From 644bfe51fa49c22244d24e896cd3fe3ee2f2cfd1 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 14 Jul 2020 15:56:37 +0200 Subject: cpumap: Formalize map value as a named struct As it has been already done for devmap, introduce 'struct bpf_cpumap_val' to formalize the expected values that can be passed in for a CPUMAP. Update cpumap code to use the struct. Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/754f950674665dae6139c061d28c1d982aaf4170.1594734381.git.lorenzo@kernel.org --- include/uapi/linux/bpf.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 5e386389913a..109623527358 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3849,6 +3849,15 @@ struct bpf_devmap_val { } bpf_prog; }; +/* CPUMAP map-value layout + * + * The struct data-layout of map-value is a configuration interface. + * New members can only be added to the end of this structure. + */ +struct bpf_cpumap_val { + __u32 qsize; /* queue size to remote target CPU */ +}; + enum sk_action { SK_DROP = 0, SK_PASS, -- cgit v1.2.3 From 9216477449f33cdbc9c9a99d49f500b7fbb81702 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 14 Jul 2020 15:56:38 +0200 Subject: bpf: cpumap: Add the possibility to attach an eBPF program to cpumap Introduce the capability to attach an eBPF program to cpumap entries. The idea behind this feature is to add the possibility to define on which CPU run the eBPF program if the underlying hw does not support RSS. Current supported verdicts are XDP_DROP and XDP_PASS. This patch has been tested on Marvell ESPRESSObin using xdp_redirect_cpu sample available in the kernel tree to identify possible performance regressions. Results show there are no observable differences in packet-per-second: $./xdp_redirect_cpu --progname xdp_cpu_map0 --dev eth0 --cpu 1 rx: 354.8 Kpps rx: 356.0 Kpps rx: 356.8 Kpps rx: 356.3 Kpps rx: 356.6 Kpps rx: 356.6 Kpps rx: 356.7 Kpps rx: 355.8 Kpps rx: 356.8 Kpps rx: 356.8 Kpps Co-developed-by: Jesper Dangaard Brouer Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/5c9febdf903d810b3415732e5cd98491d7d9067a.1594734381.git.lorenzo@kernel.org --- include/uapi/linux/bpf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 109623527358..c010b57fce3f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -227,6 +227,7 @@ enum bpf_attach_type { BPF_CGROUP_INET6_GETSOCKNAME, BPF_XDP_DEVMAP, BPF_CGROUP_INET_SOCK_RELEASE, + BPF_XDP_CPUMAP, __MAX_BPF_ATTACH_TYPE }; @@ -3856,6 +3857,10 @@ struct bpf_devmap_val { */ struct bpf_cpumap_val { __u32 qsize; /* queue size to remote target CPU */ + union { + int fd; /* prog fd on map write */ + __u32 id; /* prog id on map read */ + } bpf_prog; }; enum sk_action { -- cgit v1.2.3 From bfdfa51702dec67e9fcd52568b4cf3c7f799db8b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 18:29:11 -0700 Subject: bpf: Drop duplicated words in uapi helper comments Drop doubled words "will" and "attach". Signed-off-by: Randy Dunlap Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/6b9f71ae-4f8e-0259-2c5d-187ddaefe6eb@infradead.org --- include/uapi/linux/bpf.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c010b57fce3f..7ac3992dacfe 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2420,7 +2420,7 @@ union bpf_attr { * Look for an IPv6 socket. * * If the *netns* is a negative signed 32-bit integer, then the - * socket lookup table in the netns associated with the *ctx* will + * socket lookup table in the netns associated with the *ctx* * will be used. For the TC hooks, this is the netns of the device * in the skb. For socket hooks, this is the netns of the socket. * If *netns* is any other signed 32-bit value greater than or @@ -2457,7 +2457,7 @@ union bpf_attr { * Look for an IPv6 socket. * * If the *netns* is a negative signed 32-bit integer, then the - * socket lookup table in the netns associated with the *ctx* will + * socket lookup table in the netns associated with the *ctx* * will be used. For the TC hooks, this is the netns of the device * in the skb. For socket hooks, this is the netns of the socket. * If *netns* is any other signed 32-bit value greater than or @@ -4000,7 +4000,7 @@ struct bpf_link_info { /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed * by user and intended to be used by socket (e.g. to bind to, depends on - * attach attach type). + * attach type). */ struct bpf_sock_addr { __u32 user_family; /* Allows 4-byte read, but no write. */ -- cgit v1.2.3 From e9ddbb7707ff5891616240026062b8c1e29864ca Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Fri, 17 Jul 2020 12:35:23 +0200 Subject: bpf: Introduce SK_LOOKUP program type with a dedicated attach point Add a new program type BPF_PROG_TYPE_SK_LOOKUP with a dedicated attach type BPF_SK_LOOKUP. The new program kind is to be invoked by the transport layer when looking up a listening socket for a new connection request for connection oriented protocols, or when looking up an unconnected socket for a packet for connection-less protocols. When called, SK_LOOKUP BPF program can select a socket that will receive the packet. This serves as a mechanism to overcome the limits of what bind() API allows to express. Two use-cases driving this work are: (1) steer packets destined to an IP range, on fixed port to a socket 192.0.2.0/24, port 80 -> NGINX socket (2) steer packets destined to an IP address, on any port to a socket 198.51.100.1, any port -> L7 proxy socket In its run-time context program receives information about the packet that triggered the socket lookup. Namely IP version, L4 protocol identifier, and address 4-tuple. Context can be further extended to include ingress interface identifier. To select a socket BPF program fetches it from a map holding socket references, like SOCKMAP or SOCKHASH, and calls bpf_sk_assign(ctx, sk, ...) helper to record the selection. Transport layer then uses the selected socket as a result of socket lookup. In its basic form, SK_LOOKUP acts as a filter and hence must return either SK_PASS or SK_DROP. If the program returns with SK_PASS, transport should look for a socket to receive the packet, or use the one selected by the program if available, while SK_DROP informs the transport layer that the lookup should fail. This patch only enables the user to attach an SK_LOOKUP program to a network namespace. Subsequent patches hook it up to run on local delivery path in ipv4 and ipv6 stacks. Suggested-by: Marek Majkowski Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200717103536.397595-3-jakub@cloudflare.com --- include/uapi/linux/bpf.h | 77 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 77 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7ac3992dacfe..54d0c886e3ba 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -189,6 +189,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_STRUCT_OPS, BPF_PROG_TYPE_EXT, BPF_PROG_TYPE_LSM, + BPF_PROG_TYPE_SK_LOOKUP, }; enum bpf_attach_type { @@ -228,6 +229,7 @@ enum bpf_attach_type { BPF_XDP_DEVMAP, BPF_CGROUP_INET_SOCK_RELEASE, BPF_XDP_CPUMAP, + BPF_SK_LOOKUP, __MAX_BPF_ATTACH_TYPE }; @@ -3069,6 +3071,10 @@ union bpf_attr { * * long bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags) * Description + * Helper is overloaded depending on BPF program type. This + * description applies to **BPF_PROG_TYPE_SCHED_CLS** and + * **BPF_PROG_TYPE_SCHED_ACT** programs. + * * Assign the *sk* to the *skb*. When combined with appropriate * routing configuration to receive the packet towards the socket, * will cause *skb* to be delivered to the specified socket. @@ -3094,6 +3100,56 @@ union bpf_attr { * **-ESOCKTNOSUPPORT** if the socket type is not supported * (reuseport). * + * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags) + * Description + * Helper is overloaded depending on BPF program type. This + * description applies to **BPF_PROG_TYPE_SK_LOOKUP** programs. + * + * Select the *sk* as a result of a socket lookup. + * + * For the operation to succeed passed socket must be compatible + * with the packet description provided by the *ctx* object. + * + * L4 protocol (**IPPROTO_TCP** or **IPPROTO_UDP**) must + * be an exact match. While IP family (**AF_INET** or + * **AF_INET6**) must be compatible, that is IPv6 sockets + * that are not v6-only can be selected for IPv4 packets. + * + * Only TCP listeners and UDP unconnected sockets can be + * selected. *sk* can also be NULL to reset any previous + * selection. + * + * *flags* argument can combination of following values: + * + * * **BPF_SK_LOOKUP_F_REPLACE** to override the previous + * socket selection, potentially done by a BPF program + * that ran before us. + * + * * **BPF_SK_LOOKUP_F_NO_REUSEPORT** to skip + * load-balancing within reuseport group for the socket + * being selected. + * + * On success *ctx->sk* will point to the selected socket. + * + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EAFNOSUPPORT** if socket family (*sk->family*) is + * not compatible with packet family (*ctx->family*). + * + * * **-EEXIST** if socket has been already selected, + * potentially by another program, and + * **BPF_SK_LOOKUP_F_REPLACE** flag was not specified. + * + * * **-EINVAL** if unsupported flags were specified. + * + * * **-EPROTOTYPE** if socket L4 protocol + * (*sk->protocol*) doesn't match packet protocol + * (*ctx->protocol*). + * + * * **-ESOCKTNOSUPPORT** if socket is not in allowed + * state (TCP listening or UDP unconnected). + * * u64 bpf_ktime_get_boot_ns(void) * Description * Return the time elapsed since system boot, in nanoseconds. @@ -3607,6 +3663,12 @@ enum { BPF_RINGBUF_HDR_SZ = 8, }; +/* BPF_FUNC_sk_assign flags in bpf_sk_lookup context. */ +enum { + BPF_SK_LOOKUP_F_REPLACE = (1ULL << 0), + BPF_SK_LOOKUP_F_NO_REUSEPORT = (1ULL << 1), +}; + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, @@ -4349,4 +4411,19 @@ struct bpf_pidns_info { __u32 pid; __u32 tgid; }; + +/* User accessible data for SK_LOOKUP programs. Add new fields at the end. */ +struct bpf_sk_lookup { + __bpf_md_ptr(struct bpf_sock *, sk); /* Selected socket */ + + __u32 family; /* Protocol family (AF_INET, AF_INET6) */ + __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 */ + __u32 local_ip4; /* Network byte order */ + __u32 local_ip6[4]; /* Network byte order */ + __u32 local_port; /* Host byte order */ +}; + #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.2.3