2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* a.out loader for x86-64
|
|
|
|
*
|
|
|
|
* Copyright (C) 1991, 1992, 1996 Linus Torvalds
|
|
|
|
* Hacked together by Andi Kleen
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
|
|
|
|
|
|
|
#include <linux/time.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/mman.h>
|
|
|
|
#include <linux/a.out.h>
|
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/signal.h>
|
|
|
|
#include <linux/string.h>
|
|
|
|
#include <linux/fs.h>
|
|
|
|
#include <linux/file.h>
|
|
|
|
#include <linux/stat.h>
|
|
|
|
#include <linux/fcntl.h>
|
|
|
|
#include <linux/ptrace.h>
|
|
|
|
#include <linux/user.h>
|
|
|
|
#include <linux/binfmts.h>
|
|
|
|
#include <linux/personality.h>
|
|
|
|
#include <linux/init.h>
|
2008-01-30 20:32:17 +08:00
|
|
|
#include <linux/jiffies.h>
|
2013-10-06 23:10:08 +08:00
|
|
|
#include <linux/perf_event.h>
|
2017-02-09 01:51:37 +08:00
|
|
|
#include <linux/sched/task_stack.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2016-12-25 03:46:01 +08:00
|
|
|
#include <linux/uaccess.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <asm/pgalloc.h>
|
|
|
|
#include <asm/cacheflush.h>
|
|
|
|
#include <asm/user32.h>
|
|
|
|
#include <asm/ia32.h>
|
|
|
|
|
|
|
|
#undef WARN_OLD
|
|
|
|
|
2012-10-21 10:00:48 +08:00
|
|
|
static int load_aout_binary(struct linux_binprm *);
|
2008-01-30 20:30:07 +08:00
|
|
|
static int load_aout_library(struct file *);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2013-10-06 23:10:08 +08:00
|
|
|
#ifdef CONFIG_COREDUMP
|
|
|
|
static int aout_core_dump(struct coredump_params *);
|
|
|
|
|
|
|
|
static unsigned long get_dr(int n)
|
|
|
|
{
|
|
|
|
struct perf_event *bp = current->thread.ptrace_bps[n];
|
|
|
|
return bp ? bp->hw.info.address : 0;
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* fill in the user structure for a core dump..
|
|
|
|
*/
|
2008-01-30 20:30:07 +08:00
|
|
|
static void dump_thread32(struct pt_regs *regs, struct user32 *dump)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-01-30 20:30:07 +08:00
|
|
|
u32 fs, gs;
|
2013-10-06 23:10:08 +08:00
|
|
|
memset(dump, 0, sizeof(*dump));
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* changed the size calculations - should hopefully work better. lbt */
|
|
|
|
dump->magic = CMAGIC;
|
|
|
|
dump->start_code = 0;
|
2008-01-30 20:30:56 +08:00
|
|
|
dump->start_stack = regs->sp & ~(PAGE_SIZE - 1);
|
2005-04-17 06:20:36 +08:00
|
|
|
dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT;
|
2008-01-30 20:30:07 +08:00
|
|
|
dump->u_dsize = ((unsigned long)
|
|
|
|
(current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT;
|
2005-04-17 06:20:36 +08:00
|
|
|
dump->u_dsize -= dump->u_tsize;
|
2013-10-06 23:10:08 +08:00
|
|
|
dump->u_debugreg[0] = get_dr(0);
|
|
|
|
dump->u_debugreg[1] = get_dr(1);
|
|
|
|
dump->u_debugreg[2] = get_dr(2);
|
|
|
|
dump->u_debugreg[3] = get_dr(3);
|
2008-01-30 20:30:07 +08:00
|
|
|
dump->u_debugreg[6] = current->thread.debugreg6;
|
2013-10-06 23:10:08 +08:00
|
|
|
dump->u_debugreg[7] = current->thread.ptrace_dr7;
|
2008-01-30 20:30:07 +08:00
|
|
|
|
|
|
|
if (dump->start_stack < 0xc0000000) {
|
|
|
|
unsigned long tmp;
|
|
|
|
|
|
|
|
tmp = (unsigned long) (0xc0000000 - dump->start_stack);
|
|
|
|
dump->u_ssize = tmp >> PAGE_SHIFT;
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2013-10-06 23:10:08 +08:00
|
|
|
dump->regs.ebx = regs->bx;
|
|
|
|
dump->regs.ecx = regs->cx;
|
|
|
|
dump->regs.edx = regs->dx;
|
|
|
|
dump->regs.esi = regs->si;
|
|
|
|
dump->regs.edi = regs->di;
|
|
|
|
dump->regs.ebp = regs->bp;
|
|
|
|
dump->regs.eax = regs->ax;
|
2005-04-17 06:20:36 +08:00
|
|
|
dump->regs.ds = current->thread.ds;
|
|
|
|
dump->regs.es = current->thread.es;
|
2008-08-20 04:04:19 +08:00
|
|
|
savesegment(fs, fs);
|
|
|
|
dump->regs.fs = fs;
|
|
|
|
savesegment(gs, gs);
|
|
|
|
dump->regs.gs = gs;
|
2013-10-06 23:10:08 +08:00
|
|
|
dump->regs.orig_eax = regs->orig_ax;
|
|
|
|
dump->regs.eip = regs->ip;
|
2005-04-17 06:20:36 +08:00
|
|
|
dump->regs.cs = regs->cs;
|
2013-10-06 23:10:08 +08:00
|
|
|
dump->regs.eflags = regs->flags;
|
|
|
|
dump->regs.esp = regs->sp;
|
2005-04-17 06:20:36 +08:00
|
|
|
dump->regs.ss = regs->ss;
|
|
|
|
|
|
|
|
#if 1 /* FIXME */
|
|
|
|
dump->u_fpvalid = 0;
|
|
|
|
#else
|
2008-01-30 20:30:07 +08:00
|
|
|
dump->u_fpvalid = dump_fpu(regs, &dump->i387);
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
static struct linux_binfmt aout_format = {
|
|
|
|
.module = THIS_MODULE,
|
|
|
|
.load_binary = load_aout_binary,
|
|
|
|
.load_shlib = load_aout_library,
|
2013-10-06 23:10:08 +08:00
|
|
|
#ifdef CONFIG_COREDUMP
|
2005-04-17 06:20:36 +08:00
|
|
|
.core_dump = aout_core_dump,
|
|
|
|
#endif
|
|
|
|
.min_coredump = PAGE_SIZE
|
|
|
|
};
|
|
|
|
|
2016-05-28 06:57:31 +08:00
|
|
|
static int set_brk(unsigned long start, unsigned long end)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
start = PAGE_ALIGN(start);
|
|
|
|
end = PAGE_ALIGN(end);
|
|
|
|
if (end <= start)
|
2016-05-28 06:57:31 +08:00
|
|
|
return 0;
|
2016-05-24 07:25:36 +08:00
|
|
|
return vm_brk(start, end - start);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2013-10-06 23:10:08 +08:00
|
|
|
#ifdef CONFIG_COREDUMP
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* These are the only things you should do on a core-file: use only these
|
|
|
|
* macros to write out all the necessary info.
|
|
|
|
*/
|
|
|
|
|
2010-10-15 01:57:40 +08:00
|
|
|
#include <linux/coredump.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2013-10-06 23:10:08 +08:00
|
|
|
#define START_DATA(u) (u.u_tsize << PAGE_SHIFT)
|
2008-01-30 20:30:07 +08:00
|
|
|
#define START_STACK(u) (u.start_stack)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Routine writes a core dump image in the current directory.
|
|
|
|
* Currently only a stub-function.
|
|
|
|
*
|
|
|
|
* Note that setuid/setgid files won't make a core-dump if the uid/gid
|
|
|
|
* changed due to the set[u|g]id. It's enforced by the "current->mm->dumpable"
|
|
|
|
* field, which also makes sure the core-dumps won't be recursive if the
|
|
|
|
* dumping of the process results in another error..
|
|
|
|
*/
|
|
|
|
|
2013-10-06 23:10:08 +08:00
|
|
|
static int aout_core_dump(struct coredump_params *cprm)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
mm_segment_t fs;
|
|
|
|
int has_dumped = 0;
|
|
|
|
unsigned long dump_start, dump_size;
|
|
|
|
struct user32 dump;
|
|
|
|
|
|
|
|
fs = get_fs();
|
|
|
|
set_fs(KERNEL_DS);
|
|
|
|
has_dumped = 1;
|
2008-01-30 20:30:07 +08:00
|
|
|
strncpy(dump.u_comm, current->comm, sizeof(current->comm));
|
2008-02-07 16:15:57 +08:00
|
|
|
dump.u_ar0 = offsetof(struct user32, regs);
|
2013-10-06 23:10:08 +08:00
|
|
|
dump.signal = cprm->siginfo->si_signo;
|
|
|
|
dump_thread32(cprm->regs, &dump);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-01-30 20:30:07 +08:00
|
|
|
/*
|
|
|
|
* If the size of the dump file exceeds the rlimit, then see
|
|
|
|
* what would happen if we wrote the stack, but not the data
|
|
|
|
* area.
|
|
|
|
*/
|
2013-10-06 23:10:08 +08:00
|
|
|
if ((dump.u_dsize + dump.u_ssize + 1) * PAGE_SIZE > cprm->limit)
|
2005-04-17 06:20:36 +08:00
|
|
|
dump.u_dsize = 0;
|
|
|
|
|
2008-01-30 20:30:07 +08:00
|
|
|
/* Make sure we have enough room to write the stack and data areas. */
|
2013-10-06 23:10:08 +08:00
|
|
|
if ((dump.u_ssize + 1) * PAGE_SIZE > cprm->limit)
|
2005-04-17 06:20:36 +08:00
|
|
|
dump.u_ssize = 0;
|
|
|
|
|
2008-01-30 20:30:07 +08:00
|
|
|
/* make sure we actually have a data and stack area to dump */
|
2005-04-17 06:20:36 +08:00
|
|
|
set_fs(USER_DS);
|
Remove 'type' argument from access_ok() function
Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument
of the user address range verification function since we got rid of the
old racy i386-only code to walk page tables by hand.
It existed because the original 80386 would not honor the write protect
bit when in kernel mode, so you had to do COW by hand before doing any
user access. But we haven't supported that in a long time, and these
days the 'type' argument is a purely historical artifact.
A discussion about extending 'user_access_begin()' to do the range
checking resulted this patch, because there is no way we're going to
move the old VERIFY_xyz interface to that model. And it's best done at
the end of the merge window when I've done most of my merges, so let's
just get this done once and for all.
This patch was mostly done with a sed-script, with manual fix-ups for
the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form.
There were a couple of notable cases:
- csky still had the old "verify_area()" name as an alias.
- the iter_iov code had magical hardcoded knowledge of the actual
values of VERIFY_{READ,WRITE} (not that they mattered, since nothing
really used it)
- microblaze used the type argument for a debug printout
but other than those oddities this should be a total no-op patch.
I tried to fix up all architectures, did fairly extensive grepping for
access_ok() uses, and the changes are trivial, but I may have missed
something. Any missed conversion should be trivially fixable, though.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 10:57:57 +08:00
|
|
|
if (!access_ok((void *) (unsigned long)START_DATA(dump),
|
2008-01-30 20:30:07 +08:00
|
|
|
dump.u_dsize << PAGE_SHIFT))
|
2005-04-17 06:20:36 +08:00
|
|
|
dump.u_dsize = 0;
|
Remove 'type' argument from access_ok() function
Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument
of the user address range verification function since we got rid of the
old racy i386-only code to walk page tables by hand.
It existed because the original 80386 would not honor the write protect
bit when in kernel mode, so you had to do COW by hand before doing any
user access. But we haven't supported that in a long time, and these
days the 'type' argument is a purely historical artifact.
A discussion about extending 'user_access_begin()' to do the range
checking resulted this patch, because there is no way we're going to
move the old VERIFY_xyz interface to that model. And it's best done at
the end of the merge window when I've done most of my merges, so let's
just get this done once and for all.
This patch was mostly done with a sed-script, with manual fix-ups for
the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form.
There were a couple of notable cases:
- csky still had the old "verify_area()" name as an alias.
- the iter_iov code had magical hardcoded knowledge of the actual
values of VERIFY_{READ,WRITE} (not that they mattered, since nothing
really used it)
- microblaze used the type argument for a debug printout
but other than those oddities this should be a total no-op patch.
I tried to fix up all architectures, did fairly extensive grepping for
access_ok() uses, and the changes are trivial, but I may have missed
something. Any missed conversion should be trivially fixable, though.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 10:57:57 +08:00
|
|
|
if (!access_ok((void *) (unsigned long)START_STACK(dump),
|
2008-01-30 20:30:07 +08:00
|
|
|
dump.u_ssize << PAGE_SHIFT))
|
2005-04-17 06:20:36 +08:00
|
|
|
dump.u_ssize = 0;
|
|
|
|
|
|
|
|
set_fs(KERNEL_DS);
|
2008-01-30 20:30:07 +08:00
|
|
|
/* struct user */
|
2013-10-07 19:22:01 +08:00
|
|
|
if (!dump_emit(cprm, &dump, sizeof(dump)))
|
|
|
|
goto end_coredump;
|
2008-01-30 20:30:07 +08:00
|
|
|
/* Now dump all of the user data. Include malloced stuff as well */
|
2013-10-08 21:26:08 +08:00
|
|
|
if (!dump_skip(cprm, PAGE_SIZE - sizeof(dump)))
|
2013-10-07 19:22:01 +08:00
|
|
|
goto end_coredump;
|
2008-01-30 20:30:07 +08:00
|
|
|
/* now we start writing out the user space info */
|
2005-04-17 06:20:36 +08:00
|
|
|
set_fs(USER_DS);
|
2008-01-30 20:30:07 +08:00
|
|
|
/* Dump the data area */
|
2005-04-17 06:20:36 +08:00
|
|
|
if (dump.u_dsize != 0) {
|
|
|
|
dump_start = START_DATA(dump);
|
|
|
|
dump_size = dump.u_dsize << PAGE_SHIFT;
|
2013-10-07 19:22:01 +08:00
|
|
|
if (!dump_emit(cprm, (void *)dump_start, dump_size))
|
|
|
|
goto end_coredump;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2008-01-30 20:30:07 +08:00
|
|
|
/* Now prepare to dump the stack area */
|
2005-04-17 06:20:36 +08:00
|
|
|
if (dump.u_ssize != 0) {
|
|
|
|
dump_start = START_STACK(dump);
|
|
|
|
dump_size = dump.u_ssize << PAGE_SHIFT;
|
2013-10-07 19:22:01 +08:00
|
|
|
if (!dump_emit(cprm, (void *)dump_start, dump_size))
|
|
|
|
goto end_coredump;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
end_coredump:
|
|
|
|
set_fs(fs);
|
|
|
|
return has_dumped;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* create_aout_tables() parses the env- and arg-strings in new user
|
|
|
|
* memory and creates the pointer tables from them, and puts their
|
|
|
|
* addresses on the "stack", returning the new stack pointer value.
|
|
|
|
*/
|
|
|
|
static u32 __user *create_aout_tables(char __user *p, struct linux_binprm *bprm)
|
|
|
|
{
|
2008-01-30 20:30:07 +08:00
|
|
|
u32 __user *argv, *envp, *sp;
|
|
|
|
int argc = bprm->argc, envc = bprm->envc;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
sp = (u32 __user *) ((-(unsigned long)sizeof(u32)) & (unsigned long) p);
|
|
|
|
sp -= envc+1;
|
|
|
|
envp = sp;
|
|
|
|
sp -= argc+1;
|
|
|
|
argv = sp;
|
2008-01-30 20:30:07 +08:00
|
|
|
put_user((unsigned long) envp, --sp);
|
|
|
|
put_user((unsigned long) argv, --sp);
|
|
|
|
put_user(argc, --sp);
|
2005-04-17 06:20:36 +08:00
|
|
|
current->mm->arg_start = (unsigned long) p;
|
2008-01-30 20:30:07 +08:00
|
|
|
while (argc-- > 0) {
|
2005-04-17 06:20:36 +08:00
|
|
|
char c;
|
2008-01-30 20:30:07 +08:00
|
|
|
|
|
|
|
put_user((u32)(unsigned long)p, argv++);
|
2005-04-17 06:20:36 +08:00
|
|
|
do {
|
2008-01-30 20:30:07 +08:00
|
|
|
get_user(c, p++);
|
2005-04-17 06:20:36 +08:00
|
|
|
} while (c);
|
|
|
|
}
|
2007-01-11 08:52:45 +08:00
|
|
|
put_user(0, argv);
|
2005-04-17 06:20:36 +08:00
|
|
|
current->mm->arg_end = current->mm->env_start = (unsigned long) p;
|
2008-01-30 20:30:07 +08:00
|
|
|
while (envc-- > 0) {
|
2005-04-17 06:20:36 +08:00
|
|
|
char c;
|
2008-01-30 20:30:07 +08:00
|
|
|
|
|
|
|
put_user((u32)(unsigned long)p, envp++);
|
2005-04-17 06:20:36 +08:00
|
|
|
do {
|
2008-01-30 20:30:07 +08:00
|
|
|
get_user(c, p++);
|
2005-04-17 06:20:36 +08:00
|
|
|
} while (c);
|
|
|
|
}
|
2007-01-11 08:52:45 +08:00
|
|
|
put_user(0, envp);
|
2005-04-17 06:20:36 +08:00
|
|
|
current->mm->env_end = (unsigned long) p;
|
|
|
|
return sp;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* These are the functions used to load a.out style executables and shared
|
|
|
|
* libraries. There is no binary dependent code anywhere else.
|
|
|
|
*/
|
2012-10-21 10:00:48 +08:00
|
|
|
static int load_aout_binary(struct linux_binprm *bprm)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-01-30 20:30:07 +08:00
|
|
|
unsigned long error, fd_offset, rlim;
|
2012-10-21 10:00:48 +08:00
|
|
|
struct pt_regs *regs = current_pt_regs();
|
2005-04-17 06:20:36 +08:00
|
|
|
struct exec ex;
|
|
|
|
int retval;
|
|
|
|
|
|
|
|
ex = *((struct exec *) bprm->buf); /* exec-header */
|
|
|
|
if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != OMAGIC &&
|
|
|
|
N_MAGIC(ex) != QMAGIC && N_MAGIC(ex) != NMAGIC) ||
|
|
|
|
N_TRSIZE(ex) || N_DRSIZE(ex) ||
|
2013-01-24 06:07:38 +08:00
|
|
|
i_size_read(file_inode(bprm->file)) <
|
2008-01-30 20:30:07 +08:00
|
|
|
ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
|
2005-04-17 06:20:36 +08:00
|
|
|
return -ENOEXEC;
|
|
|
|
}
|
|
|
|
|
|
|
|
fd_offset = N_TXTOFF(ex);
|
|
|
|
|
|
|
|
/* Check initial limits. This avoids letting people circumvent
|
|
|
|
* size limits imposed on them by creating programs with large
|
|
|
|
* arrays in the data or bss.
|
|
|
|
*/
|
2010-01-28 00:32:22 +08:00
|
|
|
rlim = rlimit(RLIMIT_DATA);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (rlim >= RLIM_INFINITY)
|
|
|
|
rlim = ~0;
|
|
|
|
if (ex.a_data + ex.a_bss > rlim)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
/* Flush all traces of the currently running executable */
|
|
|
|
retval = flush_old_exec(bprm);
|
|
|
|
if (retval)
|
|
|
|
return retval;
|
|
|
|
|
|
|
|
/* OK, This is the point of no return */
|
|
|
|
set_personality(PER_LINUX);
|
2012-05-07 00:20:00 +08:00
|
|
|
set_personality_ia32(false);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
Split 'flush_old_exec' into two functions
'flush_old_exec()' is the point of no return when doing an execve(), and
it is pretty badly misnamed. It doesn't just flush the old executable
environment, it also starts up the new one.
Which is very inconvenient for things like setting up the new
personality, because we want the new personality to affect the starting
of the new environment, but at the same time we do _not_ want the new
personality to take effect if flushing the old one fails.
As a result, the x86-64 '32-bit' personality is actually done using this
insane "I'm going to change the ABI, but I haven't done it yet" bit
(TIF_ABI_PENDING), with SET_PERSONALITY() not actually setting the
personality, but just the "pending" bit, so that "flush_thread()" can do
the actual personality magic.
This patch in no way changes any of that insanity, but it does split the
'flush_old_exec()' function up into a preparatory part that can fail
(still called flush_old_exec()), and a new part that will actually set
up the new exec environment (setup_new_exec()). All callers are changed
to trivially comply with the new world order.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-01-29 14:14:42 +08:00
|
|
|
setup_new_exec(bprm);
|
|
|
|
|
|
|
|
regs->cs = __USER32_CS;
|
|
|
|
regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 =
|
|
|
|
regs->r13 = regs->r14 = regs->r15 = 0;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
current->mm->end_code = ex.a_text +
|
|
|
|
(current->mm->start_code = N_TXTADDR(ex));
|
|
|
|
current->mm->end_data = ex.a_data +
|
|
|
|
(current->mm->start_data = N_DATADDR(ex));
|
|
|
|
current->mm->brk = ex.a_bss +
|
|
|
|
(current->mm->start_brk = N_BSSADDR(ex));
|
|
|
|
|
2012-03-05 14:38:42 +08:00
|
|
|
retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT);
|
2014-05-05 08:11:36 +08:00
|
|
|
if (retval < 0)
|
2012-03-05 14:38:42 +08:00
|
|
|
return retval;
|
|
|
|
|
CRED: Make execve() take advantage of copy-on-write credentials
Make execve() take advantage of copy-on-write credentials, allowing it to set
up the credentials in advance, and then commit the whole lot after the point
of no return.
This patch and the preceding patches have been tested with the LTP SELinux
testsuite.
This patch makes several logical sets of alteration:
(1) execve().
The credential bits from struct linux_binprm are, for the most part,
replaced with a single credentials pointer (bprm->cred). This means that
all the creds can be calculated in advance and then applied at the point
of no return with no possibility of failure.
I would like to replace bprm->cap_effective with:
cap_isclear(bprm->cap_effective)
but this seems impossible due to special behaviour for processes of pid 1
(they always retain their parent's capability masks where normally they'd
be changed - see cap_bprm_set_creds()).
The following sequence of events now happens:
(a) At the start of do_execve, the current task's cred_exec_mutex is
locked to prevent PTRACE_ATTACH from obsoleting the calculation of
creds that we make.
(a) prepare_exec_creds() is then called to make a copy of the current
task's credentials and prepare it. This copy is then assigned to
bprm->cred.
This renders security_bprm_alloc() and security_bprm_free()
unnecessary, and so they've been removed.
(b) The determination of unsafe execution is now performed immediately
after (a) rather than later on in the code. The result is stored in
bprm->unsafe for future reference.
(c) prepare_binprm() is called, possibly multiple times.
(i) This applies the result of set[ug]id binaries to the new creds
attached to bprm->cred. Personality bit clearance is recorded,
but now deferred on the basis that the exec procedure may yet
fail.
(ii) This then calls the new security_bprm_set_creds(). This should
calculate the new LSM and capability credentials into *bprm->cred.
This folds together security_bprm_set() and parts of
security_bprm_apply_creds() (these two have been removed).
Anything that might fail must be done at this point.
(iii) bprm->cred_prepared is set to 1.
bprm->cred_prepared is 0 on the first pass of the security
calculations, and 1 on all subsequent passes. This allows SELinux
in (ii) to base its calculations only on the initial script and
not on the interpreter.
(d) flush_old_exec() is called to commit the task to execution. This
performs the following steps with regard to credentials:
(i) Clear pdeath_signal and set dumpable on certain circumstances that
may not be covered by commit_creds().
(ii) Clear any bits in current->personality that were deferred from
(c.i).
(e) install_exec_creds() [compute_creds() as was] is called to install the
new credentials. This performs the following steps with regard to
credentials:
(i) Calls security_bprm_committing_creds() to apply any security
requirements, such as flushing unauthorised files in SELinux, that
must be done before the credentials are changed.
This is made up of bits of security_bprm_apply_creds() and
security_bprm_post_apply_creds(), both of which have been removed.
This function is not allowed to fail; anything that might fail
must have been done in (c.ii).
(ii) Calls commit_creds() to apply the new credentials in a single
assignment (more or less). Possibly pdeath_signal and dumpable
should be part of struct creds.
(iii) Unlocks the task's cred_replace_mutex, thus allowing
PTRACE_ATTACH to take place.
(iv) Clears The bprm->cred pointer as the credentials it was holding
are now immutable.
(v) Calls security_bprm_committed_creds() to apply any security
alterations that must be done after the creds have been changed.
SELinux uses this to flush signals and signal handlers.
(f) If an error occurs before (d.i), bprm_free() will call abort_creds()
to destroy the proposed new credentials and will then unlock
cred_replace_mutex. No changes to the credentials will have been
made.
(2) LSM interface.
A number of functions have been changed, added or removed:
(*) security_bprm_alloc(), ->bprm_alloc_security()
(*) security_bprm_free(), ->bprm_free_security()
Removed in favour of preparing new credentials and modifying those.
(*) security_bprm_apply_creds(), ->bprm_apply_creds()
(*) security_bprm_post_apply_creds(), ->bprm_post_apply_creds()
Removed; split between security_bprm_set_creds(),
security_bprm_committing_creds() and security_bprm_committed_creds().
(*) security_bprm_set(), ->bprm_set_security()
Removed; folded into security_bprm_set_creds().
(*) security_bprm_set_creds(), ->bprm_set_creds()
New. The new credentials in bprm->creds should be checked and set up
as appropriate. bprm->cred_prepared is 0 on the first call, 1 on the
second and subsequent calls.
(*) security_bprm_committing_creds(), ->bprm_committing_creds()
(*) security_bprm_committed_creds(), ->bprm_committed_creds()
New. Apply the security effects of the new credentials. This
includes closing unauthorised files in SELinux. This function may not
fail. When the former is called, the creds haven't yet been applied
to the process; when the latter is called, they have.
The former may access bprm->cred, the latter may not.
(3) SELinux.
SELinux has a number of changes, in addition to those to support the LSM
interface changes mentioned above:
(a) The bprm_security_struct struct has been removed in favour of using
the credentials-under-construction approach.
(c) flush_unauthorized_files() now takes a cred pointer and passes it on
to inode_has_perm(), file_has_perm() and dentry_open().
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: James Morris <jmorris@namei.org>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: James Morris <jmorris@namei.org>
2008-11-14 07:39:24 +08:00
|
|
|
install_exec_creds(bprm);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
if (N_MAGIC(ex) == OMAGIC) {
|
|
|
|
unsigned long text_addr, map_size;
|
|
|
|
|
|
|
|
text_addr = N_TXTADDR(ex);
|
|
|
|
map_size = ex.a_text+ex.a_data;
|
|
|
|
|
2012-04-21 06:35:40 +08:00
|
|
|
error = vm_brk(text_addr & PAGE_MASK, map_size);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2016-05-28 06:57:31 +08:00
|
|
|
if (error)
|
2005-04-17 06:20:36 +08:00
|
|
|
return error;
|
|
|
|
|
2013-04-14 08:31:37 +08:00
|
|
|
error = read_code(bprm->file, text_addr, 32,
|
|
|
|
ex.a_text + ex.a_data);
|
2014-05-05 08:11:36 +08:00
|
|
|
if ((signed long)error < 0)
|
2005-04-17 06:20:36 +08:00
|
|
|
return error;
|
|
|
|
} else {
|
|
|
|
#ifdef WARN_OLD
|
|
|
|
static unsigned long error_time, error_time2;
|
|
|
|
if ((ex.a_text & 0xfff || ex.a_data & 0xfff) &&
|
2008-01-30 20:32:17 +08:00
|
|
|
(N_MAGIC(ex) != NMAGIC) &&
|
|
|
|
time_after(jiffies, error_time2 + 5*HZ)) {
|
2005-04-17 06:20:36 +08:00
|
|
|
printk(KERN_NOTICE "executable not page aligned\n");
|
|
|
|
error_time2 = jiffies;
|
|
|
|
}
|
|
|
|
|
|
|
|
if ((fd_offset & ~PAGE_MASK) != 0 &&
|
2008-01-30 20:32:17 +08:00
|
|
|
time_after(jiffies, error_time + 5*HZ)) {
|
2008-01-30 20:30:07 +08:00
|
|
|
printk(KERN_WARNING
|
|
|
|
"fd_offset is not page aligned. Please convert "
|
2014-10-22 08:11:25 +08:00
|
|
|
"program: %pD\n",
|
|
|
|
bprm->file);
|
2005-04-17 06:20:36 +08:00
|
|
|
error_time = jiffies;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2008-01-30 20:30:07 +08:00
|
|
|
if (!bprm->file->f_op->mmap || (fd_offset & ~PAGE_MASK) != 0) {
|
2016-05-24 07:25:36 +08:00
|
|
|
error = vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
|
2016-05-28 06:57:31 +08:00
|
|
|
if (error)
|
2016-05-24 07:25:36 +08:00
|
|
|
return error;
|
|
|
|
|
2013-04-14 08:31:37 +08:00
|
|
|
read_code(bprm->file, N_TXTADDR(ex), fd_offset,
|
|
|
|
ex.a_text+ex.a_data);
|
2005-04-17 06:20:36 +08:00
|
|
|
goto beyond_if;
|
|
|
|
}
|
|
|
|
|
2012-04-21 08:13:58 +08:00
|
|
|
error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
|
2008-01-30 20:30:07 +08:00
|
|
|
PROT_READ | PROT_EXEC,
|
|
|
|
MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
|
|
|
|
MAP_EXECUTABLE | MAP_32BIT,
|
|
|
|
fd_offset);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2014-05-05 08:11:36 +08:00
|
|
|
if (error != N_TXTADDR(ex))
|
2005-04-17 06:20:36 +08:00
|
|
|
return error;
|
|
|
|
|
2012-04-21 08:13:58 +08:00
|
|
|
error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
|
2005-04-17 06:20:36 +08:00
|
|
|
PROT_READ | PROT_WRITE | PROT_EXEC,
|
2008-01-30 20:30:07 +08:00
|
|
|
MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
|
|
|
|
MAP_EXECUTABLE | MAP_32BIT,
|
2005-04-17 06:20:36 +08:00
|
|
|
fd_offset + ex.a_text);
|
2014-05-05 08:11:36 +08:00
|
|
|
if (error != N_DATADDR(ex))
|
2005-04-17 06:20:36 +08:00
|
|
|
return error;
|
|
|
|
}
|
2016-05-24 07:25:36 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
beyond_if:
|
2016-05-24 07:25:36 +08:00
|
|
|
error = set_brk(current->mm->start_brk, current->mm->brk);
|
2016-05-28 06:57:31 +08:00
|
|
|
if (error)
|
2016-05-24 07:25:36 +08:00
|
|
|
return error;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2016-05-24 07:25:36 +08:00
|
|
|
set_binfmt(&aout_format);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
current->mm->start_stack =
|
|
|
|
(unsigned long)create_aout_tables((char __user *)bprm->p, bprm);
|
|
|
|
/* start thread */
|
2008-08-20 04:04:19 +08:00
|
|
|
loadsegment(fs, 0);
|
|
|
|
loadsegment(ds, __USER32_DS);
|
|
|
|
loadsegment(es, __USER32_DS);
|
2008-01-30 20:30:07 +08:00
|
|
|
load_gs_index(0);
|
2008-01-30 20:30:56 +08:00
|
|
|
(regs)->ip = ex.a_entry;
|
|
|
|
(regs)->sp = current->mm->start_stack;
|
|
|
|
(regs)->flags = 0x200;
|
2005-04-17 06:20:36 +08:00
|
|
|
(regs)->cs = __USER32_CS;
|
|
|
|
(regs)->ss = __USER32_DS;
|
2007-10-18 00:04:33 +08:00
|
|
|
regs->r8 = regs->r9 = regs->r10 = regs->r11 =
|
|
|
|
regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
set_fs(USER_DS);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int load_aout_library(struct file *file)
|
|
|
|
{
|
2008-01-30 20:30:07 +08:00
|
|
|
unsigned long bss, start_addr, len, error;
|
2005-04-17 06:20:36 +08:00
|
|
|
int retval;
|
|
|
|
struct exec ex;
|
2017-09-01 23:39:13 +08:00
|
|
|
loff_t pos = 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
retval = -ENOEXEC;
|
2017-09-01 23:39:13 +08:00
|
|
|
error = kernel_read(file, &ex, sizeof(ex), &pos);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (error != sizeof(ex))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
/* We come in here for the regular a.out style of shared libraries */
|
|
|
|
if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != QMAGIC) || N_TRSIZE(ex) ||
|
|
|
|
N_DRSIZE(ex) || ((ex.a_entry & 0xfff) && N_MAGIC(ex) == ZMAGIC) ||
|
2013-01-24 06:07:38 +08:00
|
|
|
i_size_read(file_inode(file)) <
|
2008-01-30 20:30:07 +08:00
|
|
|
ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
|
2005-04-17 06:20:36 +08:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (N_FLAGS(ex))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
/* For QMAGIC, the starting address is 0x20 into the page. We mask
|
|
|
|
this off to get the starting address for the page */
|
|
|
|
|
|
|
|
start_addr = ex.a_entry & 0xfffff000;
|
|
|
|
|
|
|
|
if ((N_TXTOFF(ex) & ~PAGE_MASK) != 0) {
|
|
|
|
#ifdef WARN_OLD
|
|
|
|
static unsigned long error_time;
|
2008-01-30 20:32:17 +08:00
|
|
|
if (time_after(jiffies, error_time + 5*HZ)) {
|
2008-01-30 20:30:07 +08:00
|
|
|
printk(KERN_WARNING
|
|
|
|
"N_TXTOFF is not page aligned. Please convert "
|
2014-10-22 08:11:25 +08:00
|
|
|
"library: %pD\n",
|
|
|
|
file);
|
2005-04-17 06:20:36 +08:00
|
|
|
error_time = jiffies;
|
|
|
|
}
|
|
|
|
#endif
|
2016-05-24 07:25:36 +08:00
|
|
|
retval = vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
|
2016-05-28 06:57:31 +08:00
|
|
|
if (retval)
|
2016-05-24 07:25:36 +08:00
|
|
|
goto out;
|
2008-01-30 20:30:07 +08:00
|
|
|
|
2013-04-14 08:31:37 +08:00
|
|
|
read_code(file, start_addr, N_TXTOFF(ex),
|
|
|
|
ex.a_text + ex.a_data);
|
2005-04-17 06:20:36 +08:00
|
|
|
retval = 0;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
/* Now use mmap to map the library into memory. */
|
2012-04-21 08:13:58 +08:00
|
|
|
error = vm_mmap(file, start_addr, ex.a_text + ex.a_data,
|
2005-04-17 06:20:36 +08:00
|
|
|
PROT_READ | PROT_WRITE | PROT_EXEC,
|
|
|
|
MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_32BIT,
|
|
|
|
N_TXTOFF(ex));
|
|
|
|
retval = error;
|
|
|
|
if (error != start_addr)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
len = PAGE_ALIGN(ex.a_text + ex.a_data);
|
|
|
|
bss = ex.a_text + ex.a_data + ex.a_bss;
|
|
|
|
if (bss > len) {
|
2016-05-28 06:57:31 +08:00
|
|
|
retval = vm_brk(start_addr + len, bss - len);
|
|
|
|
if (retval)
|
2005-04-17 06:20:36 +08:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
retval = 0;
|
|
|
|
out:
|
|
|
|
return retval;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int __init init_aout_binfmt(void)
|
|
|
|
{
|
2012-03-17 15:05:16 +08:00
|
|
|
register_binfmt(&aout_format);
|
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static void __exit exit_aout_binfmt(void)
|
|
|
|
{
|
|
|
|
unregister_binfmt(&aout_format);
|
|
|
|
}
|
|
|
|
|
|
|
|
module_init(init_aout_binfmt);
|
|
|
|
module_exit(exit_aout_binfmt);
|
|
|
|
MODULE_LICENSE("GPL");
|