linux-user/syscall: Implement execve without execveat

Support for execveat syscall was implemented in 55bbe4 and is available
since QEMU 8.0.0. It relies on host execveat, which is widely available
on most of Linux kernels today.

However, this change breaks qemu-user self emulation, if "host" qemu
version is less than 8.0.0. Indeed, it does not implement yet execveat.
This strange use case happens with most of distribution today having
binfmt support.

With a concrete failing example:
$ qemu-x86_64-7.2 qemu-x86_64-8.0 /bin/bash -c /bin/ls
/bin/bash: line 1: /bin/ls: Function not implemented
-> not implemented means execve returned ENOSYS

qemu-user-static 7.2 and 8.0 can be conveniently grabbed from debian
packages qemu-user-static* [1].

One usage of this is running wine-arm64 from linux-x64 (details [2]).
This is by updating qemu embedded in docker image that we ran into this
issue.

The solution to update host qemu is not always possible. Either it's
complicated or ask you to recompile it, or simply is not accessible
(GitLab CI, GitHub Actions). Thus, it could be worth to implement execve
without relying on execveat, which is the goal of this patch.

This patch was tested with example presented in this commit message.

[1] http://ftp.us.debian.org/debian/pool/main/q/qemu/
[1] https://www.linaro.org/blog/emulate-windows-on-arm/

Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Michael Tokarev <mjt@tls.msk.ru>
Message-Id: <20230705121023.973284-1-pierrick.bouvier@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index 420bab7c68b96f359bf9662610d4409dfcadb07f..c15d9ad743b485dcc272cbc5f5217bec7d64b994 100644 (file)
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -659,6 +659,7 @@ safe_syscall4(pid_t, wait4, pid_t, pid, int *, status, int, options, \
 #endif
 safe_syscall5(int, waitid, idtype_t, idtype, id_t, id, siginfo_t *, infop, \
               int, options, struct rusage *, rusage)
+safe_syscall3(int, execve, const char *, filename, char **, argv, char **, envp)
 safe_syscall5(int, execveat, int, dirfd, const char *, filename,
               char **, argv, char **, envp, int, flags)
 #if defined(TARGET_NR_select) || defined(TARGET_NR__newselect) || \
@@ -8629,9 +8630,9 @@ ssize_t do_guest_readlink(const char *pathname, char *buf, size_t bufsiz)
     return ret;
 }
 
-static int do_execveat(CPUArchState *cpu_env, int dirfd,
-                       abi_long pathname, abi_long guest_argp,
-                       abi_long guest_envp, int flags)
+static int do_execv(CPUArchState *cpu_env, int dirfd,
+                    abi_long pathname, abi_long guest_argp,
+                    abi_long guest_envp, int flags, bool is_execveat)
 {
     int ret;
     char **argp, **envp;
@@ -8710,11 +8711,14 @@ static int do_execveat(CPUArchState *cpu_env, int dirfd,
         goto execve_efault;
     }
 
+    const char *exe = p;
     if (is_proc_myself(p, "exe")) {
-        ret = get_errno(safe_execveat(dirfd, exec_path, argp, envp, flags));
-    } else {
-        ret = get_errno(safe_execveat(dirfd, p, argp, envp, flags));
+        exe = exec_path;
     }
+    ret = is_execveat
+        ? safe_execveat(dirfd, exe, argp, envp, flags)
+        : safe_execve(exe, argp, envp);
+    ret = get_errno(ret);
 
     unlock_user(p, pathname, 0);
 
@@ -9406,9 +9410,9 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1,
         return ret;
 #endif
     case TARGET_NR_execveat:
-        return do_execveat(cpu_env, arg1, arg2, arg3, arg4, arg5);
+        return do_execv(cpu_env, arg1, arg2, arg3, arg4, arg5, true);
     case TARGET_NR_execve:
-        return do_execveat(cpu_env, AT_FDCWD, arg1, arg2, arg3, 0);
+        return do_execv(cpu_env, AT_FDCWD, arg1, arg2, arg3, 0, false);
     case TARGET_NR_chdir:
         if (!(p = lock_user_string(arg1)))
             return -TARGET_EFAULT;