Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Alexei Starovoitov says:

====================
pull-request: bpf 2023-07-19

We've added 4 non-merge commits during the last 1 day(s) which contain
a total of 3 files changed, 55 insertions(+), 10 deletions(-).

The main changes are:

1) Fix stack depth check in presence of async callbacks,
   from Kumar Kartikeya Dwivedi.

2) Fix BTI type used for freplace attached functions,
   from Alexander Duyck.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  bpf, arm64: Fix BTI type used for freplace attached functions
  selftests/bpf: Add more tests for check_max_stack_depth bug
  bpf: Repeat check_max_stack_depth for async callbacks
  bpf: Fix subprog idx logic in check_max_stack_depth
====================

Link: https://lore.kernel.org/r/20230719174502.74023-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 55 insertions, 10 deletions

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 145b540ec34f..ec2174838f2a 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -322,7 +322,13 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 	 *
 	 */
 
-	emit_bti(A64_BTI_C, ctx);
+	/* bpf function may be invoked by 3 instruction types:
+	 * 1. bl, attached via freplace to bpf prog via short jump
+	 * 2. br, attached via freplace to bpf prog via long jump
+	 * 3. blr, working as a function pointer, used by emit_call.
+	 * So BTI_JC should used here to support both br and blr.
+	 */
+	emit_bti(A64_BTI_JC, ctx);
 
 	emit(A64_MOV(1, A64_R(9), A64_LR), ctx);
 	emit(A64_NOP, ctx);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 930b5555cfd3..02a021c524ab 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5573,16 +5573,17 @@ static int update_stack_depth(struct bpf_verifier_env *env,
  * Since recursion is prevented by check_cfg() this algorithm
  * only needs a local stack of MAX_CALL_FRAMES to remember callsites
  */
-static int check_max_stack_depth(struct bpf_verifier_env *env)
+static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx)
 {
-	int depth = 0, frame = 0, idx = 0, i = 0, subprog_end;
 	struct bpf_subprog_info *subprog = env->subprog_info;
 	struct bpf_insn *insn = env->prog->insnsi;
+	int depth = 0, frame = 0, i, subprog_end;
 	bool tail_call_reachable = false;
 	int ret_insn[MAX_CALL_FRAMES];
 	int ret_prog[MAX_CALL_FRAMES];
 	int j;
 
+	i = subprog[idx].start;
 process_func:
 	/* protect against potential stack overflow that might happen when
 	 * bpf2bpf calls get combined with tailcalls. Limit the caller's stack
@@ -5621,7 +5622,7 @@ process_func:
 continue_func:
 	subprog_end = subprog[idx + 1].start;
 	for (; i < subprog_end; i++) {
-		int next_insn;
+		int next_insn, sidx;
 
 		if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i))
 			continue;
@@ -5631,14 +5632,14 @@ continue_func:
 
 		/* find the callee */
 		next_insn = i + insn[i].imm + 1;
-		idx = find_subprog(env, next_insn);
-		if (idx < 0) {
+		sidx = find_subprog(env, next_insn);
+		if (sidx < 0) {
 			WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
 				  next_insn);
 			return -EFAULT;
 		}
-		if (subprog[idx].is_async_cb) {
-			if (subprog[idx].has_tail_call) {
+		if (subprog[sidx].is_async_cb) {
+			if (subprog[sidx].has_tail_call) {
 				verbose(env, "verifier bug. subprog has tail_call and async cb\n");
 				return -EFAULT;
 			}
@@ -5647,6 +5648,7 @@ continue_func:
 				continue;
 		}
 		i = next_insn;
+		idx = sidx;
 
 		if (subprog[idx].has_tail_call)
 			tail_call_reachable = true;
@@ -5682,6 +5684,22 @@ continue_func:
 	goto continue_func;
 }
 
+static int check_max_stack_depth(struct bpf_verifier_env *env)
+{
+	struct bpf_subprog_info *si = env->subprog_info;
+	int ret;
+
+	for (int i = 0; i < env->subprog_cnt; i++) {
+		if (!i || si[i].is_async_cb) {
+			ret = check_max_stack_depth_subprog(env, i);
+			if (ret < 0)
+				return ret;
+		}
+		continue;
+	}
+	return 0;
+}
+
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 static int get_callee_stack_depth(struct bpf_verifier_env *env,
 				  const struct bpf_insn *insn, int idx)
diff --git a/tools/testing/selftests/bpf/progs/async_stack_depth.c b/tools/testing/selftests/bpf/progs/async_stack_depth.c
index 477ba950bb43..3517c0e01206 100644
--- a/tools/testing/selftests/bpf/progs/async_stack_depth.c
+++ b/tools/testing/selftests/bpf/progs/async_stack_depth.c
@@ -22,9 +22,16 @@ static int timer_cb(void *map, int *key, struct bpf_timer *timer)
 	return buf[69];
 }
 
+__attribute__((noinline))
+static int bad_timer_cb(void *map, int *key, struct bpf_timer *timer)
+{
+	volatile char buf[300] = {};
+	return buf[255] + timer_cb(NULL, NULL, NULL);
+}
+
 SEC("tc")
-__failure __msg("combined stack size of 2 calls")
-int prog(struct __sk_buff *ctx)
+__failure __msg("combined stack size of 2 calls is 576. Too large")
+int pseudo_call_check(struct __sk_buff *ctx)
 {
 	struct hmap_elem *elem;
 	volatile char buf[256] = {};
@@ -37,4 +44,18 @@ int prog(struct __sk_buff *ctx)
 	return bpf_timer_set_callback(&elem->timer, timer_cb) + buf[0];
 }
 
+SEC("tc")
+__failure __msg("combined stack size of 2 calls is 608. Too large")
+int async_call_root_check(struct __sk_buff *ctx)
+{
+	struct hmap_elem *elem;
+	volatile char buf[256] = {};
+
+	elem = bpf_map_lookup_elem(&hmap, &(int){0});
+	if (!elem)
+		return 0;
+
+	return bpf_timer_set_callback(&elem->timer, bad_timer_cb) + buf[0];
+}
+
 char _license[] SEC("license") = "GPL";