diff options
Diffstat (limited to 'mm')
68 files changed, 2081 insertions, 1279 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 3636da27c385..02d44e3420f5 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -148,6 +148,9 @@ config MEMORY_ISOLATION config HAVE_BOOTMEM_INFO_NODE def_bool n +config ARCH_ENABLE_MEMORY_HOTPLUG + bool + # eventually, we can have this option just 'select SPARSEMEM' config MEMORY_HOTPLUG bool "Allow for memory hot-add" @@ -176,12 +179,20 @@ config MEMORY_HOTPLUG_DEFAULT_ONLINE Say N here if you want the default policy to keep all hot-plugged memory blocks in 'offline' state. +config ARCH_ENABLE_MEMORY_HOTREMOVE + bool + config MEMORY_HOTREMOVE bool "Allow for memory hot remove" select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64) depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE depends on MIGRATION +config MHP_MEMMAP_ON_MEMORY + def_bool y + depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP + depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE + # Heavily threaded applications may benefit from splitting the mm-wide # page_table_lock, so that faults on different parts of the user address # space can be handled with less contention: split it at this NR_CPUS. @@ -273,6 +284,13 @@ config ARCH_ENABLE_HUGEPAGE_MIGRATION config ARCH_ENABLE_THP_MIGRATION bool +config HUGETLB_PAGE_SIZE_VARIABLE + def_bool n + help + Allows the pageblock_order value to be dynamic instead of just standard + HUGETLB_PAGE_ORDER when there are multiple HugeTLB page sizes available + on a platform. + config CONTIG_ALLOC def_bool (MEMORY_ISOLATION && COMPACTION) || CMA @@ -511,6 +529,13 @@ config CMA_DEBUGFS help Turns on the DebugFS interface for CMA. +config CMA_SYSFS + bool "CMA information through sysfs interface" + depends on CMA && SYSFS + help + This option exposes some sysfs attributes to get information + from CMA. + config CMA_AREAS int "Maximum count of the CMA areas" depends on CMA @@ -758,6 +783,9 @@ config IDLE_PAGE_TRACKING See Documentation/admin-guide/mm/idle_page_tracking.rst for more details. +config ARCH_HAS_CACHE_LINE_SIZE + bool + config ARCH_HAS_PTE_DEVMAP bool diff --git a/mm/Makefile b/mm/Makefile index c0135e385984..bf71e295e9f6 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -58,9 +58,13 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ page-alloc-y := page_alloc.o page-alloc-$(CONFIG_SHUFFLE_PAGE_ALLOCATOR) += shuffle.o +# Give 'memory_hotplug' its own module-parameter namespace +memory-hotplug-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o + obj-y += page-alloc.o obj-y += init-mm.o obj-y += memblock.o +obj-y += $(memory-hotplug-y) ifdef CONFIG_MMU obj-$(CONFIG_ADVISE_SYSCALLS) += madvise.o @@ -83,7 +87,6 @@ obj-$(CONFIG_SLUB) += slub.o obj-$(CONFIG_KASAN) += kasan/ obj-$(CONFIG_KFENCE) += kfence/ obj-$(CONFIG_FAILSLAB) += failslab.o -obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_MEMTEST) += memtest.o obj-$(CONFIG_MIGRATION) += migrate.o obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o khugepaged.o @@ -109,6 +112,7 @@ obj-$(CONFIG_CMA) += cma.o obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o obj-$(CONFIG_CMA_DEBUGFS) += cma_debug.o +obj-$(CONFIG_CMA_SYSFS) += cma_sysfs.o obj-$(CONFIG_USERFAULTFD) += userfaultfd.o obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c index 26de020aae7b..907fefde2572 100644 --- a/mm/balloon_compaction.c +++ b/mm/balloon_compaction.c @@ -58,7 +58,7 @@ EXPORT_SYMBOL_GPL(balloon_page_list_enqueue); /** * balloon_page_list_dequeue() - removes pages from balloon's page list and * returns a list of the pages. - * @b_dev_info: balloon device decriptor where we will grab a page from. + * @b_dev_info: balloon device descriptor where we will grab a page from. * @pages: pointer to the list of pages that would be returned to the caller. * @n_req_pages: number of requested pages. * @@ -157,7 +157,7 @@ EXPORT_SYMBOL_GPL(balloon_page_enqueue); /* * balloon_page_dequeue - removes a page from balloon's page list and returns * its address to allow the driver to release the page. - * @b_dev_info: balloon device decriptor where we will grab a page from. + * @b_dev_info: balloon device descriptor where we will grab a page from. * * Driver must call this function to properly dequeue a previously enqueued page * before definitively releasing it back to the guest system. @@ -24,7 +24,6 @@ #include <linux/memblock.h> #include <linux/err.h> #include <linux/mm.h> -#include <linux/mutex.h> #include <linux/sizes.h> #include <linux/slab.h> #include <linux/log2.h> @@ -80,16 +79,17 @@ static unsigned long cma_bitmap_pages_to_bits(const struct cma *cma, } static void cma_clear_bitmap(struct cma *cma, unsigned long pfn, - unsigned int count) + unsigned long count) { unsigned long bitmap_no, bitmap_count; + unsigned long flags; bitmap_no = (pfn - cma->base_pfn) >> cma->order_per_bit; bitmap_count = cma_bitmap_pages_to_bits(cma, count); - mutex_lock(&cma->lock); + spin_lock_irqsave(&cma->lock, flags); bitmap_clear(cma->bitmap, bitmap_no, bitmap_count); - mutex_unlock(&cma->lock); + spin_unlock_irqrestore(&cma->lock, flags); } static void __init cma_activate_area(struct cma *cma) @@ -118,7 +118,7 @@ static void __init cma_activate_area(struct cma *cma) pfn += pageblock_nr_pages) init_cma_reserved_pageblock(pfn_to_page(pfn)); - mutex_init(&cma->lock); + spin_lock_init(&cma->lock); #ifdef CONFIG_CMA_DEBUGFS INIT_HLIST_HEAD(&cma->mem_head); @@ -392,7 +392,7 @@ static void cma_debug_show_areas(struct cma *cma) unsigned long nr_part, nr_total = 0; unsigned long nbits = cma_bitmap_maxno(cma); - mutex_lock(&cma->lock); + spin_lock_irq(&cma->lock); pr_info("number of available pages: "); for (;;) { next_zero_bit = find_next_zero_bit(cma->bitmap, nbits, start); @@ -407,7 +407,7 @@ static void cma_debug_show_areas(struct cma *cma) start = next_zero_bit + nr_zero; } pr_cont("=> %lu free of %lu total pages\n", nr_total, cma->count); - mutex_unlock(&cma->lock); + spin_unlock_irq(&cma->lock); } #else static inline void cma_debug_show_areas(struct cma *cma) { } @@ -423,25 +423,27 @@ static inline void cma_debug_show_areas(struct cma *cma) { } * This function allocates part of contiguous memory on specific * contiguous memory area. */ -struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, - bool no_warn) +struct page *cma_alloc(struct cma *cma, unsigned long count, + unsigned int align, bool no_warn) { unsigned long mask, offset; unsigned long pfn = -1; unsigned long start = 0; unsigned long bitmap_maxno, bitmap_no, bitmap_count; - size_t i; + unsigned long i; struct page *page = NULL; int ret = -ENOMEM; if (!cma || !cma->count || !cma->bitmap) - return NULL; + goto out; - pr_debug("%s(cma %p, count %zu, align %d)\n", __func__, (void *)cma, + pr_debug("%s(cma %p, count %lu, align %d)\n", __func__, (void *)cma, count, align); if (!count) - return NULL; + goto out; + + trace_cma_alloc_start(cma->name, count, align); mask = cma_bitmap_aligned_mask(cma, align); offset = cma_bitmap_aligned_offset(cma, align); @@ -449,15 +451,15 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, bitmap_count = cma_bitmap_pages_to_bits(cma, count); if (bitmap_count > bitmap_maxno) - return NULL; + goto out; for (;;) { - mutex_lock(&cma->lock); + spin_lock_irq(&cma->lock); bitmap_no = bitmap_find_next_zero_area_off(cma->bitmap, bitmap_maxno, start, bitmap_count, mask, offset); if (bitmap_no >= bitmap_maxno) { - mutex_unlock(&cma->lock); + spin_unlock_irq(&cma->lock); break; } bitmap_set(cma->bitmap, bitmap_no, bitmap_count); @@ -466,7 +468,7 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, * our exclusive use. If the migration fails we will take the * lock again and unmark it. */ - mutex_unlock(&cma->lock); + spin_unlock_irq(&cma->lock); pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit); ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA, @@ -483,11 +485,14 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, pr_debug("%s(): memory range at %p is busy, retrying\n", __func__, pfn_to_page(pfn)); + + trace_cma_alloc_busy_retry(cma->name, pfn, pfn_to_page(pfn), + count, align); /* try again with a bit different memory target */ start = bitmap_no + mask + 1; } - trace_cma_alloc(pfn, page, count, align); + trace_cma_alloc_finish(cma->name, pfn, page, count, align); /* * CMA can allocate multiple page blocks, which results in different @@ -500,12 +505,22 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, } if (ret && !no_warn) { - pr_err("%s: %s: alloc failed, req-size: %zu pages, ret: %d\n", - __func__, cma->name, count, ret); + pr_err_ratelimited("%s: %s: alloc failed, req-size: %lu pages, ret: %d\n", + __func__, cma->name, count, ret); cma_debug_show_areas(cma); } pr_debug("%s(): returned %p\n", __func__, page); +out: + if (page) { + count_vm_event(CMA_ALLOC_SUCCESS); + cma_sysfs_account_success_pages(cma, count); + } else { + count_vm_event(CMA_ALLOC_FAIL); + if (cma) + cma_sysfs_account_fail_pages(cma, count); + } + return page; } @@ -519,14 +534,15 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, * It returns false when provided pages do not belong to contiguous area and * true otherwise. */ -bool cma_release(struct cma *cma, const struct page *pages, unsigned int count) +bool cma_release(struct cma *cma, const struct page *pages, + unsigned long count) { unsigned long pfn; if (!cma || !pages) return false; - pr_debug("%s(page %p, count %u)\n", __func__, (void *)pages, count); + pr_debug("%s(page %p, count %lu)\n", __func__, (void *)pages, count); pfn = page_to_pfn(pages); @@ -537,7 +553,7 @@ bool cma_release(struct cma *cma, const struct page *pages, unsigned int count) free_contig_range(pfn, count); cma_clear_bitmap(cma, pfn, count); - trace_cma_release(pfn, pages, count); + trace_cma_release(cma->name, pfn, pages, count); return true; } @@ -3,19 +3,33 @@ #define __MM_CMA_H__ #include <linux/debugfs.h> +#include <linux/kobject.h> + +struct cma_kobject { + struct kobject kobj; + struct cma *cma; +}; struct cma { unsigned long base_pfn; unsigned long count; unsigned long *bitmap; unsigned int order_per_bit; /* Order of pages represented by one bit */ - struct mutex lock; + spinlock_t lock; #ifdef CONFIG_CMA_DEBUGFS struct hlist_head mem_head; spinlock_t mem_head_lock; struct debugfs_u32_array dfs_bitmap; #endif char name[CMA_MAX_NAME]; +#ifdef CONFIG_CMA_SYSFS + /* the number of CMA page successful allocations */ + atomic64_t nr_pages_succeeded; + /* the number of CMA page allocation failures */ + atomic64_t nr_pages_failed; + /* kobject requires dynamic object */ + struct cma_kobject *cma_kobj; +#endif }; extern struct cma cma_areas[MAX_CMA_AREAS]; @@ -26,4 +40,13 @@ static inline unsigned long cma_bitmap_maxno(struct cma *cma) return cma->count >> cma->order_per_bit; } +#ifdef CONFIG_CMA_SYSFS +void cma_sysfs_account_success_pages(struct cma *cma, unsigned long nr_pages); +void cma_sysfs_account_fail_pages(struct cma *cma, unsigned long nr_pages); +#else +static inline void cma_sysfs_account_success_pages(struct cma *cma, + unsigned long nr_pages) {}; +static inline void cma_sysfs_account_fail_pages(struct cma *cma, + unsigned long nr_pages) {}; +#endif #endif diff --git a/mm/cma_debug.c b/mm/cma_debug.c index d5bf8aa34fdc..2e7704955f4f 100644 --- a/mm/cma_debug.c +++ b/mm/cma_debug.c @@ -36,10 +36,10 @@ static int cma_used_get(void *data, u64 *val) struct cma *cma = data; unsigned long used; - mutex_lock(&cma->lock); + spin_lock_irq(&cma->lock); /* pages counter is smaller than sizeof(int) */ used = bitmap_weight(cma->bitmap, (int)cma_bitmap_maxno(cma)); - mutex_unlock(&cma->lock); + spin_unlock_irq(&cma->lock); *val = (u64)used << cma->order_per_bit; return 0; @@ -53,7 +53,7 @@ static int cma_maxchunk_get(void *data, u64 *val) unsigned long start, end = 0; unsigned long bitmap_maxno = cma_bitmap_maxno(cma); - mutex_lock(&cma->lock); + spin_lock_irq(&cma->lock); for (;;) { start = find_next_zero_bit(cma->bitmap, bitmap_maxno, end); if (start >= bitmap_maxno) @@ -61,7 +61,7 @@ static int cma_maxchunk_get(void *data, u64 *val) end = find_next_bit(cma->bitmap, bitmap_maxno, start); maxchunk = max(end - start, maxchunk); } - mutex_unlock(&cma->lock); + spin_unlock_irq(&cma->lock); *val = (u64)maxchunk << cma->order_per_bit; return 0; diff --git a/mm/cma_sysfs.c b/mm/cma_sysfs.c new file mode 100644 index 000000000000..eb2f39caff59 --- /dev/null +++ b/mm/cma_sysfs.c @@ -0,0 +1,112 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * CMA SysFS Interface + * + * Copyright (c) 2021 Minchan Kim <minchan@kernel.org> + */ + +#include <linux/cma.h> +#include <linux/kernel.h> +#include <linux/slab.h> + +#include "cma.h" + +#define CMA_ATTR_RO(_name) \ + static struct kobj_attribute _name##_attr = __ATTR_RO(_name) + +void cma_sysfs_account_success_pages(struct cma *cma, unsigned long nr_pages) +{ + atomic64_add(nr_pages, &cma->nr_pages_succeeded); +} + +void cma_sysfs_account_fail_pages(struct cma *cma, unsigned long nr_pages) +{ + atomic64_add(nr_pages, &cma->nr_pages_failed); +} + +static inline struct cma *cma_from_kobj(struct kobject *kobj) +{ + return container_of(kobj, struct cma_kobject, kobj)->cma; +} + +static ssize_t alloc_pages_success_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct cma *cma = cma_from_kobj(kobj); + + return sysfs_emit(buf, "%llu\n", + atomic64_read(&cma->nr_pages_succeeded)); +} +CMA_ATTR_RO(alloc_pages_success); + +static ssize_t alloc_pages_fail_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct cma *cma = cma_from_kobj(kobj); + + return sysfs_emit(buf, "%llu\n", atomic64_read(&cma->nr_pages_failed)); +} +CMA_ATTR_RO(alloc_pages_fail); + +static void cma_kobj_release(struct kobject *kobj) +{ + struct cma *cma = cma_from_kobj(kobj); + struct cma_kobject *cma_kobj = cma->cma_kobj; + + kfree(cma_kobj); + cma->cma_kobj = NULL; +} + +static struct attribute *cma_attrs[] = { + &alloc_pages_success_attr.attr, + &alloc_pages_fail_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(cma); + +static struct kobj_type cma_ktype = { + .release = cma_kobj_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = cma_groups, +}; + +static int __init cma_sysfs_init(void) +{ + struct kobject *cma_kobj_root; + struct cma_kobject *cma_kobj; + struct cma *cma; + int i, err; + + cma_kobj_root = kobject_create_and_add("cma", mm_kobj); + if (!cma_kobj_root) + return -ENOMEM; + + for (i = 0; i < cma_area_count; i++) { + cma_kobj = kzalloc(sizeof(*cma_kobj), GFP_KERNEL); + if (!cma_kobj) { + err = -ENOMEM; + goto out; + } + + cma = &cma_areas[i]; + cma->cma_kobj = cma_kobj; + cma_kobj->cma = cma; + err = kobject_init_and_add(&cma_kobj->kobj, &cma_ktype, + cma_kobj_root, "%s", cma->name); + if (err) { + kobject_put(&cma_kobj->kobj); + goto out; + } + } + + return 0; +out: + while (--i >= 0) { + cma = &cma_areas[i]; + kobject_put(&cma->cma_kobj->kobj); + } + kobject_put(cma_kobj_root); + + return err; +} +subsys_initcall(cma_sysfs_init); diff --git a/mm/compaction.c b/mm/compaction.c index e04f4476e68e..84fde270ae74 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -787,15 +787,14 @@ static bool too_many_isolated(pg_data_t *pgdat) * * Isolate all pages that can be migrated from the range specified by * [low_pfn, end_pfn). The range is expected to be within same pageblock. - * Returns zero if there is a fatal signal pending, otherwise PFN of the - * first page that was not scanned (which may be both less, equal to or more - * than end_pfn). + * Returns errno, like -EAGAIN or -EINTR in case e.g signal pending or congestion, + * -ENOMEM in case we could not allocate a page, or 0. + * cc->migrate_pfn will contain the next pfn to scan. * * The pages are isolated on cc->migratepages list (not required to be empty), - * and cc->nr_migratepages is updated accordingly. The cc->migrate_pfn field - * is neither read nor updated. + * and cc->nr_migratepages is updated accordingly. */ -static unsigned long +static int isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn, isolate_mode_t isolate_mode) { @@ -809,6 +808,9 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, bool skip_on_failure = false; unsigned long next_skip_pfn = 0; bool skip_updated = false; + int ret = 0; + + cc->migrate_pfn = low_pfn; /* * Ensure that there are not too many pages isolated from the LRU @@ -818,16 +820,16 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, while (unlikely(too_many_isolated(pgdat))) { /* stop isolation if there are still pages not migrated */ if (cc->nr_migratepages) - return 0; + return -EAGAIN; /* async migration should just abort */ if (cc->mode == MIGRATE_ASYNC) - return 0; + return -EAGAIN; congestion_wait(BLK_RW_ASYNC, HZ/10); if (fatal_signal_pending(current)) - return 0; + return -EINTR; } cond_resched(); @@ -875,8 +877,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (fatal_signal_pending(current)) { cc->contended = true; + ret = -EINTR; - low_pfn = 0; goto fatal_pending; } @@ -904,6 +906,38 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, valid_page = page; } + if (PageHuge(page) && cc->alloc_contig) { + ret = isolate_or_dissolve_huge_page(page, &cc->migratepages); + + /* + * Fail isolation in case isolate_or_dissolve_huge_page() + * reports an error. In case of -ENOMEM, abort right away. + */ + if (ret < 0) { + /* Do not report -EBUSY down the chain */ + if (ret == -EBUSY) + ret = 0; + low_pfn += (1UL << compound_order(page)) - 1; + goto isolate_fail; + } + + if (PageHuge(page)) { + /* + * Hugepage was successfully isolated and placed + * on the cc->migratepages list. + */ + low_pfn += compound_nr(page) - 1; + goto isolate_success_no_list; + } + + /* + * Ok, the hugepage was dissolved. Now these pages are + * Buddy and cannot be re-allocated because they are + * isolated. Fall-through as the check below handles + * Buddy pages. + */ + } + /* * Skip if free. We read page order here without zone lock * which is generally unsafe, but the race window is small and @@ -1037,6 +1071,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, isolate_success: list_add(&page->lru, &cc->migratepages); +isolate_success_no_list: cc->nr_migratepages += compound_nr(page); nr_isolated += compound_nr(page); @@ -1063,7 +1098,7 @@ isolate_fail_put: put_page(page); isolate_fail: - if (!skip_on_failure) + if (!skip_on_failure && ret != -ENOMEM) continue; /* @@ -1089,6 +1124,9 @@ isolate_fail: */ next_skip_pfn += 1UL << cc->order; } + + if (ret == -ENOMEM) + break; } /* @@ -1130,7 +1168,9 @@ fatal_pending: if (nr_isolated) count_compact_events(COMPACTISOLATED, nr_isolated); - return low_pfn; + cc->migrate_pfn = low_pfn; + + return ret; } /** @@ -1139,15 +1179,15 @@ fatal_pending: * @start_pfn: The first PFN to start isolating. * @end_pfn: The one-past-last PFN. * - * Returns zero if isolation fails fatally due to e.g. pending signal. - * Otherwise, function returns one-past-the-last PFN of isolated page - * (which may be greater than end_pfn if end fell in a middle of a THP page). + * Returns -EAGAIN when contented, -EINTR in case of a signal pending, -ENOMEM + * in case we could not allocate a page, or 0. */ -unsigned long +int isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn, block_start_pfn, block_end_pfn; + int ret = 0; /* Scan block by block. First and last block may be incomplete */ pfn = start_pfn; @@ -1166,17 +1206,17 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, block_end_pfn, cc->zone)) continue; - pfn = isolate_migratepages_block(cc, pfn, block_end_pfn, - ISOLATE_UNEVICTABLE); + ret = isolate_migratepages_block(cc, pfn, block_end_pfn, + ISOLATE_UNEVICTABLE); - if (!pfn) + if (ret) break; if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX) break; } - return pfn; + return ret; } #endif /* CONFIG_COMPACTION || CONFIG_CMA */ @@ -1847,7 +1887,7 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc) */ for (; block_end_pfn <= cc->free_pfn; fast_find_block = false, - low_pfn = block_end_pfn, + cc->migrate_pfn = low_pfn = block_end_pfn, block_start_pfn = block_end_pfn, block_end_pfn += pageblock_nr_pages) { @@ -1889,10 +1929,8 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc) } /* Perform the isolation */ - low_pfn = isolate_migratepages_block(cc, low_pfn, - block_end_pfn, isolate_mode); - - if (!low_pfn) + if (isolate_migratepages_block(cc, low_pfn, block_end_pfn, + isolate_mode)) return ISOLATE_ABORT; /* @@ -1903,9 +1941,6 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc) break; } - /* Record where migration scanner will be restarted. */ - cc->migrate_pfn = low_pfn; - return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE; } @@ -1977,8 +2012,8 @@ static unsigned int fragmentation_score_wmark(pg_data_t *pgdat, bool low) unsigned int wmark_low; /* - * Cap the low watermak to avoid excessive compaction - * activity in case a user sets the proactivess tunable + * Cap the low watermark to avoid excessive compaction + * activity in case a user sets the proactiveness tunable * close to 100 (maximum). */ wmark_low = max(100U - sysctl_compaction_proactiveness, 5U); @@ -2319,7 +2354,8 @@ compact_zone(struct compact_control *cc, struct capture_control *capc) trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn, sync); - migrate_prep_local(); + /* lru_add_drain_all could be expensive with involving other CPUs */ + lru_add_drain(); while ((ret = compact_finished(cc)) == COMPACT_CONTINUE) { int err; @@ -2494,6 +2530,14 @@ static enum compact_result compact_zone_order(struct zone *zone, int order, */ WRITE_ONCE(current->capture_control, NULL); *capture = READ_ONCE(capc.page); + /* + * Technically, it is also possible that compaction is skipped but + * the page is still captured out of luck(IRQ came and freed the page). + * Returning COMPACT_SUCCESS in such cases helps in properly accounting + * the COMPACT[STALL|FAIL] when compaction is skipped. + */ + if (*capture) + ret = COMPACT_SUCCESS; return ret; } @@ -2657,9 +2701,6 @@ static void compact_nodes(void) compact_node(nid); } -/* The written value is actually unused, all memory is compacted */ -int sysctl_compact_memory; - /* * Tunable for proactive compaction. It determines how * aggressively the kernel should compact memory in the @@ -2844,7 +2885,7 @@ void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx) */ static int kcompactd(void *p) { - pg_data_t *pgdat = (pg_data_t*)p; + pg_data_t *pgdat = (pg_data_t *)p; struct task_struct *tsk = current; unsigned int proactive_defer = 0; diff --git a/mm/filemap.c b/mm/filemap.c index 5be57ba01d33..66f7e9fdfbc4 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -142,17 +142,6 @@ static void page_cache_delete(struct address_space *mapping, page->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ - - if (shadow) { - mapping->nrexceptional += nr; - /* - * Make sure the nrexceptional update is committed before - * the nrpages update so that final truncate racing - * with reclaim does not see both counters 0 at the - * same time and miss a shadow entry. - */ - smp_wmb(); - } mapping->nrpages -= nr; } @@ -629,9 +618,6 @@ EXPORT_SYMBOL(filemap_fdatawait_keep_errors); /* Returns true if writeback might be needed or already in progress. */ static bool mapping_needs_writeback(struct address_space *mapping) { - if (dax_mapping(mapping)) - return mapping->nrexceptional; - return mapping->nrpages; } @@ -925,8 +911,6 @@ noinline int __add_to_page_cache_locked(struct page *page, if (xas_error(&xas)) goto unlock; - if (old) - mapping->nrexceptional--; mapping->nrpages++; /* hugetlb pages do not participate in page cache accounting */ @@ -2771,7 +2755,7 @@ unsigned int seek_page_size(struct xa_state *xas, struct page *page) * entirely memory-based such as tmpfs, and filesystems which support * unwritten extents. * - * Return: The requested offset on successs, or -ENXIO if @whence specifies + * Return: The requested offset on success, or -ENXIO if @whence specifies * SEEK_DATA and there is no data after @start. There is an implicit hole * after @end - 1, so SEEK_HOLE returns @end if all the bytes between @start * and @end contain data. @@ -3283,7 +3267,7 @@ const struct vm_operations_struct generic_file_vm_ops = { /* This is used for a general mmap of a disk file */ -int generic_file_mmap(struct file * file, struct vm_area_struct * vma) +int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { struct address_space *mapping = file->f_mapping; @@ -3308,11 +3292,11 @@ vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } -int generic_file_mmap(struct file * file, struct vm_area_struct * vma) +int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { return -ENOSYS; } -int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma) +int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { return -ENOSYS; } @@ -3740,7 +3724,7 @@ EXPORT_SYMBOL(generic_perform_write); ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; - struct address_space * mapping = file->f_mapping; + struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t written = 0; ssize_t err; diff --git a/mm/frontswap.c b/mm/frontswap.c index 2183a56c7874..130e301c5ac0 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -60,16 +60,20 @@ static u64 frontswap_succ_stores; static u64 frontswap_failed_stores; static u64 frontswap_invalidates; -static inline void inc_frontswap_loads(void) { +static inline void inc_frontswap_loads(void) +{ data_race(frontswap_loads++); } -static inline void inc_frontswap_succ_stores(void) { +static inline void inc_frontswap_succ_stores(void) +{ data_race(frontswap_succ_stores++); } -static inline void inc_frontswap_failed_stores(void) { +static inline void inc_frontswap_failed_stores(void) +{ data_race(frontswap_failed_stores++); } -static inline void inc_frontswap_invalidates(void) { +static inline void inc_frontswap_invalidates(void) +{ data_race(frontswap_invalidates++); } #else @@ -87,11 +87,12 @@ __maybe_unused struct page *try_grab_compound_head(struct page *page, int orig_refs = refs; /* - * Can't do FOLL_LONGTERM + FOLL_PIN with CMA in the gup fast - * path, so fail and let the caller fall back to the slow path. + * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a + * right zone, so fail and let the caller fall back to the slow + * path. */ - if (unlikely(flags & FOLL_LONGTERM) && - is_migrate_cma_page(page)) + if (unlikely((flags & FOLL_LONGTERM) && + !is_pinnable_page(page))) return NULL; /* @@ -1527,7 +1528,7 @@ static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, { struct vm_area_struct *vma; unsigned long vm_flags; - int i; + long i; /* calculate required read or write permissions. * If FOLL_FORCE is set, we only require the "MAY" flags. @@ -1574,7 +1575,7 @@ finish_or_fault: * Returns NULL on any kind of failure - a hole must then be inserted into * the corefile, to preserve alignment with its headers; and also returns * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - - * allowing a hole to be left in the corefile to save diskspace. + * allowing a hole to be left in the corefile to save disk space. * * Called without mmap_lock (takes and releases the mmap_lock by itself). */ @@ -1600,112 +1601,92 @@ struct page *get_dump_page(unsigned long addr) } #endif /* CONFIG_ELF_CORE */ -#ifdef CONFIG_CMA -static long check_and_migrate_cma_pages(struct mm_struct *mm, - unsigned long start, - unsigned long nr_pages, - struct page **pages, - struct vm_area_struct **vmas, - unsigned int gup_flags) +#ifdef CONFIG_MIGRATION +/* + * Check whether all pages are pinnable, if so return number of pages. If some + * pages are not pinnable, migrate them, and unpin all pages. Return zero if + * pages were migrated, or if some pages were not successfully isolated. + * Return negative error if migration fails. + */ +static long check_and_migrate_movable_pages(unsigned long nr_pages, + struct page **pages, + unsigned int gup_flags) { unsigned long i; - unsigned long step; + unsigned long isolation_error_count = 0; bool drain_allow = true; - bool migrate_allow = true; - LIST_HEAD(cma_page_list); - long ret = nr_pages; + LIST_HEAD(movable_page_list); + long ret = 0; + struct page *prev_head = NULL; + struct page *head; struct migration_target_control mtc = { .nid = NUMA_NO_NODE, - .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_NOWARN, + .gfp_mask = GFP_USER | __GFP_NOWARN, }; -check_again: - for (i = 0; i < nr_pages;) { - - struct page *head = compound_head(pages[i]); - - /* - * gup may start from a tail page. Advance step by the left - * part. - */ - step = compound_nr(head) - (pages[i] - head); + for (i = 0; i < nr_pages; i++) { + head = compound_head(pages[i]); + if (head == prev_head) + continue; + prev_head = head; /* - * If we get a page from the CMA zone, since we are going to - * be pinning these entries, we might as well move them out - * of the CMA zone if possible. + * If we get a movable page, since we are going to be pinning + * these entries, try to move them out if possible. */ - if (is_migrate_cma_page(head)) { - if (PageHuge(head)) - isolate_huge_page(head, &cma_page_list); - else { + if (!is_pinnable_page(head)) { + if (PageHuge(head)) { + if (!isolate_huge_page(head, &movable_page_list)) + isolation_error_count++; + } else { if (!PageLRU(head) && drain_allow) { lru_add_drain_all(); drain_allow = false; } - if (!isolate_lru_page(head)) { - list_add_tail(&head->lru, &cma_page_list); - mod_node_page_state(page_pgdat(head), - NR_ISOLATED_ANON + - page_is_file_lru(head), - thp_nr_pages(head)); + if (isolate_lru_page(head)) { + isolation_error_count++; + continue; } + list_add_tail(&head->lru, &movable_page_list); + mod_node_page_state(page_pgdat(head), + NR_ISOLATED_ANON + + page_is_file_lru(head), + thp_nr_pages(head)); } } - - i += step; } - if (!list_empty(&cma_page_list)) { - /* - * drop the above get_user_pages reference. - */ - if (gup_flags & FOLL_PIN) - unpin_user_pages(pages, nr_pages); - else - for (i = 0; i < nr_pages; i++) - put_page(pages[i]); - - if (migrate_pages(&cma_page_list, alloc_migration_target, NULL, - (unsigned long)&mtc, MIGRATE_SYNC, MR_CONTIG_RANGE)) { - /* - * some of the pages failed migration. Do get_user_pages - * without migration. - */ - migrate_allow = false; + /* + * If list is empty, and no isolation errors, means that all pages are + * in the correct zone. + */ + if (list_empty(&movable_page_list) && !isolation_error_count) + return nr_pages; - if (!list_empty(&cma_page_list)) - putback_movable_pages(&cma_page_list); - } - /* - * We did migrate all the pages, Try to get the page references - * again migrating any new CMA pages which we failed to isolate - * earlier. - */ - ret = __get_user_pages_locked(mm, start, nr_pages, - pages, vmas, NULL, - gup_flags); - - if ((ret > 0) && migrate_allow) { - nr_pages = ret; - drain_allow = true; - goto check_again; - } + if (gup_flags & FOLL_PIN) { + unpin_user_pages(pages, nr_pages); + } else { + for (i = 0; i < nr_pages; i++) + put_page(pages[i]); + } + if (!list_empty(&movable_page_list)) { + ret = migrate_pages(&movable_page_list, alloc_migration_target, + NULL, (unsigned long)&mtc, MIGRATE_SYNC, + MR_LONGTERM_PIN); + if (ret && !list_empty(&movable_page_list)) + putback_movable_pages(&movable_page_list); } - return ret; + return ret > 0 ? -ENOMEM : ret; } #else -static long check_and_migrate_cma_pages(struct mm_struct *mm, - unsigned long start, - unsigned long nr_pages, - struct page **pages, - struct vm_area_struct **vmas, - unsigned int gup_flags) +static long check_and_migrate_movable_pages(unsigned long nr_pages, + struct page **pages, + unsigned int gup_flags) { return nr_pages; } -#endif /* CONFIG_CMA */ +#endif /* CONFIG_MIGRATION */ /* * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which @@ -1718,21 +1699,22 @@ static long __gup_longterm_locked(struct mm_struct *mm, struct vm_area_struct **vmas, unsigned int gup_flags) { - unsigned long flags = 0; + unsigned int flags; long rc; - if (gup_flags & FOLL_LONGTERM) - flags = memalloc_nocma_save(); - - rc = __get_user_pages_locked(mm, start, nr_pages, pages, vmas, NULL, - gup_flags); + if (!(gup_flags & FOLL_LONGTERM)) + return __get_user_pages_locked(mm, start, nr_pages, pages, vmas, + NULL, gup_flags); + flags = memalloc_pin_save(); + do { + rc = __get_user_pages_locked(mm, start, nr_pages, pages, vmas, + NULL, gup_flags); + if (rc <= 0) + break; + rc = check_and_migrate_movable_pages(rc, pages, gup_flags); + } while (!rc); + memalloc_pin_restore(flags); - if (gup_flags & FOLL_LONGTERM) { - if (rc > 0) - rc = check_and_migrate_cma_pages(mm, start, rc, pages, - vmas, gup_flags); - memalloc_nocma_restore(flags); - } return rc; } diff --git a/mm/gup_test.c b/mm/gup_test.c index e3cf78e5873e..d974dec19e1c 100644 --- a/mm/gup_test.c +++ b/mm/gup_test.c @@ -52,6 +52,12 @@ static void verify_dma_pinned(unsigned int cmd, struct page **pages, dump_page(page, "gup_test failure"); break; + } else if (cmd == PIN_LONGTERM_BENCHMARK && + WARN(!is_pinnable_page(page), + "pages[%lu] is NOT pinnable but pinned\n", + i)) { + dump_page(page, "gup_test failure"); + break; } } break; @@ -94,7 +100,7 @@ static int __gup_test_ioctl(unsigned int cmd, { ktime_t start_time, end_time; unsigned long i, nr_pages, addr, next; - int nr; + long nr; struct page **pages; int ret = 0; bool needs_mmap_lock = @@ -126,37 +132,34 @@ static int __gup_test_ioctl(unsigned int cmd, nr = (next - addr) / PAGE_SIZE; } - /* Filter out most gup flags: only allow a tiny subset here: */ - gup->flags &= FOLL_WRITE; - switch (cmd) { case GUP_FAST_BENCHMARK: - nr = get_user_pages_fast(addr, nr, gup->flags, + nr = get_user_pages_fast(addr, nr, gup->gup_flags, pages + i); break; case GUP_BASIC_TEST: - nr = get_user_pages(addr, nr, gup->flags, pages + i, + nr = get_user_pages(addr, nr, gup->gup_flags, pages + i, NULL); break; case PIN_FAST_BENCHMARK: - nr = pin_user_pages_fast(addr, nr, gup->flags, + nr = pin_user_pages_fast(addr, nr, gup->gup_flags, pages + i); break; case PIN_BASIC_TEST: - nr = pin_user_pages(addr, nr, gup->flags, pages + i, + nr = pin_user_pages(addr, nr, gup->gup_flags, pages + i, NULL); break; case PIN_LONGTERM_BENCHMARK: nr = pin_user_pages(addr, nr, - gup->flags | FOLL_LONGTERM, + gup->gup_flags | FOLL_LONGTERM, pages + i, NULL); break; case DUMP_USER_PAGES_TEST: - if (gup->flags & GUP_TEST_FLAG_DUMP_PAGES_USE_PIN) - nr = pin_user_pages(addr, nr, gup->flags, + if (gup->test_flags & GUP_TEST_FLAG_DUMP_PAGES_USE_PIN) + nr = pin_user_pages(addr, nr, gup->gup_flags, pages + i, NULL); else - nr = get_user_pages(addr, nr, gup->flags, + nr = get_user_pages(addr, nr, gup->gup_flags, pages + i, NULL); break; default: @@ -187,7 +190,7 @@ static int __gup_test_ioctl(unsigned int cmd, start_time = ktime_get(); - put_back_pages(cmd, pages, nr_pages, gup->flags); + put_back_pages(cmd, pages, nr_pages, gup->test_flags); end_time = ktime_get(); gup->put_delta_usec = ktime_us_delta(end_time, start_time); diff --git a/mm/gup_test.h b/mm/gup_test.h index 90a6713d50eb..887ac1d5f5bc 100644 --- a/mm/gup_test.h +++ b/mm/gup_test.h @@ -21,7 +21,8 @@ struct gup_test { __u64 addr; __u64 size; __u32 nr_pages_per_call; - __u32 flags; + __u32 gup_flags; + __u32 test_flags; /* * Each non-zero entry is the number of the page (1-based: first page is * page 1, so that zero entries mean "do nothing") from the .addr base. diff --git a/mm/highmem.c b/mm/highmem.c index 6ef8f5e05e7e..4fb51d735aa6 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -104,7 +104,7 @@ static inline wait_queue_head_t *get_pkmap_wait_queue_head(unsigned int color) atomic_long_t _totalhigh_pages __read_mostly; EXPORT_SYMBOL(_totalhigh_pages); -unsigned int __nr_free_highpages (void) +unsigned int __nr_free_highpages(void) { struct zone *zone; unsigned int pages = 0; @@ -120,7 +120,7 @@ unsigned int __nr_free_highpages (void) static int pkmap_count[LAST_PKMAP]; static __cacheline_aligned_in_smp DEFINE_SPINLOCK(kmap_lock); -pte_t * pkmap_page_table; +pte_t *pkmap_page_table; /* * Most architectures have no use for kmap_high_get(), so let's abstract @@ -147,6 +147,7 @@ struct page *__kmap_to_page(void *vaddr) if (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) { int i = PKMAP_NR(addr); + return pte_page(pkmap_page_table[i]); } @@ -278,9 +279,8 @@ void *kmap_high(struct page *page) pkmap_count[PKMAP_NR(vaddr)]++; BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 2); unlock_kmap(); - return (void*) vaddr; + return (void *) vaddr; } - EXPORT_SYMBOL(kmap_high); #ifdef ARCH_NEEDS_KMAP_HIGH_GET @@ -305,7 +305,7 @@ void *kmap_high_get(struct page *page) pkmap_count[PKMAP_NR(vaddr)]++; } unlock_kmap_any(flags); - return (void*) vaddr; + return (void *) vaddr; } #endif @@ -519,7 +519,7 @@ void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot) /* * Disable migration so resulting virtual address is stable - * accross preemption. + * across preemption. */ migrate_disable(); preempt_disable(); @@ -737,7 +737,6 @@ done: spin_unlock_irqrestore(&pas->lock, flags); return ret; } - EXPORT_SYMBOL(page_address); /** diff --git a/mm/huge_memory.c b/mm/huge_memory.c index ae907a9c2050..63ed6b25deaa 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -7,6 +7,7 @@ #include <linux/mm.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/highmem.h> @@ -77,18 +78,18 @@ bool transparent_hugepage_enabled(struct vm_area_struct *vma) return false; } -static struct page *get_huge_zero_page(void) +static bool get_huge_zero_page(void) { struct page *zero_page; retry: if (likely(atomic_inc_not_zero(&huge_zero_refcount))) - return READ_ONCE(huge_zero_page); + return true; zero_page = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE, HPAGE_PMD_ORDER); if (!zero_page) { count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED); - return NULL; + return false; } count_vm_event(THP_ZERO_PAGE_ALLOC); preempt_disable(); @@ -101,7 +102,7 @@ retry: /* We take additional reference here. It will be put back by shrinker */ atomic_set(&huge_zero_refcount, 2); preempt_enable(); - return READ_ONCE(huge_zero_page); + return true; } static void put_huge_zero_page(void) @@ -624,14 +625,12 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, /* Deliver the page fault to userland */ if (userfaultfd_missing(vma)) { - vm_fault_t ret2; - spin_unlock(vmf->ptl); put_page(page); pte_free(vma->vm_mm, pgtable); - ret2 = handle_userfault(vmf, VM_UFFD_MISSING); - VM_BUG_ON(ret2 & VM_FAULT_FALLBACK); - return ret2; + ret = handle_userfault(vmf, VM_UFFD_MISSING); + VM_BUG_ON(ret & VM_FAULT_FALLBACK); + return ret; } entry = mk_huge_pmd(page, vma->vm_page_prot); @@ -1293,7 +1292,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) } page = pmd_page(orig_pmd); - VM_BUG_ON_PAGE(!PageCompound(page) || !PageHead(page), page); + VM_BUG_ON_PAGE(!PageHead(page), page); /* Lock page for reuse_swap_page() */ if (!trylock_page(page)) { @@ -1464,12 +1463,6 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) */ page_locked = trylock_page(page); target_nid = mpol_misplaced(page, vma, haddr); - if (target_nid == NUMA_NO_NODE) { - /* If the page was locked, there are no parallel migrations */ - if (page_locked) - goto clear_pmdnuma; - } - /* Migration could have started since the pmd_trans_migrating check */ if (!page_locked) { page_nid = NUMA_NO_NODE; @@ -1478,6 +1471,11 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) spin_unlock(vmf->ptl); put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE); goto out; + } else if (target_nid == NUMA_NO_NODE) { + /* There are no parallel migrations and page is in the right + * node. Clear the numa hinting info in this pmd. + */ + goto clear_pmdnuma; } /* @@ -1696,7 +1694,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, VM_BUG_ON(!is_pmd_migration_entry(orig_pmd)); entry = pmd_to_swp_entry(orig_pmd); - page = pfn_to_page(swp_offset(entry)); + page = migration_entry_to_page(entry); flush_needed = 0; } else WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!"); @@ -1794,8 +1792,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, /* * Returns * - 0 if PMD could not be locked - * - 1 if PMD was locked but protections unchange and TLB flush unnecessary - * - HPAGE_PMD_NR is protections changed and TLB flush necessary + * - 1 if PMD was locked but protections unchanged and TLB flush unnecessary + * - HPAGE_PMD_NR if protections changed and TLB flush necessary */ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, unsigned long cp_flags) @@ -2104,7 +2102,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, swp_entry_t entry; entry = pmd_to_swp_entry(old_pmd); - page = pfn_to_page(swp_offset(entry)); + page = migration_entry_to_page(entry); write = is_write_migration_entry(entry); young = false; soft_dirty = pmd_swp_soft_dirty(old_pmd); @@ -2303,44 +2301,38 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, __split_huge_pmd(vma, pmd, address, freeze, page); } +static inline void split_huge_pmd_if_needed(struct vm_area_struct *vma, unsigned long address) +{ + /* + * If the new address isn't hpage aligned and it could previously + * contain an hugepage: check if we need to split an huge pmd. + */ + if (!IS_ALIGNED(address, HPAGE_PMD_SIZE) && + range_in_vma(vma, ALIGN_DOWN(address, HPAGE_PMD_SIZE), + ALIGN(address, HPAGE_PMD_SIZE))) + split_huge_pmd_address(vma, address, false, NULL); +} + void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next) { - /* - * If the new start address isn't hpage aligned and it could - * previously contain an hugepage: check if we need to split - * an huge pmd. - */ - if (start & ~HPAGE_PMD_MASK && - (start & HPAGE_PMD_MASK) >= vma->vm_start && - (start & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end) - split_huge_pmd_address(vma, start, false, NULL); + /* Check if we need to split start first. */ + split_huge_pmd_if_needed(vma, start); - /* - * If the new end address isn't hpage aligned and it could - * previously contain an hugepage: check if we need to split - * an huge pmd. - */ - if (end & ~HPAGE_PMD_MASK && - (end & HPAGE_PMD_MASK) >= vma->vm_start && - (end & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end) - split_huge_pmd_address(vma, end, false, NULL); + /* Check if we need to split end next. */ + split_huge_pmd_if_needed(vma, end); /* - * If we're also updating the vma->vm_next->vm_start, if the new - * vm_next->vm_start isn't hpage aligned and it could previously - * contain an hugepage: check if we need to split an huge pmd. + * If we're also updating the vma->vm_next->vm_start, + * check if we need to split it. */ if (adjust_next > 0) { struct vm_area_struct *next = vma->vm_next; unsigned long nstart = next->vm_start; nstart += adjust_next; - if (nstart & ~HPAGE_PMD_MASK && - (nstart & HPAGE_PMD_MASK) >= next->vm_start && - (nstart & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= next->vm_end) - split_huge_pmd_address(next, nstart, false, NULL); + split_huge_pmd_if_needed(next, nstart); } } @@ -2477,7 +2469,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, xa_lock(&swap_cache->i_pages); } - /* lock lru list/PageCompound, ref freezed by page_ref_freeze */ + /* lock lru list/PageCompound, ref frozen by page_ref_freeze */ lruvec = lock_page_lruvec(head); for (i = nr - 1; i >= 1; i--) { @@ -2838,8 +2830,8 @@ void deferred_split_huge_page(struct page *page) ds_queue->split_queue_len++; #ifdef CONFIG_MEMCG if (memcg) - memcg_set_shrinker_bit(memcg, page_to_nid(page), - deferred_split_shrinker.id); + set_shrinker_bit(memcg, page_to_nid(page), + deferred_split_shrinker.id); #endif } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); @@ -2924,16 +2916,14 @@ static struct shrinker deferred_split_shrinker = { }; #ifdef CONFIG_DEBUG_FS -static int split_huge_pages_set(void *data, u64 val) +static void split_huge_pages_all(void) { struct zone *zone; struct page *page; unsigned long pfn, max_zone_pfn; unsigned long total = 0, split = 0; - if (val != 1) - return -EINVAL; - + pr_debug("Split all THPs\n"); for_each_populated_zone(zone) { max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) { @@ -2957,15 +2947,243 @@ static int split_huge_pages_set(void *data, u64 val) unlock_page(page); next: put_page(page); + cond_resched(); } } - pr_info("%lu of %lu THP split\n", split, total); + pr_debug("%lu of %lu THP split\n", split, total); +} - return 0; +static inline bool vma_not_suitable_for_thp_split(struct vm_area_struct *vma) +{ + return vma_is_special_huge(vma) || (vma->vm_flags & VM_IO) || + is_vm_hugetlb_page(vma); +} + +static int split_huge_pages_pid(int pid, unsigned long vaddr_start, + unsigned long vaddr_end) +{ + int ret = 0; + struct task_struct *task; + struct mm_struct *mm; + unsigned long total = 0, split = 0; + unsigned long addr; + + vaddr_start &= PAGE_MASK; + vaddr_end &= PAGE_MASK; + + /* Find the task_struct from pid */ + rcu_read_lock(); + task = find_task_by_vpid(pid); + if (!task) { + rcu_read_unlock(); + ret = -ESRCH; + goto out; + } + get_task_struct(task); + rcu_read_unlock(); + + /* Find the mm_struct */ + mm = get_task_mm(task); + put_task_struct(task); + + if (!mm) { + ret = -EINVAL; + goto out; + } + + pr_debug("Split huge pages in pid: %d, vaddr: [0x%lx - 0x%lx]\n", + pid, vaddr_start, vaddr_end); + + mmap_read_lock(mm); + /* + * always increase addr by PAGE_SIZE, since we could have a PTE page + * table filled with PTE-mapped THPs, each of which is distinct. + */ + for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) { + struct vm_area_struct *vma = find_vma(mm, addr); + unsigned int follflags; + struct page *page; + + if (!vma || addr < vma->vm_start) + break; + + /* skip special VMA and hugetlb VMA */ + if (vma_not_suitable_for_thp_split(vma)) { + addr = vma->vm_end; + continue; + } + + /* FOLL_DUMP to ignore special (like zero) pages */ + follflags = FOLL_GET | FOLL_DUMP; + page = follow_page(vma, addr, follflags); + + if (IS_ERR(page)) + continue; + if (!page) + continue; + + if (!is_transparent_hugepage(page)) + goto next; + + total++; + if (!can_split_huge_page(compound_head(page), NULL)) + goto next; + + if (!trylock_page(page)) + goto next; + + if (!split_huge_page(page)) + split++; + + unlock_page(page); +next: + put_page(page); + cond_resched(); + } + mmap_read_unlock(mm); + mmput(mm); + + pr_debug("%lu of %lu THP split\n", split, total); + +out: + return ret; +} + +static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, + pgoff_t off_end) +{ + struct filename *file; + struct file *candidate; + struct address_space *mapping; + int ret = -EINVAL; + pgoff_t index; + int nr_pages = 1; + unsigned long total = 0, split = 0; + + file = getname_kernel(file_path); + if (IS_ERR(file)) + return ret; + + candidate = file_open_name(file, O_RDONLY, 0); + if (IS_ERR(candidate)) + goto out; + + pr_debug("split file-backed THPs in file: %s, page offset: [0x%lx - 0x%lx]\n", + file_path, off_start, off_end); + + mapping = candidate->f_mapping; + + for (index = off_start; index < off_end; index += nr_pages) { + struct page *fpage = pagecache_get_page(mapping, index, + FGP_ENTRY | FGP_HEAD, 0); + + nr_pages = 1; + if (xa_is_value(fpage) || !fpage) + continue; + + if (!is_transparent_hugepage(fpage)) + goto next; + + total++; + nr_pages = thp_nr_pages(fpage); + + if (!trylock_page(fpage)) + goto next; + + if (!split_huge_page(fpage)) + split++; + + unlock_page(fpage); +next: + put_page(fpage); + cond_resched(); + } + + filp_close(candidate, NULL); + ret = 0; + + pr_debug("%lu of %lu file-backed THP split\n", split, total); +out: + putname(file); + return ret; } -DEFINE_DEBUGFS_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set, - "%llu\n"); + +#define MAX_INPUT_BUF_SZ 255 + +static ssize_t split_huge_pages_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppops) +{ + static DEFINE_MUTEX(split_debug_mutex); + ssize_t ret; + /* hold pid, start_vaddr, end_vaddr or file_path, off_start, off_end */ + char input_buf[MAX_INPUT_BUF_SZ]; + int pid; + unsigned long vaddr_start, vaddr_end; + + ret = mutex_lock_interruptible(&split_debug_mutex); + if (ret) + return ret; + + ret = -EFAULT; + + memset(input_buf, 0, MAX_INPUT_BUF_SZ); + if (copy_from_user(input_buf, buf, min_t(size_t, count, MAX_INPUT_BUF_SZ))) + goto out; + + input_buf[MAX_INPUT_BUF_SZ - 1] = '\0'; + + if (input_buf[0] == '/') { + char *tok; + char *buf = input_buf; + char file_path[MAX_INPUT_BUF_SZ]; + pgoff_t off_start = 0, off_end = 0; + size_t input_len = strlen(input_buf); + + tok = strsep(&buf, ","); + if (tok) { + strncpy(file_path, tok, MAX_INPUT_BUF_SZ); + } else { + ret = -EINVAL; + goto out; + } + + ret = sscanf(buf, "0x%lx,0x%lx", &off_start, &off_end); + if (ret != 2) { + ret = -EINVAL; + goto out; + } + ret = split_huge_pages_in_file(file_path, off_start, off_end); + if (!ret) + ret = input_len; + + goto out; + } + + ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end); + if (ret == 1 && pid == 1) { + split_huge_pages_all(); + ret = strlen(input_buf); + goto out; + } else if (ret != 3) { + ret = -EINVAL; + goto out; + } + + ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end); + if (!ret) + ret = strlen(input_buf); +out: + mutex_unlock(&split_debug_mutex); + return ret; + +} + +static const struct file_operations split_huge_pages_fops = { + .owner = THIS_MODULE, + .write = split_huge_pages_write, + .llseek = no_llseek, +}; static int __init split_huge_pages_debugfs(void) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6c72433bec1e..3db405dea3dc 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -39,7 +39,6 @@ #include <linux/hugetlb.h> #include <linux/hugetlb_cgroup.h> #include <linux/node.h> -#include <linux/userfaultfd_k.h> #include <linux/page_owner.h> #include "internal.h" @@ -94,9 +93,10 @@ static inline bool subpool_is_free(struct hugepage_subpool *spool) return true; } -static inline void unlock_or_release_subpool(struct hugepage_subpool *spool) +static inline void unlock_or_release_subpool(struct hugepage_subpool *spool, + unsigned long irq_flags) { - spin_unlock(&spool->lock); + spin_unlock_irqrestore(&spool->lock, irq_flags); /* If no pages are used, and no other handles to the subpool * remain, give up any reservations based on minimum size and @@ -135,10 +135,12 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, void hugepage_put_subpool(struct hugepage_subpool *spool) { - spin_lock(&spool->lock); + unsigned long flags; + + spin_lock_irqsave(&spool->lock, flags); BUG_ON(!spool->count); spool->count--; - unlock_or_release_subpool(spool); + unlock_or_release_subpool(spool, flags); } /* @@ -157,7 +159,7 @@ static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, if (!spool) return ret; - spin_lock(&spool->lock); + spin_lock_irq(&spool->lock); if (spool->max_hpages != -1) { /* maximum size accounting */ if ((spool->used_hpages + delta) <= spool->max_hpages) @@ -184,7 +186,7 @@ static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, } unlock_ret: - spin_unlock(&spool->lock); + spin_unlock_irq(&spool->lock); return ret; } @@ -198,11 +200,12 @@ static long hugepage_subpool_put_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; + unsigned long flags; if (!spool) return delta; - spin_lock(&spool->lock); + spin_lock_irqsave(&spool->lock, flags); if (spool->max_hpages != -1) /* maximum size accounting */ spool->used_hpages -= delta; @@ -223,7 +226,7 @@ static long hugepage_subpool_put_pages(struct hugepage_subpool *spool, * If hugetlbfs_put_super couldn't free spool due to an outstanding * quota reference, free it now. */ - unlock_or_release_subpool(spool); + unlock_or_release_subpool(spool, flags); return ret; } @@ -463,7 +466,7 @@ static int allocate_file_region_entries(struct resv_map *resv, resv->region_cache_count; /* At this point, we should have enough entries in the cache - * for all the existings adds_in_progress. We should only be + * for all the existing adds_in_progress. We should only be * needing to allocate for regions_needed. */ VM_BUG_ON(resv->region_cache_count < resv->adds_in_progress); @@ -553,7 +556,6 @@ retry: resv->adds_in_progress -= in_regions_needed; spin_unlock(&resv->lock); - VM_BUG_ON(add < 0); return add; } @@ -743,13 +745,20 @@ void hugetlb_fix_reserve_counts(struct inode *inode) { struct hugepage_subpool *spool = subpool_inode(inode); long rsv_adjust; + bool reserved = false; rsv_adjust = hugepage_subpool_get_pages(spool, 1); - if (rsv_adjust) { + if (rsv_adjust > 0) { struct hstate *h = hstate_inode(inode); - hugetlb_acct_memory(h, 1); + if (!hugetlb_acct_memory(h, 1)) + reserved = true; + } else if (!rsv_adjust) { + reserved = true; } + + if (!reserved) + pr_warn("hugetlb: Huge Page Reserved count may go negative.\n"); } /* @@ -1059,6 +1068,8 @@ static bool vma_has_reserves(struct vm_area_struct *vma, long chg) static void enqueue_huge_page(struct hstate *h, struct page *page) { int nid = page_to_nid(page); + + lockdep_assert_held(&hugetlb_lock); list_move(&page->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; @@ -1068,10 +1079,11 @@ static void enqueue_huge_page(struct hstate *h, struct page *page) static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid) { struct page *page; - bool nocma = !!(current->flags & PF_MEMALLOC_NOCMA); + bool pin = !!(current->flags & PF_MEMALLOC_PIN); + lockdep_assert_held(&hugetlb_lock); list_for_each_entry(page, &h->hugepage_freelists[nid], lru) { - if (nocma && is_migrate_cma_page(page)) + if (pin && !is_pinnable_page(page)) continue; if (PageHWPoison(page)) @@ -1205,7 +1217,7 @@ static int hstate_next_node_to_alloc(struct hstate *h, } /* - * helper for free_pool_huge_page() - return the previously saved + * helper for remove_pool_huge_page() - return the previously saved * node ["this node"] from which to free a huge page. Advance the * next node id whether or not we find a free huge page to free so * that the next attempt to free addresses the next node. @@ -1273,7 +1285,7 @@ static void free_gigantic_page(struct page *page, unsigned int order) static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { - unsigned long nr_pages = 1UL << huge_page_order(h); + unsigned long nr_pages = pages_per_huge_page(h); if (nid == NUMA_NO_NODE) nid = numa_mem_id(); @@ -1327,6 +1339,42 @@ static inline void destroy_compound_gigantic_page(struct page *page, unsigned int order) { } #endif +/* + * Remove hugetlb page from lists, and update dtor so that page appears + * as just a compound page. A reference is held on the page. + * + * Must be called with hugetlb lock held. + */ +static void remove_hugetlb_page(struct hstate *h, struct page *page, + bool adjust_surplus) +{ + int nid = page_to_nid(page); + + VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page); + VM_BUG_ON_PAGE(hugetlb_cgroup_from_page_rsvd(page), page); + + lockdep_assert_held(&hugetlb_lock); + if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) + return; + + list_del(&page->lru); + + if (HPageFreed(page)) { + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; + } + if (adjust_surplus) { + h->surplus_huge_pages--; + h->surplus_huge_pages_node[nid]--; + } + + set_page_refcounted(page); + set_compound_page_dtor(page, NULL_COMPOUND_DTOR); + + h->nr_huge_pages--; + h->nr_huge_pages_node[nid]--; +} + static void update_and_free_page(struct hstate *h, struct page *page) { int i; @@ -1335,8 +1383,6 @@ static void update_and_free_page(struct hstate *h, struct page *page) if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; - h->nr_huge_pages--; - h->nr_huge_pages_node[page_to_nid(page)]--; for (i = 0; i < pages_per_huge_page(h); i++, subpage = mem_map_next(subpage, page, i)) { subpage->flags &= ~(1 << PG_locked | 1 << PG_error | @@ -1344,24 +1390,24 @@ static void update_and_free_page(struct hstate *h, struct page *page) 1 << PG_active | 1 << PG_private | 1 << PG_writeback); } - VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page); - VM_BUG_ON_PAGE(hugetlb_cgroup_from_page_rsvd(page), page); - set_compound_page_dtor(page, NULL_COMPOUND_DTOR); - set_page_refcounted(page); if (hstate_is_gigantic(h)) { - /* - * Temporarily drop the hugetlb_lock, because - * we might block in free_gigantic_page(). - */ - spin_unlock(&hugetlb_lock); destroy_compound_gigantic_page(page, huge_page_order(h)); free_gigantic_page(page, huge_page_order(h)); - spin_lock(&hugetlb_lock); } else { __free_pages(page, huge_page_order(h)); } } +static void update_and_free_pages_bulk(struct hstate *h, struct list_head *list) +{ + struct page *page, *t_page; + + list_for_each_entry_safe(page, t_page, list, lru) { + update_and_free_page(h, page); + cond_resched(); + } +} + struct hstate *size_to_hstate(unsigned long size) { struct hstate *h; @@ -1373,7 +1419,7 @@ struct hstate *size_to_hstate(unsigned long size) return NULL; } -static void __free_huge_page(struct page *page) +void free_huge_page(struct page *page) { /* * Can't pass hstate in here because it is called from the @@ -1383,6 +1429,7 @@ static void __free_huge_page(struct page *page) int nid = page_to_nid(page); struct hugepage_subpool *spool = hugetlb_page_subpool(page); bool restore_reserve; + unsigned long flags; VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(page_mapcount(page), page); @@ -1411,7 +1458,7 @@ static void __free_huge_page(struct page *page) restore_reserve = true; } - spin_lock(&hugetlb_lock); + spin_lock_irqsave(&hugetlb_lock, flags); ClearHPageMigratable(page); hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h), page); @@ -1421,82 +1468,46 @@ static void __free_huge_page(struct page *page) h->resv_huge_pages++; if (HPageTemporary(page)) { - list_del(&page->lru); - ClearHPageTemporary(page); + remove_hugetlb_page(h, page, false); + spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_page(h, page); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ - list_del(&page->lru); + remove_hugetlb_page(h, page, true); + spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_page(h, page); - h->surplus_huge_pages--; - h->surplus_huge_pages_node[nid]--; } else { arch_clear_hugepage_flags(page); enqueue_huge_page(h, page); + spin_unlock_irqrestore(&hugetlb_lock, flags); } - spin_unlock(&hugetlb_lock); } /* - * As free_huge_page() can be called from a non-task context, we have - * to defer the actual freeing in a workqueue to prevent potential - * hugetlb_lock deadlock. - * - * free_hpage_workfn() locklessly retrieves the linked list of pages to - * be freed and frees them one-by-one. As the page->mapping pointer is - * going to be cleared in __free_huge_page() anyway, it is reused as the - * llist_node structure of a lockless linked list of huge pages to be freed. + * Must be called with the hugetlb lock held */ -static LLIST_HEAD(hpage_freelist); - -static void free_hpage_workfn(struct work_struct *work) +static void __prep_account_new_huge_page(struct hstate *h, int nid) { - struct llist_node *node; - struct page *page; - - node = llist_del_all(&hpage_freelist); - - while (node) { - page = container_of((struct address_space **)node, - struct page, mapping); - node = node->next; - __free_huge_page(page); - } -} -static DECLARE_WORK(free_hpage_work, free_hpage_workfn); - -void free_huge_page(struct page *page) -{ - /* - * Defer freeing if in non-task context to avoid hugetlb_lock deadlock. - */ - if (!in_task()) { - /* - * Only call schedule_work() if hpage_freelist is previously - * empty. Otherwise, schedule_work() had been called but the - * workfn hasn't retrieved the list yet. - */ - if (llist_add((struct llist_node *)&page->mapping, - &hpage_freelist)) - schedule_work(&free_hpage_work); - return; - } - - __free_huge_page(page); + lockdep_assert_held(&hugetlb_lock); + h->nr_huge_pages++; + h->nr_huge_pages_node[nid]++; } -static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) +static void __prep_new_huge_page(struct page *page) { INIT_LIST_HEAD(&page->lru); set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); hugetlb_set_page_subpool(page, NULL); set_hugetlb_cgroup(page, NULL); set_hugetlb_cgroup_rsvd(page, NULL); - spin_lock(&hugetlb_lock); - h->nr_huge_pages++; - h->nr_huge_pages_node[nid]++; - ClearHPageFreed(page); - spin_unlock(&hugetlb_lock); +} + +static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) +{ + __prep_new_huge_page(page); + spin_lock_irq(&hugetlb_lock); + __prep_account_new_huge_page(h, nid); + spin_unlock_irq(&hugetlb_lock); } static void prep_compound_gigantic_page(struct page *page, unsigned int order) @@ -1693,17 +1704,20 @@ static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, } /* - * Free huge page from pool from next node to free. - * Attempt to keep persistent huge pages more or less - * balanced over allowed nodes. + * Remove huge page from pool from next node to free. Attempt to keep + * persistent huge pages more or less balanced over allowed nodes. + * This routine only 'removes' the hugetlb page. The caller must make + * an additional call to free the page to low level allocators. * Called with hugetlb_lock locked. */ -static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, - bool acct_surplus) +static struct page *remove_pool_huge_page(struct hstate *h, + nodemask_t *nodes_allowed, + bool acct_surplus) { int nr_nodes, node; - int ret = 0; + struct page *page = NULL; + lockdep_assert_held(&hugetlb_lock); for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { /* * If we're returning unused surplus pages, only examine @@ -1711,23 +1725,14 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, */ if ((!acct_surplus || h->surplus_huge_pages_node[node]) && !list_empty(&h->hugepage_freelists[node])) { - struct page *page = - list_entry(h->hugepage_freelists[node].next, + page = list_entry(h->hugepage_freelists[node].next, struct page, lru); - list_del(&page->lru); - h->free_huge_pages--; - h->free_huge_pages_node[node]--; - if (acct_surplus) { - h->surplus_huge_pages--; - h->surplus_huge_pages_node[node]--; - } - update_and_free_page(h, page); - ret = 1; + remove_hugetlb_page(h, page, acct_surplus); break; } } - return ret; + return page; } /* @@ -1749,7 +1754,7 @@ retry: if (!PageHuge(page)) return 0; - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); if (!PageHuge(page)) { rc = 0; goto out; @@ -1758,7 +1763,6 @@ retry: if (!page_count(page)) { struct page *head = compound_head(page); struct hstate *h = page_hstate(head); - int nid = page_to_nid(head); if (h->free_huge_pages - h->resv_huge_pages == 0) goto out; @@ -1767,7 +1771,7 @@ retry: * when it is dissolved. */ if (unlikely(!HPageFreed(head))) { - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); cond_resched(); /* @@ -1789,15 +1793,14 @@ retry: SetPageHWPoison(page); ClearPageHWPoison(head); } - list_del(&head->lru); - h->free_huge_pages--; - h->free_huge_pages_node[nid]--; + remove_hugetlb_page(h, page, false); h->max_huge_pages--; + spin_unlock_irq(&hugetlb_lock); update_and_free_page(h, head); - rc = 0; + return 0; } out: - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); return rc; } @@ -1839,16 +1842,16 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, if (hstate_is_gigantic(h)) return NULL; - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) goto out_unlock; - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask, NULL); if (!page) return NULL; - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); /* * We could have raced with the pool size change. * Double check that and simply deallocate the new page @@ -1858,7 +1861,7 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, */ if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { SetHPageTemporary(page); - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); put_page(page); return NULL; } else { @@ -1867,7 +1870,7 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, } out_unlock: - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); return page; } @@ -1917,17 +1920,17 @@ struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h, struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask) { - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); if (h->free_huge_pages - h->resv_huge_pages > 0) { struct page *page; page = dequeue_huge_page_nodemask(h, gfp_mask, preferred_nid, nmask); if (page) { - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); return page; } } - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); return alloc_migrate_huge_page(h, gfp_mask, preferred_nid, nmask); } @@ -1964,6 +1967,7 @@ static int gather_surplus_pages(struct hstate *h, long delta) long needed, allocated; bool alloc_ok = true; + lockdep_assert_held(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - h->free_huge_pages; if (needed <= 0) { h->resv_huge_pages += delta; @@ -1975,7 +1979,7 @@ static int gather_surplus_pages(struct hstate *h, long delta) ret = -ENOMEM; retry: - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); for (i = 0; i < needed; i++) { page = alloc_surplus_huge_page(h, htlb_alloc_mask(h), NUMA_NO_NODE, NULL); @@ -1992,7 +1996,7 @@ retry: * After retaking hugetlb_lock, we need to recalculate 'needed' * because either resv_huge_pages or free_huge_pages may have changed. */ - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - (h->free_huge_pages + allocated); if (needed > 0) { @@ -2032,12 +2036,12 @@ retry: enqueue_huge_page(h, page); } free: - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); /* Free unnecessary surplus pages to the buddy allocator */ list_for_each_entry_safe(page, tmp, &surplus_list, lru) put_page(page); - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); return ret; } @@ -2049,17 +2053,17 @@ free: * to the associated reservation map. * 2) Free any unused surplus pages that may have been allocated to satisfy * the reservation. As many as unused_resv_pages may be freed. - * - * Called with hugetlb_lock held. However, the lock could be dropped (and - * reacquired) during calls to cond_resched_lock. Whenever dropping the lock, - * we must make sure nobody else can claim pages we are in the process of - * freeing. Do this by ensuring resv_huge_page always is greater than the - * number of huge pages we plan to free when dropping the lock. */ static void return_unused_surplus_pages(struct hstate *h, unsigned long unused_resv_pages) { unsigned long nr_pages; + struct page *page; + LIST_HEAD(page_list); + + lockdep_assert_held(&hugetlb_lock); + /* Uncommit the reservation */ + h->resv_huge_pages -= unused_resv_pages; /* Cannot return gigantic pages currently */ if (hstate_is_gigantic(h)) @@ -2076,24 +2080,21 @@ static void return_unused_surplus_pages(struct hstate *h, * evenly across all nodes with memory. Iterate across these nodes * until we can no longer free unreserved surplus pages. This occurs * when the nodes with surplus pages have no free pages. - * free_pool_huge_page() will balance the freed pages across the + * remove_pool_huge_page() will balance the freed pages across the * on-line nodes with memory and will handle the hstate accounting. - * - * Note that we decrement resv_huge_pages as we free the pages. If - * we drop the lock, resv_huge_pages will still be sufficiently large - * to cover subsequent pages we may free. */ while (nr_pages--) { - h->resv_huge_pages--; - unused_resv_pages--; - if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1)) + page = remove_pool_huge_page(h, &node_states[N_MEMORY], 1); + if (!page) goto out; - cond_resched_lock(&hugetlb_lock); + + list_add(&page->lru, &page_list); } out: - /* Fully uncommit the reservation */ - h->resv_huge_pages -= unused_resv_pages; + spin_unlock_irq(&hugetlb_lock); + update_and_free_pages_bulk(h, &page_list); + spin_lock_irq(&hugetlb_lock); } @@ -2175,27 +2176,26 @@ static long __vma_reservation_common(struct hstate *h, if (vma->vm_flags & VM_MAYSHARE) return ret; - else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && ret >= 0) { - /* - * In most cases, reserves always exist for private mappings. - * However, a file associated with mapping could have been - * hole punched or truncated after reserves were consumed. - * As subsequent fault on such a range will not use reserves. - * Subtle - The reserve map for private mappings has the - * opposite meaning than that of shared mappings. If NO - * entry is in the reserve map, it means a reservation exists. - * If an entry exists in the reserve map, it means the - * reservation has already been consumed. As a result, the - * return value of this routine is the opposite of the - * value returned from reserve map manipulation routines above. - */ - if (ret) - return 0; - else - return 1; - } - else - return ret < 0 ? ret : 0; + /* + * We know private mapping must have HPAGE_RESV_OWNER set. + * + * In most cases, reserves always exist for private mappings. + * However, a file associated with mapping could have been + * hole punched or truncated after reserves were consumed. + * As subsequent fault on such a range will not use reserves. + * Subtle - The reserve map for private mappings has the + * opposite meaning than that of shared mappings. If NO + * entry is in the reserve map, it means a reservation exists. + * If an entry exists in the reserve map, it means the + * reservation has already been consumed. As a result, the + * return value of this routine is the opposite of the + * value returned from reserve map manipulation routines above. + */ + if (ret > 0) + return 0; + if (ret == 0) + return 1; + return ret; } static long vma_needs_reservation(struct hstate *h, @@ -2266,6 +2266,134 @@ static void restore_reserve_on_error(struct hstate *h, } } +/* + * alloc_and_dissolve_huge_page - Allocate a new page and dissolve the old one + * @h: struct hstate old page belongs to + * @old_page: Old page to dissolve + * @list: List to isolate the page in case we need to + * Returns 0 on success, otherwise negated error. + */ +static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page, + struct list_head *list) +{ + gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; + int nid = page_to_nid(old_page); + struct page *new_page; + int ret = 0; + + /* + * Before dissolving the page, we need to allocate a new one for the + * pool to remain stable. Using alloc_buddy_huge_page() allows us to + * not having to deal with prep_new_huge_page() and avoids dealing of any + * counters. This simplifies and let us do the whole thing under the + * lock. + */ + new_page = alloc_buddy_huge_page(h, gfp_mask, nid, NULL, NULL); + if (!new_page) + return -ENOMEM; + +retry: + spin_lock_irq(&hugetlb_lock); + if (!PageHuge(old_page)) { + /* + * Freed from under us. Drop new_page too. + */ + goto free_new; + } else if (page_count(old_page)) { + /* + * Someone has grabbed the page, try to isolate it here. + * Fail with -EBUSY if not possible. + */ + spin_unlock_irq(&hugetlb_lock); + if (!isolate_huge_page(old_page, list)) + ret = -EBUSY; + spin_lock_irq(&hugetlb_lock); + goto free_new; + } else if (!HPageFreed(old_page)) { + /* + * Page's refcount is 0 but it has not been enqueued in the + * freelist yet. Race window is small, so we can succeed here if + * we retry. + */ + spin_unlock_irq(&hugetlb_lock); + cond_resched(); + goto retry; + } else { + /* + * Ok, old_page is still a genuine free hugepage. Remove it from + * the freelist and decrease the counters. These will be + * incremented again when calling __prep_account_new_huge_page() + * and enqueue_huge_page() for new_page. The counters will remain + * stable since this happens under the lock. + */ + remove_hugetlb_page(h, old_page, false); + + /* + * new_page needs to be initialized with the standard hugetlb + * state. This is normally done by prep_new_huge_page() but + * that takes hugetlb_lock which is already held so we need to + * open code it here. + * Reference count trick is needed because allocator gives us + * referenced page but the pool requires pages with 0 refcount. + */ + __prep_new_huge_page(new_page); + __prep_account_new_huge_page(h, nid); + page_ref_dec(new_page); + enqueue_huge_page(h, new_page); + + /* + * Pages have been replaced, we can safely free the old one. + */ + spin_unlock_irq(&hugetlb_lock); + update_and_free_page(h, old_page); + } + + return ret; + +free_new: + spin_unlock_irq(&hugetlb_lock); + __free_pages(new_page, huge_page_order(h)); + + return ret; +} + +int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) +{ + struct hstate *h; + struct page *head; + int ret = -EBUSY; + + /* + * The page might have been dissolved from under our feet, so make sure + * to carefully check the state under the lock. + * Return success when racing as if we dissolved the page ourselves. + */ + spin_lock_irq(&hugetlb_lock); + if (PageHuge(page)) { + head = compound_head(page); + h = page_hstate(head); + } else { + spin_unlock_irq(&hugetlb_lock); + return 0; + } + spin_unlock_irq(&hugetlb_lock); + + /* + * Fence off gigantic pages as there is a cyclic dependency between + * alloc_contig_range and them. Return -ENOMEM as this has the effect + * of bailing out right away without further retrying. + */ + if (hstate_is_gigantic(h)) + return -ENOMEM; + + if (page_count(head) && isolate_huge_page(head, list)) + ret = 0; + else if (!page_count(head)) + ret = alloc_and_dissolve_huge_page(h, head, list); + + return ret; +} + struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { @@ -2316,7 +2444,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, /* If this allocation is not consuming a reservation, charge it now. */ - deferred_reserve = map_chg || avoid_reserve || !vma_resv_map(vma); + deferred_reserve = map_chg || avoid_reserve; if (deferred_reserve) { ret = hugetlb_cgroup_charge_cgroup_rsvd( idx, pages_per_huge_page(h), &h_cg); @@ -2328,7 +2456,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, if (ret) goto out_uncharge_cgroup_reservation; - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); /* * glb_chg is passed to indicate whether or not a page must be taken * from the global free pool (global change). gbl_chg == 0 indicates @@ -2336,7 +2464,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, */ page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, gbl_chg); if (!page) { - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); page = alloc_buddy_huge_page_with_mpol(h, vma, addr); if (!page) goto out_uncharge_cgroup; @@ -2344,7 +2472,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, SetHPageRestoreReserve(page); h->resv_huge_pages--; } - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); list_add(&page->lru, &h->hugepage_activelist); /* Fall through */ } @@ -2357,7 +2485,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, h_cg, page); } - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); hugetlb_set_page_subpool(page, spool); @@ -2547,24 +2675,32 @@ static void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { int i; + LIST_HEAD(page_list); + lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic(h)) return; + /* + * Collect pages to be freed on a list, and free after dropping lock + */ for_each_node_mask(i, *nodes_allowed) { struct page *page, *next; struct list_head *freel = &h->hugepage_freelists[i]; list_for_each_entry_safe(page, next, freel, lru) { if (count >= h->nr_huge_pages) - return; + goto out; if (PageHighMem(page)) continue; - list_del(&page->lru); - update_and_free_page(h, page); - h->free_huge_pages--; - h->free_huge_pages_node[page_to_nid(page)]--; + remove_hugetlb_page(h, page, false); + list_add(&page->lru, &page_list); } } + +out: + spin_unlock_irq(&hugetlb_lock); + update_and_free_pages_bulk(h, &page_list); + spin_lock_irq(&hugetlb_lock); } #else static inline void try_to_free_low(struct hstate *h, unsigned long count, @@ -2583,6 +2719,7 @@ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, { int nr_nodes, node; + lockdep_assert_held(&hugetlb_lock); VM_BUG_ON(delta != -1 && delta != 1); if (delta < 0) { @@ -2610,6 +2747,8 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, nodemask_t *nodes_allowed) { unsigned long min_count, ret; + struct page *page; + LIST_HEAD(page_list); NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL); /* @@ -2622,7 +2761,12 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, else return -ENOMEM; - spin_lock(&hugetlb_lock); + /* + * resize_lock mutex prevents concurrent adjustments to number of + * pages in hstate via the proc/sysfs interfaces. + */ + mutex_lock(&h->resize_lock); + spin_lock_irq(&hugetlb_lock); /* * Check for a node specific request. @@ -2653,7 +2797,8 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, */ if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) { if (count > persistent_huge_pages(h)) { - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); + mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); return -EINVAL; } @@ -2682,14 +2827,14 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, * page, free_huge_page will handle it by freeing the page * and reducing the surplus. */ - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); /* yield cpu to avoid soft lockup */ cond_resched(); ret = alloc_pool_huge_page(h, nodes_allowed, node_alloc_noretry); - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); if (!ret) goto out; @@ -2716,18 +2861,30 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages; min_count = max(count, min_count); try_to_free_low(h, min_count, nodes_allowed); + + /* + * Collect pages to be removed on list without dropping lock + */ while (min_count < persistent_huge_pages(h)) { - if (!free_pool_huge_page(h, nodes_allowed, 0)) + page = remove_pool_huge_page(h, nodes_allowed, 0); + if (!page) break; - cond_resched_lock(&hugetlb_lock); + + list_add(&page->lru, &page_list); } + /* free the pages after dropping lock */ + spin_unlock_irq(&hugetlb_lock); + update_and_free_pages_bulk(h, &page_list); + spin_lock_irq(&hugetlb_lock); + while (count < persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, 1)) break; } out: h->max_huge_pages = persistent_huge_pages(h); - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); + mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); @@ -2882,9 +3039,9 @@ static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, if (err) return err; - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); h->nr_overcommit_huge_pages = input; - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); return count; } @@ -3215,6 +3372,7 @@ void __init hugetlb_add_hstate(unsigned int order) BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); BUG_ON(order == 0); h = &hstates[hugetlb_max_hstate++]; + mutex_init(&h->resize_lock); h->order = order; h->mask = ~(huge_page_size(h) - 1); for (i = 0; i < MAX_NUMNODES; ++i) @@ -3267,10 +3425,10 @@ static int __init hugepages_setup(char *s) /* * Global state is always initialized later in hugetlb_init. - * But we need to allocate >= MAX_ORDER hstates here early to still + * But we need to allocate gigantic hstates here early to still * use the bootmem allocator. */ - if (hugetlb_max_hstate && parsed_hstate->order >= MAX_ORDER) + if (hugetlb_max_hstate && hstate_is_gigantic(parsed_hstate)) hugetlb_hstate_alloc_pages(parsed_hstate); last_mhp = mhp; @@ -3470,9 +3628,9 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, goto out; if (write) { - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); h->nr_overcommit_huge_pages = tmp; - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); } out: return ret; @@ -3568,7 +3726,7 @@ static int hugetlb_acct_memory(struct hstate *h, long delta) if (!delta) return 0; - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); /* * When cpuset is configured, it breaks the strict hugetlb page * reservation as the accounting is done on a global variable. Such @@ -3607,7 +3765,7 @@ static int hugetlb_acct_memory(struct hstate *h, long delta) return_unused_surplus_pages(h, (unsigned long) -delta); out: - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); return ret; } @@ -3795,7 +3953,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, src_pte = huge_pte_offset(src, addr, sz); if (!src_pte) continue; - dst_pte = huge_pte_alloc(dst, addr, sz); + dst_pte = huge_pte_alloc(dst, vma, addr, sz); if (!dst_pte) { ret = -ENOMEM; break; @@ -4310,6 +4468,44 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping, return 0; } +static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma, + struct address_space *mapping, + pgoff_t idx, + unsigned int flags, + unsigned long haddr, + unsigned long reason) +{ + vm_fault_t ret; + u32 hash; + struct vm_fault vmf = { + .vma = vma, + .address = haddr, + .flags = flags, + + /* + * Hard to debug if it ends up being + * used by a callee that assumes + * something about the other + * uninitialized fields... same as in + * memory.c + */ + }; + + /* + * hugetlb_fault_mutex and i_mmap_rwsem must be + * dropped before handling userfault. Reacquire + * after handling fault to make calling code simpler. + */ + hash = hugetlb_fault_mutex_hash(mapping, idx); + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); + ret = handle_userfault(&vmf, reason); + i_mmap_lock_read(mapping); + mutex_lock(&hugetlb_fault_mutex_table[hash]); + + return ret; +} + static vm_fault_t hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, struct address_space *mapping, pgoff_t idx, @@ -4348,35 +4544,11 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, retry: page = find_lock_page(mapping, idx); if (!page) { - /* - * Check for page in userfault range - */ + /* Check for page in userfault range */ if (userfaultfd_missing(vma)) { - u32 hash; - struct vm_fault vmf = { - .vma = vma, - .address = haddr, - .flags = flags, - /* - * Hard to debug if it ends up being - * used by a callee that assumes - * something about the other - * uninitialized fields... same as in - * memory.c - */ - }; - - /* - * hugetlb_fault_mutex and i_mmap_rwsem must be - * dropped before handling userfault. Reacquire - * after handling fault to make calling code simpler. - */ - hash = hugetlb_fault_mutex_hash(mapping, idx); - mutex_unlock(&hugetlb_fault_mutex_table[hash]); - i_mmap_unlock_read(mapping); - ret = handle_userfault(&vmf, VM_UFFD_MISSING); - i_mmap_lock_read(mapping); - mutex_lock(&hugetlb_fault_mutex_table[hash]); + ret = hugetlb_handle_userfault(vma, mapping, idx, + flags, haddr, + VM_UFFD_MISSING); goto out; } @@ -4395,13 +4567,10 @@ retry: * sure there really is no pte entry. */ ptl = huge_pte_lock(h, mm, ptep); - if (!huge_pte_none(huge_ptep_get(ptep))) { - ret = 0; - spin_unlock(ptl); - goto out; - } + ret = 0; + if (huge_pte_none(huge_ptep_get(ptep))) + ret = vmf_error(PTR_ERR(page)); spin_unlock(ptl); - ret = vmf_error(PTR_ERR(page)); goto out; } clear_huge_page(page, address, pages_per_huge_page(h)); @@ -4435,6 +4604,16 @@ retry: VM_FAULT_SET_HINDEX(hstate_index(h)); goto backout_unlocked; } + + /* Check for page in userfault range. */ + if (userfaultfd_minor(vma)) { + unlock_page(page); + put_page(page); + ret = hugetlb_handle_userfault(vma, mapping, idx, + flags, haddr, + VM_UFFD_MINOR); + goto out; + } } /* @@ -4563,7 +4742,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, */ mapping = vma->vm_file->f_mapping; i_mmap_lock_read(mapping); - ptep = huge_pte_alloc(mm, haddr, huge_page_size(h)); + ptep = huge_pte_alloc(mm, vma, haddr, huge_page_size(h)); if (!ptep) { i_mmap_unlock_read(mapping); return VM_FAULT_OOM; @@ -4675,6 +4854,7 @@ out_mutex: return ret; } +#ifdef CONFIG_USERFAULTFD /* * Used by userfaultfd UFFDIO_COPY. Based on mcopy_atomic_pte with * modifications for huge pages. @@ -4684,8 +4864,10 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, + enum mcopy_atomic_mode mode, struct page **pagep) { + bool is_continue = (mode == MCOPY_ATOMIC_CONTINUE); struct address_space *mapping; pgoff_t idx; unsigned long size; @@ -4695,8 +4877,17 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, spinlock_t *ptl; int ret; struct page *page; + int writable; + + mapping = dst_vma->vm_file->f_mapping; + idx = vma_hugecache_offset(h, dst_vma, dst_addr); - if (!*pagep) { + if (is_continue) { + ret = -EFAULT; + page = find_lock_page(mapping, idx); + if (!page) + goto out; + } else if (!*pagep) { ret = -ENOMEM; page = alloc_huge_page(dst_vma, dst_addr, 0); if (IS_ERR(page)) @@ -4725,13 +4916,8 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, */ __SetPageUptodate(page); - mapping = dst_vma->vm_file->f_mapping; - idx = vma_hugecache_offset(h, dst_vma, dst_addr); - - /* - * If shared, add to page cache - */ - if (vm_shared) { + /* Add shared, newly allocated pages to the page cache. */ + if (vm_shared && !is_continue) { size = i_size_read(mapping->host) >> huge_page_shift(h); ret = -EFAULT; if (idx >= size) @@ -4776,8 +4962,14 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, hugepage_add_new_anon_rmap(page, dst_vma, dst_addr); } - _dst_pte = make_huge_pte(dst_vma, page, dst_vma->vm_flags & VM_WRITE); - if (dst_vma->vm_flags & VM_WRITE) + /* For CONTINUE on a non-shared VMA, don't set VM_WRITE for CoW. */ + if (is_continue && !vm_shared) + writable = 0; + else + writable = dst_vma->vm_flags & VM_WRITE; + + _dst_pte = make_huge_pte(dst_vma, page, writable); + if (writable) _dst_pte = huge_pte_mkdirty(_dst_pte); _dst_pte = pte_mkyoung(_dst_pte); @@ -4791,20 +4983,22 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); - SetHPageMigratable(page); - if (vm_shared) + if (!is_continue) + SetHPageMigratable(page); + if (vm_shared || is_continue) unlock_page(page); ret = 0; out: return ret; out_release_unlock: spin_unlock(ptl); - if (vm_shared) + if (vm_shared || is_continue) unlock_page(page); out_release_nounlock: put_page(page); goto out; } +#endif /* CONFIG_USERFAULTFD */ static void record_subpages_vmas(struct page *page, struct vm_area_struct *vma, int refs, struct page **pages, @@ -4996,14 +5190,6 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, return i ? i : err; } -#ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE -/* - * ARCHes with special requirements for evicting HUGETLB backing TLB entries can - * implement this. - */ -#define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) -#endif - unsigned long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot) { @@ -5280,6 +5466,9 @@ long hugetlb_unreserve_pages(struct inode *inode, long start, long end, /* * If the subpool has a minimum size, the number of global * reservations to be released may be adjusted. + * + * Note that !resv_map implies freed == 0. So (chg - freed) + * won't go negative. */ gbl_reserve = hugepage_subpool_put_pages(spool, (chg - freed)); hugetlb_acct_memory(h, -gbl_reserve); @@ -5326,6 +5515,15 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr) return false; } +bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) +{ +#ifdef CONFIG_USERFAULTFD + if (uffd_disable_huge_pmd_share(vma)) + return false; +#endif + return vma_shareable(vma, addr); +} + /* * Determine if start,end range within vma could be mapped by shared pmd. * If yes, adjust start and end to cover range associated with possible @@ -5338,8 +5536,8 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); /* - * vma need span at least one aligned PUD size and the start,end range - * must at least partialy within it. + * vma needs to span at least one aligned PUD size, and the range + * must be at least partially within in. */ if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) || (*end <= v_start) || (*start >= v_end)) @@ -5370,9 +5568,9 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, * if !vma_shareable check at the beginning of the routine. i_mmap_rwsem is * only required for subsequent processing. */ -pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) +pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pud_t *pud) { - struct vm_area_struct *vma = find_vma(mm, addr); struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; @@ -5382,9 +5580,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) pte_t *pte; spinlock_t *ptl; - if (!vma_shareable(vma, addr)) - return (pte_t *)pmd_alloc(mm, pud, addr); - i_mmap_assert_locked(mapping); vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { if (svma == vma) @@ -5448,9 +5643,10 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE; return 1; } -#define want_pmd_share() (1) + #else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ -pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) +pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pud_t *pud) { return NULL; } @@ -5465,11 +5661,15 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } -#define want_pmd_share() (0) + +bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) +{ + return false; +} #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB -pte_t *huge_pte_alloc(struct mm_struct *mm, +pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { pgd_t *pgd; @@ -5487,8 +5687,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, pte = (pte_t *)pud; } else { BUG_ON(sz != PMD_SIZE); - if (want_pmd_share() && pud_none(*pud)) - pte = huge_pmd_share(mm, addr, pud); + if (want_pmd_share(vma, addr) && pud_none(*pud)) + pte = huge_pmd_share(mm, vma, addr, pud); else pte = (pte_t *)pmd_alloc(mm, pud, addr); } @@ -5632,7 +5832,7 @@ bool isolate_huge_page(struct page *page, struct list_head *list) { bool ret = true; - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); if (!PageHeadHuge(page) || !HPageMigratable(page) || !get_page_unless_zero(page)) { @@ -5642,16 +5842,16 @@ bool isolate_huge_page(struct page *page, struct list_head *list) ClearHPageMigratable(page); list_move_tail(&page->lru, list); unlock: - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); return ret; } void putback_active_hugepage(struct page *page) { - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); SetHPageMigratable(page); list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist); - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); put_page(page); } @@ -5679,13 +5879,70 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason) SetHPageTemporary(oldpage); ClearHPageTemporary(newpage); - spin_lock(&hugetlb_lock); + /* + * There is no need to transfer the per-node surplus state + * when we do not cross the node. + */ + if (new_nid == old_nid) + return; + spin_lock_irq(&hugetlb_lock); if (h->surplus_huge_pages_node[old_nid]) { h->surplus_huge_pages_node[old_nid]--; h->surplus_huge_pages_node[new_nid]++; } - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); + } +} + +/* + * This function will unconditionally remove all the shared pmd pgtable entries + * within the specific vma for a hugetlbfs memory range. + */ +void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) +{ + struct hstate *h = hstate_vma(vma); + unsigned long sz = huge_page_size(h); + struct mm_struct *mm = vma->vm_mm; + struct mmu_notifier_range range; + unsigned long address, start, end; + spinlock_t *ptl; + pte_t *ptep; + + if (!(vma->vm_flags & VM_MAYSHARE)) + return; + + start = ALIGN(vma->vm_start, PUD_SIZE); + end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); + + if (start >= end) + return; + + /* + * No need to call adjust_range_if_pmd_sharing_possible(), because + * we have already done the PUD_SIZE alignment. + */ + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, + start, end); + mmu_notifier_invalidate_range_start(&range); + i_mmap_lock_write(vma->vm_file->f_mapping); + for (address = start; address < end; address += PUD_SIZE) { + unsigned long tmp = address; + + ptep = huge_pte_offset(mm, address, sz); + if (!ptep) + continue; + ptl = huge_pte_lock(h, mm, ptep); + /* We don't want 'address' to be changed */ + huge_pmd_unshare(mm, vma, &tmp, ptep); + spin_unlock(ptl); } + flush_hugetlb_tlb_range(vma, start, end); + i_mmap_unlock_write(vma->vm_file->f_mapping); + /* + * No need to call mmu_notifier_invalidate_range(), see + * Documentation/vm/mmu_notifier.rst. + */ + mmu_notifier_invalidate_range_end(&range); } #ifdef CONFIG_CMA diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 603a131e262d..5383023d0cca 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -204,11 +204,11 @@ static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css) do { idx = 0; for_each_hstate(h) { - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); list_for_each_entry(page, &h->hugepage_activelist, lru) hugetlb_cgroup_move_parent(idx, h_cg, page); - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); idx++; } cond_resched(); @@ -784,8 +784,7 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage) if (hugetlb_cgroup_disabled()) return; - VM_BUG_ON_PAGE(!PageHuge(oldhpage), oldhpage); - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); h_cg = hugetlb_cgroup_from_page(oldhpage); h_cg_rsvd = hugetlb_cgroup_from_page_rsvd(oldhpage); set_hugetlb_cgroup(oldhpage, NULL); @@ -795,7 +794,7 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage) set_hugetlb_cgroup(newhpage, h_cg); set_hugetlb_cgroup_rsvd(newhpage, h_cg_rsvd); list_move(&newhpage->lru, &h->hugepage_activelist); - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); return; } diff --git a/mm/internal.h b/mm/internal.h index ef5f336f59bd..54bd0dc2c23c 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -244,7 +244,13 @@ struct compact_control { unsigned int nr_freepages; /* Number of isolated free pages */ unsigned int nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ - unsigned long migrate_pfn; /* isolate_migratepages search base */ + /* + * Acts as an in/out parameter to page isolation for migration. + * isolate_migratepages uses it as a search base. + * isolate_migratepages_block will update the value to the next pfn + * after the last isolated one. + */ + unsigned long migrate_pfn; unsigned long fast_start_pfn; /* a pfn to start linear scan from */ struct zone *zone; unsigned long total_migrate_scanned; @@ -280,7 +286,7 @@ struct capture_control { unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn); -unsigned long +int isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); int find_suitable_fallback(struct free_area *area, unsigned int order, @@ -328,7 +334,7 @@ static inline bool is_exec_mapping(vm_flags_t flags) } /* - * Stack area - atomatically grows in one direction + * Stack area - automatically grows in one direction * * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: * do_mmap() forbids all other combinations. diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 3820ca54743b..8f450bc28045 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -55,9 +55,9 @@ extern bool kasan_flag_async __ro_after_init; #define KASAN_TAG_MAX 0xFD /* maximum value for random tags */ #ifdef CONFIG_KASAN_HW_TAGS -#define KASAN_TAG_MIN 0xF0 /* mimimum value for random tags */ +#define KASAN_TAG_MIN 0xF0 /* minimum value for random tags */ #else -#define KASAN_TAG_MIN 0x00 /* mimimum value for random tags */ +#define KASAN_TAG_MIN 0x00 /* minimum value for random tags */ #endif #ifdef CONFIG_KASAN_GENERIC @@ -403,7 +403,7 @@ static inline bool kasan_byte_accessible(const void *addr) #else /* CONFIG_KASAN_HW_TAGS */ /** - * kasan_poison - mark the memory range as unaccessible + * kasan_poison - mark the memory range as inaccessible * @addr - range start address, must be aligned to KASAN_GRANULE_SIZE * @size - range size, must be aligned to KASAN_GRANULE_SIZE * @value - value that's written to metadata for the range @@ -434,7 +434,7 @@ bool kasan_byte_accessible(const void *addr); /** * kasan_poison_last_granule - mark the last granule of the memory range as - * unaccessible + * inaccessible * @addr - range start address, must be aligned to KASAN_GRANULE_SIZE * @size - range size * diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 728fb24c5683..d8ccff4c1275 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -27,7 +27,7 @@ /* Data structure and operations for quarantine queues. */ /* - * Each queue is a signle-linked list, which also stores the total size of + * Each queue is a single-linked list, which also stores the total size of * objects inside of it. */ struct qlist_head { @@ -138,7 +138,7 @@ static void qlink_free(struct qlist_node *qlink, struct kmem_cache *cache) local_irq_save(flags); /* - * As the object now gets freed from the quaratine, assume that its + * As the object now gets freed from the quarantine, assume that its * free track is no longer valid. */ *(u8 *)kasan_mem_to_shadow(object) = KASAN_KMALLOC_FREE; diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 727ad4629173..082ee5b6d9a1 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -316,7 +316,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size) * // rest of vmalloc process <data dependency> * STORE p, a LOAD shadow(x+99) * - * If there is no barrier between the end of unpoisioning the shadow + * If there is no barrier between the end of unpoisoning the shadow * and the store of the result to p, the stores could be committed * in a different order by CPU#0, and CPU#1 could erroneously observe * poison in the shadow. @@ -384,7 +384,7 @@ static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr, * How does this work? * ------------------- * - * We have a region that is page aligned, labelled as A. + * We have a region that is page aligned, labeled as A. * That might not map onto the shadow in a way that is page-aligned: * * start end diff --git a/mm/kfence/core.c b/mm/kfence/core.c index d53c91f881a4..e18fbbd5d9b4 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -10,6 +10,7 @@ #include <linux/atomic.h> #include <linux/bug.h> #include <linux/debugfs.h> +#include <linux/irq_work.h> #include <linux/kcsan-checks.h> #include <linux/kfence.h> #include <linux/kmemleak.h> @@ -19,6 +20,7 @@ #include <linux/moduleparam.h> #include <linux/random.h> #include <linux/rcupdate.h> +#include <linux/sched/sysctl.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/spinlock.h> @@ -372,6 +374,7 @@ static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool z /* Restore page protection if there was an OOB access. */ if (meta->unprotected_page) { + memzero_explicit((void *)ALIGN_DOWN(meta->unprotected_page, PAGE_SIZE), PAGE_SIZE); kfence_protect(meta->unprotected_page); meta->unprotected_page = 0; } @@ -586,6 +589,17 @@ late_initcall(kfence_debugfs_init); /* === Allocation Gate Timer ================================================ */ +#ifdef CONFIG_KFENCE_STATIC_KEYS +/* Wait queue to wake up allocation-gate timer task. */ +static DECLARE_WAIT_QUEUE_HEAD(allocation_wait); + +static void wake_up_kfence_timer(struct irq_work *work) +{ + wake_up(&allocation_wait); +} +static DEFINE_IRQ_WORK(wake_up_kfence_timer_work, wake_up_kfence_timer); +#endif + /* * Set up delayed work, which will enable and disable the static key. We need to * use a work queue (rather than a simple timer), since enabling and disabling a @@ -603,29 +617,27 @@ static void toggle_allocation_gate(struct work_struct *work) if (!READ_ONCE(kfence_enabled)) return; - /* Enable static key, and await allocation to happen. */ atomic_set(&kfence_allocation_gate, 0); #ifdef CONFIG_KFENCE_STATIC_KEYS + /* Enable static key, and await allocation to happen. */ static_branch_enable(&kfence_allocation_key); - /* - * Await an allocation. Timeout after 1 second, in case the kernel stops - * doing allocations, to avoid stalling this worker task for too long. - */ - { - unsigned long end_wait = jiffies + HZ; - - do { - set_current_state(TASK_UNINTERRUPTIBLE); - if (atomic_read(&kfence_allocation_gate) != 0) - break; - schedule_timeout(1); - } while (time_before(jiffies, end_wait)); - __set_current_state(TASK_RUNNING); + + if (sysctl_hung_task_timeout_secs) { + /* + * During low activity with no allocations we might wait a + * while; let's avoid the hung task warning. + */ + wait_event_timeout(allocation_wait, atomic_read(&kfence_allocation_gate), + sysctl_hung_task_timeout_secs * HZ / 2); + } else { + wait_event(allocation_wait, atomic_read(&kfence_allocation_gate)); } + /* Disable static key and reset timer. */ static_branch_disable(&kfence_allocation_key); #endif - schedule_delayed_work(&kfence_timer, msecs_to_jiffies(kfence_sample_interval)); + queue_delayed_work(system_power_efficient_wq, &kfence_timer, + msecs_to_jiffies(kfence_sample_interval)); } static DECLARE_DELAYED_WORK(kfence_timer, toggle_allocation_gate); @@ -654,7 +666,7 @@ void __init kfence_init(void) } WRITE_ONCE(kfence_enabled, true); - schedule_delayed_work(&kfence_timer, 0); + queue_delayed_work(system_power_efficient_wq, &kfence_timer, 0); pr_info("initialized - using %lu bytes for %d objects at 0x%p-0x%p\n", KFENCE_POOL_SIZE, CONFIG_KFENCE_NUM_OBJECTS, (void *)__kfence_pool, (void *)(__kfence_pool + KFENCE_POOL_SIZE)); @@ -728,6 +740,19 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) */ if (atomic_read(&kfence_allocation_gate) || atomic_inc_return(&kfence_allocation_gate) > 1) return NULL; +#ifdef CONFIG_KFENCE_STATIC_KEYS + /* + * waitqueue_active() is fully ordered after the update of + * kfence_allocation_gate per atomic_inc_return(). + */ + if (waitqueue_active(&allocation_wait)) { + /* + * Calling wake_up() here may deadlock when allocations happen + * from within timer code. Use an irq_work to defer it. + */ + irq_work_queue(&wake_up_kfence_timer_work); + } +#endif if (!READ_ONCE(kfence_enabled)) return NULL; diff --git a/mm/kfence/report.c b/mm/kfence/report.c index e3f71451ad9e..2a319c21c939 100644 --- a/mm/kfence/report.c +++ b/mm/kfence/report.c @@ -263,6 +263,6 @@ void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *r if (panic_on_warn) panic("panic_on_warn set ...\n"); - /* We encountered a memory unsafety error, taint the kernel! */ + /* We encountered a memory safety error, taint the kernel! */ add_taint(TAINT_BAD_PAGE, LOCKDEP_STILL_OK); } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index a7d6cb912b05..6c0185fdd815 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -481,7 +481,7 @@ int __khugepaged_enter(struct mm_struct *mm) return -ENOMEM; /* __khugepaged_exit() must not run from under us */ - VM_BUG_ON_MM(atomic_read(&mm->mm_users) == 0, mm); + VM_BUG_ON_MM(khugepaged_test_exit(mm), mm); if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) { free_mm_slot(mm_slot); return 0; @@ -667,7 +667,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, * * The page table that maps the page has been already unlinked * from the page table tree and this process cannot get - * an additinal pin on the page. + * an additional pin on the page. * * New pins can come later if the page is shared across fork, * but not from this process. The other process cannot write to @@ -716,17 +716,17 @@ next: if (pte_write(pteval)) writable = true; } - if (likely(writable)) { - if (likely(referenced)) { - result = SCAN_SUCCEED; - trace_mm_collapse_huge_page_isolate(page, none_or_zero, - referenced, writable, result); - return 1; - } - } else { + + if (unlikely(!writable)) { result = SCAN_PAGE_RO; + } else if (unlikely(!referenced)) { + result = SCAN_LACK_REFERENCED_PAGE; + } else { + result = SCAN_SUCCEED; + trace_mm_collapse_huge_page_isolate(page, none_or_zero, + referenced, writable, result); + return 1; } - out: release_pte_pages(pte, _pte, compound_pagelist); trace_mm_collapse_huge_page_isolate(page, none_or_zero, @@ -809,7 +809,7 @@ static bool khugepaged_scan_abort(int nid) * If node_reclaim_mode is disabled, then no extra effort is made to * allocate memory locally. */ - if (!node_reclaim_mode) + if (!node_reclaim_enabled()) return false; /* If there is a count for this node already, it must be acceptable */ @@ -1128,10 +1128,10 @@ static void collapse_huge_page(struct mm_struct *mm, mmap_write_lock(mm); result = hugepage_vma_revalidate(mm, address, &vma); if (result) - goto out; + goto out_up_write; /* check if the pmd is still valid */ if (mm_find_pmd(mm, address) != pmd) - goto out; + goto out_up_write; anon_vma_lock_write(vma->anon_vma); @@ -1171,7 +1171,7 @@ static void collapse_huge_page(struct mm_struct *mm, spin_unlock(pmd_ptl); anon_vma_unlock_write(vma->anon_vma); result = SCAN_FAIL; - goto out; + goto out_up_write; } /* @@ -1183,19 +1183,18 @@ static void collapse_huge_page(struct mm_struct *mm, __collapse_huge_page_copy(pte, new_page, vma, address, pte_ptl, &compound_pagelist); pte_unmap(pte); + /* + * spin_lock() below is not the equivalent of smp_wmb(), but + * the smp_wmb() inside __SetPageUptodate() can be reused to + * avoid the copy_huge_page writes to become visible after + * the set_pmd_at() write. + */ __SetPageUptodate(new_page); pgtable = pmd_pgtable(_pmd); _pmd = mk_huge_pmd(new_page, vma->vm_page_prot); _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); - /* - * spin_lock() below is not the equivalent of smp_wmb(), so - * this is needed to avoid the copy_huge_page writes to become - * visible after the set_pmd_at() write. - */ - smp_wmb(); - spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); page_add_new_anon_rmap(new_page, vma, address, true); @@ -1216,8 +1215,6 @@ out_nolock: mem_cgroup_uncharge(*hpage); trace_mm_collapse_huge_page(mm, isolated, result); return; -out: - goto out_up_write; } static int khugepaged_scan_pmd(struct mm_struct *mm, @@ -1274,10 +1271,6 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, goto out_unmap; } } - if (!pte_present(pteval)) { - result = SCAN_PTE_NON_PRESENT; - goto out_unmap; - } if (pte_uffd_wp(pteval)) { /* * Don't collapse the page if any of the small @@ -1447,7 +1440,7 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) int i; if (!vma || !vma->vm_file || - vma->vm_start > haddr || vma->vm_end < haddr + HPAGE_PMD_SIZE) + !range_in_vma(vma, haddr, haddr + HPAGE_PMD_SIZE)) return; /* @@ -1533,16 +1526,16 @@ abort: goto drop_hpage; } -static int khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot) +static void khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot) { struct mm_struct *mm = mm_slot->mm; int i; if (likely(mm_slot->nr_pte_mapped_thp == 0)) - return 0; + return; if (!mmap_write_trylock(mm)) - return -EBUSY; + return; if (unlikely(khugepaged_test_exit(mm))) goto out; @@ -1553,7 +1546,6 @@ static int khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot) out: mm_slot->nr_pte_mapped_thp = 0; mmap_write_unlock(mm); - return 0; } static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) @@ -2057,9 +2049,8 @@ static void khugepaged_scan_file(struct mm_struct *mm, BUILD_BUG(); } -static int khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot) +static void khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot) { - return 0; } #endif @@ -2205,11 +2196,9 @@ static void khugepaged_do_scan(void) { struct page *hpage = NULL; unsigned int progress = 0, pass_through_head = 0; - unsigned int pages = khugepaged_pages_to_scan; + unsigned int pages = READ_ONCE(khugepaged_pages_to_scan); bool wait = true; - barrier(); /* write khugepaged_pages_to_scan to local stack */ - lru_add_drain_all(); while (progress < pages) { @@ -215,8 +215,6 @@ struct rmap_item { #define SEQNR_MASK 0x0ff /* low bits of unstable tree seqnr */ #define UNSTABLE_FLAG 0x100 /* is a node of the unstable tree */ #define STABLE_FLAG 0x200 /* is listed from the stable tree */ -#define KSM_FLAG_MASK (SEQNR_MASK|UNSTABLE_FLAG|STABLE_FLAG) - /* to mask all the flags */ /* The stable and unstable tree heads */ static struct rb_root one_stable_tree[1] = { RB_ROOT }; @@ -461,7 +459,7 @@ static inline bool ksm_test_exit(struct mm_struct *mm) * but taking great care only to touch a ksm page, in a VM_MERGEABLE vma, * in case the application has unmapped and remapped mm,addr meanwhile. * Could a ksm page appear anywhere else? Actually yes, in a VM_PFNMAP - * mmap of /dev/mem or /dev/kmem, where we would not want to touch it. + * mmap of /dev/mem, where we would not want to touch it. * * FAULT_FLAG/FOLL_REMOTE are because we do this outside the context * of the process that owns 'vma'. We also do not want to enforce @@ -778,12 +776,11 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item) struct page *page; stable_node = rmap_item->head; - page = get_ksm_page(stable_node, GET_KSM_PAGE_LOCK); + page = get_ksm_page(stable_node, GET_KSM_PAGE_NOLOCK); if (!page) goto out; hlist_del(&rmap_item->hlist); - unlock_page(page); put_page(page); if (!hlist_empty(&stable_node->hlist)) @@ -794,6 +791,7 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item) stable_node->rmap_hlist_len--; put_anon_vma(rmap_item->anon_vma); + rmap_item->head = NULL; rmap_item->address &= PAGE_MASK; } else if (rmap_item->address & UNSTABLE_FLAG) { @@ -817,8 +815,7 @@ out: cond_resched(); /* we're called from many long loops */ } -static void remove_trailing_rmap_items(struct mm_slot *mm_slot, - struct rmap_item **rmap_list) +static void remove_trailing_rmap_items(struct rmap_item **rmap_list) { while (*rmap_list) { struct rmap_item *rmap_item = *rmap_list; @@ -989,7 +986,7 @@ static int unmerge_and_remove_all_rmap_items(void) goto error; } - remove_trailing_rmap_items(mm_slot, &mm_slot->rmap_list); + remove_trailing_rmap_items(&mm_slot->rmap_list); mmap_read_unlock(mm); spin_lock(&ksm_mmlist_lock); @@ -1068,7 +1065,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, /* * Ok this is tricky, when get_user_pages_fast() run it doesn't * take any lock, therefore the check that we are going to make - * with the pagecount against the mapcount is racey and + * with the pagecount against the mapcount is racy and * O_DIRECT can happen right after the check. * So we clear the pte and flush the tlb before the check * this assure us that no O_DIRECT can happen after the check @@ -1438,7 +1435,7 @@ static struct page *stable_node_dup(struct stable_node **_stable_node_dup, */ *_stable_node = found; /* - * Just for robustneess as stable_node is + * Just for robustness, as stable_node is * otherwise left as a stable pointer, the * compiler shall optimize it away at build * time. @@ -1771,7 +1768,6 @@ chain_append: * stable_node_dup is the dup to replace. */ if (stable_node_dup == stable_node) { - VM_BUG_ON(is_stable_node_chain(stable_node_dup)); VM_BUG_ON(is_stable_node_dup(stable_node_dup)); /* chain is missing so create it */ stable_node = alloc_stable_node_chain(stable_node_dup, @@ -1785,7 +1781,6 @@ chain_append: * of the current nid for this page * content. */ - VM_BUG_ON(!is_stable_node_chain(stable_node)); VM_BUG_ON(!is_stable_node_dup(stable_node_dup)); VM_BUG_ON(page_node->head != &migrate_nodes); list_del(&page_node->list); @@ -2337,7 +2332,7 @@ next_mm: * Nuke all the rmap_items that are above this current rmap: * because there were no VM_MERGEABLE vmas with such addresses. */ - remove_trailing_rmap_items(slot, ksm_scan.rmap_list); + remove_trailing_rmap_items(ksm_scan.rmap_list); spin_lock(&ksm_mmlist_lock); ksm_scan.mm_slot = list_entry(slot->mm_list.next, @@ -2634,7 +2629,7 @@ again: vma = vmac->vma; /* Ignore the stable/unstable/sqnr flags */ - addr = rmap_item->address & ~KSM_FLAG_MASK; + addr = rmap_item->address & PAGE_MASK; if (addr < vma->vm_start || addr >= vma->vm_end) continue; diff --git a/mm/list_lru.c b/mm/list_lru.c index 6f067b6b935f..cd58790d0fb3 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -125,8 +125,8 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item) list_add_tail(item, &l->list); /* Set shrinker bit if the first element was added */ if (!l->nr_items++) - memcg_set_shrinker_bit(memcg, nid, - lru_shrinker_id(lru)); + set_shrinker_bit(memcg, nid, + lru_shrinker_id(lru)); nlru->nr_items++; spin_unlock(&nlru->lock); return true; @@ -540,7 +540,7 @@ static void memcg_drain_list_lru_node(struct list_lru *lru, int nid, if (src->nr_items) { dst->nr_items += src->nr_items; - memcg_set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); + set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); src->nr_items = 0; } diff --git a/mm/madvise.c b/mm/madvise.c index 01fef79ac761..63e489e5bfdb 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -799,7 +799,7 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, if (end > vma->vm_end) { /* * Don't fail if end > vma->vm_end. If the old - * vma was splitted while the mmap_lock was + * vma was split while the mmap_lock was * released the effect of the concurrent * operation may not cause madvise() to * have an undefined result. There may be an @@ -1039,7 +1039,7 @@ process_madvise_behavior_valid(int behavior) * MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump. * MADV_COLD - the application is not expected to use this memory soon, * deactivate pages in this range so that they can be reclaimed - * easily if memory pressure hanppens. + * easily if memory pressure happens. * MADV_PAGEOUT - the application is not expected to use this memory soon, * page out the pages in this range immediately. * diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c100265dc393..64ada9e650a5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -215,7 +215,7 @@ enum res_type { #define MEMFILE_PRIVATE(x, val) ((x) << 16 | (val)) #define MEMFILE_TYPE(val) ((val) >> 16 & 0xffff) #define MEMFILE_ATTR(val) ((val) & 0xffff) -/* Used for OOM nofiier */ +/* Used for OOM notifier */ #define OOM_CONTROL (0) /* @@ -400,130 +400,6 @@ DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key); EXPORT_SYMBOL(memcg_kmem_enabled_key); #endif -static int memcg_shrinker_map_size; -static DEFINE_MUTEX(memcg_shrinker_map_mutex); - -static void memcg_free_shrinker_map_rcu(struct rcu_head *head) -{ - kvfree(container_of(head, struct memcg_shrinker_map, rcu)); -} - -static int memcg_expand_one_shrinker_map(struct mem_cgroup *memcg, - int size, int old_size) -{ - struct memcg_shrinker_map *new, *old; - struct mem_cgroup_per_node *pn; - int nid; - - lockdep_assert_held(&memcg_shrinker_map_mutex); - - for_each_node(nid) { - pn = memcg->nodeinfo[nid]; - old = rcu_dereference_protected(pn->shrinker_map, true); - /* Not yet online memcg */ - if (!old) - return 0; - - new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid); - if (!new) - return -ENOMEM; - - /* Set all old bits, clear all new bits */ - memset(new->map, (int)0xff, old_size); - memset((void *)new->map + old_size, 0, size - old_size); - - rcu_assign_pointer(pn->shrinker_map, new); - call_rcu(&old->rcu, memcg_free_shrinker_map_rcu); - } - - return 0; -} - -static void memcg_free_shrinker_maps(struct mem_cgroup *memcg) -{ - struct mem_cgroup_per_node *pn; - struct memcg_shrinker_map *map; - int nid; - - if (mem_cgroup_is_root(memcg)) - return; - - for_each_node(nid) { - pn = memcg->nodeinfo[nid]; - map = rcu_dereference_protected(pn->shrinker_map, true); - kvfree(map); - rcu_assign_pointer(pn->shrinker_map, NULL); - } -} - -static int memcg_alloc_shrinker_maps(struct mem_cgroup *memcg) -{ - struct memcg_shrinker_map *map; - int nid, size, ret = 0; - - if (mem_cgroup_is_root(memcg)) - return 0; - - mutex_lock(&memcg_shrinker_map_mutex); - size = memcg_shrinker_map_size; - for_each_node(nid) { - map = kvzalloc_node(sizeof(*map) + size, GFP_KERNEL, nid); - if (!map) { - memcg_free_shrinker_maps(memcg); - ret = -ENOMEM; - break; - } - rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, map); - } - mutex_unlock(&memcg_shrinker_map_mutex); - - return ret; -} - -int memcg_expand_shrinker_maps(int new_id) -{ - int size, old_size, ret = 0; - struct mem_cgroup *memcg; - - size = DIV_ROUND_UP(new_id + 1, BITS_PER_LONG) * sizeof(unsigned long); - old_size = memcg_shrinker_map_size; - if (size <= old_size) - return 0; - - mutex_lock(&memcg_shrinker_map_mutex); - if (!root_mem_cgroup) - goto unlock; - - for_each_mem_cgroup(memcg) { - if (mem_cgroup_is_root(memcg)) - continue; - ret = memcg_expand_one_shrinker_map(memcg, size, old_size); - if (ret) { - mem_cgroup_iter_break(NULL, memcg); - goto unlock; - } - } -unlock: - if (!ret) - memcg_shrinker_map_size = size; - mutex_unlock(&memcg_shrinker_map_mutex); - return ret; -} - -void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) -{ - if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { - struct memcg_shrinker_map *map; - - rcu_read_lock(); - map = rcu_dereference(memcg->nodeinfo[nid]->shrinker_map); - /* Pairs with smp mb in shrink_slab() */ - smp_mb__before_atomic(); - set_bit(shrinker_id, map->map); - rcu_read_unlock(); - } -} - /** * mem_cgroup_css_from_page - css of the memcg associated with a page * @page: page of interest @@ -910,7 +786,7 @@ void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) * __count_memcg_events - account VM events in a cgroup * @memcg: the memory cgroup * @idx: the event item - * @count: the number of events that occured + * @count: the number of events that occurred */ void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) @@ -1028,7 +904,7 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) rcu_read_lock(); do { /* - * Page cache insertions can happen withou an + * Page cache insertions can happen without an * actual mm context, e.g. during disk probing * on boot, loopback IO, acct() writes etc. */ @@ -1836,7 +1712,7 @@ static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg) struct mem_cgroup *iter; /* - * Be careful about under_oom underflows becase a child memcg + * Be careful about under_oom underflows because a child memcg * could have been added after mem_cgroup_mark_under_oom. */ spin_lock(&memcg_oom_lock); @@ -2008,7 +1884,7 @@ bool mem_cgroup_oom_synchronize(bool handle) /* * There is no guarantee that an OOM-lock contender * sees the wakeups triggered by the OOM kill - * uncharges. Wake any sleepers explicitely. + * uncharges. Wake any sleepers explicitly. */ memcg_oom_recover(memcg); } @@ -4488,7 +4364,7 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, * Foreign dirty flushing * * There's an inherent mismatch between memcg and writeback. The former - * trackes ownership per-page while the latter per-inode. This was a + * tracks ownership per-page while the latter per-inode. This was a * deliberate design decision because honoring per-page ownership in the * writeback path is complicated, may lead to higher CPU and IO overheads * and deemed unnecessary given that write-sharing an inode across @@ -4503,9 +4379,9 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, * triggering background writeback. A will be slowed down without a way to * make writeback of the dirty pages happen. * - * Conditions like the above can lead to a cgroup getting repatedly and + * Conditions like the above can lead to a cgroup getting repeatedly and * severely throttled after making some progress after each - * dirty_expire_interval while the underyling IO device is almost + * dirty_expire_interval while the underlying IO device is almost * completely idle. * * Solving this problem completely requires matching the ownership tracking @@ -5242,11 +5118,11 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css) struct mem_cgroup *memcg = mem_cgroup_from_css(css); /* - * A memcg must be visible for memcg_expand_shrinker_maps() + * A memcg must be visible for expand_shrinker_info() * by the time the maps are allocated. So, we allocate maps * here, when for_each_mem_cgroup() can't skip it. */ - if (memcg_alloc_shrinker_maps(memcg)) { + if (alloc_shrinker_info(memcg)) { mem_cgroup_id_remove(memcg); return -ENOMEM; } @@ -5278,6 +5154,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) page_counter_set_low(&memcg->memory, 0); memcg_offline_kmem(memcg); + reparent_shrinker_deferred(memcg); wb_memcg_offline(memcg); drain_all_stock(memcg); @@ -5310,7 +5187,7 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css) vmpressure_cleanup(&memcg->vmpressure); cancel_work_sync(&memcg->high_work); mem_cgroup_remove_from_trees(memcg); - memcg_free_shrinker_maps(memcg); + free_shrinker_info(memcg); memcg_free_kmem(memcg); mem_cgroup_free(memcg); } @@ -5897,7 +5774,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) return 0; /* - * We are now commited to this value whatever it is. Changes in this + * We are now committed to this value whatever it is. Changes in this * tunable will only affect upcoming migrations, not the current one. * So we need to save it, and keep it going. */ diff --git a/mm/memory-failure.c b/mm/memory-failure.c index bd3945446d47..85ad98c00fd9 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -75,7 +75,7 @@ static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, boo if (dissolve_free_huge_page(page) || !take_page_off_buddy(page)) /* * We could fail to take off the target page from buddy - * for example due to racy page allocaiton, but that's + * for example due to racy page allocation, but that's * acceptable because soft-offlined page is not broken * and if someone really want to use it, they should * take it. diff --git a/mm/memory.c b/mm/memory.c index cbdc2cd9cedb..730daa00952b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3339,7 +3339,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) } - delayacct_set_flag(DELAYACCT_PF_SWAPIN); + delayacct_set_flag(current, DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry, vma, vmf->address); swapcache = page; @@ -3388,7 +3388,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) ret = VM_FAULT_OOM; - delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN); goto unlock; } @@ -3402,13 +3402,13 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) * owner processes (which may be unknown at hwpoison time) */ ret = VM_FAULT_HWPOISON; - delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN); goto out_release; } locked = lock_page_or_retry(page, vma->vm_mm, vmf->flags); - delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN); if (!locked) { ret |= VM_FAULT_RETRY; goto out_release; @@ -3727,7 +3727,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) return ret; /* - * Archs like ppc64 need additonal space to store information + * Archs like ppc64 need additional space to store information * related to pte entry. Use the preallocated table for that. */ if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) { @@ -4503,7 +4503,7 @@ retry_pud: } /** - * mm_account_fault - Do page fault accountings + * mm_account_fault - Do page fault accounting * * @regs: the pt_regs struct pointer. When set to NULL, will skip accounting * of perf event counters, but we'll still do the per-task accounting to @@ -4512,9 +4512,9 @@ retry_pud: * @flags: the fault flags. * @ret: the fault retcode. * - * This will take care of most of the page fault accountings. Meanwhile, it + * This will take care of most of the page fault accounting. Meanwhile, it * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter - * updates. However note that the handling of PERF_COUNT_SW_PAGE_FAULTS should + * updates. However, note that the handling of PERF_COUNT_SW_PAGE_FAULTS should * still be in per-arch page fault handlers at the entry of page fault. */ static inline void mm_account_fault(struct pt_regs *regs, @@ -4848,7 +4848,7 @@ out: /** * generic_access_phys - generic implementation for iomem mmap access * @vma: the vma to access - * @addr: userspace addres, not relative offset within @vma + * @addr: userspace address, not relative offset within @vma * @buf: buffer to read/write * @len: length of transfer * @write: set to FOLL_WRITE when writing, otherwise reading diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 0cdbbfbc5757..70620d0dd923 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -42,6 +42,16 @@ #include "internal.h" #include "shuffle.h" + +/* + * memory_hotplug.memmap_on_memory parameter + */ +static bool memmap_on_memory __ro_after_init; +#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY +module_param(memmap_on_memory, bool, 0444); +MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug"); +#endif + /* * online_page_callback contains pointer to current page onlining function. * Initially it is generic_online_page(). If it is required it could be @@ -648,9 +658,16 @@ static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages) * decide to not expose all pages to the buddy (e.g., expose them * later). We account all pages as being online and belonging to this * zone ("present"). + * When using memmap_on_memory, the range might not be aligned to + * MAX_ORDER_NR_PAGES - 1, but pageblock aligned. __ffs() will detect + * this and the first chunk to online will be pageblock_nr_pages. */ - for (pfn = start_pfn; pfn < end_pfn; pfn += MAX_ORDER_NR_PAGES) - (*online_page_callback)(pfn_to_page(pfn), MAX_ORDER - 1); + for (pfn = start_pfn; pfn < end_pfn;) { + int order = min(MAX_ORDER - 1UL, __ffs(pfn)); + + (*online_page_callback)(pfn_to_page(pfn), order); + pfn += (1UL << order); + } /* mark all involved sections as online */ online_mem_sections(start_pfn, end_pfn); @@ -817,7 +834,7 @@ static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn return movable_node_enabled ? movable_zone : kernel_zone; } -struct zone * zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, +struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, unsigned long nr_pages) { if (online_type == MMOP_ONLINE_KERNEL) @@ -829,24 +846,86 @@ struct zone * zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, return default_zone_for_pfn(nid, start_pfn, nr_pages); } -int __ref online_pages(unsigned long pfn, unsigned long nr_pages, - int online_type, int nid) +/* + * This function should only be called by memory_block_{online,offline}, + * and {online,offline}_pages. + */ +void adjust_present_page_count(struct zone *zone, long nr_pages) +{ + unsigned long flags; + + zone->present_pages += nr_pages; + pgdat_resize_lock(zone->zone_pgdat, &flags); + zone->zone_pgdat->node_present_pages += nr_pages; + pgdat_resize_unlock(zone->zone_pgdat, &flags); +} + +int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, + struct zone *zone) +{ + unsigned long end_pfn = pfn + nr_pages; + int ret; + + ret = kasan_add_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); + if (ret) + return ret; + + move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_UNMOVABLE); + + /* + * It might be that the vmemmap_pages fully span sections. If that is + * the case, mark those sections online here as otherwise they will be + * left offline. + */ + if (nr_pages >= PAGES_PER_SECTION) + online_mem_sections(pfn, ALIGN_DOWN(end_pfn, PAGES_PER_SECTION)); + + return ret; +} + +void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages) +{ + unsigned long end_pfn = pfn + nr_pages; + + /* + * It might be that the vmemmap_pages fully span sections. If that is + * the case, mark those sections offline here as otherwise they will be + * left online. + */ + if (nr_pages >= PAGES_PER_SECTION) + offline_mem_sections(pfn, ALIGN_DOWN(end_pfn, PAGES_PER_SECTION)); + + /* + * The pages associated with this vmemmap have been offlined, so + * we can reset its state here. + */ + remove_pfn_range_from_zone(page_zone(pfn_to_page(pfn)), pfn, nr_pages); + kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); +} + +int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone) { unsigned long flags; - struct zone *zone; int need_zonelists_rebuild = 0; + const int nid = zone_to_nid(zone); int ret; struct memory_notify arg; - /* We can only online full sections (e.g., SECTION_IS_ONLINE) */ + /* + * {on,off}lining is constrained to full memory sections (or more + * precisly to memory blocks from the user space POV). + * memmap_on_memory is an exception because it reserves initial part + * of the physical memory space for vmemmaps. That space is pageblock + * aligned. + */ if (WARN_ON_ONCE(!nr_pages || - !IS_ALIGNED(pfn | nr_pages, PAGES_PER_SECTION))) + !IS_ALIGNED(pfn, pageblock_nr_pages) || + !IS_ALIGNED(pfn + nr_pages, PAGES_PER_SECTION))) return -EINVAL; mem_hotplug_begin(); /* associate pfn range with the zone */ - zone = zone_for_pfn_range(online_type, nid, pfn, nr_pages); move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE); arg.start_pfn = pfn; @@ -877,11 +956,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, } online_pages_range(pfn, nr_pages); - zone->present_pages += nr_pages; - - pgdat_resize_lock(zone->zone_pgdat, &flags); - zone->zone_pgdat->node_present_pages += nr_pages; - pgdat_resize_unlock(zone->zone_pgdat, &flags); + adjust_present_page_count(zone, nr_pages); node_states_set_node(nid, &arg); if (need_zonelists_rebuild) @@ -1064,6 +1139,45 @@ static int online_memory_block(struct memory_block *mem, void *arg) return device_online(&mem->dev); } +bool mhp_supports_memmap_on_memory(unsigned long size) +{ + unsigned long nr_vmemmap_pages = size / PAGE_SIZE; + unsigned long vmemmap_size = nr_vmemmap_pages * sizeof(struct page); + unsigned long remaining_size = size - vmemmap_size; + + /* + * Besides having arch support and the feature enabled at runtime, we + * need a few more assumptions to hold true: + * + * a) We span a single memory block: memory onlining/offlinin;g happens + * in memory block granularity. We don't want the vmemmap of online + * memory blocks to reside on offline memory blocks. In the future, + * we might want to support variable-sized memory blocks to make the + * feature more versatile. + * + * b) The vmemmap pages span complete PMDs: We don't want vmemmap code + * to populate memory from the altmap for unrelated parts (i.e., + * other memory blocks) + * + * c) The vmemmap pages (and thereby the pages that will be exposed to + * the buddy) have to cover full pageblocks: memory onlining/offlining + * code requires applicable ranges to be page-aligned, for example, to + * set the migratetypes properly. + * + * TODO: Although we have a check here to make sure that vmemmap pages + * fully populate a PMD, it is not the right place to check for + * this. A much better solution involves improving vmemmap code + * to fallback to base pages when trying to populate vmemmap using + * altmap as an alternative source of memory, and we do not exactly + * populate a single PMD. + */ + return memmap_on_memory && + IS_ENABLED(CONFIG_MHP_MEMMAP_ON_MEMORY) && + size == memory_block_size_bytes() && + IS_ALIGNED(vmemmap_size, PMD_SIZE) && + IS_ALIGNED(remaining_size, (pageblock_nr_pages << PAGE_SHIFT)); +} + /* * NOTE: The caller must call lock_device_hotplug() to serialize hotplug * and online/offline operations (triggered e.g. by sysfs). @@ -1073,6 +1187,7 @@ static int online_memory_block(struct memory_block *mem, void *arg) int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) { struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) }; + struct vmem_altmap mhp_altmap = {}; u64 start, size; bool new_node = false; int ret; @@ -1099,13 +1214,26 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) goto error; new_node = ret; + /* + * Self hosted memmap array + */ + if (mhp_flags & MHP_MEMMAP_ON_MEMORY) { + if (!mhp_supports_memmap_on_memory(size)) { + ret = -EINVAL; + goto error; + } + mhp_altmap.free = PHYS_PFN(size); + mhp_altmap.base_pfn = PHYS_PFN(start); + params.altmap = &mhp_altmap; + } + /* call arch's memory hotadd */ ret = arch_add_memory(nid, start, size, ¶ms); if (ret < 0) goto error; /* create memory block devices after memory was added */ - ret = create_memory_block_devices(start, size); + ret = create_memory_block_devices(start, size, mhp_altmap.alloc); if (ret) { arch_remove_memory(nid, start, size, NULL); goto error; @@ -1573,9 +1701,16 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) int ret, node; char *reason; - /* We can only offline full sections (e.g., SECTION_IS_ONLINE) */ + /* + * {on,off}lining is constrained to full memory sections (or more + * precisly to memory blocks from the user space POV). + * memmap_on_memory is an exception because it reserves initial part + * of the physical memory space for vmemmaps. That space is pageblock + * aligned. + */ if (WARN_ON_ONCE(!nr_pages || - !IS_ALIGNED(start_pfn | nr_pages, PAGES_PER_SECTION))) + !IS_ALIGNED(start_pfn, pageblock_nr_pages) || + !IS_ALIGNED(start_pfn + nr_pages, PAGES_PER_SECTION))) return -EINVAL; mem_hotplug_begin(); @@ -1611,6 +1746,7 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) * in a way that pages from isolated pageblock are left on pcplists. */ zone_pcp_disable(zone); + lru_cache_disable(); /* set above range as isolated */ ret = start_isolate_page_range(start_pfn, end_pfn, @@ -1642,7 +1778,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) } cond_resched(); - lru_add_drain_all(); ret = scan_movable_pages(pfn, end_pfn, &pfn); if (!ret) { @@ -1687,15 +1822,12 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) zone->nr_isolate_pageblock -= nr_pages / pageblock_nr_pages; spin_unlock_irqrestore(&zone->lock, flags); + lru_cache_enable(); zone_pcp_enable(zone); /* removal success */ adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages); - zone->present_pages -= nr_pages; - - pgdat_resize_lock(zone->zone_pgdat, &flags); - zone->zone_pgdat->node_present_pages -= nr_pages; - pgdat_resize_unlock(zone->zone_pgdat, &flags); + adjust_present_page_count(zone, -nr_pages); init_per_zone_wmark_min(); @@ -1750,6 +1882,14 @@ static int check_memblock_offlined_cb(struct memory_block *mem, void *arg) return 0; } +static int get_nr_vmemmap_pages_cb(struct memory_block *mem, void *arg) +{ + /* + * If not set, continue with the next block. + */ + return mem->nr_vmemmap_pages; +} + static int check_cpu_on_node(pg_data_t *pgdat) { int cpu; @@ -1824,6 +1964,9 @@ EXPORT_SYMBOL(try_offline_node); static int __ref try_remove_memory(int nid, u64 start, u64 size) { int rc = 0; + struct vmem_altmap mhp_altmap = {}; + struct vmem_altmap *altmap = NULL; + unsigned long nr_vmemmap_pages; BUG_ON(check_hotplug_memory_range(start, size)); @@ -1836,6 +1979,31 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) if (rc) return rc; + /* + * We only support removing memory added with MHP_MEMMAP_ON_MEMORY in + * the same granularity it was added - a single memory block. + */ + if (memmap_on_memory) { + nr_vmemmap_pages = walk_memory_blocks(start, size, NULL, + get_nr_vmemmap_pages_cb); + if (nr_vmemmap_pages) { + if (size != memory_block_size_bytes()) { + pr_warn("Refuse to remove %#llx - %#llx," + "wrong granularity\n", + start, start + size); + return -EINVAL; + } + + /* + * Let remove_pmd_table->free_hugepage_table do the + * right thing if we used vmem_altmap when hot-adding + * the range. + */ + mhp_altmap.alloc = nr_vmemmap_pages; + altmap = &mhp_altmap; + } + } + /* remove memmap entry */ firmware_map_remove(start, start + size, "System RAM"); @@ -1847,7 +2015,7 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) mem_hotplug_begin(); - arch_remove_memory(nid, start, size, NULL); + arch_remove_memory(nid, start, size, altmap); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { memblock_free(start, size); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index cd0295567a04..d79fa299b70c 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -330,7 +330,7 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) else if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); else { - nodes_remap(tmp, pol->v.nodes,pol->w.cpuset_mems_allowed, + nodes_remap(tmp, pol->v.nodes, pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } @@ -994,7 +994,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, if (flags & MPOL_F_ADDR) { /* * Take a refcount on the mpol, lookup_node() - * wil drop the mmap_lock, so after calling + * will drop the mmap_lock, so after calling * lookup_node() only "pol" remains valid, "vma" * is stale. */ @@ -1124,7 +1124,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, int err = 0; nodemask_t tmp; - migrate_prep(); + lru_cache_disable(); mmap_read_lock(mm); @@ -1161,7 +1161,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, tmp = *from; while (!nodes_empty(tmp)) { - int s,d; + int s, d; int source = NUMA_NO_NODE; int dest = 0; @@ -1208,6 +1208,8 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, break; } mmap_read_unlock(mm); + + lru_cache_enable(); if (err < 0) return err; return busy; @@ -1323,7 +1325,7 @@ static long do_mbind(unsigned long start, unsigned long len, if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - migrate_prep(); + lru_cache_disable(); } { NODEMASK_SCRATCH(scratch); @@ -1371,6 +1373,8 @@ up_out: mmap_write_unlock(mm); mpol_out: mpol_put(new); + if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) + lru_cache_enable(); return err; } @@ -1863,7 +1867,7 @@ static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone) * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. * * policy->v.nodes is intersect with node_states[N_MEMORY]. - * so if the following test faile, it implies + * so if the following test fails, it implies * policy->v.nodes has movable memory only. */ if (!nodes_intersects(policy->v.nodes, node_states[N_HIGH_MEMORY])) @@ -2094,7 +2098,7 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask) * * If tsk's mempolicy is "default" [NULL], return 'true' to indicate default * policy. Otherwise, check for intersection between mask and the policy - * nodemask for 'bind' or 'interleave' policy. For 'perferred' or 'local' + * nodemask for 'bind' or 'interleave' policy. For 'preferred' or 'local' * policy, always return true since it may allocate elsewhere on fallback. * * Takes task_lock(tsk) to prevent freeing of its mempolicy. diff --git a/mm/mempool.c b/mm/mempool.c index fe19d290a301..a258cf4de575 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -251,7 +251,7 @@ EXPORT_SYMBOL(mempool_init); mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data) { - return mempool_create_node(min_nr,alloc_fn,free_fn, pool_data, + return mempool_create_node(min_nr, alloc_fn, free_fn, pool_data, GFP_KERNEL, NUMA_NO_NODE); } EXPORT_SYMBOL(mempool_create); diff --git a/mm/migrate.c b/mm/migrate.c index 47df0df8f21a..b234c3f3acb7 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -57,28 +57,6 @@ #include "internal.h" -/* - * migrate_prep() needs to be called before we start compiling a list of pages - * to be migrated using isolate_lru_page(). If scheduling work on other CPUs is - * undesirable, use migrate_prep_local() - */ -void migrate_prep(void) -{ - /* - * Clear the LRU lists so pages can be isolated. - * Note that pages may be moved off the LRU after we have - * drained them. Those pages will fail to migrate like other - * pages that may be busy. - */ - lru_add_drain_all(); -} - -/* Do the necessary work of migrate_prep but not if it involves other CPUs */ -void migrate_prep_local(void) -{ - lru_add_drain(); -} - int isolate_movable_page(struct page *page, isolate_mode_t mode) { struct address_space *mapping; @@ -140,15 +118,10 @@ out: return -EBUSY; } -/* It should be called on page which is PG_movable */ -void putback_movable_page(struct page *page) +static void putback_movable_page(struct page *page) { struct address_space *mapping; - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(!PageMovable(page), page); - VM_BUG_ON_PAGE(!PageIsolated(page), page); - mapping = page_mapping(page); mapping->a_ops->putback_page(page); __ClearPageIsolated(page); @@ -1375,7 +1348,7 @@ out_unlock: out: if (rc == MIGRATEPAGE_SUCCESS) putback_active_hugepage(hpage); - else if (rc != -EAGAIN && rc != MIGRATEPAGE_SUCCESS) + else if (rc != -EAGAIN) list_move_tail(&hpage->lru, ret); /* @@ -1445,6 +1418,8 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, int rc, nr_subpages; LIST_HEAD(ret_pages); + trace_mm_migrate_pages_start(mode, reason); + if (!swapwrite) current->flags |= PF_SWAPWRITE; @@ -1769,7 +1744,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, int start, i; int err = 0, err1; - migrate_prep(); + lru_cache_disable(); for (i = start = 0; i < nr_pages; i++) { const void __user *p; @@ -1838,6 +1813,7 @@ out_flush: if (err >= 0) err = err1; out: + lru_cache_enable(); return err; } @@ -2110,17 +2086,6 @@ bool pmd_trans_migrating(pmd_t pmd) return PageLocked(page); } -static inline bool is_shared_exec_page(struct vm_area_struct *vma, - struct page *page) -{ - if (page_mapcount(page) != 1 && - (page_is_file_lru(page) || vma_is_shmem(vma)) && - (vma->vm_flags & VM_EXEC)) - return true; - - return false; -} - /* * Attempt to migrate a misplaced page to the specified destination * node. Caller is expected to have an elevated reference count on @@ -2138,7 +2103,8 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, * Don't migrate file pages that are mapped in multiple processes * with execute permissions as they are probably shared libraries. */ - if (is_shared_exec_page(vma, page)) + if (page_mapcount(page) != 1 && page_is_file_lru(page) && + (vma->vm_flags & VM_EXEC)) goto out; /* @@ -2193,9 +2159,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, int page_lru = page_is_file_lru(page); unsigned long start = address & HPAGE_PMD_MASK; - if (is_shared_exec_page(vma, page)) - goto out; - new_page = alloc_pages_node(node, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), HPAGE_PMD_ORDER); @@ -2307,7 +2270,6 @@ out_fail: out_unlock: unlock_page(page); -out: put_page(page); return 0; } @@ -2316,44 +2278,38 @@ out: #endif /* CONFIG_NUMA */ #ifdef CONFIG_DEVICE_PRIVATE -static int migrate_vma_collect_hole(unsigned long start, +static int migrate_vma_collect_skip(unsigned long start, unsigned long end, - __always_unused int depth, struct mm_walk *walk) { struct migrate_vma *migrate = walk->private; unsigned long addr; - /* Only allow populating anonymous memory. */ - if (!vma_is_anonymous(walk->vma)) { - for (addr = start; addr < end; addr += PAGE_SIZE) { - migrate->src[migrate->npages] = 0; - migrate->dst[migrate->npages] = 0; - migrate->npages++; - } - return 0; - } - for (addr = start; addr < end; addr += PAGE_SIZE) { - migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE; migrate->dst[migrate->npages] = 0; - migrate->npages++; - migrate->cpages++; + migrate->src[migrate->npages++] = 0; } return 0; } -static int migrate_vma_collect_skip(unsigned long start, +static int migrate_vma_collect_hole(unsigned long start, unsigned long end, + __always_unused int depth, struct mm_walk *walk) { struct migrate_vma *migrate = walk->private; unsigned long addr; + /* Only allow populating anonymous memory. */ + if (!vma_is_anonymous(walk->vma)) + return migrate_vma_collect_skip(start, end, walk); + for (addr = start; addr < end; addr += PAGE_SIZE) { + migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE; migrate->dst[migrate->npages] = 0; - migrate->src[migrate->npages++] = 0; + migrate->npages++; + migrate->cpages++; } return 0; @@ -2823,11 +2779,11 @@ restore: * * For empty entries inside CPU page table (pte_none() or pmd_none() is true) we * do set MIGRATE_PFN_MIGRATE flag inside the corresponding source array thus - * allowing the caller to allocate device memory for those unback virtual - * address. For this the caller simply has to allocate device memory and + * allowing the caller to allocate device memory for those unbacked virtual + * addresses. For this the caller simply has to allocate device memory and * properly set the destination entry like for regular migration. Note that - * this can still fails and thus inside the device driver must check if the - * migration was successful for those entries after calling migrate_vma_pages() + * this can still fail, and thus inside the device driver you must check if the + * migration was successful for those entries after calling migrate_vma_pages(), * just like for regular migration. * * After that, the callers must call migrate_vma_pages() to go over each entry @@ -2973,6 +2929,13 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE); entry = swp_entry_to_pte(swp_entry); + } else { + /* + * For now we only support migrating to un-addressable + * device memory. + */ + pr_warn_once("Unsupported ZONE_DEVICE page type.\n"); + goto abort; } } else { entry = mk_pte(page, vma->vm_page_prot); diff --git a/mm/mlock.c b/mm/mlock.c index f8f8cc32d03d..df590fda5688 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -559,7 +559,7 @@ static int apply_vma_lock_flags(unsigned long start, size_t len, vm_flags_t flags) { unsigned long nstart, end, tmp; - struct vm_area_struct * vma, * prev; + struct vm_area_struct *vma, *prev; int error; VM_BUG_ON(offset_in_page(start)); @@ -737,7 +737,7 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) */ static int apply_mlockall_flags(int flags) { - struct vm_area_struct * vma, * prev = NULL; + struct vm_area_struct *vma, *prev = NULL; vm_flags_t to_add = 0; current->mm->def_flags &= VM_LOCKED_CLEAR_MASK; diff --git a/mm/mmap.c b/mm/mmap.c index 347ef9b83bb5..0584e540246e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -612,7 +612,7 @@ static unsigned long count_vma_pages_range(struct mm_struct *mm, unsigned long nr_pages = 0; struct vm_area_struct *vma; - /* Find first overlaping mapping */ + /* Find first overlapping mapping */ vma = find_vma_intersection(mm, addr, end); if (!vma) return 0; @@ -2875,7 +2875,7 @@ int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, if (unlikely(uf)) { /* * If userfaultfd_unmap_prep returns an error the vmas - * will remain splitted, but userland will get a + * will remain split, but userland will get a * highly unexpected error anyway. This is no * different than the case where the first of the two * __split_vma fails, but we don't undo the first @@ -3029,25 +3029,9 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, flags &= MAP_NONBLOCK; flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; - if (vma->vm_flags & VM_LOCKED) { - struct vm_area_struct *tmp; + if (vma->vm_flags & VM_LOCKED) flags |= MAP_LOCKED; - /* drop PG_Mlocked flag for over-mapped range */ - for (tmp = vma; tmp->vm_start >= start + size; - tmp = tmp->vm_next) { - /* - * Split pmd and munlock page on the border - * of the range. - */ - vma_adjust_trans_huge(tmp, start, start + size, 0); - - munlock_vma_pages_range(tmp, - max(tmp->vm_start, start), - min(tmp->vm_end, start + size)); - } - } - file = get_file(vma->vm_file); ret = do_mmap(vma->vm_file, start, size, prot, flags, pgoff, &populate, NULL); diff --git a/mm/mprotect.c b/mm/mprotect.c index 94188df1ee55..e7a443157988 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -699,7 +699,7 @@ SYSCALL_DEFINE1(pkey_free, int, pkey) mmap_write_unlock(current->mm); /* - * We could provie warnings or errors if any VMA still + * We could provide warnings or errors if any VMA still * has the pkey set here. */ return ret; diff --git a/mm/mremap.c b/mm/mremap.c index d22629ff8f3c..47c255b60150 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -730,7 +730,7 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len, * So, to avoid such scenario we can pre-compute if the whole * operation has high chances to success map-wise. * Worst-scenario case is when both vma's (new_addr and old_addr) get - * split in 3 before unmaping it. + * split in 3 before unmapping it. * That means 2 more maps (1 for each) to the ones we already hold. * Check whether current map count plus 2 still leads us to 4 maps below * the threshold, otherwise return -ENOMEM here to be more safe. diff --git a/mm/nommu.c b/mm/nommu.c index 5c9ab799c0e6..85a3a68dffb6 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -210,16 +210,6 @@ long vread(char *buf, char *addr, unsigned long count) return count; } -long vwrite(char *buf, char *addr, unsigned long count) -{ - /* Don't allow overflow */ - if ((unsigned long) addr + count < count) - count = -(unsigned long) addr; - - memcpy(addr, buf, count); - return count; -} - /* * vmalloc - allocate virtually contiguous memory * diff --git a/mm/oom_kill.c b/mm/oom_kill.c index fa1cf18bac97..eefd3f5fde46 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -74,7 +74,7 @@ static inline bool is_memcg_oom(struct oom_control *oc) #ifdef CONFIG_NUMA /** - * oom_cpuset_eligible() - check task eligiblity for kill + * oom_cpuset_eligible() - check task eligibility for kill * @start: task struct of which task to consider * @oc: pointer to struct oom_control * @@ -993,7 +993,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) if (oom_group) { mem_cgroup_print_oom_group(oom_group); mem_cgroup_scan_tasks(oom_group, oom_kill_memcg_member, - (void*)message); + (void *)message); mem_cgroup_put(oom_group); } } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 5e761fb62800..0062d5c57d41 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1806,7 +1806,7 @@ pause: break; /* - * In the case of an unresponding NFS server and the NFS dirty + * In the case of an unresponsive NFS server and the NFS dirty * pages exceeds dirty_thresh, give the other good wb's a pipe * to go through, so that tasks on them still remain responsive. * @@ -2216,7 +2216,7 @@ int write_cache_pages(struct address_space *mapping, * Page truncated or invalidated. We can freely skip it * then, even for data integrity operations: the page * has disappeared concurrently, so there could be no - * real expectation of this data interity operation + * real expectation of this data integrity operation * even if there is now a new, dirty page at the same * pagecache address. */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6b208b1843bf..aaa1655cf682 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -893,7 +893,7 @@ compaction_capture(struct capture_control *capc, struct page *page, return false; /* - * Do not let lower order allocations polluate a movable pageblock. + * Do not let lower order allocations pollute a movable pageblock. * This might let an unmovable request use a reclaimable pageblock * and vice-versa but no more than normal fallback logic which can * have trouble finding a high-order free page. @@ -2776,7 +2776,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, /* * In page freeing path, migratetype change is racy so * we can counter several free pages in a pageblock - * in this loop althoug we changed the pageblock type + * in this loop although we changed the pageblock type * from highatomic to ac->migratetype. So we should * adjust the count once. */ @@ -3080,7 +3080,7 @@ static void drain_local_pages_wq(struct work_struct *work) * drain_all_pages doesn't use proper cpu hotplug protection so * we can race with cpu offline when the WQ can move this from * a cpu pinned worker to an unbound one. We can operate on a different - * cpu which is allright but we also have to make sure to not move to + * cpu which is alright but we also have to make sure to not move to * a different one. */ preempt_disable(); @@ -3859,16 +3859,13 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask) return alloc_flags; } -static inline unsigned int current_alloc_flags(gfp_t gfp_mask, - unsigned int alloc_flags) +/* Must be called after current_gfp_context() which can change gfp_mask */ +static inline unsigned int gfp_to_alloc_flags_cma(gfp_t gfp_mask, + unsigned int alloc_flags) { #ifdef CONFIG_CMA - unsigned int pflags = current->flags; - - if (!(pflags & PF_MEMALLOC_NOCMA) && - gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE) + if (gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE) alloc_flags |= ALLOC_CMA; - #endif return alloc_flags; } @@ -3968,7 +3965,7 @@ retry: if (alloc_flags & ALLOC_NO_WATERMARKS) goto try_this_zone; - if (node_reclaim_mode == 0 || + if (!node_reclaim_enabled() || !zone_allows_reclaim(ac->preferred_zoneref->zone, zone)) continue; @@ -4176,7 +4173,7 @@ out: } /* - * Maximum number of compaction retries wit a progress before OOM + * Maximum number of compaction retries with a progress before OOM * killer is consider as the only way to move forward. */ #define MAX_COMPACT_RETRIES 16 @@ -4204,6 +4201,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, memalloc_noreclaim_restore(noreclaim_flag); psi_memstall_leave(&pflags); + if (*compact_result == COMPACT_SKIPPED) + return NULL; /* * At least in one zone compaction wasn't deferred or skipped, so let's * count a compaction stall @@ -4524,7 +4523,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask) } else if (unlikely(rt_task(current)) && !in_interrupt()) alloc_flags |= ALLOC_HARDER; - alloc_flags = current_alloc_flags(gfp_mask, alloc_flags); + alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, alloc_flags); return alloc_flags; } @@ -4826,7 +4825,7 @@ retry: reserve_flags = __gfp_pfmemalloc_flags(gfp_mask); if (reserve_flags) - alloc_flags = current_alloc_flags(gfp_mask, reserve_flags); + alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, reserve_flags); /* * Reset the nodemask and zonelist iterators if memory policies can be @@ -4995,7 +4994,7 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order, if (should_fail_alloc_page(gfp_mask, order)) return false; - *alloc_flags = current_alloc_flags(gfp_mask, *alloc_flags); + *alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, *alloc_flags); /* Dirty zone balancing only done in the fast path */ ac->spread_dirty_pages = (gfp_mask & __GFP_WRITE); @@ -5178,6 +5177,14 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, } gfp &= gfp_allowed_mask; + /* + * Apply scoped allocation constraints. This is mainly about GFP_NOFS + * resp. GFP_NOIO which has to be inherited for all allocation requests + * from a particular context which has been marked by + * memalloc_no{fs,io}_{save,restore}. And PF_MEMALLOC_PIN which ensures + * movable zones are not used during allocation. + */ + gfp = current_gfp_context(gfp); alloc_gfp = gfp; if (!prepare_alloc_pages(gfp, order, preferred_nid, nodemask, &ac, &alloc_gfp, &alloc_flags)) @@ -5194,13 +5201,7 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, if (likely(page)) goto out; - /* - * Apply scoped allocation constraints. This is mainly about GFP_NOFS - * resp. GFP_NOIO which has to be inherited for all allocation requests - * from a particular context which has been marked by - * memalloc_no{fs,io}_{save,restore}. - */ - alloc_gfp = current_gfp_context(gfp); + alloc_gfp = gfp; ac.spread_dirty_pages = false; /* @@ -5928,7 +5929,7 @@ static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs) static int __parse_numa_zonelist_order(char *s) { /* - * We used to support different zonlists modes but they turned + * We used to support different zonelists modes but they turned * out to be just not useful. Let's keep the warning in place * if somebody still use the cmd line parameter so that we do * not fail it silently @@ -7669,7 +7670,7 @@ static void check_for_memory(pg_data_t *pgdat, int nid) } /* - * Some architecturs, e.g. ARC may have ZONE_HIGHMEM below ZONE_NORMAL. For + * Some architectures, e.g. ARC may have ZONE_HIGHMEM below ZONE_NORMAL. For * such cases we allow max_zone_pfn sorted in the descending order */ bool __weak arch_has_descending_max_zone_pfns(void) @@ -8679,7 +8680,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, }; - migrate_prep(); + lru_cache_disable(); while (pfn < end || !list_empty(&cc->migratepages)) { if (fatal_signal_pending(current)) { @@ -8689,14 +8690,13 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, if (list_empty(&cc->migratepages)) { cc->nr_migratepages = 0; - pfn = isolate_migratepages_range(cc, pfn, end); - if (!pfn) { - ret = -EINTR; + ret = isolate_migratepages_range(cc, pfn, end); + if (ret && ret != -EAGAIN) break; - } + pfn = cc->migrate_pfn; tries = 0; } else if (++tries == 5) { - ret = ret < 0 ? ret : -EBUSY; + ret = -EBUSY; break; } @@ -8706,7 +8706,16 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, ret = migrate_pages(&cc->migratepages, alloc_migration_target, NULL, (unsigned long)&mtc, cc->mode, MR_CONTIG_RANGE); + + /* + * On -ENOMEM, migrate_pages() bails out right away. It is pointless + * to retry again over this error, so do the same here. + */ + if (ret == -ENOMEM) + break; } + + lru_cache_enable(); if (ret < 0) { alloc_contig_dump_pages(&cc->migratepages); putback_movable_pages(&cc->migratepages); @@ -8719,7 +8728,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, * alloc_contig_range() -- tries to allocate given range of pages * @start: start PFN to allocate * @end: one-past-the-last PFN to allocate - * @migratetype: migratetype of the underlaying pageblocks (either + * @migratetype: migratetype of the underlying pageblocks (either * #MIGRATE_MOVABLE or #MIGRATE_CMA). All pageblocks * in range must have the same migratetype and it must * be either of the two. @@ -8799,7 +8808,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, ret = __alloc_contig_migrate_range(&cc, start, end); if (ret && ret != -EBUSY) goto done; - ret =0; + ret = 0; /* * Pages from [start, end) are within a MAX_ORDER_NR_PAGES @@ -8892,12 +8901,6 @@ static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn, if (PageReserved(page)) return false; - - if (page_count(page) > 0) - return false; - - if (PageHuge(page)) - return false; } return true; } @@ -8969,9 +8972,9 @@ struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, } #endif /* CONFIG_CONTIG_ALLOC */ -void free_contig_range(unsigned long pfn, unsigned int nr_pages) +void free_contig_range(unsigned long pfn, unsigned long nr_pages) { - unsigned int count = 0; + unsigned long count = 0; for (; nr_pages--; pfn++) { struct page *page = pfn_to_page(pfn); @@ -8979,13 +8982,13 @@ void free_contig_range(unsigned long pfn, unsigned int nr_pages) count += page_count(page) != 1; __free_page(page); } - WARN(count != 0, "%d pages are still in use!\n", count); + WARN(count != 0, "%lu pages are still in use!\n", count); } EXPORT_SYMBOL(free_contig_range); /* * The zone indicated has a new number of managed_pages; batch sizes and percpu - * page high values need to be recalulated. + * page high values need to be recalculated. */ void __meminit zone_pcp_update(struct zone *zone) { @@ -9017,12 +9020,9 @@ void zone_pcp_enable(struct zone *zone) void zone_pcp_reset(struct zone *zone) { - unsigned long flags; int cpu; struct per_cpu_pageset *pset; - /* avoid races with drain_pages() */ - local_irq_save(flags); if (zone->pageset != &boot_pageset) { for_each_online_cpu(cpu) { pset = per_cpu_ptr(zone->pageset, cpu); @@ -9031,7 +9031,6 @@ void zone_pcp_reset(struct zone *zone) free_percpu(zone->pageset); zone->pageset = &boot_pageset; } - local_irq_restore(flags); } #ifdef CONFIG_MEMORY_HOTREMOVE diff --git a/mm/page_owner.c b/mm/page_owner.c index 9661d5320a07..adfabb560eb9 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -233,7 +233,7 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage) /* * We don't clear the bit on the oldpage as it's going to be freed * after migration. Until then, the info can be useful in case of - * a bug, and the overal stats will be off a bit only temporarily. + * a bug, and the overall stats will be off a bit only temporarily. * Also, migrate_misplaced_transhuge_page() can still fail the * migration and then we want the oldpage to retain the info. But * in that case we also don't need to explicitly clear the info from diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 86e3a3688d59..2cf01d933f13 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -134,7 +134,7 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) * regardless of which page table level the page is mapped at. @pvmw->pmd is * NULL. * - * Retruns false if there are no more page table entries for the page in + * Returns false if there are no more page table entries for the page in * the vma. @pvmw->ptl is unlocked and @pvmw->pte is unmapped. * * If you need to stop the walk before page_vma_mapped_walk() returned false, diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h index 095d7eaa0db4..ae26b118e246 100644 --- a/mm/percpu-internal.h +++ b/mm/percpu-internal.h @@ -170,7 +170,7 @@ struct percpu_stats { u64 nr_max_alloc; /* max # of live allocations */ u32 nr_chunks; /* current # of live chunks */ u32 nr_max_chunks; /* max # of live chunks */ - size_t min_alloc_size; /* min allocaiton size */ + size_t min_alloc_size; /* min allocation size */ size_t max_alloc_size; /* max allocation size */ }; diff --git a/mm/percpu.c b/mm/percpu.c index 23308113a5ff..f99e9306b939 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1862,7 +1862,7 @@ fail: pr_info("limit reached, disable warning\n"); } if (is_atomic) { - /* see the flag handling in pcpu_blance_workfn() */ + /* see the flag handling in pcpu_balance_workfn() */ pcpu_atomic_alloc_failed = true; pcpu_schedule_balance_work(); } else { diff --git a/mm/pgalloc-track.h b/mm/pgalloc-track.h index 1dcc865029a2..e9e879de8649 100644 --- a/mm/pgalloc-track.h +++ b/mm/pgalloc-track.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_PGALLLC_TRACK_H -#define _LINUX_PGALLLC_TRACK_H +#ifndef _LINUX_PGALLOC_TRACK_H +#define _LINUX_PGALLOC_TRACK_H #if defined(CONFIG_MMU) static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd, @@ -48,4 +48,4 @@ static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud, (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\ NULL: pte_offset_kernel(pmd, address)) -#endif /* _LINUX_PGALLLC_TRACK_H */ +#endif /* _LINUX_PGALLOC_TRACK_H */ diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index f5fee9cf90f8..4bcc11958089 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -9,7 +9,6 @@ #include <linux/mm.h> #include <linux/uio.h> #include <linux/sched.h> -#include <linux/compat.h> #include <linux/sched/mm.h> #include <linux/highmem.h> #include <linux/ptrace.h> diff --git a/mm/rmap.c b/mm/rmap.c index b0fc27e77d6d..693a610e181d 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -257,7 +257,7 @@ static inline void unlock_anon_vma_root(struct anon_vma *root) * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. * - * anon_vma_clone() is called by __vma_split(), __split_vma(), copy_vma() and + * anon_vma_clone() is called by __vma_adjust(), __split_vma(), copy_vma() and * anon_vma_fork(). The first three want an exact copy of src, while the last * one, anon_vma_fork(), may try to reuse an existing anon_vma to prevent * endless growth of anon_vma. Since dst->anon_vma is set to NULL before call, diff --git a/mm/shmem.c b/mm/shmem.c index 162d8f8993bb..a08cedefbfaa 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3508,7 +3508,7 @@ static int shmem_parse_options(struct fs_context *fc, void *data) } } if (*this_char) { - char *value = strchr(this_char,'='); + char *value = strchr(this_char, '='); size_t len = 0; int err; diff --git a/mm/slab.c b/mm/slab.c index df45c437b394..d0f725637663 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -259,7 +259,7 @@ static void kmem_cache_node_init(struct kmem_cache_node *parent) #define BATCHREFILL_LIMIT 16 /* - * Optimization question: fewer reaps means less probability for unnessary + * Optimization question: fewer reaps means less probability for unnecessary * cpucache drain/refill cycles. * * OTOH the cpuarrays can contain lots of objects, @@ -2284,7 +2284,7 @@ void __kmem_cache_release(struct kmem_cache *cachep) * Because if it is the case, that means we defer the creation of * the kmalloc_{dma,}_cache of size sizeof(slab descriptor) to this point. * And we eventually call down to __kmem_cache_create(), which - * in turn looks up in the kmalloc_{dma,}_caches for the disired-size one. + * in turn looks up in the kmalloc_{dma,}_caches for the desired-size one. * This is a "chicken-and-egg" problem. * * So the off-slab slab descriptor shall come from the kmalloc_{dma,}_caches, @@ -2381,8 +2381,8 @@ union freelist_init_state { }; /* - * Initialize the state based on the randomization methode available. - * return true if the pre-computed list is available, false otherwize. + * Initialize the state based on the randomization method available. + * return true if the pre-computed list is available, false otherwise. */ static bool freelist_state_initialize(union freelist_init_state *state, struct kmem_cache *cachep, diff --git a/mm/slub.c b/mm/slub.c index 68123b21e65f..feda53ae62ba 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3391,7 +3391,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_bulk); */ /* - * Mininum / Maximum order of slab pages. This influences locking overhead + * Minimum / Maximum order of slab pages. This influences locking overhead * and slab fragmentation. A higher order reduces the number of partial slabs * and increases the number of allocations possible without having to * take the list_lock. diff --git a/mm/sparse.c b/mm/sparse.c index 33406ea2ecc4..b2ada9dc00cb 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -257,7 +257,7 @@ static void __init memory_present(int nid, unsigned long start, unsigned long en if (unlikely(!mem_section)) { unsigned long size, align; - size = sizeof(struct mem_section*) * NR_SECTION_ROOTS; + size = sizeof(struct mem_section *) * NR_SECTION_ROOTS; align = 1 << (INTERNODE_CACHE_SHIFT); mem_section = memblock_alloc(size, align); if (!mem_section) @@ -624,7 +624,6 @@ void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn) } } -#ifdef CONFIG_MEMORY_HOTREMOVE /* Mark all memory sections within the pfn range as offline */ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn) { @@ -645,7 +644,6 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn) ms->section_mem_map &= ~SECTION_IS_ONLINE; } } -#endif #ifdef CONFIG_SPARSEMEM_VMEMMAP static struct page * __meminit populate_section_memmap(unsigned long pfn, diff --git a/mm/swap.c b/mm/swap.c index 31b844d4ed94..dfb48cf9c2c9 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -36,6 +36,7 @@ #include <linux/hugetlb.h> #include <linux/page_idle.h> #include <linux/local_lock.h> +#include <linux/buffer_head.h> #include "internal.h" @@ -235,6 +236,18 @@ static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec) } } +/* return true if pagevec needs to drain */ +static bool pagevec_add_and_need_flush(struct pagevec *pvec, struct page *page) +{ + bool ret = false; + + if (!pagevec_add(pvec, page) || PageCompound(page) || + lru_cache_disabled()) + ret = true; + + return ret; +} + /* * Writeback is about to end against a page which has been marked for immediate * reclaim. If it still appears to be reclaimable, move it to the tail of the @@ -252,7 +265,7 @@ void rotate_reclaimable_page(struct page *page) get_page(page); local_lock_irqsave(&lru_rotate.lock, flags); pvec = this_cpu_ptr(&lru_rotate.pvec); - if (!pagevec_add(pvec, page) || PageCompound(page)) + if (pagevec_add_and_need_flush(pvec, page)) pagevec_lru_move_fn(pvec, pagevec_move_tail_fn); local_unlock_irqrestore(&lru_rotate.lock, flags); } @@ -343,7 +356,7 @@ static void activate_page(struct page *page) local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.activate_page); get_page(page); - if (!pagevec_add(pvec, page) || PageCompound(page)) + if (pagevec_add_and_need_flush(pvec, page)) pagevec_lru_move_fn(pvec, __activate_page); local_unlock(&lru_pvecs.lock); } @@ -458,7 +471,7 @@ void lru_cache_add(struct page *page) get_page(page); local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_add); - if (!pagevec_add(pvec, page) || PageCompound(page)) + if (pagevec_add_and_need_flush(pvec, page)) __pagevec_lru_add(pvec); local_unlock(&lru_pvecs.lock); } @@ -483,7 +496,7 @@ void lru_cache_add_inactive_or_unevictable(struct page *page, if (unlikely(unevictable) && !TestSetPageMlocked(page)) { int nr_pages = thp_nr_pages(page); /* - * We use the irq-unsafe __mod_zone_page_stat because this + * We use the irq-unsafe __mod_zone_page_state because this * counter is not modified from interrupt context, and the pte * lock is held(spinlock), which implies preemption disabled. */ @@ -629,6 +642,7 @@ void lru_add_drain_cpu(int cpu) pagevec_lru_move_fn(pvec, lru_lazyfree_fn); activate_page_drain(cpu); + invalidate_bh_lrus_cpu(cpu); } /** @@ -654,7 +668,7 @@ void deactivate_file_page(struct page *page) local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file); - if (!pagevec_add(pvec, page) || PageCompound(page)) + if (pagevec_add_and_need_flush(pvec, page)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn); local_unlock(&lru_pvecs.lock); } @@ -676,7 +690,7 @@ void deactivate_page(struct page *page) local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate); get_page(page); - if (!pagevec_add(pvec, page) || PageCompound(page)) + if (pagevec_add_and_need_flush(pvec, page)) pagevec_lru_move_fn(pvec, lru_deactivate_fn); local_unlock(&lru_pvecs.lock); } @@ -698,7 +712,7 @@ void mark_page_lazyfree(struct page *page) local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_lazyfree); get_page(page); - if (!pagevec_add(pvec, page) || PageCompound(page)) + if (pagevec_add_and_need_flush(pvec, page)) pagevec_lru_move_fn(pvec, lru_lazyfree_fn); local_unlock(&lru_pvecs.lock); } @@ -735,7 +749,7 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy) * Calling this function with cpu hotplug locks held can actually lead * to obscure indirect dependencies via WQ context. */ -void lru_add_drain_all(void) +inline void __lru_add_drain_all(bool force_all_cpus) { /* * lru_drain_gen - Global pages generation number @@ -780,7 +794,7 @@ void lru_add_drain_all(void) * (C) Exit the draining operation if a newer generation, from another * lru_add_drain_all(), was already scheduled for draining. Check (A). */ - if (unlikely(this_gen != lru_drain_gen)) + if (unlikely(this_gen != lru_drain_gen && !force_all_cpus)) goto done; /* @@ -794,7 +808,7 @@ void lru_add_drain_all(void) * below which drains the page vectors. * * Let x, y, and z represent some system CPU numbers, where x < y < z. - * Assume CPU #z is is in the middle of the for_each_online_cpu loop + * Assume CPU #z is in the middle of the for_each_online_cpu loop * below and has already reached CPU #y's per-cpu data. CPU #x comes * along, adds some pages to its per-cpu vectors, then calls * lru_add_drain_all(). @@ -810,12 +824,14 @@ void lru_add_drain_all(void) for_each_online_cpu(cpu) { struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); - if (pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) || + if (force_all_cpus || + pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) || data_race(pagevec_count(&per_cpu(lru_rotate.pvec, cpu))) || pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) || pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) || pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree, cpu)) || - need_activate_page_drain(cpu)) { + need_activate_page_drain(cpu) || + has_bh_in_lru(cpu, NULL)) { INIT_WORK(work, lru_add_drain_per_cpu); queue_work_on(cpu, mm_percpu_wq, work); __cpumask_set_cpu(cpu, &has_work); @@ -828,6 +844,11 @@ void lru_add_drain_all(void) done: mutex_unlock(&lock); } + +void lru_add_drain_all(void) +{ + __lru_add_drain_all(false); +} #else void lru_add_drain_all(void) { @@ -835,6 +856,34 @@ void lru_add_drain_all(void) } #endif /* CONFIG_SMP */ +atomic_t lru_disable_count = ATOMIC_INIT(0); + +/* + * lru_cache_disable() needs to be called before we start compiling + * a list of pages to be migrated using isolate_lru_page(). + * It drains pages on LRU cache and then disable on all cpus until + * lru_cache_enable is called. + * + * Must be paired with a call to lru_cache_enable(). + */ +void lru_cache_disable(void) +{ + atomic_inc(&lru_disable_count); +#ifdef CONFIG_SMP + /* + * lru_add_drain_all in the force mode will schedule draining on + * all online CPUs so any calls of lru_cache_disabled wrapped by + * local_lock or preemption disabled would be ordered by that. + * The atomic operation doesn't need to have stronger ordering + * requirements because that is enforeced by the scheduling + * guarantees. + */ + __lru_add_drain_all(true); +#else + lru_add_drain(); +#endif +} + /** * release_pages - batched put_page() * @pages: array of pages to release diff --git a/mm/swap_slots.c b/mm/swap_slots.c index be9de6d5b516..6248d1030a9b 100644 --- a/mm/swap_slots.c +++ b/mm/swap_slots.c @@ -16,7 +16,7 @@ * to local caches without needing to acquire swap_info * lock. We do not reuse the returned slots directly but * move them back to the global pool in a batch. This - * allows the slots to coaellesce and reduce fragmentation. + * allows the slots to coalesce and reduce fragmentation. * * The swap entry allocated is marked with SWAP_HAS_CACHE * flag in map_count that prevents it from being allocated diff --git a/mm/swap_state.c b/mm/swap_state.c index fb7efa08fe57..272ea2108c9d 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -132,7 +132,6 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, xas_store(&xas, page); xas_next(&xas); } - address_space->nrexceptional -= nr_shadows; address_space->nrpages += nr; __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr); __mod_lruvec_page_state(page, NR_SWAPCACHE, nr); @@ -172,8 +171,6 @@ void __delete_from_swap_cache(struct page *page, xas_next(&xas); } ClearPageSwapCache(page); - if (shadow) - address_space->nrexceptional += nr; address_space->nrpages -= nr; __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr); __mod_lruvec_page_state(page, NR_SWAPCACHE, -nr); @@ -275,7 +272,6 @@ void clear_shadow_from_swap_cache(int type, unsigned long begin, xas_store(&xas, NULL); nr_shadows++; } - address_space->nrexceptional -= nr_shadows; xa_unlock_irq(&address_space->i_pages); /* search the next swapcache until we meet end */ @@ -796,7 +792,7 @@ static void swap_ra_info(struct vm_fault *vmf, * * Returns the struct page for entry and addr, after queueing swapin. * - * Primitive swap readahead code. We simply read in a few pages whoes + * Primitive swap readahead code. We simply read in a few pages whose * virtual addresses are around the fault address in the same vma. * * Caller must hold read mmap_lock if vmf->vma is not NULL. diff --git a/mm/swapfile.c b/mm/swapfile.c index 084a5b9a18e5..149e77454e3c 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2780,7 +2780,7 @@ static int swap_show(struct seq_file *swap, void *v) unsigned int bytes, inuse; if (si == SEQ_START_TOKEN) { - seq_puts(swap,"Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); + seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); return 0; } @@ -3284,7 +3284,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) sizeof(long), GFP_KERNEL); - if (p->bdev &&(swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { + if (p->bdev && (swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in diff --git a/mm/truncate.c b/mm/truncate.c index 455944264663..95af244b112a 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -40,7 +40,6 @@ static inline void __clear_shadow_entry(struct address_space *mapping, if (xas_load(&xas) != entry) return; xas_store(&xas, NULL); - mapping->nrexceptional--; } static void clear_shadow_entry(struct address_space *mapping, pgoff_t index, @@ -295,7 +294,7 @@ void truncate_inode_pages_range(struct address_space *mapping, pgoff_t index; int i; - if (mapping->nrpages == 0 && mapping->nrexceptional == 0) + if (mapping_empty(mapping)) goto out; /* Offsets within partial pages */ @@ -440,9 +439,6 @@ EXPORT_SYMBOL(truncate_inode_pages); */ void truncate_inode_pages_final(struct address_space *mapping) { - unsigned long nrexceptional; - unsigned long nrpages; - /* * Page reclaim can not participate in regular inode lifetime * management (can't call iput()) and thus can race with the @@ -452,16 +448,7 @@ void truncate_inode_pages_final(struct address_space *mapping) */ mapping_set_exiting(mapping); - /* - * When reclaim installs eviction entries, it increases - * nrexceptional first, then decreases nrpages. Make sure we see - * this in the right order or we might miss an entry. - */ - nrpages = mapping->nrpages; - smp_rmb(); - nrexceptional = mapping->nrexceptional; - - if (nrpages || nrexceptional) { + if (!mapping_empty(mapping)) { /* * As truncation uses a lockless tree lookup, cycle * the tree lock to make sure any ongoing tree @@ -633,7 +620,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, int ret2 = 0; int did_range_unmap = 0; - if (mapping->nrpages == 0 && mapping->nrexceptional == 0) + if (mapping_empty(mapping)) goto out; pagevec_init(&pvec); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 9a3d451402d7..e14b3820c6a8 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -207,7 +207,7 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, - bool zeropage) + enum mcopy_atomic_mode mode) { int vm_alloc_shared = dst_vma->vm_flags & VM_SHARED; int vm_shared = dst_vma->vm_flags & VM_SHARED; @@ -227,7 +227,7 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, * by THP. Since we can not reliably insert a zero page, this * feature is not supported. */ - if (zeropage) { + if (mode == MCOPY_ATOMIC_ZEROPAGE) { mmap_read_unlock(dst_mm); return -EINVAL; } @@ -273,8 +273,6 @@ retry: } while (src_addr < src_start + len) { - pte_t dst_pteval; - BUG_ON(dst_addr >= dst_start + len); /* @@ -290,23 +288,23 @@ retry: mutex_lock(&hugetlb_fault_mutex_table[hash]); err = -ENOMEM; - dst_pte = huge_pte_alloc(dst_mm, dst_addr, vma_hpagesize); + dst_pte = huge_pte_alloc(dst_mm, dst_vma, dst_addr, vma_hpagesize); if (!dst_pte) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); goto out_unlock; } - err = -EEXIST; - dst_pteval = huge_ptep_get(dst_pte); - if (!huge_pte_none(dst_pteval)) { + if (mode != MCOPY_ATOMIC_CONTINUE && + !huge_pte_none(huge_ptep_get(dst_pte))) { + err = -EEXIST; mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); goto out_unlock; } err = hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, - dst_addr, src_addr, &page); + dst_addr, src_addr, mode, &page); mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); @@ -408,7 +406,7 @@ extern ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, - bool zeropage); + enum mcopy_atomic_mode mode); #endif /* CONFIG_HUGETLB_PAGE */ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, @@ -458,7 +456,7 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, - bool zeropage, + enum mcopy_atomic_mode mcopy_mode, bool *mmap_changing, __u64 mode) { @@ -469,6 +467,7 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm, long copied; struct page *page; bool wp_copy; + bool zeropage = (mcopy_mode == MCOPY_ATOMIC_ZEROPAGE); /* * Sanitize the command parameters: @@ -527,10 +526,12 @@ retry: */ if (is_vm_hugetlb_page(dst_vma)) return __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start, - src_start, len, zeropage); + src_start, len, mcopy_mode); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; + if (mcopy_mode == MCOPY_ATOMIC_CONTINUE) + goto out_unlock; /* * Ensure the dst_vma has a anon_vma or this page @@ -626,14 +627,22 @@ ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, bool *mmap_changing, __u64 mode) { - return __mcopy_atomic(dst_mm, dst_start, src_start, len, false, - mmap_changing, mode); + return __mcopy_atomic(dst_mm, dst_start, src_start, len, + MCOPY_ATOMIC_NORMAL, mmap_changing, mode); } ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool *mmap_changing) { - return __mcopy_atomic(dst_mm, start, 0, len, true, mmap_changing, 0); + return __mcopy_atomic(dst_mm, start, 0, len, MCOPY_ATOMIC_ZEROPAGE, + mmap_changing, 0); +} + +ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long start, + unsigned long len, bool *mmap_changing) +{ + return __mcopy_atomic(dst_mm, start, 0, len, MCOPY_ATOMIC_CONTINUE, + mmap_changing, 0); } int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, diff --git a/mm/util.c b/mm/util.c index 083c5c417cfc..a8bf17f18a81 100644 --- a/mm/util.c +++ b/mm/util.c @@ -765,7 +765,7 @@ int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer, * The deviation of sync_overcommit_as could be big with loose policy * like OVERCOMMIT_ALWAYS/OVERCOMMIT_GUESS. When changing policy to * strict OVERCOMMIT_NEVER, we need to reduce the deviation to comply - * with the strict "NEVER", and to avoid possible race condtion (even + * with the strict "NEVER", and to avoid possible race condition (even * though user usually won't too frequently do the switching to policy * OVERCOMMIT_NEVER), the switch is done in the following order: * 1. changing the batch @@ -987,22 +987,26 @@ int __weak memcmp_pages(struct page *page1, struct page *page2) */ void mem_dump_obj(void *object) { + const char *type; + if (kmem_valid_obj(object)) { kmem_dump_obj(object); return; } + if (vmalloc_dump_obj(object)) return; - if (!virt_addr_valid(object)) { - if (object == NULL) - pr_cont(" NULL pointer.\n"); - else if (object == ZERO_SIZE_PTR) - pr_cont(" zero-size pointer.\n"); - else - pr_cont(" non-paged memory.\n"); - return; - } - pr_cont(" non-slab/vmalloc memory.\n"); + + if (virt_addr_valid(object)) + type = "non-slab/vmalloc memory"; + else if (object == NULL) + type = "NULL pointer"; + else if (object == ZERO_SIZE_PTR) + type = "zero-size pointer"; + else + type = "non-paged memory"; + + pr_cont(" %s\n", type); } EXPORT_SYMBOL_GPL(mem_dump_obj); #endif diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d33894d7b27a..a13ac524f6ff 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1583,7 +1583,7 @@ static unsigned long lazy_max_pages(void) static atomic_long_t vmap_lazy_nr = ATOMIC_LONG_INIT(0); /* - * Serialize vmap purging. There is no actual criticial section protected + * Serialize vmap purging. There is no actual critical section protected * by this look, but we want to avoid concurrent calls for performance * reasons and to make the pcpu_get_vm_areas more deterministic. */ @@ -2628,7 +2628,7 @@ static void __vfree(const void *addr) * May sleep if called *not* from interrupt context. * Must not be called in NMI context (strictly speaking, it could be * if we have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling - * conventions for vfree() arch-depenedent would be a really bad idea). + * conventions for vfree() arch-dependent would be a really bad idea). */ void vfree(const void *addr) { @@ -3083,7 +3083,7 @@ EXPORT_SYMBOL(vzalloc_node); * 64b systems should always have either DMA or DMA32 zones. For others * GFP_DMA32 should do the right thing and use the normal zone. */ -#define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL +#define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #endif /** @@ -3141,15 +3141,12 @@ static int aligned_vread(char *buf, char *addr, unsigned long count) /* * To do safe access to this _mapped_ area, we need * lock. But adding lock here means that we need to add - * overhead of vmalloc()/vfree() calles for this _debug_ + * overhead of vmalloc()/vfree() calls for this _debug_ * interface, rarely used. Instead of that, we'll use * kmap() and get small overhead in this access function. */ if (p) { - /* - * we can expect USER0 is not used (see vread/vwrite's - * function description) - */ + /* We can expect USER0 is not used -- see vread() */ void *map = kmap_atomic(p); memcpy(buf, map + offset, length); kunmap_atomic(map); @@ -3164,43 +3161,6 @@ static int aligned_vread(char *buf, char *addr, unsigned long count) return copied; } -static int aligned_vwrite(char *buf, char *addr, unsigned long count) -{ - struct page *p; - int copied = 0; - - while (count) { - unsigned long offset, length; - - offset = offset_in_page(addr); - length = PAGE_SIZE - offset; - if (length > count) - length = count; - p = vmalloc_to_page(addr); - /* - * To do safe access to this _mapped_ area, we need - * lock. But adding lock here means that we need to add - * overhead of vmalloc()/vfree() calles for this _debug_ - * interface, rarely used. Instead of that, we'll use - * kmap() and get small overhead in this access function. - */ - if (p) { - /* - * we can expect USER0 is not used (see vread/vwrite's - * function description) - */ - void *map = kmap_atomic(p); - memcpy(map + offset, buf, length); - kunmap_atomic(map); - } - addr += length; - buf += length; - copied += length; - count -= length; - } - return copied; -} - /** * vread() - read vmalloc area in a safe way. * @buf: buffer for reading data @@ -3219,7 +3179,7 @@ static int aligned_vwrite(char *buf, char *addr, unsigned long count) * Note: In usual ops, vread() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). * This is for routines which have to access vmalloc area without - * any information, as /dev/kmem. + * any information, as /proc/kcore. * * Return: number of bytes for which addr and buf should be increased * (same number as @count) or %0 if [addr...addr+count) doesn't @@ -3284,80 +3244,6 @@ finished: } /** - * vwrite() - write vmalloc area in a safe way. - * @buf: buffer for source data - * @addr: vm address. - * @count: number of bytes to be read. - * - * This function checks that addr is a valid vmalloc'ed area, and - * copy data from a buffer to the given addr. If specified range of - * [addr...addr+count) includes some valid address, data is copied from - * proper area of @buf. If there are memory holes, no copy to hole. - * IOREMAP area is treated as memory hole and no copy is done. - * - * If [addr...addr+count) doesn't includes any intersects with alive - * vm_struct area, returns 0. @buf should be kernel's buffer. - * - * Note: In usual ops, vwrite() is never necessary because the caller - * should know vmalloc() area is valid and can use memcpy(). - * This is for routines which have to access vmalloc area without - * any information, as /dev/kmem. - * - * Return: number of bytes for which addr and buf should be - * increased (same number as @count) or %0 if [addr...addr+count) - * doesn't include any intersection with valid vmalloc area - */ -long vwrite(char *buf, char *addr, unsigned long count) -{ - struct vmap_area *va; - struct vm_struct *vm; - char *vaddr; - unsigned long n, buflen; - int copied = 0; - - /* Don't allow overflow */ - if ((unsigned long) addr + count < count) - count = -(unsigned long) addr; - buflen = count; - - spin_lock(&vmap_area_lock); - list_for_each_entry(va, &vmap_area_list, list) { - if (!count) - break; - - if (!va->vm) - continue; - - vm = va->vm; - vaddr = (char *) vm->addr; - if (addr >= vaddr + get_vm_area_size(vm)) - continue; - while (addr < vaddr) { - if (count == 0) - goto finished; - buf++; - addr++; - count--; - } - n = vaddr + get_vm_area_size(vm) - addr; - if (n > count) - n = count; - if (!(vm->flags & VM_IOREMAP)) { - aligned_vwrite(buf, addr, n); - copied++; - } - buf += n; - addr += n; - count -= n; - } -finished: - spin_unlock(&vmap_area_lock); - if (!copied) - return 0; - return buflen; -} - -/** * remap_vmalloc_range_partial - map vmalloc pages to userspace * @vma: vma to cover * @uaddr: target user address to start at diff --git a/mm/vmscan.c b/mm/vmscan.c index 562e87cbd7a1..5199b9696bab 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -185,39 +185,181 @@ static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem); #ifdef CONFIG_MEMCG -/* - * We allow subsystems to populate their shrinker-related - * LRU lists before register_shrinker_prepared() is called - * for the shrinker, since we don't want to impose - * restrictions on their internal registration order. - * In this case shrink_slab_memcg() may find corresponding - * bit is set in the shrinkers map. - * - * This value is used by the function to detect registering - * shrinkers and to skip do_shrink_slab() calls for them. - */ -#define SHRINKER_REGISTERING ((struct shrinker *)~0UL) +static int shrinker_nr_max; + +/* The shrinker_info is expanded in a batch of BITS_PER_LONG */ +static inline int shrinker_map_size(int nr_items) +{ + return (DIV_ROUND_UP(nr_items, BITS_PER_LONG) * sizeof(unsigned long)); +} + +static inline int shrinker_defer_size(int nr_items) +{ + return (round_up(nr_items, BITS_PER_LONG) * sizeof(atomic_long_t)); +} + +static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, + int nid) +{ + return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, + lockdep_is_held(&shrinker_rwsem)); +} + +static int expand_one_shrinker_info(struct mem_cgroup *memcg, + int map_size, int defer_size, + int old_map_size, int old_defer_size) +{ + struct shrinker_info *new, *old; + struct mem_cgroup_per_node *pn; + int nid; + int size = map_size + defer_size; + + for_each_node(nid) { + pn = memcg->nodeinfo[nid]; + old = shrinker_info_protected(memcg, nid); + /* Not yet online memcg */ + if (!old) + return 0; + + new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid); + if (!new) + return -ENOMEM; + + new->nr_deferred = (atomic_long_t *)(new + 1); + new->map = (void *)new->nr_deferred + defer_size; + + /* map: set all old bits, clear all new bits */ + memset(new->map, (int)0xff, old_map_size); + memset((void *)new->map + old_map_size, 0, map_size - old_map_size); + /* nr_deferred: copy old values, clear all new values */ + memcpy(new->nr_deferred, old->nr_deferred, old_defer_size); + memset((void *)new->nr_deferred + old_defer_size, 0, + defer_size - old_defer_size); + + rcu_assign_pointer(pn->shrinker_info, new); + kvfree_rcu(old, rcu); + } + + return 0; +} + +void free_shrinker_info(struct mem_cgroup *memcg) +{ + struct mem_cgroup_per_node *pn; + struct shrinker_info *info; + int nid; + + for_each_node(nid) { + pn = memcg->nodeinfo[nid]; + info = rcu_dereference_protected(pn->shrinker_info, true); + kvfree(info); + rcu_assign_pointer(pn->shrinker_info, NULL); + } +} + +int alloc_shrinker_info(struct mem_cgroup *memcg) +{ + struct shrinker_info *info; + int nid, size, ret = 0; + int map_size, defer_size = 0; + + down_write(&shrinker_rwsem); + map_size = shrinker_map_size(shrinker_nr_max); + defer_size = shrinker_defer_size(shrinker_nr_max); + size = map_size + defer_size; + for_each_node(nid) { + info = kvzalloc_node(sizeof(*info) + size, GFP_KERNEL, nid); + if (!info) { + free_shrinker_info(memcg); + ret = -ENOMEM; + break; + } + info->nr_deferred = (atomic_long_t *)(info + 1); + info->map = (void *)info->nr_deferred + defer_size; + rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); + } + up_write(&shrinker_rwsem); + + return ret; +} + +static inline bool need_expand(int nr_max) +{ + return round_up(nr_max, BITS_PER_LONG) > + round_up(shrinker_nr_max, BITS_PER_LONG); +} + +static int expand_shrinker_info(int new_id) +{ + int ret = 0; + int new_nr_max = new_id + 1; + int map_size, defer_size = 0; + int old_map_size, old_defer_size = 0; + struct mem_cgroup *memcg; + + if (!need_expand(new_nr_max)) + goto out; + + if (!root_mem_cgroup) + goto out; + + lockdep_assert_held(&shrinker_rwsem); + + map_size = shrinker_map_size(new_nr_max); + defer_size = shrinker_defer_size(new_nr_max); + old_map_size = shrinker_map_size(shrinker_nr_max); + old_defer_size = shrinker_defer_size(shrinker_nr_max); + + memcg = mem_cgroup_iter(NULL, NULL, NULL); + do { + ret = expand_one_shrinker_info(memcg, map_size, defer_size, + old_map_size, old_defer_size); + if (ret) { + mem_cgroup_iter_break(NULL, memcg); + goto out; + } + } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); +out: + if (!ret) + shrinker_nr_max = new_nr_max; + + return ret; +} + +void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) +{ + if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { + struct shrinker_info *info; + + rcu_read_lock(); + info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); + /* Pairs with smp mb in shrink_slab() */ + smp_mb__before_atomic(); + set_bit(shrinker_id, info->map); + rcu_read_unlock(); + } +} static DEFINE_IDR(shrinker_idr); -static int shrinker_nr_max; static int prealloc_memcg_shrinker(struct shrinker *shrinker) { int id, ret = -ENOMEM; + if (mem_cgroup_disabled()) + return -ENOSYS; + down_write(&shrinker_rwsem); /* This may call shrinker, so it must use down_read_trylock() */ - id = idr_alloc(&shrinker_idr, SHRINKER_REGISTERING, 0, 0, GFP_KERNEL); + id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); if (id < 0) goto unlock; if (id >= shrinker_nr_max) { - if (memcg_expand_shrinker_maps(id)) { + if (expand_shrinker_info(id)) { idr_remove(&shrinker_idr, id); goto unlock; } - - shrinker_nr_max = id + 1; } shrinker->id = id; ret = 0; @@ -232,9 +374,51 @@ static void unregister_memcg_shrinker(struct shrinker *shrinker) BUG_ON(id < 0); - down_write(&shrinker_rwsem); + lockdep_assert_held(&shrinker_rwsem); + idr_remove(&shrinker_idr, id); - up_write(&shrinker_rwsem); +} + +static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + struct shrinker_info *info; + + info = shrinker_info_protected(memcg, nid); + return atomic_long_xchg(&info->nr_deferred[shrinker->id], 0); +} + +static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + struct shrinker_info *info; + + info = shrinker_info_protected(memcg, nid); + return atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]); +} + +void reparent_shrinker_deferred(struct mem_cgroup *memcg) +{ + int i, nid; + long nr; + struct mem_cgroup *parent; + struct shrinker_info *child_info, *parent_info; + + parent = parent_mem_cgroup(memcg); + if (!parent) + parent = root_mem_cgroup; + + /* Prevent from concurrent shrinker_info expand */ + down_read(&shrinker_rwsem); + for_each_node(nid) { + child_info = shrinker_info_protected(memcg, nid); + parent_info = shrinker_info_protected(parent, nid); + for (i = 0; i < shrinker_nr_max; i++) { + nr = atomic_long_read(&child_info->nr_deferred[i]); + atomic_long_add(nr, &parent_info->nr_deferred[i]); + } + } + up_read(&shrinker_rwsem); } static bool cgroup_reclaim(struct scan_control *sc) @@ -268,13 +452,25 @@ static bool writeback_throttling_sane(struct scan_control *sc) #else static int prealloc_memcg_shrinker(struct shrinker *shrinker) { - return 0; + return -ENOSYS; } static void unregister_memcg_shrinker(struct shrinker *shrinker) { } +static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + return 0; +} + +static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + return 0; +} + static bool cgroup_reclaim(struct scan_control *sc) { return false; @@ -286,6 +482,39 @@ static bool writeback_throttling_sane(struct scan_control *sc) } #endif +static long xchg_nr_deferred(struct shrinker *shrinker, + struct shrink_control *sc) +{ + int nid = sc->nid; + + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) + nid = 0; + + if (sc->memcg && + (shrinker->flags & SHRINKER_MEMCG_AWARE)) + return xchg_nr_deferred_memcg(nid, shrinker, + sc->memcg); + + return atomic_long_xchg(&shrinker->nr_deferred[nid], 0); +} + + +static long add_nr_deferred(long nr, struct shrinker *shrinker, + struct shrink_control *sc) +{ + int nid = sc->nid; + + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) + nid = 0; + + if (sc->memcg && + (shrinker->flags & SHRINKER_MEMCG_AWARE)) + return add_nr_deferred_memcg(nr, nid, shrinker, + sc->memcg); + + return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]); +} + /* * This misses isolated pages which are not accounted for to save counters. * As the data only determines if reclaim or compaction continues, it is @@ -335,8 +564,18 @@ static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, */ int prealloc_shrinker(struct shrinker *shrinker) { - unsigned int size = sizeof(*shrinker->nr_deferred); + unsigned int size; + int err; + + if (shrinker->flags & SHRINKER_MEMCG_AWARE) { + err = prealloc_memcg_shrinker(shrinker); + if (err != -ENOSYS) + return err; + + shrinker->flags &= ~SHRINKER_MEMCG_AWARE; + } + size = sizeof(*shrinker->nr_deferred); if (shrinker->flags & SHRINKER_NUMA_AWARE) size *= nr_node_ids; @@ -344,26 +583,17 @@ int prealloc_shrinker(struct shrinker *shrinker) if (!shrinker->nr_deferred) return -ENOMEM; - if (shrinker->flags & SHRINKER_MEMCG_AWARE) { - if (prealloc_memcg_shrinker(shrinker)) - goto free_deferred; - } - return 0; - -free_deferred: - kfree(shrinker->nr_deferred); - shrinker->nr_deferred = NULL; - return -ENOMEM; } void free_prealloced_shrinker(struct shrinker *shrinker) { - if (!shrinker->nr_deferred) - return; - - if (shrinker->flags & SHRINKER_MEMCG_AWARE) + if (shrinker->flags & SHRINKER_MEMCG_AWARE) { + down_write(&shrinker_rwsem); unregister_memcg_shrinker(shrinker); + up_write(&shrinker_rwsem); + return; + } kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; @@ -373,10 +603,7 @@ void register_shrinker_prepared(struct shrinker *shrinker) { down_write(&shrinker_rwsem); list_add_tail(&shrinker->list, &shrinker_list); -#ifdef CONFIG_MEMCG - if (shrinker->flags & SHRINKER_MEMCG_AWARE) - idr_replace(&shrinker_idr, shrinker, shrinker->id); -#endif + shrinker->flags |= SHRINKER_REGISTERED; up_write(&shrinker_rwsem); } @@ -396,13 +623,16 @@ EXPORT_SYMBOL(register_shrinker); */ void unregister_shrinker(struct shrinker *shrinker) { - if (!shrinker->nr_deferred) + if (!(shrinker->flags & SHRINKER_REGISTERED)) return; - if (shrinker->flags & SHRINKER_MEMCG_AWARE) - unregister_memcg_shrinker(shrinker); + down_write(&shrinker_rwsem); list_del(&shrinker->list); + shrinker->flags &= ~SHRINKER_REGISTERED; + if (shrinker->flags & SHRINKER_MEMCG_AWARE) + unregister_memcg_shrinker(shrinker); up_write(&shrinker_rwsem); + kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; } @@ -419,14 +649,10 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, long freeable; long nr; long new_nr; - int nid = shrinkctl->nid; long batch_size = shrinker->batch ? shrinker->batch : SHRINK_BATCH; long scanned = 0, next_deferred; - if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) - nid = 0; - freeable = shrinker->count_objects(shrinker, shrinkctl); if (freeable == 0 || freeable == SHRINK_EMPTY) return freeable; @@ -436,9 +662,8 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, * and zero it so that other concurrent shrinker invocations * don't also do this scanning work. */ - nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0); + nr = xchg_nr_deferred(shrinker, shrinkctl); - total_scan = nr; if (shrinker->seeks) { delta = freeable >> priority; delta *= 4; @@ -452,37 +677,9 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, delta = freeable / 2; } + total_scan = nr >> priority; total_scan += delta; - if (total_scan < 0) { - pr_err("shrink_slab: %pS negative objects to delete nr=%ld\n", - shrinker->scan_objects, total_scan); - total_scan = freeable; - next_deferred = nr; - } else - next_deferred = total_scan; - - /* - * We need to avoid excessive windup on filesystem shrinkers - * due to large numbers of GFP_NOFS allocations causing the - * shrinkers to return -1 all the time. This results in a large - * nr being built up so when a shrink that can do some work - * comes along it empties the entire cache due to nr >>> - * freeable. This is bad for sustaining a working set in - * memory. - * - * Hence only allow the shrinker to scan the entire cache when - * a large delta change is calculated directly. - */ - if (delta < freeable / 4) - total_scan = min(total_scan, freeable / 2); - - /* - * Avoid risking looping forever due to too large nr value: - * never try to free more than twice the estimate number of - * freeable entries. - */ - if (total_scan > freeable * 2) - total_scan = freeable * 2; + total_scan = min(total_scan, (2 * freeable)); trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, freeable, delta, total_scan, priority); @@ -521,22 +718,22 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, cond_resched(); } - if (next_deferred >= scanned) - next_deferred -= scanned; - else - next_deferred = 0; + /* + * The deferred work is increased by any new work (delta) that wasn't + * done, decreased by old deferred work that was done now. + * + * And it is capped to two times of the freeable items. + */ + next_deferred = max_t(long, (nr + delta - scanned), 0); + next_deferred = min(next_deferred, (2 * freeable)); + /* * move the unused scan count back into the shrinker in a - * manner that handles concurrent updates. If we exhausted the - * scan, there is no need to do an update. + * manner that handles concurrent updates. */ - if (next_deferred > 0) - new_nr = atomic_long_add_return(next_deferred, - &shrinker->nr_deferred[nid]); - else - new_nr = atomic_long_read(&shrinker->nr_deferred[nid]); + new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl); - trace_mm_shrink_slab_end(shrinker, nid, freed, nr, new_nr, total_scan); + trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan); return freed; } @@ -544,7 +741,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { - struct memcg_shrinker_map *map; + struct shrinker_info *info; unsigned long ret, freed = 0; int i; @@ -554,12 +751,11 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, if (!down_read_trylock(&shrinker_rwsem)) return 0; - map = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_map, - true); - if (unlikely(!map)) + info = shrinker_info_protected(memcg, nid); + if (unlikely(!info)) goto unlock; - for_each_set_bit(i, map->map, shrinker_nr_max) { + for_each_set_bit(i, info->map, shrinker_nr_max) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, @@ -568,9 +764,9 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct shrinker *shrinker; shrinker = idr_find(&shrinker_idr, i); - if (unlikely(!shrinker || shrinker == SHRINKER_REGISTERING)) { + if (unlikely(!shrinker || !(shrinker->flags & SHRINKER_REGISTERED))) { if (!shrinker) - clear_bit(i, map->map); + clear_bit(i, info->map); continue; } @@ -581,7 +777,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) { - clear_bit(i, map->map); + clear_bit(i, info->map); /* * After the shrinker reported that it had no objects to * free, but before we cleared the corresponding bit in @@ -590,7 +786,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, * case, we invoke the shrinker one more time and reset * the bit if it reports that it is not empty anymore. * The memory barrier here pairs with the barrier in - * memcg_set_shrinker_bit(): + * set_shrinker_bit(): * * list_lru_add() shrink_slab_memcg() * list_add_tail() clear_bit() @@ -602,7 +798,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, if (ret == SHRINK_EMPTY) ret = 0; else - memcg_set_shrinker_bit(memcg, nid, i); + set_shrinker_bit(memcg, nid, i); } freed += ret; @@ -1507,8 +1703,9 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone, LIST_HEAD(clean_pages); list_for_each_entry_safe(page, next, page_list, lru) { - if (page_is_file_lru(page) && !PageDirty(page) && - !__PageMovable(page) && !PageUnevictable(page)) { + if (!PageHuge(page) && page_is_file_lru(page) && + !PageDirty(page) && !__PageMovable(page) && + !PageUnevictable(page)) { ClearPageActive(page); list_move(&page->lru, &clean_pages); } @@ -3862,7 +4059,7 @@ static int kswapd(void *p) { unsigned int alloc_order, reclaim_order; unsigned int highest_zoneidx = MAX_NR_ZONES - 1; - pg_data_t *pgdat = (pg_data_t*)p; + pg_data_t *pgdat = (pg_data_t *)p; struct task_struct *tsk = current; const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); @@ -4086,14 +4283,6 @@ module_init(kswapd_init) int node_reclaim_mode __read_mostly; /* - * These bit locations are exposed in the vm.zone_reclaim_mode sysctl - * ABI. New bits are OK, but existing bits can never change. - */ -#define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */ -#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */ -#define RECLAIM_UNMAP (1<<2) /* Unmap pages during reclaim */ - -/* * Priority for NODE_RECLAIM. This determines the fraction of pages * of a node considered for each zone_reclaim. 4 scans 1/16th of * a zone. diff --git a/mm/vmstat.c b/mm/vmstat.c index 74b2c374b86c..cccee36b289c 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -934,7 +934,7 @@ void cpu_vm_stats_fold(int cpu) /* * this is only called if !populated_zone(zone), which implies no other users of - * pset->vm_stat_diff[] exsist. + * pset->vm_stat_diff[] exist. */ void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) { @@ -1313,6 +1313,10 @@ const char * const vmstat_text[] = { "htlb_buddy_alloc_success", "htlb_buddy_alloc_fail", #endif +#ifdef CONFIG_CMA + "cma_alloc_success", + "cma_alloc_fail", +#endif "unevictable_pgs_culled", "unevictable_pgs_scanned", "unevictable_pgs_rescued", @@ -1365,6 +1369,10 @@ const char * const vmstat_text[] = { "swap_ra", "swap_ra_hit", #endif +#ifdef CONFIG_X86 + "direct_map_level2_splits", + "direct_map_level3_splits", +#endif #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ }; #endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA || CONFIG_MEMCG */ @@ -1854,25 +1862,34 @@ int vmstat_refresh(struct ctl_table *table, int write, if (err) return err; for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { + /* + * Skip checking stats known to go negative occasionally. + */ + switch (i) { + case NR_ZONE_WRITE_PENDING: + case NR_FREE_CMA_PAGES: + continue; + } val = atomic_long_read(&vm_zone_stat[i]); if (val < 0) { pr_warn("%s: %s %ld\n", __func__, zone_stat_name(i), val); - err = -EINVAL; } } -#ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) { - val = atomic_long_read(&vm_numa_stat[i]); + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { + /* + * Skip checking stats known to go negative occasionally. + */ + switch (i) { + case NR_WRITEBACK: + continue; + } + val = atomic_long_read(&vm_node_stat[i]); if (val < 0) { pr_warn("%s: %s %ld\n", - __func__, numa_stat_name(i), val); - err = -EINVAL; + __func__, node_stat_name(i), val); } } -#endif - if (err) - return err; if (write) *ppos += *lenp; else diff --git a/mm/workingset.c b/mm/workingset.c index cd39902c1062..b7cdeca5a76d 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -554,7 +554,6 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, goto out_invalid; if (WARN_ON_ONCE(node->count != node->nr_values)) goto out_invalid; - mapping->nrexceptional -= node->nr_values; xa_delete_node(node, workingset_update_node); __inc_lruvec_kmem_state(node, WORKINGSET_NODERECLAIM); diff --git a/mm/z3fold.c b/mm/z3fold.c index 9d889ad2bb86..7fe7adaaad01 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -391,7 +391,7 @@ static void z3fold_unregister_migration(struct z3fold_pool *pool) { if (pool->inode) iput(pool->inode); - } +} /* Initializes the z3fold header of a newly allocated z3fold page */ static struct z3fold_header *init_z3fold_page(struct page *page, bool headless, diff --git a/mm/zpool.c b/mm/zpool.c index 5ed71207ced7..6d9ed48141e5 100644 --- a/mm/zpool.c +++ b/mm/zpool.c @@ -336,7 +336,7 @@ int zpool_shrink(struct zpool *zpool, unsigned int pages, * This may hold locks, disable interrupts, and/or preemption, * and the zpool_unmap_handle() must be called to undo those * actions. The code that uses the mapped handle should complete - * its operatons on the mapped handle memory quickly and unmap + * its operations on the mapped handle memory quickly and unmap * as soon as possible. As the implementation may use per-cpu * data, multiple handles should not be mapped concurrently on * any cpu. diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 30c358b72025..19b563bc6c48 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -61,7 +61,7 @@ #define ZSPAGE_MAGIC 0x58 /* - * This must be power of 2 and greater than of equal to sizeof(link_free). + * This must be power of 2 and greater than or equal to sizeof(link_free). * These two conditions ensure that any 'struct link_free' itself doesn't * span more than 1 page which avoids complex case of mapping 2 pages simply * to restore link_free pointer values. @@ -530,7 +530,7 @@ static void set_zspage_mapping(struct zspage *zspage, * class maintains a list of zspages where each zspage is divided * into equal sized chunks. Each allocation falls into one of these * classes depending on its size. This function returns index of the - * size class which has chunk size big enough to hold the give size. + * size class which has chunk size big enough to hold the given size. */ static int get_size_class_index(int size) { @@ -1227,7 +1227,7 @@ EXPORT_SYMBOL_GPL(zs_get_total_pages); * zs_map_object - get address of allocated object from handle. * @pool: pool from which the object was allocated * @handle: handle returned from zs_malloc - * @mm: maping mode to use + * @mm: mapping mode to use * * Before using an object allocated from zs_malloc, it must be mapped using * this function. When done with the object, it must be unmapped using @@ -1987,8 +1987,7 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage, head = obj_to_head(page, addr); if (head & OBJ_ALLOCATED_TAG) { handle = head & ~OBJ_ALLOCATED_TAG; - if (!testpin_tag(handle)) - BUG(); + BUG_ON(!testpin_tag(handle)); old_obj = handle_to_obj(handle); obj_to_location(old_obj, &dummy, &obj_idx); @@ -2035,8 +2034,7 @@ unpin_objects: head = obj_to_head(page, addr); if (head & OBJ_ALLOCATED_TAG) { handle = head & ~OBJ_ALLOCATED_TAG; - if (!testpin_tag(handle)) - BUG(); + BUG_ON(!testpin_tag(handle)); unpin_tag(handle); } } diff --git a/mm/zswap.c b/mm/zswap.c index 578d9f256920..20763267a219 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -614,7 +614,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) } pr_debug("using %s zpool\n", zpool_get_type(pool->zpool)); - strlcpy(pool->tfm_name, compressor, sizeof(pool->tfm_name)); + strscpy(pool->tfm_name, compressor, sizeof(pool->tfm_name)); pool->acomp_ctx = alloc_percpu(*pool->acomp_ctx); if (!pool->acomp_ctx) { |