summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorJakub Kicinski <kuba@kernel.org>2022-10-03 13:02:48 -0700
committerJakub Kicinski <kuba@kernel.org>2022-10-03 13:02:49 -0700
commita08d97a1935bee66b099b21feddad19c1fd90d0e (patch)
treeb11aaa5e616432f1012c7c738f12ab64dacef9b2 /net
parent62c07983bef9d3e78e71189441e1a470f0d1e653 (diff)
parent820dc0523e05c12810bb6bf4e56ce26e4c1948a2 (diff)
downloadlinux-a08d97a1935bee66b099b21feddad19c1fd90d0e.tar.bz2
Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says: ==================== pull-request: bpf-next 2022-10-03 We've added 143 non-merge commits during the last 27 day(s) which contain a total of 151 files changed, 8321 insertions(+), 1402 deletions(-). The main changes are: 1) Add kfuncs for PKCS#7 signature verification from BPF programs, from Roberto Sassu. 2) Add support for struct-based arguments for trampoline based BPF programs, from Yonghong Song. 3) Fix entry IP for kprobe-multi and trampoline probes under IBT enabled, from Jiri Olsa. 4) Batch of improvements to veristat selftest tool in particular to add CSV output, a comparison mode for CSV outputs and filtering, from Andrii Nakryiko. 5) Add preparatory changes needed for the BPF core for upcoming BPF HID support, from Benjamin Tissoires. 6) Support for direct writes to nf_conn's mark field from tc and XDP BPF program types, from Daniel Xu. 7) Initial batch of documentation improvements for BPF insn set spec, from Dave Thaler. 8) Add a new BPF_MAP_TYPE_USER_RINGBUF map which provides single-user-space-producer / single-kernel-consumer semantics for BPF ring buffer, from David Vernet. 9) Follow-up fixes to BPF allocator under RT to always use raw spinlock for the BPF hashtab's bucket lock, from Hou Tao. 10) Allow creating an iterator that loops through only the resources of one task/thread instead of all, from Kui-Feng Lee. 11) Add support for kptrs in the per-CPU arraymap, from Kumar Kartikeya Dwivedi. 12) Add a new kfunc helper for nf to set src/dst NAT IP/port in a newly allocated CT entry which is not yet inserted, from Lorenzo Bianconi. 13) Remove invalid recursion check for struct_ops for TCP congestion control BPF programs, from Martin KaFai Lau. 14) Fix W^X issue with BPF trampoline and BPF dispatcher, from Song Liu. 15) Fix percpu_counter leakage in BPF hashtab allocation error path, from Tetsuo Handa. 16) Various cleanups in BPF selftests to use preferred ASSERT_* macros, from Wang Yufen. 17) Add invocation for cgroup/connect{4,6} BPF programs for ICMP pings, from YiFei Zhu. 18) Lift blinding decision under bpf_jit_harden = 1 to bpf_capable(), from Yauheni Kaliuta. 19) Various libbpf fixes and cleanups including a libbpf NULL pointer deref, from Xin Liu. * https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (143 commits) net: netfilter: move bpf_ct_set_nat_info kfunc in nf_nat_bpf.c Documentation: bpf: Add implementation notes documentations to table of contents bpf, docs: Delete misformatted table. selftests/xsk: Fix double free bpftool: Fix error message of strerror libbpf: Fix overrun in netlink attribute iteration selftests/bpf: Fix spelling mistake "unpriviledged" -> "unprivileged" samples/bpf: Fix typo in xdp_router_ipv4 sample bpftool: Remove unused struct event_ring_info bpftool: Remove unused struct btf_attach_point bpf, docs: Add TOC and fix formatting. bpf, docs: Add Clang note about BPF_ALU bpf, docs: Move Clang notes to a separate file bpf, docs: Linux byteswap note bpf, docs: Move legacy packet instructions to a separate file selftests/bpf: Check -EBUSY for the recurred bpf_setsockopt(TCP_CONGESTION) bpf: tcp: Stop bpf_setsockopt(TCP_CONGESTION) in init ops to recur itself bpf: Refactor bpf_setsockopt(TCP_CONGESTION) handling into another function bpf: Move the "cdg" tcp-cc check to the common sol_tcp_sockopt() bpf: Add __bpf_prog_{enter,exit}_struct_ops for struct_ops trampoline ... ==================== Link: https://lore.kernel.org/r/20221003194915.11847-1-daniel@iogearbox.net Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net')
-rw-r--r--net/bpf/test_run.c37
-rw-r--r--net/core/filter.c124
-rw-r--r--net/core/skmsg.c12
-rw-r--r--net/core/stream.c3
-rw-r--r--net/ipv4/bpf_tcp_ca.c2
-rw-r--r--net/ipv4/ping.c15
-rw-r--r--net/ipv4/tcp_minisocks.c1
-rw-r--r--net/ipv6/ping.c16
-rw-r--r--net/netfilter/Makefile6
-rw-r--r--net/netfilter/nf_conntrack_bpf.c74
-rw-r--r--net/netfilter/nf_conntrack_core.c1
-rw-r--r--net/netfilter/nf_nat_bpf.c79
-rw-r--r--net/netfilter/nf_nat_core.c4
13 files changed, 343 insertions, 31 deletions
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 25d8ecf105aa..13d578ce2a09 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -606,6 +606,38 @@ noinline void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p)
WARN_ON_ONCE(1);
}
+static int *__bpf_kfunc_call_test_get_mem(struct prog_test_ref_kfunc *p, const int size)
+{
+ if (size > 2 * sizeof(int))
+ return NULL;
+
+ return (int *)p;
+}
+
+noinline int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size)
+{
+ return __bpf_kfunc_call_test_get_mem(p, rdwr_buf_size);
+}
+
+noinline int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size)
+{
+ return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size);
+}
+
+/* the next 2 ones can't be really used for testing expect to ensure
+ * that the verifier rejects the call.
+ * Acquire functions must return struct pointers, so these ones are
+ * failing.
+ */
+noinline int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size)
+{
+ return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size);
+}
+
+noinline void bpf_kfunc_call_int_mem_release(int *p)
+{
+}
+
noinline struct prog_test_ref_kfunc *
bpf_kfunc_call_test_kptr_get(struct prog_test_ref_kfunc **pp, int a, int b)
{
@@ -712,6 +744,10 @@ BTF_ID_FLAGS(func, bpf_kfunc_call_memb_acquire, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_kfunc_call_test_release, KF_RELEASE)
BTF_ID_FLAGS(func, bpf_kfunc_call_memb_release, KF_RELEASE)
BTF_ID_FLAGS(func, bpf_kfunc_call_memb1_release, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_get_rdwr_mem, KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_get_rdonly_mem, KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_acq_rdonly_mem, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_kfunc_call_int_mem_release, KF_RELEASE)
BTF_ID_FLAGS(func, bpf_kfunc_call_test_kptr_get, KF_ACQUIRE | KF_RET_NULL | KF_KPTR_GET)
BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass_ctx)
BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass1)
@@ -1634,6 +1670,7 @@ static int __init bpf_prog_test_run_init(void)
ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_prog_test_kfunc_set);
ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_prog_test_kfunc_set);
+ ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &bpf_prog_test_kfunc_set);
return ret ?: register_btf_id_dtor_kfuncs(bpf_prog_test_dtor_kfunc,
ARRAY_SIZE(bpf_prog_test_dtor_kfunc),
THIS_MODULE);
diff --git a/net/core/filter.c b/net/core/filter.c
index 31608801078e..bb0136e7a8e4 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -18,6 +18,7 @@
*/
#include <linux/atomic.h>
+#include <linux/bpf_verifier.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/mm.h>
@@ -5101,6 +5102,59 @@ static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname,
return 0;
}
+static int sol_tcp_sockopt_congestion(struct sock *sk, char *optval,
+ int *optlen, bool getopt)
+{
+ struct tcp_sock *tp;
+ int ret;
+
+ if (*optlen < 2)
+ return -EINVAL;
+
+ if (getopt) {
+ if (!inet_csk(sk)->icsk_ca_ops)
+ return -EINVAL;
+ /* BPF expects NULL-terminated tcp-cc string */
+ optval[--(*optlen)] = '\0';
+ return do_tcp_getsockopt(sk, SOL_TCP, TCP_CONGESTION,
+ KERNEL_SOCKPTR(optval),
+ KERNEL_SOCKPTR(optlen));
+ }
+
+ /* "cdg" is the only cc that alloc a ptr
+ * in inet_csk_ca area. The bpf-tcp-cc may
+ * overwrite this ptr after switching to cdg.
+ */
+ if (*optlen >= sizeof("cdg") - 1 && !strncmp("cdg", optval, *optlen))
+ return -ENOTSUPP;
+
+ /* It stops this looping
+ *
+ * .init => bpf_setsockopt(tcp_cc) => .init =>
+ * bpf_setsockopt(tcp_cc)" => .init => ....
+ *
+ * The second bpf_setsockopt(tcp_cc) is not allowed
+ * in order to break the loop when both .init
+ * are the same bpf prog.
+ *
+ * This applies even the second bpf_setsockopt(tcp_cc)
+ * does not cause a loop. This limits only the first
+ * '.init' can call bpf_setsockopt(TCP_CONGESTION) to
+ * pick a fallback cc (eg. peer does not support ECN)
+ * and the second '.init' cannot fallback to
+ * another.
+ */
+ tp = tcp_sk(sk);
+ if (tp->bpf_chg_cc_inprogress)
+ return -EBUSY;
+
+ tp->bpf_chg_cc_inprogress = 1;
+ ret = do_tcp_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
+ KERNEL_SOCKPTR(optval), *optlen);
+ tp->bpf_chg_cc_inprogress = 0;
+ return ret;
+}
+
static int sol_tcp_sockopt(struct sock *sk, int optname,
char *optval, int *optlen,
bool getopt)
@@ -5124,9 +5178,7 @@ static int sol_tcp_sockopt(struct sock *sk, int optname,
return -EINVAL;
break;
case TCP_CONGESTION:
- if (*optlen < 2)
- return -EINVAL;
- break;
+ return sol_tcp_sockopt_congestion(sk, optval, optlen, getopt);
case TCP_SAVED_SYN:
if (*optlen < 1)
return -EINVAL;
@@ -5151,13 +5203,6 @@ static int sol_tcp_sockopt(struct sock *sk, int optname,
return 0;
}
- if (optname == TCP_CONGESTION) {
- if (!inet_csk(sk)->icsk_ca_ops)
- return -EINVAL;
- /* BPF expects NULL-terminated tcp-cc string */
- optval[--(*optlen)] = '\0';
- }
-
return do_tcp_getsockopt(sk, SOL_TCP, optname,
KERNEL_SOCKPTR(optval),
KERNEL_SOCKPTR(optlen));
@@ -5284,12 +5329,6 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname,
BPF_CALL_5(bpf_sk_setsockopt, struct sock *, sk, int, level,
int, optname, char *, optval, int, optlen)
{
- if (level == SOL_TCP && optname == TCP_CONGESTION) {
- if (optlen >= sizeof("cdg") - 1 &&
- !strncmp("cdg", optval, optlen))
- return -ENOTSUPP;
- }
-
return _bpf_setsockopt(sk, level, optname, optval, optlen);
}
@@ -8605,6 +8644,36 @@ static bool tc_cls_act_is_valid_access(int off, int size,
return bpf_skb_is_valid_access(off, size, type, prog, info);
}
+DEFINE_MUTEX(nf_conn_btf_access_lock);
+EXPORT_SYMBOL_GPL(nf_conn_btf_access_lock);
+
+int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct btf *btf,
+ const struct btf_type *t, int off, int size,
+ enum bpf_access_type atype, u32 *next_btf_id,
+ enum bpf_type_flag *flag);
+EXPORT_SYMBOL_GPL(nfct_btf_struct_access);
+
+static int tc_cls_act_btf_struct_access(struct bpf_verifier_log *log,
+ const struct btf *btf,
+ const struct btf_type *t, int off,
+ int size, enum bpf_access_type atype,
+ u32 *next_btf_id,
+ enum bpf_type_flag *flag)
+{
+ int ret = -EACCES;
+
+ if (atype == BPF_READ)
+ return btf_struct_access(log, btf, t, off, size, atype, next_btf_id,
+ flag);
+
+ mutex_lock(&nf_conn_btf_access_lock);
+ if (nfct_btf_struct_access)
+ ret = nfct_btf_struct_access(log, btf, t, off, size, atype, next_btf_id, flag);
+ mutex_unlock(&nf_conn_btf_access_lock);
+
+ return ret;
+}
+
static bool __is_valid_xdp_access(int off, int size)
{
if (off < 0 || off >= sizeof(struct xdp_md))
@@ -8664,6 +8733,27 @@ void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog,
}
EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);
+static int xdp_btf_struct_access(struct bpf_verifier_log *log,
+ const struct btf *btf,
+ const struct btf_type *t, int off,
+ int size, enum bpf_access_type atype,
+ u32 *next_btf_id,
+ enum bpf_type_flag *flag)
+{
+ int ret = -EACCES;
+
+ if (atype == BPF_READ)
+ return btf_struct_access(log, btf, t, off, size, atype, next_btf_id,
+ flag);
+
+ mutex_lock(&nf_conn_btf_access_lock);
+ if (nfct_btf_struct_access)
+ ret = nfct_btf_struct_access(log, btf, t, off, size, atype, next_btf_id, flag);
+ mutex_unlock(&nf_conn_btf_access_lock);
+
+ return ret;
+}
+
static bool sock_addr_is_valid_access(int off, int size,
enum bpf_access_type type,
const struct bpf_prog *prog,
@@ -10558,6 +10648,7 @@ const struct bpf_verifier_ops tc_cls_act_verifier_ops = {
.convert_ctx_access = tc_cls_act_convert_ctx_access,
.gen_prologue = tc_cls_act_prologue,
.gen_ld_abs = bpf_gen_ld_abs,
+ .btf_struct_access = tc_cls_act_btf_struct_access,
};
const struct bpf_prog_ops tc_cls_act_prog_ops = {
@@ -10569,6 +10660,7 @@ const struct bpf_verifier_ops xdp_verifier_ops = {
.is_valid_access = xdp_is_valid_access,
.convert_ctx_access = xdp_convert_ctx_access,
.gen_prologue = bpf_noop_prologue,
+ .btf_struct_access = xdp_btf_struct_access,
};
const struct bpf_prog_ops xdp_prog_ops = {
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 188f8558d27d..ca70525621c7 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -434,8 +434,10 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
if (copied + copy > len)
copy = len - copied;
copy = copy_page_to_iter(page, sge->offset, copy, iter);
- if (!copy)
- return copied ? copied : -EFAULT;
+ if (!copy) {
+ copied = copied ? copied : -EFAULT;
+ goto out;
+ }
copied += copy;
if (likely(!peek)) {
@@ -455,7 +457,7 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
* didn't copy the entire length lets just break.
*/
if (copy != sge->length)
- return copied;
+ goto out;
sk_msg_iter_var_next(i);
}
@@ -477,7 +479,9 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
}
msg_rx = sk_psock_peek_msg(psock);
}
-
+out:
+ if (psock->work_state.skb && copied > 0)
+ schedule_work(&psock->work);
return copied;
}
EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
diff --git a/net/core/stream.c b/net/core/stream.c
index ccc083cdef23..1105057ce00a 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -159,7 +159,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
*timeo_p = current_timeo;
}
out:
- remove_wait_queue(sk_sleep(sk), &wait);
+ if (!sock_flag(sk, SOCK_DEAD))
+ remove_wait_queue(sk_sleep(sk), &wait);
return err;
do_error:
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 85a9e500c42d..6da16ae6a962 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -124,7 +124,7 @@ static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log,
return -EACCES;
}
- return NOT_INIT;
+ return 0;
}
BPF_CALL_2(bpf_tcp_send_ack, struct tcp_sock *, tp, u32, rcv_nxt)
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index b83c2bd9d722..517042caf6dc 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -33,6 +33,7 @@
#include <linux/skbuff.h>
#include <linux/proc_fs.h>
#include <linux/export.h>
+#include <linux/bpf-cgroup.h>
#include <net/sock.h>
#include <net/ping.h>
#include <net/udp.h>
@@ -295,6 +296,19 @@ void ping_close(struct sock *sk, long timeout)
}
EXPORT_SYMBOL_GPL(ping_close);
+static int ping_pre_connect(struct sock *sk, struct sockaddr *uaddr,
+ int addr_len)
+{
+ /* This check is replicated from __ip4_datagram_connect() and
+ * intended to prevent BPF program called below from accessing bytes
+ * that are out of the bound specified by user in addr_len.
+ */
+ if (addr_len < sizeof(struct sockaddr_in))
+ return -EINVAL;
+
+ return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr);
+}
+
/* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */
static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
struct sockaddr *uaddr, int addr_len)
@@ -1009,6 +1023,7 @@ struct proto ping_prot = {
.owner = THIS_MODULE,
.init = ping_init_sock,
.close = ping_close,
+ .pre_connect = ping_pre_connect,
.connect = ip4_datagram_connect,
.disconnect = __udp_disconnect,
.setsockopt = ip_setsockopt,
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 442838ab0253..79f30f026d89 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -561,6 +561,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
newtp->fastopen_req = NULL;
RCU_INIT_POINTER(newtp->fastopen_rsk, NULL);
+ newtp->bpf_chg_cc_inprogress = 0;
tcp_bpf_clone(sk, newsk);
__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 91b840514656..5f2ef8493714 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -20,6 +20,7 @@
#include <net/udp.h>
#include <net/transp_v6.h>
#include <linux/proc_fs.h>
+#include <linux/bpf-cgroup.h>
#include <net/ping.h>
static void ping_v6_destroy(struct sock *sk)
@@ -49,6 +50,20 @@ static int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
return 0;
}
+static int ping_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
+ int addr_len)
+{
+ /* This check is replicated from __ip6_datagram_connect() and
+ * intended to prevent BPF program called below from accessing
+ * bytes that are out of the bound specified by user in addr_len.
+ */
+
+ if (addr_len < SIN6_LEN_RFC2133)
+ return -EINVAL;
+
+ return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr);
+}
+
static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
struct inet_sock *inet = inet_sk(sk);
@@ -191,6 +206,7 @@ struct proto pingv6_prot = {
.init = ping_init_sock,
.close = ping_close,
.destroy = ping_v6_destroy,
+ .pre_connect = ping_v6_pre_connect,
.connect = ip6_datagram_connect_v6_only,
.disconnect = __udp_disconnect,
.setsockopt = ipv6_setsockopt,
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 06df49ea6329..0f060d100880 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -60,6 +60,12 @@ obj-$(CONFIG_NF_NAT) += nf_nat.o
nf_nat-$(CONFIG_NF_NAT_REDIRECT) += nf_nat_redirect.o
nf_nat-$(CONFIG_NF_NAT_MASQUERADE) += nf_nat_masquerade.o
+ifeq ($(CONFIG_NF_NAT),m)
+nf_nat-$(CONFIG_DEBUG_INFO_BTF_MODULES) += nf_nat_bpf.o
+else ifeq ($(CONFIG_NF_NAT),y)
+nf_nat-$(CONFIG_DEBUG_INFO_BTF) += nf_nat_bpf.o
+endif
+
# NAT helpers
obj-$(CONFIG_NF_NAT_AMANDA) += nf_nat_amanda.o
obj-$(CONFIG_NF_NAT_FTP) += nf_nat_ftp.o
diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c
index 1cd87b28c9b0..8639e7efd0e2 100644
--- a/net/netfilter/nf_conntrack_bpf.c
+++ b/net/netfilter/nf_conntrack_bpf.c
@@ -6,12 +6,14 @@
* are exposed through to BPF programs is explicitly unstable.
*/
+#include <linux/bpf_verifier.h>
#include <linux/bpf.h>
#include <linux/btf.h>
+#include <linux/filter.h>
+#include <linux/mutex.h>
#include <linux/types.h>
#include <linux/btf_ids.h>
#include <linux/net_namespace.h>
-#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_bpf.h>
#include <net/netfilter/nf_conntrack_core.h>
@@ -134,7 +136,6 @@ __bpf_nf_ct_alloc_entry(struct net *net, struct bpf_sock_tuple *bpf_tuple,
memset(&ct->proto, 0, sizeof(ct->proto));
__nf_ct_set_timeout(ct, timeout * HZ);
- ct->status |= IPS_CONFIRMED;
out:
if (opts->netns_id >= 0)
@@ -184,14 +185,58 @@ static struct nf_conn *__bpf_nf_ct_lookup(struct net *net,
return ct;
}
+BTF_ID_LIST(btf_nf_conn_ids)
+BTF_ID(struct, nf_conn)
+BTF_ID(struct, nf_conn___init)
+
+/* Check writes into `struct nf_conn` */
+static int _nf_conntrack_btf_struct_access(struct bpf_verifier_log *log,
+ const struct btf *btf,
+ const struct btf_type *t, int off,
+ int size, enum bpf_access_type atype,
+ u32 *next_btf_id,
+ enum bpf_type_flag *flag)
+{
+ const struct btf_type *ncit;
+ const struct btf_type *nct;
+ size_t end;
+
+ ncit = btf_type_by_id(btf, btf_nf_conn_ids[1]);
+ nct = btf_type_by_id(btf, btf_nf_conn_ids[0]);
+
+ if (t != nct && t != ncit) {
+ bpf_log(log, "only read is supported\n");
+ return -EACCES;
+ }
+
+ /* `struct nf_conn` and `struct nf_conn___init` have the same layout
+ * so we are safe to simply merge offset checks here
+ */
+ switch (off) {
+#if defined(CONFIG_NF_CONNTRACK_MARK)
+ case offsetof(struct nf_conn, mark):
+ end = offsetofend(struct nf_conn, mark);
+ break;
+#endif
+ default:
+ bpf_log(log, "no write support to nf_conn at off %d\n", off);
+ return -EACCES;
+ }
+
+ if (off + size > end) {
+ bpf_log(log,
+ "write access at off %d with size %d beyond the member of nf_conn ended at %zu\n",
+ off, size, end);
+ return -EACCES;
+ }
+
+ return 0;
+}
+
__diag_push();
__diag_ignore_all("-Wmissing-prototypes",
"Global functions as their definitions will be in nf_conntrack BTF");
-struct nf_conn___init {
- struct nf_conn ct;
-};
-
/* bpf_xdp_ct_alloc - Allocate a new CT entry
*
* Parameters:
@@ -339,6 +384,7 @@ struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i)
struct nf_conn *nfct = (struct nf_conn *)nfct_i;
int err;
+ nfct->status |= IPS_CONFIRMED;
err = nf_conntrack_hash_check_insert(nfct);
if (err < 0) {
nf_conntrack_free(nfct);
@@ -449,5 +495,19 @@ int register_nf_conntrack_bpf(void)
int ret;
ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &nf_conntrack_kfunc_set);
- return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &nf_conntrack_kfunc_set);
+ ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &nf_conntrack_kfunc_set);
+ if (!ret) {
+ mutex_lock(&nf_conn_btf_access_lock);
+ nfct_btf_struct_access = _nf_conntrack_btf_struct_access;
+ mutex_unlock(&nf_conn_btf_access_lock);
+ }
+
+ return ret;
+}
+
+void cleanup_nf_conntrack_bpf(void)
+{
+ mutex_lock(&nf_conn_btf_access_lock);
+ nfct_btf_struct_access = NULL;
+ mutex_unlock(&nf_conn_btf_access_lock);
}
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 8208a28ea342..f97bda06d2a9 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -2516,6 +2516,7 @@ static int kill_all(struct nf_conn *i, void *data)
void nf_conntrack_cleanup_start(void)
{
+ cleanup_nf_conntrack_bpf();
conntrack_gc_work.exiting = true;
}
diff --git a/net/netfilter/nf_nat_bpf.c b/net/netfilter/nf_nat_bpf.c
new file mode 100644
index 000000000000..0fa5a0bbb0ff
--- /dev/null
+++ b/net/netfilter/nf_nat_bpf.c
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Unstable NAT Helpers for XDP and TC-BPF hook
+ *
+ * These are called from the XDP and SCHED_CLS BPF programs. Note that it is
+ * allowed to break compatibility for these functions since the interface they
+ * are exposed through to BPF programs is explicitly unstable.
+ */
+
+#include <linux/bpf.h>
+#include <linux/btf_ids.h>
+#include <net/netfilter/nf_conntrack_bpf.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_nat.h>
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+ "Global functions as their definitions will be in nf_nat BTF");
+
+/* bpf_ct_set_nat_info - Set source or destination nat address
+ *
+ * Set source or destination nat address of the newly allocated
+ * nf_conn before insertion. This must be invoked for referenced
+ * PTR_TO_BTF_ID to nf_conn___init.
+ *
+ * Parameters:
+ * @nfct - Pointer to referenced nf_conn object, obtained using
+ * bpf_xdp_ct_alloc or bpf_skb_ct_alloc.
+ * @addr - Nat source/destination address
+ * @port - Nat source/destination port. Non-positive values are
+ * interpreted as select a random port.
+ * @manip - NF_NAT_MANIP_SRC or NF_NAT_MANIP_DST
+ */
+int bpf_ct_set_nat_info(struct nf_conn___init *nfct,
+ union nf_inet_addr *addr, int port,
+ enum nf_nat_manip_type manip)
+{
+ struct nf_conn *ct = (struct nf_conn *)nfct;
+ u16 proto = nf_ct_l3num(ct);
+ struct nf_nat_range2 range;
+
+ if (proto != NFPROTO_IPV4 && proto != NFPROTO_IPV6)
+ return -EINVAL;
+
+ memset(&range, 0, sizeof(struct nf_nat_range2));
+ range.flags = NF_NAT_RANGE_MAP_IPS;
+ range.min_addr = *addr;
+ range.max_addr = range.min_addr;
+ if (port > 0) {
+ range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
+ range.min_proto.all = cpu_to_be16(port);
+ range.max_proto.all = range.min_proto.all;
+ }
+
+ return nf_nat_setup_info(ct, &range, manip) == NF_DROP ? -ENOMEM : 0;
+}
+
+__diag_pop()
+
+BTF_SET8_START(nf_nat_kfunc_set)
+BTF_ID_FLAGS(func, bpf_ct_set_nat_info, KF_TRUSTED_ARGS)
+BTF_SET8_END(nf_nat_kfunc_set)
+
+static const struct btf_kfunc_id_set nf_bpf_nat_kfunc_set = {
+ .owner = THIS_MODULE,
+ .set = &nf_nat_kfunc_set,
+};
+
+int register_nf_nat_bpf(void)
+{
+ int ret;
+
+ ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP,
+ &nf_bpf_nat_kfunc_set);
+ if (ret)
+ return ret;
+
+ return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS,
+ &nf_bpf_nat_kfunc_set);
+}
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 7981be526f26..d8e6380f6337 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -16,7 +16,7 @@
#include <linux/siphash.h>
#include <linux/rtnetlink.h>
-#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_bpf.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_seqadj.h>
@@ -1152,7 +1152,7 @@ static int __init nf_nat_init(void)
WARN_ON(nf_nat_hook != NULL);
RCU_INIT_POINTER(nf_nat_hook, &nat_hook);
- return 0;
+ return register_nf_nat_bpf();
}
static void __exit nf_nat_cleanup(void)