mirror of
https://gitee.com/bianbu-linux/linux-6.6
synced 2025-04-24 14:07:52 -04:00
Although there're tons of arch-specific page fault handlers, most of them are still sharing the same initial value of the page fault flags. Say, merely all of the page fault handlers would allow the fault to be retried, and they also allow the fault to respond to SIGKILL. Let's define a default value for the fault flags to replace those initial page fault flags that were copied over. With this, it'll be far easier to introduce new fault flag that can be used by all the architectures instead of touching all the archs. Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Brian Geffon <bgeffon@google.com> Reviewed-by: David Hildenbrand <david@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bobby Powers <bobbypowers@gmail.com> Cc: Denis Plotnikov <dplotnikov@virtuozzo.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Martin Cracauer <cracauer@cons.org> Cc: Marty McFadden <mcfadden8@llnl.gov> Cc: Matthew Wilcox <willy@infradead.org> Cc: Maya Gokhale <gokhale2@llnl.gov> Cc: Mel Gorman <mgorman@suse.de> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Link: http://lkml.kernel.org/r/20200220160238.9694-1-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
202 lines
4.5 KiB
C
202 lines
4.5 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/* Page Fault Handling for ARC (TLB Miss / ProtV)
|
|
*
|
|
* Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
|
|
*/
|
|
|
|
#include <linux/signal.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/sched/signal.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/ptrace.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/kdebug.h>
|
|
#include <linux/perf_event.h>
|
|
#include <linux/mm_types.h>
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/mmu.h>
|
|
|
|
/*
|
|
* 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)
|
|
{
|
|
/*
|
|
* Synchronize this task's top level page-table
|
|
* with the 'reference' page table.
|
|
*/
|
|
pgd_t *pgd, *pgd_k;
|
|
p4d_t *p4d, *p4d_k;
|
|
pud_t *pud, *pud_k;
|
|
pmd_t *pmd, *pmd_k;
|
|
|
|
pgd = pgd_offset_fast(current->active_mm, address);
|
|
pgd_k = pgd_offset_k(address);
|
|
|
|
if (!pgd_present(*pgd_k))
|
|
goto bad_area;
|
|
|
|
p4d = p4d_offset(pgd, address);
|
|
p4d_k = p4d_offset(pgd_k, address);
|
|
if (!p4d_present(*p4d_k))
|
|
goto bad_area;
|
|
|
|
pud = pud_offset(p4d, address);
|
|
pud_k = pud_offset(p4d_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;
|
|
}
|
|
|
|
void do_page_fault(unsigned long address, struct pt_regs *regs)
|
|
{
|
|
struct vm_area_struct *vma = NULL;
|
|
struct task_struct *tsk = current;
|
|
struct mm_struct *mm = tsk->mm;
|
|
int sig, si_code = SEGV_MAPERR;
|
|
unsigned int write = 0, exec = 0, mask;
|
|
vm_fault_t fault = VM_FAULT_SIGSEGV; /* handle_mm_fault() output */
|
|
unsigned int flags; /* handle_mm_fault() input */
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
if (address >= VMALLOC_START && !user_mode(regs)) {
|
|
if (unlikely(handle_kernel_vaddr_fault(address)))
|
|
goto no_context;
|
|
else
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* If we're in an interrupt or have no user
|
|
* context, we must not take the fault..
|
|
*/
|
|
if (faulthandler_disabled() || !mm)
|
|
goto no_context;
|
|
|
|
if (regs->ecr_cause & ECR_C_PROTV_STORE) /* ST/EX */
|
|
write = 1;
|
|
else if ((regs->ecr_vec == ECR_V_PROTV) &&
|
|
(regs->ecr_cause == ECR_C_PROTV_INST_FETCH))
|
|
exec = 1;
|
|
|
|
flags = FAULT_FLAG_DEFAULT;
|
|
if (user_mode(regs))
|
|
flags |= FAULT_FLAG_USER;
|
|
if (write)
|
|
flags |= FAULT_FLAG_WRITE;
|
|
|
|
retry:
|
|
down_read(&mm->mmap_sem);
|
|
|
|
vma = find_vma(mm, address);
|
|
if (!vma)
|
|
goto bad_area;
|
|
if (unlikely(address < vma->vm_start)) {
|
|
if (!(vma->vm_flags & VM_GROWSDOWN) || expand_stack(vma, address))
|
|
goto bad_area;
|
|
}
|
|
|
|
/*
|
|
* vm_area is good, now check permissions for this memory access
|
|
*/
|
|
mask = VM_READ;
|
|
if (write)
|
|
mask = VM_WRITE;
|
|
if (exec)
|
|
mask = VM_EXEC;
|
|
|
|
if (!(vma->vm_flags & mask)) {
|
|
si_code = SEGV_ACCERR;
|
|
goto bad_area;
|
|
}
|
|
|
|
fault = handle_mm_fault(vma, address, flags);
|
|
|
|
/* Quick path to respond to signals */
|
|
if (fault_signal_pending(fault, regs)) {
|
|
if (!user_mode(regs))
|
|
goto no_context;
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* Fault retry nuances, mmap_sem already relinquished by core mm
|
|
*/
|
|
if (unlikely((fault & VM_FAULT_RETRY) &&
|
|
(flags & FAULT_FLAG_ALLOW_RETRY))) {
|
|
flags &= ~FAULT_FLAG_ALLOW_RETRY;
|
|
flags |= FAULT_FLAG_TRIED;
|
|
goto retry;
|
|
}
|
|
|
|
bad_area:
|
|
up_read(&mm->mmap_sem);
|
|
|
|
/*
|
|
* Major/minor page fault accounting
|
|
* (in case of retry we only land here once)
|
|
*/
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
|
|
|
|
if (likely(!(fault & VM_FAULT_ERROR))) {
|
|
if (fault & VM_FAULT_MAJOR) {
|
|
tsk->maj_flt++;
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
|
|
regs, address);
|
|
} else {
|
|
tsk->min_flt++;
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
|
|
regs, address);
|
|
}
|
|
|
|
/* Normal return path: fault Handled Gracefully */
|
|
return;
|
|
}
|
|
|
|
if (!user_mode(regs))
|
|
goto no_context;
|
|
|
|
if (fault & VM_FAULT_OOM) {
|
|
pagefault_out_of_memory();
|
|
return;
|
|
}
|
|
|
|
if (fault & VM_FAULT_SIGBUS) {
|
|
sig = SIGBUS;
|
|
si_code = BUS_ADRERR;
|
|
}
|
|
else {
|
|
sig = SIGSEGV;
|
|
}
|
|
|
|
tsk->thread.fault_address = address;
|
|
force_sig_fault(sig, si_code, (void __user *)address);
|
|
return;
|
|
|
|
no_context:
|
|
if (fixup_exception(regs))
|
|
return;
|
|
|
|
die("Oops", regs, address);
|
|
}
|