mirror of
https://github.com/torvalds/linux
synced 2024-11-05 18:23:50 +00:00
f400e198b2
This is an updated version of Eric Biederman's is_init() patch. (http://lkml.org/lkml/2006/2/6/280). It applies cleanly to 2.6.18-rc3 and replaces a few more instances of ->pid == 1 with is_init(). Further, is_init() checks pid and thus removes dependency on Eric's other patches for now. Eric's original description: There are a lot of places in the kernel where we test for init because we give it special properties. Most significantly init must not die. This results in code all over the kernel test ->pid == 1. Introduce is_init to capture this case. With multiple pid spaces for all of the cases affected we are looking for only the first process on the system, not some other process that has pid == 1. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Serge Hallyn <serue@us.ibm.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Cc: <lxc-devel@lists.sourceforge.net> Acked-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
250 lines
6.1 KiB
C
250 lines
6.1 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/smp_lock.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;
|
|
|
|
#if 0
|
|
printk("Cpu%d[%s:%d:%0*lx:%ld:%0*lx]\n", 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;
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
switch (handle_mm_fault(mm, vma, address, write)) {
|
|
case VM_FAULT_MINOR:
|
|
tsk->min_flt++;
|
|
break;
|
|
case VM_FAULT_MAJOR:
|
|
tsk->maj_flt++;
|
|
break;
|
|
case VM_FAULT_SIGBUS:
|
|
goto do_sigbus;
|
|
case VM_FAULT_OOM:
|
|
goto out_of_memory;
|
|
default:
|
|
BUG();
|
|
}
|
|
|
|
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",
|
|
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_init(tsk)) {
|
|
yield();
|
|
down_read(&mm->mmap_sem);
|
|
goto survive;
|
|
}
|
|
printk("VM: killing process %s\n", tsk->comm);
|
|
if (user_mode(regs))
|
|
do_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[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;
|
|
}
|
|
}
|