diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 1f9615553b82..2b59cff8be17 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -461,6 +461,7 @@ Memory Area, or VMA) there is a series of lines such as the following:: Private_Dirty: 0 kB Referenced: 892 kB Anonymous: 0 kB + KSM: 0 kB LazyFree: 0 kB AnonHugePages: 0 kB ShmemPmdMapped: 0 kB @@ -501,6 +502,9 @@ accessed. a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE and a page is modified, the file page is replaced by a private anonymous copy. +"KSM" reports how many of the pages are KSM pages. Note that KSM-placed zeropages +are not included, only actual KSM pages. + "LazyFree" shows the amount of memory which is marked by madvise(MADV_FREE). The memory isn't freed immediately with madvise(). It's freed in memory pressure if the memory is clean. Please note that the printed value might diff --git a/MAINTAINERS b/MAINTAINERS index 9c186c214c54..0e4ad56821a0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13742,6 +13742,7 @@ F: include/linux/memory_hotplug.h F: include/linux/mm.h F: include/linux/mmzone.h F: include/linux/pagewalk.h +F: include/linux/rmap.h F: include/trace/events/ksm.h F: mm/ F: tools/mm/ diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 0f2aa36a9913..3dd5be96691b 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include @@ -396,6 +397,7 @@ struct mem_size_stats { unsigned long swap; unsigned long shared_hugetlb; unsigned long private_hugetlb; + unsigned long ksm; u64 pss; u64 pss_anon; u64 pss_file; @@ -452,6 +454,9 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, mss->lazyfree += size; } + if (PageKsm(page)) + mss->ksm += size; + mss->resident += size; /* Accumulate the size in pages that have been accessed. */ if (young || page_is_young(page) || PageReferenced(page)) @@ -825,6 +830,7 @@ static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss, SEQ_PUT_DEC(" kB\nPrivate_Dirty: ", mss->private_dirty); SEQ_PUT_DEC(" kB\nReferenced: ", mss->referenced); SEQ_PUT_DEC(" kB\nAnonymous: ", mss->anonymous); + SEQ_PUT_DEC(" kB\nKSM: ", mss->ksm); SEQ_PUT_DEC(" kB\nLazyFree: ", mss->lazyfree); SEQ_PUT_DEC(" kB\nAnonHugePages: ", mss->anonymous_thp); SEQ_PUT_DEC(" kB\nShmemPmdMapped: ", mss->shmem_thp); diff --git a/include/linux/rmap.h b/include/linux/rmap.h index a3825ce81102..51cc21ebb568 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -479,7 +479,6 @@ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio, #define anon_vma_init() do {} while (0) #define anon_vma_prepare(vma) (0) -#define anon_vma_link(vma) do {} while (0) static inline int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 2918150e31bd..54c2c90d3abc 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1584,6 +1584,9 @@ static void kmemleak_scan(void) for (pfn = start_pfn; pfn < end_pfn; pfn++) { struct page *page = pfn_to_online_page(pfn); + if (!(pfn & 63)) + cond_resched(); + if (!page) continue; @@ -1594,8 +1597,6 @@ static void kmemleak_scan(void) if (page_count(page) == 0) continue; scan_block(page, page + 1, NULL); - if (!(pfn & 63)) - cond_resched(); } } put_online_mems(); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 881c35ef1daa..7b01fffe7a79 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -717,7 +717,7 @@ static void collect_procs(struct page *page, struct list_head *tokill, collect_procs_file(page, tokill, force_early); } -struct hwp_walk { +struct hwpoison_walk { struct to_kill tk; unsigned long pfn; int flags; @@ -752,7 +752,7 @@ static int check_hwpoisoned_entry(pte_t pte, unsigned long addr, short shift, #ifdef CONFIG_TRANSPARENT_HUGEPAGE static int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr, - struct hwp_walk *hwp) + struct hwpoison_walk *hwp) { pmd_t pmd = *pmdp; unsigned long pfn; @@ -770,7 +770,7 @@ static int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr, } #else static int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr, - struct hwp_walk *hwp) + struct hwpoison_walk *hwp) { return 0; } @@ -779,7 +779,7 @@ static int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr, static int hwpoison_pte_range(pmd_t *pmdp, unsigned long addr, unsigned long end, struct mm_walk *walk) { - struct hwp_walk *hwp = walk->private; + struct hwpoison_walk *hwp = walk->private; int ret = 0; pte_t *ptep, *mapped_pte; spinlock_t *ptl; @@ -813,7 +813,7 @@ static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { - struct hwp_walk *hwp = walk->private; + struct hwpoison_walk *hwp = walk->private; pte_t pte = huge_ptep_get(ptep); struct hstate *h = hstate_vma(walk->vma); @@ -824,7 +824,7 @@ static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask, #define hwpoison_hugetlb_range NULL #endif -static const struct mm_walk_ops hwp_walk_ops = { +static const struct mm_walk_ops hwpoison_walk_ops = { .pmd_entry = hwpoison_pte_range, .hugetlb_entry = hwpoison_hugetlb_range, .walk_lock = PGWALK_RDLOCK, @@ -847,7 +847,7 @@ static int kill_accessing_process(struct task_struct *p, unsigned long pfn, int flags) { int ret; - struct hwp_walk priv = { + struct hwpoison_walk priv = { .pfn = pfn, }; priv.tk.tsk = p; @@ -856,7 +856,7 @@ static int kill_accessing_process(struct task_struct *p, unsigned long pfn, return -EFAULT; mmap_read_lock(p->mm); - ret = walk_page_range(p->mm, 0, TASK_SIZE, &hwp_walk_ops, + ret = walk_page_range(p->mm, 0, TASK_SIZE, &hwpoison_walk_ops, (void *)&priv); if (ret == 1 && priv.tk.addr) kill_proc(&priv.tk, pfn, flags); @@ -1562,7 +1562,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * Here we are interested only in user-mapped pages, so skip any * other types of pages. */ - if (PageReserved(p) || PageSlab(p) || PageTable(p)) + if (PageReserved(p) || PageSlab(p) || PageTable(p) || PageOffline(p)) return true; if (!(PageLRU(hpage) || PageHuge(p))) return true; @@ -2533,7 +2533,8 @@ int unpoison_memory(unsigned long pfn) goto unlock_mutex; } - if (folio_test_slab(folio) || PageTable(&folio->page) || folio_test_reserved(folio)) + if (folio_test_slab(folio) || PageTable(&folio->page) || + folio_test_reserved(folio) || PageOffline(&folio->page)) goto unlock_mutex; /* diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 452459836b71..0c5be12f9336 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2641,12 +2641,6 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone, do { page = NULL; spin_lock_irqsave(&zone->lock, flags); - /* - * order-0 request can reach here when the pcplist is skipped - * due to non-CMA allocation context. HIGHATOMIC area is - * reserved for high-order atomic allocation, so order-0 - * request should skip it. - */ if (alloc_flags & ALLOC_HIGHATOMIC) page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); if (!page) { @@ -2780,17 +2774,10 @@ struct page *rmqueue(struct zone *preferred_zone, WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1)); if (likely(pcp_allowed_order(order))) { - /* - * MIGRATE_MOVABLE pcplist could have the pages on CMA area and - * we need to skip it when CMA area isn't allowed. - */ - if (!IS_ENABLED(CONFIG_CMA) || alloc_flags & ALLOC_CMA || - migratetype != MIGRATE_MOVABLE) { - page = rmqueue_pcplist(preferred_zone, zone, order, - migratetype, alloc_flags); - if (likely(page)) - goto out; - } + page = rmqueue_pcplist(preferred_zone, zone, order, + migratetype, alloc_flags); + if (likely(page)) + goto out; } page = rmqueue_buddy(preferred_zone, zone, order, alloc_flags,