mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-04 09:59:32 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
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>
245 lines
5.5 KiB
C
245 lines
5.5 KiB
C
/*
|
|
* Meta page fault handling.
|
|
*
|
|
* Copyright (C) 2005-2012 Imagination Technologies Ltd.
|
|
*/
|
|
|
|
#include <linux/mman.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/ptrace.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/uaccess.h>
|
|
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/mmu.h>
|
|
#include <asm/traps.h>
|
|
|
|
/* Clear any pending catch buffer state. */
|
|
static void clear_cbuf_entry(struct pt_regs *regs, unsigned long addr,
|
|
unsigned int trapno)
|
|
{
|
|
PTBICTXEXTCB0 cbuf = regs->extcb0;
|
|
|
|
switch (trapno) {
|
|
/* Instruction fetch faults leave no catch buffer state. */
|
|
case TBIXXF_SIGNUM_IGF:
|
|
case TBIXXF_SIGNUM_IPF:
|
|
return;
|
|
default:
|
|
if (cbuf[0].CBAddr == addr) {
|
|
cbuf[0].CBAddr = 0;
|
|
cbuf[0].CBFlags &= ~TXCATCH0_FAULT_BITS;
|
|
|
|
/* And, as this is the ONLY catch entry, we
|
|
* need to clear the cbuf bit from the context!
|
|
*/
|
|
regs->ctx.SaveMask &= ~(TBICTX_CBUF_BIT |
|
|
TBICTX_XCBF_BIT);
|
|
|
|
return;
|
|
}
|
|
pr_err("Failed to clear cbuf entry!\n");
|
|
}
|
|
}
|
|
|
|
int show_unhandled_signals = 1;
|
|
|
|
int do_page_fault(struct pt_regs *regs, unsigned long address,
|
|
unsigned int write_access, unsigned int trapno)
|
|
{
|
|
struct task_struct *tsk;
|
|
struct mm_struct *mm;
|
|
struct vm_area_struct *vma, *prev_vma;
|
|
siginfo_t info;
|
|
int fault;
|
|
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
|
|
|
|
tsk = current;
|
|
|
|
if ((address >= VMALLOC_START) && (address < VMALLOC_END)) {
|
|
/*
|
|
* 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_index(address);
|
|
pgd_t *pgd, *pgd_k;
|
|
pud_t *pud, *pud_k;
|
|
pmd_t *pmd, *pmd_k;
|
|
pte_t *pte_k;
|
|
|
|
pgd = ((pgd_t *)mmu_get_base()) + offset;
|
|
pgd_k = swapper_pg_dir + offset;
|
|
|
|
/* This will never happen with the folded page table. */
|
|
if (!pgd_present(*pgd)) {
|
|
if (!pgd_present(*pgd_k))
|
|
goto bad_area_nosemaphore;
|
|
set_pgd(pgd, *pgd_k);
|
|
return 0;
|
|
}
|
|
|
|
pud = pud_offset(pgd, address);
|
|
pud_k = pud_offset(pgd_k, address);
|
|
if (!pud_present(*pud_k))
|
|
goto bad_area_nosemaphore;
|
|
set_pud(pud, *pud_k);
|
|
|
|
pmd = pmd_offset(pud, address);
|
|
pmd_k = pmd_offset(pud_k, address);
|
|
if (!pmd_present(*pmd_k))
|
|
goto bad_area_nosemaphore;
|
|
set_pmd(pmd, *pmd_k);
|
|
|
|
pte_k = pte_offset_kernel(pmd_k, address);
|
|
if (!pte_present(*pte_k))
|
|
goto bad_area_nosemaphore;
|
|
|
|
/* May only be needed on Chorus2 */
|
|
flush_tlb_all();
|
|
return 0;
|
|
}
|
|
|
|
mm = tsk->mm;
|
|
|
|
if (in_atomic() || !mm)
|
|
goto no_context;
|
|
|
|
if (user_mode(regs))
|
|
flags |= FAULT_FLAG_USER;
|
|
retry:
|
|
down_read(&mm->mmap_sem);
|
|
|
|
vma = find_vma_prev(mm, address, &prev_vma);
|
|
|
|
if (!vma || address < vma->vm_start)
|
|
goto check_expansion;
|
|
|
|
good_area:
|
|
if (write_access) {
|
|
if (!(vma->vm_flags & VM_WRITE))
|
|
goto bad_area;
|
|
flags |= FAULT_FLAG_WRITE;
|
|
} else {
|
|
if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
|
|
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 0;
|
|
|
|
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)
|
|
tsk->maj_flt++;
|
|
else
|
|
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 0;
|
|
|
|
check_expansion:
|
|
vma = prev_vma;
|
|
if (vma && (expand_stack(vma, address) == 0))
|
|
goto good_area;
|
|
|
|
bad_area:
|
|
up_read(&mm->mmap_sem);
|
|
|
|
bad_area_nosemaphore:
|
|
if (user_mode(regs)) {
|
|
info.si_signo = SIGSEGV;
|
|
info.si_errno = 0;
|
|
info.si_code = SEGV_MAPERR;
|
|
info.si_addr = (__force void __user *)address;
|
|
info.si_trapno = trapno;
|
|
|
|
if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
|
|
printk_ratelimit()) {
|
|
pr_info("%s%s[%d]: segfault at %lx pc %08x sp %08x write %d trap %#x (%s)",
|
|
task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
|
|
tsk->comm, task_pid_nr(tsk), address,
|
|
regs->ctx.CurrPC, regs->ctx.AX[0].U0,
|
|
write_access, trapno, trap_name(trapno));
|
|
print_vma_addr(" in ", regs->ctx.CurrPC);
|
|
print_vma_addr(" rtp in ", regs->ctx.DX[4].U1);
|
|
printk("\n");
|
|
show_regs(regs);
|
|
}
|
|
force_sig_info(SIGSEGV, &info, tsk);
|
|
return 1;
|
|
}
|
|
goto no_context;
|
|
|
|
do_sigbus:
|
|
up_read(&mm->mmap_sem);
|
|
|
|
/*
|
|
* Send a sigbus, regardless of whether we were in kernel
|
|
* or user mode.
|
|
*/
|
|
info.si_signo = SIGBUS;
|
|
info.si_errno = 0;
|
|
info.si_code = BUS_ADRERR;
|
|
info.si_addr = (__force void __user *)address;
|
|
info.si_trapno = trapno;
|
|
force_sig_info(SIGBUS, &info, tsk);
|
|
|
|
/* Kernel mode? Handle exceptions or die */
|
|
if (!user_mode(regs))
|
|
goto no_context;
|
|
|
|
return 1;
|
|
|
|
/*
|
|
* 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);
|
|
if (user_mode(regs)) {
|
|
pagefault_out_of_memory();
|
|
return 1;
|
|
}
|
|
|
|
no_context:
|
|
/* Are we prepared to handle this kernel fault? */
|
|
if (fixup_exception(regs)) {
|
|
clear_cbuf_entry(regs, address, trapno);
|
|
return 1;
|
|
}
|
|
|
|
die("Oops", regs, (write_access << 15) | trapno, address);
|
|
do_exit(SIGKILL);
|
|
}
|