diff options
Diffstat (limited to 'upstream/fedora-40/man7/bpf-helpers.7')
| -rw-r--r-- | upstream/fedora-40/man7/bpf-helpers.7 | 5128 |
1 files changed, 5128 insertions, 0 deletions
diff --git a/upstream/fedora-40/man7/bpf-helpers.7 b/upstream/fedora-40/man7/bpf-helpers.7 new file mode 100644 index 00000000..26ddf836 --- /dev/null +++ b/upstream/fedora-40/man7/bpf-helpers.7 @@ -0,0 +1,5128 @@ +.\" Man page generated from reStructuredText. +. +. +.nr rst2man-indent-level 0 +. +.de1 rstReportMargin +\\$1 \\n[an-margin] +level \\n[rst2man-indent-level] +level margin: \\n[rst2man-indent\\n[rst2man-indent-level]] +- +\\n[rst2man-indent0] +\\n[rst2man-indent1] +\\n[rst2man-indent2] +.. +.de1 INDENT +.\" .rstReportMargin pre: +. RS \\$1 +. nr rst2man-indent\\n[rst2man-indent-level] \\n[an-margin] +. nr rst2man-indent-level +1 +.\" .rstReportMargin post: +.. +.de UNINDENT +. RE +.\" indent \\n[an-margin] +.\" old: \\n[rst2man-indent\\n[rst2man-indent-level]] +.nr rst2man-indent-level -1 +.\" new: \\n[rst2man-indent\\n[rst2man-indent-level]] +.in \\n[rst2man-indent\\n[rst2man-indent-level]]u +.. +.TH "BPF-HELPERS" 7 "2023-04-11" "Linux v6.2" +.SH NAME +BPF-HELPERS \- list of eBPF helper functions +.\" Copyright (C) All BPF authors and contributors from 2014 to present. +. +.\" See git log include/uapi/linux/bpf.h in kernel tree for details. +. +.\" +. +.\" SPDX-License-Identifier: Linux-man-pages-copyleft +. +.\" +. +.\" Please do not edit this file. It was generated from the documentation +. +.\" located in file include/uapi/linux/bpf.h of the Linux kernel sources +. +.\" (helpers description), and from scripts/bpf_doc.py in the same +. +.\" repository (header and footer). +. +.SH DESCRIPTION +.sp +The extended Berkeley Packet Filter (eBPF) subsystem consists in programs +written in a pseudo\-assembly language, then attached to one of the several +kernel hooks and run in reaction of specific events. This framework differs +from the older, \(dqclassic\(dq BPF (or \(dqcBPF\(dq) in several aspects, one of them being +the ability to call special functions (or \(dqhelpers\(dq) from within a program. +These functions are restricted to a white\-list of helpers defined in the +kernel. +.sp +These helpers are used by eBPF programs to interact with the system, or with +the context in which they work. For instance, they can be used to print +debugging messages, to get the time since the system was booted, to interact +with eBPF maps, or to manipulate network packets. Since there are several eBPF +program types, and that they do not run in the same context, each program type +can only call a subset of those helpers. +.sp +Due to eBPF conventions, a helper can not have more than five arguments. +.sp +Internally, eBPF programs call directly into the compiled helper functions +without requiring any foreign\-function interface. As a result, calling helpers +introduces no overhead, thus offering excellent performance. +.sp +This document is an attempt to list and document the helpers available to eBPF +developers. They are sorted by chronological order (the oldest helpers in the +kernel at the top). +.SH HELPERS +.INDENT 0.0 +.TP +.B \fBvoid *bpf_map_lookup_elem(struct bpf_map *\fP\fImap\fP\fB, const void *\fP\fIkey\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Perform a lookup in \fImap\fP for an entry associated to \fIkey\fP\&. +.TP +.B Return +Map value associated to \fIkey\fP, or \fBNULL\fP if no entry was +found. +.UNINDENT +.TP +.B \fBlong bpf_map_update_elem(struct bpf_map *\fP\fImap\fP\fB, const void *\fP\fIkey\fP\fB, const void *\fP\fIvalue\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Add or update the value of the entry associated to \fIkey\fP in +\fImap\fP with \fIvalue\fP\&. \fIflags\fP is one of: +.INDENT 7.0 +.TP +.B \fBBPF_NOEXIST\fP +The entry for \fIkey\fP must not exist in the map. +.TP +.B \fBBPF_EXIST\fP +The entry for \fIkey\fP must already exist in the map. +.TP +.B \fBBPF_ANY\fP +No condition on the existence of the entry for \fIkey\fP\&. +.UNINDENT +.sp +Flag value \fBBPF_NOEXIST\fP cannot be used for maps of types +\fBBPF_MAP_TYPE_ARRAY\fP or \fBBPF_MAP_TYPE_PERCPU_ARRAY\fP (all +elements always exist), the helper would return an error. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_map_delete_elem(struct bpf_map *\fP\fImap\fP\fB, const void *\fP\fIkey\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Delete entry with \fIkey\fP from \fImap\fP\&. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_probe_read(void *\fP\fIdst\fP\fB, u32\fP \fIsize\fP\fB, const void *\fP\fIunsafe_ptr\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +For tracing programs, safely attempt to read \fIsize\fP bytes from +kernel space address \fIunsafe_ptr\fP and store the data in \fIdst\fP\&. +.sp +Generally, use \fBbpf_probe_read_user\fP() or +\fBbpf_probe_read_kernel\fP() instead. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBu64 bpf_ktime_get_ns(void)\fP +.INDENT 7.0 +.TP +.B Description +Return the time elapsed since system boot, in nanoseconds. +Does not include time the system was suspended. +See: \fBclock_gettime\fP(\fBCLOCK_MONOTONIC\fP) +.TP +.B Return +Current \fIktime\fP\&. +.UNINDENT +.TP +.B \fBlong bpf_trace_printk(const char *\fP\fIfmt\fP\fB, u32\fP \fIfmt_size\fP\fB, ...)\fP +.INDENT 7.0 +.TP +.B Description +This helper is a \(dqprintk()\-like\(dq facility for debugging. It +prints a message defined by format \fIfmt\fP (of size \fIfmt_size\fP) +to file \fI/sys/kernel/debug/tracing/trace\fP from DebugFS, if +available. It can take up to three additional \fBu64\fP +arguments (as an eBPF helpers, the total number of arguments is +limited to five). +.sp +Each time the helper is called, it appends a line to the trace. +Lines are discarded while \fI/sys/kernel/debug/tracing/trace\fP is +open, use \fI/sys/kernel/debug/tracing/trace_pipe\fP to avoid this. +The format of the trace is customizable, and the exact output +one will get depends on the options set in +\fI/sys/kernel/debug/tracing/trace_options\fP (see also the +\fIREADME\fP file under the same directory). However, it usually +defaults to something like: +.INDENT 7.0 +.INDENT 3.5 +.sp +.nf +.ft C +telnet\-470 [001] .N.. 419421.045894: 0x00000001: <fmt> +.ft P +.fi +.UNINDENT +.UNINDENT +.sp +In the above: +.INDENT 7.0 +.INDENT 3.5 +.INDENT 0.0 +.IP \(bu 2 +\fBtelnet\fP is the name of the current task. +.IP \(bu 2 +\fB470\fP is the PID of the current task. +.IP \(bu 2 +\fB001\fP is the CPU number on which the task is +running. +.IP \(bu 2 +In \fB\&.N..\fP, each character refers to a set of +options (whether irqs are enabled, scheduling +options, whether hard/softirqs are running, level of +preempt_disabled respectively). \fBN\fP means that +\fBTIF_NEED_RESCHED\fP and \fBPREEMPT_NEED_RESCHED\fP +are set. +.IP \(bu 2 +\fB419421.045894\fP is a timestamp. +.IP \(bu 2 +\fB0x00000001\fP is a fake value used by BPF for the +instruction pointer register. +.IP \(bu 2 +\fB<fmt>\fP is the message formatted with \fIfmt\fP\&. +.UNINDENT +.UNINDENT +.UNINDENT +.sp +The conversion specifiers supported by \fIfmt\fP are similar, but +more limited than for printk(). They are \fB%d\fP, \fB%i\fP, +\fB%u\fP, \fB%x\fP, \fB%ld\fP, \fB%li\fP, \fB%lu\fP, \fB%lx\fP, \fB%lld\fP, +\fB%lli\fP, \fB%llu\fP, \fB%llx\fP, \fB%p\fP, \fB%s\fP\&. No modifier (size +of field, padding with zeroes, etc.) is available, and the +helper will return \fB\-EINVAL\fP (but print nothing) if it +encounters an unknown specifier. +.sp +Also, note that \fBbpf_trace_printk\fP() is slow, and should +only be used for debugging purposes. For this reason, a notice +block (spanning several lines) is printed to kernel logs and +states that the helper should not be used \(dqfor production use\(dq +the first time this helper is used (or more precisely, when +\fBtrace_printk\fP() buffers are allocated). For passing values +to user space, perf events should be preferred. +.TP +.B Return +The number of bytes written to the buffer, or a negative error +in case of failure. +.UNINDENT +.TP +.B \fBu32 bpf_get_prandom_u32(void)\fP +.INDENT 7.0 +.TP +.B Description +Get a pseudo\-random number. +.sp +From a security point of view, this helper uses its own +pseudo\-random internal state, and cannot be used to infer the +seed of other random functions in the kernel. However, it is +essential to note that the generator used by the helper is not +cryptographically secure. +.TP +.B Return +A random 32\-bit unsigned value. +.UNINDENT +.TP +.B \fBu32 bpf_get_smp_processor_id(void)\fP +.INDENT 7.0 +.TP +.B Description +Get the SMP (symmetric multiprocessing) processor id. Note that +all programs run with migration disabled, which means that the +SMP processor id is stable during all the execution of the +program. +.TP +.B Return +The SMP id of the processor running the program. +.UNINDENT +.TP +.B \fBlong bpf_skb_store_bytes(struct sk_buff *\fP\fIskb\fP\fB, u32\fP \fIoffset\fP\fB, const void *\fP\fIfrom\fP\fB, u32\fP \fIlen\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Store \fIlen\fP bytes from address \fIfrom\fP into the packet +associated to \fIskb\fP, at \fIoffset\fP\&. \fIflags\fP are a combination of +\fBBPF_F_RECOMPUTE_CSUM\fP (automatically recompute the +checksum for the packet after storing the bytes) and +\fBBPF_F_INVALIDATE_HASH\fP (set \fIskb\fP\fB\->hash\fP, \fIskb\fP\fB\->swhash\fP and \fIskb\fP\fB\->l4hash\fP to 0). +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_l3_csum_replace(struct sk_buff *\fP\fIskb\fP\fB, u32\fP \fIoffset\fP\fB, u64\fP \fIfrom\fP\fB, u64\fP \fIto\fP\fB, u64\fP \fIsize\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Recompute the layer 3 (e.g. IP) checksum for the packet +associated to \fIskb\fP\&. Computation is incremental, so the helper +must know the former value of the header field that was +modified (\fIfrom\fP), the new value of this field (\fIto\fP), and the +number of bytes (2 or 4) for this field, stored in \fIsize\fP\&. +Alternatively, it is possible to store the difference between +the previous and the new values of the header field in \fIto\fP, by +setting \fIfrom\fP and \fIsize\fP to 0. For both methods, \fIoffset\fP +indicates the location of the IP checksum within the packet. +.sp +This helper works in combination with \fBbpf_csum_diff\fP(), +which does not update the checksum in\-place, but offers more +flexibility and can handle sizes larger than 2 or 4 for the +checksum to update. +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_l4_csum_replace(struct sk_buff *\fP\fIskb\fP\fB, u32\fP \fIoffset\fP\fB, u64\fP \fIfrom\fP\fB, u64\fP \fIto\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the +packet associated to \fIskb\fP\&. Computation is incremental, so the +helper must know the former value of the header field that was +modified (\fIfrom\fP), the new value of this field (\fIto\fP), and the +number of bytes (2 or 4) for this field, stored on the lowest +four bits of \fIflags\fP\&. Alternatively, it is possible to store +the difference between the previous and the new values of the +header field in \fIto\fP, by setting \fIfrom\fP and the four lowest +bits of \fIflags\fP to 0. For both methods, \fIoffset\fP indicates the +location of the IP checksum within the packet. In addition to +the size of the field, \fIflags\fP can be added (bitwise OR) actual +flags. With \fBBPF_F_MARK_MANGLED_0\fP, a null checksum is left +untouched (unless \fBBPF_F_MARK_ENFORCE\fP is added as well), and +for updates resulting in a null checksum the value is set to +\fBCSUM_MANGLED_0\fP instead. Flag \fBBPF_F_PSEUDO_HDR\fP indicates +the checksum is to be computed against a pseudo\-header. +.sp +This helper works in combination with \fBbpf_csum_diff\fP(), +which does not update the checksum in\-place, but offers more +flexibility and can handle sizes larger than 2 or 4 for the +checksum to update. +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_tail_call(void *\fP\fIctx\fP\fB, struct bpf_map *\fP\fIprog_array_map\fP\fB, u32\fP \fIindex\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +This special helper is used to trigger a \(dqtail call\(dq, or in +other words, to jump into another eBPF program. The same stack +frame is used (but values on stack and in registers for the +caller are not accessible to the callee). This mechanism allows +for program chaining, either for raising the maximum number of +available eBPF instructions, or to execute given programs in +conditional blocks. For security reasons, there is an upper +limit to the number of successive tail calls that can be +performed. +.sp +Upon call of this helper, the program attempts to jump into a +program referenced at index \fIindex\fP in \fIprog_array_map\fP, a +special map of type \fBBPF_MAP_TYPE_PROG_ARRAY\fP, and passes +\fIctx\fP, a pointer to the context. +.sp +If the call succeeds, the kernel immediately runs the first +instruction of the new program. This is not a function call, +and it never returns to the previous program. If the call +fails, then the helper has no effect, and the caller continues +to run its subsequent instructions. A call can fail if the +destination program for the jump does not exist (i.e. \fIindex\fP +is superior to the number of entries in \fIprog_array_map\fP), or +if the maximum number of tail calls has been reached for this +chain of programs. This limit is defined in the kernel by the +macro \fBMAX_TAIL_CALL_CNT\fP (not accessible to user space), +which is currently set to 33. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_clone_redirect(struct sk_buff *\fP\fIskb\fP\fB, u32\fP \fIifindex\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Clone and redirect the packet associated to \fIskb\fP to another +net device of index \fIifindex\fP\&. Both ingress and egress +interfaces can be used for redirection. The \fBBPF_F_INGRESS\fP +value in \fIflags\fP is used to make the distinction (ingress path +is selected if the flag is present, egress path otherwise). +This is the only flag supported for now. +.sp +In comparison with \fBbpf_redirect\fP() helper, +\fBbpf_clone_redirect\fP() has the associated cost of +duplicating the packet buffer, but this can be executed out of +the eBPF program. Conversely, \fBbpf_redirect\fP() is more +efficient, but it is handled through an action code where the +redirection happens only after the eBPF program has returned. +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBu64 bpf_get_current_pid_tgid(void)\fP +.INDENT 7.0 +.TP +.B Description +Get the current pid and tgid. +.TP +.B Return +A 64\-bit integer containing the current tgid and pid, and +created as such: +\fIcurrent_task\fP\fB\->tgid << 32 |\fP +\fIcurrent_task\fP\fB\->pid\fP\&. +.UNINDENT +.TP +.B \fBu64 bpf_get_current_uid_gid(void)\fP +.INDENT 7.0 +.TP +.B Description +Get the current uid and gid. +.TP +.B Return +A 64\-bit integer containing the current GID and UID, and +created as such: \fIcurrent_gid\fP \fB<< 32 |\fP \fIcurrent_uid\fP\&. +.UNINDENT +.TP +.B \fBlong bpf_get_current_comm(void *\fP\fIbuf\fP\fB, u32\fP \fIsize_of_buf\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Copy the \fBcomm\fP attribute of the current task into \fIbuf\fP of +\fIsize_of_buf\fP\&. The \fBcomm\fP attribute contains the name of +the executable (excluding the path) for the current task. The +\fIsize_of_buf\fP must be strictly positive. On success, the +helper makes sure that the \fIbuf\fP is NUL\-terminated. On failure, +it is filled with zeroes. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBu32 bpf_get_cgroup_classid(struct sk_buff *\fP\fIskb\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Retrieve the classid for the current task, i.e. for the net_cls +cgroup to which \fIskb\fP belongs. +.sp +This helper can be used on TC egress path, but not on ingress. +.sp +The net_cls cgroup provides an interface to tag network packets +based on a user\-provided identifier for all traffic coming from +the tasks belonging to the related cgroup. See also the related +kernel documentation, available from the Linux sources in file +\fIDocumentation/admin\-guide/cgroup\-v1/net_cls.rst\fP\&. +.sp +The Linux kernel has two versions for cgroups: there are +cgroups v1 and cgroups v2. Both are available to users, who can +use a mixture of them, but note that the net_cls cgroup is for +cgroup v1 only. This makes it incompatible with BPF programs +run on cgroups, which is a cgroup\-v2\-only feature (a socket can +only hold data for one version of cgroups at a time). +.sp +This helper is only available is the kernel was compiled with +the \fBCONFIG_CGROUP_NET_CLASSID\fP configuration option set to +\(dq\fBy\fP\(dq or to \(dq\fBm\fP\(dq. +.TP +.B Return +The classid, or 0 for the default unconfigured classid. +.UNINDENT +.TP +.B \fBlong bpf_skb_vlan_push(struct sk_buff *\fP\fIskb\fP\fB, __be16\fP \fIvlan_proto\fP\fB, u16\fP \fIvlan_tci\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Push a \fIvlan_tci\fP (VLAN tag control information) of protocol +\fIvlan_proto\fP to the packet associated to \fIskb\fP, then update +the checksum. Note that if \fIvlan_proto\fP is different from +\fBETH_P_8021Q\fP and \fBETH_P_8021AD\fP, it is considered to +be \fBETH_P_8021Q\fP\&. +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_skb_vlan_pop(struct sk_buff *\fP\fIskb\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Pop a VLAN header from the packet associated to \fIskb\fP\&. +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_skb_get_tunnel_key(struct sk_buff *\fP\fIskb\fP\fB, struct bpf_tunnel_key *\fP\fIkey\fP\fB, u32\fP \fIsize\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get tunnel metadata. This helper takes a pointer \fIkey\fP to an +empty \fBstruct bpf_tunnel_key\fP of \fBsize\fP, that will be +filled with tunnel metadata for the packet associated to \fIskb\fP\&. +The \fIflags\fP can be set to \fBBPF_F_TUNINFO_IPV6\fP, which +indicates that the tunnel is based on IPv6 protocol instead of +IPv4. +.sp +The \fBstruct bpf_tunnel_key\fP is an object that generalizes the +principal parameters used by various tunneling protocols into a +single struct. This way, it can be used to easily make a +decision based on the contents of the encapsulation header, +\(dqsummarized\(dq in this struct. In particular, it holds the IP +address of the remote end (IPv4 or IPv6, depending on the case) +in \fIkey\fP\fB\->remote_ipv4\fP or \fIkey\fP\fB\->remote_ipv6\fP\&. Also, +this struct exposes the \fIkey\fP\fB\->tunnel_id\fP, which is +generally mapped to a VNI (Virtual Network Identifier), making +it programmable together with the \fBbpf_skb_set_tunnel_key\fP() helper. +.sp +Let\(aqs imagine that the following code is part of a program +attached to the TC ingress interface, on one end of a GRE +tunnel, and is supposed to filter out all messages coming from +remote ends with IPv4 address other than 10.0.0.1: +.INDENT 7.0 +.INDENT 3.5 +.sp +.nf +.ft C +int ret; +struct bpf_tunnel_key key = {}; + +ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); +if (ret < 0) + return TC_ACT_SHOT; // drop packet + +if (key.remote_ipv4 != 0x0a000001) + return TC_ACT_SHOT; // drop packet + +return TC_ACT_OK; // accept packet +.ft P +.fi +.UNINDENT +.UNINDENT +.sp +This interface can also be used with all encapsulation devices +that can operate in \(dqcollect metadata\(dq mode: instead of having +one network device per specific configuration, the \(dqcollect +metadata\(dq mode only requires a single device where the +configuration can be extracted from this helper. +.sp +This can be used together with various tunnels such as VXLan, +Geneve, GRE or IP in IP (IPIP). +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_skb_set_tunnel_key(struct sk_buff *\fP\fIskb\fP\fB, struct bpf_tunnel_key *\fP\fIkey\fP\fB, u32\fP \fIsize\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Populate tunnel metadata for packet associated to \fIskb.\fP The +tunnel metadata is set to the contents of \fIkey\fP, of \fIsize\fP\&. The +\fIflags\fP can be set to a combination of the following values: +.INDENT 7.0 +.TP +.B \fBBPF_F_TUNINFO_IPV6\fP +Indicate that the tunnel is based on IPv6 protocol +instead of IPv4. +.TP +.B \fBBPF_F_ZERO_CSUM_TX\fP +For IPv4 packets, add a flag to tunnel metadata +indicating that checksum computation should be skipped +and checksum set to zeroes. +.TP +.B \fBBPF_F_DONT_FRAGMENT\fP +Add a flag to tunnel metadata indicating that the +packet should not be fragmented. +.TP +.B \fBBPF_F_SEQ_NUMBER\fP +Add a flag to tunnel metadata indicating that a +sequence number should be added to tunnel header before +sending the packet. This flag was added for GRE +encapsulation, but might be used with other protocols +as well in the future. +.UNINDENT +.sp +Here is a typical usage on the transmit path: +.INDENT 7.0 +.INDENT 3.5 +.sp +.nf +.ft C +struct bpf_tunnel_key key; + populate key ... +bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); +bpf_clone_redirect(skb, vxlan_dev_ifindex, 0); +.ft P +.fi +.UNINDENT +.UNINDENT +.sp +See also the description of the \fBbpf_skb_get_tunnel_key\fP() +helper for additional information. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBu64 bpf_perf_event_read(struct bpf_map *\fP\fImap\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Read the value of a perf event counter. This helper relies on a +\fImap\fP of type \fBBPF_MAP_TYPE_PERF_EVENT_ARRAY\fP\&. The nature of +the perf event counter is selected when \fImap\fP is updated with +perf event file descriptors. The \fImap\fP is an array whose size +is the number of available CPUs, and each cell contains a value +relative to one CPU. The value to retrieve is indicated by +\fIflags\fP, that contains the index of the CPU to look up, masked +with \fBBPF_F_INDEX_MASK\fP\&. Alternatively, \fIflags\fP can be set to +\fBBPF_F_CURRENT_CPU\fP to indicate that the value for the +current CPU should be retrieved. +.sp +Note that before Linux 4.13, only hardware perf event can be +retrieved. +.sp +Also, be aware that the newer helper +\fBbpf_perf_event_read_value\fP() is recommended over +\fBbpf_perf_event_read\fP() in general. The latter has some ABI +quirks where error and counter value are used as a return code +(which is wrong to do since ranges may overlap). This issue is +fixed with \fBbpf_perf_event_read_value\fP(), which at the same +time provides more features over the \fBbpf_perf_event_read\fP() interface. Please refer to the description of +\fBbpf_perf_event_read_value\fP() for details. +.TP +.B Return +The value of the perf event counter read from the map, or a +negative error code in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_redirect(u32\fP \fIifindex\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Redirect the packet to another net device of index \fIifindex\fP\&. +This helper is somewhat similar to \fBbpf_clone_redirect\fP(), except that the packet is not cloned, which provides +increased performance. +.sp +Except for XDP, both ingress and egress interfaces can be used +for redirection. The \fBBPF_F_INGRESS\fP value in \fIflags\fP is used +to make the distinction (ingress path is selected if the flag +is present, egress path otherwise). Currently, XDP only +supports redirection to the egress interface, and accepts no +flag at all. +.sp +The same effect can also be attained with the more generic +\fBbpf_redirect_map\fP(), which uses a BPF map to store the +redirect target instead of providing it directly to the helper. +.TP +.B Return +For XDP, the helper returns \fBXDP_REDIRECT\fP on success or +\fBXDP_ABORTED\fP on error. For other program types, the values +are \fBTC_ACT_REDIRECT\fP on success or \fBTC_ACT_SHOT\fP on +error. +.UNINDENT +.TP +.B \fBu32 bpf_get_route_realm(struct sk_buff *\fP\fIskb\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Retrieve the realm or the route, that is to say the +\fBtclassid\fP field of the destination for the \fIskb\fP\&. The +identifier retrieved is a user\-provided tag, similar to the +one used with the net_cls cgroup (see description for +\fBbpf_get_cgroup_classid\fP() helper), but here this tag is +held by a route (a destination entry), not by a task. +.sp +Retrieving this identifier works with the clsact TC egress hook +(see also \fBtc\-bpf(8)\fP), or alternatively on conventional +classful egress qdiscs, but not on TC ingress path. In case of +clsact TC egress hook, this has the advantage that, internally, +the destination entry has not been dropped yet in the transmit +path. Therefore, the destination entry does not need to be +artificially held via \fBnetif_keep_dst\fP() for a classful +qdisc until the \fIskb\fP is freed. +.sp +This helper is available only if the kernel was compiled with +\fBCONFIG_IP_ROUTE_CLASSID\fP configuration option. +.TP +.B Return +The realm of the route for the packet associated to \fIskb\fP, or 0 +if none was found. +.UNINDENT +.TP +.B \fBlong bpf_perf_event_output(void *\fP\fIctx\fP\fB, struct bpf_map *\fP\fImap\fP\fB, u64\fP \fIflags\fP\fB, void *\fP\fIdata\fP\fB, u64\fP \fIsize\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Write raw \fIdata\fP blob into a special BPF perf event held by +\fImap\fP of type \fBBPF_MAP_TYPE_PERF_EVENT_ARRAY\fP\&. This perf +event must have the following attributes: \fBPERF_SAMPLE_RAW\fP +as \fBsample_type\fP, \fBPERF_TYPE_SOFTWARE\fP as \fBtype\fP, and +\fBPERF_COUNT_SW_BPF_OUTPUT\fP as \fBconfig\fP\&. +.sp +The \fIflags\fP are used to indicate the index in \fImap\fP for which +the value must be put, masked with \fBBPF_F_INDEX_MASK\fP\&. +Alternatively, \fIflags\fP can be set to \fBBPF_F_CURRENT_CPU\fP +to indicate that the index of the current CPU core should be +used. +.sp +The value to write, of \fIsize\fP, is passed through eBPF stack and +pointed by \fIdata\fP\&. +.sp +The context of the program \fIctx\fP needs also be passed to the +helper. +.sp +On user space, a program willing to read the values needs to +call \fBperf_event_open\fP() on the perf event (either for +one or for all CPUs) and to store the file descriptor into the +\fImap\fP\&. This must be done before the eBPF program can send data +into it. An example is available in file +\fIsamples/bpf/trace_output_user.c\fP in the Linux kernel source +tree (the eBPF program counterpart is in +\fIsamples/bpf/trace_output_kern.c\fP). +.sp +\fBbpf_perf_event_output\fP() achieves better performance +than \fBbpf_trace_printk\fP() for sharing data with user +space, and is much better suitable for streaming data from eBPF +programs. +.sp +Note that this helper is not restricted to tracing use cases +and can be used with programs attached to TC or XDP as well, +where it allows for passing data to user space listeners. Data +can be: +.INDENT 7.0 +.IP \(bu 2 +Only custom structs, +.IP \(bu 2 +Only the packet payload, or +.IP \(bu 2 +A combination of both. +.UNINDENT +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_skb_load_bytes(const void *\fP\fIskb\fP\fB, u32\fP \fIoffset\fP\fB, void *\fP\fIto\fP\fB, u32\fP \fIlen\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +This helper was provided as an easy way to load data from a +packet. It can be used to load \fIlen\fP bytes from \fIoffset\fP from +the packet associated to \fIskb\fP, into the buffer pointed by +\fIto\fP\&. +.sp +Since Linux 4.7, usage of this helper has mostly been replaced +by \(dqdirect packet access\(dq, enabling packet data to be +manipulated with \fIskb\fP\fB\->data\fP and \fIskb\fP\fB\->data_end\fP +pointing respectively to the first byte of packet data and to +the byte after the last byte of packet data. However, it +remains useful if one wishes to read large quantities of data +at once from a packet into the eBPF stack. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_get_stackid(void *\fP\fIctx\fP\fB, struct bpf_map *\fP\fImap\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Walk a user or a kernel stack and return its id. To achieve +this, the helper needs \fIctx\fP, which is a pointer to the context +on which the tracing program is executed, and a pointer to a +\fImap\fP of type \fBBPF_MAP_TYPE_STACK_TRACE\fP\&. +.sp +The last argument, \fIflags\fP, holds the number of stack frames to +skip (from 0 to 255), masked with +\fBBPF_F_SKIP_FIELD_MASK\fP\&. The next bits can be used to set +a combination of the following flags: +.INDENT 7.0 +.TP +.B \fBBPF_F_USER_STACK\fP +Collect a user space stack instead of a kernel stack. +.TP +.B \fBBPF_F_FAST_STACK_CMP\fP +Compare stacks by hash only. +.TP +.B \fBBPF_F_REUSE_STACKID\fP +If two different stacks hash into the same \fIstackid\fP, +discard the old one. +.UNINDENT +.sp +The stack id retrieved is a 32 bit long integer handle which +can be further combined with other data (including other stack +ids) and used as a key into maps. This can be useful for +generating a variety of graphs (such as flame graphs or off\-cpu +graphs). +.sp +For walking a stack, this helper is an improvement over +\fBbpf_probe_read\fP(), which can be used with unrolled loops +but is not efficient and consumes a lot of eBPF instructions. +Instead, \fBbpf_get_stackid\fP() can collect up to +\fBPERF_MAX_STACK_DEPTH\fP both kernel and user frames. Note that +this limit can be controlled with the \fBsysctl\fP program, and +that it should be manually increased in order to profile long +user stacks (such as stacks for Java programs). To do so, use: +.INDENT 7.0 +.INDENT 3.5 +.sp +.nf +.ft C +# sysctl kernel.perf_event_max_stack=<new value> +.ft P +.fi +.UNINDENT +.UNINDENT +.TP +.B Return +The positive or null stack id on success, or a negative error +in case of failure. +.UNINDENT +.TP +.B \fBs64 bpf_csum_diff(__be32 *\fP\fIfrom\fP\fB, u32\fP \fIfrom_size\fP\fB, __be32 *\fP\fIto\fP\fB, u32\fP \fIto_size\fP\fB, __wsum\fP \fIseed\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Compute a checksum difference, from the raw buffer pointed by +\fIfrom\fP, of length \fIfrom_size\fP (that must be a multiple of 4), +towards the raw buffer pointed by \fIto\fP, of size \fIto_size\fP +(same remark). An optional \fIseed\fP can be added to the value +(this can be cascaded, the seed may come from a previous call +to the helper). +.sp +This is flexible enough to be used in several ways: +.INDENT 7.0 +.IP \(bu 2 +With \fIfrom_size\fP == 0, \fIto_size\fP > 0 and \fIseed\fP set to +checksum, it can be used when pushing new data. +.IP \(bu 2 +With \fIfrom_size\fP > 0, \fIto_size\fP == 0 and \fIseed\fP set to +checksum, it can be used when removing data from a packet. +.IP \(bu 2 +With \fIfrom_size\fP > 0, \fIto_size\fP > 0 and \fIseed\fP set to 0, it +can be used to compute a diff. Note that \fIfrom_size\fP and +\fIto_size\fP do not need to be equal. +.UNINDENT +.sp +This helper can be used in combination with +\fBbpf_l3_csum_replace\fP() and \fBbpf_l4_csum_replace\fP(), to +which one can feed in the difference computed with +\fBbpf_csum_diff\fP(). +.TP +.B Return +The checksum result, or a negative error code in case of +failure. +.UNINDENT +.TP +.B \fBlong bpf_skb_get_tunnel_opt(struct sk_buff *\fP\fIskb\fP\fB, void *\fP\fIopt\fP\fB, u32\fP \fIsize\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Retrieve tunnel options metadata for the packet associated to +\fIskb\fP, and store the raw tunnel option data to the buffer \fIopt\fP +of \fIsize\fP\&. +.sp +This helper can be used with encapsulation devices that can +operate in \(dqcollect metadata\(dq mode (please refer to the related +note in the description of \fBbpf_skb_get_tunnel_key\fP() for +more details). A particular example where this can be used is +in combination with the Geneve encapsulation protocol, where it +allows for pushing (with \fBbpf_skb_get_tunnel_opt\fP() helper) +and retrieving arbitrary TLVs (Type\-Length\-Value headers) from +the eBPF program. This allows for full customization of these +headers. +.TP +.B Return +The size of the option data retrieved. +.UNINDENT +.TP +.B \fBlong bpf_skb_set_tunnel_opt(struct sk_buff *\fP\fIskb\fP\fB, void *\fP\fIopt\fP\fB, u32\fP \fIsize\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Set tunnel options metadata for the packet associated to \fIskb\fP +to the option data contained in the raw buffer \fIopt\fP of \fIsize\fP\&. +.sp +See also the description of the \fBbpf_skb_get_tunnel_opt\fP() +helper for additional information. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_skb_change_proto(struct sk_buff *\fP\fIskb\fP\fB, __be16\fP \fIproto\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Change the protocol of the \fIskb\fP to \fIproto\fP\&. Currently +supported are transition from IPv4 to IPv6, and from IPv6 to +IPv4. The helper takes care of the groundwork for the +transition, including resizing the socket buffer. The eBPF +program is expected to fill the new headers, if any, via +\fBskb_store_bytes\fP() and to recompute the checksums with +\fBbpf_l3_csum_replace\fP() and \fBbpf_l4_csum_replace\fP(). The main case for this helper is to perform NAT64 +operations out of an eBPF program. +.sp +Internally, the GSO type is marked as dodgy so that headers are +checked and segments are recalculated by the GSO/GRO engine. +The size for GSO target is adapted as well. +.sp +All values for \fIflags\fP are reserved for future usage, and must +be left at zero. +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_skb_change_type(struct sk_buff *\fP\fIskb\fP\fB, u32\fP \fItype\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Change the packet type for the packet associated to \fIskb\fP\&. This +comes down to setting \fIskb\fP\fB\->pkt_type\fP to \fItype\fP, except +the eBPF program does not have a write access to \fIskb\fP\fB\->pkt_type\fP beside this helper. Using a helper here allows +for graceful handling of errors. +.sp +The major use case is to change incoming \fIskb*s to +**PACKET_HOST*\fP in a programmatic way instead of having to +recirculate via \fBredirect\fP(..., \fBBPF_F_INGRESS\fP), for +example. +.sp +Note that \fItype\fP only allows certain values. At this time, they +are: +.INDENT 7.0 +.TP +.B \fBPACKET_HOST\fP +Packet is for us. +.TP +.B \fBPACKET_BROADCAST\fP +Send packet to all. +.TP +.B \fBPACKET_MULTICAST\fP +Send packet to group. +.TP +.B \fBPACKET_OTHERHOST\fP +Send packet to someone else. +.UNINDENT +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_skb_under_cgroup(struct sk_buff *\fP\fIskb\fP\fB, struct bpf_map *\fP\fImap\fP\fB, u32\fP \fIindex\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Check whether \fIskb\fP is a descendant of the cgroup2 held by +\fImap\fP of type \fBBPF_MAP_TYPE_CGROUP_ARRAY\fP, at \fIindex\fP\&. +.TP +.B Return +The return value depends on the result of the test, and can be: +.INDENT 7.0 +.IP \(bu 2 +0, if the \fIskb\fP failed the cgroup2 descendant test. +.IP \(bu 2 +1, if the \fIskb\fP succeeded the cgroup2 descendant test. +.IP \(bu 2 +A negative error code, if an error occurred. +.UNINDENT +.UNINDENT +.TP +.B \fBu32 bpf_get_hash_recalc(struct sk_buff *\fP\fIskb\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Retrieve the hash of the packet, \fIskb\fP\fB\->hash\fP\&. If it is +not set, in particular if the hash was cleared due to mangling, +recompute this hash. Later accesses to the hash can be done +directly with \fIskb\fP\fB\->hash\fP\&. +.sp +Calling \fBbpf_set_hash_invalid\fP(), changing a packet +prototype with \fBbpf_skb_change_proto\fP(), or calling +\fBbpf_skb_store_bytes\fP() with the +\fBBPF_F_INVALIDATE_HASH\fP are actions susceptible to clear +the hash and to trigger a new computation for the next call to +\fBbpf_get_hash_recalc\fP(). +.TP +.B Return +The 32\-bit hash. +.UNINDENT +.TP +.B \fBu64 bpf_get_current_task(void)\fP +.INDENT 7.0 +.TP +.B Description +Get the current task. +.TP +.B Return +A pointer to the current task struct. +.UNINDENT +.TP +.B \fBlong bpf_probe_write_user(void *\fP\fIdst\fP\fB, const void *\fP\fIsrc\fP\fB, u32\fP \fIlen\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Attempt in a safe way to write \fIlen\fP bytes from the buffer +\fIsrc\fP to \fIdst\fP in memory. It only works for threads that are in +user context, and \fIdst\fP must be a valid user space address. +.sp +This helper should not be used to implement any kind of +security mechanism because of TOC\-TOU attacks, but rather to +debug, divert, and manipulate execution of semi\-cooperative +processes. +.sp +Keep in mind that this feature is meant for experiments, and it +has a risk of crashing the system and running programs. +Therefore, when an eBPF program using this helper is attached, +a warning including PID and process name is printed to kernel +logs. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_current_task_under_cgroup(struct bpf_map *\fP\fImap\fP\fB, u32\fP \fIindex\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Check whether the probe is being run is the context of a given +subset of the cgroup2 hierarchy. The cgroup2 to test is held by +\fImap\fP of type \fBBPF_MAP_TYPE_CGROUP_ARRAY\fP, at \fIindex\fP\&. +.TP +.B Return +The return value depends on the result of the test, and can be: +.INDENT 7.0 +.IP \(bu 2 +1, if current task belongs to the cgroup2. +.IP \(bu 2 +0, if current task does not belong to the cgroup2. +.IP \(bu 2 +A negative error code, if an error occurred. +.UNINDENT +.UNINDENT +.TP +.B \fBlong bpf_skb_change_tail(struct sk_buff *\fP\fIskb\fP\fB, u32\fP \fIlen\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Resize (trim or grow) the packet associated to \fIskb\fP to the +new \fIlen\fP\&. The \fIflags\fP are reserved for future usage, and must +be left at zero. +.sp +The basic idea is that the helper performs the needed work to +change the size of the packet, then the eBPF program rewrites +the rest via helpers like \fBbpf_skb_store_bytes\fP(), +\fBbpf_l3_csum_replace\fP(), \fBbpf_l3_csum_replace\fP() +and others. This helper is a slow path utility intended for +replies with control messages. And because it is targeted for +slow path, the helper itself can afford to be slow: it +implicitly linearizes, unclones and drops offloads from the +\fIskb\fP\&. +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_skb_pull_data(struct sk_buff *\fP\fIskb\fP\fB, u32\fP \fIlen\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Pull in non\-linear data in case the \fIskb\fP is non\-linear and not +all of \fIlen\fP are part of the linear section. Make \fIlen\fP bytes +from \fIskb\fP readable and writable. If a zero value is passed for +\fIlen\fP, then all bytes in the linear part of \fIskb\fP will be made +readable and writable. +.sp +This helper is only needed for reading and writing with direct +packet access. +.sp +For direct packet access, testing that offsets to access +are within packet boundaries (test on \fIskb\fP\fB\->data_end\fP) is +susceptible to fail if offsets are invalid, or if the requested +data is in non\-linear parts of the \fIskb\fP\&. On failure the +program can just bail out, or in the case of a non\-linear +buffer, use a helper to make the data available. The +\fBbpf_skb_load_bytes\fP() helper is a first solution to access +the data. Another one consists in using \fBbpf_skb_pull_data\fP +to pull in once the non\-linear parts, then retesting and +eventually access the data. +.sp +At the same time, this also makes sure the \fIskb\fP is uncloned, +which is a necessary condition for direct write. As this needs +to be an invariant for the write part only, the verifier +detects writes and adds a prologue that is calling +\fBbpf_skb_pull_data()\fP to effectively unclone the \fIskb\fP from +the very beginning in case it is indeed cloned. +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBs64 bpf_csum_update(struct sk_buff *\fP\fIskb\fP\fB, __wsum\fP \fIcsum\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Add the checksum \fIcsum\fP into \fIskb\fP\fB\->csum\fP in case the +driver has supplied a checksum for the entire packet into that +field. Return an error otherwise. This helper is intended to be +used in combination with \fBbpf_csum_diff\fP(), in particular +when the checksum needs to be updated after data has been +written into the packet through direct packet access. +.TP +.B Return +The checksum on success, or a negative error code in case of +failure. +.UNINDENT +.TP +.B \fBvoid bpf_set_hash_invalid(struct sk_buff *\fP\fIskb\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Invalidate the current \fIskb\fP\fB\->hash\fP\&. It can be used after +mangling on headers through direct packet access, in order to +indicate that the hash is outdated and to trigger a +recalculation the next time the kernel tries to access this +hash or when the \fBbpf_get_hash_recalc\fP() helper is called. +.TP +.B Return +void. +.UNINDENT +.TP +.B \fBlong bpf_get_numa_node_id(void)\fP +.INDENT 7.0 +.TP +.B Description +Return the id of the current NUMA node. The primary use case +for this helper is the selection of sockets for the local NUMA +node, when the program is attached to sockets using the +\fBSO_ATTACH_REUSEPORT_EBPF\fP option (see also \fBsocket(7)\fP), +but the helper is also available to other eBPF program types, +similarly to \fBbpf_get_smp_processor_id\fP(). +.TP +.B Return +The id of current NUMA node. +.UNINDENT +.TP +.B \fBlong bpf_skb_change_head(struct sk_buff *\fP\fIskb\fP\fB, u32\fP \fIlen\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Grows headroom of packet associated to \fIskb\fP and adjusts the +offset of the MAC header accordingly, adding \fIlen\fP bytes of +space. It automatically extends and reallocates memory as +required. +.sp +This helper can be used on a layer 3 \fIskb\fP to push a MAC header +for redirection into a layer 2 device. +.sp +All values for \fIflags\fP are reserved for future usage, and must +be left at zero. +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_xdp_adjust_head(struct xdp_buff *\fP\fIxdp_md\fP\fB, int\fP \fIdelta\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Adjust (move) \fIxdp_md\fP\fB\->data\fP by \fIdelta\fP bytes. Note that +it is possible to use a negative value for \fIdelta\fP\&. This helper +can be used to prepare the packet for pushing or popping +headers. +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_probe_read_str(void *\fP\fIdst\fP\fB, u32\fP \fIsize\fP\fB, const void *\fP\fIunsafe_ptr\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Copy a NUL terminated string from an unsafe kernel address +\fIunsafe_ptr\fP to \fIdst\fP\&. See \fBbpf_probe_read_kernel_str\fP() for +more details. +.sp +Generally, use \fBbpf_probe_read_user_str\fP() or +\fBbpf_probe_read_kernel_str\fP() instead. +.TP +.B Return +On success, the strictly positive length of the string, +including the trailing NUL character. On error, a negative +value. +.UNINDENT +.TP +.B \fBu64 bpf_get_socket_cookie(struct sk_buff *\fP\fIskb\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +If the \fBstruct sk_buff\fP pointed by \fIskb\fP has a known socket, +retrieve the cookie (generated by the kernel) of this socket. +If no cookie has been set yet, generate a new cookie. Once +generated, the socket cookie remains stable for the life of the +socket. This helper can be useful for monitoring per socket +networking traffic statistics as it provides a global socket +identifier that can be assumed unique. +.TP +.B Return +A 8\-byte long unique number on success, or 0 if the socket +field is missing inside \fIskb\fP\&. +.UNINDENT +.TP +.B \fBu64 bpf_get_socket_cookie(struct bpf_sock_addr *\fP\fIctx\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Equivalent to bpf_get_socket_cookie() helper that accepts +\fIskb\fP, but gets socket from \fBstruct bpf_sock_addr\fP context. +.TP +.B Return +A 8\-byte long unique number. +.UNINDENT +.TP +.B \fBu64 bpf_get_socket_cookie(struct bpf_sock_ops *\fP\fIctx\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Equivalent to \fBbpf_get_socket_cookie\fP() helper that accepts +\fIskb\fP, but gets socket from \fBstruct bpf_sock_ops\fP context. +.TP +.B Return +A 8\-byte long unique number. +.UNINDENT +.TP +.B \fBu64 bpf_get_socket_cookie(struct sock *\fP\fIsk\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Equivalent to \fBbpf_get_socket_cookie\fP() helper that accepts +\fIsk\fP, but gets socket from a BTF \fBstruct sock\fP\&. This helper +also works for sleepable programs. +.TP +.B Return +A 8\-byte long unique number or 0 if \fIsk\fP is NULL. +.UNINDENT +.TP +.B \fBu32 bpf_get_socket_uid(struct sk_buff *\fP\fIskb\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get the owner UID of the socked associated to \fIskb\fP\&. +.TP +.B Return +The owner UID of the socket associated to \fIskb\fP\&. If the socket +is \fBNULL\fP, or if it is not a full socket (i.e. if it is a +time\-wait or a request socket instead), \fBoverflowuid\fP value +is returned (note that \fBoverflowuid\fP might also be the actual +UID value for the socket). +.UNINDENT +.TP +.B \fBlong bpf_set_hash(struct sk_buff *\fP\fIskb\fP\fB, u32\fP \fIhash\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Set the full hash for \fIskb\fP (set the field \fIskb\fP\fB\->hash\fP) +to value \fIhash\fP\&. +.TP +.B Return +0 +.UNINDENT +.TP +.B \fBlong bpf_setsockopt(void *\fP\fIbpf_socket\fP\fB, int\fP \fIlevel\fP\fB, int\fP \fIoptname\fP\fB, void *\fP\fIoptval\fP\fB, int\fP \fIoptlen\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Emulate a call to \fBsetsockopt()\fP on the socket associated to +\fIbpf_socket\fP, which must be a full socket. The \fIlevel\fP at +which the option resides and the name \fIoptname\fP of the option +must be specified, see \fBsetsockopt(2)\fP for more information. +The option value of length \fIoptlen\fP is pointed by \fIoptval\fP\&. +.sp +\fIbpf_socket\fP should be one of the following: +.INDENT 7.0 +.IP \(bu 2 +\fBstruct bpf_sock_ops\fP for \fBBPF_PROG_TYPE_SOCK_OPS\fP\&. +.IP \(bu 2 +\fBstruct bpf_sock_addr\fP for \fBBPF_CGROUP_INET4_CONNECT\fP +and \fBBPF_CGROUP_INET6_CONNECT\fP\&. +.UNINDENT +.sp +This helper actually implements a subset of \fBsetsockopt()\fP\&. +It supports the following \fIlevel\fPs: +.INDENT 7.0 +.IP \(bu 2 +\fBSOL_SOCKET\fP, which supports the following \fIoptname\fPs: +\fBSO_RCVBUF\fP, \fBSO_SNDBUF\fP, \fBSO_MAX_PACING_RATE\fP, +\fBSO_PRIORITY\fP, \fBSO_RCVLOWAT\fP, \fBSO_MARK\fP, +\fBSO_BINDTODEVICE\fP, \fBSO_KEEPALIVE\fP, \fBSO_REUSEADDR\fP, +\fBSO_REUSEPORT\fP, \fBSO_BINDTOIFINDEX\fP, \fBSO_TXREHASH\fP\&. +.IP \(bu 2 +\fBIPPROTO_TCP\fP, which supports the following \fIoptname\fPs: +\fBTCP_CONGESTION\fP, \fBTCP_BPF_IW\fP, +\fBTCP_BPF_SNDCWND_CLAMP\fP, \fBTCP_SAVE_SYN\fP, +\fBTCP_KEEPIDLE\fP, \fBTCP_KEEPINTVL\fP, \fBTCP_KEEPCNT\fP, +\fBTCP_SYNCNT\fP, \fBTCP_USER_TIMEOUT\fP, \fBTCP_NOTSENT_LOWAT\fP, +\fBTCP_NODELAY\fP, \fBTCP_MAXSEG\fP, \fBTCP_WINDOW_CLAMP\fP, +\fBTCP_THIN_LINEAR_TIMEOUTS\fP, \fBTCP_BPF_DELACK_MAX\fP, +\fBTCP_BPF_RTO_MIN\fP\&. +.IP \(bu 2 +\fBIPPROTO_IP\fP, which supports \fIoptname\fP \fBIP_TOS\fP\&. +.IP \(bu 2 +\fBIPPROTO_IPV6\fP, which supports the following \fIoptname\fPs: +\fBIPV6_TCLASS\fP, \fBIPV6_AUTOFLOWLABEL\fP\&. +.UNINDENT +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_skb_adjust_room(struct sk_buff *\fP\fIskb\fP\fB, s32\fP \fIlen_diff\fP\fB, u32\fP \fImode\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Grow or shrink the room for data in the packet associated to +\fIskb\fP by \fIlen_diff\fP, and according to the selected \fImode\fP\&. +.sp +By default, the helper will reset any offloaded checksum +indicator of the skb to CHECKSUM_NONE. This can be avoided +by the following flag: +.INDENT 7.0 +.IP \(bu 2 +\fBBPF_F_ADJ_ROOM_NO_CSUM_RESET\fP: Do not reset offloaded +checksum data of the skb to CHECKSUM_NONE. +.UNINDENT +.sp +There are two supported modes at this time: +.INDENT 7.0 +.IP \(bu 2 +\fBBPF_ADJ_ROOM_MAC\fP: Adjust room at the mac layer +(room space is added or removed between the layer 2 and +layer 3 headers). +.IP \(bu 2 +\fBBPF_ADJ_ROOM_NET\fP: Adjust room at the network layer +(room space is added or removed between the layer 3 and +layer 4 headers). +.UNINDENT +.sp +The following flags are supported at this time: +.INDENT 7.0 +.IP \(bu 2 +\fBBPF_F_ADJ_ROOM_FIXED_GSO\fP: Do not adjust gso_size. +Adjusting mss in this way is not allowed for datagrams. +.IP \(bu 2 +\fBBPF_F_ADJ_ROOM_ENCAP_L3_IPV4\fP, +\fBBPF_F_ADJ_ROOM_ENCAP_L3_IPV6\fP: +Any new space is reserved to hold a tunnel header. +Configure skb offsets and other fields accordingly. +.IP \(bu 2 +\fBBPF_F_ADJ_ROOM_ENCAP_L4_GRE\fP, +\fBBPF_F_ADJ_ROOM_ENCAP_L4_UDP\fP: +Use with ENCAP_L3 flags to further specify the tunnel type. +.IP \(bu 2 +\fBBPF_F_ADJ_ROOM_ENCAP_L2\fP(\fIlen\fP): +Use with ENCAP_L3/L4 flags to further specify the tunnel +type; \fIlen\fP is the length of the inner MAC header. +.IP \(bu 2 +\fBBPF_F_ADJ_ROOM_ENCAP_L2_ETH\fP: +Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the +L2 type as Ethernet. +.UNINDENT +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_redirect_map(struct bpf_map *\fP\fImap\fP\fB, u64\fP \fIkey\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Redirect the packet to the endpoint referenced by \fImap\fP at +index \fIkey\fP\&. Depending on its type, this \fImap\fP can contain +references to net devices (for forwarding packets through other +ports), or to CPUs (for redirecting XDP frames to another CPU; +but this is only implemented for native XDP (with driver +support) as of this writing). +.sp +The lower two bits of \fIflags\fP are used as the return code if +the map lookup fails. This is so that the return value can be +one of the XDP program return codes up to \fBXDP_TX\fP, as chosen +by the caller. The higher bits of \fIflags\fP can be set to +BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below. +.sp +With BPF_F_BROADCAST the packet will be broadcasted to all the +interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress +interface will be excluded when do broadcasting. +.sp +See also \fBbpf_redirect\fP(), which only supports redirecting +to an ifindex, but doesn\(aqt require a map to do so. +.TP +.B Return +\fBXDP_REDIRECT\fP on success, or the value of the two lower bits +of the \fIflags\fP argument on error. +.UNINDENT +.TP +.B \fBlong bpf_sk_redirect_map(struct sk_buff *\fP\fIskb\fP\fB, struct bpf_map *\fP\fImap\fP\fB, u32\fP \fIkey\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Redirect the packet to the socket referenced by \fImap\fP (of type +\fBBPF_MAP_TYPE_SOCKMAP\fP) at index \fIkey\fP\&. Both ingress and +egress interfaces can be used for redirection. The +\fBBPF_F_INGRESS\fP value in \fIflags\fP is used to make the +distinction (ingress path is selected if the flag is present, +egress path otherwise). This is the only flag supported for now. +.TP +.B Return +\fBSK_PASS\fP on success, or \fBSK_DROP\fP on error. +.UNINDENT +.TP +.B \fBlong bpf_sock_map_update(struct bpf_sock_ops *\fP\fIskops\fP\fB, struct bpf_map *\fP\fImap\fP\fB, void *\fP\fIkey\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Add an entry to, or update a \fImap\fP referencing sockets. The +\fIskops\fP is used as a new value for the entry associated to +\fIkey\fP\&. \fIflags\fP is one of: +.INDENT 7.0 +.TP +.B \fBBPF_NOEXIST\fP +The entry for \fIkey\fP must not exist in the map. +.TP +.B \fBBPF_EXIST\fP +The entry for \fIkey\fP must already exist in the map. +.TP +.B \fBBPF_ANY\fP +No condition on the existence of the entry for \fIkey\fP\&. +.UNINDENT +.sp +If the \fImap\fP has eBPF programs (parser and verdict), those will +be inherited by the socket being added. If the socket is +already attached to eBPF programs, this results in an error. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_xdp_adjust_meta(struct xdp_buff *\fP\fIxdp_md\fP\fB, int\fP \fIdelta\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Adjust the address pointed by \fIxdp_md\fP\fB\->data_meta\fP by +\fIdelta\fP (which can be positive or negative). Note that this +operation modifies the address stored in \fIxdp_md\fP\fB\->data\fP, +so the latter must be loaded only after the helper has been +called. +.sp +The use of \fIxdp_md\fP\fB\->data_meta\fP is optional and programs +are not required to use it. The rationale is that when the +packet is processed with XDP (e.g. as DoS filter), it is +possible to push further meta data along with it before passing +to the stack, and to give the guarantee that an ingress eBPF +program attached as a TC classifier on the same device can pick +this up for further post\-processing. Since TC works with socket +buffers, it remains possible to set from XDP the \fBmark\fP or +\fBpriority\fP pointers, or other pointers for the socket buffer. +Having this scratch space generic and programmable allows for +more flexibility as the user is free to store whatever meta +data they need. +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_perf_event_read_value(struct bpf_map *\fP\fImap\fP\fB, u64\fP \fIflags\fP\fB, struct bpf_perf_event_value *\fP\fIbuf\fP\fB, u32\fP \fIbuf_size\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Read the value of a perf event counter, and store it into \fIbuf\fP +of size \fIbuf_size\fP\&. This helper relies on a \fImap\fP of type +\fBBPF_MAP_TYPE_PERF_EVENT_ARRAY\fP\&. The nature of the perf event +counter is selected when \fImap\fP is updated with perf event file +descriptors. The \fImap\fP is an array whose size is the number of +available CPUs, and each cell contains a value relative to one +CPU. The value to retrieve is indicated by \fIflags\fP, that +contains the index of the CPU to look up, masked with +\fBBPF_F_INDEX_MASK\fP\&. Alternatively, \fIflags\fP can be set to +\fBBPF_F_CURRENT_CPU\fP to indicate that the value for the +current CPU should be retrieved. +.sp +This helper behaves in a way close to +\fBbpf_perf_event_read\fP() helper, save that instead of +just returning the value observed, it fills the \fIbuf\fP +structure. This allows for additional data to be retrieved: in +particular, the enabled and running times (in \fIbuf\fP\fB\->enabled\fP and \fIbuf\fP\fB\->running\fP, respectively) are +copied. In general, \fBbpf_perf_event_read_value\fP() is +recommended over \fBbpf_perf_event_read\fP(), which has some +ABI issues and provides fewer functionalities. +.sp +These values are interesting, because hardware PMU (Performance +Monitoring Unit) counters are limited resources. When there are +more PMU based perf events opened than available counters, +kernel will multiplex these events so each event gets certain +percentage (but not all) of the PMU time. In case that +multiplexing happens, the number of samples or counter value +will not reflect the case compared to when no multiplexing +occurs. This makes comparison between different runs difficult. +Typically, the counter value should be normalized before +comparing to other experiments. The usual normalization is done +as follows. +.INDENT 7.0 +.INDENT 3.5 +.sp +.nf +.ft C +normalized_counter = counter * t_enabled / t_running +.ft P +.fi +.UNINDENT +.UNINDENT +.sp +Where t_enabled is the time enabled for event and t_running is +the time running for event since last normalization. The +enabled and running times are accumulated since the perf event +open. To achieve scaling factor between two invocations of an +eBPF program, users can use CPU id as the key (which is +typical for perf array usage model) to remember the previous +value and do the calculation inside the eBPF program. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_perf_prog_read_value(struct bpf_perf_event_data *\fP\fIctx\fP\fB, struct bpf_perf_event_value *\fP\fIbuf\fP\fB, u32\fP \fIbuf_size\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +For en eBPF program attached to a perf event, retrieve the +value of the event counter associated to \fIctx\fP and store it in +the structure pointed by \fIbuf\fP and of size \fIbuf_size\fP\&. Enabled +and running times are also stored in the structure (see +description of helper \fBbpf_perf_event_read_value\fP() for +more details). +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_getsockopt(void *\fP\fIbpf_socket\fP\fB, int\fP \fIlevel\fP\fB, int\fP \fIoptname\fP\fB, void *\fP\fIoptval\fP\fB, int\fP \fIoptlen\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Emulate a call to \fBgetsockopt()\fP on the socket associated to +\fIbpf_socket\fP, which must be a full socket. The \fIlevel\fP at +which the option resides and the name \fIoptname\fP of the option +must be specified, see \fBgetsockopt(2)\fP for more information. +The retrieved value is stored in the structure pointed by +\fIopval\fP and of length \fIoptlen\fP\&. +.sp +\fIbpf_socket\fP should be one of the following: +.INDENT 7.0 +.IP \(bu 2 +\fBstruct bpf_sock_ops\fP for \fBBPF_PROG_TYPE_SOCK_OPS\fP\&. +.IP \(bu 2 +\fBstruct bpf_sock_addr\fP for \fBBPF_CGROUP_INET4_CONNECT\fP +and \fBBPF_CGROUP_INET6_CONNECT\fP\&. +.UNINDENT +.sp +This helper actually implements a subset of \fBgetsockopt()\fP\&. +It supports the same set of \fIoptname\fPs that is supported by +the \fBbpf_setsockopt\fP() helper. The exceptions are +\fBTCP_BPF_*\fP is \fBbpf_setsockopt\fP() only and +\fBTCP_SAVED_SYN\fP is \fBbpf_getsockopt\fP() only. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_override_return(struct pt_regs *\fP\fIregs\fP\fB, u64\fP \fIrc\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Used for error injection, this helper uses kprobes to override +the return value of the probed function, and to set it to \fIrc\fP\&. +The first argument is the context \fIregs\fP on which the kprobe +works. +.sp +This helper works by setting the PC (program counter) +to an override function which is run in place of the original +probed function. This means the probed function is not run at +all. The replacement function just returns with the required +value. +.sp +This helper has security implications, and thus is subject to +restrictions. It is only available if the kernel was compiled +with the \fBCONFIG_BPF_KPROBE_OVERRIDE\fP configuration +option, and in this case it only works on functions tagged with +\fBALLOW_ERROR_INJECTION\fP in the kernel code. +.sp +Also, the helper is only available for the architectures having +the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing, +x86 architecture is the only one to support this feature. +.TP +.B Return +0 +.UNINDENT +.TP +.B \fBlong bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *\fP\fIbpf_sock\fP\fB, int\fP \fIargval\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Attempt to set the value of the \fBbpf_sock_ops_cb_flags\fP field +for the full TCP socket associated to \fIbpf_sock_ops\fP to +\fIargval\fP\&. +.sp +The primary use of this field is to determine if there should +be calls to eBPF programs of type +\fBBPF_PROG_TYPE_SOCK_OPS\fP at various points in the TCP +code. A program of the same type can change its value, per +connection and as necessary, when the connection is +established. This field is directly accessible for reading, but +this helper must be used for updates in order to return an +error if an eBPF program tries to set a callback that is not +supported in the current kernel. +.sp +\fIargval\fP is a flag array which can combine these flags: +.INDENT 7.0 +.IP \(bu 2 +\fBBPF_SOCK_OPS_RTO_CB_FLAG\fP (retransmission time out) +.IP \(bu 2 +\fBBPF_SOCK_OPS_RETRANS_CB_FLAG\fP (retransmission) +.IP \(bu 2 +\fBBPF_SOCK_OPS_STATE_CB_FLAG\fP (TCP state change) +.IP \(bu 2 +\fBBPF_SOCK_OPS_RTT_CB_FLAG\fP (every RTT) +.UNINDENT +.sp +Therefore, this function can be used to clear a callback flag by +setting the appropriate bit to zero. e.g. to disable the RTO +callback: +.INDENT 7.0 +.TP +.B \fBbpf_sock_ops_cb_flags_set(bpf_sock,\fP +\fBbpf_sock\->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)\fP +.UNINDENT +.sp +Here are some examples of where one could call such eBPF +program: +.INDENT 7.0 +.IP \(bu 2 +When RTO fires. +.IP \(bu 2 +When a packet is retransmitted. +.IP \(bu 2 +When the connection terminates. +.IP \(bu 2 +When a packet is sent. +.IP \(bu 2 +When a packet is received. +.UNINDENT +.TP +.B Return +Code \fB\-EINVAL\fP if the socket is not a full TCP socket; +otherwise, a positive number containing the bits that could not +be set is returned (which comes down to 0 if all bits were set +as required). +.UNINDENT +.TP +.B \fBlong bpf_msg_redirect_map(struct sk_msg_buff *\fP\fImsg\fP\fB, struct bpf_map *\fP\fImap\fP\fB, u32\fP \fIkey\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +This helper is used in programs implementing policies at the +socket level. If the message \fImsg\fP is allowed to pass (i.e. if +the verdict eBPF program returns \fBSK_PASS\fP), redirect it to +the socket referenced by \fImap\fP (of type +\fBBPF_MAP_TYPE_SOCKMAP\fP) at index \fIkey\fP\&. Both ingress and +egress interfaces can be used for redirection. The +\fBBPF_F_INGRESS\fP value in \fIflags\fP is used to make the +distinction (ingress path is selected if the flag is present, +egress path otherwise). This is the only flag supported for now. +.TP +.B Return +\fBSK_PASS\fP on success, or \fBSK_DROP\fP on error. +.UNINDENT +.TP +.B \fBlong bpf_msg_apply_bytes(struct sk_msg_buff *\fP\fImsg\fP\fB, u32\fP \fIbytes\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +For socket policies, apply the verdict of the eBPF program to +the next \fIbytes\fP (number of bytes) of message \fImsg\fP\&. +.sp +For example, this helper can be used in the following cases: +.INDENT 7.0 +.IP \(bu 2 +A single \fBsendmsg\fP() or \fBsendfile\fP() system call +contains multiple logical messages that the eBPF program is +supposed to read and for which it should apply a verdict. +.IP \(bu 2 +An eBPF program only cares to read the first \fIbytes\fP of a +\fImsg\fP\&. If the message has a large payload, then setting up +and calling the eBPF program repeatedly for all bytes, even +though the verdict is already known, would create unnecessary +overhead. +.UNINDENT +.sp +When called from within an eBPF program, the helper sets a +counter internal to the BPF infrastructure, that is used to +apply the last verdict to the next \fIbytes\fP\&. If \fIbytes\fP is +smaller than the current data being processed from a +\fBsendmsg\fP() or \fBsendfile\fP() system call, the first +\fIbytes\fP will be sent and the eBPF program will be re\-run with +the pointer for start of data pointing to byte number \fIbytes\fP +\fB+ 1\fP\&. If \fIbytes\fP is larger than the current data being +processed, then the eBPF verdict will be applied to multiple +\fBsendmsg\fP() or \fBsendfile\fP() calls until \fIbytes\fP are +consumed. +.sp +Note that if a socket closes with the internal counter holding +a non\-zero value, this is not a problem because data is not +being buffered for \fIbytes\fP and is sent as it is received. +.TP +.B Return +0 +.UNINDENT +.TP +.B \fBlong bpf_msg_cork_bytes(struct sk_msg_buff *\fP\fImsg\fP\fB, u32\fP \fIbytes\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +For socket policies, prevent the execution of the verdict eBPF +program for message \fImsg\fP until \fIbytes\fP (byte number) have been +accumulated. +.sp +This can be used when one needs a specific number of bytes +before a verdict can be assigned, even if the data spans +multiple \fBsendmsg\fP() or \fBsendfile\fP() calls. The extreme +case would be a user calling \fBsendmsg\fP() repeatedly with +1\-byte long message segments. Obviously, this is bad for +performance, but it is still valid. If the eBPF program needs +\fIbytes\fP bytes to validate a header, this helper can be used to +prevent the eBPF program to be called again until \fIbytes\fP have +been accumulated. +.TP +.B Return +0 +.UNINDENT +.TP +.B \fBlong bpf_msg_pull_data(struct sk_msg_buff *\fP\fImsg\fP\fB, u32\fP \fIstart\fP\fB, u32\fP \fIend\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +For socket policies, pull in non\-linear data from user space +for \fImsg\fP and set pointers \fImsg\fP\fB\->data\fP and \fImsg\fP\fB\->data_end\fP to \fIstart\fP and \fIend\fP bytes offsets into \fImsg\fP, +respectively. +.sp +If a program of type \fBBPF_PROG_TYPE_SK_MSG\fP is run on a +\fImsg\fP it can only parse data that the (\fBdata\fP, \fBdata_end\fP) +pointers have already consumed. For \fBsendmsg\fP() hooks this +is likely the first scatterlist element. But for calls relying +on the \fBsendpage\fP handler (e.g. \fBsendfile\fP()) this will +be the range (\fB0\fP, \fB0\fP) because the data is shared with +user space and by default the objective is to avoid allowing +user space to modify data while (or after) eBPF verdict is +being decided. This helper can be used to pull in data and to +set the start and end pointer to given values. Data will be +copied if necessary (i.e. if data was not linear and if start +and end pointers do not point to the same chunk). +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.sp +All values for \fIflags\fP are reserved for future usage, and must +be left at zero. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_bind(struct bpf_sock_addr *\fP\fIctx\fP\fB, struct sockaddr *\fP\fIaddr\fP\fB, int\fP \fIaddr_len\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Bind the socket associated to \fIctx\fP to the address pointed by +\fIaddr\fP, of length \fIaddr_len\fP\&. This allows for making outgoing +connection from the desired IP address, which can be useful for +example when all processes inside a cgroup should use one +single IP address on a host that has multiple IP configured. +.sp +This helper works for IPv4 and IPv6, TCP and UDP sockets. The +domain (\fIaddr\fP\fB\->sa_family\fP) must be \fBAF_INET\fP (or +\fBAF_INET6\fP). It\(aqs advised to pass zero port (\fBsin_port\fP +or \fBsin6_port\fP) which triggers IP_BIND_ADDRESS_NO_PORT\-like +behavior and lets the kernel efficiently pick up an unused +port as long as 4\-tuple is unique. Passing non\-zero port might +lead to degraded performance. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_xdp_adjust_tail(struct xdp_buff *\fP\fIxdp_md\fP\fB, int\fP \fIdelta\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Adjust (move) \fIxdp_md\fP\fB\->data_end\fP by \fIdelta\fP bytes. It is +possible to both shrink and grow the packet tail. +Shrink done via \fIdelta\fP being a negative integer. +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_skb_get_xfrm_state(struct sk_buff *\fP\fIskb\fP\fB, u32\fP \fIindex\fP\fB, struct bpf_xfrm_state *\fP\fIxfrm_state\fP\fB, u32\fP \fIsize\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Retrieve the XFRM state (IP transform framework, see also +\fBip\-xfrm(8)\fP) at \fIindex\fP in XFRM \(dqsecurity path\(dq for \fIskb\fP\&. +.sp +The retrieved value is stored in the \fBstruct bpf_xfrm_state\fP +pointed by \fIxfrm_state\fP and of length \fIsize\fP\&. +.sp +All values for \fIflags\fP are reserved for future usage, and must +be left at zero. +.sp +This helper is available only if the kernel was compiled with +\fBCONFIG_XFRM\fP configuration option. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_get_stack(void *\fP\fIctx\fP\fB, void *\fP\fIbuf\fP\fB, u32\fP \fIsize\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Return a user or a kernel stack in bpf program provided buffer. +To achieve this, the helper needs \fIctx\fP, which is a pointer +to the context on which the tracing program is executed. +To store the stacktrace, the bpf program provides \fIbuf\fP with +a nonnegative \fIsize\fP\&. +.sp +The last argument, \fIflags\fP, holds the number of stack frames to +skip (from 0 to 255), masked with +\fBBPF_F_SKIP_FIELD_MASK\fP\&. The next bits can be used to set +the following flags: +.INDENT 7.0 +.TP +.B \fBBPF_F_USER_STACK\fP +Collect a user space stack instead of a kernel stack. +.TP +.B \fBBPF_F_USER_BUILD_ID\fP +Collect (build_id, file_offset) instead of ips for user +stack, only valid if \fBBPF_F_USER_STACK\fP is also +specified. +.sp +\fIfile_offset\fP is an offset relative to the beginning +of the executable or shared object file backing the vma +which the \fIip\fP falls in. It is \fInot\fP an offset relative +to that object\(aqs base address. Accordingly, it must be +adjusted by adding (sh_addr \- sh_offset), where +sh_{addr,offset} correspond to the executable section +containing \fIfile_offset\fP in the object, for comparisons +to symbols\(aq st_value to be valid. +.UNINDENT +.sp +\fBbpf_get_stack\fP() can collect up to +\fBPERF_MAX_STACK_DEPTH\fP both kernel and user frames, subject +to sufficient large buffer size. Note that +this limit can be controlled with the \fBsysctl\fP program, and +that it should be manually increased in order to profile long +user stacks (such as stacks for Java programs). To do so, use: +.INDENT 7.0 +.INDENT 3.5 +.sp +.nf +.ft C +# sysctl kernel.perf_event_max_stack=<new value> +.ft P +.fi +.UNINDENT +.UNINDENT +.TP +.B Return +The non\-negative copied \fIbuf\fP length equal to or less than +\fIsize\fP on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_skb_load_bytes_relative(const void *\fP\fIskb\fP\fB, u32\fP \fIoffset\fP\fB, void *\fP\fIto\fP\fB, u32\fP \fIlen\fP\fB, u32\fP \fIstart_header\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +This helper is similar to \fBbpf_skb_load_bytes\fP() in that +it provides an easy way to load \fIlen\fP bytes from \fIoffset\fP +from the packet associated to \fIskb\fP, into the buffer pointed +by \fIto\fP\&. The difference to \fBbpf_skb_load_bytes\fP() is that +a fifth argument \fIstart_header\fP exists in order to select a +base offset to start from. \fIstart_header\fP can be one of: +.INDENT 7.0 +.TP +.B \fBBPF_HDR_START_MAC\fP +Base offset to load data from is \fIskb\fP\(aqs mac header. +.TP +.B \fBBPF_HDR_START_NET\fP +Base offset to load data from is \fIskb\fP\(aqs network header. +.UNINDENT +.sp +In general, \(dqdirect packet access\(dq is the preferred method to +access packet data, however, this helper is in particular useful +in socket filters where \fIskb\fP\fB\->data\fP does not always point +to the start of the mac header and where \(dqdirect packet access\(dq +is not available. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_fib_lookup(void *\fP\fIctx\fP\fB, struct bpf_fib_lookup *\fP\fIparams\fP\fB, int\fP \fIplen\fP\fB, u32\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Do FIB lookup in kernel tables using parameters in \fIparams\fP\&. +If lookup is successful and result shows packet is to be +forwarded, the neighbor tables are searched for the nexthop. +If successful (ie., FIB lookup shows forwarding and nexthop +is resolved), the nexthop address is returned in ipv4_dst +or ipv6_dst based on family, smac is set to mac address of +egress device, dmac is set to nexthop mac address, rt_metric +is set to metric from route (IPv4/IPv6 only), and ifindex +is set to the device index of the nexthop from the FIB lookup. +.sp +\fIplen\fP argument is the size of the passed in struct. +\fIflags\fP argument can be a combination of one or more of the +following values: +.INDENT 7.0 +.TP +.B \fBBPF_FIB_LOOKUP_DIRECT\fP +Do a direct table lookup vs full lookup using FIB +rules. +.TP +.B \fBBPF_FIB_LOOKUP_OUTPUT\fP +Perform lookup from an egress perspective (default is +ingress). +.UNINDENT +.sp +\fIctx\fP is either \fBstruct xdp_md\fP for XDP programs or +\fBstruct sk_buff\fP tc cls_act programs. +.TP +.B Return +.INDENT 7.0 +.IP \(bu 2 +< 0 if any input argument is invalid +.IP \(bu 2 +0 on success (packet is forwarded, nexthop neighbor exists) +.IP \(bu 2 +> 0 one of \fBBPF_FIB_LKUP_RET_\fP codes explaining why the +packet is not forwarded or needs assist from full stack +.UNINDENT +.sp +If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU +was exceeded and output params\->mtu_result contains the MTU. +.UNINDENT +.TP +.B \fBlong bpf_sock_hash_update(struct bpf_sock_ops *\fP\fIskops\fP\fB, struct bpf_map *\fP\fImap\fP\fB, void *\fP\fIkey\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Add an entry to, or update a sockhash \fImap\fP referencing sockets. +The \fIskops\fP is used as a new value for the entry associated to +\fIkey\fP\&. \fIflags\fP is one of: +.INDENT 7.0 +.TP +.B \fBBPF_NOEXIST\fP +The entry for \fIkey\fP must not exist in the map. +.TP +.B \fBBPF_EXIST\fP +The entry for \fIkey\fP must already exist in the map. +.TP +.B \fBBPF_ANY\fP +No condition on the existence of the entry for \fIkey\fP\&. +.UNINDENT +.sp +If the \fImap\fP has eBPF programs (parser and verdict), those will +be inherited by the socket being added. If the socket is +already attached to eBPF programs, this results in an error. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_msg_redirect_hash(struct sk_msg_buff *\fP\fImsg\fP\fB, struct bpf_map *\fP\fImap\fP\fB, void *\fP\fIkey\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +This helper is used in programs implementing policies at the +socket level. If the message \fImsg\fP is allowed to pass (i.e. if +the verdict eBPF program returns \fBSK_PASS\fP), redirect it to +the socket referenced by \fImap\fP (of type +\fBBPF_MAP_TYPE_SOCKHASH\fP) using hash \fIkey\fP\&. Both ingress and +egress interfaces can be used for redirection. The +\fBBPF_F_INGRESS\fP value in \fIflags\fP is used to make the +distinction (ingress path is selected if the flag is present, +egress path otherwise). This is the only flag supported for now. +.TP +.B Return +\fBSK_PASS\fP on success, or \fBSK_DROP\fP on error. +.UNINDENT +.TP +.B \fBlong bpf_sk_redirect_hash(struct sk_buff *\fP\fIskb\fP\fB, struct bpf_map *\fP\fImap\fP\fB, void *\fP\fIkey\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +This helper is used in programs implementing policies at the +skb socket level. If the sk_buff \fIskb\fP is allowed to pass (i.e. +if the verdict eBPF program returns \fBSK_PASS\fP), redirect it +to the socket referenced by \fImap\fP (of type +\fBBPF_MAP_TYPE_SOCKHASH\fP) using hash \fIkey\fP\&. Both ingress and +egress interfaces can be used for redirection. The +\fBBPF_F_INGRESS\fP value in \fIflags\fP is used to make the +distinction (ingress path is selected if the flag is present, +egress otherwise). This is the only flag supported for now. +.TP +.B Return +\fBSK_PASS\fP on success, or \fBSK_DROP\fP on error. +.UNINDENT +.TP +.B \fBlong bpf_lwt_push_encap(struct sk_buff *\fP\fIskb\fP\fB, u32\fP \fItype\fP\fB, void *\fP\fIhdr\fP\fB, u32\fP \fIlen\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Encapsulate the packet associated to \fIskb\fP within a Layer 3 +protocol header. This header is provided in the buffer at +address \fIhdr\fP, with \fIlen\fP its size in bytes. \fItype\fP indicates +the protocol of the header and can be one of: +.INDENT 7.0 +.TP +.B \fBBPF_LWT_ENCAP_SEG6\fP +IPv6 encapsulation with Segment Routing Header +(\fBstruct ipv6_sr_hdr\fP). \fIhdr\fP only contains the SRH, +the IPv6 header is computed by the kernel. +.TP +.B \fBBPF_LWT_ENCAP_SEG6_INLINE\fP +Only works if \fIskb\fP contains an IPv6 packet. Insert a +Segment Routing Header (\fBstruct ipv6_sr_hdr\fP) inside +the IPv6 header. +.TP +.B \fBBPF_LWT_ENCAP_IP\fP +IP encapsulation (GRE/GUE/IPIP/etc). The outer header +must be IPv4 or IPv6, followed by zero or more +additional headers, up to \fBLWT_BPF_MAX_HEADROOM\fP +total bytes in all prepended headers. Please note that +if \fBskb_is_gso\fP(\fIskb\fP) is true, no more than two +headers can be prepended, and the inner header, if +present, should be either GRE or UDP/GUE. +.UNINDENT +.sp +\fBBPF_LWT_ENCAP_SEG6\fP* types can be called by BPF programs +of type \fBBPF_PROG_TYPE_LWT_IN\fP; \fBBPF_LWT_ENCAP_IP\fP type can +be called by bpf programs of types \fBBPF_PROG_TYPE_LWT_IN\fP and +\fBBPF_PROG_TYPE_LWT_XMIT\fP\&. +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_lwt_seg6_store_bytes(struct sk_buff *\fP\fIskb\fP\fB, u32\fP \fIoffset\fP\fB, const void *\fP\fIfrom\fP\fB, u32\fP \fIlen\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Store \fIlen\fP bytes from address \fIfrom\fP into the packet +associated to \fIskb\fP, at \fIoffset\fP\&. Only the flags, tag and TLVs +inside the outermost IPv6 Segment Routing Header can be +modified through this helper. +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_lwt_seg6_adjust_srh(struct sk_buff *\fP\fIskb\fP\fB, u32\fP \fIoffset\fP\fB, s32\fP \fIdelta\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Adjust the size allocated to TLVs in the outermost IPv6 +Segment Routing Header contained in the packet associated to +\fIskb\fP, at position \fIoffset\fP by \fIdelta\fP bytes. Only offsets +after the segments are accepted. \fIdelta\fP can be as well +positive (growing) as negative (shrinking). +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_lwt_seg6_action(struct sk_buff *\fP\fIskb\fP\fB, u32\fP \fIaction\fP\fB, void *\fP\fIparam\fP\fB, u32\fP \fIparam_len\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Apply an IPv6 Segment Routing action of type \fIaction\fP to the +packet associated to \fIskb\fP\&. Each action takes a parameter +contained at address \fIparam\fP, and of length \fIparam_len\fP bytes. +\fIaction\fP can be one of: +.INDENT 7.0 +.TP +.B \fBSEG6_LOCAL_ACTION_END_X\fP +End.X action: Endpoint with Layer\-3 cross\-connect. +Type of \fIparam\fP: \fBstruct in6_addr\fP\&. +.TP +.B \fBSEG6_LOCAL_ACTION_END_T\fP +End.T action: Endpoint with specific IPv6 table lookup. +Type of \fIparam\fP: \fBint\fP\&. +.TP +.B \fBSEG6_LOCAL_ACTION_END_B6\fP +End.B6 action: Endpoint bound to an SRv6 policy. +Type of \fIparam\fP: \fBstruct ipv6_sr_hdr\fP\&. +.TP +.B \fBSEG6_LOCAL_ACTION_END_B6_ENCAP\fP +End.B6.Encap action: Endpoint bound to an SRv6 +encapsulation policy. +Type of \fIparam\fP: \fBstruct ipv6_sr_hdr\fP\&. +.UNINDENT +.sp +A call to this helper is susceptible to change the underlying +packet buffer. Therefore, at load time, all checks on pointers +previously done by the verifier are invalidated and must be +performed again, if the helper is used in combination with +direct packet access. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_rc_repeat(void *\fP\fIctx\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +This helper is used in programs implementing IR decoding, to +report a successfully decoded repeat key message. This delays +the generation of a key up event for previously generated +key down event. +.sp +Some IR protocols like NEC have a special IR message for +repeating last button, for when a button is held down. +.sp +The \fIctx\fP should point to the lirc sample as passed into +the program. +.sp +This helper is only available is the kernel was compiled with +the \fBCONFIG_BPF_LIRC_MODE2\fP configuration option set to +\(dq\fBy\fP\(dq. +.TP +.B Return +0 +.UNINDENT +.TP +.B \fBlong bpf_rc_keydown(void *\fP\fIctx\fP\fB, u32\fP \fIprotocol\fP\fB, u64\fP \fIscancode\fP\fB, u32\fP \fItoggle\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +This helper is used in programs implementing IR decoding, to +report a successfully decoded key press with \fIscancode\fP, +\fItoggle\fP value in the given \fIprotocol\fP\&. The scancode will be +translated to a keycode using the rc keymap, and reported as +an input key down event. After a period a key up event is +generated. This period can be extended by calling either +\fBbpf_rc_keydown\fP() again with the same values, or calling +\fBbpf_rc_repeat\fP(). +.sp +Some protocols include a toggle bit, in case the button was +released and pressed again between consecutive scancodes. +.sp +The \fIctx\fP should point to the lirc sample as passed into +the program. +.sp +The \fIprotocol\fP is the decoded protocol number (see +\fBenum rc_proto\fP for some predefined values). +.sp +This helper is only available is the kernel was compiled with +the \fBCONFIG_BPF_LIRC_MODE2\fP configuration option set to +\(dq\fBy\fP\(dq. +.TP +.B Return +0 +.UNINDENT +.TP +.B \fBu64 bpf_skb_cgroup_id(struct sk_buff *\fP\fIskb\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Return the cgroup v2 id of the socket associated with the \fIskb\fP\&. +This is roughly similar to the \fBbpf_get_cgroup_classid\fP() +helper for cgroup v1 by providing a tag resp. identifier that +can be matched on or used for map lookups e.g. to implement +policy. The cgroup v2 id of a given path in the hierarchy is +exposed in user space through the f_handle API in order to get +to the same 64\-bit id. +.sp +This helper can be used on TC egress path, but not on ingress, +and is available only if the kernel was compiled with the +\fBCONFIG_SOCK_CGROUP_DATA\fP configuration option. +.TP +.B Return +The id is returned or 0 in case the id could not be retrieved. +.UNINDENT +.TP +.B \fBu64 bpf_get_current_cgroup_id(void)\fP +.INDENT 7.0 +.TP +.B Description +Get the current cgroup id based on the cgroup within which +the current task is running. +.TP +.B Return +A 64\-bit integer containing the current cgroup id based +on the cgroup within which the current task is running. +.UNINDENT +.TP +.B \fBvoid *bpf_get_local_storage(void *\fP\fImap\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get the pointer to the local storage area. +The type and the size of the local storage is defined +by the \fImap\fP argument. +The \fIflags\fP meaning is specific for each map type, +and has to be 0 for cgroup local storage. +.sp +Depending on the BPF program type, a local storage area +can be shared between multiple instances of the BPF program, +running simultaneously. +.sp +A user should care about the synchronization by himself. +For example, by using the \fBBPF_ATOMIC\fP instructions to alter +the shared data. +.TP +.B Return +A pointer to the local storage area. +.UNINDENT +.TP +.B \fBlong bpf_sk_select_reuseport(struct sk_reuseport_md *\fP\fIreuse\fP\fB, struct bpf_map *\fP\fImap\fP\fB, void *\fP\fIkey\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Select a \fBSO_REUSEPORT\fP socket from a +\fBBPF_MAP_TYPE_REUSEPORT_SOCKARRAY\fP \fImap\fP\&. +It checks the selected socket is matching the incoming +request in the socket buffer. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBu64 bpf_skb_ancestor_cgroup_id(struct sk_buff *\fP\fIskb\fP\fB, int\fP \fIancestor_level\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Return id of cgroup v2 that is ancestor of cgroup associated +with the \fIskb\fP at the \fIancestor_level\fP\&. The root cgroup is at +\fIancestor_level\fP zero and each step down the hierarchy +increments the level. If \fIancestor_level\fP == level of cgroup +associated with \fIskb\fP, then return value will be same as that +of \fBbpf_skb_cgroup_id\fP(). +.sp +The helper is useful to implement policies based on cgroups +that are upper in hierarchy than immediate cgroup associated +with \fIskb\fP\&. +.sp +The format of returned id and helper limitations are same as in +\fBbpf_skb_cgroup_id\fP(). +.TP +.B Return +The id is returned or 0 in case the id could not be retrieved. +.UNINDENT +.TP +.B \fBstruct bpf_sock *bpf_sk_lookup_tcp(void *\fP\fIctx\fP\fB, struct bpf_sock_tuple *\fP\fItuple\fP\fB, u32\fP \fItuple_size\fP\fB, u64\fP \fInetns\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Look for TCP socket matching \fItuple\fP, optionally in a child +network namespace \fInetns\fP\&. The return value must be checked, +and if non\-\fBNULL\fP, released via \fBbpf_sk_release\fP(). +.sp +The \fIctx\fP should point to the context of the program, such as +the skb or socket (depending on the hook in use). This is used +to determine the base network namespace for the lookup. +.sp +\fItuple_size\fP must be one of: +.INDENT 7.0 +.TP +.B \fBsizeof\fP(\fItuple\fP\fB\->ipv4\fP) +Look for an IPv4 socket. +.TP +.B \fBsizeof\fP(\fItuple\fP\fB\->ipv6\fP) +Look for an IPv6 socket. +.UNINDENT +.sp +If the \fInetns\fP is a negative signed 32\-bit integer, then the +socket lookup table in the netns associated with the \fIctx\fP +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 \fInetns\fP is any other signed 32\-bit value greater than or +equal to zero then it specifies the ID of the netns relative to +the netns associated with the \fIctx\fP\&. \fInetns\fP values beyond the +range of 32\-bit integers are reserved for future use. +.sp +All values for \fIflags\fP are reserved for future usage, and must +be left at zero. +.sp +This helper is available only if the kernel was compiled with +\fBCONFIG_NET\fP configuration option. +.TP +.B Return +Pointer to \fBstruct bpf_sock\fP, or \fBNULL\fP in case of failure. +For sockets with reuseport option, the \fBstruct bpf_sock\fP +result is from \fIreuse\fP\fB\->socks\fP[] using the hash of the +tuple. +.UNINDENT +.TP +.B \fBstruct bpf_sock *bpf_sk_lookup_udp(void *\fP\fIctx\fP\fB, struct bpf_sock_tuple *\fP\fItuple\fP\fB, u32\fP \fItuple_size\fP\fB, u64\fP \fInetns\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Look for UDP socket matching \fItuple\fP, optionally in a child +network namespace \fInetns\fP\&. The return value must be checked, +and if non\-\fBNULL\fP, released via \fBbpf_sk_release\fP(). +.sp +The \fIctx\fP should point to the context of the program, such as +the skb or socket (depending on the hook in use). This is used +to determine the base network namespace for the lookup. +.sp +\fItuple_size\fP must be one of: +.INDENT 7.0 +.TP +.B \fBsizeof\fP(\fItuple\fP\fB\->ipv4\fP) +Look for an IPv4 socket. +.TP +.B \fBsizeof\fP(\fItuple\fP\fB\->ipv6\fP) +Look for an IPv6 socket. +.UNINDENT +.sp +If the \fInetns\fP is a negative signed 32\-bit integer, then the +socket lookup table in the netns associated with the \fIctx\fP +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 \fInetns\fP is any other signed 32\-bit value greater than or +equal to zero then it specifies the ID of the netns relative to +the netns associated with the \fIctx\fP\&. \fInetns\fP values beyond the +range of 32\-bit integers are reserved for future use. +.sp +All values for \fIflags\fP are reserved for future usage, and must +be left at zero. +.sp +This helper is available only if the kernel was compiled with +\fBCONFIG_NET\fP configuration option. +.TP +.B Return +Pointer to \fBstruct bpf_sock\fP, or \fBNULL\fP in case of failure. +For sockets with reuseport option, the \fBstruct bpf_sock\fP +result is from \fIreuse\fP\fB\->socks\fP[] using the hash of the +tuple. +.UNINDENT +.TP +.B \fBlong bpf_sk_release(void *\fP\fIsock\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Release the reference held by \fIsock\fP\&. \fIsock\fP must be a +non\-\fBNULL\fP pointer that was returned from +\fBbpf_sk_lookup_xxx\fP(). +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_map_push_elem(struct bpf_map *\fP\fImap\fP\fB, const void *\fP\fIvalue\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Push an element \fIvalue\fP in \fImap\fP\&. \fIflags\fP is one of: +.INDENT 7.0 +.TP +.B \fBBPF_EXIST\fP +If the queue/stack is full, the oldest element is +removed to make room for this. +.UNINDENT +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_map_pop_elem(struct bpf_map *\fP\fImap\fP\fB, void *\fP\fIvalue\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Pop an element from \fImap\fP\&. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_map_peek_elem(struct bpf_map *\fP\fImap\fP\fB, void *\fP\fIvalue\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get an element from \fImap\fP without removing it. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_msg_push_data(struct sk_msg_buff *\fP\fImsg\fP\fB, u32\fP \fIstart\fP\fB, u32\fP \fIlen\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +For socket policies, insert \fIlen\fP bytes into \fImsg\fP at offset +\fIstart\fP\&. +.sp +If a program of type \fBBPF_PROG_TYPE_SK_MSG\fP is run on a +\fImsg\fP it may want to insert metadata or options into the \fImsg\fP\&. +This can later be read and used by any of the lower layer BPF +hooks. +.sp +This helper may fail if under memory pressure (a malloc +fails) in these cases BPF programs will get an appropriate +error and BPF programs will need to handle them. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_msg_pop_data(struct sk_msg_buff *\fP\fImsg\fP\fB, u32\fP \fIstart\fP\fB, u32\fP \fIlen\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Will remove \fIlen\fP bytes from a \fImsg\fP starting at byte \fIstart\fP\&. +This may result in \fBENOMEM\fP errors under certain situations if +an allocation and copy are required due to a full ring buffer. +However, the helper will try to avoid doing the allocation +if possible. Other errors can occur if input parameters are +invalid either due to \fIstart\fP byte not being valid part of \fImsg\fP +payload and/or \fIpop\fP value being to large. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_rc_pointer_rel(void *\fP\fIctx\fP\fB, s32\fP \fIrel_x\fP\fB, s32\fP \fIrel_y\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +This helper is used in programs implementing IR decoding, to +report a successfully decoded pointer movement. +.sp +The \fIctx\fP should point to the lirc sample as passed into +the program. +.sp +This helper is only available is the kernel was compiled with +the \fBCONFIG_BPF_LIRC_MODE2\fP configuration option set to +\(dq\fBy\fP\(dq. +.TP +.B Return +0 +.UNINDENT +.TP +.B \fBlong bpf_spin_lock(struct bpf_spin_lock *\fP\fIlock\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Acquire a spinlock represented by the pointer \fIlock\fP, which is +stored as part of a value of a map. Taking the lock allows to +safely update the rest of the fields in that value. The +spinlock can (and must) later be released with a call to +\fBbpf_spin_unlock\fP(\fIlock\fP). +.sp +Spinlocks in BPF programs come with a number of restrictions +and constraints: +.INDENT 7.0 +.IP \(bu 2 +\fBbpf_spin_lock\fP objects are only allowed inside maps of +types \fBBPF_MAP_TYPE_HASH\fP and \fBBPF_MAP_TYPE_ARRAY\fP (this +list could be extended in the future). +.IP \(bu 2 +BTF description of the map is mandatory. +.IP \(bu 2 +The BPF program can take ONE lock at a time, since taking two +or more could cause dead locks. +.IP \(bu 2 +Only one \fBstruct bpf_spin_lock\fP is allowed per map element. +.IP \(bu 2 +When the lock is taken, calls (either BPF to BPF or helpers) +are not allowed. +.IP \(bu 2 +The \fBBPF_LD_ABS\fP and \fBBPF_LD_IND\fP instructions are not +allowed inside a spinlock\-ed region. +.IP \(bu 2 +The BPF program MUST call \fBbpf_spin_unlock\fP() to release +the lock, on all execution paths, before it returns. +.IP \(bu 2 +The BPF program can access \fBstruct bpf_spin_lock\fP only via +the \fBbpf_spin_lock\fP() and \fBbpf_spin_unlock\fP() +helpers. Loading or storing data into the \fBstruct +bpf_spin_lock\fP \fIlock\fP\fB;\fP field of a map is not allowed. +.IP \(bu 2 +To use the \fBbpf_spin_lock\fP() helper, the BTF description +of the map value must be a struct and have \fBstruct +bpf_spin_lock\fP \fIanyname\fP\fB;\fP field at the top level. +Nested lock inside another struct is not allowed. +.IP \(bu 2 +The \fBstruct bpf_spin_lock\fP \fIlock\fP field in a map value must +be aligned on a multiple of 4 bytes in that value. +.IP \(bu 2 +Syscall with command \fBBPF_MAP_LOOKUP_ELEM\fP does not copy +the \fBbpf_spin_lock\fP field to user space. +.IP \(bu 2 +Syscall with command \fBBPF_MAP_UPDATE_ELEM\fP, or update from +a BPF program, do not update the \fBbpf_spin_lock\fP field. +.IP \(bu 2 +\fBbpf_spin_lock\fP cannot be on the stack or inside a +networking packet (it can only be inside of a map values). +.IP \(bu 2 +\fBbpf_spin_lock\fP is available to root only. +.IP \(bu 2 +Tracing programs and socket filter programs cannot use +\fBbpf_spin_lock\fP() due to insufficient preemption checks +(but this may change in the future). +.IP \(bu 2 +\fBbpf_spin_lock\fP is not allowed in inner maps of map\-in\-map. +.UNINDENT +.TP +.B Return +0 +.UNINDENT +.TP +.B \fBlong bpf_spin_unlock(struct bpf_spin_lock *\fP\fIlock\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Release the \fIlock\fP previously locked by a call to +\fBbpf_spin_lock\fP(\fIlock\fP). +.TP +.B Return +0 +.UNINDENT +.TP +.B \fBstruct bpf_sock *bpf_sk_fullsock(struct bpf_sock *\fP\fIsk\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +This helper gets a \fBstruct bpf_sock\fP pointer such +that all the fields in this \fBbpf_sock\fP can be accessed. +.TP +.B Return +A \fBstruct bpf_sock\fP pointer on success, or \fBNULL\fP in +case of failure. +.UNINDENT +.TP +.B \fBstruct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *\fP\fIsk\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +This helper gets a \fBstruct bpf_tcp_sock\fP pointer from a +\fBstruct bpf_sock\fP pointer. +.TP +.B Return +A \fBstruct bpf_tcp_sock\fP pointer on success, or \fBNULL\fP in +case of failure. +.UNINDENT +.TP +.B \fBlong bpf_skb_ecn_set_ce(struct sk_buff *\fP\fIskb\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Set ECN (Explicit Congestion Notification) field of IP header +to \fBCE\fP (Congestion Encountered) if current value is \fBECT\fP +(ECN Capable Transport). Otherwise, do nothing. Works with IPv6 +and IPv4. +.TP +.B Return +1 if the \fBCE\fP flag is set (either by the current helper call +or because it was already present), 0 if it is not set. +.UNINDENT +.TP +.B \fBstruct bpf_sock *bpf_get_listener_sock(struct bpf_sock *\fP\fIsk\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Return a \fBstruct bpf_sock\fP pointer in \fBTCP_LISTEN\fP state. +\fBbpf_sk_release\fP() is unnecessary and not allowed. +.TP +.B Return +A \fBstruct bpf_sock\fP pointer on success, or \fBNULL\fP in +case of failure. +.UNINDENT +.TP +.B \fBstruct bpf_sock *bpf_skc_lookup_tcp(void *\fP\fIctx\fP\fB, struct bpf_sock_tuple *\fP\fItuple\fP\fB, u32\fP \fItuple_size\fP\fB, u64\fP \fInetns\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Look for TCP socket matching \fItuple\fP, optionally in a child +network namespace \fInetns\fP\&. The return value must be checked, +and if non\-\fBNULL\fP, released via \fBbpf_sk_release\fP(). +.sp +This function is identical to \fBbpf_sk_lookup_tcp\fP(), except +that it also returns timewait or request sockets. Use +\fBbpf_sk_fullsock\fP() or \fBbpf_tcp_sock\fP() to access the +full structure. +.sp +This helper is available only if the kernel was compiled with +\fBCONFIG_NET\fP configuration option. +.TP +.B Return +Pointer to \fBstruct bpf_sock\fP, or \fBNULL\fP in case of failure. +For sockets with reuseport option, the \fBstruct bpf_sock\fP +result is from \fIreuse\fP\fB\->socks\fP[] using the hash of the +tuple. +.UNINDENT +.TP +.B \fBlong bpf_tcp_check_syncookie(void *\fP\fIsk\fP\fB, void *\fP\fIiph\fP\fB, u32\fP \fIiph_len\fP\fB, struct tcphdr *\fP\fIth\fP\fB, u32\fP \fIth_len\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Check whether \fIiph\fP and \fIth\fP contain a valid SYN cookie ACK for +the listening socket in \fIsk\fP\&. +.sp +\fIiph\fP points to the start of the IPv4 or IPv6 header, while +\fIiph_len\fP contains \fBsizeof\fP(\fBstruct iphdr\fP) or +\fBsizeof\fP(\fBstruct ipv6hdr\fP). +.sp +\fIth\fP points to the start of the TCP header, while \fIth_len\fP +contains the length of the TCP header (at least +\fBsizeof\fP(\fBstruct tcphdr\fP)). +.TP +.B Return +0 if \fIiph\fP and \fIth\fP are a valid SYN cookie ACK, or a negative +error otherwise. +.UNINDENT +.TP +.B \fBlong bpf_sysctl_get_name(struct bpf_sysctl *\fP\fIctx\fP\fB, char *\fP\fIbuf\fP\fB, size_t\fP \fIbuf_len\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get name of sysctl in /proc/sys/ and copy it into provided by +program buffer \fIbuf\fP of size \fIbuf_len\fP\&. +.sp +The buffer is always NUL terminated, unless it\(aqs zero\-sized. +.sp +If \fIflags\fP is zero, full name (e.g. \(dqnet/ipv4/tcp_mem\(dq) is +copied. Use \fBBPF_F_SYSCTL_BASE_NAME\fP flag to copy base name +only (e.g. \(dqtcp_mem\(dq). +.TP +.B Return +Number of character copied (not including the trailing NUL). +.sp +\fB\-E2BIG\fP if the buffer wasn\(aqt big enough (\fIbuf\fP will contain +truncated name in this case). +.UNINDENT +.TP +.B \fBlong bpf_sysctl_get_current_value(struct bpf_sysctl *\fP\fIctx\fP\fB, char *\fP\fIbuf\fP\fB, size_t\fP \fIbuf_len\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get current value of sysctl as it is presented in /proc/sys +(incl. newline, etc), and copy it as a string into provided +by program buffer \fIbuf\fP of size \fIbuf_len\fP\&. +.sp +The whole value is copied, no matter what file position user +space issued e.g. sys_read at. +.sp +The buffer is always NUL terminated, unless it\(aqs zero\-sized. +.TP +.B Return +Number of character copied (not including the trailing NUL). +.sp +\fB\-E2BIG\fP if the buffer wasn\(aqt big enough (\fIbuf\fP will contain +truncated name in this case). +.sp +\fB\-EINVAL\fP if current value was unavailable, e.g. because +sysctl is uninitialized and read returns \-EIO for it. +.UNINDENT +.TP +.B \fBlong bpf_sysctl_get_new_value(struct bpf_sysctl *\fP\fIctx\fP\fB, char *\fP\fIbuf\fP\fB, size_t\fP \fIbuf_len\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get new value being written by user space to sysctl (before +the actual write happens) and copy it as a string into +provided by program buffer \fIbuf\fP of size \fIbuf_len\fP\&. +.sp +User space may write new value at file position > 0. +.sp +The buffer is always NUL terminated, unless it\(aqs zero\-sized. +.TP +.B Return +Number of character copied (not including the trailing NUL). +.sp +\fB\-E2BIG\fP if the buffer wasn\(aqt big enough (\fIbuf\fP will contain +truncated name in this case). +.sp +\fB\-EINVAL\fP if sysctl is being read. +.UNINDENT +.TP +.B \fBlong bpf_sysctl_set_new_value(struct bpf_sysctl *\fP\fIctx\fP\fB, const char *\fP\fIbuf\fP\fB, size_t\fP \fIbuf_len\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Override new value being written by user space to sysctl with +value provided by program in buffer \fIbuf\fP of size \fIbuf_len\fP\&. +.sp +\fIbuf\fP should contain a string in same form as provided by user +space on sysctl write. +.sp +User space may write new value at file position > 0. To override +the whole sysctl value file position should be set to zero. +.TP +.B Return +0 on success. +.sp +\fB\-E2BIG\fP if the \fIbuf_len\fP is too big. +.sp +\fB\-EINVAL\fP if sysctl is being read. +.UNINDENT +.TP +.B \fBlong bpf_strtol(const char *\fP\fIbuf\fP\fB, size_t\fP \fIbuf_len\fP\fB, u64\fP \fIflags\fP\fB, long *\fP\fIres\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Convert the initial part of the string from buffer \fIbuf\fP of +size \fIbuf_len\fP to a long integer according to the given base +and save the result in \fIres\fP\&. +.sp +The string may begin with an arbitrary amount of white space +(as determined by \fBisspace\fP(3)) followed by a single +optional \(aq\fB\-\fP\(aq sign. +.sp +Five least significant bits of \fIflags\fP encode base, other bits +are currently unused. +.sp +Base must be either 8, 10, 16 or 0 to detect it automatically +similar to user space \fBstrtol\fP(3). +.TP +.B Return +Number of characters consumed on success. Must be positive but +no more than \fIbuf_len\fP\&. +.sp +\fB\-EINVAL\fP if no valid digits were found or unsupported base +was provided. +.sp +\fB\-ERANGE\fP if resulting value was out of range. +.UNINDENT +.TP +.B \fBlong bpf_strtoul(const char *\fP\fIbuf\fP\fB, size_t\fP \fIbuf_len\fP\fB, u64\fP \fIflags\fP\fB, unsigned long *\fP\fIres\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Convert the initial part of the string from buffer \fIbuf\fP of +size \fIbuf_len\fP to an unsigned long integer according to the +given base and save the result in \fIres\fP\&. +.sp +The string may begin with an arbitrary amount of white space +(as determined by \fBisspace\fP(3)). +.sp +Five least significant bits of \fIflags\fP encode base, other bits +are currently unused. +.sp +Base must be either 8, 10, 16 or 0 to detect it automatically +similar to user space \fBstrtoul\fP(3). +.TP +.B Return +Number of characters consumed on success. Must be positive but +no more than \fIbuf_len\fP\&. +.sp +\fB\-EINVAL\fP if no valid digits were found or unsupported base +was provided. +.sp +\fB\-ERANGE\fP if resulting value was out of range. +.UNINDENT +.TP +.B \fBvoid *bpf_sk_storage_get(struct bpf_map *\fP\fImap\fP\fB, void *\fP\fIsk\fP\fB, void *\fP\fIvalue\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get a bpf\-local\-storage from a \fIsk\fP\&. +.sp +Logically, it could be thought of getting the value from +a \fImap\fP with \fIsk\fP as the \fBkey\fP\&. From this +perspective, the usage is not much different from +\fBbpf_map_lookup_elem\fP(\fImap\fP, \fB&\fP\fIsk\fP) except this +helper enforces the key must be a full socket and the map must +be a \fBBPF_MAP_TYPE_SK_STORAGE\fP also. +.sp +Underneath, the value is stored locally at \fIsk\fP instead of +the \fImap\fP\&. The \fImap\fP is used as the bpf\-local\-storage +\(dqtype\(dq. The bpf\-local\-storage \(dqtype\(dq (i.e. the \fImap\fP) is +searched against all bpf\-local\-storages residing at \fIsk\fP\&. +.sp +\fIsk\fP is a kernel \fBstruct sock\fP pointer for LSM program. +\fIsk\fP is a \fBstruct bpf_sock\fP pointer for other program types. +.sp +An optional \fIflags\fP (\fBBPF_SK_STORAGE_GET_F_CREATE\fP) can be +used such that a new bpf\-local\-storage will be +created if one does not exist. \fIvalue\fP can be used +together with \fBBPF_SK_STORAGE_GET_F_CREATE\fP to specify +the initial value of a bpf\-local\-storage. If \fIvalue\fP is +\fBNULL\fP, the new bpf\-local\-storage will be zero initialized. +.TP +.B Return +A bpf\-local\-storage pointer is returned on success. +.sp +\fBNULL\fP if not found or there was an error in adding +a new bpf\-local\-storage. +.UNINDENT +.TP +.B \fBlong bpf_sk_storage_delete(struct bpf_map *\fP\fImap\fP\fB, void *\fP\fIsk\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Delete a bpf\-local\-storage from a \fIsk\fP\&. +.TP +.B Return +0 on success. +.sp +\fB\-ENOENT\fP if the bpf\-local\-storage cannot be found. +\fB\-EINVAL\fP if sk is not a fullsock (e.g. a request_sock). +.UNINDENT +.TP +.B \fBlong bpf_send_signal(u32\fP \fIsig\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Send signal \fIsig\fP to the process of the current task. +The signal may be delivered to any of this process\(aqs threads. +.TP +.B Return +0 on success or successfully queued. +.sp +\fB\-EBUSY\fP if work queue under nmi is full. +.sp +\fB\-EINVAL\fP if \fIsig\fP is invalid. +.sp +\fB\-EPERM\fP if no permission to send the \fIsig\fP\&. +.sp +\fB\-EAGAIN\fP if bpf program can try again. +.UNINDENT +.TP +.B \fBs64 bpf_tcp_gen_syncookie(void *\fP\fIsk\fP\fB, void *\fP\fIiph\fP\fB, u32\fP \fIiph_len\fP\fB, struct tcphdr *\fP\fIth\fP\fB, u32\fP \fIth_len\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Try to issue a SYN cookie for the packet with corresponding +IP/TCP headers, \fIiph\fP and \fIth\fP, on the listening socket in \fIsk\fP\&. +.sp +\fIiph\fP points to the start of the IPv4 or IPv6 header, while +\fIiph_len\fP contains \fBsizeof\fP(\fBstruct iphdr\fP) or +\fBsizeof\fP(\fBstruct ipv6hdr\fP). +.sp +\fIth\fP points to the start of the TCP header, while \fIth_len\fP +contains the length of the TCP header with options (at least +\fBsizeof\fP(\fBstruct tcphdr\fP)). +.TP +.B 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. +.sp +On failure, the returned value is one of the following: +.sp +\fB\-EINVAL\fP SYN cookie cannot be issued due to error +.sp +\fB\-ENOENT\fP SYN cookie should not be issued (no SYN flood) +.sp +\fB\-EOPNOTSUPP\fP kernel configuration does not enable SYN cookies +.sp +\fB\-EPROTONOSUPPORT\fP IP packet version is not 4 or 6 +.UNINDENT +.TP +.B \fBlong bpf_skb_output(void *\fP\fIctx\fP\fB, struct bpf_map *\fP\fImap\fP\fB, u64\fP \fIflags\fP\fB, void *\fP\fIdata\fP\fB, u64\fP \fIsize\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Write raw \fIdata\fP blob into a special BPF perf event held by +\fImap\fP of type \fBBPF_MAP_TYPE_PERF_EVENT_ARRAY\fP\&. This perf +event must have the following attributes: \fBPERF_SAMPLE_RAW\fP +as \fBsample_type\fP, \fBPERF_TYPE_SOFTWARE\fP as \fBtype\fP, and +\fBPERF_COUNT_SW_BPF_OUTPUT\fP as \fBconfig\fP\&. +.sp +The \fIflags\fP are used to indicate the index in \fImap\fP for which +the value must be put, masked with \fBBPF_F_INDEX_MASK\fP\&. +Alternatively, \fIflags\fP can be set to \fBBPF_F_CURRENT_CPU\fP +to indicate that the index of the current CPU core should be +used. +.sp +The value to write, of \fIsize\fP, is passed through eBPF stack and +pointed by \fIdata\fP\&. +.sp +\fIctx\fP is a pointer to in\-kernel struct sk_buff. +.sp +This helper is similar to \fBbpf_perf_event_output\fP() but +restricted to raw_tracepoint bpf programs. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_probe_read_user(void *\fP\fIdst\fP\fB, u32\fP \fIsize\fP\fB, const void *\fP\fIunsafe_ptr\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Safely attempt to read \fIsize\fP bytes from user space address +\fIunsafe_ptr\fP and store the data in \fIdst\fP\&. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_probe_read_kernel(void *\fP\fIdst\fP\fB, u32\fP \fIsize\fP\fB, const void *\fP\fIunsafe_ptr\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Safely attempt to read \fIsize\fP bytes from kernel space address +\fIunsafe_ptr\fP and store the data in \fIdst\fP\&. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_probe_read_user_str(void *\fP\fIdst\fP\fB, u32\fP \fIsize\fP\fB, const void *\fP\fIunsafe_ptr\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Copy a NUL terminated string from an unsafe user address +\fIunsafe_ptr\fP to \fIdst\fP\&. The \fIsize\fP should include the +terminating NUL byte. In case the string length is smaller than +\fIsize\fP, the target is not padded with further NUL bytes. If the +string length is larger than \fIsize\fP, just \fIsize\fP\-1 bytes are +copied and the last byte is set to NUL. +.sp +On success, returns the number of bytes that were written, +including the terminal NUL. This makes this helper useful in +tracing programs for reading strings, and more importantly to +get its length at runtime. See the following snippet: +.INDENT 7.0 +.INDENT 3.5 +.sp +.nf +.ft C +SEC(\(dqkprobe/sys_open\(dq) +void bpf_sys_open(struct pt_regs *ctx) +{ + char buf[PATHLEN]; // PATHLEN is defined to 256 + int res; + + res = bpf_probe_read_user_str(buf, sizeof(buf), + ctx\->di); + + // Consume buf, for example push it to + // userspace via bpf_perf_event_output(); we + // can use res (the string length) as event + // size, after checking its boundaries. +} +.ft P +.fi +.UNINDENT +.UNINDENT +.sp +In comparison, using \fBbpf_probe_read_user\fP() helper here +instead to read the string would require to estimate the length +at compile time, and would often result in copying more memory +than necessary. +.sp +Another useful use case is when parsing individual process +arguments or individual environment variables navigating +\fIcurrent\fP\fB\->mm\->arg_start\fP and \fIcurrent\fP\fB\->mm\->env_start\fP: using this helper and the return value, +one can quickly iterate at the right offset of the memory area. +.TP +.B Return +On success, the strictly positive length of the output string, +including the trailing NUL character. On error, a negative +value. +.UNINDENT +.TP +.B \fBlong bpf_probe_read_kernel_str(void *\fP\fIdst\fP\fB, u32\fP \fIsize\fP\fB, const void *\fP\fIunsafe_ptr\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Copy a NUL terminated string from an unsafe kernel address \fIunsafe_ptr\fP +to \fIdst\fP\&. Same semantics as with \fBbpf_probe_read_user_str\fP() apply. +.TP +.B Return +On success, the strictly positive length of the string, including +the trailing NUL character. On error, a negative value. +.UNINDENT +.TP +.B \fBlong bpf_tcp_send_ack(void *\fP\fItp\fP\fB, u32\fP \fIrcv_nxt\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Send out a tcp\-ack. \fItp\fP is the in\-kernel struct \fBtcp_sock\fP\&. +\fIrcv_nxt\fP is the ack_seq to be sent out. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_send_signal_thread(u32\fP \fIsig\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Send signal \fIsig\fP to the thread corresponding to the current task. +.TP +.B Return +0 on success or successfully queued. +.sp +\fB\-EBUSY\fP if work queue under nmi is full. +.sp +\fB\-EINVAL\fP if \fIsig\fP is invalid. +.sp +\fB\-EPERM\fP if no permission to send the \fIsig\fP\&. +.sp +\fB\-EAGAIN\fP if bpf program can try again. +.UNINDENT +.TP +.B \fBu64 bpf_jiffies64(void)\fP +.INDENT 7.0 +.TP +.B Description +Obtain the 64bit jiffies +.TP +.B Return +The 64 bit jiffies +.UNINDENT +.TP +.B \fBlong bpf_read_branch_records(struct bpf_perf_event_data *\fP\fIctx\fP\fB, void *\fP\fIbuf\fP\fB, u32\fP \fIsize\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +For an eBPF program attached to a perf event, retrieve the +branch records (\fBstruct perf_branch_entry\fP) associated to \fIctx\fP +and store it in the buffer pointed by \fIbuf\fP up to size +\fIsize\fP bytes. +.TP +.B Return +On success, number of bytes written to \fIbuf\fP\&. On error, a +negative value. +.sp +The \fIflags\fP can be set to \fBBPF_F_GET_BRANCH_RECORDS_SIZE\fP to +instead return the number of bytes required to store all the +branch entries. If this flag is set, \fIbuf\fP may be NULL. +.sp +\fB\-EINVAL\fP if arguments invalid or \fBsize\fP not a multiple +of \fBsizeof\fP(\fBstruct perf_branch_entry\fP). +.sp +\fB\-ENOENT\fP if architecture does not support branch records. +.UNINDENT +.TP +.B \fBlong bpf_get_ns_current_pid_tgid(u64\fP \fIdev\fP\fB, u64\fP \fIino\fP\fB, struct bpf_pidns_info *\fP\fInsdata\fP\fB, u32\fP \fIsize\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Returns 0 on success, values for \fIpid\fP and \fItgid\fP as seen from the current +\fInamespace\fP will be returned in \fInsdata\fP\&. +.TP +.B Return +0 on success, or one of the following in case of failure: +.sp +\fB\-EINVAL\fP if dev and inum supplied don\(aqt match dev_t and inode number +with nsfs of current task, or if dev conversion to dev_t lost high bits. +.sp +\fB\-ENOENT\fP if pidns does not exists for the current task. +.UNINDENT +.TP +.B \fBlong bpf_xdp_output(void *\fP\fIctx\fP\fB, struct bpf_map *\fP\fImap\fP\fB, u64\fP \fIflags\fP\fB, void *\fP\fIdata\fP\fB, u64\fP \fIsize\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Write raw \fIdata\fP blob into a special BPF perf event held by +\fImap\fP of type \fBBPF_MAP_TYPE_PERF_EVENT_ARRAY\fP\&. This perf +event must have the following attributes: \fBPERF_SAMPLE_RAW\fP +as \fBsample_type\fP, \fBPERF_TYPE_SOFTWARE\fP as \fBtype\fP, and +\fBPERF_COUNT_SW_BPF_OUTPUT\fP as \fBconfig\fP\&. +.sp +The \fIflags\fP are used to indicate the index in \fImap\fP for which +the value must be put, masked with \fBBPF_F_INDEX_MASK\fP\&. +Alternatively, \fIflags\fP can be set to \fBBPF_F_CURRENT_CPU\fP +to indicate that the index of the current CPU core should be +used. +.sp +The value to write, of \fIsize\fP, is passed through eBPF stack and +pointed by \fIdata\fP\&. +.sp +\fIctx\fP is a pointer to in\-kernel struct xdp_buff. +.sp +This helper is similar to \fBbpf_perf_eventoutput\fP() but +restricted to raw_tracepoint bpf programs. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBu64 bpf_get_netns_cookie(void *\fP\fIctx\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Retrieve the cookie (generated by the kernel) of the network +namespace the input \fIctx\fP is associated with. The network +namespace cookie remains stable for its lifetime and provides +a global identifier that can be assumed unique. If \fIctx\fP is +NULL, then the helper returns the cookie for the initial +network namespace. The cookie itself is very similar to that +of \fBbpf_get_socket_cookie\fP() helper, but for network +namespaces instead of sockets. +.TP +.B Return +A 8\-byte long opaque number. +.UNINDENT +.TP +.B \fBu64 bpf_get_current_ancestor_cgroup_id(int\fP \fIancestor_level\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Return id of cgroup v2 that is ancestor of the cgroup associated +with the current task at the \fIancestor_level\fP\&. The root cgroup +is at \fIancestor_level\fP zero and each step down the hierarchy +increments the level. If \fIancestor_level\fP == level of cgroup +associated with the current task, then return value will be the +same as that of \fBbpf_get_current_cgroup_id\fP(). +.sp +The helper is useful to implement policies based on cgroups +that are upper in hierarchy than immediate cgroup associated +with the current task. +.sp +The format of returned id and helper limitations are same as in +\fBbpf_get_current_cgroup_id\fP(). +.TP +.B Return +The id is returned or 0 in case the id could not be retrieved. +.UNINDENT +.TP +.B \fBlong bpf_sk_assign(struct sk_buff *\fP\fIskb\fP\fB, void *\fP\fIsk\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Helper is overloaded depending on BPF program type. This +description applies to \fBBPF_PROG_TYPE_SCHED_CLS\fP and +\fBBPF_PROG_TYPE_SCHED_ACT\fP programs. +.sp +Assign the \fIsk\fP to the \fIskb\fP\&. When combined with appropriate +routing configuration to receive the packet towards the socket, +will cause \fIskb\fP to be delivered to the specified socket. +Subsequent redirection of \fIskb\fP via \fBbpf_redirect\fP(), +\fBbpf_clone_redirect\fP() or other methods outside of BPF may +interfere with successful delivery to the socket. +.sp +This operation is only valid from TC ingress path. +.sp +The \fIflags\fP argument must be zero. +.TP +.B Return +0 on success, or a negative error in case of failure: +.sp +\fB\-EINVAL\fP if specified \fIflags\fP are not supported. +.sp +\fB\-ENOENT\fP if the socket is unavailable for assignment. +.sp +\fB\-ENETUNREACH\fP if the socket is unreachable (wrong netns). +.sp +\fB\-EOPNOTSUPP\fP if the operation is not supported, for example +a call from outside of TC ingress. +.sp +\fB\-ESOCKTNOSUPPORT\fP if the socket type is not supported +(reuseport). +.UNINDENT +.TP +.B \fBlong bpf_sk_assign(struct bpf_sk_lookup *\fP\fIctx\fP\fB, struct bpf_sock *\fP\fIsk\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Helper is overloaded depending on BPF program type. This +description applies to \fBBPF_PROG_TYPE_SK_LOOKUP\fP programs. +.sp +Select the \fIsk\fP as a result of a socket lookup. +.sp +For the operation to succeed passed socket must be compatible +with the packet description provided by the \fIctx\fP object. +.sp +L4 protocol (\fBIPPROTO_TCP\fP or \fBIPPROTO_UDP\fP) must +be an exact match. While IP family (\fBAF_INET\fP or +\fBAF_INET6\fP) must be compatible, that is IPv6 sockets +that are not v6\-only can be selected for IPv4 packets. +.sp +Only TCP listeners and UDP unconnected sockets can be +selected. \fIsk\fP can also be NULL to reset any previous +selection. +.sp +\fIflags\fP argument can combination of following values: +.INDENT 7.0 +.IP \(bu 2 +\fBBPF_SK_LOOKUP_F_REPLACE\fP to override the previous +socket selection, potentially done by a BPF program +that ran before us. +.IP \(bu 2 +\fBBPF_SK_LOOKUP_F_NO_REUSEPORT\fP to skip +load\-balancing within reuseport group for the socket +being selected. +.UNINDENT +.sp +On success \fIctx\->sk\fP will point to the selected socket. +.TP +.B Return +0 on success, or a negative errno in case of failure. +.INDENT 7.0 +.IP \(bu 2 +\fB\-EAFNOSUPPORT\fP if socket family (\fIsk\->family\fP) is +not compatible with packet family (\fIctx\->family\fP). +.IP \(bu 2 +\fB\-EEXIST\fP if socket has been already selected, +potentially by another program, and +\fBBPF_SK_LOOKUP_F_REPLACE\fP flag was not specified. +.IP \(bu 2 +\fB\-EINVAL\fP if unsupported flags were specified. +.IP \(bu 2 +\fB\-EPROTOTYPE\fP if socket L4 protocol +(\fIsk\->protocol\fP) doesn\(aqt match packet protocol +(\fIctx\->protocol\fP). +.IP \(bu 2 +\fB\-ESOCKTNOSUPPORT\fP if socket is not in allowed +state (TCP listening or UDP unconnected). +.UNINDENT +.UNINDENT +.TP +.B \fBu64 bpf_ktime_get_boot_ns(void)\fP +.INDENT 7.0 +.TP +.B Description +Return the time elapsed since system boot, in nanoseconds. +Does include the time the system was suspended. +See: \fBclock_gettime\fP(\fBCLOCK_BOOTTIME\fP) +.TP +.B Return +Current \fIktime\fP\&. +.UNINDENT +.TP +.B \fBlong bpf_seq_printf(struct seq_file *\fP\fIm\fP\fB, const char *\fP\fIfmt\fP\fB, u32\fP \fIfmt_size\fP\fB, const void *\fP\fIdata\fP\fB, u32\fP \fIdata_len\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +\fBbpf_seq_printf\fP() uses seq_file \fBseq_printf\fP() to print +out the format string. +The \fIm\fP represents the seq_file. The \fIfmt\fP and \fIfmt_size\fP are for +the format string itself. The \fIdata\fP and \fIdata_len\fP are format string +arguments. The \fIdata\fP are a \fBu64\fP array and corresponding format string +values are stored in the array. For strings and pointers where pointees +are accessed, only the pointer values are stored in the \fIdata\fP array. +The \fIdata_len\fP is the size of \fIdata\fP in bytes \- must be a multiple of 8. +.sp +Formats \fB%s\fP, \fB%p{i,I}{4,6}\fP requires to read kernel memory. +Reading kernel memory may fail due to either invalid address or +valid address but requiring a major memory fault. If reading kernel memory +fails, the string for \fB%s\fP will be an empty string, and the ip +address for \fB%p{i,I}{4,6}\fP will be 0. Not returning error to +bpf program is consistent with what \fBbpf_trace_printk\fP() does for now. +.TP +.B Return +0 on success, or a negative error in case of failure: +.sp +\fB\-EBUSY\fP if per\-CPU memory copy buffer is busy, can try again +by returning 1 from bpf program. +.sp +\fB\-EINVAL\fP if arguments are invalid, or if \fIfmt\fP is invalid/unsupported. +.sp +\fB\-E2BIG\fP if \fIfmt\fP contains too many format specifiers. +.sp +\fB\-EOVERFLOW\fP if an overflow happened: The same object will be tried again. +.UNINDENT +.TP +.B \fBlong bpf_seq_write(struct seq_file *\fP\fIm\fP\fB, const void *\fP\fIdata\fP\fB, u32\fP \fIlen\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +\fBbpf_seq_write\fP() uses seq_file \fBseq_write\fP() to write the data. +The \fIm\fP represents the seq_file. The \fIdata\fP and \fIlen\fP represent the +data to write in bytes. +.TP +.B Return +0 on success, or a negative error in case of failure: +.sp +\fB\-EOVERFLOW\fP if an overflow happened: The same object will be tried again. +.UNINDENT +.TP +.B \fBu64 bpf_sk_cgroup_id(void *\fP\fIsk\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Return the cgroup v2 id of the socket \fIsk\fP\&. +.sp +\fIsk\fP must be a non\-\fBNULL\fP pointer to a socket, e.g. one +returned from \fBbpf_sk_lookup_xxx\fP(), +\fBbpf_sk_fullsock\fP(), etc. The format of returned id is +same as in \fBbpf_skb_cgroup_id\fP(). +.sp +This helper is available only if the kernel was compiled with +the \fBCONFIG_SOCK_CGROUP_DATA\fP configuration option. +.TP +.B Return +The id is returned or 0 in case the id could not be retrieved. +.UNINDENT +.TP +.B \fBu64 bpf_sk_ancestor_cgroup_id(void *\fP\fIsk\fP\fB, int\fP \fIancestor_level\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Return id of cgroup v2 that is ancestor of cgroup associated +with the \fIsk\fP at the \fIancestor_level\fP\&. The root cgroup is at +\fIancestor_level\fP zero and each step down the hierarchy +increments the level. If \fIancestor_level\fP == level of cgroup +associated with \fIsk\fP, then return value will be same as that +of \fBbpf_sk_cgroup_id\fP(). +.sp +The helper is useful to implement policies based on cgroups +that are upper in hierarchy than immediate cgroup associated +with \fIsk\fP\&. +.sp +The format of returned id and helper limitations are same as in +\fBbpf_sk_cgroup_id\fP(). +.TP +.B Return +The id is returned or 0 in case the id could not be retrieved. +.UNINDENT +.TP +.B \fBlong bpf_ringbuf_output(void *\fP\fIringbuf\fP\fB, void *\fP\fIdata\fP\fB, u64\fP \fIsize\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Copy \fIsize\fP bytes from \fIdata\fP into a ring buffer \fIringbuf\fP\&. +If \fBBPF_RB_NO_WAKEUP\fP is specified in \fIflags\fP, no notification +of new data availability is sent. +If \fBBPF_RB_FORCE_WAKEUP\fP is specified in \fIflags\fP, notification +of new data availability is sent unconditionally. +If \fB0\fP is specified in \fIflags\fP, an adaptive notification +of new data availability is sent. +.sp +An adaptive notification is a notification sent whenever the user\-space +process has caught up and consumed all available payloads. In case the user\-space +process is still processing a previous payload, then no notification is needed +as it will process the newly added payload automatically. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBvoid *bpf_ringbuf_reserve(void *\fP\fIringbuf\fP\fB, u64\fP \fIsize\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Reserve \fIsize\fP bytes of payload in a ring buffer \fIringbuf\fP\&. +\fIflags\fP must be 0. +.TP +.B Return +Valid pointer with \fIsize\fP bytes of memory available; NULL, +otherwise. +.UNINDENT +.TP +.B \fBvoid bpf_ringbuf_submit(void *\fP\fIdata\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Submit reserved ring buffer sample, pointed to by \fIdata\fP\&. +If \fBBPF_RB_NO_WAKEUP\fP is specified in \fIflags\fP, no notification +of new data availability is sent. +If \fBBPF_RB_FORCE_WAKEUP\fP is specified in \fIflags\fP, notification +of new data availability is sent unconditionally. +If \fB0\fP is specified in \fIflags\fP, an adaptive notification +of new data availability is sent. +.sp +See \(aqbpf_ringbuf_output()\(aq for the definition of adaptive notification. +.TP +.B Return +Nothing. Always succeeds. +.UNINDENT +.TP +.B \fBvoid bpf_ringbuf_discard(void *\fP\fIdata\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Discard reserved ring buffer sample, pointed to by \fIdata\fP\&. +If \fBBPF_RB_NO_WAKEUP\fP is specified in \fIflags\fP, no notification +of new data availability is sent. +If \fBBPF_RB_FORCE_WAKEUP\fP is specified in \fIflags\fP, notification +of new data availability is sent unconditionally. +If \fB0\fP is specified in \fIflags\fP, an adaptive notification +of new data availability is sent. +.sp +See \(aqbpf_ringbuf_output()\(aq for the definition of adaptive notification. +.TP +.B Return +Nothing. Always succeeds. +.UNINDENT +.TP +.B \fBu64 bpf_ringbuf_query(void *\fP\fIringbuf\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Query various characteristics of provided ring buffer. What +exactly is queries is determined by \fIflags\fP: +.INDENT 7.0 +.IP \(bu 2 +\fBBPF_RB_AVAIL_DATA\fP: Amount of data not yet consumed. +.IP \(bu 2 +\fBBPF_RB_RING_SIZE\fP: The size of ring buffer. +.IP \(bu 2 +\fBBPF_RB_CONS_POS\fP: Consumer position (can wrap around). +.IP \(bu 2 +\fBBPF_RB_PROD_POS\fP: Producer(s) position (can wrap around). +.UNINDENT +.sp +Data returned is just a momentary snapshot of actual values +and could be inaccurate, so this facility should be used to +power heuristics and for reporting, not to make 100% correct +calculation. +.TP +.B Return +Requested value, or 0, if \fIflags\fP are not recognized. +.UNINDENT +.TP +.B \fBlong bpf_csum_level(struct sk_buff *\fP\fIskb\fP\fB, u64\fP \fIlevel\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Change the skbs checksum level by one layer up or down, or +reset it entirely to none in order to have the stack perform +checksum validation. The level is applicable to the following +protocols: TCP, UDP, GRE, SCTP, FCOE. For example, a decap of +| ETH | IP | UDP | GUE | IP | TCP | into | ETH | IP | TCP | +through \fBbpf_skb_adjust_room\fP() helper with passing in +\fBBPF_F_ADJ_ROOM_NO_CSUM_RESET\fP flag would require one call +to \fBbpf_csum_level\fP() with \fBBPF_CSUM_LEVEL_DEC\fP since +the UDP header is removed. Similarly, an encap of the latter +into the former could be accompanied by a helper call to +\fBbpf_csum_level\fP() with \fBBPF_CSUM_LEVEL_INC\fP if the +skb is still intended to be processed in higher layers of the +stack instead of just egressing at tc. +.sp +There are three supported level settings at this time: +.INDENT 7.0 +.IP \(bu 2 +\fBBPF_CSUM_LEVEL_INC\fP: Increases skb\->csum_level for skbs +with CHECKSUM_UNNECESSARY. +.IP \(bu 2 +\fBBPF_CSUM_LEVEL_DEC\fP: Decreases skb\->csum_level for skbs +with CHECKSUM_UNNECESSARY. +.IP \(bu 2 +\fBBPF_CSUM_LEVEL_RESET\fP: Resets skb\->csum_level to 0 and +sets CHECKSUM_NONE to force checksum validation by the stack. +.IP \(bu 2 +\fBBPF_CSUM_LEVEL_QUERY\fP: No\-op, returns the current +skb\->csum_level. +.UNINDENT +.TP +.B Return +0 on success, or a negative error in case of failure. In the +case of \fBBPF_CSUM_LEVEL_QUERY\fP, the current skb\->csum_level +is returned or the error code \-EACCES in case the skb is not +subject to CHECKSUM_UNNECESSARY. +.UNINDENT +.TP +.B \fBstruct tcp6_sock *bpf_skc_to_tcp6_sock(void *\fP\fIsk\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Dynamically cast a \fIsk\fP pointer to a \fItcp6_sock\fP pointer. +.TP +.B Return +\fIsk\fP if casting is valid, or \fBNULL\fP otherwise. +.UNINDENT +.TP +.B \fBstruct tcp_sock *bpf_skc_to_tcp_sock(void *\fP\fIsk\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Dynamically cast a \fIsk\fP pointer to a \fItcp_sock\fP pointer. +.TP +.B Return +\fIsk\fP if casting is valid, or \fBNULL\fP otherwise. +.UNINDENT +.TP +.B \fBstruct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *\fP\fIsk\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Dynamically cast a \fIsk\fP pointer to a \fItcp_timewait_sock\fP pointer. +.TP +.B Return +\fIsk\fP if casting is valid, or \fBNULL\fP otherwise. +.UNINDENT +.TP +.B \fBstruct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *\fP\fIsk\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Dynamically cast a \fIsk\fP pointer to a \fItcp_request_sock\fP pointer. +.TP +.B Return +\fIsk\fP if casting is valid, or \fBNULL\fP otherwise. +.UNINDENT +.TP +.B \fBstruct udp6_sock *bpf_skc_to_udp6_sock(void *\fP\fIsk\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Dynamically cast a \fIsk\fP pointer to a \fIudp6_sock\fP pointer. +.TP +.B Return +\fIsk\fP if casting is valid, or \fBNULL\fP otherwise. +.UNINDENT +.TP +.B \fBlong bpf_get_task_stack(struct task_struct *\fP\fItask\fP\fB, void *\fP\fIbuf\fP\fB, u32\fP \fIsize\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Return a user or a kernel stack in bpf program provided buffer. +To achieve this, the helper needs \fItask\fP, which is a valid +pointer to \fBstruct task_struct\fP\&. To store the stacktrace, the +bpf program provides \fIbuf\fP with a nonnegative \fIsize\fP\&. +.sp +The last argument, \fIflags\fP, holds the number of stack frames to +skip (from 0 to 255), masked with +\fBBPF_F_SKIP_FIELD_MASK\fP\&. The next bits can be used to set +the following flags: +.INDENT 7.0 +.TP +.B \fBBPF_F_USER_STACK\fP +Collect a user space stack instead of a kernel stack. +.TP +.B \fBBPF_F_USER_BUILD_ID\fP +Collect buildid+offset instead of ips for user stack, +only valid if \fBBPF_F_USER_STACK\fP is also specified. +.UNINDENT +.sp +\fBbpf_get_task_stack\fP() can collect up to +\fBPERF_MAX_STACK_DEPTH\fP both kernel and user frames, subject +to sufficient large buffer size. Note that +this limit can be controlled with the \fBsysctl\fP program, and +that it should be manually increased in order to profile long +user stacks (such as stacks for Java programs). To do so, use: +.INDENT 7.0 +.INDENT 3.5 +.sp +.nf +.ft C +# sysctl kernel.perf_event_max_stack=<new value> +.ft P +.fi +.UNINDENT +.UNINDENT +.TP +.B Return +The non\-negative copied \fIbuf\fP length equal to or less than +\fIsize\fP on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_load_hdr_opt(struct bpf_sock_ops *\fP\fIskops\fP\fB, void *\fP\fIsearchby_res\fP\fB, u32\fP \fIlen\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Load header option. Support reading a particular TCP header +option for bpf program (\fBBPF_PROG_TYPE_SOCK_OPS\fP). +.sp +If \fIflags\fP is 0, it will search the option from the +\fIskops\fP\fB\->skb_data\fP\&. The comment in \fBstruct bpf_sock_ops\fP +has details on what skb_data contains under different +\fIskops\fP\fB\->op\fP\&. +.sp +The first byte of the \fIsearchby_res\fP specifies the +kind that it wants to search. +.sp +If the searching kind is an experimental kind +(i.e. 253 or 254 according to RFC6994). It also +needs to specify the \(dqmagic\(dq which is either +2 bytes or 4 bytes. It then also needs to +specify the size of the magic by using +the 2nd byte which is \(dqkind\-length\(dq of a TCP +header option and the \(dqkind\-length\(dq also +includes the first 2 bytes \(dqkind\(dq and \(dqkind\-length\(dq +itself as a normal TCP header option also does. +.sp +For example, to search experimental kind 254 with +2 byte magic 0xeB9F, the searchby_res should be +[ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ]. +.sp +To search for the standard window scale option (3), +the \fIsearchby_res\fP should be [ 3, 0, 0, .... 0 ]. +Note, kind\-length must be 0 for regular option. +.sp +Searching for No\-Op (0) and End\-of\-Option\-List (1) are +not supported. +.sp +\fIlen\fP must be at least 2 bytes which is the minimal size +of a header option. +.sp +Supported flags: +.INDENT 7.0 +.IP \(bu 2 +\fBBPF_LOAD_HDR_OPT_TCP_SYN\fP to search from the +saved_syn packet or the just\-received syn packet. +.UNINDENT +.TP +.B Return +> 0 when found, the header option is copied to \fIsearchby_res\fP\&. +The return value is the total length copied. On failure, a +negative error code is returned: +.sp +\fB\-EINVAL\fP if a parameter is invalid. +.sp +\fB\-ENOMSG\fP if the option is not found. +.sp +\fB\-ENOENT\fP if no syn packet is available when +\fBBPF_LOAD_HDR_OPT_TCP_SYN\fP is used. +.sp +\fB\-ENOSPC\fP if there is not enough space. Only \fIlen\fP number of +bytes are copied. +.sp +\fB\-EFAULT\fP on failure to parse the header options in the +packet. +.sp +\fB\-EPERM\fP if the helper cannot be used under the current +\fIskops\fP\fB\->op\fP\&. +.UNINDENT +.TP +.B \fBlong bpf_store_hdr_opt(struct bpf_sock_ops *\fP\fIskops\fP\fB, const void *\fP\fIfrom\fP\fB, u32\fP \fIlen\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Store header option. The data will be copied +from buffer \fIfrom\fP with length \fIlen\fP to the TCP header. +.sp +The buffer \fIfrom\fP should have the whole option that +includes the kind, kind\-length, and the actual +option data. The \fIlen\fP must be at least kind\-length +long. The kind\-length does not have to be 4 byte +aligned. The kernel will take care of the padding +and setting the 4 bytes aligned value to th\->doff. +.sp +This helper will check for duplicated option +by searching the same option in the outgoing skb. +.sp +This helper can only be called during +\fBBPF_SOCK_OPS_WRITE_HDR_OPT_CB\fP\&. +.TP +.B Return +0 on success, or negative error in case of failure: +.sp +\fB\-EINVAL\fP If param is invalid. +.sp +\fB\-ENOSPC\fP if there is not enough space in the header. +Nothing has been written +.sp +\fB\-EEXIST\fP if the option already exists. +.sp +\fB\-EFAULT\fP on failure to parse the existing header options. +.sp +\fB\-EPERM\fP if the helper cannot be used under the current +\fIskops\fP\fB\->op\fP\&. +.UNINDENT +.TP +.B \fBlong bpf_reserve_hdr_opt(struct bpf_sock_ops *\fP\fIskops\fP\fB, u32\fP \fIlen\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Reserve \fIlen\fP bytes for the bpf header option. The +space will be used by \fBbpf_store_hdr_opt\fP() later in +\fBBPF_SOCK_OPS_WRITE_HDR_OPT_CB\fP\&. +.sp +If \fBbpf_reserve_hdr_opt\fP() is called multiple times, +the total number of bytes will be reserved. +.sp +This helper can only be called during +\fBBPF_SOCK_OPS_HDR_OPT_LEN_CB\fP\&. +.TP +.B Return +0 on success, or negative error in case of failure: +.sp +\fB\-EINVAL\fP if a parameter is invalid. +.sp +\fB\-ENOSPC\fP if there is not enough space in the header. +.sp +\fB\-EPERM\fP if the helper cannot be used under the current +\fIskops\fP\fB\->op\fP\&. +.UNINDENT +.TP +.B \fBvoid *bpf_inode_storage_get(struct bpf_map *\fP\fImap\fP\fB, void *\fP\fIinode\fP\fB, void *\fP\fIvalue\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get a bpf_local_storage from an \fIinode\fP\&. +.sp +Logically, it could be thought of as getting the value from +a \fImap\fP with \fIinode\fP as the \fBkey\fP\&. From this +perspective, the usage is not much different from +\fBbpf_map_lookup_elem\fP(\fImap\fP, \fB&\fP\fIinode\fP) except this +helper enforces the key must be an inode and the map must also +be a \fBBPF_MAP_TYPE_INODE_STORAGE\fP\&. +.sp +Underneath, the value is stored locally at \fIinode\fP instead of +the \fImap\fP\&. The \fImap\fP is used as the bpf\-local\-storage +\(dqtype\(dq. The bpf\-local\-storage \(dqtype\(dq (i.e. the \fImap\fP) is +searched against all bpf_local_storage residing at \fIinode\fP\&. +.sp +An optional \fIflags\fP (\fBBPF_LOCAL_STORAGE_GET_F_CREATE\fP) can be +used such that a new bpf_local_storage will be +created if one does not exist. \fIvalue\fP can be used +together with \fBBPF_LOCAL_STORAGE_GET_F_CREATE\fP to specify +the initial value of a bpf_local_storage. If \fIvalue\fP is +\fBNULL\fP, the new bpf_local_storage will be zero initialized. +.TP +.B Return +A bpf_local_storage pointer is returned on success. +.sp +\fBNULL\fP if not found or there was an error in adding +a new bpf_local_storage. +.UNINDENT +.TP +.B \fBint bpf_inode_storage_delete(struct bpf_map *\fP\fImap\fP\fB, void *\fP\fIinode\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Delete a bpf_local_storage from an \fIinode\fP\&. +.TP +.B Return +0 on success. +.sp +\fB\-ENOENT\fP if the bpf_local_storage cannot be found. +.UNINDENT +.TP +.B \fBlong bpf_d_path(struct path *\fP\fIpath\fP\fB, char *\fP\fIbuf\fP\fB, u32\fP \fIsz\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Return full path for given \fBstruct path\fP object, which +needs to be the kernel BTF \fIpath\fP object. The path is +returned in the provided buffer \fIbuf\fP of size \fIsz\fP and +is zero terminated. +.TP +.B Return +On success, the strictly positive length of the string, +including the trailing NUL character. On error, a negative +value. +.UNINDENT +.TP +.B \fBlong bpf_copy_from_user(void *\fP\fIdst\fP\fB, u32\fP \fIsize\fP\fB, const void *\fP\fIuser_ptr\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Read \fIsize\fP bytes from user space address \fIuser_ptr\fP and store +the data in \fIdst\fP\&. This is a wrapper of \fBcopy_from_user\fP(). +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_snprintf_btf(char *\fP\fIstr\fP\fB, u32\fP \fIstr_size\fP\fB, struct btf_ptr *\fP\fIptr\fP\fB, u32\fP \fIbtf_ptr_size\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Use BTF to store a string representation of \fIptr\fP\->ptr in \fIstr\fP, +using \fIptr\fP\->type_id. This value should specify the type +that \fIptr\fP\->ptr points to. LLVM __builtin_btf_type_id(type, 1) +can be used to look up vmlinux BTF type ids. Traversing the +data structure using BTF, the type information and values are +stored in the first \fIstr_size\fP \- 1 bytes of \fIstr\fP\&. Safe copy of +the pointer data is carried out to avoid kernel crashes during +operation. Smaller types can use string space on the stack; +larger programs can use map data to store the string +representation. +.sp +The string can be subsequently shared with userspace via +bpf_perf_event_output() or ring buffer interfaces. +bpf_trace_printk() is to be avoided as it places too small +a limit on string size to be useful. +.sp +\fIflags\fP is a combination of +.INDENT 7.0 +.TP +.B \fBBTF_F_COMPACT\fP +no formatting around type information +.TP +.B \fBBTF_F_NONAME\fP +no struct/union member names/types +.TP +.B \fBBTF_F_PTR_RAW\fP +show raw (unobfuscated) pointer values; +equivalent to printk specifier %px. +.TP +.B \fBBTF_F_ZERO\fP +show zero\-valued struct/union members; they +are not displayed by default +.UNINDENT +.TP +.B Return +The number of bytes that were written (or would have been +written if output had to be truncated due to string size), +or a negative error in cases of failure. +.UNINDENT +.TP +.B \fBlong bpf_seq_printf_btf(struct seq_file *\fP\fIm\fP\fB, struct btf_ptr *\fP\fIptr\fP\fB, u32\fP \fIptr_size\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Use BTF to write to seq_write a string representation of +\fIptr\fP\->ptr, using \fIptr\fP\->type_id as per bpf_snprintf_btf(). +\fIflags\fP are identical to those used for bpf_snprintf_btf. +.TP +.B Return +0 on success or a negative error in case of failure. +.UNINDENT +.TP +.B \fBu64 bpf_skb_cgroup_classid(struct sk_buff *\fP\fIskb\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +See \fBbpf_get_cgroup_classid\fP() for the main description. +This helper differs from \fBbpf_get_cgroup_classid\fP() in that +the cgroup v1 net_cls class is retrieved only from the \fIskb\fP\(aqs +associated socket instead of the current process. +.TP +.B Return +The id is returned or 0 in case the id could not be retrieved. +.UNINDENT +.TP +.B \fBlong bpf_redirect_neigh(u32\fP \fIifindex\fP\fB, struct bpf_redir_neigh *\fP\fIparams\fP\fB, int\fP \fIplen\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Redirect the packet to another net device of index \fIifindex\fP +and fill in L2 addresses from neighboring subsystem. This helper +is somewhat similar to \fBbpf_redirect\fP(), except that it +populates L2 addresses as well, meaning, internally, the helper +relies on the neighbor lookup for the L2 address of the nexthop. +.sp +The helper will perform a FIB lookup based on the skb\(aqs +networking header to get the address of the next hop, unless +this is supplied by the caller in the \fIparams\fP argument. The +\fIplen\fP argument indicates the len of \fIparams\fP and should be set +to 0 if \fIparams\fP is NULL. +.sp +The \fIflags\fP argument is reserved and must be 0. The helper is +currently only supported for tc BPF program types, and enabled +for IPv4 and IPv6 protocols. +.TP +.B Return +The helper returns \fBTC_ACT_REDIRECT\fP on success or +\fBTC_ACT_SHOT\fP on error. +.UNINDENT +.TP +.B \fBvoid *bpf_per_cpu_ptr(const void *\fP\fIpercpu_ptr\fP\fB, u32\fP \fIcpu\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Take a pointer to a percpu ksym, \fIpercpu_ptr\fP, and return a +pointer to the percpu kernel variable on \fIcpu\fP\&. A ksym is an +extern variable decorated with \(aq__ksym\(aq. For ksym, there is a +global var (either static or global) defined of the same name +in the kernel. The ksym is percpu if the global var is percpu. +The returned pointer points to the global percpu var on \fIcpu\fP\&. +.sp +bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the +kernel, except that bpf_per_cpu_ptr() may return NULL. This +happens if \fIcpu\fP is larger than nr_cpu_ids. The caller of +bpf_per_cpu_ptr() must check the returned value. +.TP +.B Return +A pointer pointing to the kernel percpu variable on \fIcpu\fP, or +NULL, if \fIcpu\fP is invalid. +.UNINDENT +.TP +.B \fBvoid *bpf_this_cpu_ptr(const void *\fP\fIpercpu_ptr\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Take a pointer to a percpu ksym, \fIpercpu_ptr\fP, and return a +pointer to the percpu kernel variable on this cpu. See the +description of \(aqksym\(aq in \fBbpf_per_cpu_ptr\fP(). +.sp +bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in +the kernel. Different from \fBbpf_per_cpu_ptr\fP(), it would +never return NULL. +.TP +.B Return +A pointer pointing to the kernel percpu variable on this cpu. +.UNINDENT +.TP +.B \fBlong bpf_redirect_peer(u32\fP \fIifindex\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Redirect the packet to another net device of index \fIifindex\fP\&. +This helper is somewhat similar to \fBbpf_redirect\fP(), except +that the redirection happens to the \fIifindex\fP\(aq peer device and +the netns switch takes place from ingress to ingress without +going through the CPU\(aqs backlog queue. +.sp +The \fIflags\fP argument is reserved and must be 0. The helper is +currently only supported for tc BPF program types at the ingress +hook and for veth device types. The peer device must reside in a +different network namespace. +.TP +.B Return +The helper returns \fBTC_ACT_REDIRECT\fP on success or +\fBTC_ACT_SHOT\fP on error. +.UNINDENT +.TP +.B \fBvoid *bpf_task_storage_get(struct bpf_map *\fP\fImap\fP\fB, struct task_struct *\fP\fItask\fP\fB, void *\fP\fIvalue\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get a bpf_local_storage from the \fItask\fP\&. +.sp +Logically, it could be thought of as getting the value from +a \fImap\fP with \fItask\fP as the \fBkey\fP\&. From this +perspective, the usage is not much different from +\fBbpf_map_lookup_elem\fP(\fImap\fP, \fB&\fP\fItask\fP) except this +helper enforces the key must be a task_struct and the map must also +be a \fBBPF_MAP_TYPE_TASK_STORAGE\fP\&. +.sp +Underneath, the value is stored locally at \fItask\fP instead of +the \fImap\fP\&. The \fImap\fP is used as the bpf\-local\-storage +\(dqtype\(dq. The bpf\-local\-storage \(dqtype\(dq (i.e. the \fImap\fP) is +searched against all bpf_local_storage residing at \fItask\fP\&. +.sp +An optional \fIflags\fP (\fBBPF_LOCAL_STORAGE_GET_F_CREATE\fP) can be +used such that a new bpf_local_storage will be +created if one does not exist. \fIvalue\fP can be used +together with \fBBPF_LOCAL_STORAGE_GET_F_CREATE\fP to specify +the initial value of a bpf_local_storage. If \fIvalue\fP is +\fBNULL\fP, the new bpf_local_storage will be zero initialized. +.TP +.B Return +A bpf_local_storage pointer is returned on success. +.sp +\fBNULL\fP if not found or there was an error in adding +a new bpf_local_storage. +.UNINDENT +.TP +.B \fBlong bpf_task_storage_delete(struct bpf_map *\fP\fImap\fP\fB, struct task_struct *\fP\fItask\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Delete a bpf_local_storage from a \fItask\fP\&. +.TP +.B Return +0 on success. +.sp +\fB\-ENOENT\fP if the bpf_local_storage cannot be found. +.UNINDENT +.TP +.B \fBstruct task_struct *bpf_get_current_task_btf(void)\fP +.INDENT 7.0 +.TP +.B Description +Return a BTF pointer to the \(dqcurrent\(dq task. +This pointer can also be used in helpers that accept an +\fIARG_PTR_TO_BTF_ID\fP of type \fItask_struct\fP\&. +.TP +.B Return +Pointer to the current task. +.UNINDENT +.TP +.B \fBlong bpf_bprm_opts_set(struct linux_binprm *\fP\fIbprm\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Set or clear certain options on \fIbprm\fP: +.sp +\fBBPF_F_BPRM_SECUREEXEC\fP Set the secureexec bit +which sets the \fBAT_SECURE\fP auxv for glibc. The bit +is cleared if the flag is not specified. +.TP +.B Return +\fB\-EINVAL\fP if invalid \fIflags\fP are passed, zero otherwise. +.UNINDENT +.TP +.B \fBu64 bpf_ktime_get_coarse_ns(void)\fP +.INDENT 7.0 +.TP +.B Description +Return a coarse\-grained version of the time elapsed since +system boot, in nanoseconds. Does not include time the system +was suspended. +.sp +See: \fBclock_gettime\fP(\fBCLOCK_MONOTONIC_COARSE\fP) +.TP +.B Return +Current \fIktime\fP\&. +.UNINDENT +.TP +.B \fBlong bpf_ima_inode_hash(struct inode *\fP\fIinode\fP\fB, void *\fP\fIdst\fP\fB, u32\fP \fIsize\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Returns the stored IMA hash of the \fIinode\fP (if it\(aqs available). +If the hash is larger than \fIsize\fP, then only \fIsize\fP +bytes will be copied to \fIdst\fP +.TP +.B Return +The \fBhash_algo\fP is returned on success, +\fB\-EOPNOTSUP\fP if IMA is disabled or \fB\-EINVAL\fP if +invalid arguments are passed. +.UNINDENT +.TP +.B \fBstruct socket *bpf_sock_from_file(struct file *\fP\fIfile\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +If the given file represents a socket, returns the associated +socket. +.TP +.B Return +A pointer to a struct socket on success or NULL if the file is +not a socket. +.UNINDENT +.TP +.B \fBlong bpf_check_mtu(void *\fP\fIctx\fP\fB, u32\fP \fIifindex\fP\fB, u32 *\fP\fImtu_len\fP\fB, s32\fP \fIlen_diff\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Check packet size against exceeding MTU of net device (based +on \fIifindex\fP). This helper will likely be used in combination +with helpers that adjust/change the packet size. +.sp +The argument \fIlen_diff\fP can be used for querying with a planned +size change. This allows to check MTU prior to changing packet +ctx. Providing a \fIlen_diff\fP adjustment that is larger than the +actual packet size (resulting in negative packet size) will in +principle not exceed the MTU, which is why it is not considered +a failure. Other BPF helpers are needed for performing the +planned size change; therefore the responsibility for catching +a negative packet size belongs in those helpers. +.sp +Specifying \fIifindex\fP zero means the MTU check is performed +against the current net device. This is practical if this isn\(aqt +used prior to redirect. +.sp +On input \fImtu_len\fP must be a valid pointer, else verifier will +reject BPF program. If the value \fImtu_len\fP is initialized to +zero then the ctx packet size is use. When value \fImtu_len\fP is +provided as input this specify the L3 length that the MTU check +is done against. Remember XDP and TC length operate at L2, but +this value is L3 as this correlate to MTU and IP\-header tot_len +values which are L3 (similar behavior as bpf_fib_lookup). +.sp +The Linux kernel route table can configure MTUs on a more +specific per route level, which is not provided by this helper. +For route level MTU checks use the \fBbpf_fib_lookup\fP() +helper. +.sp +\fIctx\fP is either \fBstruct xdp_md\fP for XDP programs or +\fBstruct sk_buff\fP for tc cls_act programs. +.sp +The \fIflags\fP argument can be a combination of one or more of the +following values: +.INDENT 7.0 +.TP +.B \fBBPF_MTU_CHK_SEGS\fP +This flag will only works for \fIctx\fP \fBstruct sk_buff\fP\&. +If packet context contains extra packet segment buffers +(often knows as GSO skb), then MTU check is harder to +check at this point, because in transmit path it is +possible for the skb packet to get re\-segmented +(depending on net device features). This could still be +a MTU violation, so this flag enables performing MTU +check against segments, with a different violation +return code to tell it apart. Check cannot use len_diff. +.UNINDENT +.sp +On return \fImtu_len\fP pointer contains the MTU value of the net +device. Remember the net device configured MTU is the L3 size, +which is returned here and XDP and TC length operate at L2. +Helper take this into account for you, but remember when using +MTU value in your BPF\-code. +.TP +.B Return +.INDENT 7.0 +.IP \(bu 2 +0 on success, and populate MTU value in \fImtu_len\fP pointer. +.IP \(bu 2 +< 0 if any input argument is invalid (\fImtu_len\fP not updated) +.UNINDENT +.sp +MTU violations return positive values, but also populate MTU +value in \fImtu_len\fP pointer, as this can be needed for +implementing PMTU handing: +.INDENT 7.0 +.IP \(bu 2 +\fBBPF_MTU_CHK_RET_FRAG_NEEDED\fP +.IP \(bu 2 +\fBBPF_MTU_CHK_RET_SEGS_TOOBIG\fP +.UNINDENT +.UNINDENT +.TP +.B \fBlong bpf_for_each_map_elem(struct bpf_map *\fP\fImap\fP\fB, void *\fP\fIcallback_fn\fP\fB, void *\fP\fIcallback_ctx\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +For each element in \fBmap\fP, call \fBcallback_fn\fP function with +\fBmap\fP, \fBcallback_ctx\fP and other map\-specific parameters. +The \fBcallback_fn\fP should be a static function and +the \fBcallback_ctx\fP should be a pointer to the stack. +The \fBflags\fP is used to control certain aspects of the helper. +Currently, the \fBflags\fP must be 0. +.sp +The following are a list of supported map types and their +respective expected callback signatures: +.sp +BPF_MAP_TYPE_HASH, BPF_MAP_TYPE_PERCPU_HASH, +BPF_MAP_TYPE_LRU_HASH, BPF_MAP_TYPE_LRU_PERCPU_HASH, +BPF_MAP_TYPE_ARRAY, BPF_MAP_TYPE_PERCPU_ARRAY +.sp +long (*callback_fn)(struct bpf_map *map, const void *key, void *value, void *ctx); +.sp +For per_cpu maps, the map_value is the value on the cpu where the +bpf_prog is running. +.sp +If \fBcallback_fn\fP return 0, the helper will continue to the next +element. If return value is 1, the helper will skip the rest of +elements and return. Other return values are not used now. +.TP +.B Return +The number of traversed map elements for success, \fB\-EINVAL\fP for +invalid \fBflags\fP\&. +.UNINDENT +.TP +.B \fBlong bpf_snprintf(char *\fP\fIstr\fP\fB, u32\fP \fIstr_size\fP\fB, const char *\fP\fIfmt\fP\fB, u64 *\fP\fIdata\fP\fB, u32\fP \fIdata_len\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Outputs a string into the \fBstr\fP buffer of size \fBstr_size\fP +based on a format string stored in a read\-only map pointed by +\fBfmt\fP\&. +.sp +Each format specifier in \fBfmt\fP corresponds to one u64 element +in the \fBdata\fP array. For strings and pointers where pointees +are accessed, only the pointer values are stored in the \fIdata\fP +array. The \fIdata_len\fP is the size of \fIdata\fP in bytes \- must be +a multiple of 8. +.sp +Formats \fB%s\fP and \fB%p{i,I}{4,6}\fP require to read kernel +memory. Reading kernel memory may fail due to either invalid +address or valid address but requiring a major memory fault. If +reading kernel memory fails, the string for \fB%s\fP will be an +empty string, and the ip address for \fB%p{i,I}{4,6}\fP will be 0. +Not returning error to bpf program is consistent with what +\fBbpf_trace_printk\fP() does for now. +.TP +.B Return +The strictly positive length of the formatted string, including +the trailing zero character. If the return value is greater than +\fBstr_size\fP, \fBstr\fP contains a truncated string, guaranteed to +be zero\-terminated except when \fBstr_size\fP is 0. +.sp +Or \fB\-EBUSY\fP if the per\-CPU memory copy buffer is busy. +.UNINDENT +.TP +.B \fBlong bpf_sys_bpf(u32\fP \fIcmd\fP\fB, void *\fP\fIattr\fP\fB, u32\fP \fIattr_size\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Execute bpf syscall with given arguments. +.TP +.B Return +A syscall result. +.UNINDENT +.TP +.B \fBlong bpf_btf_find_by_name_kind(char *\fP\fIname\fP\fB, int\fP \fIname_sz\fP\fB, u32\fP \fIkind\fP\fB, int\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Find BTF type with given name and kind in vmlinux BTF or in module\(aqs BTFs. +.TP +.B Return +Returns btf_id and btf_obj_fd in lower and upper 32 bits. +.UNINDENT +.TP +.B \fBlong bpf_sys_close(u32\fP \fIfd\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Execute close syscall for given FD. +.TP +.B Return +A syscall result. +.UNINDENT +.TP +.B \fBlong bpf_timer_init(struct bpf_timer *\fP\fItimer\fP\fB, struct bpf_map *\fP\fImap\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Initialize the timer. +First 4 bits of \fIflags\fP specify clockid. +Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed. +All other bits of \fIflags\fP are reserved. +The verifier will reject the program if \fItimer\fP is not from +the same \fImap\fP\&. +.TP +.B Return +0 on success. +\fB\-EBUSY\fP if \fItimer\fP is already initialized. +\fB\-EINVAL\fP if invalid \fIflags\fP are passed. +\fB\-EPERM\fP if \fItimer\fP is in a map that doesn\(aqt have any user references. +The user space should either hold a file descriptor to a map with timers +or pin such map in bpffs. When map is unpinned or file descriptor is +closed all timers in the map will be cancelled and freed. +.UNINDENT +.TP +.B \fBlong bpf_timer_set_callback(struct bpf_timer *\fP\fItimer\fP\fB, void *\fP\fIcallback_fn\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Configure the timer to call \fIcallback_fn\fP static function. +.TP +.B Return +0 on success. +\fB\-EINVAL\fP if \fItimer\fP was not initialized with bpf_timer_init() earlier. +\fB\-EPERM\fP if \fItimer\fP is in a map that doesn\(aqt have any user references. +The user space should either hold a file descriptor to a map with timers +or pin such map in bpffs. When map is unpinned or file descriptor is +closed all timers in the map will be cancelled and freed. +.UNINDENT +.TP +.B \fBlong bpf_timer_start(struct bpf_timer *\fP\fItimer\fP\fB, u64\fP \fInsecs\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Set timer expiration N nanoseconds from the current time. The +configured callback will be invoked in soft irq context on some cpu +and will not repeat unless another bpf_timer_start() is made. +In such case the next invocation can migrate to a different cpu. +Since struct bpf_timer is a field inside map element the map +owns the timer. The bpf_timer_set_callback() will increment refcnt +of BPF program to make sure that callback_fn code stays valid. +When user space reference to a map reaches zero all timers +in a map are cancelled and corresponding program\(aqs refcnts are +decremented. This is done to make sure that Ctrl\-C of a user +process doesn\(aqt leave any timers running. If map is pinned in +bpffs the callback_fn can re\-arm itself indefinitely. +bpf_map_update/delete_elem() helpers and user space sys_bpf commands +cancel and free the timer in the given map element. +The map can contain timers that invoke callback_fn\-s from different +programs. The same callback_fn can serve different timers from +different maps if key/value layout matches across maps. +Every bpf_timer_set_callback() can have different callback_fn. +.TP +.B Return +0 on success. +\fB\-EINVAL\fP if \fItimer\fP was not initialized with bpf_timer_init() earlier +or invalid \fIflags\fP are passed. +.UNINDENT +.TP +.B \fBlong bpf_timer_cancel(struct bpf_timer *\fP\fItimer\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Cancel the timer and wait for callback_fn to finish if it was running. +.TP +.B Return +0 if the timer was not active. +1 if the timer was active. +\fB\-EINVAL\fP if \fItimer\fP was not initialized with bpf_timer_init() earlier. +\fB\-EDEADLK\fP if callback_fn tried to call bpf_timer_cancel() on its +own timer which would have led to a deadlock otherwise. +.UNINDENT +.TP +.B \fBu64 bpf_get_func_ip(void *\fP\fIctx\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get address of the traced function (for tracing and kprobe programs). +.TP +.B Return +Address of the traced function. +0 for kprobes placed within the function (not at the entry). +.UNINDENT +.TP +.B \fBu64 bpf_get_attach_cookie(void *\fP\fIctx\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get bpf_cookie value provided (optionally) during the program +attachment. It might be different for each individual +attachment, even if BPF program itself is the same. +Expects BPF program context \fIctx\fP as a first argument. +.INDENT 7.0 +.TP +.B Supported for the following program types: +.INDENT 7.0 +.IP \(bu 2 +kprobe/uprobe; +.IP \(bu 2 +tracepoint; +.IP \(bu 2 +perf_event. +.UNINDENT +.UNINDENT +.TP +.B Return +Value specified by user at BPF link creation/attachment time +or 0, if it was not specified. +.UNINDENT +.TP +.B \fBlong bpf_task_pt_regs(struct task_struct *\fP\fItask\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get the struct pt_regs associated with \fBtask\fP\&. +.TP +.B Return +A pointer to struct pt_regs. +.UNINDENT +.TP +.B \fBlong bpf_get_branch_snapshot(void *\fP\fIentries\fP\fB, u32\fP \fIsize\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get branch trace from hardware engines like Intel LBR. The +hardware engine is stopped shortly after the helper is +called. Therefore, the user need to filter branch entries +based on the actual use case. To capture branch trace +before the trigger point of the BPF program, the helper +should be called at the beginning of the BPF program. +.sp +The data is stored as struct perf_branch_entry into output +buffer \fIentries\fP\&. \fIsize\fP is the size of \fIentries\fP in bytes. +\fIflags\fP is reserved for now and must be zero. +.TP +.B Return +On success, number of bytes written to \fIbuf\fP\&. On error, a +negative value. +.sp +\fB\-EINVAL\fP if \fIflags\fP is not zero. +.sp +\fB\-ENOENT\fP if architecture does not support branch records. +.UNINDENT +.TP +.B \fBlong bpf_trace_vprintk(const char *\fP\fIfmt\fP\fB, u32\fP \fIfmt_size\fP\fB, const void *\fP\fIdata\fP\fB, u32\fP \fIdata_len\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Behaves like \fBbpf_trace_printk\fP() helper, but takes an array of u64 +to format and can handle more format args as a result. +.sp +Arguments are to be used as in \fBbpf_seq_printf\fP() helper. +.TP +.B Return +The number of bytes written to the buffer, or a negative error +in case of failure. +.UNINDENT +.TP +.B \fBstruct unix_sock *bpf_skc_to_unix_sock(void *\fP\fIsk\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Dynamically cast a \fIsk\fP pointer to a \fIunix_sock\fP pointer. +.TP +.B Return +\fIsk\fP if casting is valid, or \fBNULL\fP otherwise. +.UNINDENT +.TP +.B \fBlong bpf_kallsyms_lookup_name(const char *\fP\fIname\fP\fB, int\fP \fIname_sz\fP\fB, int\fP \fIflags\fP\fB, u64 *\fP\fIres\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get the address of a kernel symbol, returned in \fIres\fP\&. \fIres\fP is +set to 0 if the symbol is not found. +.TP +.B Return +On success, zero. On error, a negative value. +.sp +\fB\-EINVAL\fP if \fIflags\fP is not zero. +.sp +\fB\-EINVAL\fP if string \fIname\fP is not the same size as \fIname_sz\fP\&. +.sp +\fB\-ENOENT\fP if symbol is not found. +.sp +\fB\-EPERM\fP if caller does not have permission to obtain kernel address. +.UNINDENT +.TP +.B \fBlong bpf_find_vma(struct task_struct *\fP\fItask\fP\fB, u64\fP \fIaddr\fP\fB, void *\fP\fIcallback_fn\fP\fB, void *\fP\fIcallback_ctx\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Find vma of \fItask\fP that contains \fIaddr\fP, call \fIcallback_fn\fP +function with \fItask\fP, \fIvma\fP, and \fIcallback_ctx\fP\&. +The \fIcallback_fn\fP should be a static function and +the \fIcallback_ctx\fP should be a pointer to the stack. +The \fIflags\fP is used to control certain aspects of the helper. +Currently, the \fIflags\fP must be 0. +.sp +The expected callback signature is +.sp +long (*callback_fn)(struct task_struct *task, struct vm_area_struct *vma, void *callback_ctx); +.TP +.B Return +0 on success. +\fB\-ENOENT\fP if \fItask\->mm\fP is NULL, or no vma contains \fIaddr\fP\&. +\fB\-EBUSY\fP if failed to try lock mmap_lock. +\fB\-EINVAL\fP for invalid \fBflags\fP\&. +.UNINDENT +.TP +.B \fBlong bpf_loop(u32\fP \fInr_loops\fP\fB, void *\fP\fIcallback_fn\fP\fB, void *\fP\fIcallback_ctx\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +For \fBnr_loops\fP, call \fBcallback_fn\fP function +with \fBcallback_ctx\fP as the context parameter. +The \fBcallback_fn\fP should be a static function and +the \fBcallback_ctx\fP should be a pointer to the stack. +The \fBflags\fP is used to control certain aspects of the helper. +Currently, the \fBflags\fP must be 0. Currently, nr_loops is +limited to 1 << 23 (~8 million) loops. +.sp +long (*callback_fn)(u32 index, void *ctx); +.sp +where \fBindex\fP is the current index in the loop. The index +is zero\-indexed. +.sp +If \fBcallback_fn\fP returns 0, the helper will continue to the next +loop. If return value is 1, the helper will skip the rest of +the loops and return. Other return values are not used now, +and will be rejected by the verifier. +.TP +.B Return +The number of loops performed, \fB\-EINVAL\fP for invalid \fBflags\fP, +\fB\-E2BIG\fP if \fBnr_loops\fP exceeds the maximum number of loops. +.UNINDENT +.TP +.B \fBlong bpf_strncmp(const char *\fP\fIs1\fP\fB, u32\fP \fIs1_sz\fP\fB, const char *\fP\fIs2\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Do strncmp() between \fBs1\fP and \fBs2\fP\&. \fBs1\fP doesn\(aqt need +to be null\-terminated and \fBs1_sz\fP is the maximum storage +size of \fBs1\fP\&. \fBs2\fP must be a read\-only string. +.TP +.B Return +An integer less than, equal to, or greater than zero +if the first \fBs1_sz\fP bytes of \fBs1\fP is found to be +less than, to match, or be greater than \fBs2\fP\&. +.UNINDENT +.TP +.B \fBlong bpf_get_func_arg(void *\fP\fIctx\fP\fB, u32\fP \fIn\fP\fB, u64 *\fP\fIvalue\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get \fBn\fP\-th argument register (zero based) of the traced function (for tracing programs) +returned in \fBvalue\fP\&. +.TP +.B Return +0 on success. +\fB\-EINVAL\fP if n >= argument register count of traced function. +.UNINDENT +.TP +.B \fBlong bpf_get_func_ret(void *\fP\fIctx\fP\fB, u64 *\fP\fIvalue\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get return value of the traced function (for tracing programs) +in \fBvalue\fP\&. +.TP +.B Return +0 on success. +\fB\-EOPNOTSUPP\fP for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN. +.UNINDENT +.TP +.B \fBlong bpf_get_func_arg_cnt(void *\fP\fIctx\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get number of registers of the traced function (for tracing programs) where +function arguments are stored in these registers. +.TP +.B Return +The number of argument registers of the traced function. +.UNINDENT +.TP +.B \fBint bpf_get_retval(void)\fP +.INDENT 7.0 +.TP +.B Description +Get the BPF program\(aqs return value that will be returned to the upper layers. +.sp +This helper is currently supported by cgroup programs and only by the hooks +where BPF program\(aqs return value is returned to the userspace via errno. +.TP +.B Return +The BPF program\(aqs return value. +.UNINDENT +.TP +.B \fBint bpf_set_retval(int\fP \fIretval\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Set the BPF program\(aqs return value that will be returned to the upper layers. +.sp +This helper is currently supported by cgroup programs and only by the hooks +where BPF program\(aqs return value is returned to the userspace via errno. +.sp +Note that there is the following corner case where the program exports an error +via bpf_set_retval but signals success via \(aqreturn 1\(aq: +.INDENT 7.0 +.INDENT 3.5 +bpf_set_retval(\-EPERM); +return 1; +.UNINDENT +.UNINDENT +.sp +In this case, the BPF program\(aqs return value will use helper\(aqs \-EPERM. This +still holds true for cgroup/bind{4,6} which supports extra \(aqreturn 3\(aq success case. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBu64 bpf_xdp_get_buff_len(struct xdp_buff *\fP\fIxdp_md\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get the total size of a given xdp buff (linear and paged area) +.TP +.B Return +The total size of a given xdp buffer. +.UNINDENT +.TP +.B \fBlong bpf_xdp_load_bytes(struct xdp_buff *\fP\fIxdp_md\fP\fB, u32\fP \fIoffset\fP\fB, void *\fP\fIbuf\fP\fB, u32\fP \fIlen\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +This helper is provided as an easy way to load data from a +xdp buffer. It can be used to load \fIlen\fP bytes from \fIoffset\fP from +the frame associated to \fIxdp_md\fP, into the buffer pointed by +\fIbuf\fP\&. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_xdp_store_bytes(struct xdp_buff *\fP\fIxdp_md\fP\fB, u32\fP \fIoffset\fP\fB, void *\fP\fIbuf\fP\fB, u32\fP \fIlen\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Store \fIlen\fP bytes from buffer \fIbuf\fP into the frame +associated to \fIxdp_md\fP, at \fIoffset\fP\&. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBlong bpf_copy_from_user_task(void *\fP\fIdst\fP\fB, u32\fP \fIsize\fP\fB, const void *\fP\fIuser_ptr\fP\fB, struct task_struct *\fP\fItsk\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Read \fIsize\fP bytes from user space address \fIuser_ptr\fP in \fItsk\fP\(aqs +address space, and stores the data in \fIdst\fP\&. \fIflags\fP is not +used yet and is provided for future extensibility. This helper +can only be used by sleepable programs. +.TP +.B Return +0 on success, or a negative error in case of failure. On error +\fIdst\fP buffer is zeroed out. +.UNINDENT +.TP +.B \fBlong bpf_skb_set_tstamp(struct sk_buff *\fP\fIskb\fP\fB, u64\fP \fItstamp\fP\fB, u32\fP \fItstamp_type\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Change the __sk_buff\->tstamp_type to \fItstamp_type\fP +and set \fItstamp\fP to the __sk_buff\->tstamp together. +.sp +If there is no need to change the __sk_buff\->tstamp_type, +the tstamp value can be directly written to __sk_buff\->tstamp +instead. +.sp +BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that +will be kept during bpf_redirect_*(). A non zero +\fItstamp\fP must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO +\fItstamp_type\fP\&. +.sp +A BPF_SKB_TSTAMP_UNSPEC \fItstamp_type\fP can only be used +with a zero \fItstamp\fP\&. +.sp +Only IPv4 and IPv6 skb\->protocol are supported. +.sp +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 \fI\%sch_fq@phy\-dev\fP\&. +.TP +.B Return +0 on success. +\fB\-EINVAL\fP for invalid input +\fB\-EOPNOTSUPP\fP for unsupported protocol +.UNINDENT +.TP +.B \fBlong bpf_ima_file_hash(struct file *\fP\fIfile\fP\fB, void *\fP\fIdst\fP\fB, u32\fP \fIsize\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Returns a calculated IMA hash of the \fIfile\fP\&. +If the hash is larger than \fIsize\fP, then only \fIsize\fP +bytes will be copied to \fIdst\fP +.TP +.B Return +The \fBhash_algo\fP is returned on success, +\fB\-EOPNOTSUP\fP if the hash calculation failed or \fB\-EINVAL\fP if +invalid arguments are passed. +.UNINDENT +.TP +.B \fBvoid *bpf_kptr_xchg(void *\fP\fImap_value\fP\fB, void *\fP\fIptr\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Exchange kptr at pointer \fImap_value\fP with \fIptr\fP, and return the +old value. \fIptr\fP can be NULL, otherwise it must be a referenced +pointer which will be released when this helper is called. +.TP +.B Return +The old value of kptr (which can be NULL). The returned pointer +if not NULL, is a reference which must be released using its +corresponding release function, or moved into a BPF map before +program exit. +.UNINDENT +.TP +.B \fBvoid *bpf_map_lookup_percpu_elem(struct bpf_map *\fP\fImap\fP\fB, const void *\fP\fIkey\fP\fB, u32\fP \fIcpu\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Perform a lookup in \fIpercpu map\fP for an entry associated to +\fIkey\fP on \fIcpu\fP\&. +.TP +.B Return +Map value associated to \fIkey\fP on \fIcpu\fP, or \fBNULL\fP if no entry +was found or \fIcpu\fP is invalid. +.UNINDENT +.TP +.B \fBstruct mptcp_sock *bpf_skc_to_mptcp_sock(void *\fP\fIsk\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Dynamically cast a \fIsk\fP pointer to a \fImptcp_sock\fP pointer. +.TP +.B Return +\fIsk\fP if casting is valid, or \fBNULL\fP otherwise. +.UNINDENT +.TP +.B \fBlong bpf_dynptr_from_mem(void *\fP\fIdata\fP\fB, u32\fP \fIsize\fP\fB, u64\fP \fIflags\fP\fB, struct bpf_dynptr *\fP\fIptr\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get a dynptr to local memory \fIdata\fP\&. +.sp +\fIdata\fP must be a ptr to a map value. +The maximum \fIsize\fP supported is DYNPTR_MAX_SIZE. +\fIflags\fP is currently unused. +.TP +.B Return +0 on success, \-E2BIG if the size exceeds DYNPTR_MAX_SIZE, +\-EINVAL if flags is not 0. +.UNINDENT +.TP +.B \fBlong bpf_ringbuf_reserve_dynptr(void *\fP\fIringbuf\fP\fB, u32\fP \fIsize\fP\fB, u64\fP \fIflags\fP\fB, struct bpf_dynptr *\fP\fIptr\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Reserve \fIsize\fP bytes of payload in a ring buffer \fIringbuf\fP +through the dynptr interface. \fIflags\fP must be 0. +.sp +Please note that a corresponding bpf_ringbuf_submit_dynptr or +bpf_ringbuf_discard_dynptr must be called on \fIptr\fP, even if the +reservation fails. This is enforced by the verifier. +.TP +.B Return +0 on success, or a negative error in case of failure. +.UNINDENT +.TP +.B \fBvoid bpf_ringbuf_submit_dynptr(struct bpf_dynptr *\fP\fIptr\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Submit reserved ring buffer sample, pointed to by \fIdata\fP, +through the dynptr interface. This is a no\-op if the dynptr is +invalid/null. +.sp +For more information on \fIflags\fP, please see +\(aqbpf_ringbuf_submit\(aq. +.TP +.B Return +Nothing. Always succeeds. +.UNINDENT +.TP +.B \fBvoid bpf_ringbuf_discard_dynptr(struct bpf_dynptr *\fP\fIptr\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Discard reserved ring buffer sample through the dynptr +interface. This is a no\-op if the dynptr is invalid/null. +.sp +For more information on \fIflags\fP, please see +\(aqbpf_ringbuf_discard\(aq. +.TP +.B Return +Nothing. Always succeeds. +.UNINDENT +.TP +.B \fBlong bpf_dynptr_read(void *\fP\fIdst\fP\fB, u32\fP \fIlen\fP\fB, const struct bpf_dynptr *\fP\fIsrc\fP\fB, u32\fP \fIoffset\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Read \fIlen\fP bytes from \fIsrc\fP into \fIdst\fP, starting from \fIoffset\fP +into \fIsrc\fP\&. +\fIflags\fP is currently unused. +.TP +.B Return +0 on success, \-E2BIG if \fIoffset\fP + \fIlen\fP exceeds the length +of \fIsrc\fP\(aqs data, \-EINVAL if \fIsrc\fP is an invalid dynptr or if +\fIflags\fP is not 0. +.UNINDENT +.TP +.B \fBlong bpf_dynptr_write(const struct bpf_dynptr *\fP\fIdst\fP\fB, u32\fP \fIoffset\fP\fB, void *\fP\fIsrc\fP\fB, u32\fP \fIlen\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Write \fIlen\fP bytes from \fIsrc\fP into \fIdst\fP, starting from \fIoffset\fP +into \fIdst\fP\&. +\fIflags\fP is currently unused. +.TP +.B Return +0 on success, \-E2BIG if \fIoffset\fP + \fIlen\fP exceeds the length +of \fIdst\fP\(aqs data, \-EINVAL if \fIdst\fP is an invalid dynptr or if \fIdst\fP +is a read\-only dynptr or if \fIflags\fP is not 0. +.UNINDENT +.TP +.B \fBvoid *bpf_dynptr_data(const struct bpf_dynptr *\fP\fIptr\fP\fB, u32\fP \fIoffset\fP\fB, u32\fP \fIlen\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get a pointer to the underlying dynptr data. +.sp +\fIlen\fP must be a statically known value. The returned data slice +is invalidated whenever the dynptr is invalidated. +.TP +.B Return +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. +.UNINDENT +.TP +.B \fBs64 bpf_tcp_raw_gen_syncookie_ipv4(struct iphdr *\fP\fIiph\fP\fB, struct tcphdr *\fP\fIth\fP\fB, u32\fP \fIth_len\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Try to issue a SYN cookie for the packet with corresponding +IPv4/TCP headers, \fIiph\fP and \fIth\fP, without depending on a +listening socket. +.sp +\fIiph\fP points to the IPv4 header. +.sp +\fIth\fP points to the start of the TCP header, while \fIth_len\fP +contains the length of the TCP header (at least +\fBsizeof\fP(\fBstruct tcphdr\fP)). +.TP +.B 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. +.sp +On failure, the returned value is one of the following: +.sp +\fB\-EINVAL\fP if \fIth_len\fP is invalid. +.UNINDENT +.TP +.B \fBs64 bpf_tcp_raw_gen_syncookie_ipv6(struct ipv6hdr *\fP\fIiph\fP\fB, struct tcphdr *\fP\fIth\fP\fB, u32\fP \fIth_len\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Try to issue a SYN cookie for the packet with corresponding +IPv6/TCP headers, \fIiph\fP and \fIth\fP, without depending on a +listening socket. +.sp +\fIiph\fP points to the IPv6 header. +.sp +\fIth\fP points to the start of the TCP header, while \fIth_len\fP +contains the length of the TCP header (at least +\fBsizeof\fP(\fBstruct tcphdr\fP)). +.TP +.B 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. +.sp +On failure, the returned value is one of the following: +.sp +\fB\-EINVAL\fP if \fIth_len\fP is invalid. +.sp +\fB\-EPROTONOSUPPORT\fP if CONFIG_IPV6 is not builtin. +.UNINDENT +.TP +.B \fBlong bpf_tcp_raw_check_syncookie_ipv4(struct iphdr *\fP\fIiph\fP\fB, struct tcphdr *\fP\fIth\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Check whether \fIiph\fP and \fIth\fP contain a valid SYN cookie ACK +without depending on a listening socket. +.sp +\fIiph\fP points to the IPv4 header. +.sp +\fIth\fP points to the TCP header. +.TP +.B Return +0 if \fIiph\fP and \fIth\fP are a valid SYN cookie ACK. +.sp +On failure, the returned value is one of the following: +.sp +\fB\-EACCES\fP if the SYN cookie is not valid. +.UNINDENT +.TP +.B \fBlong bpf_tcp_raw_check_syncookie_ipv6(struct ipv6hdr *\fP\fIiph\fP\fB, struct tcphdr *\fP\fIth\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Check whether \fIiph\fP and \fIth\fP contain a valid SYN cookie ACK +without depending on a listening socket. +.sp +\fIiph\fP points to the IPv6 header. +.sp +\fIth\fP points to the TCP header. +.TP +.B Return +0 if \fIiph\fP and \fIth\fP are a valid SYN cookie ACK. +.sp +On failure, the returned value is one of the following: +.sp +\fB\-EACCES\fP if the SYN cookie is not valid. +.sp +\fB\-EPROTONOSUPPORT\fP if CONFIG_IPV6 is not builtin. +.UNINDENT +.TP +.B \fBu64 bpf_ktime_get_tai_ns(void)\fP +.INDENT 7.0 +.TP +.B Description +A nonsettable system\-wide clock derived from wall\-clock time but +ignoring leap seconds. This clock does not experience +discontinuities and backwards jumps caused by NTP inserting leap +seconds as CLOCK_REALTIME does. +.sp +See: \fBclock_gettime\fP(\fBCLOCK_TAI\fP) +.TP +.B Return +Current \fIktime\fP\&. +.UNINDENT +.TP +.B \fBlong bpf_user_ringbuf_drain(struct bpf_map *\fP\fImap\fP\fB, void *\fP\fIcallback_fn\fP\fB, void *\fP\fIctx\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Drain samples from the specified user ring buffer, and invoke +the provided callback for each such sample: +.sp +long (*callback_fn)(const struct bpf_dynptr *dynptr, void *ctx); +.sp +If \fBcallback_fn\fP returns 0, the helper will continue to try +and drain the next sample, up to a maximum of +BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1, +the helper will skip the rest of the samples and return. Other +return values are not used now, and will be rejected by the +verifier. +.TP +.B Return +The number of drained samples if no error was encountered while +draining samples, or 0 if no samples were present in the ring +buffer. If a user\-space producer was epoll\-waiting on this map, +and at least one sample was drained, they will receive an event +notification notifying them of available space in the ring +buffer. If the BPF_RB_NO_WAKEUP flag is passed to this +function, no wakeup notification will be sent. If the +BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will +be sent even if no sample was drained. +.sp +On failure, the returned value is one of the following: +.sp +\fB\-EBUSY\fP if the ring buffer is contended, and another calling +context was concurrently draining the ring buffer. +.sp +\fB\-EINVAL\fP if user\-space is not properly tracking the ring +buffer due to the producer position not being aligned to 8 +bytes, a sample not being aligned to 8 bytes, or the producer +position not matching the advertised length of a sample. +.sp +\fB\-E2BIG\fP if user\-space has tried to publish a sample which is +larger than the size of the ring buffer, or which cannot fit +within a struct bpf_dynptr. +.UNINDENT +.TP +.B \fBvoid *bpf_cgrp_storage_get(struct bpf_map *\fP\fImap\fP\fB, struct cgroup *\fP\fIcgroup\fP\fB, void *\fP\fIvalue\fP\fB, u64\fP \fIflags\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Get a bpf_local_storage from the \fIcgroup\fP\&. +.sp +Logically, it could be thought of as getting the value from +a \fImap\fP with \fIcgroup\fP as the \fBkey\fP\&. From this +perspective, the usage is not much different from +\fBbpf_map_lookup_elem\fP(\fImap\fP, \fB&\fP\fIcgroup\fP) except this +helper enforces the key must be a cgroup struct and the map must also +be a \fBBPF_MAP_TYPE_CGRP_STORAGE\fP\&. +.sp +In reality, the local\-storage value is embedded directly inside of the +\fIcgroup\fP object itself, rather than being located in the +\fBBPF_MAP_TYPE_CGRP_STORAGE\fP map. When the local\-storage value is +queried for some \fImap\fP on a \fIcgroup\fP object, the kernel will perform an +O(n) iteration over all of the live local\-storage values for that +\fIcgroup\fP object until the local\-storage value for the \fImap\fP is found. +.sp +An optional \fIflags\fP (\fBBPF_LOCAL_STORAGE_GET_F_CREATE\fP) can be +used such that a new bpf_local_storage will be +created if one does not exist. \fIvalue\fP can be used +together with \fBBPF_LOCAL_STORAGE_GET_F_CREATE\fP to specify +the initial value of a bpf_local_storage. If \fIvalue\fP is +\fBNULL\fP, the new bpf_local_storage will be zero initialized. +.TP +.B Return +A bpf_local_storage pointer is returned on success. +.sp +\fBNULL\fP if not found or there was an error in adding +a new bpf_local_storage. +.UNINDENT +.TP +.B \fBlong bpf_cgrp_storage_delete(struct bpf_map *\fP\fImap\fP\fB, struct cgroup *\fP\fIcgroup\fP\fB)\fP +.INDENT 7.0 +.TP +.B Description +Delete a bpf_local_storage from a \fIcgroup\fP\&. +.TP +.B Return +0 on success. +.sp +\fB\-ENOENT\fP if the bpf_local_storage cannot be found. +.UNINDENT +.UNINDENT +.SH EXAMPLES +.sp +Example usage for most of the eBPF helpers listed in this manual page are +available within the Linux kernel sources, at the following locations: +.INDENT 0.0 +.IP \(bu 2 +\fIsamples/bpf/\fP +.IP \(bu 2 +\fItools/testing/selftests/bpf/\fP +.UNINDENT +.SH LICENSE +.sp +eBPF programs can have an associated license, passed along with the bytecode +instructions to the kernel when the programs are loaded. The format for that +string is identical to the one in use for kernel modules (Dual licenses, such +as \(dqDual BSD/GPL\(dq, may be used). Some helper functions are only accessible to +programs that are compatible with the GNU Privacy License (GPL). +.sp +In order to use such helpers, the eBPF program must be loaded with the correct +license string passed (via \fBattr\fP) to the \fBbpf\fP() system call, and this +generally translates into the C source code of the program containing a line +similar to the following: +.INDENT 0.0 +.INDENT 3.5 +.sp +.nf +.ft C +char ____license[] __attribute__((section(\(dqlicense\(dq), used)) = \(dqGPL\(dq; +.ft P +.fi +.UNINDENT +.UNINDENT +.SH IMPLEMENTATION +.sp +This manual page is an effort to document the existing eBPF helper functions. +But as of this writing, the BPF sub\-system is under heavy development. New eBPF +program or map types are added, along with new helper functions. Some helpers +are occasionally made available for additional program types. So in spite of +the efforts of the community, this page might not be up\-to\-date. If you want to +check by yourself what helper functions exist in your kernel, or what types of +programs they can support, here are some files among the kernel tree that you +may be interested in: +.INDENT 0.0 +.IP \(bu 2 +\fIinclude/uapi/linux/bpf.h\fP is the main BPF header. It contains the full list +of all helper functions, as well as many other BPF definitions including most +of the flags, structs or constants used by the helpers. +.IP \(bu 2 +\fInet/core/filter.c\fP contains the definition of most network\-related helper +functions, and the list of program types from which they can be used. +.IP \(bu 2 +\fIkernel/trace/bpf_trace.c\fP is the equivalent for most tracing program\-related +helpers. +.IP \(bu 2 +\fIkernel/bpf/verifier.c\fP contains the functions used to check that valid types +of eBPF maps are used with a given helper function. +.IP \(bu 2 +\fIkernel/bpf/\fP directory contains other files in which additional helpers are +defined (for cgroups, sockmaps, etc.). +.IP \(bu 2 +The bpftool utility can be used to probe the availability of helper functions +on the system (as well as supported program and map types, and a number of +other parameters). To do so, run \fBbpftool feature probe\fP (see +\fBbpftool\-feature\fP(8) for details). Add the \fBunprivileged\fP keyword to +list features available to unprivileged users. +.UNINDENT +.sp +Compatibility between helper functions and program types can generally be found +in the files where helper functions are defined. Look for the \fBstruct +bpf_func_proto\fP objects and for functions returning them: these functions +contain a list of helpers that a given program type can call. Note that the +\fBdefault:\fP label of the \fBswitch ... case\fP used to filter helpers can call +other functions, themselves allowing access to additional helpers. The +requirement for GPL license is also in those \fBstruct bpf_func_proto\fP\&. +.sp +Compatibility between helper functions and map types can be found in the +\fBcheck_map_func_compatibility\fP() function in file \fIkernel/bpf/verifier.c\fP\&. +.sp +Helper functions that invalidate the checks on \fBdata\fP and \fBdata_end\fP +pointers for network processing are listed in function +\fBbpf_helper_changes_pkt_data\fP() in file \fInet/core/filter.c\fP\&. +.SH SEE ALSO +.sp +\fBbpf\fP(2), +\fBbpftool\fP(8), +\fBcgroups\fP(7), +\fBip\fP(8), +\fBperf_event_open\fP(2), +\fBsendmsg\fP(2), +\fBsocket\fP(7), +\fBtc\-bpf\fP(8) +.\" Generated by docutils manpage writer. +. |