From 6089fb325cf737eeb2c4d236c94697112ca860da Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 6 Jun 2022 23:26:00 -0700 Subject: bpf: Add btf enum64 support Currently, BTF only supports upto 32bit enum value with BTF_KIND_ENUM. But in kernel, some enum indeed has 64bit values, e.g., in uapi bpf.h, we have enum { BPF_F_INDEX_MASK = 0xffffffffULL, BPF_F_CURRENT_CPU = BPF_F_INDEX_MASK, BPF_F_CTXLEN_MASK = (0xfffffULL << 32), }; In this case, BTF_KIND_ENUM will encode the value of BPF_F_CTXLEN_MASK as 0, which certainly is incorrect. This patch added a new btf kind, BTF_KIND_ENUM64, which permits 64bit value to cover the above use case. The BTF_KIND_ENUM64 has the following three fields followed by the common type: struct bpf_enum64 { __u32 nume_off; __u32 val_lo32; __u32 val_hi32; }; Currently, btf type section has an alignment of 4 as all element types are u32. Representing the value with __u64 will introduce a pad for bpf_enum64 and may also introduce misalignment for the 64bit value. Hence, two members of val_hi32 and val_lo32 are chosen to avoid these issues. The kflag is also introduced for BTF_KIND_ENUM and BTF_KIND_ENUM64 to indicate whether the value is signed or unsigned. The kflag intends to provide consistent output of BTF C fortmat with the original source code. For example, the original BTF_KIND_ENUM bit value is 0xffffffff. The format C has two choices, printing out 0xffffffff or -1 and current libbpf prints out as unsigned value. But if the signedness is preserved in btf, the value can be printed the same as the original source code. The kflag value 0 means unsigned values, which is consistent to the default by libbpf and should also cover most cases as well. The new BTF_KIND_ENUM64 is intended to support the enum value represented as 64bit value. But it can represent all BTF_KIND_ENUM values as well. The compiler ([1]) and pahole will generate BTF_KIND_ENUM64 only if the value has to be represented with 64 bits. In addition, a static inline function btf_kind_core_compat() is introduced which will be used later when libbpf relo_core.c changed. Here the kernel shares the same relo_core.c with libbpf. [1] https://reviews.llvm.org/D124641 Acked-by: Andrii Nakryiko Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20220607062600.3716578-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- tools/include/uapi/linux/btf.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'tools/include/uapi') diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index a9162a6c0284..ec1798b6d3ff 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -36,10 +36,10 @@ struct btf_type { * bits 24-28: kind (e.g. int, ptr, array...etc) * bits 29-30: unused * bit 31: kind_flag, currently used by - * struct, union and fwd + * struct, union, enum, fwd and enum64 */ __u32 info; - /* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC. + /* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64. * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, @@ -63,7 +63,7 @@ enum { BTF_KIND_ARRAY = 3, /* Array */ BTF_KIND_STRUCT = 4, /* Struct */ BTF_KIND_UNION = 5, /* Union */ - BTF_KIND_ENUM = 6, /* Enumeration */ + BTF_KIND_ENUM = 6, /* Enumeration up to 32-bit values */ BTF_KIND_FWD = 7, /* Forward */ BTF_KIND_TYPEDEF = 8, /* Typedef */ BTF_KIND_VOLATILE = 9, /* Volatile */ @@ -76,6 +76,7 @@ enum { BTF_KIND_FLOAT = 16, /* Floating point */ BTF_KIND_DECL_TAG = 17, /* Decl Tag */ BTF_KIND_TYPE_TAG = 18, /* Type Tag */ + BTF_KIND_ENUM64 = 19, /* Enumeration up to 64-bit values */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, @@ -186,4 +187,14 @@ struct btf_decl_tag { __s32 component_idx; }; +/* BTF_KIND_ENUM64 is followed by multiple "struct btf_enum64". + * The exact number of btf_enum64 is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_enum64 { + __u32 name_off; + __u32 val_lo32; + __u32 val_hi32; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ -- cgit From ac80287a6af9fc3f3d189d6d1f523889a0a9e1bc Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 15 Jun 2022 16:48:42 +0300 Subject: bpf: Fix documentation of th_len in bpf_tcp_{gen,check}_syncookie bpf_tcp_gen_syncookie expects the full length of the TCP header (with all options), and bpf_tcp_check_syncookie accepts lengths bigger than sizeof(struct tcphdr). Fix the documentation that says these lengths should be exactly sizeof(struct tcphdr). While at it, fix a typo in the name of struct ipv6hdr. Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Link: https://lore.kernel.org/r/20220615134847.3753567-2-maximmi@nvidia.com Signed-off-by: Alexei Starovoitov --- tools/include/uapi/linux/bpf.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'tools/include/uapi') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f4009dbdf62d..f545e39df72a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3597,10 +3597,11 @@ union bpf_attr { * * *iph* points to the start of the IPv4 or IPv6 header, while * *iph_len* contains **sizeof**\ (**struct iphdr**) or - * **sizeof**\ (**struct ip6hdr**). + * **sizeof**\ (**struct ipv6hdr**). * * *th* points to the start of the TCP header, while *th_len* - * contains **sizeof**\ (**struct tcphdr**). + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). * Return * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative * error otherwise. @@ -3783,10 +3784,11 @@ union bpf_attr { * * *iph* points to the start of the IPv4 or IPv6 header, while * *iph_len* contains **sizeof**\ (**struct iphdr**) or - * **sizeof**\ (**struct ip6hdr**). + * **sizeof**\ (**struct ipv6hdr**). * * *th* points to the start of the TCP header, while *th_len* - * contains the length of the TCP header. + * contains the length of the TCP header with options (at least + * **sizeof**\ (**struct tcphdr**)). * Return * On success, lower 32 bits hold the generated SYN cookie in * followed by 16 bits which hold the MSS value for that cookie, -- cgit From 33bf9885040c399cf6a95bd33216644126728e14 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 15 Jun 2022 16:48:44 +0300 Subject: bpf: Add helpers to issue and check SYN cookies in XDP The new helpers bpf_tcp_raw_{gen,check}_syncookie_ipv{4,6} allow an XDP program to generate SYN cookies in response to TCP SYN packets and to check those cookies upon receiving the first ACK packet (the final packet of the TCP handshake). Unlike bpf_tcp_{gen,check}_syncookie these new helpers don't need a listening socket on the local machine, which allows to use them together with synproxy to accelerate SYN cookie generation. Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Link: https://lore.kernel.org/r/20220615134847.3753567-4-maximmi@nvidia.com Signed-off-by: Alexei Starovoitov --- tools/include/uapi/linux/bpf.h | 78 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 78 insertions(+) (limited to 'tools/include/uapi') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f545e39df72a..e81362891596 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5251,6 +5251,80 @@ union bpf_attr { * Pointer to the underlying dynptr data, NULL if the dynptr is * read-only, if the dynptr is invalid, or if the offset and length * is out of bounds. + * + * s64 bpf_tcp_raw_gen_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IPv4/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + * + * s64 bpf_tcp_raw_gen_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IPv6/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + * + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. + * + * long bpf_tcp_raw_check_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the TCP header. + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK. + * + * On failure, the returned value is one of the following: + * + * **-EACCES** if the SYN cookie is not valid. + * + * long bpf_tcp_raw_check_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the TCP header. + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK. + * + * On failure, the returned value is one of the following: + * + * **-EACCES** if the SYN cookie is not valid. + * + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5457,6 +5531,10 @@ union bpf_attr { FN(dynptr_read), \ FN(dynptr_write), \ FN(dynptr_data), \ + FN(tcp_raw_gen_syncookie_ipv4), \ + FN(tcp_raw_gen_syncookie_ipv6), \ + FN(tcp_raw_check_syncookie_ipv4), \ + FN(tcp_raw_check_syncookie_ipv6), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit