selftests/bpf: Tracing prog can still do lookup under busy lock

This patch modifies the task_ls_recursion test to check that
the first bpf_task_storage_get(&map_a, ...) in BPF_PROG(on_update)
can still do the lockless lookup even it cannot acquire the percpu
busy lock.  If the lookup succeeds, it will increment the value
by 1 and the value in the task storage map_a will become 200+1=201.
After that, BPF_PROG(on_update) tries to delete from map_a and
should get -EBUSY because it cannot acquire the percpu busy lock
after finding the data.

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20221025184524.3526117-10-martin.lau@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Author: Martin KaFai Lau

tools/testing/selftests/bpf/prog_tests/task_local_storage.c

@@ -8,6 +8,7 @@
 #include <sys/syscall.h>   /* For SYS_xxx definitions */
 #include <sys/types.h>
 #include <test_progs.h>
+#include "task_local_storage_helpers.h"
 #include "task_local_storage.skel.h"
 #include "task_local_storage_exit_creds.skel.h"
 #include "task_ls_recursion.skel.h"
@@ -78,21 +79,64 @@ static void test_exit_creds(void)
 
 static void test_recursion(void)
 {
+	int err, map_fd, prog_fd, task_fd;
 	struct task_ls_recursion *skel;
-	int err;
+	struct bpf_prog_info info;
+	__u32 info_len = sizeof(info);
+	long value;
+
+	task_fd = sys_pidfd_open(getpid(), 0);
+	if (!ASSERT_NEQ(task_fd, -1, "sys_pidfd_open"))
+		return;
 
 	skel = task_ls_recursion__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
-		return;
+		goto out;
 
 	err = task_ls_recursion__attach(skel);
 	if (!ASSERT_OK(err, "skel_attach"))
 		goto out;
 
 	/* trigger sys_enter, make sure it does not cause deadlock */
+	skel->bss->test_pid = getpid();
 	syscall(SYS_gettid);
+	skel->bss->test_pid = 0;
+	task_ls_recursion__detach(skel);
+
+	/* Refer to the comment in BPF_PROG(on_update) for
+	 * the explanation on the value 201 and 100.
+	 */
+	map_fd = bpf_map__fd(skel->maps.map_a);
+	err = bpf_map_lookup_elem(map_fd, &task_fd, &value);
+	ASSERT_OK(err, "lookup map_a");
+	ASSERT_EQ(value, 201, "map_a value");
+	ASSERT_EQ(skel->bss->nr_del_errs, 1, "bpf_task_storage_delete busy");
+
+	map_fd = bpf_map__fd(skel->maps.map_b);
+	err = bpf_map_lookup_elem(map_fd, &task_fd, &value);
+	ASSERT_OK(err, "lookup map_b");
+	ASSERT_EQ(value, 100, "map_b value");
+
+	prog_fd = bpf_program__fd(skel->progs.on_lookup);
+	memset(&info, 0, sizeof(info));
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	ASSERT_OK(err, "get prog info");
+	ASSERT_GT(info.recursion_misses, 0, "on_lookup prog recursion");
+
+	prog_fd = bpf_program__fd(skel->progs.on_update);
+	memset(&info, 0, sizeof(info));
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	ASSERT_OK(err, "get prog info");
+	ASSERT_EQ(info.recursion_misses, 0, "on_update prog recursion");
+
+	prog_fd = bpf_program__fd(skel->progs.on_enter);
+	memset(&info, 0, sizeof(info));
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	ASSERT_OK(err, "get prog info");
+	ASSERT_EQ(info.recursion_misses, 0, "on_enter prog recursion");
 
 out:
+	close(task_fd);
 	task_ls_recursion__destroy(skel);
 }
 

tools/testing/selftests/bpf/progs/task_ls_recursion.c

@@ -5,7 +5,13 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
+#ifndef EBUSY
+#define EBUSY 16
+#endif
+
 char _license[] SEC("license") = "GPL";
+int nr_del_errs = 0;
+int test_pid = 0;
 
 struct {
 	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
@@ -26,6 +32,13 @@ int BPF_PROG(on_lookup)
 {
 	struct task_struct *task = bpf_get_current_task_btf();
 
+	if (!test_pid || task->pid != test_pid)
+		return 0;
+
+	/* The bpf_task_storage_delete will call
+	 * bpf_local_storage_lookup.  The prog->active will
+	 * stop the recursion.
+	 */
 	bpf_task_storage_delete(&map_a, task);
 	bpf_task_storage_delete(&map_b, task);
 	return 0;
@@ -37,11 +50,32 @@ int BPF_PROG(on_update)
 	struct task_struct *task = bpf_get_current_task_btf();
 	long *ptr;
 
+	if (!test_pid || task->pid != test_pid)
+		return 0;
+
 	ptr = bpf_task_storage_get(&map_a, task, 0,
 				   BPF_LOCAL_STORAGE_GET_F_CREATE);
-	if (ptr)
+	/* ptr will not be NULL when it is called from
+	 * the bpf_task_storage_get(&map_b,...F_CREATE) in
+	 * the BPF_PROG(on_enter) below.  It is because
+	 * the value can be found in map_a and the kernel
+	 * does not need to acquire any spin_lock.
+	 */
+	if (ptr) {
+		int err;
+
 		*ptr += 1;
+		err = bpf_task_storage_delete(&map_a, task);
+		if (err == -EBUSY)
+			nr_del_errs++;
+	}
 
+	/* This will still fail because map_b is empty and
+	 * this BPF_PROG(on_update) has failed to acquire
+	 * the percpu busy lock => meaning potential
+	 * deadlock is detected and it will fail to create
+	 * new storage.
+	 */
 	ptr = bpf_task_storage_get(&map_b, task, 0,
 				   BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (ptr)
@@ -57,14 +91,17 @@ int BPF_PROG(on_enter, struct pt_regs *regs, long id)
 	long *ptr;
 
 	task = bpf_get_current_task_btf();
+	if (!test_pid || task->pid != test_pid)
+		return 0;
+
 	ptr = bpf_task_storage_get(&map_a, task, 0,
 				   BPF_LOCAL_STORAGE_GET_F_CREATE);
-	if (ptr)
+	if (ptr && !*ptr)
 		*ptr = 200;
 
 	ptr = bpf_task_storage_get(&map_b, task, 0,
 				   BPF_LOCAL_STORAGE_GET_F_CREATE);
-	if (ptr)
+	if (ptr && !*ptr)
 		*ptr = 100;
 	return 0;
 }