2013-01-18 17:42:20 +08:00
|
|
|
/* Page Fault Handling for ARC (TLB Miss / ProtV)
|
|
|
|
*
|
|
|
|
* Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
|
|
|
|
*
|
|
|
|
* 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/interrupt.h>
|
2017-02-09 01:51:30 +08:00
|
|
|
#include <linux/sched/signal.h>
|
2013-01-18 17:42:20 +08:00
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/ptrace.h>
|
|
|
|
#include <linux/uaccess.h>
|
|
|
|
#include <linux/kdebug.h>
|
2014-10-02 15:00:42 +08:00
|
|
|
#include <linux/perf_event.h>
|
2013-01-18 17:42:20 +08:00
|
|
|
#include <asm/pgalloc.h>
|
2013-05-14 15:58:17 +08:00
|
|
|
#include <asm/mmu.h>
|
2013-01-18 17:42:20 +08:00
|
|
|
|
2015-03-05 19:36:31 +08:00
|
|
|
/*
|
|
|
|
* kernel virtual address is required to implement vmalloc/pkmap/fixmap
|
|
|
|
* Refer to asm/processor.h for System Memory Map
|
|
|
|
*
|
|
|
|
* It simply copies the PMD entry (pointer to 2nd level page table or hugepage)
|
|
|
|
* from swapper pgdir to task pgdir. The 2nd level table/page is thus shared
|
|
|
|
*/
|
|
|
|
noinline static int handle_kernel_vaddr_fault(unsigned long address)
|
2013-01-18 17:42:20 +08:00
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Synchronize this task's top level page-table
|
|
|
|
* with the 'reference' page table.
|
|
|
|
*/
|
|
|
|
pgd_t *pgd, *pgd_k;
|
|
|
|
pud_t *pud, *pud_k;
|
|
|
|
pmd_t *pmd, *pmd_k;
|
|
|
|
|
2013-11-02 20:17:49 +08:00
|
|
|
pgd = pgd_offset_fast(current->active_mm, address);
|
2013-01-18 17:42:20 +08:00
|
|
|
pgd_k = pgd_offset_k(address);
|
|
|
|
|
|
|
|
if (!pgd_present(*pgd_k))
|
|
|
|
goto bad_area;
|
|
|
|
|
|
|
|
pud = pud_offset(pgd, address);
|
|
|
|
pud_k = pud_offset(pgd_k, address);
|
|
|
|
if (!pud_present(*pud_k))
|
|
|
|
goto bad_area;
|
|
|
|
|
|
|
|
pmd = pmd_offset(pud, address);
|
|
|
|
pmd_k = pmd_offset(pud_k, address);
|
|
|
|
if (!pmd_present(*pmd_k))
|
|
|
|
goto bad_area;
|
|
|
|
|
|
|
|
set_pmd(pmd, *pmd_k);
|
|
|
|
|
|
|
|
/* XXX: create the TLB entry here */
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
bad_area:
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2013-09-18 18:55:40 +08:00
|
|
|
void do_page_fault(unsigned long address, struct pt_regs *regs)
|
2013-01-18 17:42:20 +08:00
|
|
|
{
|
|
|
|
struct vm_area_struct *vma = NULL;
|
|
|
|
struct task_struct *tsk = current;
|
|
|
|
struct mm_struct *mm = tsk->mm;
|
|
|
|
siginfo_t info;
|
|
|
|
int fault, ret;
|
2013-06-12 17:43:40 +08:00
|
|
|
int write = regs->ecr_cause & ECR_C_PROTV_STORE; /* ST/EX */
|
2013-09-13 06:13:39 +08:00
|
|
|
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
|
2013-01-18 17:42:20 +08:00
|
|
|
|
2018-04-18 04:26:37 +08:00
|
|
|
clear_siginfo(&info);
|
|
|
|
|
2013-01-18 17:42:20 +08:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2015-03-05 19:36:31 +08:00
|
|
|
if (address >= VMALLOC_START) {
|
|
|
|
ret = handle_kernel_vaddr_fault(address);
|
2013-01-18 17:42:20 +08:00
|
|
|
if (unlikely(ret))
|
|
|
|
goto bad_area_nosemaphore;
|
|
|
|
else
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
info.si_code = SEGV_MAPERR;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If we're in an interrupt or have no user
|
|
|
|
* context, we must not take the fault..
|
|
|
|
*/
|
2015-05-11 23:52:11 +08:00
|
|
|
if (faulthandler_disabled() || !mm)
|
2013-01-18 17:42:20 +08:00
|
|
|
goto no_context;
|
|
|
|
|
2013-09-13 06:13:39 +08:00
|
|
|
if (user_mode(regs))
|
|
|
|
flags |= FAULT_FLAG_USER;
|
2013-01-18 17:42:20 +08:00
|
|
|
retry:
|
|
|
|
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;
|
|
|
|
|
|
|
|
/* Handle protection violation, execute on heap or stack */
|
|
|
|
|
2013-06-12 17:43:40 +08:00
|
|
|
if ((regs->ecr_vec == ECR_V_PROTV) &&
|
|
|
|
(regs->ecr_cause == ECR_C_PROTV_INST_FETCH))
|
2013-01-18 17:42:20 +08:00
|
|
|
goto bad_area;
|
|
|
|
|
|
|
|
if (write) {
|
|
|
|
if (!(vma->vm_flags & VM_WRITE))
|
|
|
|
goto bad_area;
|
2013-09-13 06:13:39 +08:00
|
|
|
flags |= FAULT_FLAG_WRITE;
|
2013-01-18 17:42:20 +08:00
|
|
|
} else {
|
|
|
|
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
|
|
|
|
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);
|
2013-01-18 17:42:20 +08:00
|
|
|
|
|
|
|
/* If Pagefault was interrupted by SIGKILL, exit page fault "early" */
|
|
|
|
if (unlikely(fatal_signal_pending(current))) {
|
|
|
|
if ((fault & VM_FAULT_ERROR) && !(fault & VM_FAULT_RETRY))
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
if (user_mode(regs))
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2014-10-02 15:00:42 +08:00
|
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
|
|
|
|
|
2013-01-18 17:42:20 +08:00
|
|
|
if (likely(!(fault & VM_FAULT_ERROR))) {
|
|
|
|
if (flags & FAULT_FLAG_ALLOW_RETRY) {
|
|
|
|
/* To avoid updating stats twice for retry case */
|
2014-10-02 15:00:42 +08:00
|
|
|
if (fault & VM_FAULT_MAJOR) {
|
2013-01-18 17:42:20 +08:00
|
|
|
tsk->maj_flt++;
|
2014-10-02 15:00:42 +08:00
|
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
|
|
|
|
regs, address);
|
|
|
|
} else {
|
2013-01-18 17:42:20 +08:00
|
|
|
tsk->min_flt++;
|
2014-10-02 15:00:42 +08:00
|
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
|
|
|
|
regs, address);
|
|
|
|
}
|
2013-01-18 17:42:20 +08:00
|
|
|
|
|
|
|
if (fault & VM_FAULT_RETRY) {
|
|
|
|
flags &= ~FAULT_FLAG_ALLOW_RETRY;
|
|
|
|
flags |= FAULT_FLAG_TRIED;
|
|
|
|
goto retry;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Fault Handled Gracefully */
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (fault & VM_FAULT_OOM)
|
|
|
|
goto out_of_memory;
|
2015-01-30 11:15:33 +08:00
|
|
|
else if (fault & VM_FAULT_SIGSEGV)
|
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
|
|
|
goto bad_area;
|
2013-01-18 17:42:20 +08:00
|
|
|
else if (fault & VM_FAULT_SIGBUS)
|
|
|
|
goto do_sigbus;
|
|
|
|
|
|
|
|
/* no man's land */
|
|
|
|
BUG();
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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.fault_address = address;
|
|
|
|
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?
|
|
|
|
*
|
|
|
|
* (The kernel has valid exception-points in the source
|
2017-05-28 14:52:00 +08:00
|
|
|
* when it accesses user-memory. When it fails in one
|
2013-01-18 17:42:20 +08:00
|
|
|
* of those points, we find it in a table and do a jump
|
|
|
|
* to some fixup code that loads an appropriate error
|
|
|
|
* code)
|
|
|
|
*/
|
|
|
|
if (fixup_exception(regs))
|
|
|
|
return;
|
|
|
|
|
2013-06-12 17:43:40 +08:00
|
|
|
die("Oops", regs, address);
|
2013-01-18 17:42:20 +08:00
|
|
|
|
|
|
|
out_of_memory:
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
|
2013-07-09 06:59:50 +08:00
|
|
|
if (user_mode(regs)) {
|
|
|
|
pagefault_out_of_memory();
|
|
|
|
return;
|
|
|
|
}
|
2013-01-18 17:42:20 +08:00
|
|
|
|
|
|
|
goto no_context;
|
|
|
|
|
|
|
|
do_sigbus:
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
|
|
|
|
if (!user_mode(regs))
|
|
|
|
goto no_context;
|
|
|
|
|
|
|
|
tsk->thread.fault_address = 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);
|
|
|
|
}
|