Merge branch 'allow-struct_ops-to-create-map-id-to'

Amery Hung says:

====================
This patchset allows struct_ops implementors to get map id from kdata in
reg(), unreg() and update() so that they create an id to struct_ops
instance mapping. This in turn allows struct_ops kfuncs to refer to the
calling instance without passing a pointer to the struct_ops. The selftest
provides an end-to-end example.

Some struct_ops users extend themselves with other bpf programs, which
also need to call struct_ops kfuncs. For example, scx_layered uses
syscall bpf programs as a scx_layered specific control plane and uses
tracing programs to get additional information for scheduling [0].
The kfuncs may need to refer to the struct_ops instance and perform
jobs accordingly. To allow calling struct_ops kfuncs referring to
specific instances from different program types and context (e.g.,
struct_ops, tracing, async callbacks), the traditional way is to pass
the struct_ops pointer to kfuncs.

This patchset provides an alternative way, through a combination of
bpf map id and global variable. First, a struct_ops implementor will
use the map id of the struct_ops map as the id of an instance. Then,
it needs to maintain an id to instance mapping: inserting a new mapping
during reg() and removing it during unreg(). The map id can be acquired
by calling bpf_struct_ops_id().

v1 -> v2
    Add bpf_struct_ops_id() instead of using bpf_struct_ops_get()

[0] https://github.com/sched-ext/scx/blob/main/scheds/rust/scx_layered/src/bpf/main.bpf.c
====================

Link: https://patch.msgid.link/20250806162540.681679-1-ameryhung@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

include/linux/bpf.h

@@ -1985,6 +1985,7 @@ static inline void bpf_module_put(const void *data, struct module *owner)
 		module_put(owner);
 }
 int bpf_struct_ops_link_create(union bpf_attr *attr);
+u32 bpf_struct_ops_id(const void *kdata);
 
 #ifdef CONFIG_NET
 /* Define it here to avoid the use of forward declaration */

kernel/bpf/bpf_struct_ops.c

@@ -1174,6 +1174,18 @@ void bpf_struct_ops_put(const void *kdata)
 	bpf_map_put(&st_map->map);
 }
 
+u32 bpf_struct_ops_id(const void *kdata)
+{
+	struct bpf_struct_ops_value *kvalue;
+	struct bpf_struct_ops_map *st_map;
+
+	kvalue = container_of(kdata, struct bpf_struct_ops_value, data);
+	st_map = container_of(kvalue, struct bpf_struct_ops_map, kvalue);
+
+	return st_map->map.id;
+}
+EXPORT_SYMBOL_GPL(bpf_struct_ops_id);
+
 static bool bpf_struct_ops_valid_to_reg(struct bpf_map *map)
 {
 	struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map;

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

@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "struct_ops_id_ops_mapping1.skel.h"
+#include "struct_ops_id_ops_mapping2.skel.h"
+
+static void test_st_ops_id_ops_mapping(void)
+{
+	struct struct_ops_id_ops_mapping1 *skel1 = NULL;
+	struct struct_ops_id_ops_mapping2 *skel2 = NULL;
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+	int err, pid, prog1_fd, prog2_fd;
+
+	skel1 = struct_ops_id_ops_mapping1__open_and_load();
+	if (!ASSERT_OK_PTR(skel1, "struct_ops_id_ops_mapping1__open"))
+		goto out;
+
+	skel2 = struct_ops_id_ops_mapping2__open_and_load();
+	if (!ASSERT_OK_PTR(skel2, "struct_ops_id_ops_mapping2__open"))
+		goto out;
+
+	err = bpf_map_get_info_by_fd(bpf_map__fd(skel1->maps.st_ops_map),
+				     &info, &len);
+	if (!ASSERT_OK(err, "bpf_map_get_info_by_fd"))
+		goto out;
+
+	skel1->bss->st_ops_id = info.id;
+
+	err = bpf_map_get_info_by_fd(bpf_map__fd(skel2->maps.st_ops_map),
+				     &info, &len);
+	if (!ASSERT_OK(err, "bpf_map_get_info_by_fd"))
+		goto out;
+
+	skel2->bss->st_ops_id = info.id;
+
+	err = struct_ops_id_ops_mapping1__attach(skel1);
+	if (!ASSERT_OK(err, "struct_ops_id_ops_mapping1__attach"))
+		goto out;
+
+	err = struct_ops_id_ops_mapping2__attach(skel2);
+	if (!ASSERT_OK(err, "struct_ops_id_ops_mapping2__attach"))
+		goto out;
+
+	/* run tracing prog that calls .test_1 and checks return */
+	pid = getpid();
+	skel1->bss->test_pid = pid;
+	skel2->bss->test_pid = pid;
+	sys_gettid();
+	skel1->bss->test_pid = 0;
+	skel2->bss->test_pid = 0;
+
+	/* run syscall_prog that calls .test_1 and checks return */
+	prog1_fd = bpf_program__fd(skel1->progs.syscall_prog);
+	err = bpf_prog_test_run_opts(prog1_fd, NULL);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+	prog2_fd = bpf_program__fd(skel2->progs.syscall_prog);
+	err = bpf_prog_test_run_opts(prog2_fd, NULL);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+	ASSERT_EQ(skel1->bss->test_err, 0, "skel1->bss->test_err");
+	ASSERT_EQ(skel2->bss->test_err, 0, "skel2->bss->test_err");
+
+out:
+	struct_ops_id_ops_mapping1__destroy(skel1);
+	struct_ops_id_ops_mapping2__destroy(skel2);
+}
+
+void test_struct_ops_id_ops_mapping(void)
+{
+	if (test__start_subtest("st_ops_id_ops_mapping"))
+		test_st_ops_id_ops_mapping();
+}

tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping1.c

@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define bpf_kfunc_multi_st_ops_test_1(args) bpf_kfunc_multi_st_ops_test_1(args, st_ops_id)
+int st_ops_id;
+
+int test_pid;
+int test_err;
+
+#define MAP1_MAGIC 1234
+
+SEC("struct_ops")
+int BPF_PROG(test_1, struct st_ops_args *args)
+{
+	return MAP1_MAGIC;
+}
+
+SEC("tp_btf/sys_enter")
+int BPF_PROG(sys_enter, struct pt_regs *regs, long id)
+{
+	struct st_ops_args args = {};
+	struct task_struct *task;
+	int ret;
+
+	task = bpf_get_current_task_btf();
+	if (!test_pid || task->pid != test_pid)
+		return 0;
+
+	ret = bpf_kfunc_multi_st_ops_test_1(&args);
+	if (ret != MAP1_MAGIC)
+		test_err++;
+
+	return 0;
+}
+
+SEC("syscall")
+int syscall_prog(void *ctx)
+{
+	struct st_ops_args args = {};
+	int ret;
+
+	ret = bpf_kfunc_multi_st_ops_test_1(&args);
+	if (ret != MAP1_MAGIC)
+		test_err++;
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_multi_st_ops st_ops_map = {
+	.test_1 = (void *)test_1,
+};

tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping2.c

@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define bpf_kfunc_multi_st_ops_test_1(args) bpf_kfunc_multi_st_ops_test_1(args, st_ops_id)
+int st_ops_id;
+
+int test_pid;
+int test_err;
+
+#define MAP2_MAGIC 4567
+
+SEC("struct_ops")
+int BPF_PROG(test_1, struct st_ops_args *args)
+{
+	return MAP2_MAGIC;
+}
+
+SEC("tp_btf/sys_enter")
+int BPF_PROG(sys_enter, struct pt_regs *regs, long id)
+{
+	struct st_ops_args args = {};
+	struct task_struct *task;
+	int ret;
+
+	task = bpf_get_current_task_btf();
+	if (!test_pid || task->pid != test_pid)
+		return 0;
+
+	ret = bpf_kfunc_multi_st_ops_test_1(&args);
+	if (ret != MAP2_MAGIC)
+		test_err++;
+
+	return 0;
+}
+
+SEC("syscall")
+int syscall_prog(void *ctx)
+{
+	struct st_ops_args args = {};
+	int ret;
+
+	ret = bpf_kfunc_multi_st_ops_test_1(&args);
+	if (ret != MAP2_MAGIC)
+		test_err++;
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_multi_st_ops st_ops_map = {
+	.test_1 = (void *)test_1,
+};

tools/testing/selftests/bpf/test_kmods/bpf_testmod.c

@@ -1057,6 +1057,8 @@ __bpf_kfunc int bpf_kfunc_st_ops_inc10(struct st_ops_args *args)
 	return args->a;
 }
 
+__bpf_kfunc int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id);
+
 BTF_KFUNCS_START(bpf_testmod_check_kfunc_ids)
 BTF_ID_FLAGS(func, bpf_testmod_test_mod_kfunc)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test1)
@@ -1097,6 +1099,7 @@ BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_prologue, KF_TRUSTED_ARGS | KF_SLEEPABL
 BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_epilogue, KF_TRUSTED_ARGS | KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_pro_epilogue, KF_TRUSTED_ARGS | KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_kfunc_st_ops_inc10, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_kfunc_multi_st_ops_test_1, KF_TRUSTED_ARGS)
 BTF_KFUNCS_END(bpf_testmod_check_kfunc_ids)
 
 static int bpf_testmod_ops_init(struct btf *btf)
@@ -1528,6 +1531,114 @@ static struct bpf_struct_ops testmod_st_ops = {
 	.owner = THIS_MODULE,
 };
 
+struct hlist_head multi_st_ops_list;
+static DEFINE_SPINLOCK(multi_st_ops_lock);
+
+static int multi_st_ops_init(struct btf *btf)
+{
+	spin_lock_init(&multi_st_ops_lock);
+	INIT_HLIST_HEAD(&multi_st_ops_list);
+
+	return 0;
+}
+
+static int multi_st_ops_init_member(const struct btf_type *t,
+				    const struct btf_member *member,
+				    void *kdata, const void *udata)
+{
+	return 0;
+}
+
+static struct bpf_testmod_multi_st_ops *multi_st_ops_find_nolock(u32 id)
+{
+	struct bpf_testmod_multi_st_ops *st_ops;
+
+	hlist_for_each_entry(st_ops, &multi_st_ops_list, node) {
+		if (st_ops->id == id)
+			return st_ops;
+	}
+
+	return NULL;
+}
+
+int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id)
+{
+	struct bpf_testmod_multi_st_ops *st_ops;
+	unsigned long flags;
+	int ret = -1;
+
+	spin_lock_irqsave(&multi_st_ops_lock, flags);
+	st_ops = multi_st_ops_find_nolock(id);
+	if (st_ops)
+		ret = st_ops->test_1(args);
+	spin_unlock_irqrestore(&multi_st_ops_lock, flags);
+
+	return ret;
+}
+
+static int multi_st_ops_reg(void *kdata, struct bpf_link *link)
+{
+	struct bpf_testmod_multi_st_ops *st_ops =
+		(struct bpf_testmod_multi_st_ops *)kdata;
+	unsigned long flags;
+	int err = 0;
+	u32 id;
+
+	if (!st_ops->test_1)
+		return -EINVAL;
+
+	id = bpf_struct_ops_id(kdata);
+
+	spin_lock_irqsave(&multi_st_ops_lock, flags);
+	if (multi_st_ops_find_nolock(id)) {
+		pr_err("multi_st_ops(id:%d) has already been registered\n", id);
+		err = -EEXIST;
+		goto unlock;
+	}
+
+	st_ops->id = id;
+	hlist_add_head(&st_ops->node, &multi_st_ops_list);
+unlock:
+	spin_unlock_irqrestore(&multi_st_ops_lock, flags);
+
+	return err;
+}
+
+static void multi_st_ops_unreg(void *kdata, struct bpf_link *link)
+{
+	struct bpf_testmod_multi_st_ops *st_ops;
+	unsigned long flags;
+	u32 id;
+
+	id = bpf_struct_ops_id(kdata);
+
+	spin_lock_irqsave(&multi_st_ops_lock, flags);
+	st_ops = multi_st_ops_find_nolock(id);
+	if (st_ops)
+		hlist_del(&st_ops->node);
+	spin_unlock_irqrestore(&multi_st_ops_lock, flags);
+}
+
+static int bpf_testmod_multi_st_ops__test_1(struct st_ops_args *args)
+{
+	return 0;
+}
+
+static struct bpf_testmod_multi_st_ops multi_st_ops_cfi_stubs = {
+	.test_1 = bpf_testmod_multi_st_ops__test_1,
+};
+
+struct bpf_struct_ops testmod_multi_st_ops = {
+	.verifier_ops = &bpf_testmod_verifier_ops,
+	.init = multi_st_ops_init,
+	.init_member = multi_st_ops_init_member,
+	.reg = multi_st_ops_reg,
+	.unreg = multi_st_ops_unreg,
+	.cfi_stubs = &multi_st_ops_cfi_stubs,
+	.name = "bpf_testmod_multi_st_ops",
+	.owner = THIS_MODULE,
+};
+
 extern int bpf_fentry_test1(int a);
 
 static int bpf_testmod_init(void)
@@ -1550,6 +1661,7 @@ static int bpf_testmod_init(void)
 	ret = ret ?: register_bpf_struct_ops(&bpf_testmod_ops2, bpf_testmod_ops2);
 	ret = ret ?: register_bpf_struct_ops(&bpf_testmod_ops3, bpf_testmod_ops3);
 	ret = ret ?: register_bpf_struct_ops(&testmod_st_ops, bpf_testmod_st_ops);
+	ret = ret ?: register_bpf_struct_ops(&testmod_multi_st_ops, bpf_testmod_multi_st_ops);
 	ret = ret ?: register_btf_id_dtor_kfuncs(bpf_testmod_dtors,
 						 ARRAY_SIZE(bpf_testmod_dtors),
 						 THIS_MODULE);

tools/testing/selftests/bpf/test_kmods/bpf_testmod.h

@@ -116,4 +116,10 @@ struct bpf_testmod_st_ops {
 	struct module *owner;
 };
 
+struct bpf_testmod_multi_st_ops {
+	int (*test_1)(struct st_ops_args *args);
+	struct hlist_node node;
+	int id;
+};
+
 #endif /* _BPF_TESTMOD_H */

tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h

@@ -159,4 +159,6 @@ void bpf_kfunc_trusted_task_test(struct task_struct *ptr) __ksym;
 void bpf_kfunc_trusted_num_test(int *ptr) __ksym;
 void bpf_kfunc_rcu_task_test(struct task_struct *ptr) __ksym;
 
+int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id) __ksym;
+
 #endif /* _BPF_TESTMOD_KFUNC_H */