linux-user: manage binfmt-misc preserve-arg[0] flag

Add --preserve-argv0 in qemu-binfmt-conf.sh to configure the preserve-argv0
flag.

This patch allows to use new flag in AT_FLAGS to detect if
preserve-argv0 is configured for this interpreter:
argv[0] (the full pathname provided by binfmt-misc) is removed and
replaced by argv[1] (the original argv[0] provided by binfmt-misc when
'P'/preserve-arg[0] is set)

For instance with this patch and kernel support for AT_FLAGS:

  $ sudo chroot m68k-chroot sh -c 'echo $0'
  sh

without this patch:

  $ sudo chroot m68k-chroot sh -c 'echo $0'
  /usr/bin/sh

The new flag is available in kernel (v5.12) since:
2347961b11d4 ("binfmt_misc: pass binfmt_misc flags to the interpreter")

This can be tested with something like:

  # cp ..../qemu-ppc /chroot/powerpc/jessie

  # qemu-binfmt-conf.sh --qemu-path / --systemd ppc --credential yes \
                        --persistent no --preserve-argv0 yes
  # systemctl restart systemd-binfmt.service
  # cat /proc/sys/fs/binfmt_misc/qemu-ppc
  enabled
  interpreter //qemu-ppc
  flags: POC
  offset 0
  magic 7f454c4601020100000000000000000000020014
  mask ffffffffffffff00fffffffffffffffffffeffff
  # chroot /chroot/powerpc/jessie  sh -c 'echo $0'
  sh

  # qemu-binfmt-conf.sh --qemu-path / --systemd ppc --credential yes \
                        --persistent no --preserve-argv0 no
  # systemctl restart systemd-binfmt.service
  # cat /proc/sys/fs/binfmt_misc/qemu-ppc
  enabled
  interpreter //qemu-ppc
  flags: OC
  offset 0
  magic 7f454c4601020100000000000000000000020014
  mask ffffffffffffff00fffffffffffffffffffeffff
  # chroot /chroot/powerpc/jessie  sh -c 'echo $0'
  /bin/sh

Signed-off-by: Laurent Vivier <laurent@vivier.eu>
Message-Id: <20210222105004.1642234-1-laurent@vivier.eu>

2 files changed, 51 insertions, 17 deletions

diff --git a/linux-user/main.c b/linux-user/main.c
index 4f4746dce8..f956afccab 100644
--- a/linux-user/main.c
+++ b/linux-user/main.c
@@ -26,6 +26,7 @@
 #include <sys/syscall.h>
 #include <sys/resource.h>
 #include <sys/shm.h>
+#include <linux/binfmts.h>
 
 #include "qapi/error.h"
 #include "qemu.h"
@@ -49,6 +50,11 @@
 #include "cpu_loop-common.h"
 #include "crypto/init.h"
 
+#ifndef AT_FLAGS_PRESERVE_ARGV0
+#define AT_FLAGS_PRESERVE_ARGV0_BIT 0
+#define AT_FLAGS_PRESERVE_ARGV0 (1 << AT_FLAGS_PRESERVE_ARGV0_BIT)
+#endif
+
 char *exec_path;
 
 int singlestep;
@@ -632,6 +638,7 @@ int main(int argc, char **argv, char **envp)
     int execfd;
     int log_mask;
     unsigned long max_reserved_va;
+    bool preserve_argv0;
 
     error_init(argv[0]);
     module_call_init(MODULE_INIT_TRACE);
@@ -688,6 +695,9 @@ int main(int argc, char **argv, char **envp)
 
     init_qemu_uname_release();
 
+    /*
+     * Manage binfmt-misc open-binary flag
+     */
     execfd = qemu_getauxval(AT_EXECFD);
     if (execfd == 0) {
         execfd = open(exec_path, O_RDONLY);
@@ -697,6 +707,20 @@ int main(int argc, char **argv, char **envp)
         }
     }
 
+    /*
+     * get binfmt_misc flags
+     */
+    preserve_argv0 = !!(qemu_getauxval(AT_FLAGS) & AT_FLAGS_PRESERVE_ARGV0);
+
+    /*
+     * Manage binfmt-misc preserve-arg[0] flag
+     *    argv[optind]     full path to the binary
+     *    argv[optind + 1] original argv[0]
+     */
+    if (optind + 1 < argc && preserve_argv0) {
+        optind++;
+    }
+
     if (cpu_model == NULL) {
         cpu_model = cpu_get_model(get_elf_eflags(execfd));
     }
diff --git a/scripts/qemu-binfmt-conf.sh b/scripts/qemu-binfmt-conf.sh
index 7b5d54b887..573b5dc6ac 100755
--- a/scripts/qemu-binfmt-conf.sh
+++ b/scripts/qemu-binfmt-conf.sh
@@ -178,25 +178,27 @@ usage() {
 Usage: qemu-binfmt-conf.sh [--qemu-path PATH][--debian][--systemd CPU]
                            [--help][--credential yes|no][--exportdir PATH]
                            [--persistent yes|no][--qemu-suffix SUFFIX]
+                           [--preserve-argv0 yes|no]
 
        Configure binfmt_misc to use qemu interpreter
 
-       --help:        display this usage
-       --qemu-path:   set path to qemu interpreter ($QEMU_PATH)
-       --qemu-suffix: add a suffix to the default interpreter name
-       --debian:      don't write into /proc,
-                      instead generate update-binfmts templates
-       --systemd:     don't write into /proc,
-                      instead generate file for systemd-binfmt.service
-                      for the given CPU. If CPU is "ALL", generate a
-                      file for all known cpus
-       --exportdir:   define where to write configuration files
-                      (default: $SYSTEMDDIR or $DEBIANDIR)
-       --credential:  if yes, credential and security tokens are
-                      calculated according to the binary to interpret
-       --persistent:  if yes, the interpreter is loaded when binfmt is
-                      configured and remains in memory. All future uses
-                      are cloned from the open file.
+       --help:          display this usage
+       --qemu-path:     set path to qemu interpreter ($QEMU_PATH)
+       --qemu-suffix:   add a suffix to the default interpreter name
+       --debian:        don't write into /proc,
+                        instead generate update-binfmts templates
+       --systemd:       don't write into /proc,
+                        instead generate file for systemd-binfmt.service
+                        for the given CPU. If CPU is "ALL", generate a
+                        file for all known cpus
+       --exportdir:     define where to write configuration files
+                        (default: $SYSTEMDDIR or $DEBIANDIR)
+       --credential:    if yes, credential and security tokens are
+                        calculated according to the binary to interpret
+       --persistent:    if yes, the interpreter is loaded when binfmt is
+                        configured and remains in memory. All future uses
+                        are cloned from the open file.
+       --preserve-argv0 preserve argv[0]
 
     To import templates with update-binfmts, use :
 
@@ -269,6 +271,9 @@ qemu_generate_register() {
     if [ "$PERSISTENT" = "yes" ] ; then
         flags="${flags}F"
     fi
+    if [ "$PRESERVE_ARG0" = "yes" ] ; then
+        flags="${flags}P"
+    fi
 
     echo ":qemu-$cpu:M::$magic:$mask:$qemu:$flags"
 }
@@ -330,9 +335,10 @@ DEBIANDIR="/usr/share/binfmts"
 QEMU_PATH=/usr/local/bin
 CREDENTIAL=no
 PERSISTENT=no
+PRESERVE_ARG0=no
 QEMU_SUFFIX=""
 
-options=$(getopt -o ds:Q:S:e:hc:p: -l debian,systemd:,qemu-path:,qemu-suffix:,exportdir:,help,credential:,persistent: -- "$@")
+options=$(getopt -o ds:Q:S:e:hc:p:g: -l debian,systemd:,qemu-path:,qemu-suffix:,exportdir:,help,credential:,persistent:,preserve-argv0: -- "$@")
 eval set -- "$options"
 
 while true ; do
@@ -388,6 +394,10 @@ while true ; do
         shift
         PERSISTENT="$1"
         ;;
+    -g|--preserve-argv0)
+        shift
+        PRESERVE_ARG0="$1"
+        ;;
     *)
         break
         ;;