2009-05-26 22:30:13 +08:00
|
|
|
/*
|
|
|
|
* arch/microblaze/mm/fault.c
|
|
|
|
*
|
|
|
|
* Copyright (C) 2007 Xilinx, Inc. All rights reserved.
|
|
|
|
*
|
|
|
|
* Derived from "arch/ppc/mm/fault.c"
|
|
|
|
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
|
|
|
|
*
|
|
|
|
* Derived from "arch/i386/mm/fault.c"
|
|
|
|
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
|
|
|
|
*
|
|
|
|
* Modified by Cort Dougan and Paul Mackerras.
|
|
|
|
*
|
|
|
|
* 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.
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
2017-01-11 03:13:29 +08:00
|
|
|
#include <linux/extable.h>
|
2009-05-26 22:30:13 +08:00
|
|
|
#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 <asm/page.h>
|
|
|
|
#include <asm/pgtable.h>
|
|
|
|
#include <asm/mmu.h>
|
2012-12-27 17:40:38 +08:00
|
|
|
#include <linux/mmu_context.h>
|
2009-05-26 22:30:13 +08:00
|
|
|
#include <linux/uaccess.h>
|
|
|
|
#include <asm/exceptions.h>
|
|
|
|
|
|
|
|
static unsigned long pte_misses; /* updated by do_page_fault() */
|
|
|
|
static unsigned long pte_errors; /* updated by do_page_fault() */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check whether the instruction at regs->pc is a store using
|
|
|
|
* an update addressing form which will update r1.
|
|
|
|
*/
|
|
|
|
static int store_updates_sp(struct pt_regs *regs)
|
|
|
|
{
|
|
|
|
unsigned int inst;
|
|
|
|
|
2011-02-07 19:24:39 +08:00
|
|
|
if (get_user(inst, (unsigned int __user *)regs->pc))
|
2009-05-26 22:30:13 +08:00
|
|
|
return 0;
|
|
|
|
/* check for 1 in the rD field */
|
|
|
|
if (((inst >> 21) & 0x1f) != 1)
|
|
|
|
return 0;
|
|
|
|
/* check for store opcodes */
|
|
|
|
if ((inst & 0xd0000000) == 0xd0000000)
|
|
|
|
return 1;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* bad_page_fault is called when we have a bad access from the kernel.
|
|
|
|
* It is called from do_page_fault above and from some of the procedures
|
|
|
|
* in traps.c.
|
|
|
|
*/
|
2009-07-21 18:48:01 +08:00
|
|
|
void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
|
2009-05-26 22:30:13 +08:00
|
|
|
{
|
|
|
|
const struct exception_table_entry *fixup;
|
|
|
|
/* MS: no context */
|
|
|
|
/* Are we prepared to handle this fault? */
|
|
|
|
fixup = search_exception_tables(regs->pc);
|
|
|
|
if (fixup) {
|
|
|
|
regs->pc = fixup->fixup;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* kernel has accessed a bad area */
|
|
|
|
die("kernel access of bad area", regs, sig);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The error_code parameter is ESR for a data fault,
|
|
|
|
* 0 for an instruction fault.
|
|
|
|
*/
|
|
|
|
void do_page_fault(struct pt_regs *regs, unsigned long address,
|
|
|
|
unsigned long error_code)
|
|
|
|
{
|
|
|
|
struct vm_area_struct *vma;
|
|
|
|
struct mm_struct *mm = current->mm;
|
|
|
|
int code = SEGV_MAPERR;
|
|
|
|
int is_write = error_code & ESR_S;
|
2018-08-18 06:44:47 +08:00
|
|
|
vm_fault_t fault;
|
2013-09-13 06:13:39 +08:00
|
|
|
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
|
2009-05-26 22:30:13 +08:00
|
|
|
|
|
|
|
regs->ear = address;
|
|
|
|
regs->esr = error_code;
|
|
|
|
|
|
|
|
/* On a kernel SLB miss we can only check for a valid exception entry */
|
2010-03-23 22:37:02 +08:00
|
|
|
if (unlikely(kernel_mode(regs) && (address >= TASK_SIZE))) {
|
2012-12-27 17:40:38 +08:00
|
|
|
pr_warn("kernel task_size exceed");
|
2009-05-26 22:30:13 +08:00
|
|
|
_exception(SIGSEGV, regs, code, address);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* for instr TLB miss and instr storage exception ESR_S is undefined */
|
|
|
|
if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11)
|
|
|
|
is_write = 0;
|
|
|
|
|
2015-05-11 23:52:11 +08:00
|
|
|
if (unlikely(faulthandler_disabled() || !mm)) {
|
2009-07-16 22:00:49 +08:00
|
|
|
if (kernel_mode(regs))
|
|
|
|
goto bad_area_nosemaphore;
|
|
|
|
|
2015-05-11 23:52:11 +08:00
|
|
|
/* faulthandler_disabled() in user mode is really bad,
|
2009-05-26 22:30:13 +08:00
|
|
|
as is current->mm == NULL. */
|
2015-05-11 23:52:11 +08:00
|
|
|
pr_emerg("Page fault in user mode with faulthandler_disabled(), mm = %p\n",
|
|
|
|
mm);
|
2012-12-27 17:40:38 +08:00
|
|
|
pr_emerg("r15 = %lx MSR = %lx\n",
|
2009-05-26 22:30:13 +08:00
|
|
|
regs->r15, regs->msr);
|
|
|
|
die("Weird page fault", regs, SIGSEGV);
|
|
|
|
}
|
|
|
|
|
2013-09-13 06:13:39 +08:00
|
|
|
if (user_mode(regs))
|
|
|
|
flags |= FAULT_FLAG_USER;
|
|
|
|
|
2009-05-26 22:30:13 +08:00
|
|
|
/* When running in the kernel we expect faults to occur only to
|
|
|
|
* addresses in user space. All other faults represent errors in the
|
|
|
|
* kernel and should generate an OOPS. Unfortunately, in the case of an
|
|
|
|
* erroneous fault occurring in a code path which already holds mmap_sem
|
|
|
|
* we will deadlock attempting to validate the fault against the
|
|
|
|
* address space. Luckily the kernel only validly references user
|
|
|
|
* space from well defined areas of code, which are listed in the
|
|
|
|
* exceptions table.
|
|
|
|
*
|
|
|
|
* As the vast majority of faults will be valid we will only perform
|
|
|
|
* the source reference check when there is a possibility of a deadlock.
|
|
|
|
* Attempt to lock the address space, if we cannot we then validate the
|
|
|
|
* source. If this is invalid we can skip the address space check,
|
|
|
|
* thus avoiding the deadlock.
|
|
|
|
*/
|
2010-03-23 22:37:02 +08:00
|
|
|
if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
|
2009-05-26 22:30:13 +08:00
|
|
|
if (kernel_mode(regs) && !search_exception_tables(regs->pc))
|
|
|
|
goto bad_area_nosemaphore;
|
|
|
|
|
2012-03-20 21:21:40 +08:00
|
|
|
retry:
|
2009-05-26 22:30:13 +08:00
|
|
|
down_read(&mm->mmap_sem);
|
|
|
|
}
|
|
|
|
|
|
|
|
vma = find_vma(mm, address);
|
2010-03-23 22:37:02 +08:00
|
|
|
if (unlikely(!vma))
|
2009-05-26 22:30:13 +08:00
|
|
|
goto bad_area;
|
|
|
|
|
|
|
|
if (vma->vm_start <= address)
|
|
|
|
goto good_area;
|
|
|
|
|
2010-03-23 22:37:02 +08:00
|
|
|
if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
|
2009-05-26 22:30:13 +08:00
|
|
|
goto bad_area;
|
|
|
|
|
2010-03-23 22:37:02 +08:00
|
|
|
if (unlikely(!is_write))
|
2009-05-26 22:30:13 +08:00
|
|
|
goto bad_area;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* N.B. The ABI allows programs to access up to
|
|
|
|
* a few hundred bytes below the stack pointer (TBD).
|
|
|
|
* The kernel signal delivery code writes up to about 1.5kB
|
|
|
|
* below the stack pointer (r1) before decrementing it.
|
|
|
|
* The exec code can write slightly over 640kB to the stack
|
|
|
|
* before setting the user r1. Thus we allow the stack to
|
|
|
|
* expand to 1MB without further checks.
|
|
|
|
*/
|
2010-03-23 22:37:02 +08:00
|
|
|
if (unlikely(address + 0x100000 < vma->vm_end)) {
|
2009-05-26 22:30:13 +08:00
|
|
|
|
|
|
|
/* get user regs even if this fault is in kernel mode */
|
|
|
|
struct pt_regs *uregs = current->thread.regs;
|
|
|
|
if (uregs == NULL)
|
|
|
|
goto bad_area;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* A user-mode access to an address a long way below
|
|
|
|
* the stack pointer is only valid if the instruction
|
|
|
|
* is one which would update the stack pointer to the
|
|
|
|
* address accessed if the instruction completed,
|
|
|
|
* i.e. either stwu rs,n(r1) or stwux rs,r1,rb
|
|
|
|
* (or the byte, halfword, float or double forms).
|
|
|
|
*
|
|
|
|
* If we don't check this then any write to the area
|
|
|
|
* between the last mapped region and the stack will
|
|
|
|
* expand the stack rather than segfaulting.
|
|
|
|
*/
|
|
|
|
if (address + 2048 < uregs->r1
|
|
|
|
&& (kernel_mode(regs) || !store_updates_sp(regs)))
|
|
|
|
goto bad_area;
|
|
|
|
}
|
|
|
|
if (expand_stack(vma, address))
|
|
|
|
goto bad_area;
|
|
|
|
|
|
|
|
good_area:
|
|
|
|
code = SEGV_ACCERR;
|
|
|
|
|
|
|
|
/* a write */
|
2010-03-23 22:37:02 +08:00
|
|
|
if (unlikely(is_write)) {
|
|
|
|
if (unlikely(!(vma->vm_flags & VM_WRITE)))
|
2009-05-26 22:30:13 +08:00
|
|
|
goto bad_area;
|
2013-09-13 06:13:39 +08:00
|
|
|
flags |= FAULT_FLAG_WRITE;
|
2009-05-26 22:30:13 +08:00
|
|
|
/* a read */
|
|
|
|
} else {
|
|
|
|
/* protection fault */
|
2010-03-23 22:37:02 +08:00
|
|
|
if (unlikely(error_code & 0x08000000))
|
2009-05-26 22:30:13 +08:00
|
|
|
goto bad_area;
|
2010-03-23 22:37:02 +08:00
|
|
|
if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC))))
|
2009-05-26 22:30:13 +08:00
|
|
|
goto bad_area;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If for any reason at all we couldn't handle the fault,
|
|
|
|
* make sure we exit gracefully rather than endlessly redo
|
|
|
|
* the fault.
|
|
|
|
*/
|
2016-07-27 06:25:18 +08:00
|
|
|
fault = handle_mm_fault(vma, address, flags);
|
2012-03-20 21:21:40 +08:00
|
|
|
|
|
|
|
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
|
|
|
|
return;
|
|
|
|
|
2009-05-26 22:30:13 +08:00
|
|
|
if (unlikely(fault & VM_FAULT_ERROR)) {
|
|
|
|
if (fault & VM_FAULT_OOM)
|
|
|
|
goto out_of_memory;
|
vm: add VM_FAULT_SIGSEGV handling support
The core VM already knows about VM_FAULT_SIGBUS, but cannot return a
"you should SIGSEGV" error, because the SIGSEGV case was generally
handled by the caller - usually the architecture fault handler.
That results in lots of duplication - all the architecture fault
handlers end up doing very similar "look up vma, check permissions, do
retries etc" - but it generally works. However, there are cases where
the VM actually wants to SIGSEGV, and applications _expect_ SIGSEGV.
In particular, when accessing the stack guard page, libsigsegv expects a
SIGSEGV. And it usually got one, because the stack growth is handled by
that duplicated architecture fault handler.
However, when the generic VM layer started propagating the error return
from the stack expansion in commit fee7e49d4514 ("mm: propagate error
from stack expansion even for guard page"), that now exposed the
existing VM_FAULT_SIGBUS result to user space. And user space really
expected SIGSEGV, not SIGBUS.
To fix that case, we need to add a VM_FAULT_SIGSEGV, and teach all those
duplicate architecture fault handlers about it. They all already have
the code to handle SIGSEGV, so it's about just tying that new return
value to the existing code, but it's all a bit annoying.
This is the mindless minimal patch to do this. A more extensive patch
would be to try to gather up the mostly shared fault handling logic into
one generic helper routine, and long-term we really should do that
cleanup.
Just from this patch, you can generally see that most architectures just
copied (directly or indirectly) the old x86 way of doing things, but in
the meantime that original x86 model has been improved to hold the VM
semaphore for shorter times etc and to handle VM_FAULT_RETRY and other
"newer" things, so it would be a good idea to bring all those
improvements to the generic case and teach other architectures about
them too.
Reported-and-tested-by: Takashi Iwai <tiwai@suse.de>
Tested-by: Jan Engelhardt <jengelh@inai.de>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # "s390 still compiles and boots"
Cc: linux-arch@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-01-30 02:51:32 +08:00
|
|
|
else if (fault & VM_FAULT_SIGSEGV)
|
|
|
|
goto bad_area;
|
2009-05-26 22:30:13 +08:00
|
|
|
else if (fault & VM_FAULT_SIGBUS)
|
|
|
|
goto do_sigbus;
|
|
|
|
BUG();
|
|
|
|
}
|
2012-03-20 21:21:40 +08:00
|
|
|
|
|
|
|
if (flags & FAULT_FLAG_ALLOW_RETRY) {
|
|
|
|
if (unlikely(fault & VM_FAULT_MAJOR))
|
|
|
|
current->maj_flt++;
|
|
|
|
else
|
|
|
|
current->min_flt++;
|
|
|
|
if (fault & VM_FAULT_RETRY) {
|
|
|
|
flags &= ~FAULT_FLAG_ALLOW_RETRY;
|
2012-10-09 07:32:19 +08:00
|
|
|
flags |= FAULT_FLAG_TRIED;
|
2012-03-20 21:21:40 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2009-05-26 22:30:13 +08:00
|
|
|
up_read(&mm->mmap_sem);
|
2012-03-20 21:21:40 +08:00
|
|
|
|
2009-05-26 22:30:13 +08:00
|
|
|
/*
|
|
|
|
* keep track of tlb+htab misses that are good addrs but
|
|
|
|
* just need pte's created via handle_mm_fault()
|
|
|
|
* -- Cort
|
|
|
|
*/
|
|
|
|
pte_misses++;
|
|
|
|
return;
|
|
|
|
|
|
|
|
bad_area:
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
|
|
|
|
bad_area_nosemaphore:
|
|
|
|
pte_errors++;
|
|
|
|
|
|
|
|
/* User mode accesses cause a SIGSEGV */
|
|
|
|
if (user_mode(regs)) {
|
|
|
|
_exception(SIGSEGV, regs, code, address);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
bad_page_fault(regs, address, SIGSEGV);
|
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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);
|
2010-04-23 00:06:21 +08:00
|
|
|
if (!user_mode(regs))
|
|
|
|
bad_page_fault(regs, address, SIGKILL);
|
|
|
|
else
|
|
|
|
pagefault_out_of_memory();
|
2009-05-26 22:30:13 +08:00
|
|
|
return;
|
|
|
|
|
|
|
|
do_sigbus:
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
if (user_mode(regs)) {
|
2018-04-17 00:24:24 +08:00
|
|
|
force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address, current);
|
2009-05-26 22:30:13 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
bad_page_fault(regs, address, SIGBUS);
|
|
|
|
}
|