tmp_suning_uos_patched/arch/ia64/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

283 lines
7.2 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* MMU fault handling support.
*
* Copyright (C) 1998-2002 Hewlett-Packard Co
* David Mosberger-Tang <davidm@hpl.hp.com>
*/
#include <linux/sched/signal.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/extable.h>
#include <linux/interrupt.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/prefetch.h>
#include <linux/uaccess.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/exception.h>
extern int die(char *, struct pt_regs *, long);
/*
* Return TRUE if ADDRESS points at a page in the kernel's mapped segment
* (inside region 5, on ia64) and that page is present.
*/
static int
mapped_kernel_page_is_present (unsigned long address)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *ptep, pte;
pgd = pgd_offset_k(address);
if (pgd_none(*pgd) || pgd_bad(*pgd))
return 0;
pud = pud_offset(pgd, address);
if (pud_none(*pud) || pud_bad(*pud))
return 0;
pmd = pmd_offset(pud, address);
if (pmd_none(*pmd) || pmd_bad(*pmd))
return 0;
ptep = pte_offset_kernel(pmd, address);
if (!ptep)
return 0;
pte = *ptep;
return pte_present(pte);
}
# define VM_READ_BIT 0
# define VM_WRITE_BIT 1
# define VM_EXEC_BIT 2
void __kprobes
ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *regs)
{
int signal = SIGSEGV, code = SEGV_MAPERR;
struct vm_area_struct *vma, *prev_vma;
struct mm_struct *mm = current->mm;
unsigned long mask;
vm_fault_t fault;
unsigned int flags = FAULT_FLAG_DEFAULT;
mask = ((((isr >> IA64_ISR_X_BIT) & 1UL) << VM_EXEC_BIT)
| (((isr >> IA64_ISR_W_BIT) & 1UL) << VM_WRITE_BIT));
/* mmap_sem is performance critical.... */
prefetchw(&mm->mmap_sem);
/*
* If we're in an interrupt or have no user context, we must not take the fault..
*/
if (faulthandler_disabled() || !mm)
goto no_context;
#ifdef CONFIG_VIRTUAL_MEM_MAP
/*
* If fault is in region 5 and we are in the kernel, we may already
* have the mmap_sem (pfn_valid macro is called during mmap). There
* is no vma for region 5 addr's anyway, so skip getting the semaphore
* and go directly to the exception handling code.
*/
if ((REGION_NUMBER(address) == 5) && !user_mode(regs))
goto bad_area_no_up;
#endif
/*
* This is to handle the kprobes on user space access instructions
*/
if (kprobe_page_fault(regs, TRAP_BRKPT))
return;
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
if (mask & VM_WRITE)
flags |= FAULT_FLAG_WRITE;
retry:
down_read(&mm->mmap_sem);
vma = find_vma_prev(mm, address, &prev_vma);
if (!vma && !prev_vma )
goto bad_area;
/*
* find_vma_prev() returns vma such that address < vma->vm_end or NULL
*
* May find no vma, but could be that the last vm area is the
* register backing store that needs to expand upwards, in
* this case vma will be null, but prev_vma will ne non-null
*/
if (( !vma && prev_vma ) || (address < vma->vm_start) )
goto check_expansion;
good_area:
code = SEGV_ACCERR;
/* OK, we've got a good vm_area for this memory area. Check the access permissions: */
# if (((1 << VM_READ_BIT) != VM_READ || (1 << VM_WRITE_BIT) != VM_WRITE) \
|| (1 << VM_EXEC_BIT) != VM_EXEC)
# error File is out of sync with <linux/mm.h>. Please update.
# endif
if (((isr >> IA64_ISR_R_BIT) & 1UL) && (!(vma->vm_flags & (VM_READ | VM_WRITE))))
goto bad_area;
if ((vma->vm_flags & mask) != mask)
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(vma, address, flags);
if (fault_signal_pending(fault, regs))
return;
if (unlikely(fault & VM_FAULT_ERROR)) {
/*
* We ran out of memory, or some other thing happened
* to us that made us unable to handle the page fault
* gracefully.
*/
if (fault & VM_FAULT_OOM) {
goto out_of_memory;
} else if (fault & VM_FAULT_SIGSEGV) {
goto bad_area;
} else if (fault & VM_FAULT_SIGBUS) {
signal = SIGBUS;
goto bad_area;
}
BUG();
}
if (flags & FAULT_FLAG_ALLOW_RETRY) {
if (fault & VM_FAULT_MAJOR)
current->maj_flt++;
else
current->min_flt++;
if (fault & VM_FAULT_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;
check_expansion:
if (!(prev_vma && (prev_vma->vm_flags & VM_GROWSUP) && (address == prev_vma->vm_end))) {
if (!vma)
goto bad_area;
if (!(vma->vm_flags & VM_GROWSDOWN))
goto bad_area;
if (REGION_NUMBER(address) != REGION_NUMBER(vma->vm_start)
|| REGION_OFFSET(address) >= RGN_MAP_LIMIT)
goto bad_area;
if (expand_stack(vma, address))
goto bad_area;
} else {
vma = prev_vma;
if (REGION_NUMBER(address) != REGION_NUMBER(vma->vm_start)
|| REGION_OFFSET(address) >= RGN_MAP_LIMIT)
goto bad_area;
/*
* Since the register backing store is accessed sequentially,
* we disallow growing it by more than a page at a time.
*/
if (address > vma->vm_end + PAGE_SIZE - sizeof(long))
goto bad_area;
if (expand_upwards(vma, address))
goto bad_area;
}
goto good_area;
bad_area:
up_read(&mm->mmap_sem);
#ifdef CONFIG_VIRTUAL_MEM_MAP
bad_area_no_up:
#endif
if ((isr & IA64_ISR_SP)
|| ((isr & IA64_ISR_NA) && (isr & IA64_ISR_CODE_MASK) == IA64_ISR_CODE_LFETCH))
{
/*
* This fault was due to a speculative load or lfetch.fault, set the "ed"
* bit in the psr to ensure forward progress. (Target register will get a
* NaT for ld.s, lfetch will be canceled.)
*/
ia64_psr(regs)->ed = 1;
return;
}
if (user_mode(regs)) {
force_sig_fault(signal, code, (void __user *) address,
0, __ISR_VALID, isr);
return;
}
no_context:
if ((isr & IA64_ISR_SP)
|| ((isr & IA64_ISR_NA) && (isr & IA64_ISR_CODE_MASK) == IA64_ISR_CODE_LFETCH))
{
/*
* This fault was due to a speculative load or lfetch.fault, set the "ed"
* bit in the psr to ensure forward progress. (Target register will get a
* NaT for ld.s, lfetch will be canceled.)
*/
ia64_psr(regs)->ed = 1;
return;
}
/*
* Since we have no vma's for region 5, we might get here even if the address is
* valid, due to the VHPT walker inserting a non present translation that becomes
* stale. If that happens, the non present fault handler already purged the stale
* translation, which fixed the problem. So, we check to see if the translation is
* valid, and return if it is.
*/
if (REGION_NUMBER(address) == 5 && mapped_kernel_page_is_present(address))
return;
if (ia64_done_with_exception(regs))
return;
/*
* Oops. The kernel tried to access some bad page. We'll have to terminate things
* with extreme prejudice.
*/
bust_spinlocks(1);
if (address < PAGE_SIZE)
printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference (address %016lx)\n", address);
else
printk(KERN_ALERT "Unable to handle kernel paging request at "
"virtual address %016lx\n", address);
if (die("Oops", regs, isr))
regs = NULL;
bust_spinlocks(0);
if (regs)
do_exit(SIGKILL);
return;
out_of_memory:
up_read(&mm->mmap_sem);
if (!user_mode(regs))
goto no_context;
pagefault_out_of_memory();
}