Merge branch 'bpf: add a ksym BPF iterator'

Alan Maguire says:

====================

a ksym BPF iterator would be useful as it would allow more flexible
interactions with kernel symbols than are currently supported; it could
for example create more efficient map representations for lookup,
speed up symbol resolution etc.

The idea was initially discussed here [1].

Changes since v5 [2]:
- no need to add kallsym_iter to bpf_iter.h as it has existed in kernels
  for a long time so will by in vmlinux.h for older kernels too, unlike
 struct bpf_iter__ksym (Yonghong, patch 2)

Changes since v4 [3]:

- add BPF_ITER_RESCHED to improve responsiveness (Hao, patch 1)
- remove pr_warn to be consistent with other iterators (Andrii, patch 1)
- add definitions to bpf_iter.h to ensure iter tests build on older
  kernels (Andrii, patch 2)

Changes since v3 [4]:

- use late_initcall() to register iter; means we are both consistent
  with other iters and can encapsulate all iter-specific code in
  kallsyms.c in CONFIG_BPF_SYSCALL (Alexei, Yonghong, patch 1).

Changes since v2 [5]:

- set iter->show_value on initialization based on current creds
  and use it in selftest to determine if we show values
  (Yonghong, patches 1/2)
- inline iter registration into kallsyms_init (Yonghong, patch 1)

Changes since RFC [6]:

- change name of iterator (and associated structures/fields) to "ksym"
  (Andrii, patches 1, 2)
- remove dependency on CONFIG_PROC_FS; it was used for other BPF
  iterators, and I assumed it was needed because of seq ops but I
  don't think it is required on digging futher (Andrii, patch 1)

[1] https://lore.kernel.org/all/YjRPZj6Z8vuLeEZo@krava/
[2] https://lore.kernel.org/bpf/1657490998-31468-1-git-send-email-alan.maguire@oracle.com/
[3] https://lore.kernel.org/bpf/1657113391-5624-1-git-send-email-alan.maguire@oracle.com/
[4] https://lore.kernel.org/bpf/1656942916-13491-1-git-send-email-alan.maguire@oracle.com
[5] https://lore.kernel.org/bpf/1656667620-18718-1-git-send-email-alan.maguire@oracle.com/
[6] https://lore.kernel.org/all/1656089118-577-1-git-send-email-alan.maguire@oracle.com/
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

4 files changed, 188 insertions, 0 deletions

diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index fbdf8d3279ac..79a85834ce9d 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -30,6 +30,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/bsearch.h>
+#include <linux/btf_ids.h>
 
 /*
  * These will be re-linked against their real values
@@ -799,6 +800,96 @@ static const struct seq_operations kallsyms_op = {
 	.show = s_show
 };
 
+#ifdef CONFIG_BPF_SYSCALL
+
+struct bpf_iter__ksym {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct kallsym_iter *, ksym);
+};
+
+static int ksym_prog_seq_show(struct seq_file *m, bool in_stop)
+{
+	struct bpf_iter__ksym ctx;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	meta.seq = m;
+	prog = bpf_iter_get_info(&meta, in_stop);
+	if (!prog)
+		return 0;
+
+	ctx.meta = &meta;
+	ctx.ksym = m ? m->private : NULL;
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static int bpf_iter_ksym_seq_show(struct seq_file *m, void *p)
+{
+	return ksym_prog_seq_show(m, false);
+}
+
+static void bpf_iter_ksym_seq_stop(struct seq_file *m, void *p)
+{
+	if (!p)
+		(void) ksym_prog_seq_show(m, true);
+	else
+		s_stop(m, p);
+}
+
+static const struct seq_operations bpf_iter_ksym_ops = {
+	.start = s_start,
+	.next = s_next,
+	.stop = bpf_iter_ksym_seq_stop,
+	.show = bpf_iter_ksym_seq_show,
+};
+
+static int bpf_iter_ksym_init(void *priv_data, struct bpf_iter_aux_info *aux)
+{
+	struct kallsym_iter *iter = priv_data;
+
+	reset_iter(iter, 0);
+
+	/* cache here as in kallsyms_open() case; use current process
+	 * credentials to tell BPF iterators if values should be shown.
+	 */
+	iter->show_value = kallsyms_show_value(current_cred());
+
+	return 0;
+}
+
+DEFINE_BPF_ITER_FUNC(ksym, struct bpf_iter_meta *meta, struct kallsym_iter *ksym)
+
+static const struct bpf_iter_seq_info ksym_iter_seq_info = {
+	.seq_ops		= &bpf_iter_ksym_ops,
+	.init_seq_private	= bpf_iter_ksym_init,
+	.fini_seq_private	= NULL,
+	.seq_priv_size		= sizeof(struct kallsym_iter),
+};
+
+static struct bpf_iter_reg ksym_iter_reg_info = {
+	.target                 = "ksym",
+	.feature		= BPF_ITER_RESCHED,
+	.ctx_arg_info_size	= 1,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__ksym, ksym),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+	.seq_info		= &ksym_iter_seq_info,
+};
+
+BTF_ID_LIST(btf_ksym_iter_id)
+BTF_ID(struct, kallsym_iter)
+
+static int __init bpf_ksym_iter_register(void)
+{
+	ksym_iter_reg_info.ctx_arg_info[0].btf_id = *btf_ksym_iter_id;
+	return bpf_iter_reg_target(&ksym_iter_reg_info);
+}
+
+late_initcall(bpf_ksym_iter_register);
+
+#endif /* CONFIG_BPF_SYSCALL */
+
 static inline int kallsyms_for_perf(void)
 {
 #ifdef CONFIG_PERF_EVENTS
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 7ff5fa93d056..a33874b081b6 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -27,6 +27,7 @@
 #include "bpf_iter_test_kern5.skel.h"
 #include "bpf_iter_test_kern6.skel.h"
 #include "bpf_iter_bpf_link.skel.h"
+#include "bpf_iter_ksym.skel.h"
 
 static int duration;
 
@@ -1120,6 +1121,19 @@ static void test_link_iter(void)
 	bpf_iter_bpf_link__destroy(skel);
 }
 
+static void test_ksym_iter(void)
+{
+	struct bpf_iter_ksym *skel;
+
+	skel = bpf_iter_ksym__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bpf_iter_ksym__open_and_load"))
+		return;
+
+	do_dummy_read(skel->progs.dump_ksym);
+
+	bpf_iter_ksym__destroy(skel);
+}
+
 #define CMP_BUFFER_SIZE 1024
 static char task_vma_output[CMP_BUFFER_SIZE];
 static char proc_maps_output[CMP_BUFFER_SIZE];
@@ -1267,4 +1281,6 @@ void test_bpf_iter(void)
 		test_buf_neg_offset();
 	if (test__start_subtest("link-iter"))
 		test_link_iter();
+	if (test__start_subtest("ksym"))
+		test_ksym_iter();
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h
index 97ec8bc76ae6..e9846606690d 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter.h
+++ b/tools/testing/selftests/bpf/progs/bpf_iter.h
@@ -22,6 +22,7 @@
 #define BTF_F_NONAME BTF_F_NONAME___not_used
 #define BTF_F_PTR_RAW BTF_F_PTR_RAW___not_used
 #define BTF_F_ZERO BTF_F_ZERO___not_used
+#define bpf_iter__ksym bpf_iter__ksym___not_used
 #include "vmlinux.h"
 #undef bpf_iter_meta
 #undef bpf_iter__bpf_map
@@ -44,6 +45,7 @@
 #undef BTF_F_NONAME
 #undef BTF_F_PTR_RAW
 #undef BTF_F_ZERO
+#undef bpf_iter__ksym
 
 struct bpf_iter_meta {
 	struct seq_file *seq;
@@ -151,3 +153,8 @@ enum {
 	BTF_F_PTR_RAW	=	(1ULL << 2),
 	BTF_F_ZERO	=	(1ULL << 3),
 };
+
+struct bpf_iter__ksym {
+	struct bpf_iter_meta *meta;
+	struct kallsym_iter *ksym;
+};
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c b/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c
new file mode 100644
index 000000000000..285c008cbf9c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022, Oracle and/or its affiliates. */
+#include "bpf_iter.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+unsigned long last_sym_value = 0;
+
+static inline char tolower(char c)
+{
+	if (c >= 'A' && c <= 'Z')
+		c += ('a' - 'A');
+	return c;
+}
+
+static inline char toupper(char c)
+{
+	if (c >= 'a' && c <= 'z')
+		c -= ('a' - 'A');
+	return c;
+}
+
+/* Dump symbols with max size; the latter is calculated by caching symbol N value
+ * and when iterating on symbol N+1, we can print max size of symbol N via
+ * address of N+1 - address of N.
+ */
+SEC("iter/ksym")
+int dump_ksym(struct bpf_iter__ksym *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct kallsym_iter *iter = ctx->ksym;
+	__u32 seq_num = ctx->meta->seq_num;
+	unsigned long value;
+	char type;
+	int ret;
+
+	if (!iter)
+		return 0;
+
+	if (seq_num == 0) {
+		BPF_SEQ_PRINTF(seq, "ADDR TYPE NAME MODULE_NAME KIND MAX_SIZE\n");
+		return 0;
+	}
+	if (last_sym_value)
+		BPF_SEQ_PRINTF(seq, "0x%x\n", iter->value - last_sym_value);
+	else
+		BPF_SEQ_PRINTF(seq, "\n");
+
+	value = iter->show_value ? iter->value : 0;
+
+	last_sym_value = value;
+
+	type = iter->type;
+
+	if (iter->module_name[0]) {
+		type = iter->exported ? toupper(type) : tolower(type);
+		BPF_SEQ_PRINTF(seq, "0x%llx %c %s [ %s ] ",
+			       value, type, iter->name, iter->module_name);
+	} else {
+		BPF_SEQ_PRINTF(seq, "0x%llx %c %s ", value, type, iter->name);
+	}
+	if (!iter->pos_arch_end || iter->pos_arch_end > iter->pos)
+		BPF_SEQ_PRINTF(seq, "CORE ");
+	else if (!iter->pos_mod_end || iter->pos_mod_end > iter->pos)
+		BPF_SEQ_PRINTF(seq, "MOD ");
+	else if (!iter->pos_ftrace_mod_end || iter->pos_ftrace_mod_end > iter->pos)
+		BPF_SEQ_PRINTF(seq, "FTRACE_MOD ");
+	else if (!iter->pos_bpf_end || iter->pos_bpf_end > iter->pos)
+		BPF_SEQ_PRINTF(seq, "BPF ");
+	else
+		BPF_SEQ_PRINTF(seq, "KPROBE ");
+	return 0;
+}