2005-04-17 02:20:36 +04:00
|
|
|
/*
|
|
|
|
* linux/arch/m68k/mm/fault.c
|
|
|
|
*
|
|
|
|
* Copyright (C) 1995 Hamish Macdonald
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/mman.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/ptrace.h>
|
|
|
|
#include <linux/interrupt.h>
|
|
|
|
#include <linux/module.h>
|
|
|
|
|
|
|
|
#include <asm/setup.h>
|
|
|
|
#include <asm/traps.h>
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
#include <asm/pgalloc.h>
|
|
|
|
|
|
|
|
extern void die_if_kernel(char *, struct pt_regs *, long);
|
|
|
|
|
|
|
|
int send_fault_sig(struct pt_regs *regs)
|
|
|
|
{
|
|
|
|
siginfo_t siginfo = { 0, 0, 0, };
|
|
|
|
|
|
|
|
siginfo.si_signo = current->thread.signo;
|
|
|
|
siginfo.si_code = current->thread.code;
|
|
|
|
siginfo.si_addr = (void *)current->thread.faddr;
|
|
|
|
#ifdef DEBUG
|
|
|
|
printk("send_fault_sig: %p,%d,%d\n", siginfo.si_addr, siginfo.si_signo, siginfo.si_code);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
if (user_mode(regs)) {
|
|
|
|
force_sig_info(siginfo.si_signo,
|
|
|
|
&siginfo, current);
|
|
|
|
} else {
|
2008-11-18 23:25:17 +03:00
|
|
|
if (handle_kernel_fault(regs))
|
2005-04-17 02:20:36 +04:00
|
|
|
return -1;
|
|
|
|
|
|
|
|
//if (siginfo.si_signo == SIGBUS)
|
|
|
|
// force_sig_info(siginfo.si_signo,
|
|
|
|
// &siginfo, current);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Oops. The kernel tried to access some bad page. We'll have to
|
|
|
|
* terminate things with extreme prejudice.
|
|
|
|
*/
|
|
|
|
if ((unsigned long)siginfo.si_addr < PAGE_SIZE)
|
|
|
|
printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference");
|
|
|
|
else
|
|
|
|
printk(KERN_ALERT "Unable to handle kernel access");
|
|
|
|
printk(" at virtual address %p\n", siginfo.si_addr);
|
|
|
|
die_if_kernel("Oops", regs, 0 /*error_code*/);
|
|
|
|
do_exit(SIGKILL);
|
|
|
|
}
|
|
|
|
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This routine handles page faults. It determines the problem, and
|
|
|
|
* then passes it off to one of the appropriate routines.
|
|
|
|
*
|
|
|
|
* error_code:
|
|
|
|
* bit 0 == 0 means no page found, 1 means protection fault
|
|
|
|
* bit 1 == 0 means read, 1 means write
|
|
|
|
*
|
|
|
|
* If this routine detects a bad access, it returns 1, otherwise it
|
|
|
|
* returns 0.
|
|
|
|
*/
|
|
|
|
int do_page_fault(struct pt_regs *regs, unsigned long address,
|
|
|
|
unsigned long error_code)
|
|
|
|
{
|
|
|
|
struct mm_struct *mm = current->mm;
|
|
|
|
struct vm_area_struct * vma;
|
2012-03-25 14:37:48 +04:00
|
|
|
int fault;
|
|
|
|
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
#ifdef DEBUG
|
|
|
|
printk ("do page fault:\nregs->sr=%#x, regs->pc=%#lx, address=%#lx, %ld, %p\n",
|
|
|
|
regs->sr, regs->pc, address, error_code,
|
|
|
|
current->mm->pgd);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If we're in an interrupt or have no user
|
|
|
|
* context, we must not take the fault..
|
|
|
|
*/
|
2006-12-07 07:32:18 +03:00
|
|
|
if (in_atomic() || !mm)
|
2005-04-17 02:20:36 +04:00
|
|
|
goto no_context;
|
|
|
|
|
2012-03-25 14:37:48 +04:00
|
|
|
retry:
|
2005-04-17 02:20:36 +04:00
|
|
|
down_read(&mm->mmap_sem);
|
|
|
|
|
|
|
|
vma = find_vma(mm, address);
|
|
|
|
if (!vma)
|
|
|
|
goto map_err;
|
|
|
|
if (vma->vm_flags & VM_IO)
|
|
|
|
goto acc_err;
|
|
|
|
if (vma->vm_start <= address)
|
|
|
|
goto good_area;
|
|
|
|
if (!(vma->vm_flags & VM_GROWSDOWN))
|
|
|
|
goto map_err;
|
|
|
|
if (user_mode(regs)) {
|
|
|
|
/* Accessing the stack below usp is always a bug. The
|
|
|
|
"+ 256" is there due to some instructions doing
|
|
|
|
pre-decrement on the stack and that doesn't show up
|
|
|
|
until later. */
|
|
|
|
if (address + 256 < rdusp())
|
|
|
|
goto map_err;
|
|
|
|
}
|
|
|
|
if (expand_stack(vma, address))
|
|
|
|
goto map_err;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Ok, we have a good vm_area for this memory access, so
|
|
|
|
* we can handle it..
|
|
|
|
*/
|
|
|
|
good_area:
|
|
|
|
#ifdef DEBUG
|
|
|
|
printk("do_page_fault: good_area\n");
|
|
|
|
#endif
|
|
|
|
switch (error_code & 3) {
|
|
|
|
default: /* 3: write, present */
|
|
|
|
/* fall through */
|
|
|
|
case 2: /* write, not present */
|
|
|
|
if (!(vma->vm_flags & VM_WRITE))
|
|
|
|
goto acc_err;
|
2012-03-25 14:37:48 +04:00
|
|
|
flags |= FAULT_FLAG_WRITE;
|
2005-04-17 02:20:36 +04:00
|
|
|
break;
|
|
|
|
case 1: /* read, present */
|
|
|
|
goto acc_err;
|
|
|
|
case 0: /* read, not present */
|
[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 12:58:58 +04:00
|
|
|
if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
|
2005-04-17 02:20:36 +04:00
|
|
|
goto acc_err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If for any reason at all we couldn't handle the fault,
|
|
|
|
* make sure we exit gracefully rather than endlessly redo
|
|
|
|
* the fault.
|
|
|
|
*/
|
|
|
|
|
2012-03-25 14:37:48 +04:00
|
|
|
fault = handle_mm_fault(mm, vma, address, flags);
|
2005-04-17 02:20:36 +04:00
|
|
|
#ifdef DEBUG
|
|
|
|
printk("handle_mm_fault returns %d\n",fault);
|
|
|
|
#endif
|
2012-03-25 14:37:48 +04:00
|
|
|
|
|
|
|
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
|
|
|
|
return 0;
|
|
|
|
|
2007-07-19 12:47:05 +04:00
|
|
|
if (unlikely(fault & VM_FAULT_ERROR)) {
|
|
|
|
if (fault & VM_FAULT_OOM)
|
|
|
|
goto out_of_memory;
|
|
|
|
else if (fault & VM_FAULT_SIGBUS)
|
|
|
|
goto bus_err;
|
|
|
|
BUG();
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
2012-03-25 14:37:48 +04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Major/minor page fault accounting is only done on the
|
|
|
|
* initial attempt. If we go through a retry, it is extremely
|
|
|
|
* likely that the page will be found in page cache at that point.
|
|
|
|
*/
|
|
|
|
if (flags & FAULT_FLAG_ALLOW_RETRY) {
|
|
|
|
if (fault & VM_FAULT_MAJOR)
|
|
|
|
current->maj_flt++;
|
|
|
|
else
|
|
|
|
current->min_flt++;
|
|
|
|
if (fault & VM_FAULT_RETRY) {
|
|
|
|
/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
|
|
|
|
* of starvation. */
|
|
|
|
flags &= ~FAULT_FLAG_ALLOW_RETRY;
|
2012-10-09 03:32:19 +04:00
|
|
|
flags |= FAULT_FLAG_TRIED;
|
2012-03-25 14:37:48 +04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* No need to up_read(&mm->mmap_sem) as we would
|
|
|
|
* have already released it in __lock_page_or_retry
|
|
|
|
* in mm/filemap.c.
|
|
|
|
*/
|
|
|
|
|
|
|
|
goto retry;
|
|
|
|
}
|
|
|
|
}
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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);
|
2010-04-22 20:06:20 +04:00
|
|
|
if (!user_mode(regs))
|
|
|
|
goto no_context;
|
|
|
|
pagefault_out_of_memory();
|
|
|
|
return 0;
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
no_context:
|
|
|
|
current->thread.signo = SIGBUS;
|
|
|
|
current->thread.faddr = address;
|
|
|
|
return send_fault_sig(regs);
|
|
|
|
|
|
|
|
bus_err:
|
|
|
|
current->thread.signo = SIGBUS;
|
|
|
|
current->thread.code = BUS_ADRERR;
|
|
|
|
current->thread.faddr = address;
|
|
|
|
goto send_sig;
|
|
|
|
|
|
|
|
map_err:
|
|
|
|
current->thread.signo = SIGSEGV;
|
|
|
|
current->thread.code = SEGV_MAPERR;
|
|
|
|
current->thread.faddr = address;
|
|
|
|
goto send_sig;
|
|
|
|
|
|
|
|
acc_err:
|
|
|
|
current->thread.signo = SIGSEGV;
|
|
|
|
current->thread.code = SEGV_ACCERR;
|
|
|
|
current->thread.faddr = address;
|
|
|
|
|
|
|
|
send_sig:
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
return send_fault_sig(regs);
|
|
|
|
}
|