As syscall translation done by zpoline assumes that there are no direct
syscalls issued by userspace code, but there would be possibly issued by
1) dlopen-ed code containing syscall instructions, or 2) JIT-generated
code.  This commit add a seccomp filter to prevent such syscalls from
userspace code.

Signed-off-by: Hajime Tazaki <thehaj...@gmail.com>
---
 arch/um/include/shared/os.h |  3 ++
 arch/um/kernel/um_arch.c    |  4 ++
 arch/um/os-Linux/process.c  | 76 +++++++++++++++++++++++++++++++++++++
 3 files changed, 83 insertions(+)

diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index 6874be0c38a8..5a6722f254d5 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -220,6 +220,9 @@ extern int os_unmap_memory(void *addr, int len);
 extern int os_drop_memory(void *addr, int length);
 extern int can_drop_memory(void);
 extern int os_mincore(void *addr, unsigned long len);
+#ifndef CONFIG_MMU
+extern int os_setup_seccomp(void);
+#endif
 
 void os_set_pdeathsig(void);
 
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index ec17576ce9fc..694e428ddf35 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -433,6 +433,10 @@ void __init setup_arch(char **cmdline_p)
                add_bootloader_randomness(rng_seed, sizeof(rng_seed));
                memzero_explicit(rng_seed, sizeof(rng_seed));
        }
+
+#ifndef CONFIG_MMU
+       os_setup_seccomp();
+#endif
 }
 
 void __init arch_cpu_finalize_init(void)
diff --git a/arch/um/os-Linux/process.c b/arch/um/os-Linux/process.c
index ef1a2f0aa06a..ed3d99301dc8 100644
--- a/arch/um/os-Linux/process.c
+++ b/arch/um/os-Linux/process.c
@@ -17,7 +17,11 @@
 #include <asm/unistd.h>
 #include <init.h>
 #include <longjmp.h>
+#include <as-layout.h>
 #include <os.h>
+#include <sys/prctl.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
 
 void os_alarm_process(int pid)
 {
@@ -209,3 +213,75 @@ void os_set_pdeathsig(void)
 {
        prctl(PR_SET_PDEATHSIG, SIGKILL);
 }
+
+#ifndef CONFIG_MMU
+int os_setup_seccomp(void)
+{
+       int err;
+       unsigned long __userspace_start = uml_reserved,
+               __userspace_end = high_physmem;
+
+       struct sock_filter filter[] = {
+               /* if (IP_high > __userspace_end) allow; */
+               BPF_STMT(BPF_LD + BPF_W + BPF_ABS,
+                        offsetof(struct seccomp_data, instruction_pointer) + 
4),
+               BPF_JUMP(BPF_JMP + BPF_JGT + BPF_K, __userspace_end >> 32,
+                        /*true-skip=*/0, /*false-skip=*/1),
+               BPF_STMT(BPF_RET + BPF_K, SECCOMP_RET_ALLOW),
+
+               /* if (IP_high == __userspace_end && IP_low >= __userspace_end) 
allow; */
+               BPF_STMT(BPF_LD + BPF_W + BPF_ABS,
+                        offsetof(struct seccomp_data, instruction_pointer) + 
4),
+               BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, __userspace_end >> 32,
+                        /*true-skip=*/0, /*false-skip=*/3),
+               BPF_STMT(BPF_LD + BPF_W + BPF_ABS,
+                        offsetof(struct seccomp_data, instruction_pointer)),
+               BPF_JUMP(BPF_JMP + BPF_JGE + BPF_K, __userspace_end,
+                        /*true-skip=*/0, /*false-skip=*/1),
+               BPF_STMT(BPF_RET + BPF_K, SECCOMP_RET_ALLOW),
+
+               /* if (IP_high < __userspace_start) allow; */
+               BPF_STMT(BPF_LD + BPF_W + BPF_ABS,
+                        offsetof(struct seccomp_data, instruction_pointer) + 
4),
+               BPF_JUMP(BPF_JMP + BPF_JGE + BPF_K, __userspace_start >> 32,
+                        /*true-skip=*/1, /*false-skip=*/0),
+               BPF_STMT(BPF_RET + BPF_K, SECCOMP_RET_ALLOW),
+
+               /* if (IP_high == __userspace_start && IP_low < 
__userspace_start) allow; */
+               BPF_STMT(BPF_LD + BPF_W + BPF_ABS,
+                        offsetof(struct seccomp_data, instruction_pointer) + 
4),
+               BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, __userspace_start >> 32,
+                        /*true-skip=*/0, /*false-skip=*/3),
+               BPF_STMT(BPF_LD + BPF_W + BPF_ABS,
+                        offsetof(struct seccomp_data, instruction_pointer)),
+               BPF_JUMP(BPF_JMP + BPF_JGE + BPF_K, __userspace_start,
+                        /*true-skip=*/1, /*false-skip=*/0),
+               BPF_STMT(BPF_RET + BPF_K, SECCOMP_RET_ALLOW),
+
+               /* other address; trap  */
+               BPF_STMT(BPF_RET + BPF_K, SECCOMP_RET_TRAP),
+       };
+       struct sock_fprog prog = {
+               .len = ARRAY_SIZE(filter),
+               .filter = filter,
+       };
+
+       err = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+       if (err)
+               os_warn("PR_SET_NO_NEW_PRIVS (err=%d, ernro=%d)\n",
+                      err, errno);
+
+       err = syscall(SYS_seccomp, SECCOMP_SET_MODE_FILTER,
+                     SECCOMP_FILTER_FLAG_TSYNC, &prog);
+       if (err) {
+               os_warn("SECCOMP_SET_MODE_FILTER (err=%d, ernro=%d)\n",
+                      err, errno);
+               exit(-1);
+       }
+
+       os_info("seccomp: filter syscalls in the range: 0x%lx-0x%lx\n",
+               __userspace_start, __userspace_end);
+
+       return 0;
+}
+#endif
-- 
2.43.0


Reply via email to