[PATCH v4 bpf-next 3/5] libbpf: add auto-attach for uprobes based on section name

[Alan Maguire <alan.maguire@xxxxxxxxxx>]

Now that u[ret]probes can use name-based specification, it makes
sense to add support for auto-attach based on SEC() definition.
The format proposed is

        SEC("u[ret]probe/prog:[raw_offset|[function_name[+offset]]")

For example, to trace malloc() in libc:

        SEC("uprobe/libc.so.6:malloc")

...or to trace function foo2 in /usr/bin/foo:

	SEC("uprobe//usr/bin/foo:foo2")

Auto-attach is done for all tasks (pid -1).  prog can be an absolute
path or simply a program/library name; in the latter case, we use
PATH/LD_LIBRARY_PATH to resolve the full path, falling back to
standard locations (/usr/bin:/usr/sbin or /usr/lib64:/usr/lib) if
the file is not found via environment-variable specified locations.

Signed-off-by: Alan Maguire <alan.maguire@xxxxxxxxxx>
---
 tools/lib/bpf/libbpf.c | 68 ++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 66 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2b50b01..0dcbca8 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8593,6 +8593,7 @@ int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log
 }
 
 static int attach_kprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link);
+static int attach_uprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 static int attach_trace(const struct bpf_program *prog, long cookie, struct bpf_link **link);
@@ -8604,9 +8605,9 @@ int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log
 	SEC_DEF("sk_reuseport/migrate",	SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
 	SEC_DEF("sk_reuseport",		SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
 	SEC_DEF("kprobe/",		KPROBE,	0, SEC_NONE, attach_kprobe),
-	SEC_DEF("uprobe/",		KPROBE,	0, SEC_NONE),
+	SEC_DEF("uprobe/",		KPROBE,	0, SEC_NONE, attach_uprobe),
 	SEC_DEF("kretprobe/",		KPROBE, 0, SEC_NONE, attach_kprobe),
-	SEC_DEF("uretprobe/",		KPROBE, 0, SEC_NONE),
+	SEC_DEF("uretprobe/",		KPROBE, 0, SEC_NONE, attach_uprobe),
 	SEC_DEF("tc",			SCHED_CLS, 0, SEC_NONE),
 	SEC_DEF("classifier",		SCHED_CLS, 0, SEC_NONE | SEC_SLOPPY_PFX | SEC_DEPRECATED),
 	SEC_DEF("action",		SCHED_ACT, 0, SEC_NONE | SEC_SLOPPY_PFX),
@@ -10761,6 +10762,69 @@ struct bpf_link *bpf_program__attach_uprobe(const struct bpf_program *prog,
 	return bpf_program__attach_uprobe_opts(prog, pid, binary_path, func_offset, &opts);
 }
 
+/* Format of u[ret]probe section definition supporting auto-attach:
+ * u[ret]probe/prog:function[+offset]
+ *
+ * prog can be an absolute/relative path or a filename; the latter is resolved to a
+ * full path via bpf_program__attach_uprobe_opts.
+ *
+ * Many uprobe programs do not avail of auto-attach, so we need to handle the
+ * case where the format is uprobe/myfunc by returning 0 with *link set to NULL
+ * to identify the case where auto-attach is not supported.
+ */
+static int attach_uprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link)
+{
+	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts);
+	char *func, *probe_name, *func_end;
+	char *func_name, binary_path[512];
+	unsigned long long raw_offset;
+	size_t offset = 0;
+	int n;
+
+	*link = NULL;
+
+	opts.retprobe = str_has_pfx(prog->sec_name, "uretprobe/");
+	if (opts.retprobe)
+		probe_name = prog->sec_name + sizeof("uretprobe/") - 1;
+	else
+		probe_name = prog->sec_name + sizeof("uprobe/") - 1;
+
+	snprintf(binary_path, sizeof(binary_path), "%s", probe_name);
+	/* ':' should be prior to function+offset */
+	func_name = strrchr(binary_path, ':');
+	if (!func_name) {
+		pr_debug("section '%s' is old-style u[ret]probe/function, cannot auto-attach\n",
+			 prog->sec_name);
+		return 0;
+	}
+	func_name[0] = '\0';
+	func_name++;
+	n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%li", &func, &offset);
+	if (n < 1) {
+		pr_warn("uprobe name '%s' is invalid\n", func_name);
+		return -EINVAL;
+	}
+	if (opts.retprobe && offset != 0) {
+		free(func);
+		pr_warn("uretprobes do not support offset specification\n");
+		return -EINVAL;
+	}
+
+	/* Is func a raw address? */
+	errno = 0;
+	raw_offset = strtoull(func, &func_end, 0);
+	if (!errno && !*func_end) {
+		free(func);
+		func = NULL;
+		offset = (size_t)raw_offset;
+	}
+	opts.func_name = func;
+
+	*link = bpf_program__attach_uprobe_opts(prog, -1, binary_path, offset, &opts);
+	free(func);
+	return 0;
+}
+
 static int determine_tracepoint_id(const char *tp_category,
 				   const char *tp_name)
 {
-- 
1.8.3.1