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 --- tools/include/uapi/linux/bpf.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index b0383d371b9a..a9c96c21330a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/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 * @@ -2369,6 +2377,8 @@ union bpf_attr { * indicate that the hash is outdated and to trigger a * recalculation the next time the kernel tries to access this * hash or when the **bpf_get_hash_recalc**\ () helper is called.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 v1.2.3-71-gd317 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 'tools/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 v1.2.3-71-gd317 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 'tools/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 v1.2.3-71-gd317 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 'tools/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 v1.2.3-71-gd317 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 'tools/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 v1.2.3-71-gd317