diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/debug.c | 7 | ||||
-rw-r--r-- | mm/filemap.c | 4 | ||||
-rw-r--r-- | mm/gup.c | 11 | ||||
-rw-r--r-- | mm/huge_memory.c | 19 | ||||
-rw-r--r-- | mm/hugetlb.c | 5 | ||||
-rw-r--r-- | mm/internal.h | 6 | ||||
-rw-r--r-- | mm/kasan/kasan_test_c.c | 2 | ||||
-rw-r--r-- | mm/kasan/report.c | 6 | ||||
-rw-r--r-- | mm/memblock.c | 4 | ||||
-rw-r--r-- | mm/memcontrol-v1.h | 2 | ||||
-rw-r--r-- | mm/memory.c | 18 | ||||
-rw-r--r-- | mm/mempolicy.c | 4 | ||||
-rw-r--r-- | mm/migrate.c | 2 | ||||
-rw-r--r-- | mm/mmap.c | 1 | ||||
-rw-r--r-- | mm/page_alloc.c | 6 | ||||
-rw-r--r-- | mm/pgtable-generic.c | 2 | ||||
-rw-r--r-- | mm/readahead.c | 5 | ||||
-rw-r--r-- | mm/shmem.c | 22 | ||||
-rw-r--r-- | mm/slub.c | 21 | ||||
-rw-r--r-- | mm/vma.c | 7 | ||||
-rw-r--r-- | mm/vmalloc.c | 9 |
21 files changed, 100 insertions, 63 deletions
diff --git a/mm/debug.c b/mm/debug.c index aa57d3ffd4ed..95b6ab809c0e 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -124,19 +124,22 @@ static void __dump_page(const struct page *page) { struct folio *foliop, folio; struct page precise; + unsigned long head; unsigned long pfn = page_to_pfn(page); unsigned long idx, nr_pages = 1; int loops = 5; again: memcpy(&precise, page, sizeof(*page)); - foliop = page_folio(&precise); - if (foliop == (struct folio *)&precise) { + head = precise.compound_head; + if ((head & 1) == 0) { + foliop = (struct folio *)&precise; idx = 0; if (!folio_test_large(foliop)) goto dump; foliop = (struct folio *)page; } else { + foliop = (struct folio *)(head - 1); idx = folio_page_idx(foliop, page); } diff --git a/mm/filemap.c b/mm/filemap.c index 7c76a123ba18..f61cf51c2238 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3501,10 +3501,10 @@ static struct folio *next_uptodate_folio(struct xa_state *xas, continue; if (xa_is_value(folio)) continue; - if (folio_test_locked(folio)) - continue; if (!folio_try_get(folio)) continue; + if (folio_test_locked(folio)) + goto skip; /* Has the page moved or been split? */ if (unlikely(folio != xas_reload(xas))) goto skip; @@ -52,7 +52,12 @@ static inline void sanity_check_pinned_pages(struct page **pages, */ for (; npages; npages--, pages++) { struct page *page = *pages; - struct folio *folio = page_folio(page); + struct folio *folio; + + if (!page) + continue; + + folio = page_folio(page); if (is_zero_page(page) || !folio_test_anon(folio)) @@ -409,6 +414,10 @@ void unpin_user_pages(struct page **pages, unsigned long npages) sanity_check_pinned_pages(pages, npages); for (i = 0; i < npages; i += nr) { + if (!pages[i]) { + nr = 1; + continue; + } folio = gup_folio_next(pages, npages, i, &nr); gup_put_folio(folio, nr, FOLL_PIN); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index ee335d96fc39..e53d83b3e5cf 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1176,11 +1176,12 @@ static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma, folio_throttle_swaprate(folio, gfp); /* - * When a folio is not zeroed during allocation (__GFP_ZERO not used), - * folio_zero_user() is used to make sure that the page corresponding - * to the faulting address will be hot in the cache after zeroing. + * When a folio is not zeroed during allocation (__GFP_ZERO not used) + * or user folios require special handling, folio_zero_user() is used to + * make sure that the page corresponding to the faulting address will be + * hot in the cache after zeroing. */ - if (!alloc_zeroed()) + if (user_alloc_needs_zeroing()) folio_zero_user(folio, addr); /* * The memory barrier inside __folio_mark_uptodate makes sure that @@ -3576,7 +3577,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, !list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; if (folio_test_partially_mapped(folio)) { - __folio_clear_partially_mapped(folio); + folio_clear_partially_mapped(folio); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } @@ -3688,7 +3689,7 @@ bool __folio_unqueue_deferred_split(struct folio *folio) if (!list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; if (folio_test_partially_mapped(folio)) { - __folio_clear_partially_mapped(folio); + folio_clear_partially_mapped(folio); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } @@ -3732,7 +3733,7 @@ void deferred_split_folio(struct folio *folio, bool partially_mapped) spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (partially_mapped) { if (!folio_test_partially_mapped(folio)) { - __folio_set_partially_mapped(folio); + folio_set_partially_mapped(folio); if (folio_test_pmd_mappable(folio)) count_vm_event(THP_DEFERRED_SPLIT_PAGE); count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED); @@ -3825,7 +3826,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, } else { /* We lost race with folio_put() */ if (folio_test_partially_mapped(folio)) { - __folio_clear_partially_mapped(folio); + folio_clear_partially_mapped(folio); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } @@ -4168,7 +4169,7 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf, size_t input_len = strlen(input_buf); tok = strsep(&buf, ","); - if (tok) { + if (tok && buf) { strscpy(file_path, tok); } else { ret = -EINVAL; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ea2ed8e301ef..cec4b121193f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5340,7 +5340,7 @@ again: break; } ret = copy_user_large_folio(new_folio, pte_folio, - ALIGN_DOWN(addr, sz), dst_vma); + addr, dst_vma); folio_put(pte_folio); if (ret) { folio_put(new_folio); @@ -6643,8 +6643,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, *foliop = NULL; goto out; } - ret = copy_user_large_folio(folio, *foliop, - ALIGN_DOWN(dst_addr, size), dst_vma); + ret = copy_user_large_folio(folio, *foliop, dst_addr, dst_vma); folio_put(*foliop); *foliop = NULL; if (ret) { diff --git a/mm/internal.h b/mm/internal.h index cb8d8e8e3ffa..3bd08bafad04 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1285,12 +1285,6 @@ void touch_pud(struct vm_area_struct *vma, unsigned long addr, void touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, bool write); -static inline bool alloc_zeroed(void) -{ - return static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, - &init_on_alloc); -} - /* * Parses a string with mem suffixes into its order. Useful to parse kernel * parameters. diff --git a/mm/kasan/kasan_test_c.c b/mm/kasan/kasan_test_c.c index e0ec5a6d15be..99d4ff0ed57a 100644 --- a/mm/kasan/kasan_test_c.c +++ b/mm/kasan/kasan_test_c.c @@ -33,7 +33,7 @@ #define OOB_TAG_OFF (IS_ENABLED(CONFIG_KASAN_GENERIC) ? 0 : KASAN_GRANULE_SIZE) -MODULE_IMPORT_NS(EXPORTED_FOR_KUNIT_TESTING); +MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING"); static bool multishot; diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 50fb19ad4388..3fe77a360f1c 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -201,7 +201,7 @@ static inline void fail_non_kasan_kunit_test(void) { } #endif /* CONFIG_KUNIT */ -static DEFINE_SPINLOCK(report_lock); +static DEFINE_RAW_SPINLOCK(report_lock); static void start_report(unsigned long *flags, bool sync) { @@ -212,7 +212,7 @@ static void start_report(unsigned long *flags, bool sync) lockdep_off(); /* Make sure we don't end up in loop. */ report_suppress_start(); - spin_lock_irqsave(&report_lock, *flags); + raw_spin_lock_irqsave(&report_lock, *flags); pr_err("==================================================================\n"); } @@ -222,7 +222,7 @@ static void end_report(unsigned long *flags, const void *addr, bool is_write) trace_error_report_end(ERROR_DETECTOR_KASAN, (unsigned long)addr); pr_err("==================================================================\n"); - spin_unlock_irqrestore(&report_lock, *flags); + raw_spin_unlock_irqrestore(&report_lock, *flags); if (!test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags)) check_panic_on_warn("KASAN"); switch (kasan_arg_fault) { diff --git a/mm/memblock.c b/mm/memblock.c index 0389ce5cd281..095c18b5c430 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -735,7 +735,7 @@ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) /** * memblock_validate_numa_coverage - check if amount of memory with * no node ID assigned is less than a threshold - * @threshold_bytes: maximal number of pages that can have unassigned node + * @threshold_bytes: maximal memory size that can have unassigned node * ID (in bytes). * * A buggy firmware may report memory that does not belong to any node. @@ -755,7 +755,7 @@ bool __init_memblock memblock_validate_numa_coverage(unsigned long threshold_byt nr_pages += end_pfn - start_pfn; } - if ((nr_pages << PAGE_SHIFT) >= threshold_bytes) { + if ((nr_pages << PAGE_SHIFT) > threshold_bytes) { mem_size_mb = memblock_phys_mem_size() >> 20; pr_err("NUMA: no nodes coverage for %luMB of %luMB RAM\n", (nr_pages << PAGE_SHIFT) >> 20, mem_size_mb); diff --git a/mm/memcontrol-v1.h b/mm/memcontrol-v1.h index 0e3b82951d91..144d71b65907 100644 --- a/mm/memcontrol-v1.h +++ b/mm/memcontrol-v1.h @@ -38,7 +38,7 @@ void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n); iter = mem_cgroup_iter(NULL, iter, NULL)) /* Whether legacy memory+swap accounting is active */ -static bool do_memsw_account(void) +static inline bool do_memsw_account(void) { return !cgroup_subsys_on_dfl(memory_cgrp_subsys); } diff --git a/mm/memory.c b/mm/memory.c index 75c2dfd04f72..398c031be9ba 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4733,12 +4733,12 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf) folio_throttle_swaprate(folio, gfp); /* * When a folio is not zeroed during allocation - * (__GFP_ZERO not used), folio_zero_user() is used - * to make sure that the page corresponding to the - * faulting address will be hot in the cache after - * zeroing. + * (__GFP_ZERO not used) or user folios require special + * handling, folio_zero_user() is used to make sure + * that the page corresponding to the faulting address + * will be hot in the cache after zeroing. */ - if (!alloc_zeroed()) + if (user_alloc_needs_zeroing()) folio_zero_user(folio, vmf->address); return folio; } @@ -6815,9 +6815,10 @@ static inline int process_huge_page( return 0; } -static void clear_gigantic_page(struct folio *folio, unsigned long addr, +static void clear_gigantic_page(struct folio *folio, unsigned long addr_hint, unsigned int nr_pages) { + unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(folio)); int i; might_sleep(); @@ -6851,13 +6852,14 @@ void folio_zero_user(struct folio *folio, unsigned long addr_hint) } static int copy_user_gigantic_page(struct folio *dst, struct folio *src, - unsigned long addr, + unsigned long addr_hint, struct vm_area_struct *vma, unsigned int nr_pages) { - int i; + unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(dst)); struct page *dst_page; struct page *src_page; + int i; for (i = 0; i < nr_pages; i++) { dst_page = folio_page(dst, i); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index bb37cd1a51d8..04f35659717a 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1080,6 +1080,10 @@ static long migrate_to_node(struct mm_struct *mm, int source, int dest, mmap_read_lock(mm); vma = find_vma(mm, 0); + if (unlikely(!vma)) { + mmap_read_unlock(mm); + return 0; + } /* * This does not migrate the range, but isolates all pages that diff --git a/mm/migrate.c b/mm/migrate.c index 2ce6b4b814df..cc68583c86f9 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -745,7 +745,7 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) folio_set_readahead(newfolio); folio_copy_owner(newfolio, folio); - pgalloc_tag_copy(newfolio, folio); + pgalloc_tag_swap(newfolio, folio); mem_cgroup_migrate(folio, newfolio); } diff --git a/mm/mmap.c b/mm/mmap.c index 386429f7db5a..d32b7e701058 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -889,6 +889,7 @@ __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, if (get_area) { addr = get_area(file, addr, len, pgoff, flags); } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) + && !addr /* no hint */ && IS_ALIGNED(len, PMD_SIZE)) { /* Ensures that larger anonymous mappings are THP aligned. */ addr = thp_get_unmapped_area_vmflags(file, addr, len, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 1cb4b8c8886d..cae7b93864c2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1238,13 +1238,15 @@ static void split_large_buddy(struct zone *zone, struct page *page, if (order > pageblock_order) order = pageblock_order; - while (pfn != end) { + do { int mt = get_pfnblock_migratetype(page, pfn); __free_one_page(page, pfn, zone, order, mt, fpi); pfn += 1 << order; + if (pfn == end) + break; page = pfn_to_page(pfn); - } + } while (1); } static void free_one_page(struct zone *zone, struct page *page, diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 5297dcc38c37..5a882f2b10f9 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -279,7 +279,7 @@ static unsigned long pmdp_get_lockless_start(void) { return 0; } static void pmdp_get_lockless_end(unsigned long irqflags) { } #endif -pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp) +pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp) { unsigned long irqflags; pmd_t pmdval; diff --git a/mm/readahead.c b/mm/readahead.c index 8f1cf599b572..ea650b8b02fb 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -458,8 +458,7 @@ void page_cache_ra_order(struct readahead_control *ractl, struct file_ra_state *ra, unsigned int new_order) { struct address_space *mapping = ractl->mapping; - pgoff_t start = readahead_index(ractl); - pgoff_t index = start; + pgoff_t index = readahead_index(ractl); unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; pgoff_t mark = index + ra->size - ra->async_size; @@ -522,7 +521,7 @@ void page_cache_ra_order(struct readahead_control *ractl, if (!err) return; fallback: - do_page_cache_ra(ractl, ra->size - (index - start), ra->async_size); + do_page_cache_ra(ractl, ra->size, ra->async_size); } static unsigned long ractl_max_pages(struct readahead_control *ractl, diff --git a/mm/shmem.c b/mm/shmem.c index ccb9629a0f70..f6fb053ac50d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -787,6 +787,14 @@ static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static void shmem_update_stats(struct folio *folio, int nr_pages) +{ + if (folio_test_pmd_mappable(folio)) + __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr_pages); + __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr_pages); + __lruvec_stat_mod_folio(folio, NR_SHMEM, nr_pages); +} + /* * Somewhat like filemap_add_folio, but error if expected item has gone. */ @@ -821,10 +829,7 @@ static int shmem_add_to_page_cache(struct folio *folio, xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; - if (folio_test_pmd_mappable(folio)) - __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr); - __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr); - __lruvec_stat_mod_folio(folio, NR_SHMEM, nr); + shmem_update_stats(folio, nr); mapping->nrpages += nr; unlock: xas_unlock_irq(&xas); @@ -852,8 +857,7 @@ static void shmem_delete_from_page_cache(struct folio *folio, void *radswap) error = shmem_replace_entry(mapping, folio->index, folio, radswap); folio->mapping = NULL; mapping->nrpages -= nr; - __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr); - __lruvec_stat_mod_folio(folio, NR_SHMEM, -nr); + shmem_update_stats(folio, -nr); xa_unlock_irq(&mapping->i_pages); folio_put_refs(folio, nr); BUG_ON(error); @@ -1969,10 +1973,8 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp, } if (!error) { mem_cgroup_replace_folio(old, new); - __lruvec_stat_mod_folio(new, NR_FILE_PAGES, nr_pages); - __lruvec_stat_mod_folio(new, NR_SHMEM, nr_pages); - __lruvec_stat_mod_folio(old, NR_FILE_PAGES, -nr_pages); - __lruvec_stat_mod_folio(old, NR_SHMEM, -nr_pages); + shmem_update_stats(new, nr_pages); + shmem_update_stats(old, -nr_pages); } xa_unlock_irq(&swap_mapping->i_pages); diff --git a/mm/slub.c b/mm/slub.c index 19980419b176..c2151c9fee22 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2189,9 +2189,24 @@ bool memcg_slab_post_charge(void *p, gfp_t flags) folio = virt_to_folio(p); if (!folio_test_slab(folio)) { - return folio_memcg_kmem(folio) || - (__memcg_kmem_charge_page(folio_page(folio, 0), flags, - folio_order(folio)) == 0); + int size; + + if (folio_memcg_kmem(folio)) + return true; + + if (__memcg_kmem_charge_page(folio_page(folio, 0), flags, + folio_order(folio))) + return false; + + /* + * This folio has already been accounted in the global stats but + * not in the memcg stats. So, subtract from the global and use + * the interface which adds to both global and memcg stats. + */ + size = folio_size(folio); + node_stat_mod_folio(folio, NR_SLAB_UNRECLAIMABLE_B, -size); + lruvec_stat_mod_folio(folio, NR_SLAB_UNRECLAIMABLE_B, size); + return true; } slab = folio_slab(folio); @@ -35,7 +35,7 @@ struct mmap_state { .mm = mm_, \ .vmi = vmi_, \ .addr = addr_, \ - .end = (addr_) + len, \ + .end = (addr_) + (len_), \ .pgoff = pgoff_, \ .pglen = PHYS_PFN(len_), \ .flags = flags_, \ @@ -2460,10 +2460,13 @@ unsigned long __mmap_region(struct file *file, unsigned long addr, /* If flags changed, we might be able to merge, so try again. */ if (map.retry_merge) { + struct vm_area_struct *merged; VMG_MMAP_STATE(vmg, &map, vma); vma_iter_config(map.vmi, map.addr, map.end); - vma_merge_existing_range(&vmg); + merged = vma_merge_existing_range(&vmg); + if (merged) + vma = merged; } __mmap_complete(&map, vma); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 7ed39d104201..5c88d0e90c20 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3374,7 +3374,8 @@ void vfree(const void *addr) struct page *page = vm->pages[i]; BUG_ON(!page); - mod_memcg_page_state(page, MEMCG_VMALLOC, -1); + if (!(vm->flags & VM_MAP_PUT_PAGES)) + mod_memcg_page_state(page, MEMCG_VMALLOC, -1); /* * High-order allocs for huge vmallocs are split, so * can be freed as an array of order-0 allocations @@ -3382,7 +3383,8 @@ void vfree(const void *addr) __free_page(page); cond_resched(); } - atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); + if (!(vm->flags & VM_MAP_PUT_PAGES)) + atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); kvfree(vm->pages); kfree(vm); } @@ -4093,7 +4095,8 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) /* Zero out spare memory. */ if (want_init_on_alloc(flags)) memset((void *)p + size, 0, old_size - size); - + kasan_poison_vmalloc(p + size, old_size - size); + kasan_unpoison_vmalloc(p, size, KASAN_VMALLOC_PROT_NORMAL); return (void *)p; } |