0001-execve-patch-series.patch

From 436f5d97ba3c0ebdfbd233f31751ca2ad5b6feba Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=90=D0=BB=D0=B5=D0=BA=D1=81=D0=B0=D0=BD=D0=B4=D1=80?=
 =?UTF-8?q?=D0=BE=D0=B2=20=D0=9E=D0=BB=D0=B5=D0=B3?=
 <[email protected]>
Date: Tue, 12 Jul 2016 11:34:12 +0500
Subject: [PATCH] execve patch series

---
 linux-user/main.c    |  36 +++++++++++
 linux-user/qemu.h    |   1 +
 linux-user/syscall.c | 168 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 204 insertions(+), 1 deletion(-)

diff --git a/linux-user/main.c b/linux-user/main.c
index 617a179..ac6e017 100644
--- a/linux-user/main.c
+++ b/linux-user/main.c
@@ -20,6 +20,7 @@
 #include "qemu-version.h"
 #include <sys/syscall.h>
 #include <sys/resource.h>
+#include <sys/auxv.h>
 
 #include "qapi/error.h"
 #include "qemu.h"
@@ -79,6 +80,7 @@ static void usage(int exitcode);
 
 static const char *interp_prefix = CONFIG_QEMU_INTERP_PREFIX;
 const char *qemu_uname_release;
+const char *qemu_execve_path;
 
 /* XXX: on x86 MAP_GROWSDOWN only works if ESP <= address + 32, so
    we allocate a bigger stack. Need a better solution, for example
@@ -3948,6 +3950,38 @@ static void handle_arg_guest_base(const char *arg)
     have_guest_base = 1;
 }
 
+static void handle_arg_execve(const char *arg)
+{
+    const char *execfn;
+    char buf[PATH_MAX];
+    char *ret;
+    int len;
+
+    /* try getauxval() */
+    execfn = (const char *) getauxval(AT_EXECFN);
+
+    if (execfn != 0) {
+        ret = realpath(execfn, buf);
+
+        if (ret != NULL) {
+            qemu_execve_path = strdup(buf);
+            return;
+        }
+    }
+
+    /* try /proc/self/exe */
+    len = readlink("/proc/self/exe", buf, sizeof(buf) - 1);
+
+    if (len != -1) {
+        buf[len] = '\0';
+        qemu_execve_path = strdup(buf);
+        return;
+    }
+
+    fprintf(stderr, "qemu_execve: unable to determine intepreter's path\n");
+    exit(EXIT_FAILURE);
+}
+
 static void handle_arg_reserved_va(const char *arg)
 {
     char *p;
@@ -4033,6 +4067,8 @@ static const struct qemu_argument arg_table[] = {
      "uname",      "set qemu uname release string to 'uname'"},
     {"B",          "QEMU_GUEST_BASE",  true,  handle_arg_guest_base,
      "address",    "set guest_base address to 'address'"},
+    {"execve",     "QEMU_EXECVE",      false, handle_arg_execve,
+     "",           "use this interpreter when a process calls execve()"},
     {"R",          "QEMU_RESERVED_VA", true,  handle_arg_reserved_va,
      "size",       "reserve 'size' bytes for guest virtual address space"},
     {"d",          "QEMU_LOG",         true,  handle_arg_log,
diff --git a/linux-user/qemu.h b/linux-user/qemu.h
index cdf23a7..56c875d 100644
--- a/linux-user/qemu.h
+++ b/linux-user/qemu.h
@@ -154,6 +154,7 @@ void init_task_state(TaskState *ts);
 void task_settid(TaskState *);
 void stop_all_tasks(void);
 extern const char *qemu_uname_release;
+extern const char *qemu_execve_path;
 extern unsigned long mmap_min_addr;
 
 /* ??? See if we can avoid exposing so much of the loader internals.  */
diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index 8bf6205..28334c9 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -100,6 +100,7 @@ int __clone2(int (*fn)(void *), void *child_stack_base,
 #include <linux/route.h>
 #include <linux/filter.h>
 #include <linux/blkpg.h>
+#include <linux/binfmts.h>
 #include <linux/netlink.h>
 #ifdef CONFIG_RTNETLINK
 #include <linux/rtnetlink.h>
@@ -6772,6 +6773,169 @@ static target_timer_t get_timer_id(abi_long arg)
     return timerid;
 }
 
+/* qemu_execve() Must return target values and target errnos. */
+static abi_long qemu_execve(char *filename, char *argv[],
+                  char *envp[])
+{
+    char *i_arg = NULL, *i_name = NULL;
+    char **qemu_argp, **argp;
+    int i, j;
+    size_t qemu_argc = 5, argc, host_envc, envpc;
+    int fd, ret;
+    char *cp;
+    size_t def_envc = 0, undef_envc = 0;
+    char **def_env, **undef_env;
+    char buf[BINPRM_BUF_SIZE];
+
+    /* normal execve case */
+    if (qemu_execve_path == NULL || *qemu_execve_path == 0) {
+        return get_errno(execve(filename, argv, envp));
+    }
+
+    /* count the number of arguments and environment variables */
+    for (argc = 0; argv[argc]; argc++);
+    for (host_envc = 0; environ[host_envc]; host_envc++);
+    for (envpc = 0; envp[envpc]; envpc++);
+
+    /* read the file header so we can check the shebang */
+    fd = open(filename, O_RDONLY);
+    if (fd == -1) {
+        return get_errno(fd);
+    }
+
+    ret = read(fd, buf, BINPRM_BUF_SIZE);
+    if (ret == -1) {
+        close(fd);
+        return get_errno(ret);
+    }
+
+    /* if we have less than 2 bytes, we can guess it is not executable */
+    if (ret < 2) {
+        close(fd);
+        return -host_to_target_errno(ENOEXEC);
+    }
+
+    close(fd);
+
+    /* adapted from the kernel
+     * https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/tree/fs/binfmt_script.c
+     */
+    if ((buf[0] == '#') && (buf[1] == '!')) {
+        /*
+         * This section does the #! interpretation.
+         * Sorta complicated, but hopefully it will work.  -TYT
+         */
+
+        buf[BINPRM_BUF_SIZE - 1] = '\0';
+        cp = strchr(buf, '\n');
+        if (cp == NULL) {
+            cp = buf + BINPRM_BUF_SIZE - 1;
+        }
+        *cp = '\0';
+        while (cp > buf) {
+            cp--;
+            if ((*cp == ' ') || (*cp == '\t')) {
+                *cp = '\0';
+            } else {
+                break;
+            }
+        }
+        for (cp = buf + 2; (*cp == ' ') || (*cp == '\t'); cp++) {
+            /* nothing */ ;
+        }
+        if (*cp == '\0') {
+            return -ENOEXEC; /* No interpreter name found */
+        }
+        i_name = cp;
+        i_arg = NULL;
+        for ( ; *cp && (*cp != ' ') && (*cp != '\t'); cp++) {
+            /* nothing */ ;
+        }
+        while ((*cp == ' ') || (*cp == '\t')) {
+            *cp++ = '\0';
+        }
+        if (*cp) {
+            i_arg = cp;
+        }
+
+        if (i_arg)
+            qemu_argc += 2;
+        else
+            qemu_argc += 1;
+    }
+
+    /* list environment variables to define */
+    def_env = alloca((envpc + 1) * sizeof(envp[0]));
+    for (i = 0; i != envpc; i++) {
+        for (j = 0; j != host_envc; j++)
+            if (!strcmp(envp[i], environ[j]))
+                break;
+        if (j == host_envc)
+            def_env[def_envc++] = envp[i];
+    }
+
+    argc += def_envc * 2;
+
+    /* list environment variables to undefine */
+    undef_env = alloca((host_envc + 1) * sizeof(envp[0]));
+    for (i = 0; i != host_envc; i++) {
+        const char *const host_env = environ[i];
+       const size_t key_len = strchr(host_env, '=') - host_env;
+        for (j = 0; j != envpc; j++)
+            if (!strncmp(host_env, envp[j], key_len))
+                break;
+        if (j == envpc)
+            undef_env[undef_envc++] = strndup(environ[i], key_len);
+    }
+
+    argc += undef_envc * 2;
+
+    /* allocate the argument list */
+    if (do_strace)
+        qemu_argc++;
+    argp = qemu_argp = alloca((qemu_argc + 1) * sizeof(void *));
+
+    /* set up the qemu arguments */
+    *argp++ = strdup(qemu_execve_path);
+    *argp++ = strdup("-L");
+    *argp++ = strdup(path("/"));
+    
+    if (do_strace)
+        *argp++ = strdup("-strace");
+
+    /* add arguments for the enironment variables */
+    for (i = 0; i < def_envc; i++) {
+        *argp++ = strdup("-E");
+        *argp++ = def_env[i];
+    }
+
+    for (i = 0; i < undef_envc; i++) {
+        *argp++ = strdup("-U");
+        *argp++ = undef_env[i];
+    }
+
+    /* add the path to the executable */
+    *argp++ = strdup("-0");
+    if (i_name) {
+        *argp++ = i_name;
+        *argp++ = i_name;
+        if (i_arg)
+            *argp++ = i_arg;
+    } else {
+        *argp++ = argv[0];
+    }
+
+    *argp++ = filename;
+
+    /* copy the original arguments with offset */
+    for (i = 1; i < argc; i++)
+        *argp++ = argv[i];
+
+    *argp++ = NULL;
+
+    return get_errno(execv(qemu_execve_path, qemu_argp));
+}
+
 /* do_syscall() should always have a single exit point at the end so
    that actions, such as logging of syscall results, can be performed.
    All errnos that do_syscall() returns must be -TARGET_<errcode>. */
@@ -7061,7 +7225,9 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
              * before the execve completes and makes it the other
              * program's problem.
              */
-            ret = get_errno(safe_execve(p, argp, envp));
+            //ret = get_errno(safe_execve(p, argp, envp));+
+            ret = qemu_execve(p, argp, envp);
+
             unlock_user(p, arg1, 0);
 
             goto execve_end;
-- 
2.7.4