diff --git a/include/linux/rmap.h b/include/linux/rmap.h index d7d6d4eb1794..91ccae946716 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -98,7 +98,8 @@ enum ttu_flags { * do a final flush if necessary */ TTU_RMAP_LOCKED = 0x80, /* do not grab rmap lock: * caller holds it */ - TTU_SPLIT_FREEZE = 0x100, /* freeze pte under splitting thp */ + TTU_SPLIT_FREEZE = 0x100, /* freeze pte under splitting thp */ + TTU_SYNC = 0x200, /* avoid racy checks with PVMW_SYNC */ }; #ifdef CONFIG_MMU diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 47d95048f31e..9cb4e1e7e282 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2461,7 +2461,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, static void unmap_page(struct page *page) { enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS | - TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD; + TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC; bool unmap_success; VM_BUG_ON_PAGE(!PageHead(page), page); diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index eff4b4520c8d..5a2a371a2c98 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -207,6 +207,17 @@ restart: pvmw->ptl = NULL; } } else if (!pmd_present(pmde)) { + /* + * If PVMW_SYNC, take and drop THP pmd lock so that we + * cannot return prematurely, while zap_huge_pmd() has + * cleared *pmd but not decremented compound_mapcount(). + */ + if ((pvmw->flags & PVMW_SYNC) && + PageTransCompound(pvmw->page)) { + spinlock_t *ptl = pmd_lock(mm, pvmw->pmd); + + spin_unlock(ptl); + } return false; } if (!map_pte(pvmw)) diff --git a/mm/rmap.c b/mm/rmap.c index cbde11c06a76..c61a6384d950 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1353,6 +1353,15 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)arg; + /* + * When racing against e.g. zap_pte_range() on another cpu, + * in between its ptep_get_and_clear_full() and page_remove_rmap(), + * try_to_unmap() may return false when it is about to become true, + * if page table locking is skipped: use TTU_SYNC to wait for that. + */ + if (flags & TTU_SYNC) + pvmw.flags = PVMW_SYNC; + /* munlock has nothing to gain from examining un-locked vmas */ if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED)) return true; @@ -1731,7 +1740,13 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags) else rmap_walk(page, &rwc); - return !page_mapcount(page) ? true : false; + /* + * When racing against e.g. zap_pte_range() on another cpu, + * in between its ptep_get_and_clear_full() and page_remove_rmap(), + * try_to_unmap() may return false when it is about to become true, + * if page table locking is skipped: use TTU_SYNC to wait for that. + */ + return !page_mapcount(page); } /**