summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
authorJakub Kicinski <kuba@kernel.org>2022-10-03 23:02:48 +0300
committerJakub Kicinski <kuba@kernel.org>2022-10-03 23:02:49 +0300
commita08d97a1935bee66b099b21feddad19c1fd90d0e (patch)
treeb11aaa5e616432f1012c7c738f12ab64dacef9b2 /net/core
parent62c07983bef9d3e78e71189441e1a470f0d1e653 (diff)
parent820dc0523e05c12810bb6bf4e56ce26e4c1948a2 (diff)
downloadlinux-a08d97a1935bee66b099b21feddad19c1fd90d0e.tar.xz
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/core')
-rw-r--r--net/core/filter.c124
-rw-r--r--net/core/skmsg.c12
-rw-r--r--net/core/stream.c3
3 files changed, 118 insertions, 21 deletions
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: