diff options
Diffstat (limited to 'mm')
39 files changed, 1102 insertions, 396 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 9b8fccb969dc..beb7a455915d 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -312,7 +312,6 @@ config NEED_BOUNCE_POOL config NR_QUICK int depends on QUICKLIST - default "2" if AVR32 default "1" config VIRT_TO_BUS diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 6d861d090e9f..f028a9a472fd 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -12,8 +12,6 @@ #include <linux/device.h> #include <trace/events/writeback.h> -static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); - struct backing_dev_info noop_backing_dev_info = { .name = "noop", .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, @@ -242,6 +240,8 @@ static __init int bdi_class_init(void) } postcore_initcall(bdi_class_init); +static int bdi_init(struct backing_dev_info *bdi); + static int __init default_bdi_init(void) { int err; @@ -294,6 +294,8 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, memset(wb, 0, sizeof(*wb)); + if (wb != &bdi->wb) + bdi_get(bdi); wb->bdi = bdi; wb->last_old_flush = jiffies; INIT_LIST_HEAD(&wb->b_dirty); @@ -314,8 +316,10 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, wb->dirty_sleep = jiffies; wb->congested = wb_congested_get_create(bdi, blkcg_id, gfp); - if (!wb->congested) - return -ENOMEM; + if (!wb->congested) { + err = -ENOMEM; + goto out_put_bdi; + } err = fprop_local_init_percpu(&wb->completions, gfp); if (err) @@ -335,9 +339,14 @@ out_destroy_stat: fprop_local_destroy_percpu(&wb->completions); out_put_cong: wb_congested_put(wb->congested); +out_put_bdi: + if (wb != &bdi->wb) + bdi_put(bdi); return err; } +static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb); + /* * Remove bdi from the global list and shutdown any threads we have running */ @@ -347,10 +356,18 @@ static void wb_shutdown(struct bdi_writeback *wb) spin_lock_bh(&wb->work_lock); if (!test_and_clear_bit(WB_registered, &wb->state)) { spin_unlock_bh(&wb->work_lock); + /* + * Wait for wb shutdown to finish if someone else is just + * running wb_shutdown(). Otherwise we could proceed to wb / + * bdi destruction before wb_shutdown() is finished. + */ + wait_on_bit(&wb->state, WB_shutting_down, TASK_UNINTERRUPTIBLE); return; } + set_bit(WB_shutting_down, &wb->state); spin_unlock_bh(&wb->work_lock); + cgwb_remove_from_bdi_list(wb); /* * Drain work list and shutdown the delayed_work. !WB_registered * tells wb_workfn() that @wb is dying and its work_list needs to @@ -359,6 +376,12 @@ static void wb_shutdown(struct bdi_writeback *wb) mod_delayed_work(bdi_wq, &wb->dwork, 0); flush_delayed_work(&wb->dwork); WARN_ON(!list_empty(&wb->work_list)); + /* + * Make sure bit gets cleared after shutdown is finished. Matches with + * the barrier provided by test_and_clear_bit() above. + */ + smp_wmb(); + clear_bit(WB_shutting_down, &wb->state); } static void wb_exit(struct bdi_writeback *wb) @@ -372,6 +395,8 @@ static void wb_exit(struct bdi_writeback *wb) fprop_local_destroy_percpu(&wb->completions); wb_congested_put(wb->congested); + if (wb != &wb->bdi->wb) + bdi_put(wb->bdi); } #ifdef CONFIG_CGROUP_WRITEBACK @@ -381,11 +406,9 @@ static void wb_exit(struct bdi_writeback *wb) /* * cgwb_lock protects bdi->cgwb_tree, bdi->cgwb_congested_tree, * blkcg->cgwb_list, and memcg->cgwb_list. bdi->cgwb_tree is also RCU - * protected. cgwb_release_wait is used to wait for the completion of cgwb - * releases from bdi destruction path. + * protected. */ static DEFINE_SPINLOCK(cgwb_lock); -static DECLARE_WAIT_QUEUE_HEAD(cgwb_release_wait); /** * wb_congested_get_create - get or create a wb_congested @@ -438,7 +461,7 @@ retry: return NULL; atomic_set(&new_congested->refcnt, 0); - new_congested->bdi = bdi; + new_congested->__bdi = bdi; new_congested->blkcg_id = blkcg_id; goto retry; @@ -466,10 +489,10 @@ void wb_congested_put(struct bdi_writeback_congested *congested) } /* bdi might already have been destroyed leaving @congested unlinked */ - if (congested->bdi) { + if (congested->__bdi) { rb_erase(&congested->rb_node, - &congested->bdi->cgwb_congested_tree); - congested->bdi = NULL; + &congested->__bdi->cgwb_congested_tree); + congested->__bdi = NULL; } spin_unlock_irqrestore(&cgwb_lock, flags); @@ -480,11 +503,6 @@ static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); - struct backing_dev_info *bdi = wb->bdi; - - spin_lock_irq(&cgwb_lock); - list_del_rcu(&wb->bdi_node); - spin_unlock_irq(&cgwb_lock); wb_shutdown(wb); @@ -495,9 +513,6 @@ static void cgwb_release_workfn(struct work_struct *work) percpu_ref_exit(&wb->refcnt); wb_exit(wb); kfree_rcu(wb, rcu); - - if (atomic_dec_and_test(&bdi->usage_cnt)) - wake_up_all(&cgwb_release_wait); } static void cgwb_release(struct percpu_ref *refcnt) @@ -517,6 +532,13 @@ static void cgwb_kill(struct bdi_writeback *wb) percpu_ref_kill(&wb->refcnt); } +static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) +{ + spin_lock_irq(&cgwb_lock); + list_del_rcu(&wb->bdi_node); + spin_unlock_irq(&cgwb_lock); +} + static int cgwb_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp) { @@ -580,7 +602,6 @@ static int cgwb_create(struct backing_dev_info *bdi, /* we might have raced another instance of this function */ ret = radix_tree_insert(&bdi->cgwb_tree, memcg_css->id, wb); if (!ret) { - atomic_inc(&bdi->usage_cnt); list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); list_add(&wb->memcg_node, memcg_cgwb_list); list_add(&wb->blkcg_node, blkcg_cgwb_list); @@ -670,7 +691,6 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); bdi->cgwb_congested_tree = RB_ROOT; - atomic_set(&bdi->usage_cnt, 1); ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); if (!ret) { @@ -680,36 +700,26 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) return ret; } -static void cgwb_bdi_destroy(struct backing_dev_info *bdi) +static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { struct radix_tree_iter iter; - struct rb_node *rbn; void **slot; + struct bdi_writeback *wb; WARN_ON(test_bit(WB_registered, &bdi->wb.state)); spin_lock_irq(&cgwb_lock); - radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) cgwb_kill(*slot); - while ((rbn = rb_first(&bdi->cgwb_congested_tree))) { - struct bdi_writeback_congested *congested = - rb_entry(rbn, struct bdi_writeback_congested, rb_node); - - rb_erase(rbn, &bdi->cgwb_congested_tree); - congested->bdi = NULL; /* mark @congested unlinked */ + while (!list_empty(&bdi->wb_list)) { + wb = list_first_entry(&bdi->wb_list, struct bdi_writeback, + bdi_node); + spin_unlock_irq(&cgwb_lock); + wb_shutdown(wb); + spin_lock_irq(&cgwb_lock); } - spin_unlock_irq(&cgwb_lock); - - /* - * All cgwb's and their congested states must be shutdown and - * released before returning. Drain the usage counter to wait for - * all cgwb's and cgwb_congested's ever created on @bdi. - */ - atomic_dec(&bdi->usage_cnt); - wait_event(cgwb_release_wait, !atomic_read(&bdi->usage_cnt)); } /** @@ -749,6 +759,28 @@ void wb_blkcg_offline(struct blkcg *blkcg) spin_unlock_irq(&cgwb_lock); } +static void cgwb_bdi_exit(struct backing_dev_info *bdi) +{ + struct rb_node *rbn; + + spin_lock_irq(&cgwb_lock); + while ((rbn = rb_first(&bdi->cgwb_congested_tree))) { + struct bdi_writeback_congested *congested = + rb_entry(rbn, struct bdi_writeback_congested, rb_node); + + rb_erase(rbn, &bdi->cgwb_congested_tree); + congested->__bdi = NULL; /* mark @congested unlinked */ + } + spin_unlock_irq(&cgwb_lock); +} + +static void cgwb_bdi_register(struct backing_dev_info *bdi) +{ + spin_lock_irq(&cgwb_lock); + list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); + spin_unlock_irq(&cgwb_lock); +} + #else /* CONFIG_CGROUP_WRITEBACK */ static int cgwb_bdi_init(struct backing_dev_info *bdi) @@ -769,14 +801,26 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) return 0; } -static void cgwb_bdi_destroy(struct backing_dev_info *bdi) +static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { } + +static void cgwb_bdi_exit(struct backing_dev_info *bdi) { wb_congested_put(bdi->wb_congested); } +static void cgwb_bdi_register(struct backing_dev_info *bdi) +{ + list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); +} + +static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) +{ + list_del_rcu(&wb->bdi_node); +} + #endif /* CONFIG_CGROUP_WRITEBACK */ -int bdi_init(struct backing_dev_info *bdi) +static int bdi_init(struct backing_dev_info *bdi) { int ret; @@ -792,11 +836,8 @@ int bdi_init(struct backing_dev_info *bdi) ret = cgwb_bdi_init(bdi); - list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); - return ret; } -EXPORT_SYMBOL(bdi_init); struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id) { @@ -813,22 +854,20 @@ struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id) } return bdi; } +EXPORT_SYMBOL(bdi_alloc_node); -int bdi_register(struct backing_dev_info *bdi, struct device *parent, - const char *fmt, ...) +int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) { - va_list args; struct device *dev; if (bdi->dev) /* The driver needs to use separate queues per device */ return 0; - va_start(args, fmt); - dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args); - va_end(args); + dev = device_create_vargs(bdi_class, NULL, MKDEV(0, 0), bdi, fmt, args); if (IS_ERR(dev)) return PTR_ERR(dev); + cgwb_bdi_register(bdi); bdi->dev = dev; bdi_debug_register(bdi, dev_name(dev)); @@ -841,22 +880,29 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, trace_writeback_bdi_register(bdi); return 0; } -EXPORT_SYMBOL(bdi_register); +EXPORT_SYMBOL(bdi_register_va); -int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev) +int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...) { - return bdi_register(bdi, NULL, "%u:%u", MAJOR(dev), MINOR(dev)); + va_list args; + int ret; + + va_start(args, fmt); + ret = bdi_register_va(bdi, fmt, args); + va_end(args); + return ret; } -EXPORT_SYMBOL(bdi_register_dev); +EXPORT_SYMBOL(bdi_register); int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner) { int rc; - rc = bdi_register(bdi, NULL, "%u:%u", MAJOR(owner->devt), - MINOR(owner->devt)); + rc = bdi_register(bdi, "%u:%u", MAJOR(owner->devt), MINOR(owner->devt)); if (rc) return rc; + /* Leaking owner reference... */ + WARN_ON(bdi->owner); bdi->owner = owner; get_device(owner); return 0; @@ -880,7 +926,7 @@ void bdi_unregister(struct backing_dev_info *bdi) /* make sure nobody finds us on the bdi_list anymore */ bdi_remove_from_list(bdi); wb_shutdown(&bdi->wb); - cgwb_bdi_destroy(bdi); + cgwb_bdi_unregister(bdi); if (bdi->dev) { bdi_debug_unregister(bdi); @@ -894,18 +940,16 @@ void bdi_unregister(struct backing_dev_info *bdi) } } -static void bdi_exit(struct backing_dev_info *bdi) -{ - WARN_ON_ONCE(bdi->dev); - wb_exit(&bdi->wb); -} - static void release_bdi(struct kref *ref) { struct backing_dev_info *bdi = container_of(ref, struct backing_dev_info, refcnt); - bdi_exit(bdi); + if (test_bit(WB_registered, &bdi->wb.state)) + bdi_unregister(bdi); + WARN_ON_ONCE(bdi->dev); + wb_exit(&bdi->wb); + cgwb_bdi_exit(bdi); kfree(bdi); } @@ -913,38 +957,7 @@ void bdi_put(struct backing_dev_info *bdi) { kref_put(&bdi->refcnt, release_bdi); } - -void bdi_destroy(struct backing_dev_info *bdi) -{ - bdi_unregister(bdi); - bdi_exit(bdi); -} -EXPORT_SYMBOL(bdi_destroy); - -/* - * For use from filesystems to quickly init and register a bdi associated - * with dirty writeback - */ -int bdi_setup_and_register(struct backing_dev_info *bdi, char *name) -{ - int err; - - bdi->name = name; - bdi->capabilities = 0; - err = bdi_init(bdi); - if (err) - return err; - - err = bdi_register(bdi, NULL, "%.28s-%ld", name, - atomic_long_inc_return(&bdi_seq)); - if (err) { - bdi_destroy(bdi); - return err; - } - - return 0; -} -EXPORT_SYMBOL(bdi_setup_and_register); +EXPORT_SYMBOL(bdi_put); static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]), @@ -226,6 +226,7 @@ struct page *follow_page_mask(struct vm_area_struct *vma, unsigned int *page_mask) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; spinlock_t *ptl; @@ -243,8 +244,13 @@ struct page *follow_page_mask(struct vm_area_struct *vma, pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) return no_page_table(vma, flags); - - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (p4d_none(*p4d)) + return no_page_table(vma, flags); + BUILD_BUG_ON(p4d_huge(*p4d)); + if (unlikely(p4d_bad(*p4d))) + return no_page_table(vma, flags); + pud = pud_offset(p4d, address); if (pud_none(*pud)) return no_page_table(vma, flags); if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { @@ -325,6 +331,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, struct page **page) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -338,7 +345,9 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, else pgd = pgd_offset_gate(mm, address); BUG_ON(pgd_none(*pgd)); - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + BUG_ON(p4d_none(*p4d)); + pud = pud_offset(p4d, address); BUG_ON(pud_none(*pud)); pmd = pmd_offset(pud, address); if (pmd_none(*pmd)) @@ -1180,34 +1189,57 @@ struct page *get_dump_page(unsigned long addr) */ #ifdef CONFIG_HAVE_GENERIC_RCU_GUP +#ifndef gup_get_pte +/* + * We assume that the PTE can be read atomically. If this is not the case for + * your architecture, please provide the helper. + */ +static inline pte_t gup_get_pte(pte_t *ptep) +{ + return READ_ONCE(*ptep); +} +#endif + +static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) +{ + while ((*nr) - nr_start) { + struct page *page = pages[--(*nr)]; + + ClearPageReferenced(page); + put_page(page); + } +} + #ifdef __HAVE_ARCH_PTE_SPECIAL static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { + struct dev_pagemap *pgmap = NULL; + int nr_start = *nr, ret = 0; pte_t *ptep, *ptem; - int ret = 0; ptem = ptep = pte_offset_map(&pmd, addr); do { - /* - * In the line below we are assuming that the pte can be read - * atomically. If this is not the case for your architecture, - * please wrap this in a helper function! - * - * for an example see gup_get_pte in arch/x86/mm/gup.c - */ - pte_t pte = READ_ONCE(*ptep); + pte_t pte = gup_get_pte(ptep); struct page *head, *page; /* * Similar to the PMD case below, NUMA hinting must take slow * path using the pte_protnone check. */ - if (!pte_present(pte) || pte_special(pte) || - pte_protnone(pte) || (write && !pte_write(pte))) + if (pte_protnone(pte)) goto pte_unmap; - if (!arch_pte_access_permitted(pte, write)) + if (!pte_access_permitted(pte, write)) + goto pte_unmap; + + if (pte_devmap(pte)) { + pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); + if (unlikely(!pgmap)) { + undo_dev_pagemap(nr, nr_start, pages); + goto pte_unmap; + } + } else if (pte_special(pte)) goto pte_unmap; VM_BUG_ON(!pfn_valid(pte_pfn(pte))); @@ -1223,6 +1255,9 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, } VM_BUG_ON_PAGE(compound_head(page) != head, page); + + put_dev_pagemap(pgmap); + SetPageReferenced(page); pages[*nr] = page; (*nr)++; @@ -1252,15 +1287,76 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, } #endif /* __HAVE_ARCH_PTE_SPECIAL */ +#ifdef __HAVE_ARCH_PTE_DEVMAP +static int __gup_device_huge(unsigned long pfn, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + int nr_start = *nr; + struct dev_pagemap *pgmap = NULL; + + do { + struct page *page = pfn_to_page(pfn); + + pgmap = get_dev_pagemap(pfn, pgmap); + if (unlikely(!pgmap)) { + undo_dev_pagemap(nr, nr_start, pages); + return 0; + } + SetPageReferenced(page); + pages[*nr] = page; + get_page(page); + put_dev_pagemap(pgmap); + (*nr)++; + pfn++; + } while (addr += PAGE_SIZE, addr != end); + return 1; +} + +static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + unsigned long fault_pfn; + + fault_pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + return __gup_device_huge(fault_pfn, addr, end, pages, nr); +} + +static int __gup_device_huge_pud(pud_t pud, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + unsigned long fault_pfn; + + fault_pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + return __gup_device_huge(fault_pfn, addr, end, pages, nr); +} +#else +static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + BUILD_BUG(); + return 0; +} + +static int __gup_device_huge_pud(pud_t pud, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + BUILD_BUG(); + return 0; +} +#endif + static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { struct page *head, *page; int refs; - if (write && !pmd_write(orig)) + if (!pmd_access_permitted(orig, write)) return 0; + if (pmd_devmap(orig)) + return __gup_device_huge_pmd(orig, addr, end, pages, nr); + refs = 0; head = pmd_page(orig); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); @@ -1284,6 +1380,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, return 0; } + SetPageReferenced(head); return 1; } @@ -1293,9 +1390,12 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, struct page *head, *page; int refs; - if (write && !pud_write(orig)) + if (!pud_access_permitted(orig, write)) return 0; + if (pud_devmap(orig)) + return __gup_device_huge_pud(orig, addr, end, pages, nr); + refs = 0; head = pud_page(orig); page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); @@ -1319,6 +1419,7 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, return 0; } + SetPageReferenced(head); return 1; } @@ -1329,9 +1430,10 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, int refs; struct page *head, *page; - if (write && !pgd_write(orig)) + if (!pgd_access_permitted(orig, write)) return 0; + BUILD_BUG_ON(pgd_devmap(orig)); refs = 0; head = pgd_page(orig); page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT); @@ -1355,6 +1457,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, return 0; } + SetPageReferenced(head); return 1; } @@ -1400,13 +1503,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, return 1; } -static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, +static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; - pudp = pud_offset(&pgd, addr); + pudp = pud_offset(&p4d, addr); do { pud_t pud = READ_ONCE(*pudp); @@ -1428,6 +1531,31 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, return 1; } +static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + p4d_t *p4dp; + + p4dp = p4d_offset(&pgd, addr); + do { + p4d_t p4d = READ_ONCE(*p4dp); + + next = p4d_addr_end(addr, end); + if (p4d_none(p4d)) + return 0; + BUILD_BUG_ON(p4d_huge(p4d)); + if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) { + if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr, + P4D_SHIFT, next, write, pages, nr)) + return 0; + } else if (!gup_pud_range(p4d, addr, next, write, pages, nr)) + return 0; + } while (p4dp++, addr = next, addr != end); + + return 1; +} + /* * 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. @@ -1478,7 +1606,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr, PGDIR_SHIFT, next, write, pages, &nr)) break; - } else if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + } else if (!gup_p4d_range(pgd, addr, next, write, pages, &nr)) break; } while (pgdp++, addr = next, addr != end); local_irq_restore(flags); @@ -1486,6 +1614,21 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, return nr; } +#ifndef gup_fast_permitted +/* + * Check if it's allowed to use __get_user_pages_fast() for the range, or + * we need to fall back to the slow version: + */ +bool gup_fast_permitted(unsigned long start, int nr_pages, int write) +{ + unsigned long len, end; + + len = (unsigned long) nr_pages << PAGE_SHIFT; + end = start + len; + return end >= start; +} +#endif + /** * get_user_pages_fast() - pin user pages in memory * @start: starting user address @@ -1505,11 +1648,14 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { - int nr, ret; + int nr = 0, ret = 0; start &= PAGE_MASK; - nr = __get_user_pages_fast(start, nr_pages, write, pages); - ret = nr; + + if (gup_fast_permitted(start, nr_pages, write)) { + nr = __get_user_pages_fast(start, nr_pages, write, pages); + ret = nr; + } if (nr < nr_pages) { /* Try to get the remaining pages with get_user_pages */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index d36b2af4d1bf..f3c4f9d22821 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -240,18 +240,18 @@ static ssize_t defrag_store(struct kobject *kobj, clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("defer", buf, - min(sizeof("defer")-1, count))) { - clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); - clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); - clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); - set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); } else if (!memcmp("defer+madvise", buf, min(sizeof("defer+madvise")-1, count))) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + } else if (!memcmp("defer", buf, + min(sizeof("defer")-1, count))) { + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); } else if (!memcmp("madvise", buf, min(sizeof("madvise")-1, count))) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); @@ -1568,8 +1568,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, deactivate_page(page); if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) { - orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd, - tlb->fullmm); + pmdp_invalidate(vma, addr, pmd); orig_pmd = pmd_mkold(orig_pmd); orig_pmd = pmd_mkclean(orig_pmd); @@ -1724,37 +1723,69 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, { struct mm_struct *mm = vma->vm_mm; spinlock_t *ptl; - int ret = 0; + pmd_t entry; + bool preserve_write; + int ret; ptl = __pmd_trans_huge_lock(pmd, vma); - if (ptl) { - pmd_t entry; - bool preserve_write = prot_numa && pmd_write(*pmd); - ret = 1; + if (!ptl) + return 0; - /* - * Avoid trapping faults against the zero page. The read-only - * data is likely to be read-cached on the local CPU and - * local/remote hits to the zero page are not interesting. - */ - if (prot_numa && is_huge_zero_pmd(*pmd)) { - spin_unlock(ptl); - return ret; - } + preserve_write = prot_numa && pmd_write(*pmd); + ret = 1; - if (!prot_numa || !pmd_protnone(*pmd)) { - entry = pmdp_huge_get_and_clear_notify(mm, addr, pmd); - entry = pmd_modify(entry, newprot); - if (preserve_write) - entry = pmd_mk_savedwrite(entry); - ret = HPAGE_PMD_NR; - set_pmd_at(mm, addr, pmd, entry); - BUG_ON(vma_is_anonymous(vma) && !preserve_write && - pmd_write(entry)); - } - spin_unlock(ptl); - } + /* + * Avoid trapping faults against the zero page. The read-only + * data is likely to be read-cached on the local CPU and + * local/remote hits to the zero page are not interesting. + */ + if (prot_numa && is_huge_zero_pmd(*pmd)) + goto unlock; + + if (prot_numa && pmd_protnone(*pmd)) + goto unlock; + + /* + * In case prot_numa, we are under down_read(mmap_sem). It's critical + * to not clear pmd intermittently to avoid race with MADV_DONTNEED + * which is also under down_read(mmap_sem): + * + * CPU0: CPU1: + * change_huge_pmd(prot_numa=1) + * pmdp_huge_get_and_clear_notify() + * madvise_dontneed() + * zap_pmd_range() + * pmd_trans_huge(*pmd) == 0 (without ptl) + * // skip the pmd + * set_pmd_at(); + * // pmd is re-established + * + * The race makes MADV_DONTNEED miss the huge pmd and don't clear it + * which may break userspace. + * + * pmdp_invalidate() is required to make sure we don't miss + * dirty/young flags set by hardware. + */ + entry = *pmd; + pmdp_invalidate(vma, addr, pmd); + + /* + * Recover dirty/young flags. It relies on pmdp_invalidate to not + * corrupt them. + */ + if (pmd_dirty(*pmd)) + entry = pmd_mkdirty(entry); + if (pmd_young(*pmd)) + entry = pmd_mkyoung(entry); + entry = pmd_modify(entry, newprot); + if (preserve_write) + entry = pmd_mk_savedwrite(entry); + ret = HPAGE_PMD_NR; + set_pmd_at(mm, addr, pmd, entry); + BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry)); +unlock: + spin_unlock(ptl); return ret; } @@ -1828,7 +1859,7 @@ static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud, VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma); VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud)); - count_vm_event(THP_SPLIT_PMD); + count_vm_event(THP_SPLIT_PUD); pudp_huge_clear_flush_notify(vma, haddr, pud); } @@ -2048,6 +2079,7 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct page *page) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -2055,7 +2087,11 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, if (!pgd_present(*pgd)) return; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + return; + + pud = pud_offset(p4d, address); if (!pud_present(*pud)) return; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a7aa811b7d14..e5828875f7bb 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4403,7 +4403,9 @@ int hugetlb_reserve_pages(struct inode *inode, return 0; out_err: if (!vma || vma->vm_flags & VM_MAYSHARE) - region_abort(resv_map, from, to); + /* Don't call region_abort if region_chg failed */ + if (chg >= 0) + region_abort(resv_map, from, to); if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) kref_put(&resv_map->refs, resv_map_release); return ret; @@ -4555,7 +4557,8 @@ out: int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) { pgd_t *pgd = pgd_offset(mm, *addr); - pud_t *pud = pud_offset(pgd, *addr); + p4d_t *p4d = p4d_offset(pgd, *addr); + pud_t *pud = pud_offset(p4d, *addr); BUG_ON(page_count(virt_to_page(ptep)) == 0); if (page_count(virt_to_page(ptep)) == 1) @@ -4586,11 +4589,13 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pte_t *pte = NULL; pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); + p4d = p4d_offset(pgd, addr); + pud = pud_alloc(mm, p4d, addr); if (pud) { if (sz == PUD_SIZE) { pte = (pte_t *)pud; @@ -4610,18 +4615,22 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; - pmd_t *pmd = NULL; + pmd_t *pmd; pgd = pgd_offset(mm, addr); - if (pgd_present(*pgd)) { - pud = pud_offset(pgd, addr); - if (pud_present(*pud)) { - if (pud_huge(*pud)) - return (pte_t *)pud; - pmd = pmd_offset(pud, addr); - } - } + if (!pgd_present(*pgd)) + return NULL; + p4d = p4d_offset(pgd, addr); + if (!p4d_present(*p4d)) + return NULL; + pud = pud_offset(p4d, addr); + if (!pud_present(*pud)) + return NULL; + if (pud_huge(*pud)) + return (pte_t *)pud; + pmd = pmd_offset(pud, addr); return (pte_t *) pmd; } @@ -4644,6 +4653,7 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, { struct page *page = NULL; spinlock_t *ptl; + pte_t pte; retry: ptl = pmd_lockptr(mm, pmd); spin_lock(ptl); @@ -4653,12 +4663,13 @@ retry: */ if (!pmd_huge(*pmd)) goto out; - if (pmd_present(*pmd)) { + pte = huge_ptep_get((pte_t *)pmd); + if (pte_present(pte)) { page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT); if (flags & FOLL_GET) get_page(page); } else { - if (is_hugetlb_entry_migration(huge_ptep_get((pte_t *)pmd))) { + if (is_hugetlb_entry_migration(pte)) { spin_unlock(ptl); __migration_entry_wait(mm, (pte_t *)pmd, ptl); goto retry; diff --git a/mm/internal.h b/mm/internal.h index ccfc2a2969f4..266efaeaa370 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -481,6 +481,13 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, enum ttu_flags; struct tlbflush_unmap_batch; + +/* + * only for MM internal work items which do not depend on + * any allocations or locks which might depend on allocations + */ +extern struct workqueue_struct *mm_percpu_wq; + #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); void try_to_unmap_flush_dirty(void); diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 1c260e6b3b3c..dd2dea8eb077 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -96,11 +96,6 @@ static inline const void *kasan_shadow_to_mem(const void *shadow_addr) << KASAN_SHADOW_SCALE_SHIFT); } -static inline bool kasan_report_enabled(void) -{ - return !current->kasan_depth; -} - void kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip); void kasan_report_double_free(struct kmem_cache *cache, void *object, diff --git a/mm/kasan/kasan_init.c b/mm/kasan/kasan_init.c index 31238dad85fb..b96a5f773d88 100644 --- a/mm/kasan/kasan_init.c +++ b/mm/kasan/kasan_init.c @@ -30,6 +30,9 @@ */ unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss; +#if CONFIG_PGTABLE_LEVELS > 4 +p4d_t kasan_zero_p4d[PTRS_PER_P4D] __page_aligned_bss; +#endif #if CONFIG_PGTABLE_LEVELS > 3 pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss; #endif @@ -82,10 +85,10 @@ static void __init zero_pmd_populate(pud_t *pud, unsigned long addr, } while (pmd++, addr = next, addr != end); } -static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr, +static void __init zero_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long end) { - pud_t *pud = pud_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); unsigned long next; do { @@ -107,6 +110,23 @@ static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr, } while (pud++, addr = next, addr != end); } +static void __init zero_p4d_populate(pgd_t *pgd, unsigned long addr, + unsigned long end) +{ + p4d_t *p4d = p4d_offset(pgd, addr); + unsigned long next; + + do { + next = p4d_addr_end(addr, end); + + if (p4d_none(*p4d)) { + p4d_populate(&init_mm, p4d, + early_alloc(PAGE_SIZE, NUMA_NO_NODE)); + } + zero_pud_populate(p4d, addr, next); + } while (p4d++, addr = next, addr != end); +} + /** * kasan_populate_zero_shadow - populate shadow memory region with * kasan_zero_page @@ -125,6 +145,7 @@ void __init kasan_populate_zero_shadow(const void *shadow_start, next = pgd_addr_end(addr, end); if (IS_ALIGNED(addr, PGDIR_SIZE) && end - addr >= PGDIR_SIZE) { + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -135,9 +156,22 @@ void __init kasan_populate_zero_shadow(const void *shadow_start, * 3,2 - level page tables where we don't have * puds,pmds, so pgd_populate(), pud_populate() * is noops. + * + * The ifndef is required to avoid build breakage. + * + * With 5level-fixup.h, pgd_populate() is not nop and + * we reference kasan_zero_p4d. It's not defined + * unless 5-level paging enabled. + * + * The ifndef can be dropped once all KASAN-enabled + * architectures will switch to pgtable-nop4d.h. */ - pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_pud)); - pud = pud_offset(pgd, addr); +#ifndef __ARCH_HAS_5LEVEL_HACK + pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_p4d)); +#endif + p4d = p4d_offset(pgd, addr); + p4d_populate(&init_mm, p4d, lm_alias(kasan_zero_pud)); + pud = pud_offset(p4d, addr); pud_populate(&init_mm, pud, lm_alias(kasan_zero_pmd)); pmd = pmd_offset(pud, addr); pmd_populate_kernel(&init_mm, pmd, lm_alias(kasan_zero_pte)); @@ -148,6 +182,6 @@ void __init kasan_populate_zero_shadow(const void *shadow_start, pgd_populate(&init_mm, pgd, early_alloc(PAGE_SIZE, NUMA_NO_NODE)); } - zero_pud_populate(pgd, addr, next); + zero_p4d_populate(pgd, addr, next); } while (pgd++, addr = next, addr != end); } diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 6f1ed1630873..3a8ddf8baf7d 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -25,6 +25,7 @@ #include <linux/printk.h> #include <linux/shrinker.h> #include <linux/slab.h> +#include <linux/srcu.h> #include <linux/string.h> #include <linux/types.h> @@ -103,6 +104,7 @@ static int quarantine_tail; /* Total size of all objects in global_quarantine across all batches. */ static unsigned long quarantine_size; static DEFINE_SPINLOCK(quarantine_lock); +DEFINE_STATIC_SRCU(remove_cache_srcu); /* Maximum size of the global queue. */ static unsigned long quarantine_max_size; @@ -173,17 +175,22 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) struct qlist_head *q; struct qlist_head temp = QLIST_INIT; + /* + * Note: irq must be disabled until after we move the batch to the + * global quarantine. Otherwise quarantine_remove_cache() can miss + * some objects belonging to the cache if they are in our local temp + * list. quarantine_remove_cache() executes on_each_cpu() at the + * beginning which ensures that it either sees the objects in per-cpu + * lists or in the global quarantine. + */ local_irq_save(flags); q = this_cpu_ptr(&cpu_quarantine); qlist_put(q, &info->quarantine_link, cache->size); - if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) + if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) { qlist_move_all(q, &temp); - local_irq_restore(flags); - - if (unlikely(!qlist_empty(&temp))) { - spin_lock_irqsave(&quarantine_lock, flags); + spin_lock(&quarantine_lock); WRITE_ONCE(quarantine_size, quarantine_size + temp.bytes); qlist_move_all(&temp, &global_quarantine[quarantine_tail]); if (global_quarantine[quarantine_tail].bytes >= @@ -196,20 +203,33 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) if (new_tail != quarantine_head) quarantine_tail = new_tail; } - spin_unlock_irqrestore(&quarantine_lock, flags); + spin_unlock(&quarantine_lock); } + + local_irq_restore(flags); } void quarantine_reduce(void) { size_t total_size, new_quarantine_size, percpu_quarantines; unsigned long flags; + int srcu_idx; struct qlist_head to_free = QLIST_INIT; if (likely(READ_ONCE(quarantine_size) <= READ_ONCE(quarantine_max_size))) return; + /* + * srcu critical section ensures that quarantine_remove_cache() + * will not miss objects belonging to the cache while they are in our + * local to_free list. srcu is chosen because (1) it gives us private + * grace period domain that does not interfere with anything else, + * and (2) it allows synchronize_srcu() to return without waiting + * if there are no pending read critical sections (which is the + * expected case). + */ + srcu_idx = srcu_read_lock(&remove_cache_srcu); spin_lock_irqsave(&quarantine_lock, flags); /* @@ -237,6 +257,7 @@ void quarantine_reduce(void) spin_unlock_irqrestore(&quarantine_lock, flags); qlist_free_all(&to_free, NULL); + srcu_read_unlock(&remove_cache_srcu, srcu_idx); } static void qlist_move_cache(struct qlist_head *from, @@ -280,12 +301,28 @@ void quarantine_remove_cache(struct kmem_cache *cache) unsigned long flags, i; struct qlist_head to_free = QLIST_INIT; + /* + * Must be careful to not miss any objects that are being moved from + * per-cpu list to the global quarantine in quarantine_put(), + * nor objects being freed in quarantine_reduce(). on_each_cpu() + * achieves the first goal, while synchronize_srcu() achieves the + * second. + */ on_each_cpu(per_cpu_remove_cache, cache, 1); spin_lock_irqsave(&quarantine_lock, flags); - for (i = 0; i < QUARANTINE_BATCHES; i++) + for (i = 0; i < QUARANTINE_BATCHES; i++) { + if (qlist_empty(&global_quarantine[i])) + continue; qlist_move_cache(&global_quarantine[i], &to_free, cache); + /* Scanning whole quarantine can take a while. */ + spin_unlock_irqrestore(&quarantine_lock, flags); + cond_resched(); + spin_lock_irqsave(&quarantine_lock, flags); + } spin_unlock_irqrestore(&quarantine_lock, flags); qlist_free_all(&to_free, cache); + + synchronize_srcu(&remove_cache_srcu); } diff --git a/mm/kasan/report.c b/mm/kasan/report.c index f479365530b6..ab42a0803f16 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -13,7 +13,9 @@ * */ +#include <linux/bitops.h> #include <linux/ftrace.h> +#include <linux/init.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/printk.h> @@ -293,6 +295,40 @@ static void kasan_report_error(struct kasan_access_info *info) kasan_end_report(&flags); } +static unsigned long kasan_flags; + +#define KASAN_BIT_REPORTED 0 +#define KASAN_BIT_MULTI_SHOT 1 + +bool kasan_save_enable_multi_shot(void) +{ + return test_and_set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags); +} +EXPORT_SYMBOL_GPL(kasan_save_enable_multi_shot); + +void kasan_restore_multi_shot(bool enabled) +{ + if (!enabled) + clear_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags); +} +EXPORT_SYMBOL_GPL(kasan_restore_multi_shot); + +static int __init kasan_set_multi_shot(char *str) +{ + set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags); + return 1; +} +__setup("kasan_multi_shot", kasan_set_multi_shot); + +static inline bool kasan_report_enabled(void) +{ + if (current->kasan_depth) + return false; + if (test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags)) + return true; + return !test_and_set_bit(KASAN_BIT_REPORTED, &kasan_flags); +} + void kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip) { diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 26c874e90b12..20036d4f9f13 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1416,7 +1416,7 @@ static void kmemleak_scan(void) /* data/bss scanning */ scan_large_block(_sdata, _edata); scan_large_block(__bss_start, __bss_stop); - scan_large_block(__start_data_ro_after_init, __end_data_ro_after_init); + scan_large_block(__start_ro_after_init, __end_ro_after_init); #ifdef CONFIG_SMP /* per-cpu sections scanning */ diff --git a/mm/madvise.c b/mm/madvise.c index dc5927c812d3..7a2abf0127ae 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -513,7 +513,43 @@ static long madvise_dontneed(struct vm_area_struct *vma, if (!can_madv_dontneed_vma(vma)) return -EINVAL; - userfaultfd_remove(vma, prev, start, end); + if (!userfaultfd_remove(vma, start, end)) { + *prev = NULL; /* mmap_sem has been dropped, prev is stale */ + + down_read(¤t->mm->mmap_sem); + vma = find_vma(current->mm, start); + if (!vma) + return -ENOMEM; + if (start < vma->vm_start) { + /* + * This "vma" under revalidation is the one + * with the lowest vma->vm_start where start + * is also < vma->vm_end. If start < + * vma->vm_start it means an hole materialized + * in the user address space within the + * virtual range passed to MADV_DONTNEED. + */ + return -ENOMEM; + } + if (!can_madv_dontneed_vma(vma)) + return -EINVAL; + if (end > vma->vm_end) { + /* + * Don't fail if end > vma->vm_end. If the old + * vma was splitted while the mmap_sem was + * released the effect of the concurrent + * operation may not cause MADV_DONTNEED to + * have an undefined result. There may be an + * adjacent next vma that we'll walk + * next. userfaultfd_remove() will generate an + * UFFD_EVENT_REMOVE repetition on the + * end-vma->vm_end range, but the manager can + * handle a repetition fine. + */ + end = vma->vm_end; + } + VM_WARN_ON(start >= end); + } zap_page_range(vma, start, end - start); return 0; } @@ -554,8 +590,10 @@ static long madvise_remove(struct vm_area_struct *vma, * mmap_sem. */ get_file(f); - userfaultfd_remove(vma, prev, start, end); - up_read(¤t->mm->mmap_sem); + if (userfaultfd_remove(vma, start, end)) { + /* mmap_sem was not released by userfaultfd_remove() */ + up_read(¤t->mm->mmap_sem); + } error = vfs_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); diff --git a/mm/memblock.c b/mm/memblock.c index b64b47803e52..696f06d17c4e 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1118,7 +1118,10 @@ unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn, } } while (left < right); - return min(PHYS_PFN(type->regions[right].base), max_pfn); + if (right == type->cnt) + return max_pfn; + else + return min(PHYS_PFN(type->regions[right].base), max_pfn); } /** diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c52ec893e241..2bd7541d7c11 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -466,6 +466,8 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) struct mem_cgroup_tree_per_node *mctz; mctz = soft_limit_tree_from_page(page); + if (!mctz) + return; /* * Necessary to update all ancestors when hierarchy is used. * because their event counter is not touched. @@ -503,7 +505,8 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) for_each_node(nid) { mz = mem_cgroup_nodeinfo(memcg, nid); mctz = soft_limit_tree_node(nid); - mem_cgroup_remove_exceeded(mz, mctz); + if (mctz) + mem_cgroup_remove_exceeded(mz, mctz); } } @@ -2558,7 +2561,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, * is empty. Do it lockless to prevent lock bouncing. Races * are acceptable as soft limit is best effort anyway. */ - if (RB_EMPTY_ROOT(&mctz->rb_root)) + if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root)) return 0; /* @@ -4135,17 +4138,22 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) kfree(memcg->nodeinfo[node]); } -static void mem_cgroup_free(struct mem_cgroup *memcg) +static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; - memcg_wb_domain_exit(memcg); for_each_node(node) free_mem_cgroup_per_node_info(memcg, node); free_percpu(memcg->stat); kfree(memcg); } +static void mem_cgroup_free(struct mem_cgroup *memcg) +{ + memcg_wb_domain_exit(memcg); + __mem_cgroup_free(memcg); +} + static struct mem_cgroup *mem_cgroup_alloc(void) { struct mem_cgroup *memcg; @@ -4196,7 +4204,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) fail: if (memcg->id.id > 0) idr_remove(&mem_cgroup_idr, memcg->id.id); - mem_cgroup_free(memcg); + __mem_cgroup_free(memcg); return NULL; } diff --git a/mm/memory.c b/mm/memory.c index a97a4cec2e1f..6ff5d729ded0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -445,7 +445,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, mm_dec_nr_pmds(tlb->mm); } -static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, +static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { @@ -454,7 +454,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, unsigned long start; start = addr; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) @@ -462,6 +462,39 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, free_pmd_range(tlb, pud, addr, next, floor, ceiling); } while (pud++, addr = next, addr != end); + start &= P4D_MASK; + if (start < floor) + return; + if (ceiling) { + ceiling &= P4D_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + return; + + pud = pud_offset(p4d, start); + p4d_clear(p4d); + pud_free_tlb(tlb, pud, start); +} + +static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + p4d_t *p4d; + unsigned long next; + unsigned long start; + + start = addr; + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + free_pud_range(tlb, p4d, addr, next, floor, ceiling); + } while (p4d++, addr = next, addr != end); + start &= PGDIR_MASK; if (start < floor) return; @@ -473,9 +506,9 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, if (end - 1 > ceiling - 1) return; - pud = pud_offset(pgd, start); + p4d = p4d_offset(pgd, start); pgd_clear(pgd); - pud_free_tlb(tlb, pud, start); + p4d_free_tlb(tlb, p4d, start); } /* @@ -539,7 +572,7 @@ void free_pgd_range(struct mmu_gather *tlb, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - free_pud_range(tlb, pgd, addr, next, floor, ceiling); + free_p4d_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); } @@ -658,7 +691,8 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, pte_t pte, struct page *page) { pgd_t *pgd = pgd_offset(vma->vm_mm, addr); - pud_t *pud = pud_offset(pgd, addr); + p4d_t *p4d = p4d_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); pmd_t *pmd = pmd_offset(pud, addr); struct address_space *mapping; pgoff_t index; @@ -1023,16 +1057,16 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src } static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, + p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { pud_t *src_pud, *dst_pud; unsigned long next; - dst_pud = pud_alloc(dst_mm, dst_pgd, addr); + dst_pud = pud_alloc(dst_mm, dst_p4d, addr); if (!dst_pud) return -ENOMEM; - src_pud = pud_offset(src_pgd, addr); + src_pud = pud_offset(src_p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { @@ -1056,6 +1090,28 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src return 0; } +static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + p4d_t *src_p4d, *dst_p4d; + unsigned long next; + + dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr); + if (!dst_p4d) + return -ENOMEM; + src_p4d = p4d_offset(src_pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(src_p4d)) + continue; + if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d, + vma, addr, next)) + return -ENOMEM; + } while (dst_p4d++, src_p4d++, addr = next, addr != end); + return 0; +} + int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, struct vm_area_struct *vma) { @@ -1111,7 +1167,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; - if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, + if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd, vma, addr, next))) { ret = -ENOMEM; break; @@ -1267,14 +1323,14 @@ next: } static inline unsigned long zap_pud_range(struct mmu_gather *tlb, - struct vm_area_struct *vma, pgd_t *pgd, + struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, struct zap_details *details) { pud_t *pud; unsigned long next; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*pud) || pud_devmap(*pud)) { @@ -1295,6 +1351,25 @@ next: return addr; } +static inline unsigned long zap_p4d_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pgd_t *pgd, + unsigned long addr, unsigned long end, + struct zap_details *details) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + next = zap_pud_range(tlb, vma, p4d, addr, next, details); + } while (p4d++, addr = next, addr != end); + + return addr; +} + void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, @@ -1310,7 +1385,7 @@ void unmap_page_range(struct mmu_gather *tlb, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - next = zap_pud_range(tlb, vma, pgd, addr, next, details); + next = zap_p4d_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); } @@ -1465,16 +1540,24 @@ EXPORT_SYMBOL_GPL(zap_vma_ptes); pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { - pgd_t *pgd = pgd_offset(mm, addr); - pud_t *pud = pud_alloc(mm, pgd, addr); - if (pud) { - pmd_t *pmd = pmd_alloc(mm, pud, addr); - if (pmd) { - VM_BUG_ON(pmd_trans_huge(*pmd)); - return pte_alloc_map_lock(mm, pmd, addr, ptl); - } - } - return NULL; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset(mm, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, addr); + if (!pud) + return NULL; + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return NULL; + + VM_BUG_ON(pmd_trans_huge(*pmd)); + return pte_alloc_map_lock(mm, pmd, addr, ptl); } /* @@ -1740,7 +1823,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, return 0; } -static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, +static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { @@ -1748,7 +1831,7 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, unsigned long next; pfn -= addr >> PAGE_SHIFT; - pud = pud_alloc(mm, pgd, addr); + pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { @@ -1760,6 +1843,26 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, return 0; } +static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) +{ + p4d_t *p4d; + unsigned long next; + + pfn -= addr >> PAGE_SHIFT; + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + if (remap_pud_range(mm, p4d, addr, next, + pfn + (addr >> PAGE_SHIFT), prot)) + return -ENOMEM; + } while (p4d++, addr = next, addr != end); + return 0; +} + /** * remap_pfn_range - remap kernel memory to userspace * @vma: user vma to map to @@ -1816,7 +1919,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, flush_cache_range(vma, addr, end); do { next = pgd_addr_end(addr, end); - err = remap_pud_range(mm, pgd, addr, next, + err = remap_p4d_range(mm, pgd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) break; @@ -1932,7 +2035,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, return err; } -static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd, +static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, pte_fn_t fn, void *data) { @@ -1940,7 +2043,7 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd, unsigned long next; int err; - pud = pud_alloc(mm, pgd, addr); + pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { @@ -1952,6 +2055,26 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd, return err; } +static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data) +{ + p4d_t *p4d; + unsigned long next; + int err; + + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + err = apply_to_pud_range(mm, p4d, addr, next, fn, data); + if (err) + break; + } while (p4d++, addr = next, addr != end); + return err; +} + /* * Scan a region of virtual memory, filling in page tables as necessary * and calling a provided function on each leaf page table. @@ -1970,7 +2093,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); - err = apply_to_pud_range(mm, pgd, addr, next, fn, data); + err = apply_to_p4d_range(mm, pgd, addr, next, fn, data); if (err) break; } while (pgd++, addr = next, addr != end); @@ -3653,11 +3776,15 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, }; struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; + p4d_t *p4d; int ret; pgd = pgd_offset(mm, address); + p4d = p4d_alloc(mm, pgd, address); + if (!p4d) + return VM_FAULT_OOM; - vmf.pud = pud_alloc(mm, pgd, address); + vmf.pud = pud_alloc(mm, p4d, address); if (!vmf.pud) return VM_FAULT_OOM; if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) { @@ -3779,12 +3906,35 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address, } EXPORT_SYMBOL_GPL(handle_mm_fault); +#ifndef __PAGETABLE_P4D_FOLDED +/* + * Allocate p4d page table. + * We've already handled the fast-path in-line. + */ +int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +{ + p4d_t *new = p4d_alloc_one(mm, address); + if (!new) + return -ENOMEM; + + smp_wmb(); /* See comment in __pte_alloc */ + + spin_lock(&mm->page_table_lock); + if (pgd_present(*pgd)) /* Another has populated it */ + p4d_free(mm, new); + else + pgd_populate(mm, pgd, new); + spin_unlock(&mm->page_table_lock); + return 0; +} +#endif /* __PAGETABLE_P4D_FOLDED */ + #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. * We've already handled the fast-path in-line. */ -int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { pud_t *new = pud_alloc_one(mm, address); if (!new) @@ -3793,10 +3943,17 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&mm->page_table_lock); - if (pgd_present(*pgd)) /* Another has populated it */ +#ifndef __ARCH_HAS_5LEVEL_HACK + if (p4d_present(*p4d)) /* Another has populated it */ pud_free(mm, new); else - pgd_populate(mm, pgd, new); + p4d_populate(mm, p4d, new); +#else + if (pgd_present(*p4d)) /* Another has populated it */ + pud_free(mm, new); + else + pgd_populate(mm, p4d, new); +#endif /* __ARCH_HAS_5LEVEL_HACK */ spin_unlock(&mm->page_table_lock); return 0; } @@ -3839,6 +3996,7 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *ptep; @@ -3847,7 +4005,11 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) goto out; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d))) + goto out; + + pud = pud_offset(p4d, address); if (pud_none(*pud) || unlikely(pud_bad(*pud))) goto out; @@ -4136,7 +4298,7 @@ void __might_fault(const char *file, int line) * get paged out, therefore we'll never actually fault, and the * below annotations will generate false positives. */ - if (segment_eq(get_fs(), KERNEL_DS)) + if (uaccess_kernel()) return; if (pagefault_disabled()) return; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 295479b792ec..6fa7208bcd56 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -125,9 +125,12 @@ void put_online_mems(void) } +/* Serializes write accesses to mem_hotplug.active_writer. */ +static DEFINE_MUTEX(memory_add_remove_lock); + void mem_hotplug_begin(void) { - assert_held_device_hotplug(); + mutex_lock(&memory_add_remove_lock); mem_hotplug.active_writer = current; @@ -147,6 +150,7 @@ void mem_hotplug_done(void) mem_hotplug.active_writer = NULL; mutex_unlock(&mem_hotplug.lock); memhp_lock_release(); + mutex_unlock(&memory_add_remove_lock); } /* add this memory to iomem resource */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 75b2745bac41..37d0b334bfe9 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1529,7 +1529,6 @@ COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode) { - long err = 0; unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; DECLARE_BITMAP(bm, MAX_NUMNODES); @@ -1538,14 +1537,13 @@ COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) { - err = compat_get_bitmap(bm, nmask, nr_bits); + if (compat_get_bitmap(bm, nmask, nr_bits)) + return -EFAULT; nm = compat_alloc_user_space(alloc_size); - err |= copy_to_user(nm, bm, alloc_size); + if (copy_to_user(nm, bm, alloc_size)) + return -EFAULT; } - if (err) - return -EFAULT; - return sys_set_mempolicy(mode, nm, nr_bits+1); } @@ -1553,7 +1551,6 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, compat_ulong_t, mode, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode, compat_ulong_t, flags) { - long err = 0; unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; nodemask_t bm; @@ -1562,14 +1559,13 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) { - err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits); + if (compat_get_bitmap(nodes_addr(bm), nmask, nr_bits)) + return -EFAULT; nm = compat_alloc_user_space(alloc_size); - err |= copy_to_user(nm, nodes_addr(bm), alloc_size); + if (copy_to_user(nm, nodes_addr(bm), alloc_size)) + return -EFAULT; } - if (err) - return -EFAULT; - return sys_mbind(start, len, mode, nm, nr_bits+1, flags); } diff --git a/mm/migrate.c b/mm/migrate.c index 9a0897a14d37..738f1d5f8350 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -184,9 +184,9 @@ void putback_movable_pages(struct list_head *l) unlock_page(page); put_page(page); } else { - putback_lru_page(page); dec_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); + putback_lru_page(page); } } } @@ -209,8 +209,11 @@ static int remove_migration_pte(struct page *page, struct vm_area_struct *vma, VM_BUG_ON_PAGE(PageTail(page), page); while (page_vma_mapped_walk(&pvmw)) { - new = page - pvmw.page->index + - linear_page_index(vma, pvmw.address); + if (PageKsm(page)) + new = page; + else + new = page - pvmw.page->index + + linear_page_index(vma, pvmw.address); get_page(new); pte = pte_mkold(mk_pte(new, READ_ONCE(vma->vm_page_prot))); diff --git a/mm/mlock.c b/mm/mlock.c index 1050511f8b2b..0dd9ca18e19e 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -380,6 +380,7 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec, pte = get_locked_pte(vma->vm_mm, start, &ptl); /* Make sure we do not cross the page table boundary */ end = pgd_addr_end(start, end); + end = p4d_addr_end(start, end); end = pud_addr_end(start, end); end = pmd_addr_end(start, end); @@ -442,7 +443,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, while (start < end) { struct page *page; - unsigned int page_mask; + unsigned int page_mask = 0; unsigned long page_increm; struct pagevec pvec; struct zone *zone; @@ -456,8 +457,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, * suits munlock very well (and if somehow an abnormal page * has sneaked into the range, we won't oops here: great). */ - page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP, - &page_mask); + page = follow_page(vma, start, FOLL_GET | FOLL_DUMP); if (page && !IS_ERR(page)) { if (PageTransTail(page)) { @@ -468,8 +468,8 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, /* * Any THP page found by follow_page_mask() may * have gotten split before reaching - * munlock_vma_page(), so we need to recompute - * the page_mask here. + * munlock_vma_page(), so we need to compute + * the page_mask here instead. */ page_mask = munlock_vma_page(page); unlock_page(page); diff --git a/mm/mprotect.c b/mm/mprotect.c index 848e946b08e5..8edd0d576254 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -193,14 +193,14 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, } static inline unsigned long change_pud_range(struct vm_area_struct *vma, - pgd_t *pgd, unsigned long addr, unsigned long end, + p4d_t *p4d, unsigned long addr, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa) { pud_t *pud; unsigned long next; unsigned long pages = 0; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) @@ -212,6 +212,26 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma, return pages; } +static inline unsigned long change_p4d_range(struct vm_area_struct *vma, + pgd_t *pgd, unsigned long addr, unsigned long end, + pgprot_t newprot, int dirty_accountable, int prot_numa) +{ + p4d_t *p4d; + unsigned long next; + unsigned long pages = 0; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + pages += change_pud_range(vma, p4d, addr, next, newprot, + dirty_accountable, prot_numa); + } while (p4d++, addr = next, addr != end); + + return pages; +} + static unsigned long change_protection_range(struct vm_area_struct *vma, unsigned long addr, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa) @@ -230,7 +250,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - pages += change_pud_range(vma, pgd, addr, next, newprot, + pages += change_p4d_range(vma, pgd, addr, next, newprot, dirty_accountable, prot_numa); } while (pgd++, addr = next, addr != end); diff --git a/mm/mremap.c b/mm/mremap.c index 8233b0105c82..cd8a1b199ef9 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -32,6 +32,7 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -39,7 +40,11 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr) if (pgd_none_or_clear_bad(pgd)) return NULL; - pud = pud_offset(pgd, addr); + p4d = p4d_offset(pgd, addr); + if (p4d_none_or_clear_bad(p4d)) + return NULL; + + pud = pud_offset(p4d, addr); if (pud_none_or_clear_bad(pud)) return NULL; @@ -54,11 +59,15 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, addr); if (!pud) return NULL; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c1b68edaf106..bd01501efab9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -873,7 +873,8 @@ done_merging: higher_page = page + (combined_pfn - pfn); buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1); higher_buddy = higher_page + (buddy_pfn - combined_pfn); - if (page_is_buddy(higher_page, higher_buddy, order + 1)) { + if (pfn_valid_within(buddy_pfn) && + page_is_buddy(higher_page, higher_buddy, order + 1)) { list_add_tail(&page->lru, &zone->free_area[order].free_list[migratetype]); goto out; @@ -1089,10 +1090,10 @@ static void free_pcppages_bulk(struct zone *zone, int count, { int migratetype = 0; int batch_free = 0; - unsigned long nr_scanned, flags; + unsigned long nr_scanned; bool isolated_pageblocks; - spin_lock_irqsave(&zone->lock, flags); + spin_lock(&zone->lock); isolated_pageblocks = has_isolate_pageblock(zone); nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED); if (nr_scanned) @@ -1141,7 +1142,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, trace_mm_page_pcpu_drain(page, 0, mt); } while (--count && --batch_free && !list_empty(list)); } - spin_unlock_irqrestore(&zone->lock, flags); + spin_unlock(&zone->lock); } static void free_one_page(struct zone *zone, @@ -1149,9 +1150,8 @@ static void free_one_page(struct zone *zone, unsigned int order, int migratetype) { - unsigned long nr_scanned, flags; - spin_lock_irqsave(&zone->lock, flags); - __count_vm_events(PGFREE, 1 << order); + unsigned long nr_scanned; + spin_lock(&zone->lock); nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED); if (nr_scanned) __mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned); @@ -1161,7 +1161,7 @@ static void free_one_page(struct zone *zone, migratetype = get_pfnblock_migratetype(page, pfn); } __free_one_page(page, pfn, zone, order, migratetype); - spin_unlock_irqrestore(&zone->lock, flags); + spin_unlock(&zone->lock); } static void __meminit __init_single_page(struct page *page, unsigned long pfn, @@ -1239,6 +1239,7 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end) static void __free_pages_ok(struct page *page, unsigned int order) { + unsigned long flags; int migratetype; unsigned long pfn = page_to_pfn(page); @@ -1246,7 +1247,10 @@ static void __free_pages_ok(struct page *page, unsigned int order) return; migratetype = get_pfnblock_migratetype(page, pfn); + local_irq_save(flags); + __count_vm_events(PGFREE, 1 << order); free_one_page(page_zone(page), page, pfn, order, migratetype); + local_irq_restore(flags); } static void __init __free_pages_boot_core(struct page *page, unsigned int order) @@ -2218,9 +2222,8 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, int migratetype, bool cold) { int i, alloced = 0; - unsigned long flags; - spin_lock_irqsave(&zone->lock, flags); + spin_lock(&zone->lock); for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype); if (unlikely(page == NULL)) @@ -2256,7 +2259,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * pages added to the pcp list. */ __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); - spin_unlock_irqrestore(&zone->lock, flags); + spin_unlock(&zone->lock); return alloced; } @@ -2372,6 +2375,13 @@ void drain_all_pages(struct zone *zone) */ static cpumask_t cpus_with_pcps; + /* + * Make sure nobody triggers this path before mm_percpu_wq is fully + * initialized. + */ + if (WARN_ON_ONCE(!mm_percpu_wq)) + return; + /* Workqueues cannot recurse */ if (current->flags & PF_WQ_WORKER) return; @@ -2421,7 +2431,7 @@ void drain_all_pages(struct zone *zone) for_each_cpu(cpu, &cpus_with_pcps) { struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu); INIT_WORK(work, drain_local_pages_wq); - schedule_work_on(cpu, work); + queue_work_on(cpu, mm_percpu_wq, work); } for_each_cpu(cpu, &cpus_with_pcps) flush_work(per_cpu_ptr(&pcpu_drain, cpu)); @@ -2477,20 +2487,17 @@ void free_hot_cold_page(struct page *page, bool cold) { struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; + unsigned long flags; unsigned long pfn = page_to_pfn(page); int migratetype; - if (in_interrupt()) { - __free_pages_ok(page, 0); - return; - } - if (!free_pcp_prepare(page)) return; migratetype = get_pfnblock_migratetype(page, pfn); set_pcppage_migratetype(page, migratetype); - preempt_disable(); + local_irq_save(flags); + __count_vm_event(PGFREE); /* * We only track unmovable, reclaimable and movable on pcp lists. @@ -2507,7 +2514,6 @@ void free_hot_cold_page(struct page *page, bool cold) migratetype = MIGRATE_MOVABLE; } - __count_vm_event(PGFREE); pcp = &this_cpu_ptr(zone->pageset)->pcp; if (!cold) list_add(&page->lru, &pcp->lists[migratetype]); @@ -2521,7 +2527,7 @@ void free_hot_cold_page(struct page *page, bool cold) } out: - preempt_enable(); + local_irq_restore(flags); } /* @@ -2646,8 +2652,6 @@ static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype, { struct page *page; - VM_BUG_ON(in_interrupt()); - do { if (list_empty(list)) { pcp->count += rmqueue_bulk(zone, 0, @@ -2678,8 +2682,9 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, struct list_head *list; bool cold = ((gfp_flags & __GFP_COLD) != 0); struct page *page; + unsigned long flags; - preempt_disable(); + local_irq_save(flags); pcp = &this_cpu_ptr(zone->pageset)->pcp; list = &pcp->lists[migratetype]; page = __rmqueue_pcplist(zone, migratetype, cold, pcp, list); @@ -2687,7 +2692,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); zone_statistics(preferred_zone, zone); } - preempt_enable(); + local_irq_restore(flags); return page; } @@ -2703,7 +2708,7 @@ struct page *rmqueue(struct zone *preferred_zone, unsigned long flags; struct page *page; - if (likely(order == 0) && !in_interrupt()) { + if (likely(order == 0)) { page = rmqueue_pcplist(preferred_zone, zone, order, gfp_flags, migratetype); goto out; @@ -4519,13 +4524,13 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) K(node_page_state(pgdat, NR_FILE_MAPPED)), K(node_page_state(pgdat, NR_FILE_DIRTY)), K(node_page_state(pgdat, NR_WRITEBACK)), + K(node_page_state(pgdat, NR_SHMEM)), #ifdef CONFIG_TRANSPARENT_HUGEPAGE K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR), K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR), K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR), #endif - K(node_page_state(pgdat, NR_SHMEM)), K(node_page_state(pgdat, NR_WRITEBACK_TEMP)), K(node_page_state(pgdat, NR_UNSTABLE_NFS)), node_page_state(pgdat, NR_PAGES_SCANNED), diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index a23001a22c15..de9c40d7304a 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -104,18 +104,15 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) struct mm_struct *mm = pvmw->vma->vm_mm; struct page *page = pvmw->page; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; /* The only possible pmd mapping has been handled on last iteration */ if (pvmw->pmd && !pvmw->pte) return not_found(pvmw); - /* Only for THP, seek to next pte entry makes sense */ - if (pvmw->pte) { - if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page)) - return not_found(pvmw); + if (pvmw->pte) goto next_pte; - } if (unlikely(PageHuge(pvmw->page))) { /* when pud is not present, pte will be NULL */ @@ -133,7 +130,10 @@ restart: pgd = pgd_offset(mm, pvmw->address); if (!pgd_present(*pgd)) return false; - pud = pud_offset(pgd, pvmw->address); + p4d = p4d_offset(pgd, pvmw->address); + if (!p4d_present(*p4d)) + return false; + pud = pud_offset(p4d, pvmw->address); if (!pud_present(*pud)) return false; pvmw->pmd = pmd_offset(pud, pvmw->address); @@ -161,9 +161,14 @@ restart: while (1) { if (check_pte(pvmw)) return true; -next_pte: do { +next_pte: + /* Seek to next pte only makes sense for THP */ + if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page)) + return not_found(pvmw); + do { pvmw->address += PAGE_SIZE; - if (pvmw->address >= + if (pvmw->address >= pvmw->vma->vm_end || + pvmw->address >= __vma_address(pvmw->page, pvmw->vma) + hpage_nr_pages(pvmw->page) * PAGE_SIZE) return not_found(pvmw); diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 03761577ae86..60f7856e508f 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -69,14 +69,14 @@ again: return err; } -static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, +static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, struct mm_walk *walk) { pud_t *pud; unsigned long next; int err = 0; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { again: next = pud_addr_end(addr, end); @@ -113,6 +113,32 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, return err; } +static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + p4d_t *p4d; + unsigned long next; + int err = 0; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) { + if (walk->pte_hole) + err = walk->pte_hole(addr, next, walk); + if (err) + break; + continue; + } + if (walk->pmd_entry || walk->pte_entry) + err = walk_pud_range(p4d, addr, next, walk); + if (err) + break; + } while (p4d++, addr = next, addr != end); + + return err; +} + static int walk_pgd_range(unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -131,7 +157,7 @@ static int walk_pgd_range(unsigned long addr, unsigned long end, continue; } if (walk->pmd_entry || walk->pte_entry) - err = walk_pud_range(pgd, addr, next, walk); + err = walk_p4d_range(pgd, addr, next, walk); if (err) break; } while (pgd++, addr = next, addr != end); diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index 538998a137d2..9ac639499bd1 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -21,7 +21,6 @@ static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, /** * pcpu_get_pages - get temp pages array - * @chunk: chunk of interest * * Returns pointer to array of pointers to struct page which can be indexed * with pcpu_page_idx(). Note that there is only one array and accesses @@ -30,7 +29,7 @@ static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, * RETURNS: * Pointer to temp pages array on success. */ -static struct page **pcpu_get_pages(struct pcpu_chunk *chunk_alloc) +static struct page **pcpu_get_pages(void) { static struct page **pages; size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]); @@ -275,7 +274,7 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, { struct page **pages; - pages = pcpu_get_pages(chunk); + pages = pcpu_get_pages(); if (!pages) return -ENOMEM; @@ -313,7 +312,7 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, * successful population attempt so the temp pages array must * be available now. */ - pages = pcpu_get_pages(chunk); + pages = pcpu_get_pages(); BUG_ON(!pages); /* unmap and free */ diff --git a/mm/percpu.c b/mm/percpu.c index 5696039b5c07..e0aa8ae7bde7 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1011,8 +1011,11 @@ area_found: mutex_unlock(&pcpu_alloc_mutex); } - if (chunk != pcpu_reserved_chunk) + if (chunk != pcpu_reserved_chunk) { + spin_lock_irqsave(&pcpu_lock, flags); pcpu_nr_empty_pop_pages -= occ_pages; + spin_unlock_irqrestore(&pcpu_lock, flags); + } if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW) pcpu_schedule_balance_work(); @@ -1281,18 +1284,7 @@ void free_percpu(void __percpu *ptr) } EXPORT_SYMBOL_GPL(free_percpu); -/** - * is_kernel_percpu_address - test whether address is from static percpu area - * @addr: address to test - * - * Test whether @addr belongs to in-kernel static percpu area. Module - * static percpu areas are not considered. For those, use - * is_module_percpu_address(). - * - * RETURNS: - * %true if @addr is from in-kernel static percpu area, %false otherwise. - */ -bool is_kernel_percpu_address(unsigned long addr) +bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr) { #ifdef CONFIG_SMP const size_t static_size = __per_cpu_end - __per_cpu_start; @@ -1301,16 +1293,39 @@ bool is_kernel_percpu_address(unsigned long addr) for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(base, cpu); + void *va = (void *)addr; - if ((void *)addr >= start && (void *)addr < start + static_size) + if (va >= start && va < start + static_size) { + if (can_addr) { + *can_addr = (unsigned long) (va - start); + *can_addr += (unsigned long) + per_cpu_ptr(base, get_boot_cpu_id()); + } return true; - } + } + } #endif /* on UP, can't distinguish from other static vars, always false */ return false; } /** + * is_kernel_percpu_address - test whether address is from static percpu area + * @addr: address to test + * + * Test whether @addr belongs to in-kernel static percpu area. Module + * static percpu areas are not considered. For those, use + * is_module_percpu_address(). + * + * RETURNS: + * %true if @addr is from in-kernel static percpu area, %false otherwise. + */ +bool is_kernel_percpu_address(unsigned long addr) +{ + return __is_kernel_percpu_address(addr, NULL); +} + +/** * per_cpu_ptr_to_phys - convert translated percpu address to physical address * @addr: the address to be converted to physical address * diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 4ed5908c65b0..c99d9512a45b 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -22,6 +22,12 @@ void pgd_clear_bad(pgd_t *pgd) pgd_clear(pgd); } +void p4d_clear_bad(p4d_t *p4d) +{ + p4d_ERROR(*p4d); + p4d_clear(p4d); +} + void pud_clear_bad(pud_t *pud) { pud_ERROR(*pud); diff --git a/mm/rmap.c b/mm/rmap.c index 2da487d6cea8..f6838015810f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -684,6 +684,7 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd = NULL; pmd_t pmde; @@ -692,7 +693,11 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) if (!pgd_present(*pgd)) goto out; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + goto out; + + pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; @@ -1154,7 +1159,7 @@ void page_add_file_rmap(struct page *page, bool compound) goto out; } __mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, nr); - mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); + mem_cgroup_update_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED, nr); out: unlock_page_memcg(page); } @@ -1194,7 +1199,7 @@ static void page_remove_file_rmap(struct page *page, bool compound) * pte lock(a spinlock) is held, which implies preemption disabled. */ __mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, -nr); - mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); + mem_cgroup_update_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED, -nr); if (unlikely(PageMlocked(page))) clear_page_mlock(page); @@ -1316,12 +1321,6 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } while (page_vma_mapped_walk(&pvmw)) { - subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); - address = pvmw.address; - - /* Unexpected PMD-mapped THP? */ - VM_BUG_ON_PAGE(!pvmw.pte, page); - /* * If the page is mlock()d, we cannot swap it out. * If it's recently referenced (perhaps page_referenced @@ -1345,6 +1344,13 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, continue; } + /* Unexpected PMD-mapped THP? */ + VM_BUG_ON_PAGE(!pvmw.pte, page); + + subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); + address = pvmw.address; + + if (!(flags & TTU_IGNORE_ACCESS)) { if (ptep_clear_flush_young_notify(vma, address, pvmw.pte)) { diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 574c67b663fe..a56c3989f773 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -196,9 +196,9 @@ pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node) return pmd; } -pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node) +pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node) { - pud_t *pud = pud_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); if (pud_none(*pud)) { void *p = vmemmap_alloc_block(PAGE_SIZE, node); if (!p) @@ -208,6 +208,18 @@ pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node) return pud; } +p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) +{ + p4d_t *p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) { + void *p = vmemmap_alloc_block(PAGE_SIZE, node); + if (!p) + return NULL; + p4d_populate(&init_mm, p4d, p); + } + return p4d; +} + pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node) { pgd_t *pgd = pgd_offset_k(addr); @@ -225,6 +237,7 @@ int __meminit vmemmap_populate_basepages(unsigned long start, { unsigned long addr = start; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -233,7 +246,10 @@ int __meminit vmemmap_populate_basepages(unsigned long start, pgd = vmemmap_pgd_populate(addr, node); if (!pgd) return -ENOMEM; - pud = vmemmap_pud_populate(pgd, addr, node); + p4d = vmemmap_p4d_populate(pgd, addr, node); + if (!p4d) + return -ENOMEM; + pud = vmemmap_pud_populate(p4d, addr, node); if (!pud) return -ENOMEM; pmd = vmemmap_pmd_populate(pud, addr, node); diff --git a/mm/swap.c b/mm/swap.c index c4910f14f957..d8d9ee9e311a 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -97,6 +97,16 @@ static void __put_compound_page(struct page *page) void __put_page(struct page *page) { + if (is_zone_device_page(page)) { + put_dev_pagemap(page->pgmap); + + /* + * The page belongs to the device that created pgmap. Do + * not return it to page allocator. + */ + return; + } + if (unlikely(PageCompound(page))) __put_compound_page(page); else @@ -670,30 +680,19 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy) static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); -/* - * lru_add_drain_wq is used to do lru_add_drain_all() from a WQ_MEM_RECLAIM - * workqueue, aiding in getting memory freed. - */ -static struct workqueue_struct *lru_add_drain_wq; - -static int __init lru_init(void) -{ - lru_add_drain_wq = alloc_workqueue("lru-add-drain", WQ_MEM_RECLAIM, 0); - - if (WARN(!lru_add_drain_wq, - "Failed to create workqueue lru_add_drain_wq")) - return -ENOMEM; - - return 0; -} -early_initcall(lru_init); - void lru_add_drain_all(void) { static DEFINE_MUTEX(lock); static struct cpumask has_work; int cpu; + /* + * Make sure nobody triggers this path before mm_percpu_wq is fully + * initialized. + */ + if (WARN_ON(!mm_percpu_wq)) + return; + mutex_lock(&lock); get_online_cpus(); cpumask_clear(&has_work); @@ -707,7 +706,7 @@ void lru_add_drain_all(void) pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) || need_activate_page_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); - queue_work_on(cpu, lru_add_drain_wq, work); + queue_work_on(cpu, mm_percpu_wq, work); cpumask_set_cpu(cpu, &has_work); } } diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c index 310ac0b8f974..ac6318a064d3 100644 --- a/mm/swap_cgroup.c +++ b/mm/swap_cgroup.c @@ -201,6 +201,8 @@ void swap_cgroup_swapoff(int type) struct page *page = map[i]; if (page) __free_page(page); + if (!(i % SWAP_CLUSTER_MAX)) + cond_resched(); } vfree(map); } diff --git a/mm/swap_slots.c b/mm/swap_slots.c index 9b5bc86f96ad..b1ccb58ad397 100644 --- a/mm/swap_slots.c +++ b/mm/swap_slots.c @@ -267,8 +267,6 @@ int free_swap_slot(swp_entry_t entry) { struct swap_slots_cache *cache; - BUG_ON(!swap_slot_cache_initialized); - cache = &get_cpu_var(swp_slots); if (use_swap_slot_cache && cache->slots_ret) { spin_lock_irq(&cache->free_lock); diff --git a/mm/swapfile.c b/mm/swapfile.c index 521ef9b6064f..178130880b90 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1517,7 +1517,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, return 0; } -static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd, +static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, swp_entry_t entry, struct page *page) { @@ -1525,7 +1525,7 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long next; int ret; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) @@ -1537,6 +1537,26 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd, return 0; } +static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, + unsigned long addr, unsigned long end, + swp_entry_t entry, struct page *page) +{ + p4d_t *p4d; + unsigned long next; + int ret; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + ret = unuse_pud_range(vma, p4d, addr, next, entry, page); + if (ret) + return ret; + } while (p4d++, addr = next, addr != end); + return 0; +} + static int unuse_vma(struct vm_area_struct *vma, swp_entry_t entry, struct page *page) { @@ -1560,7 +1580,7 @@ static int unuse_vma(struct vm_area_struct *vma, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - ret = unuse_pud_range(vma, pgd, addr, next, entry, page); + ret = unuse_p4d_range(vma, pgd, addr, next, entry, page); if (ret) return ret; } while (pgd++, addr = next, addr != end); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 479e631d43c2..8bcb501bce60 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -128,19 +128,22 @@ out_unlock: static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; - pmd_t *pmd = NULL; pgd = pgd_offset(mm, address); - pud = pud_alloc(mm, pgd, address); - if (pud) - /* - * Note that we didn't run this because the pmd was - * missing, the *pmd may be already established and in - * turn it may also be a trans_huge_pmd. - */ - pmd = pmd_alloc(mm, pud, address); - return pmd; + p4d = p4d_alloc(mm, pgd, address); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, address); + if (!pud) + return NULL; + /* + * Note that we didn't run this because the pmd was + * missing, the *pmd may be already established and in + * turn it may also be a trans_huge_pmd. + */ + return pmd_alloc(mm, pud, address); } #ifdef CONFIG_HUGETLB_PAGE diff --git a/mm/vmalloc.c b/mm/vmalloc.c index c24db06f15c4..b52aeed3f58e 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -86,12 +86,12 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end) } while (pmd++, addr = next, addr != end); } -static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end) +static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end) { pud_t *pud; unsigned long next; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_clear_huge(pud)) @@ -102,6 +102,22 @@ static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end) } while (pud++, addr = next, addr != end); } +static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_clear_huge(p4d)) + continue; + if (p4d_none_or_clear_bad(p4d)) + continue; + vunmap_pud_range(p4d, addr, next); + } while (p4d++, addr = next, addr != end); +} + static void vunmap_page_range(unsigned long addr, unsigned long end) { pgd_t *pgd; @@ -113,7 +129,7 @@ static void vunmap_page_range(unsigned long addr, unsigned long end) next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - vunmap_pud_range(pgd, addr, next); + vunmap_p4d_range(pgd, addr, next); } while (pgd++, addr = next, addr != end); } @@ -160,13 +176,13 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, return 0; } -static int vmap_pud_range(pgd_t *pgd, unsigned long addr, +static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr) { pud_t *pud; unsigned long next; - pud = pud_alloc(&init_mm, pgd, addr); + pud = pud_alloc(&init_mm, p4d, addr); if (!pud) return -ENOMEM; do { @@ -177,6 +193,23 @@ static int vmap_pud_range(pgd_t *pgd, unsigned long addr, return 0; } +static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, + unsigned long end, pgprot_t prot, struct page **pages, int *nr) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_alloc(&init_mm, pgd, addr); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + if (vmap_pud_range(p4d, addr, next, prot, pages, nr)) + return -ENOMEM; + } while (p4d++, addr = next, addr != end); + return 0; +} + /* * Set up page tables in kva (addr, end). The ptes shall have prot "prot", and * will have pfns corresponding to the "pages" array. @@ -196,7 +229,7 @@ static int vmap_page_range_noflush(unsigned long start, unsigned long end, pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); - err = vmap_pud_range(pgd, addr, next, prot, pages, &nr); + err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr); if (err) return err; } while (pgd++, addr = next, addr != end); @@ -237,6 +270,10 @@ struct page *vmalloc_to_page(const void *vmalloc_addr) unsigned long addr = (unsigned long) vmalloc_addr; struct page *page = NULL; pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *ptep, pte; /* * XXX we might need to change this if we add VIRTUAL_BUG_ON for @@ -244,21 +281,23 @@ struct page *vmalloc_to_page(const void *vmalloc_addr) */ VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr)); - if (!pgd_none(*pgd)) { - pud_t *pud = pud_offset(pgd, addr); - if (!pud_none(*pud)) { - pmd_t *pmd = pmd_offset(pud, addr); - if (!pmd_none(*pmd)) { - pte_t *ptep, pte; - - ptep = pte_offset_map(pmd, addr); - pte = *ptep; - if (pte_present(pte)) - page = pte_page(pte); - pte_unmap(ptep); - } - } - } + if (pgd_none(*pgd)) + return NULL; + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) + return NULL; + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) + return NULL; + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return NULL; + + ptep = pte_offset_map(pmd, addr); + pte = *ptep; + if (pte_present(pte)) + page = pte_page(pte); + pte_unmap(ptep); return page; } EXPORT_SYMBOL(vmalloc_to_page); @@ -1644,7 +1683,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, if (fatal_signal_pending(current)) { area->nr_pages = i; - goto fail; + goto fail_no_warn; } if (node == NUMA_NO_NODE) @@ -1670,6 +1709,7 @@ fail: warn_alloc(gfp_mask, NULL, "vmalloc: allocation failure, allocated %ld of %ld bytes", (area->nr_pages*PAGE_SIZE), area->size); +fail_no_warn: vfree(area->addr); return NULL; } diff --git a/mm/vmstat.c b/mm/vmstat.c index 69f9aff39a2e..5a4f5c5a31e8 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1065,6 +1065,9 @@ const char * const vmstat_text[] = { "thp_split_page_failed", "thp_deferred_split_page", "thp_split_pmd", +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD + "thp_split_pud", +#endif "thp_zero_page_alloc", "thp_zero_page_alloc_failed", #endif @@ -1549,7 +1552,6 @@ static const struct file_operations proc_vmstat_file_operations = { #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SMP -static struct workqueue_struct *vmstat_wq; static DEFINE_PER_CPU(struct delayed_work, vmstat_work); int sysctl_stat_interval __read_mostly = HZ; @@ -1620,7 +1622,7 @@ static void vmstat_update(struct work_struct *w) * to occur in the future. Keep on running the * update worker thread. */ - queue_delayed_work_on(smp_processor_id(), vmstat_wq, + queue_delayed_work_on(smp_processor_id(), mm_percpu_wq, this_cpu_ptr(&vmstat_work), round_jiffies_relative(sysctl_stat_interval)); } @@ -1699,7 +1701,7 @@ static void vmstat_shepherd(struct work_struct *w) struct delayed_work *dw = &per_cpu(vmstat_work, cpu); if (!delayed_work_pending(dw) && need_update(cpu)) - queue_delayed_work_on(cpu, vmstat_wq, dw, 0); + queue_delayed_work_on(cpu, mm_percpu_wq, dw, 0); } put_online_cpus(); @@ -1715,7 +1717,6 @@ static void __init start_shepherd_timer(void) INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu), vmstat_update); - vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); schedule_delayed_work(&shepherd, round_jiffies_relative(sysctl_stat_interval)); } @@ -1761,11 +1762,15 @@ static int vmstat_cpu_dead(unsigned int cpu) #endif -static int __init setup_vmstat(void) +struct workqueue_struct *mm_percpu_wq; + +void __init init_mm_internals(void) { -#ifdef CONFIG_SMP - int ret; + int ret __maybe_unused; + mm_percpu_wq = alloc_workqueue("mm_percpu_wq", WQ_MEM_RECLAIM, 0); + +#ifdef CONFIG_SMP ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead", NULL, vmstat_cpu_dead); if (ret < 0) @@ -1789,9 +1794,7 @@ static int __init setup_vmstat(void) proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations); proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations); #endif - return 0; } -module_init(setup_vmstat) #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION) diff --git a/mm/workingset.c b/mm/workingset.c index ac839fca0e76..eda05c71fa49 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -532,7 +532,7 @@ static int __init workingset_init(void) pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", timestamp_bits, max_order, bucket_order); - ret = list_lru_init_key(&shadow_nodes, &shadow_nodes_key); + ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key); if (ret) goto err; ret = register_shrinker(&workingset_shadow_shrinker); diff --git a/mm/z3fold.c b/mm/z3fold.c index 8970a2fd3b1a..54f63c4a809a 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -185,6 +185,12 @@ static inline void z3fold_page_lock(struct z3fold_header *zhdr) spin_lock(&zhdr->page_lock); } +/* Try to lock a z3fold page */ +static inline int z3fold_page_trylock(struct z3fold_header *zhdr) +{ + return spin_trylock(&zhdr->page_lock); +} + /* Unlock a z3fold page */ static inline void z3fold_page_unlock(struct z3fold_header *zhdr) { @@ -385,7 +391,7 @@ static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp, spin_lock(&pool->lock); zhdr = list_first_entry_or_null(&pool->unbuddied[i], struct z3fold_header, buddy); - if (!zhdr) { + if (!zhdr || !z3fold_page_trylock(zhdr)) { spin_unlock(&pool->lock); continue; } @@ -394,7 +400,6 @@ static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp, spin_unlock(&pool->lock); page = virt_to_page(zhdr); - z3fold_page_lock(zhdr); if (zhdr->first_chunks == 0) { if (zhdr->middle_chunks != 0 && chunks >= zhdr->start_middle) @@ -667,6 +672,7 @@ next: z3fold_page_unlock(zhdr); spin_lock(&pool->lock); if (kref_put(&zhdr->refcount, release_z3fold_page)) { + spin_unlock(&pool->lock); atomic64_dec(&pool->pages_nr); return 0; } diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index b7ee9c34dbd6..d41edd28298b 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -276,7 +276,7 @@ struct zs_pool { struct zspage { struct { unsigned int fullness:FULLNESS_BITS; - unsigned int class:CLASS_BITS; + unsigned int class:CLASS_BITS + 1; unsigned int isolated:ISOLATED_BITS; unsigned int magic:MAGIC_VAL_BITS; }; |