linux/arch/arc/mm/fault.c
Peter Xu 4064b98270 mm: allow VM_FAULT_RETRY for multiple times
The idea comes from a discussion between Linus and Andrea [1].

Before this patch we only allow a page fault to retry once.  We achieved
this by clearing the FAULT_FLAG_ALLOW_RETRY flag when doing
handle_mm_fault() the second time.  This was majorly used to avoid
unexpected starvation of the system by looping over forever to handle the
page fault on a single page.  However that should hardly happen, and after
all for each code path to return a VM_FAULT_RETRY we'll first wait for a
condition (during which time we should possibly yield the cpu) to happen
before VM_FAULT_RETRY is really returned.

This patch removes the restriction by keeping the FAULT_FLAG_ALLOW_RETRY
flag when we receive VM_FAULT_RETRY.  It means that the page fault handler
now can retry the page fault for multiple times if necessary without the
need to generate another page fault event.  Meanwhile we still keep the
FAULT_FLAG_TRIED flag so page fault handler can still identify whether a
page fault is the first attempt or not.

Then we'll have these combinations of fault flags (only considering
ALLOW_RETRY flag and TRIED flag):

  - ALLOW_RETRY and !TRIED:  this means the page fault allows to
                             retry, and this is the first try

  - ALLOW_RETRY and TRIED:   this means the page fault allows to
                             retry, and this is not the first try

  - !ALLOW_RETRY and !TRIED: this means the page fault does not allow
                             to retry at all

  - !ALLOW_RETRY and TRIED:  this is forbidden and should never be used

In existing code we have multiple places that has taken special care of
the first condition above by checking against (fault_flags &
FAULT_FLAG_ALLOW_RETRY).  This patch introduces a simple helper to detect
the first retry of a page fault by checking against both (fault_flags &
FAULT_FLAG_ALLOW_RETRY) and !(fault_flag & FAULT_FLAG_TRIED) because now
even the 2nd try will have the ALLOW_RETRY set, then use that helper in
all existing special paths.  One example is in __lock_page_or_retry(), now
we'll drop the mmap_sem only in the first attempt of page fault and we'll
keep it in follow up retries, so old locking behavior will be retained.

This will be a nice enhancement for current code [2] at the same time a
supporting material for the future userfaultfd-writeprotect work, since in
that work there will always be an explicit userfault writeprotect retry
for protected pages, and if that cannot resolve the page fault (e.g., when
userfaultfd-writeprotect is used in conjunction with swapped pages) then
we'll possibly need a 3rd retry of the page fault.  It might also benefit
other potential users who will have similar requirement like userfault
write-protection.

GUP code is not touched yet and will be covered in follow up patch.

Please read the thread below for more information.

[1] https://lore.kernel.org/lkml/20171102193644.GB22686@redhat.com/
[2] https://lore.kernel.org/lkml/20181230154648.GB9832@redhat.com/

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Suggested-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Brian Geffon <bgeffon@google.com>
Cc: Bobby Powers <bobbypowers@gmail.com>
Cc: David Hildenbrand <david@redhat.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/20200220160246.9790-1-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-02 09:35:30 -07:00

202 lines
4.4 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_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);
}