linux_dsm_epyc7002/arch/um/include/asm/tlb.h
Minchan Kim 99baac21e4 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>
2017-08-10 15:54:07 -07:00

163 lines
3.9 KiB
C

#ifndef __UM_TLB_H
#define __UM_TLB_H
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <asm/percpu.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#define tlb_start_vma(tlb, vma) do { } while (0)
#define tlb_end_vma(tlb, vma) do { } while (0)
#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
/* struct mmu_gather is an opaque type used by the mm code for passing around
* any data needed by arch specific code for tlb_remove_page.
*/
struct mmu_gather {
struct mm_struct *mm;
unsigned int need_flush; /* Really unmapped some ptes? */
unsigned long start;
unsigned long end;
unsigned int fullmm; /* non-zero means full mm flush */
};
static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
unsigned long address)
{
if (tlb->start > address)
tlb->start = address;
if (tlb->end < address + PAGE_SIZE)
tlb->end = address + PAGE_SIZE;
}
static inline void init_tlb_gather(struct mmu_gather *tlb)
{
tlb->need_flush = 0;
tlb->start = TASK_SIZE;
tlb->end = 0;
if (tlb->fullmm) {
tlb->start = 0;
tlb->end = TASK_SIZE;
}
}
static inline void
arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
unsigned long start, unsigned long end)
{
tlb->mm = mm;
tlb->start = start;
tlb->end = end;
tlb->fullmm = !(start | (end+1));
init_tlb_gather(tlb);
}
extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
unsigned long end);
static inline void
tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
{
flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end);
}
static inline void
tlb_flush_mmu_free(struct mmu_gather *tlb)
{
init_tlb_gather(tlb);
}
static inline void
tlb_flush_mmu(struct mmu_gather *tlb)
{
if (!tlb->need_flush)
return;
tlb_flush_mmu_tlbonly(tlb);
tlb_flush_mmu_free(tlb);
}
/* arch_tlb_finish_mmu
* Called at the end of the shootdown operation to free up any resources
* that were required.
*/
static inline void
arch_tlb_finish_mmu(struct mmu_gather *tlb,
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 */
check_pgt_cache();
}
/* tlb_remove_page
* Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)),
* while handling the additional races in SMP caused by other CPUs
* caching valid mappings in their TLBs.
*/
static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
tlb->need_flush = 1;
free_page_and_swap_cache(page);
return false; /* avoid calling tlb_flush_mmu */
}
static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
__tlb_remove_page(tlb, page);
}
static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
struct page *page, int page_size)
{
return __tlb_remove_page(tlb, page);
}
static inline void tlb_remove_page_size(struct mmu_gather *tlb,
struct page *page, int page_size)
{
return tlb_remove_page(tlb, page);
}
/**
* tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
*
* Record the fact that pte's were really umapped in ->need_flush, so we can
* later optimise away the tlb invalidate. This helps when userspace is
* unmapping already-unmapped pages, which happens quite a lot.
*/
#define tlb_remove_tlb_entry(tlb, ptep, address) \
do { \
tlb->need_flush = 1; \
__tlb_remove_tlb_entry(tlb, ptep, address); \
} while (0)
#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \
tlb_remove_tlb_entry(tlb, ptep, address)
#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
unsigned int page_size)
{
}
#define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr)
#define pud_free_tlb(tlb, pudp, addr) __pud_free_tlb(tlb, pudp, addr)
#define pmd_free_tlb(tlb, pmdp, addr) __pmd_free_tlb(tlb, pmdp, addr)
#define tlb_migrate_finish(mm) do {} while (0)
#endif