jumbo ring ``ETHTOOL_A_RINGS_TX`` u32 size of TX ring ``ETHTOOL_A_RINGS_RX_BUF_LEN`` u32 size of buffers on the ring + ``ETHTOOL_A_RINGS_CQE_SIZE`` u32 Size of TX/RX CQE ==================================== ====== =========================== Kernel checks that requested ring sizes do not exceed limits reported by @@ -892,6 +894,15 @@ driver. Driver may impose additional constraints and may not suspport all attributes. +``ETHTOOL_A_RINGS_CQE_SIZE`` specifies the completion queue event size. +Completion queue events(CQE) are the events posted by NIC to indicate the +completion status of a packet when the packet is sent(like send success or +error) or received(like pointers to packet fragments). The CQE size parameter +enables to modify the CQE size other than default size if NIC supports it. +A bigger CQE can have more receive buffer pointers inturn NIC can transfer +a bigger frame from wire. Based on the NIC hardware, the overall completion +queue size can be adjusted in the driver if CQE size is modified. + CHANNELS_GET ============ diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index e0853f48b75e..4af58459a1e7 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -71,18 +71,22 @@ enum { * struct kernel_ethtool_ringparam - RX/TX ring configuration * @rx_buf_len: Current length of buffers on the rx ring. * @tcp_data_split: Scatter packet headers and data to separate buffers + * @cqe_size: Size of TX/RX completion queue event */ struct kernel_ethtool_ringparam { u32 rx_buf_len; u8 tcp_data_split; + u32 cqe_size; }; /** * enum ethtool_supported_ring_param - indicator caps for setting ring params * @ETHTOOL_RING_USE_RX_BUF_LEN: capture for setting rx_buf_len + * @ETHTOOL_RING_USE_CQE_SIZE: capture for setting cqe_size */ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), + ETHTOOL_RING_USE_CQE_SIZE = BIT(1), }; #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 417d4280d7b5..979850221b8d 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -337,6 +337,7 @@ enum { ETHTOOL_A_RINGS_TX, /* u32 */ ETHTOOL_A_RINGS_RX_BUF_LEN, /* u32 */ ETHTOOL_A_RINGS_TCP_DATA_SPLIT, /* u8 */ + ETHTOOL_A_RINGS_CQE_SIZE, /* u32 */ /* add new constants above here */ __ETHTOOL_A_RINGS_CNT, diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 75856db299e9..29d01662a48b 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -363,7 +363,7 @@ extern const struct nla_policy ethnl_features_set_policy[ETHTOOL_A_FEATURES_WANT extern const struct nla_policy ethnl_privflags_get_policy[ETHTOOL_A_PRIVFLAGS_HEADER + 1]; extern const struct nla_policy ethnl_privflags_set_policy[ETHTOOL_A_PRIVFLAGS_FLAGS + 1]; extern const struct nla_policy ethnl_rings_get_policy[ETHTOOL_A_RINGS_HEADER + 1]; -extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_RX_BUF_LEN + 1]; +extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_CQE_SIZE + 1]; extern const struct nla_policy ethnl_channels_get_policy[ETHTOOL_A_CHANNELS_HEADER + 1]; extern const struct nla_policy ethnl_channels_set_policy[ETHTOOL_A_CHANNELS_COMBINED_COUNT + 1]; extern const struct nla_policy ethnl_coalesce_get_policy[ETHTOOL_A_COALESCE_HEADER + 1]; diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c index 18a5035d3bee..9f33c9689b56 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -54,7 +54,8 @@ static int rings_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u32)) + /* _RINGS_RX_JUMBO */ nla_total_size(sizeof(u32)) + /* _RINGS_TX */ nla_total_size(sizeof(u32)) + /* _RINGS_RX_BUF_LEN */ - nla_total_size(sizeof(u8)); /* _RINGS_TCP_DATA_SPLIT */ + nla_total_size(sizeof(u8)) + /* _RINGS_TCP_DATA_SPLIT */ + nla_total_size(sizeof(u32)); /* _RINGS_CQE_SIZE */ } static int rings_fill_reply(struct sk_buff *skb, @@ -91,7 +92,9 @@ static int rings_fill_reply(struct sk_buff *skb, (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_BUF_LEN, kr->rx_buf_len))) || (kr->tcp_data_split && (nla_put_u8(skb, ETHTOOL_A_RINGS_TCP_DATA_SPLIT, - kr->tcp_data_split)))) + kr->tcp_data_split))) || + (kr->cqe_size && + (nla_put_u32(skb, ETHTOOL_A_RINGS_CQE_SIZE, kr->cqe_size)))) return -EMSGSIZE; return 0; @@ -119,6 +122,7 @@ const struct nla_policy ethnl_rings_set_policy[] = { [ETHTOOL_A_RINGS_RX_JUMBO] = { .type = NLA_U32 }, [ETHTOOL_A_RINGS_TX] = { .type = NLA_U32 }, [ETHTOOL_A_RINGS_RX_BUF_LEN] = NLA_POLICY_MIN(NLA_U32, 1), + [ETHTOOL_A_RINGS_CQE_SIZE] = NLA_POLICY_MIN(NLA_U32, 1), }; int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info) @@ -159,6 +163,8 @@ int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info) ethnl_update_u32(&ringparam.tx_pending, tb[ETHTOOL_A_RINGS_TX], &mod); ethnl_update_u32(&kernel_ringparam.rx_buf_len, tb[ETHTOOL_A_RINGS_RX_BUF_LEN], &mod); + ethnl_update_u32(&kernel_ringparam.cqe_size, + tb[ETHTOOL_A_RINGS_CQE_SIZE], &mod); ret = 0; if (!mod) goto out_ops; @@ -190,6 +196,15 @@ int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info) goto out_ops; } + if (kernel_ringparam.cqe_size && + !(ops->supported_ring_params & ETHTOOL_RING_USE_CQE_SIZE)) { + ret = -EOPNOTSUPP; + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_RINGS_CQE_SIZE], + "setting cqe size not supported"); + goto out_ops; + } + ret = dev->ethtool_ops->set_ringparam(dev, &ringparam, &kernel_ringparam, info->extack); if (ret < 0) -- cgit v1.2.3 From 28a3f0601727d521a1c6cce62ecbcb7402a9e4f5 Mon Sep 17 00:00:00 2001 From: Toms Atteka Date: Wed, 23 Feb 2022 16:54:09 -0800 Subject: net: openvswitch: IPv6: Add IPv6 extension header support This change adds a new OpenFlow field OFPXMT_OFB_IPV6_EXTHDR and packets can be filtered using ipv6_ext flag. Signed-off-by: Toms Atteka Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 6 ++ net/openvswitch/flow.c | 140 +++++++++++++++++++++++++++++++++++++++ net/openvswitch/flow.h | 14 ++++ net/openvswitch/flow_netlink.c | 26 +++++++- 4 files changed, 184 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 150bcff49b1c..9d1710f20505 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -351,6 +351,7 @@ enum ovs_key_attr { OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, /* struct ovs_key_ct_tuple_ipv4 */ OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, /* struct ovs_key_ct_tuple_ipv6 */ OVS_KEY_ATTR_NSH, /* Nested set of ovs_nsh_key_* */ + OVS_KEY_ATTR_IPV6_EXTHDRS, /* struct ovs_key_ipv6_exthdr */ #ifdef __KERNEL__ OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */ @@ -430,6 +431,11 @@ struct ovs_key_ipv6 { __u8 ipv6_frag; /* One of OVS_FRAG_TYPE_*. */ }; +/* separate structure to support backward compatibility with older user space */ +struct ovs_key_ipv6_exthdrs { + __u16 hdrs; +}; + struct ovs_key_tcp { __be16 tcp_src; __be16 tcp_dst; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index f6cd24fd530c..8df73d86b968 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -241,6 +241,144 @@ static bool icmphdr_ok(struct sk_buff *skb) sizeof(struct icmphdr)); } +/** + * get_ipv6_ext_hdrs() - Parses packet and sets IPv6 extension header flags. + * + * @skb: buffer where extension header data starts in packet + * @nh: ipv6 header + * @ext_hdrs: flags are stored here + * + * OFPIEH12_UNREP is set if more than one of a given IPv6 extension header + * is unexpectedly encountered. (Two destination options headers may be + * expected and would not cause this bit to be set.) + * + * OFPIEH12_UNSEQ is set if IPv6 extension headers were not in the order + * preferred (but not required) by RFC 2460: + * + * When more than one extension header is used in the same packet, it is + * recommended that those headers appear in the following order: + * IPv6 header + * Hop-by-Hop Options header + * Destination Options header + * Routing header + * Fragment header + * Authentication header + * Encapsulating Security Payload header + * Destination Options header + * upper-layer header + */ +static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh, + u16 *ext_hdrs) +{ + u8 next_type = nh->nexthdr; + unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr); + int dest_options_header_count = 0; + + *ext_hdrs = 0; + + while (ipv6_ext_hdr(next_type)) { + struct ipv6_opt_hdr _hdr, *hp; + + switch (next_type) { + case IPPROTO_NONE: + *ext_hdrs |= OFPIEH12_NONEXT; + /* stop parsing */ + return; + + case IPPROTO_ESP: + if (*ext_hdrs & OFPIEH12_ESP) + *ext_hdrs |= OFPIEH12_UNREP; + if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST | + OFPIEH12_ROUTER | IPPROTO_FRAGMENT | + OFPIEH12_AUTH | OFPIEH12_UNREP)) || + dest_options_header_count >= 2) { + *ext_hdrs |= OFPIEH12_UNSEQ; + } + *ext_hdrs |= OFPIEH12_ESP; + break; + + case IPPROTO_AH: + if (*ext_hdrs & OFPIEH12_AUTH) + *ext_hdrs |= OFPIEH12_UNREP; + if ((*ext_hdrs & + ~(OFPIEH12_HOP | OFPIEH12_DEST | OFPIEH12_ROUTER | + IPPROTO_FRAGMENT | OFPIEH12_UNREP)) || + dest_options_header_count >= 2) { + *ext_hdrs |= OFPIEH12_UNSEQ; + } + *ext_hdrs |= OFPIEH12_AUTH; + break; + + case IPPROTO_DSTOPTS: + if (dest_options_header_count == 0) { + if (*ext_hdrs & + ~(OFPIEH12_HOP | OFPIEH12_UNREP)) + *ext_hdrs |= OFPIEH12_UNSEQ; + *ext_hdrs |= OFPIEH12_DEST; + } else if (dest_options_header_count == 1) { + if (*ext_hdrs & + ~(OFPIEH12_HOP | OFPIEH12_DEST | + OFPIEH12_ROUTER | OFPIEH12_FRAG | + OFPIEH12_AUTH | OFPIEH12_ESP | + OFPIEH12_UNREP)) { + *ext_hdrs |= OFPIEH12_UNSEQ; + } + } else { + *ext_hdrs |= OFPIEH12_UNREP; + } + dest_options_header_count++; + break; + + case IPPROTO_FRAGMENT: + if (*ext_hdrs & OFPIEH12_FRAG) + *ext_hdrs |= OFPIEH12_UNREP; + if ((*ext_hdrs & ~(OFPIEH12_HOP | + OFPIEH12_DEST | + OFPIEH12_ROUTER | + OFPIEH12_UNREP)) || + dest_options_header_count >= 2) { + *ext_hdrs |= OFPIEH12_UNSEQ; + } + *ext_hdrs |= OFPIEH12_FRAG; + break; + + case IPPROTO_ROUTING: + if (*ext_hdrs & OFPIEH12_ROUTER) + *ext_hdrs |= OFPIEH12_UNREP; + if ((*ext_hdrs & ~(OFPIEH12_HOP | + OFPIEH12_DEST | + OFPIEH12_UNREP)) || + dest_options_header_count >= 2) { + *ext_hdrs |= OFPIEH12_UNSEQ; + } + *ext_hdrs |= OFPIEH12_ROUTER; + break; + + case IPPROTO_HOPOPTS: + if (*ext_hdrs & OFPIEH12_HOP) + *ext_hdrs |= OFPIEH12_UNREP; + /* OFPIEH12_HOP is set to 1 if a hop-by-hop IPv6 + * extension header is present as the first + * extension header in the packet. + */ + if (*ext_hdrs == 0) + *ext_hdrs |= OFPIEH12_HOP; + else + *ext_hdrs |= OFPIEH12_UNSEQ; + break; + + default: + return; + } + + hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr); + if (!hp) + break; + next_type = hp->nexthdr; + start += ipv6_optlen(hp); + }; +} + static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) { unsigned short frag_off; @@ -256,6 +394,8 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) nh = ipv6_hdr(skb); + get_ipv6_ext_hdrs(skb, nh, &key->ipv6.exthdrs); + key->ip.proto = NEXTHDR_NONE; key->ip.tos = ipv6_get_dsfield(nh); key->ip.ttl = nh->hop_limit; diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 758a8c77f736..073ab73ffeaa 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -32,6 +32,19 @@ enum sw_flow_mac_proto { #define SW_FLOW_KEY_INVALID 0x80 #define MPLS_LABEL_DEPTH 3 +/* Bit definitions for IPv6 Extension Header pseudo-field. */ +enum ofp12_ipv6exthdr_flags { + OFPIEH12_NONEXT = 1 << 0, /* "No next header" encountered. */ + OFPIEH12_ESP = 1 << 1, /* Encrypted Sec Payload header present. */ + OFPIEH12_AUTH = 1 << 2, /* Authentication header present. */ + OFPIEH12_DEST = 1 << 3, /* 1 or 2 dest headers present. */ + OFPIEH12_FRAG = 1 << 4, /* Fragment header present. */ + OFPIEH12_ROUTER = 1 << 5, /* Router header present. */ + OFPIEH12_HOP = 1 << 6, /* Hop-by-hop header present. */ + OFPIEH12_UNREP = 1 << 7, /* Unexpected repeats encountered. */ + OFPIEH12_UNSEQ = 1 << 8 /* Unexpected sequencing encountered. */ +}; + /* Store options at the end of the array if they are less than the * maximum size. This allows us to get the benefits of variable length * matching for small options. @@ -121,6 +134,7 @@ struct sw_flow_key { struct in6_addr dst; /* IPv6 destination address. */ } addr; __be32 label; /* IPv6 flow label. */ + u16 exthdrs; /* IPv6 extension header flags */ union { struct { struct in6_addr src; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index fd1f809e9bc1..8b4124820f7d 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -346,7 +346,7 @@ size_t ovs_key_attr_size(void) /* Whenever adding new OVS_KEY_ FIELDS, we should consider * updating this function. */ - BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 29); + BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 30); return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */ + nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */ @@ -369,7 +369,8 @@ size_t ovs_key_attr_size(void) + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */ + nla_total_size(40) /* OVS_KEY_ATTR_IPV6 */ + nla_total_size(2) /* OVS_KEY_ATTR_ICMPV6 */ - + nla_total_size(28); /* OVS_KEY_ATTR_ND */ + + nla_total_size(28) /* OVS_KEY_ATTR_ND */ + + nla_total_size(2); /* OVS_KEY_ATTR_IPV6_EXTHDRS */ } static const struct ovs_len_tbl ovs_vxlan_ext_key_lens[OVS_VXLAN_EXT_MAX + 1] = { @@ -437,6 +438,8 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { .len = sizeof(struct ovs_key_ct_tuple_ipv6) }, [OVS_KEY_ATTR_NSH] = { .len = OVS_ATTR_NESTED, .next = ovs_nsh_key_attr_lens, }, + [OVS_KEY_ATTR_IPV6_EXTHDRS] = { + .len = sizeof(struct ovs_key_ipv6_exthdrs) }, }; static bool check_attr_len(unsigned int attr_len, unsigned int expected_len) @@ -1597,6 +1600,17 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match, attrs &= ~(1 << OVS_KEY_ATTR_IPV6); } + if (attrs & (1ULL << OVS_KEY_ATTR_IPV6_EXTHDRS)) { + const struct ovs_key_ipv6_exthdrs *ipv6_exthdrs_key; + + ipv6_exthdrs_key = nla_data(a[OVS_KEY_ATTR_IPV6_EXTHDRS]); + + SW_FLOW_KEY_PUT(match, ipv6.exthdrs, + ipv6_exthdrs_key->hdrs, is_mask); + + attrs &= ~(1ULL << OVS_KEY_ATTR_IPV6_EXTHDRS); + } + if (attrs & (1 << OVS_KEY_ATTR_ARP)) { const struct ovs_key_arp *arp_key; @@ -2099,6 +2113,7 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, ipv4_key->ipv4_frag = output->ip.frag; } else if (swkey->eth.type == htons(ETH_P_IPV6)) { struct ovs_key_ipv6 *ipv6_key; + struct ovs_key_ipv6_exthdrs *ipv6_exthdrs_key; nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6, sizeof(*ipv6_key)); if (!nla) @@ -2113,6 +2128,13 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, ipv6_key->ipv6_tclass = output->ip.tos; ipv6_key->ipv6_hlimit = output->ip.ttl; ipv6_key->ipv6_frag = output->ip.frag; + + nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6_EXTHDRS, + sizeof(*ipv6_exthdrs_key)); + if (!nla) + goto nla_put_failure; + ipv6_exthdrs_key = nla_data(nla); + ipv6_exthdrs_key->hdrs = output->ipv6.exthdrs; } else if (swkey->eth.type == htons(ETH_P_NSH)) { if (nsh_key_to_nlattr(&output->nsh, is_mask, skb)) goto nla_put_failure; -- cgit v1.2.3 From 7b8135f4df98b155b23754b6065c157861e268f1 Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Tue, 1 Mar 2022 05:04:34 +0000 Subject: rtnetlink: add new rtm tunnel api for tunnel id filtering This patch adds new rtm tunnel msg and api for tunnel id filtering in dst_metadata devices. First dst_metadata device to use the api is vxlan driver with AF_BRIDGE family. This and later changes add ability in vxlan driver to do tunnel id filtering (or vni filtering) on dst_metadata devices. This is similar to vlan api in the vlan filtering bridge. this patch includes selinux nlmsg_route_perms support for RTM_*TUNNEL api from Benjamin Poirier. Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 26 ++++++++++++++++++++++++++ include/uapi/linux/rtnetlink.h | 9 +++++++++ security/selinux/nlmsgtab.c | 5 ++++- 3 files changed, 39 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index be09d2ad4b5d..3dfc9ff2ec9b 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -713,7 +713,32 @@ enum ipvlan_mode { #define IPVLAN_F_PRIVATE 0x01 #define IPVLAN_F_VEPA 0x02 +/* Tunnel RTM header */ +struct tunnel_msg { + __u8 family; + __u8 reserved1; + __u16 reserved2; + __u32 ifindex; +}; + /* VXLAN section */ +enum { + VXLAN_VNIFILTER_ENTRY_UNSPEC, + VXLAN_VNIFILTER_ENTRY_START, + VXLAN_VNIFILTER_ENTRY_END, + VXLAN_VNIFILTER_ENTRY_GROUP, + VXLAN_VNIFILTER_ENTRY_GROUP6, + __VXLAN_VNIFILTER_ENTRY_MAX +}; +#define VXLAN_VNIFILTER_ENTRY_MAX (__VXLAN_VNIFILTER_ENTRY_MAX - 1) + +enum { + VXLAN_VNIFILTER_UNSPEC, + VXLAN_VNIFILTER_ENTRY, + __VXLAN_VNIFILTER_MAX +}; +#define VXLAN_VNIFILTER_MAX (__VXLAN_VNIFILTER_MAX - 1) + enum { IFLA_VXLAN_UNSPEC, IFLA_VXLAN_ID, @@ -745,6 +770,7 @@ enum { IFLA_VXLAN_GPE, IFLA_VXLAN_TTL_INHERIT, IFLA_VXLAN_DF, + IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */ __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 93d934cc4613..0970cb4b1b88 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -185,6 +185,13 @@ enum { RTM_GETNEXTHOPBUCKET, #define RTM_GETNEXTHOPBUCKET RTM_GETNEXTHOPBUCKET + RTM_NEWTUNNEL = 120, +#define RTM_NEWTUNNEL RTM_NEWTUNNEL + RTM_DELTUNNEL, +#define RTM_DELTUNNEL RTM_DELTUNNEL + RTM_GETTUNNEL, +#define RTM_GETTUNNEL RTM_GETTUNNEL + __RTM_MAX, #define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1) }; @@ -756,6 +763,8 @@ enum rtnetlink_groups { #define RTNLGRP_BRVLAN RTNLGRP_BRVLAN RTNLGRP_MCTP_IFADDR, #define RTNLGRP_MCTP_IFADDR RTNLGRP_MCTP_IFADDR + RTNLGRP_TUNNEL, +#define RTNLGRP_TUNNEL RTNLGRP_TUNNEL __RTNLGRP_MAX }; #define RTNLGRP_MAX (__RTNLGRP_MAX - 1) diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index 94ea2a8b2bb7..6ad3ee02e023 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -91,6 +91,9 @@ static const struct nlmsg_perm nlmsg_route_perms[] = { RTM_NEWNEXTHOPBUCKET, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELNEXTHOPBUCKET, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETNEXTHOPBUCKET, NETLINK_ROUTE_SOCKET__NLMSG_READ }, + { RTM_NEWTUNNEL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, + { RTM_DELTUNNEL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, + { RTM_GETTUNNEL, NETLINK_ROUTE_SOCKET__NLMSG_READ }, }; static const struct nlmsg_perm nlmsg_tcpdiag_perms[] = @@ -176,7 +179,7 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm) * structures at the top of this file with the new mappings * before updating the BUILD_BUG_ON() macro! */ - BUILD_BUG_ON(RTM_MAX != (RTM_NEWNEXTHOPBUCKET + 3)); + BUILD_BUG_ON(RTM_MAX != (RTM_NEWTUNNEL + 3)); err = nlmsg_perm(nlmsg_type, perm, nlmsg_route_perms, sizeof(nlmsg_route_perms)); break; -- cgit v1.2.3 From 445b2f36bb4efb81f064e931f28b9ec19f114355 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 1 Mar 2022 05:04:39 +0000 Subject: drivers: vxlan: vnifilter: add support for stats dumping Add support for VXLAN vni filter entries' stats dumping Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- drivers/net/vxlan/vxlan_vnifilter.c | 92 ++++++++++++++++++++++++++++++++++--- include/uapi/linux/if_link.h | 25 +++++++++- 2 files changed, 110 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c index 2d23312f4f62..9f28d0b6a6b2 100644 --- a/drivers/net/vxlan/vxlan_vnifilter.c +++ b/drivers/net/vxlan/vxlan_vnifilter.c @@ -116,6 +116,34 @@ void vxlan_vs_del_vnigrp(struct vxlan_dev *vxlan) spin_unlock(&vn->sock_lock); } +static void vxlan_vnifilter_stats_get(const struct vxlan_vni_node *vninode, + struct vxlan_vni_stats *dest) +{ + int i; + + memset(dest, 0, sizeof(*dest)); + for_each_possible_cpu(i) { + struct vxlan_vni_stats_pcpu *pstats; + struct vxlan_vni_stats temp; + unsigned int start; + + pstats = per_cpu_ptr(vninode->stats, i); + do { + start = u64_stats_fetch_begin_irq(&pstats->syncp); + memcpy(&temp, &pstats->stats, sizeof(temp)); + } while (u64_stats_fetch_retry_irq(&pstats->syncp, start)); + + dest->rx_packets += temp.rx_packets; + dest->rx_bytes += temp.rx_bytes; + dest->rx_drops += temp.rx_drops; + dest->rx_errors += temp.rx_errors; + dest->tx_packets += temp.tx_packets; + dest->tx_bytes += temp.tx_bytes; + dest->tx_drops += temp.tx_drops; + dest->tx_errors += temp.tx_errors; + } +} + static void vxlan_vnifilter_stats_add(struct vxlan_vni_node *vninode, int type, unsigned int len) { @@ -182,9 +210,48 @@ static size_t vxlan_vnifilter_entry_nlmsg_size(void) + nla_total_size(sizeof(struct in6_addr));/* VXLAN_VNIFILTER_ENTRY_GROUP{6} */ } +static int __vnifilter_entry_fill_stats(struct sk_buff *skb, + const struct vxlan_vni_node *vbegin) +{ + struct vxlan_vni_stats vstats; + struct nlattr *vstats_attr; + + vstats_attr = nla_nest_start(skb, VXLAN_VNIFILTER_ENTRY_STATS); + if (!vstats_attr) + goto out_stats_err; + + vxlan_vnifilter_stats_get(vbegin, &vstats); + if (nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_RX_BYTES, + vstats.rx_bytes, VNIFILTER_ENTRY_STATS_PAD) || + nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_RX_PKTS, + vstats.rx_packets, VNIFILTER_ENTRY_STATS_PAD) || + nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_RX_DROPS, + vstats.rx_drops, VNIFILTER_ENTRY_STATS_PAD) || + nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_RX_ERRORS, + vstats.rx_errors, VNIFILTER_ENTRY_STATS_PAD) || + nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_TX_BYTES, + vstats.tx_bytes, VNIFILTER_ENTRY_STATS_PAD) || + nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_TX_PKTS, + vstats.tx_packets, VNIFILTER_ENTRY_STATS_PAD) || + nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_TX_DROPS, + vstats.tx_drops, VNIFILTER_ENTRY_STATS_PAD) || + nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_TX_ERRORS, + vstats.tx_errors, VNIFILTER_ENTRY_STATS_PAD)) + goto out_stats_err; + + nla_nest_end(skb, vstats_attr); + + return 0; + +out_stats_err: + nla_nest_cancel(skb, vstats_attr); + return -EMSGSIZE; +} + static bool vxlan_fill_vni_filter_entry(struct sk_buff *skb, struct vxlan_vni_node *vbegin, - struct vxlan_vni_node *vend) + struct vxlan_vni_node *vend, + bool fill_stats) { struct nlattr *ventry; u32 vs = be32_to_cpu(vbegin->vni); @@ -217,6 +284,9 @@ static bool vxlan_fill_vni_filter_entry(struct sk_buff *skb, } } + if (fill_stats && __vnifilter_entry_fill_stats(skb, vbegin)) + goto out_err; + nla_nest_end(skb, ventry); return true; @@ -249,7 +319,7 @@ static void vxlan_vnifilter_notify(const struct vxlan_dev *vxlan, tmsg->family = AF_BRIDGE; tmsg->ifindex = vxlan->dev->ifindex; - if (!vxlan_fill_vni_filter_entry(skb, vninode, vninode)) + if (!vxlan_fill_vni_filter_entry(skb, vninode, vninode, false)) goto out_err; nlmsg_end(skb, nlh); @@ -269,10 +339,11 @@ static int vxlan_vnifilter_dump_dev(const struct net_device *dev, { struct vxlan_vni_node *tmp, *v, *vbegin = NULL, *vend = NULL; struct vxlan_dev *vxlan = netdev_priv(dev); - struct tunnel_msg *new_tmsg; + struct tunnel_msg *new_tmsg, *tmsg; int idx = 0, s_idx = cb->args[1]; struct vxlan_vni_group *vg; struct nlmsghdr *nlh; + bool dump_stats; int err = 0; if (!(vxlan->cfg.flags & VXLAN_F_VNIFILTER)) @@ -283,6 +354,9 @@ static int vxlan_vnifilter_dump_dev(const struct net_device *dev, if (!vg || !vg->num_vnis) return 0; + tmsg = nlmsg_data(cb->nlh); + dump_stats = !!(tmsg->flags & TUNNEL_MSG_FLAG_STATS); + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWTUNNEL, sizeof(*new_tmsg), NLM_F_MULTI); if (!nlh) @@ -302,11 +376,12 @@ static int vxlan_vnifilter_dump_dev(const struct net_device *dev, vend = v; continue; } - if (vnirange(vend, v) == 1 && + if (!dump_stats && vnirange(vend, v) == 1 && vxlan_addr_equal(&v->remote_ip, &vend->remote_ip)) { goto update_end; } else { - if (!vxlan_fill_vni_filter_entry(skb, vbegin, vend)) { + if (!vxlan_fill_vni_filter_entry(skb, vbegin, vend, + dump_stats)) { err = -EMSGSIZE; break; } @@ -318,7 +393,7 @@ update_end: } if (!err && vbegin) { - if (!vxlan_fill_vni_filter_entry(skb, vbegin, vend)) + if (!vxlan_fill_vni_filter_entry(skb, vbegin, vend, dump_stats)) err = -EMSGSIZE; } @@ -338,6 +413,11 @@ static int vxlan_vnifilter_dump(struct sk_buff *skb, struct netlink_callback *cb tmsg = nlmsg_data(cb->nlh); + if (tmsg->flags & ~TUNNEL_MSG_VALID_USER_FLAGS) { + NL_SET_ERR_MSG(cb->extack, "Invalid tunnelmsg flags in ancillary header"); + return -EINVAL; + } + rcu_read_lock(); if (tmsg->ifindex) { dev = dev_get_by_index_rcu(net, tmsg->ifindex); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 3dfc9ff2ec9b..e315e53125f4 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -716,18 +716,41 @@ enum ipvlan_mode { /* Tunnel RTM header */ struct tunnel_msg { __u8 family; - __u8 reserved1; + __u8 flags; __u16 reserved2; __u32 ifindex; }; /* VXLAN section */ + +/* include statistics in the dump */ +#define TUNNEL_MSG_FLAG_STATS 0x01 + +#define TUNNEL_MSG_VALID_USER_FLAGS TUNNEL_MSG_FLAG_STATS + +/* Embedded inside VXLAN_VNIFILTER_ENTRY_STATS */ +enum { + VNIFILTER_ENTRY_STATS_UNSPEC, + VNIFILTER_ENTRY_STATS_RX_BYTES, + VNIFILTER_ENTRY_STATS_RX_PKTS, + VNIFILTER_ENTRY_STATS_RX_DROPS, + VNIFILTER_ENTRY_STATS_RX_ERRORS, + VNIFILTER_ENTRY_STATS_TX_BYTES, + VNIFILTER_ENTRY_STATS_TX_PKTS, + VNIFILTER_ENTRY_STATS_TX_DROPS, + VNIFILTER_ENTRY_STATS_TX_ERRORS, + VNIFILTER_ENTRY_STATS_PAD, + __VNIFILTER_ENTRY_STATS_MAX +}; +#define VNIFILTER_ENTRY_STATS_MAX (__VNIFILTER_ENTRY_STATS_MAX - 1) + enum { VXLAN_VNIFILTER_ENTRY_UNSPEC, VXLAN_VNIFILTER_ENTRY_START, VXLAN_VNIFILTER_ENTRY_END, VXLAN_VNIFILTER_ENTRY_GROUP, VXLAN_VNIFILTER_ENTRY_GROUP6, + VXLAN_VNIFILTER_ENTRY_STATS, __VXLAN_VNIFILTER_ENTRY_MAX }; #define VXLAN_VNIFILTER_ENTRY_MAX (__VXLAN_VNIFILTER_ENTRY_MAX - 1) -- cgit v1.2.3 From dd0ca255f3d27a1bb43d8e9529fb3645f9a341a3 Mon Sep 17 00:00:00 2001 From: Daniel Braunwarth Date: Mon, 28 Feb 2022 14:30:28 +0100 Subject: if_ether.h: add PROFINET Ethertype Add the Ethertype for PROFINET protocol. Signed-off-by: Daniel Braunwarth Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index c0c2f3ed5729..4f4ed35a16db 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -86,6 +86,7 @@ * over Ethernet */ #define ETH_P_PAE 0x888E /* Port Access Entity (IEEE 802.1X) */ +#define ETH_P_PROFINET 0x8892 /* PROFINET */ #define ETH_P_REALTEK 0x8899 /* Multiple proprietary protocols */ #define ETH_P_AOE 0x88A2 /* ATA over Ethernet */ #define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */ -- cgit v1.2.3 From cd73cda742fbe1f33ed7306c7a01aa64f4e6ebd5 Mon Sep 17 00:00:00 2001 From: Daniel Braunwarth Date: Mon, 28 Feb 2022 14:30:29 +0100 Subject: if_ether.h: add EtherCAT Ethertype Add the Ethertype for EtherCAT protocol. Signed-off-by: Daniel Braunwarth Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 4f4ed35a16db..1d0bccc3fa54 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -89,6 +89,7 @@ #define ETH_P_PROFINET 0x8892 /* PROFINET */ #define ETH_P_REALTEK 0x8899 /* Multiple proprietary protocols */ #define ETH_P_AOE 0x88A2 /* ATA over Ethernet */ +#define ETH_P_ETHERCAT 0x88A4 /* EtherCAT */ #define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */ #define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */ #define ETH_P_PREAUTH 0x88C7 /* 802.11 Preauthentication */ -- cgit v1.2.3 From 46efc97b73060823fdc18103a5e317a8327d44e1 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 2 Mar 2022 18:31:17 +0200 Subject: net: rtnetlink: RTM_GETSTATS: Allow filtering inside nests The filter_mask field of RTM_GETSTATS header determines which top-level attributes should be included in the netlink response. This saves processing time by only including the bits that the user cares about instead of always dumping everything. This is doubly important for HW-backed statistics that would typically require a trip to the device to fetch the stats. So far there was only one HW-backed stat suite per attribute. However, IFLA_STATS_LINK_OFFLOAD_XSTATS is a nest, and will gain a new stat suite in the following patches. It would therefore be advantageous to be able to filter within that nest, and select just one or the other HW-backed statistics suite. Extend rtnetlink so that RTM_GETSTATS permits attributes in the payload. The scheme is as follows: - RTM_GETSTATS - struct if_stats_msg - attr nest IFLA_STATS_GET_FILTERS - attr IFLA_STATS_LINK_OFFLOAD_XSTATS - u32 filter_mask This scheme reuses the existing enumerators by nesting them in a dedicated context attribute. This is covered by policies as usual, therefore a gradual opt-in is possible. Currently only IFLA_STATS_LINK_OFFLOAD_XSTATS nest has filtering enabled, because for the SW counters the issue does not seem to be that important. rtnl_offload_xstats_get_size() and _fill() are extended to observe the requested filters. Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 10 +++ net/core/rtnetlink.c | 141 ++++++++++++++++++++++++++++++++++++------- 2 files changed, 128 insertions(+), 23 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index e315e53125f4..4d62ea6e1288 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1207,6 +1207,16 @@ enum { #define IFLA_STATS_FILTER_BIT(ATTR) (1 << (ATTR - 1)) +enum { + IFLA_STATS_GETSET_UNSPEC, + IFLA_STATS_GET_FILTERS, /* Nest of IFLA_STATS_LINK_xxx, each a u32 with + * a filter mask for the corresponding group. + */ + __IFLA_STATS_GETSET_MAX, +}; + +#define IFLA_STATS_GETSET_MAX (__IFLA_STATS_GETSET_MAX - 1) + /* These are embedded into IFLA_STATS_LINK_XSTATS: * [IFLA_STATS_LINK_XSTATS] * -> [LINK_XSTATS_TYPE_xxx] diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index ad858799fd93..31aa26062070 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -5092,13 +5092,15 @@ rtnl_offload_xstats_fill_ndo(struct net_device *dev, int attr_id, } static int rtnl_offload_xstats_fill(struct sk_buff *skb, struct net_device *dev, - int *prividx) + int *prividx, u32 off_filter_mask) { int attr_id_cpu_hit = IFLA_OFFLOAD_XSTATS_CPU_HIT; bool have_data = false; int err; - if (*prividx <= attr_id_cpu_hit) { + if (*prividx <= attr_id_cpu_hit && + (off_filter_mask & + IFLA_STATS_FILTER_BIT(attr_id_cpu_hit))) { err = rtnl_offload_xstats_fill_ndo(dev, attr_id_cpu_hit, skb); if (!err) { have_data = true; @@ -5115,14 +5117,18 @@ static int rtnl_offload_xstats_fill(struct sk_buff *skb, struct net_device *dev, return 0; } -static int rtnl_offload_xstats_get_size(const struct net_device *dev) +static int rtnl_offload_xstats_get_size(const struct net_device *dev, + u32 off_filter_mask) { int attr_id_cpu_hit = IFLA_OFFLOAD_XSTATS_CPU_HIT; int nla_size = 0; int size; - size = rtnl_offload_xstats_get_size_ndo(dev, attr_id_cpu_hit); - nla_size += nla_total_size_64bit(size); + if (off_filter_mask & + IFLA_STATS_FILTER_BIT(attr_id_cpu_hit)) { + size = rtnl_offload_xstats_get_size_ndo(dev, attr_id_cpu_hit); + nla_size += nla_total_size_64bit(size); + } if (nla_size != 0) nla_size += nla_total_size(0); @@ -5130,11 +5136,20 @@ static int rtnl_offload_xstats_get_size(const struct net_device *dev) return nla_size; } +struct rtnl_stats_dump_filters { + /* mask[0] filters outer attributes. Then individual nests have their + * filtering mask at the index of the nested attribute. + */ + u32 mask[IFLA_STATS_MAX + 1]; +}; + static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, - unsigned int flags, unsigned int filter_mask, + unsigned int flags, + const struct rtnl_stats_dump_filters *filters, int *idxattr, int *prividx) { + unsigned int filter_mask = filters->mask[0]; struct if_stats_msg *ifsm; struct nlmsghdr *nlh; struct nlattr *attr; @@ -5210,13 +5225,17 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_OFFLOAD_XSTATS, *idxattr)) { + u32 off_filter_mask; + + off_filter_mask = filters->mask[IFLA_STATS_LINK_OFFLOAD_XSTATS]; *idxattr = IFLA_STATS_LINK_OFFLOAD_XSTATS; attr = nla_nest_start_noflag(skb, IFLA_STATS_LINK_OFFLOAD_XSTATS); if (!attr) goto nla_put_failure; - err = rtnl_offload_xstats_fill(skb, dev, prividx); + err = rtnl_offload_xstats_fill(skb, dev, prividx, + off_filter_mask); if (err == -ENODATA) nla_nest_cancel(skb, attr); else @@ -5281,9 +5300,10 @@ nla_put_failure: } static size_t if_nlmsg_stats_size(const struct net_device *dev, - u32 filter_mask) + const struct rtnl_stats_dump_filters *filters) { size_t size = NLMSG_ALIGN(sizeof(struct if_stats_msg)); + unsigned int filter_mask = filters->mask[0]; if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_64, 0)) size += nla_total_size_64bit(sizeof(struct rtnl_link_stats64)); @@ -5319,8 +5339,12 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev, } } - if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_OFFLOAD_XSTATS, 0)) - size += rtnl_offload_xstats_get_size(dev); + if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_OFFLOAD_XSTATS, 0)) { + u32 off_filter_mask; + + off_filter_mask = filters->mask[IFLA_STATS_LINK_OFFLOAD_XSTATS]; + size += rtnl_offload_xstats_get_size(dev, off_filter_mask); + } if (stats_attr_valid(filter_mask, IFLA_STATS_AF_SPEC, 0)) { struct rtnl_af_ops *af_ops; @@ -5344,6 +5368,74 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev, return size; } +#define RTNL_STATS_OFFLOAD_XSTATS_VALID ((1 << __IFLA_OFFLOAD_XSTATS_MAX) - 1) + +static const struct nla_policy +rtnl_stats_get_policy_filters[IFLA_STATS_MAX + 1] = { + [IFLA_STATS_LINK_OFFLOAD_XSTATS] = + NLA_POLICY_MASK(NLA_U32, RTNL_STATS_OFFLOAD_XSTATS_VALID), +}; + +static const struct nla_policy +rtnl_stats_get_policy[IFLA_STATS_GETSET_MAX + 1] = { + [IFLA_STATS_GET_FILTERS] = + NLA_POLICY_NESTED(rtnl_stats_get_policy_filters), +}; + +static int rtnl_stats_get_parse_filters(struct nlattr *ifla_filters, + struct rtnl_stats_dump_filters *filters, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_STATS_MAX + 1]; + int err; + int at; + + err = nla_parse_nested(tb, IFLA_STATS_MAX, ifla_filters, + rtnl_stats_get_policy_filters, extack); + if (err < 0) + return err; + + for (at = 1; at <= IFLA_STATS_MAX; at++) { + if (tb[at]) { + if (!(filters->mask[0] & IFLA_STATS_FILTER_BIT(at))) { + NL_SET_ERR_MSG(extack, "Filtered attribute not enabled in filter_mask"); + return -EINVAL; + } + filters->mask[at] = nla_get_u32(tb[at]); + } + } + + return 0; +} + +static int rtnl_stats_get_parse(const struct nlmsghdr *nlh, + u32 filter_mask, + struct rtnl_stats_dump_filters *filters, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_STATS_GETSET_MAX + 1]; + int err; + int i; + + filters->mask[0] = filter_mask; + for (i = 1; i < ARRAY_SIZE(filters->mask); i++) + filters->mask[i] = -1U; + + err = nlmsg_parse(nlh, sizeof(struct if_stats_msg), tb, + IFLA_STATS_GETSET_MAX, rtnl_stats_get_policy, extack); + if (err < 0) + return err; + + if (tb[IFLA_STATS_GET_FILTERS]) { + err = rtnl_stats_get_parse_filters(tb[IFLA_STATS_GET_FILTERS], + filters, extack); + if (err) + return err; + } + + return 0; +} + static int rtnl_valid_stats_req(const struct nlmsghdr *nlh, bool strict_check, bool is_dump, struct netlink_ext_ack *extack) { @@ -5366,10 +5458,6 @@ static int rtnl_valid_stats_req(const struct nlmsghdr *nlh, bool strict_check, NL_SET_ERR_MSG(extack, "Invalid values in header for stats dump request"); return -EINVAL; } - if (nlmsg_attrlen(nlh, sizeof(*ifsm))) { - NL_SET_ERR_MSG(extack, "Invalid attributes after stats header"); - return -EINVAL; - } if (ifsm->filter_mask >= IFLA_STATS_FILTER_BIT(IFLA_STATS_MAX + 1)) { NL_SET_ERR_MSG(extack, "Invalid stats requested through filter mask"); return -EINVAL; @@ -5381,12 +5469,12 @@ static int rtnl_valid_stats_req(const struct nlmsghdr *nlh, bool strict_check, static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { + struct rtnl_stats_dump_filters filters; struct net *net = sock_net(skb->sk); struct net_device *dev = NULL; int idxattr = 0, prividx = 0; struct if_stats_msg *ifsm; struct sk_buff *nskb; - u32 filter_mask; int err; err = rtnl_valid_stats_req(nlh, netlink_strict_get_check(skb), @@ -5403,19 +5491,22 @@ static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh, if (!dev) return -ENODEV; - filter_mask = ifsm->filter_mask; - if (!filter_mask) { + if (!ifsm->filter_mask) { NL_SET_ERR_MSG(extack, "Filter mask must be set for stats get"); return -EINVAL; } - nskb = nlmsg_new(if_nlmsg_stats_size(dev, filter_mask), GFP_KERNEL); + err = rtnl_stats_get_parse(nlh, ifsm->filter_mask, &filters, extack); + if (err) + return err; + + nskb = nlmsg_new(if_nlmsg_stats_size(dev, &filters), GFP_KERNEL); if (!nskb) return -ENOBUFS; err = rtnl_fill_statsinfo(nskb, dev, RTM_NEWSTATS, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, - 0, filter_mask, &idxattr, &prividx); + 0, &filters, &idxattr, &prividx); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_stats_size */ WARN_ON(err == -EMSGSIZE); @@ -5431,12 +5522,12 @@ static int rtnl_stats_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; int h, s_h, err, s_idx, s_idxattr, s_prividx; + struct rtnl_stats_dump_filters filters; struct net *net = sock_net(skb->sk); unsigned int flags = NLM_F_MULTI; struct if_stats_msg *ifsm; struct hlist_head *head; struct net_device *dev; - u32 filter_mask = 0; int idx = 0; s_h = cb->args[0]; @@ -5451,12 +5542,16 @@ static int rtnl_stats_dump(struct sk_buff *skb, struct netlink_callback *cb) return err; ifsm = nlmsg_data(cb->nlh); - filter_mask = ifsm->filter_mask; - if (!filter_mask) { + if (!ifsm->filter_mask) { NL_SET_ERR_MSG(extack, "Filter mask must be set for stats dump"); return -EINVAL; } + err = rtnl_stats_get_parse(cb->nlh, ifsm->filter_mask, &filters, + extack); + if (err) + return err; + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; @@ -5466,7 +5561,7 @@ static int rtnl_stats_dump(struct sk_buff *skb, struct netlink_callback *cb) err = rtnl_fill_statsinfo(skb, dev, RTM_NEWSTATS, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, 0, - flags, filter_mask, + flags, &filters, &s_idxattr, &s_prividx); /* If we ran out of room on the first message, * we're in trouble -- cgit v1.2.3 From 9309f97aef6d8250bb484dabeac925c3a7c57716 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 2 Mar 2022 18:31:20 +0200 Subject: net: dev: Add hardware stats support Offloading switch device drivers may be able to collect statistics of the traffic taking place in the HW datapath that pertains to a certain soft netdevice, such as VLAN. Add the necessary infrastructure to allow exposing these statistics to the offloaded netdevice in question. The API was shaped by the following considerations: - Collection of HW statistics is not free: there may be a finite number of counters, and the act of counting may have a performance impact. It is therefore necessary to allow toggling whether HW counting should be done for any particular SW netdevice. - As the drivers are loaded and removed, a particular device may get offloaded and unoffloaded again. At the same time, the statistics values need to stay monotonic (modulo the eventual 64-bit wraparound), increasing only to reflect traffic measured in the device. To that end, the netdevice keeps around a lazily-allocated copy of struct rtnl_link_stats64. Device drivers then contribute to the values kept therein at various points. Even as the driver goes away, the struct stays around to maintain the statistics values. - Different HW devices may be able to count different things. The motivation behind this patch in particular is exposure of HW counters on Nvidia Spectrum switches, where the only practical approach to counting traffic on offloaded soft netdevices currently is to use router interface counters, and count L3 traffic. Correspondingly that is the statistics suite added in this patch. Other devices may be able to measure different kinds of traffic, and for that reason, the APIs are built to allow uniform access to different statistics suites. - Because soft netdevices and offloading drivers are only loosely bound, a netdevice uses a notifier chain to communicate with the drivers. Several new notifiers, NETDEV_OFFLOAD_XSTATS_*, have been added to carry messages to the offloading drivers. - Devices can have various conditions for when a particular counter is available. As the device is configured and reconfigured, the device offload may become or cease being suitable for counter binding. A netdevice can use a notifier type NETDEV_OFFLOAD_XSTATS_REPORT_USED to ping offloading drivers and determine whether anyone currently implements a given statistics suite. This information can then be propagated to user space. When the driver decides to unoffload a netdevice, it can use a newly-added function, netdev_offload_xstats_report_delta(), to record outstanding collected statistics, before destroying the HW counter. This patch adds a helper, call_netdevice_notifiers_info_robust(), for dispatching a notifier with the possibility of unwind when one of the consumers bails. Given the wish to eventually get rid of the global notifier block altogether, this helper only invokes the per-netns notifier block. Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 42 +++++++ include/uapi/linux/if_link.h | 15 +++ net/core/dev.c | 267 ++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 323 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c79ee2296296..19a27ac361ef 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1950,6 +1950,7 @@ enum netdev_ml_priv_type { * @watchdog_dev_tracker: refcount tracker used by watchdog. * @dev_registered_tracker: tracker for reference held while * registered + * @offload_xstats_l3: L3 HW stats for this netdevice. * * FIXME: cleanup struct net_device such that network protocol info * moves out. @@ -2287,6 +2288,7 @@ struct net_device { netdevice_tracker linkwatch_dev_tracker; netdevice_tracker watchdog_dev_tracker; netdevice_tracker dev_registered_tracker; + struct rtnl_hw_stats64 *offload_xstats_l3; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -2727,6 +2729,10 @@ enum netdev_cmd { NETDEV_CVLAN_FILTER_DROP_INFO, NETDEV_SVLAN_FILTER_PUSH_INFO, NETDEV_SVLAN_FILTER_DROP_INFO, + NETDEV_OFFLOAD_XSTATS_ENABLE, + NETDEV_OFFLOAD_XSTATS_DISABLE, + NETDEV_OFFLOAD_XSTATS_REPORT_USED, + NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, }; const char *netdev_cmd_to_name(enum netdev_cmd cmd); @@ -2777,6 +2783,42 @@ struct netdev_notifier_pre_changeaddr_info { const unsigned char *dev_addr; }; +enum netdev_offload_xstats_type { + NETDEV_OFFLOAD_XSTATS_TYPE_L3 = 1, +}; + +struct netdev_notifier_offload_xstats_info { + struct netdev_notifier_info info; /* must be first */ + enum netdev_offload_xstats_type type; + + union { + /* NETDEV_OFFLOAD_XSTATS_REPORT_DELTA */ + struct netdev_notifier_offload_xstats_rd *report_delta; + /* NETDEV_OFFLOAD_XSTATS_REPORT_USED */ + struct netdev_notifier_offload_xstats_ru *report_used; + }; +}; + +int netdev_offload_xstats_enable(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct netlink_ext_ack *extack); +int netdev_offload_xstats_disable(struct net_device *dev, + enum netdev_offload_xstats_type type); +bool netdev_offload_xstats_enabled(const struct net_device *dev, + enum netdev_offload_xstats_type type); +int netdev_offload_xstats_get(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct rtnl_hw_stats64 *stats, bool *used, + struct netlink_ext_ack *extack); +void +netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *rd, + const struct rtnl_hw_stats64 *stats); +void +netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *ru); +void netdev_offload_xstats_push_delta(struct net_device *dev, + enum netdev_offload_xstats_type type, + const struct rtnl_hw_stats64 *stats); + static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 4d62ea6e1288..ef6a62a2e15d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -245,6 +245,21 @@ struct rtnl_link_stats64 { __u64 rx_nohandler; }; +/* Subset of link stats useful for in-HW collection. Meaning of the fields is as + * for struct rtnl_link_stats64. + */ +struct rtnl_hw_stats64 { + __u64 rx_packets; + __u64 tx_packets; + __u64 rx_bytes; + __u64 tx_bytes; + __u64 rx_errors; + __u64 tx_errors; + __u64 rx_dropped; + __u64 tx_dropped; + __u64 multicast; +}; + /* The struct should be in sync with struct ifmap */ struct rtnl_link_ifmap { __u64 mem_start; diff --git a/net/core/dev.c b/net/core/dev.c index 2d6771075720..c9e54e5ad48d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1622,7 +1622,8 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd) N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) - N(PRE_CHANGEADDR) + N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE) + N(OFFLOAD_XSTATS_REPORT_USED) N(OFFLOAD_XSTATS_REPORT_DELTA) } #undef N return "UNKNOWN_NETDEV_EVENT"; @@ -1939,6 +1940,32 @@ static int call_netdevice_notifiers_info(unsigned long val, return raw_notifier_call_chain(&netdev_chain, val, info); } +/** + * call_netdevice_notifiers_info_robust - call per-netns notifier blocks + * for and rollback on error + * @val_up: value passed unmodified to notifier function + * @val_down: value passed unmodified to the notifier function when + * recovering from an error on @val_up + * @info: notifier information data + * + * Call all per-netns network notifier blocks, but not notifier blocks on + * the global notifier chain. Parameters and return value are as for + * raw_notifier_call_chain_robust(). + */ + +static int +call_netdevice_notifiers_info_robust(unsigned long val_up, + unsigned long val_down, + struct netdev_notifier_info *info) +{ + struct net *net = dev_net(info->dev); + + ASSERT_RTNL(); + + return raw_notifier_call_chain_robust(&net->netdev_chain, + val_up, val_down, info); +} + static int call_netdevice_notifiers_extack(unsigned long val, struct net_device *dev, struct netlink_ext_ack *extack) @@ -7728,6 +7755,242 @@ void netdev_bonding_info_change(struct net_device *dev, } EXPORT_SYMBOL(netdev_bonding_info_change); +static int netdev_offload_xstats_enable_l3(struct net_device *dev, + struct netlink_ext_ack *extack) +{ + struct netdev_notifier_offload_xstats_info info = { + .info.dev = dev, + .info.extack = extack, + .type = NETDEV_OFFLOAD_XSTATS_TYPE_L3, + }; + int err; + int rc; + + dev->offload_xstats_l3 = kzalloc(sizeof(*dev->offload_xstats_l3), + GFP_KERNEL); + if (!dev->offload_xstats_l3) + return -ENOMEM; + + rc = call_netdevice_notifiers_info_robust(NETDEV_OFFLOAD_XSTATS_ENABLE, + NETDEV_OFFLOAD_XSTATS_DISABLE, + &info.info); + err = notifier_to_errno(rc); + if (err) + goto free_stats; + + return 0; + +free_stats: + kfree(dev->offload_xstats_l3); + dev->offload_xstats_l3 = NULL; + return err; +} + +int netdev_offload_xstats_enable(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct netlink_ext_ack *extack) +{ + ASSERT_RTNL(); + + if (netdev_offload_xstats_enabled(dev, type)) + return -EALREADY; + + switch (type) { + case NETDEV_OFFLOAD_XSTATS_TYPE_L3: + return netdev_offload_xstats_enable_l3(dev, extack); + } + + WARN_ON(1); + return -EINVAL; +} +EXPORT_SYMBOL(netdev_offload_xstats_enable); + +static void netdev_offload_xstats_disable_l3(struct net_device *dev) +{ + struct netdev_notifier_offload_xstats_info info = { + .info.dev = dev, + .type = NETDEV_OFFLOAD_XSTATS_TYPE_L3, + }; + + call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_DISABLE, + &info.info); + kfree(dev->offload_xstats_l3); + dev->offload_xstats_l3 = NULL; +} + +int netdev_offload_xstats_disable(struct net_device *dev, + enum netdev_offload_xstats_type type) +{ + ASSERT_RTNL(); + + if (!netdev_offload_xstats_enabled(dev, type)) + return -EALREADY; + + switch (type) { + case NETDEV_OFFLOAD_XSTATS_TYPE_L3: + netdev_offload_xstats_disable_l3(dev); + return 0; + } + + WARN_ON(1); + return -EINVAL; +} +EXPORT_SYMBOL(netdev_offload_xstats_disable); + +static void netdev_offload_xstats_disable_all(struct net_device *dev) +{ + netdev_offload_xstats_disable(dev, NETDEV_OFFLOAD_XSTATS_TYPE_L3); +} + +static struct rtnl_hw_stats64 * +netdev_offload_xstats_get_ptr(const struct net_device *dev, + enum netdev_offload_xstats_type type) +{ + switch (type) { + case NETDEV_OFFLOAD_XSTATS_TYPE_L3: + return dev->offload_xstats_l3; + } + + WARN_ON(1); + return NULL; +} + +bool netdev_offload_xstats_enabled(const struct net_device *dev, + enum netdev_offload_xstats_type type) +{ + ASSERT_RTNL(); + + return netdev_offload_xstats_get_ptr(dev, type); +} +EXPORT_SYMBOL(netdev_offload_xstats_enabled); + +struct netdev_notifier_offload_xstats_ru { + bool used; +}; + +struct netdev_notifier_offload_xstats_rd { + struct rtnl_hw_stats64 stats; + bool used; +}; + +static void netdev_hw_stats64_add(struct rtnl_hw_stats64 *dest, + const struct rtnl_hw_stats64 *src) +{ + dest->rx_packets += src->rx_packets; + dest->tx_packets += src->tx_packets; + dest->rx_bytes += src->rx_bytes; + dest->tx_bytes += src->tx_bytes; + dest->rx_errors += src->rx_errors; + dest->tx_errors += src->tx_errors; + dest->rx_dropped += src->rx_dropped; + dest->tx_dropped += src->tx_dropped; + dest->multicast += src->multicast; +} + +static int netdev_offload_xstats_get_used(struct net_device *dev, + enum netdev_offload_xstats_type type, + bool *p_used, + struct netlink_ext_ack *extack) +{ + struct netdev_notifier_offload_xstats_ru report_used = {}; + struct netdev_notifier_offload_xstats_info info = { + .info.dev = dev, + .info.extack = extack, + .type = type, + .report_used = &report_used, + }; + int rc; + + WARN_ON(!netdev_offload_xstats_enabled(dev, type)); + rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_USED, + &info.info); + *p_used = report_used.used; + return notifier_to_errno(rc); +} + +static int netdev_offload_xstats_get_stats(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct rtnl_hw_stats64 *p_stats, + bool *p_used, + struct netlink_ext_ack *extack) +{ + struct netdev_notifier_offload_xstats_rd report_delta = {}; + struct netdev_notifier_offload_xstats_info info = { + .info.dev = dev, + .info.extack = extack, + .type = type, + .report_delta = &report_delta, + }; + struct rtnl_hw_stats64 *stats; + int rc; + + stats = netdev_offload_xstats_get_ptr(dev, type); + if (WARN_ON(!stats)) + return -EINVAL; + + rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, + &info.info); + + /* Cache whatever we got, even if there was an error, otherwise the + * successful stats retrievals would get lost. + */ + netdev_hw_stats64_add(stats, &report_delta.stats); + + if (p_stats) + *p_stats = *stats; + *p_used = report_delta.used; + + return notifier_to_errno(rc); +} + +int netdev_offload_xstats_get(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct rtnl_hw_stats64 *p_stats, bool *p_used, + struct netlink_ext_ack *extack) +{ + ASSERT_RTNL(); + + if (p_stats) + return netdev_offload_xstats_get_stats(dev, type, p_stats, + p_used, extack); + else + return netdev_offload_xstats_get_used(dev, type, p_used, + extack); +} +EXPORT_SYMBOL(netdev_offload_xstats_get); + +void +netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *report_delta, + const struct rtnl_hw_stats64 *stats) +{ + report_delta->used = true; + netdev_hw_stats64_add(&report_delta->stats, stats); +} +EXPORT_SYMBOL(netdev_offload_xstats_report_delta); + +void +netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *report_used) +{ + report_used->used = true; +} +EXPORT_SYMBOL(netdev_offload_xstats_report_used); + +void netdev_offload_xstats_push_delta(struct net_device *dev, + enum netdev_offload_xstats_type type, + const struct rtnl_hw_stats64 *p_stats) +{ + struct rtnl_hw_stats64 *stats; + + ASSERT_RTNL(); + + stats = netdev_offload_xstats_get_ptr(dev, type); + if (WARN_ON(!stats)) + return; + + netdev_hw_stats64_add(stats, p_stats); +} +EXPORT_SYMBOL(netdev_offload_xstats_push_delta); + /** * netdev_get_xmit_slave - Get the xmit slave of master device * @dev: device @@ -10417,6 +10680,8 @@ void unregister_netdevice_many(struct list_head *head) dev_xdp_uninstall(dev); + netdev_offload_xstats_disable_all(dev); + /* Notify protocols, that we are about to destroy * this device. They should clean all the things. */ -- cgit v1.2.3 From 0e7788fd76222dba3229eada9162efab185923fc Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 2 Mar 2022 18:31:21 +0200 Subject: net: rtnetlink: Add UAPI for obtaining L3 offload xstats Add a new IFLA_STATS_LINK_OFFLOAD_XSTATS child attribute, IFLA_OFFLOAD_XSTATS_L3_STATS, to carry statistics for traffic that takes place in a HW router. The offloaded HW stats are designed to allow per-netdevice enablement and disablement. Additionally, as a netdevice is configured, it may become or cease being suitable for binding of a HW counter. Both of these aspects need to be communicated to the userspace. To that end, add another child attribute, IFLA_OFFLOAD_XSTATS_HW_S_INFO: - attr nest IFLA_OFFLOAD_XSTATS_HW_S_INFO - attr nest IFLA_OFFLOAD_XSTATS_L3_STATS - attr IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST - {0,1} as u8 - attr IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED - {0,1} as u8 Thus this one attribute is a nest that can be used to carry information about various types of HW statistics, and indexing is very simply done by wrapping the information for a given statistics suite into the attribute that carries the suite is the RTM_GETSTATS query. At the same time, because _HW_S_INFO is nested directly below IFLA_STATS_LINK_OFFLOAD_XSTATS, it is possible through filtering to request only the metadata about individual statistics suites, without having to hit the HW to get the actual counters. Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 11 +++ net/core/rtnetlink.c | 170 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 181 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ef6a62a2e15d..b1031f481d2f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1249,10 +1249,21 @@ enum { enum { IFLA_OFFLOAD_XSTATS_UNSPEC, IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */ + IFLA_OFFLOAD_XSTATS_HW_S_INFO, /* HW stats info. A nest */ + IFLA_OFFLOAD_XSTATS_L3_STATS, /* struct rtnl_hw_stats64 */ __IFLA_OFFLOAD_XSTATS_MAX }; #define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1) +enum { + IFLA_OFFLOAD_XSTATS_HW_S_INFO_UNSPEC, + IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST, /* u8 */ + IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED, /* u8 */ + __IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX, +}; +#define IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX \ + (__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX - 1) + /* XDP section */ #define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 4db1d6c01a7d..9ce894a9454c 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -5091,10 +5091,110 @@ rtnl_offload_xstats_fill_ndo(struct net_device *dev, int attr_id, return 0; } +static unsigned int +rtnl_offload_xstats_get_size_stats(const struct net_device *dev, + enum netdev_offload_xstats_type type) +{ + bool enabled = netdev_offload_xstats_enabled(dev, type); + + return enabled ? sizeof(struct rtnl_hw_stats64) : 0; +} + +struct rtnl_offload_xstats_request_used { + bool request; + bool used; +}; + +static int +rtnl_offload_xstats_get_stats(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct rtnl_offload_xstats_request_used *ru, + struct rtnl_hw_stats64 *stats, + struct netlink_ext_ack *extack) +{ + bool request; + bool used; + int err; + + request = netdev_offload_xstats_enabled(dev, type); + if (!request) { + used = false; + goto out; + } + + err = netdev_offload_xstats_get(dev, type, stats, &used, extack); + if (err) + return err; + +out: + if (ru) { + ru->request = request; + ru->used = used; + } + return 0; +} + +static int +rtnl_offload_xstats_fill_hw_s_info_one(struct sk_buff *skb, int attr_id, + struct rtnl_offload_xstats_request_used *ru) +{ + struct nlattr *nest; + + nest = nla_nest_start(skb, attr_id); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u8(skb, IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST, ru->request)) + goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED, ru->used)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int +rtnl_offload_xstats_fill_hw_s_info(struct sk_buff *skb, struct net_device *dev, + struct netlink_ext_ack *extack) +{ + enum netdev_offload_xstats_type t_l3 = NETDEV_OFFLOAD_XSTATS_TYPE_L3; + struct rtnl_offload_xstats_request_used ru_l3; + struct nlattr *nest; + int err; + + err = rtnl_offload_xstats_get_stats(dev, t_l3, &ru_l3, NULL, extack); + if (err) + return err; + + nest = nla_nest_start(skb, IFLA_OFFLOAD_XSTATS_HW_S_INFO); + if (!nest) + return -EMSGSIZE; + + if (rtnl_offload_xstats_fill_hw_s_info_one(skb, + IFLA_OFFLOAD_XSTATS_L3_STATS, + &ru_l3)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + static int rtnl_offload_xstats_fill(struct sk_buff *skb, struct net_device *dev, int *prividx, u32 off_filter_mask, struct netlink_ext_ack *extack) { + enum netdev_offload_xstats_type t_l3 = NETDEV_OFFLOAD_XSTATS_TYPE_L3; + int attr_id_hw_s_info = IFLA_OFFLOAD_XSTATS_HW_S_INFO; + int attr_id_l3_stats = IFLA_OFFLOAD_XSTATS_L3_STATS; int attr_id_cpu_hit = IFLA_OFFLOAD_XSTATS_CPU_HIT; bool have_data = false; int err; @@ -5111,6 +5211,40 @@ static int rtnl_offload_xstats_fill(struct sk_buff *skb, struct net_device *dev, } } + if (*prividx <= attr_id_hw_s_info && + (off_filter_mask & IFLA_STATS_FILTER_BIT(attr_id_hw_s_info))) { + *prividx = attr_id_hw_s_info; + + err = rtnl_offload_xstats_fill_hw_s_info(skb, dev, extack); + if (err) + return err; + + have_data = true; + *prividx = 0; + } + + if (*prividx <= attr_id_l3_stats && + (off_filter_mask & IFLA_STATS_FILTER_BIT(attr_id_l3_stats))) { + unsigned int size_l3; + struct nlattr *attr; + + *prividx = attr_id_l3_stats; + + size_l3 = rtnl_offload_xstats_get_size_stats(dev, t_l3); + attr = nla_reserve_64bit(skb, attr_id_l3_stats, size_l3, + IFLA_OFFLOAD_XSTATS_UNSPEC); + if (!attr) + return -EMSGSIZE; + + err = rtnl_offload_xstats_get_stats(dev, t_l3, NULL, + nla_data(attr), extack); + if (err) + return err; + + have_data = true; + *prividx = 0; + } + if (!have_data) return -ENODATA; @@ -5118,9 +5252,35 @@ static int rtnl_offload_xstats_fill(struct sk_buff *skb, struct net_device *dev, return 0; } +static unsigned int +rtnl_offload_xstats_get_size_hw_s_info_one(const struct net_device *dev, + enum netdev_offload_xstats_type type) +{ + bool enabled = netdev_offload_xstats_enabled(dev, type); + + return nla_total_size(0) + + /* IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST */ + nla_total_size(sizeof(u8)) + + /* IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED */ + (enabled ? nla_total_size(sizeof(u8)) : 0) + + 0; +} + +static unsigned int +rtnl_offload_xstats_get_size_hw_s_info(const struct net_device *dev) +{ + enum netdev_offload_xstats_type t_l3 = NETDEV_OFFLOAD_XSTATS_TYPE_L3; + + return nla_total_size(0) + + /* IFLA_OFFLOAD_XSTATS_L3_STATS */ + rtnl_offload_xstats_get_size_hw_s_info_one(dev, t_l3) + + 0; +} + static int rtnl_offload_xstats_get_size(const struct net_device *dev, u32 off_filter_mask) { + enum netdev_offload_xstats_type t_l3 = NETDEV_OFFLOAD_XSTATS_TYPE_L3; int attr_id_cpu_hit = IFLA_OFFLOAD_XSTATS_CPU_HIT; int nla_size = 0; int size; @@ -5131,6 +5291,16 @@ static int rtnl_offload_xstats_get_size(const struct net_device *dev, nla_size += nla_total_size_64bit(size); } + if (off_filter_mask & + IFLA_STATS_FILTER_BIT(IFLA_OFFLOAD_XSTATS_HW_S_INFO)) + nla_size += rtnl_offload_xstats_get_size_hw_s_info(dev); + + if (off_filter_mask & + IFLA_STATS_FILTER_BIT(IFLA_OFFLOAD_XSTATS_L3_STATS)) { + size = rtnl_offload_xstats_get_size_stats(dev, t_l3); + nla_size += nla_total_size_64bit(size); + } + if (nla_size != 0) nla_size += nla_total_size(0); -- cgit v1.2.3 From 03ba35667091337d8e632cf4b814f1c1b914609b Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 2 Mar 2022 18:31:22 +0200 Subject: net: rtnetlink: Add RTM_SETSTATS The offloaded HW stats are designed to allow per-netdevice enablement and disablement. These stats are only accessible through RTM_GETSTATS, and therefore should be toggled by a RTM_SETSTATS message. Add it, and the necessary skeleton handler. Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 2 ++ net/core/rtnetlink.c | 66 ++++++++++++++++++++++++++++++++++++++++++ security/selinux/nlmsgtab.c | 1 + 3 files changed, 69 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 0970cb4b1b88..14462dc159fd 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -146,6 +146,8 @@ enum { #define RTM_NEWSTATS RTM_NEWSTATS RTM_GETSTATS = 94, #define RTM_GETSTATS RTM_GETSTATS + RTM_SETSTATS, +#define RTM_SETSTATS RTM_SETSTATS RTM_NEWCACHEREPORT = 96, #define RTM_NEWCACHEREPORT RTM_NEWCACHEREPORT diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 9ce894a9454c..d09354514355 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -5564,6 +5564,10 @@ rtnl_stats_get_policy[IFLA_STATS_GETSET_MAX + 1] = { NLA_POLICY_NESTED(rtnl_stats_get_policy_filters), }; +static const struct nla_policy +ifla_stats_set_policy[IFLA_STATS_GETSET_MAX + 1] = { +}; + static int rtnl_stats_get_parse_filters(struct nlattr *ifla_filters, struct rtnl_stats_dump_filters *filters, struct netlink_ext_ack *extack) @@ -5769,6 +5773,67 @@ out: return skb->len; } +static int rtnl_stats_set(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct rtnl_stats_dump_filters response_filters = {}; + struct nlattr *tb[IFLA_STATS_GETSET_MAX + 1]; + struct net *net = sock_net(skb->sk); + struct net_device *dev = NULL; + int idxattr = 0, prividx = 0; + struct if_stats_msg *ifsm; + struct sk_buff *nskb; + int err; + + err = rtnl_valid_stats_req(nlh, netlink_strict_get_check(skb), + false, extack); + if (err) + return err; + + ifsm = nlmsg_data(nlh); + if (ifsm->family != AF_UNSPEC) { + NL_SET_ERR_MSG(extack, "Address family should be AF_UNSPEC"); + return -EINVAL; + } + + if (ifsm->ifindex > 0) + dev = __dev_get_by_index(net, ifsm->ifindex); + else + return -EINVAL; + + if (!dev) + return -ENODEV; + + if (ifsm->filter_mask) { + NL_SET_ERR_MSG(extack, "Filter mask must be 0 for stats set"); + return -EINVAL; + } + + err = nlmsg_parse(nlh, sizeof(*ifsm), tb, IFLA_STATS_GETSET_MAX, + ifla_stats_set_policy, extack); + if (err < 0) + return err; + + nskb = nlmsg_new(if_nlmsg_stats_size(dev, &response_filters), + GFP_KERNEL); + if (!nskb) + return -ENOBUFS; + + err = rtnl_fill_statsinfo(nskb, dev, RTM_NEWSTATS, + NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, + 0, &response_filters, &idxattr, &prividx, + extack); + if (err < 0) { + /* -EMSGSIZE implies BUG in if_nlmsg_stats_size */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(nskb); + } else { + err = rtnl_unicast(nskb, net, NETLINK_CB(skb).portid); + } + + return err; +} + /* Process one rtnetlink message. */ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -5994,4 +6059,5 @@ void __init rtnetlink_init(void) rtnl_register(PF_UNSPEC, RTM_GETSTATS, rtnl_stats_get, rtnl_stats_dump, 0); + rtnl_register(PF_UNSPEC, RTM_SETSTATS, rtnl_stats_set, NULL, 0); } diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index 6ad3ee02e023..d8ceee9e0d6f 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -76,6 +76,7 @@ static const struct nlmsg_perm nlmsg_route_perms[] = { RTM_GETNSID, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWSTATS, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_GETSTATS, NETLINK_ROUTE_SOCKET__NLMSG_READ }, + { RTM_SETSTATS, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_NEWCACHEREPORT, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWCHAIN, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELCHAIN, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, -- cgit v1.2.3 From 5fd0b838efac16046509f7fb100455d0463b9687 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 2 Mar 2022 18:31:23 +0200 Subject: net: rtnetlink: Add UAPI toggle for IFLA_OFFLOAD_XSTATS_L3_STATS The offloaded HW stats are designed to allow per-netdevice enablement and disablement. Add an attribute, IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS, which should be carried by the RTM_SETSTATS message, and expresses a desire to toggle L3 offload xstats on or off. As part of the above, add an exported function rtnl_offload_xstats_notify() that drivers can use when they have installed or deinstalled the counters backing the HW stats. At this point, it is possible to enable, disable and query L3 offload xstats on netdevices. (However there is no driver actually implementing these.) Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 3 ++ include/uapi/linux/if_link.h | 1 + include/uapi/linux/rtnetlink.h | 2 ++ net/core/rtnetlink.c | 75 ++++++++++++++++++++++++++++++++---------- 4 files changed, 64 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index bb9cb84114c1..7f970b16da3a 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -134,4 +134,7 @@ extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, int (*vlan_fill)(struct sk_buff *skb, struct net_device *dev, u32 filter_mask)); + +extern void rtnl_offload_xstats_notify(struct net_device *dev); + #endif /* __LINUX_RTNETLINK_H */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index b1031f481d2f..ddca20357e7e 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1227,6 +1227,7 @@ enum { IFLA_STATS_GET_FILTERS, /* Nest of IFLA_STATS_LINK_xxx, each a u32 with * a filter mask for the corresponding group. */ + IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS, /* 0 or 1 as u8 */ __IFLA_STATS_GETSET_MAX, }; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 14462dc159fd..51530aade46e 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -767,6 +767,8 @@ enum rtnetlink_groups { #define RTNLGRP_MCTP_IFADDR RTNLGRP_MCTP_IFADDR RTNLGRP_TUNNEL, #define RTNLGRP_TUNNEL RTNLGRP_TUNNEL + RTNLGRP_STATS, +#define RTNLGRP_STATS RTNLGRP_STATS __RTNLGRP_MAX }; #define RTNLGRP_MAX (__RTNLGRP_MAX - 1) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d09354514355..a66b6761b88b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -5566,6 +5566,7 @@ rtnl_stats_get_policy[IFLA_STATS_GETSET_MAX + 1] = { static const struct nla_policy ifla_stats_set_policy[IFLA_STATS_GETSET_MAX + 1] = { + [IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS] = NLA_POLICY_MAX(NLA_U8, 1), }; static int rtnl_stats_get_parse_filters(struct nlattr *ifla_filters, @@ -5773,16 +5774,51 @@ out: return skb->len; } +void rtnl_offload_xstats_notify(struct net_device *dev) +{ + struct rtnl_stats_dump_filters response_filters = {}; + struct net *net = dev_net(dev); + int idxattr = 0, prividx = 0; + struct sk_buff *skb; + int err = -ENOBUFS; + + ASSERT_RTNL(); + + response_filters.mask[0] |= + IFLA_STATS_FILTER_BIT(IFLA_STATS_LINK_OFFLOAD_XSTATS); + response_filters.mask[IFLA_STATS_LINK_OFFLOAD_XSTATS] |= + IFLA_STATS_FILTER_BIT(IFLA_OFFLOAD_XSTATS_HW_S_INFO); + + skb = nlmsg_new(if_nlmsg_stats_size(dev, &response_filters), + GFP_KERNEL); + if (!skb) + goto errout; + + err = rtnl_fill_statsinfo(skb, dev, RTM_NEWSTATS, 0, 0, 0, 0, + &response_filters, &idxattr, &prividx, NULL); + if (err < 0) { + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_STATS, NULL, GFP_KERNEL); + return; + +errout: + rtnl_set_sk_err(net, RTNLGRP_STATS, err); +} +EXPORT_SYMBOL(rtnl_offload_xstats_notify); + static int rtnl_stats_set(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { + enum netdev_offload_xstats_type t_l3 = NETDEV_OFFLOAD_XSTATS_TYPE_L3; struct rtnl_stats_dump_filters response_filters = {}; struct nlattr *tb[IFLA_STATS_GETSET_MAX + 1]; struct net *net = sock_net(skb->sk); struct net_device *dev = NULL; - int idxattr = 0, prividx = 0; struct if_stats_msg *ifsm; - struct sk_buff *nskb; + bool notify = false; int err; err = rtnl_valid_stats_req(nlh, netlink_strict_get_check(skb), @@ -5814,24 +5850,29 @@ static int rtnl_stats_set(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) return err; - nskb = nlmsg_new(if_nlmsg_stats_size(dev, &response_filters), - GFP_KERNEL); - if (!nskb) - return -ENOBUFS; + if (tb[IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS]) { + u8 req = nla_get_u8(tb[IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS]); - err = rtnl_fill_statsinfo(nskb, dev, RTM_NEWSTATS, - NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, - 0, &response_filters, &idxattr, &prividx, - extack); - if (err < 0) { - /* -EMSGSIZE implies BUG in if_nlmsg_stats_size */ - WARN_ON(err == -EMSGSIZE); - kfree_skb(nskb); - } else { - err = rtnl_unicast(nskb, net, NETLINK_CB(skb).portid); + if (req) + err = netdev_offload_xstats_enable(dev, t_l3, extack); + else + err = netdev_offload_xstats_disable(dev, t_l3); + + if (!err) + notify = true; + else if (err != -EALREADY) + return err; + + response_filters.mask[0] |= + IFLA_STATS_FILTER_BIT(IFLA_STATS_LINK_OFFLOAD_XSTATS); + response_filters.mask[IFLA_STATS_LINK_OFFLOAD_XSTATS] |= + IFLA_STATS_FILTER_BIT(IFLA_OFFLOAD_XSTATS_HW_S_INFO); } - return err; + if (notify) + rtnl_offload_xstats_notify(dev); + + return 0; } /* Process one rtnetlink message. */ -- cgit v1.2.3 From 8d21ec0e46ed6e39994accff8eb4f2be3d2e76b5 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 2 Mar 2022 11:56:34 -0800 Subject: bpf: Add __sk_buff->delivery_time_type and bpf_skb_set_skb_delivery_time() * __sk_buff->delivery_time_type: This patch adds __sk_buff->delivery_time_type. It tells if the delivery_time is stored in __sk_buff->tstamp or not. It will be most useful for ingress to tell if the __sk_buff->tstamp has the (rcv) timestamp or delivery_time. If delivery_time_type is 0 (BPF_SKB_DELIVERY_TIME_NONE), it has the (rcv) timestamp. Two non-zero types are defined for the delivery_time_type, BPF_SKB_DELIVERY_TIME_MONO and BPF_SKB_DELIVERY_TIME_UNSPEC. For UNSPEC, it can only happen in egress because only mono delivery_time can be forwarded to ingress now. The clock of UNSPEC delivery_time can be deduced from the skb->sk->sk_clockid which is how the sch_etf doing it also. * Provide forwarded delivery_time to tc-bpf@ingress: With the help of the new delivery_time_type, the tc-bpf has a way to tell if the __sk_buff->tstamp has the (rcv) timestamp or the delivery_time. During bpf load time, the verifier will learn if the bpf prog has accessed the new __sk_buff->delivery_time_type. If it does, it means the tc-bpf@ingress is expecting the skb->tstamp could have the delivery_time. The kernel will then read the skb->tstamp as-is during bpf insn rewrite without checking the skb->mono_delivery_time. This is done by adding a new prog->delivery_time_access bit. The same goes for writing skb->tstamp. * bpf_skb_set_delivery_time(): The bpf_skb_set_delivery_time() helper is added to allow setting both delivery_time and the delivery_time_type at the same time. If the tc-bpf does not need to change the delivery_time_type, it can directly write to the __sk_buff->tstamp as the existing tc-bpf has already been doing. It will be most useful at ingress to change the __sk_buff->tstamp from the (rcv) timestamp to a mono delivery_time and then bpf_redirect_*(). bpf only has mono clock helper (bpf_ktime_get_ns), and the current known use case is the mono EDT for fq, and only mono delivery time can be kept during forward now, so bpf_skb_set_delivery_time() only supports setting BPF_SKB_DELIVERY_TIME_MONO. It can be extended later when use cases come up and the forwarding path also supports other clock bases. Signed-off-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/linux/filter.h | 3 +- include/uapi/linux/bpf.h | 41 +++++++++- net/core/filter.c | 169 ++++++++++++++++++++++++++++++++--------- tools/include/uapi/linux/bpf.h | 41 +++++++++- 4 files changed, 216 insertions(+), 38 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 1cb1af917617..9bf26307247f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -572,7 +572,8 @@ struct bpf_prog { has_callchain_buf:1, /* callchain buffer allocated? */ enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ - call_get_func_ip:1; /* Do we call get_func_ip() */ + call_get_func_ip:1, /* Do we call get_func_ip() */ + delivery_time_access:1; /* Accessed __sk_buff->delivery_time_type */ 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 */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index afe3d0d7f5f2..4eebea830613 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5086,6 +5086,37 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. On error * *dst* buffer is zeroed out. + * + * long bpf_skb_set_delivery_time(struct sk_buff *skb, u64 dtime, u32 dtime_type) + * Description + * Set a *dtime* (delivery time) to the __sk_buff->tstamp and also + * change the __sk_buff->delivery_time_type to *dtime_type*. + * + * When setting a delivery time (non zero *dtime*) to + * __sk_buff->tstamp, only BPF_SKB_DELIVERY_TIME_MONO *dtime_type* + * is supported. It is the only delivery_time_type that will be + * kept after bpf_redirect_*(). + * + * If there is no need to change the __sk_buff->delivery_time_type, + * the delivery time can be directly written to __sk_buff->tstamp + * instead. + * + * *dtime* 0 and *dtime_type* BPF_SKB_DELIVERY_TIME_NONE + * can be used to clear any delivery time stored in + * __sk_buff->tstamp. + * + * Only IPv4 and IPv6 skb->protocol are supported. + * + * This function is most useful when it needs to set a + * mono delivery time to __sk_buff->tstamp and then + * bpf_redirect_*() to the egress of an iface. For example, + * changing the (rcv) timestamp in __sk_buff->tstamp at + * ingress to a mono delivery time and then bpf_redirect_*() + * to sch_fq@phy-dev. + * Return + * 0 on success. + * **-EINVAL** for invalid input + * **-EOPNOTSUPP** for unsupported delivery_time_type and protocol */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5280,6 +5311,7 @@ union bpf_attr { FN(xdp_load_bytes), \ FN(xdp_store_bytes), \ FN(copy_from_user_task), \ + FN(skb_set_delivery_time), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5469,6 +5501,12 @@ union { \ __u64 :64; \ } __attribute__((aligned(8))) +enum { + BPF_SKB_DELIVERY_TIME_NONE, + BPF_SKB_DELIVERY_TIME_UNSPEC, + BPF_SKB_DELIVERY_TIME_MONO, +}; + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -5509,7 +5547,8 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; - __u32 :32; /* Padding, future use. */ + __u8 delivery_time_type; + __u32 :24; /* Padding, future use. */ __u64 hwtstamp; }; diff --git a/net/core/filter.c b/net/core/filter.c index 5072733743e9..88767f7da150 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7388,6 +7388,43 @@ static const struct bpf_func_proto bpf_sock_ops_reserve_hdr_opt_proto = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_3(bpf_skb_set_delivery_time, struct sk_buff *, skb, + u64, dtime, u32, dtime_type) +{ + /* skb_clear_delivery_time() is done for inet protocol */ + if (skb->protocol != htons(ETH_P_IP) && + skb->protocol != htons(ETH_P_IPV6)) + return -EOPNOTSUPP; + + switch (dtime_type) { + case BPF_SKB_DELIVERY_TIME_MONO: + if (!dtime) + return -EINVAL; + skb->tstamp = dtime; + skb->mono_delivery_time = 1; + break; + case BPF_SKB_DELIVERY_TIME_NONE: + if (dtime) + return -EINVAL; + skb->tstamp = 0; + skb->mono_delivery_time = 0; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static const struct bpf_func_proto bpf_skb_set_delivery_time_proto = { + .func = bpf_skb_set_delivery_time, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(void *func) @@ -7749,6 +7786,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_gen_syncookie_proto; case BPF_FUNC_sk_assign: return &bpf_sk_assign_proto; + case BPF_FUNC_skb_set_delivery_time: + return &bpf_skb_set_delivery_time_proto; #endif default: return bpf_sk_base_func_proto(func_id); @@ -8088,7 +8127,9 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type return false; info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; break; - case offsetofend(struct __sk_buff, gso_size) ... offsetof(struct __sk_buff, hwtstamp) - 1: + case offsetof(struct __sk_buff, delivery_time_type): + return false; + case offsetofend(struct __sk_buff, delivery_time_type) ... offsetof(struct __sk_buff, hwtstamp) - 1: /* Explicitly prohibit access to padding in __sk_buff. */ return false; default: @@ -8443,6 +8484,15 @@ static bool tc_cls_act_is_valid_access(int off, int size, break; case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; + case offsetof(struct __sk_buff, delivery_time_type): + /* The convert_ctx_access() on reading and writing + * __sk_buff->tstamp depends on whether the bpf prog + * has used __sk_buff->delivery_time_type or not. + * Thus, we need to set prog->delivery_time_access + * earlier during is_valid_access() here. + */ + ((struct bpf_prog *)prog)->delivery_time_access = 1; + return size == sizeof(__u8); } return bpf_skb_is_valid_access(off, size, type, prog, info); @@ -8838,6 +8888,45 @@ static u32 flow_dissector_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } +static struct bpf_insn *bpf_convert_dtime_type_read(const struct bpf_insn *si, + struct bpf_insn *insn) +{ + __u8 value_reg = si->dst_reg; + __u8 skb_reg = si->src_reg; + __u8 tmp_reg = BPF_REG_AX; + + *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, + SKB_MONO_DELIVERY_TIME_OFFSET); + *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, + SKB_MONO_DELIVERY_TIME_MASK); + *insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0, 2); + /* value_reg = BPF_SKB_DELIVERY_TIME_MONO */ + *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_DELIVERY_TIME_MONO); + *insn++ = BPF_JMP_A(IS_ENABLED(CONFIG_NET_CLS_ACT) ? 10 : 5); + + *insn++ = BPF_LDX_MEM(BPF_DW, tmp_reg, skb_reg, + offsetof(struct sk_buff, tstamp)); + *insn++ = BPF_JMP_IMM(BPF_JNE, tmp_reg, 0, 2); + /* value_reg = BPF_SKB_DELIVERY_TIME_NONE */ + *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_DELIVERY_TIME_NONE); + *insn++ = BPF_JMP_A(IS_ENABLED(CONFIG_NET_CLS_ACT) ? 6 : 1); + +#ifdef CONFIG_NET_CLS_ACT + *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, TC_AT_INGRESS_OFFSET); + *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, TC_AT_INGRESS_MASK); + *insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0, 2); + /* At ingress, value_reg = 0 */ + *insn++ = BPF_MOV32_IMM(value_reg, 0); + *insn++ = BPF_JMP_A(1); +#endif + + /* value_reg = BPF_SKB_DELIVERYT_TIME_UNSPEC */ + *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_DELIVERY_TIME_UNSPEC); + + /* 15 insns with CONFIG_NET_CLS_ACT */ + return insn; +} + static struct bpf_insn *bpf_convert_shinfo_access(const struct bpf_insn *si, struct bpf_insn *insn) { @@ -8859,29 +8948,32 @@ static struct bpf_insn *bpf_convert_shinfo_access(const struct bpf_insn *si, return insn; } -static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_insn *si, +static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog, + const struct bpf_insn *si, struct bpf_insn *insn) { __u8 value_reg = si->dst_reg; __u8 skb_reg = si->src_reg; #ifdef CONFIG_NET_CLS_ACT - __u8 tmp_reg = BPF_REG_AX; - - *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, TC_AT_INGRESS_OFFSET); - *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, TC_AT_INGRESS_MASK); - *insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0, 5); - /* @ingress, read __sk_buff->tstamp as the (rcv) timestamp, - * so check the skb->mono_delivery_time. - */ - *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, - SKB_MONO_DELIVERY_TIME_OFFSET); - *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, - SKB_MONO_DELIVERY_TIME_MASK); - *insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0, 2); - /* skb->mono_delivery_time is set, read 0 as the (rcv) timestamp. */ - *insn++ = BPF_MOV64_IMM(value_reg, 0); - *insn++ = BPF_JMP_A(1); + if (!prog->delivery_time_access) { + __u8 tmp_reg = BPF_REG_AX; + + *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, TC_AT_INGRESS_OFFSET); + *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, TC_AT_INGRESS_MASK); + *insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0, 5); + /* @ingress, read __sk_buff->tstamp as the (rcv) timestamp, + * so check the skb->mono_delivery_time. + */ + *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, + SKB_MONO_DELIVERY_TIME_OFFSET); + *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, + SKB_MONO_DELIVERY_TIME_MASK); + *insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0, 2); + /* skb->mono_delivery_time is set, read 0 as the (rcv) timestamp. */ + *insn++ = BPF_MOV64_IMM(value_reg, 0); + *insn++ = BPF_JMP_A(1); + } #endif *insn++ = BPF_LDX_MEM(BPF_DW, value_reg, skb_reg, @@ -8889,27 +8981,30 @@ static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_insn *si, return insn; } -static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_insn *si, +static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog, + const struct bpf_insn *si, struct bpf_insn *insn) { __u8 value_reg = si->src_reg; __u8 skb_reg = si->dst_reg; #ifdef CONFIG_NET_CLS_ACT - __u8 tmp_reg = BPF_REG_AX; - - *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, TC_AT_INGRESS_OFFSET); - *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, TC_AT_INGRESS_MASK); - *insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0, 3); - /* Writing __sk_buff->tstamp at ingress as the (rcv) timestamp. - * Clear the skb->mono_delivery_time. - */ - *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, - SKB_MONO_DELIVERY_TIME_OFFSET); - *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, - ~SKB_MONO_DELIVERY_TIME_MASK); - *insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, - SKB_MONO_DELIVERY_TIME_OFFSET); + if (!prog->delivery_time_access) { + __u8 tmp_reg = BPF_REG_AX; + + *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, TC_AT_INGRESS_OFFSET); + *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, TC_AT_INGRESS_MASK); + *insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0, 3); + /* Writing __sk_buff->tstamp at ingress as the (rcv) timestamp. + * Clear the skb->mono_delivery_time. + */ + *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, + SKB_MONO_DELIVERY_TIME_OFFSET); + *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, + ~SKB_MONO_DELIVERY_TIME_MASK); + *insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, + SKB_MONO_DELIVERY_TIME_OFFSET); + } #endif /* skb->tstamp = tstamp */ @@ -9226,9 +9321,13 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, BUILD_BUG_ON(sizeof_field(struct sk_buff, tstamp) != 8); if (type == BPF_WRITE) - insn = bpf_convert_tstamp_write(si, insn); + insn = bpf_convert_tstamp_write(prog, si, insn); else - insn = bpf_convert_tstamp_read(si, insn); + insn = bpf_convert_tstamp_read(prog, si, insn); + break; + + case offsetof(struct __sk_buff, delivery_time_type): + insn = bpf_convert_dtime_type_read(si, insn); break; case offsetof(struct __sk_buff, gso_segs): diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index afe3d0d7f5f2..4eebea830613 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5086,6 +5086,37 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. On error * *dst* buffer is zeroed out. + * + * long bpf_skb_set_delivery_time(struct sk_buff *skb, u64 dtime, u32 dtime_type) + * Description + * Set a *dtime* (delivery time) to the __sk_buff->tstamp and also + * change the __sk_buff->delivery_time_type to *dtime_type*. + * + * When setting a delivery time (non zero *dtime*) to + * __sk_buff->tstamp, only BPF_SKB_DELIVERY_TIME_MONO *dtime_type* + * is supported. It is the only delivery_time_type that will be + * kept after bpf_redirect_*(). + * + * If there is no need to change the __sk_buff->delivery_time_type, + * the delivery time can be directly written to __sk_buff->tstamp + * instead. + * + * *dtime* 0 and *dtime_type* BPF_SKB_DELIVERY_TIME_NONE + * can be used to clear any delivery time stored in + * __sk_buff->tstamp. + * + * Only IPv4 and IPv6 skb->protocol are supported. + * + * This function is most useful when it needs to set a + * mono delivery time to __sk_buff->tstamp and then + * bpf_redirect_*() to the egress of an iface. For example, + * changing the (rcv) timestamp in __sk_buff->tstamp at + * ingress to a mono delivery time and then bpf_redirect_*() + * to sch_fq@phy-dev. + * Return + * 0 on success. + * **-EINVAL** for invalid input + * **-EOPNOTSUPP** for unsupported delivery_time_type and protocol */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5280,6 +5311,7 @@ union bpf_attr { FN(xdp_load_bytes), \ FN(xdp_store_bytes), \ FN(copy_from_user_task), \ + FN(skb_set_delivery_time), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5469,6 +5501,12 @@ union { \ __u64 :64; \ } __attribute__((aligned(8))) +enum { + BPF_SKB_DELIVERY_TIME_NONE, + BPF_SKB_DELIVERY_TIME_UNSPEC, + BPF_SKB_DELIVERY_TIME_MONO, +}; + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -5509,7 +5547,8 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; - __u32 :32; /* Padding, future use. */ + __u8 delivery_time_type; + __u32 :24; /* Padding, future use. */ __u64 hwtstamp; }; -- cgit v1.2.3 From d045b9eb95a9b611c483897a69e7285aefdc66d7 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 7 Mar 2022 12:44:36 -0800 Subject: mptcp: introduce implicit endpoints In some edge scenarios, an MPTCP subflows can use a local address mapped by a "implicit" endpoint created by the in-kernel path manager. Such endpoints presence can be confusing, as it's creation is hard to track and will prevent the later endpoint creation from the user-space using the same address. Define a new endpoint flag to mark implicit endpoints and allow the user-space to replace implicit them with user-provided data at endpoint creation time. Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 1 + net/mptcp/pm_netlink.c | 61 ++++++++++++++++++------- tools/testing/selftests/net/mptcp/mptcp_join.sh | 4 +- 3 files changed, 47 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index f106a3941cdf..9690efedb5fa 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -81,6 +81,7 @@ enum { #define MPTCP_PM_ADDR_FLAG_SUBFLOW (1 << 1) #define MPTCP_PM_ADDR_FLAG_BACKUP (1 << 2) #define MPTCP_PM_ADDR_FLAG_FULLMESH (1 << 3) +#define MPTCP_PM_ADDR_FLAG_IMPLICIT (1 << 4) enum { MPTCP_PM_CMD_UNSPEC, diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 91b77d1162cf..10368a4f1c4a 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -877,10 +877,18 @@ static bool address_use_port(struct mptcp_pm_addr_entry *entry) MPTCP_PM_ADDR_FLAG_SIGNAL; } +/* caller must ensure the RCU grace period is already elapsed */ +static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) +{ + if (entry->lsk) + sock_release(entry->lsk); + kfree(entry); +} + static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, struct mptcp_pm_addr_entry *entry) { - struct mptcp_pm_addr_entry *cur; + struct mptcp_pm_addr_entry *cur, *del_entry = NULL; unsigned int addr_max; int ret = -EINVAL; @@ -901,8 +909,22 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, list_for_each_entry(cur, &pernet->local_addr_list, list) { if (addresses_equal(&cur->addr, &entry->addr, address_use_port(entry) && - address_use_port(cur))) - goto out; + address_use_port(cur))) { + /* allow replacing the exiting endpoint only if such + * endpoint is an implicit one and the user-space + * did not provide an endpoint id + */ + if (!(cur->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)) + goto out; + if (entry->addr.id) + goto out; + + pernet->addrs--; + entry->addr.id = cur->addr.id; + list_del_rcu(&cur->list); + del_entry = cur; + break; + } } if (!entry->addr.id) { @@ -938,6 +960,12 @@ find_next: out: spin_unlock_bh(&pernet->lock); + + /* just replaced an existing entry, free it */ + if (del_entry) { + synchronize_rcu(); + __mptcp_pm_release_addr_entry(del_entry); + } return ret; } @@ -1036,7 +1064,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) entry->addr.id = 0; entry->addr.port = 0; entry->ifindex = 0; - entry->flags = 0; + entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT; entry->lsk = NULL; ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); if (ret < 0) @@ -1249,6 +1277,11 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } + if (addr.flags & MPTCP_PM_ADDR_FLAG_IMPLICIT) { + GENL_SET_ERR_MSG(info, "can't create IMPLICIT endpoint"); + return -EINVAL; + } + entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) { GENL_SET_ERR_MSG(info, "can't allocate addr"); @@ -1333,11 +1366,12 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, } static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, - struct mptcp_addr_info *addr) + const struct mptcp_pm_addr_entry *entry) { - struct mptcp_sock *msk; - long s_slot = 0, s_num = 0; + const struct mptcp_addr_info *addr = &entry->addr; struct mptcp_rm_list list = { .nr = 0 }; + long s_slot = 0, s_num = 0; + struct mptcp_sock *msk; pr_debug("remove_id=%d", addr->id); @@ -1354,7 +1388,8 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, lock_sock(sk); remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr); - mptcp_pm_remove_anno_addr(msk, addr, remove_subflow); + mptcp_pm_remove_anno_addr(msk, addr, remove_subflow && + !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)); if (remove_subflow) mptcp_pm_remove_subflow(msk, &list); release_sock(sk); @@ -1367,14 +1402,6 @@ next: return 0; } -/* caller must ensure the RCU grace period is already elapsed */ -static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) -{ - if (entry->lsk) - sock_release(entry->lsk); - kfree(entry); -} - static int mptcp_nl_remove_id_zero_address(struct net *net, struct mptcp_addr_info *addr) { @@ -1451,7 +1478,7 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) __clear_bit(entry->addr.id, pernet->id_bitmap); spin_unlock_bh(&pernet->lock); - mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), &entry->addr); + mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), entry); synchronize_rcu(); __mptcp_pm_release_addr_entry(entry); diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 02bab8a2d5a5..1e2e8dd9f0d6 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1938,7 +1938,7 @@ backup_tests() run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup chk_join_nr "single address, backup" 1 1 1 chk_add_nr 1 1 - chk_prio_nr 1 0 + chk_prio_nr 1 1 # single address with port, backup reset @@ -1948,7 +1948,7 @@ backup_tests() run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup chk_join_nr "single address with port, backup" 1 1 1 chk_add_nr 1 1 - chk_prio_nr 1 0 + chk_prio_nr 1 1 } add_addr_ports_tests() -- cgit v1.2.3 From b530e9e1063ed2b817eae7eec6ed2daa8be11608 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Wed, 9 Mar 2022 11:53:42 +0100 Subject: bpf: Add "live packet" mode for XDP in BPF_PROG_RUN MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This adds support for running XDP programs through BPF_PROG_RUN in a mode that enables live packet processing of the resulting frames. Previous uses of BPF_PROG_RUN for XDP returned the XDP program return code and the modified packet data to userspace, which is useful for unit testing of XDP programs. The existing BPF_PROG_RUN for XDP allows userspace to set the ingress ifindex and RXQ number as part of the context object being passed to the kernel. This patch reuses that code, but adds a new mode with different semantics, which can be selected with the new BPF_F_TEST_XDP_LIVE_FRAMES flag. When running BPF_PROG_RUN in this mode, the XDP program return codes will be honoured: returning XDP_PASS will result in the frame being injected into the networking stack as if it came from the selected networking interface, while returning XDP_TX and XDP_REDIRECT will result in the frame being transmitted out that interface. XDP_TX is translated into an XDP_REDIRECT operation to the same interface, since the real XDP_TX action is only possible from within the network drivers themselves, not from the process context where BPF_PROG_RUN is executed. Internally, this new mode of operation creates a page pool instance while setting up the test run, and feeds pages from that into the XDP program. The setup cost of this is amortised over the number of repetitions specified by userspace. To support the performance testing use case, we further optimise the setup step so that all pages in the pool are pre-initialised with the packet data, and pre-computed context and xdp_frame objects stored at the start of each page. This makes it possible to entirely avoid touching the page content on each XDP program invocation, and enables sending up to 9 Mpps/core on my test box. Because the data pages are recycled by the page pool, and the test runner doesn't re-initialise them for each run, subsequent invocations of the XDP program will see the packet data in the state it was after the last time it ran on that particular page. This means that an XDP program that modifies the packet before redirecting it has to be careful about which assumptions it makes about the packet content, but that is only an issue for the most naively written programs. Enabling the new flag is only allowed when not setting ctx_out and data_out in the test specification, since using it means frames will be redirected somewhere else, so they can't be returned. Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20220309105346.100053-2-toke@redhat.com --- include/uapi/linux/bpf.h | 3 + kernel/bpf/Kconfig | 1 + kernel/bpf/syscall.c | 2 +- net/bpf/test_run.c | 334 +++++++++++++++++++++++++++++++++++++++-- tools/include/uapi/linux/bpf.h | 3 + 5 files changed, 328 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4eebea830613..bc23020b638d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1232,6 +1232,8 @@ enum { /* If set, run the test on the cpu specified by bpf_attr.test.cpu */ #define BPF_F_TEST_RUN_ON_CPU (1U << 0) +/* If set, XDP frames will be transmitted after processing */ +#define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1) /* type for BPF_ENABLE_STATS */ enum bpf_stats_type { @@ -1393,6 +1395,7 @@ union bpf_attr { __aligned_u64 ctx_out; __u32 flags; __u32 cpu; + __u32 batch_size; } test; struct { /* anonymous struct used by BPF_*_GET_*_ID */ diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig index c3cf0b86eeb2..d56ee177d5f8 100644 --- a/kernel/bpf/Kconfig +++ b/kernel/bpf/Kconfig @@ -30,6 +30,7 @@ config BPF_SYSCALL select TASKS_TRACE_RCU select BINARY_PRINTF select NET_SOCK_MSG if NET + select PAGE_POOL if NET default n help Enable the bpf() system call that allows to manipulate BPF programs diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index db402ebc5570..9beb585be5a6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3336,7 +3336,7 @@ static int bpf_prog_query(const union bpf_attr *attr, } } -#define BPF_PROG_TEST_RUN_LAST_FIELD test.cpu +#define BPF_PROG_TEST_RUN_LAST_FIELD test.batch_size static int bpf_prog_test_run(const union bpf_attr *attr, union bpf_attr __user *uattr) diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index ba410b069824..25169908be4a 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -53,10 +54,11 @@ static void bpf_test_timer_leave(struct bpf_test_timer *t) rcu_read_unlock(); } -static bool bpf_test_timer_continue(struct bpf_test_timer *t, u32 repeat, int *err, u32 *duration) +static bool bpf_test_timer_continue(struct bpf_test_timer *t, int iterations, + u32 repeat, int *err, u32 *duration) __must_hold(rcu) { - t->i++; + t->i += iterations; if (t->i >= repeat) { /* We're done. */ t->time_spent += ktime_get_ns() - t->time_start; @@ -88,6 +90,286 @@ reset: return false; } +/* We put this struct at the head of each page with a context and frame + * initialised when the page is allocated, so we don't have to do this on each + * repetition of the test run. + */ +struct xdp_page_head { + struct xdp_buff orig_ctx; + struct xdp_buff ctx; + struct xdp_frame frm; + u8 data[]; +}; + +struct xdp_test_data { + struct xdp_buff *orig_ctx; + struct xdp_rxq_info rxq; + struct net_device *dev; + struct page_pool *pp; + struct xdp_frame **frames; + struct sk_buff **skbs; + u32 batch_size; + u32 frame_cnt; +}; + +#define TEST_XDP_FRAME_SIZE (PAGE_SIZE - sizeof(struct xdp_page_head) \ + - sizeof(struct skb_shared_info)) +#define TEST_XDP_MAX_BATCH 256 + +static void xdp_test_run_init_page(struct page *page, void *arg) +{ + struct xdp_page_head *head = phys_to_virt(page_to_phys(page)); + struct xdp_buff *new_ctx, *orig_ctx; + u32 headroom = XDP_PACKET_HEADROOM; + struct xdp_test_data *xdp = arg; + size_t frm_len, meta_len; + struct xdp_frame *frm; + void *data; + + orig_ctx = xdp->orig_ctx; + frm_len = orig_ctx->data_end - orig_ctx->data_meta; + meta_len = orig_ctx->data - orig_ctx->data_meta; + headroom -= meta_len; + + new_ctx = &head->ctx; + frm = &head->frm; + data = &head->data; + memcpy(data + headroom, orig_ctx->data_meta, frm_len); + + xdp_init_buff(new_ctx, TEST_XDP_FRAME_SIZE, &xdp->rxq); + xdp_prepare_buff(new_ctx, data, headroom, frm_len, true); + new_ctx->data = new_ctx->data_meta + meta_len; + + xdp_update_frame_from_buff(new_ctx, frm); + frm->mem = new_ctx->rxq->mem; + + memcpy(&head->orig_ctx, new_ctx, sizeof(head->orig_ctx)); +} + +static int xdp_test_run_setup(struct xdp_test_data *xdp, struct xdp_buff *orig_ctx) +{ + struct xdp_mem_info mem = {}; + struct page_pool *pp; + int err = -ENOMEM; + struct page_pool_params pp_params = { + .order = 0, + .flags = 0, + .pool_size = xdp->batch_size, + .nid = NUMA_NO_NODE, + .max_len = TEST_XDP_FRAME_SIZE, + .init_callback = xdp_test_run_init_page, + .init_arg = xdp, + }; + + xdp->frames = kvmalloc_array(xdp->batch_size, sizeof(void *), GFP_KERNEL); + if (!xdp->frames) + return -ENOMEM; + + xdp->skbs = kvmalloc_array(xdp->batch_size, sizeof(void *), GFP_KERNEL); + if (!xdp->skbs) + goto err_skbs; + + pp = page_pool_create(&pp_params); + if (IS_ERR(pp)) { + err = PTR_ERR(pp); + goto err_pp; + } + + /* will copy 'mem.id' into pp->xdp_mem_id */ + err = xdp_reg_mem_model(&mem, MEM_TYPE_PAGE_POOL, pp); + if (err) + goto err_mmodel; + + xdp->pp = pp; + + /* We create a 'fake' RXQ referencing the original dev, but with an + * xdp_mem_info pointing to our page_pool + */ + xdp_rxq_info_reg(&xdp->rxq, orig_ctx->rxq->dev, 0, 0); + xdp->rxq.mem.type = MEM_TYPE_PAGE_POOL; + xdp->rxq.mem.id = pp->xdp_mem_id; + xdp->dev = orig_ctx->rxq->dev; + xdp->orig_ctx = orig_ctx; + + return 0; + +err_mmodel: + page_pool_destroy(pp); +err_pp: + kfree(xdp->skbs); +err_skbs: + kfree(xdp->frames); + return err; +} + +static void xdp_test_run_teardown(struct xdp_test_data *xdp) +{ + page_pool_destroy(xdp->pp); + kfree(xdp->frames); + kfree(xdp->skbs); +} + +static bool ctx_was_changed(struct xdp_page_head *head) +{ + return head->orig_ctx.data != head->ctx.data || + head->orig_ctx.data_meta != head->ctx.data_meta || + head->orig_ctx.data_end != head->ctx.data_end; +} + +static void reset_ctx(struct xdp_page_head *head) +{ + if (likely(!ctx_was_changed(head))) + return; + + head->ctx.data = head->orig_ctx.data; + head->ctx.data_meta = head->orig_ctx.data_meta; + head->ctx.data_end = head->orig_ctx.data_end; + xdp_update_frame_from_buff(&head->ctx, &head->frm); +} + +static int xdp_recv_frames(struct xdp_frame **frames, int nframes, + struct sk_buff **skbs, + struct net_device *dev) +{ + gfp_t gfp = __GFP_ZERO | GFP_ATOMIC; + int i, n; + LIST_HEAD(list); + + n = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, (void **)skbs); + if (unlikely(n == 0)) { + for (i = 0; i < nframes; i++) + xdp_return_frame(frames[i]); + return -ENOMEM; + } + + for (i = 0; i < nframes; i++) { + struct xdp_frame *xdpf = frames[i]; + struct sk_buff *skb = skbs[i]; + + skb = __xdp_build_skb_from_frame(xdpf, skb, dev); + if (!skb) { + xdp_return_frame(xdpf); + continue; + } + + list_add_tail(&skb->list, &list); + } + netif_receive_skb_list(&list); + + return 0; +} + +static int xdp_test_run_batch(struct xdp_test_data *xdp, struct bpf_prog *prog, + u32 repeat) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + int err = 0, act, ret, i, nframes = 0, batch_sz; + struct xdp_frame **frames = xdp->frames; + struct xdp_page_head *head; + struct xdp_frame *frm; + bool redirect = false; + struct xdp_buff *ctx; + struct page *page; + + batch_sz = min_t(u32, repeat, xdp->batch_size); + + local_bh_disable(); + xdp_set_return_frame_no_direct(); + + for (i = 0; i < batch_sz; i++) { + page = page_pool_dev_alloc_pages(xdp->pp); + if (!page) { + err = -ENOMEM; + goto out; + } + + head = phys_to_virt(page_to_phys(page)); + reset_ctx(head); + ctx = &head->ctx; + frm = &head->frm; + xdp->frame_cnt++; + + act = bpf_prog_run_xdp(prog, ctx); + + /* if program changed pkt bounds we need to update the xdp_frame */ + if (unlikely(ctx_was_changed(head))) { + ret = xdp_update_frame_from_buff(ctx, frm); + if (ret) { + xdp_return_buff(ctx); + continue; + } + } + + switch (act) { + case XDP_TX: + /* we can't do a real XDP_TX since we're not in the + * driver, so turn it into a REDIRECT back to the same + * index + */ + ri->tgt_index = xdp->dev->ifindex; + ri->map_id = INT_MAX; + ri->map_type = BPF_MAP_TYPE_UNSPEC; + fallthrough; + case XDP_REDIRECT: + redirect = true; + ret = xdp_do_redirect_frame(xdp->dev, ctx, frm, prog); + if (ret) + xdp_return_buff(ctx); + break; + case XDP_PASS: + frames[nframes++] = frm; + break; + default: + bpf_warn_invalid_xdp_action(NULL, prog, act); + fallthrough; + case XDP_DROP: + xdp_return_buff(ctx); + break; + } + } + +out: + if (redirect) + xdp_do_flush(); + if (nframes) { + ret = xdp_recv_frames(frames, nframes, xdp->skbs, xdp->dev); + if (ret) + err = ret; + } + + xdp_clear_return_frame_no_direct(); + local_bh_enable(); + return err; +} + +static int bpf_test_run_xdp_live(struct bpf_prog *prog, struct xdp_buff *ctx, + u32 repeat, u32 batch_size, u32 *time) + +{ + struct xdp_test_data xdp = { .batch_size = batch_size }; + struct bpf_test_timer t = { .mode = NO_MIGRATE }; + int ret; + + if (!repeat) + repeat = 1; + + ret = xdp_test_run_setup(&xdp, ctx); + if (ret) + return ret; + + bpf_test_timer_enter(&t); + do { + xdp.frame_cnt = 0; + ret = xdp_test_run_batch(&xdp, prog, repeat - t.i); + if (unlikely(ret < 0)) + break; + } while (bpf_test_timer_continue(&t, xdp.frame_cnt, repeat, &ret, time)); + bpf_test_timer_leave(&t); + + xdp_test_run_teardown(&xdp); + return ret; +} + static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *retval, u32 *time, bool xdp) { @@ -119,7 +401,7 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, *retval = bpf_prog_run_xdp(prog, ctx); else *retval = bpf_prog_run(prog, ctx); - } while (bpf_test_timer_continue(&t, repeat, &ret, time)); + } while (bpf_test_timer_continue(&t, 1, repeat, &ret, time)); bpf_reset_run_ctx(old_ctx); bpf_test_timer_leave(&t); @@ -446,7 +728,7 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog, int b = 2, err = -EFAULT; u32 retval = 0; - if (kattr->test.flags || kattr->test.cpu) + if (kattr->test.flags || kattr->test.cpu || kattr->test.batch_size) return -EINVAL; switch (prog->expected_attach_type) { @@ -510,7 +792,7 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, /* doesn't support data_in/out, ctx_out, duration, or repeat */ if (kattr->test.data_in || kattr->test.data_out || kattr->test.ctx_out || kattr->test.duration || - kattr->test.repeat) + kattr->test.repeat || kattr->test.batch_size) return -EINVAL; if (ctx_size_in < prog->aux->max_ctx_offset || @@ -741,7 +1023,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, void *data; int ret; - if (kattr->test.flags || kattr->test.cpu) + if (kattr->test.flags || kattr->test.cpu || kattr->test.batch_size) return -EINVAL; data = bpf_test_init(kattr, kattr->test.data_size_in, @@ -922,7 +1204,9 @@ static void xdp_convert_buff_to_md(struct xdp_buff *xdp, struct xdp_md *xdp_md) int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { + bool do_live = (kattr->test.flags & BPF_F_TEST_XDP_LIVE_FRAMES); u32 tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + u32 batch_size = kattr->test.batch_size; u32 size = kattr->test.data_size_in; u32 headroom = XDP_PACKET_HEADROOM; u32 retval, duration, max_data_sz; @@ -938,6 +1222,18 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, prog->expected_attach_type == BPF_XDP_CPUMAP) return -EINVAL; + if (kattr->test.flags & ~BPF_F_TEST_XDP_LIVE_FRAMES) + return -EINVAL; + + if (do_live) { + if (!batch_size) + batch_size = NAPI_POLL_WEIGHT; + else if (batch_size > TEST_XDP_MAX_BATCH) + return -E2BIG; + } else if (batch_size) { + return -EINVAL; + } + ctx = bpf_ctx_init(kattr, sizeof(struct xdp_md)); if (IS_ERR(ctx)) return PTR_ERR(ctx); @@ -946,14 +1242,20 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, /* There can't be user provided data before the meta data */ if (ctx->data_meta || ctx->data_end != size || ctx->data > ctx->data_end || - unlikely(xdp_metalen_invalid(ctx->data))) + unlikely(xdp_metalen_invalid(ctx->data)) || + (do_live && (kattr->test.data_out || kattr->test.ctx_out))) goto free_ctx; /* Meta data is allocated from the headroom */ headroom -= ctx->data; } max_data_sz = 4096 - headroom - tailroom; - size = min_t(u32, size, max_data_sz); + if (size > max_data_sz) { + /* disallow live data mode for jumbo frames */ + if (do_live) + goto free_ctx; + size = max_data_sz; + } data = bpf_test_init(kattr, size, max_data_sz, headroom, tailroom); if (IS_ERR(data)) { @@ -1011,7 +1313,10 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, if (repeat > 1) bpf_prog_change_xdp(NULL, prog); - ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true); + if (do_live) + ret = bpf_test_run_xdp_live(prog, &xdp, repeat, batch_size, &duration); + else + ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true); /* We convert the xdp_buff back to an xdp_md before checking the return * code so the reference count of any held netdevice will be decremented * even if the test run failed. @@ -1073,7 +1378,7 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR) return -EINVAL; - if (kattr->test.flags || kattr->test.cpu) + if (kattr->test.flags || kattr->test.cpu || kattr->test.batch_size) return -EINVAL; if (size < ETH_HLEN) @@ -1108,7 +1413,7 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, do { retval = bpf_flow_dissect(prog, &ctx, eth->h_proto, ETH_HLEN, size, flags); - } while (bpf_test_timer_continue(&t, repeat, &ret, &duration)); + } while (bpf_test_timer_continue(&t, 1, repeat, &ret, &duration)); bpf_test_timer_leave(&t); if (ret < 0) @@ -1140,7 +1445,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat if (prog->type != BPF_PROG_TYPE_SK_LOOKUP) return -EINVAL; - if (kattr->test.flags || kattr->test.cpu) + if (kattr->test.flags || kattr->test.cpu || kattr->test.batch_size) return -EINVAL; if (kattr->test.data_in || kattr->test.data_size_in || kattr->test.data_out || @@ -1203,7 +1508,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat do { ctx.selected_sk = NULL; retval = BPF_PROG_SK_LOOKUP_RUN_ARRAY(progs, ctx, bpf_prog_run); - } while (bpf_test_timer_continue(&t, repeat, &ret, &duration)); + } while (bpf_test_timer_continue(&t, 1, repeat, &ret, &duration)); bpf_test_timer_leave(&t); if (ret < 0) @@ -1242,7 +1547,8 @@ int bpf_prog_test_run_syscall(struct bpf_prog *prog, /* doesn't support data_in/out, ctx_out, duration, or repeat or flags */ if (kattr->test.data_in || kattr->test.data_out || kattr->test.ctx_out || kattr->test.duration || - kattr->test.repeat || kattr->test.flags) + kattr->test.repeat || kattr->test.flags || + kattr->test.batch_size) return -EINVAL; if (ctx_size_in < prog->aux->max_ctx_offset || diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 4eebea830613..bc23020b638d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1232,6 +1232,8 @@ enum { /* If set, run the test on the cpu specified by bpf_attr.test.cpu */ #define BPF_F_TEST_RUN_ON_CPU (1U << 0) +/* If set, XDP frames will be transmitted after processing */ +#define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1) /* type for BPF_ENABLE_STATS */ enum bpf_stats_type { @@ -1393,6 +1395,7 @@ union bpf_attr { __aligned_u64 ctx_out; __u32 flags; __u32 cpu; + __u32 batch_size; } test; struct { /* anonymous struct used by BPF_*_GET_*_ID */ -- cgit v1.2.3 From 530e0d46c61314c59ecfdb8d3bcb87edbc0f85d3 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Wed, 9 Mar 2022 13:04:13 +0100 Subject: can: isotp: set default value for N_As to 50 micro seconds The N_As value describes the time a CAN frame needs on the wire when transmitted by the CAN controller. Even very short CAN FD frames need arround 100 usecs (bitrate 1Mbit/s, data bitrate 8Mbit/s). Having N_As to be zero (the former default) leads to 'no CAN frame separation' when STmin is set to zero by the receiving node. This 'burst mode' should not be enabled by default as it could potentially dump a high number of CAN frames into the netdev queue from the soft hrtimer context. This does not affect the system stability but is just not nice and cooperative. With this N_As/frame_txtime value the 'burst mode' is disabled by default. As user space applications usually do not set the frame_txtime element of struct can_isotp_options the new in-kernel default is very likely overwritten with zero when the sockopt() CAN_ISOTP_OPTS is invoked. To make sure that a N_As value of zero is only set intentional the value '0' is now interpreted as 'do not change the current value'. When a frame_txtime of zero is required for testing purposes this CAN_ISOTP_FRAME_TXTIME_ZERO u32 value has to be set in frame_txtime. Link: https://lore.kernel.org/all/20220309120416.83514-2-socketcan@hartkopp.net Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/isotp.h | 28 ++++++++++++++++++++++------ net/can/isotp.c | 12 +++++++++++- 2 files changed, 33 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/can/isotp.h b/include/uapi/linux/can/isotp.h index c55935b64ccc..590f8aea2b6d 100644 --- a/include/uapi/linux/can/isotp.h +++ b/include/uapi/linux/can/isotp.h @@ -137,20 +137,16 @@ struct can_isotp_ll_options { #define CAN_ISOTP_WAIT_TX_DONE 0x400 /* wait for tx completion */ #define CAN_ISOTP_SF_BROADCAST 0x800 /* 1-to-N functional addressing */ -/* default values */ +/* protocol machine default values */ #define CAN_ISOTP_DEFAULT_FLAGS 0 #define CAN_ISOTP_DEFAULT_EXT_ADDRESS 0x00 #define CAN_ISOTP_DEFAULT_PAD_CONTENT 0xCC /* prevent bit-stuffing */ -#define CAN_ISOTP_DEFAULT_FRAME_TXTIME 0 +#define CAN_ISOTP_DEFAULT_FRAME_TXTIME 50000 /* 50 micro seconds */ #define CAN_ISOTP_DEFAULT_RECV_BS 0 #define CAN_ISOTP_DEFAULT_RECV_STMIN 0x00 #define CAN_ISOTP_DEFAULT_RECV_WFTMAX 0 -#define CAN_ISOTP_DEFAULT_LL_MTU CAN_MTU -#define CAN_ISOTP_DEFAULT_LL_TX_DL CAN_MAX_DLEN -#define CAN_ISOTP_DEFAULT_LL_TX_FLAGS 0 - /* * Remark on CAN_ISOTP_DEFAULT_RECV_* values: * @@ -162,4 +158,24 @@ struct can_isotp_ll_options { * consistency and copied directly into the flow control (FC) frame. */ +/* link layer default values => make use of Classical CAN frames */ + +#define CAN_ISOTP_DEFAULT_LL_MTU CAN_MTU +#define CAN_ISOTP_DEFAULT_LL_TX_DL CAN_MAX_DLEN +#define CAN_ISOTP_DEFAULT_LL_TX_FLAGS 0 + +/* + * The CAN_ISOTP_DEFAULT_FRAME_TXTIME has become a non-zero value as + * it only makes sense for isotp implementation tests to run without + * a N_As value. As user space applications usually do not set the + * frame_txtime element of struct can_isotp_options the new in-kernel + * default is very likely overwritten with zero when the sockopt() + * CAN_ISOTP_OPTS is invoked. + * To make sure that a N_As value of zero is only set intentional the + * value '0' is now interpreted as 'do not change the current value'. + * When a frame_txtime of zero is required for testing purposes this + * CAN_ISOTP_FRAME_TXTIME_ZERO u32 value has to be set in frame_txtime. + */ +#define CAN_ISOTP_FRAME_TXTIME_ZERO 0xFFFFFFFF + #endif /* !_UAPI_CAN_ISOTP_H */ diff --git a/net/can/isotp.c b/net/can/isotp.c index d59f1758ac9c..47404ba59981 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -140,6 +140,7 @@ struct isotp_sock { struct can_isotp_options opt; struct can_isotp_fc_options rxfc, txfc; struct can_isotp_ll_options ll; + u32 frame_txtime; u32 force_tx_stmin; u32 force_rx_stmin; u32 cfecho; /* consecutive frame echo tag */ @@ -360,7 +361,7 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) so->tx_gap = ktime_set(0, 0); /* add transmission time for CAN frame N_As */ - so->tx_gap = ktime_add_ns(so->tx_gap, so->opt.frame_txtime); + so->tx_gap = ktime_add_ns(so->tx_gap, so->frame_txtime); /* add waiting time for consecutive frames N_Cs */ if (so->opt.flags & CAN_ISOTP_FORCE_TXSTMIN) so->tx_gap = ktime_add_ns(so->tx_gap, @@ -1293,6 +1294,14 @@ static int isotp_setsockopt_locked(struct socket *sock, int level, int optname, /* no separate rx_ext_address is given => use ext_address */ if (!(so->opt.flags & CAN_ISOTP_RX_EXT_ADDR)) so->opt.rx_ext_address = so->opt.ext_address; + + /* check for frame_txtime changes (0 => no changes) */ + if (so->opt.frame_txtime) { + if (so->opt.frame_txtime == CAN_ISOTP_FRAME_TXTIME_ZERO) + so->frame_txtime = 0; + else + so->frame_txtime = so->opt.frame_txtime; + } break; case CAN_ISOTP_RECV_FC: @@ -1498,6 +1507,7 @@ static int isotp_init(struct sock *sk) so->opt.rxpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT; so->opt.txpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT; so->opt.frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME; + so->frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME; so->rxfc.bs = CAN_ISOTP_DEFAULT_RECV_BS; so->rxfc.stmin = CAN_ISOTP_DEFAULT_RECV_STMIN; so->rxfc.wftmax = CAN_ISOTP_DEFAULT_RECV_WFTMAX; -- cgit v1.2.3 From 9bb984f28d5bcb917d35d930fcfb89f90f9449fd Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 9 Mar 2022 01:05:09 -0800 Subject: bpf: Remove BPF_SKB_DELIVERY_TIME_NONE and rename s/delivery_time_/tstamp_/ This patch is to simplify the uapi bpf.h regarding to the tstamp type and use a similar way as the kernel to describe the value stored in __sk_buff->tstamp. My earlier thought was to avoid describing the semantic and clock base for the rcv timestamp until there is more clarity on the use case, so the __sk_buff->delivery_time_type naming instead of __sk_buff->tstamp_type. With some thoughts, it can reuse the UNSPEC naming. This patch first removes BPF_SKB_DELIVERY_TIME_NONE and also rename BPF_SKB_DELIVERY_TIME_UNSPEC to BPF_SKB_TSTAMP_UNSPEC and BPF_SKB_DELIVERY_TIME_MONO to BPF_SKB_TSTAMP_DELIVERY_MONO. The semantic of BPF_SKB_TSTAMP_DELIVERY_MONO is the same: __sk_buff->tstamp has delivery time in mono clock base. BPF_SKB_TSTAMP_UNSPEC means __sk_buff->tstamp has the (rcv) tstamp at ingress and the delivery time at egress. At egress, the clock base could be found from skb->sk->sk_clockid. __sk_buff->tstamp == 0 naturally means NONE, so NONE is not needed. With BPF_SKB_TSTAMP_UNSPEC for the rcv tstamp at ingress, the __sk_buff->delivery_time_type is also renamed to __sk_buff->tstamp_type which was also suggested in the earlier discussion: https://lore.kernel.org/bpf/b181acbe-caf8-502d-4b7b-7d96b9fc5d55@iogearbox.net/ The above will then make __sk_buff->tstamp and __sk_buff->tstamp_type the same as its kernel skb->tstamp and skb->mono_delivery_time counter part. The internal kernel function bpf_skb_convert_dtime_type_read() is then renamed to bpf_skb_convert_tstamp_type_read() and it can be simplified with the BPF_SKB_DELIVERY_TIME_NONE gone. A BPF_ALU32_IMM(BPF_AND) insn is also saved by using BPF_JMP32_IMM(BPF_JSET). The bpf helper bpf_skb_set_delivery_time() is also renamed to bpf_skb_set_tstamp(). The arg name is changed from dtime to tstamp also. It only allows setting tstamp 0 for BPF_SKB_TSTAMP_UNSPEC and it could be relaxed later if there is use case to change mono delivery time to non mono. prog->delivery_time_access is also renamed to prog->tstamp_type_access. Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20220309090509.3712315-1-kafai@fb.com --- include/linux/filter.h | 2 +- include/uapi/linux/bpf.h | 40 ++++++++++--------- net/core/filter.c | 88 ++++++++++++++++-------------------------- tools/include/uapi/linux/bpf.h | 40 ++++++++++--------- 4 files changed, 77 insertions(+), 93 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 9bf26307247f..05ed9bd31b45 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -573,7 +573,7 @@ struct bpf_prog { enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ call_get_func_ip:1, /* Do we call get_func_ip() */ - delivery_time_access:1; /* Accessed __sk_buff->delivery_time_type */ + tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */ 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 */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bc23020b638d..d288a0a9f797 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5090,23 +5090,22 @@ union bpf_attr { * 0 on success, or a negative error in case of failure. On error * *dst* buffer is zeroed out. * - * long bpf_skb_set_delivery_time(struct sk_buff *skb, u64 dtime, u32 dtime_type) + * long bpf_skb_set_tstamp(struct sk_buff *skb, u64 tstamp, u32 tstamp_type) * Description - * Set a *dtime* (delivery time) to the __sk_buff->tstamp and also - * change the __sk_buff->delivery_time_type to *dtime_type*. + * Change the __sk_buff->tstamp_type to *tstamp_type* + * and set *tstamp* to the __sk_buff->tstamp together. * - * When setting a delivery time (non zero *dtime*) to - * __sk_buff->tstamp, only BPF_SKB_DELIVERY_TIME_MONO *dtime_type* - * is supported. It is the only delivery_time_type that will be - * kept after bpf_redirect_*(). - * - * If there is no need to change the __sk_buff->delivery_time_type, - * the delivery time can be directly written to __sk_buff->tstamp + * If there is no need to change the __sk_buff->tstamp_type, + * the tstamp value can be directly written to __sk_buff->tstamp * instead. * - * *dtime* 0 and *dtime_type* BPF_SKB_DELIVERY_TIME_NONE - * can be used to clear any delivery time stored in - * __sk_buff->tstamp. + * BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that + * will be kept during bpf_redirect_*(). A non zero + * *tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO + * *tstamp_type*. + * + * A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used + * with a zero *tstamp*. * * Only IPv4 and IPv6 skb->protocol are supported. * @@ -5119,7 +5118,7 @@ union bpf_attr { * Return * 0 on success. * **-EINVAL** for invalid input - * **-EOPNOTSUPP** for unsupported delivery_time_type and protocol + * **-EOPNOTSUPP** for unsupported protocol */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5314,7 +5313,7 @@ union bpf_attr { FN(xdp_load_bytes), \ FN(xdp_store_bytes), \ FN(copy_from_user_task), \ - FN(skb_set_delivery_time), \ + FN(skb_set_tstamp), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5505,9 +5504,12 @@ union { \ } __attribute__((aligned(8))) enum { - BPF_SKB_DELIVERY_TIME_NONE, - BPF_SKB_DELIVERY_TIME_UNSPEC, - BPF_SKB_DELIVERY_TIME_MONO, + BPF_SKB_TSTAMP_UNSPEC, + BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */ + /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle, + * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC + * and try to deduce it by ingress, egress or skb->sk->sk_clockid. + */ }; /* user accessible mirror of in-kernel sk_buff. @@ -5550,7 +5552,7 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; - __u8 delivery_time_type; + __u8 tstamp_type; __u32 :24; /* Padding, future use. */ __u64 hwtstamp; }; diff --git a/net/core/filter.c b/net/core/filter.c index f914e4b13b18..03655f2074ae 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7388,36 +7388,36 @@ static const struct bpf_func_proto bpf_sock_ops_reserve_hdr_opt_proto = { .arg3_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_skb_set_delivery_time, struct sk_buff *, skb, - u64, dtime, u32, dtime_type) +BPF_CALL_3(bpf_skb_set_tstamp, struct sk_buff *, skb, + u64, tstamp, u32, tstamp_type) { /* skb_clear_delivery_time() is done for inet protocol */ if (skb->protocol != htons(ETH_P_IP) && skb->protocol != htons(ETH_P_IPV6)) return -EOPNOTSUPP; - switch (dtime_type) { - case BPF_SKB_DELIVERY_TIME_MONO: - if (!dtime) + switch (tstamp_type) { + case BPF_SKB_TSTAMP_DELIVERY_MONO: + if (!tstamp) return -EINVAL; - skb->tstamp = dtime; + skb->tstamp = tstamp; skb->mono_delivery_time = 1; break; - case BPF_SKB_DELIVERY_TIME_NONE: - if (dtime) + case BPF_SKB_TSTAMP_UNSPEC: + if (tstamp) return -EINVAL; skb->tstamp = 0; skb->mono_delivery_time = 0; break; default: - return -EOPNOTSUPP; + return -EINVAL; } return 0; } -static const struct bpf_func_proto bpf_skb_set_delivery_time_proto = { - .func = bpf_skb_set_delivery_time, +static const struct bpf_func_proto bpf_skb_set_tstamp_proto = { + .func = bpf_skb_set_tstamp, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, @@ -7786,8 +7786,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_gen_syncookie_proto; case BPF_FUNC_sk_assign: return &bpf_sk_assign_proto; - case BPF_FUNC_skb_set_delivery_time: - return &bpf_skb_set_delivery_time_proto; + case BPF_FUNC_skb_set_tstamp: + return &bpf_skb_set_tstamp_proto; #endif default: return bpf_sk_base_func_proto(func_id); @@ -8127,9 +8127,9 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type return false; info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; break; - case offsetof(struct __sk_buff, delivery_time_type): + case offsetof(struct __sk_buff, tstamp_type): return false; - case offsetofend(struct __sk_buff, delivery_time_type) ... offsetof(struct __sk_buff, hwtstamp) - 1: + case offsetofend(struct __sk_buff, tstamp_type) ... offsetof(struct __sk_buff, hwtstamp) - 1: /* Explicitly prohibit access to padding in __sk_buff. */ return false; default: @@ -8484,14 +8484,14 @@ static bool tc_cls_act_is_valid_access(int off, int size, break; case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; - case offsetof(struct __sk_buff, delivery_time_type): + case offsetof(struct __sk_buff, tstamp_type): /* The convert_ctx_access() on reading and writing * __sk_buff->tstamp depends on whether the bpf prog - * has used __sk_buff->delivery_time_type or not. - * Thus, we need to set prog->delivery_time_access + * has used __sk_buff->tstamp_type or not. + * Thus, we need to set prog->tstamp_type_access * earlier during is_valid_access() here. */ - ((struct bpf_prog *)prog)->delivery_time_access = 1; + ((struct bpf_prog *)prog)->tstamp_type_access = 1; return size == sizeof(__u8); } @@ -8888,42 +8888,22 @@ static u32 flow_dissector_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } -static struct bpf_insn *bpf_convert_dtime_type_read(const struct bpf_insn *si, - struct bpf_insn *insn) +static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si, + struct bpf_insn *insn) { __u8 value_reg = si->dst_reg; __u8 skb_reg = si->src_reg; + /* AX is needed because src_reg and dst_reg could be the same */ __u8 tmp_reg = BPF_REG_AX; *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, PKT_VLAN_PRESENT_OFFSET); - *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, - SKB_MONO_DELIVERY_TIME_MASK); - *insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0, 2); - /* value_reg = BPF_SKB_DELIVERY_TIME_MONO */ - *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_DELIVERY_TIME_MONO); - *insn++ = BPF_JMP_A(IS_ENABLED(CONFIG_NET_CLS_ACT) ? 10 : 5); - - *insn++ = BPF_LDX_MEM(BPF_DW, tmp_reg, skb_reg, - offsetof(struct sk_buff, tstamp)); - *insn++ = BPF_JMP_IMM(BPF_JNE, tmp_reg, 0, 2); - /* value_reg = BPF_SKB_DELIVERY_TIME_NONE */ - *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_DELIVERY_TIME_NONE); - *insn++ = BPF_JMP_A(IS_ENABLED(CONFIG_NET_CLS_ACT) ? 6 : 1); - -#ifdef CONFIG_NET_CLS_ACT - *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, PKT_VLAN_PRESENT_OFFSET); - *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, TC_AT_INGRESS_MASK); - *insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0, 2); - /* At ingress, value_reg = 0 */ - *insn++ = BPF_MOV32_IMM(value_reg, 0); + *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, + SKB_MONO_DELIVERY_TIME_MASK, 2); + *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_UNSPEC); *insn++ = BPF_JMP_A(1); -#endif - - /* value_reg = BPF_SKB_DELIVERYT_TIME_UNSPEC */ - *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_DELIVERY_TIME_UNSPEC); + *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_DELIVERY_MONO); - /* 15 insns with CONFIG_NET_CLS_ACT */ return insn; } @@ -8956,11 +8936,11 @@ static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog, __u8 skb_reg = si->src_reg; #ifdef CONFIG_NET_CLS_ACT - /* If the delivery_time_type is read, + /* If the tstamp_type is read, * the bpf prog is aware the tstamp could have delivery time. - * Thus, read skb->tstamp as is if delivery_time_access is true. + * Thus, read skb->tstamp as is if tstamp_type_access is true. */ - if (!prog->delivery_time_access) { + if (!prog->tstamp_type_access) { /* AX is needed because src_reg and dst_reg could be the same */ __u8 tmp_reg = BPF_REG_AX; @@ -8990,13 +8970,13 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog, __u8 skb_reg = si->dst_reg; #ifdef CONFIG_NET_CLS_ACT - /* If the delivery_time_type is read, + /* If the tstamp_type is read, * the bpf prog is aware the tstamp could have delivery time. - * Thus, write skb->tstamp as is if delivery_time_access is true. + * Thus, write skb->tstamp as is if tstamp_type_access is true. * Otherwise, writing at ingress will have to clear the * mono_delivery_time bit also. */ - if (!prog->delivery_time_access) { + if (!prog->tstamp_type_access) { __u8 tmp_reg = BPF_REG_AX; *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, PKT_VLAN_PRESENT_OFFSET); @@ -9329,8 +9309,8 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, insn = bpf_convert_tstamp_read(prog, si, insn); break; - case offsetof(struct __sk_buff, delivery_time_type): - insn = bpf_convert_dtime_type_read(si, insn); + case offsetof(struct __sk_buff, tstamp_type): + insn = bpf_convert_tstamp_type_read(si, insn); break; case offsetof(struct __sk_buff, gso_segs): diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index bc23020b638d..d288a0a9f797 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5090,23 +5090,22 @@ union bpf_attr { * 0 on success, or a negative error in case of failure. On error * *dst* buffer is zeroed out. * - * long bpf_skb_set_delivery_time(struct sk_buff *skb, u64 dtime, u32 dtime_type) + * long bpf_skb_set_tstamp(struct sk_buff *skb, u64 tstamp, u32 tstamp_type) * Description - * Set a *dtime* (delivery time) to the __sk_buff->tstamp and also - * change the __sk_buff->delivery_time_type to *dtime_type*. + * Change the __sk_buff->tstamp_type to *tstamp_type* + * and set *tstamp* to the __sk_buff->tstamp together. * - * When setting a delivery time (non zero *dtime*) to - * __sk_buff->tstamp, only BPF_SKB_DELIVERY_TIME_MONO *dtime_type* - * is supported. It is the only delivery_time_type that will be - * kept after bpf_redirect_*(). - * - * If there is no need to change the __sk_buff->delivery_time_type, - * the delivery time can be directly written to __sk_buff->tstamp + * If there is no need to change the __sk_buff->tstamp_type, + * the tstamp value can be directly written to __sk_buff->tstamp * instead. * - * *dtime* 0 and *dtime_type* BPF_SKB_DELIVERY_TIME_NONE - * can be used to clear any delivery time stored in - * __sk_buff->tstamp. + * BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that + * will be kept during bpf_redirect_*(). A non zero + * *tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO + * *tstamp_type*. + * + * A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used + * with a zero *tstamp*. * * Only IPv4 and IPv6 skb->protocol are supported. * @@ -5119,7 +5118,7 @@ union bpf_attr { * Return * 0 on success. * **-EINVAL** for invalid input - * **-EOPNOTSUPP** for unsupported delivery_time_type and protocol + * **-EOPNOTSUPP** for unsupported protocol */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5314,7 +5313,7 @@ union bpf_attr { FN(xdp_load_bytes), \ FN(xdp_store_bytes), \ FN(copy_from_user_task), \ - FN(skb_set_delivery_time), \ + FN(skb_set_tstamp), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5505,9 +5504,12 @@ union { \ } __attribute__((aligned(8))) enum { - BPF_SKB_DELIVERY_TIME_NONE, - BPF_SKB_DELIVERY_TIME_UNSPEC, - BPF_SKB_DELIVERY_TIME_MONO, + BPF_SKB_TSTAMP_UNSPEC, + BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */ + /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle, + * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC + * and try to deduce it by ingress, egress or skb->sk->sk_clockid. + */ }; /* user accessible mirror of in-kernel sk_buff. @@ -5550,7 +5552,7 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; - __u8 delivery_time_type; + __u8 tstamp_type; __u32 :24; /* Padding, future use. */ __u64 hwtstamp; }; -- cgit v1.2.3 From 58617014405ad5c9f94f464444f4972dabb71ca7 Mon Sep 17 00:00:00 2001 From: Hengqi Chen Date: Thu, 10 Mar 2022 23:53:35 +0800 Subject: bpf: Fix comment for helper bpf_current_task_under_cgroup() Fix the descriptions of the return values of helper bpf_current_task_under_cgroup(). Fixes: c6b5fb8690fa ("bpf: add documentation for eBPF helpers (42-50)") Signed-off-by: Hengqi Chen Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20220310155335.1278783-1-hengqi.chen@gmail.com --- include/uapi/linux/bpf.h | 4 ++-- tools/include/uapi/linux/bpf.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d288a0a9f797..e9978a916c3e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2302,8 +2302,8 @@ union bpf_attr { * Return * The return value depends on the result of the test, and can be: * - * * 0, if current task belongs to the cgroup2. - * * 1, if current task does not belong to the cgroup2. + * * 1, if current task belongs to the cgroup2. + * * 0, if current task does not belong to the cgroup2. * * A negative error code, if an error occurred. * * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index d288a0a9f797..e9978a916c3e 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2302,8 +2302,8 @@ union bpf_attr { * Return * The return value depends on the result of the test, and can be: * - * * 0, if current task belongs to the cgroup2. - * * 1, if current task does not belong to the cgroup2. + * * 1, if current task belongs to the cgroup2. + * * 0, if current task does not belong to the cgroup2. * * A negative error code, if an error occurred. * * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) -- cgit v1.2.3 From 174b16946e39ebd369097e0f773536c91a8c1a4c Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Wed, 2 Mar 2022 12:13:58 +0100 Subject: bpf-lsm: Introduce new helper bpf_ima_file_hash() ima_file_hash() has been modified to calculate the measurement of a file on demand, if it has not been already performed by IMA or the measurement is not fresh. For compatibility reasons, ima_inode_hash() remains unchanged. Keep the same approach in eBPF and introduce the new helper bpf_ima_file_hash() to take advantage of the modified behavior of ima_file_hash(). Signed-off-by: Roberto Sassu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220302111404.193900-4-roberto.sassu@huawei.com --- include/uapi/linux/bpf.h | 11 +++++++++++ kernel/bpf/bpf_lsm.c | 20 ++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 11 +++++++++++ 3 files changed, 42 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e9978a916c3e..99fab54ae9c0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5119,6 +5119,16 @@ union bpf_attr { * 0 on success. * **-EINVAL** for invalid input * **-EOPNOTSUPP** for unsupported protocol + * + * long bpf_ima_file_hash(struct file *file, void *dst, u32 size) + * Description + * Returns a calculated IMA hash of the *file*. + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if + * invalid arguments are passed. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5314,6 +5324,7 @@ union bpf_attr { FN(xdp_store_bytes), \ FN(copy_from_user_task), \ FN(skb_set_tstamp), \ + FN(ima_file_hash), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 9e4ecc990647..e8d27af5bbcc 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -99,6 +99,24 @@ static const struct bpf_func_proto bpf_ima_inode_hash_proto = { .allowed = bpf_ima_inode_hash_allowed, }; +BPF_CALL_3(bpf_ima_file_hash, struct file *, file, void *, dst, u32, size) +{ + return ima_file_hash(file, dst, size); +} + +BTF_ID_LIST_SINGLE(bpf_ima_file_hash_btf_ids, struct, file) + +static const struct bpf_func_proto bpf_ima_file_hash_proto = { + .func = bpf_ima_file_hash, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_ima_file_hash_btf_ids[0], + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, + .allowed = bpf_ima_inode_hash_allowed, +}; + static const struct bpf_func_proto * bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -121,6 +139,8 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_bprm_opts_set_proto; case BPF_FUNC_ima_inode_hash: return prog->aux->sleepable ? &bpf_ima_inode_hash_proto : NULL; + case BPF_FUNC_ima_file_hash: + return prog->aux->sleepable ? &bpf_ima_file_hash_proto : NULL; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e9978a916c3e..99fab54ae9c0 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5119,6 +5119,16 @@ union bpf_attr { * 0 on success. * **-EINVAL** for invalid input * **-EOPNOTSUPP** for unsupported protocol + * + * long bpf_ima_file_hash(struct file *file, void *dst, u32 size) + * Description + * Returns a calculated IMA hash of the *file*. + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if + * invalid arguments are passed. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5314,6 +5324,7 @@ union bpf_attr { FN(xdp_store_bytes), \ FN(copy_from_user_task), \ FN(skb_set_tstamp), \ + FN(ima_file_hash), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 1926407a4ab0e59d5a27bed7b82029b356d80fa0 Mon Sep 17 00:00:00 2001 From: Ilya Maximets Date: Wed, 9 Mar 2022 23:20:33 +0100 Subject: net: openvswitch: fix uAPI incompatibility with existing user space Few years ago OVS user space made a strange choice in the commit [1] to define types only valid for the user space inside the copy of a kernel uAPI header. '#ifndef __KERNEL__' and another attribute was added later. This leads to the inevitable clash between user space and kernel types when the kernel uAPI is extended. The issue was unveiled with the addition of a new type for IPv6 extension header in kernel uAPI. When kernel provides the OVS_KEY_ATTR_IPV6_EXTHDRS attribute to the older user space application, application tries to parse it as OVS_KEY_ATTR_PACKET_TYPE and discards the whole netlink message as malformed. Since OVS_KEY_ATTR_IPV6_EXTHDRS is supplied along with every IPv6 packet that goes to the user space, IPv6 support is fully broken. Fixing that by bringing these user space attributes to the kernel uAPI to avoid the clash. Strictly speaking this is not the problem of the kernel uAPI, but changing it is the only way to avoid breakage of the older user space applications at this point. These 2 types are explicitly rejected now since they should not be passed to the kernel. Additionally, OVS_KEY_ATTR_TUNNEL_INFO moved out from the '#ifdef __KERNEL__' as there is no good reason to hide it from the userspace. And it's also explicitly rejected now, because it's for in-kernel use only. Comments with warnings were added to avoid the problem coming back. (1 << type) converted to (1ULL << type) to avoid integer overflow on OVS_KEY_ATTR_IPV6_EXTHDRS, since it equals 32 now. [1] beb75a40fdc2 ("userspace: Switching of L3 packets in L2 pipeline") Fixes: 28a3f0601727 ("net: openvswitch: IPv6: Add IPv6 extension header support") Link: https://lore.kernel.org/netdev/3adf00c7-fe65-3ef4-b6d7-6d8a0cad8a5f@nvidia.com Link: https://github.com/openvswitch/ovs/commit/beb75a40fdc295bfd6521b0068b4cd12f6de507c Reported-by: Roi Dayan Signed-off-by: Ilya Maximets Acked-by: Nicolas Dichtel Acked-by: Aaron Conole Link: https://lore.kernel.org/r/20220309222033.3018976-1-i.maximets@ovn.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/openvswitch.h | 18 ++++++++++++++---- net/openvswitch/flow_netlink.c | 13 ++++++++++--- 2 files changed, 24 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 9d1710f20505..ce3e1738d427 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -351,11 +351,21 @@ enum ovs_key_attr { OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, /* struct ovs_key_ct_tuple_ipv4 */ OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, /* struct ovs_key_ct_tuple_ipv6 */ OVS_KEY_ATTR_NSH, /* Nested set of ovs_nsh_key_* */ - OVS_KEY_ATTR_IPV6_EXTHDRS, /* struct ovs_key_ipv6_exthdr */ -#ifdef __KERNEL__ - OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */ -#endif + /* User space decided to squat on types 29 and 30. They are defined + * below, but should not be sent to the kernel. + * + * WARNING: No new types should be added unless they are defined + * for both kernel and user space (no 'ifdef's). It's hard + * to keep compatibility otherwise. + */ + OVS_KEY_ATTR_PACKET_TYPE, /* be32 packet type */ + OVS_KEY_ATTR_ND_EXTENSIONS, /* IPv6 Neighbor Discovery extensions */ + + OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info. + * For in-kernel use only. + */ + OVS_KEY_ATTR_IPV6_EXTHDRS, /* struct ovs_key_ipv6_exthdr */ __OVS_KEY_ATTR_MAX }; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 8b4124820f7d..5176f6ccac8e 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -346,7 +346,7 @@ size_t ovs_key_attr_size(void) /* Whenever adding new OVS_KEY_ FIELDS, we should consider * updating this function. */ - BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 30); + BUILD_BUG_ON(OVS_KEY_ATTR_MAX != 32); return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */ + nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */ @@ -482,7 +482,14 @@ static int __parse_flow_nlattrs(const struct nlattr *attr, return -EINVAL; } - if (attrs & (1 << type)) { + if (type == OVS_KEY_ATTR_PACKET_TYPE || + type == OVS_KEY_ATTR_ND_EXTENSIONS || + type == OVS_KEY_ATTR_TUNNEL_INFO) { + OVS_NLERR(log, "Key type %d is not supported", type); + return -EINVAL; + } + + if (attrs & (1ULL << type)) { OVS_NLERR(log, "Duplicate key (type %d).", type); return -EINVAL; } @@ -495,7 +502,7 @@ static int __parse_flow_nlattrs(const struct nlattr *attr, } if (!nz || !is_all_zero(nla_data(nla), nla_len(nla))) { - attrs |= 1 << type; + attrs |= 1ULL << type; a[type] = nla; } } -- cgit v1.2.3 From 2916b7a9c7c25ecf9be2f37e567a277e861f8e3f Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Tue, 22 Feb 2022 20:36:39 +0530 Subject: nl80211: fix typo of NL80211_IF_TYPE_OCB in documentation It should be NL80211_IFTYPE_OCB instead. Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/1645542399-4680-1-git-send-email-quic_vjakkam@quicinc.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 98ed52663d6b..0568a79097b8 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3259,7 +3259,7 @@ enum nl80211_attrs { * and therefore can't be created in the normal ways, use the * %NL80211_CMD_START_P2P_DEVICE and %NL80211_CMD_STOP_P2P_DEVICE * commands to create and destroy one - * @NL80211_IF_TYPE_OCB: Outside Context of a BSS + * @NL80211_IFTYPE_OCB: Outside Context of a BSS * This mode corresponds to the MIB variable dot11OCBActivated=true * @NL80211_IFTYPE_NAN: NAN device interface type (not a netdev) * @NL80211_IFTYPE_MAX: highest interface type number currently defined -- cgit v1.2.3 From b20dc3c684580ddc07eb48ee3c3dc7597cd5eebf Mon Sep 17 00:00:00 2001 From: Wojciech Drewek Date: Fri, 4 Mar 2022 17:40:42 +0100 Subject: gtp: Allow to create GTP device without FDs Currently, when the user wants to create GTP device, he has to provide file handles to the sockets created in userspace (IFLA_GTP_FD0, IFLA_GTP_FD1). This behaviour is not ideal, considering the option of adding support for GTP device creation through ip link. Ip link application is not a good place to create such sockets. This patch allows to create GTP device without providing IFLA_GTP_FD0 and IFLA_GTP_FD1 arguments. If the user sets IFLA_GTP_CREATE_SOCKETS attribute, then GTP module takes care of creating UDP sockets by itself. Sockets are created with the commonly known UDP ports used for GTP protocol (GTP0_PORT and GTP1U_PORT). In this case we don't have to provide encap_destroy because no extra deinitialization is needed, everything is covered by udp_tunnel_sock_release. Note: GTP instance created with only this change applied, does not handle GTP Echo Requests. This is implemented in the following patch. Signed-off-by: Wojciech Drewek Signed-off-by: Tony Nguyen --- drivers/net/gtp.c | 101 +++++++++++++++++++++++++++++++++++-------- include/uapi/linux/if_link.h | 1 + 2 files changed, 85 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index bf087171bcf0..25d8521897b3 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -66,8 +66,10 @@ struct gtp_dev { struct sock *sk0; struct sock *sk1u; + u8 sk_created; struct net_device *dev; + struct net *net; unsigned int role; unsigned int hash_size; @@ -320,8 +322,16 @@ static void gtp_encap_disable_sock(struct sock *sk) static void gtp_encap_disable(struct gtp_dev *gtp) { - gtp_encap_disable_sock(gtp->sk0); - gtp_encap_disable_sock(gtp->sk1u); + if (gtp->sk_created) { + udp_tunnel_sock_release(gtp->sk0->sk_socket); + udp_tunnel_sock_release(gtp->sk1u->sk_socket); + gtp->sk_created = false; + gtp->sk0 = NULL; + gtp->sk1u = NULL; + } else { + gtp_encap_disable_sock(gtp->sk0); + gtp_encap_disable_sock(gtp->sk1u); + } } /* UDP encapsulation receive handler. See net/ipv4/udp.c. @@ -656,17 +666,69 @@ static void gtp_destructor(struct net_device *dev) kfree(gtp->tid_hash); } +static struct sock *gtp_create_sock(int type, struct gtp_dev *gtp) +{ + struct udp_tunnel_sock_cfg tuncfg = {}; + struct udp_port_cfg udp_conf = { + .local_ip.s_addr = htonl(INADDR_ANY), + .family = AF_INET, + }; + struct net *net = gtp->net; + struct socket *sock; + int err; + + if (type == UDP_ENCAP_GTP0) + udp_conf.local_udp_port = htons(GTP0_PORT); + else if (type == UDP_ENCAP_GTP1U) + udp_conf.local_udp_port = htons(GTP1U_PORT); + else + return ERR_PTR(-EINVAL); + + err = udp_sock_create(net, &udp_conf, &sock); + if (err) + return ERR_PTR(err); + + tuncfg.sk_user_data = gtp; + tuncfg.encap_type = type; + tuncfg.encap_rcv = gtp_encap_recv; + tuncfg.encap_destroy = NULL; + + setup_udp_tunnel_sock(net, sock, &tuncfg); + + return sock->sk; +} + +static int gtp_create_sockets(struct gtp_dev *gtp, struct nlattr *data[]) +{ + struct sock *sk1u = NULL; + struct sock *sk0 = NULL; + + sk0 = gtp_create_sock(UDP_ENCAP_GTP0, gtp); + if (IS_ERR(sk0)) + return PTR_ERR(sk0); + + sk1u = gtp_create_sock(UDP_ENCAP_GTP1U, gtp); + if (IS_ERR(sk1u)) { + udp_tunnel_sock_release(sk0->sk_socket); + return PTR_ERR(sk1u); + } + + gtp->sk_created = true; + gtp->sk0 = sk0; + gtp->sk1u = sk1u; + + return 0; +} + static int gtp_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { + unsigned int role = GTP_ROLE_GGSN; struct gtp_dev *gtp; struct gtp_net *gn; int hashsize, err; - if (!data[IFLA_GTP_FD0] && !data[IFLA_GTP_FD1]) - return -EINVAL; - gtp = netdev_priv(dev); if (!data[IFLA_GTP_PDP_HASHSIZE]) { @@ -677,11 +739,23 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, hashsize = 1024; } + if (data[IFLA_GTP_ROLE]) { + role = nla_get_u32(data[IFLA_GTP_ROLE]); + if (role > GTP_ROLE_SGSN) + return -EINVAL; + } + gtp->role = role; + + gtp->net = src_net; + err = gtp_hashtable_new(gtp, hashsize); if (err < 0) return err; - err = gtp_encap_enable(gtp, data); + if (data[IFLA_GTP_CREATE_SOCKETS]) + err = gtp_create_sockets(gtp, data); + else + err = gtp_encap_enable(gtp, data); if (err < 0) goto out_hashtable; @@ -726,6 +800,7 @@ static const struct nla_policy gtp_policy[IFLA_GTP_MAX + 1] = { [IFLA_GTP_FD1] = { .type = NLA_U32 }, [IFLA_GTP_PDP_HASHSIZE] = { .type = NLA_U32 }, [IFLA_GTP_ROLE] = { .type = NLA_U32 }, + [IFLA_GTP_CREATE_SOCKETS] = { .type = NLA_U8 }, }; static int gtp_validate(struct nlattr *tb[], struct nlattr *data[], @@ -848,7 +923,9 @@ static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]) { struct sock *sk1u = NULL; struct sock *sk0 = NULL; - unsigned int role = GTP_ROLE_GGSN; + + if (!data[IFLA_GTP_FD0] && !data[IFLA_GTP_FD1]) + return -EINVAL; if (data[IFLA_GTP_FD0]) { u32 fd0 = nla_get_u32(data[IFLA_GTP_FD0]); @@ -868,18 +945,8 @@ static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]) } } - if (data[IFLA_GTP_ROLE]) { - role = nla_get_u32(data[IFLA_GTP_ROLE]); - if (role > GTP_ROLE_SGSN) { - gtp_encap_disable_sock(sk0); - gtp_encap_disable_sock(sk1u); - return -EINVAL; - } - } - gtp->sk0 = sk0; gtp->sk1u = sk1u; - gtp->role = role; return 0; } diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ddca20357e7e..ebd2aa3ef809 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -887,6 +887,7 @@ enum { IFLA_GTP_FD1, IFLA_GTP_PDP_HASHSIZE, IFLA_GTP_ROLE, + IFLA_GTP_CREATE_SOCKETS, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) -- cgit v1.2.3 From 9af41cc33471ea1efa6f77e188f055cc77d0a5c5 Mon Sep 17 00:00:00 2001 From: Wojciech Drewek Date: Fri, 4 Mar 2022 17:40:43 +0100 Subject: gtp: Implement GTP echo response Adding GTP device through ip link creates the situation where there is no userspace daemon which would handle GTP messages (Echo Request for example). GTP-U instance which would not respond to echo requests would violate GTP specification. When GTP packet arrives with GTP_ECHO_REQ message type, GTP_ECHO_RSP is send to the sender. GTP_ECHO_RSP message should contain information element with GTPIE_RECOVERY tag and restart counter value. For GTPv1 restart counter is not used and should be equal to 0, for GTPv0 restart counter contains information provided from userspace(IFLA_GTP_RESTART_COUNT). Signed-off-by: Wojciech Drewek Suggested-by: Harald Welte Reviewed-by: Harald Welte Tested-by: Harald Welte Signed-off-by: Tony Nguyen --- drivers/net/gtp.c | 213 +++++++++++++++++++++++++++++++++++++++---- include/net/gtp.h | 31 +++++++ include/uapi/linux/if_link.h | 1 + 3 files changed, 229 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 25d8521897b3..bf434d79f868 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -75,6 +75,8 @@ struct gtp_dev { unsigned int hash_size; struct hlist_head *tid_hash; struct hlist_head *addr_hash; + + u8 restart_count; }; static unsigned int gtp_net_id __read_mostly; @@ -217,6 +219,106 @@ err: return -1; } +static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4, + const struct sock *sk, + __be32 daddr, __be32 saddr) +{ + memset(fl4, 0, sizeof(*fl4)); + fl4->flowi4_oif = sk->sk_bound_dev_if; + fl4->daddr = daddr; + fl4->saddr = saddr; + fl4->flowi4_tos = RT_CONN_FLAGS(sk); + fl4->flowi4_proto = sk->sk_protocol; + + return ip_route_output_key(sock_net(sk), fl4); +} + +/* GSM TS 09.60. 7.3 + * In all Path Management messages: + * - TID: is not used and shall be set to 0. + * - Flow Label is not used and shall be set to 0 + * In signalling messages: + * - number: this field is not yet used in signalling messages. + * It shall be set to 255 by the sender and shall be ignored + * by the receiver + * Returns true if the echo req was correct, false otherwise. + */ +static bool gtp0_validate_echo_req(struct gtp0_header *gtp0) +{ + return !(gtp0->tid || (gtp0->flags ^ 0x1e) || + gtp0->number != 0xff || gtp0->flow); +} + +static int gtp0_send_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) +{ + struct gtp0_packet *gtp_pkt; + struct gtp0_header *gtp0; + struct rtable *rt; + struct flowi4 fl4; + struct iphdr *iph; + __be16 seq; + + gtp0 = (struct gtp0_header *)(skb->data + sizeof(struct udphdr)); + + if (!gtp0_validate_echo_req(gtp0)) + return -1; + + seq = gtp0->seq; + + /* pull GTP and UDP headers */ + skb_pull_data(skb, sizeof(struct gtp0_header) + sizeof(struct udphdr)); + + gtp_pkt = skb_push(skb, sizeof(struct gtp0_packet)); + memset(gtp_pkt, 0, sizeof(struct gtp0_packet)); + + gtp_pkt->gtp0_h.flags = 0x1e; /* v0, GTP-non-prime. */ + gtp_pkt->gtp0_h.type = GTP_ECHO_RSP; + gtp_pkt->gtp0_h.length = + htons(sizeof(struct gtp0_packet) - sizeof(struct gtp0_header)); + + /* GSM TS 09.60. 7.3 The Sequence Number in a signalling response + * message shall be copied from the signalling request message + * that the GSN is replying to. + */ + gtp_pkt->gtp0_h.seq = seq; + + /* GSM TS 09.60. 7.3 In all Path Management Flow Label and TID + * are not used and shall be set to 0. + */ + gtp_pkt->gtp0_h.flow = 0; + gtp_pkt->gtp0_h.tid = 0; + gtp_pkt->gtp0_h.number = 0xff; + gtp_pkt->gtp0_h.spare[0] = 0xff; + gtp_pkt->gtp0_h.spare[1] = 0xff; + gtp_pkt->gtp0_h.spare[2] = 0xff; + + gtp_pkt->ie.tag = GTPIE_RECOVERY; + gtp_pkt->ie.val = gtp->restart_count; + + iph = ip_hdr(skb); + + /* find route to the sender, + * src address becomes dst address and vice versa. + */ + rt = ip4_route_output_gtp(&fl4, gtp->sk0, iph->saddr, iph->daddr); + if (IS_ERR(rt)) { + netdev_dbg(gtp->dev, "no route for echo response from %pI4\n", + &iph->saddr); + return -1; + } + + udp_tunnel_xmit_skb(rt, gtp->sk0, skb, + fl4.saddr, fl4.daddr, + iph->tos, + ip4_dst_hoplimit(&rt->dst), + 0, + htons(GTP0_PORT), htons(GTP0_PORT), + !net_eq(sock_net(gtp->sk1u), + dev_net(gtp->dev)), + false); + return 0; +} + /* 1 means pass up to the stack, -1 means drop and 0 means decapsulated. */ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) { @@ -233,6 +335,13 @@ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) if ((gtp0->flags >> 5) != GTP_V0) return 1; + /* If the sockets were created in kernel, it means that + * there is no daemon running in userspace which would + * handle echo request. + */ + if (gtp0->type == GTP_ECHO_REQ && gtp->sk_created) + return gtp0_send_echo_resp(gtp, skb); + if (gtp0->type != GTP_TPDU) return 1; @@ -245,6 +354,75 @@ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) return gtp_rx(pctx, skb, hdrlen, gtp->role); } +static int gtp1u_send_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) +{ + struct gtp1_header_long *gtp1u; + struct gtp1u_packet *gtp_pkt; + struct rtable *rt; + struct flowi4 fl4; + struct iphdr *iph; + + gtp1u = (struct gtp1_header_long *)(skb->data + sizeof(struct udphdr)); + + /* 3GPP TS 29.281 5.1 - For the Echo Request, Echo Response, + * Error Indication and Supported Extension Headers Notification + * messages, the S flag shall be set to 1 and TEID shall be set to 0. + */ + if (!(gtp1u->flags & GTP1_F_SEQ) || gtp1u->tid) + return -1; + + /* pull GTP and UDP headers */ + skb_pull_data(skb, + sizeof(struct gtp1_header_long) + sizeof(struct udphdr)); + + gtp_pkt = skb_push(skb, sizeof(struct gtp1u_packet)); + memset(gtp_pkt, 0, sizeof(struct gtp1u_packet)); + + /* S flag must be set to 1 */ + gtp_pkt->gtp1u_h.flags = 0x32; + gtp_pkt->gtp1u_h.type = GTP_ECHO_RSP; + /* seq, npdu and next should be counted to the length of the GTP packet + * that's why szie of gtp1_header should be subtracted, + * not why szie of gtp1_header_long. + */ + gtp_pkt->gtp1u_h.length = + htons(sizeof(struct gtp1u_packet) - sizeof(struct gtp1_header)); + /* 3GPP TS 29.281 5.1 - TEID has to be set to 0 */ + gtp_pkt->gtp1u_h.tid = 0; + + /* 3GPP TS 29.281 7.7.2 - The Restart Counter value in the + * Recovery information element shall not be used, i.e. it shall + * be set to zero by the sender and shall be ignored by the receiver. + * The Recovery information element is mandatory due to backwards + * compatibility reasons. + */ + gtp_pkt->ie.tag = GTPIE_RECOVERY; + gtp_pkt->ie.val = 0; + + iph = ip_hdr(skb); + + /* find route to the sender, + * src address becomes dst address and vice versa. + */ + rt = ip4_route_output_gtp(&fl4, gtp->sk1u, iph->saddr, iph->daddr); + if (IS_ERR(rt)) { + netdev_dbg(gtp->dev, "no route for echo response from %pI4\n", + &iph->saddr); + return -1; + } + + udp_tunnel_xmit_skb(rt, gtp->sk1u, skb, + fl4.saddr, fl4.daddr, + iph->tos, + ip4_dst_hoplimit(&rt->dst), + 0, + htons(GTP1U_PORT), htons(GTP1U_PORT), + !net_eq(sock_net(gtp->sk1u), + dev_net(gtp->dev)), + false); + return 0; +} + static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) { unsigned int hdrlen = sizeof(struct udphdr) + @@ -260,6 +438,13 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) if ((gtp1->flags >> 5) != GTP_V1) return 1; + /* If the sockets were created in kernel, it means that + * there is no daemon running in userspace which would + * handle echo request. + */ + if (gtp1->type == GTP_ECHO_REQ && gtp->sk_created) + return gtp1u_send_echo_resp(gtp, skb); + if (gtp1->type != GTP_TPDU) return 1; @@ -398,20 +583,6 @@ static void gtp_dev_uninit(struct net_device *dev) free_percpu(dev->tstats); } -static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4, - const struct sock *sk, - __be32 daddr) -{ - memset(fl4, 0, sizeof(*fl4)); - fl4->flowi4_oif = sk->sk_bound_dev_if; - fl4->daddr = daddr; - fl4->saddr = inet_sk(sk)->inet_saddr; - fl4->flowi4_tos = RT_CONN_FLAGS(sk); - fl4->flowi4_proto = sk->sk_protocol; - - return ip_route_output_key(sock_net(sk), fl4); -} - static inline void gtp0_push_header(struct sk_buff *skb, struct pdp_ctx *pctx) { int payload_len = skb->len; @@ -517,7 +688,8 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, } netdev_dbg(dev, "found PDP context %p\n", pctx); - rt = ip4_route_output_gtp(&fl4, pctx->sk, pctx->peer_addr_ip4.s_addr); + rt = ip4_route_output_gtp(&fl4, pctx->sk, pctx->peer_addr_ip4.s_addr, + inet_sk(pctx->sk)->inet_saddr); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to SSGN %pI4\n", &pctx->peer_addr_ip4.s_addr); @@ -746,6 +918,11 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, } gtp->role = role; + if (!data[IFLA_GTP_RESTART_COUNT]) + gtp->restart_count = 0; + else + gtp->restart_count = nla_get_u8(data[IFLA_GTP_RESTART_COUNT]); + gtp->net = src_net; err = gtp_hashtable_new(gtp, hashsize); @@ -801,6 +978,7 @@ static const struct nla_policy gtp_policy[IFLA_GTP_MAX + 1] = { [IFLA_GTP_PDP_HASHSIZE] = { .type = NLA_U32 }, [IFLA_GTP_ROLE] = { .type = NLA_U32 }, [IFLA_GTP_CREATE_SOCKETS] = { .type = NLA_U8 }, + [IFLA_GTP_RESTART_COUNT] = { .type = NLA_U8 }, }; static int gtp_validate(struct nlattr *tb[], struct nlattr *data[], @@ -815,7 +993,8 @@ static int gtp_validate(struct nlattr *tb[], struct nlattr *data[], static size_t gtp_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_GTP_PDP_HASHSIZE */ - nla_total_size(sizeof(__u32)); /* IFLA_GTP_ROLE */ + nla_total_size(sizeof(__u32)) + /* IFLA_GTP_ROLE */ + nla_total_size(sizeof(__u8)); /* IFLA_GTP_RESTART_COUNT */ } static int gtp_fill_info(struct sk_buff *skb, const struct net_device *dev) @@ -826,6 +1005,8 @@ static int gtp_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; if (nla_put_u32(skb, IFLA_GTP_ROLE, gtp->role)) goto nla_put_failure; + if (nla_put_u8(skb, IFLA_GTP_RESTART_COUNT, gtp->restart_count)) + goto nla_put_failure; return 0; diff --git a/include/net/gtp.h b/include/net/gtp.h index 0e16ebb2a82d..0e12c37f2958 100644 --- a/include/net/gtp.h +++ b/include/net/gtp.h @@ -7,8 +7,13 @@ #define GTP0_PORT 3386 #define GTP1U_PORT 2152 +/* GTP messages types */ +#define GTP_ECHO_REQ 1 /* Echo Request */ +#define GTP_ECHO_RSP 2 /* Echo Response */ #define GTP_TPDU 255 +#define GTPIE_RECOVERY 14 + struct gtp0_header { /* According to GSM TS 09.60. */ __u8 flags; __u8 type; @@ -27,6 +32,32 @@ struct gtp1_header { /* According to 3GPP TS 29.060. */ __be32 tid; } __attribute__ ((packed)); +struct gtp1_header_long { /* According to 3GPP TS 29.060. */ + __u8 flags; + __u8 type; + __be16 length; + __be32 tid; + __be16 seq; + __u8 npdu; + __u8 next; +} __packed; + +/* GTP Information Element */ +struct gtp_ie { + __u8 tag; + __u8 val; +} __packed; + +struct gtp0_packet { + struct gtp0_header gtp0_h; + struct gtp_ie ie; +} __packed; + +struct gtp1u_packet { + struct gtp1_header_long gtp1u_h; + struct gtp_ie ie; +} __packed; + #define GTP1_F_NPDU 0x01 #define GTP1_F_SEQ 0x02 #define GTP1_F_EXTHDR 0x04 diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ebd2aa3ef809..bd24c7dc10a2 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -888,6 +888,7 @@ enum { IFLA_GTP_PDP_HASHSIZE, IFLA_GTP_ROLE, IFLA_GTP_CREATE_SOCKETS, + IFLA_GTP_RESTART_COUNT, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) -- cgit v1.2.3 From d33bd757d362699cfce3c68b53cd12b947d196f4 Mon Sep 17 00:00:00 2001 From: Wojciech Drewek Date: Fri, 4 Mar 2022 17:40:44 +0100 Subject: gtp: Implement GTP echo request Adding GTP device through ip link creates the situation where GTP instance is not able to send GTP echo requests. Echo requests are used to check if GTP peer is still alive. With this patch, gtp_genl_ops are extended by new cmd (GTP_CMD_ECHOREQ) which allows to send echo request in the given version of GTP protocol (v0 or v1), from the given ms address to he given peer. TID is not inclued because in all path management messages it should be equal to 0. When GTP echo response is detected, multicast message is send to everyone in the gtp_genl_family. Message contains GTP version, ms address and peer address. Suggested-by: Harald Welte Signed-off-by: Wojciech Drewek Reviewed-by: Harald Welte Signed-off-by: Tony Nguyen --- drivers/net/gtp.c | 305 +++++++++++++++++++++++++++++++++++++++++------ include/uapi/linux/gtp.h | 1 + 2 files changed, 269 insertions(+), 37 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index bf434d79f868..756714d4ad92 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -79,6 +79,12 @@ struct gtp_dev { u8 restart_count; }; +struct echo_info { + struct in_addr ms_addr_ip4; + struct in_addr peer_addr_ip4; + u8 gtp_version; +}; + static unsigned int gtp_net_id __read_mostly; struct gtp_net { @@ -87,6 +93,16 @@ struct gtp_net { static u32 gtp_h_initval; +static struct genl_family gtp_genl_family; + +enum gtp_multicast_groups { + GTP_GENL_MCGRP, +}; + +static const struct genl_multicast_group gtp_genl_mcgrps[] = { + [GTP_GENL_MCGRP] = { .name = GTP_GENL_MCGRP_NAME }, +}; + static void pdp_context_delete(struct pdp_ctx *pctx); static inline u32 gtp0_hashfn(u64 tid) @@ -243,12 +259,38 @@ static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4, * by the receiver * Returns true if the echo req was correct, false otherwise. */ -static bool gtp0_validate_echo_req(struct gtp0_header *gtp0) +static bool gtp0_validate_echo_hdr(struct gtp0_header *gtp0) { return !(gtp0->tid || (gtp0->flags ^ 0x1e) || gtp0->number != 0xff || gtp0->flow); } +/* msg_type has to be GTP_ECHO_REQ or GTP_ECHO_RSP */ +static void gtp0_build_echo_msg(struct gtp0_header *hdr, __u8 msg_type) +{ + int len_pkt, len_hdr; + + hdr->flags = 0x1e; /* v0, GTP-non-prime. */ + hdr->type = msg_type; + /* GSM TS 09.60. 7.3 In all Path Management Flow Label and TID + * are not used and shall be set to 0. + */ + hdr->flow = 0; + hdr->tid = 0; + hdr->number = 0xff; + hdr->spare[0] = 0xff; + hdr->spare[1] = 0xff; + hdr->spare[2] = 0xff; + + len_pkt = sizeof(struct gtp0_packet); + len_hdr = sizeof(struct gtp0_header); + + if (msg_type == GTP_ECHO_RSP) + hdr->length = htons(len_pkt - len_hdr); + else + hdr->length = 0; +} + static int gtp0_send_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) { struct gtp0_packet *gtp_pkt; @@ -260,7 +302,7 @@ static int gtp0_send_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) gtp0 = (struct gtp0_header *)(skb->data + sizeof(struct udphdr)); - if (!gtp0_validate_echo_req(gtp0)) + if (!gtp0_validate_echo_hdr(gtp0)) return -1; seq = gtp0->seq; @@ -271,10 +313,7 @@ static int gtp0_send_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) gtp_pkt = skb_push(skb, sizeof(struct gtp0_packet)); memset(gtp_pkt, 0, sizeof(struct gtp0_packet)); - gtp_pkt->gtp0_h.flags = 0x1e; /* v0, GTP-non-prime. */ - gtp_pkt->gtp0_h.type = GTP_ECHO_RSP; - gtp_pkt->gtp0_h.length = - htons(sizeof(struct gtp0_packet) - sizeof(struct gtp0_header)); + gtp0_build_echo_msg(>p_pkt->gtp0_h, GTP_ECHO_RSP); /* GSM TS 09.60. 7.3 The Sequence Number in a signalling response * message shall be copied from the signalling request message @@ -282,16 +321,6 @@ static int gtp0_send_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) */ gtp_pkt->gtp0_h.seq = seq; - /* GSM TS 09.60. 7.3 In all Path Management Flow Label and TID - * are not used and shall be set to 0. - */ - gtp_pkt->gtp0_h.flow = 0; - gtp_pkt->gtp0_h.tid = 0; - gtp_pkt->gtp0_h.number = 0xff; - gtp_pkt->gtp0_h.spare[0] = 0xff; - gtp_pkt->gtp0_h.spare[1] = 0xff; - gtp_pkt->gtp0_h.spare[2] = 0xff; - gtp_pkt->ie.tag = GTPIE_RECOVERY; gtp_pkt->ie.val = gtp->restart_count; @@ -319,6 +348,61 @@ static int gtp0_send_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) return 0; } +static int gtp_genl_fill_echo(struct sk_buff *skb, u32 snd_portid, u32 snd_seq, + int flags, u32 type, struct echo_info echo) +{ + void *genlh; + + genlh = genlmsg_put(skb, snd_portid, snd_seq, >p_genl_family, flags, + type); + if (!genlh) + goto failure; + + if (nla_put_u32(skb, GTPA_VERSION, echo.gtp_version) || + nla_put_be32(skb, GTPA_PEER_ADDRESS, echo.peer_addr_ip4.s_addr) || + nla_put_be32(skb, GTPA_MS_ADDRESS, echo.ms_addr_ip4.s_addr)) + goto failure; + + genlmsg_end(skb, genlh); + return 0; + +failure: + genlmsg_cancel(skb, genlh); + return -EMSGSIZE; +} + +static int gtp0_handle_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) +{ + struct gtp0_header *gtp0; + struct echo_info echo; + struct sk_buff *msg; + struct iphdr *iph; + int ret; + + gtp0 = (struct gtp0_header *)(skb->data + sizeof(struct udphdr)); + + if (!gtp0_validate_echo_hdr(gtp0)) + return -1; + + iph = ip_hdr(skb); + echo.ms_addr_ip4.s_addr = iph->daddr; + echo.peer_addr_ip4.s_addr = iph->saddr; + echo.gtp_version = GTP_V0; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!msg) + return -ENOMEM; + + ret = gtp_genl_fill_echo(msg, 0, 0, 0, GTP_CMD_ECHOREQ, echo); + if (ret < 0) { + nlmsg_free(msg); + return ret; + } + + return genlmsg_multicast_netns(>p_genl_family, dev_net(gtp->dev), + msg, 0, GTP_GENL_MCGRP, GFP_ATOMIC); +} + /* 1 means pass up to the stack, -1 means drop and 0 means decapsulated. */ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) { @@ -342,6 +426,9 @@ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) if (gtp0->type == GTP_ECHO_REQ && gtp->sk_created) return gtp0_send_echo_resp(gtp, skb); + if (gtp0->type == GTP_ECHO_RSP && gtp->sk_created) + return gtp0_handle_echo_resp(gtp, skb); + if (gtp0->type != GTP_TPDU) return 1; @@ -354,6 +441,36 @@ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) return gtp_rx(pctx, skb, hdrlen, gtp->role); } +/* msg_type has to be GTP_ECHO_REQ or GTP_ECHO_RSP */ +static void gtp1u_build_echo_msg(struct gtp1_header_long *hdr, __u8 msg_type) +{ + int len_pkt, len_hdr; + + /* S flag must be set to 1 */ + hdr->flags = 0x32; /* v1, GTP-non-prime. */ + hdr->type = msg_type; + /* 3GPP TS 29.281 5.1 - TEID has to be set to 0 */ + hdr->tid = 0; + + /* seq, npdu and next should be counted to the length of the GTP packet + * that's why szie of gtp1_header should be subtracted, + * not size of gtp1_header_long. + */ + + len_hdr = sizeof(struct gtp1_header); + + if (msg_type == GTP_ECHO_RSP) { + len_pkt = sizeof(struct gtp1u_packet); + hdr->length = htons(len_pkt - len_hdr); + } else { + /* GTP_ECHO_REQ does not carry GTP Information Element, + * the why gtp1_header_long is used here. + */ + len_pkt = sizeof(struct gtp1_header_long); + hdr->length = htons(len_pkt - len_hdr); + } +} + static int gtp1u_send_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) { struct gtp1_header_long *gtp1u; @@ -378,17 +495,7 @@ static int gtp1u_send_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) gtp_pkt = skb_push(skb, sizeof(struct gtp1u_packet)); memset(gtp_pkt, 0, sizeof(struct gtp1u_packet)); - /* S flag must be set to 1 */ - gtp_pkt->gtp1u_h.flags = 0x32; - gtp_pkt->gtp1u_h.type = GTP_ECHO_RSP; - /* seq, npdu and next should be counted to the length of the GTP packet - * that's why szie of gtp1_header should be subtracted, - * not why szie of gtp1_header_long. - */ - gtp_pkt->gtp1u_h.length = - htons(sizeof(struct gtp1u_packet) - sizeof(struct gtp1_header)); - /* 3GPP TS 29.281 5.1 - TEID has to be set to 0 */ - gtp_pkt->gtp1u_h.tid = 0; + gtp1u_build_echo_msg(>p_pkt->gtp1u_h, GTP_ECHO_RSP); /* 3GPP TS 29.281 7.7.2 - The Restart Counter value in the * Recovery information element shall not be used, i.e. it shall @@ -423,6 +530,42 @@ static int gtp1u_send_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) return 0; } +static int gtp1u_handle_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) +{ + struct gtp1_header_long *gtp1u; + struct echo_info echo; + struct sk_buff *msg; + struct iphdr *iph; + int ret; + + gtp1u = (struct gtp1_header_long *)(skb->data + sizeof(struct udphdr)); + + /* 3GPP TS 29.281 5.1 - For the Echo Request, Echo Response, + * Error Indication and Supported Extension Headers Notification + * messages, the S flag shall be set to 1 and TEID shall be set to 0. + */ + if (!(gtp1u->flags & GTP1_F_SEQ) || gtp1u->tid) + return -1; + + iph = ip_hdr(skb); + echo.ms_addr_ip4.s_addr = iph->daddr; + echo.peer_addr_ip4.s_addr = iph->saddr; + echo.gtp_version = GTP_V1; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!msg) + return -ENOMEM; + + ret = gtp_genl_fill_echo(msg, 0, 0, 0, GTP_CMD_ECHOREQ, echo); + if (ret < 0) { + nlmsg_free(msg); + return ret; + } + + return genlmsg_multicast_netns(>p_genl_family, dev_net(gtp->dev), + msg, 0, GTP_GENL_MCGRP, GFP_ATOMIC); +} + static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) { unsigned int hdrlen = sizeof(struct udphdr) + @@ -445,6 +588,9 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) if (gtp1->type == GTP_ECHO_REQ && gtp->sk_created) return gtp1u_send_echo_resp(gtp, skb); + if (gtp1->type == GTP_ECHO_RSP && gtp->sk_created) + return gtp1u_handle_echo_resp(gtp, skb); + if (gtp1->type != GTP_TPDU) return 1; @@ -1431,16 +1577,6 @@ out_unlock: return err; } -static struct genl_family gtp_genl_family; - -enum gtp_multicast_groups { - GTP_GENL_MCGRP, -}; - -static const struct genl_multicast_group gtp_genl_mcgrps[] = { - [GTP_GENL_MCGRP] = { .name = GTP_GENL_MCGRP_NAME }, -}; - static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq, int flags, u32 type, struct pdp_ctx *pctx) { @@ -1584,6 +1720,95 @@ out: return skb->len; } +static int gtp_genl_send_echo_req(struct sk_buff *skb, struct genl_info *info) +{ + struct sk_buff *skb_to_send; + __be32 src_ip, dst_ip; + unsigned int version; + struct gtp_dev *gtp; + struct flowi4 fl4; + struct rtable *rt; + struct sock *sk; + __be16 port; + int len; + + if (!info->attrs[GTPA_VERSION] || + !info->attrs[GTPA_LINK] || + !info->attrs[GTPA_PEER_ADDRESS] || + !info->attrs[GTPA_MS_ADDRESS]) + return -EINVAL; + + version = nla_get_u32(info->attrs[GTPA_VERSION]); + dst_ip = nla_get_be32(info->attrs[GTPA_PEER_ADDRESS]); + src_ip = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]); + + gtp = gtp_find_dev(sock_net(skb->sk), info->attrs); + if (!gtp) + return -ENODEV; + + if (!gtp->sk_created) + return -EOPNOTSUPP; + if (!(gtp->dev->flags & IFF_UP)) + return -ENETDOWN; + + if (version == GTP_V0) { + struct gtp0_header *gtp0_h; + + len = LL_RESERVED_SPACE(gtp->dev) + sizeof(struct gtp0_header) + + sizeof(struct iphdr) + sizeof(struct udphdr); + + skb_to_send = netdev_alloc_skb_ip_align(gtp->dev, len); + if (!skb_to_send) + return -ENOMEM; + + sk = gtp->sk0; + port = htons(GTP0_PORT); + + gtp0_h = skb_push(skb_to_send, sizeof(struct gtp0_header)); + memset(gtp0_h, 0, sizeof(struct gtp0_header)); + gtp0_build_echo_msg(gtp0_h, GTP_ECHO_REQ); + } else if (version == GTP_V1) { + struct gtp1_header_long *gtp1u_h; + + len = LL_RESERVED_SPACE(gtp->dev) + + sizeof(struct gtp1_header_long) + + sizeof(struct iphdr) + sizeof(struct udphdr); + + skb_to_send = netdev_alloc_skb_ip_align(gtp->dev, len); + if (!skb_to_send) + return -ENOMEM; + + sk = gtp->sk1u; + port = htons(GTP1U_PORT); + + gtp1u_h = skb_push(skb_to_send, + sizeof(struct gtp1_header_long)); + memset(gtp1u_h, 0, sizeof(struct gtp1_header_long)); + gtp1u_build_echo_msg(gtp1u_h, GTP_ECHO_REQ); + } else { + return -ENODEV; + } + + rt = ip4_route_output_gtp(&fl4, sk, dst_ip, src_ip); + if (IS_ERR(rt)) { + netdev_dbg(gtp->dev, "no route for echo request to %pI4\n", + &dst_ip); + kfree_skb(skb_to_send); + return -ENODEV; + } + + udp_tunnel_xmit_skb(rt, sk, skb_to_send, + fl4.saddr, fl4.daddr, + fl4.flowi4_tos, + ip4_dst_hoplimit(&rt->dst), + 0, + port, port, + !net_eq(sock_net(sk), + dev_net(gtp->dev)), + false); + return 0; +} + static const struct nla_policy gtp_genl_policy[GTPA_MAX + 1] = { [GTPA_LINK] = { .type = NLA_U32, }, [GTPA_VERSION] = { .type = NLA_U32, }, @@ -1616,6 +1841,12 @@ static const struct genl_small_ops gtp_genl_ops[] = { .dumpit = gtp_genl_dump_pdp, .flags = GENL_ADMIN_PERM, }, + { + .cmd = GTP_CMD_ECHOREQ, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = gtp_genl_send_echo_req, + .flags = GENL_ADMIN_PERM, + }, }; static struct genl_family gtp_genl_family __ro_after_init = { diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index 79f9191bbb24..2f61298a7b77 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -8,6 +8,7 @@ enum gtp_genl_cmds { GTP_CMD_NEWPDP, GTP_CMD_DELPDP, GTP_CMD_GETPDP, + GTP_CMD_ECHOREQ, GTP_CMD_MAX, }; -- cgit v1.2.3 From e3acda7ade0a36c5cbebc2b54d30b7f08a4ba29b Mon Sep 17 00:00:00 2001 From: Wojciech Drewek Date: Fri, 4 Mar 2022 17:40:45 +0100 Subject: net/sched: Allow flower to match on GTP options Options are as follows: PDU_TYPE:QFI and they refernce to the fields from the PDU Session Protocol. PDU Session data is conveyed in GTP-U Extension Header. GTP-U Extension Header is described in 3GPP TS 29.281. PDU Session Protocol is described in 3GPP TS 38.415. PDU_TYPE - indicates the type of the PDU Session Information (4 bits) QFI - QoS Flow Identifier (6 bits) # ip link add gtp_dev type gtp role sgsn # tc qdisc add dev gtp_dev ingress # tc filter add dev gtp_dev protocol ip parent ffff: \ flower \ enc_key_id 11 \ gtp_opts 1:8/ff:ff \ action mirred egress redirect dev eth0 Signed-off-by: Wojciech Drewek Signed-off-by: Tony Nguyen --- include/net/gtp.h | 5 ++ include/uapi/linux/if_tunnel.h | 4 +- include/uapi/linux/pkt_cls.h | 15 ++++++ net/sched/cls_flower.c | 116 +++++++++++++++++++++++++++++++++++++++++ 4 files changed, 139 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/gtp.h b/include/net/gtp.h index 0e12c37f2958..23c2aaae8a42 100644 --- a/include/net/gtp.h +++ b/include/net/gtp.h @@ -58,6 +58,11 @@ struct gtp1u_packet { struct gtp_ie ie; } __packed; +struct gtp_pdu_session_info { /* According to 3GPP TS 38.415. */ + u8 pdu_type; + u8 qfi; +}; + #define GTP1_F_NPDU 0x01 #define GTP1_F_SEQ 0x02 #define GTP1_F_EXTHDR 0x04 diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 7d9105533c7b..102119628ff5 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -176,8 +176,10 @@ enum { #define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000) #define TUNNEL_NOCACHE __cpu_to_be16(0x2000) #define TUNNEL_ERSPAN_OPT __cpu_to_be16(0x4000) +#define TUNNEL_GTP_OPT __cpu_to_be16(0x8000) #define TUNNEL_OPTIONS_PRESENT \ - (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT) + (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT | \ + TUNNEL_GTP_OPT) #endif /* _UAPI_IF_TUNNEL_H_ */ diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index ee38b35c3f57..404f97fb239c 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -616,6 +616,10 @@ enum { * TCA_FLOWER_KEY_ENC_OPT_ERSPAN_ * attributes */ + TCA_FLOWER_KEY_ENC_OPTS_GTP, /* Nested + * TCA_FLOWER_KEY_ENC_OPT_GTP_ + * attributes + */ __TCA_FLOWER_KEY_ENC_OPTS_MAX, }; @@ -654,6 +658,17 @@ enum { #define TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX \ (__TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX - 1) +enum { + TCA_FLOWER_KEY_ENC_OPT_GTP_UNSPEC, + TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE, /* u8 */ + TCA_FLOWER_KEY_ENC_OPT_GTP_QFI, /* u8 */ + + __TCA_FLOWER_KEY_ENC_OPT_GTP_MAX, +}; + +#define TCA_FLOWER_KEY_ENC_OPT_GTP_MAX \ + (__TCA_FLOWER_KEY_ENC_OPT_GTP_MAX - 1) + enum { TCA_FLOWER_KEY_MPLS_OPTS_UNSPEC, TCA_FLOWER_KEY_MPLS_OPTS_LSE, diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 1a9b1f140f9e..c80fc49c0da1 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -723,6 +724,7 @@ enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = { [TCA_FLOWER_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED }, [TCA_FLOWER_KEY_ENC_OPTS_VXLAN] = { .type = NLA_NESTED }, [TCA_FLOWER_KEY_ENC_OPTS_ERSPAN] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_OPTS_GTP] = { .type = NLA_NESTED }, }; static const struct nla_policy @@ -746,6 +748,12 @@ erspan_opt_policy[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX + 1] = { [TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID] = { .type = NLA_U8 }, }; +static const struct nla_policy +gtp_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GTP_MAX + 1] = { + [TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_OPT_GTP_QFI] = { .type = NLA_U8 }, +}; + static const struct nla_policy mpls_stack_entry_policy[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1] = { [TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH] = { .type = NLA_U8 }, @@ -1262,6 +1270,49 @@ static int fl_set_erspan_opt(const struct nlattr *nla, struct fl_flow_key *key, return sizeof(*md); } +static int fl_set_gtp_opt(const struct nlattr *nla, struct fl_flow_key *key, + int depth, int option_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_GTP_MAX + 1]; + struct gtp_pdu_session_info *sinfo; + u8 len = key->enc_opts.len; + int err; + + sinfo = (struct gtp_pdu_session_info *)&key->enc_opts.data[len]; + memset(sinfo, 0xff, option_len); + + if (!depth) + return sizeof(*sinfo); + + if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_GTP) { + NL_SET_ERR_MSG_MOD(extack, "Non-gtp option type for mask"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_GTP_MAX, nla, + gtp_opt_policy, extack); + if (err < 0) + return err; + + if (!option_len && + (!tb[TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE] || + !tb[TCA_FLOWER_KEY_ENC_OPT_GTP_QFI])) { + NL_SET_ERR_MSG_MOD(extack, + "Missing tunnel key gtp option pdu type or qfi"); + return -EINVAL; + } + + if (tb[TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE]) + sinfo->pdu_type = + nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE]); + + if (tb[TCA_FLOWER_KEY_ENC_OPT_GTP_QFI]) + sinfo->qfi = nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_GTP_QFI]); + + return sizeof(*sinfo); +} + static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask, struct netlink_ext_ack *extack) @@ -1386,6 +1437,38 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } break; + case TCA_FLOWER_KEY_ENC_OPTS_GTP: + if (key->enc_opts.dst_opt_type) { + NL_SET_ERR_MSG_MOD(extack, + "Duplicate type for gtp options"); + return -EINVAL; + } + option_len = 0; + key->enc_opts.dst_opt_type = TUNNEL_GTP_OPT; + option_len = fl_set_gtp_opt(nla_opt_key, key, + key_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + key->enc_opts.len += option_len; + /* At the same time we need to parse through the mask + * in order to verify exact and mask attribute lengths. + */ + mask->enc_opts.dst_opt_type = TUNNEL_GTP_OPT; + option_len = fl_set_gtp_opt(nla_opt_msk, mask, + msk_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + mask->enc_opts.len += option_len; + if (key->enc_opts.len != mask->enc_opts.len) { + NL_SET_ERR_MSG_MOD(extack, + "Key and mask miss aligned"); + return -EINVAL; + } + break; default: NL_SET_ERR_MSG(extack, "Unknown tunnel option type"); return -EINVAL; @@ -2761,6 +2844,34 @@ nla_put_failure: return -EMSGSIZE; } +static int fl_dump_key_gtp_opt(struct sk_buff *skb, + struct flow_dissector_key_enc_opts *enc_opts) + +{ + struct gtp_pdu_session_info *session_info; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_GTP); + if (!nest) + goto nla_put_failure; + + session_info = (struct gtp_pdu_session_info *)&enc_opts->data[0]; + + if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE, + session_info->pdu_type)) + goto nla_put_failure; + + if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_GTP_QFI, session_info->qfi)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + static int fl_dump_key_ct(struct sk_buff *skb, struct flow_dissector_key_ct *key, struct flow_dissector_key_ct *mask) @@ -2824,6 +2935,11 @@ static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type, if (err) goto nla_put_failure; break; + case TUNNEL_GTP_OPT: + err = fl_dump_key_gtp_opt(skb, enc_opts); + if (err) + goto nla_put_failure; + break; default: goto nla_put_failure; } -- cgit v1.2.3 From 435fe1c0c1f74b682dba85641406abf4337aade6 Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Wed, 16 Mar 2022 08:15:57 +0200 Subject: net: geneve: support IPv4/IPv6 as inner protocol This patch adds support for encapsulating IPv4/IPv6 within GENEVE. In order to use this, a new IFLA_GENEVE_INNER_PROTO_INHERIT flag needs to be provided at device creation. This property cannot be changed for the time being. In case IP traffic is received on a non-tun device the drop count is increased. Signed-off-by: Eyal Birger Link: https://lore.kernel.org/r/20220316061557.431872-1-eyal.birger@gmail.com Signed-off-by: Paolo Abeni --- drivers/net/geneve.c | 82 ++++++++++++++++++++++++++++++++++---------- include/uapi/linux/if_link.h | 1 + 2 files changed, 64 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index a895ff756093..8f30660224c5 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -56,6 +56,7 @@ struct geneve_config { bool use_udp6_rx_checksums; bool ttl_inherit; enum ifla_geneve_df df; + bool inner_proto_inherit; }; /* Pseudo network device */ @@ -251,17 +252,24 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, } } - skb_reset_mac_header(skb); - skb->protocol = eth_type_trans(skb, geneve->dev); - skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); - if (tun_dst) skb_dst_set(skb, &tun_dst->dst); - /* Ignore packet loops (and multicast echo) */ - if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr)) { - geneve->dev->stats.rx_errors++; - goto drop; + if (gnvh->proto_type == htons(ETH_P_TEB)) { + skb_reset_mac_header(skb); + skb->protocol = eth_type_trans(skb, geneve->dev); + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); + + /* Ignore packet loops (and multicast echo) */ + if (ether_addr_equal(eth_hdr(skb)->h_source, + geneve->dev->dev_addr)) { + geneve->dev->stats.rx_errors++; + goto drop; + } + } else { + skb_reset_mac_header(skb); + skb->dev = geneve->dev; + skb->pkt_type = PACKET_HOST; } oiph = skb_network_header(skb); @@ -345,6 +353,7 @@ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb) struct genevehdr *geneveh; struct geneve_dev *geneve; struct geneve_sock *gs; + __be16 inner_proto; int opts_len; /* Need UDP and Geneve header to be present */ @@ -356,7 +365,11 @@ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb) if (unlikely(geneveh->ver != GENEVE_VER)) goto drop; - if (unlikely(geneveh->proto_type != htons(ETH_P_TEB))) + inner_proto = geneveh->proto_type; + + if (unlikely((inner_proto != htons(ETH_P_TEB) && + inner_proto != htons(ETH_P_IP) && + inner_proto != htons(ETH_P_IPV6)))) goto drop; gs = rcu_dereference_sk_user_data(sk); @@ -367,9 +380,14 @@ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb) if (!geneve) goto drop; + if (unlikely((!geneve->cfg.inner_proto_inherit && + inner_proto != htons(ETH_P_TEB)))) { + geneve->dev->stats.rx_dropped++; + goto drop; + } + opts_len = geneveh->opt_len * 4; - if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len, - htons(ETH_P_TEB), + if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len, inner_proto, !net_eq(geneve->net, dev_net(geneve->dev)))) { geneve->dev->stats.rx_dropped++; goto drop; @@ -717,7 +735,8 @@ static int geneve_stop(struct net_device *dev) } static void geneve_build_header(struct genevehdr *geneveh, - const struct ip_tunnel_info *info) + const struct ip_tunnel_info *info, + __be16 inner_proto) { geneveh->ver = GENEVE_VER; geneveh->opt_len = info->options_len / 4; @@ -725,7 +744,7 @@ static void geneve_build_header(struct genevehdr *geneveh, geneveh->critical = !!(info->key.tun_flags & TUNNEL_CRIT_OPT); geneveh->rsvd1 = 0; tunnel_id_to_vni(info->key.tun_id, geneveh->vni); - geneveh->proto_type = htons(ETH_P_TEB); + geneveh->proto_type = inner_proto; geneveh->rsvd2 = 0; if (info->key.tun_flags & TUNNEL_GENEVE_OPT) @@ -734,10 +753,12 @@ static void geneve_build_header(struct genevehdr *geneveh, static int geneve_build_skb(struct dst_entry *dst, struct sk_buff *skb, const struct ip_tunnel_info *info, - bool xnet, int ip_hdr_len) + bool xnet, int ip_hdr_len, + bool inner_proto_inherit) { bool udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); struct genevehdr *gnvh; + __be16 inner_proto; int min_headroom; int err; @@ -755,8 +776,9 @@ static int geneve_build_skb(struct dst_entry *dst, struct sk_buff *skb, goto free_dst; gnvh = __skb_push(skb, sizeof(*gnvh) + info->options_len); - geneve_build_header(gnvh, info); - skb_set_inner_protocol(skb, htons(ETH_P_TEB)); + inner_proto = inner_proto_inherit ? skb->protocol : htons(ETH_P_TEB); + geneve_build_header(gnvh, info, inner_proto); + skb_set_inner_protocol(skb, inner_proto); return 0; free_dst: @@ -959,7 +981,8 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, } } - err = geneve_build_skb(&rt->dst, skb, info, xnet, sizeof(struct iphdr)); + err = geneve_build_skb(&rt->dst, skb, info, xnet, sizeof(struct iphdr), + geneve->cfg.inner_proto_inherit); if (unlikely(err)) return err; @@ -1038,7 +1061,8 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, ttl = key->ttl; ttl = ttl ? : ip6_dst_hoplimit(dst); } - err = geneve_build_skb(dst, skb, info, xnet, sizeof(struct ipv6hdr)); + err = geneve_build_skb(dst, skb, info, xnet, sizeof(struct ipv6hdr), + geneve->cfg.inner_proto_inherit); if (unlikely(err)) return err; @@ -1388,6 +1412,14 @@ static int geneve_configure(struct net *net, struct net_device *dev, dst_cache_reset(&geneve->cfg.info.dst_cache); memcpy(&geneve->cfg, cfg, sizeof(*cfg)); + if (geneve->cfg.inner_proto_inherit) { + dev->header_ops = NULL; + dev->type = ARPHRD_NONE; + dev->hard_header_len = 0; + dev->addr_len = 0; + dev->flags = IFF_NOARP; + } + err = register_netdevice(dev); if (err) return err; @@ -1561,10 +1593,18 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], #endif } + if (data[IFLA_GENEVE_INNER_PROTO_INHERIT]) { + if (changelink) { + attrtype = IFLA_GENEVE_INNER_PROTO_INHERIT; + goto change_notsup; + } + cfg->inner_proto_inherit = true; + } + return 0; change_notsup: NL_SET_ERR_MSG_ATTR(extack, data[attrtype], - "Changing VNI, Port, endpoint IP address family, external, and UDP checksum attributes are not supported"); + "Changing VNI, Port, endpoint IP address family, external, inner_proto_inherit, and UDP checksum attributes are not supported"); return -EOPNOTSUPP; } @@ -1799,6 +1839,10 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) if (nla_put_u8(skb, IFLA_GENEVE_TTL_INHERIT, ttl_inherit)) goto nla_put_failure; + if (geneve->cfg.inner_proto_inherit && + nla_put_flag(skb, IFLA_GENEVE_INNER_PROTO_INHERIT)) + goto nla_put_failure; + return 0; nla_put_failure: diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index bd24c7dc10a2..cc284c048e69 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -842,6 +842,7 @@ enum { IFLA_GENEVE_LABEL, IFLA_GENEVE_TTL_INHERIT, IFLA_GENEVE_DF, + IFLA_GENEVE_INNER_PROTO_INHERIT, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) -- cgit v1.2.3 From ec7328b59176227216c461601c6bd0e922232a9b Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 16 Mar 2022 16:08:43 +0100 Subject: net: bridge: mst: Multiple Spanning Tree (MST) mode Allow the user to switch from the current per-VLAN STP mode to an MST mode. Up to this point, per-VLAN STP states where always isolated from each other. This is in contrast to the MSTP standard (802.1Q-2018, Clause 13.5), where VLANs are grouped into MST instances (MSTIs), and the state is managed on a per-MSTI level, rather that at the per-VLAN level. Perhaps due to the prevalence of the standard, many switching ASICs are built after the same model. Therefore, add a corresponding MST mode to the bridge, which we can later add offloading support for in a straight-forward way. For now, all VLANs are fixed to MSTI 0, also called the Common Spanning Tree (CST). That is, all VLANs will follow the port-global state. Upcoming changes will make this actually useful by allowing VLANs to be mapped to arbitrary MSTIs and allow individual MSTI states to be changed. Signed-off-by: Tobias Waldekranz Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bridge.h | 1 + net/bridge/Makefile | 2 +- net/bridge/br.c | 5 +++ net/bridge/br_input.c | 17 ++++++++- net/bridge/br_mst.c | 87 ++++++++++++++++++++++++++++++++++++++++++ net/bridge/br_private.h | 37 ++++++++++++++++++ net/bridge/br_stp.c | 6 +++ net/bridge/br_vlan.c | 20 +++++++++- net/bridge/br_vlan_options.c | 5 +++ 9 files changed, 176 insertions(+), 4 deletions(-) create mode 100644 net/bridge/br_mst.c (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 2711c3522010..30a242195ced 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -759,6 +759,7 @@ struct br_mcast_stats { enum br_boolopt_id { BR_BOOLOPT_NO_LL_LEARN, BR_BOOLOPT_MCAST_VLAN_SNOOPING, + BR_BOOLOPT_MST_ENABLE, BR_BOOLOPT_MAX }; diff --git a/net/bridge/Makefile b/net/bridge/Makefile index 7fb9a021873b..24bd1c0a9a5a 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -20,7 +20,7 @@ obj-$(CONFIG_BRIDGE_NETFILTER) += br_netfilter.o bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o br_multicast_eht.o -bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o br_vlan_tunnel.o br_vlan_options.o +bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o br_vlan_tunnel.o br_vlan_options.o br_mst.o bridge-$(CONFIG_NET_SWITCHDEV) += br_switchdev.o diff --git a/net/bridge/br.c b/net/bridge/br.c index b1dea3febeea..96e91d69a9a8 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -265,6 +265,9 @@ int br_boolopt_toggle(struct net_bridge *br, enum br_boolopt_id opt, bool on, case BR_BOOLOPT_MCAST_VLAN_SNOOPING: err = br_multicast_toggle_vlan_snooping(br, on, extack); break; + case BR_BOOLOPT_MST_ENABLE: + err = br_mst_set_enabled(br, on, extack); + break; default: /* shouldn't be called with unsupported options */ WARN_ON(1); @@ -281,6 +284,8 @@ int br_boolopt_get(const struct net_bridge *br, enum br_boolopt_id opt) return br_opt_get(br, BROPT_NO_LL_LEARN); case BR_BOOLOPT_MCAST_VLAN_SNOOPING: return br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED); + case BR_BOOLOPT_MST_ENABLE: + return br_opt_get(br, BROPT_MST_ENABLED); default: /* shouldn't be called with unsupported options */ WARN_ON(1); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index e0c13fcc50ed..196417859c4a 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -78,13 +78,22 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb u16 vid = 0; u8 state; - if (!p || p->state == BR_STATE_DISABLED) + if (!p) goto drop; br = p->br; + + if (br_mst_is_enabled(br)) { + state = BR_STATE_FORWARDING; + } else { + if (p->state == BR_STATE_DISABLED) + goto drop; + + state = p->state; + } + brmctx = &p->br->multicast_ctx; pmctx = &p->multicast_ctx; - state = p->state; if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid, &state, &vlan)) goto out; @@ -370,9 +379,13 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) return RX_HANDLER_PASS; forward: + if (br_mst_is_enabled(p->br)) + goto defer_stp_filtering; + switch (p->state) { case BR_STATE_FORWARDING: case BR_STATE_LEARNING: +defer_stp_filtering: if (ether_addr_equal(p->br->dev->dev_addr, dest)) skb->pkt_type = PACKET_HOST; diff --git a/net/bridge/br_mst.c b/net/bridge/br_mst.c new file mode 100644 index 000000000000..0f9f596f86bc --- /dev/null +++ b/net/bridge/br_mst.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Bridge Multiple Spanning Tree Support + * + * Authors: + * Tobias Waldekranz + */ + +#include + +#include "br_private.h" + +DEFINE_STATIC_KEY_FALSE(br_mst_used); + +static void br_mst_vlan_set_state(struct net_bridge_port *p, struct net_bridge_vlan *v, + u8 state) +{ + struct net_bridge_vlan_group *vg = nbp_vlan_group(p); + + if (v->state == state) + return; + + br_vlan_set_state(v, state); + + if (v->vid == vg->pvid) + br_vlan_set_pvid_state(vg, state); +} + +int br_mst_set_state(struct net_bridge_port *p, u16 msti, u8 state, + struct netlink_ext_ack *extack) +{ + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *v; + + vg = nbp_vlan_group(p); + if (!vg) + return 0; + + list_for_each_entry(v, &vg->vlan_list, vlist) { + if (v->brvlan->msti != msti) + continue; + + br_mst_vlan_set_state(p, v, state); + } + + return 0; +} + +void br_mst_vlan_init_state(struct net_bridge_vlan *v) +{ + /* VLANs always start out in MSTI 0 (CST) */ + v->msti = 0; + + if (br_vlan_is_master(v)) + v->state = BR_STATE_FORWARDING; + else + v->state = v->port->state; +} + +int br_mst_set_enabled(struct net_bridge *br, bool on, + struct netlink_ext_ack *extack) +{ + struct net_bridge_vlan_group *vg; + struct net_bridge_port *p; + + list_for_each_entry(p, &br->port_list, list) { + vg = nbp_vlan_group(p); + + if (!vg->num_vlans) + continue; + + NL_SET_ERR_MSG(extack, + "MST mode can't be changed while VLANs exist"); + return -EBUSY; + } + + if (br_opt_get(br, BROPT_MST_ENABLED) == on) + return 0; + + if (on) + static_branch_enable(&br_mst_used); + else + static_branch_disable(&br_mst_used); + + br_opt_toggle(br, BROPT_MST_ENABLED, on); + return 0; +} diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 48bc61ebc211..c2190c8841fb 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -178,6 +178,7 @@ enum { * @br_mcast_ctx: if MASTER flag set, this is the global vlan multicast context * @port_mcast_ctx: if MASTER flag unset, this is the per-port/vlan multicast * context + * @msti: if MASTER flag set, this holds the VLANs MST instance * @vlist: sorted list of VLAN entries * @rcu: used for entry destruction * @@ -210,6 +211,8 @@ struct net_bridge_vlan { struct net_bridge_mcast_port port_mcast_ctx; }; + u16 msti; + struct list_head vlist; struct rcu_head rcu; @@ -445,6 +448,7 @@ enum net_bridge_opts { BROPT_NO_LL_LEARN, BROPT_VLAN_BRIDGE_BINDING, BROPT_MCAST_VLAN_SNOOPING_ENABLED, + BROPT_MST_ENABLED, }; struct net_bridge { @@ -1765,6 +1769,39 @@ static inline bool br_vlan_state_allowed(u8 state, bool learn_allow) } #endif +/* br_mst.c */ +#ifdef CONFIG_BRIDGE_VLAN_FILTERING +DECLARE_STATIC_KEY_FALSE(br_mst_used); +static inline bool br_mst_is_enabled(struct net_bridge *br) +{ + return static_branch_unlikely(&br_mst_used) && + br_opt_get(br, BROPT_MST_ENABLED); +} + +int br_mst_set_state(struct net_bridge_port *p, u16 msti, u8 state, + struct netlink_ext_ack *extack); +void br_mst_vlan_init_state(struct net_bridge_vlan *v); +int br_mst_set_enabled(struct net_bridge *br, bool on, + struct netlink_ext_ack *extack); +#else +static inline bool br_mst_is_enabled(struct net_bridge *br) +{ + return false; +} + +static inline int br_mst_set_state(struct net_bridge_port *p, u16 msti, + u8 state, struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} + +static inline int br_mst_set_enabled(struct net_bridge *br, bool on, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} +#endif + struct nf_br_ops { int (*br_dev_xmit_hook)(struct sk_buff *skb); }; diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 1d80f34a139c..7d27b2e6038f 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -43,6 +43,12 @@ void br_set_state(struct net_bridge_port *p, unsigned int state) return; p->state = state; + if (br_opt_get(p->br, BROPT_MST_ENABLED)) { + err = br_mst_set_state(p, 0, state, NULL); + if (err) + br_warn(p->br, "error setting MST state on port %u(%s)\n", + p->port_no, netdev_name(p->dev)); + } err = switchdev_port_attr_set(p->dev, &attr, NULL); if (err && err != -EOPNOTSUPP) br_warn(p->br, "error setting offload STP state on port %u(%s)\n", diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 7557e90b60e1..0f5e75ccac79 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -226,6 +226,24 @@ static void nbp_vlan_rcu_free(struct rcu_head *rcu) kfree(v); } +static void br_vlan_init_state(struct net_bridge_vlan *v) +{ + struct net_bridge *br; + + if (br_vlan_is_master(v)) + br = v->br; + else + br = v->port->br; + + if (br_opt_get(br, BROPT_MST_ENABLED)) { + br_mst_vlan_init_state(v); + return; + } + + v->state = BR_STATE_FORWARDING; + v->msti = 0; +} + /* This is the shared VLAN add function which works for both ports and bridge * devices. There are four possible calls to this function in terms of the * vlan entry type: @@ -322,7 +340,7 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, } /* set the state before publishing */ - v->state = BR_STATE_FORWARDING; + br_vlan_init_state(v); err = rhashtable_lookup_insert_fast(&vg->vlan_hash, &v->vnode, br_vlan_rht_params); diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c index a6382973b3e7..09112b56e79c 100644 --- a/net/bridge/br_vlan_options.c +++ b/net/bridge/br_vlan_options.c @@ -99,6 +99,11 @@ static int br_vlan_modify_state(struct net_bridge_vlan_group *vg, return -EBUSY; } + if (br_opt_get(br, BROPT_MST_ENABLED)) { + NL_SET_ERR_MSG_MOD(extack, "Can't modify vlan state directly when MST is enabled"); + return -EBUSY; + } + if (v->state == state) return 0; -- cgit v1.2.3 From 8c678d60562f3e5f6d0a5f5465e27930ffedb8ca Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 16 Mar 2022 16:08:44 +0100 Subject: net: bridge: mst: Allow changing a VLAN's MSTI Allow a VLAN to move out of the CST (MSTI 0), to an independent tree. The user manages the VID to MSTI mappings via a global VLAN setting. The proposed iproute2 interface would be: bridge vlan global set dev br0 vid msti Changing the state in non-zero MSTIs is still not supported, but will be addressed in upcoming changes. Signed-off-by: Tobias Waldekranz Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bridge.h | 1 + net/bridge/br_mst.c | 42 ++++++++++++++++++++++++++++++++++++++++++ net/bridge/br_private.h | 1 + net/bridge/br_vlan_options.c | 15 +++++++++++++++ 4 files changed, 59 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 30a242195ced..f60244b747ae 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -564,6 +564,7 @@ enum { BRIDGE_VLANDB_GOPTS_MCAST_QUERIER, BRIDGE_VLANDB_GOPTS_MCAST_ROUTER_PORTS, BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_STATE, + BRIDGE_VLANDB_GOPTS_MSTI, __BRIDGE_VLANDB_GOPTS_MAX }; #define BRIDGE_VLANDB_GOPTS_MAX (__BRIDGE_VLANDB_GOPTS_MAX - 1) diff --git a/net/bridge/br_mst.c b/net/bridge/br_mst.c index 0f9f596f86bc..d7a7b5d7ddb3 100644 --- a/net/bridge/br_mst.c +++ b/net/bridge/br_mst.c @@ -46,6 +46,48 @@ int br_mst_set_state(struct net_bridge_port *p, u16 msti, u8 state, return 0; } +static void br_mst_vlan_sync_state(struct net_bridge_vlan *pv, u16 msti) +{ + struct net_bridge_vlan_group *vg = nbp_vlan_group(pv->port); + struct net_bridge_vlan *v; + + list_for_each_entry(v, &vg->vlan_list, vlist) { + /* If this port already has a defined state in this + * MSTI (through some other VLAN membership), inherit + * it. + */ + if (v != pv && v->brvlan->msti == msti) { + br_mst_vlan_set_state(pv->port, pv, v->state); + return; + } + } + + /* Otherwise, start out in a new MSTI with all ports disabled. */ + return br_mst_vlan_set_state(pv->port, pv, BR_STATE_DISABLED); +} + +int br_mst_vlan_set_msti(struct net_bridge_vlan *mv, u16 msti) +{ + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *pv; + struct net_bridge_port *p; + + if (mv->msti == msti) + return 0; + + mv->msti = msti; + + list_for_each_entry(p, &mv->br->port_list, list) { + vg = nbp_vlan_group(p); + + pv = br_vlan_find(vg, mv->vid); + if (pv) + br_mst_vlan_sync_state(pv, msti); + } + + return 0; +} + void br_mst_vlan_init_state(struct net_bridge_vlan *v) { /* VLANs always start out in MSTI 0 (CST) */ diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index c2190c8841fb..3978e1d9ffb5 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1780,6 +1780,7 @@ static inline bool br_mst_is_enabled(struct net_bridge *br) int br_mst_set_state(struct net_bridge_port *p, u16 msti, u8 state, struct netlink_ext_ack *extack); +int br_mst_vlan_set_msti(struct net_bridge_vlan *v, u16 msti); void br_mst_vlan_init_state(struct net_bridge_vlan *v); int br_mst_set_enabled(struct net_bridge *br, bool on, struct netlink_ext_ack *extack); diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c index 09112b56e79c..a2724d03278c 100644 --- a/net/bridge/br_vlan_options.c +++ b/net/bridge/br_vlan_options.c @@ -296,6 +296,7 @@ bool br_vlan_global_opts_can_enter_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *r_end) { return v_curr->vid - r_end->vid == 1 && + v_curr->msti == r_end->msti && ((v_curr->priv_flags ^ r_end->priv_flags) & BR_VLFLAG_GLOBAL_MCAST_ENABLED) == 0 && br_multicast_ctx_options_equal(&v_curr->br_mcast_ctx, @@ -384,6 +385,9 @@ bool br_vlan_global_opts_fill(struct sk_buff *skb, u16 vid, u16 vid_range, #endif #endif + if (nla_put_u16(skb, BRIDGE_VLANDB_GOPTS_MSTI, v_opts->msti)) + goto out_err; + nla_nest_end(skb, nest); return true; @@ -415,6 +419,7 @@ static size_t rtnl_vlan_global_opts_nlmsg_size(const struct net_bridge_vlan *v) + nla_total_size(0) /* BRIDGE_VLANDB_GOPTS_MCAST_ROUTER_PORTS */ + br_rports_size(&v->br_mcast_ctx) /* BRIDGE_VLANDB_GOPTS_MCAST_ROUTER_PORTS */ #endif + + nla_total_size(sizeof(u16)) /* BRIDGE_VLANDB_GOPTS_MSTI */ + nla_total_size(sizeof(u16)); /* BRIDGE_VLANDB_GOPTS_RANGE */ } @@ -564,6 +569,15 @@ static int br_vlan_process_global_one_opts(const struct net_bridge *br, } #endif #endif + if (tb[BRIDGE_VLANDB_GOPTS_MSTI]) { + u16 msti; + + msti = nla_get_u16(tb[BRIDGE_VLANDB_GOPTS_MSTI]); + err = br_mst_vlan_set_msti(v, msti); + if (err) + return err; + *changed = true; + } return 0; } @@ -583,6 +597,7 @@ static const struct nla_policy br_vlan_db_gpol[BRIDGE_VLANDB_GOPTS_MAX + 1] = { [BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_INTVL] = { .type = NLA_U64 }, [BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_INTVL] = { .type = NLA_U64 }, [BRIDGE_VLANDB_GOPTS_MCAST_QUERY_RESPONSE_INTVL] = { .type = NLA_U64 }, + [BRIDGE_VLANDB_GOPTS_MSTI] = NLA_POLICY_MAX(NLA_U16, VLAN_N_VID - 1), }; int br_vlan_rtm_process_global_options(struct net_device *dev, -- cgit v1.2.3 From 122c29486e1ff78033c45d0d31c710e7dc8945a5 Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 16 Mar 2022 16:08:45 +0100 Subject: net: bridge: mst: Support setting and reporting MST port states Make it possible to change the port state in a given MSTI by extending the bridge port netlink interface (RTM_SETLINK on PF_BRIDGE).The proposed iproute2 interface would be: bridge mst set dev msti state Current states in all applicable MSTIs can also be dumped via a corresponding RTM_GETLINK. The proposed iproute interface looks like this: $ bridge mst port msti vb1 0 state forwarding 100 state disabled vb2 0 state forwarding 100 state forwarding The preexisting per-VLAN states are still valid in the MST mode (although they are read-only), and can be queried as usual if one is interested in knowing a particular VLAN's state without having to care about the VID to MSTI mapping (in this example VLAN 20 and 30 are bound to MSTI 100): $ bridge -d vlan port vlan-id vb1 10 state forwarding mcast_router 1 20 state disabled mcast_router 1 30 state disabled mcast_router 1 40 state forwarding mcast_router 1 vb2 10 state forwarding mcast_router 1 20 state forwarding mcast_router 1 30 state forwarding mcast_router 1 40 state forwarding mcast_router 1 Signed-off-by: Tobias Waldekranz Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bridge.h | 16 ++++++ include/uapi/linux/rtnetlink.h | 1 + net/bridge/br_mst.c | 126 +++++++++++++++++++++++++++++++++++++++++ net/bridge/br_netlink.c | 44 +++++++++++++- net/bridge/br_private.h | 23 ++++++++ 5 files changed, 209 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index f60244b747ae..a86a7e7b811f 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -122,6 +122,7 @@ enum { IFLA_BRIDGE_VLAN_TUNNEL_INFO, IFLA_BRIDGE_MRP, IFLA_BRIDGE_CFM, + IFLA_BRIDGE_MST, __IFLA_BRIDGE_MAX, }; #define IFLA_BRIDGE_MAX (__IFLA_BRIDGE_MAX - 1) @@ -453,6 +454,21 @@ enum { #define IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX (__IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX - 1) +enum { + IFLA_BRIDGE_MST_UNSPEC, + IFLA_BRIDGE_MST_ENTRY, + __IFLA_BRIDGE_MST_MAX, +}; +#define IFLA_BRIDGE_MST_MAX (__IFLA_BRIDGE_MST_MAX - 1) + +enum { + IFLA_BRIDGE_MST_ENTRY_UNSPEC, + IFLA_BRIDGE_MST_ENTRY_MSTI, + IFLA_BRIDGE_MST_ENTRY_STATE, + __IFLA_BRIDGE_MST_ENTRY_MAX, +}; +#define IFLA_BRIDGE_MST_ENTRY_MAX (__IFLA_BRIDGE_MST_ENTRY_MAX - 1) + struct bridge_stp_xstats { __u64 transition_blk; __u64 transition_fwd; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 51530aade46e..83849a37db5b 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -817,6 +817,7 @@ enum { #define RTEXT_FILTER_MRP (1 << 4) #define RTEXT_FILTER_CFM_CONFIG (1 << 5) #define RTEXT_FILTER_CFM_STATUS (1 << 6) +#define RTEXT_FILTER_MST (1 << 7) /* End of information exported to user level */ diff --git a/net/bridge/br_mst.c b/net/bridge/br_mst.c index d7a7b5d7ddb3..5c1831c73fc2 100644 --- a/net/bridge/br_mst.c +++ b/net/bridge/br_mst.c @@ -127,3 +127,129 @@ int br_mst_set_enabled(struct net_bridge *br, bool on, br_opt_toggle(br, BROPT_MST_ENABLED, on); return 0; } + +size_t br_mst_info_size(const struct net_bridge_vlan_group *vg) +{ + DECLARE_BITMAP(seen, VLAN_N_VID) = { 0 }; + const struct net_bridge_vlan *v; + size_t sz; + + /* IFLA_BRIDGE_MST */ + sz = nla_total_size(0); + + list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { + if (test_bit(v->brvlan->msti, seen)) + continue; + + /* IFLA_BRIDGE_MST_ENTRY */ + sz += nla_total_size(0) + + /* IFLA_BRIDGE_MST_ENTRY_MSTI */ + nla_total_size(sizeof(u16)) + + /* IFLA_BRIDGE_MST_ENTRY_STATE */ + nla_total_size(sizeof(u8)); + + __set_bit(v->brvlan->msti, seen); + } + + return sz; +} + +int br_mst_fill_info(struct sk_buff *skb, + const struct net_bridge_vlan_group *vg) +{ + DECLARE_BITMAP(seen, VLAN_N_VID) = { 0 }; + const struct net_bridge_vlan *v; + struct nlattr *nest; + int err = 0; + + list_for_each_entry(v, &vg->vlan_list, vlist) { + if (test_bit(v->brvlan->msti, seen)) + continue; + + nest = nla_nest_start_noflag(skb, IFLA_BRIDGE_MST_ENTRY); + if (!nest || + nla_put_u16(skb, IFLA_BRIDGE_MST_ENTRY_MSTI, v->brvlan->msti) || + nla_put_u8(skb, IFLA_BRIDGE_MST_ENTRY_STATE, v->state)) { + err = -EMSGSIZE; + break; + } + nla_nest_end(skb, nest); + + __set_bit(v->brvlan->msti, seen); + } + + return err; +} + +static const struct nla_policy br_mst_nl_policy[IFLA_BRIDGE_MST_ENTRY_MAX + 1] = { + [IFLA_BRIDGE_MST_ENTRY_MSTI] = NLA_POLICY_RANGE(NLA_U16, + 1, /* 0 reserved for CST */ + VLAN_N_VID - 1), + [IFLA_BRIDGE_MST_ENTRY_STATE] = NLA_POLICY_RANGE(NLA_U8, + BR_STATE_DISABLED, + BR_STATE_BLOCKING), +}; + +static int br_mst_process_one(struct net_bridge_port *p, + const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_MST_ENTRY_MAX + 1]; + u16 msti; + u8 state; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_MST_ENTRY_MAX, attr, + br_mst_nl_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_MST_ENTRY_MSTI]) { + NL_SET_ERR_MSG_MOD(extack, "MSTI not specified"); + return -EINVAL; + } + + if (!tb[IFLA_BRIDGE_MST_ENTRY_STATE]) { + NL_SET_ERR_MSG_MOD(extack, "State not specified"); + return -EINVAL; + } + + msti = nla_get_u16(tb[IFLA_BRIDGE_MST_ENTRY_MSTI]); + state = nla_get_u8(tb[IFLA_BRIDGE_MST_ENTRY_STATE]); + + return br_mst_set_state(p, msti, state, extack); +} + +int br_mst_process(struct net_bridge_port *p, const struct nlattr *mst_attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *attr; + int err, msts = 0; + int rem; + + if (!br_opt_get(p->br, BROPT_MST_ENABLED)) { + NL_SET_ERR_MSG_MOD(extack, "Can't modify MST state when MST is disabled"); + return -EBUSY; + } + + nla_for_each_nested(attr, mst_attr, rem) { + switch (nla_type(attr)) { + case IFLA_BRIDGE_MST_ENTRY: + err = br_mst_process_one(p, attr, extack); + break; + default: + continue; + } + + msts++; + if (err) + break; + } + + if (!msts) { + NL_SET_ERR_MSG_MOD(extack, "Found no MST entries to process"); + err = -EINVAL; + } + + return err; +} diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 7d4432ca9a20..a8d90fa8621e 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -119,6 +119,9 @@ static size_t br_get_link_af_size_filtered(const struct net_device *dev, /* Each VLAN is returned in bridge_vlan_info along with flags */ vinfo_sz += num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info)); + if (filter_mask & RTEXT_FILTER_MST) + vinfo_sz += br_mst_info_size(vg); + if (!(filter_mask & RTEXT_FILTER_CFM_STATUS)) return vinfo_sz; @@ -485,7 +488,8 @@ static int br_fill_ifinfo(struct sk_buff *skb, RTEXT_FILTER_BRVLAN_COMPRESSED | RTEXT_FILTER_MRP | RTEXT_FILTER_CFM_CONFIG | - RTEXT_FILTER_CFM_STATUS)) { + RTEXT_FILTER_CFM_STATUS | + RTEXT_FILTER_MST)) { af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!af) goto nla_put_failure; @@ -564,7 +568,28 @@ static int br_fill_ifinfo(struct sk_buff *skb, nla_nest_end(skb, cfm_nest); } + if ((filter_mask & RTEXT_FILTER_MST) && + br_opt_get(br, BROPT_MST_ENABLED) && port) { + const struct net_bridge_vlan_group *vg = nbp_vlan_group(port); + struct nlattr *mst_nest; + int err; + + if (!vg || !vg->num_vlans) + goto done; + + mst_nest = nla_nest_start(skb, IFLA_BRIDGE_MST); + if (!mst_nest) + goto nla_put_failure; + + err = br_mst_fill_info(skb, vg); + if (err) + goto nla_put_failure; + + nla_nest_end(skb, mst_nest); + } + done: + if (af) nla_nest_end(skb, af); nlmsg_end(skb, nlh); @@ -803,6 +828,23 @@ static int br_afspec(struct net_bridge *br, if (err) return err; break; + case IFLA_BRIDGE_MST: + if (!p) { + NL_SET_ERR_MSG(extack, + "MST states can only be set on bridge ports"); + return -EINVAL; + } + + if (cmd != RTM_SETLINK) { + NL_SET_ERR_MSG(extack, + "MST states can only be set through RTM_SETLINK"); + return -EINVAL; + } + + err = br_mst_process(p, attr, extack); + if (err) + return err; + break; } } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 3978e1d9ffb5..18ccc3d5d296 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1784,6 +1784,11 @@ int br_mst_vlan_set_msti(struct net_bridge_vlan *v, u16 msti); void br_mst_vlan_init_state(struct net_bridge_vlan *v); int br_mst_set_enabled(struct net_bridge *br, bool on, struct netlink_ext_ack *extack); +size_t br_mst_info_size(const struct net_bridge_vlan_group *vg); +int br_mst_fill_info(struct sk_buff *skb, + const struct net_bridge_vlan_group *vg); +int br_mst_process(struct net_bridge_port *p, const struct nlattr *mst_attr, + struct netlink_ext_ack *extack); #else static inline bool br_mst_is_enabled(struct net_bridge *br) { @@ -1801,6 +1806,24 @@ static inline int br_mst_set_enabled(struct net_bridge *br, bool on, { return -EOPNOTSUPP; } + +static inline size_t br_mst_info_size(const struct net_bridge_vlan_group *vg) +{ + return 0; +} + +static inline int br_mst_fill_info(struct sk_buff *skb, + const struct net_bridge_vlan_group *vg) +{ + return -EOPNOTSUPP; +} + +static inline int br_mst_process(struct net_bridge_port *p, + const struct nlattr *mst_attr, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} #endif struct nf_br_ops { -- cgit v1.2.3 From 0dcac272540613d41c05e89679e4ddb978b612f1 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 16 Mar 2022 13:24:09 +0100 Subject: bpf: Add multi kprobe link Adding new link type BPF_LINK_TYPE_KPROBE_MULTI that attaches kprobe program through fprobe API. The fprobe API allows to attach probe on multiple functions at once very fast, because it works on top of ftrace. On the other hand this limits the probe point to the function entry or return. The kprobe program gets the same pt_regs input ctx as when it's attached through the perf API. Adding new attach type BPF_TRACE_KPROBE_MULTI that allows attachment kprobe to multiple function with new link. User provides array of addresses or symbols with count to attach the kprobe program to. The new link_create uapi interface looks like: struct { __u32 flags; __u32 cnt; __aligned_u64 syms; __aligned_u64 addrs; } kprobe_multi; The flags field allows single BPF_TRACE_KPROBE_MULTI bit to create return multi kprobe. Signed-off-by: Masami Hiramatsu Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220316122419.933957-4-jolsa@kernel.org --- include/linux/bpf_types.h | 1 + include/linux/trace_events.h | 7 ++ include/uapi/linux/bpf.h | 13 +++ kernel/bpf/syscall.c | 26 ++++- kernel/trace/bpf_trace.c | 211 +++++++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 13 +++ 6 files changed, 266 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 48a91c51c015..3e24ad0c4b3c 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -140,3 +140,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) #ifdef CONFIG_PERF_EVENTS BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf) #endif +BPF_LINK_TYPE(BPF_LINK_TYPE_KPROBE_MULTI, kprobe_multi) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index dcea51fb60e2..8f0e9e7cb493 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -15,6 +15,7 @@ struct array_buffer; struct tracer; struct dentry; struct bpf_prog; +union bpf_attr; const char *trace_print_flags_seq(struct trace_seq *p, const char *delim, unsigned long flags, @@ -738,6 +739,7 @@ void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, u64 *probe_addr); +int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); #else static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { @@ -779,6 +781,11 @@ static inline int bpf_get_perf_event_info(const struct perf_event *event, { return -EOPNOTSUPP; } +static inline int +bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif enum { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 99fab54ae9c0..d77f47af7752 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -997,6 +997,7 @@ enum bpf_attach_type { BPF_SK_REUSEPORT_SELECT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, BPF_PERF_EVENT, + BPF_TRACE_KPROBE_MULTI, __MAX_BPF_ATTACH_TYPE }; @@ -1011,6 +1012,7 @@ enum bpf_link_type { BPF_LINK_TYPE_NETNS = 5, BPF_LINK_TYPE_XDP = 6, BPF_LINK_TYPE_PERF_EVENT = 7, + BPF_LINK_TYPE_KPROBE_MULTI = 8, MAX_BPF_LINK_TYPE, }; @@ -1118,6 +1120,11 @@ enum bpf_link_type { */ #define BPF_F_XDP_HAS_FRAGS (1U << 5) +/* link_create.kprobe_multi.flags used in LINK_CREATE command for + * BPF_TRACE_KPROBE_MULTI attach type to create return probe. + */ +#define BPF_F_KPROBE_MULTI_RETURN (1U << 0) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * @@ -1475,6 +1482,12 @@ union bpf_attr { */ __u64 bpf_cookie; } perf_event; + struct { + __u32 flags; + __u32 cnt; + __aligned_u64 syms; + __aligned_u64 addrs; + } kprobe_multi; }; } link_create; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 9beb585be5a6..b8bb67ee6c57 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -32,6 +32,7 @@ #include #include #include +#include #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ @@ -3022,6 +3023,11 @@ out_put_file: fput(perf_file); return err; } +#else +static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_PERF_EVENTS */ #define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd @@ -4255,7 +4261,7 @@ static int tracing_bpf_link_attach(const union bpf_attr *attr, bpfptr_t uattr, return -EINVAL; } -#define BPF_LINK_CREATE_LAST_FIELD link_create.iter_info_len +#define BPF_LINK_CREATE_LAST_FIELD link_create.kprobe_multi.addrs static int link_create(union bpf_attr *attr, bpfptr_t uattr) { enum bpf_prog_type ptype; @@ -4279,7 +4285,6 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) ret = tracing_bpf_link_attach(attr, uattr, prog); goto out; case BPF_PROG_TYPE_PERF_EVENT: - case BPF_PROG_TYPE_KPROBE: case BPF_PROG_TYPE_TRACEPOINT: if (attr->link_create.attach_type != BPF_PERF_EVENT) { ret = -EINVAL; @@ -4287,6 +4292,14 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) } ptype = prog->type; break; + case BPF_PROG_TYPE_KPROBE: + if (attr->link_create.attach_type != BPF_PERF_EVENT && + attr->link_create.attach_type != BPF_TRACE_KPROBE_MULTI) { + ret = -EINVAL; + goto out; + } + ptype = prog->type; + break; default: ptype = attach_type_to_prog_type(attr->link_create.attach_type); if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) { @@ -4318,13 +4331,16 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) ret = bpf_xdp_link_attach(attr, prog); break; #endif -#ifdef CONFIG_PERF_EVENTS case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_TRACEPOINT: - case BPF_PROG_TYPE_KPROBE: ret = bpf_perf_link_attach(attr, prog); break; -#endif + case BPF_PROG_TYPE_KPROBE: + if (attr->link_create.attach_type == BPF_PERF_EVENT) + ret = bpf_perf_link_attach(attr, prog); + else + ret = bpf_kprobe_multi_link_attach(attr, prog); + break; default: ret = -EINVAL; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index a2024ba32a20..fffa2171fae4 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -17,6 +17,7 @@ #include #include #include +#include #include @@ -2181,3 +2182,213 @@ static int __init bpf_event_init(void) fs_initcall(bpf_event_init); #endif /* CONFIG_MODULES */ + +#ifdef CONFIG_FPROBE +struct bpf_kprobe_multi_link { + struct bpf_link link; + struct fprobe fp; + unsigned long *addrs; +}; + +static void bpf_kprobe_multi_link_release(struct bpf_link *link) +{ + struct bpf_kprobe_multi_link *kmulti_link; + + kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); + unregister_fprobe(&kmulti_link->fp); +} + +static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link) +{ + struct bpf_kprobe_multi_link *kmulti_link; + + kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); + kvfree(kmulti_link->addrs); + kfree(kmulti_link); +} + +static const struct bpf_link_ops bpf_kprobe_multi_link_lops = { + .release = bpf_kprobe_multi_link_release, + .dealloc = bpf_kprobe_multi_link_dealloc, +}; + +static int +kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, + struct pt_regs *regs) +{ + int err; + + if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { + err = 0; + goto out; + } + + migrate_disable(); + rcu_read_lock(); + err = bpf_prog_run(link->link.prog, regs); + rcu_read_unlock(); + migrate_enable(); + + out: + __this_cpu_dec(bpf_prog_active); + return err; +} + +static void +kprobe_multi_link_handler(struct fprobe *fp, unsigned long entry_ip, + struct pt_regs *regs) +{ + unsigned long saved_ip = instruction_pointer(regs); + struct bpf_kprobe_multi_link *link; + + /* + * Because fprobe's regs->ip is set to the next instruction of + * dynamic-ftrace instruction, correct entry ip must be set, so + * that the bpf program can access entry address via regs as same + * as kprobes. + * + * Both kprobe and kretprobe see the entry ip of traced function + * as instruction pointer. + */ + instruction_pointer_set(regs, entry_ip); + + link = container_of(fp, struct bpf_kprobe_multi_link, fp); + kprobe_multi_link_prog_run(link, regs); + + instruction_pointer_set(regs, saved_ip); +} + +static int +kprobe_multi_resolve_syms(const void *usyms, u32 cnt, + unsigned long *addrs) +{ + unsigned long addr, size; + const char **syms; + int err = -ENOMEM; + unsigned int i; + char *func; + + size = cnt * sizeof(*syms); + syms = kvzalloc(size, GFP_KERNEL); + if (!syms) + return -ENOMEM; + + func = kmalloc(KSYM_NAME_LEN, GFP_KERNEL); + if (!func) + goto error; + + if (copy_from_user(syms, usyms, size)) { + err = -EFAULT; + goto error; + } + + for (i = 0; i < cnt; i++) { + err = strncpy_from_user(func, syms[i], KSYM_NAME_LEN); + if (err == KSYM_NAME_LEN) + err = -E2BIG; + if (err < 0) + goto error; + err = -EINVAL; + addr = kallsyms_lookup_name(func); + if (!addr) + goto error; + if (!kallsyms_lookup_size_offset(addr, &size, NULL)) + goto error; + addr = ftrace_location_range(addr, addr + size - 1); + if (!addr) + goto error; + addrs[i] = addr; + } + + err = 0; +error: + kvfree(syms); + kfree(func); + return err; +} + +int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_kprobe_multi_link *link = NULL; + struct bpf_link_primer link_primer; + unsigned long *addrs; + u32 flags, cnt, size; + void __user *uaddrs; + void __user *usyms; + int err; + + /* no support for 32bit archs yet */ + if (sizeof(u64) != sizeof(void *)) + return -EOPNOTSUPP; + + if (prog->expected_attach_type != BPF_TRACE_KPROBE_MULTI) + return -EINVAL; + + flags = attr->link_create.kprobe_multi.flags; + if (flags & ~BPF_F_KPROBE_MULTI_RETURN) + return -EINVAL; + + uaddrs = u64_to_user_ptr(attr->link_create.kprobe_multi.addrs); + usyms = u64_to_user_ptr(attr->link_create.kprobe_multi.syms); + if (!!uaddrs == !!usyms) + return -EINVAL; + + cnt = attr->link_create.kprobe_multi.cnt; + if (!cnt) + return -EINVAL; + + size = cnt * sizeof(*addrs); + addrs = kvmalloc(size, GFP_KERNEL); + if (!addrs) + return -ENOMEM; + + if (uaddrs) { + if (copy_from_user(addrs, uaddrs, size)) { + err = -EFAULT; + goto error; + } + } else { + err = kprobe_multi_resolve_syms(usyms, cnt, addrs); + if (err) + goto error; + } + + link = kzalloc(sizeof(*link), GFP_KERNEL); + if (!link) { + err = -ENOMEM; + goto error; + } + + bpf_link_init(&link->link, BPF_LINK_TYPE_KPROBE_MULTI, + &bpf_kprobe_multi_link_lops, prog); + + err = bpf_link_prime(&link->link, &link_primer); + if (err) + goto error; + + if (flags & BPF_F_KPROBE_MULTI_RETURN) + link->fp.exit_handler = kprobe_multi_link_handler; + else + link->fp.entry_handler = kprobe_multi_link_handler; + + link->addrs = addrs; + + err = register_fprobe_ips(&link->fp, addrs, cnt); + if (err) { + bpf_link_cleanup(&link_primer); + return err; + } + + return bpf_link_settle(&link_primer); + +error: + kfree(link); + kvfree(addrs); + return err; +} +#else /* !CONFIG_FPROBE */ +int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} +#endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 99fab54ae9c0..d77f47af7752 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -997,6 +997,7 @@ enum bpf_attach_type { BPF_SK_REUSEPORT_SELECT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, BPF_PERF_EVENT, + BPF_TRACE_KPROBE_MULTI, __MAX_BPF_ATTACH_TYPE }; @@ -1011,6 +1012,7 @@ enum bpf_link_type { BPF_LINK_TYPE_NETNS = 5, BPF_LINK_TYPE_XDP = 6, BPF_LINK_TYPE_PERF_EVENT = 7, + BPF_LINK_TYPE_KPROBE_MULTI = 8, MAX_BPF_LINK_TYPE, }; @@ -1118,6 +1120,11 @@ enum bpf_link_type { */ #define BPF_F_XDP_HAS_FRAGS (1U << 5) +/* link_create.kprobe_multi.flags used in LINK_CREATE command for + * BPF_TRACE_KPROBE_MULTI attach type to create return probe. + */ +#define BPF_F_KPROBE_MULTI_RETURN (1U << 0) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * @@ -1475,6 +1482,12 @@ union bpf_attr { */ __u64 bpf_cookie; } perf_event; + struct { + __u32 flags; + __u32 cnt; + __aligned_u64 syms; + __aligned_u64 addrs; + } kprobe_multi; }; } link_create; -- cgit v1.2.3 From ca74823c6e16dd42b7cf60d9fdde80e2a81a67bb Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 16 Mar 2022 13:24:12 +0100 Subject: bpf: Add cookie support to programs attached with kprobe multi link Adding support to call bpf_get_attach_cookie helper from kprobe programs attached with kprobe multi link. The cookie is provided by array of u64 values, where each value is paired with provided function address or symbol with the same array index. When cookie array is provided it's sorted together with addresses (check bpf_kprobe_multi_cookie_swap). This way we can find cookie based on the address in bpf_get_attach_cookie helper. Suggested-by: Andrii Nakryiko Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220316122419.933957-7-jolsa@kernel.org --- include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 2 +- kernel/trace/bpf_trace.c | 114 ++++++++++++++++++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 1 + 4 files changed, 116 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d77f47af7752..7604e7d5438f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1487,6 +1487,7 @@ union bpf_attr { __u32 cnt; __aligned_u64 syms; __aligned_u64 addrs; + __aligned_u64 cookies; } kprobe_multi; }; } link_create; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b8bb67ee6c57..cdaa1152436a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4261,7 +4261,7 @@ static int tracing_bpf_link_attach(const union bpf_attr *attr, bpfptr_t uattr, return -EINVAL; } -#define BPF_LINK_CREATE_LAST_FIELD link_create.kprobe_multi.addrs +#define BPF_LINK_CREATE_LAST_FIELD link_create.kprobe_multi.cookies static int link_create(union bpf_attr *attr, bpfptr_t uattr) { enum bpf_prog_type ptype; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 0e7f8c9bc756..9a7b6be655e4 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -18,6 +18,8 @@ #include #include #include +#include +#include #include @@ -78,6 +80,7 @@ u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags, const struct btf **btf, s32 *btf_id); +static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx, u64 ip); /** * trace_call_bpf - invoke BPF program @@ -1050,6 +1053,18 @@ static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe_multi = { .arg1_type = ARG_PTR_TO_CTX, }; +BPF_CALL_1(bpf_get_attach_cookie_kprobe_multi, struct pt_regs *, regs) +{ + return bpf_kprobe_multi_cookie(current->bpf_ctx, instruction_pointer(regs)); +} + +static const struct bpf_func_proto bpf_get_attach_cookie_proto_kmulti = { + .func = bpf_get_attach_cookie_kprobe_multi, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + BPF_CALL_1(bpf_get_attach_cookie_trace, void *, ctx) { struct bpf_trace_run_ctx *run_ctx; @@ -1297,7 +1312,9 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) &bpf_get_func_ip_proto_kprobe_multi : &bpf_get_func_ip_proto_kprobe; case BPF_FUNC_get_attach_cookie: - return &bpf_get_attach_cookie_proto_trace; + return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ? + &bpf_get_attach_cookie_proto_kmulti : + &bpf_get_attach_cookie_proto_trace; default: return bpf_tracing_func_proto(func_id, prog); } @@ -2203,6 +2220,13 @@ struct bpf_kprobe_multi_link { struct bpf_link link; struct fprobe fp; unsigned long *addrs; + /* + * The run_ctx here is used to get struct bpf_kprobe_multi_link in + * get_attach_cookie helper, so it can't be used to store data. + */ + struct bpf_run_ctx run_ctx; + u64 *cookies; + u32 cnt; }; static void bpf_kprobe_multi_link_release(struct bpf_link *link) @@ -2219,6 +2243,7 @@ static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link) kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); kvfree(kmulti_link->addrs); + kvfree(kmulti_link->cookies); kfree(kmulti_link); } @@ -2227,10 +2252,60 @@ static const struct bpf_link_ops bpf_kprobe_multi_link_lops = { .dealloc = bpf_kprobe_multi_link_dealloc, }; +static void bpf_kprobe_multi_cookie_swap(void *a, void *b, int size, const void *priv) +{ + const struct bpf_kprobe_multi_link *link = priv; + unsigned long *addr_a = a, *addr_b = b; + u64 *cookie_a, *cookie_b; + unsigned long tmp1; + u64 tmp2; + + cookie_a = link->cookies + (addr_a - link->addrs); + cookie_b = link->cookies + (addr_b - link->addrs); + + /* swap addr_a/addr_b and cookie_a/cookie_b values */ + tmp1 = *addr_a; *addr_a = *addr_b; *addr_b = tmp1; + tmp2 = *cookie_a; *cookie_a = *cookie_b; *cookie_b = tmp2; +} + +static int __bpf_kprobe_multi_cookie_cmp(const void *a, const void *b) +{ + const unsigned long *addr_a = a, *addr_b = b; + + if (*addr_a == *addr_b) + return 0; + return *addr_a < *addr_b ? -1 : 1; +} + +static int bpf_kprobe_multi_cookie_cmp(const void *a, const void *b, const void *priv) +{ + return __bpf_kprobe_multi_cookie_cmp(a, b); +} + +static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx, u64 ip) +{ + struct bpf_kprobe_multi_link *link; + unsigned long *addr; + u64 *cookie; + + if (WARN_ON_ONCE(!ctx)) + return 0; + link = container_of(ctx, struct bpf_kprobe_multi_link, run_ctx); + if (!link->cookies) + return 0; + addr = bsearch(&ip, link->addrs, link->cnt, sizeof(ip), + __bpf_kprobe_multi_cookie_cmp); + if (!addr) + return 0; + cookie = link->cookies + (addr - link->addrs); + return *cookie; +} + static int kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, struct pt_regs *regs) { + struct bpf_run_ctx *old_run_ctx; int err; if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { @@ -2240,7 +2315,9 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, migrate_disable(); rcu_read_lock(); + old_run_ctx = bpf_set_run_ctx(&link->run_ctx); err = bpf_prog_run(link->link.prog, regs); + bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); @@ -2326,9 +2403,11 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr { struct bpf_kprobe_multi_link *link = NULL; struct bpf_link_primer link_primer; + void __user *ucookies; unsigned long *addrs; u32 flags, cnt, size; void __user *uaddrs; + u64 *cookies = NULL; void __user *usyms; int err; @@ -2368,6 +2447,19 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr goto error; } + ucookies = u64_to_user_ptr(attr->link_create.kprobe_multi.cookies); + if (ucookies) { + cookies = kvmalloc(size, GFP_KERNEL); + if (!cookies) { + err = -ENOMEM; + goto error; + } + if (copy_from_user(cookies, ucookies, size)) { + err = -EFAULT; + goto error; + } + } + link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) { err = -ENOMEM; @@ -2387,6 +2479,21 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr link->fp.entry_handler = kprobe_multi_link_handler; link->addrs = addrs; + link->cookies = cookies; + link->cnt = cnt; + + if (cookies) { + /* + * Sorting addresses will trigger sorting cookies as well + * (check bpf_kprobe_multi_cookie_swap). This way we can + * find cookie based on the address in bpf_get_attach_cookie + * helper. + */ + sort_r(addrs, cnt, sizeof(*addrs), + bpf_kprobe_multi_cookie_cmp, + bpf_kprobe_multi_cookie_swap, + link); + } err = register_fprobe_ips(&link->fp, addrs, cnt); if (err) { @@ -2399,6 +2506,7 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr error: kfree(link); kvfree(addrs); + kvfree(cookies); return err; } #else /* !CONFIG_FPROBE */ @@ -2406,4 +2514,8 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr { return -EOPNOTSUPP; } +static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx, u64 ip) +{ + return 0; +} #endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index d77f47af7752..7604e7d5438f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1487,6 +1487,7 @@ union bpf_attr { __u32 cnt; __aligned_u64 syms; __aligned_u64 addrs; + __aligned_u64 cookies; } kprobe_multi; }; } link_create; -- cgit v1.2.3 From 54f586a9153201c6cff55e1f561990c78bd99aa7 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 16 Mar 2022 21:27:51 +0100 Subject: rfkill: make new event layout opt-in Again new complaints surfaced that we had broken the ABI here, although previously all the userspace tools had agreed that it was their mistake and fixed it. Yet now there are cases (e.g. RHEL) that want to run old userspace with newer kernels, and thus are broken. Since this is a bit of a whack-a-mole thing, change the whole extensibility scheme of rfkill to no longer just rely on the message lengths, but instead require userspace to opt in via a new ioctl to a given maximum event size that it is willing to understand. By default, set that to RFKILL_EVENT_SIZE_V1 (8), so that the behaviour for userspace not calling the ioctl will look as if it's just running on an older kernel. Fixes: 14486c82612a ("rfkill: add a reason to the HW rfkill state") Cc: stable@vger.kernel.org # 5.11+ Signed-off-by: Johannes Berg Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20220316212749.16491491b270.Ifcb1950998330a596f29a2a162e00b7546a1d6d0@changeid --- include/uapi/linux/rfkill.h | 14 +++++++++++-- net/rfkill/core.c | 48 ++++++++++++++++++++++++++++++++------------- 2 files changed, 46 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h index 9b77cfc42efa..283c5a7b3f2c 100644 --- a/include/uapi/linux/rfkill.h +++ b/include/uapi/linux/rfkill.h @@ -159,8 +159,16 @@ struct rfkill_event_ext { * old behaviour for all userspace, unless it explicitly opts in to the * rules outlined here by using the new &struct rfkill_event_ext. * - * Userspace using &struct rfkill_event_ext must adhere to the following - * rules + * Additionally, some other userspace (bluez, g-s-d) was reading with a + * large size but as streaming reads rather than message-based, or with + * too strict checks for the returned size. So eventually, we completely + * reverted this, and extended messages need to be opted in to by using + * an ioctl: + * + * ioctl(fd, RFKILL_IOCTL_MAX_SIZE, sizeof(struct rfkill_event_ext)); + * + * Userspace using &struct rfkill_event_ext and the ioctl must adhere to + * the following rules: * * 1. accept short writes, optionally using them to detect that it's * running on an older kernel; @@ -175,6 +183,8 @@ struct rfkill_event_ext { #define RFKILL_IOC_MAGIC 'R' #define RFKILL_IOC_NOINPUT 1 #define RFKILL_IOCTL_NOINPUT _IO(RFKILL_IOC_MAGIC, RFKILL_IOC_NOINPUT) +#define RFKILL_IOC_MAX_SIZE 2 +#define RFKILL_IOCTL_MAX_SIZE _IOW(RFKILL_IOC_MAGIC, RFKILL_IOC_EXT_SIZE, __u32) /* and that's all userspace gets */ diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 5b1927d66f0d..dac4fdc7488a 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -78,6 +78,7 @@ struct rfkill_data { struct mutex mtx; wait_queue_head_t read_wait; bool input_handler; + u8 max_size; }; @@ -1153,6 +1154,8 @@ static int rfkill_fop_open(struct inode *inode, struct file *file) if (!data) return -ENOMEM; + data->max_size = RFKILL_EVENT_SIZE_V1; + INIT_LIST_HEAD(&data->events); mutex_init(&data->mtx); init_waitqueue_head(&data->read_wait); @@ -1235,6 +1238,7 @@ static ssize_t rfkill_fop_read(struct file *file, char __user *buf, list); sz = min_t(unsigned long, sizeof(ev->ev), count); + sz = min_t(unsigned long, sz, data->max_size); ret = sz; if (copy_to_user(buf, &ev->ev, sz)) ret = -EFAULT; @@ -1249,6 +1253,7 @@ static ssize_t rfkill_fop_read(struct file *file, char __user *buf, static ssize_t rfkill_fop_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { + struct rfkill_data *data = file->private_data; struct rfkill *rfkill; struct rfkill_event_ext ev; int ret; @@ -1263,6 +1268,7 @@ static ssize_t rfkill_fop_write(struct file *file, const char __user *buf, * our API version even in a write() call, if it cares. */ count = min(count, sizeof(ev)); + count = min_t(size_t, count, data->max_size); if (copy_from_user(&ev, buf, count)) return -EFAULT; @@ -1322,31 +1328,47 @@ static int rfkill_fop_release(struct inode *inode, struct file *file) return 0; } -#ifdef CONFIG_RFKILL_INPUT static long rfkill_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct rfkill_data *data = file->private_data; + int ret = -ENOSYS; + u32 size; if (_IOC_TYPE(cmd) != RFKILL_IOC_MAGIC) return -ENOSYS; - if (_IOC_NR(cmd) != RFKILL_IOC_NOINPUT) - return -ENOSYS; - mutex_lock(&data->mtx); - - if (!data->input_handler) { - if (atomic_inc_return(&rfkill_input_disabled) == 1) - printk(KERN_DEBUG "rfkill: input handler disabled\n"); - data->input_handler = true; + switch (_IOC_NR(cmd)) { +#ifdef CONFIG_RFKILL_INPUT + case RFKILL_IOC_NOINPUT: + if (!data->input_handler) { + if (atomic_inc_return(&rfkill_input_disabled) == 1) + printk(KERN_DEBUG "rfkill: input handler disabled\n"); + data->input_handler = true; + } + ret = 0; + break; +#endif + case RFKILL_IOC_MAX_SIZE: + if (get_user(size, (__u32 __user *)arg)) { + ret = -EFAULT; + break; + } + if (size < RFKILL_EVENT_SIZE_V1 || size > U8_MAX) { + ret = -EINVAL; + break; + } + data->max_size = size; + ret = 0; + break; + default: + break; } - mutex_unlock(&data->mtx); - return 0; + return ret; } -#endif static const struct file_operations rfkill_fops = { .owner = THIS_MODULE, @@ -1355,10 +1377,8 @@ static const struct file_operations rfkill_fops = { .write = rfkill_fop_write, .poll = rfkill_fop_poll, .release = rfkill_fop_release, -#ifdef CONFIG_RFKILL_INPUT .unlocked_ioctl = rfkill_fop_ioctl, .compat_ioctl = compat_ptr_ioctl, -#endif .llseek = no_llseek, }; -- cgit v1.2.3 From ee2a098851bfbe8bcdd964c0121f4246f00ff41e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 14 Mar 2022 11:20:41 -0700 Subject: bpf: Adjust BPF stack helper functions to accommodate skip > 0 Let's say that the caller has storage for num_elem stack frames. Then, the BPF stack helper functions walk the stack for only num_elem frames. This means that if skip > 0, one keeps only 'num_elem - skip' frames. This is because it sets init_nr in the perf_callchain_entry to the end of the buffer to save num_elem entries only. I believe it was because the perf callchain code unwound the stack frames until it reached the global max size (sysctl_perf_event_max_stack). However it now has perf_callchain_entry_ctx.max_stack to limit the iteration locally. This simplifies the code to handle init_nr in the BPF callstack entries and removes the confusion with the perf_event's __PERF_SAMPLE_CALLCHAIN_EARLY which sets init_nr to 0. Also change the comment on bpf_get_stack() in the header file to be more explicit what the return value means. Fixes: c195651e565a ("bpf: add bpf_get_stack helper") Signed-off-by: Namhyung Kim Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/30a7b5d5-6726-1cc2-eaee-8da2828a9a9c@oracle.com Link: https://lore.kernel.org/bpf/20220314182042.71025-1-namhyung@kernel.org Based-on-patch-by: Eugene Loh --- include/uapi/linux/bpf.h | 8 +++---- kernel/bpf/stackmap.c | 56 +++++++++++++++++++++--------------------------- 2 files changed, 28 insertions(+), 36 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7604e7d5438f..d14b10b85e51 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3009,8 +3009,8 @@ union bpf_attr { * * # sysctl kernel.perf_event_max_stack= * Return - * A non-negative value equal to or less than *size* on success, - * or a negative error in case of failure. + * The non-negative copied *buf* length equal to or less than + * *size* on success, or a negative error in case of failure. * * long bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header) * Description @@ -4316,8 +4316,8 @@ union bpf_attr { * * # sysctl kernel.perf_event_max_stack= * Return - * A non-negative value equal to or less than *size* on success, - * or a negative error in case of failure. + * The non-negative copied *buf* length equal to or less than + * *size* on success, or a negative error in case of failure. * * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags) * Description diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 38bdfcd06f55..34725bfa1e97 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -176,7 +176,7 @@ build_id_valid: } static struct perf_callchain_entry * -get_callchain_entry_for_task(struct task_struct *task, u32 init_nr) +get_callchain_entry_for_task(struct task_struct *task, u32 max_depth) { #ifdef CONFIG_STACKTRACE struct perf_callchain_entry *entry; @@ -187,9 +187,8 @@ get_callchain_entry_for_task(struct task_struct *task, u32 init_nr) if (!entry) return NULL; - entry->nr = init_nr + - stack_trace_save_tsk(task, (unsigned long *)(entry->ip + init_nr), - sysctl_perf_event_max_stack - init_nr, 0); + entry->nr = stack_trace_save_tsk(task, (unsigned long *)entry->ip, + max_depth, 0); /* stack_trace_save_tsk() works on unsigned long array, while * perf_callchain_entry uses u64 array. For 32-bit systems, it is @@ -201,7 +200,7 @@ get_callchain_entry_for_task(struct task_struct *task, u32 init_nr) int i; /* copy data from the end to avoid using extra buffer */ - for (i = entry->nr - 1; i >= (int)init_nr; i--) + for (i = entry->nr - 1; i >= 0; i--) to[i] = (u64)(from[i]); } @@ -218,27 +217,19 @@ static long __bpf_get_stackid(struct bpf_map *map, { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); struct stack_map_bucket *bucket, *new_bucket, *old_bucket; - u32 max_depth = map->value_size / stack_map_data_size(map); - /* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */ - u32 init_nr = sysctl_perf_event_max_stack - max_depth; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; u32 hash, id, trace_nr, trace_len; bool user = flags & BPF_F_USER_STACK; u64 *ips; bool hash_matches; - /* get_perf_callchain() guarantees that trace->nr >= init_nr - * and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth - */ - trace_nr = trace->nr - init_nr; - - if (trace_nr <= skip) + if (trace->nr <= skip) /* skipping more than usable stack trace */ return -EFAULT; - trace_nr -= skip; + trace_nr = trace->nr - skip; trace_len = trace_nr * sizeof(u64); - ips = trace->ip + skip + init_nr; + ips = trace->ip + skip; hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0); id = hash & (smap->n_buckets - 1); bucket = READ_ONCE(smap->buckets[id]); @@ -295,8 +286,7 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, u64, flags) { u32 max_depth = map->value_size / stack_map_data_size(map); - /* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */ - u32 init_nr = sysctl_perf_event_max_stack - max_depth; + u32 skip = flags & BPF_F_SKIP_FIELD_MASK; bool user = flags & BPF_F_USER_STACK; struct perf_callchain_entry *trace; bool kernel = !user; @@ -305,8 +295,12 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) return -EINVAL; - trace = get_perf_callchain(regs, init_nr, kernel, user, - sysctl_perf_event_max_stack, false, false); + max_depth += skip; + if (max_depth > sysctl_perf_event_max_stack) + max_depth = sysctl_perf_event_max_stack; + + trace = get_perf_callchain(regs, 0, kernel, user, max_depth, + false, false); if (unlikely(!trace)) /* couldn't fetch the stack trace */ @@ -397,7 +391,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, struct perf_callchain_entry *trace_in, void *buf, u32 size, u64 flags) { - u32 init_nr, trace_nr, copy_len, elem_size, num_elem; + u32 trace_nr, copy_len, elem_size, num_elem, max_depth; bool user_build_id = flags & BPF_F_USER_BUILD_ID; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; bool user = flags & BPF_F_USER_STACK; @@ -422,30 +416,28 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, goto err_fault; num_elem = size / elem_size; - if (sysctl_perf_event_max_stack < num_elem) - init_nr = 0; - else - init_nr = sysctl_perf_event_max_stack - num_elem; + max_depth = num_elem + skip; + if (sysctl_perf_event_max_stack < max_depth) + max_depth = sysctl_perf_event_max_stack; if (trace_in) trace = trace_in; else if (kernel && task) - trace = get_callchain_entry_for_task(task, init_nr); + trace = get_callchain_entry_for_task(task, max_depth); else - trace = get_perf_callchain(regs, init_nr, kernel, user, - sysctl_perf_event_max_stack, + trace = get_perf_callchain(regs, 0, kernel, user, max_depth, false, false); if (unlikely(!trace)) goto err_fault; - trace_nr = trace->nr - init_nr; - if (trace_nr < skip) + if (trace->nr < skip) goto err_fault; - trace_nr -= skip; + trace_nr = trace->nr - skip; trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem; copy_len = trace_nr * elem_size; - ips = trace->ip + skip + init_nr; + + ips = trace->ip + skip; if (user && user_build_id) stack_map_get_build_id_offset(buf, ips, trace_nr, user); else -- cgit v1.2.3