Archived
14
0
Fork 0
This repository has been archived on 2022-02-17. You can view files and clone it, but cannot push or open issues or pull requests.
linux-2.6/arch/alpha/mm/fault.c
Sukadev Bhattiprolu f400e198b2 [PATCH] pidspace: is_init()
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>
2006-09-29 09:18:12 -07:00

247 lines
5.9 KiB
C

/*
* linux/arch/alpha/mm/fault.c
*
* Copyright (C) 1995 Linus Torvalds
*/
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <asm/io.h>
#define __EXTERN_INLINE inline
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
#undef __EXTERN_INLINE
#include <linux/signal.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/smp.h>
#include <linux/smp_lock.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <asm/system.h>
#include <asm/uaccess.h>
extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *);
/*
* Force a new ASN for a task.
*/
#ifndef CONFIG_SMP
unsigned long last_asn = ASN_FIRST_VERSION;
#endif
void
__load_new_mm_context(struct mm_struct *next_mm)
{
unsigned long mmc;
struct pcb_struct *pcb;
mmc = __get_new_mm_context(next_mm, smp_processor_id());
next_mm->context[smp_processor_id()] = mmc;
pcb = &current_thread_info()->pcb;
pcb->asn = mmc & HARDWARE_ASN_MASK;
pcb->ptbr = ((unsigned long) next_mm->pgd - IDENT_ADDR) >> PAGE_SHIFT;
__reload_thread(pcb);
}
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to handle_mm_fault().
*
* mmcsr:
* 0 = translation not valid
* 1 = access violation
* 2 = fault-on-read
* 3 = fault-on-execute
* 4 = fault-on-write
*
* cause:
* -1 = instruction fetch
* 0 = load
* 1 = store
*
* Registers $9 through $15 are saved in a block just prior to `regs' and
* are saved and restored around the call to allow exception code to
* modify them.
*/
/* Macro for exception fixup code to access integer registers. */
#define dpf_reg(r) \
(((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-16 : \
(r) <= 18 ? (r)+8 : (r)-10])
asmlinkage void
do_page_fault(unsigned long address, unsigned long mmcsr,
long cause, struct pt_regs *regs)
{
struct vm_area_struct * vma;
struct mm_struct *mm = current->mm;
const struct exception_table_entry *fixup;
int fault, si_code = SEGV_MAPERR;
siginfo_t info;
/* As of EV6, a load into $31/$f31 is a prefetch, and never faults
(or is suppressed by the PALcode). Support that for older CPUs
by ignoring such an instruction. */
if (cause == 0) {
unsigned int insn;
__get_user(insn, (unsigned int __user *)regs->pc);
if ((insn >> 21 & 0x1f) == 0x1f &&
/* ldq ldl ldt lds ldg ldf ldwu ldbu */
(1ul << (insn >> 26) & 0x30f00001400ul)) {
regs->pc += 4;
return;
}
}
/* If we're in an interrupt context, or have no user context,
we must not take the fault. */
if (!mm || in_interrupt())
goto no_context;
#ifdef CONFIG_ALPHA_LARGE_VMALLOC
if (address >= TASK_SIZE)
goto vmalloc_fault;
#endif
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:
si_code = SEGV_ACCERR;
if (cause < 0) {
if (!(vma->vm_flags & VM_EXEC))
goto bad_area;
} else if (!cause) {
/* Allow reads even for write-only mappings */
if (!(vma->vm_flags & (VM_READ | VM_WRITE)))
goto bad_area;
} else {
if (!(vma->vm_flags & VM_WRITE))
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, cause > 0);
up_read(&mm->mmap_sem);
switch (fault) {
case VM_FAULT_MINOR:
current->min_flt++;
break;
case VM_FAULT_MAJOR:
current->maj_flt++;
break;
case VM_FAULT_SIGBUS:
goto do_sigbus;
case VM_FAULT_OOM:
goto out_of_memory;
default:
BUG();
}
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);
if (user_mode(regs))
goto do_sigsegv;
no_context:
/* Are we prepared to handle this fault as an exception? */
if ((fixup = search_exception_tables(regs->pc)) != 0) {
unsigned long newpc;
newpc = fixup_exception(dpf_reg, fixup, regs->pc);
regs->pc = newpc;
return;
}
/* Oops. The kernel tried to access some bad page. We'll have to
terminate things with extreme prejudice. */
printk(KERN_ALERT "Unable to handle kernel paging request at "
"virtual address %016lx\n", address);
die_if_kernel("Oops", regs, cause, (unsigned long*)regs - 16);
do_exit(SIGKILL);
/* 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:
if (is_init(current)) {
yield();
down_read(&mm->mmap_sem);
goto survive;
}
printk(KERN_ALERT "VM: killing process %s(%d)\n",
current->comm, current->pid);
if (!user_mode(regs))
goto no_context;
do_exit(SIGKILL);
do_sigbus:
/* Send a sigbus, regardless of whether we were in kernel
or user mode. */
info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_ADRERR;
info.si_addr = (void __user *) address;
force_sig_info(SIGBUS, &info, current);
if (!user_mode(regs))
goto no_context;
return;
do_sigsegv:
info.si_signo = SIGSEGV;
info.si_errno = 0;
info.si_code = si_code;
info.si_addr = (void __user *) address;
force_sig_info(SIGSEGV, &info, current);
return;
#ifdef CONFIG_ALPHA_LARGE_VMALLOC
vmalloc_fault:
if (user_mode(regs))
goto do_sigsegv;
else {
/* Synchronize this task's top level page-table
with the "reference" page table from init. */
long index = pgd_index(address);
pgd_t *pgd, *pgd_k;
pgd = current->active_mm->pgd + index;
pgd_k = swapper_pg_dir + index;
if (!pgd_present(*pgd) && pgd_present(*pgd_k)) {
pgd_val(*pgd) = pgd_val(*pgd_k);
return;
}
goto no_context;
}
#endif
}