kernel_optimize_test/fs/binfmt_aout.c

559 lines
15 KiB
C
Raw Normal View History

/*
* linux/fs/binfmt_aout.c
*
* Copyright (C) 1991, 1992, 1996 Linus Torvalds
*/
#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/slab.h>
#include <linux/binfmts.h>
#include <linux/personality.h>
#include <linux/init.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/a.out-core.h>
static int load_aout_binary(struct linux_binprm *, struct pt_regs * regs);
static int load_aout_library(struct file*);
core_pattern: ignore RLIMIT_CORE if core_pattern is a pipe For some time /proc/sys/kernel/core_pattern has been able to set its output destination as a pipe, allowing a user space helper to receive and intellegently process a core. This infrastructure however has some shortcommings which can be enhanced. Specifically: 1) The coredump code in the kernel should ignore RLIMIT_CORE limitation when core_pattern is a pipe, since file system resources are not being consumed in this case, unless the user application wishes to save the core, at which point the app is restricted by usual file system limits and restrictions. 2) The core_pattern code should be able to parse and pass options to the user space helper as an argv array. The real core limit of the uid of the crashing proces should also be passable to the user space helper (since it is overridden to zero when called). 3) Some miscellaneous bugs need to be cleaned up (specifically the recognition of a recursive core dump, should the user mode helper itself crash. Also, the core dump code in the kernel should not wait for the user mode helper to exit, since the same context is responsible for writing to the pipe, and a read of the pipe by the user mode helper will result in a deadlock. This patch: Remove the check of RLIMIT_CORE if core_pattern is a pipe. In the event that core_pattern is a pipe, the entire core will be fed to the user mode helper. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Cc: <martin.pitt@ubuntu.com> Cc: <wwoods@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:26:34 +08:00
static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, unsigned long limit);
static struct linux_binfmt aout_format = {
.module = THIS_MODULE,
.load_binary = load_aout_binary,
.load_shlib = load_aout_library,
.core_dump = aout_core_dump,
.min_coredump = PAGE_SIZE
};
#define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE)
static int set_brk(unsigned long start, unsigned long end)
{
start = PAGE_ALIGN(start);
end = PAGE_ALIGN(end);
if (end > start) {
unsigned long addr;
down_write(&current->mm->mmap_sem);
addr = do_brk(start, end - start);
up_write(&current->mm->mmap_sem);
if (BAD_ADDR(addr))
return addr;
}
return 0;
}
/*
* These are the only things you should do on a core-file: use only these
* macros to write out all the necessary info.
*/
static int dump_write(struct file *file, const void *addr, int nr)
{
return file->f_op->write(file, addr, nr, &file->f_pos) == nr;
}
#define DUMP_WRITE(addr, nr) \
if (!dump_write(file, (void *)(addr), (nr))) \
goto end_coredump;
#define DUMP_SEEK(offset) \
if (file->f_op->llseek) { \
if (file->f_op->llseek(file,(offset),0) != (offset)) \
goto end_coredump; \
} else file->f_pos = (offset)
/*
* 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..
*/
core_pattern: ignore RLIMIT_CORE if core_pattern is a pipe For some time /proc/sys/kernel/core_pattern has been able to set its output destination as a pipe, allowing a user space helper to receive and intellegently process a core. This infrastructure however has some shortcommings which can be enhanced. Specifically: 1) The coredump code in the kernel should ignore RLIMIT_CORE limitation when core_pattern is a pipe, since file system resources are not being consumed in this case, unless the user application wishes to save the core, at which point the app is restricted by usual file system limits and restrictions. 2) The core_pattern code should be able to parse and pass options to the user space helper as an argv array. The real core limit of the uid of the crashing proces should also be passable to the user space helper (since it is overridden to zero when called). 3) Some miscellaneous bugs need to be cleaned up (specifically the recognition of a recursive core dump, should the user mode helper itself crash. Also, the core dump code in the kernel should not wait for the user mode helper to exit, since the same context is responsible for writing to the pipe, and a read of the pipe by the user mode helper will result in a deadlock. This patch: Remove the check of RLIMIT_CORE if core_pattern is a pipe. In the event that core_pattern is a pipe, the entire core will be fed to the user mode helper. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Cc: <martin.pitt@ubuntu.com> Cc: <wwoods@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:26:34 +08:00
static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, unsigned long limit)
{
mm_segment_t fs;
int has_dumped = 0;
unsigned long dump_start, dump_size;
struct user dump;
#if defined(__alpha__)
# define START_DATA(u) (u.start_data)
#elif defined(__arm__)
# define START_DATA(u) ((u.u_tsize << PAGE_SHIFT) + u.start_code)
#elif defined(__sparc__)
# define START_DATA(u) (u.u_tsize)
#elif defined(__i386__) || defined(__mc68000__) || defined(__arch_um__)
# define START_DATA(u) (u.u_tsize << PAGE_SHIFT)
#endif
#ifdef __sparc__
# define START_STACK(u) ((regs->u_regs[UREG_FP]) & ~(PAGE_SIZE - 1))
#else
# define START_STACK(u) (u.start_stack)
#endif
fs = get_fs();
set_fs(KERNEL_DS);
has_dumped = 1;
current->flags |= PF_DUMPCORE;
strncpy(dump.u_comm, current->comm, sizeof(dump.u_comm));
#ifndef __sparc__
Sanitize the type of struct user.u_ar0 struct user.u_ar0 is defined to contain a pointer offset on all architectures in which it is defined (all architectures which define an a.out format except SPARC.) However, it has a pointer type in the headers, which is pointless -- <asm/user.h> is not exported to userspace, and it just makes the code messy. Redefine the field as "unsigned long" (which is the same size as a pointer on all Linux architectures) and change the setting code to user offsetof() instead of hand-coded arithmetic. Cc: Linux Arch Mailing List <linux-arch@vger.kernel.org> Cc: Bryan Wu <bryan.wu@analog.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Lennert Buytenhek <kernel@wantstofly.org> Cc: Håvard Skinnemoen <hskinnemoen@atmel.com> Cc: Mikael Starvik <starvik@axis.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Tony Luck <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:15:57 +08:00
dump.u_ar0 = offsetof(struct user, regs);
#endif
dump.signal = signr;
aout_dump_thread(regs, &dump);
/* 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. */
#ifdef __sparc__
core_pattern: ignore RLIMIT_CORE if core_pattern is a pipe For some time /proc/sys/kernel/core_pattern has been able to set its output destination as a pipe, allowing a user space helper to receive and intellegently process a core. This infrastructure however has some shortcommings which can be enhanced. Specifically: 1) The coredump code in the kernel should ignore RLIMIT_CORE limitation when core_pattern is a pipe, since file system resources are not being consumed in this case, unless the user application wishes to save the core, at which point the app is restricted by usual file system limits and restrictions. 2) The core_pattern code should be able to parse and pass options to the user space helper as an argv array. The real core limit of the uid of the crashing proces should also be passable to the user space helper (since it is overridden to zero when called). 3) Some miscellaneous bugs need to be cleaned up (specifically the recognition of a recursive core dump, should the user mode helper itself crash. Also, the core dump code in the kernel should not wait for the user mode helper to exit, since the same context is responsible for writing to the pipe, and a read of the pipe by the user mode helper will result in a deadlock. This patch: Remove the check of RLIMIT_CORE if core_pattern is a pipe. In the event that core_pattern is a pipe, the entire core will be fed to the user mode helper. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Cc: <martin.pitt@ubuntu.com> Cc: <wwoods@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:26:34 +08:00
if ((dump.u_dsize + dump.u_ssize) > limit)
dump.u_dsize = 0;
#else
core_pattern: ignore RLIMIT_CORE if core_pattern is a pipe For some time /proc/sys/kernel/core_pattern has been able to set its output destination as a pipe, allowing a user space helper to receive and intellegently process a core. This infrastructure however has some shortcommings which can be enhanced. Specifically: 1) The coredump code in the kernel should ignore RLIMIT_CORE limitation when core_pattern is a pipe, since file system resources are not being consumed in this case, unless the user application wishes to save the core, at which point the app is restricted by usual file system limits and restrictions. 2) The core_pattern code should be able to parse and pass options to the user space helper as an argv array. The real core limit of the uid of the crashing proces should also be passable to the user space helper (since it is overridden to zero when called). 3) Some miscellaneous bugs need to be cleaned up (specifically the recognition of a recursive core dump, should the user mode helper itself crash. Also, the core dump code in the kernel should not wait for the user mode helper to exit, since the same context is responsible for writing to the pipe, and a read of the pipe by the user mode helper will result in a deadlock. This patch: Remove the check of RLIMIT_CORE if core_pattern is a pipe. In the event that core_pattern is a pipe, the entire core will be fed to the user mode helper. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Cc: <martin.pitt@ubuntu.com> Cc: <wwoods@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:26:34 +08:00
if ((dump.u_dsize + dump.u_ssize+1) * PAGE_SIZE > limit)
dump.u_dsize = 0;
#endif
/* Make sure we have enough room to write the stack and data areas. */
#ifdef __sparc__
core_pattern: ignore RLIMIT_CORE if core_pattern is a pipe For some time /proc/sys/kernel/core_pattern has been able to set its output destination as a pipe, allowing a user space helper to receive and intellegently process a core. This infrastructure however has some shortcommings which can be enhanced. Specifically: 1) The coredump code in the kernel should ignore RLIMIT_CORE limitation when core_pattern is a pipe, since file system resources are not being consumed in this case, unless the user application wishes to save the core, at which point the app is restricted by usual file system limits and restrictions. 2) The core_pattern code should be able to parse and pass options to the user space helper as an argv array. The real core limit of the uid of the crashing proces should also be passable to the user space helper (since it is overridden to zero when called). 3) Some miscellaneous bugs need to be cleaned up (specifically the recognition of a recursive core dump, should the user mode helper itself crash. Also, the core dump code in the kernel should not wait for the user mode helper to exit, since the same context is responsible for writing to the pipe, and a read of the pipe by the user mode helper will result in a deadlock. This patch: Remove the check of RLIMIT_CORE if core_pattern is a pipe. In the event that core_pattern is a pipe, the entire core will be fed to the user mode helper. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Cc: <martin.pitt@ubuntu.com> Cc: <wwoods@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:26:34 +08:00
if (dump.u_ssize > limit)
dump.u_ssize = 0;
#else
core_pattern: ignore RLIMIT_CORE if core_pattern is a pipe For some time /proc/sys/kernel/core_pattern has been able to set its output destination as a pipe, allowing a user space helper to receive and intellegently process a core. This infrastructure however has some shortcommings which can be enhanced. Specifically: 1) The coredump code in the kernel should ignore RLIMIT_CORE limitation when core_pattern is a pipe, since file system resources are not being consumed in this case, unless the user application wishes to save the core, at which point the app is restricted by usual file system limits and restrictions. 2) The core_pattern code should be able to parse and pass options to the user space helper as an argv array. The real core limit of the uid of the crashing proces should also be passable to the user space helper (since it is overridden to zero when called). 3) Some miscellaneous bugs need to be cleaned up (specifically the recognition of a recursive core dump, should the user mode helper itself crash. Also, the core dump code in the kernel should not wait for the user mode helper to exit, since the same context is responsible for writing to the pipe, and a read of the pipe by the user mode helper will result in a deadlock. This patch: Remove the check of RLIMIT_CORE if core_pattern is a pipe. In the event that core_pattern is a pipe, the entire core will be fed to the user mode helper. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Cc: <martin.pitt@ubuntu.com> Cc: <wwoods@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:26:34 +08:00
if ((dump.u_ssize + 1) * PAGE_SIZE > limit)
dump.u_ssize = 0;
#endif
/* make sure we actually have a data and stack area to dump */
set_fs(USER_DS);
#ifdef __sparc__
if (!access_ok(VERIFY_READ, (void __user *)START_DATA(dump), dump.u_dsize))
dump.u_dsize = 0;
if (!access_ok(VERIFY_READ, (void __user *)START_STACK(dump), dump.u_ssize))
dump.u_ssize = 0;
#else
if (!access_ok(VERIFY_READ, (void __user *)START_DATA(dump), dump.u_dsize << PAGE_SHIFT))
dump.u_dsize = 0;
if (!access_ok(VERIFY_READ, (void __user *)START_STACK(dump), dump.u_ssize << PAGE_SHIFT))
dump.u_ssize = 0;
#endif
set_fs(KERNEL_DS);
/* struct user */
DUMP_WRITE(&dump,sizeof(dump));
/* Now dump all of the user data. Include malloced stuff as well */
#ifndef __sparc__
DUMP_SEEK(PAGE_SIZE);
#endif
/* now we start writing out the user space info */
set_fs(USER_DS);
/* Dump the data area */
if (dump.u_dsize != 0) {
dump_start = START_DATA(dump);
#ifdef __sparc__
dump_size = dump.u_dsize;
#else
dump_size = dump.u_dsize << PAGE_SHIFT;
#endif
DUMP_WRITE(dump_start,dump_size);
}
/* Now prepare to dump the stack area */
if (dump.u_ssize != 0) {
dump_start = START_STACK(dump);
#ifdef __sparc__
dump_size = dump.u_ssize;
#else
dump_size = dump.u_ssize << PAGE_SHIFT;
#endif
DUMP_WRITE(dump_start,dump_size);
}
/* Finally dump the task struct. Not be used by gdb, but could be useful */
set_fs(KERNEL_DS);
DUMP_WRITE(current,sizeof(*current));
end_coredump:
set_fs(fs);
return has_dumped;
}
/*
* 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 unsigned long __user *create_aout_tables(char __user *p, struct linux_binprm * bprm)
{
char __user * __user *argv;
char __user * __user *envp;
unsigned long __user *sp;
int argc = bprm->argc;
int envc = bprm->envc;
sp = (void __user *)((-(unsigned long)sizeof(char *)) & (unsigned long) p);
#ifdef __sparc__
/* This imposes the proper stack alignment for a new process. */
sp = (void __user *) (((unsigned long) sp) & ~7);
if ((envc+argc+3)&1) --sp;
#endif
#ifdef __alpha__
/* whee.. test-programs are so much fun. */
put_user(0, --sp);
put_user(0, --sp);
if (bprm->loader) {
put_user(0, --sp);
put_user(0x3eb, --sp);
put_user(bprm->loader, --sp);
put_user(0x3ea, --sp);
}
put_user(bprm->exec, --sp);
put_user(0x3e9, --sp);
#endif
sp -= envc+1;
envp = (char __user * __user *) sp;
sp -= argc+1;
argv = (char __user * __user *) sp;
#if defined(__i386__) || defined(__mc68000__) || defined(__arm__) || defined(__arch_um__)
put_user((unsigned long) envp,--sp);
put_user((unsigned long) argv,--sp);
#endif
put_user(argc,--sp);
current->mm->arg_start = (unsigned long) p;
while (argc-->0) {
char c;
put_user(p,argv++);
do {
get_user(c,p++);
} while (c);
}
put_user(NULL,argv);
current->mm->arg_end = current->mm->env_start = (unsigned long) p;
while (envc-->0) {
char c;
put_user(p,envp++);
do {
get_user(c,p++);
} while (c);
}
put_user(NULL,envp);
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.
*/
static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
{
struct exec ex;
unsigned long error;
unsigned long fd_offset;
unsigned long rlim;
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) ||
i_size_read(bprm->file->f_path.dentry->d_inode) < ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
return -ENOEXEC;
}
/*
* Requires a mmap handler. This prevents people from using a.out
* as part of an exploit attack against /proc-related vulnerabilities.
*/
if (!bprm->file->f_op || !bprm->file->f_op->mmap)
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.
*/
rlim = current->signal->rlim[RLIMIT_DATA].rlim_cur;
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 */
#if defined(__alpha__)
SET_AOUT_PERSONALITY(bprm, ex);
#elif defined(__sparc__)
set_personality(PER_SUNOS);
#if !defined(__sparc_v9__)
memcpy(&current->thread.core_exec, &ex, sizeof(struct exec));
#endif
#else
set_personality(PER_LINUX);
#endif
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));
current->mm->free_area_cache = current->mm->mmap_base;
[PATCH] Avoiding mmap fragmentation Ingo recently introduced a great speedup for allocating new mmaps using the free_area_cache pointer which boosts the specweb SSL benchmark by 4-5% and causes huge performance increases in thread creation. The downside of this patch is that it does lead to fragmentation in the mmap-ed areas (visible via /proc/self/maps), such that some applications that work fine under 2.4 kernels quickly run out of memory on any 2.6 kernel. The problem is twofold: 1) the free_area_cache is used to continue a search for memory where the last search ended. Before the change new areas were always searched from the base address on. So now new small areas are cluttering holes of all sizes throughout the whole mmap-able region whereas before small holes tended to close holes near the base leaving holes far from the base large and available for larger requests. 2) the free_area_cache also is set to the location of the last munmap-ed area so in scenarios where we allocate e.g. five regions of 1K each, then free regions 4 2 3 in this order the next request for 1K will be placed in the position of the old region 3, whereas before we appended it to the still active region 1, placing it at the location of the old region 2. Before we had 1 free region of 2K, now we only get two free regions of 1K -> fragmentation. The patch addresses thes issues by introducing yet another cache descriptor cached_hole_size that contains the largest known hole size below the current free_area_cache. If a new request comes in the size is compared against the cached_hole_size and if the request can be filled with a hole below free_area_cache the search is started from the base instead. The results look promising: Whereas 2.6.12-rc4 fragments quickly and my (earlier posted) leakme.c test program terminates after 50000+ iterations with 96 distinct and fragmented maps in /proc/self/maps it performs nicely (as expected) with thread creation, Ingo's test_str02 with 20000 threads requires 0.7s system time. Taking out Ingo's patch (un-patch available per request) by basically deleting all mentions of free_area_cache from the kernel and starting the search for new memory always at the respective bases we observe: leakme terminates successfully with 11 distinctive hardly fragmented areas in /proc/self/maps but thread creating is gringdingly slow: 30+s(!) system time for Ingo's test_str02 with 20000 threads. Now - drumroll ;-) the appended patch works fine with leakme: it ends with only 7 distinct areas in /proc/self/maps and also thread creation seems sufficiently fast with 0.71s for 20000 threads. Signed-off-by: Wolfgang Wander <wwc@rentec.com> Credit-to: "Richard Purdie" <rpurdie@rpsys.net> Signed-off-by: Ken Chen <kenneth.w.chen@intel.com> Acked-by: Ingo Molnar <mingo@elte.hu> (partly) Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-22 08:14:49 +08:00
current->mm->cached_hole_size = 0;
compute_creds(bprm);
current->flags &= ~PF_FORKNOEXEC;
#ifdef __sparc__
if (N_MAGIC(ex) == NMAGIC) {
loff_t pos = fd_offset;
/* Fuck me plenty... */
/* <AOL></AOL> */
down_write(&current->mm->mmap_sem);
error = do_brk(N_TXTADDR(ex), ex.a_text);
up_write(&current->mm->mmap_sem);
bprm->file->f_op->read(bprm->file, (char *) N_TXTADDR(ex),
ex.a_text, &pos);
down_write(&current->mm->mmap_sem);
error = do_brk(N_DATADDR(ex), ex.a_data);
up_write(&current->mm->mmap_sem);
bprm->file->f_op->read(bprm->file, (char *) N_DATADDR(ex),
ex.a_data, &pos);
goto beyond_if;
}
#endif
if (N_MAGIC(ex) == OMAGIC) {
unsigned long text_addr, map_size;
loff_t pos;
text_addr = N_TXTADDR(ex);
#if defined(__alpha__) || defined(__sparc__)
pos = fd_offset;
map_size = ex.a_text+ex.a_data + PAGE_SIZE - 1;
#else
pos = 32;
map_size = ex.a_text+ex.a_data;
#endif
down_write(&current->mm->mmap_sem);
error = do_brk(text_addr & PAGE_MASK, map_size);
up_write(&current->mm->mmap_sem);
if (error != (text_addr & PAGE_MASK)) {
send_sig(SIGKILL, current, 0);
return error;
}
error = bprm->file->f_op->read(bprm->file,
(char __user *)text_addr,
ex.a_text+ex.a_data, &pos);
if ((signed long)error < 0) {
send_sig(SIGKILL, current, 0);
return error;
}
flush_icache_range(text_addr, text_addr+ex.a_text+ex.a_data);
} else {
static unsigned long error_time, error_time2;
if ((ex.a_text & 0xfff || ex.a_data & 0xfff) &&
(N_MAGIC(ex) != NMAGIC) && (jiffies-error_time2) > 5*HZ)
{
printk(KERN_NOTICE "executable not page aligned\n");
error_time2 = jiffies;
}
if ((fd_offset & ~PAGE_MASK) != 0 &&
(jiffies-error_time) > 5*HZ)
{
printk(KERN_WARNING
"fd_offset is not page aligned. Please convert program: %s\n",
bprm->file->f_path.dentry->d_name.name);
error_time = jiffies;
}
if (!bprm->file->f_op->mmap||((fd_offset & ~PAGE_MASK) != 0)) {
loff_t pos = fd_offset;
down_write(&current->mm->mmap_sem);
do_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
up_write(&current->mm->mmap_sem);
bprm->file->f_op->read(bprm->file,
(char __user *)N_TXTADDR(ex),
ex.a_text+ex.a_data, &pos);
flush_icache_range((unsigned long) N_TXTADDR(ex),
(unsigned long) N_TXTADDR(ex) +
ex.a_text+ex.a_data);
goto beyond_if;
}
down_write(&current->mm->mmap_sem);
error = do_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
PROT_READ | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE,
fd_offset);
up_write(&current->mm->mmap_sem);
if (error != N_TXTADDR(ex)) {
send_sig(SIGKILL, current, 0);
return error;
}
down_write(&current->mm->mmap_sem);
error = do_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
PROT_READ | PROT_WRITE | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE,
fd_offset + ex.a_text);
up_write(&current->mm->mmap_sem);
if (error != N_DATADDR(ex)) {
send_sig(SIGKILL, current, 0);
return error;
}
}
beyond_if:
set_binfmt(&aout_format);
retval = set_brk(current->mm->start_brk, current->mm->brk);
if (retval < 0) {
send_sig(SIGKILL, current, 0);
return retval;
}
retval = setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT);
if (retval < 0) {
/* Someone check-me: is this error path enough? */
send_sig(SIGKILL, current, 0);
return retval;
}
current->mm->start_stack =
(unsigned long) create_aout_tables((char __user *) bprm->p, bprm);
#ifdef __alpha__
regs->gp = ex.a_gpvalue;
#endif
start_thread(regs, ex.a_entry, current->mm->start_stack);
if (unlikely(current->ptrace & PT_PTRACED)) {
if (current->ptrace & PT_TRACE_EXEC)
ptrace_notify ((PTRACE_EVENT_EXEC << 8) | SIGTRAP);
else
send_sig(SIGTRAP, current, 0);
}
return 0;
}
static int load_aout_library(struct file *file)
{
struct inode * inode;
unsigned long bss, start_addr, len;
unsigned long error;
int retval;
struct exec ex;
inode = file->f_path.dentry->d_inode;
retval = -ENOEXEC;
error = kernel_read(file, 0, (char *) &ex, sizeof(ex));
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) ||
i_size_read(inode) < ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
goto out;
}
/*
* Requires a mmap handler. This prevents people from using a.out
* as part of an exploit attack against /proc-related vulnerabilities.
*/
if (!file->f_op || !file->f_op->mmap)
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) {
static unsigned long error_time;
loff_t pos = N_TXTOFF(ex);
if ((jiffies-error_time) > 5*HZ)
{
printk(KERN_WARNING
"N_TXTOFF is not page aligned. Please convert library: %s\n",
file->f_path.dentry->d_name.name);
error_time = jiffies;
}
down_write(&current->mm->mmap_sem);
do_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
up_write(&current->mm->mmap_sem);
file->f_op->read(file, (char __user *)start_addr,
ex.a_text + ex.a_data, &pos);
flush_icache_range((unsigned long) start_addr,
(unsigned long) start_addr + ex.a_text + ex.a_data);
retval = 0;
goto out;
}
/* Now use mmap to map the library into memory. */
down_write(&current->mm->mmap_sem);
error = do_mmap(file, start_addr, ex.a_text + ex.a_data,
PROT_READ | PROT_WRITE | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE,
N_TXTOFF(ex));
up_write(&current->mm->mmap_sem);
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) {
down_write(&current->mm->mmap_sem);
error = do_brk(start_addr + len, bss - len);
up_write(&current->mm->mmap_sem);
retval = error;
if (error != start_addr + len)
goto out;
}
retval = 0;
out:
return retval;
}
static int __init init_aout_binfmt(void)
{
return register_binfmt(&aout_format);
}
static void __exit exit_aout_binfmt(void)
{
unregister_binfmt(&aout_format);
}
core_initcall(init_aout_binfmt);
module_exit(exit_aout_binfmt);
MODULE_LICENSE("GPL");