static int sg_close(struct inode * inode, struct file * filp)
{
int dev=MINOR(inode->i_rdev);
scsi_generics[dev].users--;
if (scsi_generics[dev].device->host->hostt->module)
__MOD_DEC_USE_COUNT(scsi_generics[dev].device->host->hostt->module);
if(sg_template.module)
__MOD_DEC_USE_COUNT(sg_template.module);
scsi_generics[dev].exclude=0;
wake_up(&scsi_generics[dev].generic_wait);
return 0;
}
NORET_TYPE void do_exit(long code)
{
struct task_struct *tsk = current;
if (in_interrupt())
printk("Aiee, killing interrupt handler\n");
if (!tsk->pid)
panic("Attempted to kill the idle task!");
tsk->flags |= PF_EXITING;
start_bh_atomic();
del_timer(&tsk->real_timer);
end_bh_atomic();
lock_kernel();
fake_volatile:
#ifdef CONFIG_BSD_PROCESS_ACCT
acct_process(code);
#endif
sem_exit();
__exit_mm(tsk);
#if CONFIG_AP1000
exit_msc(tsk);
#endif
__exit_files(tsk);
__exit_fs(tsk);
__exit_sighand(tsk);
exit_thread();
tsk->state = TASK_ZOMBIE;
tsk->exit_code = code;
exit_notify();
#ifdef DEBUG_PROC_TREE
audit_ptree();
#endif
if (tsk->exec_domain && tsk->exec_domain->module)
__MOD_DEC_USE_COUNT(tsk->exec_domain->module);
if (tsk->binfmt && tsk->binfmt->module)
__MOD_DEC_USE_COUNT(tsk->binfmt->module);
schedule();
/*
* In order to get rid of the "volatile function does return" message
* I did this little loop that confuses gcc to think do_exit really
* is volatile. In fact it's schedule() that is volatile in some
* circumstances: when current->state = ZOMBIE, schedule() never
* returns.
*
* In fact the natural way to do all this is to have the label and the
* goto right after each other, but I put the fake_volatile label at
* the start of the function just in case something /really/ bad
* happens, and the schedule returns. This way we can try again. I'm
* not paranoid: it's just that everybody is out to get me.
*/
goto fake_volatile;
}
NORET_TYPE void do_exit(long code)
{
struct task_struct *tsk = current;
if (in_interrupt())
panic("Aiee, killing interrupt handler!");
if (!tsk->pid)
panic("Attempted to kill the idle task!");
if (tsk->pid == 1)
panic("Attempted to kill init!");
tsk->flags |= PF_EXITING;
del_timer_sync(&tsk->real_timer);
fake_volatile:
#ifdef CONFIG_BSD_PROCESS_ACCT
acct_process(code);
#endif
if (current->tux_info) {
#ifdef CONFIG_TUX_DEBUG
printk("Possibly unexpected TUX-thread exit(%ld) at %p?\n",
code, __builtin_return_address(0));
#endif
current->tux_exit();
}
__exit_mm(tsk);
lock_kernel();
sem_exit();
__exit_files(tsk);
__exit_fs(tsk);
exit_namespace(tsk);
exit_sighand(tsk);
exit_thread();
if (current->leader)
disassociate_ctty(1);
put_exec_domain(tsk->exec_domain);
if (tsk->binfmt && tsk->binfmt->module)
__MOD_DEC_USE_COUNT(tsk->binfmt->module);
tsk->exit_code = code;
exit_notify();
schedule();
BUG();
/*
* In order to get rid of the "volatile function does return" message
* I did this little loop that confuses gcc to think do_exit really
* is volatile. In fact it's schedule() that is volatile in some
* circumstances: when current->state = ZOMBIE, schedule() never
* returns.
*
* In fact the natural way to do all this is to have the label and the
* goto right after each other, but I put the fake_volatile label at
* the start of the function just in case something /really/ bad
* happens, and the schedule returns. This way we can try again. I'm
* not paranoid: it's just that everybody is out to get me.
*/
goto fake_volatile;
}
static void serial_close(struct tty_struct *tty, struct file * filp)
{
struct usb_serial_port *port = (struct usb_serial_port *) tty->driver_data;
struct usb_serial *serial = get_usb_serial (port, __FUNCTION__);
if (!serial) {
return;
}
dbg(__FUNCTION__ " - port %d", port->number);
if (!port->open_count) {
dbg (__FUNCTION__ " - port not opened");
return;
}
/* pass on to the driver specific version of this function if it is available */
if (serial->type->close) {
serial->type->close(port, filp);
if (serial->type->owner)
__MOD_DEC_USE_COUNT(serial->type->owner);
} else {
generic_close(port, filp);
}
}
void cleanup_tap_devices(void)
{
int i;
struct rtnet_device *rtdev;
for (i = 0; i < MAX_RT_DEVICES; i++)
if ((tap_device[i].present & TAP_DEV) != 0) {
if ((tap_device[i].present & XMIT_HOOK) != 0) {
rtdev = (struct rtnet_device *)tap_device[i].tap_dev.priv;
down(&rtdev->nrt_sem);
rtdev->hard_start_xmit = tap_device[i].orig_xmit;
if (rtdev->features & RTNETIF_F_NON_EXCLUSIVE_XMIT)
rtdev->start_xmit = tap_device[i].orig_xmit;
__MOD_DEC_USE_COUNT(rtdev->owner);
up(&rtdev->nrt_sem);
rtdev_dereference(rtdev);
}
if ((tap_device[i].present & RTMAC_TAP_DEV) != 0)
unregister_netdev(&tap_device[i].rtmac_tap_dev);
unregister_netdev(&tap_device[i].tap_dev);
}
}
static int sound_release(struct inode *inode, struct file *file)
{
int dev = MINOR(inode->i_rdev);
lock_kernel();
DEB(printk("sound_release(dev=%d)\n", dev));
switch (dev & 0x0f) {
case SND_DEV_CTL:
dev >>= 4;
if (mixer_devs[dev]->owner)
__MOD_DEC_USE_COUNT (mixer_devs[dev]->owner);
break;
case SND_DEV_SEQ:
case SND_DEV_SEQ2:
sequencer_release(dev, file);
break;
case SND_DEV_MIDIN:
MIDIbuf_release(dev, file);
break;
case SND_DEV_DSP:
case SND_DEV_DSP16:
case SND_DEV_AUDIO:
audio_release(dev, file);
break;
default:
printk(KERN_ERR "Sound error: Releasing unknown device 0x%02x\n", dev);
}
unlock_kernel();
return 0;
}
static int prism2_close(struct net_device *dev)
{
local_info_t *local = (local_info_t *) dev->priv;
PDEBUG(DEBUG_FLOW, "%s: prism2_close\n", dev->name);
#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
if (!local->hostapd && dev == local->dev &&
(!local->func->card_present || local->func->card_present(local)) &&
local->hw_ready && local->ap && local->iw_mode == IW_MODE_MASTER)
hostap_deauth_all_stas(dev, local->ap, 1);
#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
if (local->func->dev_close && local->func->dev_close(local))
return 0;
if (local->disable_on_close) {
local->func->hw_shutdown(dev, HOSTAP_HW_ENABLE_CMDCOMPL);
}
if (netif_running(dev)) {
netif_stop_queue(dev);
netif_device_detach(dev);
}
PRISM2_FLUSH_SCHEDULED_TASKS();
#ifdef NEW_MODULE_CODE
module_put(local->hw_module);
#elif MODULE
__MOD_DEC_USE_COUNT(local->hw_module);
#endif
return 0;
}
static void __ipsec_alg_usage_dec(struct ipsec_alg *ixt) {
atomic_dec(&ixt->ixt_refcnt);
#ifdef MODULE
if (ixt->ixt_module)
__MOD_DEC_USE_COUNT(ixt->ixt_module);
#endif
}
static struct net_device *find_lec_by_itfnum(int itf)
{
struct net_device *dev;
if (!try_atm_lane_ops())
return NULL;
dev = atm_lane_ops->get_lec(itf);
if (atm_lane_ops->owner)
__MOD_DEC_USE_COUNT(atm_lane_ops->owner);
return dev;
}
static int init_or_cleanup(int init)
{
int ret = 0;
if (!init) goto cleanup;
ret = ip_nat_rule_init();
if (ret < 0) {
printk("ip_nat_init: can't setup rules.\n");
goto cleanup_nothing;
}
ret = ip_nat_init();
if (ret < 0) {
printk("ip_nat_init: can't setup rules.\n");
goto cleanup_rule_init;
}
ret = nf_register_hook(&ip_nat_in_ops);
if (ret < 0) {
printk("ip_nat_init: can't register in hook.\n");
goto cleanup_nat;
}
ret = nf_register_hook(&ip_nat_out_ops);
if (ret < 0) {
printk("ip_nat_init: can't register out hook.\n");
goto cleanup_inops;
}
ret = nf_register_hook(&ip_nat_local_out_ops);
if (ret < 0) {
printk("ip_nat_init: can't register local out hook.\n");
goto cleanup_outops;
}
if (ip_conntrack_module)
__MOD_INC_USE_COUNT(ip_conntrack_module);
return ret;
cleanup:
if (ip_conntrack_module)
__MOD_DEC_USE_COUNT(ip_conntrack_module);
nf_unregister_hook(&ip_nat_local_out_ops);
cleanup_outops:
nf_unregister_hook(&ip_nat_out_ops);
cleanup_inops:
nf_unregister_hook(&ip_nat_in_ops);
cleanup_nat:
ip_nat_cleanup();
cleanup_rule_init:
ip_nat_rule_cleanup();
cleanup_nothing:
MUST_BE_READ_WRITE_UNLOCKED(&ip_nat_lock);
return ret;
}
/*****************************************************************************
* Driver tty interface functions
*****************************************************************************/
static int serial_open (struct tty_struct *tty, struct file * filp)
{
struct usb_serial *serial;
struct usb_serial_port *port;
unsigned int portNumber;
int retval = 0;
dbg("%s", __FUNCTION__);
/* initialize the pointer incase something fails */
tty->driver_data = NULL;
/* get the serial object associated with this tty pointer */
serial = get_serial_by_minor (MINOR(tty->device));
if (serial_paranoia_check (serial, __FUNCTION__))
return -ENODEV;
/* set up our port structure making the tty driver remember our port object, and us it */
portNumber = MINOR(tty->device) - serial->minor;
port = &serial->port[portNumber];
tty->driver_data = port;
down (&port->sem);
port->tty = tty;
/* lock this module before we call it */
if (serial->type->owner)
__MOD_INC_USE_COUNT(serial->type->owner);
++port->open_count;
if (port->open_count == 1) {
/* only call the device specific open if this
* is the first time the port is opened */
if (serial->type->open)
retval = serial->type->open(port, filp);
else
retval = generic_open(port, filp);
}
if (retval) {
port->open_count = 0;
if (serial->type->owner)
__MOD_DEC_USE_COUNT(serial->type->owner);
}
up (&port->sem);
return retval;
}
/*
* Decrement the use count of the proc_dir_entry.
*/
static void proc_delete_inode(struct inode *inode)
{
struct proc_dir_entry *de = inode->u.generic_ip;
inode->i_state = I_CLEAR;
if (PROC_INODE_PROPER(inode)) {
proc_pid_delete_inode(inode);
return;
}
if (de) {
if (de->owner)
__MOD_DEC_USE_COUNT(de->owner);
de_put(de);
}
}
long
asmlinkage sys_nfsservctl(int cmd, void *argp, void *resp)
{
int ret = -ENOSYS;
#if defined(CONFIG_MODULES)
lock_kernel();
if (nfsd_linkage ||
(request_module ("nfsd") == 0 && nfsd_linkage)) {
__MOD_INC_USE_COUNT(nfsd_linkage->owner);
unlock_kernel();
ret = nfsd_linkage->do_nfsservctl(cmd, argp, resp);
__MOD_DEC_USE_COUNT(nfsd_linkage->owner);
} else
unlock_kernel();
#endif
return ret;
}
static void __serial_close(struct usb_serial_port *port, struct file *filp)
{
if (!port->open_count) {
dbg ("%s - port not opened", __FUNCTION__);
return;
}
--port->open_count;
if (port->open_count <= 0) {
/* only call the device specific close if this
* port is being closed by the last owner */
if (port->serial->type->close)
port->serial->type->close(port, filp);
else
generic_close(port, filp);
port->open_count = 0;
}
if (port->serial->type->owner)
__MOD_DEC_USE_COUNT(port->serial->type->owner);
}
/*****************************************************************************
* Driver tty interface functions
*****************************************************************************/
static int serial_open (struct tty_struct *tty, struct file * filp)
{
struct usb_serial *serial;
struct usb_serial_port *port;
unsigned int portNumber;
int retval;
dbg(__FUNCTION__);
/* initialize the pointer incase something fails */
tty->driver_data = NULL;
/* get the serial object associated with this tty pointer */
serial = get_serial_by_minor (minor(tty->device));
if (serial_paranoia_check (serial, __FUNCTION__)) {
return -ENODEV;
}
/* set up our port structure making the tty driver remember our port object, and us it */
portNumber = minor(tty->device) - serial->minor;
port = &serial->port[portNumber];
tty->driver_data = port;
port->tty = tty;
/* pass on to the driver specific version of this function if it is available */
if (serial->type->open) {
if (serial->type->owner)
__MOD_INC_USE_COUNT(serial->type->owner);
retval = serial->type->open(port, filp);
if (retval)
__MOD_DEC_USE_COUNT(serial->type->owner);
} else {
retval = generic_open(port, filp);
}
return retval;
}
/*
* Get scheduler in the scheduler list by name
*/
static struct ip_vs_scheduler *ip_vs_sched_getbyname(const char *sched_name)
{
struct ip_vs_scheduler *sched;
struct list_head *l, *e;
IP_VS_DBG(2, "ip_vs_sched_getbyname(): sched_name \"%s\"\n",
sched_name);
l = &ip_vs_schedulers;
read_lock_bh(&__ip_vs_sched_lock);
for (e=l->next; e!=l; e=e->next) {
sched = list_entry(e, struct ip_vs_scheduler, n_list);
/*
* Test and MOD_INC_USE_COUNT atomically
*/
if (sched->module && !try_inc_mod_count(sched->module)) {
/*
* This scheduler is just deleted
*/
continue;
}
if (strcmp(sched_name, sched->name)==0) {
/* HIT */
read_unlock_bh(&__ip_vs_sched_lock);
return sched;
}
if (sched->module)
__MOD_DEC_USE_COUNT(sched->module);
}
read_unlock_bh(&__ip_vs_sched_lock);
return NULL;
}
static inline void module_put(struct module *module)
{
if (module)
__MOD_DEC_USE_COUNT(module);
}
NORET_TYPE void do_exit(long code)
{
struct task_struct *tsk = current;
if (in_interrupt())
panic("Aiee, killing interrupt handler!");
if (!tsk->pid)
panic("Attempted to kill the idle task!");
if (tsk->pid == 1)
panic("Attempted to kill init!");
/*
* If do_exit is called because this processes oopsed, it's possible
* that get_fs() was left as KERNEL_DS, so reset it to USER_DS before
* continuing. Amongst other possible reasons, this is to prevent
* mm_release()->clear_child_tid() from writing to a user-controlled
* kernel address.
*/
set_fs(USER_DS);
tsk->flags |= PF_EXITING;
del_timer_sync(&tsk->real_timer);
fake_volatile:
#ifdef CONFIG_BSD_PROCESS_ACCT
acct_process(code);
#endif
__exit_mm(tsk);
lock_kernel();
sem_exit();
__exit_files(tsk);
__exit_fs(tsk);
exit_namespace(tsk);
exit_sighand(tsk);
exit_thread();
if (current->leader)
disassociate_ctty(1);
put_exec_domain(tsk->exec_domain);
if (tsk->binfmt && tsk->binfmt->module)
__MOD_DEC_USE_COUNT(tsk->binfmt->module);
tsk->exit_code = code;
exit_notify();
schedule();
BUG();
/*
* In order to get rid of the "volatile function does return" message
* I did this little loop that confuses gcc to think do_exit really
* is volatile. In fact it's schedule() that is volatile in some
* circumstances: when current->state = ZOMBIE, schedule() never
* returns.
*
* In fact the natural way to do all this is to have the label and the
* goto right after each other, but I put the fake_volatile label at
* the start of the function just in case something /really/ bad
* happens, and the schedule returns. This way we can try again. I'm
* not paranoid: it's just that everybody is out to get me.
*/
goto fake_volatile;
}
static inline int
do_load_elf_binary(struct linux_binprm * bprm, struct pt_regs * regs)
{
struct file * file;
struct dentry *interpreter_dentry = NULL; /* to shut gcc up */
unsigned long load_addr = 0, load_bias;
int load_addr_set = 0;
char * elf_interpreter = NULL;
unsigned int interpreter_type = INTERPRETER_NONE;
unsigned char ibcs2_interpreter = 0;
mm_segment_t old_fs;
unsigned long error;
struct elf_phdr * elf_ppnt, *elf_phdata;
unsigned long elf_bss, k, elf_brk;
int elf_exec_fileno;
int retval, size, i;
unsigned long elf_entry, interp_load_addr = 0;
unsigned long start_code, end_code, end_data;
struct elfhdr elf_ex;
struct elfhdr interp_elf_ex;
struct exec interp_ex;
char passed_fileno[6];
/* Get the exec-header */
elf_ex = *((struct elfhdr *) bprm->buf);
retval = -ENOEXEC;
/* First of all, some simple consistency checks */
if (elf_ex.e_ident[0] != 0x7f ||
strncmp(&elf_ex.e_ident[1], "ELF", 3) != 0)
goto out;
if (elf_ex.e_type != ET_EXEC && elf_ex.e_type != ET_DYN)
goto out;
if (!elf_check_arch(elf_ex.e_machine))
goto out;
#ifdef __mips__
/* allow only mips1 if exec is MIPSEB elf,
because IRIX binaries handled elsewhere. */
/* borrowed from binutils/include/elf/common.h*/
#define EI_DATA 5 /* Data encoding */
#define ELFDATA2MSB 2 /* 2's complement, big endian */
if ((elf_ex.e_ident[EI_DATA] == ELFDATA2MSB ) &&
(elf_ex.e_flags & EF_MIPS_ARCH) ) {
retval = -ENOEXEC;
goto out;
}
#endif
if (!bprm->dentry->d_inode->i_op ||
!bprm->dentry->d_inode->i_op->default_file_ops ||
!bprm->dentry->d_inode->i_op->default_file_ops->mmap)
goto out;
/* Now read in all of the header information */
retval = -ENOMEM;
size = elf_ex.e_phentsize * elf_ex.e_phnum;
elf_phdata = (struct elf_phdr *) kmalloc(size, GFP_KERNEL);
if (!elf_phdata)
goto out;
retval = read_exec(bprm->dentry, elf_ex.e_phoff,
(char *) elf_phdata, size, 1);
if (retval < 0)
goto out_free_ph;
retval = open_dentry(bprm->dentry, O_RDONLY);
if (retval < 0)
goto out_free_ph;
elf_exec_fileno = retval;
file = fget(elf_exec_fileno);
elf_ppnt = elf_phdata;
elf_bss = 0;
elf_brk = 0;
start_code = ~0UL;
end_code = 0;
end_data = 0;
for (i = 0; i < elf_ex.e_phnum; i++) {
if (elf_ppnt->p_type == PT_INTERP) {
retval = -EINVAL;
if (elf_interpreter)
goto out_free_interp;
/* This is the program interpreter used for
* shared libraries - for now assume that this
* is an a.out format binary
*/
retval = -ENOMEM;
elf_interpreter = (char *) kmalloc(elf_ppnt->p_filesz,
GFP_KERNEL);
if (!elf_interpreter)
goto out_free_file;
retval = read_exec(bprm->dentry, elf_ppnt->p_offset,
elf_interpreter,
elf_ppnt->p_filesz, 1);
if (retval < 0)
goto out_free_interp;
/* If the program interpreter is one of these two,
* then assume an iBCS2 image. Otherwise assume
* a native linux image.
*/
if (strcmp(elf_interpreter,"/usr/lib/libc.so.1") == 0 ||
strcmp(elf_interpreter,"/usr/lib/ld.so.1") == 0)
ibcs2_interpreter = 1;
#if 0
printk("Using ELF interpreter %s\n", elf_interpreter);
#endif
old_fs = get_fs(); /* This could probably be optimized */
set_fs(get_ds());
#ifdef __sparc__
if (ibcs2_interpreter) {
unsigned long old_pers = current->personality;
current->personality = PER_SVR4;
interpreter_dentry = open_namei(elf_interpreter,
0, 0);
current->personality = old_pers;
} else
#endif
interpreter_dentry = open_namei(elf_interpreter,
0, 0);
set_fs(old_fs);
retval = PTR_ERR(interpreter_dentry);
if (IS_ERR(interpreter_dentry))
goto out_free_interp;
retval = permission(interpreter_dentry->d_inode, MAY_EXEC);
if (retval < 0)
goto out_free_dentry;
retval = read_exec(interpreter_dentry, 0, bprm->buf, 128, 1);
if (retval < 0)
goto out_free_dentry;
/* Get the exec headers */
interp_ex = *((struct exec *) bprm->buf);
interp_elf_ex = *((struct elfhdr *) bprm->buf);
}
elf_ppnt++;
}
/* Some simple consistency checks for the interpreter */
if (elf_interpreter) {
interpreter_type = INTERPRETER_ELF | INTERPRETER_AOUT;
/* Now figure out which format our binary is */
if ((N_MAGIC(interp_ex) != OMAGIC) &&
(N_MAGIC(interp_ex) != ZMAGIC) &&
(N_MAGIC(interp_ex) != QMAGIC))
interpreter_type = INTERPRETER_ELF;
if (interp_elf_ex.e_ident[0] != 0x7f ||
strncmp(&interp_elf_ex.e_ident[1], "ELF", 3) != 0)
interpreter_type &= ~INTERPRETER_ELF;
retval = -ELIBBAD;
if (!interpreter_type)
goto out_free_dentry;
/* Make sure only one type was selected */
if ((interpreter_type & INTERPRETER_ELF) &&
interpreter_type != INTERPRETER_ELF) {
printk(KERN_WARNING "ELF: Ambiguous type, using ELF\n");
interpreter_type = INTERPRETER_ELF;
}
}
/* OK, we are done with that, now set up the arg stuff,
and then start this sucker up */
if (!bprm->sh_bang) {
char * passed_p;
if (interpreter_type == INTERPRETER_AOUT) {
sprintf(passed_fileno, "%d", elf_exec_fileno);
passed_p = passed_fileno;
if (elf_interpreter) {
bprm->p = copy_strings(1,&passed_p,bprm->page,bprm->p,2);
bprm->argc++;
}
}
retval = -E2BIG;
if (!bprm->p)
goto out_free_dentry;
}
/* Flush all traces of the currently running executable */
retval = flush_old_exec(bprm);
if (retval)
goto out_free_dentry;
/* OK, This is the point of no return */
current->mm->end_data = 0;
current->mm->end_code = 0;
current->mm->mmap = NULL;
current->flags &= ~PF_FORKNOEXEC;
elf_entry = (unsigned long) elf_ex.e_entry;
/* Do this immediately, since STACK_TOP as used in setup_arg_pages
may depend on the personality. */
SET_PERSONALITY(elf_ex, ibcs2_interpreter);
/* Do this so that we can load the interpreter, if need be. We will
change some of these later */
current->mm->rss = 0;
bprm->p = setup_arg_pages(bprm->p, bprm);
current->mm->start_stack = bprm->p;
/* Try and get dynamic programs out of the way of the default mmap
base, as well as whatever program they might try to exec. This
is because the brk will follow the loader, and is not movable. */
load_bias = ELF_PAGESTART(elf_ex.e_type==ET_DYN ? ELF_ET_DYN_BASE : 0);
/* Now we do a little grungy work by mmaping the ELF image into
the correct location in memory. At this point, we assume that
the image should be loaded at fixed address, not at a variable
address. */
old_fs = get_fs();
set_fs(get_ds());
for(i = 0, elf_ppnt = elf_phdata; i < elf_ex.e_phnum; i++, elf_ppnt++) {
int elf_prot = 0, elf_flags;
unsigned long vaddr;
if (elf_ppnt->p_type != PT_LOAD)
continue;
if (elf_ppnt->p_flags & PF_R) elf_prot |= PROT_READ;
if (elf_ppnt->p_flags & PF_W) elf_prot |= PROT_WRITE;
if (elf_ppnt->p_flags & PF_X) elf_prot |= PROT_EXEC;
elf_flags = MAP_PRIVATE|MAP_DENYWRITE|MAP_EXECUTABLE;
vaddr = elf_ppnt->p_vaddr;
if (elf_ex.e_type == ET_EXEC || load_addr_set) {
elf_flags |= MAP_FIXED;
}
error = do_mmap(file, ELF_PAGESTART(load_bias + vaddr),
(elf_ppnt->p_filesz +
ELF_PAGEOFFSET(elf_ppnt->p_vaddr)),
elf_prot, elf_flags, (elf_ppnt->p_offset -
ELF_PAGEOFFSET(elf_ppnt->p_vaddr)));
if (!load_addr_set) {
load_addr_set = 1;
load_addr = (elf_ppnt->p_vaddr - elf_ppnt->p_offset);
if (elf_ex.e_type == ET_DYN) {
load_bias += error -
ELF_PAGESTART(load_bias + vaddr);
load_addr += error;
}
}
k = elf_ppnt->p_vaddr;
if (k < start_code) start_code = k;
k = elf_ppnt->p_vaddr + elf_ppnt->p_filesz;
if (k > elf_bss)
elf_bss = k;
if ((elf_ppnt->p_flags & PF_X) && end_code < k)
end_code = k;
if (end_data < k)
end_data = k;
k = elf_ppnt->p_vaddr + elf_ppnt->p_memsz;
if (k > elf_brk)
elf_brk = k;
}
set_fs(old_fs);
fput(file); /* all done with the file */
elf_entry += load_bias;
elf_bss += load_bias;
elf_brk += load_bias;
start_code += load_bias;
end_code += load_bias;
end_data += load_bias;
if (elf_interpreter) {
if (interpreter_type == INTERPRETER_AOUT)
elf_entry = load_aout_interp(&interp_ex,
interpreter_dentry);
else
elf_entry = load_elf_interp(&interp_elf_ex,
interpreter_dentry,
&interp_load_addr);
dput(interpreter_dentry);
kfree(elf_interpreter);
if (elf_entry == ~0UL) {
printk(KERN_ERR "Unable to load interpreter\n");
kfree(elf_phdata);
send_sig(SIGSEGV, current, 0);
return 0;
}
}
kfree(elf_phdata);
if (interpreter_type != INTERPRETER_AOUT)
sys_close(elf_exec_fileno);
if (current->exec_domain && current->exec_domain->module)
__MOD_DEC_USE_COUNT(current->exec_domain->module);
if (current->binfmt && current->binfmt->module)
__MOD_DEC_USE_COUNT(current->binfmt->module);
current->exec_domain = lookup_exec_domain(current->personality);
current->binfmt = &elf_format;
if (current->exec_domain && current->exec_domain->module)
__MOD_INC_USE_COUNT(current->exec_domain->module);
if (current->binfmt && current->binfmt->module)
__MOD_INC_USE_COUNT(current->binfmt->module);
#ifndef VM_STACK_FLAGS
current->executable = dget(bprm->dentry);
#endif
compute_creds(bprm);
current->flags &= ~PF_FORKNOEXEC;
bprm->p = (unsigned long)
create_elf_tables((char *)bprm->p,
bprm->argc,
bprm->envc,
(interpreter_type == INTERPRETER_ELF ? &elf_ex : NULL),
load_addr, load_bias,
interp_load_addr,
(interpreter_type == INTERPRETER_AOUT ? 0 : 1));
/* N.B. passed_fileno might not be initialized? */
if (interpreter_type == INTERPRETER_AOUT)
current->mm->arg_start += strlen(passed_fileno) + 1;
current->mm->start_brk = current->mm->brk = elf_brk;
current->mm->end_code = end_code;
current->mm->start_code = start_code;
current->mm->end_data = end_data;
current->mm->start_stack = bprm->p;
/* Calling set_brk effectively mmaps the pages that we need
* for the bss and break sections
*/
set_brk(elf_bss, elf_brk);
padzero(elf_bss);
#if 0
printk("(start_brk) %x\n" , current->mm->start_brk);
printk("(end_code) %x\n" , current->mm->end_code);
printk("(start_code) %x\n" , current->mm->start_code);
printk("(end_data) %x\n" , current->mm->end_data);
printk("(start_stack) %x\n" , current->mm->start_stack);
printk("(brk) %x\n" , current->mm->brk);
#endif
if ( current->personality == PER_SVR4 )
{
/* Why this, you ask??? Well SVr4 maps page 0 as read-only,
and some applications "depend" upon this behavior.
Since we do not have the power to recompile these, we
emulate the SVr4 behavior. Sigh. */
/* N.B. Shouldn't the size here be PAGE_SIZE?? */
error = do_mmap(NULL, 0, 4096, PROT_READ | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE, 0);
}
#ifdef ELF_PLAT_INIT
/*
* The ABI may specify that certain registers be set up in special
* ways (on i386 %edx is the address of a DT_FINI function, for
* example. This macro performs whatever initialization to
* the regs structure is required.
*/
ELF_PLAT_INIT(regs);
#endif
start_thread(regs, elf_entry, bprm->p);
if (current->flags & PF_PTRACED)
send_sig(SIGTRAP, current, 0);
retval = 0;
out:
return retval;
/* error cleanup */
out_free_dentry:
dput(interpreter_dentry);
out_free_interp:
if (elf_interpreter)
kfree(elf_interpreter);
out_free_file:
fput(file);
sys_close(elf_exec_fileno);
out_free_ph:
kfree(elf_phdata);
goto out;
}
static void __exit fini(void)
{
ipt_unregister_match(&state_match);
if (ip_conntrack_module)
__MOD_DEC_USE_COUNT(ip_conntrack_module);
}
void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler)
{
if (scheduler->module)
__MOD_DEC_USE_COUNT(scheduler->module);
}
/*
* This creates a new process as a copy of the old one,
* but does not actually start it yet.
*
* It copies the registers, and all the appropriate
* parts of the process environment (as per the clone
* flags). The actual kick-off is left to the caller.
*/
struct task_struct *copy_process(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int *parent_tidptr,
int *child_tidptr)
{
int retval;
struct task_struct *p = NULL;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
/*
* Thread groups must share signals as well, and detached threads
* can only be started up within the thread group.
*/
if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND))
return ERR_PTR(-EINVAL);
if ((clone_flags & CLONE_DETACHED) && !(clone_flags & CLONE_THREAD))
return ERR_PTR(-EINVAL);
if (!(clone_flags & CLONE_DETACHED) && (clone_flags & CLONE_THREAD))
return ERR_PTR(-EINVAL);
retval = -ENOMEM;
p = dup_task_struct(current);
if (!p)
goto fork_out;
p->tux_info = NULL;
retval = -EAGAIN;
/*
* Increment user->__count before the rlimit test so that it would
* be correct if we take the bad_fork_free failure path.
*/
atomic_inc(&p->user->__count);
if (atomic_read(&p->user->processes) >= p->rlim[RLIMIT_NPROC].rlim_cur) {
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE))
goto bad_fork_free;
}
atomic_inc(&p->user->processes);
/*
* Counter increases are protected by
* the kernel lock so nr_threads can't
* increase under us (but it may decrease).
*/
if (nr_threads >= max_threads)
goto bad_fork_cleanup_count;
get_exec_domain(p->exec_domain);
if (p->binfmt && p->binfmt->module)
__MOD_INC_USE_COUNT(p->binfmt->module);
p->did_exec = 0;
p->swappable = 0;
p->state = TASK_UNINTERRUPTIBLE;
copy_flags(clone_flags, p);
if (clone_flags & CLONE_IDLETASK)
p->pid = 0;
else {
p->pid = alloc_pidmap();
if (p->pid == -1)
goto bad_fork_cleanup;
}
retval = -EFAULT;
if (clone_flags & CLONE_PARENT_SETTID)
if (put_user(p->pid, parent_tidptr))
goto bad_fork_cleanup;
INIT_LIST_HEAD(&p->run_list);
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
init_waitqueue_head(&p->wait_chldexit);
p->vfork_done = NULL;
spin_lock_init(&p->alloc_lock);
spin_lock_init(&p->switch_lock);
p->sigpending = 0;
init_sigpending(&p->pending);
p->it_real_value = p->it_virt_value = p->it_prof_value = 0;
p->it_real_incr = p->it_virt_incr = p->it_prof_incr = 0;
init_timer(&p->real_timer);
p->real_timer.data = (unsigned long) p;
p->leader = 0; /* session leadership doesn't inherit */
p->tty_old_pgrp = 0;
memset(&p->utime, 0, sizeof(p->utime));
memset(&p->stime, 0, sizeof(p->stime));
memset(&p->cutime, 0, sizeof(p->cutime));
memset(&p->cstime, 0, sizeof(p->cstime));
memset(&p->group_utime, 0, sizeof(p->group_utime));
memset(&p->group_stime, 0, sizeof(p->group_stime));
memset(&p->group_cutime, 0, sizeof(p->group_cutime));
memset(&p->group_cstime, 0, sizeof(p->group_cstime));
#ifdef CONFIG_SMP
memset(&p->per_cpu_utime, 0, sizeof(p->per_cpu_utime));
memset(&p->per_cpu_stime, 0, sizeof(p->per_cpu_stime));
#endif
memset(&p->timing_state, 0, sizeof(p->timing_state));
p->timing_state.type = PROCESS_TIMING_USER;
p->last_sigxcpu = 0;
p->array = NULL;
p->lock_depth = -1; /* -1 = no lock */
p->start_time = jiffies;
retval = -ENOMEM;
/* copy all the process information */
if (copy_files(clone_flags, p))
goto bad_fork_cleanup;
if (copy_fs(clone_flags, p))
goto bad_fork_cleanup_files;
if (copy_sighand(clone_flags, p))
goto bad_fork_cleanup_fs;
if (copy_signal(clone_flags, p))
goto bad_fork_cleanup_sighand;
if (copy_mm(clone_flags, p))
goto bad_fork_cleanup_signal;
if (copy_namespace(clone_flags, p))
goto bad_fork_cleanup_mm;
retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
if (retval)
goto bad_fork_cleanup_namespace;
p->semundo = NULL;
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID)
? child_tidptr : NULL;
/*
* Clear TID on mm_release()?
*/
p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID)
? child_tidptr : NULL;
/* Our parent execution domain becomes current domain
These must match for thread signalling to apply */
p->parent_exec_id = p->self_exec_id;
/* ok, now we should be set up.. */
p->swappable = 1;
if (clone_flags & CLONE_DETACHED)
p->exit_signal = -1;
else
p->exit_signal = clone_flags & CSIGNAL;
p->pdeath_signal = 0;
/*
* Share the timeslice between parent and child, thus the
* total amount of pending timeslices in the system doesnt change,
* resulting in more scheduling fairness.
*/
local_irq_disable();
p->time_slice = (current->time_slice + 1) >> 1;
p->first_time_slice = 1;
/*
* The remainder of the first timeslice might be recovered by
* the parent if the child exits early enough.
*/
current->time_slice >>= 1;
p->last_run = jiffies;
if (!current->time_slice) {
/*
* This case is rare, it happens when the parent has only
* a single jiffy left from its timeslice. Taking the
* runqueue lock is not a problem.
*/
current->time_slice = 1;
scheduler_tick(0 /* don't update the time stats */);
}
local_irq_enable();
if ((int)current->time_slice <= 0)
BUG();
if ((int)p->time_slice <= 0)
BUG();
/*
* Ok, add it to the run-queues and make it
* visible to the rest of the system.
*
* Let it rip!
*/
p->tgid = p->pid;
p->group_leader = p;
INIT_LIST_HEAD(&p->ptrace_children);
INIT_LIST_HEAD(&p->ptrace_list);
/* Need tasklist lock for parent etc handling! */
write_lock_irq(&tasklist_lock);
/*
* Check for pending SIGKILL! The new thread should not be allowed
* to slip out of an OOM kill. (or normal SIGKILL.)
*/
if (sigismember(¤t->pending.signal, SIGKILL)) {
write_unlock_irq(&tasklist_lock);
retval = -EINTR;
goto bad_fork_cleanup_namespace;
}
/* CLONE_PARENT re-uses the old parent */
if (clone_flags & (CLONE_PARENT|CLONE_THREAD))
p->real_parent = current->real_parent;
else
p->real_parent = current;
p->parent = p->real_parent;
if (clone_flags & CLONE_THREAD) {
spin_lock(¤t->sighand->siglock);
/*
* Important: if an exit-all has been started then
* do not create this new thread - the whole thread
* group is supposed to exit anyway.
*/
if (current->signal->group_exit) {
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -EINTR;
goto bad_fork_cleanup_namespace;
}
p->tgid = current->tgid;
p->group_leader = current->group_leader;
if (current->signal->group_stop_count > 0) {
/*
* There is an all-stop in progress for the group.
* We ourselves will stop as soon as we check signals.
* Make the new thread part of that group stop too.
*/
current->signal->group_stop_count++;
p->sigpending = 1;
}
spin_unlock(¤t->sighand->siglock);
}
SET_LINKS(p);
if (p->ptrace & PT_PTRACED)
__ptrace_link(p, current->parent);
attach_pid(p, PIDTYPE_PID, p->pid);
if (thread_group_leader(p)) {
attach_pid(p, PIDTYPE_TGID, p->tgid);
attach_pid(p, PIDTYPE_PGID, p->pgrp);
attach_pid(p, PIDTYPE_SID, p->session);
} else {
link_pid(p, p->pids + PIDTYPE_TGID,
&p->group_leader->pids[PIDTYPE_TGID].pid);
}
/* clear controlling tty of new task if parent's was just cleared */
if (!current->tty && p->tty)
p->tty = NULL;
nr_threads++;
write_unlock_irq(&tasklist_lock);
retval = 0;
fork_out:
if (retval)
return ERR_PTR(retval);
return p;
bad_fork_cleanup_namespace:
exit_namespace(p);
bad_fork_cleanup_mm:
exit_mm(p);
if (p->active_mm)
mmdrop(p->active_mm);
bad_fork_cleanup_signal:
exit_signal(p);
bad_fork_cleanup_sighand:
exit_sighand(p);
bad_fork_cleanup_fs:
exit_fs(p); /* blocking */
bad_fork_cleanup_files:
exit_files(p); /* blocking */
bad_fork_cleanup:
if (p->pid > 0)
free_pidmap(p->pid);
put_exec_domain(p->exec_domain);
if (p->binfmt && p->binfmt->module)
__MOD_DEC_USE_COUNT(p->binfmt->module);
bad_fork_cleanup_count:
atomic_dec(&p->user->processes);
bad_fork_free:
p->state = TASK_ZOMBIE; /* debug */
atomic_dec(&p->usage);
put_task_struct(p);
goto fork_out;
}