mm: fix MADV_[FREE|DONTNEED] TLB flush miss problem
Nadav reported parallel MADV_DONTNEED on same range has a stale TLB problem and Mel fixed it[1] and found same problem on MADV_FREE[2]. Quote from Mel Gorman: "The race in question is CPU 0 running madv_free and updating some PTEs while CPU 1 is also running madv_free and looking at the same PTEs. CPU 1 may have writable TLB entries for a page but fail the pte_dirty check (because CPU 0 has updated it already) and potentially fail to flush. Hence, when madv_free on CPU 1 returns, there are still potentially writable TLB entries and the underlying PTE is still present so that a subsequent write does not necessarily propagate the dirty bit to the underlying PTE any more. Reclaim at some unknown time at the future may then see that the PTE is still clean and discard the page even though a write has happened in the meantime. I think this is possible but I could have missed some protection in madv_free that prevents it happening." This patch aims for solving both problems all at once and is ready for other problem with KSM, MADV_FREE and soft-dirty story[3]. TLB batch API(tlb_[gather|finish]_mmu] uses [inc|dec]_tlb_flush_pending and mmu_tlb_flush_pending so that when tlb_finish_mmu is called, we can catch there are parallel threads going on. In that case, forcefully, flush TLB to prevent for user to access memory via stale TLB entry although it fail to gather page table entry. I confirmed this patch works with [4] test program Nadav gave so this patch supersedes "mm: Always flush VMA ranges affected by zap_page_range v2" in current mmotm. NOTE: This patch modifies arch-specific TLB gathering interface(x86, ia64, s390, sh, um). It seems most of architecture are straightforward but s390 need to be careful because tlb_flush_mmu works only if mm->context.flush_mm is set to non-zero which happens only a pte entry really is cleared by ptep_get_and_clear and friends. However, this problem never changes the pte entries but need to flush to prevent memory access from stale tlb. [1] http://lkml.kernel.org/r/20170725101230.5v7gvnjmcnkzzql3@techsingularity.net [2] http://lkml.kernel.org/r/20170725100722.2dxnmgypmwnrfawp@suse.de [3] http://lkml.kernel.org/r/BD3A0EBE-ECF4-41D4-87FA-C755EA9AB6BD@gmail.com [4] https://patchwork.kernel.org/patch/9861621/ [minchan@kernel.org: decrease tlb flush pending count in tlb_finish_mmu] Link: http://lkml.kernel.org/r/20170808080821.GA31730@bbox Link: http://lkml.kernel.org/r/20170802000818.4760-7-namit@vmware.com Signed-off-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Nadav Amit <namit@vmware.com> Reported-by: Nadav Amit <namit@vmware.com> Reported-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Mel Gorman <mgorman@techsingularity.net> Cc: Ingo Molnar <mingo@redhat.com> Cc: Russell King <linux@armlinux.org.uk> Cc: Tony Luck <tony.luck@intel.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Jeff Dike <jdike@addtoit.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
parent
0a2dd266dd
commit
99baac21e4
|
@ -168,8 +168,13 @@ arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
|
|||
|
||||
static inline void
|
||||
arch_tlb_finish_mmu(struct mmu_gather *tlb,
|
||||
unsigned long start, unsigned long end)
|
||||
unsigned long start, unsigned long end, bool force)
|
||||
{
|
||||
if (force) {
|
||||
tlb->range_start = start;
|
||||
tlb->range_end = end;
|
||||
}
|
||||
|
||||
tlb_flush_mmu(tlb);
|
||||
|
||||
/* keep the page table cache within bounds */
|
||||
|
|
|
@ -187,8 +187,10 @@ arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
|
|||
*/
|
||||
static inline void
|
||||
arch_tlb_finish_mmu(struct mmu_gather *tlb,
|
||||
unsigned long start, unsigned long end)
|
||||
unsigned long start, unsigned long end, bool force)
|
||||
{
|
||||
if (force)
|
||||
tlb->need_flush = 1;
|
||||
/*
|
||||
* Note: tlb->nr may be 0 at this point, so we can't rely on tlb->start_addr and
|
||||
* tlb->end_addr.
|
||||
|
|
|
@ -77,8 +77,13 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
|
|||
|
||||
static inline void
|
||||
arch_tlb_finish_mmu(struct mmu_gather *tlb,
|
||||
unsigned long start, unsigned long end)
|
||||
unsigned long start, unsigned long end, bool force)
|
||||
{
|
||||
if (force) {
|
||||
tlb->start = start;
|
||||
tlb->end = end;
|
||||
}
|
||||
|
||||
tlb_flush_mmu(tlb);
|
||||
}
|
||||
|
||||
|
|
|
@ -49,9 +49,9 @@ arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
|
|||
|
||||
static inline void
|
||||
arch_tlb_finish_mmu(struct mmu_gather *tlb,
|
||||
unsigned long start, unsigned long end)
|
||||
unsigned long start, unsigned long end, bool force)
|
||||
{
|
||||
if (tlb->fullmm)
|
||||
if (tlb->fullmm || force)
|
||||
flush_tlb_mm(tlb->mm);
|
||||
|
||||
/* keep the page table cache within bounds */
|
||||
|
|
|
@ -87,8 +87,13 @@ tlb_flush_mmu(struct mmu_gather *tlb)
|
|||
*/
|
||||
static inline void
|
||||
arch_tlb_finish_mmu(struct mmu_gather *tlb,
|
||||
unsigned long start, unsigned long end)
|
||||
unsigned long start, unsigned long end, bool force)
|
||||
{
|
||||
if (force) {
|
||||
tlb->start = start;
|
||||
tlb->end = end;
|
||||
tlb->need_flush = 1;
|
||||
}
|
||||
tlb_flush_mmu(tlb);
|
||||
|
||||
/* keep the page table cache within bounds */
|
||||
|
|
|
@ -116,7 +116,7 @@ void arch_tlb_gather_mmu(struct mmu_gather *tlb,
|
|||
struct mm_struct *mm, unsigned long start, unsigned long end);
|
||||
void tlb_flush_mmu(struct mmu_gather *tlb);
|
||||
void arch_tlb_finish_mmu(struct mmu_gather *tlb,
|
||||
unsigned long start, unsigned long end);
|
||||
unsigned long start, unsigned long end, bool force);
|
||||
extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
|
||||
int page_size);
|
||||
|
||||
|
|
|
@ -538,6 +538,14 @@ static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
|
|||
return atomic_read(&mm->tlb_flush_pending) > 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* Returns true if there are two above TLB batching threads in parallel.
|
||||
*/
|
||||
static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
|
||||
{
|
||||
return atomic_read(&mm->tlb_flush_pending) > 1;
|
||||
}
|
||||
|
||||
static inline void init_tlb_flush_pending(struct mm_struct *mm)
|
||||
{
|
||||
atomic_set(&mm->tlb_flush_pending, 0);
|
||||
|
|
18
mm/memory.c
18
mm/memory.c
|
@ -272,10 +272,13 @@ void tlb_flush_mmu(struct mmu_gather *tlb)
|
|||
* that were required.
|
||||
*/
|
||||
void arch_tlb_finish_mmu(struct mmu_gather *tlb,
|
||||
unsigned long start, unsigned long end)
|
||||
unsigned long start, unsigned long end, bool force)
|
||||
{
|
||||
struct mmu_gather_batch *batch, *next;
|
||||
|
||||
if (force)
|
||||
__tlb_adjust_range(tlb, start, end - start);
|
||||
|
||||
tlb_flush_mmu(tlb);
|
||||
|
||||
/* keep the page table cache within bounds */
|
||||
|
@ -404,12 +407,23 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
|
|||
unsigned long start, unsigned long end)
|
||||
{
|
||||
arch_tlb_gather_mmu(tlb, mm, start, end);
|
||||
inc_tlb_flush_pending(tlb->mm);
|
||||
}
|
||||
|
||||
void tlb_finish_mmu(struct mmu_gather *tlb,
|
||||
unsigned long start, unsigned long end)
|
||||
{
|
||||
arch_tlb_finish_mmu(tlb, start, end);
|
||||
/*
|
||||
* If there are parallel threads are doing PTE changes on same range
|
||||
* under non-exclusive lock(e.g., mmap_sem read-side) but defer TLB
|
||||
* flush by batching, a thread has stable TLB entry can fail to flush
|
||||
* the TLB by observing pte_none|!pte_dirty, for example so flush TLB
|
||||
* forcefully if we detect parallel PTE batching threads.
|
||||
*/
|
||||
bool force = mm_tlb_flush_nested(tlb->mm);
|
||||
|
||||
arch_tlb_finish_mmu(tlb, start, end, force);
|
||||
dec_tlb_flush_pending(tlb->mm);
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
Loading…
Reference in a new issue