From 1c48104ffc7f8d2c27dd8660a03a7728540fa946 Mon Sep 17 00:00:00 2001
From: Michal Sojka <sojkam1@fel.cvut.cz>
Date: Sun, 24 Sep 2017 16:38:21 +0200
Subject: [PATCH] utrace: Support non-contiguous syscall numbers

ARM architecture does not have its system call numbers contiguous. So
far, utrace ignored the non-contiguous system calls, but it makes it
difficult to setup seccomp whitelists. This patch adds support for
these extra out-of-range syscalls.

It extends the generated file syscall_names.h to include a few
functions. Now, for ARM this file looks like:

    #include <asm/unistd.h>
    static const char *__syscall_names[] = {
     [280] = "waitid",
     [148] = "fdatasync",
    ...
     [252] = "epoll_wait",
     [74] = "sethostname",
    };
    static inline const char *syscall_name(unsigned i) {
      if (i < ARRAY_SIZE(__syscall_names))
        return __syscall_names[i];
      switch (i) {
        case 0x0f0001: return "breakpoint";
        case 0x0f0003: return "usr26";
        case 0x0f0004: return "usr32";
        case 0x0f0005: return "set_tls";
        case 0x0f0002: return "cacheflush";
      default: return (void*)0;
      }
    }
    static inline int syscall_index(unsigned i) {
      if (i < ARRAY_SIZE(__syscall_names))
        return i;
      switch (i) {
      case 0x0f0001: return ARRAY_SIZE(__syscall_names) + 0;
      case 0x0f0003: return ARRAY_SIZE(__syscall_names) + 1;
      case 0x0f0004: return ARRAY_SIZE(__syscall_names) + 2;
      case 0x0f0005: return ARRAY_SIZE(__syscall_names) + 3;
      case 0x0f0002: return ARRAY_SIZE(__syscall_names) + 4;
      default: return -1;
      }
    }
    static inline int syscall_index_to_number(unsigned i) {
      if (i < ARRAY_SIZE(__syscall_names))
        return i;
      switch (i) {
      case ARRAY_SIZE(__syscall_names) + 0: return 0x0f0001;
      case ARRAY_SIZE(__syscall_names) + 1: return 0x0f0003;
      case ARRAY_SIZE(__syscall_names) + 2: return 0x0f0004;
      case ARRAY_SIZE(__syscall_names) + 3: return 0x0f0005;
      case ARRAY_SIZE(__syscall_names) + 4: return 0x0f0002;
      default: return -1;
      }
    }
    #define SYSCALL_COUNT (ARRAY_SIZE(__syscall_names) + 5)

For x86, which does not have extra syscalls, the file looks this way:

    #include <asm/unistd.h>
    static const char *__syscall_names[] = {
     [247] = "waitid",
     [75] = "fdatasync",
     ...
     [232] = "epoll_wait",
     [170] = "sethostname",
    };
    static inline const char *syscall_name(unsigned i) {
      if (i < ARRAY_SIZE(__syscall_names))
        return __syscall_names[i];
      switch (i) {
      default: return (void*)0;
      }
    }
    static inline int syscall_index(unsigned i) {
      if (i < ARRAY_SIZE(__syscall_names))
        return i;
      switch (i) {
      default: return -1;
      }
    }
    static inline int syscall_index_to_number(unsigned i) {
      if (i < ARRAY_SIZE(__syscall_names))
        return i;
      switch (i) {
      default: return -1;
      }
    }
    #define SYSCALL_COUNT (ARRAY_SIZE(__syscall_names) + 0)

Signed-off-by: Michal Sojka <sojkam1@fel.cvut.cz>
---
 jail/seccomp.c    | 10 +++++-----
 make_syscall_h.sh | 48 ++++++++++++++++++++++++++++++++++++++++++++++-
 trace/trace.c     | 44 +++++++++++++++++++++----------------------
 3 files changed, 73 insertions(+), 29 deletions(-)

diff --git a/jail/seccomp.c b/jail/seccomp.c
index 27bf3ce..eeb5781 100644
--- a/jail/seccomp.c
+++ b/jail/seccomp.c
@@ -22,15 +22,15 @@
 #include "seccomp.h"
 #include "../syscall-names.h"
 
-static int max_syscall = ARRAY_SIZE(syscall_names);
-
 static int find_syscall(const char *name)
 {
 	int i;
 
-	for (i = 0; i < max_syscall; i++)
-		if (syscall_names[i] && !strcmp(syscall_names[i], name))
-			return i;
+	for (i = 0; i < SYSCALL_COUNT; i++) {
+		int sc = syscall_index_to_number(i);
+		if (syscall_name(sc) && !strcmp(syscall_name(sc), name))
+			return sc;
+	}
 
 	return -1;
 }
diff --git a/make_syscall_h.sh b/make_syscall_h.sh
index 3363bc7..18d9131 100755
--- a/make_syscall_h.sh
+++ b/make_syscall_h.sh
@@ -12,7 +12,53 @@ CC=$1
 [ -n "$TARGET_CC_NOCACHE" ] && CC=$TARGET_CC_NOCACHE
 
 echo "#include <asm/unistd.h>"
-echo "static const char *syscall_names[] = {"
+echo "static const char *__syscall_names[] = {"
 echo "#include <sys/syscall.h>" | ${CC} -E -dM - | grep '^#define __NR_' | \
 	LC_ALL=C sed -r -n -e 's/^\#define[ \t]+__NR_([a-z0-9_]+)[ \t]+([ ()+0-9a-zNR_Linux]+)(.*)/ [\2] = "\1",/p'
 echo "};"
+
+extra_syscalls="$(echo "#include <sys/syscall.h>" | ${CC} -E -dM - | sed -n -e '/^#define __ARM_NR_/ s///p')"
+
+cat <<EOF
+static inline const char *syscall_name(unsigned i) {
+  if (i < ARRAY_SIZE(__syscall_names))
+    return __syscall_names[i];
+  switch (i) {
+EOF
+echo "$extra_syscalls" | \
+    LC_ALL=C sed -r -n -e 's/^([a-z0-9_]+)[ \t]+([ ()+0-9a-zNR_Linux]+)(.*)/    case \2: return "\1";/p'
+cat <<EOF
+  default: return (void*)0;
+  }
+}
+EOF
+
+cat <<EOF
+static inline int syscall_index(unsigned i) {
+  if (i < ARRAY_SIZE(__syscall_names))
+    return i;
+  switch (i) {
+EOF
+echo "$extra_syscalls" | \
+    LC_ALL=C perl -ne 'print "  case $2: return ARRAY_SIZE(__syscall_names) + ", $. - 1, ";\n" if /^([a-z0-9_]+)[ \t]+([ ()+0-9a-zNR_Linux]+)(.*)/;'
+cat <<EOF
+  default: return -1;
+  }
+}
+EOF
+
+cat <<EOF
+static inline int syscall_index_to_number(unsigned i) {
+  if (i < ARRAY_SIZE(__syscall_names))
+    return i;
+  switch (i) {
+EOF
+echo "$extra_syscalls" | \
+    LC_ALL=C perl -ne 'print "  case ARRAY_SIZE(__syscall_names) + ", $. - 1, ": return $2;\n" if /^([a-z0-9_]+)[ \t]+([ ()+0-9a-zNR_Linux]+)(.*)/;'
+cat <<EOF
+  default: return -1;
+  }
+}
+EOF
+
+echo "#define SYSCALL_COUNT (ARRAY_SIZE(__syscall_names) + $({ test -n "$extra_syscalls" && echo "$extra_syscalls"; } | wc -l))"
diff --git a/trace/trace.c b/trace/trace.c
index d878a65..e7b7610 100644
--- a/trace/trace.c
+++ b/trace/trace.c
@@ -87,25 +87,24 @@ struct tracee {
 };
 
 static struct tracee tracer;
-static int *syscall_count;
+static int syscall_count[SYSCALL_COUNT];
 static int violation_count;
 static struct blob_buf b;
-static int syscall_max;
 static int debug;
 char *json = NULL;
 int ptrace_restart;
 
-static int max_syscall = ARRAY_SIZE(syscall_names);
-
 static void set_syscall(const char *name, int val)
 {
 	int i;
 
-	for (i = 0; i < max_syscall; i++)
-		if (syscall_names[i] && !strcmp(syscall_names[i], name)) {
+	for (i = 0; i < SYSCALL_COUNT; i++) {
+		int sc = syscall_index_to_number(i);
+		if (syscall_name(sc) && !strcmp(syscall_name(sc), name)) {
 			syscall_count[i] = val;
 			return;
 		}
+	}
 }
 
 struct syscall {
@@ -131,27 +130,27 @@ static void print_syscalls(int policy, const char *json)
 		set_syscall("exit", 1);
 	}
 
-	struct syscall sorted[ARRAY_SIZE(syscall_names)];
+	struct syscall sorted[SYSCALL_COUNT];
 
-	for (i = 0; i < ARRAY_SIZE(syscall_names); i++) {
-		sorted[i].syscall = i;
+	for (i = 0; i < SYSCALL_COUNT; i++) {
+		sorted[i].syscall = syscall_index_to_number(i);
 		sorted[i].count = syscall_count[i];
 	}
 
-	qsort(sorted, ARRAY_SIZE(syscall_names), sizeof(sorted[0]), cmp_count);
+	qsort(sorted, SYSCALL_COUNT, sizeof(sorted[0]), cmp_count);
 
 	blob_buf_init(&b, 0);
 	c = blobmsg_open_array(&b, "whitelist");
 
-	for (i = 0; i < ARRAY_SIZE(syscall_names); i++) {
+	for (i = 0; i < SYSCALL_COUNT; i++) {
 		int sc = sorted[i].syscall;
 		if (!sorted[i].count)
 			break;
-		if (syscall_names[sc]) {
+		if (syscall_name(sc)) {
 			if (debug)
 				printf("syscall %d (%s) was called %d times\n",
-					sc, syscall_names[sc], sorted[i].count);
-			blobmsg_add_string(&b, NULL, syscall_names[sc]);
+				       sc, syscall_name(sc), sorted[i].count);
+			blobmsg_add_string(&b, NULL, syscall_name(sc));
 		} else {
 			ERROR("no name found for syscall(%d)\n", sc);
 		}
@@ -188,10 +187,11 @@ static void report_seccomp_vialation(pid_t pid, unsigned syscall)
 
 	if (violation_count < INT_MAX)
 		violation_count++;
-	if (syscall < ARRAY_SIZE(syscall_names)) {
-		syscall_count[syscall]++;
+	int i = syscall_index(syscall);
+	if (i >= 0) {
+		syscall_count[i]++;
 		LOGERR("%s[%u] tried to call non-whitelisted syscall: %s (see %s)\n",
-		       buf, pid,  syscall_names[syscall], json);
+		       buf, pid,  syscall_name(syscall), json);
 	} else {
 		LOGERR("%s[%u] tried to call non-whitelisted syscall: %d (see %s)\n",
 		       buf, pid,  syscall, json);
@@ -210,11 +210,11 @@ static void tracer_cb(struct uloop_process *c, int ret)
 		if (WSTOPSIG(ret) & 0x80) {
 			if (!tracee->in_syscall) {
 				int syscall = ptrace(PTRACE_PEEKUSER, c->pid, reg_syscall_nr);
-
-				if (syscall < syscall_max) {
-					syscall_count[syscall]++;
+				int i = syscall_index(syscall);
+				if (i >= 0) {
+					syscall_count[i]++;
 					if (debug)
-						fprintf(stderr, "%s()\n", syscall_names[syscall]);
+						fprintf(stderr, "%s()\n", syscall_name(syscall));
 				} else if (debug) {
 					fprintf(stderr, "syscal(%d)\n", syscall);
 				}
@@ -351,8 +351,6 @@ int main(int argc, char **argv, char **envp)
 	if (child < 0)
 		return -1;
 
-	syscall_max = ARRAY_SIZE(syscall_names);
-	syscall_count = calloc(syscall_max, sizeof(int));
 	waitpid(child, &status, WUNTRACED);
 	if (!WIFSTOPPED(status)) {
 		ERROR("failed to start %s\n", *argv);
-- 
2.30.2