Merge tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Pull BPF fixes from Daniel Borkmann:

 - Fix a soft-lockup in BPF arena_map_free on 64k page size kernels
   (Alan Maguire)

 - Fix a missing allocation failure check in BPF verifier's
   acquire_lock_state (Kumar Kartikeya Dwivedi)

 - Fix a NULL-pointer dereference in trace_kfree_skb by adding kfree_skb
   to the raw_tp_null_args set (Kuniyuki Iwashima)

 - Fix a deadlock when freeing BPF cgroup storage (Abel Wu)

 - Fix a syzbot-reported deadlock when holding BPF map's freeze_mutex
   (Andrii Nakryiko)

 - Fix a use-after-free issue in bpf_test_init when eth_skb_pkt_type is
   accessing skb data not containing an Ethernet header (Shigeru
   Yoshida)

 - Fix skipping non-existing keys in generic_map_lookup_batch (Yan Zhai)

 - Several BPF sockmap fixes to address incorrect TCP copied_seq
   calculations, which prevented correct data reads from recv(2) in user
   space (Jiayuan Chen)

 - Two fixes for BPF map lookup nullness elision (Daniel Xu)

 - Fix a NULL-pointer dereference from vmlinux BTF lookup in
   bpf_sk_storage_tracing_allowed (Jared Kangas)

* tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  selftests: bpf: test batch lookup on array of maps with holes
  bpf: skip non exist keys in generic_map_lookup_batch
  bpf: Handle allocation failure in acquire_lock_state
  bpf: verifier: Disambiguate get_constant_map_key() errors
  bpf: selftests: Test constant key extraction on irrelevant maps
  bpf: verifier: Do not extract constant map keys for irrelevant maps
  bpf: Fix softlockup in arena_map_free on 64k page kernel
  net: Add rx_skb of kfree_skb to raw_tp_null_args[].
  bpf: Fix deadlock when freeing cgroup storage
  selftests/bpf: Add strparser test for bpf
  selftests/bpf: Fix invalid flag of recv()
  bpf: Disable non stream socket for strparser
  bpf: Fix wrong copied_seq calculation
  strparser: Add read_sock callback
  bpf: avoid holding freeze_mutex during mmap operation
  bpf: unify VM_WRITE vs VM_MAYWRITE use in BPF map mmaping logic
  selftests/bpf: Adjust data size to have ETH_HLEN
  bpf, test_run: Fix use-after-free issue in eth_skb_pkt_type()
  bpf: Remove unnecessary BTF lookups in bpf_sk_storage_tracing_allowed

7 files changed, 575 insertions, 80 deletions

diff --git a/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c
index 66191ae9863c..79c3ccadb962 100644
--- a/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c
+++ b/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c
@@ -120,11 +120,12 @@ static void validate_fetch_results(int outer_map_fd,
 
 static void fetch_and_validate(int outer_map_fd,
 			       struct bpf_map_batch_opts *opts,
-			       __u32 batch_size, bool delete_entries)
+			       __u32 batch_size, bool delete_entries,
+			       bool has_holes)
 {
-	__u32 *fetched_keys, *fetched_values, total_fetched = 0;
-	__u32 batch_key = 0, fetch_count, step_size;
-	int err, max_entries = OUTER_MAP_ENTRIES;
+	int err, max_entries = OUTER_MAP_ENTRIES - !!has_holes;
+	__u32 *fetched_keys, *fetched_values, total_fetched = 0, i;
+	__u32 batch_key = 0, fetch_count, step_size = batch_size;
 	__u32 value_size = sizeof(__u32);
 
 	/* Total entries needs to be fetched */
@@ -134,9 +135,8 @@ static void fetch_and_validate(int outer_map_fd,
 	      "Memory allocation failed for fetched_keys or fetched_values",
 	      "error=%s\n", strerror(errno));
 
-	for (step_size = batch_size;
-	     step_size <= max_entries;
-	     step_size += batch_size) {
+	/* hash map may not always return full batch */
+	for (i = 0; i < OUTER_MAP_ENTRIES; i++) {
 		fetch_count = step_size;
 		err = delete_entries
 		      ? bpf_map_lookup_and_delete_batch(outer_map_fd,
@@ -155,6 +155,7 @@ static void fetch_and_validate(int outer_map_fd,
 		if (err && errno == ENOSPC) {
 			/* Fetch again with higher batch size */
 			total_fetched = 0;
+			step_size += batch_size;
 			continue;
 		}
 
@@ -184,18 +185,19 @@ static void fetch_and_validate(int outer_map_fd,
 }
 
 static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type,
-				  enum bpf_map_type inner_map_type)
+				  enum bpf_map_type inner_map_type,
+				  bool has_holes)
 {
+	__u32 max_entries = OUTER_MAP_ENTRIES - !!has_holes;
 	__u32 *outer_map_keys, *inner_map_fds;
-	__u32 max_entries = OUTER_MAP_ENTRIES;
 	LIBBPF_OPTS(bpf_map_batch_opts, opts);
 	__u32 value_size = sizeof(__u32);
 	int batch_size[2] = {5, 10};
 	__u32 map_index, op_index;
 	int outer_map_fd, ret;
 
-	outer_map_keys = calloc(max_entries, value_size);
-	inner_map_fds = calloc(max_entries, value_size);
+	outer_map_keys = calloc(OUTER_MAP_ENTRIES, value_size);
+	inner_map_fds = calloc(OUTER_MAP_ENTRIES, value_size);
 	CHECK((!outer_map_keys || !inner_map_fds),
 	      "Memory allocation failed for outer_map_keys or inner_map_fds",
 	      "error=%s\n", strerror(errno));
@@ -209,6 +211,24 @@ static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type,
 			((outer_map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
 			 ? 9 : 1000) - map_index;
 
+	/* This condition is only meaningful for array of maps.
+	 *
+	 * max_entries == OUTER_MAP_ENTRIES - 1 if it is true. Say
+	 * max_entries is short for n, then outer_map_keys looks like:
+	 *
+	 *   [n, n-1, ... 2, 1]
+	 *
+	 * We change it to
+	 *
+	 *   [n, n-1, ... 2, 0]
+	 *
+	 * So it will leave key 1 as a hole. It will serve to test the
+	 * correctness when batch on an array: a "non-exist" key might be
+	 * actually allocated and returned from key iteration.
+	 */
+	if (has_holes)
+		outer_map_keys[max_entries - 1]--;
+
 	/* batch operation - map_update */
 	ret = bpf_map_update_batch(outer_map_fd, outer_map_keys,
 				   inner_map_fds, &max_entries, &opts);
@@ -219,15 +239,17 @@ static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type,
 	/* batch operation - map_lookup */
 	for (op_index = 0; op_index < 2; ++op_index)
 		fetch_and_validate(outer_map_fd, &opts,
-				   batch_size[op_index], false);
+				   batch_size[op_index], false,
+				   has_holes);
 
 	/* batch operation - map_lookup_delete */
 	if (outer_map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
 		fetch_and_validate(outer_map_fd, &opts,
-				   max_entries, true /*delete*/);
+				   max_entries, true /*delete*/,
+				   has_holes);
 
 	/* close all map fds */
-	for (map_index = 0; map_index < max_entries; map_index++)
+	for (map_index = 0; map_index < OUTER_MAP_ENTRIES; map_index++)
 		close(inner_map_fds[map_index]);
 	close(outer_map_fd);
 
@@ -237,16 +259,20 @@ static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type,
 
 void test_map_in_map_batch_ops_array(void)
 {
-	_map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY);
+	_map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY, false);
 	printf("%s:PASS with inner ARRAY map\n", __func__);
-	_map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH);
+	_map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH, false);
 	printf("%s:PASS with inner HASH map\n", __func__);
+	_map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY, true);
+	printf("%s:PASS with inner ARRAY map with holes\n", __func__);
+	_map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH, true);
+	printf("%s:PASS with inner HASH map with holes\n", __func__);
 }
 
 void test_map_in_map_batch_ops_hash(void)
 {
-	_map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_ARRAY);
+	_map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_ARRAY, false);
 	printf("%s:PASS with inner ARRAY map\n", __func__);
-	_map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_HASH);
+	_map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_HASH, false);
 	printf("%s:PASS with inner HASH map\n", __func__);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 05eb37935c3e..1e3e4392dcca 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -526,8 +526,8 @@ static void test_sockmap_skb_verdict_shutdown(void)
 	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)");
+	n = recv(c1, &b, 1, MSG_DONTWAIT);
+	ASSERT_EQ(n, 0, "recv(fin)");
 out_close:
 	close(c1);
 	close(p1);
@@ -535,57 +535,6 @@ out:
 	test_sockmap_pass_prog__destroy(skel);
 }
 
-static void test_sockmap_stream_pass(void)
-{
-	int zero = 0, sent, recvd;
-	int verdict, parser;
-	int err, map;
-	int c = -1, p = -1;
-	struct test_sockmap_pass_prog *pass = NULL;
-	char snd[256] = "0123456789";
-	char rcv[256] = "0";
-
-	pass = test_sockmap_pass_prog__open_and_load();
-	verdict = bpf_program__fd(pass->progs.prog_skb_verdict);
-	parser = bpf_program__fd(pass->progs.prog_skb_parser);
-	map = bpf_map__fd(pass->maps.sock_map_rx);
-
-	err = bpf_prog_attach(parser, map, BPF_SK_SKB_STREAM_PARSER, 0);
-	if (!ASSERT_OK(err, "bpf_prog_attach stream parser"))
-		goto out;
-
-	err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0);
-	if (!ASSERT_OK(err, "bpf_prog_attach stream verdict"))
-		goto out;
-
-	err = create_pair(AF_INET, SOCK_STREAM, &c, &p);
-	if (err)
-		goto out;
-
-	/* sk_data_ready of 'p' will be replaced by strparser handler */
-	err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
-	if (!ASSERT_OK(err, "bpf_map_update_elem(p)"))
-		goto out_close;
-
-	/*
-	 * as 'prog_skb_parser' return the original skb len and
-	 * 'prog_skb_verdict' return SK_PASS, the kernel will just
-	 * pass it through to original socket 'p'
-	 */
-	sent = xsend(c, snd, sizeof(snd), 0);
-	ASSERT_EQ(sent, sizeof(snd), "xsend(c)");
-
-	recvd = recv_timeout(p, rcv, sizeof(rcv), SOCK_NONBLOCK,
-			     IO_TIMEOUT_SEC);
-	ASSERT_EQ(recvd, sizeof(rcv), "recv_timeout(p)");
-
-out_close:
-	close(c);
-	close(p);
-
-out:
-	test_sockmap_pass_prog__destroy(pass);
-}
 
 static void test_sockmap_skb_verdict_fionread(bool pass_prog)
 {
@@ -632,7 +581,7 @@ static void test_sockmap_skb_verdict_fionread(bool pass_prog)
 	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);
+		recvd = recv_timeout(c1, &buf, sizeof(buf), MSG_DONTWAIT, IO_TIMEOUT_SEC);
 		ASSERT_EQ(recvd, sizeof(buf), "recv_timeout(c0)");
 	}
 
@@ -1133,8 +1082,6 @@ void test_sockmap_basic(void)
 		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 stream parser and verdict pass"))
-		test_sockmap_stream_pass();
 	if (test__start_subtest("sockmap skb_verdict fionread"))
 		test_sockmap_skb_verdict_fionread(true);
 	if (test__start_subtest("sockmap skb_verdict fionread on drop"))
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c b/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c
new file mode 100644
index 000000000000..621b3b71888e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c
@@ -0,0 +1,454 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <error.h>
+#include <netinet/tcp.h>
+#include <test_progs.h>
+#include "sockmap_helpers.h"
+#include "test_skmsg_load_helpers.skel.h"
+#include "test_sockmap_strp.skel.h"
+
+#define STRP_PKT_HEAD_LEN 4
+#define STRP_PKT_BODY_LEN 6
+#define STRP_PKT_FULL_LEN (STRP_PKT_HEAD_LEN + STRP_PKT_BODY_LEN)
+
+static const char packet[STRP_PKT_FULL_LEN] = "head+body\0";
+static const int test_packet_num = 100;
+
+/* Current implementation of tcp_bpf_recvmsg_parser() invokes data_ready
+ * with sk held if an skb exists in sk_receive_queue. Then for the
+ * data_ready implementation of strparser, it will delay the read
+ * operation if sk is held and EAGAIN is returned.
+ */
+static int sockmap_strp_consume_pre_data(int p)
+{
+	int recvd;
+	bool retried = false;
+	char rcv[10];
+
+retry:
+	errno = 0;
+	recvd = recv_timeout(p, rcv, sizeof(rcv), 0, 1);
+	if (recvd < 0 && errno == EAGAIN && retried == false) {
+		/* On the first call, EAGAIN will certainly be returned.
+		 * A 1-second wait is enough for the workqueue to finish.
+		 */
+		sleep(1);
+		retried = true;
+		goto retry;
+	}
+
+	if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "recv error or truncated data") ||
+	    !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN),
+				"data mismatch"))
+		return -1;
+	return 0;
+}
+
+static struct test_sockmap_strp *sockmap_strp_init(int *out_map, bool pass,
+						   bool need_parser)
+{
+	struct test_sockmap_strp *strp = NULL;
+	int verdict, parser;
+	int err;
+
+	strp = test_sockmap_strp__open_and_load();
+	*out_map = bpf_map__fd(strp->maps.sock_map);
+
+	if (need_parser)
+		parser = bpf_program__fd(strp->progs.prog_skb_parser_partial);
+	else
+		parser = bpf_program__fd(strp->progs.prog_skb_parser);
+
+	if (pass)
+		verdict = bpf_program__fd(strp->progs.prog_skb_verdict_pass);
+	else
+		verdict = bpf_program__fd(strp->progs.prog_skb_verdict);
+
+	err = bpf_prog_attach(parser, *out_map, BPF_SK_SKB_STREAM_PARSER, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach stream parser"))
+		goto err;
+
+	err = bpf_prog_attach(verdict, *out_map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach stream verdict"))
+		goto err;
+
+	return strp;
+err:
+	test_sockmap_strp__destroy(strp);
+	return NULL;
+}
+
+/* Dispatch packets to different socket by packet size:
+ *
+ *                      ------  ------
+ *                     | pkt4 || pkt1 |... > remote socket
+ *  ------ ------     / ------  ------
+ * | pkt8 | pkt7 |...
+ *  ------ ------     \ ------  ------
+ *                     | pkt3 || pkt2 |... > local socket
+ *                      ------  ------
+ */
+static void test_sockmap_strp_dispatch_pkt(int family, int sotype)
+{
+	int i, j, zero = 0, one = 1, recvd;
+	int err, map;
+	int c0 = -1, p0 = -1, c1 = -1, p1 = -1;
+	struct test_sockmap_strp *strp = NULL;
+	int test_cnt = 6;
+	char rcv[10];
+	struct {
+		char	data[7];
+		int	data_len;
+		int	send_cnt;
+		int	*receiver;
+	} send_dir[2] = {
+		/* data expected to deliver to local */
+		{"llllll", 6, 0, &p0},
+		/* data expected to deliver to remote */
+		{"rrrrr",  5, 0, &c1}
+	};
+
+	strp = sockmap_strp_init(&map, false, false);
+	if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+		return;
+
+	err = create_socket_pairs(family, sotype, &c0, &c1, &p0, &p1);
+	if (!ASSERT_OK(err, "create_socket_pairs()"))
+		goto out;
+
+	err = bpf_map_update_elem(map, &zero, &p0, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p0)"))
+		goto out_close;
+
+	err = bpf_map_update_elem(map, &one, &p1, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p1)"))
+		goto out_close;
+
+	err = setsockopt(c1, IPPROTO_TCP, TCP_NODELAY, &zero, sizeof(zero));
+	if (!ASSERT_OK(err, "setsockopt(TCP_NODELAY)"))
+		goto out_close;
+
+	/* deliver data with data size greater than 5 to local */
+	strp->data->verdict_max_size = 5;
+
+	for (i = 0; i < test_cnt; i++) {
+		int d = i % 2;
+
+		xsend(c0, send_dir[d].data, send_dir[d].data_len, 0);
+		send_dir[d].send_cnt++;
+	}
+
+	for (i = 0; i < 2; i++) {
+		for (j = 0; j < send_dir[i].send_cnt; j++) {
+			int expected = send_dir[i].data_len;
+
+			recvd = recv_timeout(*send_dir[i].receiver, rcv,
+					     expected, MSG_DONTWAIT,
+					     IO_TIMEOUT_SEC);
+			if (!ASSERT_EQ(recvd, expected, "recv_timeout()"))
+				goto out_close;
+			if (!ASSERT_OK(memcmp(send_dir[i].data, rcv, recvd),
+				       "data mismatch"))
+				goto out_close;
+		}
+	}
+out_close:
+	close(c0);
+	close(c1);
+	close(p0);
+	close(p1);
+out:
+	test_sockmap_strp__destroy(strp);
+}
+
+/* We have multiple packets in one skb
+ * ------------ ------------ ------------
+ * |  packet1  |   packet2  |  ...
+ * ------------ ------------ ------------
+ */
+static void test_sockmap_strp_multiple_pkt(int family, int sotype)
+{
+	int i, zero = 0;
+	int sent, recvd, total;
+	int err, map;
+	int c = -1, p = -1;
+	struct test_sockmap_strp *strp = NULL;
+	char *snd = NULL, *rcv = NULL;
+
+	strp = sockmap_strp_init(&map, true, true);
+	if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+		return;
+
+	err = create_pair(family, sotype, &c, &p);
+	if (err)
+		goto out;
+
+	err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(zero, p)"))
+		goto out_close;
+
+	/* construct multiple packets in one buffer */
+	total = test_packet_num * STRP_PKT_FULL_LEN;
+	snd = malloc(total);
+	rcv = malloc(total + 1);
+	if (!ASSERT_TRUE(snd, "malloc(snd)") ||
+	    !ASSERT_TRUE(rcv, "malloc(rcv)"))
+		goto out_close;
+
+	for (i = 0; i < test_packet_num; i++) {
+		memcpy(snd + i * STRP_PKT_FULL_LEN,
+		       packet, STRP_PKT_FULL_LEN);
+	}
+
+	sent = xsend(c, snd, total, 0);
+	if (!ASSERT_EQ(sent, total, "xsend(c)"))
+		goto out_close;
+
+	/* try to recv one more byte to avoid truncation check */
+	recvd = recv_timeout(p, rcv, total + 1, MSG_DONTWAIT, IO_TIMEOUT_SEC);
+	if (!ASSERT_EQ(recvd, total, "recv(rcv)"))
+		goto out_close;
+
+	/* we sent TCP segment with multiple encapsulation
+	 * then check whether packets are handled correctly
+	 */
+	if (!ASSERT_OK(memcmp(snd, rcv, total), "data mismatch"))
+		goto out_close;
+
+out_close:
+	close(c);
+	close(p);
+	if (snd)
+		free(snd);
+	if (rcv)
+		free(rcv);
+out:
+	test_sockmap_strp__destroy(strp);
+}
+
+/* Test strparser with partial read */
+static void test_sockmap_strp_partial_read(int family, int sotype)
+{
+	int zero = 0, recvd, off;
+	int err, map;
+	int c = -1, p = -1;
+	struct test_sockmap_strp *strp = NULL;
+	char rcv[STRP_PKT_FULL_LEN + 1] = "0";
+
+	strp = sockmap_strp_init(&map, true, true);
+	if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+		return;
+
+	err = create_pair(family, sotype, &c, &p);
+	if (err)
+		goto out;
+
+	/* sk_data_ready of 'p' will be replaced by strparser handler */
+	err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(zero, p)"))
+		goto out_close;
+
+	/* 1.1 send partial head, 1 byte header left */
+	off = STRP_PKT_HEAD_LEN - 1;
+	xsend(c, packet, off, 0);
+	recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1);
+	if (!ASSERT_EQ(-1, recvd, "partial head sent, expected no data"))
+		goto out_close;
+
+	/* 1.2 send remaining head and body */
+	xsend(c, packet + off, STRP_PKT_FULL_LEN - off, 0);
+	recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, IO_TIMEOUT_SEC);
+	if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "expected full data"))
+		goto out_close;
+
+	/* 2.1 send partial head, 1 byte header left */
+	off = STRP_PKT_HEAD_LEN - 1;
+	xsend(c, packet, off, 0);
+
+	/* 2.2 send remaining head and partial body, 1 byte body left */
+	xsend(c, packet + off, STRP_PKT_FULL_LEN - off - 1, 0);
+	off = STRP_PKT_FULL_LEN - 1;
+	recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1);
+	if (!ASSERT_EQ(-1, recvd, "partial body sent, expected no data"))
+		goto out_close;
+
+	/* 2.3 send remaining body */
+	xsend(c, packet + off, STRP_PKT_FULL_LEN - off, 0);
+	recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, IO_TIMEOUT_SEC);
+	if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "expected full data"))
+		goto out_close;
+
+out_close:
+	close(c);
+	close(p);
+
+out:
+	test_sockmap_strp__destroy(strp);
+}
+
+/* Test simple socket read/write with strparser + FIONREAD */
+static void test_sockmap_strp_pass(int family, int sotype, bool fionread)
+{
+	int zero = 0, pkt_size = STRP_PKT_FULL_LEN, sent, recvd, avail;
+	int err, map;
+	int c = -1, p = -1;
+	int test_cnt = 10, i;
+	struct test_sockmap_strp *strp = NULL;
+	char rcv[STRP_PKT_FULL_LEN + 1] = "0";
+
+	strp = sockmap_strp_init(&map, true, true);
+	if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+		return;
+
+	err = create_pair(family, sotype, &c, &p);
+	if (err)
+		goto out;
+
+	/* inject some data before bpf process, it should be read
+	 * correctly because we check sk_receive_queue in
+	 * tcp_bpf_recvmsg_parser().
+	 */
+	sent = xsend(c, packet, pkt_size, 0);
+	if (!ASSERT_EQ(sent, pkt_size, "xsend(pre-data)"))
+		goto out_close;
+
+	/* sk_data_ready of 'p' will be replaced by strparser handler */
+	err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p)"))
+		goto out_close;
+
+	/* consume previous data we injected */
+	if (sockmap_strp_consume_pre_data(p))
+		goto out_close;
+
+	/* Previously, we encountered issues such as deadlocks and
+	 * sequence errors that resulted in the inability to read
+	 * continuously. Therefore, we perform multiple iterations
+	 * of testing here.
+	 */
+	for (i = 0; i < test_cnt; i++) {
+		sent = xsend(c, packet, pkt_size, 0);
+		if (!ASSERT_EQ(sent, pkt_size, "xsend(c)"))
+			goto out_close;
+
+		recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT,
+				     IO_TIMEOUT_SEC);
+		if (!ASSERT_EQ(recvd, pkt_size, "recv_timeout(p)") ||
+		    !ASSERT_OK(memcmp(packet, rcv, pkt_size),
+				  "memcmp, data mismatch"))
+			goto out_close;
+	}
+
+	if (fionread) {
+		sent = xsend(c, packet, pkt_size, 0);
+		if (!ASSERT_EQ(sent, pkt_size, "second xsend(c)"))
+			goto out_close;
+
+		err = ioctl(p, FIONREAD, &avail);
+		if (!ASSERT_OK(err, "ioctl(FIONREAD) error") ||
+		    !ASSERT_EQ(avail, pkt_size, "ioctl(FIONREAD)"))
+			goto out_close;
+
+		recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT,
+				     IO_TIMEOUT_SEC);
+		if (!ASSERT_EQ(recvd, pkt_size, "second recv_timeout(p)") ||
+		    !ASSERT_OK(memcmp(packet, rcv, pkt_size),
+			      "second memcmp, data mismatch"))
+			goto out_close;
+	}
+
+out_close:
+	close(c);
+	close(p);
+
+out:
+	test_sockmap_strp__destroy(strp);
+}
+
+/* Test strparser with verdict mode */
+static void test_sockmap_strp_verdict(int family, int sotype)
+{
+	int zero = 0, one = 1, sent, recvd, off;
+	int err, map;
+	int c0 = -1, p0 = -1, c1 = -1, p1 = -1;
+	struct test_sockmap_strp *strp = NULL;
+	char rcv[STRP_PKT_FULL_LEN + 1] = "0";
+
+	strp = sockmap_strp_init(&map, false, true);
+	if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+		return;
+
+	/* We simulate a reverse proxy server.
+	 * When p0 receives data from c0, we forward it to c1.
+	 * From c1's perspective, it will consider this data
+	 * as being sent by p1.
+	 */
+	err = create_socket_pairs(family, sotype, &c0, &c1, &p0, &p1);
+	if (!ASSERT_OK(err, "create_socket_pairs()"))
+		goto out;
+
+	err = bpf_map_update_elem(map, &zero, &p0, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p0)"))
+		goto out_close;
+
+	err = bpf_map_update_elem(map, &one, &p1, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p1)"))
+		goto out_close;
+
+	sent = xsend(c0, packet, STRP_PKT_FULL_LEN, 0);
+	if (!ASSERT_EQ(sent, STRP_PKT_FULL_LEN, "xsend(c0)"))
+		goto out_close;
+
+	recvd = recv_timeout(c1, rcv, sizeof(rcv), MSG_DONTWAIT,
+			     IO_TIMEOUT_SEC);
+	if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "recv_timeout(c1)") ||
+	    !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN),
+			  "received data does not match the sent data"))
+		goto out_close;
+
+	/* send again to ensure the stream is functioning correctly. */
+	sent = xsend(c0, packet, STRP_PKT_FULL_LEN, 0);
+	if (!ASSERT_EQ(sent, STRP_PKT_FULL_LEN, "second xsend(c0)"))
+		goto out_close;
+
+	/* partial read */
+	off = STRP_PKT_FULL_LEN / 2;
+	recvd = recv_timeout(c1, rcv, off, MSG_DONTWAIT,
+			     IO_TIMEOUT_SEC);
+	recvd += recv_timeout(c1, rcv + off, sizeof(rcv) - off, MSG_DONTWAIT,
+			      IO_TIMEOUT_SEC);
+
+	if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "partial recv_timeout(c1)") ||
+	    !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN),
+			  "partial received data does not match the sent data"))
+		goto out_close;
+
+out_close:
+	close(c0);
+	close(c1);
+	close(p0);
+	close(p1);
+out:
+	test_sockmap_strp__destroy(strp);
+}
+
+void test_sockmap_strp(void)
+{
+	if (test__start_subtest("sockmap strp tcp pass"))
+		test_sockmap_strp_pass(AF_INET, SOCK_STREAM, false);
+	if (test__start_subtest("sockmap strp tcp v6 pass"))
+		test_sockmap_strp_pass(AF_INET6, SOCK_STREAM, false);
+	if (test__start_subtest("sockmap strp tcp pass fionread"))
+		test_sockmap_strp_pass(AF_INET, SOCK_STREAM, true);
+	if (test__start_subtest("sockmap strp tcp v6 pass fionread"))
+		test_sockmap_strp_pass(AF_INET6, SOCK_STREAM, true);
+	if (test__start_subtest("sockmap strp tcp verdict"))
+		test_sockmap_strp_verdict(AF_INET, SOCK_STREAM);
+	if (test__start_subtest("sockmap strp tcp v6 verdict"))
+		test_sockmap_strp_verdict(AF_INET6, SOCK_STREAM);
+	if (test__start_subtest("sockmap strp tcp partial read"))
+		test_sockmap_strp_partial_read(AF_INET, SOCK_STREAM);
+	if (test__start_subtest("sockmap strp tcp multiple packets"))
+		test_sockmap_strp_multiple_pkt(AF_INET, SOCK_STREAM);
+	if (test__start_subtest("sockmap strp tcp dispatch"))
+		test_sockmap_strp_dispatch_pkt(AF_INET, SOCK_STREAM);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
index c7f74f068e78..df27535995af 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
@@ -52,10 +52,10 @@ static void test_xdp_with_cpumap_helpers(void)
 	ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to cpumap entry prog_id");
 
 	/* send a packet to trigger any potential bugs in there */
-	char data[10] = {};
+	char data[ETH_HLEN] = {};
 	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
 			    .data_in = &data,
-			    .data_size_in = 10,
+			    .data_size_in = sizeof(data),
 			    .flags = BPF_F_TEST_XDP_LIVE_FRAMES,
 			    .repeat = 1,
 		);
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
index 27ffed17d4be..461ab18705d5 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
@@ -23,7 +23,7 @@ static void test_xdp_with_devmap_helpers(void)
 	__u32 len = sizeof(info);
 	int err, dm_fd, dm_fd_redir, map_fd;
 	struct nstoken *nstoken = NULL;
-	char data[10] = {};
+	char data[ETH_HLEN] = {};
 	__u32 idx = 0;
 
 	SYS(out_close, "ip netns add %s", TEST_NS);
@@ -58,7 +58,7 @@ static void test_xdp_with_devmap_helpers(void)
 	/* send a packet to trigger any potential bugs in there */
 	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
 			    .data_in = &data,
-			    .data_size_in = 10,
+			    .data_size_in = sizeof(data),
 			    .flags = BPF_F_TEST_XDP_LIVE_FRAMES,
 			    .repeat = 1,
 		);
@@ -158,7 +158,7 @@ static void test_xdp_with_devmap_helpers_veth(void)
 	struct nstoken *nstoken = NULL;
 	__u32 len = sizeof(info);
 	int err, dm_fd, dm_fd_redir, map_fd, ifindex_dst;
-	char data[10] = {};
+	char data[ETH_HLEN] = {};
 	__u32 idx = 0;
 
 	SYS(out_close, "ip netns add %s", TEST_NS);
@@ -208,7 +208,7 @@ static void test_xdp_with_devmap_helpers_veth(void)
 	/* send a packet to trigger any potential bugs in there */
 	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
 			    .data_in = &data,
-			    .data_size_in = 10,
+			    .data_size_in = sizeof(data),
 			    .flags = BPF_F_TEST_XDP_LIVE_FRAMES,
 			    .repeat = 1,
 		);
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_strp.c b/tools/testing/selftests/bpf/progs/test_sockmap_strp.c
new file mode 100644
index 000000000000..dde3d5bec515
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_strp.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+int verdict_max_size = 10000;
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 20);
+	__type(key, int);
+	__type(value, int);
+} sock_map SEC(".maps");
+
+SEC("sk_skb/stream_verdict")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+	__u32 one = 1;
+
+	if (skb->len > verdict_max_size)
+		return SK_PASS;
+
+	return bpf_sk_redirect_map(skb, &sock_map, one, 0);
+}
+
+SEC("sk_skb/stream_verdict")
+int prog_skb_verdict_pass(struct __sk_buff *skb)
+{
+	return SK_PASS;
+}
+
+SEC("sk_skb/stream_parser")
+int prog_skb_parser(struct __sk_buff *skb)
+{
+	return skb->len;
+}
+
+SEC("sk_skb/stream_parser")
+int prog_skb_parser_partial(struct __sk_buff *skb)
+{
+	/* agreement with the test program on a 4-byte size header
+	 * and 6-byte body.
+	 */
+	if (skb->len < 4) {
+		/* need more header to determine full length */
+		return 0;
+	}
+	/* return full length decoded from header.
+	 * the return value may be larger than skb->len which
+	 * means framework must wait body coming.
+	 */
+	return 10;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_array_access.c b/tools/testing/selftests/bpf/progs/verifier_array_access.c
index 29eb9568633f..0a187ff725cc 100644
--- a/tools/testing/selftests/bpf/progs/verifier_array_access.c
+++ b/tools/testing/selftests/bpf/progs/verifier_array_access.c
@@ -713,4 +713,19 @@ unsigned int non_stack_key_lookup(void)
 	return val->index;
 }
 
+SEC("socket")
+__description("doesn't reject UINT64_MAX as s64 for irrelevant maps")
+__success __retval(42)
+unsigned int doesnt_reject_irrelevant_maps(void)
+{
+	__u64 key = 0xFFFFFFFFFFFFFFFF;
+	struct test_val *val;
+
+	val = bpf_map_lookup_elem(&map_hash_48b, &key);
+	if (val)
+		return val->index;
+
+	return 42;
+}
+
 char _license[] SEC("license") = "GPL";