bpf: Add a bpf_snprintf helper

The implementation takes inspiration from the existing bpf_trace_printk
helper but there are a few differences:

To allow for a large number of format-specifiers, parameters are
provided in an array, like in bpf_seq_printf.

Because the output string takes two arguments and the array of
parameters also takes two arguments, the format string needs to fit in
one argument. Thankfully, ARG_PTR_TO_CONST_STR is guaranteed to point to
a zero-terminated read-only map so we don't need a format string length
arg.

Because the format-string is known at verification time, we also do
a first pass of format string validation in the verifier logic. This
makes debugging easier.

Signed-off-by: Florent Revest <revest@chromium.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210419155243.1632274-4-revest@chromium.org

2 files changed, 91 insertions, 0 deletions

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 9ca57eb1fc0d..85b26ca5aacd 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -925,6 +925,54 @@ out:
 	return err;
 }
 
+#define MAX_SNPRINTF_VARARGS		12
+
+BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt,
+	   const void *, data, u32, data_len)
+{
+	enum bpf_printf_mod_type mod[MAX_SNPRINTF_VARARGS];
+	u64 args[MAX_SNPRINTF_VARARGS];
+	int err, num_args;
+
+	if (data_len % 8 || data_len > MAX_SNPRINTF_VARARGS * 8 ||
+	    (data_len && !data))
+		return -EINVAL;
+	num_args = data_len / 8;
+
+	/* ARG_PTR_TO_CONST_STR guarantees that fmt is zero-terminated so we
+	 * can safely give an unbounded size.
+	 */
+	err = bpf_printf_prepare(fmt, UINT_MAX, data, args, mod, num_args);
+	if (err < 0)
+		return err;
+
+	/* Maximumly we can have MAX_SNPRINTF_VARARGS parameters, just give
+	 * all of them to snprintf().
+	 */
+	err = snprintf(str, str_size, fmt, BPF_CAST_FMT_ARG(0, args, mod),
+		BPF_CAST_FMT_ARG(1, args, mod), BPF_CAST_FMT_ARG(2, args, mod),
+		BPF_CAST_FMT_ARG(3, args, mod), BPF_CAST_FMT_ARG(4, args, mod),
+		BPF_CAST_FMT_ARG(5, args, mod), BPF_CAST_FMT_ARG(6, args, mod),
+		BPF_CAST_FMT_ARG(7, args, mod), BPF_CAST_FMT_ARG(8, args, mod),
+		BPF_CAST_FMT_ARG(9, args, mod), BPF_CAST_FMT_ARG(10, args, mod),
+		BPF_CAST_FMT_ARG(11, args, mod));
+
+	bpf_printf_cleanup();
+
+	return err + 1;
+}
+
+const struct bpf_func_proto bpf_snprintf_proto = {
+	.func		= bpf_snprintf,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM_OR_NULL,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg3_type	= ARG_PTR_TO_CONST_STR,
+	.arg4_type	= ARG_PTR_TO_MEM_OR_NULL,
+	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
+};
+
 const struct bpf_func_proto bpf_get_current_task_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_str_proto __weak;
@@ -1013,6 +1061,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_probe_read_kernel_str_proto;
 	case BPF_FUNC_snprintf_btf:
 		return &bpf_snprintf_btf_proto;
+	case BPF_FUNC_snprintf:
+		return &bpf_snprintf_proto;
 	default:
 		return NULL;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5f46dd6f3383..994ef36c5f60 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5918,6 +5918,41 @@ static int check_reference_leak(struct bpf_verifier_env *env)
 	return state->acquired_refs ? -EINVAL : 0;
 }
 
+static int check_bpf_snprintf_call(struct bpf_verifier_env *env,
+				   struct bpf_reg_state *regs)
+{
+	struct bpf_reg_state *fmt_reg = &regs[BPF_REG_3];
+	struct bpf_reg_state *data_len_reg = &regs[BPF_REG_5];
+	struct bpf_map *fmt_map = fmt_reg->map_ptr;
+	int err, fmt_map_off, num_args;
+	u64 fmt_addr;
+	char *fmt;
+
+	/* data must be an array of u64 */
+	if (data_len_reg->var_off.value % 8)
+		return -EINVAL;
+	num_args = data_len_reg->var_off.value / 8;
+
+	/* fmt being ARG_PTR_TO_CONST_STR guarantees that var_off is const
+	 * and map_direct_value_addr is set.
+	 */
+	fmt_map_off = fmt_reg->off + fmt_reg->var_off.value;
+	err = fmt_map->ops->map_direct_value_addr(fmt_map, &fmt_addr,
+						  fmt_map_off);
+	if (err)
+		return err;
+	fmt = (char *)(long)fmt_addr + fmt_map_off;
+
+	/* We are also guaranteed that fmt+fmt_map_off is NULL terminated, we
+	 * can focus on validating the format specifiers.
+	 */
+	err = bpf_printf_prepare(fmt, UINT_MAX, NULL, NULL, NULL, num_args);
+	if (err < 0)
+		verbose(env, "Invalid format string\n");
+
+	return err;
+}
+
 static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			     int *insn_idx_p)
 {
@@ -6032,6 +6067,12 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 			return -EINVAL;
 	}
 
+	if (func_id == BPF_FUNC_snprintf) {
+		err = check_bpf_snprintf_call(env, regs);
+		if (err < 0)
+			return err;
+	}
+
 	/* reset caller saved regs */
 	for (i = 0; i < CALLER_SAVED_REGS; i++) {
 		mark_reg_not_init(env, regs, caller_saved[i]);