diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c9bf68c239a0..45bf05ad5c53 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -944,10 +944,37 @@ static inline bool htlb_allow_alloc_fallback(int reason) static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { - if (huge_page_size(h) == PMD_SIZE) + const unsigned long size = huge_page_size(h); + + VM_WARN_ON(size == PAGE_SIZE); + + /* + * hugetlb must use the exact same PT locks as core-mm page table + * walkers would. When modifying a PTE table, hugetlb must take the + * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD + * PT lock etc. + * + * The expectation is that any hugetlb folio smaller than a PMD is + * always mapped into a single PTE table and that any hugetlb folio + * smaller than a PUD (but at least as big as a PMD) is always mapped + * into a single PMD table. + * + * If that does not hold for an architecture, then that architecture + * must disable split PT locks such that all *_lockptr() functions + * will give us the same result: the per-MM PT lock. + * + * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where + * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr() + * and core-mm would use pmd_lockptr(). However, in such configurations + * split PMD locks are disabled -- they don't make sense on a single + * PGDIR page table -- and the end result is the same. + */ + if (size >= PUD_SIZE) + return pud_lockptr(mm, (pud_t *) pte); + else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE)) return pmd_lockptr(mm, (pmd_t *) pte); - VM_BUG_ON(huge_page_size(h) == PAGE_SIZE); - return &mm->page_table_lock; + /* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */ + return ptep_lockptr(mm, pte); } #ifndef hugepages_supported diff --git a/include/linux/mm.h b/include/linux/mm.h index c4b238a20b76..6549d0979b28 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2920,6 +2920,13 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) return ptlock_ptr(page_ptdesc(pmd_page(*pmd))); } +static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) +{ + BUILD_BUG_ON(IS_ENABLED(CONFIG_HIGHPTE)); + BUILD_BUG_ON(MAX_PTRS_PER_PTE * sizeof(pte_t) > PAGE_SIZE); + return ptlock_ptr(virt_to_ptdesc(pte)); +} + static inline bool ptlock_init(struct ptdesc *ptdesc) { /* @@ -2944,6 +2951,10 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } +static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) +{ + return &mm->page_table_lock; +} static inline void ptlock_cache_init(void) {} static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 41458892bc8a..1dc6248feb83 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -220,8 +220,6 @@ enum node_stat_item { PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, - NR_MEMMAP, /* page metadata allocated through buddy allocator */ - NR_MEMMAP_BOOT, /* page metadata allocated through boot allocator */ NR_VM_NODE_STAT_ITEMS }; diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h index 18cd0c0c73d9..207f0c83c8e9 100644 --- a/include/linux/pgalloc_tag.h +++ b/include/linux/pgalloc_tag.h @@ -43,6 +43,18 @@ static inline void put_page_tag_ref(union codetag_ref *ref) page_ext_put(page_ext_from_codetag_ref(ref)); } +static inline void clear_page_tag_ref(struct page *page) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + set_codetag_empty(ref); + put_page_tag_ref(ref); + } + } +} + static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) { @@ -126,6 +138,7 @@ static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) static inline union codetag_ref *get_page_tag_ref(struct page *page) { return NULL; } static inline void put_page_tag_ref(union codetag_ref *ref) {} +static inline void clear_page_tag_ref(struct page *page) {} static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) {} static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 23cd17942036..9eb77c9007e6 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -34,10 +34,13 @@ struct reclaim_stat { unsigned nr_lazyfree_fail; }; -enum writeback_stat_item { +/* Stat data for system wide items */ +enum vm_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, - NR_VM_WRITEBACK_STAT_ITEMS, + NR_MEMMAP_PAGES, /* page metadata allocated through buddy allocator */ + NR_MEMMAP_BOOT_PAGES, /* page metadata allocated through boot allocator */ + NR_VM_STAT_ITEMS, }; #ifdef CONFIG_VM_EVENT_COUNTERS @@ -514,21 +517,13 @@ static inline const char *lru_list_name(enum lru_list lru) return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" } -static inline const char *writeback_stat_name(enum writeback_stat_item item) -{ - return vmstat_text[NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_EVENT_ITEMS + - NR_VM_NODE_STAT_ITEMS + - item]; -} - #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + - NR_VM_WRITEBACK_STAT_ITEMS + + NR_VM_STAT_ITEMS + item]; } #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ @@ -625,7 +620,6 @@ static inline void lruvec_stat_sub_folio(struct folio *folio, lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } -void __meminit mod_node_early_perpage_metadata(int nid, long delta); -void __meminit store_early_perpage_metadata(void); - +void memmap_boot_pages_add(long delta); +void memmap_pages_add(long delta); #endif /* _LINUX_VMSTAT_H */ diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c index d3b4cd12bdd1..64d44a52c011 100644 --- a/kernel/crash_reserve.c +++ b/kernel/crash_reserve.c @@ -423,7 +423,8 @@ retry: if (high && search_end == CRASH_ADDR_HIGH_MAX) { search_end = CRASH_ADDR_LOW_MAX; search_base = 0; - goto retry; + if (search_end != CRASH_ADDR_HIGH_MAX) + goto retry; } pr_warn("cannot allocate crashkernel (size:0x%llx)\n", crash_size); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f4be468e06a4..67c86a5d64a6 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1685,7 +1685,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { spin_unlock(vmf->ptl); - goto out; + return 0; } pmd = pmd_modify(oldpmd, vma->vm_page_prot); @@ -1728,22 +1728,16 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) if (!migrate_misplaced_folio(folio, vma, target_nid)) { flags |= TNF_MIGRATED; nid = target_nid; - } else { - flags |= TNF_MIGRATE_FAIL; - vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); - if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { - spin_unlock(vmf->ptl); - goto out; - } - goto out_map; + task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); + return 0; } -out: - if (nid != NUMA_NO_NODE) - task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); - - return 0; - + flags |= TNF_MIGRATE_FAIL; + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { + spin_unlock(vmf->ptl); + return 0; + } out_map: /* Restore the PMD */ pmd = pmd_modify(oldpmd, vma->vm_page_prot); @@ -1753,7 +1747,10 @@ out_map: set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd); update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); - goto out; + + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); + return 0; } /* diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 829112b0a914..0c3f56b3578e 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -185,11 +185,11 @@ static int vmemmap_remap_range(unsigned long start, unsigned long end, static inline void free_vmemmap_page(struct page *page) { if (PageReserved(page)) { + memmap_boot_pages_add(-1); free_bootmem_page(page); - mod_node_page_state(page_pgdat(page), NR_MEMMAP_BOOT, -1); } else { + memmap_pages_add(-1); __free_page(page); - mod_node_page_state(page_pgdat(page), NR_MEMMAP, -1); } } @@ -341,7 +341,7 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end, copy_page(page_to_virt(walk.reuse_page), (void *)walk.reuse_addr); list_add(&walk.reuse_page->lru, vmemmap_pages); - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, 1); + memmap_pages_add(1); } /* @@ -392,14 +392,11 @@ static int alloc_vmemmap_page_list(unsigned long start, unsigned long end, for (i = 0; i < nr_pages; i++) { page = alloc_pages_node(nid, gfp_mask, 0); - if (!page) { - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, i); + if (!page) goto out; - } list_add(&page->lru, list); } - - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, nr_pages); + memmap_pages_add(nr_pages); return 0; out: diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 581d3e5c9117..7066fc84f351 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2417,7 +2417,7 @@ struct memory_failure_entry { struct memory_failure_cpu { DECLARE_KFIFO(fifo, struct memory_failure_entry, MEMORY_FAILURE_FIFO_SIZE); - spinlock_t lock; + raw_spinlock_t lock; struct work_struct work; }; @@ -2443,20 +2443,22 @@ void memory_failure_queue(unsigned long pfn, int flags) { struct memory_failure_cpu *mf_cpu; unsigned long proc_flags; + bool buffer_overflow; struct memory_failure_entry entry = { .pfn = pfn, .flags = flags, }; mf_cpu = &get_cpu_var(memory_failure_cpu); - spin_lock_irqsave(&mf_cpu->lock, proc_flags); - if (kfifo_put(&mf_cpu->fifo, entry)) + raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags); + buffer_overflow = !kfifo_put(&mf_cpu->fifo, entry); + if (!buffer_overflow) schedule_work_on(smp_processor_id(), &mf_cpu->work); - else + raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + put_cpu_var(memory_failure_cpu); + if (buffer_overflow) pr_err("buffer overflow when queuing memory failure at %#lx\n", pfn); - spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); - put_cpu_var(memory_failure_cpu); } EXPORT_SYMBOL_GPL(memory_failure_queue); @@ -2469,9 +2471,9 @@ static void memory_failure_work_func(struct work_struct *work) mf_cpu = container_of(work, struct memory_failure_cpu, work); for (;;) { - spin_lock_irqsave(&mf_cpu->lock, proc_flags); + raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags); gotten = kfifo_get(&mf_cpu->fifo, &entry); - spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); if (!gotten) break; if (entry.flags & MF_SOFT_OFFLINE) @@ -2501,7 +2503,7 @@ static int __init memory_failure_init(void) for_each_possible_cpu(cpu) { mf_cpu = &per_cpu(memory_failure_cpu, cpu); - spin_lock_init(&mf_cpu->lock); + raw_spin_lock_init(&mf_cpu->lock); INIT_KFIFO(mf_cpu->fifo); INIT_WORK(&mf_cpu->work, memory_failure_work_func); } diff --git a/mm/memory.c b/mm/memory.c index 34f8402d2046..3c01d68065be 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5295,7 +5295,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) if (unlikely(!pte_same(old_pte, vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); - goto out; + return 0; } pte = pte_modify(old_pte, vma->vm_page_prot); @@ -5358,23 +5358,19 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) if (!migrate_misplaced_folio(folio, vma, target_nid)) { nid = target_nid; flags |= TNF_MIGRATED; - } else { - flags |= TNF_MIGRATE_FAIL; - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, - vmf->address, &vmf->ptl); - if (unlikely(!vmf->pte)) - goto out; - if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { - pte_unmap_unlock(vmf->pte, vmf->ptl); - goto out; - } - goto out_map; + task_numa_fault(last_cpupid, nid, nr_pages, flags); + return 0; } -out: - if (nid != NUMA_NO_NODE) - task_numa_fault(last_cpupid, nid, nr_pages, flags); - return 0; + flags |= TNF_MIGRATE_FAIL; + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (unlikely(!vmf->pte)) + return 0; + if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; + } out_map: /* * Make it present again, depending on how arch implements @@ -5387,7 +5383,10 @@ out_map: numa_rebuild_single_mapping(vmf, vma, vmf->address, vmf->pte, writable); pte_unmap_unlock(vmf->pte, vmf->ptl); - goto out; + + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, nr_pages, flags); + return 0; } static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) diff --git a/mm/migrate.c b/mm/migrate.c index e7296c0fb5d5..923ea80ba744 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1479,11 +1479,17 @@ out: return rc; } -static inline int try_split_folio(struct folio *folio, struct list_head *split_folios) +static inline int try_split_folio(struct folio *folio, struct list_head *split_folios, + enum migrate_mode mode) { int rc; - folio_lock(folio); + if (mode == MIGRATE_ASYNC) { + if (!folio_trylock(folio)) + return -EAGAIN; + } else { + folio_lock(folio); + } rc = split_folio_to_list(folio, split_folios); folio_unlock(folio); if (!rc) @@ -1677,7 +1683,7 @@ static int migrate_pages_batch(struct list_head *from, */ if (nr_pages > 2 && !list_empty(&folio->_deferred_list)) { - if (try_split_folio(folio, split_folios) == 0) { + if (!try_split_folio(folio, split_folios, mode)) { nr_failed++; stats->nr_thp_failed += is_thp; stats->nr_thp_split += is_thp; @@ -1699,7 +1705,7 @@ static int migrate_pages_batch(struct list_head *from, if (!thp_migration_supported() && is_thp) { nr_failed++; stats->nr_thp_failed++; - if (!try_split_folio(folio, split_folios)) { + if (!try_split_folio(folio, split_folios, mode)) { stats->nr_thp_split++; stats->nr_split++; continue; @@ -1731,7 +1737,7 @@ static int migrate_pages_batch(struct list_head *from, stats->nr_thp_failed += is_thp; /* Large folio NUMA faulting doesn't split to retry. */ if (is_large && !nosplit) { - int ret = try_split_folio(folio, split_folios); + int ret = try_split_folio(folio, split_folios, mode); if (!ret) { stats->nr_thp_split += is_thp; diff --git a/mm/mm_init.c b/mm/mm_init.c index 75c3bd42799b..51960079875b 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1623,8 +1623,7 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat) panic("Failed to allocate %ld bytes for node %d memory map\n", size, pgdat->node_id); pgdat->node_mem_map = map + offset; - mod_node_early_perpage_metadata(pgdat->node_id, - DIV_ROUND_UP(size, PAGE_SIZE)); + memmap_boot_pages_add(DIV_ROUND_UP(size, PAGE_SIZE)); pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n", __func__, pgdat->node_id, (unsigned long)pgdat, (unsigned long)pgdat->node_mem_map); @@ -2245,6 +2244,8 @@ void __init init_cma_reserved_pageblock(struct page *page) set_pageblock_migratetype(page, MIGRATE_CMA); set_page_refcounted(page); + /* pages were reserved and not allocated */ + clear_page_tag_ref(page); __free_pages(page, pageblock_order); adjust_managed_page_count(page, pageblock_nr_pages); @@ -2460,15 +2461,7 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn, } /* pages were reserved and not allocated */ - if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); - - if (ref) { - set_codetag_empty(ref); - put_page_tag_ref(ref); - } - } - + clear_page_tag_ref(page); __free_pages_core(page, order, MEMINIT_EARLY); } diff --git a/mm/mseal.c b/mm/mseal.c index bf783bba8ed0..15bba28acc00 100644 --- a/mm/mseal.c +++ b/mm/mseal.c @@ -40,9 +40,17 @@ static bool can_modify_vma(struct vm_area_struct *vma) static bool is_madv_discard(int behavior) { - return behavior & - (MADV_FREE | MADV_DONTNEED | MADV_DONTNEED_LOCKED | - MADV_REMOVE | MADV_DONTFORK | MADV_WIPEONFORK); + switch (behavior) { + case MADV_FREE: + case MADV_DONTNEED: + case MADV_DONTNEED_LOCKED: + case MADV_REMOVE: + case MADV_DONTFORK: + case MADV_WIPEONFORK: + return true; + } + + return false; } static bool is_ro_anon(struct vm_area_struct *vma) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 28f80daf5c04..c565de8f48e9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -287,7 +287,7 @@ EXPORT_SYMBOL(nr_online_nodes); static bool page_contains_unaccepted(struct page *page, unsigned int order); static void accept_page(struct page *page, unsigned int order); -static bool try_to_accept_memory(struct zone *zone, unsigned int order); +static bool cond_accept_memory(struct zone *zone, unsigned int order); static inline bool has_unaccepted_memory(void); static bool __free_unaccepted(struct page *page); @@ -3072,9 +3072,6 @@ static inline long __zone_watermark_unusable_free(struct zone *z, if (!(alloc_flags & ALLOC_CMA)) unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES); #endif -#ifdef CONFIG_UNACCEPTED_MEMORY - unusable_free += zone_page_state(z, NR_UNACCEPTED); -#endif return unusable_free; } @@ -3368,6 +3365,8 @@ retry: } } + cond_accept_memory(zone, order); + /* * Detect whether the number of free pages is below high * watermark. If so, we will decrease pcp->high and free @@ -3393,10 +3392,8 @@ check_alloc_wmark: gfp_mask)) { int ret; - if (has_unaccepted_memory()) { - if (try_to_accept_memory(zone, order)) - goto try_this_zone; - } + if (cond_accept_memory(zone, order)) + goto try_this_zone; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* @@ -3450,10 +3447,8 @@ try_this_zone: return page; } else { - if (has_unaccepted_memory()) { - if (try_to_accept_memory(zone, order)) - goto try_this_zone; - } + if (cond_accept_memory(zone, order)) + goto try_this_zone; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* Try again if zone has deferred pages */ @@ -5755,7 +5750,6 @@ void __init setup_per_cpu_pageset(void) for_each_online_pgdat(pgdat) pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat); - store_early_perpage_metadata(); } __meminit void zone_pcp_init(struct zone *zone) @@ -5821,14 +5815,7 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char void free_reserved_page(struct page *page) { - if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); - - if (ref) { - set_codetag_empty(ref); - put_page_tag_ref(ref); - } - } + clear_page_tag_ref(page); ClearPageReserved(page); init_page_count(page); __free_page(page); @@ -6951,9 +6938,6 @@ static bool try_to_accept_memory_one(struct zone *zone) struct page *page; bool last; - if (list_empty(&zone->unaccepted_pages)) - return false; - spin_lock_irqsave(&zone->lock, flags); page = list_first_entry_or_null(&zone->unaccepted_pages, struct page, lru); @@ -6979,23 +6963,29 @@ static bool try_to_accept_memory_one(struct zone *zone) return true; } -static bool try_to_accept_memory(struct zone *zone, unsigned int order) +static bool cond_accept_memory(struct zone *zone, unsigned int order) { long to_accept; - int ret = false; + bool ret = false; + + if (!has_unaccepted_memory()) + return false; + + if (list_empty(&zone->unaccepted_pages)) + return false; /* How much to accept to get to high watermark? */ to_accept = high_wmark_pages(zone) - (zone_page_state(zone, NR_FREE_PAGES) - - __zone_watermark_unusable_free(zone, order, 0)); + __zone_watermark_unusable_free(zone, order, 0) - + zone_page_state(zone, NR_UNACCEPTED)); - /* Accept at least one page */ - do { + while (to_accept > 0) { if (!try_to_accept_memory_one(zone)) break; ret = true; to_accept -= MAX_ORDER_NR_PAGES; - } while (to_accept > 0); + } return ret; } @@ -7038,7 +7028,7 @@ static void accept_page(struct page *page, unsigned int order) { } -static bool try_to_accept_memory(struct zone *zone, unsigned int order) +static bool cond_accept_memory(struct zone *zone, unsigned int order) { return false; } diff --git a/mm/page_ext.c b/mm/page_ext.c index c191e490c401..641d93f6af4c 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -214,8 +214,7 @@ static int __init alloc_node_page_ext(int nid) return -ENOMEM; NODE_DATA(nid)->node_page_ext = base; total_usage += table_size; - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP_BOOT, - DIV_ROUND_UP(table_size, PAGE_SIZE)); + memmap_boot_pages_add(DIV_ROUND_UP(table_size, PAGE_SIZE)); return 0; } @@ -275,10 +274,8 @@ static void *__meminit alloc_page_ext(size_t size, int nid) else addr = vzalloc_node(size, nid); - if (addr) { - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, - DIV_ROUND_UP(size, PAGE_SIZE)); - } + if (addr) + memmap_pages_add(DIV_ROUND_UP(size, PAGE_SIZE)); return addr; } @@ -323,25 +320,18 @@ static void free_page_ext(void *addr) { size_t table_size; struct page *page; - struct pglist_data *pgdat; table_size = page_ext_size * PAGES_PER_SECTION; + memmap_pages_add(-1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); if (is_vmalloc_addr(addr)) { - page = vmalloc_to_page(addr); - pgdat = page_pgdat(page); vfree(addr); } else { page = virt_to_page(addr); - pgdat = page_pgdat(page); BUG_ON(PageReserved(page)); kmemleak_free(addr); free_pages_exact(addr, table_size); } - - mod_node_page_state(pgdat, NR_MEMMAP, - -1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); - } static void __free_page_ext(unsigned long pfn) diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 1dda6c53370b..edcc7a6b0f6f 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -469,13 +469,10 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn, if (r < 0) return NULL; - if (system_state == SYSTEM_BOOTING) { - mod_node_early_perpage_metadata(nid, DIV_ROUND_UP(end - start, - PAGE_SIZE)); - } else { - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, - DIV_ROUND_UP(end - start, PAGE_SIZE)); - } + if (system_state == SYSTEM_BOOTING) + memmap_boot_pages_add(DIV_ROUND_UP(end - start, PAGE_SIZE)); + else + memmap_pages_add(DIV_ROUND_UP(end - start, PAGE_SIZE)); return pfn_to_page(pfn); } diff --git a/mm/sparse.c b/mm/sparse.c index e4b830091d13..0f018c6f9ec5 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -463,7 +463,7 @@ static void __init sparse_buffer_init(unsigned long size, int nid) sparsemap_buf = memmap_alloc(size, section_map_size(), addr, nid, true); sparsemap_buf_end = sparsemap_buf + size; #ifndef CONFIG_SPARSEMEM_VMEMMAP - mod_node_early_perpage_metadata(nid, DIV_ROUND_UP(size, PAGE_SIZE)); + memmap_boot_pages_add(DIV_ROUND_UP(size, PAGE_SIZE)); #endif } @@ -643,8 +643,7 @@ static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages, unsigned long start = (unsigned long) pfn_to_page(pfn); unsigned long end = start + nr_pages * sizeof(struct page); - mod_node_page_state(page_pgdat(pfn_to_page(pfn)), NR_MEMMAP, - -1L * (DIV_ROUND_UP(end - start, PAGE_SIZE))); + memmap_pages_add(-1L * (DIV_ROUND_UP(end - start, PAGE_SIZE))); vmemmap_free(start, end, altmap); } static void free_map_bootmem(struct page *memmap) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 6b783baf12a1..af2de36549d6 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3584,15 +3584,8 @@ vm_area_alloc_pages(gfp_t gfp, int nid, page = alloc_pages_noprof(alloc_gfp, order); else page = alloc_pages_node_noprof(nid, alloc_gfp, order); - if (unlikely(!page)) { - if (!nofail) - break; - - /* fall back to the zero order allocations */ - alloc_gfp |= __GFP_NOFAIL; - order = 0; - continue; - } + if (unlikely(!page)) + break; /* * Higher order allocations must be able to be treated as diff --git a/mm/vmstat.c b/mm/vmstat.c index 04a1cb6cc636..e875f2a4915f 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1033,6 +1033,24 @@ unsigned long node_page_state(struct pglist_data *pgdat, } #endif +/* + * Count number of pages "struct page" and "struct page_ext" consume. + * nr_memmap_boot_pages: # of pages allocated by boot allocator + * nr_memmap_pages: # of pages that were allocated by buddy allocator + */ +static atomic_long_t nr_memmap_boot_pages = ATOMIC_LONG_INIT(0); +static atomic_long_t nr_memmap_pages = ATOMIC_LONG_INIT(0); + +void memmap_boot_pages_add(long delta) +{ + atomic_long_add(delta, &nr_memmap_boot_pages); +} + +void memmap_pages_add(long delta) +{ + atomic_long_add(delta, &nr_memmap_pages); +} + #ifdef CONFIG_COMPACTION struct contig_page_info { @@ -1255,11 +1273,11 @@ const char * const vmstat_text[] = { "pgdemote_kswapd", "pgdemote_direct", "pgdemote_khugepaged", - "nr_memmap", - "nr_memmap_boot", - /* enum writeback_stat_item counters */ + /* system-wide enum vm_stat_item counters */ "nr_dirty_threshold", "nr_dirty_background_threshold", + "nr_memmap_pages", + "nr_memmap_boot_pages", #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) /* enum vm_event_item counters */ @@ -1790,7 +1808,7 @@ static const struct seq_operations zoneinfo_op = { #define NR_VMSTAT_ITEMS (NR_VM_ZONE_STAT_ITEMS + \ NR_VM_NUMA_EVENT_ITEMS + \ NR_VM_NODE_STAT_ITEMS + \ - NR_VM_WRITEBACK_STAT_ITEMS + \ + NR_VM_STAT_ITEMS + \ (IS_ENABLED(CONFIG_VM_EVENT_COUNTERS) ? \ NR_VM_EVENT_ITEMS : 0)) @@ -1827,7 +1845,9 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD, v + NR_DIRTY_THRESHOLD); - v += NR_VM_WRITEBACK_STAT_ITEMS; + v[NR_MEMMAP_PAGES] = atomic_long_read(&nr_memmap_pages); + v[NR_MEMMAP_BOOT_PAGES] = atomic_long_read(&nr_memmap_boot_pages); + v += NR_VM_STAT_ITEMS; #ifdef CONFIG_VM_EVENT_COUNTERS all_vm_events(v); @@ -2285,25 +2305,3 @@ static int __init extfrag_debug_init(void) module_init(extfrag_debug_init); #endif - -/* - * Page metadata size (struct page and page_ext) in pages - */ -static unsigned long early_perpage_metadata[MAX_NUMNODES] __meminitdata; - -void __meminit mod_node_early_perpage_metadata(int nid, long delta) -{ - early_perpage_metadata[nid] += delta; -} - -void __meminit store_early_perpage_metadata(void) -{ - int nid; - struct pglist_data *pgdat; - - for_each_online_pgdat(pgdat) { - nid = pgdat->node_id; - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP_BOOT, - early_perpage_metadata[nid]); - } -} diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 7b8a5def54a1..cfad627e8d94 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -53,7 +53,9 @@ TEST_GEN_FILES += madv_populate TEST_GEN_FILES += map_fixed_noreplace TEST_GEN_FILES += map_hugetlb TEST_GEN_FILES += map_populate +ifneq (,$(filter $(ARCH),arm64 riscv riscv64 x86 x86_64)) TEST_GEN_FILES += memfd_secret +endif TEST_GEN_FILES += migration TEST_GEN_FILES += mkdirty TEST_GEN_FILES += mlock-random-test diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index e140558e6f53..2c3a0eb6b22d 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -89,9 +89,10 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, int fd, ret = -1; int compaction_index = 0; char nr_hugepages[20] = {0}; - char init_nr_hugepages[20] = {0}; + char init_nr_hugepages[24] = {0}; - sprintf(init_nr_hugepages, "%lu", initial_nr_hugepages); + snprintf(init_nr_hugepages, sizeof(init_nr_hugepages), + "%lu", initial_nr_hugepages); /* We want to test with 80% of available memory. Else, OOM killer comes in to play */ diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 03ac4f2e1cce..36045edb10de 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -374,8 +374,11 @@ CATEGORY="hmm" run_test bash ./test_hmm.sh smoke # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate +if [ -x ./memfd_secret ] +then (echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope 2>&1) | tap_prefix CATEGORY="memfd_secret" run_test ./memfd_secret +fi # KSM KSM_MERGE_TIME_HUGE_PAGES test with size of 100 CATEGORY="ksm" run_test ./ksm_tests -H -s 100