linux/kernel/bpf/cgroup.c
Lawrence Brakmo 40304b2a15 bpf: BPF support for sock_ops
Created a new BPF program type, BPF_PROG_TYPE_SOCK_OPS, and a corresponding
struct that allows BPF programs of this type to access some of the
socket's fields (such as IP addresses, ports, etc.). It uses the
existing bpf cgroups infrastructure so the programs can be attached per
cgroup with full inheritance support. The program will be called at
appropriate times to set relevant connections parameters such as buffer
sizes, SYN and SYN-ACK RTOs, etc., based on connection information such
as IP addresses, port numbers, etc.

Alghough there are already 3 mechanisms to set parameters (sysctls,
route metrics and setsockopts), this new mechanism provides some
distinct advantages. Unlike sysctls, it can set parameters per
connection. In contrast to route metrics, it can also use port numbers
and information provided by a user level program. In addition, it could
set parameters probabilistically for evaluation purposes (i.e. do
something different on 10% of the flows and compare results with the
other 90% of the flows). Also, in cases where IPv6 addresses contain
geographic information, the rules to make changes based on the distance
(or RTT) between the hosts are much easier than route metric rules and
can be global. Finally, unlike setsockopt, it oes not require
application changes and it can be updated easily at any time.

Although the bpf cgroup framework already contains a sock related
program type (BPF_PROG_TYPE_CGROUP_SOCK), I created the new type
(BPF_PROG_TYPE_SOCK_OPS) beccause the existing type expects to be called
only once during the connections's lifetime. In contrast, the new
program type will be called multiple times from different places in the
network stack code.  For example, before sending SYN and SYN-ACKs to set
an appropriate timeout, when the connection is established to set
congestion control, etc. As a result it has "op" field to specify the
type of operation requested.

The purpose of this new program type is to simplify setting connection
parameters, such as buffer sizes, TCP's SYN RTO, etc. For example, it is
easy to use facebook's internal IPv6 addresses to determine if both hosts
of a connection are in the same datacenter. Therefore, it is easy to
write a BPF program to choose a small SYN RTO value when both hosts are
in the same datacenter.

This patch only contains the framework to support the new BPF program
type, following patches add the functionality to set various connection
parameters.

This patch defines a new BPF program type: BPF_PROG_TYPE_SOCKET_OPS
and a new bpf syscall command to load a new program of this type:
BPF_PROG_LOAD_SOCKET_OPS.

Two new corresponding structs (one for the kernel one for the user/BPF
program):

/* kernel version */
struct bpf_sock_ops_kern {
        struct sock *sk;
        __u32  op;
        union {
                __u32 reply;
                __u32 replylong[4];
        };
};

/* user version
 * Some fields are in network byte order reflecting the sock struct
 * Use the bpf_ntohl helper macro in samples/bpf/bpf_endian.h to
 * convert them to host byte order.
 */
struct bpf_sock_ops {
        __u32 op;
        union {
                __u32 reply;
                __u32 replylong[4];
        };
        __u32 family;
        __u32 remote_ip4;     /* In network byte order */
        __u32 local_ip4;      /* In network byte order */
        __u32 remote_ip6[4];  /* In network byte order */
        __u32 local_ip6[4];   /* In network byte order */
        __u32 remote_port;    /* In network byte order */
        __u32 local_port;     /* In host byte horder */
};

Currently there are two types of ops. The first type expects the BPF
program to return a value which is then used by the caller (or a
negative value to indicate the operation is not supported). The second
type expects state changes to be done by the BPF program, for example
through a setsockopt BPF helper function, and they ignore the return
value.

The reply fields of the bpf_sockt_ops struct are there in case a bpf
program needs to return a value larger than an integer.

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-01 16:15:13 -07:00

276 lines
7.8 KiB
C

/*
* Functions to manage eBPF programs attached to cgroups
*
* Copyright (c) 2016 Daniel Mack
*
* This file is subject to the terms and conditions of version 2 of the GNU
* General Public License. See the file COPYING in the main directory of the
* Linux distribution for more details.
*/
#include <linux/kernel.h>
#include <linux/atomic.h>
#include <linux/cgroup.h>
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/bpf-cgroup.h>
#include <net/sock.h>
DEFINE_STATIC_KEY_FALSE(cgroup_bpf_enabled_key);
EXPORT_SYMBOL(cgroup_bpf_enabled_key);
/**
* cgroup_bpf_put() - put references of all bpf programs
* @cgrp: the cgroup to modify
*/
void cgroup_bpf_put(struct cgroup *cgrp)
{
unsigned int type;
for (type = 0; type < ARRAY_SIZE(cgrp->bpf.prog); type++) {
struct bpf_prog *prog = cgrp->bpf.prog[type];
if (prog) {
bpf_prog_put(prog);
static_branch_dec(&cgroup_bpf_enabled_key);
}
}
}
/**
* cgroup_bpf_inherit() - inherit effective programs from parent
* @cgrp: the cgroup to modify
* @parent: the parent to inherit from
*/
void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent)
{
unsigned int type;
for (type = 0; type < ARRAY_SIZE(cgrp->bpf.effective); type++) {
struct bpf_prog *e;
e = rcu_dereference_protected(parent->bpf.effective[type],
lockdep_is_held(&cgroup_mutex));
rcu_assign_pointer(cgrp->bpf.effective[type], e);
cgrp->bpf.disallow_override[type] = parent->bpf.disallow_override[type];
}
}
/**
* __cgroup_bpf_update() - Update the pinned program of a cgroup, and
* propagate the change to descendants
* @cgrp: The cgroup which descendants to traverse
* @parent: The parent of @cgrp, or %NULL if @cgrp is the root
* @prog: A new program to pin
* @type: Type of pinning operation (ingress/egress)
*
* Each cgroup has a set of two pointers for bpf programs; one for eBPF
* programs it owns, and which is effective for execution.
*
* If @prog is not %NULL, this function attaches a new program to the cgroup
* and releases the one that is currently attached, if any. @prog is then made
* the effective program of type @type in that cgroup.
*
* If @prog is %NULL, the currently attached program of type @type is released,
* and the effective program of the parent cgroup (if any) is inherited to
* @cgrp.
*
* Then, the descendants of @cgrp are walked and the effective program for
* each of them is set to the effective program of @cgrp unless the
* descendant has its own program attached, in which case the subbranch is
* skipped. This ensures that delegated subcgroups with own programs are left
* untouched.
*
* Must be called with cgroup_mutex held.
*/
int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
struct bpf_prog *prog, enum bpf_attach_type type,
bool new_overridable)
{
struct bpf_prog *old_prog, *effective = NULL;
struct cgroup_subsys_state *pos;
bool overridable = true;
if (parent) {
overridable = !parent->bpf.disallow_override[type];
effective = rcu_dereference_protected(parent->bpf.effective[type],
lockdep_is_held(&cgroup_mutex));
}
if (prog && effective && !overridable)
/* if parent has non-overridable prog attached, disallow
* attaching new programs to descendent cgroup
*/
return -EPERM;
if (prog && effective && overridable != new_overridable)
/* if parent has overridable prog attached, only
* allow overridable programs in descendent cgroup
*/
return -EPERM;
old_prog = cgrp->bpf.prog[type];
if (prog) {
overridable = new_overridable;
effective = prog;
if (old_prog &&
cgrp->bpf.disallow_override[type] == new_overridable)
/* disallow attaching non-overridable on top
* of existing overridable in this cgroup
* and vice versa
*/
return -EPERM;
}
if (!prog && !old_prog)
/* report error when trying to detach and nothing is attached */
return -ENOENT;
cgrp->bpf.prog[type] = prog;
css_for_each_descendant_pre(pos, &cgrp->self) {
struct cgroup *desc = container_of(pos, struct cgroup, self);
/* skip the subtree if the descendant has its own program */
if (desc->bpf.prog[type] && desc != cgrp) {
pos = css_rightmost_descendant(pos);
} else {
rcu_assign_pointer(desc->bpf.effective[type],
effective);
desc->bpf.disallow_override[type] = !overridable;
}
}
if (prog)
static_branch_inc(&cgroup_bpf_enabled_key);
if (old_prog) {
bpf_prog_put(old_prog);
static_branch_dec(&cgroup_bpf_enabled_key);
}
return 0;
}
/**
* __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
* @sk: The socket sending or receiving traffic
* @skb: The skb that is being sent or received
* @type: The type of program to be exectuted
*
* If no socket is passed, or the socket is not of type INET or INET6,
* this function does nothing and returns 0.
*
* The program type passed in via @type must be suitable for network
* filtering. No further check is performed to assert that.
*
* This function will return %-EPERM if any if an attached program was found
* and if it returned != 1 during execution. In all other cases, 0 is returned.
*/
int __cgroup_bpf_run_filter_skb(struct sock *sk,
struct sk_buff *skb,
enum bpf_attach_type type)
{
struct bpf_prog *prog;
struct cgroup *cgrp;
int ret = 0;
if (!sk || !sk_fullsock(sk))
return 0;
if (sk->sk_family != AF_INET &&
sk->sk_family != AF_INET6)
return 0;
cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
rcu_read_lock();
prog = rcu_dereference(cgrp->bpf.effective[type]);
if (prog) {
unsigned int offset = skb->data - skb_network_header(skb);
struct sock *save_sk = skb->sk;
skb->sk = sk;
__skb_push(skb, offset);
ret = bpf_prog_run_save_cb(prog, skb) == 1 ? 0 : -EPERM;
__skb_pull(skb, offset);
skb->sk = save_sk;
}
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb);
/**
* __cgroup_bpf_run_filter_sk() - Run a program on a sock
* @sk: sock structure to manipulate
* @type: The type of program to be exectuted
*
* socket is passed is expected to be of type INET or INET6.
*
* The program type passed in via @type must be suitable for sock
* filtering. No further check is performed to assert that.
*
* This function will return %-EPERM if any if an attached program was found
* and if it returned != 1 during execution. In all other cases, 0 is returned.
*/
int __cgroup_bpf_run_filter_sk(struct sock *sk,
enum bpf_attach_type type)
{
struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
struct bpf_prog *prog;
int ret = 0;
rcu_read_lock();
prog = rcu_dereference(cgrp->bpf.effective[type]);
if (prog)
ret = BPF_PROG_RUN(prog, sk) == 1 ? 0 : -EPERM;
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
/**
* __cgroup_bpf_run_filter_sock_ops() - Run a program on a sock
* @sk: socket to get cgroup from
* @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains
* sk with connection information (IP addresses, etc.) May not contain
* cgroup info if it is a req sock.
* @type: The type of program to be exectuted
*
* socket passed is expected to be of type INET or INET6.
*
* The program type passed in via @type must be suitable for sock_ops
* filtering. No further check is performed to assert that.
*
* This function will return %-EPERM if any if an attached program was found
* and if it returned != 1 during execution. In all other cases, 0 is returned.
*/
int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
struct bpf_sock_ops_kern *sock_ops,
enum bpf_attach_type type)
{
struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
struct bpf_prog *prog;
int ret = 0;
rcu_read_lock();
prog = rcu_dereference(cgrp->bpf.effective[type]);
if (prog)
ret = BPF_PROG_RUN(prog, sock_ops) == 1 ? 0 : -EPERM;
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops);