update qemu-user-execve.patch

[packages/qemu.git] / qemu-user-execve.patch

Discussion:
https://resin.io/blog/building-arm-containers-on-any-x86-machine-even-dockerhub/

https://github.com/resin-io/qemu/commit/782e5bb77014ff136f7bb6133a911e5f53e914a7

https://github.com/resin-io/qemu/commit/782e5bb77014ff136f7bb6133a911e5f53e914a7#commitcomment-17193923
It has gone through review[1][2][3] and I'm waiting for the maintainer of the linux-user subsystem to accept it in his tree.

[1] https://patchwork.ozlabs.org/patch/569452/
[2] https://patchwork.ozlabs.org/patch/573877/
[3] https://patchwork.ozlabs.org/patch/582756/

From patchwork Mon Feb 15 05:51:47 2016
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Subject: [v3] linux-user: add option to intercept execve() syscalls
From: Petros Angelatos <petrosagg@resin.io>
X-Patchwork-Id: 582756
Message-Id: <1455515507-26877-1-git-send-email-petrosagg@resin.io>
To: qemu-devel@nongnu.org
Cc: lucas.kaldstrom@hotmail.co.uk, peter.maydell@linaro.org,
 riku.voipio@iki.fi, 
 laurent@vivier.eu, Petros Angelatos <petrosagg@resin.io>
Date: Sun, 14 Feb 2016 21:51:47 -0800

In order for one to use QEMU user mode emulation under a chroot, it is
required to use binfmt_misc. This can be avoided by QEMU never doing a
raw execve() to the host system.

Introduce a new option, -execve, that uses the current QEMU interpreter
to intercept execve().

qemu_execve() will prepend the interpreter path , similar to what
binfmt_misc would do, and then pass the modified execve() to the host.

It is necessary to parse hashbang scripts in that function otherwise
the kernel will try to run the interpreter of a script without QEMU and
get an invalid exec format error.

Signed-off-by: Petros Angelatos <petrosagg@resin.io>
Tested-by: Laurent Vivier <laurent@vivier.eu>
Reviewed-by: Laurent Vivier <laurent@vivier.eu>
---
v3 changes:
	- rebase the patchset against current code

diff --git a/linux-user/main.c b/linux-user/main.c
index ee12035..5951279 100644
--- a/linux-user/main.c
+++ b/linux-user/main.c
@@ -79,6 +79,7 @@ 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
@@ -3828,6 +3829,11 @@ static void handle_arg_guest_base(const char *arg)
     have_guest_base = 1;
 }
 
+static void handle_arg_execve(const char *arg)
+{
+    qemu_execve_path = strdup(arg);
+}
+
 static void handle_arg_reserved_va(const char *arg)
 {
     char *p;
@@ -3913,6 +3919,8 @@ 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",      true,   handle_arg_execve,
+     "path",       "use interpreter at 'path' 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 bd90cc3..0d9b058 100644
--- a/linux-user/qemu.h
+++ b/linux-user/qemu.h
@@ -140,6 +140,7 @@ 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 0cbace4..d0b5442 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -5854,6 +5854,109 @@ static target_timer_t get_timer_id(abi_long arg)
     return timerid;
 }
 
+#define BINPRM_BUF_SIZE 128
+
+/* 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 **new_argp;
+    int argc, fd, ret, i, offset = 3;
+    char *cp;
+    char buf[BINPRM_BUF_SIZE];
+
+    for (argc = 0; argv[argc] != NULL; argc++) {
+        /* nothing */ ;
+    }
+
+    fd = open(filename, O_RDONLY);
+    if (fd == -1) {
+        return -ENOENT;
+    }
+
+    ret = read(fd, buf, BINPRM_BUF_SIZE);
+    if (ret == -1) {
+        close(fd);
+        return -ENOENT;
+    }
+
+    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) {
+            offset = 5;
+        } else {
+            offset = 4;
+        }
+    }
+
+    new_argp = alloca((argc + offset + 1) * sizeof(void *));
+
+    /* Copy the original arguments with offset */
+    for (i = 0; i < argc; i++) {
+        new_argp[i + offset] = argv[i];
+    }
+
+    new_argp[0] = strdup(qemu_execve_path);
+    new_argp[1] = strdup("-0");
+    new_argp[offset] = filename;
+    new_argp[argc + offset] = NULL;
+
+    if (i_name) {
+        new_argp[2] = i_name;
+        new_argp[3] = i_name;
+
+        if (i_arg) {
+            new_argp[4] = i_arg;
+        }
+    } else {
+        new_argp[2] = argv[0];
+    }
+
+    return get_errno(execve(qemu_execve_path, new_argp, envp));
+}
+
 /* 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>. */
@@ -6113,7 +6216,13 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
 
             if (!(p = lock_user_string(arg1)))
                 goto execve_efault;
-            ret = get_errno(execve(p, argp, envp));
+
+            if (qemu_execve_path && *qemu_execve_path) {
+                ret = get_errno(qemu_execve(p, argp, envp));
+            } else {
+                ret = get_errno(execve(p, argp, envp));
+            }
+
             unlock_user(p, arg1, 0);
 
             goto execve_end;