diff options
Diffstat (limited to 'mm/vmalloc.c')
| -rw-r--r-- | mm/vmalloc.c | 840 |
1 files changed, 580 insertions, 260 deletions
diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e34ea860153f..ecbac900c35f 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -100,12 +100,18 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct page *page; unsigned long size = PAGE_SIZE; + if (WARN_ON_ONCE(!PAGE_ALIGNED(end - addr))) + return -EINVAL; + pfn = phys_addr >> PAGE_SHIFT; pte = pte_alloc_kernel_track(pmd, addr, mask); if (!pte) return -ENOMEM; + + arch_enter_lazy_mmu_mode(); + do { - if (!pte_none(ptep_get(pte))) { + if (unlikely(!pte_none(ptep_get(pte)))) { if (pfn_valid(pfn)) { page = pfn_to_page(pfn); dump_page(page, "remapping already mapped page"); @@ -127,6 +133,8 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot)); pfn++; } while (pte += PFN_DOWN(size), addr += size, addr != end); + + arch_leave_lazy_mmu_mode(); *mask |= PGTBL_PTE_MODIFIED; return 0; } @@ -162,6 +170,7 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, { pmd_t *pmd; unsigned long next; + int err = 0; pmd = pmd_alloc_track(&init_mm, pud, addr, mask); if (!pmd) @@ -175,10 +184,11 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, continue; } - if (vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask)) - return -ENOMEM; + err = vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask); + if (err) + break; } while (pmd++, phys_addr += (next - addr), addr = next, addr != end); - return 0; + return err; } static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end, @@ -212,6 +222,7 @@ static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, { pud_t *pud; unsigned long next; + int err = 0; pud = pud_alloc_track(&init_mm, p4d, addr, mask); if (!pud) @@ -225,11 +236,11 @@ static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, continue; } - if (vmap_pmd_range(pud, addr, next, phys_addr, prot, - max_page_shift, mask)) - return -ENOMEM; + err = vmap_pmd_range(pud, addr, next, phys_addr, prot, max_page_shift, mask); + if (err) + break; } while (pud++, phys_addr += (next - addr), addr = next, addr != end); - return 0; + return err; } static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end, @@ -263,6 +274,7 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, { p4d_t *p4d; unsigned long next; + int err = 0; p4d = p4d_alloc_track(&init_mm, pgd, addr, mask); if (!p4d) @@ -276,11 +288,11 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, continue; } - if (vmap_pud_range(p4d, addr, next, phys_addr, prot, - max_page_shift, mask)) - return -ENOMEM; + err = vmap_pud_range(p4d, addr, next, phys_addr, prot, max_page_shift, mask); + if (err) + break; } while (p4d++, phys_addr += (next - addr), addr = next, addr != end); - return 0; + return err; } static int vmap_range_noflush(unsigned long addr, unsigned long end, @@ -350,12 +362,30 @@ static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pte_t *pte; + pte_t ptent; + unsigned long size = PAGE_SIZE; pte = pte_offset_kernel(pmd, addr); + arch_enter_lazy_mmu_mode(); + do { - pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte); +#ifdef CONFIG_HUGETLB_PAGE + size = arch_vmap_pte_range_unmap_size(addr, pte); + if (size != PAGE_SIZE) { + if (WARN_ON(!IS_ALIGNED(addr, size))) { + addr = ALIGN_DOWN(addr, size); + pte = PTR_ALIGN_DOWN(pte, sizeof(*pte) * (size >> PAGE_SHIFT)); + } + ptent = huge_ptep_get_and_clear(&init_mm, addr, pte, size); + if (WARN_ON(end - addr < size)) + size = end - addr; + } else +#endif + ptent = ptep_get_and_clear(&init_mm, addr, pte); WARN_ON(!pte_none(ptent) && !pte_present(ptent)); - } while (pte++, addr += PAGE_SIZE, addr != end); + } while (pte += (size >> PAGE_SHIFT), addr += size, addr != end); + + arch_leave_lazy_mmu_mode(); *mask |= PGTBL_PTE_MODIFIED; } @@ -374,8 +404,10 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, if (cleared || pmd_bad(*pmd)) *mask |= PGTBL_PMD_MODIFIED; - if (cleared) + if (cleared) { + WARN_ON(next - addr < PMD_SIZE); continue; + } if (pmd_none_or_clear_bad(pmd)) continue; vunmap_pte_range(pmd, addr, next, mask); @@ -399,8 +431,10 @@ static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, if (cleared || pud_bad(*pud)) *mask |= PGTBL_PUD_MODIFIED; - if (cleared) + if (cleared) { + WARN_ON(next - addr < PUD_SIZE); continue; + } if (pud_none_or_clear_bad(pud)) continue; vunmap_pmd_range(pud, addr, next, mask); @@ -487,6 +521,7 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { + int err = 0; pte_t *pte; /* @@ -497,21 +532,33 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, pte = pte_alloc_kernel_track(pmd, addr, mask); if (!pte) return -ENOMEM; + + arch_enter_lazy_mmu_mode(); + do { struct page *page = pages[*nr]; - if (WARN_ON(!pte_none(ptep_get(pte)))) - return -EBUSY; - if (WARN_ON(!page)) - return -ENOMEM; - if (WARN_ON(!pfn_valid(page_to_pfn(page)))) - return -EINVAL; + if (WARN_ON(!pte_none(ptep_get(pte)))) { + err = -EBUSY; + break; + } + if (WARN_ON(!page)) { + err = -ENOMEM; + break; + } + if (WARN_ON(!pfn_valid(page_to_pfn(page)))) { + err = -EINVAL; + break; + } set_pte_at(&init_mm, addr, pte, mk_pte(page, prot)); (*nr)++; } while (pte++, addr += PAGE_SIZE, addr != end); + + arch_leave_lazy_mmu_mode(); *mask |= PGTBL_PTE_MODIFIED; - return 0; + + return err; } static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr, @@ -586,13 +633,13 @@ static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end, mask |= PGTBL_PGD_MODIFIED; err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask); if (err) - return err; + break; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); - return 0; + return err; } /* @@ -631,16 +678,28 @@ int __vmap_pages_range_noflush(unsigned long addr, unsigned long end, } int vmap_pages_range_noflush(unsigned long addr, unsigned long end, - pgprot_t prot, struct page **pages, unsigned int page_shift) + pgprot_t prot, struct page **pages, unsigned int page_shift, + gfp_t gfp_mask) { int ret = kmsan_vmap_pages_range_noflush(addr, end, prot, pages, - page_shift); + page_shift, gfp_mask); if (ret) return ret; return __vmap_pages_range_noflush(addr, end, prot, pages, page_shift); } +static int __vmap_pages_range(unsigned long addr, unsigned long end, + pgprot_t prot, struct page **pages, unsigned int page_shift, + gfp_t gfp_mask) +{ + int err; + + err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift, gfp_mask); + flush_cache_vmap(addr, end); + return err; +} + /** * vmap_pages_range - map pages to a kernel virtual address * @addr: start of the VM area to map @@ -653,14 +712,10 @@ int vmap_pages_range_noflush(unsigned long addr, unsigned long end, * RETURNS: * 0 on success, -errno on failure. */ -static int vmap_pages_range(unsigned long addr, unsigned long end, +int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { - int err; - - err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift); - flush_cache_vmap(addr, end); - return err; + return __vmap_pages_range(addr, end, prot, pages, page_shift, GFP_KERNEL); } static int check_sparse_vm_area(struct vm_struct *area, unsigned long start, @@ -900,6 +955,11 @@ static struct vmap_node *vmap_nodes = &single; static __read_mostly unsigned int nr_vmap_nodes = 1; static __read_mostly unsigned int vmap_zone_size = 1; +/* A simple iterator over all vmap-nodes. */ +#define for_each_vmap_node(vn) \ + for ((vn) = &vmap_nodes[0]; \ + (vn) < &vmap_nodes[nr_vmap_nodes]; (vn)++) + static inline unsigned int addr_to_node_id(unsigned long addr) { @@ -918,6 +978,19 @@ id_to_node(unsigned int id) return &vmap_nodes[id % nr_vmap_nodes]; } +static inline unsigned int +node_to_id(struct vmap_node *node) +{ + /* Pointer arithmetic. */ + unsigned int id = node - vmap_nodes; + + if (likely(id < nr_vmap_nodes)) + return id; + + WARN_ONCE(1, "An address 0x%p is out-of-bounds.\n", node); + return 0; +} + /* * We use the value 0 to represent "no node", that is why * an encoded value will be the node-id incremented by 1. @@ -990,7 +1063,8 @@ static BLOCKING_NOTIFIER_HEAD(vmap_notify_list); static void drain_vmap_area_work(struct work_struct *work); static DECLARE_WORK(drain_vmap_work, drain_vmap_area_work); -static atomic_long_t nr_vmalloc_pages; +static __cacheline_aligned_in_smp atomic_long_t nr_vmalloc_pages; +static __cacheline_aligned_in_smp atomic_long_t vmap_lazy_nr; unsigned long vmalloc_nr_pages(void) { @@ -1056,12 +1130,11 @@ find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va) { unsigned long va_start_lowest; struct vmap_node *vn; - int i; repeat: - for (i = 0, va_start_lowest = 0; i < nr_vmap_nodes; i++) { - vn = &vmap_nodes[i]; + va_start_lowest = 0; + for_each_vmap_node(vn) { spin_lock(&vn->busy.lock); *va = __find_vmap_area_exceed_addr(addr, &vn->busy.root); @@ -1698,7 +1771,7 @@ va_clip(struct rb_root *root, struct list_head *head, */ lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT); if (!lva) - return -1; + return -ENOMEM; } /* @@ -1712,7 +1785,7 @@ va_clip(struct rb_root *root, struct list_head *head, */ va->va_start = nva_start_addr + size; } else { - return -1; + return -EINVAL; } if (type != FL_FIT_TYPE) { @@ -1741,19 +1814,19 @@ va_alloc(struct vmap_area *va, /* Check the "vend" restriction. */ if (nva_start_addr + size > vend) - return vend; + return -ERANGE; /* Update the free vmap_area. */ ret = va_clip(root, head, va, nva_start_addr, size); if (WARN_ON_ONCE(ret)) - return vend; + return ret; return nva_start_addr; } /* * Returns a start address of the newly allocated area, if success. - * Otherwise a vend is returned that indicates failure. + * Otherwise an error value is returned that indicates failure. */ static __always_inline unsigned long __alloc_vmap_area(struct rb_root *root, struct list_head *head, @@ -1778,14 +1851,13 @@ __alloc_vmap_area(struct rb_root *root, struct list_head *head, va = find_vmap_lowest_match(root, size, align, vstart, adjust_search_size); if (unlikely(!va)) - return vend; + return -ENOENT; nva_start_addr = va_alloc(va, root, head, size, align, vstart, vend); - if (nva_start_addr == vend) - return vend; #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK - find_vmap_lowest_match_check(root, head, size, align); + if (!IS_ERR_VALUE(nva_start_addr)) + find_vmap_lowest_match_check(root, head, size, align); #endif return nva_start_addr; @@ -1816,7 +1888,7 @@ static void free_vmap_area(struct vmap_area *va) static inline void preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node) { - struct vmap_area *va = NULL; + struct vmap_area *va = NULL, *tmp; /* * Preload this CPU with one extra vmap_area object. It is used @@ -1832,7 +1904,8 @@ preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node) spin_lock(lock); - if (va && __this_cpu_cmpxchg(ne_fit_preload_node, NULL, va)) + tmp = NULL; + if (va && !__this_cpu_try_cmpxchg(ne_fit_preload_node, &tmp, va)) kmem_cache_free(vmap_area_cachep, va); } @@ -1914,7 +1987,7 @@ node_alloc(unsigned long size, unsigned long align, struct vmap_area *va; *vn_id = 0; - *addr = vend; + *addr = -EINVAL; /* * Fallback to a global heap if not vmalloc or there @@ -1939,7 +2012,7 @@ static inline void setup_vmalloc_vm(struct vm_struct *vm, { vm->flags = flags; vm->addr = (void *)va->va_start; - vm->size = va->va_end - va->va_start; + vm->size = vm->requested_size = va_size(va); vm->caller = caller; va->vm = vm; } @@ -1959,6 +2032,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long freed; unsigned long addr; unsigned int vn_id; + bool allow_block; int purged = 0; int ret; @@ -1968,7 +2042,10 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, if (unlikely(!vmap_initialized)) return ERR_PTR(-EBUSY); - might_sleep(); + /* Only reclaim behaviour flags are relevant. */ + gfp_mask = gfp_mask & GFP_RECLAIM_MASK; + allow_block = gfpflags_allow_blocking(gfp_mask); + might_sleep_if(allow_block); /* * If a VA is obtained from a global heap(if it fails here) @@ -1980,8 +2057,6 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, */ va = node_alloc(size, align, vstart, vend, &addr, &vn_id); if (!va) { - gfp_mask = gfp_mask & GFP_RECLAIM_MASK; - va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); if (unlikely(!va)) return ERR_PTR(-ENOMEM); @@ -1994,21 +2069,36 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, } retry: - if (addr == vend) { + if (IS_ERR_VALUE(addr)) { preload_this_cpu_lock(&free_vmap_area_lock, gfp_mask, node); addr = __alloc_vmap_area(&free_vmap_area_root, &free_vmap_area_list, size, align, vstart, vend); spin_unlock(&free_vmap_area_lock); + + /* + * This is not a fast path. Check if yielding is needed. This + * is the only reschedule point in the vmalloc() path. + */ + if (allow_block) + cond_resched(); } - trace_alloc_vmap_area(addr, size, align, vstart, vend, addr == vend); + trace_alloc_vmap_area(addr, size, align, vstart, vend, IS_ERR_VALUE(addr)); /* - * If an allocation fails, the "vend" address is + * If an allocation fails, the error value is * returned. Therefore trigger the overflow path. */ - if (unlikely(addr == vend)) - goto overflow; + if (IS_ERR_VALUE(addr)) { + if (allow_block) + goto overflow; + + /* + * We can not trigger any reclaim logic because + * sleeping is not allowed, thus fail an allocation. + */ + goto out_free_va; + } va->va_start = addr; va->va_end = addr + size; @@ -2017,7 +2107,7 @@ retry: if (vm) { vm->addr = (void *)va->va_start; - vm->size = va->va_end - va->va_start; + vm->size = va_size(va); va->vm = vm; } @@ -2031,7 +2121,7 @@ retry: BUG_ON(va->va_start < vstart); BUG_ON(va->va_end > vend); - ret = kasan_populate_vmalloc(addr, size); + ret = kasan_populate_vmalloc(addr, size, gfp_mask); if (ret) { free_vmap_area(va); return ERR_PTR(ret); @@ -2055,9 +2145,10 @@ overflow: } if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) - pr_warn("vmap allocation for size %lu failed: use vmalloc=<size> to increase size\n", - size); + pr_warn("vmalloc_node_range for size %lu failed: Address range restricted to %#lx - %#lx\n", + size, vstart, vend); +out_free_va: kmem_cache_free(vmap_area_cachep, va); return ERR_PTR(-EBUSY); } @@ -2099,8 +2190,6 @@ static unsigned long lazy_max_pages(void) return log * (32UL * 1024 * 1024 / PAGE_SIZE); } -static atomic_long_t vmap_lazy_nr = ATOMIC_LONG_INIT(0); - /* * Serialize vmap purging. There is no actual critical section protected * by this lock, but we want to avoid concurrent calls for performance @@ -2110,7 +2199,6 @@ static DEFINE_MUTEX(vmap_purge_lock); /* for per-CPU blocks */ static void purge_fragmented_blocks_allcpus(void); -static cpumask_t purge_nodes; static void reclaim_list_global(struct list_head *head) @@ -2130,44 +2218,37 @@ reclaim_list_global(struct list_head *head) static void decay_va_pool_node(struct vmap_node *vn, bool full_decay) { + LIST_HEAD(decay_list); + struct rb_root decay_root = RB_ROOT; struct vmap_area *va, *nva; - struct list_head decay_list; - struct rb_root decay_root; - unsigned long n_decay; + unsigned long n_decay, pool_len; int i; - decay_root = RB_ROOT; - INIT_LIST_HEAD(&decay_list); - for (i = 0; i < MAX_VA_SIZE_PAGES; i++) { - struct list_head tmp_list; + LIST_HEAD(tmp_list); if (list_empty(&vn->pool[i].head)) continue; - INIT_LIST_HEAD(&tmp_list); - /* Detach the pool, so no-one can access it. */ spin_lock(&vn->pool_lock); list_replace_init(&vn->pool[i].head, &tmp_list); spin_unlock(&vn->pool_lock); - if (full_decay) - WRITE_ONCE(vn->pool[i].len, 0); + pool_len = n_decay = vn->pool[i].len; + WRITE_ONCE(vn->pool[i].len, 0); /* Decay a pool by ~25% out of left objects. */ - n_decay = vn->pool[i].len >> 2; + if (!full_decay) + n_decay >>= 2; + pool_len -= n_decay; list_for_each_entry_safe(va, nva, &tmp_list, list) { + if (!n_decay--) + break; + list_del_init(&va->list); merge_or_add_vmap_area(va, &decay_root, &decay_list); - - if (!full_decay) { - WRITE_ONCE(vn->pool[i].len, vn->pool[i].len - 1); - - if (!--n_decay) - break; - } } /* @@ -2176,9 +2257,10 @@ decay_va_pool_node(struct vmap_node *vn, bool full_decay) * can populate the pool therefore a simple list replace * operation takes place here. */ - if (!full_decay && !list_empty(&tmp_list)) { + if (!list_empty(&tmp_list)) { spin_lock(&vn->pool_lock); list_replace_init(&tmp_list, &vn->pool[i].head); + WRITE_ONCE(vn->pool[i].len, pool_len); spin_unlock(&vn->pool_lock); } } @@ -2186,28 +2268,45 @@ decay_va_pool_node(struct vmap_node *vn, bool full_decay) reclaim_list_global(&decay_list); } +static void +kasan_release_vmalloc_node(struct vmap_node *vn) +{ + struct vmap_area *va; + unsigned long start, end; + + start = list_first_entry(&vn->purge_list, struct vmap_area, list)->va_start; + end = list_last_entry(&vn->purge_list, struct vmap_area, list)->va_end; + + list_for_each_entry(va, &vn->purge_list, list) { + if (is_vmalloc_or_module_addr((void *) va->va_start)) + kasan_release_vmalloc(va->va_start, va->va_end, + va->va_start, va->va_end, + KASAN_VMALLOC_PAGE_RANGE); + } + + kasan_release_vmalloc(start, end, start, end, KASAN_VMALLOC_TLB_FLUSH); +} + static void purge_vmap_node(struct work_struct *work) { struct vmap_node *vn = container_of(work, struct vmap_node, purge_work); + unsigned long nr_purged_pages = 0; struct vmap_area *va, *n_va; LIST_HEAD(local_list); + if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) + kasan_release_vmalloc_node(vn); + vn->nr_purged = 0; list_for_each_entry_safe(va, n_va, &vn->purge_list, list) { - unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT; - unsigned long orig_start = va->va_start; - unsigned long orig_end = va->va_end; + unsigned long nr = va_size(va) >> PAGE_SHIFT; unsigned int vn_id = decode_vn_id(va->flags); list_del_init(&va->list); - if (is_vmalloc_or_module_addr((void *)orig_start)) - kasan_release_vmalloc(orig_start, orig_end, - va->va_start, va->va_end); - - atomic_long_sub(nr, &vmap_lazy_nr); + nr_purged_pages += nr; vn->nr_purged++; if (is_vn_id_valid(vn_id) && !vn->skip_populate) @@ -2218,6 +2317,8 @@ static void purge_vmap_node(struct work_struct *work) list_add(&va->list, &local_list); } + atomic_long_sub(nr_purged_pages, &vmap_lazy_nr); + reclaim_list_global(&local_list); } @@ -2229,6 +2330,7 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end, { unsigned long nr_purged_areas = 0; unsigned int nr_purge_helpers; + static cpumask_t purge_nodes; unsigned int nr_purge_nodes; struct vmap_node *vn; int i; @@ -2240,9 +2342,7 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end, */ purge_nodes = CPU_MASK_NONE; - for (i = 0; i < nr_vmap_nodes; i++) { - vn = &vmap_nodes[i]; - + for_each_vmap_node(vn) { INIT_LIST_HEAD(&vn->purge_list); vn->skip_populate = full_pool_decay; decay_va_pool_node(vn, full_pool_decay); @@ -2261,7 +2361,7 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end, end = max(end, list_last_entry(&vn->purge_list, struct vmap_area, list)->va_end); - cpumask_set_cpu(i, &purge_nodes); + cpumask_set_cpu(node_to_id(vn), &purge_nodes); } nr_purge_nodes = cpumask_weight(&purge_nodes); @@ -2340,8 +2440,8 @@ static void free_vmap_area_noflush(struct vmap_area *va) if (WARN_ON_ONCE(!list_empty(&va->list))) return; - nr_lazy = atomic_long_add_return((va->va_end - va->va_start) >> - PAGE_SHIFT, &vmap_lazy_nr); + nr_lazy = atomic_long_add_return_relaxed(va_size(va) >> PAGE_SHIFT, + &vmap_lazy_nr); /* * If it was request by a certain node we would like to @@ -2406,7 +2506,7 @@ struct vmap_area *find_vmap_area(unsigned long addr) if (va) return va; - } while ((i = (i + 1) % nr_vmap_nodes) != j); + } while ((i = (i + nr_vmap_nodes - 1) % nr_vmap_nodes) != j); return NULL; } @@ -2432,7 +2532,7 @@ static struct vmap_area *find_unlink_vmap_area(unsigned long addr) if (va) return va; - } while ((i = (i + 1) % nr_vmap_nodes) != j); + } while ((i = (i + nr_vmap_nodes - 1) % nr_vmap_nodes) != j); return NULL; } @@ -2599,8 +2699,7 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) node = numa_node_id(); - vb = kmalloc_node(sizeof(struct vmap_block), - gfp_mask & GFP_RECLAIM_MASK, node); + vb = kmalloc_node(sizeof(struct vmap_block), gfp_mask, node); if (unlikely(!vb)) return ERR_PTR(-ENOMEM); @@ -2625,6 +2724,7 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) vb->dirty_max = 0; bitmap_set(vb->used_map, 0, (1UL << order)); INIT_LIST_HEAD(&vb->free_list); + vb->cpu = raw_smp_processor_id(); xa = addr_to_vb_xa(va->va_start); vb_idx = addr_to_vb_idx(va->va_start); @@ -2641,7 +2741,6 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) * integrity together with list_for_each_rcu from read * side. */ - vb->cpu = raw_smp_processor_id(); vbq = per_cpu_ptr(&vmap_block_queue, vb->cpu); spin_lock(&vbq->lock); list_add_tail_rcu(&vb->free_list, &vbq->free); @@ -2901,10 +3000,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush) */ void vm_unmap_aliases(void) { - unsigned long start = ULONG_MAX, end = 0; - int flush = 0; - - _vm_unmap_aliases(start, end, flush); + _vm_unmap_aliases(ULONG_MAX, 0, 0); } EXPORT_SYMBOL_GPL(vm_unmap_aliases); @@ -2937,8 +3033,7 @@ void vm_unmap_ram(const void *mem, unsigned int count) if (WARN_ON_ONCE(!va)) return; - debug_check_no_locks_freed((void *)va->va_start, - (va->va_end - va->va_start)); + debug_check_no_locks_freed((void *)va->va_start, va_size(va)); free_unmap_vmap_area(va); } EXPORT_SYMBOL(vm_unmap_ram); @@ -3009,6 +3104,11 @@ static inline unsigned int vm_area_page_order(struct vm_struct *vm) #endif } +unsigned int get_vm_area_page_order(struct vm_struct *vm) +{ + return vm_area_page_order(vm); +} + static inline void set_vm_area_page_order(struct vm_struct *vm, unsigned int order) { #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC @@ -3081,13 +3181,13 @@ static void clear_vm_uninitialized_flag(struct vm_struct *vm) /* * Before removing VM_UNINITIALIZED, * we should make sure that vm has proper values. - * Pair with smp_rmb() in show_numa_info(). + * Pair with smp_rmb() in vread_iter() and vmalloc_info_show(). */ smp_wmb(); vm->flags &= ~VM_UNINITIALIZED; } -static struct vm_struct *__get_vm_area_node(unsigned long size, +struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long shift, unsigned long flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, const void *caller) @@ -3114,6 +3214,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, area->flags = flags; area->caller = caller; + area->requested_size = requested_size; va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area); if (IS_ERR(va)) { @@ -3351,11 +3452,13 @@ void vfree(const void *addr) if (unlikely(vm->flags & VM_FLUSH_RESET_PERMS)) vm_reset_perms(vm); + /* All pages of vm should be charged to same memcg, so use first one. */ + if (vm->nr_pages && !(vm->flags & VM_MAP_PUT_PAGES)) + mod_memcg_page_state(vm->pages[0], MEMCG_VMALLOC, -vm->nr_pages); for (i = 0; i < vm->nr_pages; i++) { struct page *page = vm->pages[i]; BUG_ON(!page); - mod_memcg_page_state(page, MEMCG_VMALLOC, -1); /* * High-order allocs for huge vmallocs are split, so * can be freed as an array of order-0 allocations @@ -3363,7 +3466,8 @@ void vfree(const void *addr) __free_page(page); cond_resched(); } - atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); + if (!(vm->flags & VM_MAP_PUT_PAGES)) + atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); kvfree(vm->pages); kfree(vm); } @@ -3509,15 +3613,58 @@ void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot) EXPORT_SYMBOL_GPL(vmap_pfn); #endif /* CONFIG_VMAP_PFN */ +/* + * Helper for vmalloc to adjust the gfp flags for certain allocations. + */ +static inline gfp_t vmalloc_gfp_adjust(gfp_t flags, const bool large) +{ + flags |= __GFP_NOWARN; + if (large) + flags &= ~__GFP_NOFAIL; + return flags; +} + static inline unsigned int vm_area_alloc_pages(gfp_t gfp, int nid, unsigned int order, unsigned int nr_pages, struct page **pages) { unsigned int nr_allocated = 0; - gfp_t alloc_gfp = gfp; - bool nofail = gfp & __GFP_NOFAIL; + unsigned int nr_remaining = nr_pages; + unsigned int max_attempt_order = MAX_PAGE_ORDER; struct page *page; int i; + unsigned int large_order = ilog2(nr_remaining); + gfp_t large_gfp = vmalloc_gfp_adjust(gfp, large_order) & ~__GFP_DIRECT_RECLAIM; + + large_order = min(max_attempt_order, large_order); + + /* + * Initially, attempt to have the page allocator give us large order + * pages. Do not attempt allocating smaller than order chunks since + * __vmap_pages_range() expects physically contigous pages of exactly + * order long chunks. + */ + while (large_order > order && nr_remaining) { + if (nid == NUMA_NO_NODE) + page = alloc_pages_noprof(large_gfp, large_order); + else + page = alloc_pages_node_noprof(nid, large_gfp, large_order); + + if (unlikely(!page)) { + max_attempt_order = --large_order; + continue; + } + + split_page(page, large_order); + for (i = 0; i < (1U << large_order); i++) + pages[nr_allocated + i] = page + i; + + nr_allocated += 1U << large_order; + nr_remaining = nr_pages - nr_allocated; + + large_order = ilog2(nr_remaining); + large_order = min(max_attempt_order, large_order); + } /* * For order-0 pages we make use of bulk allocator, if @@ -3526,9 +3673,6 @@ vm_area_alloc_pages(gfp_t gfp, int nid, * more permissive. */ if (!order) { - /* bulk allocator doesn't support nofail req. officially */ - gfp_t bulk_gfp = gfp & ~__GFP_NOFAIL; - while (nr_allocated < nr_pages) { unsigned int nr, nr_pages_request; @@ -3546,17 +3690,15 @@ vm_area_alloc_pages(gfp_t gfp, int nid, * but mempolicy wants to alloc memory by interleaving. */ if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE) - nr = alloc_pages_bulk_array_mempolicy_noprof(bulk_gfp, + nr = alloc_pages_bulk_mempolicy_noprof(gfp, nr_pages_request, pages + nr_allocated); - else - nr = alloc_pages_bulk_array_node_noprof(bulk_gfp, nid, + nr = alloc_pages_bulk_node_noprof(gfp, nid, nr_pages_request, pages + nr_allocated); nr_allocated += nr; - cond_resched(); /* * If zero or pages were obtained partly, @@ -3565,37 +3707,24 @@ vm_area_alloc_pages(gfp_t gfp, int nid, if (nr != nr_pages_request) break; } - } else if (gfp & __GFP_NOFAIL) { - /* - * Higher order nofail allocations are really expensive and - * potentially dangerous (pre-mature OOM, disruptive reclaim - * and compaction etc. - */ - alloc_gfp &= ~__GFP_NOFAIL; } /* High-order pages or fallback path if "bulk" fails. */ while (nr_allocated < nr_pages) { - if (!nofail && fatal_signal_pending(current)) + if (!(gfp & __GFP_NOFAIL) && fatal_signal_pending(current)) break; if (nid == NUMA_NO_NODE) - page = alloc_pages_noprof(alloc_gfp, order); + page = alloc_pages_noprof(gfp, order); else - page = alloc_pages_node_noprof(nid, alloc_gfp, order); - if (unlikely(!page)) { - if (!nofail) - break; + page = alloc_pages_node_noprof(nid, gfp, order); - /* fall back to the zero order allocations */ - alloc_gfp |= __GFP_NOFAIL; - order = 0; - continue; - } + if (unlikely(!page)) + break; /* - * Higher order allocations must be able to be treated as - * indepdenent small pages by callers (as they can with + * High-order allocations must be able to be treated as + * independent small pages by callers (as they can with * small-page vmallocs). Some drivers do their own refcounting * on vmalloc_to_page() pages, some use page->mapping, * page->lru, etc. @@ -3611,13 +3740,77 @@ vm_area_alloc_pages(gfp_t gfp, int nid, for (i = 0; i < (1U << order); i++) pages[nr_allocated + i] = page + i; - cond_resched(); nr_allocated += 1U << order; } return nr_allocated; } +static LLIST_HEAD(pending_vm_area_cleanup); +static void cleanup_vm_area_work(struct work_struct *work) +{ + struct vm_struct *area, *tmp; + struct llist_node *head; + + head = llist_del_all(&pending_vm_area_cleanup); + if (!head) + return; + + llist_for_each_entry_safe(area, tmp, head, llnode) { + if (!area->pages) + free_vm_area(area); + else + vfree(area->addr); + } +} + +/* + * Helper for __vmalloc_area_node() to defer cleanup + * of partially initialized vm_struct in error paths. + */ +static DECLARE_WORK(cleanup_vm_area, cleanup_vm_area_work); +static void defer_vm_area_cleanup(struct vm_struct *area) +{ + if (llist_add(&area->llnode, &pending_vm_area_cleanup)) + schedule_work(&cleanup_vm_area); +} + +/* + * Page tables allocations ignore external GFP. Enforces it by + * the memalloc scope API. It is used by vmalloc internals and + * KASAN shadow population only. + * + * GFP to scope mapping: + * + * non-blocking (no __GFP_DIRECT_RECLAIM) - memalloc_noreclaim_save() + * GFP_NOFS - memalloc_nofs_save() + * GFP_NOIO - memalloc_noio_save() + * + * Returns a flag cookie to pair with restore. + */ +unsigned int +memalloc_apply_gfp_scope(gfp_t gfp_mask) +{ + unsigned int flags = 0; + + if (!gfpflags_allow_blocking(gfp_mask)) + flags = memalloc_noreclaim_save(); + else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) + flags = memalloc_nofs_save(); + else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) + flags = memalloc_noio_save(); + + /* 0 - no scope applied. */ + return flags; +} + +void +memalloc_restore_scope(unsigned int flags) +{ + if (flags) + memalloc_flags_restore(flags); +} + static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot, unsigned int page_shift, int node) @@ -3634,6 +3827,10 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, array_size = (unsigned long)nr_small_pages * sizeof(struct page *); + /* __GFP_NOFAIL and "noblock" flags are mutually exclusive. */ + if (!gfpflags_allow_blocking(gfp_mask)) + nofail = false; + if (!(gfp_mask & (GFP_DMA | GFP_DMA32))) gfp_mask |= __GFP_HIGHMEM; @@ -3649,23 +3846,29 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, failed to allocated page array size %lu", nr_small_pages * PAGE_SIZE, array_size); - free_vm_area(area); - return NULL; + goto fail; } set_vm_area_page_order(area, page_shift - PAGE_SHIFT); page_order = vm_area_page_order(area); - area->nr_pages = vm_area_alloc_pages(gfp_mask | __GFP_NOWARN, - node, page_order, nr_small_pages, area->pages); + /* + * High-order nofail allocations are really expensive and + * potentially dangerous (pre-mature OOM, disruptive reclaim + * and compaction etc. + * + * Please note, the __vmalloc_node_range_noprof() falls-back + * to order-0 pages if high-order attempt is unsuccessful. + */ + area->nr_pages = vm_area_alloc_pages( + vmalloc_gfp_adjust(gfp_mask, page_order), node, + page_order, nr_small_pages, area->pages); atomic_long_add(area->nr_pages, &nr_vmalloc_pages); - if (gfp_mask & __GFP_ACCOUNT) { - int i; - - for (i = 0; i < area->nr_pages; i++) - mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC, 1); - } + /* All pages of vm should be charged to same memcg, so use first one. */ + if (gfp_mask & __GFP_ACCOUNT && area->nr_pages) + mod_memcg_page_state(area->pages[0], MEMCG_VMALLOC, + area->nr_pages); /* * If not enough pages were obtained to accomplish an @@ -3693,22 +3896,14 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, * page tables allocations ignore external gfp mask, enforce it * by the scope API */ - if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) - flags = memalloc_nofs_save(); - else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) - flags = memalloc_noio_save(); - + flags = memalloc_apply_gfp_scope(gfp_mask); do { - ret = vmap_pages_range(addr, addr + size, prot, area->pages, - page_shift); + ret = __vmap_pages_range(addr, addr + size, prot, area->pages, + page_shift, nested_gfp); if (nofail && (ret < 0)) schedule_timeout_uninterruptible(1); } while (nofail && (ret < 0)); - - if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) - memalloc_nofs_restore(flags); - else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) - memalloc_noio_restore(flags); + memalloc_restore_scope(flags); if (ret < 0) { warn_alloc(gfp_mask, NULL, @@ -3720,10 +3915,32 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, return area->addr; fail: - vfree(area->addr); + defer_vm_area_cleanup(area); return NULL; } +/* + * See __vmalloc_node_range() for a clear list of supported vmalloc flags. + * This gfp lists all flags currently passed through vmalloc. Currently, + * __GFP_ZERO is used by BPF and __GFP_NORETRY is used by percpu. Both drm + * and BPF also use GFP_USER. Additionally, various users pass + * GFP_KERNEL_ACCOUNT. Xfs uses __GFP_NOLOCKDEP. + */ +#define GFP_VMALLOC_SUPPORTED (GFP_KERNEL | GFP_ATOMIC | GFP_NOWAIT |\ + __GFP_NOFAIL | __GFP_ZERO | __GFP_NORETRY |\ + GFP_NOFS | GFP_NOIO | GFP_KERNEL_ACCOUNT |\ + GFP_USER | __GFP_NOLOCKDEP) + +static gfp_t vmalloc_fix_flags(gfp_t flags) +{ + gfp_t invalid_mask = flags & ~GFP_VMALLOC_SUPPORTED; + + flags &= GFP_VMALLOC_SUPPORTED; + WARN_ONCE(1, "Unexpected gfp: %#x (%pGg). Fixing up to gfp: %#x (%pGg). Fix your code!\n", + invalid_mask, &invalid_mask, flags, &flags); + return flags; +} + /** * __vmalloc_node_range - allocate virtually contiguous memory * @size: allocation size @@ -3737,19 +3954,20 @@ fail: * @caller: caller's return address * * Allocate enough pages to cover @size from the page level - * allocator with @gfp_mask flags. Please note that the full set of gfp - * flags are not supported. GFP_KERNEL, GFP_NOFS and GFP_NOIO are all - * supported. - * Zone modifiers are not supported. From the reclaim modifiers - * __GFP_DIRECT_RECLAIM is required (aka GFP_NOWAIT is not supported) - * and only __GFP_NOFAIL is supported (i.e. __GFP_NORETRY and - * __GFP_RETRY_MAYFAIL are not supported). + * allocator with @gfp_mask flags and map them into contiguous + * virtual range with protection @prot. + * + * Supported GFP classes: %GFP_KERNEL, %GFP_ATOMIC, %GFP_NOWAIT, + * %GFP_NOFS and %GFP_NOIO. Zone modifiers are not supported. + * Please note %GFP_ATOMIC and %GFP_NOWAIT are supported only + * by __vmalloc(). * - * __GFP_NOWARN can be used to suppress failures messages. + * Retry modifiers: only %__GFP_NOFAIL is supported; %__GFP_NORETRY + * and %__GFP_RETRY_MAYFAIL are not supported. * - * Map them into contiguous kernel virtual space, using a pagetable - * protection of @prot. + * %__GFP_NOWARN can be used to suppress failure messages. * + * Can not be called from interrupt nor NMI contexts. * Return: the address of the area or %NULL on failure */ void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, @@ -3760,8 +3978,7 @@ void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, struct vm_struct *area; void *ret; kasan_vmalloc_flags_t kasan_flags = KASAN_VMALLOC_NONE; - unsigned long real_size = size; - unsigned long real_align = align; + unsigned long original_align = align; unsigned int shift = PAGE_SHIFT; if (WARN_ON_ONCE(!size)) @@ -3770,13 +3987,11 @@ void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, if ((size >> PAGE_SHIFT) > totalram_pages()) { warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, exceeds total pages", - real_size); + size); return NULL; } if (vmap_allow_huge && (vm_flags & VM_ALLOW_HUGE_VMAP)) { - unsigned long size_per_node; - /* * Try huge pages. Only try for PAGE_KERNEL allocations, * others like modules don't yet expect huge pages in @@ -3784,27 +3999,23 @@ void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, * supporting them. */ - size_per_node = size; - if (node == NUMA_NO_NODE) - size_per_node /= num_online_nodes(); - if (arch_vmap_pmd_supported(prot) && size_per_node >= PMD_SIZE) + if (arch_vmap_pmd_supported(prot) && size >= PMD_SIZE) shift = PMD_SHIFT; else - shift = arch_vmap_pte_supported_shift(size_per_node); + shift = arch_vmap_pte_supported_shift(size); - align = max(real_align, 1UL << shift); - size = ALIGN(real_size, 1UL << shift); + align = max(original_align, 1UL << shift); } again: - area = __get_vm_area_node(real_size, align, shift, VM_ALLOC | + area = __get_vm_area_node(size, align, shift, VM_ALLOC | VM_UNINITIALIZED | vm_flags, start, end, node, gfp_mask, caller); if (!area) { bool nofail = gfp_mask & __GFP_NOFAIL; warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, vm_struct allocation failed%s", - real_size, (nofail) ? ". Retrying." : ""); + size, (nofail) ? ". Retrying." : ""); if (nofail) { schedule_timeout_uninterruptible(1); goto again; @@ -3854,7 +4065,7 @@ again: (gfp_mask & __GFP_SKIP_ZERO)) kasan_flags |= KASAN_VMALLOC_INIT; /* KASAN_VMALLOC_PROT_NORMAL already set if required. */ - area->addr = kasan_unpoison_vmalloc(area->addr, real_size, kasan_flags); + area->addr = kasan_unpoison_vmalloc(area->addr, size, kasan_flags); /* * In this function, newly allocated vm_struct has VM_UNINITIALIZED @@ -3863,17 +4074,15 @@ again: */ clear_vm_uninitialized_flag(area); - size = PAGE_ALIGN(size); if (!(vm_flags & VM_DEFER_KMEMLEAK)) - kmemleak_vmalloc(area, size, gfp_mask); + kmemleak_vmalloc(area, PAGE_ALIGN(size), gfp_mask); return area->addr; fail: if (shift > PAGE_SHIFT) { shift = PAGE_SHIFT; - align = real_align; - size = real_size; + align = original_align; goto again; } @@ -3891,11 +4100,8 @@ fail: * Allocate enough pages to cover @size from the page level allocator with * @gfp_mask flags. Map them into contiguous kernel virtual space. * - * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL - * and __GFP_NOFAIL are not supported - * - * Any use of gfp flags outside of GFP_KERNEL should be consulted - * with mm people. + * Semantics of @gfp_mask (including reclaim/retry modifiers such as + * __GFP_NOFAIL) are the same as in __vmalloc_node_range_noprof(). * * Return: pointer to the allocated memory or %NULL on error */ @@ -3916,6 +4122,8 @@ EXPORT_SYMBOL_GPL(__vmalloc_node_noprof); void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask) { + if (unlikely(gfp_mask & ~GFP_VMALLOC_SUPPORTED)) + gfp_mask = vmalloc_fix_flags(gfp_mask); return __vmalloc_node_noprof(size, 1, gfp_mask, NUMA_NO_NODE, __builtin_return_address(0)); } @@ -3941,9 +4149,10 @@ void *vmalloc_noprof(unsigned long size) EXPORT_SYMBOL(vmalloc_noprof); /** - * vmalloc_huge - allocate virtually contiguous memory, allow huge pages + * vmalloc_huge_node - allocate virtually contiguous memory, allow huge pages * @size: allocation size * @gfp_mask: flags for the page level allocator + * @node: node to use for allocation or NUMA_NO_NODE * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. @@ -3952,13 +4161,15 @@ EXPORT_SYMBOL(vmalloc_noprof); * * Return: pointer to the allocated memory or %NULL on error */ -void *vmalloc_huge_noprof(unsigned long size, gfp_t gfp_mask) +void *vmalloc_huge_node_noprof(unsigned long size, gfp_t gfp_mask, int node) { + if (unlikely(gfp_mask & ~GFP_VMALLOC_SUPPORTED)) + gfp_mask = vmalloc_fix_flags(gfp_mask); return __vmalloc_node_range_noprof(size, 1, VMALLOC_START, VMALLOC_END, - gfp_mask, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, - NUMA_NO_NODE, __builtin_return_address(0)); + gfp_mask, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, + node, __builtin_return_address(0)); } -EXPORT_SYMBOL_GPL(vmalloc_huge_noprof); +EXPORT_SYMBOL_GPL(vmalloc_huge_node_noprof); /** * vzalloc - allocate virtually contiguous memory with zero fill @@ -4036,6 +4247,115 @@ void *vzalloc_node_noprof(unsigned long size, int node) } EXPORT_SYMBOL(vzalloc_node_noprof); +/** + * vrealloc_node_align_noprof - reallocate virtually contiguous memory; contents + * remain unchanged + * @p: object to reallocate memory for + * @size: the size to reallocate + * @align: requested alignment + * @flags: the flags for the page level allocator + * @nid: node number of the target node + * + * If @p is %NULL, vrealloc_XXX() behaves exactly like vmalloc_XXX(). If @size + * is 0 and @p is not a %NULL pointer, the object pointed to is freed. + * + * If the caller wants the new memory to be on specific node *only*, + * __GFP_THISNODE flag should be set, otherwise the function will try to avoid + * reallocation and possibly disregard the specified @nid. + * + * If __GFP_ZERO logic is requested, callers must ensure that, starting with the + * initial memory allocation, every subsequent call to this API for the same + * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that + * __GFP_ZERO is not fully honored by this API. + * + * Requesting an alignment that is bigger than the alignment of the existing + * allocation will fail. + * + * In any case, the contents of the object pointed to are preserved up to the + * lesser of the new and old sizes. + * + * This function must not be called concurrently with itself or vfree() for the + * same memory allocation. + * + * Return: pointer to the allocated memory; %NULL if @size is zero or in case of + * failure + */ +void *vrealloc_node_align_noprof(const void *p, size_t size, unsigned long align, + gfp_t flags, int nid) +{ + struct vm_struct *vm = NULL; + size_t alloced_size = 0; + size_t old_size = 0; + void *n; + + if (!size) { + vfree(p); + return NULL; + } + + if (p) { + vm = find_vm_area(p); + if (unlikely(!vm)) { + WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p); + return NULL; + } + + alloced_size = get_vm_area_size(vm); + old_size = vm->requested_size; + if (WARN(alloced_size < old_size, + "vrealloc() has mismatched area vs requested sizes (%p)\n", p)) + return NULL; + if (WARN(!IS_ALIGNED((unsigned long)p, align), + "will not reallocate with a bigger alignment (0x%lx)\n", align)) + return NULL; + if (unlikely(flags & __GFP_THISNODE) && nid != NUMA_NO_NODE && + nid != page_to_nid(vmalloc_to_page(p))) + goto need_realloc; + } + + /* + * TODO: Shrink the vm_area, i.e. unmap and free unused pages. What + * would be a good heuristic for when to shrink the vm_area? + */ + if (size <= old_size) { + /* Zero out "freed" memory, potentially for future realloc. */ + if (want_init_on_free() || want_init_on_alloc(flags)) + memset((void *)p + size, 0, old_size - size); + vm->requested_size = size; + kasan_poison_vmalloc(p + size, old_size - size); + return (void *)p; + } + + /* + * We already have the bytes available in the allocation; use them. + */ + if (size <= alloced_size) { + kasan_unpoison_vmalloc(p + old_size, size - old_size, + KASAN_VMALLOC_PROT_NORMAL); + /* + * No need to zero memory here, as unused memory will have + * already been zeroed at initial allocation time or during + * realloc shrink time. + */ + vm->requested_size = size; + return (void *)p; + } + +need_realloc: + /* TODO: Grow the vm_area, i.e. allocate and map additional pages. */ + n = __vmalloc_node_noprof(size, align, flags, nid, __builtin_return_address(0)); + + if (!n) + return NULL; + + if (p) { + memcpy(n, p, old_size); + vfree(p); + } + + return n; +} + #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA) @@ -4684,7 +5004,7 @@ retry: /* populate the kasan shadow space */ for (area = 0; area < nr_vms; area++) { - if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area])) + if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area], GFP_KERNEL)) goto err_free_shadow; } @@ -4726,7 +5046,8 @@ recovery: &free_vmap_area_list); if (va) kasan_release_vmalloc(orig_start, orig_end, - va->va_start, va->va_end); + va->va_start, va->va_end, + KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH); vas[area] = NULL; } @@ -4776,7 +5097,8 @@ err_free_shadow: &free_vmap_area_list); if (va) kasan_release_vmalloc(orig_start, orig_end, - va->va_start, va->va_end); + va->va_start, va->va_end, + KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH); vas[area] = NULL; kfree(vms[area]); } @@ -4839,44 +5161,42 @@ bool vmalloc_dump_obj(void *object) #endif #ifdef CONFIG_PROC_FS -static void show_numa_info(struct seq_file *m, struct vm_struct *v) -{ - if (IS_ENABLED(CONFIG_NUMA)) { - unsigned int nr, *counters = m->private; - unsigned int step = 1U << vm_area_page_order(v); - if (!counters) - return; +/* + * Print number of pages allocated on each memory node. + * + * This function can only be called if CONFIG_NUMA is enabled + * and VM_UNINITIALIZED bit in v->flags is disabled. + */ +static void show_numa_info(struct seq_file *m, struct vm_struct *v, + unsigned int *counters) +{ + unsigned int nr; + unsigned int step = 1U << vm_area_page_order(v); - if (v->flags & VM_UNINITIALIZED) - return; - /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ - smp_rmb(); + if (!counters) + return; - memset(counters, 0, nr_node_ids * sizeof(unsigned int)); + memset(counters, 0, nr_node_ids * sizeof(unsigned int)); - for (nr = 0; nr < v->nr_pages; nr += step) - counters[page_to_nid(v->pages[nr])] += step; - for_each_node_state(nr, N_HIGH_MEMORY) - if (counters[nr]) - seq_printf(m, " N%u=%u", nr, counters[nr]); - } + for (nr = 0; nr < v->nr_pages; nr += step) + counters[page_to_nid(v->pages[nr])] += step; + for_each_node_state(nr, N_HIGH_MEMORY) + if (counters[nr]) + seq_printf(m, " N%u=%u", nr, counters[nr]); } static void show_purge_info(struct seq_file *m) { struct vmap_node *vn; struct vmap_area *va; - int i; - - for (i = 0; i < nr_vmap_nodes; i++) { - vn = &vmap_nodes[i]; + for_each_vmap_node(vn) { spin_lock(&vn->lazy.lock); list_for_each_entry(va, &vn->lazy.head, list) { seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n", (void *)va->va_start, (void *)va->va_end, - va->va_end - va->va_start); + va_size(va)); } spin_unlock(&vn->lazy.lock); } @@ -4887,23 +5207,29 @@ static int vmalloc_info_show(struct seq_file *m, void *p) struct vmap_node *vn; struct vmap_area *va; struct vm_struct *v; - int i; + unsigned int *counters; - for (i = 0; i < nr_vmap_nodes; i++) { - vn = &vmap_nodes[i]; + if (IS_ENABLED(CONFIG_NUMA)) + counters = kmalloc_array(nr_node_ids, sizeof(unsigned int), GFP_KERNEL); + for_each_vmap_node(vn) { spin_lock(&vn->busy.lock); list_for_each_entry(va, &vn->busy.head, list) { if (!va->vm) { if (va->flags & VMAP_RAM) seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n", (void *)va->va_start, (void *)va->va_end, - va->va_end - va->va_start); + va_size(va)); continue; } v = va->vm; + if (v->flags & VM_UNINITIALIZED) + continue; + + /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ + smp_rmb(); seq_printf(m, "0x%pK-0x%pK %7ld", v->addr, v->addr + v->size, v->size); @@ -4938,7 +5264,9 @@ static int vmalloc_info_show(struct seq_file *m, void *p) if (is_vmalloc_addr(v->pages)) seq_puts(m, " vpages"); - show_numa_info(m, v); + if (IS_ENABLED(CONFIG_NUMA)) + show_numa_info(m, v, counters); + seq_putc(m, '\n'); } spin_unlock(&vn->busy.lock); @@ -4948,19 +5276,14 @@ static int vmalloc_info_show(struct seq_file *m, void *p) * As a final step, dump "unpurged" areas. */ show_purge_info(m); + if (IS_ENABLED(CONFIG_NUMA)) + kfree(counters); return 0; } static int __init proc_vmalloc_init(void) { - void *priv_data = NULL; - - if (IS_ENABLED(CONFIG_NUMA)) - priv_data = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); - - proc_create_single_data("vmallocinfo", - 0400, NULL, vmalloc_info_show, priv_data); - + proc_create_single("vmallocinfo", 0400, NULL, vmalloc_info_show); return 0; } module_init(proc_vmalloc_init); @@ -5012,7 +5335,7 @@ static void __init vmap_init_free_space(void) static void vmap_init_nodes(void) { struct vmap_node *vn; - int i, n; + int i; #if BITS_PER_LONG == 64 /* @@ -5029,10 +5352,10 @@ static void vmap_init_nodes(void) * set of cores. Therefore a per-domain purging is supposed to * be added as well as a per-domain balancing. */ - n = clamp_t(unsigned int, num_possible_cpus(), 1, 128); + int n = clamp_t(unsigned int, num_possible_cpus(), 1, 128); if (n > 1) { - vn = kmalloc_array(n, sizeof(*vn), GFP_NOWAIT | __GFP_NOWARN); + vn = kmalloc_array(n, sizeof(*vn), GFP_NOWAIT); if (vn) { /* Node partition is 16 pages. */ vmap_zone_size = (1 << 4) * PAGE_SIZE; @@ -5044,8 +5367,7 @@ static void vmap_init_nodes(void) } #endif - for (n = 0; n < nr_vmap_nodes; n++) { - vn = &vmap_nodes[n]; + for_each_vmap_node(vn) { vn->busy.root = RB_ROOT; INIT_LIST_HEAD(&vn->busy.head); spin_lock_init(&vn->busy.lock); @@ -5066,15 +5388,13 @@ static void vmap_init_nodes(void) static unsigned long vmap_node_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { - unsigned long count; + unsigned long count = 0; struct vmap_node *vn; - int i, j; - - for (count = 0, i = 0; i < nr_vmap_nodes; i++) { - vn = &vmap_nodes[i]; + int i; - for (j = 0; j < MAX_VA_SIZE_PAGES; j++) - count += READ_ONCE(vn->pool[j].len); + for_each_vmap_node(vn) { + for (i = 0; i < MAX_VA_SIZE_PAGES; i++) + count += READ_ONCE(vn->pool[i].len); } return count ? count : SHRINK_EMPTY; @@ -5083,10 +5403,10 @@ vmap_node_shrink_count(struct shrinker *shrink, struct shrink_control *sc) static unsigned long vmap_node_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { - int i; + struct vmap_node *vn; - for (i = 0; i < nr_vmap_nodes; i++) - decay_va_pool_node(&vmap_nodes[i], true); + for_each_vmap_node(vn) + decay_va_pool_node(vn, true); return SHRINK_STOP; } |