mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-21 10:06:00 +07:00
b2197755b2
This work adds support for "persistent" eBPF maps/programs. The term "persistent" is to be understood that maps/programs have a facility that lets them survive process termination. This is desired by various eBPF subsystem users. Just to name one example: tc classifier/action. Whenever tc parses the ELF object, extracts and loads maps/progs into the kernel, these file descriptors will be out of reach after the tc instance exits. So a subsequent tc invocation won't be able to access/relocate on this resource, and therefore maps cannot easily be shared, f.e. between the ingress and egress networking data path. The current workaround is that Unix domain sockets (UDS) need to be instrumented in order to pass the created eBPF map/program file descriptors to a third party management daemon through UDS' socket passing facility. This makes it a bit complicated to deploy shared eBPF maps or programs (programs f.e. for tail calls) among various processes. We've been brainstorming on how we could tackle this issue and various approches have been tried out so far, which can be read up further in the below reference. The architecture we eventually ended up with is a minimal file system that can hold map/prog objects. The file system is a per mount namespace singleton, and the default mount point is /sys/fs/bpf/. Any subsequent mounts within a given namespace will point to the same instance. The file system allows for creating a user-defined directory structure. The objects for maps/progs are created/fetched through bpf(2) with two new commands (BPF_OBJ_PIN/BPF_OBJ_GET). I.e. a bpf file descriptor along with a pathname is being passed to bpf(2) that in turn creates (we call it eBPF object pinning) the file system nodes. Only the pathname is being passed to bpf(2) for getting a new BPF file descriptor to an existing node. The user can use that to access maps and progs later on, through bpf(2). Removal of file system nodes is being managed through normal VFS functions such as unlink(2), etc. The file system code is kept to a very minimum and can be further extended later on. The next step I'm working on is to add dump eBPF map/prog commands to bpf(2), so that a specification from a given file descriptor can be retrieved. This can be used by things like CRIU but also applications can inspect the meta data after calling BPF_OBJ_GET. Big thanks also to Alexei and Hannes who significantly contributed in the design discussion that eventually let us end up with this architecture here. Reference: https://lkml.org/lkml/2015/10/15/925 Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
302 lines
8.2 KiB
C
302 lines
8.2 KiB
C
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of version 2 of the GNU General Public
|
|
* License as published by the Free Software Foundation.
|
|
*/
|
|
#ifndef _UAPI__LINUX_BPF_H__
|
|
#define _UAPI__LINUX_BPF_H__
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/bpf_common.h>
|
|
|
|
/* Extended instruction set based on top of classic BPF */
|
|
|
|
/* instruction classes */
|
|
#define BPF_ALU64 0x07 /* alu mode in double word width */
|
|
|
|
/* ld/ldx fields */
|
|
#define BPF_DW 0x18 /* double word */
|
|
#define BPF_XADD 0xc0 /* exclusive add */
|
|
|
|
/* alu/jmp fields */
|
|
#define BPF_MOV 0xb0 /* mov reg to reg */
|
|
#define BPF_ARSH 0xc0 /* sign extending arithmetic shift right */
|
|
|
|
/* change endianness of a register */
|
|
#define BPF_END 0xd0 /* flags for endianness conversion: */
|
|
#define BPF_TO_LE 0x00 /* convert to little-endian */
|
|
#define BPF_TO_BE 0x08 /* convert to big-endian */
|
|
#define BPF_FROM_LE BPF_TO_LE
|
|
#define BPF_FROM_BE BPF_TO_BE
|
|
|
|
#define BPF_JNE 0x50 /* jump != */
|
|
#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */
|
|
#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */
|
|
#define BPF_CALL 0x80 /* function call */
|
|
#define BPF_EXIT 0x90 /* function return */
|
|
|
|
/* Register numbers */
|
|
enum {
|
|
BPF_REG_0 = 0,
|
|
BPF_REG_1,
|
|
BPF_REG_2,
|
|
BPF_REG_3,
|
|
BPF_REG_4,
|
|
BPF_REG_5,
|
|
BPF_REG_6,
|
|
BPF_REG_7,
|
|
BPF_REG_8,
|
|
BPF_REG_9,
|
|
BPF_REG_10,
|
|
__MAX_BPF_REG,
|
|
};
|
|
|
|
/* BPF has 10 general purpose 64-bit registers and stack frame. */
|
|
#define MAX_BPF_REG __MAX_BPF_REG
|
|
|
|
struct bpf_insn {
|
|
__u8 code; /* opcode */
|
|
__u8 dst_reg:4; /* dest register */
|
|
__u8 src_reg:4; /* source register */
|
|
__s16 off; /* signed offset */
|
|
__s32 imm; /* signed immediate constant */
|
|
};
|
|
|
|
/* BPF syscall commands, see bpf(2) man-page for details. */
|
|
enum bpf_cmd {
|
|
BPF_MAP_CREATE,
|
|
BPF_MAP_LOOKUP_ELEM,
|
|
BPF_MAP_UPDATE_ELEM,
|
|
BPF_MAP_DELETE_ELEM,
|
|
BPF_MAP_GET_NEXT_KEY,
|
|
BPF_PROG_LOAD,
|
|
BPF_OBJ_PIN,
|
|
BPF_OBJ_GET,
|
|
};
|
|
|
|
enum bpf_map_type {
|
|
BPF_MAP_TYPE_UNSPEC,
|
|
BPF_MAP_TYPE_HASH,
|
|
BPF_MAP_TYPE_ARRAY,
|
|
BPF_MAP_TYPE_PROG_ARRAY,
|
|
BPF_MAP_TYPE_PERF_EVENT_ARRAY,
|
|
};
|
|
|
|
enum bpf_prog_type {
|
|
BPF_PROG_TYPE_UNSPEC,
|
|
BPF_PROG_TYPE_SOCKET_FILTER,
|
|
BPF_PROG_TYPE_KPROBE,
|
|
BPF_PROG_TYPE_SCHED_CLS,
|
|
BPF_PROG_TYPE_SCHED_ACT,
|
|
};
|
|
|
|
#define BPF_PSEUDO_MAP_FD 1
|
|
|
|
/* flags for BPF_MAP_UPDATE_ELEM command */
|
|
#define BPF_ANY 0 /* create new element or update existing */
|
|
#define BPF_NOEXIST 1 /* create new element if it didn't exist */
|
|
#define BPF_EXIST 2 /* update existing element */
|
|
|
|
union bpf_attr {
|
|
struct { /* anonymous struct used by BPF_MAP_CREATE command */
|
|
__u32 map_type; /* one of enum bpf_map_type */
|
|
__u32 key_size; /* size of key in bytes */
|
|
__u32 value_size; /* size of value in bytes */
|
|
__u32 max_entries; /* max number of entries in a map */
|
|
};
|
|
|
|
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
|
|
__u32 map_fd;
|
|
__aligned_u64 key;
|
|
union {
|
|
__aligned_u64 value;
|
|
__aligned_u64 next_key;
|
|
};
|
|
__u64 flags;
|
|
};
|
|
|
|
struct { /* anonymous struct used by BPF_PROG_LOAD command */
|
|
__u32 prog_type; /* one of enum bpf_prog_type */
|
|
__u32 insn_cnt;
|
|
__aligned_u64 insns;
|
|
__aligned_u64 license;
|
|
__u32 log_level; /* verbosity level of verifier */
|
|
__u32 log_size; /* size of user buffer */
|
|
__aligned_u64 log_buf; /* user supplied buffer */
|
|
__u32 kern_version; /* checked when prog_type=kprobe */
|
|
};
|
|
|
|
struct { /* anonymous struct used by BPF_OBJ_* commands */
|
|
__aligned_u64 pathname;
|
|
__u32 bpf_fd;
|
|
};
|
|
} __attribute__((aligned(8)));
|
|
|
|
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
|
|
* function eBPF program intends to call
|
|
*/
|
|
enum bpf_func_id {
|
|
BPF_FUNC_unspec,
|
|
BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */
|
|
BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */
|
|
BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */
|
|
BPF_FUNC_probe_read, /* int bpf_probe_read(void *dst, int size, void *src) */
|
|
BPF_FUNC_ktime_get_ns, /* u64 bpf_ktime_get_ns(void) */
|
|
BPF_FUNC_trace_printk, /* int bpf_trace_printk(const char *fmt, int fmt_size, ...) */
|
|
BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */
|
|
BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */
|
|
|
|
/**
|
|
* skb_store_bytes(skb, offset, from, len, flags) - store bytes into packet
|
|
* @skb: pointer to skb
|
|
* @offset: offset within packet from skb->mac_header
|
|
* @from: pointer where to copy bytes from
|
|
* @len: number of bytes to store into packet
|
|
* @flags: bit 0 - if true, recompute skb->csum
|
|
* other bits - reserved
|
|
* Return: 0 on success
|
|
*/
|
|
BPF_FUNC_skb_store_bytes,
|
|
|
|
/**
|
|
* l3_csum_replace(skb, offset, from, to, flags) - recompute IP checksum
|
|
* @skb: pointer to skb
|
|
* @offset: offset within packet where IP checksum is located
|
|
* @from: old value of header field
|
|
* @to: new value of header field
|
|
* @flags: bits 0-3 - size of header field
|
|
* other bits - reserved
|
|
* Return: 0 on success
|
|
*/
|
|
BPF_FUNC_l3_csum_replace,
|
|
|
|
/**
|
|
* l4_csum_replace(skb, offset, from, to, flags) - recompute TCP/UDP checksum
|
|
* @skb: pointer to skb
|
|
* @offset: offset within packet where TCP/UDP checksum is located
|
|
* @from: old value of header field
|
|
* @to: new value of header field
|
|
* @flags: bits 0-3 - size of header field
|
|
* bit 4 - is pseudo header
|
|
* other bits - reserved
|
|
* Return: 0 on success
|
|
*/
|
|
BPF_FUNC_l4_csum_replace,
|
|
|
|
/**
|
|
* bpf_tail_call(ctx, prog_array_map, index) - jump into another BPF program
|
|
* @ctx: context pointer passed to next program
|
|
* @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
|
|
* @index: index inside array that selects specific program to run
|
|
* Return: 0 on success
|
|
*/
|
|
BPF_FUNC_tail_call,
|
|
|
|
/**
|
|
* bpf_clone_redirect(skb, ifindex, flags) - redirect to another netdev
|
|
* @skb: pointer to skb
|
|
* @ifindex: ifindex of the net device
|
|
* @flags: bit 0 - if set, redirect to ingress instead of egress
|
|
* other bits - reserved
|
|
* Return: 0 on success
|
|
*/
|
|
BPF_FUNC_clone_redirect,
|
|
|
|
/**
|
|
* u64 bpf_get_current_pid_tgid(void)
|
|
* Return: current->tgid << 32 | current->pid
|
|
*/
|
|
BPF_FUNC_get_current_pid_tgid,
|
|
|
|
/**
|
|
* u64 bpf_get_current_uid_gid(void)
|
|
* Return: current_gid << 32 | current_uid
|
|
*/
|
|
BPF_FUNC_get_current_uid_gid,
|
|
|
|
/**
|
|
* bpf_get_current_comm(char *buf, int size_of_buf)
|
|
* stores current->comm into buf
|
|
* Return: 0 on success
|
|
*/
|
|
BPF_FUNC_get_current_comm,
|
|
|
|
/**
|
|
* bpf_get_cgroup_classid(skb) - retrieve a proc's classid
|
|
* @skb: pointer to skb
|
|
* Return: classid if != 0
|
|
*/
|
|
BPF_FUNC_get_cgroup_classid,
|
|
BPF_FUNC_skb_vlan_push, /* bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) */
|
|
BPF_FUNC_skb_vlan_pop, /* bpf_skb_vlan_pop(skb) */
|
|
|
|
/**
|
|
* bpf_skb_[gs]et_tunnel_key(skb, key, size, flags)
|
|
* retrieve or populate tunnel metadata
|
|
* @skb: pointer to skb
|
|
* @key: pointer to 'struct bpf_tunnel_key'
|
|
* @size: size of 'struct bpf_tunnel_key'
|
|
* @flags: room for future extensions
|
|
* Retrun: 0 on success
|
|
*/
|
|
BPF_FUNC_skb_get_tunnel_key,
|
|
BPF_FUNC_skb_set_tunnel_key,
|
|
BPF_FUNC_perf_event_read, /* u64 bpf_perf_event_read(&map, index) */
|
|
/**
|
|
* bpf_redirect(ifindex, flags) - redirect to another netdev
|
|
* @ifindex: ifindex of the net device
|
|
* @flags: bit 0 - if set, redirect to ingress instead of egress
|
|
* other bits - reserved
|
|
* Return: TC_ACT_REDIRECT
|
|
*/
|
|
BPF_FUNC_redirect,
|
|
|
|
/**
|
|
* bpf_get_route_realm(skb) - retrieve a dst's tclassid
|
|
* @skb: pointer to skb
|
|
* Return: realm if != 0
|
|
*/
|
|
BPF_FUNC_get_route_realm,
|
|
|
|
/**
|
|
* bpf_perf_event_output(ctx, map, index, data, size) - output perf raw sample
|
|
* @ctx: struct pt_regs*
|
|
* @map: pointer to perf_event_array map
|
|
* @index: index of event in the map
|
|
* @data: data on stack to be output as raw data
|
|
* @size: size of data
|
|
* Return: 0 on success
|
|
*/
|
|
BPF_FUNC_perf_event_output,
|
|
__BPF_FUNC_MAX_ID,
|
|
};
|
|
|
|
/* user accessible mirror of in-kernel sk_buff.
|
|
* new fields can only be added to the end of this structure
|
|
*/
|
|
struct __sk_buff {
|
|
__u32 len;
|
|
__u32 pkt_type;
|
|
__u32 mark;
|
|
__u32 queue_mapping;
|
|
__u32 protocol;
|
|
__u32 vlan_present;
|
|
__u32 vlan_tci;
|
|
__u32 vlan_proto;
|
|
__u32 priority;
|
|
__u32 ingress_ifindex;
|
|
__u32 ifindex;
|
|
__u32 tc_index;
|
|
__u32 cb[5];
|
|
__u32 hash;
|
|
__u32 tc_classid;
|
|
};
|
|
|
|
struct bpf_tunnel_key {
|
|
__u32 tunnel_id;
|
|
__u32 remote_ipv4;
|
|
};
|
|
|
|
#endif /* _UAPI__LINUX_BPF_H__ */
|