diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/pagewalk.c | 21 | ||||
| -rw-r--r-- | mm/ptdump.c | 4 | ||||
| -rw-r--r-- | mm/rmap.c | 29 | ||||
| -rw-r--r-- | mm/slab_common.c | 45 |
4 files changed, 59 insertions, 40 deletions
diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 9b3db11a4d1d..fa7a3d21a751 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -110,7 +110,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, do { again: next = pmd_addr_end(addr, end); - if (pmd_none(*pmd) || (!walk->vma && !walk->no_vma)) { + if (pmd_none(*pmd)) { if (ops->pte_hole) err = ops->pte_hole(addr, next, depth, walk); if (err) @@ -171,7 +171,7 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, do { again: next = pud_addr_end(addr, end); - if (pud_none(*pud) || (!walk->vma && !walk->no_vma)) { + if (pud_none(*pud)) { if (ops->pte_hole) err = ops->pte_hole(addr, next, depth, walk); if (err) @@ -366,19 +366,19 @@ static int __walk_page_range(unsigned long start, unsigned long end, struct vm_area_struct *vma = walk->vma; const struct mm_walk_ops *ops = walk->ops; - if (vma && ops->pre_vma) { + if (ops->pre_vma) { err = ops->pre_vma(start, end, walk); if (err) return err; } - if (vma && is_vm_hugetlb_page(vma)) { + if (is_vm_hugetlb_page(vma)) { if (ops->hugetlb_entry) err = walk_hugetlb_range(start, end, walk); } else err = walk_pgd_range(start, end, walk); - if (vma && ops->post_vma) + if (ops->post_vma) ops->post_vma(walk); return err; @@ -450,9 +450,13 @@ int walk_page_range(struct mm_struct *mm, unsigned long start, if (!vma) { /* after the last vma */ walk.vma = NULL; next = end; + if (ops->pte_hole) + err = ops->pte_hole(start, next, -1, &walk); } else if (start < vma->vm_start) { /* outside vma */ walk.vma = NULL; next = min(end, vma->vm_start); + if (ops->pte_hole) + err = ops->pte_hole(start, next, -1, &walk); } else { /* inside vma */ walk.vma = vma; next = min(end, vma->vm_end); @@ -470,9 +474,8 @@ int walk_page_range(struct mm_struct *mm, unsigned long start, } if (err < 0) break; - } - if (walk.vma || walk.ops->pte_hole) err = __walk_page_range(start, next, &walk); + } if (err) break; } while (start = next, start < end); @@ -501,9 +504,9 @@ int walk_page_range_novma(struct mm_struct *mm, unsigned long start, if (start >= end || !walk.mm) return -EINVAL; - mmap_assert_locked(walk.mm); + mmap_assert_write_locked(walk.mm); - return __walk_page_range(start, end, &walk); + return walk_pgd_range(start, end, &walk); } int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, diff --git a/mm/ptdump.c b/mm/ptdump.c index eea3d28d173c..8adab455a68b 100644 --- a/mm/ptdump.c +++ b/mm/ptdump.c @@ -152,13 +152,13 @@ void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd) { const struct ptdump_range *range = st->range; - mmap_read_lock(mm); + mmap_write_lock(mm); while (range->start != range->end) { walk_page_range_novma(mm, range->start, range->end, &ptdump_ops, pgd, st); range++; } - mmap_read_unlock(mm); + mmap_write_unlock(mm); /* Flush out the last page */ st->note_page(st, 0, -1, 0); diff --git a/mm/rmap.c b/mm/rmap.c index edc06c52bc82..93d5a6f793d2 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -93,7 +93,8 @@ static inline struct anon_vma *anon_vma_alloc(void) anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); - anon_vma->degree = 1; /* Reference for first vma */ + anon_vma->num_children = 0; + anon_vma->num_active_vmas = 0; anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called @@ -201,6 +202,7 @@ int __anon_vma_prepare(struct vm_area_struct *vma) anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; + anon_vma->num_children++; /* self-parent link for new root */ allocated = anon_vma; } @@ -210,8 +212,7 @@ int __anon_vma_prepare(struct vm_area_struct *vma) if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_link(vma, avc, anon_vma); - /* vma reference or self-parent link for new root */ - anon_vma->degree++; + anon_vma->num_active_vmas++; allocated = NULL; avc = NULL; } @@ -296,19 +297,19 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) anon_vma_chain_link(dst, avc, anon_vma); /* - * Reuse existing anon_vma if its degree lower than two, - * that means it has no vma and only one anon_vma child. + * Reuse existing anon_vma if it has no vma and only one + * anon_vma child. * - * Do not choose parent anon_vma, otherwise first child - * will always reuse it. Root anon_vma is never reused: + * Root anon_vma is never reused: * it has self-parent reference and at least one child. */ if (!dst->anon_vma && src->anon_vma && - anon_vma != src->anon_vma && anon_vma->degree < 2) + anon_vma->num_children < 2 && + anon_vma->num_active_vmas == 0) dst->anon_vma = anon_vma; } if (dst->anon_vma) - dst->anon_vma->degree++; + dst->anon_vma->num_active_vmas++; unlock_anon_vma_root(root); return 0; @@ -358,6 +359,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) anon_vma = anon_vma_alloc(); if (!anon_vma) goto out_error; + anon_vma->num_active_vmas++; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_error_free_anon_vma; @@ -378,7 +380,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); - anon_vma->parent->degree++; + anon_vma->parent->num_children++; anon_vma_unlock_write(anon_vma); return 0; @@ -410,7 +412,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma) * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { - anon_vma->parent->degree--; + anon_vma->parent->num_children--; continue; } @@ -418,7 +420,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma) anon_vma_chain_free(avc); } if (vma->anon_vma) { - vma->anon_vma->degree--; + vma->anon_vma->num_active_vmas--; /* * vma would still be needed after unlink, and anon_vma will be prepared @@ -436,7 +438,8 @@ void unlink_anon_vmas(struct vm_area_struct *vma) list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; - VM_WARN_ON(anon_vma->degree); + VM_WARN_ON(anon_vma->num_children); + VM_WARN_ON(anon_vma->num_active_vmas); put_anon_vma(anon_vma); list_del(&avc->same_vma); diff --git a/mm/slab_common.c b/mm/slab_common.c index 17996649cfe3..07b948288f84 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -392,6 +392,28 @@ kmem_cache_create(const char *name, unsigned int size, unsigned int align, } EXPORT_SYMBOL(kmem_cache_create); +#ifdef SLAB_SUPPORTS_SYSFS +/* + * For a given kmem_cache, kmem_cache_destroy() should only be called + * once or there will be a use-after-free problem. The actual deletion + * and release of the kobject does not need slab_mutex or cpu_hotplug_lock + * protection. So they are now done without holding those locks. + * + * Note that there will be a slight delay in the deletion of sysfs files + * if kmem_cache_release() is called indrectly from a work function. + */ +static void kmem_cache_release(struct kmem_cache *s) +{ + sysfs_slab_unlink(s); + sysfs_slab_release(s); +} +#else +static void kmem_cache_release(struct kmem_cache *s) +{ + slab_kmem_cache_release(s); +} +#endif + static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work) { LIST_HEAD(to_destroy); @@ -418,11 +440,7 @@ static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work) list_for_each_entry_safe(s, s2, &to_destroy, list) { debugfs_slab_release(s); kfence_shutdown_cache(s); -#ifdef SLAB_SUPPORTS_SYSFS - sysfs_slab_release(s); -#else - slab_kmem_cache_release(s); -#endif + kmem_cache_release(s); } } @@ -437,20 +455,11 @@ static int shutdown_cache(struct kmem_cache *s) list_del(&s->list); if (s->flags & SLAB_TYPESAFE_BY_RCU) { -#ifdef SLAB_SUPPORTS_SYSFS - sysfs_slab_unlink(s); -#endif list_add_tail(&s->list, &slab_caches_to_rcu_destroy); schedule_work(&slab_caches_to_rcu_destroy_work); } else { kfence_shutdown_cache(s); debugfs_slab_release(s); -#ifdef SLAB_SUPPORTS_SYSFS - sysfs_slab_unlink(s); - sysfs_slab_release(s); -#else - slab_kmem_cache_release(s); -#endif } return 0; @@ -465,14 +474,16 @@ void slab_kmem_cache_release(struct kmem_cache *s) void kmem_cache_destroy(struct kmem_cache *s) { + int refcnt; + if (unlikely(!s) || !kasan_check_byte(s)) return; cpus_read_lock(); mutex_lock(&slab_mutex); - s->refcount--; - if (s->refcount) + refcnt = --s->refcount; + if (refcnt) goto out_unlock; WARN(shutdown_cache(s), @@ -481,6 +492,8 @@ void kmem_cache_destroy(struct kmem_cache *s) out_unlock: mutex_unlock(&slab_mutex); cpus_read_unlock(); + if (!refcnt && !(s->flags & SLAB_TYPESAFE_BY_RCU)) + kmem_cache_release(s); } EXPORT_SYMBOL(kmem_cache_destroy); |