Add a hook on syscall using Kprobes under x86 (#260)

For x86 architecture, the system call table cannot be used to invoke
a system call after commit 1e3ad78 since v6.9. This commit has been
backported to long term stable kernels, like v5.15.154+, v6.1.85+,
v6.6.26+ and v6.8.5+[1]. In this case, thanks to Kprobes, a hook can be
used instead on the system call entry to intercept the system call.

[1] https://stackoverflow.com/a/78607015

Co-authored-by: Hao Dong <hao.dong.work@outlook.com>

examples/syscall-steal.c

@@ -43,6 +43,14 @@
 
 #if defined(CONFIG_KPROBES)
 #define HAVE_KPROBES 1
+#if defined(CONFIG_X86_64)
+/* If you have tried to use the syscall table to intercept syscalls and it 
+ * doesn't work, you can try to use Kprobes to intercept syscalls.
+ * Set USE_KPROBES_PRE_HANDLER_BEFORE_SYSCALL to 1 to register a pre-handler
+ * before the syscall.
+ */
+#define USE_KPROBES_PRE_HANDLER_BEFORE_SYSCALL 0
+#endif
 #include <linux/kprobes.h>
 #else
 #define HAVE_PARAM 1
@@ -58,12 +66,37 @@ module_param(sym, ulong, 0644);
 
 #endif /* Version < v5.7 */
 
-static unsigned long **sys_call_table_stolen;
-
 /* UID we want to spy on - will be filled from the command line. */
 static uid_t uid = -1;
 module_param(uid, int, 0644);
 
+#if USE_KPROBES_PRE_HANDLER_BEFORE_SYSCALL
+
+/* syscall_sym is the symbol name of the syscall to spy on. The default is
+ * "__x64_sys_openat", which can be changed by the module parameter. You can 
+ * look up the symbol name of a syscall in /proc/kallsyms.
+ */
+static char *syscall_sym = "__x64_sys_openat";
+module_param(syscall_sym, charp, 0644);
+
+static int sys_call_kprobe_pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+    if (__kuid_val(current_uid()) != uid) {
+        return 0;
+    }
+
+    pr_info("%s called by %d\n", syscall_sym, uid);
+    return 0;
+}
+
+static struct kprobe syscall_kprobe = {
+    .symbol_name = "__x64_sys_openat",
+    .pre_handler = sys_call_kprobe_pre_handler,
+};
+#else
+
+static unsigned long **sys_call_table_stolen;
+
 /* A pointer to the original system call. The reason we keep this, rather
  * than call the original function (sys_openat), is because somebody else
  * might have replaced the system call before us. Note that this is not
@@ -202,9 +235,23 @@ static void disable_write_protection(void)
     clear_bit(16, &cr0);
     __write_cr0(cr0);
 }
+#endif
 
 static int __init syscall_steal_start(void)
 {
+#if USE_KPROBES_PRE_HANDLER_BEFORE_SYSCALL
+
+    int err;
+    /* use symbol name from the module parameter */
+    syscall_kprobe.symbol_name = syscall_sym;
+    err = register_kprobe(&syscall_kprobe);
+    if (err) {
+        pr_err("register_kprobe() on %s failed: %d\n", syscall_sym, err);
+        pr_err("Please check the symbol name from 'syscall_sym' parameter.\n");
+        return err;
+    }
+
+#else
     if (!(sys_call_table_stolen = acquire_sys_call_table()))
         return -1;
 
@@ -218,13 +265,17 @@ static int __init syscall_steal_start(void)
 
     enable_write_protection();
 
-    pr_info("Spying on UID:%d\n", uid);
+#endif
 
+    pr_info("Spying on UID:%d\n", uid);
     return 0;
 }
 
 static void __exit syscall_steal_end(void)
 {
+#if USE_KPROBES_PRE_HANDLER_BEFORE_SYSCALL
+    unregister_kprobe(&syscall_kprobe);
+#else
     if (!sys_call_table_stolen)
         return;
 
@@ -239,6 +290,7 @@ static void __exit syscall_steal_end(void)
     disable_write_protection();
     sys_call_table_stolen[__NR_openat] = (unsigned long *)original_call;
     enable_write_protection();
+#endif
 
     msleep(2000);
 }

lkmpg.tex

@@ -1566,6 +1566,11 @@ At first glance, it appears we could solve this particular problem by checking i
 When A is removed, it sees that the system call was changed to \cpp|B_openat| so that it is no longer pointing to \cpp|A_openat|, so it will not restore it to \cpp|sys_openat| before it is removed from memory.
 Unfortunately, \cpp|B_openat| will still try to call \cpp|A_openat| which is no longer there, so that even without removing B the system would crash.
 
+For x86 architecture, the system call table cannot be used to invoke a system call after commit 
+\href{https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=1e3ad78334a69b36e107232e337f9d693dcc9df2}{1e3ad78} since v6.9. 
+This commit has been backported to long term stable kernels, like v5.15.154+, v6.1.85+, v6.6.26+ and v6.8.5+, see this \href{https://stackoverflow.com/a/78607015}{answer} for more details.
+In this case, thanks to Kprobes, a hook can be used instead on the system call entry to intercept the system call.
+
 Note that all the related problems make syscall stealing unfeasible for production use.
 In order to keep people from doing potential harmful things \cpp|sys_call_table| is no longer exported.
 This means, if you want to do something more than a mere dry run of this example, you will have to patch your current kernel in order to have \cpp|sys_call_table| exported.