[PATCH tip 2/9] tracing: allow eBPF programs to call bpf_printk()

[Alexei Starovoitov]

Debugging of eBPF programs needs some form of printk from the program,
so let programs call limited trace_printk() with %d %u %x %p modifiers only.

Signed-off-by: Alexei Starovoitov <ast@xxxxxxxxxxxx>
---
 include/uapi/linux/bpf.h    |    1 +
 kernel/trace/bpf_trace.c    |   61 +++++++++++++++++++++++++++++++++++++++++++
 kernel/trace/trace_events.c |    8 ++++++
 3 files changed, 70 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 959538c50117..ef88e3f45b85 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -170,6 +170,7 @@ enum bpf_func_id {
 	BPF_FUNC_fetch_u8,        /* u8 bpf_fetch_u8(void *unsafe_ptr) */
 	BPF_FUNC_memcmp,          /* int bpf_memcmp(void *unsafe_ptr, void *safe_ptr, int size) */
 	BPF_FUNC_dump_stack,      /* void bpf_dump_stack(void) */
+	BPF_FUNC_printk,          /* int bpf_printk(const char *fmt, int fmt_size, ...) */
 	__BPF_FUNC_MAX_ID,
 };
 
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 639d3c25dead..3825d7a3cbd1 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -60,6 +60,60 @@ static u64 bpf_dump_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 	return 0;
 }
 
+/* limited printk()
+ * only %d %u %x %ld %lu %lx %lld %llu %llx %p conversion specifiers allowed
+ */
+static u64 bpf_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5)
+{
+	char *fmt = (char *) (long) r1;
+	int fmt_cnt = 0;
+	bool mod_l[3] = {};
+	int i;
+
+	/* bpf_check() guarantees that fmt points to bpf program stack and
+	 * fmt_size bytes of it were initialized by bpf program
+	 */
+	if (fmt[fmt_size - 1] != 0)
+		return -EINVAL;
+
+	/* check format string for allowed specifiers */
+	for (i = 0; i < fmt_size; i++)
+		if (fmt[i] == '%') {
+			if (fmt_cnt >= 3)
+				return -EINVAL;
+			i++;
+			if (i >= fmt_size)
+				return -EINVAL;
+
+			if (fmt[i] == 'l') {
+				mod_l[fmt_cnt] = true;
+				i++;
+				if (i >= fmt_size)
+					return -EINVAL;
+			} else if (fmt[i] == 'p') {
+				mod_l[fmt_cnt] = true;
+				fmt_cnt++;
+				continue;
+			}
+
+			if (fmt[i] == 'l') {
+				mod_l[fmt_cnt] = true;
+				i++;
+				if (i >= fmt_size)
+					return -EINVAL;
+			}
+
+			if (fmt[i] != 'd' && fmt[i] != 'u' && fmt[i] != 'x')
+				return -EINVAL;
+			fmt_cnt++;
+		}
+
+	return __trace_printk((unsigned long) __builtin_return_address(3), fmt,
+			      mod_l[0] ? r3 : (u32) r3,
+			      mod_l[1] ? r4 : (u32) r4,
+			      mod_l[2] ? r5 : (u32) r5);
+}
+
 static struct bpf_func_proto tracing_filter_funcs[] = {
 #define FETCH(SIZE)				\
 	[BPF_FUNC_fetch_##SIZE] = {		\
@@ -86,6 +140,13 @@ static struct bpf_func_proto tracing_filter_funcs[] = {
 		.gpl_only = false,
 		.ret_type = RET_VOID,
 	},
+	[BPF_FUNC_printk] = {
+		.func = bpf_printk,
+		.gpl_only = true,
+		.ret_type = RET_INTEGER,
+		.arg1_type = ARG_PTR_TO_STACK,
+		.arg2_type = ARG_CONST_STACK_SIZE,
+	},
 };
 
 static const struct bpf_func_proto *tracing_filter_func_proto(enum bpf_func_id func_id)
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 189cc4d697b5..282ea5822480 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1141,6 +1141,14 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
 	mutex_unlock(&event_mutex);
 
+	if (file && file->flags & TRACE_EVENT_FL_BPF) {
+		/*
+		 * allocate per-cpu printk buffers, since programs
+		 * might be calling bpf_printk
+		 */
+		trace_printk_init_buffers();
+	}
+
 	free_page((unsigned long) buf);
 	if (err < 0)
 		return err;
-- 
1.7.9.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/