[PATCH AUTOSEL 5.15 10/69] bpf, sockmap: Fix sk->sk_forward_alloc warn_on in sk_stream_kill_queues

[PATCH AUTOSEL 5.15 10/69] bpf, sockmap: Fix sk->sk_forward_alloc warn_on in sk_stream_kill_queues

[Sasha Levin]

From: Wang Yufen <wangyufen@huawei.com>

[ Upstream commit d8616ee2affcff37c5d315310da557a694a3303d ]

During TCP sockmap redirect pressure test, the following warning is triggered:

WARNING: CPU: 3 PID: 2145 at net/core/stream.c:205 sk_stream_kill_queues+0xbc/0xd0
CPU: 3 PID: 2145 Comm: iperf Kdump: loaded Tainted: G        W         5.10.0+ #9
Call Trace:
 inet_csk_destroy_sock+0x55/0x110
 inet_csk_listen_stop+0xbb/0x380
 tcp_close+0x41b/0x480
 inet_release+0x42/0x80
 __sock_release+0x3d/0xa0
 sock_close+0x11/0x20
 __fput+0x9d/0x240
 task_work_run+0x62/0x90
 exit_to_user_mode_prepare+0x110/0x120
 syscall_exit_to_user_mode+0x27/0x190
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

The reason we observed is that:

When the listener is closing, a connection may have completed the three-way
handshake but not accepted, and the client has sent some packets. The child
sks in accept queue release by inet_child_forget()->inet_csk_destroy_sock(),
but psocks of child sks have not released.

To fix, add sock_map_destroy to release psocks.

Signed-off-by: Wang Yufen <wangyufen@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20220524075311.649153-1-wangyufen@huawei.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/bpf.h   |  1 +
 include/linux/skmsg.h |  1 +
 net/core/skmsg.c      |  1 +
 net/core/sock_map.c   | 23 +++++++++++++++++++++++
 net/ipv4/tcp_bpf.c    |  1 +
 5 files changed, 27 insertions(+)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 818cd594e922..84efd8dd139d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2022,6 +2022,7 @@ int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog);
 int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
 int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags);
 void sock_map_unhash(struct sock *sk);
+void sock_map_destroy(struct sock *sk);
 void sock_map_close(struct sock *sk, long timeout);
 #else
 static inline int bpf_prog_offload_init(struct bpf_prog *prog,
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 73bedd128d52..ad3b798d9944 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -96,6 +96,7 @@ struct sk_psock {
 	spinlock_t			link_lock;
 	refcount_t			refcnt;
 	void (*saved_unhash)(struct sock *sk);
+	void (*saved_destroy)(struct sock *sk);
 	void (*saved_close)(struct sock *sk, long timeout);
 	void (*saved_write_space)(struct sock *sk);
 	void (*saved_data_ready)(struct sock *sk);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index ede0af308f40..2742d8e4dd82 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -716,6 +716,7 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
 	psock->eval = __SK_NONE;
 	psock->sk_proto = prot;
 	psock->saved_unhash = prot->unhash;
+	psock->saved_destroy = prot->destroy;
 	psock->saved_close = prot->close;
 	psock->saved_write_space = sk->sk_write_space;
 
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 6351b6af7aca..d846ed9c5855 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -1506,6 +1506,29 @@ void sock_map_unhash(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(sock_map_unhash);
 
+void sock_map_destroy(struct sock *sk)
+{
+	void (*saved_destroy)(struct sock *sk);
+	struct sk_psock *psock;
+
+	rcu_read_lock();
+	psock = sk_psock_get(sk);
+	if (unlikely(!psock)) {
+		rcu_read_unlock();
+		if (sk->sk_prot->destroy)
+			sk->sk_prot->destroy(sk);
+		return;
+	}
+
+	saved_destroy = psock->saved_destroy;
+	sock_map_remove_links(sk, psock);
+	rcu_read_unlock();
+	sk_psock_stop(psock, true);
+	sk_psock_put(sk, psock);
+	saved_destroy(sk);
+}
+EXPORT_SYMBOL_GPL(sock_map_destroy);
+
 void sock_map_close(struct sock *sk, long timeout)
 {
 	void (*saved_close)(struct sock *sk, long timeout);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 2c597a4e429a..25e83d35138b 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -541,6 +541,7 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
 				   struct proto *base)
 {
 	prot[TCP_BPF_BASE]			= *base;
+	prot[TCP_BPF_BASE].destroy		= sock_map_destroy;
 	prot[TCP_BPF_BASE].close		= sock_map_close;
 	prot[TCP_BPF_BASE].recvmsg		= tcp_bpf_recvmsg;
 	prot[TCP_BPF_BASE].sock_is_readable	= sk_msg_is_readable;
-- 
2.35.1

[PATCH AUTOSEL 5.15 14/69] libbpf: Fix an error in 64bit relocation value computation

[Sasha Levin]

From: Yonghong Song <yhs@fb.com>

[ Upstream commit b58b2b3a31228bd9aaed9b96e9452dafd0d46024 ]

Currently, the 64bit relocation value in the instruction
is computed as follows:
  __u64 imm = insn[0].imm + ((__u64)insn[1].imm << 32)

Suppose insn[0].imm = -1 (0xffffffff) and insn[1].imm = 1.
With the above computation, insn[0].imm will first sign-extend
to 64bit -1 (0xffffffffFFFFFFFF) and then add 0x1FFFFFFFF,
producing incorrect value 0xFFFFFFFF. The correct value
should be 0x1FFFFFFFF.

Changing insn[0].imm to __u32 first will prevent 64bit sign
extension and fix the issue. Merging high and low 32bit values
also changed from '+' to '|' to be consistent with other
similar occurences in kernel and libbpf.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20220607062610.3717378-1-yhs@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/lib/bpf/relo_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c
index 4016ed492d0c..1d65b47c0779 100644
--- a/tools/lib/bpf/relo_core.c
+++ b/tools/lib/bpf/relo_core.c
@@ -1015,7 +1015,7 @@ static int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn,
 			return -EINVAL;
 		}
 
-		imm = insn[0].imm + ((__u64)insn[1].imm << 32);
+		imm = (__u32)insn[0].imm | ((__u64)insn[1].imm << 32);
 		if (res->validate && imm != orig_val) {
 			pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDIMM64) value: got %llu, exp %u -> %u\n",
 				prog_name, relo_idx,
-- 
2.35.1

[PATCH AUTOSEL 5.15 31/69] uprobe: gate bpf call behind BPF_EVENTS

[Sasha Levin]

From: Delyan Kratunov <delyank@fb.com>

[ Upstream commit aca80dd95e20f1fa0daa212afc83c9fa0ad239e5 ]

The call into bpf from uprobes needs to be gated now that it doesn't use
the trace_events.h helpers.

Randy found this as a randconfig build failure on linux-next [1].

  [1]: https://lore.kernel.org/linux-next/2de99180-7d55-2fdf-134d-33198c27cc58@infradead.org/

Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Delyan Kratunov <delyank@fb.com>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/cb8bfbbcde87ed5d811227a393ef4925f2aadb7b.camel@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/trace/trace_uprobe.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 78ec1c16ccf4..798c99994e2a 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1352,6 +1352,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 	int size, esize;
 	int rctx;
 
+#ifdef CONFIG_BPF_EVENTS
 	if (bpf_prog_array_valid(call)) {
 		u32 ret;
 
@@ -1361,6 +1362,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 		if (!ret)
 			return;
 	}
+#endif /* CONFIG_BPF_EVENTS */
 
 	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
 
-- 
2.35.1

[PATCH AUTOSEL 5.15 49/69] libbpf: Disable SEC pragma macro on GCC

[Sasha Levin]

From: James Hilliard <james.hilliard1@gmail.com>

[ Upstream commit 18410251f66aee7e82234073ce6656ca20a732a9 ]

It seems the gcc preprocessor breaks with pragmas when surrounding
__attribute__.

Disable these pragmas on GCC due to upstream bugs see:
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=55578
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90400

Fixes errors like:
error: expected identifier or '(' before '#pragma'
  106 | SEC("cgroup/bind6")
      | ^~~

error: expected '=', ',', ';', 'asm' or '__attribute__' before '#pragma'
  114 | char _license[] SEC("license") = "GPL";
      | ^~~

Signed-off-by: James Hilliard <james.hilliard1@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220706111839.1247911-1-james.hilliard1@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/lib/bpf/bpf_helpers.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index b9987c3efa3c..409b85d1cbd0 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -30,12 +30,25 @@
  * To allow use of SEC() with externs (e.g., for extern .maps declarations),
  * make sure __attribute__((unused)) doesn't trigger compilation warning.
  */
+#if __GNUC__ && !__clang__
+
+/*
+ * Pragma macros are broken on GCC
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=55578
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90400
+ */
+#define SEC(name) __attribute__((section(name), used))
+
+#else
+
 #define SEC(name) \
 	_Pragma("GCC diagnostic push")					    \
 	_Pragma("GCC diagnostic ignored \"-Wignored-attributes\"")	    \
 	__attribute__((section(name), used))				    \
 	_Pragma("GCC diagnostic pop")					    \
 
+#endif
+
 /* Avoid 'linux/stddef.h' definition of '__always_inline'. */
 #undef __always_inline
 #define __always_inline inline __attribute__((always_inline))
-- 
2.35.1

[PATCH AUTOSEL 5.15 52/69] bpf: Fix check against plain integer v 'NULL'

[Sasha Levin]

From: Ben Dooks <ben.dooks@sifive.com>

[ Upstream commit a2a5580fcbf808e7c2310e4959b62f9d2157fdb6 ]

When checking with sparse, btf_show_type_value() is causing a
warning about checking integer vs NULL when the macro is passed
a pointer, due to the 'value != 0' check. Stop sparse complaining
about any type-casting by adding a cast to the typeof(value).

This fixes the following sparse warnings:

kernel/bpf/btf.c:2579:17: warning: Using plain integer as NULL pointer
kernel/bpf/btf.c:2581:17: warning: Using plain integer as NULL pointer
kernel/bpf/btf.c:3407:17: warning: Using plain integer as NULL pointer
kernel/bpf/btf.c:3758:9: warning: Using plain integer as NULL pointer

Signed-off-by: Ben Dooks <ben.dooks@sifive.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20220714100322.260467-1-ben.dooks@sifive.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/btf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 3cfba41a0829..cf89c99d4f28 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1013,7 +1013,8 @@ __printf(2, 3) static void btf_show(struct btf_show *show, const char *fmt, ...)
  */
 #define btf_show_type_value(show, fmt, value)				       \
 	do {								       \
-		if ((value) != 0 || (show->flags & BTF_SHOW_ZERO) ||	       \
+		if ((value) != (__typeof__(value))0 ||			       \
+		    (show->flags & BTF_SHOW_ZERO) ||			       \
 		    show->state.depth == 0) {				       \
 			btf_show(show, "%s%s" fmt "%s%s",		       \
 				 btf_show_indent(show),			       \
-- 
2.35.1

[PATCH AUTOSEL 5.15 54/69] bpf: Don't redirect packets with invalid pkt_len

[Sasha Levin]

From: Zhengchao Shao <shaozhengchao@huawei.com>

[ Upstream commit fd1894224407c484f652ad456e1ce423e89bb3eb ]

Syzbot found an issue [1]: fq_codel_drop() try to drop a flow whitout any
skbs, that is, the flow->head is null.
The root cause, as the [2] says, is because that bpf_prog_test_run_skb()
run a bpf prog which redirects empty skbs.
So we should determine whether the length of the packet modified by bpf
prog or others like bpf_prog_test is valid before forwarding it directly.

LINK: [1] https://syzkaller.appspot.com/bug?id=0b84da80c2917757915afa89f7738a9d16ec96c5
LINK: [2] https://www.spinics.net/lists/netdev/msg777503.html

Reported-by: syzbot+7a12909485b94426aceb@syzkaller.appspotmail.com
Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20220715115559.139691-1-shaozhengchao@huawei.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/skbuff.h | 8 ++++++++
 net/bpf/test_run.c     | 3 +++
 net/core/dev.c         | 1 +
 3 files changed, 12 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index cbd719e5329a..ae598ed86b50 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2328,6 +2328,14 @@ static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset)
 
 #endif /* NET_SKBUFF_DATA_USES_OFFSET */
 
+static inline void skb_assert_len(struct sk_buff *skb)
+{
+#ifdef CONFIG_DEBUG_NET
+	if (WARN_ONCE(!skb->len, "%s\n", __func__))
+		DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false);
+#endif /* CONFIG_DEBUG_NET */
+}
+
 /*
  *	Add data to an sk_buff
  */
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 655ee0e2de86..a9fb16b9c735 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -469,6 +469,9 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb)
 {
 	struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb;
 
+	if (!skb->len)
+		return -EINVAL;
+
 	if (!__skb)
 		return 0;
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 12b1811cb488..89a7528dfce2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4147,6 +4147,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	bool again = false;
 
 	skb_reset_mac_header(skb);
+	skb_assert_len(skb);
 
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP))
 		__skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED);
-- 
2.35.1

[PATCH AUTOSEL 5.15 59/69] bpf/selftests: Fix couldn't retrieve pinned program in xdp veth test

[Sasha Levin]

From: Jie2x Zhou <jie2x.zhou@intel.com>

[ Upstream commit f664f9c6b4a1bb9a10af812df0fbbf6aac28fcc6 ]

Before change:

  selftests: bpf: test_xdp_veth.sh
  Couldn't retrieve pinned program '/sys/fs/bpf/test_xdp_veth/progs/redirect_map_0': No such file or directory
  selftests: xdp_veth [SKIP]
  ok 20 selftests: bpf: test_xdp_veth.sh # SKIP

After change:

  PING 10.1.1.33 (10.1.1.33) 56(84) bytes of data.
  64 bytes from 10.1.1.33: icmp_seq=1 ttl=64 time=0.320 ms
  --- 10.1.1.33 ping statistics ---
  1 packets transmitted, 1 received, 0% packet loss, time 0ms
  rtt min/avg/max/mdev = 0.320/0.320/0.320/0.000 ms
  selftests: xdp_veth [PASS]

For the test case, the following can be found:

  ls /sys/fs/bpf/test_xdp_veth/progs/redirect_map_0
  ls: cannot access '/sys/fs/bpf/test_xdp_veth/progs/redirect_map_0': No such file or directory
  ls /sys/fs/bpf/test_xdp_veth/progs/
  xdp_redirect_map_0  xdp_redirect_map_1  xdp_redirect_map_2

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Jie2x Zhou <jie2x.zhou@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220719082430.9916-1-jie2x.zhou@intel.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/test_xdp_veth.sh | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_xdp_veth.sh b/tools/testing/selftests/bpf/test_xdp_veth.sh
index a3a1eaee26ea..73a9e1b22290 100755
--- a/tools/testing/selftests/bpf/test_xdp_veth.sh
+++ b/tools/testing/selftests/bpf/test_xdp_veth.sh
@@ -103,9 +103,9 @@ bpftool prog loadall \
 bpftool map update pinned $BPF_DIR/maps/tx_port key 0 0 0 0 value 122 0 0 0
 bpftool map update pinned $BPF_DIR/maps/tx_port key 1 0 0 0 value 133 0 0 0
 bpftool map update pinned $BPF_DIR/maps/tx_port key 2 0 0 0 value 111 0 0 0
-ip link set dev veth1 xdp pinned $BPF_DIR/progs/redirect_map_0
-ip link set dev veth2 xdp pinned $BPF_DIR/progs/redirect_map_1
-ip link set dev veth3 xdp pinned $BPF_DIR/progs/redirect_map_2
+ip link set dev veth1 xdp pinned $BPF_DIR/progs/xdp_redirect_map_0
+ip link set dev veth2 xdp pinned $BPF_DIR/progs/xdp_redirect_map_1
+ip link set dev veth3 xdp pinned $BPF_DIR/progs/xdp_redirect_map_2
 
 ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp
 ip -n ns2 link set dev veth22 xdp obj xdp_tx.o sec xdp
-- 
2.35.1