diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/gup.c | 48 | ||||
| -rw-r--r-- | mm/huge_memory.c | 10 | ||||
| -rw-r--r-- | mm/memory.c | 12 |
3 files changed, 50 insertions, 20 deletions
@@ -59,13 +59,22 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, } /* - * FOLL_FORCE can write to even unwritable pte's, but only - * after we've gone through a COW cycle and they are dirty. + * FOLL_FORCE or a forced COW break can write even to unwritable pte's, + * but only after we've gone through a COW cycle and they are dirty. */ static inline bool can_follow_write_pte(pte_t pte, unsigned int flags) { - return pte_write(pte) || - ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte)); + return pte_write(pte) || ((flags & FOLL_COW) && pte_dirty(pte)); +} + +/* + * A (separate) COW fault might break the page the other way and + * get_user_pages() would return the page from what is now the wrong + * VM. So we need to force a COW break at GUP time even for reads. + */ +static inline bool should_force_cow_break(struct vm_area_struct *vma, unsigned int flags) +{ + return is_cow_mapping(vma->vm_flags) && (flags & FOLL_GET); } static struct page *follow_page_pte(struct vm_area_struct *vma, @@ -509,12 +518,18 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, if (!vma || check_vma_flags(vma, gup_flags)) return i ? : -EFAULT; if (is_vm_hugetlb_page(vma)) { + if (should_force_cow_break(vma, foll_flags)) + foll_flags |= FOLL_WRITE; i = follow_hugetlb_page(mm, vma, pages, vmas, &start, &nr_pages, i, - gup_flags); + foll_flags); continue; } } + + if (should_force_cow_break(vma, foll_flags)) + foll_flags |= FOLL_WRITE; + retry: /* * If we have a pending SIGKILL, don't keep faulting pages and @@ -1346,6 +1361,10 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, /* * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to * the regular GUP. It will only return non-negative values. + * + * Careful, careful! COW breaking can go either way, so a non-write + * access can get ambiguous page results. If you call this function without + * 'write' set, you'd better be sure that you're ok with that ambiguity. */ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) @@ -1375,6 +1394,12 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, * * We do not adopt an rcu_read_lock(.) here as we also want to * block IPIs that come from THPs splitting. + * + * NOTE! We allow read-only gup_fast() here, but you'd better be + * careful about possible COW pages. You'll get _a_ COW page, but + * not necessarily the one you intended to get depending on what + * COW event happens after this. COW may break the page copy in a + * random direction. */ local_irq_save(flags); @@ -1385,15 +1410,22 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, next = pgd_addr_end(addr, end); if (pgd_none(pgd)) break; + /* + * The FAST_GUP case requires FOLL_WRITE even for pure reads, + * because get_user_pages() may need to cause an early COW in + * order to avoid confusing the normal COW routines. So only + * targets that are already writable are safe to do by just + * looking at the page tables. + */ if (unlikely(pgd_huge(pgd))) { - if (!gup_huge_pgd(pgd, pgdp, addr, next, write, + if (!gup_huge_pgd(pgd, pgdp, addr, next, 1, pages, &nr)) break; } else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) { if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr, - PGDIR_SHIFT, next, write, pages, &nr)) + PGDIR_SHIFT, next, 1, pages, &nr)) break; - } else if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + } else if (!gup_pud_range(pgd, addr, next, 1, pages, &nr)) break; } while (pgdp++, addr = next, addr != end); local_irq_restore(flags); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 8e035439ec2c..f7c63bd6506e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1267,13 +1267,12 @@ out_unlock: } /* - * FOLL_FORCE can write to even unwritable pmd's, but only - * after we've gone through a COW cycle and they are dirty. + * FOLL_FORCE or a forced COW break can write even to unwritable pmd's, + * but only after we've gone through a COW cycle and they are dirty. */ static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags) { - return pmd_write(pmd) || - ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd)); + return pmd_write(pmd) || ((flags & FOLL_COW) && pmd_dirty(pmd)); } struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, @@ -1340,9 +1339,6 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, bool was_writable; int flags = 0; - /* A PROT_NONE fault should not end up here */ - BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))); - ptl = pmd_lock(mm, pmdp); if (unlikely(!pmd_same(pmd, *pmdp))) goto out_unlock; diff --git a/mm/memory.c b/mm/memory.c index 360d28224a8e..6bfc6a021c4f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3209,9 +3209,6 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, bool was_writable = pte_write(pte); int flags = 0; - /* A PROT_NONE fault should not end up here */ - BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))); - /* * The "pte" at this point cannot be used safely without * validation through pte_unmap_same(). It's of NUMA type but @@ -3304,6 +3301,11 @@ static int wp_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma, return VM_FAULT_FALLBACK; } +static inline bool vma_is_accessible(struct vm_area_struct *vma) +{ + return vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE); +} + /* * These routines also need to handle stuff like marking pages dirty * and/or accessed for architectures that don't do it in hardware (most @@ -3350,7 +3352,7 @@ static int handle_pte_fault(struct mm_struct *mm, pte, pmd, flags, entry); } - if (pte_protnone(entry)) + if (pte_protnone(entry) && vma_is_accessible(vma)) return do_numa_page(mm, vma, address, entry, pte, pmd); ptl = pte_lockptr(mm, pmd); @@ -3425,7 +3427,7 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (pmd_trans_splitting(orig_pmd)) return 0; - if (pmd_protnone(orig_pmd)) + if (pmd_protnone(orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(mm, vma, address, orig_pmd, pmd); |