diff --git a/arch/Kconfig b/arch/Kconfig index e1e540ffa979..b70c952ac838 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -535,6 +535,11 @@ config HAVE_IRQ_TIME_ACCOUNTING Archs need to ensure they use a high enough resolution clock to support irq time accounting and then call enable_sched_clock_irqtime(). +config HAVE_MOVE_PMD + bool + help + Archs that select this are able to move page tables at the PMD level. + config HAVE_ARCH_TRANSPARENT_HUGEPAGE bool diff --git a/mm/mremap.c b/mm/mremap.c index fc3f92962a7e..3320616ed93f 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -191,6 +191,52 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, drop_rmap_locks(vma); } +#ifdef CONFIG_HAVE_MOVE_PMD +static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr, + unsigned long new_addr, unsigned long old_end, + pmd_t *old_pmd, pmd_t *new_pmd) +{ + spinlock_t *old_ptl, *new_ptl; + struct mm_struct *mm = vma->vm_mm; + pmd_t pmd; + + if ((old_addr & ~PMD_MASK) || (new_addr & ~PMD_MASK) + || old_end - old_addr < PMD_SIZE) + return false; + + /* + * The destination pmd shouldn't be established, free_pgtables() + * should have release it. + */ + if (WARN_ON(!pmd_none(*new_pmd))) + return false; + + /* + * We don't have to worry about the ordering of src and dst + * ptlocks because exclusive mmap_sem prevents deadlock. + */ + old_ptl = pmd_lock(vma->vm_mm, old_pmd); + new_ptl = pmd_lockptr(mm, new_pmd); + if (new_ptl != old_ptl) + spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); + + /* Clear the pmd */ + pmd = *old_pmd; + pmd_clear(old_pmd); + + VM_BUG_ON(!pmd_none(*new_pmd)); + + /* Set the new pmd */ + set_pmd_at(mm, new_addr, new_pmd, pmd); + flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE); + if (new_ptl != old_ptl) + spin_unlock(new_ptl); + spin_unlock(old_ptl); + + return true; +} +#endif + unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, @@ -235,7 +281,25 @@ unsigned long move_page_tables(struct vm_area_struct *vma, split_huge_pmd(vma, old_pmd, old_addr); if (pmd_trans_unstable(old_pmd)) continue; + } else if (extent == PMD_SIZE) { +#ifdef CONFIG_HAVE_MOVE_PMD + /* + * If the extent is PMD-sized, try to speed the move by + * moving at the PMD level if possible. + */ + bool moved; + + if (need_rmap_locks) + take_rmap_locks(vma); + moved = move_normal_pmd(vma, old_addr, new_addr, + old_end, old_pmd, new_pmd); + if (need_rmap_locks) + drop_rmap_locks(vma); + if (moved) + continue; +#endif } + if (pte_alloc(new_vma->vm_mm, new_pmd)) break; next = (new_addr + PMD_SIZE) & PMD_MASK;