Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2023-05-24

We've added 19 non-merge commits during the last 10 day(s) which contain
a total of 20 files changed, 738 insertions(+), 448 deletions(-).

The main changes are:

1) Batch of BPF sockmap fixes found when running against NGINX TCP tests,
   from John Fastabend.

2) Fix a memleak in the LRU{,_PERCPU} hash map when bucket locking fails,
   from Anton Protopopov.

3) Init the BPF offload table earlier than just late_initcall,
   from Jakub Kicinski.

4) Fix ctx access mask generation for 32-bit narrow loads of 64-bit fields,
   from Will Deacon.

5) Remove a now unsupported __fallthrough in BPF samples,
   from Andrii Nakryiko.

6) Fix a typo in pkg-config call for building sign-file,
   from Jeremy Sowden.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  bpf, sockmap: Test progs verifier error with latest clang
  bpf, sockmap: Test FIONREAD returns correct bytes in rx buffer with drops
  bpf, sockmap: Test FIONREAD returns correct bytes in rx buffer
  bpf, sockmap: Test shutdown() correctly exits epoll and recv()=0
  bpf, sockmap: Build helper to create connected socket pair
  bpf, sockmap: Pull socket helpers out of listen test for general use
  bpf, sockmap: Incorrectly handling copied_seq
  bpf, sockmap: Wake up polling after data copy
  bpf, sockmap: TCP data stall on recv before accept
  bpf, sockmap: Handle fin correctly
  bpf, sockmap: Improved check for empty queue
  bpf, sockmap: Reschedule is now done through backlog
  bpf, sockmap: Convert schedule_work into delayed_work
  bpf, sockmap: Pass skb ownership through read_skb
  bpf: fix a memory leak in the LRU and LRU_PERCPU hash maps
  bpf: Fix mask generation for 32-bit narrow loads of 64-bit fields
  samples/bpf: Drop unnecessary fallthrough
  bpf: netdev: init the offload table earlier
  selftests/bpf: Fix pkg-config call building sign-file
====================

Link: https://lore.kernel.org/r/20230524170839.13905-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 131 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 0ce25a967481..064cc5e8d9ad 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -2,6 +2,7 @@
 // Copyright (c) 2020 Cloudflare
 #include <error.h>
 #include <netinet/tcp.h>
+#include <sys/epoll.h>
 
 #include "test_progs.h"
 #include "test_skmsg_load_helpers.skel.h"
@@ -9,8 +10,12 @@
 #include "test_sockmap_invalid_update.skel.h"
 #include "test_sockmap_skb_verdict_attach.skel.h"
 #include "test_sockmap_progs_query.skel.h"
+#include "test_sockmap_pass_prog.skel.h"
+#include "test_sockmap_drop_prog.skel.h"
 #include "bpf_iter_sockmap.skel.h"
 
+#include "sockmap_helpers.h"
+
 #define TCP_REPAIR		19	/* TCP sock is under repair right now */
 
 #define TCP_REPAIR_ON		1
@@ -350,6 +355,126 @@ out:
 	test_sockmap_progs_query__destroy(skel);
 }
 
+#define MAX_EVENTS 10
+static void test_sockmap_skb_verdict_shutdown(void)
+{
+	struct epoll_event ev, events[MAX_EVENTS];
+	int n, err, map, verdict, s, c1, p1;
+	struct test_sockmap_pass_prog *skel;
+	int epollfd;
+	int zero = 0;
+	char b;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach"))
+		goto out;
+
+	s = socket_loopback(AF_INET, SOCK_STREAM);
+	if (s < 0)
+		goto out;
+	err = create_pair(s, AF_INET, SOCK_STREAM, &c1, &p1);
+	if (err < 0)
+		goto out;
+
+	err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST);
+	if (err < 0)
+		goto out_close;
+
+	shutdown(p1, SHUT_WR);
+
+	ev.events = EPOLLIN;
+	ev.data.fd = c1;
+
+	epollfd = epoll_create1(0);
+	if (!ASSERT_GT(epollfd, -1, "epoll_create(0)"))
+		goto out_close;
+	err = epoll_ctl(epollfd, EPOLL_CTL_ADD, c1, &ev);
+	if (!ASSERT_OK(err, "epoll_ctl(EPOLL_CTL_ADD)"))
+		goto out_close;
+	err = epoll_wait(epollfd, events, MAX_EVENTS, -1);
+	if (!ASSERT_EQ(err, 1, "epoll_wait(fd)"))
+		goto out_close;
+
+	n = recv(c1, &b, 1, SOCK_NONBLOCK);
+	ASSERT_EQ(n, 0, "recv_timeout(fin)");
+out_close:
+	close(c1);
+	close(p1);
+out:
+	test_sockmap_pass_prog__destroy(skel);
+}
+
+static void test_sockmap_skb_verdict_fionread(bool pass_prog)
+{
+	int expected, zero = 0, sent, recvd, avail;
+	int err, map, verdict, s, c0, c1, p0, p1;
+	struct test_sockmap_pass_prog *pass;
+	struct test_sockmap_drop_prog *drop;
+	char buf[256] = "0123456789";
+
+	if (pass_prog) {
+		pass = test_sockmap_pass_prog__open_and_load();
+		if (!ASSERT_OK_PTR(pass, "open_and_load"))
+			return;
+		verdict = bpf_program__fd(pass->progs.prog_skb_verdict);
+		map = bpf_map__fd(pass->maps.sock_map_rx);
+		expected = sizeof(buf);
+	} else {
+		drop = test_sockmap_drop_prog__open_and_load();
+		if (!ASSERT_OK_PTR(drop, "open_and_load"))
+			return;
+		verdict = bpf_program__fd(drop->progs.prog_skb_verdict);
+		map = bpf_map__fd(drop->maps.sock_map_rx);
+		/* On drop data is consumed immediately and copied_seq inc'd */
+		expected = 0;
+	}
+
+
+	err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach"))
+		goto out;
+
+	s = socket_loopback(AF_INET, SOCK_STREAM);
+	if (!ASSERT_GT(s, -1, "socket_loopback(s)"))
+		goto out;
+	err = create_socket_pairs(s, AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1);
+	if (!ASSERT_OK(err, "create_socket_pairs(s)"))
+		goto out;
+
+	err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(c1)"))
+		goto out_close;
+
+	sent = xsend(p1, &buf, sizeof(buf), 0);
+	ASSERT_EQ(sent, sizeof(buf), "xsend(p0)");
+	err = ioctl(c1, FIONREAD, &avail);
+	ASSERT_OK(err, "ioctl(FIONREAD) error");
+	ASSERT_EQ(avail, expected, "ioctl(FIONREAD)");
+	/* On DROP test there will be no data to read */
+	if (pass_prog) {
+		recvd = recv_timeout(c1, &buf, sizeof(buf), SOCK_NONBLOCK, IO_TIMEOUT_SEC);
+		ASSERT_EQ(recvd, sizeof(buf), "recv_timeout(c0)");
+	}
+
+out_close:
+	close(c0);
+	close(p0);
+	close(c1);
+	close(p1);
+out:
+	if (pass_prog)
+		test_sockmap_pass_prog__destroy(pass);
+	else
+		test_sockmap_drop_prog__destroy(drop);
+}
+
 void test_sockmap_basic(void)
 {
 	if (test__start_subtest("sockmap create_update_free"))
@@ -384,4 +509,10 @@ void test_sockmap_basic(void)
 		test_sockmap_progs_query(BPF_SK_SKB_STREAM_VERDICT);
 	if (test__start_subtest("sockmap skb_verdict progs query"))
 		test_sockmap_progs_query(BPF_SK_SKB_VERDICT);
+	if (test__start_subtest("sockmap skb_verdict shutdown"))
+		test_sockmap_skb_verdict_shutdown();
+	if (test__start_subtest("sockmap skb_verdict fionread"))
+		test_sockmap_skb_verdict_fionread(true);
+	if (test__start_subtest("sockmap skb_verdict fionread on drop"))
+		test_sockmap_skb_verdict_fionread(false);
 }