diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/backing-dev.c | 22 | ||||
| -rw-r--r-- | mm/early_ioremap.c | 2 | ||||
| -rw-r--r-- | mm/frame_vector.c | 14 | ||||
| -rw-r--r-- | mm/gup.c | 64 | ||||
| -rw-r--r-- | mm/huge_memory.c | 31 | ||||
| -rw-r--r-- | mm/hugetlb.c | 12 | ||||
| -rw-r--r-- | mm/internal.h | 3 | ||||
| -rw-r--r-- | mm/kasan/report.c | 8 | ||||
| -rw-r--r-- | mm/khugepaged.c | 2 | ||||
| -rw-r--r-- | mm/kmemcheck.c | 1 | ||||
| -rw-r--r-- | mm/kmemleak.c | 2 | ||||
| -rw-r--r-- | mm/madvise.c | 4 | ||||
| -rw-r--r-- | mm/memcontrol.c | 2 | ||||
| -rw-r--r-- | mm/memory.c | 5 | ||||
| -rw-r--r-- | mm/migrate.c | 2 | ||||
| -rw-r--r-- | mm/mmap.c | 18 | ||||
| -rw-r--r-- | mm/oom_kill.c | 11 | ||||
| -rw-r--r-- | mm/page-writeback.c | 5 | ||||
| -rw-r--r-- | mm/page_alloc.c | 24 | ||||
| -rw-r--r-- | mm/percpu.c | 4 | ||||
| -rw-r--r-- | mm/slab.c | 23 |
21 files changed, 186 insertions, 73 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 74b52dfd5852..84b2dc76f140 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -113,11 +113,23 @@ static const struct file_operations bdi_debug_stats_fops = { .release = single_release, }; -static void bdi_debug_register(struct backing_dev_info *bdi, const char *name) +static int bdi_debug_register(struct backing_dev_info *bdi, const char *name) { + if (!bdi_debug_root) + return -ENOMEM; + bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root); + if (!bdi->debug_dir) + return -ENOMEM; + bdi->debug_stats = debugfs_create_file("stats", 0444, bdi->debug_dir, bdi, &bdi_debug_stats_fops); + if (!bdi->debug_stats) { + debugfs_remove(bdi->debug_dir); + return -ENOMEM; + } + + return 0; } static void bdi_debug_unregister(struct backing_dev_info *bdi) @@ -129,9 +141,10 @@ static void bdi_debug_unregister(struct backing_dev_info *bdi) static inline void bdi_debug_init(void) { } -static inline void bdi_debug_register(struct backing_dev_info *bdi, +static inline int bdi_debug_register(struct backing_dev_info *bdi, const char *name) { + return 0; } static inline void bdi_debug_unregister(struct backing_dev_info *bdi) { @@ -869,10 +882,13 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) if (IS_ERR(dev)) return PTR_ERR(dev); + if (bdi_debug_register(bdi, dev_name(dev))) { + device_destroy(bdi_class, dev->devt); + return -ENOMEM; + } cgwb_bdi_register(bdi); bdi->dev = dev; - bdi_debug_register(bdi, dev_name(dev)); set_bit(WB_registered, &bdi->wb.state); spin_lock_bh(&bdi_lock); diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c index d04ac1ec0559..1826f191e72c 100644 --- a/mm/early_ioremap.c +++ b/mm/early_ioremap.c @@ -111,7 +111,7 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot) enum fixed_addresses idx; int i, slot; - WARN_ON(system_state != SYSTEM_BOOTING); + WARN_ON(system_state >= SYSTEM_RUNNING); slot = -1; for (i = 0; i < FIX_BTMAPS_SLOTS; i++) { diff --git a/mm/frame_vector.c b/mm/frame_vector.c index 2f98df0d460e..c64dca6e27c2 100644 --- a/mm/frame_vector.c +++ b/mm/frame_vector.c @@ -53,6 +53,20 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, ret = -EFAULT; goto out; } + + /* + * While get_vaddr_frames() could be used for transient (kernel + * controlled lifetime) pinning of memory pages all current + * users establish long term (userspace controlled lifetime) + * page pinning. Treat get_vaddr_frames() like + * get_user_pages_longterm() and disallow it for filesystem-dax + * mappings. + */ + if (vma_is_fsdax(vma)) { + ret = -EOPNOTSUPP; + goto out; + } + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) { vec->got_ref = true; vec->is_pfns = false; @@ -1095,6 +1095,70 @@ long get_user_pages(unsigned long start, unsigned long nr_pages, } EXPORT_SYMBOL(get_user_pages); +#ifdef CONFIG_FS_DAX +/* + * This is the same as get_user_pages() in that it assumes we are + * operating on the current task's mm, but it goes further to validate + * that the vmas associated with the address range are suitable for + * longterm elevated page reference counts. For example, filesystem-dax + * mappings are subject to the lifetime enforced by the filesystem and + * we need guarantees that longterm users like RDMA and V4L2 only + * establish mappings that have a kernel enforced revocation mechanism. + * + * "longterm" == userspace controlled elevated page count lifetime. + * Contrast this to iov_iter_get_pages() usages which are transient. + */ +long get_user_pages_longterm(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas_arg) +{ + struct vm_area_struct **vmas = vmas_arg; + struct vm_area_struct *vma_prev = NULL; + long rc, i; + + if (!pages) + return -EINVAL; + + if (!vmas) { + vmas = kcalloc(nr_pages, sizeof(struct vm_area_struct *), + GFP_KERNEL); + if (!vmas) + return -ENOMEM; + } + + rc = get_user_pages(start, nr_pages, gup_flags, pages, vmas); + + for (i = 0; i < rc; i++) { + struct vm_area_struct *vma = vmas[i]; + + if (vma == vma_prev) + continue; + + vma_prev = vma; + + if (vma_is_fsdax(vma)) + break; + } + + /* + * Either get_user_pages() failed, or the vma validation + * succeeded, in either case we don't need to put_page() before + * returning. + */ + if (i >= rc) + goto out; + + for (i = 0; i < rc; i++) + put_page(pages[i]); + rc = -EOPNOTSUPP; +out: + if (vmas != vmas_arg) + kfree(vmas); + return rc; +} +EXPORT_SYMBOL(get_user_pages_longterm); +#endif /* CONFIG_FS_DAX */ + /** * populate_vma_page_range() - populate a range of pages in the vma. * @vma: target vma diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f22401fd83b5..0e7ded98d114 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -474,13 +474,10 @@ out: } __setup("transparent_hugepage=", setup_transparent_hugepage); -pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma, bool dirty) +pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) { - if (likely(vma->vm_flags & VM_WRITE)) { + if (likely(vma->vm_flags & VM_WRITE)) pmd = pmd_mkwrite(pmd); - if (dirty) - pmd = pmd_mkdirty(pmd); - } return pmd; } @@ -602,7 +599,7 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page, } entry = mk_huge_pmd(page, vma->vm_page_prot); - entry = maybe_pmd_mkwrite(entry, vma, true); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); page_add_new_anon_rmap(page, vma, haddr, true); mem_cgroup_commit_charge(page, memcg, false, true); lru_cache_add_active_or_unevictable(page, vma); @@ -744,8 +741,8 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, if (pfn_t_devmap(pfn)) entry = pmd_mkdevmap(entry); if (write) { - entry = pmd_mkyoung(entry); - entry = maybe_pmd_mkwrite(entry, vma, true); + entry = pmd_mkyoung(pmd_mkdirty(entry)); + entry = maybe_pmd_mkwrite(entry, vma); } if (pgtable) { @@ -791,14 +788,10 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd); #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD -static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma, - bool dirty) +static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma) { - if (likely(vma->vm_flags & VM_WRITE)) { + if (likely(vma->vm_flags & VM_WRITE)) pud = pud_mkwrite(pud); - if (dirty) - pud = pud_mkdirty(pud); - } return pud; } @@ -814,8 +807,8 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, if (pfn_t_devmap(pfn)) entry = pud_mkdevmap(entry); if (write) { - entry = pud_mkyoung(entry); - entry = maybe_pud_mkwrite(entry, vma, true); + entry = pud_mkyoung(pud_mkdirty(entry)); + entry = maybe_pud_mkwrite(entry, vma); } set_pud_at(mm, addr, pud, entry); update_mmu_cache_pud(vma, addr, pud); @@ -1286,7 +1279,7 @@ int do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) if (reuse_swap_page(page, NULL)) { pmd_t entry; entry = pmd_mkyoung(orig_pmd); - entry = maybe_pmd_mkwrite(entry, vma, true); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1)) update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); ret |= VM_FAULT_WRITE; @@ -1356,7 +1349,7 @@ alloc: } else { pmd_t entry; entry = mk_huge_pmd(new_page, vma->vm_page_prot); - entry = maybe_pmd_mkwrite(entry, vma, true); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); pmdp_huge_clear_flush_notify(vma, haddr, vmf->pmd); page_add_new_anon_rmap(new_page, vma, haddr, true); mem_cgroup_commit_charge(new_page, memcg, false, true); @@ -2935,7 +2928,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) if (pmd_swp_soft_dirty(*pvmw->pmd)) pmde = pmd_mksoft_dirty(pmde); if (is_write_migration_entry(entry)) - pmde = maybe_pmd_mkwrite(pmde, vma, false); + pmde = maybe_pmd_mkwrite(pmde, vma); flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE); page_add_anon_rmap(new, vma, mmun_start, true); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 681b300185c0..9a334f5fb730 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3125,6 +3125,13 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma) } } +static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) +{ + if (addr & ~(huge_page_mask(hstate_vma(vma)))) + return -EINVAL; + return 0; +} + /* * We cannot handle pagefaults against hugetlb pages at all. They cause * handle_mm_fault() to try to instantiate regular-sized pages in the @@ -3141,6 +3148,7 @@ const struct vm_operations_struct hugetlb_vm_ops = { .fault = hugetlb_vm_op_fault, .open = hugetlb_vm_op_open, .close = hugetlb_vm_op_close, + .split = hugetlb_vm_op_split, }; static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, @@ -4627,7 +4635,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, pte_t *pte = NULL; pgd = pgd_offset(mm, addr); - p4d = p4d_offset(pgd, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return NULL; pud = pud_alloc(mm, p4d, addr); if (pud) { if (sz == PUD_SIZE) { diff --git a/mm/internal.h b/mm/internal.h index b35cdebda0ce..e6bd35182dae 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -328,8 +328,7 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page) } } -extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma, - bool dirty); +extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /* * At what user virtual address is page expected in @vma? diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 6bcfb01ba038..410c8235e671 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -134,7 +134,7 @@ static void print_error_description(struct kasan_access_info *info) pr_err("BUG: KASAN: %s in %pS\n", bug_type, (void *)info->ip); - pr_err("%s of size %zu at addr %p by task %s/%d\n", + pr_err("%s of size %zu at addr %px by task %s/%d\n", info->is_write ? "Write" : "Read", info->access_size, info->access_addr, current->comm, task_pid_nr(current)); } @@ -206,7 +206,7 @@ static void describe_object_addr(struct kmem_cache *cache, void *object, const char *rel_type; int rel_bytes; - pr_err("The buggy address belongs to the object at %p\n" + pr_err("The buggy address belongs to the object at %px\n" " which belongs to the cache %s of size %d\n", object, cache->name, cache->object_size); @@ -225,7 +225,7 @@ static void describe_object_addr(struct kmem_cache *cache, void *object, } pr_err("The buggy address is located %d bytes %s of\n" - " %d-byte region [%p, %p)\n", + " %d-byte region [%px, %px)\n", rel_bytes, rel_type, cache->object_size, (void *)object_addr, (void *)(object_addr + cache->object_size)); } @@ -302,7 +302,7 @@ static void print_shadow_for_address(const void *addr) char shadow_buf[SHADOW_BYTES_PER_ROW]; snprintf(buffer, sizeof(buffer), - (i == 0) ? ">%p: " : " %p: ", kaddr); + (i == 0) ? ">%px: " : " %px: ", kaddr); /* * We should not pass a shadow pointer to generic * function, because generic functions may try to diff --git a/mm/khugepaged.c b/mm/khugepaged.c index db43dc8a8ae6..ea4ff259b671 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1057,7 +1057,7 @@ static void collapse_huge_page(struct mm_struct *mm, pgtable = pmd_pgtable(_pmd); _pmd = mk_huge_pmd(new_page, vma->vm_page_prot); - _pmd = maybe_pmd_mkwrite(_pmd, vma, false); + _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); /* * spin_lock() below is not the equivalent of smp_wmb(), so diff --git a/mm/kmemcheck.c b/mm/kmemcheck.c deleted file mode 100644 index cec594032515..000000000000 --- a/mm/kmemcheck.c +++ /dev/null @@ -1 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 diff --git a/mm/kmemleak.c b/mm/kmemleak.c index e4738d5e9b8c..d73c14294f3a 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1523,6 +1523,8 @@ static void kmemleak_scan(void) if (page_count(page) == 0) continue; scan_block(page, page + 1, NULL); + if (!(pfn & 63)) + cond_resched(); } } put_online_mems(); diff --git a/mm/madvise.c b/mm/madvise.c index 375cf32087e4..751e97aa2210 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -276,15 +276,14 @@ static long madvise_willneed(struct vm_area_struct *vma, { struct file *file = vma->vm_file; + *prev = vma; #ifdef CONFIG_SWAP if (!file) { - *prev = vma; force_swapin_readahead(vma, start, end); return 0; } if (shmem_mapping(file->f_mapping)) { - *prev = vma; force_shm_swapin_readahead(vma, start, end, file->f_mapping); return 0; @@ -299,7 +298,6 @@ static long madvise_willneed(struct vm_area_struct *vma, return 0; } - *prev = vma; start = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; if (end > vma->vm_end) end = vma->vm_end; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 50e6906314f8..ac2ffd5e02b9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6044,7 +6044,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) memcg_check_events(memcg, page); if (!mem_cgroup_is_root(memcg)) - css_put(&memcg->css); + css_put_many(&memcg->css, nr_entries); } /** diff --git a/mm/memory.c b/mm/memory.c index b10c1d26f675..ca5674cbaff2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3335,7 +3335,7 @@ static int do_set_pmd(struct vm_fault *vmf, struct page *page) entry = mk_huge_pmd(page, vma->vm_page_prot); if (write) - entry = maybe_pmd_mkwrite(entry, vma, true); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); add_mm_counter(vma->vm_mm, MM_FILEPAGES, HPAGE_PMD_NR); page_add_file_rmap(page, true); @@ -3831,7 +3831,8 @@ static inline int create_huge_pmd(struct vm_fault *vmf) return VM_FAULT_FALLBACK; } -static int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd) +/* `inline' is required to avoid gcc 4.1.2 build error */ +static inline int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd) { if (vma_is_anonymous(vmf->vma)) return do_huge_pmd_wp_page(vmf, orig_pmd); diff --git a/mm/migrate.c b/mm/migrate.c index 57865fc8cfe3..4d0be47a322a 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2068,7 +2068,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, } entry = mk_huge_pmd(new_page, vma->vm_page_prot); - entry = maybe_pmd_mkwrite(entry, vma, false); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); /* * Clear the old entry under pagetable lock and establish the new PTE. diff --git a/mm/mmap.c b/mm/mmap.c index 924839fac0e6..9efdc021ad22 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2555,9 +2555,11 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *new; int err; - if (is_vm_hugetlb_page(vma) && (addr & - ~(huge_page_mask(hstate_vma(vma))))) - return -EINVAL; + if (vma->vm_ops && vma->vm_ops->split) { + err = vma->vm_ops->split(vma, addr); + if (err) + return err; + } new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!new) @@ -3017,20 +3019,20 @@ void exit_mmap(struct mm_struct *mm) /* Use -1 here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, vma, 0, -1); - set_bit(MMF_OOM_SKIP, &mm->flags); - if (unlikely(tsk_is_oom_victim(current))) { + if (unlikely(mm_is_oom_victim(mm))) { /* * Wait for oom_reap_task() to stop working on this * mm. Because MMF_OOM_SKIP is already set before * calling down_read(), oom_reap_task() will not run * on this "mm" post up_write(). * - * tsk_is_oom_victim() cannot be set from under us - * either because current->mm is already set to NULL + * mm_is_oom_victim() cannot be set from under us + * either because victim->mm is already set to NULL * under task_lock before calling mmput and oom_mm is - * set not NULL by the OOM killer only if current->mm + * set not NULL by the OOM killer only if victim->mm * is found not NULL while holding the task_lock. */ + set_bit(MMF_OOM_SKIP, &mm->flags); down_write(&mm->mmap_sem); up_write(&mm->mmap_sem); } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index c86fbd1b590e..29f855551efe 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -550,7 +550,6 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) */ set_bit(MMF_UNSTABLE, &mm->flags); - tlb_gather_mmu(&tlb, mm, 0, -1); for (vma = mm->mmap ; vma; vma = vma->vm_next) { if (!can_madv_dontneed_vma(vma)) continue; @@ -565,11 +564,13 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) * we do not want to block exit_mmap by keeping mm ref * count elevated without a good reason. */ - if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) + if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) { + tlb_gather_mmu(&tlb, mm, vma->vm_start, vma->vm_end); unmap_page_range(&tlb, vma, vma->vm_start, vma->vm_end, NULL); + tlb_finish_mmu(&tlb, vma->vm_start, vma->vm_end); + } } - tlb_finish_mmu(&tlb, 0, -1); pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n", task_pid_nr(tsk), tsk->comm, K(get_mm_counter(mm, MM_ANONPAGES)), @@ -682,8 +683,10 @@ static void mark_oom_victim(struct task_struct *tsk) return; /* oom_mm is bound to the signal struct life time. */ - if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) + if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) { mmgrab(tsk->signal->oom_mm); + set_bit(MMF_OOM_VICTIM, &mm->flags); + } /* * Make sure that the task is woken up from uninterruptible sleep diff --git a/mm/page-writeback.c b/mm/page-writeback.c index e7095030aa1f..586f31261c83 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -433,11 +433,8 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc) else bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE; - if (unlikely(bg_thresh >= thresh)) { - pr_warn("vm direct limit must be set greater than background limit.\n"); + if (bg_thresh >= thresh) bg_thresh = thresh / 2; - } - tsk = current; if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) { bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d4096f4a5c1f..7e5e775e97f4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2507,10 +2507,6 @@ void drain_all_pages(struct zone *zone) if (WARN_ON_ONCE(!mm_percpu_wq)) return; - /* Workqueues cannot recurse */ - if (current->flags & PF_WQ_WORKER) - return; - /* * Do not drain if one is already in progress unless it's specific to * a zone. Such callers are primarily CMA and memory hotplug and need @@ -2688,6 +2684,7 @@ void free_unref_page_list(struct list_head *list) { struct page *page, *next; unsigned long flags, pfn; + int batch_count = 0; /* Prepare pages for freeing */ list_for_each_entry_safe(page, next, list, lru) { @@ -2704,6 +2701,16 @@ void free_unref_page_list(struct list_head *list) set_page_private(page, 0); trace_mm_page_free_batched(page); free_unref_page_commit(page, pfn); + + /* + * Guard against excessive IRQ disabled times when we get + * a large list of pages to free. + */ + if (++batch_count == SWAP_CLUSTER_MAX) { + local_irq_restore(flags); + batch_count = 0; + local_irq_save(flags); + } } local_irq_restore(flags); } @@ -7656,11 +7663,18 @@ int alloc_contig_range(unsigned long start, unsigned long end, /* * In case of -EBUSY, we'd like to know which page causes problem. - * So, just fall through. We will check it in test_pages_isolated(). + * So, just fall through. test_pages_isolated() has a tracepoint + * which will report the busy page. + * + * It is possible that busy pages could become available before + * the call to test_pages_isolated, and the range will actually be + * allocated. So, if we fall through be sure to clear ret so that + * -EBUSY is not accidentally used or returned to caller. */ ret = __alloc_contig_migrate_range(&cc, start, end); if (ret && ret != -EBUSY) goto done; + ret =0; /* * Pages from [start, end) are within a MAX_ORDER_NR_PAGES diff --git a/mm/percpu.c b/mm/percpu.c index 79e3549cab0f..50e7fdf84055 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2719,7 +2719,11 @@ void __init setup_per_cpu_areas(void) if (pcpu_setup_first_chunk(ai, fc) < 0) panic("Failed to initialize percpu areas."); +#ifdef CONFIG_CRIS +#warning "the CRIS architecture has physical and virtual addresses confused" +#else pcpu_free_alloc_info(ai); +#endif } #endif /* CONFIG_SMP */ diff --git a/mm/slab.c b/mm/slab.c index 183e996dde5f..4e51ef954026 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1584,11 +1584,8 @@ static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines) *dbg_redzone2(cachep, objp)); } - if (cachep->flags & SLAB_STORE_USER) { - pr_err("Last user: [<%p>](%pSR)\n", - *dbg_userword(cachep, objp), - *dbg_userword(cachep, objp)); - } + if (cachep->flags & SLAB_STORE_USER) + pr_err("Last user: (%pSR)\n", *dbg_userword(cachep, objp)); realobj = (char *)objp + obj_offset(cachep); size = cachep->object_size; for (i = 0; i < size && lines; i += 16, lines--) { @@ -1621,7 +1618,7 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp) /* Mismatch ! */ /* Print header */ if (lines == 0) { - pr_err("Slab corruption (%s): %s start=%p, len=%d\n", + pr_err("Slab corruption (%s): %s start=%px, len=%d\n", print_tainted(), cachep->name, realobj, size); print_objinfo(cachep, objp, 0); @@ -1650,13 +1647,13 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp) if (objnr) { objp = index_to_obj(cachep, page, objnr - 1); realobj = (char *)objp + obj_offset(cachep); - pr_err("Prev obj: start=%p, len=%d\n", realobj, size); + pr_err("Prev obj: start=%px, len=%d\n", realobj, size); print_objinfo(cachep, objp, 2); } if (objnr + 1 < cachep->num) { objp = index_to_obj(cachep, page, objnr + 1); realobj = (char *)objp + obj_offset(cachep); - pr_err("Next obj: start=%p, len=%d\n", realobj, size); + pr_err("Next obj: start=%px, len=%d\n", realobj, size); print_objinfo(cachep, objp, 2); } } @@ -2608,7 +2605,7 @@ static void slab_put_obj(struct kmem_cache *cachep, /* Verify double free bug */ for (i = page->active; i < cachep->num; i++) { if (get_free_obj(page, i) == objnr) { - pr_err("slab: double free detected in cache '%s', objp %p\n", + pr_err("slab: double free detected in cache '%s', objp %px\n", cachep->name, objp); BUG(); } @@ -2772,7 +2769,7 @@ static inline void verify_redzone_free(struct kmem_cache *cache, void *obj) else slab_error(cache, "memory outside object was overwritten"); - pr_err("%p: redzone 1:0x%llx, redzone 2:0x%llx\n", + pr_err("%px: redzone 1:0x%llx, redzone 2:0x%llx\n", obj, redzone1, redzone2); } @@ -3078,7 +3075,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, if (*dbg_redzone1(cachep, objp) != RED_INACTIVE || *dbg_redzone2(cachep, objp) != RED_INACTIVE) { slab_error(cachep, "double free, or memory outside object was overwritten"); - pr_err("%p: redzone 1:0x%llx, redzone 2:0x%llx\n", + pr_err("%px: redzone 1:0x%llx, redzone 2:0x%llx\n", objp, *dbg_redzone1(cachep, objp), *dbg_redzone2(cachep, objp)); } @@ -3091,7 +3088,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, cachep->ctor(objp); if (ARCH_SLAB_MINALIGN && ((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))) { - pr_err("0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n", + pr_err("0x%px: not aligned to ARCH_SLAB_MINALIGN=%d\n", objp, (int)ARCH_SLAB_MINALIGN); } return objp; @@ -4283,7 +4280,7 @@ static void show_symbol(struct seq_file *m, unsigned long address) return; } #endif - seq_printf(m, "%p", (void *)address); + seq_printf(m, "%px", (void *)address); } static int leaks_show(struct seq_file *m, void *p) |
