| Message ID | 1465932382-28645-2-git-send-email-joel.holdsworth@vcatechnology.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
Le 14/06/2016 à 21:26, Joel Holdsworth a écrit : > From: Petros Angelatos <petrosagg@resin.io> > > 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> > --- > linux-user/main.c | 37 ++++++++++++++ > linux-user/qemu.h | 1 + > linux-user/syscall.c | 137 ++++++++++++++++++++++++++++++++++++++++++++++----- > 3 files changed, 164 insertions(+), 11 deletions(-) > > diff --git a/linux-user/main.c b/linux-user/main.c > index f8a8764..429dc06 100644 > --- a/linux-user/main.c > +++ b/linux-user/main.c > @@ -18,6 +18,8 @@ > */ > #include "qemu/osdep.h" > #include "qemu-version.h" > + > +#include <sys/auxv.h> > #include <sys/mman.h> > #include <sys/syscall.h> > #include <sys/resource.h> > @@ -79,6 +81,7 @@ 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 > @@ -3947,6 +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; > @@ -4032,6 +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 56f29c3..567bcc1 100644 > --- a/linux-user/qemu.h > +++ b/linux-user/qemu.h > @@ -149,6 +149,7 @@ 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 71ccbd9..a478f56 100644 > --- a/linux-user/syscall.c > +++ b/linux-user/syscall.c > @@ -106,6 +106,7 @@ int __clone2(int (*fn)(void *), void *child_stack_base, > #include <linux/rtnetlink.h> > #endif > #include <linux/audit.h> > +#include <linux/binfmts.h> > #include "linux_loop.h" > #include "uname.h" > > @@ -6659,6 +6660,128 @@ 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 **new_argp; > + int argc, fd, ret, i, offset = 3; > + char *cp; > + char buf[BINPRM_BUF_SIZE]; > + > + /* normal execve case */ > + if (qemu_execve_path == NULL || *qemu_execve_path == 0) { > + return get_errno(execve(filename, argv, envp)); You need a safe_execve() here, too. Laurent
On 15/06/16 20:31, Laurent Vivier wrote: > > Le 14/06/2016 à 21:26, Joel Holdsworth a écrit : >> From: Petros Angelatos <petrosagg@resin.io> >> >> 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> >> --- >> linux-user/main.c | 37 ++++++++++++++ >> linux-user/qemu.h | 1 + >> linux-user/syscall.c | 137 ++++++++++++++++++++++++++++++++++++++++++++++----- >> 3 files changed, 164 insertions(+), 11 deletions(-) >> >> diff --git a/linux-user/main.c b/linux-user/main.c >> index f8a8764..429dc06 100644 >> --- a/linux-user/main.c >> +++ b/linux-user/main.c >> @@ -18,6 +18,8 @@ >> */ >> #include "qemu/osdep.h" >> #include "qemu-version.h" >> + >> +#include <sys/auxv.h> >> #include <sys/mman.h> >> #include <sys/syscall.h> >> #include <sys/resource.h> >> @@ -79,6 +81,7 @@ 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 >> @@ -3947,6 +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; >> @@ -4032,6 +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 56f29c3..567bcc1 100644 >> --- a/linux-user/qemu.h >> +++ b/linux-user/qemu.h >> @@ -149,6 +149,7 @@ 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 71ccbd9..a478f56 100644 >> --- a/linux-user/syscall.c >> +++ b/linux-user/syscall.c >> @@ -106,6 +106,7 @@ int __clone2(int (*fn)(void *), void *child_stack_base, >> #include <linux/rtnetlink.h> >> #endif >> #include <linux/audit.h> >> +#include <linux/binfmts.h> >> #include "linux_loop.h" >> #include "uname.h" >> >> @@ -6659,6 +6660,128 @@ 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 **new_argp; >> + int argc, fd, ret, i, offset = 3; >> + char *cp; >> + char buf[BINPRM_BUF_SIZE]; >> + >> + /* normal execve case */ >> + if (qemu_execve_path == NULL || *qemu_execve_path == 0) { >> + return get_errno(execve(filename, argv, envp)); > You need a safe_execve() here, too. > > Laurent Thanks - now fixed on my branch. I will resubmit when the discussion has died down. Joel
diff --git a/linux-user/main.c b/linux-user/main.c index f8a8764..429dc06 100644 --- a/linux-user/main.c +++ b/linux-user/main.c @@ -18,6 +18,8 @@ */ #include "qemu/osdep.h" #include "qemu-version.h" + +#include <sys/auxv.h> #include <sys/mman.h> #include <sys/syscall.h> #include <sys/resource.h> @@ -79,6 +81,7 @@ 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 @@ -3947,6 +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; @@ -4032,6 +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 56f29c3..567bcc1 100644 --- a/linux-user/qemu.h +++ b/linux-user/qemu.h @@ -149,6 +149,7 @@ 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 71ccbd9..a478f56 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -106,6 +106,7 @@ int __clone2(int (*fn)(void *), void *child_stack_base, #include <linux/rtnetlink.h> #endif #include <linux/audit.h> +#include <linux/binfmts.h> #include "linux_loop.h" #include "uname.h" @@ -6659,6 +6660,128 @@ 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 **new_argp; + int argc, fd, ret, i, offset = 3; + char *cp; + char buf[BINPRM_BUF_SIZE]; + + /* normal execve case */ + if (qemu_execve_path == NULL || *qemu_execve_path == 0) { + return get_errno(execve(filename, argv, envp)); + } + + for (argc = 0; argv[argc] != NULL; argc++) { + /* nothing */ ; + } + + 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) { + 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]; + } + + /* Although execve() is not an interruptible syscall it is + * a special case where we must use the safe_syscall wrapper: + * if we allow a signal to happen before we make the host + * syscall then we will 'lose' it, because at the point of + * execve the process leaves QEMU's control. So we use the + * safe syscall wrapper to ensure that we either take the + * signal as a guest signal, or else it does not happen + * before the execve completes and makes it the other + * program's problem. + */ + return get_errno(safe_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>. */ @@ -6937,17 +7060,9 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1, if (!(p = lock_user_string(arg1))) goto execve_efault; - /* Although execve() is not an interruptible syscall it is - * a special case where we must use the safe_syscall wrapper: - * if we allow a signal to happen before we make the host - * syscall then we will 'lose' it, because at the point of - * execve the process leaves QEMU's control. So we use the - * safe syscall wrapper to ensure that we either take the - * signal as a guest signal, or else it does not happen - * before the execve completes and makes it the other - * program's problem. - */ - ret = get_errno(safe_execve(p, argp, envp)); + + ret = qemu_execve(p, argp, envp); + unlock_user(p, arg1, 0); goto execve_end;