blob: 1d8b271ef8cc240775ba4313a7cf03bc142b4822 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Linux Socket Filter - Kernel level socket filtering
*
* Based on the design of the Berkeley Packet Filter. The new
* internal format has been designed by PLUMgrid:
*
* Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com
*
* Authors:
*
* Jay Schulist <jschlst@samba.org>
* Alexei Starovoitov <ast@plumgrid.com>
* Daniel Borkmann <dborkman@redhat.com>
*
* Andi Kleen - Fix a few bad bugs and races.
* Kris Katterjohn - Added many additional checks in bpf_check_classic()
*/
#include <linux/atomic.h>
#include <linux/bpf_verifier.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/fcntl.h>
#include <linux/socket.h>
#include <linux/sock_diag.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/if_packet.h>
#include <linux/if_arp.h>
#include <linux/gfp.h>
#include <net/inet_common.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/netlink.h>
#include <linux/skbuff.h>
#include <linux/skmsg.h>
#include <net/sock.h>
#include <net/flow_dissector.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/uaccess.h>
#include <asm/unaligned.h>
#include <linux/filter.h>
#include <linux/ratelimit.h>
#include <linux/seccomp.h>
#include <linux/if_vlan.h>
#include <linux/bpf.h>
#include <linux/btf.h>
#include <net/sch_generic.h>
#include <net/cls_cgroup.h>
#include <net/dst_metadata.h>
#include <net/dst.h>
#include <net/sock_reuseport.h>
#include <net/busy_poll.h>
#include <net/tcp.h>
#include <net/xfrm.h>
#include <net/udp.h>
#include <linux/bpf_trace.h>
#include <net/xdp_sock.h>
#include <linux/inetdevice.h>
#include <net/inet_hashtables.h>
#include <net/inet6_hashtables.h>
#include <net/ip_fib.h>
#include <net/nexthop.h>
#include <net/flow.h>
#include <net/arp.h>
#include <net/ipv6.h>
#include <net/net_namespace.h>
#include <linux/seg6_local.h>
#include <net/seg6.h>
#include <net/seg6_local.h>
#include <net/lwtunnel.h>
#include <net/ipv6_stubs.h>
#include <net/bpf_sk_storage.h>
#include <net/transp_v6.h>
#include <linux/btf_ids.h>
#include <net/tls.h>
#include <net/xdp.h>
#include <net/mptcp.h>
#include <net/netfilter/nf_conntrack_bpf.h>
static const struct bpf_func_proto *
bpf_sk_base_func_proto(enum bpf_func_id func_id);
int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len)
{
if (in_compat_syscall()) {
struct compat_sock_fprog f32;
if (len != sizeof(f32))
return -EINVAL;
if (copy_from_sockptr(&f32, src, sizeof(f32)))
return -EFAULT;
memset(dst, 0, sizeof(*dst));
dst->len = f32.len;
dst->filter = compat_ptr(f32.filter);
} else {
if (len != sizeof(*dst))
return -EINVAL;
if (copy_from_sockptr(dst, src, sizeof(*dst)))
return -EFAULT;
}
return 0;
}
EXPORT_SYMBOL_GPL(copy_bpf_fprog_from_user);
/**
* sk_filter_trim_cap - run a packet through a socket filter
* @sk: sock associated with &sk_buff
* @skb: buffer to filter
* @cap: limit on how short the eBPF program may trim the packet
*
* Run the eBPF program and then cut skb->data to correct size returned by
* the program. If pkt_len is 0 we toss packet. If skb->len is smaller
* than pkt_len we keep whole skb->data. This is the socket level
* wrapper to bpf_prog_run. It returns 0 if the packet should
* be accepted or -EPERM if the packet should be tossed.
*
*/
int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
{
int err;
struct sk_filter *filter;
/*
* If the skb was allocated from pfmemalloc reserves, only
* allow SOCK_MEMALLOC sockets to use it as this socket is
* helping free memory
*/
if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_PFMEMALLOCDROP);
return -ENOMEM;
}
err = BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb);
if (err)
return err;
err = security_sock_rcv_skb(sk, skb);
if (err)
return err;
rcu_read_lock();
filter = rcu_dereference(sk->sk_filter);
if (filter) {
struct sock *save_sk = skb->sk;
unsigned int pkt_len;
skb->sk = sk;
pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
skb->sk = save_sk;
err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM;
}
rcu_read_unlock();
return err;
}
EXPORT_SYMBOL(sk_filter_trim_cap);
BPF_CALL_1(bpf_skb_get_pay_offset, struct sk_buff *, skb)
{
return skb_get_poff(skb);
}
BPF_CALL_3(bpf_skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x)
{
struct nlattr *nla;
if (skb_is_nonlinear(skb))
return 0;
if (skb->len < sizeof(struct nlattr))
return 0;
if (a > skb->len - sizeof(struct nlattr))
return 0;
nla = nla_find((struct nlattr *) &skb->data[a], skb->len - a, x);
if (nla)
return (void *) nla - (void *) skb->data;
return 0;
}
BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x)
{
struct nlattr *nla;
if (skb_is_nonlinear(skb))
return 0;
if (skb->len < sizeof(struct nlattr))
return 0;
if (a > skb->len - sizeof(struct nlattr))
return 0;
nla = (struct nlattr *) &skb->data[a];
if (nla->nla_len > skb->len - a)
return 0;
nla = nla_find_nested(nla, x);
if (nla)
return (void *) nla - (void *) skb->data;
return 0;
}
BPF_CALL_4(bpf_skb_load_helper_8, const struct sk_buff *, skb, const void *,
data, int, headlen, int, offset)
{
u8 tmp, *ptr;
const int len = sizeof(tmp);
if (offset >= 0) {
if (headlen - offset >= len)
return *(u8 *)(data + offset);
if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
return tmp;
} else {
ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
if (likely(ptr))
return *(u8 *)ptr;
}
return -EFAULT;
}
BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb,
int, offset)
{
return ____bpf_skb_load_helper_8(skb, skb->data, skb->len - skb->data_len,
offset);
}
BPF_CALL_4(bpf_skb_load_helper_16, const struct sk_buff *, skb, const void *,
data, int, headlen, int, offset)
{
__be16 tmp, *ptr;
const int len = sizeof(tmp);
if (offset >= 0) {
if (headlen - offset >= len)
return get_unaligned_be16(data + offset);
if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
return be16_to_cpu(tmp);
} else {
ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
if (likely(ptr))
return get_unaligned_be16(ptr);
}
return -EFAULT;
}
BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb,
int, offset)
{
return ____bpf_skb_load_helper_16(skb, skb->data, skb->len - skb->data_len,
offset);
}
BPF_CALL_4(bpf_skb_load_helper_32, const struct sk_buff *, skb, const void *,
data, int, headlen, int, offset)
{
__be32 tmp, *ptr;
const int len = sizeof(tmp);
if (likely(offset >= 0)) {
if (headlen - offset >= len)
return get_unaligned_be32(data + offset);
if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
return be32_to_cpu(tmp);
} else {
ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
if (likely(ptr))
return get_unaligned_be32(ptr);
}
return -EFAULT;
}
BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb,
int, offset)
{
return ____bpf_skb_load_helper_32(skb, skb->data, skb->len - skb->data_len,
offset);
}
static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
struct bpf_insn *insn_buf)
{
struct bpf_insn *insn = insn_buf;
switch (skb_field) {
case SKF_AD_MARK:
BUILD_BUG_ON(sizeof_field(struct sk_buff, mark) != 4);
*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
offsetof(struct sk_buff, mark));
break;
case SKF_AD_PKTTYPE:
*insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_TYPE_OFFSET);
*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, PKT_TYPE_MAX);
#ifdef __BIG_ENDIAN_BITFIELD
*insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 5);
#endif
break;
case SKF_AD_QUEUE:
BUILD_BUG_ON(sizeof_field(struct sk_buff, queue_mapping) != 2);
*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
offsetof(struct sk_buff, queue_mapping));
break;
case SKF_AD_VLAN_TAG:
BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_tci) != 2);
/* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */
*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
offsetof(struct sk_buff, vlan_tci));
break;
case SKF_AD_VLAN_TAG_PRESENT:
*insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_VLAN_PRESENT_OFFSET);
if (PKT_VLAN_PRESENT_BIT)
*insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, PKT_VLAN_PRESENT_BIT);
if (PKT_VLAN_PRESENT_BIT < 7)
*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, 1);
break;
}
return insn - insn_buf;
}
static bool convert_bpf_extensions(struct sock_filter *fp,
struct bpf_insn **insnp)
{
struct bpf_insn *insn = *insnp;
u32 cnt;
switch (fp->k) {
case SKF_AD_OFF + SKF_AD_PROTOCOL:
BUILD_BUG_ON(sizeof_field(struct sk_buff, protocol) != 2);
/* A = *(u16 *) (CTX + offsetof(protocol)) */
*insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
offsetof(struct sk_buff, protocol));
/* A = ntohs(A) [emitting a nop or swap16] */
*insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16);
break;
case SKF_AD_OFF + SKF_AD_PKTTYPE:
cnt = convert_skb_access(SKF_AD_PKTTYPE, BPF_REG_A, BPF_REG_CTX, insn);
insn += cnt - 1;
break;
case SKF_AD_OFF + SKF_AD_IFINDEX:
case SKF_AD_OFF + SKF_AD_HATYPE:
BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4);
BUILD_BUG_ON(sizeof_field(struct net_device, type) != 2);
*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev),
BPF_REG_TMP, BPF_REG_CTX,
offsetof(struct sk_buff, dev));
/* if (tmp != 0) goto pc + 1 */
*insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1);
*insn++ = BPF_EXIT_INSN();
if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX)
*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_TMP,
offsetof(struct net_device, ifindex));
else
*insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_TMP,
offsetof(struct net_device, type));
break;
case SKF_AD_OFF + SKF_AD_MARK:
cnt = convert_skb_access(SKF_AD_MARK, BPF_REG_A, BPF_REG_CTX, insn);
insn += cnt - 1;
break;
case SKF_AD_OFF + SKF_AD_RXHASH:
BUILD_BUG_ON(sizeof_field(struct sk_buff, hash) != 4);
*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX,
offsetof(struct sk_buff, hash));
break;
case SKF_AD_OFF + SKF_AD_QUEUE:
cnt = convert_skb_access(SKF_AD_QUEUE, BPF_REG_A, BPF_REG_CTX, insn);
insn += cnt - 1;
break;
case SKF_AD_OFF + SKF_AD_VLAN_TAG:
cnt = convert_skb_access(SKF_AD_VLAN_TAG,
BPF_REG_A, BPF_REG_CTX, insn);
insn += cnt - 1;
break;
case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT:
cnt = convert_skb_access(SKF_AD_VLAN_TAG_PRESENT,
BPF_REG_A, BPF_REG_CTX, insn);
insn += cnt - 1;
break;
case SKF_AD_OFF + SKF_AD_VLAN_TPID:
BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_proto) != 2);
/* A = *(u16 *) (CTX + offsetof(vlan_proto)) */
*insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
offsetof(struct sk_buff, vlan_proto));
/* A = ntohs(A) [emitting a nop or swap16] */
*insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16);
break;
case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
case SKF_AD_OFF + SKF_AD_NLATTR:
case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
case SKF_AD_OFF + SKF_AD_CPU:
case SKF_AD_OFF + SKF_AD_RANDOM:
/* arg1 = CTX */
*insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX);
/* arg2 = A */
*insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_A);
/* arg3 = X */
*insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_X);
/* Emit call(arg1=CTX, arg2=A, arg3=X) */
switch (fp->k) {
case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
*insn = BPF_EMIT_CALL(bpf_skb_get_pay_offset);
break;
case SKF_AD_OFF + SKF_AD_NLATTR:
*insn = BPF_EMIT_CALL(bpf_skb_get_nlattr);
break;
case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
*insn = BPF_EMIT_CALL(bpf_skb_get_nlattr_nest);
break;
case SKF_AD_OFF + SKF_AD_CPU:
*insn = BPF_EMIT_CALL(bpf_get_raw_cpu_id);
break;
case SKF_AD_OFF + SKF_AD_RANDOM:
*insn = BPF_EMIT_CALL(bpf_user_rnd_u32);
bpf_user_rnd_init_once();
break;
}
break;
case SKF_AD_OFF + SKF_AD_ALU_XOR_X:
/* A ^= X */
*insn = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_X);
break;
default:
/* This is just a dummy call to avoid letting the compiler
* evict __bpf_call_base() as an optimization. Placed here
* where no-one bothers.
*/
BUG_ON(__bpf_call_base(0, 0, 0, 0, 0) != 0);
return false;
}
*insnp = insn;
return true;
}
static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp)
{
const bool unaligned_ok = IS_BUILTIN(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS);
int size = bpf_size_to_bytes(BPF_SIZE(fp->code));
bool endian = BPF_SIZE(fp->code) == BPF_H ||
BPF_SIZE(fp->code) == BPF_W;
bool indirect = BPF_MODE(fp->code) == BPF_IND;
const int ip_align = NET_IP_ALIGN;
struct bpf_insn *insn = *insnp;
int offset = fp->k;
if (!indirect &&
((unaligned_ok && offset >= 0) ||
(!unaligned_ok && offset >= 0 &&
offset + ip_align >= 0 &&
offset + ip_align % size == 0))) {
bool ldx_off_ok = offset <= S16_MAX;
*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H);
if (offset)
*insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
*insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP,
size, 2 + endian + (!ldx_off_ok * 2));
if (ldx_off_ok) {
*insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A,
BPF_REG_D, offset);
} else {
*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_D);
*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_TMP, offset);
*insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A,
BPF_REG_TMP, 0);
}
if (endian)
*insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8);
*insn++ = BPF_JMP_A(8);
}
*insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX);
*insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_D);
*insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_H);
if (!indirect) {
*insn++ = BPF_MOV64_IMM(BPF_REG_ARG4, offset);
} else {
*insn++ = BPF_MOV64_REG(BPF_REG_ARG4, BPF_REG_X);
if (fp->k)
*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG4, offset);
}
switch (BPF_SIZE(fp->code)) {
case BPF_B:
*insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8);
break;
case BPF_H:
*insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16);
break;
case BPF_W:
*insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32);
break;
default:
return false;
}
*insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_A, 0, 2);
*insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A);
*insn = BPF_EXIT_INSN();
*insnp = insn;
return true;
}
/**
* bpf_convert_filter - convert filter program
* @prog: the user passed filter program
* @len: the length of the user passed filter program
* @new_prog: allocated 'struct bpf_prog' or NULL
* @new_len: pointer to store length of converted program
* @seen_ld_abs: bool whether we've seen ld_abs/ind
*
* Remap 'sock_filter' style classic BPF (cBPF) instruction set to 'bpf_insn'
* style extended BPF (eBPF).
* Conversion workflow:
*
* 1) First pass for calculating the new program length:
* bpf_convert_filter(old_prog, old_len, NULL, &new_len, &seen_ld_abs)
*
* 2) 2nd pass to remap in two passes: 1st pass finds new
* jump offsets, 2nd pass remapping:
* bpf_convert_filter(old_prog, old_len, new_prog, &new_len, &seen_ld_abs)
*/
static int bpf_convert_filter(struct sock_filter *prog, int len,
struct bpf_prog *new_prog, int *new_len,
bool *seen_ld_abs)
{
int new_flen = 0, pass = 0, target, i, stack_off;
struct bpf_insn *new_insn, *first_insn = NULL;
struct sock_filter *fp;
int *addrs = NULL;
u8 bpf_src;
BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK);
BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG);
if (len <= 0 || len > BPF_MAXINSNS)
return -EINVAL;
if (new_prog) {
first_insn = new_prog->insnsi;
addrs = kcalloc(len, sizeof(*addrs),
GFP_KERNEL | __GFP_NOWARN);
if (!addrs)
return -ENOMEM;
}
do_pass:
new_insn = first_insn;
fp = prog;
/* Classic BPF related prologue emission. */
if (new_prog) {
/* Classic BPF expects A and X to be reset first. These need
* to be guaranteed to be the first two instructions.
*/
*new_insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A);
*new_insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_X, BPF_REG_X);
/* All programs must keep CTX in callee saved BPF_REG_CTX.
* In eBPF case it's done by the compiler, here we need to
* do this ourself. Initial CTX is present in BPF_REG_ARG1.
*/
*new_insn++ = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1);
if (*seen_ld_abs) {
/* For packet access in classic BPF, cache skb->data
* in callee-saved BPF R8 and skb->len - skb->data_len
* (headlen) in BPF R9. Since classic BPF is read-only
* on CTX, we only need to cache it once.
*/
*new_insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data),
BPF_REG_D, BPF_REG_CTX,
offsetof(struct sk_buff, data));
*new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_H, BPF_REG_CTX,
offsetof(struct sk_buff, len));
*new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_TMP, BPF_REG_CTX,
offsetof(struct sk_buff, data_len));
*new_insn++ = BPF_ALU32_REG(BPF_SUB, BPF_REG_H, BPF_REG_TMP);
}
} else {
new_insn += 3;
}
for (i = 0; i < len; fp++, i++) {
struct bpf_insn tmp_insns[32] = { };
struct bpf_insn *insn = tmp_insns;
if (addrs)
addrs[i] = new_insn - first_insn;
switch (fp->code) {
/* All arithmetic insns and skb loads map as-is. */
case BPF_ALU | BPF_ADD | BPF_X:
case BPF_ALU | BPF_ADD | BPF_K:
case BPF_ALU | BPF_SUB | BPF_X:
case BPF_ALU | BPF_SUB | BPF_K:
case BPF_ALU | BPF_AND | BPF_X:
case BPF_ALU | BPF_AND | BPF_K:
case BPF_ALU | BPF_OR | BPF_X:
case BPF_ALU | BPF_OR | BPF_K:
case BPF_ALU | BPF_LSH | BPF_X:
case BPF_ALU | BPF_LSH | BPF_K:
case BPF_ALU | BPF_RSH | BPF_X:
case BPF_ALU | BPF_RSH | BPF_K:
case BPF_ALU | BPF_XOR | BPF_X:
case BPF_ALU | BPF_XOR | BPF_K:
case BPF_ALU | BPF_MUL | BPF_X:
case BPF_ALU | BPF_MUL | BPF_K:
case BPF_ALU | BPF_DIV | BPF_X:
case BPF_ALU | BPF_DIV | BPF_K:
case BPF_ALU | BPF_MOD | BPF_X:
case BPF_ALU | BPF_MOD | BPF_K:
case BPF_ALU | BPF_NEG:
case BPF_LD | BPF_ABS | BPF_W:
case BPF_LD | BPF_ABS | BPF_H:
case BPF_LD | BPF_ABS | BPF_B:
case BPF_LD | BPF_IND | BPF_W:
case BPF_LD | BPF_IND | BPF_H:
case BPF_LD | BPF_IND | BPF_B:
/* Check for overloaded BPF extension and
* directly convert it if found, otherwise
* just move on with mapping.
*/
if (BPF_CLASS(fp->code) == BPF_LD &&
BPF_MODE(fp->code) == BPF_ABS &&
convert_bpf_extensions(fp, &insn))
break;
if (BPF_CLASS(fp->code) == BPF_LD &&
convert_bpf_ld_abs(fp, &insn)) {
*seen_ld_abs = true;
break;
}
if (fp->code == (BPF_ALU | BPF_DIV | BPF_X) ||
fp->code == (BPF_ALU | BPF_MOD | BPF_X)) {
*insn++ = BPF_MOV32_REG(BPF_REG_X, BPF_REG_X);
/* Error with exception code on div/mod by 0.
* For cBPF programs, this was always return 0.
*/
*insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_X, 0, 2);
*insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A);
*insn++ = BPF_EXIT_INSN();
}
*insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k);
break;
/* Jump transformation cannot use BPF block macros
* everywhere as offset calculation and target updates
* require a bit more work than the rest, i.e. jump
* opcodes map as-is, but offsets need adjustment.
*/
#define BPF_EMIT_JMP \
do { \
const s32 off_min = S16_MIN, off_max = S16_MAX; \
s32 off; \
\
if (target >= len || target < 0) \
goto err; \
off = addrs ? addrs[target] - addrs[i] - 1 : 0; \
/* Adjust pc relative offset for 2nd or 3rd insn. */ \
off -= insn - tmp_insns; \
/* Reject anything not fitting into insn->off. */ \
if (off < off_min || off > off_max) \
goto err; \
insn->off = off; \
} while (0)
case BPF_JMP | BPF_JA:
target = i + fp->k + 1;
insn->code = fp->code;
BPF_EMIT_JMP;
break;
case BPF_JMP | BPF_JEQ | BPF_K:
case BPF_JMP | BPF_JEQ | BPF_X:
case BPF_JMP | BPF_JSET | BPF_K:
case BPF_JMP | BPF_JSET | BPF_X:
case BPF_JMP | BPF_JGT | BPF_K:
case BPF_JMP | BPF_JGT | BPF_X:
case BPF_JMP | BPF_JGE | BPF_K:
case BPF_JMP | BPF_JGE | BPF_X:
if (BPF_SRC(fp->code) == BPF_K && (int) fp->k < 0) {
/* BPF immediates are signed, zero extend
* immediate into tmp register and use it
* in compare insn.
*/
*insn++ = BPF_MOV32_IMM(BPF_REG_TMP, fp->k);
insn->dst_reg = BPF_REG_A;
insn->src_reg = BPF_REG_TMP;
bpf_src = BPF_X;
} else {
insn->dst_reg = BPF_REG_A;
insn->imm = fp->k;
bpf_src = BPF_SRC(fp->code);
insn->src_reg = bpf_src == BPF_X ? BPF_REG_X : 0;
}
/* Common case where 'jump_false' is next insn. */
if (fp->jf == 0) {
insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
target = i + fp->jt + 1;
BPF_EMIT_JMP;
break;
}
/* Convert some jumps when 'jump_true' is next insn. */
if (fp->jt == 0) {
switch (BPF_OP(fp->code)) {
case BPF_JEQ:
insn->code = BPF_JMP | BPF_JNE | bpf_src;
break;
case BPF_JGT:
insn->code = BPF_JMP | BPF_JLE | bpf_src;
break;
case BPF_JGE:
insn->code = BPF_JMP | BPF_JLT | bpf_src;
break;
default:
goto jmp_rest;
}
target = i + fp->jf + 1;
BPF_EMIT_JMP;
break;
}
jmp_rest:
/* Other jumps are mapped into two insns: Jxx and JA. */
target = i + fp->jt + 1;
insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
BPF_EMIT_JMP;
insn++;
insn->code = BPF_JMP | BPF_JA;
target = i + fp->jf + 1;
BPF_EMIT_JMP;
break;
/* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */
case BPF_LDX | BPF_MSH | BPF_B: {
struct sock_filter tmp = {
.code = BPF_LD | BPF_ABS | BPF_B,
.k = fp->k,
};
*seen_ld_abs = true;
/* X = A */
*insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
/* A = BPF_R0 = *(u8 *) (skb->data + K) */
convert_bpf_ld_abs(&tmp, &insn);
insn++;
/* A &= 0xf */
*insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf);
/* A <<= 2 */
*insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2);
/* tmp = X */
*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_X);
/* X = A */
*insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
/* A = tmp */
*insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP);
break;
}
/* RET_K is remaped into 2 insns. RET_A case doesn't need an
* extra mov as BPF_REG_0 is already mapped into BPF_REG_A.
*/
case BPF_RET | BPF_A:
case BPF_RET | BPF_K:
if (BPF_RVAL(fp->code) == BPF_K)
*insn++ = BPF_MOV32_RAW(BPF_K, BPF_REG_0,
0, fp->k);
*insn = BPF_EXIT_INSN();
break;
/* Store to stack. */
case BPF_ST:
case BPF_STX:
stack_off = fp->k * 4 + 4;
*insn = BPF_STX_MEM(BPF_W, BPF_REG_FP, BPF_CLASS(fp->code) ==
BPF_ST ? BPF_REG_A : BPF_REG_X,
-stack_off);
/* check_load_and_stores() verifies that classic BPF can
* load from stack only after write, so tracking
* stack_depth for ST|STX insns is enough
*/
if (new_prog && new_prog->aux->stack_depth < stack_off)
new_prog->aux->stack_depth = stack_off;
break;
/* Load from stack. */
case BPF_LD | BPF_MEM:
case BPF_LDX | BPF_MEM:
stack_off = fp->k * 4 + 4;
*insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ?
BPF_REG_A : BPF_REG_X, BPF_REG_FP,
-stack_off);
break;
/* A = K or X = K */
case BPF_LD | BPF_IMM:
case BPF_LDX | BPF_IMM:
*insn = BPF_MOV32_IMM(BPF_CLASS(fp->code) == BPF_LD ?
BPF_REG_A : BPF_REG_X, fp->k);
break;
/* X = A */
case BPF_MISC | BPF_TAX:
*insn = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
break;
/* A = X */
case BPF_MISC | BPF_TXA:
*insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_X);
break;
/* A = skb->len or X = skb->len */
case BPF_LD | BPF_W | BPF_LEN:
case BPF_LDX | BPF_W | BPF_LEN:
*insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ?
BPF_REG_A : BPF_REG_X, BPF_REG_CTX,
offsetof(struct sk_buff, len));
break;
/* Access seccomp_data fields. */
case BPF_LDX | BPF_ABS | BPF_W:
/* A = *(u32 *) (ctx + K) */
*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k);
break;
/* Unknown instruction. */
default:
goto err;
}
insn++;
if (new_prog)
memcpy(new_insn, tmp_insns,
sizeof(*insn) * (insn - tmp_insns));
new_insn += insn - tmp_insns;
}
if (!new_prog) {
/* Only calculating new length. */
*new_len = new_insn - first_insn;
if (*seen_ld_abs)
*new_len += 4; /* Prologue bits. */
return 0;
}
pass++;
if (new_flen != new_insn - first_insn) {
new_flen = new_insn - first_insn;
if (pass > 2)
goto err;
goto do_pass;
}
kfree(addrs);
BUG_ON(*new_len != new_flen);
return 0;
err:
kfree(addrs);
return -EINVAL;
}
/* Security:
*
* As we dont want to clear mem[] array for each packet going through
* __bpf_prog_run(), we check that filter loaded by user never try to read
* a cell if not previously written, and we check all branches to be sure
* a malicious user doesn't try to abuse us.
*/
static int check_load_and_stores(const struct sock_filter *filter, int flen)
{
u16 *masks, memvalid = 0; /* One bit per cell, 16 cells */
int pc, ret = 0;
BUILD_BUG_ON(BPF_MEMWORDS > 16);
masks = kmalloc_array(flen, sizeof(*masks), GFP_KERNEL);
if (!masks)
return -ENOMEM;
memset(masks, 0xff, flen * sizeof(*masks));
for (pc = 0; pc < flen; pc++) {
memvalid &= masks[pc];
switch (filter[pc].code) {
case BPF_ST:
case BPF_STX:
memvalid |= (1 << filter[pc].k);
break;
case BPF_LD | BPF_MEM:
case BPF_LDX | BPF_MEM:
if (!(memvalid & (1 << filter[pc].k))) {
ret = -EINVAL;
goto error;
}
break;
case BPF_JMP | BPF_JA:
/* A jump must set masks on target */
masks[pc + 1 + filter[pc].k] &= memvalid;
memvalid = ~0;
break;
case BPF_JMP | BPF_JEQ | BPF_K:
case BPF_JMP | BPF_JEQ | BPF_X:
case BPF_JMP | BPF_JGE | BPF_K:
case BPF_JMP | BPF_JGE | BPF_X:
case BPF_JMP | BPF_JGT | BPF_K:
case BPF_JMP | BPF_JGT | BPF_X:
case BPF_JMP | BPF_JSET | BPF_K:
case BPF_JMP | BPF_JSET | BPF_X:
/* A jump must set masks on targets */
masks[pc + 1 + filter[pc].jt] &= memvalid;
masks[pc + 1 + filter[pc].jf] &= memvalid;
memvalid = ~0;
break;
}
}
error:
kfree(masks);
return ret;
}
static bool chk_code_allowed(u16 code_to_probe)
{
static const bool codes[] = {
/* 32 bit ALU operations */
[BPF_ALU | BPF_ADD | BPF_K] = true,
[BPF_ALU | BPF_ADD | BPF_X] = true,
[BPF_ALU | BPF_SUB | BPF_K] = true,
[BPF_ALU | BPF_SUB | BPF_X] = true,
[BPF_ALU | BPF_MUL | BPF_K] = true,
[BPF_ALU | BPF_MUL | BPF_X] = true,
[BPF_ALU | BPF_DIV | BPF_K] = true,
[BPF_ALU | BPF_DIV | BPF_X] = true,
[BPF_ALU | BPF_MOD | BPF_K] = true,
[BPF_ALU | BPF_MOD | BPF_X] = true,
[BPF_ALU | BPF_AND | BPF_K] = true,
[BPF_ALU | BPF_AND | BPF_X] = true,
[BPF_ALU | BPF_OR | BPF_K] = true,
[BPF_ALU | BPF_OR | BPF_X] = true,
[BPF_ALU | BPF_XOR | BPF_K] = true,
[BPF_ALU | BPF_XOR | BPF_X] = true,
[BPF_ALU | BPF_LSH | BPF_K] = true,
[BPF_ALU | BPF_LSH | BPF_X] = true,
[BPF_ALU | BPF_RSH | BPF_K] = true,
[BPF_ALU | BPF_RSH | BPF_X] = true,
[BPF_ALU | BPF_NEG] = true,
/* Load instructions */
[BPF_LD | BPF_W | BPF_ABS] = true,
[BPF_LD | BPF_H | BPF_ABS] = true,
[BPF_LD | BPF_B | BPF_ABS] = true,
[BPF_LD | BPF_W | BPF_LEN] = true,
[BPF_LD | BPF_W | BPF_IND] = true,
[BPF_LD | BPF_H | BPF_IND] = true,
[BPF_LD | BPF_B | BPF_IND] = true,
[BPF_LD | BPF_IMM] = true,
[BPF_LD | BPF_MEM] = true,
[BPF_LDX | BPF_W | BPF_LEN] = true,
[BPF_LDX | BPF_B | BPF_MSH] = true,
[BPF_LDX | BPF_IMM] = true,
[BPF_LDX | BPF_MEM] = true,
/* Store instructions */
[BPF_ST] = true,
[BPF_STX] = true,
/* Misc instructions */
[BPF_MISC | BPF_TAX] = true,
[BPF_MISC | BPF_TXA] = true,
/* Return instructions */
[BPF_RET | BPF_K] = true,
[BPF_RET | BPF_A] = true,
/* Jump instructions */
[BPF_JMP | BPF_JA] = true,
[BPF_JMP | BPF_JEQ | BPF_K] = true,
[BPF_JMP | BPF_JEQ | BPF_X] = true,
[BPF_JMP | BPF_JGE | BPF_K] = true,
[BPF_JMP | BPF_JGE | BPF_X] = true,
[BPF_JMP | BPF_JGT | BPF_K] = true,
[BPF_JMP | BPF_JGT | BPF_X] = true,
[BPF_JMP | BPF_JSET | BPF_K] = true,
[BPF_JMP | BPF_JSET | BPF_X] = true,
};
if (code_to_probe >= ARRAY_SIZE(codes))
return false;
return codes[code_to_probe];
}
static bool bpf_check_basics_ok(const struct sock_filter *filter,
unsigned int flen)
{
if (filter == NULL)
return false;
if (flen == 0 || flen > BPF_MAXINSNS)
return false;
return true;
}
/**
* bpf_check_classic - verify socket filter code
* @filter: filter to verify
* @flen: length of filter
*
* Check the user's filter code. If we let some ugly
* filter code slip through kaboom! The filter must contain
* no references or jumps that are out of range, no illegal
* instructions, and must end with a RET instruction.
*
* All jumps are forward as they are not signed.
*
* Returns 0 if the rule set is legal or -EINVAL if not.
*/
static int bpf_check_classic(const struct sock_filter *filter,
unsigned int flen)
{
bool anc_found;
int pc;
/* Check the filter code now */
for (pc = 0; pc < flen; pc++) {
const struct sock_filter *ftest = &filter[pc];
/* May we actually operate on this code? */
if (!chk_code_allowed(ftest->code))
return -EINVAL;
/* Some instructions need special checks */
switch (ftest->code) {
case BPF_ALU | BPF_DIV | BPF_K:
case BPF_ALU | BPF_MOD | BPF_K:
/* Check for division by zero */
if (ftest->k == 0)
return -EINVAL;
break;
case BPF_ALU | BPF_LSH | BPF_K:
case BPF_ALU | BPF_RSH | BPF_K:
if (ftest->k >= 32)
return -EINVAL;
break;
case BPF_LD | BPF_MEM:
case BPF_LDX | BPF_MEM:
case BPF_ST:
case BPF_STX:
/* Check for invalid memory addresses */
if (ftest->k >= BPF_MEMWORDS)
return -EINVAL;
break;
case BPF_JMP | BPF_JA:
/* Note, the large ftest->k might cause loops.
* Compare this with conditional jumps below,
* where offsets are limited. --ANK (981016)
*/
if (ftest->k >= (unsigned int)(flen - pc - 1))
return -EINVAL;
break;
case BPF_JMP | BPF_JEQ | BPF_K:
case BPF_JMP | BPF_JEQ | BPF_X:
case BPF_JMP | BPF_JGE | BPF_K:
case BPF_JMP | BPF_JGE | BPF_X:
case BPF_JMP | BPF_JGT | BPF_K:
case BPF_JMP | BPF_JGT | BPF_X:
case BPF_JMP | BPF_JSET | BPF_K:
case BPF_JMP | BPF_JSET | BPF_X:
/* Both conditionals must be safe */
if (pc + ftest->jt + 1 >= flen ||
pc + ftest->jf + 1 >= flen)
return -EINVAL;
break;
case BPF_LD | BPF_W | BPF_ABS:
case BPF_LD | BPF_H | BPF_ABS:
case BPF_LD | BPF_B | BPF_ABS:
anc_found = false;
if (bpf_anc_helper(ftest) & BPF_ANC)
anc_found = true;
/* Ancillary operation unknown or unsupported */
if (anc_found == false && ftest->k >= SKF_AD_OFF)
return -EINVAL;
}
}
/* Last instruction must be a RET code */
switch (filter[flen - 1].code) {
case BPF_RET | BPF_K:
case BPF_RET | BPF_A:
return check_load_and_stores(filter, flen);
}
return -EINVAL;
}
static int bpf_prog_store_orig_filter(struct bpf_prog *fp,
const struct sock_fprog *fprog)
{
unsigned int fsize = bpf_classic_proglen(fprog);
struct sock_fprog_kern *fkprog;
fp->orig_prog = kmalloc(sizeof(*fkprog), GFP_KERNEL);
if (!fp->orig_prog)
return -ENOMEM;
fkprog = fp->orig_prog;
fkprog->len = fprog->len;
fkprog->filter = kmemdup(fp->insns, fsize,
GFP_KERNEL | __GFP_NOWARN);
if (!fkprog->filter) {
kfree(fp->orig_prog);
return -ENOMEM;
}
return 0;
}
static void bpf_release_orig_filter(struct bpf_prog *fp)
{
struct sock_fprog_kern *fprog = fp->orig_prog;
if (fprog) {
kfree(fprog->filter);
kfree(fprog);
}
}
static void __bpf_prog_release(struct bpf_prog *prog)
{
if (prog->type == BPF_PROG_TYPE_SOCKET_FILTER) {
bpf_prog_put(prog);
} else {
bpf_release_orig_filter(prog);
bpf_prog_free(prog);
}
}
static void __sk_filter_release(struct sk_filter *fp)
{
__bpf_prog_release(fp->prog);
kfree(fp);
}
/**
* sk_filter_release_rcu - Release a socket filter by rcu_head
* @rcu: rcu_head that contains the sk_filter to free
*/
static void sk_filter_release_rcu(struct rcu_head *rcu)
{
struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
__sk_filter_release(fp);
}
/**
* sk_filter_release - release a socket filter
* @fp: filter to remove
*
* Remove a filter from a socket and release its resources.
*/
static void sk_filter_release(struct sk_filter *fp)
{
if (refcount_dec_and_test(&fp->refcnt))
call_rcu(&fp->rcu, sk_filter_release_rcu);
}
void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
{
u32 filter_size = bpf_prog_size(fp->prog->len);
atomic_sub(filter_size, &sk->sk_omem_alloc);
sk_filter_release(fp);
}
/* try to charge the socket memory if there is space available
* return true on success
*/
static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
{
u32 filter_size = bpf_prog_size(fp->prog->len);
int optmem_max = READ_ONCE(sysctl_optmem_max);
/* same check as in sock_kmalloc() */
if (filter_size <= optmem_max &&
atomic_read(&sk->sk_omem_alloc) + filter_size < optmem_max) {
atomic_add(filter_size, &sk->sk_omem_alloc);
return true;
}
return false;
}
bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
{
if (!refcount_inc_not_zero(&fp->refcnt))
return false;
if (!__sk_filter_charge(sk, fp)) {
sk_filter_release(fp);
return false;
}
return true;
}
static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
{
struct sock_filter *old_prog;
struct bpf_prog *old_fp;
int err, new_len, old_len = fp->len;
bool seen_ld_abs = false;
/* We are free to overwrite insns et al right here as it won't be used at
* this point in time anymore internally after the migration to the eBPF
* instruction representation.
*/
BUILD_BUG_ON(sizeof(struct sock_filter) !=
sizeof(struct bpf_insn));
/* Conversion cannot happen on overlapping memory areas,
* so we need to keep the user BPF around until the 2nd
* pass. At this time, the user BPF is stored in fp->insns.
*/
old_prog = kmemdup(fp->insns, old_len * sizeof(struct sock_filter),
GFP_KERNEL | __GFP_NOWARN);
if (!old_prog) {
err = -ENOMEM;
goto out_err;
}
/* 1st pass: calculate the new program length. */
err = bpf_convert_filter(old_prog, old_len, NULL, &new_len,
&seen_ld_abs);
if (err)
goto out_err_free;
/* Expand fp for appending the new filter representation. */
old_fp = fp;
fp = bpf_prog_realloc(old_fp, bpf_prog_size(new_len), 0);
if (!fp) {
/* The old_fp is still around in case we couldn't
* allocate new memory, so uncharge on that one.
*/
fp = old_fp;
err = -ENOMEM;
goto out_err_free;
}
fp->len = new_len;
/* 2nd pass: remap sock_filter insns into bpf_insn insns. */
err = bpf_convert_filter(old_prog, old_len, fp, &new_len,
&seen_ld_abs);
if (err)
/* 2nd bpf_convert_filter() can fail only if it fails
* to allocate memory, remapping must succeed. Note,
* that at this time old_fp has already been released
* by krealloc().
*/
goto out_err_free;
fp = bpf_prog_select_runtime(fp, &err);
if (err)
goto out_err_free;
kfree(old_prog);
return fp;
out_err_free:
kfree(old_prog);
out_err:
__bpf_prog_release(fp);
return ERR_PTR(err);
}
static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp,
bpf_aux_classic_check_t trans)
{
int err;
fp->bpf_func = NULL;
fp->jited = 0;
err = bpf_check_classic(fp->insns, fp->len);
if (err) {
__bpf_prog_release(fp);
return ERR_PTR(err);
}
/* There might be additional checks and transformations
* needed on classic filters, f.e. in case of seccomp.
*/
if (trans) {
err = trans(fp->insns, fp->len);
if (err) {
__bpf_prog_release(fp);
return ERR_PTR(err);
}
}
/* Probe if we can JIT compile the filter and if so, do
* the compilation of the filter.
*/
bpf_jit_compile(fp);
/* JIT compiler couldn't process this filter, so do the eBPF translation
* for the optimized interpreter.
*/
if (!fp->jited)
fp = bpf_migrate_filter(fp);
return fp;
}
/**
* bpf_prog_create - create an unattached filter
* @pfp: the unattached filter that is created
* @fprog: the filter program
*
* Create a filter independent of any socket. We first run some
* sanity checks on it to make sure it does not explode on us later.
* If an error occurs or there is insufficient memory for the filter
* a negative errno code is returned. On success the return is zero.
*/
int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog)
{
unsigned int fsize = bpf_classic_proglen(fprog);
struct bpf_prog *fp;
/* Make sure new filter is there and in the right amounts. */
if (!bpf_check_basics_ok(fprog->filter, fprog->len))
return -EINVAL;
fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
if (!fp)
return -ENOMEM;
memcpy(fp->insns, fprog->filter, fsize);
fp->len = fprog->len;
/* Since unattached filters are not copied back to user
* space through sk_get_filter(), we do not need to hold
* a copy here, and can spare us the work.
*/
fp->orig_prog = NULL;
/* bpf_prepare_filter() already takes care of freeing
* memory in case something goes wrong.
*/
fp = bpf_prepare_filter(fp, NULL);
if (IS_ERR(fp))
return PTR_ERR(fp);
*pfp = fp;
return 0;
}
EXPORT_SYMBOL_GPL(bpf_prog_create);
/**
* bpf_prog_create_from_user - create an unattached filter from user buffer
* @pfp: the unattached filter that is created
* @fprog: the filter program
* @trans: post-classic verifier transformation handler
* @save_orig: save classic BPF program
*
* This function effectively does the same as bpf_prog_create(), only
* that it builds up its insns buffer from user space provided buffer.
* It also allows for passing a bpf_aux_classic_check_t handler.
*/
int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
bpf_aux_classic_check_t trans, bool save_orig)
{
unsigned int fsize = bpf_classic_proglen(fprog);
struct bpf_prog *fp;
int err;
/* Make sure new filter is there and in the right amounts. */
if (!bpf_check_basics_ok(fprog->filter, fprog->len))
return -EINVAL;
fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
if (!fp)
return -ENOMEM;
if (copy_from_user(fp->insns, fprog->filter, fsize)) {
__bpf_prog_free(fp);
return -EFAULT;
}
fp->len = fprog->len;
fp->orig_prog = NULL;
if (save_orig) {
err = bpf_prog_store_orig_filter(fp, fprog);
if (err) {
__bpf_prog_free(fp);
return -ENOMEM;
}
}
/* bpf_prepare_filter() already takes care of freeing
* memory in case something goes wrong.
*/
fp = bpf_prepare_filter(fp, trans);
if (IS_ERR(fp))
return PTR_ERR(fp);
*pfp = fp;
return 0;
}
EXPORT_SYMBOL_GPL(bpf_prog_create_from_user);
void bpf_prog_destroy(struct bpf_prog *fp)
{
__bpf_prog_release(fp);
}
EXPORT_SYMBOL_GPL(bpf_prog_destroy);
static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
{
struct sk_filter *fp, *old_fp;
fp = kmalloc(sizeof(*fp), GFP_KERNEL);
if (!fp)
return -ENOMEM;
fp->prog = prog;
if (!__sk_filter_charge(sk, fp)) {
kfree(fp);
return -ENOMEM;
}
refcount_set(&fp->refcnt, 1);
old_fp = rcu_dereference_protected(sk->sk_filter,
lockdep_sock_is_held(sk));
rcu_assign_pointer(sk->sk_filter, fp);
if (old_fp)
sk_filter_uncharge(sk, old_fp);
return 0;
}
static
struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk)
{
unsigned int fsize = bpf_classic_proglen(fprog);
struct bpf_prog *prog;
int err;
if (sock_flag(sk, SOCK_FILTER_LOCKED))
return ERR_PTR(-EPERM);
/* Make sure new filter is there and in the right amounts. */
if (!bpf_check_basics_ok(fprog->filter, fprog->len))
return ERR_PTR(-EINVAL);
prog = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
if (!prog)
return ERR_PTR(-ENOMEM);
if (copy_from_user(prog->insns, fprog->filter, fsize)) {
__bpf_prog_free(prog);
return ERR_PTR(-EFAULT);
}
prog->len = fprog->len;
err = bpf_prog_store_orig_filter(prog, fprog);
if (err) {
__bpf_prog_free(prog);
return ERR_PTR(-ENOMEM);
}
/* bpf_prepare_filter() already takes care of freeing
* memory in case something goes wrong.
*/
return bpf_prepare_filter(prog, NULL);
}
/**
* sk_attach_filter - attach a socket filter
* @fprog: the filter program
* @sk: the socket to use
*
* Attach the user's filter code. We first run some sanity checks on
* it to make sure it does not explode on us later. If an error
* occurs or there is insufficient memory for the filter a negative
* errno code is returned. On success the return is zero.
*/
int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
{
struct bpf_prog *prog = __get_filter(fprog, sk);
int err;
if (IS_ERR(prog))
return PTR_ERR(prog);
err = __sk_attach_prog(prog, sk);
if (err < 0) {
__bpf_prog_release(prog);
return err;
}
return 0;
}
EXPORT_SYMBOL_GPL(sk_attach_filter);
int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk)
{
struct bpf_prog *prog = __get_filter(fprog, sk);
int err;
if (IS_ERR(prog))
return PTR_ERR(prog);
if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max))
err = -ENOMEM;
else
err = reuseport_attach_prog(sk, prog);
if (err)
__bpf_prog_release(prog);
return err;
}
static struct bpf_prog *__get_bpf(u32 ufd, struct sock *sk)
{
if (sock_flag(sk, SOCK_FILTER_LOCKED))
return ERR_PTR(-EPERM);
return bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER);
}
int sk_attach_bpf(u32 ufd, struct sock *sk)
{
struct bpf_prog *prog = __get_bpf(ufd, sk);
int err;
if (IS_ERR(prog))
return PTR_ERR(prog);
err = __sk_attach_prog(prog, sk);
if (err < 0) {
bpf_prog_put(prog);
return err;
}
return 0;
}
int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
{
struct bpf_prog *prog;
int err;
if (sock_flag(sk, SOCK_FILTER_LOCKED))
return -EPERM;
prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER);
if (PTR_ERR(prog) == -EINVAL)
prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SK_REUSEPORT);
if (IS_ERR(prog))
return PTR_ERR(prog);
if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) {
/* Like other non BPF_PROG_TYPE_SOCKET_FILTER
* bpf prog (e.g. sockmap). It depends on the
* limitation imposed by bpf_prog_load().
* Hence, sysctl_optmem_max is not checked.
*/
if ((sk->sk_type != SOCK_STREAM &&
sk->sk_type != SOCK_DGRAM) ||
(sk->sk_protocol != IPPROTO_UDP &&
sk->sk_protocol != IPPROTO_TCP) ||
(sk->sk_family != AF_INET &&
sk->sk_family != AF_INET6)) {
err = -ENOTSUPP;
goto err_prog_put;
}
} else {
/* BPF_PROG_TYPE_SOCKET_FILTER */
if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) {
err = -ENOMEM;
goto err_prog_put;
}
}
err = reuseport_attach_prog(sk, prog);
err_prog_put:
if (err)
bpf_prog_put(prog);
return err;
}
void sk_reuseport_prog_free(struct bpf_prog *prog)
{
if (!prog)
return;
if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT)
bpf_prog_put(prog);
else
bpf_prog_destroy(prog);
}
struct bpf_scratchpad {
union {
__be32 diff[MAX_BPF_STACK / sizeof(__be32)];
u8 buff[MAX_BPF_STACK];
};
};
static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp);
static inline int __bpf_try_make_writable(struct sk_buff *skb,
unsigned int write_len)
{
return skb_ensure_writable(skb, write_len);
}
static inline int bpf_try_make_writable(struct sk_buff *skb,
unsigned int write_len)
{
int err = __bpf_try_make_writable(skb, write_len);
bpf_compute_data_pointers(skb);
return err;
}
static int bpf_try_make_head_writable(struct sk_buff *skb)
{
return bpf_try_make_writable(skb, skb_headlen(skb));
}
static inline void bpf_push_mac_rcsum(struct sk_buff *skb)
{
if (skb_at_tc_ingress(skb))
skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len);
}
static inline void bpf_pull_mac_rcsum(struct sk_buff *skb)
{
if (skb_at_tc_ingress(skb))
skb_postpull_rcsum(skb, skb_mac_header(skb), skb->mac_len);
}
BPF_CALL_5(bpf_skb_store_bytes, struct sk_buff *, skb, u32, offset,
const void *, from, u32, len, u64, flags)
{
void *ptr;
if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH)))
return -EINVAL;
if (unlikely(offset > INT_MAX))
return -EFAULT;
if (unlikely(bpf_try_make_writable(skb, offset + len)))
return -EFAULT;
ptr = skb->data + offset;
if (flags & BPF_F_RECOMPUTE_CSUM)
__skb_postpull_rcsum(skb, ptr, len, offset);
memcpy(ptr, from, len);
if (flags & BPF_F_RECOMPUTE_CSUM)
__skb_postpush_rcsum(skb, ptr, len, offset);
if (flags & BPF_F_INVALIDATE_HASH)
skb_clear_hash(skb);
return 0;
}
static const struct bpf_func_proto bpf_skb_store_bytes_proto = {
.func = bpf_skb_store_bytes,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg4_type = ARG_CONST_SIZE,
.arg5_type = ARG_ANYTHING,
};
BPF_CALL_4(bpf_skb_load_bytes, const struct sk_buff *, skb, u32, offset,
void *, to, u32, len)
{
void *ptr;
if (unlikely(offset > INT_MAX))
goto err_clear;
ptr = skb_header_pointer(skb, offset, len, to);
if (unlikely(!ptr))
goto err_clear;
if (ptr != to)
memcpy(to, ptr, len);
return 0;
err_clear:
memset(to, 0, len);
return -EFAULT;
}
static const struct bpf_func_proto bpf_skb_load_bytes_proto = {
.func = bpf_skb_load_bytes,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_PTR_TO_UNINIT_MEM,
.arg4_type = ARG_CONST_SIZE,
};
BPF_CALL_4(bpf_flow_dissector_load_bytes,
const struct bpf_flow_dissector *, ctx, u32, offset,
void *, to, u32, len)
{
void *ptr;
if (unlikely(offset > 0xffff))
goto err_clear;
if (unlikely(!ctx->skb))
goto err_clear;
ptr = skb_header_pointer(ctx->skb, offset, len, to);
if (unlikely(!ptr))
goto err_clear;
if (ptr != to)
memcpy(to, ptr, len);
return 0;
err_clear:
memset(to, 0, len);
return -EFAULT;
}
static const struct bpf_func_proto bpf_flow_dissector_load_bytes_proto = {
.func = bpf_flow_dissector_load_bytes,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_PTR_TO_UNINIT_MEM,
.arg4_type = ARG_CONST_SIZE,
};
BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb,
u32, offset, void *, to, u32, len, u32, start_header)
{
u8 *end = skb_tail_pointer(skb);
u8 *start, *ptr;
if (unlikely(offset > 0xffff))
goto err_clear;
switch (start_header) {
case BPF_HDR_START_MAC:
if (unlikely(!skb_mac_header_was_set(skb)))
goto err_clear;
start = skb_mac_header(skb);
break;
case BPF_HDR_START_NET:
start = skb_network_header(skb);
break;
default:
goto err_clear;
}
ptr = start + offset;
if (likely(ptr + len <= end)) {
memcpy(to, ptr, len);
return 0;
}
err_clear:
memset(to, 0, len);
return -EFAULT;
}
static const struct bpf_func_proto bpf_skb_load_bytes_relative_proto = {
.func = bpf_skb_load_bytes_relative,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_PTR_TO_UNINIT_MEM,
.arg4_type = ARG_CONST_SIZE,
.arg5_type = ARG_ANYTHING,
};
BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len)
{
/* Idea is the following: should the needed direct read/write
* test fail during runtime, we can pull in more data and redo
* again, since implicitly, we invalidate previous checks here.
*
* Or, since we know how much we need to make read/writeable,
* this can be done once at the program beginning for direct
* access case. By this we overcome limitations of only current
* headroom being accessible.
*/
return bpf_try_make_writable(skb, len ? : skb_headlen(skb));
}
static const struct bpf_func_proto bpf_skb_pull_data_proto = {
.func = bpf_skb_pull_data,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
};
BPF_CALL_1(bpf_sk_fullsock, struct sock *, sk)
{
return sk_fullsock(sk) ? (unsigned long)sk : (unsigned long)NULL;
}
static const struct bpf_func_proto bpf_sk_fullsock_proto = {
.func = bpf_sk_fullsock,
.gpl_only = false,
.ret_type = RET_PTR_TO_SOCKET_OR_NULL,
.arg1_type = ARG_PTR_TO_SOCK_COMMON,
};
static inline int sk_skb_try_make_writable(struct sk_buff *skb,
unsigned int write_len)
{
return __bpf_try_make_writable(skb, write_len);
}
BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len)
{
/* Idea is the following: should the needed direct read/write
* test fail during runtime, we can pull in more data and redo
* again, since implicitly, we invalidate previous checks here.
*
* Or, since we know how much we need to make read/writeable,
* this can be done once at the program beginning for direct
* access case. By this we overcome limitations of only current
* headroom being accessible.
*/
return sk_skb_try_make_writable(skb, len ? : skb_headlen(skb));
}
static const struct bpf_func_proto sk_skb_pull_data_proto = {
.func = sk_skb_pull_data,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
};
BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset,
u64, from, u64, to, u64, flags)
{
__sum16 *ptr;
if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK)))
return -EINVAL;
if (unlikely(offset > 0xffff || offset & 1))
return -EFAULT;
if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr))))
return -EFAULT;
ptr = (__sum16 *)(skb->data + offset);
switch (flags & BPF_F_HDR_FIELD_MASK) {
case 0:
if (unlikely(from != 0))
return -EINVAL;
csum_replace_by_diff(ptr, to);
break;
case 2:
csum_replace2(ptr, from, to);
break;
case 4:
csum_replace4(ptr, from, to);
break;
default:
return -EINVAL;
}
return 0;
}
static const struct bpf_func_proto bpf_l3_csum_replace_proto = {
.func = bpf_l3_csum_replace,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_ANYTHING,
.arg4_type = ARG_ANYTHING,
.arg5_type = ARG_ANYTHING,
};
BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset,
u64, from, u64, to, u64, flags)
{
bool is_pseudo = flags & BPF_F_PSEUDO_HDR;
bool is_mmzero = flags & BPF_F_MARK_MANGLED_0;
bool do_mforce = flags & BPF_F_MARK_ENFORCE;
__sum16 *ptr;
if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_MARK_ENFORCE |
BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK)))
return -EINVAL;
if (unlikely(offset > 0xffff || offset & 1))
return -EFAULT;
if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr))))
return -EFAULT;
ptr = (__sum16 *)(skb->data + offset);
if (is_mmzero && !do_mforce && !*ptr)
return 0;
switch (flags & BPF_F_HDR_FIELD_MASK) {
case 0:
if (unlikely(from != 0))
return -EINVAL;
inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo);
break;
case 2:
inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo);
break;
case 4:
inet_proto_csum_replace4(ptr, skb, from, to, is_pseudo);
break;
default:
return -EINVAL;
}
if (is_mmzero && !*ptr)
*ptr = CSUM_MANGLED_0;
return 0;
}
static const struct bpf_func_proto bpf_l4_csum_replace_proto = {
.func = bpf_l4_csum_replace,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_ANYTHING,
.arg4_type = ARG_ANYTHING,
.arg5_type = ARG_ANYTHING,
};
BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size,
__be32 *, to, u32, to_size, __wsum, seed)
{
struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp);
u32 diff_size = from_size + to_size;
int i, j = 0;
/* This is quite flexible, some examples:
*
* from_size == 0, to_size > 0, seed := csum --> pushing data
* from_size > 0, to_size == 0, seed := csum --> pulling data
* from_size > 0, to_size > 0, seed := 0 --> diffing data
*
* Even for diffing, from_size and to_size don't need to be equal.
*/
if (unlikely(((from_size | to_size) & (sizeof(__be32) - 1)) ||
diff_size > sizeof(sp->diff)))
return -EINVAL;
for (i = 0; i < from_size / sizeof(__be32); i++, j++)
sp->diff[j] = ~from[i];
for (i = 0; i < to_size / sizeof(__be32); i++, j++)
sp->diff[j] = to[i];
return csum_partial(sp->diff, diff_size, seed);
}
static const struct bpf_func_proto bpf_csum_diff_proto = {
.func = bpf_csum_diff,
.gpl_only = false,
.pkt_access = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE_OR_ZERO,
.arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
.arg4_type = ARG_CONST_SIZE_OR_ZERO,
.arg5_type = ARG_ANYTHING,
};
BPF_CALL_2(bpf_csum_update, struct sk_buff *, skb, __wsum, csum)
{
/* The interface is to be used in combination with bpf_csum_diff()
* for direct packet writes. csum rotation for alignment as well
* as emulating csum_sub() can be done from the eBPF program.
*/
if (skb->ip_summed == CHECKSUM_COMPLETE)
return (skb->csum = csum_add(skb->csum, csum));
return -ENOTSUPP;
}
static const struct bpf_func_proto bpf_csum_update_proto = {
.func = bpf_csum_update,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
};
BPF_CALL_2(bpf_csum_level, struct sk_buff *, skb, u64, level)
{
/* The interface is to be used in combination with bpf_skb_adjust_room()
* for encap/decap of packet headers when BPF_F_ADJ_ROOM_NO_CSUM_RESET
* is passed as flags, for example.
*/
switch (level) {
case BPF_CSUM_LEVEL_INC:
__skb_incr_checksum_unnecessary(skb);
break;
case BPF_CSUM_LEVEL_DEC:
__skb_decr_checksum_unnecessary(skb);
break;
case BPF_CSUM_LEVEL_RESET:
__skb_reset_checksum_unnecessary(skb);
break;
case BPF_CSUM_LEVEL_QUERY:
return skb->ip_summed == CHECKSUM_UNNECESSARY ?
skb->csum_level : -EACCES;
default:
return -EINVAL;
}
return 0;
}
static const struct bpf_func_proto bpf_csum_level_proto = {
.func = bpf_csum_level,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
};
static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
{
return dev_forward_skb_nomtu(dev, skb);
}
static inline int __bpf_rx_skb_no_mac(struct net_device *dev,
struct sk_buff *skb)
{
int ret = ____dev_forward_skb(dev, skb, false);
if (likely(!ret)) {
skb->dev = dev;
ret = netif_rx(skb);
}
return ret;
}
static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
{
int ret;
if (dev_xmit_recursion()) {
net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
kfree_skb(skb);
return -ENETDOWN;
}
skb->dev = dev;
skb_clear_tstamp(skb);
dev_xmit_recursion_inc();
ret = dev_queue_xmit(skb);
dev_xmit_recursion_dec();
return ret;
}
static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev,
u32 flags)
{
unsigned int mlen = skb_network_offset(skb);
if (unlikely(skb->len <= mlen)) {
kfree_skb(skb);
return -ERANGE;
}
if (mlen) {
__skb_pull(skb, mlen);
if (unlikely(!skb->len)) {
kfree_skb(skb);
return -ERANGE;
}
/* At ingress, the mac header has already been pulled once.
* At egress, skb_pospull_rcsum has to be done in case that
* the skb is originated from ingress (i.e. a forwarded skb)
* to ensure that rcsum starts at net header.
*/
if (!skb_at_tc_ingress(skb))
skb_postpull_rcsum(skb, skb_mac_header(skb), mlen);
}
skb_pop_mac_header(skb);
skb_reset_mac_len(skb);
return flags & BPF_F_INGRESS ?
__bpf_rx_skb_no_mac(dev, skb) : __bpf_tx_skb(dev, skb);
}
static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev,
u32 flags)
{
/* Verify that a link layer header is carried */
if (unlikely(skb->mac_header >= skb->network_header || skb->len == 0)) {
kfree_skb(skb);
return -ERANGE;
}
bpf_push_mac_rcsum(skb);
return flags & BPF_F_INGRESS ?
__bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
}
static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev,
u32 flags)
{
if (dev_is_mac_header_xmit(dev))
return __bpf_redirect_common(skb, dev, flags);
else
return __bpf_redirect_no_mac(skb, dev, flags);
}
#if IS_ENABLED(CONFIG_IPV6)
static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb,
struct net_device *dev, struct bpf_nh_params *nh)
{
u32 hh_len = LL_RESERVED_SPACE(dev);
const struct in6_addr *nexthop;
struct dst_entry *dst = NULL;
struct neighbour *neigh;
if (dev_xmit_recursion()) {
net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
goto out_drop;
}
skb->dev = dev;
skb_clear_tstamp(skb);
if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
skb = skb_expand_head(skb, hh_len);
if (!skb)
return -ENOMEM;
}
rcu_read_lock();
if (!nh) {
dst = skb_dst(skb);
nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst),
&ipv6_hdr(skb)->daddr);
} else {
nexthop = &nh->ipv6_nh;
}
neigh = ip_neigh_gw6(dev, nexthop);
if (likely(!IS_ERR(neigh))) {
int ret;
sock_confirm_neigh(skb, neigh);
local_bh_disable();
dev_xmit_recursion_inc();
ret = neigh_output(neigh, skb, false);
dev_xmit_recursion_dec();
local_bh_enable();
rcu_read_unlock();
return ret;
}
rcu_read_unlock_bh();
if (dst)
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
out_drop:
kfree_skb(skb);
return -ENETDOWN;
}
static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev,
struct bpf_nh_params *nh)
{
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
struct net *net = dev_net(dev);
int err, ret = NET_XMIT_DROP;
if (!nh) {
struct dst_entry *dst;
struct flowi6 fl6 = {
.flowi6_flags = FLOWI_FLAG_ANYSRC,
.flowi6_mark = skb->mark,
.flowlabel = ip6_flowinfo(ip6h),
.flowi6_oif = dev->ifindex,
.flowi6_proto = ip6h->nexthdr,
.daddr = ip6h->daddr,
.saddr = ip6h->saddr,
};
dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL);
if (IS_ERR(dst))
goto out_drop;
skb_dst_set(skb, dst);
} else if (nh->nh_family != AF_INET6) {
goto out_drop;
}
err = bpf_out_neigh_v6(net, skb, dev, nh);
if (unlikely(net_xmit_eval(err)))
dev->stats.tx_errors++;
else
ret = NET_XMIT_SUCCESS;
goto out_xmit;
out_drop:
dev->stats.tx_errors++;
kfree_skb(skb);
out_xmit:
return ret;
}
#else
static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev,
struct bpf_nh_params *nh)
{
kfree_skb(skb);
return NET_XMIT_DROP;
}
#endif /* CONFIG_IPV6 */
#if IS_ENABLED(CONFIG_INET)
static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb,
struct net_device *dev, struct bpf_nh_params *nh)
{
u32 hh_len = LL_RESERVED_SPACE(dev);
struct neighbour *neigh;
bool is_v6gw = false;
if (dev_xmit_recursion()) {
net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
goto out_drop;
}
skb->dev = dev;
skb_clear_tstamp(skb);
if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
skb = skb_expand_head(skb, hh_len);
if (!skb)
return -ENOMEM;
}
rcu_read_lock();
if (!nh) {
struct dst_entry *dst = skb_dst(skb);
struct rtable *rt = container_of(dst, struct rtable, dst);
neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
} else if (nh->nh_family == AF_INET6) {
neigh = ip_neigh_gw6(dev, &nh->ipv6_nh);
is_v6gw = true;
} else if (nh->nh_family == AF_INET) {
neigh = ip_neigh_gw4(dev, nh->ipv4_nh);
} else {
rcu_read_unlock();
goto out_drop;
}
if (likely(!IS_ERR(neigh))) {
int ret;
sock_confirm_neigh(skb, neigh);
local_bh_disable();
dev_xmit_recursion_inc();
ret = neigh_output(neigh, skb, is_v6gw);
dev_xmit_recursion_dec();
local_bh_enable();
rcu_read_unlock();
return ret;
}
rcu_read_unlock();
out_drop:
kfree_skb(skb);
return -ENETDOWN;
}
static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
struct bpf_nh_params *nh)
{
const struct iphdr *ip4h = ip_hdr(skb);
struct net *net = dev_net(dev);
int err, ret = NET_XMIT_DROP;
if (!nh) {
struct flowi4 fl4 = {
.flowi4_flags = FLOWI_FLAG_ANYSRC,
.flowi4_mark = skb->mark,
.flowi4_tos = RT_TOS(ip4h->tos),
.flowi4_oif = dev->ifindex,
.flowi4_proto = ip4h->protocol,
.daddr = ip4h->daddr,
.saddr = ip4h->saddr,
};
struct rtable *rt;
rt = ip_route_output_flow(net, &fl4, NULL);
if (IS_ERR(rt))
goto out_drop;
if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
ip_rt_put(rt);
goto out_drop;
}
skb_dst_set(skb, &rt->dst);
}
err = bpf_out_neigh_v4(net, skb, dev, nh);
if (unlikely(net_xmit_eval(err)))
dev->stats.tx_errors++;
else
ret = NET_XMIT_SUCCESS;
goto out_xmit;
out_drop:
dev->stats.tx_errors++;
kfree_skb(skb);
out_xmit:
return ret;
}
#else
static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
struct bpf_nh_params *nh)
{
kfree_skb(skb);
return NET_XMIT_DROP;
}
#endif /* CONFIG_INET */
static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev,
struct bpf_nh_params *nh)
{
struct ethhdr *ethh = eth_hdr(skb);
if (unlikely(skb->mac_header >= skb->network_header))
goto out;
bpf_push_mac_rcsum(skb);
if (is_multicast_ether_addr(ethh->h_dest))
goto out;
skb_pull(skb, sizeof(*ethh));
skb_unset_mac_header(skb);
skb_reset_network_header(skb);
if (skb->protocol == htons(ETH_P_IP))
return __bpf_redirect_neigh_v4(skb, dev, nh);
else if (skb->protocol == htons(ETH_P_IPV6))
return __bpf_redirect_neigh_v6(skb, dev, nh);
out:
kfree_skb(skb);
return -ENOTSUPP;
}
/* Internal, non-exposed redirect flags. */
enum {
BPF_F_NEIGH = (1ULL << 1),
BPF_F_PEER = (1ULL << 2),
BPF_F_NEXTHOP = (1ULL << 3),
#define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER | BPF_F_NEXTHOP)
};
BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
{
struct net_device *dev;
struct sk_buff *clone;
int ret;
if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL)))
return -EINVAL;
dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex);
if (unlikely(!dev))
return -EINVAL;
clone = skb_clone(skb, GFP_ATOMIC);
if (unlikely(!clone))
return -ENOMEM;
/* For direct write, we need to keep the invariant that the skbs
* we're dealing with need to be uncloned. Should uncloning fail
* here, we need to free the just generated clone to unclone once
* again.
*/
ret = bpf_try_make_head_writable(skb);
if (unlikely(ret)) {
kfree_skb(clone);
return -ENOMEM;
}
return __bpf_redirect(clone, dev, flags);
}
static const struct bpf_func_proto bpf_clone_redirect_proto = {
.func = bpf_clone_redirect,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_ANYTHING,
};
DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
int skb_do_redirect(struct sk_buff *skb)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
struct net *net = dev_net(skb->dev);
struct net_device *dev;
u32 flags = ri->flags;
dev = dev_get_by_index_rcu(net, ri->tgt_index);
ri->tgt_index = 0;
ri->flags = 0;
if (unlikely(!dev))
goto out_drop;
if (flags & BPF_F_PEER) {
const struct net_device_ops *ops = dev->netdev_ops;
if (unlikely(!ops->ndo_get_peer_dev ||
!skb_at_tc_ingress(skb)))
goto out_drop;
dev = ops->ndo_get_peer_dev(dev);
if (unlikely(!dev ||
!(dev->flags & IFF_UP) ||
net_eq(net, dev_net(dev))))
goto out_drop;
skb->dev = dev;
return -EAGAIN;
}
return flags & BPF_F_NEIGH ?
__bpf_redirect_neigh(skb, dev, flags & BPF_F_NEXTHOP ?
&ri->nh : NULL) :
__bpf_redirect(skb, dev, flags);
out_drop:
kfree_skb(skb);
return -EINVAL;
}
BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL)))
return TC_ACT_SHOT;
ri->flags = flags;
ri->tgt_index = ifindex;
return TC_ACT_REDIRECT;
}
static const struct bpf_func_proto bpf_redirect_proto = {
.func = bpf_redirect,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_ANYTHING,
.arg2_type = ARG_ANYTHING,
};
BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
if (unlikely(flags))
return TC_ACT_SHOT;
ri->flags = BPF_F_PEER;
ri->tgt_index = ifindex;
return TC_ACT_REDIRECT;
}
static const struct bpf_func_proto bpf_redirect_peer_proto = {
.func = bpf_redirect_peer,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_ANYTHING,
.arg2_type = ARG_ANYTHING,
};
BPF_CALL_4(bpf_redirect_neigh, u32, ifindex, struct bpf_redir_neigh *, params,
int, plen, u64, flags)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
if (unlikely((plen && plen < sizeof(*params)) || flags))
return TC_ACT_SHOT;
ri->flags = BPF_F_NEIGH | (plen ? BPF_F_NEXTHOP : 0);
ri->tgt_index = ifindex;
BUILD_BUG_ON(sizeof(struct bpf_redir_neigh) != sizeof(struct bpf_nh_params));
if (plen)
memcpy(&ri->nh, params, sizeof(ri->nh));
return TC_ACT_REDIRECT;
}
static const struct bpf_func_proto bpf_redirect_neigh_proto = {
.func = bpf_redirect_neigh,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_ANYTHING,
.arg2_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE_OR_ZERO,
.arg4_type = ARG_ANYTHING,
};
BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes)
{
msg->apply_bytes = bytes;
return 0;
}
static const struct bpf_func_proto bpf_msg_apply_bytes_proto = {
.func = bpf_msg_apply_bytes,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
};
BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg *, msg, u32, bytes)
{
msg->cork_bytes = bytes;
return 0;
}
static void sk_msg_reset_curr(struct sk_msg *msg)
{
u32 i = msg->sg.start;
u32 len = 0;
do {
len += sk_msg_elem(msg, i)->length;
sk_msg_iter_var_next(i);
if (len >= msg->sg.size)
break;
} while (i != msg->sg.end);
msg->sg.curr = i;
msg->sg.copybreak = 0;
}
static const struct bpf_func_proto bpf_msg_cork_bytes_proto = {
.func = bpf_msg_cork_bytes,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
};
BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
u32, end, u64, flags)
{
u32 len = 0, offset = 0, copy = 0, poffset = 0, bytes = end - start;
u32 first_sge, last_sge, i, shift, bytes_sg_total;
struct scatterlist *sge;
u8 *raw, *to, *from;
struct page *page;
if (unlikely(flags || end <= start))
return -EINVAL;
/* First find the starting scatterlist element */
i = msg->sg.start;
do {
offset += len;
len = sk_msg_elem(msg, i)->length;
if (start < offset + len)
break;
sk_msg_iter_var_next(i);
} while (i != msg->sg.end);
if (unlikely(start >= offset + len))
return -EINVAL;
first_sge = i;
/* The start may point into the sg element so we need to also
* account for the headroom.
*/
bytes_sg_total = start - offset + bytes;
if (!test_bit(i, msg->sg.copy) && bytes_sg_total <= len)
goto out;
/* At this point we need to linearize multiple scatterlist
* elements or a single shared page. Either way we need to
* copy into a linear buffer exclusively owned by BPF. Then
* place the buffer in the scatterlist and fixup the original
* entries by removing the entries now in the linear buffer
* and shifting the remaining entries. For now we do not try
* to copy partial entries to avoid complexity of running out
* of sg_entry slots. The downside is reading a single byte
* will copy the entire sg entry.
*/
do {
copy += sk_msg_elem(msg, i)->length;
sk_msg_iter_var_next(i);
if (bytes_sg_total <= copy)
break;
} while (i != msg->sg.end);
last_sge = i;
if (unlikely(bytes_sg_total > copy))
return -EINVAL;
page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP,
get_order(copy));
if (unlikely(!page))
return -ENOMEM;
raw = page_address(page);
i = first_sge;
do {
sge = sk_msg_elem(msg, i);
from = sg_virt(sge);
len = sge->length;
to = raw + poffset;
memcpy(to, from, len);
poffset += len;
sge->length = 0;
put_page(sg_page(sge));
sk_msg_iter_var_next(i);
} while (i != last_sge);
sg_set_page(&msg->sg.data[first_sge], page, copy, 0);
/* To repair sg ring we need to shift entries. If we only
* had a single entry though we can just replace it and
* be done. Otherwise walk the ring and shift the entries.
*/
WARN_ON_ONCE(last_sge == first_sge);
shift = last_sge > first_sge ?
last_sge - first_sge - 1 :
NR_MSG_FRAG_IDS - first_sge + last_sge - 1;
if (!shift)
goto out;
i = first_sge;
sk_msg_iter_var_next(i);
do {
u32 move_from;
if (i + shift >= NR_MSG_FRAG_IDS)
move_from = i + shift - NR_MSG_FRAG_IDS;
else
move_from = i + shift;
if (move_from == msg->sg.end)
break;
msg->sg.data[i] = msg->sg.data[move_from];
msg->sg.data[move_from].length = 0;
msg->sg.data[move_from].page_link = 0;
msg->sg.data[move_from].offset = 0;
sk_msg_iter_var_next(i);
} while (1);
msg->sg.end = msg->sg.end - shift > msg->sg.end ?
msg->sg.end - shift + NR_MSG_FRAG_IDS :
msg->sg.end - shift;
out:
sk_msg_reset_curr(msg);
msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset;
msg->data_end = msg->data + bytes;
return 0;
}
static const struct bpf_func_proto bpf_msg_pull_data_proto = {
.func = bpf_msg_pull_data,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_ANYTHING,
.arg4_type = ARG_ANYTHING,
};
BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
u32, len, u64, flags)
{
struct scatterlist sge, nsge, nnsge, rsge = {0}, *psge;
u32 new, i = 0, l = 0, space, copy = 0, offset = 0;
u8 *raw, *to, *from;
struct page *page;
if (unlikely(flags))
return -EINVAL;
if (unlikely(len == 0))
return 0;
/* First find the starting scatterlist element */
i = msg->sg.start;
do {
offset += l;
l = sk_msg_elem(msg, i)->length;
if (start < offset + l)
break;
sk_msg_iter_var_next(i);
} while (i != msg->sg.end);
if (start >= offset + l)
return -EINVAL;
space = MAX_MSG_FRAGS - sk_msg_elem_used(msg);
/* If no space available will fallback to copy, we need at
* least one scatterlist elem available to push data into
* when start aligns to the beginning of an element or two
* when it falls inside an element. We handle the start equals
* offset case because its the common case for inserting a
* header.
*/
if (!space || (space == 1 && start != offset))
copy = msg->sg.data[i].length;
page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP,
get_order(copy + len));
if (unlikely(!page))
return -ENOMEM;
if (copy) {
int front, back;
raw = page_address(page);
psge = sk_msg_elem(msg, i);
front = start - offset;
back = psge->length - front;
from = sg_virt(psge);
if (front)
memcpy(raw, from, front);
if (back) {
from += front;
to = raw + front + len;
memcpy(to, from, back);
}
put_page(sg_page(psge));
} else if (start - offset) {
psge = sk_msg_elem(msg, i);
rsge = sk_msg_elem_cpy(msg, i);
psge->length = start - offset;
rsge.length -= psge->length;
rsge.offset += start;
sk_msg_iter_var_next(i);
sg_unmark_end(psge);
sg_unmark_end(&rsge);
sk_msg_iter_next(msg, end);
}
/* Slot(s) to place newly allocated data */
new = i;
/* Shift one or two slots as needed */
if (!copy) {
sge = sk_msg_elem_cpy(msg, i);
sk_msg_iter_var_next(i);
sg_unmark_end(&sge);
sk_msg_iter_next(msg, end);
nsge = sk_msg_elem_cpy(msg, i);
if (rsge.length) {
sk_msg_iter_var_next(i);
nnsge = sk_msg_elem_cpy(msg, i);
}
while (i != msg->sg.end) {
msg->sg.data[i] = sge;
sge = nsge;
sk_msg_iter_var_next(i);
if (rsge.length) {
nsge = nnsge;
nnsge = sk_msg_elem_cpy(msg, i);
} else {
nsge = sk_msg_elem_cpy(msg, i);
}
}
}
/* Place newly allocated data buffer */
sk_mem_charge(msg->sk, len);
msg->sg.size += len;
__clear_bit(new, msg->sg.copy);
sg_set_page(&msg->sg.data[new], page, len + copy, 0);
if (rsge.length) {
get_page(sg_page(&rsge));
sk_msg_iter_var_next(new);
msg->sg.data[new] = rsge;
}
sk_msg_reset_curr(msg);
sk_msg_compute_data_pointers(msg);
return 0;
}
static const struct bpf_func_proto bpf_msg_push_data_proto = {
.func = bpf_msg_push_data,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_ANYTHING,
.arg4_type = ARG_ANYTHING,
};
static void sk_msg_shift_left(struct sk_msg *msg, int i)
{
int prev;
do {
prev = i;
sk_msg_iter_var_next(i);
msg->sg.data[prev] = msg->sg.data[i];
} while (i != msg->sg.end);
sk_msg_iter_prev(msg, end);
}
static void sk_msg_shift_right(struct sk_msg *msg, int i)
{
struct scatterlist tmp, sge;
sk_msg_iter_next(msg, end);
sge = sk_msg_elem_cpy(msg, i);
sk_msg_iter_var_next(i);
tmp = sk_msg_elem_cpy(msg, i);
while (i != msg->sg.end) {
msg->sg.data[i] = sge;
sk_msg_iter_var_next(i);
sge = tmp;
tmp = sk_msg_elem_cpy(msg, i);
}
}
BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
u32, len, u64, flags)
{
u32 i = 0, l = 0, space, offset = 0;
u64 last = start + len;
int pop;
if (unlikely(flags))
return -EINVAL;
/* First find the starting scatterlist element */
i = msg->sg.start;
do {
offset += l;
l = sk_msg_elem(msg, i)->length;
if (start < offset + l)
break;
sk_msg_iter_var_next(i);
} while (i != msg->sg.end);
/* Bounds checks: start and pop must be inside message */
if (start >= offset + l || last >= msg->sg.size)
return -EINVAL;
space = MAX_MSG_FRAGS - sk_msg_elem_used(msg);
pop = len;
/* --------------| offset
* -| start |-------- len -------|
*
* |----- a ----|-------- pop -------|----- b ----|
* |______________________________________________| length
*
*
* a: region at front of scatter element to save
* b: region at back of scatter element to save when length > A + pop
* pop: region to pop from element, same as input 'pop' here will be
* decremented below per iteration.
*
* Two top-level cases to handle when start != offset, first B is non
* zero and second B is zero corresponding to when a pop includes more
* than one element.
*
* Then if B is non-zero AND there is no space allocate space and
* compact A, B regions into page. If there is space shift ring to
* the rigth free'ing the next element in ring to place B, leaving
* A untouched except to reduce length.
*/
if (start != offset) {
struct scatterlist *nsge, *sge = sk_msg_elem(msg, i);
int a = start;
int b = sge->length - pop - a;
sk_msg_iter_var_next(i);
if (pop < sge->length - a) {
if (space) {
sge->length = a;
sk_msg_shift_right(msg, i);
nsge = sk_msg_elem(msg, i);
get_page(sg_page(sge));
sg_set_page(nsge,
sg_page(sge),
b, sge->offset + pop + a);
} else {
struct page *page, *orig;
u8 *to, *from;
page = alloc_pages(__GFP_NOWARN |
__GFP_COMP | GFP_ATOMIC,
get_order(a + b));
if (unlikely(!page))
return -ENOMEM;
sge->length = a;
orig = sg_page(sge);
from = sg_virt(sge);
to = page_address(page);
memcpy(to, from, a);
memcpy(to + a, from + a + pop, b);
sg_set_page(sge, page, a + b, 0);
put_page(orig);
}
pop = 0;
} else if (pop >= sge->length - a) {
pop -= (sge->length - a);
sge->length = a;
}
}
/* From above the current layout _must_ be as follows,
*
* -| offset
* -| start
*
* |---- pop ---|---------------- b ------------|
* |____________________________________________| length
*
* Offset and start of the current msg elem are equal because in the
* previous case we handled offset != start and either consumed the
* entire element and advanced to the next element OR pop == 0.
*
* Two cases to handle here are first pop is less than the length
* leaving some remainder b above. Simply adjust the element's layout
* in this case. Or pop >= length of the element so that b = 0. In this
* case advance to next element decrementing pop.
*/
while (pop) {
struct scatterlist *sge = sk_msg_elem(msg, i);
if (pop < sge->length) {
sge->length -= pop;
sge->offset += pop;
pop = 0;
} else {
pop -= sge->length;
sk_msg_shift_left(msg, i);<