[PATCH AUTOSEL 5.19 010/105] bpf, sockmap: Fix sk->sk_forward_alloc warn_on in sk_stream_kill_queues

[PATCH AUTOSEL 5.19 010/105] 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 2b914a56a2c5..8e6092d0ea95 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2104,6 +2104,7 @@ int sock_map_bpf_prog_query(const union bpf_attr *attr,
 			    union bpf_attr __user *uattr);
 
 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 c5a2d6f50f25..153b6dec9b6a 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -95,6 +95,7 @@ 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 b0fcd0200e84..fc69154bbc88 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -720,6 +720,7 @@ 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 81d4b4756a02..9f08ccfaf6da 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -1561,6 +1561,29 @@ 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 0d3f68bb51c0..a1626afe87a1 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -540,6 +540,7 @@ 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 5.19 014/105] 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 ba4453dfd1ed..a9216b65724a 100644
--- a/tools/lib/bpf/relo_core.c
+++ b/tools/lib/bpf/relo_core.c
@@ -1024,7 +1024,7 @@ 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 5.19 024/105] selftests/bpf: Avoid skipping certain subtests

[Sasha Levin]

From: Yonghong Song <yhs@fb.com>

[ Upstream commit 3831cd1f9ff627734096f22d8e37f72a5cabf92e ]

Commit 704c91e59fe0 ('selftests/bpf: Test "bpftool gen min_core_btf"')
added a test test_core_btfgen to test core relocation with btf
generated with 'bpftool gen min_core_btf'. Currently,
among 76 subtests, 25 are skipped.

  ...
  #46/69   core_reloc_btfgen/enumval:OK
  #46/70   core_reloc_btfgen/enumval___diff:OK
  #46/71   core_reloc_btfgen/enumval___val3_missing:OK
  #46/72   core_reloc_btfgen/enumval___err_missing:SKIP
  #46/73   core_reloc_btfgen/enum64val:OK
  #46/74   core_reloc_btfgen/enum64val___diff:OK
  #46/75   core_reloc_btfgen/enum64val___val3_missing:OK
  #46/76   core_reloc_btfgen/enum64val___err_missing:SKIP
  ...
  #46      core_reloc_btfgen:SKIP
  Summary: 1/51 PASSED, 25 SKIPPED, 0 FAILED

Alexei found that in the above core_reloc_btfgen/enum64val___err_missing
should not be skipped.

Currently, the core_reloc tests have some negative tests.
In Commit 704c91e59fe0, for core_reloc_btfgen, all negative tests
are skipped with the following condition
  if (!test_case->btf_src_file || test_case->fails) {
	test__skip();
	continue;
  }
This is too conservative. Negative tests do not fail
mkstemp() and run_btfgen() should not be skipped.
There are a few negative tests indeed failing run_btfgen()
and this patch added 'run_btfgen_fails' to mark these tests
so that they can be skipped for btfgen tests. With this,
we have
  ...
  #46/69   core_reloc_btfgen/enumval:OK
  #46/70   core_reloc_btfgen/enumval___diff:OK
  #46/71   core_reloc_btfgen/enumval___val3_missing:OK
  #46/72   core_reloc_btfgen/enumval___err_missing:OK
  #46/73   core_reloc_btfgen/enum64val:OK
  #46/74   core_reloc_btfgen/enum64val___diff:OK
  #46/75   core_reloc_btfgen/enum64val___val3_missing:OK
  #46/76   core_reloc_btfgen/enum64val___err_missing:OK
  ...
  Summary: 1/62 PASSED, 14 SKIPPED, 0 FAILED

Totally 14 subtests are skipped instead of 25.

Reported-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20220614055526.628299-1-yhs@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/core_reloc.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 3712dfe1be59..ed85abd6782c 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -84,6 +84,7 @@ static int duration = 0;
 #define NESTING_ERR_CASE(name) {					\
 	NESTING_CASE_COMMON(name),					\
 	.fails = true,							\
+	.run_btfgen_fails = true,							\
 }
 
 #define ARRAYS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) {	\
@@ -258,12 +259,14 @@ static int duration = 0;
 	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_probed.o",	\
 			      "probed:", name),				\
 	.fails = true,							\
+	.run_btfgen_fails = true,							\
 	.raw_tp_name = "sys_enter",					\
 	.prog_name = "test_core_bitfields",				\
 }, {									\
 	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.o",	\
 			      "direct:", name),				\
 	.fails = true,							\
+	.run_btfgen_fails = true,							\
 	.prog_name = "test_core_bitfields_direct",			\
 }
 
@@ -304,6 +307,7 @@ static int duration = 0;
 #define SIZE_ERR_CASE(name) {						\
 	SIZE_CASE_COMMON(name),						\
 	.fails = true,							\
+	.run_btfgen_fails = true,							\
 }
 
 #define TYPE_BASED_CASE_COMMON(name)					\
@@ -377,6 +381,7 @@ struct core_reloc_test_case {
 	const char *output;
 	int output_len;
 	bool fails;
+	bool run_btfgen_fails;
 	bool needs_testmod;
 	bool relaxed_core_relocs;
 	const char *prog_name;
@@ -894,7 +899,7 @@ static void run_core_reloc_tests(bool use_btfgen)
 		/* generate a "minimal" BTF file and use it as source */
 		if (use_btfgen) {
 
-			if (!test_case->btf_src_file || test_case->fails) {
+			if (!test_case->btf_src_file || test_case->run_btfgen_fails) {
 				test__skip();
 				continue;
 			}
-- 
2.35.1

[PATCH AUTOSEL 5.19 039/105] 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 c3dc4f859a6b..687520c675fd 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1342,6 +1342,7 @@ 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;
 
@@ -1351,6 +1352,7 @@ 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 5.19 053/105] libbpf: fix up few libbpf.map problems

[Sasha Levin]

From: Andrii Nakryiko <andrii@kernel.org>

[ Upstream commit ab9a5a05dc480f8994eddd31093a8920b08ee71d ]

Seems like we missed to add 2 APIs to libbpf.map and another API was
misspelled. Fix it in libbpf.map.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20220627211527.2245459-16-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/lib/bpf/libbpf.map      | 3 ++-
 tools/lib/bpf/libbpf_legacy.h | 4 ++--
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 52973cffc20c..b6592c93a9d4 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -434,10 +434,11 @@ LIBBPF_0.7.0 {
 		bpf_xdp_detach;
 		bpf_xdp_query;
 		bpf_xdp_query_id;
+		btf_ext__raw_data;
 		libbpf_probe_bpf_helper;
 		libbpf_probe_bpf_map_type;
 		libbpf_probe_bpf_prog_type;
-		libbpf_set_memlock_rlim_max;
+		libbpf_set_memlock_rlim;
 } LIBBPF_0.6.0;
 
 LIBBPF_0.8.0 {
diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h
index d7bcbd01f66f..a3503c02e4a9 100644
--- a/tools/lib/bpf/libbpf_legacy.h
+++ b/tools/lib/bpf/libbpf_legacy.h
@@ -71,8 +71,8 @@ enum libbpf_strict_mode {
 	 * first BPF program or map creation operation. This is done only if
 	 * kernel is too old to support memcg-based memory accounting for BPF
 	 * subsystem. By default, RLIMIT_MEMLOCK limit is set to RLIM_INFINITY,
-	 * but it can be overriden with libbpf_set_memlock_rlim_max() API.
-	 * Note that libbpf_set_memlock_rlim_max() needs to be called before
+	 * but it can be overriden with libbpf_set_memlock_rlim() API.
+	 * Note that libbpf_set_memlock_rlim() needs to be called before
 	 * the very first bpf_prog_load(), bpf_map_create() or bpf_object__load()
 	 * operation.
 	 */
-- 
2.35.1

[PATCH AUTOSEL 5.19 067/105] 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 fb04eaf367f1..7349b16b8e2f 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -22,12 +22,25 @@
  * 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 5.19 068/105] bpf: Make non-preallocated allocation low priority

[Sasha Levin]

From: Yafang Shao <laoar.shao@gmail.com>

[ Upstream commit ace2bee839e08df324cb320763258dfd72e6120e ]

GFP_ATOMIC doesn't cooperate well with memcg pressure so far, especially
if we allocate too much GFP_ATOMIC memory. For example, when we set the
memcg limit to limit a non-preallocated bpf memory, the GFP_ATOMIC can
easily break the memcg limit by force charge. So it is very dangerous to
use GFP_ATOMIC in non-preallocated case. One way to make it safe is to
remove __GFP_HIGH from GFP_ATOMIC, IOW, use (__GFP_ATOMIC |
__GFP_KSWAPD_RECLAIM) instead, then it will be limited if we allocate
too much memory. There's a plan to completely remove __GFP_ATOMIC in the
mm side[1], so let's use GFP_NOWAIT instead.

We introduced BPF_F_NO_PREALLOC is because full map pre-allocation is
too memory expensive for some cases. That means removing __GFP_HIGH
doesn't break the rule of BPF_F_NO_PREALLOC, but has the same goal with
it-avoiding issues caused by too much memory. So let's remove it.

This fix can also apply to other run-time allocations, for example, the
allocation in lpm trie, local storage and devmap. So let fix it
consistently over the bpf code

It also fixes a typo in the comment.

[1]. https://lore.kernel.org/linux-mm/163712397076.13692.4727608274002939094@noble.neil.brown.name/

Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: NeilBrown <neilb@suse.de>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Link: https://lore.kernel.org/r/20220709154457.57379-2-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/devmap.c        | 2 +-
 kernel/bpf/hashtab.c       | 6 +++---
 kernel/bpf/local_storage.c | 2 +-
 kernel/bpf/lpm_trie.c      | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index c2867068e5bd..1400561efb15 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -845,7 +845,7 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 	struct bpf_dtab_netdev *dev;
 
 	dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev),
-				   GFP_ATOMIC | __GFP_NOWARN,
+				   GFP_NOWAIT | __GFP_NOWARN,
 				   dtab->map.numa_node);
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 17fb69c0e0dc..da7578426a46 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -61,7 +61,7 @@
  *
  * As regular device interrupt handlers and soft interrupts are forced into
  * thread context, the existing code which does
- *   spin_lock*(); alloc(GPF_ATOMIC); spin_unlock*();
+ *   spin_lock*(); alloc(GFP_ATOMIC); spin_unlock*();
  * just works.
  *
  * In theory the BPF locks could be converted to regular spinlocks as well,
@@ -978,7 +978,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 				goto dec_count;
 			}
 		l_new = bpf_map_kmalloc_node(&htab->map, htab->elem_size,
-					     GFP_ATOMIC | __GFP_NOWARN,
+					     GFP_NOWAIT | __GFP_NOWARN,
 					     htab->map.numa_node);
 		if (!l_new) {
 			l_new = ERR_PTR(-ENOMEM);
@@ -996,7 +996,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 		} else {
 			/* alloc_percpu zero-fills */
 			pptr = bpf_map_alloc_percpu(&htab->map, size, 8,
-						    GFP_ATOMIC | __GFP_NOWARN);
+						    GFP_NOWAIT | __GFP_NOWARN);
 			if (!pptr) {
 				kfree(l_new);
 				l_new = ERR_PTR(-ENOMEM);
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 8654fc97f5fe..49ef0ce040c7 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -165,7 +165,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *key,
 	}
 
 	new = bpf_map_kmalloc_node(map, struct_size(new, data, map->value_size),
-				   __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN,
+				   __GFP_ZERO | GFP_NOWAIT | __GFP_NOWARN,
 				   map->numa_node);
 	if (!new)
 		return -ENOMEM;
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index f0d05a3cc4b9..d789e3b831ad 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -285,7 +285,7 @@ static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie,
 	if (value)
 		size += trie->map.value_size;
 
-	node = bpf_map_kmalloc_node(&trie->map, size, GFP_ATOMIC | __GFP_NOWARN,
+	node = bpf_map_kmalloc_node(&trie->map, size, GFP_NOWAIT | __GFP_NOWARN,
 				    trie->map.numa_node);
 	if (!node)
 		return NULL;
-- 
2.35.1

[PATCH AUTOSEL 5.19 071/105] selftests/bpf: Do not attach kprobe_multi bench to bpf_dispatcher_xdp_func

[Sasha Levin]

From: Jiri Olsa <jolsa@kernel.org>

[ Upstream commit 7fb27a56b9ebd8a77d9dd188e8a42bff99bc3443 ]

Alexei reported crash by running test_progs -j on system
with 32 cpus.

It turned out the kprobe_multi bench test that attaches all
ftrace-able functions will race with bpf_dispatcher_update,
that calls bpf_arch_text_poke on bpf_dispatcher_xdp_func,
which is ftrace-able function.

Ftrace is not aware of this update so this will cause
ftrace_bug with:

  WARNING: CPU: 6 PID: 1985 at
  arch/x86/kernel/ftrace.c:94 ftrace_verify_code+0x27/0x50
  ...
  ftrace_replace_code+0xa3/0x170
  ftrace_modify_all_code+0xbd/0x150
  ftrace_startup_enable+0x3f/0x50
  ftrace_startup+0x98/0xf0
  register_ftrace_function+0x20/0x60
  register_fprobe_ips+0xbb/0xd0
  bpf_kprobe_multi_link_attach+0x179/0x430
  __sys_bpf+0x18a1/0x2440
  ...
  ------------[ ftrace bug ]------------
  ftrace failed to modify
  [<ffffffff818d9380>] bpf_dispatcher_xdp_func+0x0/0x10
   actual:   ffffffe9:7b:ffffff9c:77:1e
  Setting ftrace call site to call ftrace function

It looks like we need some way to hide some functions
from ftrace, but meanwhile we workaround this by skipping
bpf_dispatcher_xdp_func from kprobe_multi bench test.

Reported-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20220714082316.479181-1-jolsa@kernel.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index 5b93d5d0bd93..48681bf73e0b 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -364,6 +364,8 @@ static int get_syms(char ***symsp, size_t *cntp)
 			continue;
 		if (!strncmp(name, "rcu_", 4))
 			continue;
+		if (!strcmp(name, "bpf_dispatcher_xdp_func"))
+			continue;
 		if (!strncmp(name, "__ftrace_invalid_address__",
 			     sizeof("__ftrace_invalid_address__") - 1))
 			continue;
-- 
2.35.1

[PATCH AUTOSEL 5.19 073/105] 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 eb12d4f705cc..9a6e5f71bbd2 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1108,7 +1108,8 @@ __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 5.19 077/105] 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 d3d10556f0fa..2f41364a6791 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2624,6 +2624,14 @@ 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 56f059b3c242..42f8de4ebbd7 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -955,6 +955,9 @@ 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 30a1603a7225..fe487dc6798e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4168,6 +4168,7 @@ 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 5.19 090/105] 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 392d28cc4e58..49936c4c8567 100755
--- a/tools/testing/selftests/bpf/test_xdp_veth.sh
+++ b/tools/testing/selftests/bpf/test_xdp_veth.sh
@@ -106,9 +106,9 @@ 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