e041c68341
The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
389 lines
10 KiB
C
389 lines
10 KiB
C
/*
|
|
* arch/s390/kernel/process.c
|
|
*
|
|
* S390 version
|
|
* Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
|
|
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
|
|
* Hartmut Penner (hp@de.ibm.com),
|
|
* Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
|
|
*
|
|
* Derived from "arch/i386/kernel/process.c"
|
|
* Copyright (C) 1995, Linus Torvalds
|
|
*/
|
|
|
|
/*
|
|
* This file handles the architecture-dependent parts of process handling..
|
|
*/
|
|
|
|
#include <linux/config.h>
|
|
#include <linux/compiler.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/smp_lock.h>
|
|
#include <linux/stddef.h>
|
|
#include <linux/unistd.h>
|
|
#include <linux/ptrace.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/user.h>
|
|
#include <linux/a.out.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/delay.h>
|
|
#include <linux/reboot.h>
|
|
#include <linux/init.h>
|
|
#include <linux/module.h>
|
|
#include <linux/notifier.h>
|
|
|
|
#include <asm/uaccess.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/system.h>
|
|
#include <asm/io.h>
|
|
#include <asm/processor.h>
|
|
#include <asm/irq.h>
|
|
#include <asm/timer.h>
|
|
|
|
asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
|
|
|
|
/*
|
|
* Return saved PC of a blocked thread. used in kernel/sched.
|
|
* resume in entry.S does not create a new stack frame, it
|
|
* just stores the registers %r6-%r15 to the frame given by
|
|
* schedule. We want to return the address of the caller of
|
|
* schedule, so we have to walk the backchain one time to
|
|
* find the frame schedule() store its return address.
|
|
*/
|
|
unsigned long thread_saved_pc(struct task_struct *tsk)
|
|
{
|
|
struct stack_frame *sf, *low, *high;
|
|
|
|
if (!tsk || !task_stack_page(tsk))
|
|
return 0;
|
|
low = task_stack_page(tsk);
|
|
high = (struct stack_frame *) task_pt_regs(tsk);
|
|
sf = (struct stack_frame *) (tsk->thread.ksp & PSW_ADDR_INSN);
|
|
if (sf <= low || sf > high)
|
|
return 0;
|
|
sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN);
|
|
if (sf <= low || sf > high)
|
|
return 0;
|
|
return sf->gprs[8];
|
|
}
|
|
|
|
/*
|
|
* Need to know about CPUs going idle?
|
|
*/
|
|
static ATOMIC_NOTIFIER_HEAD(idle_chain);
|
|
|
|
int register_idle_notifier(struct notifier_block *nb)
|
|
{
|
|
return atomic_notifier_chain_register(&idle_chain, nb);
|
|
}
|
|
EXPORT_SYMBOL(register_idle_notifier);
|
|
|
|
int unregister_idle_notifier(struct notifier_block *nb)
|
|
{
|
|
return atomic_notifier_chain_unregister(&idle_chain, nb);
|
|
}
|
|
EXPORT_SYMBOL(unregister_idle_notifier);
|
|
|
|
void do_monitor_call(struct pt_regs *regs, long interruption_code)
|
|
{
|
|
/* disable monitor call class 0 */
|
|
__ctl_clear_bit(8, 15);
|
|
|
|
atomic_notifier_call_chain(&idle_chain, CPU_NOT_IDLE,
|
|
(void *)(long) smp_processor_id());
|
|
}
|
|
|
|
extern void s390_handle_mcck(void);
|
|
/*
|
|
* The idle loop on a S390...
|
|
*/
|
|
static void default_idle(void)
|
|
{
|
|
int cpu, rc;
|
|
|
|
/* CPU is going idle. */
|
|
cpu = smp_processor_id();
|
|
|
|
local_irq_disable();
|
|
if (need_resched()) {
|
|
local_irq_enable();
|
|
return;
|
|
}
|
|
|
|
rc = atomic_notifier_call_chain(&idle_chain,
|
|
CPU_IDLE, (void *)(long) cpu);
|
|
if (rc != NOTIFY_OK && rc != NOTIFY_DONE)
|
|
BUG();
|
|
if (rc != NOTIFY_OK) {
|
|
local_irq_enable();
|
|
return;
|
|
}
|
|
|
|
/* enable monitor call class 0 */
|
|
__ctl_set_bit(8, 15);
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
if (cpu_is_offline(cpu)) {
|
|
preempt_enable_no_resched();
|
|
cpu_die();
|
|
}
|
|
#endif
|
|
|
|
local_mcck_disable();
|
|
if (test_thread_flag(TIF_MCCK_PENDING)) {
|
|
local_mcck_enable();
|
|
local_irq_enable();
|
|
s390_handle_mcck();
|
|
return;
|
|
}
|
|
|
|
/* Wait for external, I/O or machine check interrupt. */
|
|
__load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_WAIT |
|
|
PSW_MASK_IO | PSW_MASK_EXT);
|
|
}
|
|
|
|
void cpu_idle(void)
|
|
{
|
|
for (;;) {
|
|
while (!need_resched())
|
|
default_idle();
|
|
|
|
preempt_enable_no_resched();
|
|
schedule();
|
|
preempt_disable();
|
|
}
|
|
}
|
|
|
|
void show_regs(struct pt_regs *regs)
|
|
{
|
|
struct task_struct *tsk = current;
|
|
|
|
printk("CPU: %d %s\n", task_thread_info(tsk)->cpu, print_tainted());
|
|
printk("Process %s (pid: %d, task: %p, ksp: %p)\n",
|
|
current->comm, current->pid, (void *) tsk,
|
|
(void *) tsk->thread.ksp);
|
|
|
|
show_registers(regs);
|
|
/* Show stack backtrace if pt_regs is from kernel mode */
|
|
if (!(regs->psw.mask & PSW_MASK_PSTATE))
|
|
show_trace(0,(unsigned long *) regs->gprs[15]);
|
|
}
|
|
|
|
extern void kernel_thread_starter(void);
|
|
|
|
__asm__(".align 4\n"
|
|
"kernel_thread_starter:\n"
|
|
" la 2,0(10)\n"
|
|
" basr 14,9\n"
|
|
" la 2,0\n"
|
|
" br 11\n");
|
|
|
|
int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
|
|
{
|
|
struct pt_regs regs;
|
|
|
|
memset(®s, 0, sizeof(regs));
|
|
regs.psw.mask = PSW_KERNEL_BITS | PSW_MASK_IO | PSW_MASK_EXT;
|
|
regs.psw.addr = (unsigned long) kernel_thread_starter | PSW_ADDR_AMODE;
|
|
regs.gprs[9] = (unsigned long) fn;
|
|
regs.gprs[10] = (unsigned long) arg;
|
|
regs.gprs[11] = (unsigned long) do_exit;
|
|
regs.orig_gpr2 = -1;
|
|
|
|
/* Ok, create the new process.. */
|
|
return do_fork(flags | CLONE_VM | CLONE_UNTRACED,
|
|
0, ®s, 0, NULL, NULL);
|
|
}
|
|
|
|
/*
|
|
* Free current thread data structures etc..
|
|
*/
|
|
void exit_thread(void)
|
|
{
|
|
}
|
|
|
|
void flush_thread(void)
|
|
{
|
|
clear_used_math();
|
|
clear_tsk_thread_flag(current, TIF_USEDFPU);
|
|
}
|
|
|
|
void release_thread(struct task_struct *dead_task)
|
|
{
|
|
}
|
|
|
|
int copy_thread(int nr, unsigned long clone_flags, unsigned long new_stackp,
|
|
unsigned long unused,
|
|
struct task_struct * p, struct pt_regs * regs)
|
|
{
|
|
struct fake_frame
|
|
{
|
|
struct stack_frame sf;
|
|
struct pt_regs childregs;
|
|
} *frame;
|
|
|
|
frame = container_of(task_pt_regs(p), struct fake_frame, childregs);
|
|
p->thread.ksp = (unsigned long) frame;
|
|
/* Store access registers to kernel stack of new process. */
|
|
frame->childregs = *regs;
|
|
frame->childregs.gprs[2] = 0; /* child returns 0 on fork. */
|
|
frame->childregs.gprs[15] = new_stackp;
|
|
frame->sf.back_chain = 0;
|
|
|
|
/* new return point is ret_from_fork */
|
|
frame->sf.gprs[8] = (unsigned long) ret_from_fork;
|
|
|
|
/* fake return stack for resume(), don't go back to schedule */
|
|
frame->sf.gprs[9] = (unsigned long) frame;
|
|
|
|
/* Save access registers to new thread structure. */
|
|
save_access_regs(&p->thread.acrs[0]);
|
|
|
|
#ifndef CONFIG_64BIT
|
|
/*
|
|
* save fprs to current->thread.fp_regs to merge them with
|
|
* the emulated registers and then copy the result to the child.
|
|
*/
|
|
save_fp_regs(¤t->thread.fp_regs);
|
|
memcpy(&p->thread.fp_regs, ¤t->thread.fp_regs,
|
|
sizeof(s390_fp_regs));
|
|
p->thread.user_seg = __pa((unsigned long) p->mm->pgd) | _SEGMENT_TABLE;
|
|
/* Set a new TLS ? */
|
|
if (clone_flags & CLONE_SETTLS)
|
|
p->thread.acrs[0] = regs->gprs[6];
|
|
#else /* CONFIG_64BIT */
|
|
/* Save the fpu registers to new thread structure. */
|
|
save_fp_regs(&p->thread.fp_regs);
|
|
p->thread.user_seg = __pa((unsigned long) p->mm->pgd) | _REGION_TABLE;
|
|
/* Set a new TLS ? */
|
|
if (clone_flags & CLONE_SETTLS) {
|
|
if (test_thread_flag(TIF_31BIT)) {
|
|
p->thread.acrs[0] = (unsigned int) regs->gprs[6];
|
|
} else {
|
|
p->thread.acrs[0] = (unsigned int)(regs->gprs[6] >> 32);
|
|
p->thread.acrs[1] = (unsigned int) regs->gprs[6];
|
|
}
|
|
}
|
|
#endif /* CONFIG_64BIT */
|
|
/* start new process with ar4 pointing to the correct address space */
|
|
p->thread.mm_segment = get_fs();
|
|
/* Don't copy debug registers */
|
|
memset(&p->thread.per_info,0,sizeof(p->thread.per_info));
|
|
|
|
return 0;
|
|
}
|
|
|
|
asmlinkage long sys_fork(struct pt_regs regs)
|
|
{
|
|
return do_fork(SIGCHLD, regs.gprs[15], ®s, 0, NULL, NULL);
|
|
}
|
|
|
|
asmlinkage long sys_clone(struct pt_regs regs)
|
|
{
|
|
unsigned long clone_flags;
|
|
unsigned long newsp;
|
|
int __user *parent_tidptr, *child_tidptr;
|
|
|
|
clone_flags = regs.gprs[3];
|
|
newsp = regs.orig_gpr2;
|
|
parent_tidptr = (int __user *) regs.gprs[4];
|
|
child_tidptr = (int __user *) regs.gprs[5];
|
|
if (!newsp)
|
|
newsp = regs.gprs[15];
|
|
return do_fork(clone_flags, newsp, ®s, 0,
|
|
parent_tidptr, child_tidptr);
|
|
}
|
|
|
|
/*
|
|
* This is trivial, and on the face of it looks like it
|
|
* could equally well be done in user mode.
|
|
*
|
|
* Not so, for quite unobvious reasons - register pressure.
|
|
* In user mode vfork() cannot have a stack frame, and if
|
|
* done by calling the "clone()" system call directly, you
|
|
* do not have enough call-clobbered registers to hold all
|
|
* the information you need.
|
|
*/
|
|
asmlinkage long sys_vfork(struct pt_regs regs)
|
|
{
|
|
return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD,
|
|
regs.gprs[15], ®s, 0, NULL, NULL);
|
|
}
|
|
|
|
/*
|
|
* sys_execve() executes a new program.
|
|
*/
|
|
asmlinkage long sys_execve(struct pt_regs regs)
|
|
{
|
|
int error;
|
|
char * filename;
|
|
|
|
filename = getname((char __user *) regs.orig_gpr2);
|
|
error = PTR_ERR(filename);
|
|
if (IS_ERR(filename))
|
|
goto out;
|
|
error = do_execve(filename, (char __user * __user *) regs.gprs[3],
|
|
(char __user * __user *) regs.gprs[4], ®s);
|
|
if (error == 0) {
|
|
task_lock(current);
|
|
current->ptrace &= ~PT_DTRACE;
|
|
task_unlock(current);
|
|
current->thread.fp_regs.fpc = 0;
|
|
if (MACHINE_HAS_IEEE)
|
|
asm volatile("sfpc %0,%0" : : "d" (0));
|
|
}
|
|
putname(filename);
|
|
out:
|
|
return error;
|
|
}
|
|
|
|
|
|
/*
|
|
* fill in the FPU structure for a core dump.
|
|
*/
|
|
int dump_fpu (struct pt_regs * regs, s390_fp_regs *fpregs)
|
|
{
|
|
#ifndef CONFIG_64BIT
|
|
/*
|
|
* save fprs to current->thread.fp_regs to merge them with
|
|
* the emulated registers and then copy the result to the dump.
|
|
*/
|
|
save_fp_regs(¤t->thread.fp_regs);
|
|
memcpy(fpregs, ¤t->thread.fp_regs, sizeof(s390_fp_regs));
|
|
#else /* CONFIG_64BIT */
|
|
save_fp_regs(fpregs);
|
|
#endif /* CONFIG_64BIT */
|
|
return 1;
|
|
}
|
|
|
|
unsigned long get_wchan(struct task_struct *p)
|
|
{
|
|
struct stack_frame *sf, *low, *high;
|
|
unsigned long return_address;
|
|
int count;
|
|
|
|
if (!p || p == current || p->state == TASK_RUNNING || !task_stack_page(p))
|
|
return 0;
|
|
low = task_stack_page(p);
|
|
high = (struct stack_frame *) task_pt_regs(p);
|
|
sf = (struct stack_frame *) (p->thread.ksp & PSW_ADDR_INSN);
|
|
if (sf <= low || sf > high)
|
|
return 0;
|
|
for (count = 0; count < 16; count++) {
|
|
sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN);
|
|
if (sf <= low || sf > high)
|
|
return 0;
|
|
return_address = sf->gprs[8] & PSW_ADDR_INSN;
|
|
if (!in_sched_functions(return_address))
|
|
return return_address;
|
|
}
|
|
return 0;
|
|
}
|
|
|