bpf: Add multi kprobe link

Adding new link type BPF_LINK_TYPE_KPROBE_MULTI that attaches kprobe
program through fprobe API.

The fprobe API allows to attach probe on multiple functions at once
very fast, because it works on top of ftrace. On the other hand this
limits the probe point to the function entry or return.

The kprobe program gets the same pt_regs input ctx as when it's attached
through the perf API.

Adding new attach type BPF_TRACE_KPROBE_MULTI that allows attachment
kprobe to multiple function with new link.

User provides array of addresses or symbols with count to attach the
kprobe program to. The new link_create uapi interface looks like:

  struct {
          __u32           flags;
          __u32           cnt;
          __aligned_u64   syms;
          __aligned_u64   addrs;
  } kprobe_multi;

The flags field allows single BPF_TRACE_KPROBE_MULTI bit to create
return multi kprobe.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220316122419.933957-4-jolsa@kernel.org

2 files changed, 232 insertions, 5 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 9beb585be5a6..b8bb67ee6c57 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -32,6 +32,7 @@
 #include <linux/bpf-netns.h>
 #include <linux/rcupdate_trace.h>
 #include <linux/memcontrol.h>
+#include <linux/trace_events.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
 			  (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
@@ -3022,6 +3023,11 @@ out_put_file:
 	fput(perf_file);
 	return err;
 }
+#else
+static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_PERF_EVENTS */
 
 #define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd
@@ -4255,7 +4261,7 @@ static int tracing_bpf_link_attach(const union bpf_attr *attr, bpfptr_t uattr,
 	return -EINVAL;
 }
 
-#define BPF_LINK_CREATE_LAST_FIELD link_create.iter_info_len
+#define BPF_LINK_CREATE_LAST_FIELD link_create.kprobe_multi.addrs
 static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 {
 	enum bpf_prog_type ptype;
@@ -4279,7 +4285,6 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 		ret = tracing_bpf_link_attach(attr, uattr, prog);
 		goto out;
 	case BPF_PROG_TYPE_PERF_EVENT:
-	case BPF_PROG_TYPE_KPROBE:
 	case BPF_PROG_TYPE_TRACEPOINT:
 		if (attr->link_create.attach_type != BPF_PERF_EVENT) {
 			ret = -EINVAL;
@@ -4287,6 +4292,14 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 		}
 		ptype = prog->type;
 		break;
+	case BPF_PROG_TYPE_KPROBE:
+		if (attr->link_create.attach_type != BPF_PERF_EVENT &&
+		    attr->link_create.attach_type != BPF_TRACE_KPROBE_MULTI) {
+			ret = -EINVAL;
+			goto out;
+		}
+		ptype = prog->type;
+		break;
 	default:
 		ptype = attach_type_to_prog_type(attr->link_create.attach_type);
 		if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) {
@@ -4318,13 +4331,16 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 		ret = bpf_xdp_link_attach(attr, prog);
 		break;
 #endif
-#ifdef CONFIG_PERF_EVENTS
 	case BPF_PROG_TYPE_PERF_EVENT:
 	case BPF_PROG_TYPE_TRACEPOINT:
-	case BPF_PROG_TYPE_KPROBE:
 		ret = bpf_perf_link_attach(attr, prog);
 		break;
-#endif
+	case BPF_PROG_TYPE_KPROBE:
+		if (attr->link_create.attach_type == BPF_PERF_EVENT)
+			ret = bpf_perf_link_attach(attr, prog);
+		else
+			ret = bpf_kprobe_multi_link_attach(attr, prog);
+		break;
 	default:
 		ret = -EINVAL;
 	}
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index a2024ba32a20..fffa2171fae4 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -17,6 +17,7 @@
 #include <linux/error-injection.h>
 #include <linux/btf_ids.h>
 #include <linux/bpf_lsm.h>
+#include <linux/fprobe.h>
 
 #include <net/bpf_sk_storage.h>
 
@@ -2181,3 +2182,213 @@ static int __init bpf_event_init(void)
 
 fs_initcall(bpf_event_init);
 #endif /* CONFIG_MODULES */
+
+#ifdef CONFIG_FPROBE
+struct bpf_kprobe_multi_link {
+	struct bpf_link link;
+	struct fprobe fp;
+	unsigned long *addrs;
+};
+
+static void bpf_kprobe_multi_link_release(struct bpf_link *link)
+{
+	struct bpf_kprobe_multi_link *kmulti_link;
+
+	kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
+	unregister_fprobe(&kmulti_link->fp);
+}
+
+static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_kprobe_multi_link *kmulti_link;
+
+	kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
+	kvfree(kmulti_link->addrs);
+	kfree(kmulti_link);
+}
+
+static const struct bpf_link_ops bpf_kprobe_multi_link_lops = {
+	.release = bpf_kprobe_multi_link_release,
+	.dealloc = bpf_kprobe_multi_link_dealloc,
+};
+
+static int
+kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
+			   struct pt_regs *regs)
+{
+	int err;
+
+	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
+		err = 0;
+		goto out;
+	}
+
+	migrate_disable();
+	rcu_read_lock();
+	err = bpf_prog_run(link->link.prog, regs);
+	rcu_read_unlock();
+	migrate_enable();
+
+ out:
+	__this_cpu_dec(bpf_prog_active);
+	return err;
+}
+
+static void
+kprobe_multi_link_handler(struct fprobe *fp, unsigned long entry_ip,
+			  struct pt_regs *regs)
+{
+	unsigned long saved_ip = instruction_pointer(regs);
+	struct bpf_kprobe_multi_link *link;
+
+	/*
+	 * Because fprobe's regs->ip is set to the next instruction of
+	 * dynamic-ftrace instruction, correct entry ip must be set, so
+	 * that the bpf program can access entry address via regs as same
+	 * as kprobes.
+	 *
+	 * Both kprobe and kretprobe see the entry ip of traced function
+	 * as instruction pointer.
+	 */
+	instruction_pointer_set(regs, entry_ip);
+
+	link = container_of(fp, struct bpf_kprobe_multi_link, fp);
+	kprobe_multi_link_prog_run(link, regs);
+
+	instruction_pointer_set(regs, saved_ip);
+}
+
+static int
+kprobe_multi_resolve_syms(const void *usyms, u32 cnt,
+			  unsigned long *addrs)
+{
+	unsigned long addr, size;
+	const char **syms;
+	int err = -ENOMEM;
+	unsigned int i;
+	char *func;
+
+	size = cnt * sizeof(*syms);
+	syms = kvzalloc(size, GFP_KERNEL);
+	if (!syms)
+		return -ENOMEM;
+
+	func = kmalloc(KSYM_NAME_LEN, GFP_KERNEL);
+	if (!func)
+		goto error;
+
+	if (copy_from_user(syms, usyms, size)) {
+		err = -EFAULT;
+		goto error;
+	}
+
+	for (i = 0; i < cnt; i++) {
+		err = strncpy_from_user(func, syms[i], KSYM_NAME_LEN);
+		if (err == KSYM_NAME_LEN)
+			err = -E2BIG;
+		if (err < 0)
+			goto error;
+		err = -EINVAL;
+		addr = kallsyms_lookup_name(func);
+		if (!addr)
+			goto error;
+		if (!kallsyms_lookup_size_offset(addr, &size, NULL))
+			goto error;
+		addr = ftrace_location_range(addr, addr + size - 1);
+		if (!addr)
+			goto error;
+		addrs[i] = addr;
+	}
+
+	err = 0;
+error:
+	kvfree(syms);
+	kfree(func);
+	return err;
+}
+
+int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct bpf_kprobe_multi_link *link = NULL;
+	struct bpf_link_primer link_primer;
+	unsigned long *addrs;
+	u32 flags, cnt, size;
+	void __user *uaddrs;
+	void __user *usyms;
+	int err;
+
+	/* no support for 32bit archs yet */
+	if (sizeof(u64) != sizeof(void *))
+		return -EOPNOTSUPP;
+
+	if (prog->expected_attach_type != BPF_TRACE_KPROBE_MULTI)
+		return -EINVAL;
+
+	flags = attr->link_create.kprobe_multi.flags;
+	if (flags & ~BPF_F_KPROBE_MULTI_RETURN)
+		return -EINVAL;
+
+	uaddrs = u64_to_user_ptr(attr->link_create.kprobe_multi.addrs);
+	usyms = u64_to_user_ptr(attr->link_create.kprobe_multi.syms);
+	if (!!uaddrs == !!usyms)
+		return -EINVAL;
+
+	cnt = attr->link_create.kprobe_multi.cnt;
+	if (!cnt)
+		return -EINVAL;
+
+	size = cnt * sizeof(*addrs);
+	addrs = kvmalloc(size, GFP_KERNEL);
+	if (!addrs)
+		return -ENOMEM;
+
+	if (uaddrs) {
+		if (copy_from_user(addrs, uaddrs, size)) {
+			err = -EFAULT;
+			goto error;
+		}
+	} else {
+		err = kprobe_multi_resolve_syms(usyms, cnt, addrs);
+		if (err)
+			goto error;
+	}
+
+	link = kzalloc(sizeof(*link), GFP_KERNEL);
+	if (!link) {
+		err = -ENOMEM;
+		goto error;
+	}
+
+	bpf_link_init(&link->link, BPF_LINK_TYPE_KPROBE_MULTI,
+		      &bpf_kprobe_multi_link_lops, prog);
+
+	err = bpf_link_prime(&link->link, &link_primer);
+	if (err)
+		goto error;
+
+	if (flags & BPF_F_KPROBE_MULTI_RETURN)
+		link->fp.exit_handler = kprobe_multi_link_handler;
+	else
+		link->fp.entry_handler = kprobe_multi_link_handler;
+
+	link->addrs = addrs;
+
+	err = register_fprobe_ips(&link->fp, addrs, cnt);
+	if (err) {
+		bpf_link_cleanup(&link_primer);
+		return err;
+	}
+
+	return bpf_link_settle(&link_primer);
+
+error:
+	kfree(link);
+	kvfree(addrs);
+	return err;
+}
+#else /* !CONFIG_FPROBE */
+int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
+#endif