[PATCH v2] seccomp: passthrough uretprobe systemcall without filtering

[Eyal Birger <eyal.birger@gmail.com>]

When attaching uretprobes to processes running inside docker, the attached
process is segfaulted when encountering the retprobe.

The reason is that now that uretprobe is a system call the default seccomp
filters in docker block it as they only allow a specific set of known
syscalls. This is true for other userspace applications which use seccomp
to control their syscall surface.

Since uretprobe is a "kernel implementation detail" system call which is
not used by userspace application code directly, it is impractical and
there's very little point in forcing all userspace applications to
explicitly allow it in order to avoid crashing tracked processes.

Pass this systemcall through seccomp without depending on configuration.

Note: uretprobe isn't supported in i386 and __NR_ia32_rt_tgsigqueueinfo
uses the same number as __NR_uretprobe so the syscall isn't forced in the
compat bitmap.

Fixes: ff474a78cef5 ("uprobe: Add uretprobe syscall to speed up return probe")
Reported-by: Rafael Buchbinder <rafi@rbk.io>
Link: https://lore.kernel.org/lkml/CAHsH6Gs3Eh8DFU0wq58c_LF8A4_+o6z456J7BidmcVY2AqOnHQ@mail.gmail.com/
Link: https://lore.kernel.org/lkml/20250121182939.33d05470@gandalf.local.home/T/#me2676c378eff2d6a33f3054fed4a5f3afa64e65b
Cc: stable@vger.kernel.org
Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
---
v2: use action_cache bitmap and mode1 array to check the syscall

The following reproduction script synthetically demonstrates the problem
for seccomp filters:

cat > /tmp/x.c << EOF

char *syscalls[] = {
	"write",
	"exit_group",
	"fstat",
};

__attribute__((noinline)) int probed(void)
{
	printf("Probed\n");
	return 1;
}

void apply_seccomp_filter(char **syscalls, int num_syscalls)
{
	scmp_filter_ctx ctx;

	ctx = seccomp_init(SCMP_ACT_KILL);
	for (int i = 0; i < num_syscalls; i++) {
		seccomp_rule_add(ctx, SCMP_ACT_ALLOW,
				 seccomp_syscall_resolve_name(syscalls[i]), 0);
	}
	seccomp_load(ctx);
	seccomp_release(ctx);
}

int main(int argc, char *argv[])
{
	int num_syscalls = sizeof(syscalls) / sizeof(syscalls[0]);

	apply_seccomp_filter(syscalls, num_syscalls);

	probed();

	return 0;
}
EOF

cat > /tmp/trace.bt << EOF
uretprobe:/tmp/x:probed
{
    printf("ret=%d\n", retval);
}
EOF

gcc -o /tmp/x /tmp/x.c -lseccomp

/usr/bin/bpftrace /tmp/trace.bt &

sleep 5 # wait for uretprobe attach
/tmp/x

pkill bpftrace

rm /tmp/x /tmp/x.c /tmp/trace.bt
---
 kernel/seccomp.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 385d48293a5f..23b594a68bc0 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -734,13 +734,13 @@ seccomp_prepare_user_filter(const char __user *user_filter)
 
 #ifdef SECCOMP_ARCH_NATIVE
 /**
- * seccomp_is_const_allow - check if filter is constant allow with given data
+ * seccomp_is_filter_const_allow - check if filter is constant allow with given data
  * @fprog: The BPF programs
  * @sd: The seccomp data to check against, only syscall number and arch
  *      number are considered constant.
  */
-static bool seccomp_is_const_allow(struct sock_fprog_kern *fprog,
-				   struct seccomp_data *sd)
+static bool seccomp_is_filter_const_allow(struct sock_fprog_kern *fprog,
+					  struct seccomp_data *sd)
 {
 	unsigned int reg_value = 0;
 	unsigned int pc;
@@ -812,6 +812,21 @@ static bool seccomp_is_const_allow(struct sock_fprog_kern *fprog,
 	return false;
 }
 
+static bool seccomp_is_const_allow(struct sock_fprog_kern *fprog,
+				   struct seccomp_data *sd)
+{
+#ifdef __NR_uretprobe
+	if (sd->nr == __NR_uretprobe
+#ifdef SECCOMP_ARCH_COMPAT
+	    && sd->arch != SECCOMP_ARCH_COMPAT
+#endif
+	   )
+		return true;
+#endif
+
+	return seccomp_is_filter_const_allow(fprog, sd);
+}
+
 static void seccomp_cache_prepare_bitmap(struct seccomp_filter *sfilter,
 					 void *bitmap, const void *bitmap_prev,
 					 size_t bitmap_size, int arch)
@@ -1023,6 +1038,9 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action,
  */
 static const int mode1_syscalls[] = {
 	__NR_seccomp_read, __NR_seccomp_write, __NR_seccomp_exit, __NR_seccomp_sigreturn,
+#ifdef __NR_uretprobe
+	__NR_uretprobe,
+#endif
 	-1, /* negative terminated */
 };
 
-- 
2.43.0