korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-11-19 10:14:23 +08:00
Code Issues Packages Projects Releases Wiki Activity
33692f2759
linux/arch/mips/mm/fault.c
Linus Torvalds 33692f2759 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 fee7e49d45 ("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>
2015-01-29 10:51:32 -08:00

332 lines
8.3 KiB
C
Raw Blame History

/*
* 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.
*
* Copyright (C) 1995 - 2000 by Ralf Baechle
*/
#include <linux/context_tracking.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/interrupt.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/smp.h>
#include <linux/module.h>
#include <linux/kprobes.h>
#include <linux/perf_event.h>
#include <asm/branch.h>
#include <asm/mmu_context.h>
#include <asm/uaccess.h>
#include <asm/ptrace.h>
#include <asm/highmem.h> /* For VMALLOC_END */
#include <linux/kdebug.h>
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
* routines.
*/
static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
unsigned long address)
{
struct vm_area_struct * vma = NULL;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
const int field = sizeof(unsigned long) * 2;
siginfo_t info;
int fault;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
#if 0
printk("Cpu%d[%s:%d:%0*lx:%ld:%0*lx]\n", raw_smp_processor_id(),
current->comm, current->pid, field, address, write,
field, regs->cp0_epc);
#endif
#ifdef CONFIG_KPROBES
/*
* This is to notify the fault handler of the kprobes. The
* exception code is redundant as it is also carried in REGS,
* but we pass it anyhow.
*/
if (notify_die(DIE_PAGE_FAULT, "page fault", regs, -1,
(regs->cp0_cause >> 2) & 0x1f, SIGSEGV) == NOTIFY_STOP)
return;
#endif
info.si_code = SEGV_MAPERR;
/*
* 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.
*/
#ifdef CONFIG_64BIT
# define VMALLOC_FAULT_TARGET no_context
#else
# define VMALLOC_FAULT_TARGET vmalloc_fault
#endif
if (unlikely(address >= VMALLOC_START && address <= VMALLOC_END))
goto VMALLOC_FAULT_TARGET;
#ifdef MODULE_START
if (unlikely(address >= MODULE_START && address < MODULE_END))
goto VMALLOC_FAULT_TARGET;
#endif
/*
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
if (in_atomic() || !mm)
goto bad_area_nosemaphore;
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
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;
if (write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
flags |= FAULT_FLAG_WRITE;
} else {
if (cpu_has_rixi) {
if (address == regs->cp0_epc && !(vma->vm_flags & VM_EXEC)) {
#if 0
pr_notice("Cpu%d[%s:%d:%0*lx:%ld:%0*lx] XI violation\n",
raw_smp_processor_id(),
current->comm, current->pid,
field, address, write,
field, regs->cp0_epc);
#endif
goto bad_area;
}
if (!(vma->vm_flags & VM_READ)) {
#if 0
pr_notice("Cpu%d[%s:%d:%0*lx:%ld:%0*lx] RI violation\n",
raw_smp_processor_id(),
current->comm, current->pid,
field, address, write,
field, regs->cp0_epc);
#endif
goto bad_area;
}
} else {
if (!(vma->vm_flags & (VM_READ | VM_WRITE | 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.
*/
fault = handle_mm_fault(mm, vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
}
if (flags & FAULT_FLAG_ALLOW_RETRY) {
if (fault & VM_FAULT_MAJOR) {
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
regs, address);
tsk->maj_flt++;
} else {
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
regs, address);
tsk->min_flt++;
}
if (fault & VM_FAULT_RETRY) {
flags &= ~FAULT_FLAG_ALLOW_RETRY;
flags |= FAULT_FLAG_TRIED;
/*
* 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;
}
}
up_read(&mm->mmap_sem);
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);
bad_area_nosemaphore:
/* User mode accesses just cause a SIGSEGV */
if (user_mode(regs)) {
tsk->thread.cp0_badvaddr = address;
tsk->thread.error_code = write;
#if 0
printk("do_page_fault() #2: sending SIGSEGV to %s for "
"invalid %s\n%0*lx (epc == %0*lx, ra == %0*lx)\n",
tsk->comm,
write ? "write access to" : "read access from",
field, address,
field, (unsigned long) regs->cp0_epc,
field, (unsigned long) regs->regs[31]);
#endif
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? */
if (fixup_exception(regs)) {
current->thread.cp0_baduaddr = address;
return;
}
/*
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice.
*/
bust_spinlocks(1);
printk(KERN_ALERT "CPU %d Unable to handle kernel paging request at "
"virtual address %0*lx, epc == %0*lx, ra == %0*lx\n",
raw_smp_processor_id(), field, address, field, regs->cp0_epc,
field, regs->regs[31]);
die("Oops", regs);
out_of_memory:
/*
* We ran out of memory, call the OOM killer, and return the userspace
* (which will retry the fault, or kill us if we got oom-killed).
*/
up_read(&mm->mmap_sem);
if (!user_mode(regs))
goto no_context;
pagefault_out_of_memory();
return;
do_sigbus:
up_read(&mm->mmap_sem);
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs))
goto no_context;
else
/*
* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
#if 0
printk("do_page_fault() #3: sending SIGBUS to %s for "
"invalid %s\n%0*lx (epc == %0*lx, ra == %0*lx)\n",
tsk->comm,
write ? "write access to" : "read access from",
field, address,
field, (unsigned long) regs->cp0_epc,
field, (unsigned long) regs->regs[31]);
#endif
tsk->thread.cp0_badvaddr = 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);
return;
#ifndef CONFIG_64BIT
vmalloc_fault:
{
/*
* Synchronize this task's top level page-table
* with the 'reference' page table.
*
* Do _not_ use "tsk" here. We might be inside
* an interrupt in the middle of a task switch..
*/
int offset = __pgd_offset(address);
pgd_t *pgd, *pgd_k;
pud_t *pud, *pud_k;
pmd_t *pmd, *pmd_k;
pte_t *pte_k;
pgd = (pgd_t *) pgd_current[raw_smp_processor_id()] + offset;
pgd_k = init_mm.pgd + offset;
if (!pgd_present(*pgd_k))
goto no_context;
set_pgd(pgd, *pgd_k);
pud = pud_offset(pgd, address);
pud_k = pud_offset(pgd_k, address);
if (!pud_present(*pud_k))
goto no_context;
pmd = pmd_offset(pud, address);
pmd_k = pmd_offset(pud_k, address);
if (!pmd_present(*pmd_k))
goto no_context;
set_pmd(pmd, *pmd_k);
pte_k = pte_offset_kernel(pmd_k, address);
if (!pte_present(*pte_k))
goto no_context;
return;
}
#endif
}
asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
unsigned long write, unsigned long address)
{
enum ctx_state prev_state;
prev_state = exception_enter();
__do_page_fault(regs, write, address);
exception_exit(prev_state);
}
Reference in New Issue View Git Blame Copy Permalink