From cff908463d91a6b2fb8c8ab6c41d9c308c29fd42 Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@kernel.org>
Date: Mon, 22 Mar 2021 17:07:20 +0000
Subject: selftests/bpf: Better error messages for ima_setup.sh failures

The current implementation uses the CHECK_FAIL macro which does not
provide useful error messages when the script fails. Use the CHECK macro
instead and provide more descriptive messages to aid debugging.

Signed-off-by: KP Singh <kpsingh@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210322170720.2926715-1-kpsingh@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/test_ima.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/test_ima.c b/tools/testing/selftests/bpf/prog_tests/test_ima.c
index b54bc0c351b7..0252f61d611a 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_ima.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_ima.c
@@ -68,7 +68,8 @@ void test_test_ima(void)
 		goto close_prog;
 
 	snprintf(cmd, sizeof(cmd), "./ima_setup.sh setup %s", measured_dir);
-	if (CHECK_FAIL(system(cmd)))
+	err = system(cmd);
+	if (CHECK(err, "failed to run command", "%s, errno = %d\n", cmd, errno))
 		goto close_clean;
 
 	err = run_measured_process(measured_dir, &skel->bss->monitored_pid);
@@ -81,7 +82,8 @@ void test_test_ima(void)
 
 close_clean:
 	snprintf(cmd, sizeof(cmd), "./ima_setup.sh cleanup %s", measured_dir);
-	CHECK_FAIL(system(cmd));
+	err = system(cmd);
+	CHECK(err, "failed to run command", "%s, errno = %d\n", cmd, errno);
 close_prog:
 	ima__destroy(skel);
 }
-- 
cgit v1.2.3


From e9bd8cbd970bedd3cca8ee334c76ab90feb78760 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Mon, 22 Mar 2021 23:50:54 -0300
Subject: bpf: selftests: Add tests for batched ops in LPM trie maps

Uses the already existing infrastructure for testing batched ops.
The testing code is essentially the same, with minor tweaks for this use
case.

Suggested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210323025058.315763-3-pctammela@gmail.com
---
 .../bpf/map_tests/lpm_trie_map_batch_ops.c         | 158 +++++++++++++++++++++
 1 file changed, 158 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c
new file mode 100644
index 000000000000..2e986e5e4cac
--- /dev/null
+++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <arpa/inet.h>
+#include <linux/bpf.h>
+#include <netinet/in.h>
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <stdlib.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include <test_maps.h>
+
+struct test_lpm_key {
+	__u32 prefix;
+	struct in_addr ipv4;
+};
+
+static void map_batch_update(int map_fd, __u32 max_entries,
+			     struct test_lpm_key *keys, int *values)
+{
+	__u32 i;
+	int err;
+	char buff[16] = { 0 };
+	DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+		.elem_flags = 0,
+		.flags = 0,
+	);
+
+	for (i = 0; i < max_entries; i++) {
+		keys[i].prefix = 32;
+		snprintf(buff, 16, "192.168.1.%d", i + 1);
+		inet_pton(AF_INET, buff, &keys[i].ipv4);
+		values[i] = i + 1;
+	}
+
+	err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &opts);
+	CHECK(err, "bpf_map_update_batch()", "error:%s\n", strerror(errno));
+}
+
+static void map_batch_verify(int *visited, __u32 max_entries,
+			     struct test_lpm_key *keys, int *values)
+{
+	char buff[16] = { 0 };
+	int lower_byte = 0;
+	__u32 i;
+
+	memset(visited, 0, max_entries * sizeof(*visited));
+	for (i = 0; i < max_entries; i++) {
+		inet_ntop(AF_INET, &keys[i].ipv4, buff, 32);
+		CHECK(sscanf(buff, "192.168.1.%d", &lower_byte) == EOF,
+		      "sscanf()", "error: i %d\n", i);
+		CHECK(lower_byte != values[i], "key/value checking",
+		      "error: i %d key %s value %d\n", i, buff, values[i]);
+		visited[i] = 1;
+	}
+	for (i = 0; i < max_entries; i++) {
+		CHECK(visited[i] != 1, "visited checking",
+		      "error: keys array at index %d missing\n", i);
+	}
+}
+
+void test_lpm_trie_map_batch_ops(void)
+{
+	struct bpf_create_map_attr xattr = {
+		.name = "lpm_trie_map",
+		.map_type = BPF_MAP_TYPE_LPM_TRIE,
+		.key_size = sizeof(struct test_lpm_key),
+		.value_size = sizeof(int),
+		.map_flags = BPF_F_NO_PREALLOC,
+	};
+	struct test_lpm_key *keys, key;
+	int map_fd, *values, *visited;
+	__u32 step, count, total, total_success;
+	const __u32 max_entries = 10;
+	__u64 batch = 0;
+	int err;
+	DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+		.elem_flags = 0,
+		.flags = 0,
+	);
+
+	xattr.max_entries = max_entries;
+	map_fd = bpf_create_map_xattr(&xattr);
+	CHECK(map_fd == -1, "bpf_create_map_xattr()", "error:%s\n",
+	      strerror(errno));
+
+	keys = malloc(max_entries * sizeof(struct test_lpm_key));
+	values = malloc(max_entries * sizeof(int));
+	visited = malloc(max_entries * sizeof(int));
+	CHECK(!keys || !values || !visited, "malloc()", "error:%s\n",
+	      strerror(errno));
+
+	total_success = 0;
+	for (step = 1; step < max_entries; step++) {
+		map_batch_update(map_fd, max_entries, keys, values);
+		map_batch_verify(visited, max_entries, keys, values);
+		memset(keys, 0, max_entries * sizeof(*keys));
+		memset(values, 0, max_entries * sizeof(*values));
+		batch = 0;
+		total = 0;
+		/* iteratively lookup/delete elements with 'step'
+		 * elements each.
+		 */
+		count = step;
+		while (true) {
+			err = bpf_map_lookup_batch(map_fd,
+				total ? &batch : NULL, &batch,
+				keys + total, values + total, &count, &opts);
+
+			CHECK((err && errno != ENOENT), "lookup with steps",
+			      "error: %s\n", strerror(errno));
+
+			total += count;
+			if (err)
+				break;
+		}
+
+		CHECK(total != max_entries, "lookup with steps",
+		      "total = %u, max_entries = %u\n", total, max_entries);
+
+		map_batch_verify(visited, max_entries, keys, values);
+
+		total = 0;
+		count = step;
+		while (total < max_entries) {
+			if (max_entries - total < step)
+				count = max_entries - total;
+			err = bpf_map_delete_batch(map_fd, keys + total, &count,
+						   &opts);
+			CHECK((err && errno != ENOENT), "delete batch",
+			      "error: %s\n", strerror(errno));
+			total += count;
+			if (err)
+				break;
+		}
+		CHECK(total != max_entries, "delete with steps",
+		      "total = %u, max_entries = %u\n", total, max_entries);
+
+		/* check map is empty, errono == ENOENT */
+		err = bpf_map_get_next_key(map_fd, NULL, &key);
+		CHECK(!err || errno != ENOENT, "bpf_map_get_next_key()",
+		      "error: %s\n", strerror(errno));
+
+		total_success++;
+	}
+
+	CHECK(total_success == 0, "check total_success",
+	      "unexpected failure\n");
+
+	printf("%s:PASS\n", __func__);
+
+	free(keys);
+	free(values);
+	free(visited);
+}
-- 
cgit v1.2.3


From e6ac2450d6dee3121cd8bbf2907b78a68a8a353d Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 24 Mar 2021 18:51:42 -0700
Subject: bpf: Support bpf program calling kernel function

This patch adds support to BPF verifier to allow bpf program calling
kernel function directly.

The use case included in this set is to allow bpf-tcp-cc to directly
call some tcp-cc helper functions (e.g. "tcp_cong_avoid_ai()").  Those
functions have already been used by some kernel tcp-cc implementations.

This set will also allow the bpf-tcp-cc program to directly call the
kernel tcp-cc implementation,  For example, a bpf_dctcp may only want to
implement its own dctcp_cwnd_event() and reuse other dctcp_*() directly
from the kernel tcp_dctcp.c instead of reimplementing (or
copy-and-pasting) them.

The tcp-cc kernel functions mentioned above will be white listed
for the struct_ops bpf-tcp-cc programs to use in a later patch.
The white listed functions are not bounded to a fixed ABI contract.
Those functions have already been used by the existing kernel tcp-cc.
If any of them has changed, both in-tree and out-of-tree kernel tcp-cc
implementations have to be changed.  The same goes for the struct_ops
bpf-tcp-cc programs which have to be adjusted accordingly.

This patch is to make the required changes in the bpf verifier.

First change is in btf.c, it adds a case in "btf_check_func_arg_match()".
When the passed in "btf->kernel_btf == true", it means matching the
verifier regs' states with a kernel function.  This will handle the
PTR_TO_BTF_ID reg.  It also maps PTR_TO_SOCK_COMMON, PTR_TO_SOCKET,
and PTR_TO_TCP_SOCK to its kernel's btf_id.

In the later libbpf patch, the insn calling a kernel function will
look like:

insn->code == (BPF_JMP | BPF_CALL)
insn->src_reg == BPF_PSEUDO_KFUNC_CALL /* <- new in this patch */
insn->imm == func_btf_id /* btf_id of the running kernel */

[ For the future calling function-in-kernel-module support, an array
  of module btf_fds can be passed at the load time and insn->off
  can be used to index into this array. ]

At the early stage of verifier, the verifier will collect all kernel
function calls into "struct bpf_kfunc_desc".  Those
descriptors are stored in "prog->aux->kfunc_tab" and will
be available to the JIT.  Since this "add" operation is similar
to the current "add_subprog()" and looking for the same insn->code,
they are done together in the new "add_subprog_and_kfunc()".

In the "do_check()" stage, the new "check_kfunc_call()" is added
to verify the kernel function call instruction:
1. Ensure the kernel function can be used by a particular BPF_PROG_TYPE.
   A new bpf_verifier_ops "check_kfunc_call" is added to do that.
   The bpf-tcp-cc struct_ops program will implement this function in
   a later patch.
2. Call "btf_check_kfunc_args_match()" to ensure the regs can be
   used as the args of a kernel function.
3. Mark the regs' type, subreg_def, and zext_dst.

At the later do_misc_fixups() stage, the new fixup_kfunc_call()
will replace the insn->imm with the function address (relative
to __bpf_call_base).  If needed, the jit can find the btf_func_model
by calling the new bpf_jit_find_kfunc_model(prog, insn).
With the imm set to the function address, "bpftool prog dump xlated"
will be able to display the kernel function calls the same way as
it displays other bpf helper calls.

gpl_compatible program is required to call kernel function.

This feature currently requires JIT.

The verifier selftests are adjusted because of the changes in
the verbose log in add_subprog_and_kfunc().

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210325015142.1544736-1-kafai@fb.com
---
 tools/testing/selftests/bpf/verifier/calls.c     | 12 ++++++------
 tools/testing/selftests/bpf/verifier/dead_code.c | 10 +++++-----
 2 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index eb888c8479c3..336a749673d1 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -19,7 +19,7 @@
 	BPF_MOV64_IMM(BPF_REG_0, 2),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 1,
@@ -136,7 +136,7 @@
 {
 	"calls: wrong src reg",
 	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 2, 0, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 3, 0, 0),
 	BPF_MOV64_IMM(BPF_REG_0, 1),
 	BPF_EXIT_INSN(),
 	},
@@ -397,7 +397,7 @@
 	BPF_MOV64_IMM(BPF_REG_0, 1),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.fixup_map_hash_48b = { 3 },
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
@@ -1977,7 +1977,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
@@ -2003,7 +2003,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.errstr = "!read_ok",
 	.result = REJECT,
 },
@@ -2028,7 +2028,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.errstr = "!read_ok",
 	.result = REJECT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/dead_code.c b/tools/testing/selftests/bpf/verifier/dead_code.c
index 5cf361d8eb1c..17fe33a75034 100644
--- a/tools/testing/selftests/bpf/verifier/dead_code.c
+++ b/tools/testing/selftests/bpf/verifier/dead_code.c
@@ -85,7 +85,7 @@
 	BPF_MOV64_IMM(BPF_REG_0, 12),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 7,
@@ -103,7 +103,7 @@
 	BPF_MOV64_IMM(BPF_REG_0, 12),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 7,
@@ -121,7 +121,7 @@
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -5),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 7,
@@ -137,7 +137,7 @@
 	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
@@ -152,7 +152,7 @@
 	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
-- 
cgit v1.2.3


From 39cd9e0f6783fd2dd2b0e95500e34575b3707ed8 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 24 Mar 2021 18:52:40 -0700
Subject: bpf: selftests: Rename bictcp to bpf_cubic

As a similar chanage in the kernel, this patch gives the proper
name to the bpf cubic.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210325015240.1550074-1-kafai@fb.com
---
 tools/testing/selftests/bpf/progs/bpf_cubic.c | 30 +++++++++++++--------------
 1 file changed, 15 insertions(+), 15 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c
index 6939bfd8690f..33c4d2bded64 100644
--- a/tools/testing/selftests/bpf/progs/bpf_cubic.c
+++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c
@@ -174,8 +174,8 @@ static __always_inline void bictcp_hystart_reset(struct sock *sk)
  * as long as it is used in one of the func ptr
  * under SEC(".struct_ops").
  */
-SEC("struct_ops/bictcp_init")
-void BPF_PROG(bictcp_init, struct sock *sk)
+SEC("struct_ops/bpf_cubic_init")
+void BPF_PROG(bpf_cubic_init, struct sock *sk)
 {
 	struct bictcp *ca = inet_csk_ca(sk);
 
@@ -192,7 +192,7 @@ void BPF_PROG(bictcp_init, struct sock *sk)
  * The remaining tcp-cubic functions have an easier way.
  */
 SEC("no-sec-prefix-bictcp_cwnd_event")
-void BPF_PROG(bictcp_cwnd_event, struct sock *sk, enum tcp_ca_event event)
+void BPF_PROG(bpf_cubic_cwnd_event, struct sock *sk, enum tcp_ca_event event)
 {
 	if (event == CA_EVENT_TX_START) {
 		struct bictcp *ca = inet_csk_ca(sk);
@@ -384,7 +384,7 @@ tcp_friendliness:
 }
 
 /* Or simply use the BPF_STRUCT_OPS to avoid the SEC boiler plate. */
-void BPF_STRUCT_OPS(bictcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
+void BPF_STRUCT_OPS(bpf_cubic_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
@@ -403,7 +403,7 @@ void BPF_STRUCT_OPS(bictcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
 	tcp_cong_avoid_ai(tp, ca->cnt, acked);
 }
 
-__u32 BPF_STRUCT_OPS(bictcp_recalc_ssthresh, struct sock *sk)
+__u32 BPF_STRUCT_OPS(bpf_cubic_recalc_ssthresh, struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
@@ -420,7 +420,7 @@ __u32 BPF_STRUCT_OPS(bictcp_recalc_ssthresh, struct sock *sk)
 	return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U);
 }
 
-void BPF_STRUCT_OPS(bictcp_state, struct sock *sk, __u8 new_state)
+void BPF_STRUCT_OPS(bpf_cubic_state, struct sock *sk, __u8 new_state)
 {
 	if (new_state == TCP_CA_Loss) {
 		bictcp_reset(inet_csk_ca(sk));
@@ -496,7 +496,7 @@ static __always_inline void hystart_update(struct sock *sk, __u32 delay)
 	}
 }
 
-void BPF_STRUCT_OPS(bictcp_acked, struct sock *sk,
+void BPF_STRUCT_OPS(bpf_cubic_acked, struct sock *sk,
 		    const struct ack_sample *sample)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
@@ -525,7 +525,7 @@ void BPF_STRUCT_OPS(bictcp_acked, struct sock *sk,
 		hystart_update(sk, delay);
 }
 
-__u32 BPF_STRUCT_OPS(tcp_reno_undo_cwnd, struct sock *sk)
+__u32 BPF_STRUCT_OPS(bpf_cubic_undo_cwnd, struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 
@@ -534,12 +534,12 @@ __u32 BPF_STRUCT_OPS(tcp_reno_undo_cwnd, struct sock *sk)
 
 SEC(".struct_ops")
 struct tcp_congestion_ops cubic = {
-	.init		= (void *)bictcp_init,
-	.ssthresh	= (void *)bictcp_recalc_ssthresh,
-	.cong_avoid	= (void *)bictcp_cong_avoid,
-	.set_state	= (void *)bictcp_state,
-	.undo_cwnd	= (void *)tcp_reno_undo_cwnd,
-	.cwnd_event	= (void *)bictcp_cwnd_event,
-	.pkts_acked     = (void *)bictcp_acked,
+	.init		= (void *)bpf_cubic_init,
+	.ssthresh	= (void *)bpf_cubic_recalc_ssthresh,
+	.cong_avoid	= (void *)bpf_cubic_cong_avoid,
+	.set_state	= (void *)bpf_cubic_state,
+	.undo_cwnd	= (void *)bpf_cubic_undo_cwnd,
+	.cwnd_event	= (void *)bpf_cubic_cwnd_event,
+	.pkts_acked     = (void *)bpf_cubic_acked,
 	.name		= "bpf_cubic",
 };
-- 
cgit v1.2.3


From 78e60bbbe8e8f614b6a453d8a780d9e6f77749a8 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 24 Mar 2021 18:52:46 -0700
Subject: bpf: selftests: Bpf_cubic and bpf_dctcp calling kernel functions

This patch removes the bpf implementation of tcp_slow_start()
and tcp_cong_avoid_ai().  Instead, it directly uses the kernel
implementation.

It also replaces the bpf_cubic_undo_cwnd implementation by directly
calling tcp_reno_undo_cwnd().  bpf_dctcp also directly calls
tcp_reno_cong_avoid() instead.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210325015246.1551062-1-kafai@fb.com
---
 tools/testing/selftests/bpf/bpf_tcp_helpers.h | 29 ++-------------------------
 tools/testing/selftests/bpf/progs/bpf_cubic.c |  6 +++---
 tools/testing/selftests/bpf/progs/bpf_dctcp.c | 22 ++++++--------------
 3 files changed, 11 insertions(+), 46 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index 91f0fac632f4..029589c008c9 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -187,16 +187,6 @@ struct tcp_congestion_ops {
 	typeof(y) __y = (y);			\
 	__x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
 
-static __always_inline __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked)
-{
-	__u32 cwnd = min(tp->snd_cwnd + acked, tp->snd_ssthresh);
-
-	acked -= cwnd - tp->snd_cwnd;
-	tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
-
-	return acked;
-}
-
 static __always_inline bool tcp_in_slow_start(const struct tcp_sock *tp)
 {
 	return tp->snd_cwnd < tp->snd_ssthresh;
@@ -213,22 +203,7 @@ static __always_inline bool tcp_is_cwnd_limited(const struct sock *sk)
 	return !!BPF_CORE_READ_BITFIELD(tp, is_cwnd_limited);
 }
 
-static __always_inline void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked)
-{
-	/* If credits accumulated at a higher w, apply them gently now. */
-	if (tp->snd_cwnd_cnt >= w) {
-		tp->snd_cwnd_cnt = 0;
-		tp->snd_cwnd++;
-	}
-
-	tp->snd_cwnd_cnt += acked;
-	if (tp->snd_cwnd_cnt >= w) {
-		__u32 delta = tp->snd_cwnd_cnt / w;
-
-		tp->snd_cwnd_cnt -= delta * w;
-		tp->snd_cwnd += delta;
-	}
-	tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_cwnd_clamp);
-}
+extern __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked) __ksym;
+extern void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked) __ksym;
 
 #endif
diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c
index 33c4d2bded64..f62df4d023f9 100644
--- a/tools/testing/selftests/bpf/progs/bpf_cubic.c
+++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c
@@ -525,11 +525,11 @@ void BPF_STRUCT_OPS(bpf_cubic_acked, struct sock *sk,
 		hystart_update(sk, delay);
 }
 
+extern __u32 tcp_reno_undo_cwnd(struct sock *sk) __ksym;
+
 __u32 BPF_STRUCT_OPS(bpf_cubic_undo_cwnd, struct sock *sk)
 {
-	const struct tcp_sock *tp = tcp_sk(sk);
-
-	return max(tp->snd_cwnd, tp->prior_cwnd);
+	return tcp_reno_undo_cwnd(sk);
 }
 
 SEC(".struct_ops")
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
index 4dc1a967776a..fd42247da8b4 100644
--- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
@@ -194,22 +194,12 @@ __u32 BPF_PROG(dctcp_cwnd_undo, struct sock *sk)
 	return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
 }
 
-SEC("struct_ops/tcp_reno_cong_avoid")
-void BPF_PROG(tcp_reno_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (!tcp_is_cwnd_limited(sk))
-		return;
+extern void tcp_reno_cong_avoid(struct sock *sk, __u32 ack, __u32 acked) __ksym;
 
-	/* In "safe" area, increase. */
-	if (tcp_in_slow_start(tp)) {
-		acked = tcp_slow_start(tp, acked);
-		if (!acked)
-			return;
-	}
-	/* In dangerous area, increase slowly. */
-	tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked);
+SEC("struct_ops/dctcp_reno_cong_avoid")
+void BPF_PROG(dctcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
+{
+	tcp_reno_cong_avoid(sk, ack, acked);
 }
 
 SEC(".struct_ops")
@@ -226,7 +216,7 @@ struct tcp_congestion_ops dctcp = {
 	.in_ack_event   = (void *)dctcp_update_alpha,
 	.cwnd_event	= (void *)dctcp_cwnd_event,
 	.ssthresh	= (void *)dctcp_ssthresh,
-	.cong_avoid	= (void *)tcp_reno_cong_avoid,
+	.cong_avoid	= (void *)dctcp_cong_avoid,
 	.undo_cwnd	= (void *)dctcp_cwnd_undo,
 	.set_state	= (void *)dctcp_state,
 	.flags		= TCP_CONG_NEEDS_ECN,
-- 
cgit v1.2.3


From 7bd1590d4eba1583f6ee85e8cfe556505f761e19 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 24 Mar 2021 18:52:52 -0700
Subject: bpf: selftests: Add kfunc_call test

This patch adds a few kernel function bpf_kfunc_call_test*() for the
selftest's test_run purpose.  They will be allowed for tc_cls prog.

The selftest calling the kernel function bpf_kfunc_call_test*()
is also added in this patch.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210325015252.1551395-1-kafai@fb.com
---
 .../testing/selftests/bpf/prog_tests/kfunc_call.c  | 59 ++++++++++++++++++++++
 .../testing/selftests/bpf/progs/kfunc_call_test.c  | 47 +++++++++++++++++
 .../selftests/bpf/progs/kfunc_call_test_subprog.c  | 42 +++++++++++++++
 3 files changed, 148 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/kfunc_call.c
 create mode 100644 tools/testing/selftests/bpf/progs/kfunc_call_test.c
 create mode 100644 tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
new file mode 100644
index 000000000000..7fc0951ee75f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "kfunc_call_test.skel.h"
+#include "kfunc_call_test_subprog.skel.h"
+
+static void test_main(void)
+{
+	struct kfunc_call_test *skel;
+	int prog_fd, retval, err;
+
+	skel = kfunc_call_test__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel"))
+		return;
+
+	prog_fd = bpf_program__fd(skel->progs.kfunc_call_test1);
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				NULL, NULL, (__u32 *)&retval, NULL);
+	ASSERT_OK(err, "bpf_prog_test_run(test1)");
+	ASSERT_EQ(retval, 12, "test1-retval");
+
+	prog_fd = bpf_program__fd(skel->progs.kfunc_call_test2);
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				NULL, NULL, (__u32 *)&retval, NULL);
+	ASSERT_OK(err, "bpf_prog_test_run(test2)");
+	ASSERT_EQ(retval, 3, "test2-retval");
+
+	kfunc_call_test__destroy(skel);
+}
+
+static void test_subprog(void)
+{
+	struct kfunc_call_test_subprog *skel;
+	int prog_fd, retval, err;
+
+	skel = kfunc_call_test_subprog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel"))
+		return;
+
+	prog_fd = bpf_program__fd(skel->progs.kfunc_call_test1);
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				NULL, NULL, (__u32 *)&retval, NULL);
+	ASSERT_OK(err, "bpf_prog_test_run(test1)");
+	ASSERT_EQ(retval, 10, "test1-retval");
+	ASSERT_NEQ(skel->data->active_res, -1, "active_res");
+	ASSERT_EQ(skel->data->sk_state, BPF_TCP_CLOSE, "sk_state");
+
+	kfunc_call_test_subprog__destroy(skel);
+}
+
+void test_kfunc_call(void)
+{
+	if (test__start_subtest("main"))
+		test_main();
+
+	if (test__start_subtest("subprog"))
+		test_subprog();
+}
diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c
new file mode 100644
index 000000000000..470f8723e463
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_tcp_helpers.h"
+
+extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym;
+extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b,
+				  __u32 c, __u64 d) __ksym;
+
+SEC("classifier")
+int kfunc_call_test2(struct __sk_buff *skb)
+{
+	struct bpf_sock *sk = skb->sk;
+
+	if (!sk)
+		return -1;
+
+	sk = bpf_sk_fullsock(sk);
+	if (!sk)
+		return -1;
+
+	return bpf_kfunc_call_test2((struct sock *)sk, 1, 2);
+}
+
+SEC("classifier")
+int kfunc_call_test1(struct __sk_buff *skb)
+{
+	struct bpf_sock *sk = skb->sk;
+	__u64 a = 1ULL << 32;
+	__u32 ret;
+
+	if (!sk)
+		return -1;
+
+	sk = bpf_sk_fullsock(sk);
+	if (!sk)
+		return -1;
+
+	a = bpf_kfunc_call_test1((struct sock *)sk, 1, a | 2, 3, a | 4);
+	ret = a >> 32;   /* ret should be 2 */
+	ret += (__u32)a; /* ret should be 12 */
+
+	return ret;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c
new file mode 100644
index 000000000000..b2dcb7d9cb03
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_tcp_helpers.h"
+
+extern const int bpf_prog_active __ksym;
+extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b,
+				  __u32 c, __u64 d) __ksym;
+extern struct sock *bpf_kfunc_call_test3(struct sock *sk) __ksym;
+int active_res = -1;
+int sk_state = -1;
+
+int __noinline f1(struct __sk_buff *skb)
+{
+	struct bpf_sock *sk = skb->sk;
+	int *active;
+
+	if (!sk)
+		return -1;
+
+	sk = bpf_sk_fullsock(sk);
+	if (!sk)
+		return -1;
+
+	active = (int *)bpf_per_cpu_ptr(&bpf_prog_active,
+					bpf_get_smp_processor_id());
+	if (active)
+		active_res = *active;
+
+	sk_state = bpf_kfunc_call_test3((struct sock *)sk)->__sk_common.skc_state;
+
+	return (__u32)bpf_kfunc_call_test1((struct sock *)sk, 1, 2, 3, 4);
+}
+
+SEC("classifier")
+int kfunc_call_test1(struct __sk_buff *skb)
+{
+	return f1(skb);
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 2ba4badca9977b64c966b0177920daadbd5501fe Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Mon, 29 Mar 2021 22:41:56 -0700
Subject: bpf: selftests: Update clang requirement in README.rst for testing
 kfunc call

This patch updates the README.rst to specify the clang requirement
to compile the bpf selftests that call kernel function.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20210330054156.2933804-1-kafai@fb.com
---
 tools/testing/selftests/bpf/README.rst | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index 3464161c8eea..65fe318d1e71 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -179,3 +179,17 @@ types, which was introduced in `Clang 13`__. The older Clang versions will
 either crash when compiling these tests, or generate an incorrect BTF.
 
 __  https://reviews.llvm.org/D83289
+
+Kernel function call test and Clang version
+===========================================
+
+Some selftests (e.g. kfunc_call and bpf_tcp_ca) require a LLVM support
+to generate extern function in BTF.  It was introduced in `Clang 13`__.
+
+Without it, the error from compiling bpf selftests looks like:
+
+.. code-block:: console
+
+  libbpf: failed to find BTF for extern 'tcp_slow_start' [25] section: -2
+
+__ https://reviews.llvm.org/D93563
-- 
cgit v1.2.3


From 9f33df73a929ed91dddad036f518d690b3094eda Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:00 +0200
Subject: selftests: xsk: Don't call worker_pkt_dump() for stats test

For TEST_TYPE_STATS, worker_pkt_validate() that places frames onto
pkt_buf is not called. Therefore, when dump mode is set, don't call
worker_pkt_dump() for mentioned test type, so that it won't crash on
pkt_buf() access.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-2-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 1e21a3172687..09429ed2ddf6 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -999,7 +999,7 @@ static void testapp_validate(void)
 	pthread_join(t1, NULL);
 	pthread_join(t0, NULL);
 
-	if (debug_pkt_dump) {
+	if (debug_pkt_dump && test_type != TEST_TYPE_STATS) {
 		worker_pkt_dump();
 		for (int iter = 0; iter < num_frames - 1; iter++) {
 			free(pkt_buf[iter]->payload);
-- 
cgit v1.2.3


From e623bfdef713ddda1b9f57d1759df3a1cd97255a Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:01 +0200
Subject: selftests: xsk: Remove struct ifaceconfigobj

ifaceconfigobj is not really useful, it is possible to keep the
functionality and simplify the code.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-3-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 65 +++++++++++++++-----------------
 tools/testing/selftests/bpf/xdpxceiver.h |  9 -----
 2 files changed, 30 insertions(+), 44 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 09429ed2ddf6..e2ff3cd48ccf 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -93,6 +93,13 @@ typedef __u16 __sum16;
 #include "xdpxceiver.h"
 #include "../kselftest.h"
 
+static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62";
+static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61";
+static const char *IP1 = "192.168.100.162";
+static const char *IP2 = "192.168.100.161";
+static const u16 UDP_PORT1 = 2020;
+static const u16 UDP_PORT2 = 2121;
+
 static void __exit_with_error(int error, const char *file, const char *func, int line)
 {
 	if (configured_mode == TEST_MODE_UNCONFIGURED) {
@@ -1053,25 +1060,24 @@ static void testapp_stats(void)
 	print_ksft_result();
 }
 
-static void init_iface_config(struct ifaceconfigobj *ifaceconfig)
+static void init_iface(struct ifobject *ifobj, const char *dst_mac,
+		       const char *src_mac, const char *dst_ip,
+		       const char *src_ip, const u16 dst_port,
+		       const u16 src_port)
 {
-	/*Init interface0 */
-	ifdict[0]->fv.vector = tx;
-	memcpy(ifdict[0]->dst_mac, ifaceconfig->dst_mac, ETH_ALEN);
-	memcpy(ifdict[0]->src_mac, ifaceconfig->src_mac, ETH_ALEN);
-	ifdict[0]->dst_ip = ifaceconfig->dst_ip.s_addr;
-	ifdict[0]->src_ip = ifaceconfig->src_ip.s_addr;
-	ifdict[0]->dst_port = ifaceconfig->dst_port;
-	ifdict[0]->src_port = ifaceconfig->src_port;
-
-	/*Init interface1 */
-	ifdict[1]->fv.vector = rx;
-	memcpy(ifdict[1]->dst_mac, ifaceconfig->src_mac, ETH_ALEN);
-	memcpy(ifdict[1]->src_mac, ifaceconfig->dst_mac, ETH_ALEN);
-	ifdict[1]->dst_ip = ifaceconfig->src_ip.s_addr;
-	ifdict[1]->src_ip = ifaceconfig->dst_ip.s_addr;
-	ifdict[1]->dst_port = ifaceconfig->src_port;
-	ifdict[1]->src_port = ifaceconfig->dst_port;
+	struct in_addr ip;
+
+	memcpy(ifobj->dst_mac, dst_mac, ETH_ALEN);
+	memcpy(ifobj->src_mac, src_mac, ETH_ALEN);
+
+	inet_aton(dst_ip, &ip);
+	ifobj->dst_ip = ip.s_addr;
+
+	inet_aton(src_ip, &ip);
+	ifobj->src_ip = ip.s_addr;
+
+	ifobj->dst_port = dst_port;
+	ifobj->src_port = src_port;
 }
 
 static void *nsdisablemodethread(void *args)
@@ -1175,26 +1181,11 @@ static void run_pkt_test(int mode, int type)
 int main(int argc, char **argv)
 {
 	struct rlimit _rlim = { RLIM_INFINITY, RLIM_INFINITY };
+	int i, j;
 
 	if (setrlimit(RLIMIT_MEMLOCK, &_rlim))
 		exit_with_error(errno);
 
-	const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62";
-	const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61";
-	const char *IP1 = "192.168.100.162";
-	const char *IP2 = "192.168.100.161";
-	u16 UDP_DST_PORT = 2020;
-	u16 UDP_SRC_PORT = 2121;
-	int i, j;
-
-	ifaceconfig = malloc(sizeof(struct ifaceconfigobj));
-	memcpy(ifaceconfig->dst_mac, MAC1, ETH_ALEN);
-	memcpy(ifaceconfig->src_mac, MAC2, ETH_ALEN);
-	inet_aton(IP1, &ifaceconfig->dst_ip);
-	inet_aton(IP2, &ifaceconfig->src_ip);
-	ifaceconfig->dst_port = UDP_DST_PORT;
-	ifaceconfig->src_port = UDP_SRC_PORT;
-
 	for (int i = 0; i < MAX_INTERFACES; i++) {
 		ifdict[i] = malloc(sizeof(struct ifobject));
 		if (!ifdict[i])
@@ -1209,7 +1200,11 @@ int main(int argc, char **argv)
 
 	num_frames = ++opt_pkt_count;
 
-	init_iface_config(ifaceconfig);
+	ifdict[0]->fv.vector = tx;
+	init_iface(ifdict[0], MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2);
+
+	ifdict[1]->fv.vector = rx;
+	init_iface(ifdict[1], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1);
 
 	disable_xdp_mode(XDP_FLAGS_DRV_MODE);
 
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 30314ef305c2..8f9308099318 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -125,15 +125,6 @@ struct generic_data {
 	u32 seqnum;
 };
 
-struct ifaceconfigobj {
-	u8 dst_mac[ETH_ALEN];
-	u8 src_mac[ETH_ALEN];
-	struct in_addr dst_ip;
-	struct in_addr src_ip;
-	u16 src_port;
-	u16 dst_port;
-} *ifaceconfig;
-
 struct ifobject {
 	int ifindex;
 	int ifdict_index;
-- 
cgit v1.2.3


From 7519c387e69d367075bf493de8a9ea427c9d2a1b Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:02 +0200
Subject: selftests: xsk: Remove unused function

Probably it was ported from xdpsock but is not used anywhere.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-4-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 13 -------------
 1 file changed, 13 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index e2ff3cd48ccf..593e8be41fce 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -153,19 +153,6 @@ static void *memset32_htonl(void *dest, u32 val, u32 size)
 	return dest;
 }
 
-/*
- * This function code has been taken from
- * Linux kernel lib/checksum.c
- */
-static inline unsigned short from32to16(unsigned int x)
-{
-	/* add up 16-bit and 16-bit for 16+c bit */
-	x = (x & 0xffff) + (x >> 16);
-	/* add up carry.. */
-	x = (x & 0xffff) + (x >> 16);
-	return x;
-}
-
 /*
  * Fold a partial checksum
  * This function code has been taken from
-- 
cgit v1.2.3


From 965d2cb0f675e5f60af441c9bd430c284d66179d Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:03 +0200
Subject: selftests: xsk: Remove inline keyword from source file

Follow the kernel coding style guidelines and let compiler do the
decision about inlining.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-5-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 593e8be41fce..77880abd818c 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -158,7 +158,7 @@ static void *memset32_htonl(void *dest, u32 val, u32 size)
  * This function code has been taken from
  * Linux kernel include/asm-generic/checksum.h
  */
-static inline __u16 csum_fold(__u32 csum)
+static __u16 csum_fold(__u32 csum)
 {
 	u32 sum = (__force u32)csum;
 
@@ -171,7 +171,7 @@ static inline __u16 csum_fold(__u32 csum)
  * This function code has been taken from
  * Linux kernel lib/checksum.c
  */
-static inline u32 from64to32(u64 x)
+static u32 from64to32(u64 x)
 {
 	/* add up 32-bit and 32-bit for 32+c bit */
 	x = (x & 0xffffffff) + (x >> 32);
@@ -180,13 +180,11 @@ static inline u32 from64to32(u64 x)
 	return (u32)x;
 }
 
-__u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum);
-
 /*
  * This function code has been taken from
  * Linux kernel lib/checksum.c
  */
-__u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
+static __u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
 {
 	unsigned long long s = (__force u32)sum;
 
@@ -204,13 +202,12 @@ __u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u3
  * This function has been taken from
  * Linux kernel include/asm-generic/checksum.h
  */
-static inline __u16
-csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
+static __u16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
 }
 
-static inline u16 udp_csum(u32 saddr, u32 daddr, u32 len, u8 proto, u16 *udp_pkt)
+static u16 udp_csum(u32 saddr, u32 daddr, u32 len, u8 proto, u16 *udp_pkt)
 {
 	u32 csum = 0;
 	u32 cnt = 0;
@@ -500,7 +497,7 @@ static void kick_tx(struct xsk_socket_info *xsk)
 	exit_with_error(errno);
 }
 
-static inline void complete_tx_only(struct xsk_socket_info *xsk, int batch_size)
+static void complete_tx_only(struct xsk_socket_info *xsk, int batch_size)
 {
 	unsigned int rcvd;
 	u32 idx;
@@ -605,7 +602,7 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frameptr, int batch_size)
 	complete_tx_only(xsk, batch_size);
 }
 
-static inline int get_batch_size(int pkt_cnt)
+static int get_batch_size(int pkt_cnt)
 {
 	if (!opt_pkt_count)
 		return BATCH_SIZE;
-- 
cgit v1.2.3


From aa2d61c154f9387883664e3873bc0700419640a3 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:04 +0200
Subject: selftests: xsk: Simplify frame traversal in dumping thread
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Store offsets to each layer in a separate variables rather than compute
them every single time.

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-6-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 47 ++++++++++++++------------------
 1 file changed, 21 insertions(+), 26 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 77880abd818c..ae2f7d71f041 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -658,45 +658,40 @@ static void tx_only_all(struct ifobject *ifobject)
 
 static void worker_pkt_dump(void)
 {
-	struct in_addr ipaddr;
+	struct ethhdr *ethhdr;
+	struct iphdr *iphdr;
+	struct udphdr *udphdr;
+	char s[128];
+	int payload;
+	void *ptr;
 
 	fprintf(stdout, "---------------------------------------\n");
 	for (int iter = 0; iter < num_frames - 1; iter++) {
+		ptr = pkt_buf[iter]->payload;
+		ethhdr = ptr;
+		iphdr = ptr + sizeof(*ethhdr);
+		udphdr = ptr + sizeof(*ethhdr) + sizeof(*iphdr);
+
 		/*extract L2 frame */
 		fprintf(stdout, "DEBUG>> L2: dst mac: ");
 		for (int i = 0; i < ETH_ALEN; i++)
-			fprintf(stdout, "%02X", ((struct ethhdr *)
-						 pkt_buf[iter]->payload)->h_dest[i]);
+			fprintf(stdout, "%02X", ethhdr->h_dest[i]);
 
 		fprintf(stdout, "\nDEBUG>> L2: src mac: ");
 		for (int i = 0; i < ETH_ALEN; i++)
-			fprintf(stdout, "%02X", ((struct ethhdr *)
-						 pkt_buf[iter]->payload)->h_source[i]);
+			fprintf(stdout, "%02X", ethhdr->h_source[i]);
 
 		/*extract L3 frame */
-		fprintf(stdout, "\nDEBUG>> L3: ip_hdr->ihl: %02X\n",
-			((struct iphdr *)(pkt_buf[iter]->payload + sizeof(struct ethhdr)))->ihl);
-
-		ipaddr.s_addr =
-		    ((struct iphdr *)(pkt_buf[iter]->payload + sizeof(struct ethhdr)))->saddr;
-		fprintf(stdout, "DEBUG>> L3: ip_hdr->saddr: %s\n", inet_ntoa(ipaddr));
-
-		ipaddr.s_addr =
-		    ((struct iphdr *)(pkt_buf[iter]->payload + sizeof(struct ethhdr)))->daddr;
-		fprintf(stdout, "DEBUG>> L3: ip_hdr->daddr: %s\n", inet_ntoa(ipaddr));
-
+		fprintf(stdout, "\nDEBUG>> L3: ip_hdr->ihl: %02X\n", iphdr->ihl);
+		fprintf(stdout, "DEBUG>> L3: ip_hdr->saddr: %s\n",
+			inet_ntop(AF_INET, &iphdr->saddr, s, sizeof(s)));
+		fprintf(stdout, "DEBUG>> L3: ip_hdr->daddr: %s\n",
+			inet_ntop(AF_INET, &iphdr->daddr, s, sizeof(s)));
 		/*extract L4 frame */
-		fprintf(stdout, "DEBUG>> L4: udp_hdr->src: %d\n",
-			ntohs(((struct udphdr *)(pkt_buf[iter]->payload +
-						 sizeof(struct ethhdr) +
-						 sizeof(struct iphdr)))->source));
-
-		fprintf(stdout, "DEBUG>> L4: udp_hdr->dst: %d\n",
-			ntohs(((struct udphdr *)(pkt_buf[iter]->payload +
-						 sizeof(struct ethhdr) +
-						 sizeof(struct iphdr)))->dest));
+		fprintf(stdout, "DEBUG>> L4: udp_hdr->src: %d\n", ntohs(udphdr->source));
+		fprintf(stdout, "DEBUG>> L4: udp_hdr->dst: %d\n", ntohs(udphdr->dest));
 		/*extract L5 frame */
-		int payload = *((uint32_t *)(pkt_buf[iter]->payload + PKT_HDR_SIZE));
+		payload = *((uint32_t *)(ptr + PKT_HDR_SIZE));
 
 		if (payload == EOT) {
 			print_verbose("End-of-transmission frame received\n");
-- 
cgit v1.2.3


From ef9280789773c974b45f809d58b47b481f2cf9f5 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:07 +0200
Subject: selftests: xsk: Remove thread for netns switch

Currently, there is a dedicated thread for following remote ns operations:
- grabbing the ifindex of the interface moved to remote netns
- removing xdp prog from that interface

With bpf_link usage in place, this can be simply omitted, so remove
mentioned thread, as BPF resources will be managed by bpf_link itself,
so there's no further need for creating the thread that will switch to
remote netns and do the cleanup.

Keep most of the logic for switching the ns, though, but make
switch_namespace() return the fd so that it will be possible to close it
at the process termination time. Get rid of logic around making sure
that it's possible to switch ns in validate_interfaces().

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-9-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 123 +++----------------------------
 tools/testing/selftests/bpf/xdpxceiver.h |  10 +--
 2 files changed, 14 insertions(+), 119 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index ae2f7d71f041..a856b2935d66 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -355,12 +355,15 @@ static void usage(const char *prog)
 	ksft_print_msg(str, prog);
 }
 
-static bool switch_namespace(int idx)
+static int switch_namespace(const char *nsname)
 {
 	char fqns[26] = "/var/run/netns/";
 	int nsfd;
 
-	strncat(fqns, ifdict[idx]->nsname, sizeof(fqns) - strlen(fqns) - 1);
+	if (!nsname || strlen(nsname) == 0)
+		return -1;
+
+	strncat(fqns, nsname, sizeof(fqns) - strlen(fqns) - 1);
 	nsfd = open(fqns, O_RDONLY);
 
 	if (nsfd == -1)
@@ -369,26 +372,9 @@ static bool switch_namespace(int idx)
 	if (setns(nsfd, 0) == -1)
 		exit_with_error(errno);
 
-	return true;
-}
-
-static void *nsswitchthread(void *args)
-{
-	struct targs *targs = args;
+	print_verbose("NS switched: %s\n", nsname);
 
-	targs->retptr = false;
-
-	if (switch_namespace(targs->idx)) {
-		ifdict[targs->idx]->ifindex = if_nametoindex(ifdict[targs->idx]->ifname);
-		if (!ifdict[targs->idx]->ifindex) {
-			ksft_test_result_fail("ERROR: [%s] interface \"%s\" does not exist\n",
-					      __func__, ifdict[targs->idx]->ifname);
-		} else {
-			print_verbose("Interface found: %s\n", ifdict[targs->idx]->ifname);
-			targs->retptr = true;
-		}
-	}
-	pthread_exit(NULL);
+	return nsfd;
 }
 
 static int validate_interfaces(void)
@@ -400,33 +386,6 @@ static int validate_interfaces(void)
 			ret = false;
 			ksft_test_result_fail("ERROR: interfaces: -i <int>,<ns> -i <int>,<ns>.");
 		}
-		if (strcmp(ifdict[i]->nsname, "")) {
-			struct targs *targs;
-
-			targs = malloc(sizeof(*targs));
-			if (!targs)
-				exit_with_error(errno);
-
-			targs->idx = i;
-			if (pthread_create(&ns_thread, NULL, nsswitchthread, targs))
-				exit_with_error(errno);
-
-			pthread_join(ns_thread, NULL);
-
-			if (targs->retptr)
-				print_verbose("NS switched: %s\n", ifdict[i]->nsname);
-
-			free(targs);
-		} else {
-			ifdict[i]->ifindex = if_nametoindex(ifdict[i]->ifname);
-			if (!ifdict[i]->ifindex) {
-				ksft_test_result_fail
-				    ("ERROR: interface \"%s\" does not exist\n", ifdict[i]->ifname);
-				ret = false;
-			} else {
-				print_verbose("Interface found: %s\n", ifdict[i]->ifname);
-			}
-		}
 	}
 	return ret;
 }
@@ -843,8 +802,7 @@ static void *worker_testapp_validate(void *arg)
 		if (bufs == MAP_FAILED)
 			exit_with_error(errno);
 
-		if (strcmp(ifobject->nsname, ""))
-			switch_namespace(ifobject->ifdict_index);
+		ifobject->ns_fd = switch_namespace(ifobject->nsname);
 	}
 
 	if (ifobject->fv.vector == tx) {
@@ -1059,60 +1017,6 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac,
 	ifobj->src_port = src_port;
 }
 
-static void *nsdisablemodethread(void *args)
-{
-	struct targs *targs = args;
-
-	targs->retptr = false;
-
-	if (switch_namespace(targs->idx)) {
-		targs->retptr = bpf_set_link_xdp_fd(ifdict[targs->idx]->ifindex, -1, targs->flags);
-	} else {
-		targs->retptr = errno;
-		print_verbose("Failed to switch namespace to %s\n", ifdict[targs->idx]->nsname);
-	}
-
-	pthread_exit(NULL);
-}
-
-static void disable_xdp_mode(int mode)
-{
-	int err = 0;
-	__u32 flags = XDP_FLAGS_UPDATE_IF_NOEXIST | mode;
-	char *mode_str = mode & XDP_FLAGS_SKB_MODE ? "skb" : "drv";
-
-	for (int i = 0; i < MAX_INTERFACES; i++) {
-		if (strcmp(ifdict[i]->nsname, "")) {
-			struct targs *targs;
-
-			targs = malloc(sizeof(*targs));
-			memset(targs, 0, sizeof(*targs));
-			if (!targs)
-				exit_with_error(errno);
-
-			targs->idx = i;
-			targs->flags = flags;
-			if (pthread_create(&ns_thread, NULL, nsdisablemodethread, targs))
-				exit_with_error(errno);
-
-			pthread_join(ns_thread, NULL);
-			err = targs->retptr;
-			free(targs);
-		} else {
-			err = bpf_set_link_xdp_fd(ifdict[i]->ifindex, -1, flags);
-		}
-
-		if (err) {
-			print_verbose("Failed to disable %s mode on interface %s\n",
-						mode_str, ifdict[i]->ifname);
-			exit_with_error(err);
-		}
-
-		print_verbose("Disabled %s mode for interface: %s\n", mode_str, ifdict[i]->ifname);
-		configured_mode = mode & XDP_FLAGS_SKB_MODE ? TEST_MODE_DRV : TEST_MODE_SKB;
-	}
-}
-
 static void run_pkt_test(int mode, int type)
 {
 	test_type = type;
@@ -1132,13 +1036,9 @@ static void run_pkt_test(int mode, int type)
 
 	switch (mode) {
 	case (TEST_MODE_SKB):
-		if (configured_mode == TEST_MODE_DRV)
-			disable_xdp_mode(XDP_FLAGS_DRV_MODE);
 		xdp_flags |= XDP_FLAGS_SKB_MODE;
 		break;
 	case (TEST_MODE_DRV):
-		if (configured_mode == TEST_MODE_SKB)
-			disable_xdp_mode(XDP_FLAGS_SKB_MODE);
 		xdp_flags |= XDP_FLAGS_DRV_MODE;
 		break;
 	default:
@@ -1185,8 +1085,6 @@ int main(int argc, char **argv)
 	ifdict[1]->fv.vector = rx;
 	init_iface(ifdict[1], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1);
 
-	disable_xdp_mode(XDP_FLAGS_DRV_MODE);
-
 	ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX);
 
 	for (i = 0; i < TEST_MODE_MAX; i++) {
@@ -1194,8 +1092,11 @@ int main(int argc, char **argv)
 			run_pkt_test(i, j);
 	}
 
-	for (int i = 0; i < MAX_INTERFACES; i++)
+	for (int i = 0; i < MAX_INTERFACES; i++) {
+		if (ifdict[i]->ns_fd != -1)
+			close(ifdict[i]->ns_fd);
 		free(ifdict[i]);
+	}
 
 	ksft_exit_pass();
 
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 8f9308099318..493f7498d40e 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -126,7 +126,7 @@ struct generic_data {
 };
 
 struct ifobject {
-	int ifindex;
+	int ns_fd;
 	int ifdict_index;
 	char ifname[MAX_INTERFACE_NAME_CHARS];
 	char nsname[MAX_INTERFACES_NAMESPACE_CHARS];
@@ -150,15 +150,9 @@ pthread_mutex_t sync_mutex;
 pthread_mutex_t sync_mutex_tx;
 pthread_cond_t signal_rx_condition;
 pthread_cond_t signal_tx_condition;
-pthread_t t0, t1, ns_thread;
+pthread_t t0, t1;
 pthread_attr_t attr;
 
-struct targs {
-	u8 retptr;
-	int idx;
-	u32 flags;
-};
-
 TAILQ_HEAD(head_s, pkt) head = TAILQ_HEAD_INITIALIZER(head);
 struct head_s *head_p;
 struct pkt {
-- 
cgit v1.2.3


From 9866bcd6635c264aaf3de1d89e44773a269048eb Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:08 +0200
Subject: selftests: xsk: Split worker thread

Let's a have a separate Tx/Rx worker threads instead of a one common
thread packed with Tx/Rx specific checks.

Move mmap for umem buffer space and a switch_namespace() call to
thread_common_ops.

This also allows for a bunch of simplifactions that are the subject of
the next commits. The final result will be a code base that is much
easier to follow.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-10-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 156 +++++++++++++++----------------
 1 file changed, 77 insertions(+), 79 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index a856b2935d66..cb6583b8ad67 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -760,6 +760,15 @@ static void thread_common_ops(struct ifobject *ifobject, void *bufs, pthread_mut
 	int ctr = 0;
 	int ret;
 
+	pthread_attr_setstacksize(&attr, THREAD_STACK);
+
+	bufs = mmap(NULL, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE,
+		    PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	if (bufs == MAP_FAILED)
+		exit_with_error(errno);
+
+	ifobject->ns_fd = switch_namespace(ifobject->nsname);
+
 	xsk_configure_umem(ifobject, bufs, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE);
 	ret = xsk_configure_socket(ifobject);
 
@@ -782,9 +791,12 @@ static void thread_common_ops(struct ifobject *ifobject, void *bufs, pthread_mut
 
 	if (ctr >= SOCK_RECONF_CTR)
 		exit_with_error(ret);
+
+	print_verbose("Interface [%s] vector [%s]\n",
+		      ifobject->ifname, ifobject->fv.vector == tx ? "Tx" : "Rx");
 }
 
-static void *worker_testapp_validate(void *arg)
+static void *worker_testapp_validate_tx(void *arg)
 {
 	struct udphdr *udp_hdr =
 	    (struct udphdr *)(pkt_data + sizeof(struct ethhdr) + sizeof(struct iphdr));
@@ -792,97 +804,83 @@ static void *worker_testapp_validate(void *arg)
 	struct ethhdr *eth_hdr = (struct ethhdr *)pkt_data;
 	struct ifobject *ifobject = (struct ifobject *)arg;
 	struct generic_data data;
+	int spinningrxctr = 0;
 	void *bufs = NULL;
 
-	pthread_attr_setstacksize(&attr, THREAD_STACK);
-
-	if (!bidi_pass) {
-		bufs = mmap(NULL, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE,
-			    PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
-		if (bufs == MAP_FAILED)
-			exit_with_error(errno);
+	if (!bidi_pass)
+		thread_common_ops(ifobject, bufs, &sync_mutex_tx, &spinning_tx);
 
-		ifobject->ns_fd = switch_namespace(ifobject->nsname);
+	while (atomic_load(&spinning_rx) && spinningrxctr < SOCK_RECONF_CTR) {
+		spinningrxctr++;
+		usleep(USLEEP_MAX);
 	}
 
-	if (ifobject->fv.vector == tx) {
-		int spinningrxctr = 0;
+	for (int i = 0; i < num_frames; i++) {
+		/*send EOT frame */
+		if (i == (num_frames - 1))
+			data.seqnum = -1;
+		else
+			data.seqnum = i;
+		gen_udp_hdr(&data, ifobject, udp_hdr);
+		gen_ip_hdr(ifobject, ip_hdr);
+		gen_udp_csum(udp_hdr, ip_hdr);
+		gen_eth_hdr(ifobject, eth_hdr);
+		gen_eth_frame(ifobject->umem, i * XSK_UMEM__DEFAULT_FRAME_SIZE);
+	}
 
-		if (!bidi_pass)
-			thread_common_ops(ifobject, bufs, &sync_mutex_tx, &spinning_tx);
+	print_verbose("Sending %d packets on interface %s\n",
+		      (opt_pkt_count - 1), ifobject->ifname);
+	tx_only_all(ifobject);
 
-		while (atomic_load(&spinning_rx) && spinningrxctr < SOCK_RECONF_CTR) {
-			spinningrxctr++;
-			usleep(USLEEP_MAX);
-		}
+	if (test_type != TEST_TYPE_BIDI || bidi_pass) {
+		xsk_socket__delete(ifobject->xsk->xsk);
+		(void)xsk_umem__delete(ifobject->umem->umem);
+	}
+	pthread_exit(NULL);
+}
 
-		print_verbose("Interface [%s] vector [Tx]\n", ifobject->ifname);
-		for (int i = 0; i < num_frames; i++) {
-			/*send EOT frame */
-			if (i == (num_frames - 1))
-				data.seqnum = -1;
-			else
-				data.seqnum = i;
-			gen_udp_hdr(&data, ifobject, udp_hdr);
-			gen_ip_hdr(ifobject, ip_hdr);
-			gen_udp_csum(udp_hdr, ip_hdr);
-			gen_eth_hdr(ifobject, eth_hdr);
-			gen_eth_frame(ifobject->umem, i * XSK_UMEM__DEFAULT_FRAME_SIZE);
-		}
+static void *worker_testapp_validate_rx(void *arg)
+{
+	struct ifobject *ifobject = (struct ifobject *)arg;
+	struct pollfd fds[MAX_SOCKS] = { };
+	void *bufs = NULL;
 
-		print_verbose("Sending %d packets on interface %s\n",
-			       (opt_pkt_count - 1), ifobject->ifname);
-		tx_only_all(ifobject);
-	} else if (ifobject->fv.vector == rx) {
-		struct pollfd fds[MAX_SOCKS] = { };
-		int ret;
-
-		if (!bidi_pass)
-			thread_common_ops(ifobject, bufs, &sync_mutex_tx, &spinning_rx);
-
-		print_verbose("Interface [%s] vector [Rx]\n", ifobject->ifname);
-		if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
-			xsk_populate_fill_ring(ifobject->umem);
-
-		TAILQ_INIT(&head);
-		if (debug_pkt_dump) {
-			pkt_buf = calloc(num_frames, sizeof(*pkt_buf));
-			if (!pkt_buf)
-				exit_with_error(errno);
-		}
+	if (!bidi_pass)
+		thread_common_ops(ifobject, bufs, &sync_mutex_tx, &spinning_rx);
 
-		fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk);
-		fds[0].events = POLLIN;
+	if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
+		xsk_populate_fill_ring(ifobject->umem);
 
-		pthread_mutex_lock(&sync_mutex);
-		pthread_cond_signal(&signal_rx_condition);
-		pthread_mutex_unlock(&sync_mutex);
+	TAILQ_INIT(&head);
+	if (debug_pkt_dump) {
+		pkt_buf = calloc(num_frames, sizeof(*pkt_buf));
+		if (!pkt_buf)
+			exit_with_error(errno);
+	}
 
-		while (1) {
-			if (test_type == TEST_TYPE_POLL) {
-				ret = poll(fds, 1, POLL_TMOUT);
-				if (ret <= 0)
-					continue;
-			}
+	fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk);
+	fds[0].events = POLLIN;
 
-			if (test_type != TEST_TYPE_STATS) {
-				rx_pkt(ifobject->xsk, fds);
-				worker_pkt_validate();
-			} else {
-				worker_stats_validate(ifobject);
-			}
+	pthread_mutex_lock(&sync_mutex);
+	pthread_cond_signal(&signal_rx_condition);
+	pthread_mutex_unlock(&sync_mutex);
 
-			if (sigvar)
-				break;
+	while (1) {
+		if (test_type != TEST_TYPE_STATS) {
+			rx_pkt(ifobject->xsk, fds);
+			worker_pkt_validate();
+		} else {
+			worker_stats_validate(ifobject);
 		}
+		if (sigvar)
+			break;
+	}
 
-		if (test_type != TEST_TYPE_STATS)
-			print_verbose("Received %d packets on interface %s\n",
-				pkt_counter, ifobject->ifname);
+	print_verbose("Received %d packets on interface %s\n",
+		      pkt_counter, ifobject->ifname);
 
-		if (test_type == TEST_TYPE_TEARDOWN)
-			print_verbose("Destroying socket\n");
-	}
+	if (test_type == TEST_TYPE_TEARDOWN)
+		print_verbose("Destroying socket\n");
 
 	if ((test_type != TEST_TYPE_BIDI) || bidi_pass) {
 		xsk_socket__delete(ifobject->xsk->xsk);
@@ -911,12 +909,12 @@ static void testapp_validate(void)
 
 	/*Spawn RX thread */
 	if (!bidi || !bidi_pass) {
-		if (pthread_create(&t0, &attr, worker_testapp_validate, ifdict[1]))
+		if (pthread_create(&t0, &attr, worker_testapp_validate_rx, ifdict[1]))
 			exit_with_error(errno);
 	} else if (bidi && bidi_pass) {
 		/*switch Tx/Rx vectors */
 		ifdict[0]->fv.vector = rx;
-		if (pthread_create(&t0, &attr, worker_testapp_validate, ifdict[0]))
+		if (pthread_create(&t0, &attr, worker_testapp_validate_rx, ifdict[0]))
 			exit_with_error(errno);
 	}
 
@@ -931,12 +929,12 @@ static void testapp_validate(void)
 
 	/*Spawn TX thread */
 	if (!bidi || !bidi_pass) {
-		if (pthread_create(&t1, &attr, worker_testapp_validate, ifdict[0]))
+		if (pthread_create(&t1, &attr, worker_testapp_validate_tx, ifdict[0]))
 			exit_with_error(errno);
 	} else if (bidi && bidi_pass) {
 		/*switch Tx/Rx vectors */
 		ifdict[1]->fv.vector = tx;
-		if (pthread_create(&t1, &attr, worker_testapp_validate, ifdict[1]))
+		if (pthread_create(&t1, &attr, worker_testapp_validate_tx, ifdict[1]))
 			exit_with_error(errno);
 	}
 
-- 
cgit v1.2.3


From 99f9bcb65705dda07288b759c569d30d8a4f297c Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:09 +0200
Subject: selftests: xsk: Remove Tx synchronization resources

Tx thread needs to be started after the Rx side is fully initialized so
that packets are not xmitted until xsk Rx socket is ready to be used.

It can be observed that atomic variable spinning_tx is not checked from
Rx side in any way, so thread_common_ops can be modified to only address
the spinning_rx. This means that spinning_tx can be removed altogheter.

signal_tx_condition is never utilized, so simply remove it.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-11-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 15 +++++++--------
 tools/testing/selftests/bpf/xdpxceiver.h |  2 --
 2 files changed, 7 insertions(+), 10 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index cb6583b8ad67..9f7ee9a38752 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -126,7 +126,6 @@ static void pthread_init_mutex(void)
 	pthread_mutex_init(&sync_mutex, NULL);
 	pthread_mutex_init(&sync_mutex_tx, NULL);
 	pthread_cond_init(&signal_rx_condition, NULL);
-	pthread_cond_init(&signal_tx_condition, NULL);
 }
 
 static void pthread_destroy_mutex(void)
@@ -134,7 +133,6 @@ static void pthread_destroy_mutex(void)
 	pthread_mutex_destroy(&sync_mutex);
 	pthread_mutex_destroy(&sync_mutex_tx);
 	pthread_cond_destroy(&signal_rx_condition);
-	pthread_cond_destroy(&signal_tx_condition);
 }
 
 static void *memset32_htonl(void *dest, u32 val, u32 size)
@@ -754,8 +752,7 @@ static void worker_pkt_validate(void)
 	}
 }
 
-static void thread_common_ops(struct ifobject *ifobject, void *bufs, pthread_mutex_t *mutexptr,
-			      atomic_int *spinningptr)
+static void thread_common_ops(struct ifobject *ifobject, void *bufs, pthread_mutex_t *mutexptr)
 {
 	int ctr = 0;
 	int ret;
@@ -780,13 +777,15 @@ static void thread_common_ops(struct ifobject *ifobject, void *bufs, pthread_mut
 	 */
 	pthread_mutex_lock(mutexptr);
 	while (ret && ctr < SOCK_RECONF_CTR) {
-		atomic_store(spinningptr, 1);
+		if (ifobject->fv.vector == rx)
+			atomic_store(&spinning_rx, 1);
 		xsk_configure_umem(ifobject, bufs, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE);
 		ret = xsk_configure_socket(ifobject);
 		usleep(USLEEP_MAX);
 		ctr++;
 	}
-	atomic_store(spinningptr, 0);
+	if (ifobject->fv.vector == rx)
+		atomic_store(&spinning_rx, 0);
 	pthread_mutex_unlock(mutexptr);
 
 	if (ctr >= SOCK_RECONF_CTR)
@@ -808,7 +807,7 @@ static void *worker_testapp_validate_tx(void *arg)
 	void *bufs = NULL;
 
 	if (!bidi_pass)
-		thread_common_ops(ifobject, bufs, &sync_mutex_tx, &spinning_tx);
+		thread_common_ops(ifobject, bufs, &sync_mutex_tx);
 
 	while (atomic_load(&spinning_rx) && spinningrxctr < SOCK_RECONF_CTR) {
 		spinningrxctr++;
@@ -846,7 +845,7 @@ static void *worker_testapp_validate_rx(void *arg)
 	void *bufs = NULL;
 
 	if (!bidi_pass)
-		thread_common_ops(ifobject, bufs, &sync_mutex_tx, &spinning_rx);
+		thread_common_ops(ifobject, bufs, &sync_mutex_tx);
 
 	if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
 		xsk_populate_fill_ring(ifobject->umem);
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 493f7498d40e..483be41229c6 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -144,12 +144,10 @@ struct ifobject {
 static struct ifobject *ifdict[MAX_INTERFACES];
 
 /*threads*/
-atomic_int spinning_tx;
 atomic_int spinning_rx;
 pthread_mutex_t sync_mutex;
 pthread_mutex_t sync_mutex_tx;
 pthread_cond_t signal_rx_condition;
-pthread_cond_t signal_tx_condition;
 pthread_t t0, t1;
 pthread_attr_t attr;
 
-- 
cgit v1.2.3


From 9445f8c765838edf84dd0d3910ff309bdab8f95f Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:10 +0200
Subject: selftests: xsk: Refactor teardown/bidi test cases and
 testapp_validate

Currently, there is a testapp_sockets() that acts like a wrapper around
testapp_validate() and it is called for bidi and teardown test types.
Other test types call testapp_validate() directly.

Split testapp_sockets() onto two separate functions so a bunch of bidi
specific logic can be moved there and out of testapp_validate() itself.

Introduce function pointer to ifobject struct which will be used for
assigning the Rx/Tx function that is assigned to worker thread. Let's
also have a global ifobject Rx/Tx pointers so it's easier to swap the
vectors on a second run of a bi-directional test. Thread creation now is
easey to follow.

switching_notify variable is useless, info about vector switch can be
printed based on bidi_pass state.

Last but not least, init/destroy synchronization variables only once,
not per each test.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-12-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 117 ++++++++++++++++++-------------
 tools/testing/selftests/bpf/xdpxceiver.h |  14 ++--
 2 files changed, 78 insertions(+), 53 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 9f7ee9a38752..c0ebca8f55f8 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -896,26 +896,10 @@ static void testapp_validate(void)
 	pthread_attr_init(&attr);
 	pthread_attr_setstacksize(&attr, THREAD_STACK);
 
-	if ((test_type == TEST_TYPE_BIDI) && bidi_pass) {
-		pthread_init_mutex();
-		if (!switching_notify) {
-			print_verbose("Switching Tx/Rx vectors\n");
-			switching_notify++;
-		}
-	}
-
 	pthread_mutex_lock(&sync_mutex);
 
 	/*Spawn RX thread */
-	if (!bidi || !bidi_pass) {
-		if (pthread_create(&t0, &attr, worker_testapp_validate_rx, ifdict[1]))
-			exit_with_error(errno);
-	} else if (bidi && bidi_pass) {
-		/*switch Tx/Rx vectors */
-		ifdict[0]->fv.vector = rx;
-		if (pthread_create(&t0, &attr, worker_testapp_validate_rx, ifdict[0]))
-			exit_with_error(errno);
-	}
+	pthread_create(&t0, &attr, ifdict_rx->func_ptr, ifdict_rx);
 
 	if (clock_gettime(CLOCK_REALTIME, &max_wait))
 		exit_with_error(errno);
@@ -927,15 +911,7 @@ static void testapp_validate(void)
 	pthread_mutex_unlock(&sync_mutex);
 
 	/*Spawn TX thread */
-	if (!bidi || !bidi_pass) {
-		if (pthread_create(&t1, &attr, worker_testapp_validate_tx, ifdict[0]))
-			exit_with_error(errno);
-	} else if (bidi && bidi_pass) {
-		/*switch Tx/Rx vectors */
-		ifdict[1]->fv.vector = tx;
-		if (pthread_create(&t1, &attr, worker_testapp_validate_tx, ifdict[1]))
-			exit_with_error(errno);
-	}
+	pthread_create(&t1, &attr, ifdict_tx->func_ptr, ifdict_tx);
 
 	pthread_join(t1, NULL);
 	pthread_join(t0, NULL);
@@ -953,18 +929,53 @@ static void testapp_validate(void)
 		print_ksft_result();
 }
 
-static void testapp_sockets(void)
+static void testapp_teardown(void)
+{
+	int i;
+
+	for (i = 0; i < MAX_TEARDOWN_ITER; i++) {
+		pkt_counter = 0;
+		prev_pkt = -1;
+		sigvar = 0;
+		print_verbose("Creating socket\n");
+		testapp_validate();
+	}
+
+	print_ksft_result();
+}
+
+static void swap_vectors(struct ifobject *ifobj1, struct ifobject *ifobj2)
+{
+	void *(*tmp_func_ptr)(void *) = ifobj1->func_ptr;
+	enum fvector tmp_vector = ifobj1->fv.vector;
+
+	ifobj1->func_ptr = ifobj2->func_ptr;
+	ifobj1->fv.vector = ifobj2->fv.vector;
+
+	ifobj2->func_ptr = tmp_func_ptr;
+	ifobj2->fv.vector = tmp_vector;
+
+	ifdict_tx = ifobj1;
+	ifdict_rx = ifobj2;
+}
+
+static void testapp_bidi(void)
 {
-	for (int i = 0; i < ((test_type == TEST_TYPE_TEARDOWN) ? MAX_TEARDOWN_ITER : MAX_BIDI_ITER);
-	     i++) {
+	for (int i = 0; i < MAX_BIDI_ITER; i++) {
 		pkt_counter = 0;
 		prev_pkt = -1;
 		sigvar = 0;
 		print_verbose("Creating socket\n");
 		testapp_validate();
-		test_type == TEST_TYPE_BIDI ? bidi_pass++ : bidi_pass;
+		if (!bidi_pass) {
+			print_verbose("Switching Tx/Rx vectors\n");
+			swap_vectors(ifdict[1], ifdict[0]);
+		}
+		bidi_pass++;
 	}
 
+	swap_vectors(ifdict[0], ifdict[1]);
+
 	print_ksft_result();
 }
 
@@ -997,7 +1008,7 @@ static void testapp_stats(void)
 static void init_iface(struct ifobject *ifobj, const char *dst_mac,
 		       const char *src_mac, const char *dst_ip,
 		       const char *src_ip, const u16 dst_port,
-		       const u16 src_port)
+		       const u16 src_port, enum fvector vector)
 {
 	struct in_addr ip;
 
@@ -1012,6 +1023,16 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac,
 
 	ifobj->dst_port = dst_port;
 	ifobj->src_port = src_port;
+
+	if (vector == tx) {
+		ifobj->fv.vector = tx;
+		ifobj->func_ptr = worker_testapp_validate_tx;
+		ifdict_tx = ifobj;
+	} else {
+		ifobj->fv.vector = rx;
+		ifobj->func_ptr = worker_testapp_validate_rx;
+		ifdict_rx = ifobj;
+	}
 }
 
 static void run_pkt_test(int mode, int type)
@@ -1021,11 +1042,8 @@ static void run_pkt_test(int mode, int type)
 	/* reset defaults after potential previous test */
 	xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 	pkt_counter = 0;
-	switching_notify = 0;
 	bidi_pass = 0;
 	prev_pkt = -1;
-	ifdict[0]->fv.vector = tx;
-	ifdict[1]->fv.vector = rx;
 	sigvar = 0;
 	stat_test_type = -1;
 	rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
@@ -1042,16 +1060,20 @@ static void run_pkt_test(int mode, int type)
 		break;
 	}
 
-	pthread_init_mutex();
-
-	if (test_type == TEST_TYPE_STATS)
+	switch (test_type) {
+	case TEST_TYPE_STATS:
 		testapp_stats();
-	else if ((test_type != TEST_TYPE_TEARDOWN) && (test_type != TEST_TYPE_BIDI))
+		break;
+	case TEST_TYPE_TEARDOWN:
+		testapp_teardown();
+		break;
+	case TEST_TYPE_BIDI:
+		testapp_bidi();
+		break;
+	default:
 		testapp_validate();
-	else
-		testapp_sockets();
-
-	pthread_destroy_mutex();
+		break;
+	}
 }
 
 int main(int argc, char **argv)
@@ -1076,14 +1098,13 @@ int main(int argc, char **argv)
 
 	num_frames = ++opt_pkt_count;
 
-	ifdict[0]->fv.vector = tx;
-	init_iface(ifdict[0], MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2);
-
-	ifdict[1]->fv.vector = rx;
-	init_iface(ifdict[1], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1);
+	init_iface(ifdict[0], MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, tx);
+	init_iface(ifdict[1], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, rx);
 
 	ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX);
 
+	pthread_init_mutex();
+
 	for (i = 0; i < TEST_MODE_MAX; i++) {
 		for (j = 0; j < TEST_TYPE_MAX; j++)
 			run_pkt_test(i, j);
@@ -1095,6 +1116,8 @@ int main(int argc, char **argv)
 		free(ifdict[i]);
 	}
 
+	pthread_destroy_mutex();
+
 	ksft_exit_pass();
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 483be41229c6..3945746900af 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -77,7 +77,6 @@ enum STAT_TEST_TYPES {
 static int configured_mode = TEST_MODE_UNCONFIGURED;
 static u8 debug_pkt_dump;
 static u32 num_frames;
-static u8 switching_notify;
 static u8 bidi_pass;
 static int test_type;
 
@@ -126,22 +125,25 @@ struct generic_data {
 };
 
 struct ifobject {
-	int ns_fd;
-	int ifdict_index;
 	char ifname[MAX_INTERFACE_NAME_CHARS];
 	char nsname[MAX_INTERFACES_NAMESPACE_CHARS];
-	struct flow_vector fv;
 	struct xsk_socket_info *xsk;
 	struct xsk_umem_info *umem;
-	u8 dst_mac[ETH_ALEN];
-	u8 src_mac[ETH_ALEN];
+	void *(*func_ptr)(void *arg);
+	struct flow_vector fv;
+	int ns_fd;
+	int ifdict_index;
 	u32 dst_ip;
 	u32 src_ip;
 	u16 src_port;
 	u16 dst_port;
+	u8 dst_mac[ETH_ALEN];
+	u8 src_mac[ETH_ALEN];
 };
 
 static struct ifobject *ifdict[MAX_INTERFACES];
+static struct ifobject *ifdict_rx;
+static struct ifobject *ifdict_tx;
 
 /*threads*/
 atomic_int spinning_rx;
-- 
cgit v1.2.3


From 0464b1ed07677f869005bde3fade1580b48de67e Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:11 +0200
Subject: selftests: xsk: Remove sync_mutex_tx and atomic var

Although thread_common_ops() are called in both Tx and Rx threads,
testapp_validate() will not spawn Tx thread until Rx thread signals that
it has finished its initialization via condition variable.

Therefore, locking in thread_common_ops is not needed and furthermore Tx
thread does not have to spin on atomic variable.

Note that this simplification wouldn't be possible if there would still
be a common worker thread.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-13-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 31 +++++++------------------------
 tools/testing/selftests/bpf/xdpxceiver.h |  2 --
 2 files changed, 7 insertions(+), 26 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index c0ebca8f55f8..35e14ad8097e 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -121,17 +121,15 @@ static void __exit_with_error(int error, const char *file, const char *func, int
 			       test_type == TEST_TYPE_BIDI ? "Bi-directional Sockets" : "",\
 			       test_type == TEST_TYPE_STATS ? "Stats" : ""))
 
-static void pthread_init_mutex(void)
+static void init_sync_resources(void)
 {
 	pthread_mutex_init(&sync_mutex, NULL);
-	pthread_mutex_init(&sync_mutex_tx, NULL);
 	pthread_cond_init(&signal_rx_condition, NULL);
 }
 
-static void pthread_destroy_mutex(void)
+static void destroy_sync_resources(void)
 {
 	pthread_mutex_destroy(&sync_mutex);
-	pthread_mutex_destroy(&sync_mutex_tx);
 	pthread_cond_destroy(&signal_rx_condition);
 }
 
@@ -752,7 +750,7 @@ static void worker_pkt_validate(void)
 	}
 }
 
-static void thread_common_ops(struct ifobject *ifobject, void *bufs, pthread_mutex_t *mutexptr)
+static void thread_common_ops(struct ifobject *ifobject, void *bufs)
 {
 	int ctr = 0;
 	int ret;
@@ -771,22 +769,13 @@ static void thread_common_ops(struct ifobject *ifobject, void *bufs, pthread_mut
 
 	/* Retry Create Socket if it fails as xsk_socket__create()
 	 * is asynchronous
-	 *
-	 * Essential to lock Mutex here to prevent Tx thread from
-	 * entering before Rx and causing a deadlock
 	 */
-	pthread_mutex_lock(mutexptr);
 	while (ret && ctr < SOCK_RECONF_CTR) {
-		if (ifobject->fv.vector == rx)
-			atomic_store(&spinning_rx, 1);
 		xsk_configure_umem(ifobject, bufs, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE);
 		ret = xsk_configure_socket(ifobject);
 		usleep(USLEEP_MAX);
 		ctr++;
 	}
-	if (ifobject->fv.vector == rx)
-		atomic_store(&spinning_rx, 0);
-	pthread_mutex_unlock(mutexptr);
 
 	if (ctr >= SOCK_RECONF_CTR)
 		exit_with_error(ret);
@@ -803,16 +792,10 @@ static void *worker_testapp_validate_tx(void *arg)
 	struct ethhdr *eth_hdr = (struct ethhdr *)pkt_data;
 	struct ifobject *ifobject = (struct ifobject *)arg;
 	struct generic_data data;
-	int spinningrxctr = 0;
 	void *bufs = NULL;
 
 	if (!bidi_pass)
-		thread_common_ops(ifobject, bufs, &sync_mutex_tx);
-
-	while (atomic_load(&spinning_rx) && spinningrxctr < SOCK_RECONF_CTR) {
-		spinningrxctr++;
-		usleep(USLEEP_MAX);
-	}
+		thread_common_ops(ifobject, bufs);
 
 	for (int i = 0; i < num_frames; i++) {
 		/*send EOT frame */
@@ -845,7 +828,7 @@ static void *worker_testapp_validate_rx(void *arg)
 	void *bufs = NULL;
 
 	if (!bidi_pass)
-		thread_common_ops(ifobject, bufs, &sync_mutex_tx);
+		thread_common_ops(ifobject, bufs);
 
 	if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
 		xsk_populate_fill_ring(ifobject->umem);
@@ -1103,7 +1086,7 @@ int main(int argc, char **argv)
 
 	ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX);
 
-	pthread_init_mutex();
+	init_sync_resources();
 
 	for (i = 0; i < TEST_MODE_MAX; i++) {
 		for (j = 0; j < TEST_TYPE_MAX; j++)
@@ -1116,7 +1099,7 @@ int main(int argc, char **argv)
 		free(ifdict[i]);
 	}
 
-	pthread_destroy_mutex();
+	destroy_sync_resources();
 
 	ksft_exit_pass();
 
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 3945746900af..e304229d8a4c 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -146,9 +146,7 @@ static struct ifobject *ifdict_rx;
 static struct ifobject *ifdict_tx;
 
 /*threads*/
-atomic_int spinning_rx;
 pthread_mutex_t sync_mutex;
-pthread_mutex_t sync_mutex_tx;
 pthread_cond_t signal_rx_condition;
 pthread_t t0, t1;
 pthread_attr_t attr;
-- 
cgit v1.2.3


From 27e1ca2525de264901b5c2d9d0c4403c3fe8608c Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:13 +0200
Subject: selftests: xsk: Implement bpf_link test

Introduce a test that is supposed to verify the persistence of BPF
resources based on underlying bpf_link usage.

Test will:
1) create and bind two sockets on queue ids 0 and 1
2) run a traffic on queue ids 0
3) remove xsk sockets from queue 0 on both veth interfaces
4) run a traffic on queues ids 1

Running traffic successfully on qids 1 means that BPF resources were
not removed on step 3).

In order to make it work, change the command that creates veth pair to
have the 4 queue pairs by default.

Introduce the arrays of xsks and umems to ifobject struct but keep a
pointers to single entities, so rest of the logic around Rx/Tx can be
kept as-is.

For umem handling, double the size of mmapped space and split that
between the two sockets.

Rename also bidi_pass to a variable 'second_step' of a boolean type as
it's now used also for the test that is introduced here and it doesn't
have anything in common with bi-directional testing.

Drop opt_queue command line argument as it wasn't working before anyway.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-15-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/test_xsk.sh  |   3 +-
 tools/testing/selftests/bpf/xdpxceiver.c | 179 +++++++++++++++++++++++--------
 tools/testing/selftests/bpf/xdpxceiver.h |   7 +-
 3 files changed, 139 insertions(+), 50 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
index 56d4474e2c83..46633a3bfb0b 100755
--- a/tools/testing/selftests/bpf/test_xsk.sh
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -107,7 +107,7 @@ setup_vethPairs() {
 	        echo "setting up ${VETH0}: namespace: ${NS0}"
 	fi
 	ip netns add ${NS1}
-	ip link add ${VETH0} type veth peer name ${VETH1}
+	ip link add ${VETH0} numtxqueues 4 numrxqueues 4 type veth peer name ${VETH1} numtxqueues 4 numrxqueues 4
 	if [ -f /proc/net/if_inet6 ]; then
 		echo 1 > /proc/sys/net/ipv6/conf/${VETH0}/disable_ipv6
 	fi
@@ -118,6 +118,7 @@ setup_vethPairs() {
 	ip netns exec ${NS1} ip link set ${VETH1} mtu ${MTU}
 	ip link set ${VETH0} mtu ${MTU}
 	ip netns exec ${NS1} ip link set ${VETH1} up
+	ip netns exec ${NS1} ip link set dev lo up
 	ip link set ${VETH0} up
 }
 
diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 35e14ad8097e..5c0d6dbd076f 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -41,8 +41,12 @@
  *            Reduce the size of the RX ring to a fraction of the fill ring size.
  *       iv.  fill queue empty
  *            Do not populate the fill queue and then try to receive pkts.
+ *    f. bpf_link resource persistence
+ *       Configure sockets at indexes 0 and 1, run a traffic on queue ids 0,
+ *       then remove xsk sockets from queue 0 on both veth interfaces and
+ *       finally run a traffic on queues ids 1
  *
- * Total tests: 10
+ * Total tests: 12
  *
  * Flow:
  * -----
@@ -115,11 +119,12 @@ static void __exit_with_error(int error, const char *file, const char *func, int
 #define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, __LINE__)
 
 #define print_ksft_result(void)\
-	(ksft_test_result_pass("PASS: %s %s %s%s%s\n", configured_mode ? "DRV" : "SKB",\
+	(ksft_test_result_pass("PASS: %s %s %s%s%s%s\n", configured_mode ? "DRV" : "SKB",\
 			       test_type == TEST_TYPE_POLL ? "POLL" : "NOPOLL",\
 			       test_type == TEST_TYPE_TEARDOWN ? "Socket Teardown" : "",\
 			       test_type == TEST_TYPE_BIDI ? "Bi-directional Sockets" : "",\
-			       test_type == TEST_TYPE_STATS ? "Stats" : ""))
+			       test_type == TEST_TYPE_STATS ? "Stats" : "",\
+			       test_type == TEST_TYPE_BPF_RES ? "BPF RES" : ""))
 
 static void init_sync_resources(void)
 {
@@ -258,9 +263,8 @@ static void gen_eth_frame(struct xsk_umem_info *umem, u64 addr)
 	memcpy(xsk_umem__get_data(umem->buffer, addr), pkt_data, PKT_SIZE);
 }
 
-static void xsk_configure_umem(struct ifobject *data, void *buffer, u64 size)
+static void xsk_configure_umem(struct ifobject *data, void *buffer, int idx)
 {
-	int ret;
 	struct xsk_umem_config cfg = {
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
@@ -268,17 +272,22 @@ static void xsk_configure_umem(struct ifobject *data, void *buffer, u64 size)
 		.frame_headroom = frame_headroom,
 		.flags = XSK_UMEM__DEFAULT_FLAGS
 	};
+	int size = num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE;
+	struct xsk_umem_info *umem;
+	int ret;
 
-	data->umem = calloc(1, sizeof(struct xsk_umem_info));
-	if (!data->umem)
+	umem = calloc(1, sizeof(struct xsk_umem_info));
+	if (!umem)
 		exit_with_error(errno);
 
-	ret = xsk_umem__create(&data->umem->umem, buffer, size,
-			       &data->umem->fq, &data->umem->cq, &cfg);
+	ret = xsk_umem__create(&umem->umem, buffer, size,
+			       &umem->fq, &umem->cq, &cfg);
 	if (ret)
 		exit_with_error(ret);
 
-	data->umem->buffer = buffer;
+	umem->buffer = buffer;
+
+	data->umem_arr[idx] = umem;
 }
 
 static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
@@ -294,18 +303,19 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
 	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
 }
 
-static int xsk_configure_socket(struct ifobject *ifobject)
+static int xsk_configure_socket(struct ifobject *ifobject, int idx)
 {
 	struct xsk_socket_config cfg;
+	struct xsk_socket_info *xsk;
 	struct xsk_ring_cons *rxr;
 	struct xsk_ring_prod *txr;
 	int ret;
 
-	ifobject->xsk = calloc(1, sizeof(struct xsk_socket_info));
-	if (!ifobject->xsk)
+	xsk = calloc(1, sizeof(struct xsk_socket_info));
+	if (!xsk)
 		exit_with_error(errno);
 
-	ifobject->xsk->umem = ifobject->umem;
+	xsk->umem = ifobject->umem;
 	cfg.rx_size = rxqsize;
 	cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
 	cfg.libbpf_flags = 0;
@@ -313,19 +323,20 @@ static int xsk_configure_socket(struct ifobject *ifobject)
 	cfg.bind_flags = xdp_bind_flags;
 
 	if (test_type != TEST_TYPE_BIDI) {
-		rxr = (ifobject->fv.vector == rx) ? &ifobject->xsk->rx : NULL;
-		txr = (ifobject->fv.vector == tx) ? &ifobject->xsk->tx : NULL;
+		rxr = (ifobject->fv.vector == rx) ? &xsk->rx : NULL;
+		txr = (ifobject->fv.vector == tx) ? &xsk->tx : NULL;
 	} else {
-		rxr = &ifobject->xsk->rx;
-		txr = &ifobject->xsk->tx;
+		rxr = &xsk->rx;
+		txr = &xsk->tx;
 	}
 
-	ret = xsk_socket__create(&ifobject->xsk->xsk, ifobject->ifname,
-				 opt_queue, ifobject->umem->umem, rxr, txr, &cfg);
-
+	ret = xsk_socket__create(&xsk->xsk, ifobject->ifname, idx,
+				 ifobject->umem->umem, rxr, txr, &cfg);
 	if (ret)
 		return 1;
 
+	ifobject->xsk_arr[idx] = xsk;
+
 	return 0;
 }
 
@@ -393,7 +404,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "i:q:DC:v", long_options, &option_index);
+		c = getopt_long(argc, argv, "i:DC:v", long_options, &option_index);
 
 		if (c == -1)
 			break;
@@ -413,9 +424,6 @@ static void parse_command_line(int argc, char **argv)
 				       MAX_INTERFACES_NAMESPACE_CHARS);
 			interface_index++;
 			break;
-		case 'q':
-			opt_queue = atoi(optarg);
-			break;
 		case 'D':
 			debug_pkt_dump = 1;
 			break;
@@ -752,27 +760,33 @@ static void worker_pkt_validate(void)
 
 static void thread_common_ops(struct ifobject *ifobject, void *bufs)
 {
+	int umem_sz = num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE;
 	int ctr = 0;
 	int ret;
 
 	pthread_attr_setstacksize(&attr, THREAD_STACK);
 
-	bufs = mmap(NULL, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE,
+	ifobject->ns_fd = switch_namespace(ifobject->nsname);
+
+	if (test_type == TEST_TYPE_BPF_RES)
+		umem_sz *= 2;
+
+	bufs = mmap(NULL, umem_sz,
 		    PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 	if (bufs == MAP_FAILED)
 		exit_with_error(errno);
 
-	ifobject->ns_fd = switch_namespace(ifobject->nsname);
-
-	xsk_configure_umem(ifobject, bufs, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE);
-	ret = xsk_configure_socket(ifobject);
+	xsk_configure_umem(ifobject, bufs, 0);
+	ifobject->umem = ifobject->umem_arr[0];
+	ret = xsk_configure_socket(ifobject, 0);
 
 	/* Retry Create Socket if it fails as xsk_socket__create()
 	 * is asynchronous
 	 */
 	while (ret && ctr < SOCK_RECONF_CTR) {
-		xsk_configure_umem(ifobject, bufs, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE);
-		ret = xsk_configure_socket(ifobject);
+		xsk_configure_umem(ifobject, bufs, 0);
+		ifobject->umem = ifobject->umem_arr[0];
+		ret = xsk_configure_socket(ifobject, 0);
 		usleep(USLEEP_MAX);
 		ctr++;
 	}
@@ -780,10 +794,34 @@ static void thread_common_ops(struct ifobject *ifobject, void *bufs)
 	if (ctr >= SOCK_RECONF_CTR)
 		exit_with_error(ret);
 
+	ifobject->umem = ifobject->umem_arr[0];
+	ifobject->xsk = ifobject->xsk_arr[0];
+
+	if (test_type == TEST_TYPE_BPF_RES) {
+		xsk_configure_umem(ifobject, (u8 *)bufs + (umem_sz / 2), 1);
+		ifobject->umem = ifobject->umem_arr[1];
+		ret = xsk_configure_socket(ifobject, 1);
+	}
+
+	ifobject->umem = ifobject->umem_arr[0];
+	ifobject->xsk = ifobject->xsk_arr[0];
 	print_verbose("Interface [%s] vector [%s]\n",
 		      ifobject->ifname, ifobject->fv.vector == tx ? "Tx" : "Rx");
 }
 
+static bool testapp_is_test_two_stepped(void)
+{
+	return (test_type != TEST_TYPE_BIDI && test_type != TEST_TYPE_BPF_RES) || second_step;
+}
+
+static void testapp_cleanup_xsk_res(struct ifobject *ifobj)
+{
+	if (testapp_is_test_two_stepped()) {
+		xsk_socket__delete(ifobj->xsk->xsk);
+		(void)xsk_umem__delete(ifobj->umem->umem);
+	}
+}
+
 static void *worker_testapp_validate_tx(void *arg)
 {
 	struct udphdr *udp_hdr =
@@ -794,7 +832,7 @@ static void *worker_testapp_validate_tx(void *arg)
 	struct generic_data data;
 	void *bufs = NULL;
 
-	if (!bidi_pass)
+	if (!second_step)
 		thread_common_ops(ifobject, bufs);
 
 	for (int i = 0; i < num_frames; i++) {
@@ -814,10 +852,7 @@ static void *worker_testapp_validate_tx(void *arg)
 		      (opt_pkt_count - 1), ifobject->ifname);
 	tx_only_all(ifobject);
 
-	if (test_type != TEST_TYPE_BIDI || bidi_pass) {
-		xsk_socket__delete(ifobject->xsk->xsk);
-		(void)xsk_umem__delete(ifobject->umem->umem);
-	}
+	testapp_cleanup_xsk_res(ifobject);
 	pthread_exit(NULL);
 }
 
@@ -827,7 +862,7 @@ static void *worker_testapp_validate_rx(void *arg)
 	struct pollfd fds[MAX_SOCKS] = { };
 	void *bufs = NULL;
 
-	if (!bidi_pass)
+	if (!second_step)
 		thread_common_ops(ifobject, bufs);
 
 	if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
@@ -864,10 +899,7 @@ static void *worker_testapp_validate_rx(void *arg)
 	if (test_type == TEST_TYPE_TEARDOWN)
 		print_verbose("Destroying socket\n");
 
-	if ((test_type != TEST_TYPE_BIDI) || bidi_pass) {
-		xsk_socket__delete(ifobject->xsk->xsk);
-		(void)xsk_umem__delete(ifobject->umem->umem);
-	}
+	testapp_cleanup_xsk_res(ifobject);
 	pthread_exit(NULL);
 }
 
@@ -875,6 +907,7 @@ static void testapp_validate(void)
 {
 	struct timespec max_wait = { 0, 0 };
 	bool bidi = test_type == TEST_TYPE_BIDI;
+	bool bpf = test_type == TEST_TYPE_BPF_RES;
 
 	pthread_attr_init(&attr);
 	pthread_attr_setstacksize(&attr, THREAD_STACK);
@@ -908,7 +941,7 @@ static void testapp_validate(void)
 		free(pkt_buf);
 	}
 
-	if (!(test_type == TEST_TYPE_TEARDOWN) && !bidi && !(test_type == TEST_TYPE_STATS))
+	if (!(test_type == TEST_TYPE_TEARDOWN) && !bidi && !bpf && !(test_type == TEST_TYPE_STATS))
 		print_ksft_result();
 }
 
@@ -950,11 +983,11 @@ static void testapp_bidi(void)
 		sigvar = 0;
 		print_verbose("Creating socket\n");
 		testapp_validate();
-		if (!bidi_pass) {
+		if (!second_step) {
 			print_verbose("Switching Tx/Rx vectors\n");
 			swap_vectors(ifdict[1], ifdict[0]);
 		}
-		bidi_pass++;
+		second_step = true;
 	}
 
 	swap_vectors(ifdict[0], ifdict[1]);
@@ -962,6 +995,36 @@ static void testapp_bidi(void)
 	print_ksft_result();
 }
 
+static void swap_xsk_res(void)
+{
+	xsk_socket__delete(ifdict_tx->xsk->xsk);
+	xsk_umem__delete(ifdict_tx->umem->umem);
+	xsk_socket__delete(ifdict_rx->xsk->xsk);
+	xsk_umem__delete(ifdict_rx->umem->umem);
+	ifdict_tx->umem = ifdict_tx->umem_arr[1];
+	ifdict_tx->xsk = ifdict_tx->xsk_arr[1];
+	ifdict_rx->umem = ifdict_rx->umem_arr[1];
+	ifdict_rx->xsk = ifdict_rx->xsk_arr[1];
+}
+
+static void testapp_bpf_res(void)
+{
+	int i;
+
+	for (i = 0; i < MAX_BPF_ITER; i++) {
+		pkt_counter = 0;
+		prev_pkt = -1;
+		sigvar = 0;
+		print_verbose("Creating socket\n");
+		testapp_validate();
+		if (!second_step)
+			swap_xsk_res();
+		second_step = true;
+	}
+
+	print_ksft_result();
+}
+
 static void testapp_stats(void)
 {
 	for (int i = 0; i < STAT_TEST_TYPE_MAX; i++) {
@@ -1025,13 +1088,15 @@ static void run_pkt_test(int mode, int type)
 	/* reset defaults after potential previous test */
 	xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 	pkt_counter = 0;
-	bidi_pass = 0;
+	second_step = 0;
 	prev_pkt = -1;
 	sigvar = 0;
 	stat_test_type = -1;
 	rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
 	frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM;
 
+	configured_mode = mode;
+
 	switch (mode) {
 	case (TEST_MODE_SKB):
 		xdp_flags |= XDP_FLAGS_SKB_MODE;
@@ -1053,6 +1118,9 @@ static void run_pkt_test(int mode, int type)
 	case TEST_TYPE_BIDI:
 		testapp_bidi();
 		break;
+	case TEST_TYPE_BPF_RES:
+		testapp_bpf_res();
+		break;
 	default:
 		testapp_validate();
 		break;
@@ -1062,6 +1130,7 @@ static void run_pkt_test(int mode, int type)
 int main(int argc, char **argv)
 {
 	struct rlimit _rlim = { RLIM_INFINITY, RLIM_INFINITY };
+	bool failure = false;
 	int i, j;
 
 	if (setrlimit(RLIMIT_MEMLOCK, &_rlim))
@@ -1073,6 +1142,16 @@ int main(int argc, char **argv)
 			exit_with_error(errno);
 
 		ifdict[i]->ifdict_index = i;
+		ifdict[i]->xsk_arr = calloc(2, sizeof(struct xsk_socket_info *));
+		if (!ifdict[i]->xsk_arr) {
+			failure = true;
+			goto cleanup;
+		}
+		ifdict[i]->umem_arr = calloc(2, sizeof(struct xsk_umem_info *));
+		if (!ifdict[i]->umem_arr) {
+			failure = true;
+			goto cleanup;
+		}
 	}
 
 	setlocale(LC_ALL, "");
@@ -1093,13 +1172,19 @@ int main(int argc, char **argv)
 			run_pkt_test(i, j);
 	}
 
+	destroy_sync_resources();
+
+cleanup:
 	for (int i = 0; i < MAX_INTERFACES; i++) {
 		if (ifdict[i]->ns_fd != -1)
 			close(ifdict[i]->ns_fd);
+		free(ifdict[i]->xsk_arr);
+		free(ifdict[i]->umem_arr);
 		free(ifdict[i]);
 	}
 
-	destroy_sync_resources();
+	if (failure)
+		exit_with_error(errno);
 
 	ksft_exit_pass();
 
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index e304229d8a4c..e431ecb9bb95 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -23,6 +23,7 @@
 #define MAX_SOCKS 1
 #define MAX_TEARDOWN_ITER 10
 #define MAX_BIDI_ITER 2
+#define MAX_BPF_ITER 2
 #define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \
 			sizeof(struct udphdr))
 #define MIN_PKT_SIZE 64
@@ -63,6 +64,7 @@ enum TEST_TYPES {
 	TEST_TYPE_TEARDOWN,
 	TEST_TYPE_BIDI,
 	TEST_TYPE_STATS,
+	TEST_TYPE_BPF_RES,
 	TEST_TYPE_MAX
 };
 
@@ -77,10 +79,9 @@ enum STAT_TEST_TYPES {
 static int configured_mode = TEST_MODE_UNCONFIGURED;
 static u8 debug_pkt_dump;
 static u32 num_frames;
-static u8 bidi_pass;
+static bool second_step;
 static int test_type;
 
-static int opt_queue;
 static int opt_pkt_count;
 static u8 opt_verbose;
 
@@ -128,6 +129,8 @@ struct ifobject {
 	char ifname[MAX_INTERFACE_NAME_CHARS];
 	char nsname[MAX_INTERFACES_NAMESPACE_CHARS];
 	struct xsk_socket_info *xsk;
+	struct xsk_socket_info **xsk_arr;
+	struct xsk_umem_info **umem_arr;
 	struct xsk_umem_info *umem;
 	void *(*func_ptr)(void *arg);
 	struct flow_vector fv;
-- 
cgit v1.2.3


From 7651910257c8fb1ec76b50bef0330fcf739105c7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= <bjorn.topel@intel.com>
Date: Tue, 30 Mar 2021 00:43:14 +0200
Subject: selftests: xsk: Remove thread attribute
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is really no reason to have a non-default thread stack
size. Remove that.

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-16-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 9 ++-------
 tools/testing/selftests/bpf/xdpxceiver.h | 2 --
 2 files changed, 2 insertions(+), 9 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 5c0d6dbd076f..ec09b8fe1178 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -764,8 +764,6 @@ static void thread_common_ops(struct ifobject *ifobject, void *bufs)
 	int ctr = 0;
 	int ret;
 
-	pthread_attr_setstacksize(&attr, THREAD_STACK);
-
 	ifobject->ns_fd = switch_namespace(ifobject->nsname);
 
 	if (test_type == TEST_TYPE_BPF_RES)
@@ -909,13 +907,10 @@ static void testapp_validate(void)
 	bool bidi = test_type == TEST_TYPE_BIDI;
 	bool bpf = test_type == TEST_TYPE_BPF_RES;
 
-	pthread_attr_init(&attr);
-	pthread_attr_setstacksize(&attr, THREAD_STACK);
-
 	pthread_mutex_lock(&sync_mutex);
 
 	/*Spawn RX thread */
-	pthread_create(&t0, &attr, ifdict_rx->func_ptr, ifdict_rx);
+	pthread_create(&t0, NULL, ifdict_rx->func_ptr, ifdict_rx);
 
 	if (clock_gettime(CLOCK_REALTIME, &max_wait))
 		exit_with_error(errno);
@@ -927,7 +922,7 @@ static void testapp_validate(void)
 	pthread_mutex_unlock(&sync_mutex);
 
 	/*Spawn TX thread */
-	pthread_create(&t1, &attr, ifdict_tx->func_ptr, ifdict_tx);
+	pthread_create(&t1, NULL, ifdict_tx->func_ptr, ifdict_tx);
 
 	pthread_join(t1, NULL);
 	pthread_join(t0, NULL);
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index e431ecb9bb95..78863820fb81 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -37,7 +37,6 @@
 #define TMOUT_SEC (3)
 #define EOT (-1)
 #define USLEEP_MAX 200000
-#define THREAD_STACK 60000000
 #define SOCK_RECONF_CTR 10
 #define BATCH_SIZE 64
 #define POLL_TMOUT 1000
@@ -152,7 +151,6 @@ static struct ifobject *ifdict_tx;
 pthread_mutex_t sync_mutex;
 pthread_cond_t signal_rx_condition;
 pthread_t t0, t1;
-pthread_attr_t attr;
 
 TAILQ_HEAD(head_s, pkt) head = TAILQ_HEAD_INITIALIZER(head);
 struct head_s *head_p;
-- 
cgit v1.2.3


From 96539f1c5efb0022b94412e8623722aad23dee6b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= <bjorn.topel@intel.com>
Date: Tue, 30 Mar 2021 00:43:15 +0200
Subject: selftests: xsk: Remove mutex and condition variable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The usage of the condition variable is broken, and overkill. Replace it
with a pthread barrier.

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-17-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 33 +++++---------------------------
 tools/testing/selftests/bpf/xdpxceiver.h |  3 +--
 2 files changed, 6 insertions(+), 30 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index ec09b8fe1178..6d87bdf3574a 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -126,18 +126,6 @@ static void __exit_with_error(int error, const char *file, const char *func, int
 			       test_type == TEST_TYPE_STATS ? "Stats" : "",\
 			       test_type == TEST_TYPE_BPF_RES ? "BPF RES" : ""))
 
-static void init_sync_resources(void)
-{
-	pthread_mutex_init(&sync_mutex, NULL);
-	pthread_cond_init(&signal_rx_condition, NULL);
-}
-
-static void destroy_sync_resources(void)
-{
-	pthread_mutex_destroy(&sync_mutex);
-	pthread_cond_destroy(&signal_rx_condition);
-}
-
 static void *memset32_htonl(void *dest, u32 val, u32 size)
 {
 	u32 *ptr = (u32 *)dest;
@@ -876,9 +864,7 @@ static void *worker_testapp_validate_rx(void *arg)
 	fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk);
 	fds[0].events = POLLIN;
 
-	pthread_mutex_lock(&sync_mutex);
-	pthread_cond_signal(&signal_rx_condition);
-	pthread_mutex_unlock(&sync_mutex);
+	pthread_barrier_wait(&barr);
 
 	while (1) {
 		if (test_type != TEST_TYPE_STATS) {
@@ -903,24 +889,19 @@ static void *worker_testapp_validate_rx(void *arg)
 
 static void testapp_validate(void)
 {
-	struct timespec max_wait = { 0, 0 };
 	bool bidi = test_type == TEST_TYPE_BIDI;
 	bool bpf = test_type == TEST_TYPE_BPF_RES;
 
-	pthread_mutex_lock(&sync_mutex);
+	if (pthread_barrier_init(&barr, NULL, 2))
+		exit_with_error(errno);
 
 	/*Spawn RX thread */
 	pthread_create(&t0, NULL, ifdict_rx->func_ptr, ifdict_rx);
 
-	if (clock_gettime(CLOCK_REALTIME, &max_wait))
-		exit_with_error(errno);
-	max_wait.tv_sec += TMOUT_SEC;
-
-	if (pthread_cond_timedwait(&signal_rx_condition, &sync_mutex, &max_wait) == ETIMEDOUT)
+	pthread_barrier_wait(&barr);
+	if (pthread_barrier_destroy(&barr))
 		exit_with_error(errno);
 
-	pthread_mutex_unlock(&sync_mutex);
-
 	/*Spawn TX thread */
 	pthread_create(&t1, NULL, ifdict_tx->func_ptr, ifdict_tx);
 
@@ -1160,15 +1141,11 @@ int main(int argc, char **argv)
 
 	ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX);
 
-	init_sync_resources();
-
 	for (i = 0; i < TEST_MODE_MAX; i++) {
 		for (j = 0; j < TEST_TYPE_MAX; j++)
 			run_pkt_test(i, j);
 	}
 
-	destroy_sync_resources();
-
 cleanup:
 	for (int i = 0; i < MAX_INTERFACES; i++) {
 		if (ifdict[i]->ns_fd != -1)
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 78863820fb81..ef219c0785eb 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -148,8 +148,7 @@ static struct ifobject *ifdict_rx;
 static struct ifobject *ifdict_tx;
 
 /*threads*/
-pthread_mutex_t sync_mutex;
-pthread_cond_t signal_rx_condition;
+pthread_barrier_t barr;
 pthread_t t0, t1;
 
 TAILQ_HEAD(head_s, pkt) head = TAILQ_HEAD_INITIALIZER(head);
-- 
cgit v1.2.3


From ae6b6a17800f34dd5215286b44a4e99a0a1cf862 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= <bjorn.topel@intel.com>
Date: Tue, 30 Mar 2021 00:43:16 +0200
Subject: selftests: xsk: Remove unused defines
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove two unused defines.

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-18-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 7 +++----
 tools/testing/selftests/bpf/xdpxceiver.h | 2 --
 2 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 6d87bdf3574a..1135fb980814 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -456,7 +456,7 @@ static void complete_tx_only(struct xsk_socket_info *xsk, int batch_size)
 	if (!xsk->outstanding_tx)
 		return;
 
-	if (!NEED_WAKEUP || xsk_ring_prod__needs_wakeup(&xsk->tx))
+	if (xsk_ring_prod__needs_wakeup(&xsk->tx))
 		kick_tx(xsk);
 
 	rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx);
@@ -544,9 +544,8 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frameptr, int batch_size)
 	xsk_ring_prod__submit(&xsk->tx, batch_size);
 	if (!tx_invalid_test) {
 		xsk->outstanding_tx += batch_size;
-	} else {
-		if (!NEED_WAKEUP || xsk_ring_prod__needs_wakeup(&xsk->tx))
-			kick_tx(xsk);
+	} else if (xsk_ring_prod__needs_wakeup(&xsk->tx)) {
+		kick_tx(xsk);
 	}
 	*frameptr += batch_size;
 	*frameptr %= num_frames;
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index ef219c0785eb..6c428b276ab6 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -34,13 +34,11 @@
 #define IP_PKT_TOS 0x9
 #define UDP_PKT_SIZE (IP_PKT_SIZE - sizeof(struct iphdr))
 #define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr))
-#define TMOUT_SEC (3)
 #define EOT (-1)
 #define USLEEP_MAX 200000
 #define SOCK_RECONF_CTR 10
 #define BATCH_SIZE 64
 #define POLL_TMOUT 1000
-#define NEED_WAKEUP true
 #define DEFAULT_PKT_CNT 10000
 #define RX_FULL_RXQSIZE 32
 
-- 
cgit v1.2.3


From 63f8af0fc34197a276674fa0d4d865aeff1f0172 Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@kernel.org>
Date: Tue, 23 Mar 2021 01:47:52 +0000
Subject: selftests/bpf: Add an option for a debug shell in vmtest.sh

The newly introduced -s command line option starts an interactive shell.
If a command is specified, the shell is started after the command
finishes executing. It's useful to have a shell especially when
debugging failing tests or developing new tests.

Since the user may terminate the VM forcefully, an extra "sync" is added
after the execution of the command to persist any logs from the command
into the log file.

Signed-off-by: KP Singh <kpsingh@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210323014752.3198283-1-kpsingh@kernel.org
---
 tools/testing/selftests/bpf/vmtest.sh | 39 +++++++++++++++++++++++++----------
 1 file changed, 28 insertions(+), 11 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh
index 22554894db99..8889b3f55236 100755
--- a/tools/testing/selftests/bpf/vmtest.sh
+++ b/tools/testing/selftests/bpf/vmtest.sh
@@ -24,15 +24,15 @@ EXIT_STATUS_FILE="${LOG_FILE_BASE}.exit_status"
 usage()
 {
 	cat <<EOF
-Usage: $0 [-i] [-d <output_dir>] -- [<command>]
+Usage: $0 [-i] [-s] [-d <output_dir>] -- [<command>]
 
 <command> is the command you would normally run when you are in
 tools/testing/selftests/bpf. e.g:
 
 	$0 -- ./test_progs -t test_lsm
 
-If no command is specified, "${DEFAULT_COMMAND}" will be run by
-default.
+If no command is specified and a debug shell (-s) is not requested,
+"${DEFAULT_COMMAND}" will be run by default.
 
 If you build your kernel using KBUILD_OUTPUT= or O= options, these
 can be passed as environment variables to the script:
@@ -49,6 +49,9 @@ Options:
 	-d)		Update the output directory (default: ${OUTPUT_DIR})
 	-j)		Number of jobs for compilation, similar to -j in make
 			(default: ${NUM_COMPILE_JOBS})
+	-s)		Instead of powering off the VM, start an interactive
+			shell. If <command> is specified, the shell runs after
+			the command finishes executing
 EOF
 }
 
@@ -149,6 +152,7 @@ update_init_script()
 	local init_script_dir="${OUTPUT_DIR}/${MOUNT_DIR}/etc/rcS.d"
 	local init_script="${init_script_dir}/S50-startup"
 	local command="$1"
+	local exit_command="$2"
 
 	mount_image
 
@@ -162,9 +166,10 @@ EOF
 
 	fi
 
-	sudo bash -c "cat >${init_script}" <<EOF
-#!/bin/bash
+	sudo bash -c "echo '#!/bin/bash' > ${init_script}"
 
+	if [[ "${command}" != "" ]]; then
+		sudo bash -c "cat >>${init_script}" <<EOF
 # Have a default value in the exit status file
 # incase the VM is forcefully stopped.
 echo "130" > "/root/${EXIT_STATUS_FILE}"
@@ -175,9 +180,12 @@ echo "130" > "/root/${EXIT_STATUS_FILE}"
 	stdbuf -oL -eL ${command}
 	echo "\$?" > "/root/${EXIT_STATUS_FILE}"
 } 2>&1 | tee "/root/${LOG_FILE}"
-poweroff -f
+# Ensure that the logs are written to disk
+sync
 EOF
+	fi
 
+	sudo bash -c "echo ${exit_command} >> ${init_script}"
 	sudo chmod a+x "${init_script}"
 	unmount_image
 }
@@ -277,8 +285,10 @@ main()
 	local kernel_bzimage="${kernel_checkout}/${X86_BZIMAGE}"
 	local command="${DEFAULT_COMMAND}"
 	local update_image="no"
+	local exit_command="poweroff -f"
+	local debug_shell="no"
 
-	while getopts 'hkid:j:' opt; do
+	while getopts 'hskid:j:' opt; do
 		case ${opt} in
 		i)
 			update_image="yes"
@@ -289,6 +299,11 @@ main()
 		j)
 			NUM_COMPILE_JOBS="$OPTARG"
 			;;
+		s)
+			command=""
+			debug_shell="yes"
+			exit_command="bash"
+			;;
 		h)
 			usage
 			exit 0
@@ -307,7 +322,7 @@ main()
 	done
 	shift $((OPTIND -1))
 
-	if [[ $# -eq 0 ]]; then
+	if [[ $# -eq 0  && "${debug_shell}" == "no" ]]; then
 		echo "No command specified, will run ${DEFAULT_COMMAND} in the vm"
 	else
 		command="$@"
@@ -355,10 +370,12 @@ main()
 	fi
 
 	update_selftests "${kernel_checkout}" "${make_command}"
-	update_init_script "${command}"
+	update_init_script "${command}" "${exit_command}"
 	run_vm "${kernel_bzimage}"
-	copy_logs
-	echo "Logs saved in ${OUTPUT_DIR}/${LOG_FILE}"
+	if [[ "${command}" != "" ]]; then
+		copy_logs
+		echo "Logs saved in ${OUTPUT_DIR}/${LOG_FILE}"
+	fi
 }
 
 catch()
-- 
cgit v1.2.3


From d6378af615275435ce6e390a538c980ac19b6659 Mon Sep 17 00:00:00 2001
From: Cong Wang <cong.wang@bytedance.com>
Date: Tue, 30 Mar 2021 19:32:36 -0700
Subject: selftests/bpf: Add a test case for udp sockmap

Add a test case to ensure redirection between two UDP sockets work.

Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210331023237.41094-16-xiyou.wangcong@gmail.com
---
 .../selftests/bpf/prog_tests/sockmap_listen.c      | 136 +++++++++++++++++++++
 .../selftests/bpf/progs/test_sockmap_listen.c      |  22 ++++
 2 files changed, 158 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index c26e6bf05e49..648d9ae898d2 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -1603,6 +1603,141 @@ static void test_reuseport(struct test_sockmap_listen *skel,
 	}
 }
 
+static void udp_redir_to_connected(int family, int sotype, int sock_mapfd,
+				   int verd_mapfd, enum redir_mode mode)
+{
+	const char *log_prefix = redir_mode_str(mode);
+	struct sockaddr_storage addr;
+	int c0, c1, p0, p1;
+	unsigned int pass;
+	socklen_t len;
+	int err, n;
+	u64 value;
+	u32 key;
+	char b;
+
+	zero_verdict_count(verd_mapfd);
+
+	p0 = socket_loopback(family, sotype | SOCK_NONBLOCK);
+	if (p0 < 0)
+		return;
+	len = sizeof(addr);
+	err = xgetsockname(p0, sockaddr(&addr), &len);
+	if (err)
+		goto close_peer0;
+
+	c0 = xsocket(family, sotype | SOCK_NONBLOCK, 0);
+	if (c0 < 0)
+		goto close_peer0;
+	err = xconnect(c0, sockaddr(&addr), len);
+	if (err)
+		goto close_cli0;
+	err = xgetsockname(c0, sockaddr(&addr), &len);
+	if (err)
+		goto close_cli0;
+	err = xconnect(p0, sockaddr(&addr), len);
+	if (err)
+		goto close_cli0;
+
+	p1 = socket_loopback(family, sotype | SOCK_NONBLOCK);
+	if (p1 < 0)
+		goto close_cli0;
+	err = xgetsockname(p1, sockaddr(&addr), &len);
+	if (err)
+		goto close_cli0;
+
+	c1 = xsocket(family, sotype | SOCK_NONBLOCK, 0);
+	if (c1 < 0)
+		goto close_peer1;
+	err = xconnect(c1, sockaddr(&addr), len);
+	if (err)
+		goto close_cli1;
+	err = xgetsockname(c1, sockaddr(&addr), &len);
+	if (err)
+		goto close_cli1;
+	err = xconnect(p1, sockaddr(&addr), len);
+	if (err)
+		goto close_cli1;
+
+	key = 0;
+	value = p0;
+	err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+	if (err)
+		goto close_cli1;
+
+	key = 1;
+	value = p1;
+	err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+	if (err)
+		goto close_cli1;
+
+	n = write(c1, "a", 1);
+	if (n < 0)
+		FAIL_ERRNO("%s: write", log_prefix);
+	if (n == 0)
+		FAIL("%s: incomplete write", log_prefix);
+	if (n < 1)
+		goto close_cli1;
+
+	key = SK_PASS;
+	err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
+	if (err)
+		goto close_cli1;
+	if (pass != 1)
+		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
+
+	n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
+	if (n < 0)
+		FAIL_ERRNO("%s: read", log_prefix);
+	if (n == 0)
+		FAIL("%s: incomplete read", log_prefix);
+
+close_cli1:
+	xclose(c1);
+close_peer1:
+	xclose(p1);
+close_cli0:
+	xclose(c0);
+close_peer0:
+	xclose(p0);
+}
+
+static void udp_skb_redir_to_connected(struct test_sockmap_listen *skel,
+				       struct bpf_map *inner_map, int family)
+{
+	int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+	int verdict_map = bpf_map__fd(skel->maps.verdict_map);
+	int sock_map = bpf_map__fd(inner_map);
+	int err;
+
+	err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
+	if (err)
+		return;
+
+	skel->bss->test_ingress = false;
+	udp_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
+			       REDIR_EGRESS);
+	skel->bss->test_ingress = true;
+	udp_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
+			       REDIR_INGRESS);
+
+	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
+}
+
+static void test_udp_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
+			   int family)
+{
+	const char *family_name, *map_name;
+	char s[MAX_TEST_NAME];
+
+	family_name = family_str(family);
+	map_name = map_type_str(map);
+	snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
+	if (!test__start_subtest(s))
+		return;
+	udp_skb_redir_to_connected(skel, map, family);
+}
+
 static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
 		      int family)
 {
@@ -1611,6 +1746,7 @@ static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
 	test_redir(skel, map, family, SOCK_STREAM);
 	test_reuseport(skel, map, family, SOCK_STREAM);
 	test_reuseport(skel, map, family, SOCK_DGRAM);
+	test_udp_redir(skel, map, family);
 }
 
 void test_sockmap_listen(void)
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
index fa221141e9c1..a39eba9f5201 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
@@ -29,6 +29,7 @@ struct {
 } verdict_map SEC(".maps");
 
 static volatile bool test_sockmap; /* toggled by user-space */
+static volatile bool test_ingress; /* toggled by user-space */
 
 SEC("sk_skb/stream_parser")
 int prog_stream_parser(struct __sk_buff *skb)
@@ -55,6 +56,27 @@ int prog_stream_verdict(struct __sk_buff *skb)
 	return verdict;
 }
 
+SEC("sk_skb/skb_verdict")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+	unsigned int *count;
+	__u32 zero = 0;
+	int verdict;
+
+	if (test_sockmap)
+		verdict = bpf_sk_redirect_map(skb, &sock_map, zero,
+					      test_ingress ? BPF_F_INGRESS : 0);
+	else
+		verdict = bpf_sk_redirect_hash(skb, &sock_hash, &zero,
+					       test_ingress ? BPF_F_INGRESS : 0);
+
+	count = bpf_map_lookup_elem(&verdict_map, &verdict);
+	if (count)
+		(*count)++;
+
+	return verdict;
+}
+
 SEC("sk_msg")
 int prog_msg_verdict(struct sk_msg_md *msg)
 {
-- 
cgit v1.2.3


From 8d7cb74f2ccb5486ab8c631a8fcdc7621bbbc42c Mon Sep 17 00:00:00 2001
From: Cong Wang <cong.wang@bytedance.com>
Date: Tue, 30 Mar 2021 19:32:37 -0700
Subject: selftests/bpf: Add a test case for loading BPF_SK_SKB_VERDICT

This adds a test case to ensure BPF_SK_SKB_VERDICT and
BPF_SK_STREAM_VERDICT will never be attached at the same time.

Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210331023237.41094-17-xiyou.wangcong@gmail.com
---
 .../selftests/bpf/prog_tests/sockmap_basic.c       | 40 ++++++++++++++++++++++
 .../bpf/progs/test_sockmap_skb_verdict_attach.c    | 18 ++++++++++
 2 files changed, 58 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index b8b48cac2ac3..ab77596b64e3 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -7,6 +7,7 @@
 #include "test_skmsg_load_helpers.skel.h"
 #include "test_sockmap_update.skel.h"
 #include "test_sockmap_invalid_update.skel.h"
+#include "test_sockmap_skb_verdict_attach.skel.h"
 #include "bpf_iter_sockmap.skel.h"
 
 #define TCP_REPAIR		19	/* TCP sock is under repair right now */
@@ -281,6 +282,39 @@ out:
 	bpf_iter_sockmap__destroy(skel);
 }
 
+static void test_sockmap_skb_verdict_attach(enum bpf_attach_type first,
+					    enum bpf_attach_type second)
+{
+	struct test_sockmap_skb_verdict_attach *skel;
+	int err, map, verdict;
+
+	skel = test_sockmap_skb_verdict_attach__open_and_load();
+	if (CHECK_FAIL(!skel)) {
+		perror("test_sockmap_skb_verdict_attach__open_and_load");
+		return;
+	}
+
+	verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+	map = bpf_map__fd(skel->maps.sock_map);
+
+	err = bpf_prog_attach(verdict, map, first, 0);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_prog_attach");
+		goto out;
+	}
+
+	err = bpf_prog_attach(verdict, map, second, 0);
+	assert(err == -1 && errno == EBUSY);
+
+	err = bpf_prog_detach2(verdict, map, first);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_prog_detach2");
+		goto out;
+	}
+out:
+	test_sockmap_skb_verdict_attach__destroy(skel);
+}
+
 void test_sockmap_basic(void)
 {
 	if (test__start_subtest("sockmap create_update_free"))
@@ -301,4 +335,10 @@ void test_sockmap_basic(void)
 		test_sockmap_copy(BPF_MAP_TYPE_SOCKMAP);
 	if (test__start_subtest("sockhash copy"))
 		test_sockmap_copy(BPF_MAP_TYPE_SOCKHASH);
+	if (test__start_subtest("sockmap skb_verdict attach")) {
+		test_sockmap_skb_verdict_attach(BPF_SK_SKB_VERDICT,
+						BPF_SK_SKB_STREAM_VERDICT);
+		test_sockmap_skb_verdict_attach(BPF_SK_SKB_STREAM_VERDICT,
+						BPF_SK_SKB_VERDICT);
+	}
 }
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c
new file mode 100644
index 000000000000..2d31f66e4f23
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, __u64);
+} sock_map SEC(".maps");
+
+SEC("sk_skb/skb_verdict")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+	return SK_DROP;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3