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>

1 files changed, 91 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