diff options
Diffstat (limited to 'mm/memory.c')
-rw-r--r-- | mm/memory.c | 35 |
1 files changed, 27 insertions, 8 deletions
diff --git a/mm/memory.c b/mm/memory.c index 83be99d9d8a1..fc1987dfd8cc 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1649,10 +1649,14 @@ EXPORT_SYMBOL(vm_insert_pfn_prot); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { + pgprot_t pgprot = vma->vm_page_prot; + BUG_ON(!(vma->vm_flags & VM_MIXEDMAP)); if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; + if (track_pfn_insert(vma, &pgprot, pfn)) + return -EINVAL; /* * If we don't have pte special, then we have to use the pfn_valid() @@ -1670,9 +1674,9 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, * result in pfn_t_has_page() == false. */ page = pfn_to_page(pfn_t_to_pfn(pfn)); - return insert_page(vma, addr, page, vma->vm_page_prot); + return insert_page(vma, addr, page, pgprot); } - return insert_pfn(vma, addr, pfn, vma->vm_page_prot); + return insert_pfn(vma, addr, pfn, pgprot); } EXPORT_SYMBOL(vm_insert_mixed); @@ -3351,9 +3355,6 @@ static int do_numa_page(struct fault_env *fe, pte_t pte) 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 @@ -3398,7 +3399,7 @@ static int do_numa_page(struct fault_env *fe, pte_t pte) * pte_dirty has unpredictable behaviour between PTE scan updates, * background writeback, dirty balancing and application behaviour. */ - if (!(vma->vm_flags & VM_WRITE)) + if (!pte_write(pte)) flags |= TNF_NO_GROUP; /* @@ -3458,6 +3459,11 @@ static int wp_huge_pmd(struct fault_env *fe, pmd_t orig_pmd) 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 @@ -3524,7 +3530,7 @@ static int handle_pte_fault(struct fault_env *fe) if (!pte_present(entry)) return do_swap_page(fe, entry); - if (pte_protnone(entry)) + if (pte_protnone(entry) && vma_is_accessible(fe->vma)) return do_numa_page(fe, entry); fe->ptl = pte_lockptr(fe->vma->vm_mm, fe->pmd); @@ -3590,7 +3596,7 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, barrier(); if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) { - if (pmd_protnone(orig_pmd)) + if (pmd_protnone(orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(&fe, orig_pmd); if ((fe.flags & FAULT_FLAG_WRITE) && @@ -3656,6 +3662,19 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address, mem_cgroup_oom_synchronize(false); } + /* + * This mm has been already reaped by the oom reaper and so the + * refault cannot be trusted in general. Anonymous refaults would + * lose data and give a zero page instead e.g. This is especially + * problem for use_mm() because regular tasks will just die and + * the corrupted data will not be visible anywhere while kthread + * will outlive the oom victim and potentially propagate the date + * further. + */ + if (unlikely((current->flags & PF_KTHREAD) && !(ret & VM_FAULT_ERROR) + && test_bit(MMF_UNSTABLE, &vma->vm_mm->flags))) + ret = VM_FAULT_SIGBUS; + return ret; } EXPORT_SYMBOL_GPL(handle_mm_fault); |