![Serge E. Hallyn](/assets/img/avatar_default.png)
is_init() is an ambiguous name for the pid==1 check. Split it into is_global_init() and is_container_init(). A cgroup init has it's tsk->pid == 1. A global init also has it's tsk->pid == 1 and it's active pid namespace is the init_pid_ns. But rather than check the active pid namespace, compare the task structure with 'init_pid_ns.child_reaper', which is initialized during boot to the /sbin/init process and never changes. Changelog: 2.6.22-rc4-mm2-pidns1: - Use 'init_pid_ns.child_reaper' to determine if a given task is the global init (/sbin/init) process. This would improve performance and remove dependence on the task_pid(). 2.6.21-mm2-pidns2: - [Sukadev Bhattiprolu] Changed is_container_init() calls in {powerpc, ppc,avr32}/traps.c for the _exception() call to is_global_init(). This way, we kill only the cgroup if the cgroup's init has a bug rather than force a kernel panic. [akpm@linux-foundation.org: fix comment] [sukadev@us.ibm.com: Use is_global_init() in arch/m32r/mm/fault.c] [bunk@stusta.de: kernel/pid.c: remove unused exports] [sukadev@us.ibm.com: Fix capability.c to work with threaded init] Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com> Acked-by: Pavel Emelianov <xemul@openvz.org> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Herbert Poetzel <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
253 lines
6.3 KiB
C
253 lines
6.3 KiB
C
/*
|
|
* This file is subject to the terms and conditions of the GNU General Public
|
|
* License. See the file "COPYING" in the main directory of this archive
|
|
* for more details.
|
|
*
|
|
* Copyright (C) 1995 - 2000 by Ralf Baechle
|
|
*/
|
|
#include <linux/signal.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/string.h>
|
|
#include <linux/types.h>
|
|
#include <linux/ptrace.h>
|
|
#include <linux/mman.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/vt_kern.h> /* For unblank_screen() */
|
|
#include <linux/module.h>
|
|
|
|
#include <asm/branch.h>
|
|
#include <asm/mmu_context.h>
|
|
#include <asm/system.h>
|
|
#include <asm/uaccess.h>
|
|
#include <asm/ptrace.h>
|
|
#include <asm/highmem.h> /* For VMALLOC_END */
|
|
|
|
/*
|
|
* This routine handles page faults. It determines the address,
|
|
* and the problem, and then passes it off to one of the appropriate
|
|
* routines.
|
|
*/
|
|
asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
|
|
unsigned long address)
|
|
{
|
|
struct vm_area_struct * vma = NULL;
|
|
struct task_struct *tsk = current;
|
|
struct mm_struct *mm = tsk->mm;
|
|
const int field = sizeof(unsigned long) * 2;
|
|
siginfo_t info;
|
|
int fault;
|
|
|
|
#if 0
|
|
printk("Cpu%d[%s:%d:%0*lx:%ld:%0*lx]\n", raw_smp_processor_id(),
|
|
current->comm, current->pid, field, address, write,
|
|
field, regs->cp0_epc);
|
|
#endif
|
|
|
|
info.si_code = SEGV_MAPERR;
|
|
|
|
/*
|
|
* We fault-in kernel-space virtual memory on-demand. The
|
|
* 'reference' page table is init_mm.pgd.
|
|
*
|
|
* NOTE! We MUST NOT take any locks for this case. We may
|
|
* be in an interrupt or a critical region, and should
|
|
* only copy the information from the master page table,
|
|
* nothing more.
|
|
*/
|
|
if (unlikely(address >= VMALLOC_START && address <= VMALLOC_END))
|
|
goto vmalloc_fault;
|
|
#ifdef MODULE_START
|
|
if (unlikely(address >= MODULE_START && address < MODULE_END))
|
|
goto vmalloc_fault;
|
|
#endif
|
|
|
|
/*
|
|
* If we're in an interrupt or have no user
|
|
* context, we must not take the fault..
|
|
*/
|
|
if (in_atomic() || !mm)
|
|
goto bad_area_nosemaphore;
|
|
|
|
down_read(&mm->mmap_sem);
|
|
vma = find_vma(mm, address);
|
|
if (!vma)
|
|
goto bad_area;
|
|
if (vma->vm_start <= address)
|
|
goto good_area;
|
|
if (!(vma->vm_flags & VM_GROWSDOWN))
|
|
goto bad_area;
|
|
if (expand_stack(vma, address))
|
|
goto bad_area;
|
|
/*
|
|
* Ok, we have a good vm_area for this memory access, so
|
|
* we can handle it..
|
|
*/
|
|
good_area:
|
|
info.si_code = SEGV_ACCERR;
|
|
|
|
if (write) {
|
|
if (!(vma->vm_flags & VM_WRITE))
|
|
goto bad_area;
|
|
} else {
|
|
if (!(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)))
|
|
goto bad_area;
|
|
}
|
|
|
|
survive:
|
|
/*
|
|
* If for any reason at all we couldn't handle the fault,
|
|
* make sure we exit gracefully rather than endlessly redo
|
|
* the fault.
|
|
*/
|
|
fault = handle_mm_fault(mm, vma, address, write);
|
|
if (unlikely(fault & VM_FAULT_ERROR)) {
|
|
if (fault & VM_FAULT_OOM)
|
|
goto out_of_memory;
|
|
else if (fault & VM_FAULT_SIGBUS)
|
|
goto do_sigbus;
|
|
BUG();
|
|
}
|
|
if (fault & VM_FAULT_MAJOR)
|
|
tsk->maj_flt++;
|
|
else
|
|
tsk->min_flt++;
|
|
|
|
up_read(&mm->mmap_sem);
|
|
return;
|
|
|
|
/*
|
|
* Something tried to access memory that isn't in our memory map..
|
|
* Fix it, but check if it's kernel or user first..
|
|
*/
|
|
bad_area:
|
|
up_read(&mm->mmap_sem);
|
|
|
|
bad_area_nosemaphore:
|
|
/* User mode accesses just cause a SIGSEGV */
|
|
if (user_mode(regs)) {
|
|
tsk->thread.cp0_badvaddr = address;
|
|
tsk->thread.error_code = write;
|
|
#if 0
|
|
printk("do_page_fault() #2: sending SIGSEGV to %s for "
|
|
"invalid %s\n%0*lx (epc == %0*lx, ra == %0*lx)\n",
|
|
tsk->comm,
|
|
write ? "write access to" : "read access from",
|
|
field, address,
|
|
field, (unsigned long) regs->cp0_epc,
|
|
field, (unsigned long) regs->regs[31]);
|
|
#endif
|
|
info.si_signo = SIGSEGV;
|
|
info.si_errno = 0;
|
|
/* info.si_code has been set above */
|
|
info.si_addr = (void __user *) address;
|
|
force_sig_info(SIGSEGV, &info, tsk);
|
|
return;
|
|
}
|
|
|
|
no_context:
|
|
/* Are we prepared to handle this kernel fault? */
|
|
if (fixup_exception(regs)) {
|
|
current->thread.cp0_baduaddr = address;
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* Oops. The kernel tried to access some bad page. We'll have to
|
|
* terminate things with extreme prejudice.
|
|
*/
|
|
bust_spinlocks(1);
|
|
|
|
printk(KERN_ALERT "CPU %d Unable to handle kernel paging request at "
|
|
"virtual address %0*lx, epc == %0*lx, ra == %0*lx\n",
|
|
raw_smp_processor_id(), field, address, field, regs->cp0_epc,
|
|
field, regs->regs[31]);
|
|
die("Oops", regs);
|
|
|
|
/*
|
|
* We ran out of memory, or some other thing happened to us that made
|
|
* us unable to handle the page fault gracefully.
|
|
*/
|
|
out_of_memory:
|
|
up_read(&mm->mmap_sem);
|
|
if (is_global_init(tsk)) {
|
|
yield();
|
|
down_read(&mm->mmap_sem);
|
|
goto survive;
|
|
}
|
|
printk("VM: killing process %s\n", tsk->comm);
|
|
if (user_mode(regs))
|
|
do_group_exit(SIGKILL);
|
|
goto no_context;
|
|
|
|
do_sigbus:
|
|
up_read(&mm->mmap_sem);
|
|
|
|
/* Kernel mode? Handle exceptions or die */
|
|
if (!user_mode(regs))
|
|
goto no_context;
|
|
else
|
|
/*
|
|
* Send a sigbus, regardless of whether we were in kernel
|
|
* or user mode.
|
|
*/
|
|
#if 0
|
|
printk("do_page_fault() #3: sending SIGBUS to %s for "
|
|
"invalid %s\n%0*lx (epc == %0*lx, ra == %0*lx)\n",
|
|
tsk->comm,
|
|
write ? "write access to" : "read access from",
|
|
field, address,
|
|
field, (unsigned long) regs->cp0_epc,
|
|
field, (unsigned long) regs->regs[31]);
|
|
#endif
|
|
tsk->thread.cp0_badvaddr = address;
|
|
info.si_signo = SIGBUS;
|
|
info.si_errno = 0;
|
|
info.si_code = BUS_ADRERR;
|
|
info.si_addr = (void __user *) address;
|
|
force_sig_info(SIGBUS, &info, tsk);
|
|
|
|
return;
|
|
vmalloc_fault:
|
|
{
|
|
/*
|
|
* Synchronize this task's top level page-table
|
|
* with the 'reference' page table.
|
|
*
|
|
* Do _not_ use "tsk" here. We might be inside
|
|
* an interrupt in the middle of a task switch..
|
|
*/
|
|
int offset = __pgd_offset(address);
|
|
pgd_t *pgd, *pgd_k;
|
|
pud_t *pud, *pud_k;
|
|
pmd_t *pmd, *pmd_k;
|
|
pte_t *pte_k;
|
|
|
|
pgd = (pgd_t *) pgd_current[raw_smp_processor_id()] + offset;
|
|
pgd_k = init_mm.pgd + offset;
|
|
|
|
if (!pgd_present(*pgd_k))
|
|
goto no_context;
|
|
set_pgd(pgd, *pgd_k);
|
|
|
|
pud = pud_offset(pgd, address);
|
|
pud_k = pud_offset(pgd_k, address);
|
|
if (!pud_present(*pud_k))
|
|
goto no_context;
|
|
|
|
pmd = pmd_offset(pud, address);
|
|
pmd_k = pmd_offset(pud_k, address);
|
|
if (!pmd_present(*pmd_k))
|
|
goto no_context;
|
|
set_pmd(pmd, *pmd_k);
|
|
|
|
pte_k = pte_offset_kernel(pmd_k, address);
|
|
if (!pte_present(*pte_k))
|
|
goto no_context;
|
|
return;
|
|
}
|
|
}
|