2005-04-16 18:20:36 -04:00
|
|
|
/*
|
|
|
|
* linux/arch/arm26/mm/fault.c
|
|
|
|
*
|
|
|
|
* Copyright (C) 1995 Linus Torvalds
|
|
|
|
* Modifications for ARM processor (c) 1995-2001 Russell King
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
|
|
* published by the Free Software Foundation.
|
|
|
|
*/
|
|
|
|
#include <linux/signal.h>
|
|
|
|
#include <linux/sched.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/interrupt.h>
|
|
|
|
#include <linux/proc_fs.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
|
|
|
|
#include <asm/system.h>
|
|
|
|
#include <asm/pgtable.h>
|
|
|
|
#include <asm/uaccess.h> //FIXME this header may be bogusly included
|
|
|
|
|
|
|
|
#include "fault.h"
|
|
|
|
|
|
|
|
#define FAULT_CODE_LDRSTRPOST 0x80
|
|
|
|
#define FAULT_CODE_LDRSTRPRE 0x40
|
|
|
|
#define FAULT_CODE_LDRSTRREG 0x20
|
|
|
|
#define FAULT_CODE_LDMSTM 0x10
|
|
|
|
#define FAULT_CODE_LDCSTC 0x08
|
|
|
|
#define FAULT_CODE_PREFETCH 0x04
|
|
|
|
#define FAULT_CODE_WRITE 0x02
|
|
|
|
#define FAULT_CODE_FORCECOW 0x01
|
|
|
|
|
|
|
|
#define DO_COW(m) ((m) & (FAULT_CODE_WRITE|FAULT_CODE_FORCECOW))
|
|
|
|
#define READ_FAULT(m) (!((m) & FAULT_CODE_WRITE))
|
|
|
|
#define DEBUG
|
|
|
|
/*
|
|
|
|
* This is useful to dump out the page tables associated with
|
|
|
|
* 'addr' in mm 'mm'.
|
|
|
|
*/
|
|
|
|
void show_pte(struct mm_struct *mm, unsigned long addr)
|
|
|
|
{
|
|
|
|
pgd_t *pgd;
|
|
|
|
|
|
|
|
if (!mm)
|
|
|
|
mm = &init_mm;
|
|
|
|
|
|
|
|
printk(KERN_ALERT "pgd = %p\n", mm->pgd);
|
|
|
|
pgd = pgd_offset(mm, addr);
|
|
|
|
printk(KERN_ALERT "[%08lx] *pgd=%08lx", addr, pgd_val(*pgd));
|
|
|
|
|
|
|
|
do {
|
|
|
|
pmd_t *pmd;
|
|
|
|
pte_t *pte;
|
|
|
|
|
|
|
|
pmd = pmd_offset(pgd, addr);
|
|
|
|
|
|
|
|
if (pmd_none(*pmd))
|
|
|
|
break;
|
|
|
|
|
|
|
|
if (pmd_bad(*pmd)) {
|
|
|
|
printk("(bad)");
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* We must not map this if we have highmem enabled */
|
|
|
|
/* FIXME */
|
|
|
|
pte = pte_offset_map(pmd, addr);
|
|
|
|
printk(", *pte=%08lx", pte_val(*pte));
|
|
|
|
pte_unmap(pte);
|
|
|
|
} while(0);
|
|
|
|
|
|
|
|
printk("\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Oops. The kernel tried to access some page that wasn't present.
|
|
|
|
*/
|
|
|
|
static void
|
|
|
|
__do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
|
|
|
|
struct pt_regs *regs)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Are we prepared to handle this kernel fault?
|
|
|
|
*/
|
|
|
|
if (fixup_exception(regs))
|
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* No handler, we'll have to terminate things with extreme prejudice.
|
|
|
|
*/
|
|
|
|
bust_spinlocks(1);
|
|
|
|
printk(KERN_ALERT
|
|
|
|
"Unable to handle kernel %s at virtual address %08lx\n",
|
|
|
|
(addr < PAGE_SIZE) ? "NULL pointer dereference" :
|
|
|
|
"paging request", addr);
|
|
|
|
|
|
|
|
show_pte(mm, addr);
|
|
|
|
die("Oops", regs, fsr);
|
|
|
|
bust_spinlocks(0);
|
|
|
|
do_exit(SIGKILL);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Something tried to access memory that isn't in our memory map..
|
|
|
|
* User mode accesses just cause a SIGSEGV
|
|
|
|
*/
|
|
|
|
static void
|
|
|
|
__do_user_fault(struct task_struct *tsk, unsigned long addr,
|
|
|
|
unsigned int fsr, int code, struct pt_regs *regs)
|
|
|
|
{
|
|
|
|
struct siginfo si;
|
|
|
|
|
|
|
|
#ifdef CONFIG_DEBUG_USER
|
|
|
|
printk("%s: unhandled page fault at 0x%08lx, code 0x%03x\n",
|
|
|
|
tsk->comm, addr, fsr);
|
|
|
|
show_pte(tsk->mm, addr);
|
|
|
|
show_regs(regs);
|
|
|
|
//dump_backtrace(regs, tsk); // FIXME ARM32 dropped this - why?
|
|
|
|
while(1); //FIXME - hack to stop debug going nutso
|
|
|
|
#endif
|
|
|
|
|
|
|
|
tsk->thread.address = addr;
|
|
|
|
tsk->thread.error_code = fsr;
|
|
|
|
tsk->thread.trap_no = 14;
|
|
|
|
si.si_signo = SIGSEGV;
|
|
|
|
si.si_errno = 0;
|
|
|
|
si.si_code = code;
|
|
|
|
si.si_addr = (void *)addr;
|
|
|
|
force_sig_info(SIGSEGV, &si, tsk);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
|
|
|
__do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
|
|
|
|
struct task_struct *tsk)
|
|
|
|
{
|
|
|
|
struct vm_area_struct *vma;
|
|
|
|
int fault, mask;
|
|
|
|
|
|
|
|
vma = find_vma(mm, addr);
|
|
|
|
fault = -2; /* bad map area */
|
|
|
|
if (!vma)
|
|
|
|
goto out;
|
|
|
|
if (vma->vm_start > addr)
|
|
|
|
goto check_stack;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Ok, we have a good vm_area for this
|
|
|
|
* memory access, so we can handle it.
|
|
|
|
*/
|
|
|
|
good_area:
|
|
|
|
if (READ_FAULT(fsr)) /* read? */
|
[PATCH] make PROT_WRITE imply PROT_READ
Make PROT_WRITE imply PROT_READ for a number of architectures which don't
support write only in hardware.
While looking at this, I noticed that some architectures which do not
support write only mappings already take the exact same approach. For
example, in arch/alpha/mm/fault.c:
"
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;
}
"
Thus, this patch brings other architectures which do not support write only
mappings in-line and consistent with the rest. I've verified the patch on
ia64, x86_64 and x86.
Additional discussion:
Several architectures, including x86, can not support write-only mappings.
The pte for x86 reserves a single bit for protection and its two states are
read only or read/write. Thus, write only is not supported in h/w.
Currently, if i 'mmap' a page write-only, the first read attempt on that page
creates a page fault and will SEGV. That check is enforced in
arch/blah/mm/fault.c. However, if i first write that page it will fault in
and the pte will be set to read/write. Thus, any subsequent reads to the page
will succeed. It is this inconsistency in behavior that this patch is
attempting to address. Furthermore, if the page is swapped out, and then
brought back the first read will also cause a SEGV. Thus, any arbitrary read
on a page can potentially result in a SEGV.
According to the SuSv3 spec, "if the application requests only PROT_WRITE, the
implementation may also allow read access." Also as mentioned, some
archtectures, such as alpha, shown above already take the approach that i am
suggesting.
The counter-argument to this raised by Arjan, is that the kernel is enforcing
the write only mapping the best it can given the h/w limitations. This is
true, however Alan Cox, and myself would argue that the inconsitency in
behavior, that is applications can sometimes work/sometimes fails is highly
undesireable. If you read through the thread, i think people, came to an
agreement on the last patch i posted, as nobody has objected to it...
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Roman Zippel <zippel@linux-m68k.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Andi Kleen <ak@muc.de>
Acked-by: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: Paul Mundt <lethal@linux-sh.org>
Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp>
Cc: Ian Molton <spyro@f2s.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-29 04:58:58 -04:00
|
|
|
mask = VM_READ|VM_EXEC|VM_WRITE;
|
2005-04-16 18:20:36 -04:00
|
|
|
else
|
|
|
|
mask = VM_WRITE;
|
|
|
|
|
|
|
|
fault = -1; /* bad access type */
|
|
|
|
if (!(vma->vm_flags & mask))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If for any reason at all we couldn't handle
|
|
|
|
* the fault, make sure we exit gracefully rather
|
|
|
|
* than endlessly redo the fault.
|
|
|
|
*/
|
|
|
|
survive:
|
|
|
|
fault = handle_mm_fault(mm, vma, addr & PAGE_MASK, DO_COW(fsr));
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Handle the "normal" cases first - successful and sigbus
|
|
|
|
*/
|
|
|
|
switch (fault) {
|
2005-08-04 11:33:38 -04:00
|
|
|
case VM_FAULT_MAJOR:
|
2005-04-16 18:20:36 -04:00
|
|
|
tsk->maj_flt++;
|
|
|
|
return fault;
|
2005-08-04 11:33:38 -04:00
|
|
|
case VM_FAULT_MINOR:
|
2005-04-16 18:20:36 -04:00
|
|
|
tsk->min_flt++;
|
2005-08-04 11:33:38 -04:00
|
|
|
case VM_FAULT_SIGBUS:
|
2005-04-16 18:20:36 -04:00
|
|
|
return fault;
|
|
|
|
}
|
|
|
|
|
|
|
|
fault = -3; /* out of memory */
|
2006-09-29 05:00:07 -04:00
|
|
|
if (!is_init(tsk))
|
2005-04-16 18:20:36 -04:00
|
|
|
goto out;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If we are out of memory for pid1,
|
|
|
|
* sleep for a while and retry
|
|
|
|
*/
|
|
|
|
yield();
|
|
|
|
goto survive;
|
|
|
|
|
|
|
|
check_stack:
|
|
|
|
if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
|
|
|
|
goto good_area;
|
|
|
|
out:
|
|
|
|
return fault;
|
|
|
|
}
|
|
|
|
|
|
|
|
int do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
|
|
|
|
{
|
|
|
|
struct task_struct *tsk;
|
|
|
|
struct mm_struct *mm;
|
|
|
|
int fault;
|
|
|
|
|
|
|
|
tsk = current;
|
|
|
|
mm = tsk->mm;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If we're in an interrupt or have no user
|
|
|
|
* context, we must not take the fault..
|
|
|
|
*/
|
2006-12-06 23:32:18 -05:00
|
|
|
if (in_atomic() || !mm)
|
2005-04-16 18:20:36 -04:00
|
|
|
goto no_context;
|
|
|
|
|
|
|
|
down_read(&mm->mmap_sem);
|
|
|
|
fault = __do_page_fault(mm, addr, fsr, tsk);
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Handle the "normal" case first
|
|
|
|
*/
|
2005-08-04 11:33:38 -04:00
|
|
|
switch (fault) {
|
|
|
|
case VM_FAULT_MINOR:
|
|
|
|
case VM_FAULT_MAJOR:
|
2005-04-16 18:20:36 -04:00
|
|
|
return 0;
|
2005-08-04 11:33:38 -04:00
|
|
|
case VM_FAULT_SIGBUS:
|
2005-04-16 18:20:36 -04:00
|
|
|
goto do_sigbus;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If we are in kernel mode at this point, we
|
|
|
|
* have no context to handle this fault with.
|
|
|
|
* FIXME - is this test right?
|
|
|
|
*/
|
|
|
|
if (!user_mode(regs)){
|
|
|
|
goto no_context;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (fault == -3) {
|
|
|
|
/*
|
|
|
|
* We ran out of memory, or some other thing happened to
|
|
|
|
* us that made us unable to handle the page fault gracefully.
|
|
|
|
*/
|
|
|
|
printk("VM: killing process %s\n", tsk->comm);
|
|
|
|
do_exit(SIGKILL);
|
|
|
|
}
|
|
|
|
else{
|
|
|
|
__do_user_fault(tsk, addr, fsr, fault == -1 ? SEGV_ACCERR : SEGV_MAPERR, regs);
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We ran out of memory, or some other thing happened to us that made
|
|
|
|
* us unable to handle the page fault gracefully.
|
|
|
|
*/
|
|
|
|
do_sigbus:
|
|
|
|
/*
|
|
|
|
* Send a sigbus, regardless of whether we were in kernel
|
|
|
|
* or user mode.
|
|
|
|
*/
|
|
|
|
tsk->thread.address = addr; //FIXME - need other bits setting?
|
|
|
|
tsk->thread.error_code = fsr;
|
|
|
|
tsk->thread.trap_no = 14;
|
|
|
|
force_sig(SIGBUS, tsk);
|
|
|
|
#ifdef CONFIG_DEBUG_USER
|
|
|
|
printk(KERN_DEBUG "%s: sigbus at 0x%08lx, pc=0x%08lx\n",
|
|
|
|
current->comm, addr, instruction_pointer(regs));
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* Kernel mode? Handle exceptions or die */
|
|
|
|
if (user_mode(regs))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
no_context:
|
|
|
|
__do_kernel_fault(mm, addr, fsr, regs);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Handle a data abort. Note that we have to handle a range of addresses
|
|
|
|
* on ARM2/3 for ldm. If both pages are zero-mapped, then we have to force
|
|
|
|
* a copy-on-write. However, on the second page, we always force COW.
|
|
|
|
*/
|
|
|
|
asmlinkage void
|
|
|
|
do_DataAbort(unsigned long min_addr, unsigned long max_addr, int mode, struct pt_regs *regs)
|
|
|
|
{
|
|
|
|
do_page_fault(min_addr, mode, regs);
|
|
|
|
|
|
|
|
if ((min_addr ^ max_addr) >> PAGE_SHIFT){
|
|
|
|
do_page_fault(max_addr, mode | FAULT_CODE_FORCECOW, regs);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
asmlinkage int
|
|
|
|
do_PrefetchAbort(unsigned long addr, struct pt_regs *regs)
|
|
|
|
{
|
|
|
|
#if 0
|
|
|
|
if (the memc mapping for this page exists) {
|
|
|
|
printk ("Page in, but got abort (undefined instruction?)\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
do_page_fault(addr, FAULT_CODE_PREFETCH, regs);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|