diff options
Diffstat (limited to 'mm/hugetlb.c')
| -rw-r--r-- | mm/hugetlb.c | 39 |
1 files changed, 23 insertions, 16 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9fd722769927..85032de5e20f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -582,7 +582,7 @@ retry_cpuset: for_each_zone_zonelist_nodemask(zone, z, zonelist, MAX_NR_ZONES - 1, nodemask) { - if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask(h))) { + if (cpuset_zone_allowed(zone, htlb_alloc_mask(h))) { page = dequeue_huge_page_node(h, zone_to_nid(zone)); if (page) { if (avoid_reserve) @@ -1457,7 +1457,7 @@ int __weak alloc_bootmem_huge_page(struct hstate *h) return 0; found: - BUG_ON((unsigned long)virt_to_phys(m) & (huge_page_size(h) - 1)); + BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h))); /* Put them into a private list first because mem_map is not up yet */ list_add(&m->list, &huge_boot_pages); m->hstate = h; @@ -2083,7 +2083,7 @@ static void hugetlb_register_node(struct node *node) * devices of nodes that have memory. All on-line nodes should have * registered their associated device by this time. */ -static void hugetlb_register_all_nodes(void) +static void __init hugetlb_register_all_nodes(void) { int nid; @@ -2598,8 +2598,11 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, } set_huge_pte_at(dst, addr, dst_pte, entry); } else { - if (cow) + if (cow) { huge_ptep_set_wrprotect(src, addr, src_pte); + mmu_notifier_invalidate_range(src, mmun_start, + mmun_end); + } entry = huge_ptep_get(src_pte); ptepage = pte_page(entry); get_page(ptepage); @@ -2638,8 +2641,9 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, tlb_start_vma(tlb, vma); mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); + address = start; again: - for (address = start; address < end; address += sz) { + for (; address < end; address += sz) { ptep = huge_pte_offset(mm, address); if (!ptep) continue; @@ -2686,6 +2690,7 @@ again: page_remove_rmap(page); force_flush = !__tlb_remove_page(tlb, page); if (force_flush) { + address += sz; spin_unlock(ptl); break; } @@ -2724,9 +2729,9 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb, * on its way out. We're lucky that the flag has such an appropriate * name, and can in fact be safely cleared here. We could clear it * before the __unmap_hugepage_range above, but all that's necessary - * is to clear it before releasing the i_mmap_mutex. This works + * is to clear it before releasing the i_mmap_rwsem. This works * because in the context this is called, the VMA is about to be - * destroyed and the i_mmap_mutex is held. + * destroyed and the i_mmap_rwsem is held. */ vma->vm_flags &= ~VM_MAYSHARE; } @@ -2772,7 +2777,7 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, * this mapping should be shared between all the VMAs, * __unmap_hugepage_range() is called as the lock is already held */ - mutex_lock(&mapping->i_mmap_mutex); + i_mmap_lock_write(mapping); vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) { /* Do not unmap the current VMA */ if (iter_vma == vma) @@ -2789,7 +2794,7 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, unmap_hugepage_range(iter_vma, address, address + huge_page_size(h), page); } - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_write(mapping); } /* @@ -2899,6 +2904,7 @@ retry_avoidcopy: /* Break COW */ huge_ptep_clear_flush(vma, address, ptep); + mmu_notifier_invalidate_range(mm, mmun_start, mmun_end); set_huge_pte_at(mm, address, ptep, make_huge_pte(vma, new_page, 1)); page_remove_rmap(old_page); @@ -3346,7 +3352,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, flush_cache_range(vma, address, end); mmu_notifier_invalidate_range_start(mm, start, end); - mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex); + i_mmap_lock_write(vma->vm_file->f_mapping); for (; address < end; address += huge_page_size(h)) { spinlock_t *ptl; ptep = huge_pte_offset(mm, address); @@ -3368,13 +3374,14 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, spin_unlock(ptl); } /* - * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare + * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare * may have cleared our pud entry and done put_page on the page table: - * once we release i_mmap_mutex, another task can do the final put_page + * once we release i_mmap_rwsem, another task can do the final put_page * and that page table be reused and filled with junk. */ flush_tlb_range(vma, start, end); - mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); + mmu_notifier_invalidate_range(mm, start, end); + i_mmap_unlock_write(vma->vm_file->f_mapping); mmu_notifier_invalidate_range_end(mm, start, end); return pages << h->order; @@ -3523,7 +3530,7 @@ static int vma_shareable(struct vm_area_struct *vma, unsigned long addr) * and returns the corresponding pte. While this is not necessary for the * !shared pmd case because we can allocate the pmd later as well, it makes the * code much cleaner. pmd allocation is essential for the shared case because - * pud has to be populated inside the same i_mmap_mutex section - otherwise + * pud has to be populated inside the same i_mmap_rwsem section - otherwise * racing tasks could either miss the sharing (see huge_pte_offset) or select a * bad pmd for sharing. */ @@ -3542,7 +3549,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) if (!vma_shareable(vma, addr)) return (pte_t *)pmd_alloc(mm, pud, addr); - mutex_lock(&mapping->i_mmap_mutex); + i_mmap_lock_write(mapping); vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { if (svma == vma) continue; @@ -3570,7 +3577,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) spin_unlock(ptl); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_write(mapping); return pte; } |