[PATCH bpf] bpf: Fix prog_array UAF in __uprobe_perf_func()

[Jann Horn <jannh@xxxxxxxxxx>]

Currently, the pointer stored in call->prog_array is loaded in
__uprobe_perf_func(), with no RCU annotation and no RCU protection, so the
loaded pointer can immediately be dangling. Later,
bpf_prog_run_array_uprobe() starts a RCU-trace read-side critical section,
but this is too late. It then uses rcu_dereference_check(), but this use of
rcu_dereference_check() does not actually dereference anything.

It looks like the intention was to pass a pointer to the member
call->prog_array into bpf_prog_run_array_uprobe() and actually dereference
the pointer in there. Fix the issue by actually doing that.

Fixes: 8c7dcb84e3b7 ("bpf: implement sleepable uprobes by chaining gps")
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Jann Horn <jannh@xxxxxxxxxx>
---
To reproduce, patch include/linux/bpf.h like this:
```
@@ -30,6 +30,7 @@
 #include <linux/static_call.h>
 #include <linux/memcontrol.h>
 #include <linux/cfi.h>
+#include <linux/delay.h>

 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -2203,6 +2204,7 @@ bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu,
        struct bpf_trace_run_ctx run_ctx;
        u32 ret = 1;

+       mdelay(10000);
        might_fault();

        rcu_read_lock_trace();
```

Build this userspace program:

```
$ cat dummy.c
#include <stdio.h>
int main(void) {
  printf("hello world\n");
}
$ gcc -o dummy dummy.c
```

Then build this BPF program and load it (change the path to point to
the "dummy" binary you built):

```
$ cat bpf-uprobe-kern.c
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
char _license[] SEC("license") = "GPL";

SEC("uprobe//home/user/bpf-uprobe-uaf/dummy:main")
int BPF_UPROBE(main_uprobe) {
  bpf_printk("main uprobe triggered\n");
  return 0;
}
$ clang -O2 -g -target bpf -c -o bpf-uprobe-kern.o bpf-uprobe-kern.c
$ sudo bpftool prog loadall bpf-uprobe-kern.o uprobe-test autoattach
```

Then run ./dummy in one terminal, and after launching it, run
`sudo umount uprobe-test` in another terminal. Once the 10-second
mdelay() is over, a use-after-free should occur, which may or may
not crash your kernel at the `prog->sleepable` check in
bpf_prog_run_array_uprobe() depending on your luck.
---
 include/linux/bpf.h         | 4 ++--
 kernel/trace/trace_uprobe.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index eaee2a819f4c150a34a7b1075584711609682e4c..00b3c5b197df75a0386233b9885b480b2ce72f5f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2193,7 +2193,7 @@ bpf_prog_run_array(const struct bpf_prog_array *array,
  * rcu-protected dynamically sized maps.
  */
 static __always_inline u32
-bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu,
+bpf_prog_run_array_uprobe(struct bpf_prog_array __rcu **array_rcu,
 			  const void *ctx, bpf_prog_run_fn run_prog)
 {
 	const struct bpf_prog_array_item *item;
@@ -2210,7 +2210,7 @@ bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu,
 
 	run_ctx.is_uprobe = true;
 
-	array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held());
+	array = rcu_dereference_check(*array_rcu, rcu_read_lock_trace_held());
 	if (unlikely(!array))
 		goto out;
 	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index fed382b7881b82ee3c334ea77860cce77581a74d..c4eef1eb5ddb3c65205aa9d64af1c72d62fab87f 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1404,7 +1404,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 	if (bpf_prog_array_valid(call)) {
 		u32 ret;
 
-		ret = bpf_prog_run_array_uprobe(call->prog_array, regs, bpf_prog_run);
+		ret = bpf_prog_run_array_uprobe(&call->prog_array, regs, bpf_prog_run);
 		if (!ret)
 			return;
 	}

---
base-commit: 509df676c2d79c985ec2eaa3e3a3bbe557645861
change-id: 20241206-bpf-fix-uprobe-uaf-53d928bab3d0

-- 
Jann Horn <jannh@xxxxxxxxxx>