diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 48 | ||||
| -rw-r--r-- | mm/Makefile | 3 | ||||
| -rw-r--r-- | mm/backing-dev.c | 54 | ||||
| -rw-r--r-- | mm/balloon_compaction.c | 94 | ||||
| -rw-r--r-- | mm/cma.c | 7 | ||||
| -rw-r--r-- | mm/compaction.c | 557 | ||||
| -rw-r--r-- | mm/fadvise.c | 19 | ||||
| -rw-r--r-- | mm/filemap.c | 425 | ||||
| -rw-r--r-- | mm/frontswap.c | 35 | ||||
| -rw-r--r-- | mm/gup.c | 64 | ||||
| -rw-r--r-- | mm/highmem.c | 12 | ||||
| -rw-r--r-- | mm/huge_memory.c | 2068 | ||||
| -rw-r--r-- | mm/hugetlb.c | 171 | ||||
| -rw-r--r-- | mm/hugetlb_cgroup.c | 35 | ||||
| -rw-r--r-- | mm/internal.h | 35 | ||||
| -rw-r--r-- | mm/kasan/Makefile | 2 | ||||
| -rw-r--r-- | mm/kasan/kasan.c | 211 | ||||
| -rw-r--r-- | mm/kasan/kasan.h | 36 | ||||
| -rw-r--r-- | mm/kasan/quarantine.c | 291 | ||||
| -rw-r--r-- | mm/kasan/report.c | 86 | ||||
| -rw-r--r-- | mm/khugepaged.c | 1922 | ||||
| -rw-r--r-- | mm/kmemleak.c | 6 | ||||
| -rw-r--r-- | mm/ksm.c | 24 | ||||
| -rw-r--r-- | mm/maccess.c | 3 | ||||
| -rw-r--r-- | mm/madvise.c | 14 | ||||
| -rw-r--r-- | mm/memblock.c | 103 | ||||
| -rw-r--r-- | mm/memcontrol.c | 608 | ||||
| -rw-r--r-- | mm/memory-failure.c | 88 | ||||
| -rw-r--r-- | mm/memory.c | 1036 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 140 | ||||
| -rw-r--r-- | mm/mempolicy.c | 69 | ||||
| -rw-r--r-- | mm/mempool.c | 30 | ||||
| -rw-r--r-- | mm/migrate.c | 306 | ||||
| -rw-r--r-- | mm/mincore.c | 8 | ||||
| -rw-r--r-- | mm/mlock.c | 28 | ||||
| -rw-r--r-- | mm/mmap.c | 117 | ||||
| -rw-r--r-- | mm/mmu_context.c | 2 | ||||
| -rw-r--r-- | mm/mmzone.c | 2 | ||||
| -rw-r--r-- | mm/mprotect.c | 5 | ||||
| -rw-r--r-- | mm/mremap.c | 53 | ||||
| -rw-r--r-- | mm/nommu.c | 51 | ||||
| -rw-r--r-- | mm/oom_kill.c | 306 | ||||
| -rw-r--r-- | mm/page-writeback.c | 190 | ||||
| -rw-r--r-- | mm/page_alloc.c | 1789 | ||||
| -rw-r--r-- | mm/page_ext.c | 4 | ||||
| -rw-r--r-- | mm/page_idle.c | 4 | ||||
| -rw-r--r-- | mm/page_io.c | 22 | ||||
| -rw-r--r-- | mm/page_isolation.c | 25 | ||||
| -rw-r--r-- | mm/page_owner.c | 180 | ||||
| -rw-r--r-- | mm/page_poison.c | 16 | ||||
| -rw-r--r-- | mm/percpu.c | 73 | ||||
| -rw-r--r-- | mm/readahead.c | 33 | ||||
| -rw-r--r-- | mm/rmap.c | 134 | ||||
| -rw-r--r-- | mm/shmem.c | 1181 | ||||
| -rw-r--r-- | mm/slab.c | 757 | ||||
| -rw-r--r-- | mm/slab.h | 34 | ||||
| -rw-r--r-- | mm/slab_common.c | 55 | ||||
| -rw-r--r-- | mm/slub.c | 226 | ||||
| -rw-r--r-- | mm/sparse-vmemmap.c | 2 | ||||
| -rw-r--r-- | mm/sparse.c | 14 | ||||
| -rw-r--r-- | mm/swap.c | 133 | ||||
| -rw-r--r-- | mm/swap_state.c | 22 | ||||
| -rw-r--r-- | mm/swapfile.c | 27 | ||||
| -rw-r--r-- | mm/truncate.c | 128 | ||||
| -rw-r--r-- | mm/userfaultfd.c | 4 | ||||
| -rw-r--r-- | mm/util.c | 42 | ||||
| -rw-r--r-- | mm/vmalloc.c | 81 | ||||
| -rw-r--r-- | mm/vmscan.c | 1181 | ||||
| -rw-r--r-- | mm/vmstat.c | 574 | ||||
| -rw-r--r-- | mm/workingset.c | 64 | ||||
| -rw-r--r-- | mm/z3fold.c | 796 | ||||
| -rw-r--r-- | mm/zsmalloc.c | 1507 | ||||
| -rw-r--r-- | mm/zswap.c | 24 |
73 files changed, 11895 insertions, 6601 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 989f8f3d77e0..78a23c5c302d 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -187,11 +187,28 @@ config MEMORY_HOTPLUG bool "Allow for memory hot-add" depends on SPARSEMEM || X86_64_ACPI_NUMA depends on ARCH_ENABLE_MEMORY_HOTPLUG + depends on !KASAN config MEMORY_HOTPLUG_SPARSE def_bool y depends on SPARSEMEM && MEMORY_HOTPLUG +config MEMORY_HOTPLUG_DEFAULT_ONLINE + bool "Online the newly added memory blocks by default" + default n + depends on MEMORY_HOTPLUG + help + This option sets the default policy setting for memory hotplug + onlining policy (/sys/devices/system/memory/auto_online_blocks) which + determines what happens to newly added memory regions. Policy setting + can always be changed at runtime. + See Documentation/memory-hotplug.txt for more information. + + Say Y here if you want all hot-plugged memory blocks to appear in + 'online' state by default. + Say N here if you want the default policy to keep all hot-plugged + memory blocks in 'offline' state. + config MEMORY_HOTREMOVE bool "Allow for memory hot remove" select MEMORY_ISOLATION @@ -268,11 +285,6 @@ config ARCH_ENABLE_HUGEPAGE_MIGRATION config PHYS_ADDR_T_64BIT def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT -config ZONE_DMA_FLAG - int - default "0" if !ZONE_DMA - default "1" - config BOUNCE bool "Enable bounce buffers" default y @@ -393,6 +405,7 @@ config TRANSPARENT_HUGEPAGE bool "Transparent Hugepage Support" depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE select COMPACTION + select RADIX_TREE_MULTIORDER help Transparent Hugepages allows the kernel to use huge pages and huge tlb transparently to the applications whenever possible. @@ -428,6 +441,14 @@ choice endchoice # +# We don't deposit page tables on file THP mapping, +# but Power makes use of them to address MMU quirk. +# +config TRANSPARENT_HUGE_PAGECACHE + def_bool y + depends on TRANSPARENT_HUGEPAGE && !PPC + +# # UP and nommu archs use km based percpu allocator # config NEED_PER_CPU_KM @@ -556,7 +577,7 @@ config ZPOOL zsmalloc. config ZBUD - tristate "Low density storage for compressed pages" + tristate "Low (Up to 2x) density storage for compressed pages" default n help A special purpose allocator for storing compressed pages. @@ -565,6 +586,16 @@ config ZBUD deterministic reclaim properties that make it preferable to a higher density approach when reclaim will be used. +config Z3FOLD + tristate "Up to 3x density storage for compressed pages" + depends on ZPOOL + default n + help + A special purpose allocator for storing compressed pages. + It is designed to store up to three compressed pages per physical + page. It is a ZBUD derivative so the simplicity and determinism are + still there. + config ZSMALLOC tristate "Memory allocator for compressed pages" depends on MMU @@ -626,7 +657,8 @@ config DEFERRED_STRUCT_PAGE_INIT bool "Defer initialisation of struct pages to kthreads" default n depends on ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT - depends on MEMORY_HOTPLUG + depends on NO_BOOTMEM && MEMORY_HOTPLUG + depends on !FLATMEM help Ordinarily all struct pages are initialised during early boot in a single thread. On very large machines this can take a considerable @@ -650,7 +682,7 @@ config IDLE_PAGE_TRACKING See Documentation/vm/idle_page_tracking.txt for more details. config ZONE_DEVICE - bool "Device memory (pmem, etc...) hotplug support" if EXPERT + bool "Device memory (pmem, etc...) hotplug support" depends on MEMORY_HOTPLUG depends on MEMORY_HOTREMOVE depends on SPARSEMEM_VMEMMAP diff --git a/mm/Makefile b/mm/Makefile index deb467edca2d..fc059666c760 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -74,7 +74,7 @@ obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_MEMTEST) += memtest.o obj-$(CONFIG_MIGRATION) += migrate.o obj-$(CONFIG_QUICKLIST) += quicklist.o -obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o +obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o khugepaged.o obj-$(CONFIG_PAGE_COUNTER) += page_counter.o obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o obj-$(CONFIG_MEMCG_SWAP) += swap_cgroup.o @@ -89,6 +89,7 @@ obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o obj-$(CONFIG_ZPOOL) += zpool.o obj-$(CONFIG_ZBUD) += zbud.o obj-$(CONFIG_ZSMALLOC) += zsmalloc.o +obj-$(CONFIG_Z3FOLD) += z3fold.o obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o obj-$(CONFIG_CMA) += cma.o obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c index bfbd7096b6ed..8fde443f36d7 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -825,6 +825,20 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev) } EXPORT_SYMBOL(bdi_register_dev); +int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner) +{ + int rc; + + rc = bdi_register(bdi, NULL, "%u:%u", MAJOR(owner->devt), + MINOR(owner->devt)); + if (rc) + return rc; + bdi->owner = owner; + get_device(owner); + return 0; +} +EXPORT_SYMBOL(bdi_register_owner); + /* * Remove bdi from bdi_list, and ensure that it is no longer visible */ @@ -849,6 +863,11 @@ void bdi_unregister(struct backing_dev_info *bdi) device_unregister(bdi->dev); bdi->dev = NULL; } + + if (bdi->owner) { + put_device(bdi->owner); + bdi->owner = NULL; + } } void bdi_exit(struct backing_dev_info *bdi) @@ -898,7 +917,7 @@ static atomic_t nr_wb_congested[2]; void clear_wb_congested(struct bdi_writeback_congested *congested, int sync) { wait_queue_head_t *wqh = &congestion_wqh[sync]; - enum wb_state bit; + enum wb_congested_state bit; bit = sync ? WB_sync_congested : WB_async_congested; if (test_and_clear_bit(bit, &congested->state)) @@ -911,7 +930,7 @@ EXPORT_SYMBOL(clear_wb_congested); void set_wb_congested(struct bdi_writeback_congested *congested, int sync) { - enum wb_state bit; + enum wb_congested_state bit; bit = sync ? WB_sync_congested : WB_async_congested; if (!test_and_set_bit(bit, &congested->state)) @@ -947,25 +966,24 @@ long congestion_wait(int sync, long timeout) EXPORT_SYMBOL(congestion_wait); /** - * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a zone to complete writes - * @zone: A zone to check if it is heavily congested + * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a pgdat to complete writes + * @pgdat: A pgdat to check if it is heavily congested * @sync: SYNC or ASYNC IO * @timeout: timeout in jiffies * * In the event of a congested backing_dev (any backing_dev) and the given - * @zone has experienced recent congestion, this waits for up to @timeout + * @pgdat has experienced recent congestion, this waits for up to @timeout * jiffies for either a BDI to exit congestion of the given @sync queue * or a write to complete. * - * In the absence of zone congestion, a short sleep or a cond_resched is - * performed to yield the processor and to allow other subsystems to make - * a forward progress. + * In the absence of pgdat congestion, cond_resched() is called to yield + * the processor if necessary but otherwise does not sleep. * * The return value is 0 if the sleep is for the full timeout. Otherwise, * it is the number of jiffies that were still remaining when the function * returned. return_value == timeout implies the function did not sleep. */ -long wait_iff_congested(struct zone *zone, int sync, long timeout) +long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout) { long ret; unsigned long start = jiffies; @@ -974,24 +992,12 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout) /* * If there is no congestion, or heavy congestion is not being - * encountered in the current zone, yield if necessary instead + * encountered in the current pgdat, yield if necessary instead * of sleeping on the congestion queue */ if (atomic_read(&nr_wb_congested[sync]) == 0 || - !test_bit(ZONE_CONGESTED, &zone->flags)) { - - /* - * Memory allocation/reclaim might be called from a WQ - * context and the current implementation of the WQ - * concurrency control doesn't recognize that a particular - * WQ is congested if the worker thread is looping without - * ever sleeping. Therefore we have to do a short sleep - * here rather than calling cond_resched(). - */ - if (current->flags & PF_WQ_WORKER) - schedule_timeout_uninterruptible(1); - else - cond_resched(); + !test_bit(PGDAT_CONGESTED, &pgdat->flags)) { + cond_resched(); /* In case we scheduled, work out time remaining */ ret = timeout - (jiffies - start); diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c index 57b3e9bd6bc5..da91df50ba31 100644 --- a/mm/balloon_compaction.c +++ b/mm/balloon_compaction.c @@ -70,7 +70,7 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info) */ if (trylock_page(page)) { #ifdef CONFIG_BALLOON_COMPACTION - if (!PagePrivate(page)) { + if (PageIsolated(page)) { /* raced with isolation */ unlock_page(page); continue; @@ -106,110 +106,50 @@ EXPORT_SYMBOL_GPL(balloon_page_dequeue); #ifdef CONFIG_BALLOON_COMPACTION -static inline void __isolate_balloon_page(struct page *page) +bool balloon_page_isolate(struct page *page, isolate_mode_t mode) + { struct balloon_dev_info *b_dev_info = balloon_page_device(page); unsigned long flags; spin_lock_irqsave(&b_dev_info->pages_lock, flags); - ClearPagePrivate(page); list_del(&page->lru); b_dev_info->isolated_pages++; spin_unlock_irqrestore(&b_dev_info->pages_lock, flags); + + return true; } -static inline void __putback_balloon_page(struct page *page) +void balloon_page_putback(struct page *page) { struct balloon_dev_info *b_dev_info = balloon_page_device(page); unsigned long flags; spin_lock_irqsave(&b_dev_info->pages_lock, flags); - SetPagePrivate(page); list_add(&page->lru, &b_dev_info->pages); b_dev_info->isolated_pages--; spin_unlock_irqrestore(&b_dev_info->pages_lock, flags); } -/* __isolate_lru_page() counterpart for a ballooned page */ -bool balloon_page_isolate(struct page *page) -{ - /* - * Avoid burning cycles with pages that are yet under __free_pages(), - * or just got freed under us. - * - * In case we 'win' a race for a balloon page being freed under us and - * raise its refcount preventing __free_pages() from doing its job - * the put_page() at the end of this block will take care of - * release this page, thus avoiding a nasty leakage. - */ - if (likely(get_page_unless_zero(page))) { - /* - * As balloon pages are not isolated from LRU lists, concurrent - * compaction threads can race against page migration functions - * as well as race against the balloon driver releasing a page. - * - * In order to avoid having an already isolated balloon page - * being (wrongly) re-isolated while it is under migration, - * or to avoid attempting to isolate pages being released by - * the balloon driver, lets be sure we have the page lock - * before proceeding with the balloon page isolation steps. - */ - if (likely(trylock_page(page))) { - /* - * A ballooned page, by default, has PagePrivate set. - * Prevent concurrent compaction threads from isolating - * an already isolated balloon page by clearing it. - */ - if (balloon_page_movable(page)) { - __isolate_balloon_page(page); - unlock_page(page); - return true; - } - unlock_page(page); - } - put_page(page); - } - return false; -} - -/* putback_lru_page() counterpart for a ballooned page */ -void balloon_page_putback(struct page *page) -{ - /* - * 'lock_page()' stabilizes the page and prevents races against - * concurrent isolation threads attempting to re-isolate it. - */ - lock_page(page); - - if (__is_movable_balloon_page(page)) { - __putback_balloon_page(page); - /* drop the extra ref count taken for page isolation */ - put_page(page); - } else { - WARN_ON(1); - dump_page(page, "not movable balloon page"); - } - unlock_page(page); -} /* move_to_new_page() counterpart for a ballooned page */ -int balloon_page_migrate(struct page *newpage, - struct page *page, enum migrate_mode mode) +int balloon_page_migrate(struct address_space *mapping, + struct page *newpage, struct page *page, + enum migrate_mode mode) { struct balloon_dev_info *balloon = balloon_page_device(page); - int rc = -EAGAIN; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); - if (WARN_ON(!__is_movable_balloon_page(page))) { - dump_page(page, "not movable balloon page"); - return rc; - } + return balloon->migratepage(balloon, newpage, page, mode); +} - if (balloon && balloon->migratepage) - rc = balloon->migratepage(balloon, newpage, page, mode); +const struct address_space_operations balloon_aops = { + .migratepage = balloon_page_migrate, + .isolate_page = balloon_page_isolate, + .putback_page = balloon_page_putback, +}; +EXPORT_SYMBOL_GPL(balloon_aops); - return rc; -} #endif /* CONFIG_BALLOON_COMPACTION */ @@ -183,7 +183,8 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, return -EINVAL; /* ensure minimal alignment required by mm core */ - alignment = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order); + alignment = PAGE_SIZE << + max_t(unsigned long, MAX_ORDER - 1, pageblock_order); /* alignment should be aligned with order_per_bit */ if (!IS_ALIGNED(alignment >> PAGE_SHIFT, 1 << order_per_bit)) @@ -266,8 +267,8 @@ int __init cma_declare_contiguous(phys_addr_t base, * migratetype page by page allocator's buddy algorithm. In the case, * you couldn't get a contiguous memory, which is not what we want. */ - alignment = max(alignment, - (phys_addr_t)PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order)); + alignment = max(alignment, (phys_addr_t)PAGE_SIZE << + max_t(unsigned long, MAX_ORDER - 1, pageblock_order)); base = ALIGN(base, alignment); size = ALIGN(size, alignment); limit &= ~(alignment - 1); diff --git a/mm/compaction.c b/mm/compaction.c index ccf97b02b85f..9affb2908304 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -15,11 +15,11 @@ #include <linux/backing-dev.h> #include <linux/sysctl.h> #include <linux/sysfs.h> -#include <linux/balloon_compaction.h> #include <linux/page-isolation.h> #include <linux/kasan.h> #include <linux/kthread.h> #include <linux/freezer.h> +#include <linux/page_owner.h> #include "internal.h" #ifdef CONFIG_COMPACTION @@ -42,6 +42,11 @@ static inline void count_compact_events(enum vm_event_item item, long delta) #define CREATE_TRACE_POINTS #include <trace/events/compaction.h> +#define block_start_pfn(pfn, order) round_down(pfn, 1UL << (order)) +#define block_end_pfn(pfn, order) ALIGN((pfn) + 1, 1UL << (order)) +#define pageblock_start_pfn(pfn) block_start_pfn(pfn, pageblock_order) +#define pageblock_end_pfn(pfn) block_end_pfn(pfn, pageblock_order) + static unsigned long release_freepages(struct list_head *freelist) { struct page *page, *next; @@ -60,13 +65,27 @@ static unsigned long release_freepages(struct list_head *freelist) static void map_pages(struct list_head *list) { - struct page *page; + unsigned int i, order, nr_pages; + struct page *page, *next; + LIST_HEAD(tmp_list); + + list_for_each_entry_safe(page, next, list, lru) { + list_del(&page->lru); + + order = page_private(page); + nr_pages = 1 << order; - list_for_each_entry(page, list, lru) { - arch_alloc_page(page, 0); - kernel_map_pages(page, 1, 1); - kasan_alloc_pages(page, 0); + post_alloc_hook(page, order, __GFP_MOVABLE); + if (order) + split_page(page, order); + + for (i = 0; i < nr_pages; i++) { + list_add(&page->lru, &tmp_list); + page++; + } } + + list_splice(&tmp_list, list); } static inline bool migrate_async_suitable(int migratetype) @@ -76,6 +95,44 @@ static inline bool migrate_async_suitable(int migratetype) #ifdef CONFIG_COMPACTION +int PageMovable(struct page *page) +{ + struct address_space *mapping; + + VM_BUG_ON_PAGE(!PageLocked(page), page); + if (!__PageMovable(page)) + return 0; + + mapping = page_mapping(page); + if (mapping && mapping->a_ops && mapping->a_ops->isolate_page) + return 1; + + return 0; +} +EXPORT_SYMBOL(PageMovable); + +void __SetPageMovable(struct page *page, struct address_space *mapping) +{ + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE((unsigned long)mapping & PAGE_MAPPING_MOVABLE, page); + page->mapping = (void *)((unsigned long)mapping | PAGE_MAPPING_MOVABLE); +} +EXPORT_SYMBOL(__SetPageMovable); + +void __ClearPageMovable(struct page *page) +{ + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageMovable(page), page); + /* + * Clear registered address_space val with keeping PAGE_MAPPING_MOVABLE + * flag so that VM can catch up released page by driver after isolation. + * With it, VM migration doesn't try to put it back. + */ + page->mapping = (void *)((unsigned long)page->mapping & + PAGE_MAPPING_MOVABLE); +} +EXPORT_SYMBOL(__ClearPageMovable); + /* Do not skip compaction more than 64 times */ #define COMPACT_MAX_DEFER_SHIFT 6 @@ -161,7 +218,7 @@ static void reset_cached_positions(struct zone *zone) zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn; zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn; zone->compact_cached_free_pfn = - round_down(zone_end_pfn(zone) - 1, pageblock_nr_pages); + pageblock_start_pfn(zone_end_pfn(zone) - 1); } /* @@ -274,7 +331,7 @@ static bool compact_trylock_irqsave(spinlock_t *lock, unsigned long *flags, { if (cc->mode == MIGRATE_ASYNC) { if (!spin_trylock_irqsave(lock, *flags)) { - cc->contended = COMPACT_CONTENDED_LOCK; + cc->contended = true; return false; } } else { @@ -308,13 +365,13 @@ static bool compact_unlock_should_abort(spinlock_t *lock, } if (fatal_signal_pending(current)) { - cc->contended = COMPACT_CONTENDED_SCHED; + cc->contended = true; return true; } if (need_resched()) { if (cc->mode == MIGRATE_ASYNC) { - cc->contended = COMPACT_CONTENDED_SCHED; + cc->contended = true; return true; } cond_resched(); @@ -337,7 +394,7 @@ static inline bool compact_should_abort(struct compact_control *cc) /* async compaction aborts if contended */ if (need_resched()) { if (cc->mode == MIGRATE_ASYNC) { - cc->contended = COMPACT_CONTENDED_SCHED; + cc->contended = true; return true; } @@ -363,12 +420,13 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, unsigned long flags = 0; bool locked = false; unsigned long blockpfn = *start_pfn; + unsigned int order; cursor = pfn_to_page(blockpfn); /* Isolate free pages. */ for (; blockpfn < end_pfn; blockpfn++, cursor++) { - int isolated, i; + int isolated; struct page *page = cursor; /* @@ -434,27 +492,25 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, goto isolate_fail; } - /* Found a free page, break it into order-0 pages */ - isolated = split_free_page(page); - total_isolated += isolated; - for (i = 0; i < isolated; i++) { - list_add(&page->lru, freelist); - page++; - } + /* Found a free page, will break it into order-0 pages */ + order = page_order(page); + isolated = __isolate_free_page(page, order); + if (!isolated) + break; + set_page_private(page, order); - /* If a page was split, advance to the end of it */ - if (isolated) { - cc->nr_freepages += isolated; - if (!strict && - cc->nr_migratepages <= cc->nr_freepages) { - blockpfn += isolated; - break; - } + total_isolated += isolated; + cc->nr_freepages += isolated; + list_add_tail(&page->lru, freelist); - blockpfn += isolated - 1; - cursor += isolated - 1; - continue; + if (!strict && cc->nr_migratepages <= cc->nr_freepages) { + blockpfn += isolated; + break; } + /* Advance to the end of split page */ + blockpfn += isolated - 1; + cursor += isolated - 1; + continue; isolate_fail: if (strict) @@ -464,6 +520,9 @@ isolate_fail: } + if (locked) + spin_unlock_irqrestore(&cc->zone->lock, flags); + /* * There is a tiny chance that we have read bogus compound_order(), * so be careful to not go outside of the pageblock. @@ -485,9 +544,6 @@ isolate_fail: if (strict && blockpfn < end_pfn) total_isolated = 0; - if (locked) - spin_unlock_irqrestore(&cc->zone->lock, flags); - /* Update the pageblock-skip if the whole pageblock was scanned */ if (blockpfn == end_pfn) update_pageblock_skip(cc, valid_page, total_isolated, false); @@ -519,10 +575,10 @@ isolate_freepages_range(struct compact_control *cc, LIST_HEAD(freelist); pfn = start_pfn; - block_start_pfn = pfn & ~(pageblock_nr_pages - 1); + block_start_pfn = pageblock_start_pfn(pfn); if (block_start_pfn < cc->zone->zone_start_pfn) block_start_pfn = cc->zone->zone_start_pfn; - block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); + block_end_pfn = pageblock_end_pfn(pfn); for (; pfn < end_pfn; pfn += isolated, block_start_pfn = block_end_pfn, @@ -538,8 +594,8 @@ isolate_freepages_range(struct compact_control *cc, * scanning range to right one. */ if (pfn >= block_end_pfn) { - block_start_pfn = pfn & ~(pageblock_nr_pages - 1); - block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); + block_start_pfn = pageblock_start_pfn(pfn); + block_end_pfn = pageblock_end_pfn(pfn); block_end_pfn = min(block_end_pfn, end_pfn); } @@ -565,7 +621,7 @@ isolate_freepages_range(struct compact_control *cc, */ } - /* split_free_page does not map the pages */ + /* __isolate_free_page() does not map the pages */ map_pages(&freelist); if (pfn < end_pfn) { @@ -590,8 +646,8 @@ static void acct_isolated(struct zone *zone, struct compact_control *cc) list_for_each_entry(page, &cc->migratepages, lru) count[!!page_is_file_cache(page)]++; - mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]); - mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]); + mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, count[0]); + mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, count[1]); } /* Similar to reclaim, but different enough that they don't share logic */ @@ -599,12 +655,12 @@ static bool too_many_isolated(struct zone *zone) { unsigned long active, inactive, isolated; - inactive = zone_page_state(zone, NR_INACTIVE_FILE) + - zone_page_state(zone, NR_INACTIVE_ANON); - active = zone_page_state(zone, NR_ACTIVE_FILE) + - zone_page_state(zone, NR_ACTIVE_ANON); - isolated = zone_page_state(zone, NR_ISOLATED_FILE) + - zone_page_state(zone, NR_ISOLATED_ANON); + inactive = node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE) + + node_page_state(zone->zone_pgdat, NR_INACTIVE_ANON); + active = node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE) + + node_page_state(zone->zone_pgdat, NR_ACTIVE_ANON); + isolated = node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE) + + node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON); return isolated > (inactive + active) / 2; } @@ -633,12 +689,13 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, { struct zone *zone = cc->zone; unsigned long nr_scanned = 0, nr_isolated = 0; - struct list_head *migratelist = &cc->migratepages; struct lruvec *lruvec; unsigned long flags = 0; bool locked = false; struct page *page = NULL, *valid_page = NULL; unsigned long start_pfn = low_pfn; + bool skip_on_failure = false; + unsigned long next_skip_pfn = 0; /* * Ensure that there are not too many pages isolated from the LRU @@ -659,9 +716,35 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (compact_should_abort(cc)) return 0; + if (cc->direct_compaction && (cc->mode == MIGRATE_ASYNC)) { + skip_on_failure = true; + next_skip_pfn = block_end_pfn(low_pfn, cc->order); + } + /* Time to isolate some pages for migration */ for (; low_pfn < end_pfn; low_pfn++) { - bool is_lru; + + if (skip_on_failure && low_pfn >= next_skip_pfn) { + /* + * We have isolated all migration candidates in the + * previous order-aligned block, and did not skip it due + * to failure. We should migrate the pages now and + * hopefully succeed compaction. + */ + if (nr_isolated) + break; + + /* + * We failed to isolate in the previous order-aligned + * block. Set the new boundary to the end of the + * current block. Note we can't simply increase + * next_skip_pfn by 1 << order, as low_pfn might have + * been incremented by a higher number due to skipping + * a compound or a high-order buddy page in the + * previous loop iteration. + */ + next_skip_pfn = block_end_pfn(low_pfn, cc->order); + } /* * Periodically drop the lock (if held) regardless of its @@ -669,12 +752,12 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, * if contended. */ if (!(low_pfn % SWAP_CLUSTER_MAX) - && compact_unlock_should_abort(&zone->lru_lock, flags, + && compact_unlock_should_abort(zone_lru_lock(zone), flags, &locked, cc)) break; if (!pfn_valid_within(low_pfn)) - continue; + goto isolate_fail; nr_scanned++; page = pfn_to_page(low_pfn); @@ -702,21 +785,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, } /* - * Check may be lockless but that's ok as we recheck later. - * It's possible to migrate LRU pages and balloon pages - * Skip any other type of page - */ - is_lru = PageLRU(page); - if (!is_lru) { - if (unlikely(balloon_page_movable(page))) { - if (balloon_page_isolate(page)) { - /* Successfully isolated */ - goto isolate_success; - } - } - } - - /* * Regardless of being on LRU, compound pages such as THP and * hugetlbfs are not to be compacted. We can potentially save * a lot of iterations if we skip them at once. The check is @@ -729,11 +797,33 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (likely(comp_order < MAX_ORDER)) low_pfn += (1UL << comp_order) - 1; - continue; + goto isolate_fail; } - if (!is_lru) - continue; + /* + * Check may be lockless but that's ok as we recheck later. + * It's possible to migrate LRU and non-lru movable pages. + * Skip any other type of page + */ + if (!PageLRU(page)) { + /* + * __PageMovable can return false positive so we need + * to verify it under page_lock. + */ + if (unlikely(__PageMovable(page)) && + !PageIsolated(page)) { + if (locked) { + spin_unlock_irqrestore(zone_lru_lock(zone), + flags); + locked = false; + } + + if (isolate_movable_page(page, isolate_mode)) + goto isolate_success; + } + + goto isolate_fail; + } /* * Migration will fail if an anonymous page is pinned in memory, @@ -742,18 +832,18 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, */ if (!page_mapping(page) && page_count(page) > page_mapcount(page)) - continue; + goto isolate_fail; /* If we already hold the lock, we can skip some rechecking */ if (!locked) { - locked = compact_trylock_irqsave(&zone->lru_lock, + locked = compact_trylock_irqsave(zone_lru_lock(zone), &flags, cc); if (!locked) break; /* Recheck PageLRU and PageCompound under lock */ if (!PageLRU(page)) - continue; + goto isolate_fail; /* * Page become compound since the non-locked check, @@ -762,15 +852,15 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, */ if (unlikely(PageCompound(page))) { low_pfn += (1UL << compound_order(page)) - 1; - continue; + goto isolate_fail; } } - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); /* Try isolate the page */ if (__isolate_lru_page(page, isolate_mode) != 0) - continue; + goto isolate_fail; VM_BUG_ON_PAGE(PageCompound(page), page); @@ -778,15 +868,55 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, del_page_from_lru_list(page, lruvec, page_lru(page)); isolate_success: - list_add(&page->lru, migratelist); + list_add(&page->lru, &cc->migratepages); cc->nr_migratepages++; nr_isolated++; + /* + * Record where we could have freed pages by migration and not + * yet flushed them to buddy allocator. + * - this is the lowest page that was isolated and likely be + * then freed by migration. + */ + if (!cc->last_migrated_pfn) + cc->last_migrated_pfn = low_pfn; + /* Avoid isolating too much */ if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) { ++low_pfn; break; } + + continue; +isolate_fail: + if (!skip_on_failure) + continue; + + /* + * We have isolated some pages, but then failed. Release them + * instead of migrating, as we cannot form the cc->order buddy + * page anyway. + */ + if (nr_isolated) { + if (locked) { + spin_unlock_irqrestore(zone_lru_lock(zone), flags); + locked = false; + } + acct_isolated(zone, cc); + putback_movable_pages(&cc->migratepages); + cc->nr_migratepages = 0; + cc->last_migrated_pfn = 0; + nr_isolated = 0; + } + + if (low_pfn < next_skip_pfn) { + low_pfn = next_skip_pfn - 1; + /* + * The check near the loop beginning would have updated + * next_skip_pfn too, but this is a bit simpler. + */ + next_skip_pfn += 1UL << cc->order; + } } /* @@ -797,7 +927,7 @@ isolate_success: low_pfn = end_pfn; if (locked) - spin_unlock_irqrestore(&zone->lru_lock, flags); + spin_unlock_irqrestore(zone_lru_lock(zone), flags); /* * Update the pageblock-skip information and cached scanner pfn, @@ -834,10 +964,10 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, /* Scan block by block. First and last block may be incomplete */ pfn = start_pfn; - block_start_pfn = pfn & ~(pageblock_nr_pages - 1); + block_start_pfn = pageblock_start_pfn(pfn); if (block_start_pfn < cc->zone->zone_start_pfn) block_start_pfn = cc->zone->zone_start_pfn; - block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); + block_end_pfn = pageblock_end_pfn(pfn); for (; pfn < end_pfn; pfn = block_end_pfn, block_start_pfn = block_end_pfn, @@ -852,16 +982,8 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, pfn = isolate_migratepages_block(cc, pfn, block_end_pfn, ISOLATE_UNEVICTABLE); - /* - * In case of fatal failure, release everything that might - * have been isolated in the previous iteration, and signal - * the failure back to caller. - */ - if (!pfn) { - putback_movable_pages(&cc->migratepages); - cc->nr_migratepages = 0; + if (!pfn) break; - } if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) break; @@ -932,10 +1054,10 @@ static void isolate_freepages(struct compact_control *cc) * is using. */ isolate_start_pfn = cc->free_pfn; - block_start_pfn = cc->free_pfn & ~(pageblock_nr_pages-1); + block_start_pfn = pageblock_start_pfn(cc->free_pfn); block_end_pfn = min(block_start_pfn + pageblock_nr_pages, zone_end_pfn(zone)); - low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages); + low_pfn = pageblock_end_pfn(cc->migrate_pfn); /* * Isolate free pages until enough are available to migrate the @@ -946,7 +1068,6 @@ static void isolate_freepages(struct compact_control *cc) block_end_pfn = block_start_pfn, block_start_pfn -= pageblock_nr_pages, isolate_start_pfn = block_start_pfn) { - /* * This can iterate a massively long zone without finding any * suitable migration targets, so periodically check if we need @@ -970,36 +1091,34 @@ static void isolate_freepages(struct compact_control *cc) continue; /* Found a block suitable for isolating free pages from. */ - isolate_freepages_block(cc, &isolate_start_pfn, - block_end_pfn, freelist, false); + isolate_freepages_block(cc, &isolate_start_pfn, block_end_pfn, + freelist, false); /* - * If we isolated enough freepages, or aborted due to async - * compaction being contended, terminate the loop. - * Remember where the free scanner should restart next time, - * which is where isolate_freepages_block() left off. - * But if it scanned the whole pageblock, isolate_start_pfn - * now points at block_end_pfn, which is the start of the next - * pageblock. - * In that case we will however want to restart at the start - * of the previous pageblock. + * If we isolated enough freepages, or aborted due to lock + * contention, terminate. */ if ((cc->nr_freepages >= cc->nr_migratepages) || cc->contended) { - if (isolate_start_pfn >= block_end_pfn) + if (isolate_start_pfn >= block_end_pfn) { + /* + * Restart at previous pageblock if more + * freepages can be isolated next time. + */ isolate_start_pfn = block_start_pfn - pageblock_nr_pages; + } break; - } else { + } else if (isolate_start_pfn < block_end_pfn) { /* - * isolate_freepages_block() should not terminate - * prematurely unless contended, or isolated enough + * If isolation failed early, do not continue + * needlessly. */ - VM_BUG_ON(isolate_start_pfn < block_end_pfn); + break; } } - /* split_free_page does not map the pages */ + /* __isolate_free_page() does not map the pages */ map_pages(freelist); /* @@ -1078,23 +1197,22 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, unsigned long block_start_pfn; unsigned long block_end_pfn; unsigned long low_pfn; - unsigned long isolate_start_pfn; struct page *page; const isolate_mode_t isolate_mode = (sysctl_compact_unevictable_allowed ? ISOLATE_UNEVICTABLE : 0) | - (cc->mode == MIGRATE_ASYNC ? ISOLATE_ASYNC_MIGRATE : 0); + (cc->mode != MIGRATE_SYNC ? ISOLATE_ASYNC_MIGRATE : 0); /* * Start at where we last stopped, or beginning of the zone as * initialized by compact_zone() */ low_pfn = cc->migrate_pfn; - block_start_pfn = cc->migrate_pfn & ~(pageblock_nr_pages - 1); + block_start_pfn = pageblock_start_pfn(low_pfn); if (block_start_pfn < zone->zone_start_pfn) block_start_pfn = zone->zone_start_pfn; /* Only scan within a pageblock boundary */ - block_end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages); + block_end_pfn = pageblock_end_pfn(low_pfn); /* * Iterate over whole pageblocks until we find the first suitable. @@ -1133,7 +1251,6 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, continue; /* Perform the isolation */ - isolate_start_pfn = low_pfn; low_pfn = isolate_migratepages_block(cc, low_pfn, block_end_pfn, isolate_mode); @@ -1143,15 +1260,6 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, } /* - * Record where we could have freed pages by migration and not - * yet flushed them to buddy allocator. - * - this is the lowest page that could have been isolated and - * then freed by migration. - */ - if (cc->nr_migratepages && !cc->last_migrated_pfn) - cc->last_migrated_pfn = isolate_start_pfn; - - /* * Either we isolated something and proceed with migration. Or * we failed and compact_zone should decide if we should * continue or not. @@ -1175,7 +1283,7 @@ static inline bool is_via_compact_memory(int order) return order == -1; } -static int __compact_finished(struct zone *zone, struct compact_control *cc, +static enum compact_result __compact_finished(struct zone *zone, struct compact_control *cc, const int migratetype) { unsigned int order; @@ -1198,7 +1306,10 @@ static int __compact_finished(struct zone *zone, struct compact_control *cc, if (cc->direct_compaction) zone->compact_blockskip_flush = true; - return COMPACT_COMPLETE; + if (cc->whole_zone) + return COMPACT_COMPLETE; + else + return COMPACT_PARTIAL_SKIPPED; } if (is_via_compact_memory(cc->order)) @@ -1238,8 +1349,9 @@ static int __compact_finished(struct zone *zone, struct compact_control *cc, return COMPACT_NO_SUITABLE_PAGE; } -static int compact_finished(struct zone *zone, struct compact_control *cc, - const int migratetype) +static enum compact_result compact_finished(struct zone *zone, + struct compact_control *cc, + const int migratetype) { int ret; @@ -1258,8 +1370,10 @@ static int compact_finished(struct zone *zone, struct compact_control *cc, * COMPACT_PARTIAL - If the allocation would succeed without compaction * COMPACT_CONTINUE - If compaction should run now */ -static unsigned long __compaction_suitable(struct zone *zone, int order, - int alloc_flags, int classzone_idx) +static enum compact_result __compaction_suitable(struct zone *zone, int order, + unsigned int alloc_flags, + int classzone_idx, + unsigned long wmark_target) { int fragindex; unsigned long watermark; @@ -1282,7 +1396,8 @@ static unsigned long __compaction_suitable(struct zone *zone, int order, * allocated and for a short time, the footprint is higher */ watermark += (2UL << order); - if (!zone_watermark_ok(zone, 0, watermark, classzone_idx, alloc_flags)) + if (!__zone_watermark_ok(zone, 0, watermark, classzone_idx, + alloc_flags, wmark_target)) return COMPACT_SKIPPED; /* @@ -1303,12 +1418,14 @@ static unsigned long __compaction_suitable(struct zone *zone, int order, return COMPACT_CONTINUE; } -unsigned long compaction_suitable(struct zone *zone, int order, - int alloc_flags, int classzone_idx) +enum compact_result compaction_suitable(struct zone *zone, int order, + unsigned int alloc_flags, + int classzone_idx) { - unsigned long ret; + enum compact_result ret; - ret = __compaction_suitable(zone, order, alloc_flags, classzone_idx); + ret = __compaction_suitable(zone, order, alloc_flags, classzone_idx, + zone_page_state(zone, NR_FREE_PAGES)); trace_mm_compaction_suitable(zone, order, ret); if (ret == COMPACT_NOT_SUITABLE_ZONE) ret = COMPACT_SKIPPED; @@ -1316,9 +1433,42 @@ unsigned long compaction_suitable(struct zone *zone, int order, return ret; } -static int compact_zone(struct zone *zone, struct compact_control *cc) +bool compaction_zonelist_suitable(struct alloc_context *ac, int order, + int alloc_flags) { - int ret; + struct zone *zone; + struct zoneref *z; + + /* + * Make sure at least one zone would pass __compaction_suitable if we continue + * retrying the reclaim. + */ + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, + ac->nodemask) { + unsigned long available; + enum compact_result compact_result; + + /* + * Do not consider all the reclaimable memory because we do not + * want to trash just for a single high order allocation which + * is even not guaranteed to appear even if __compaction_suitable + * is happy about the watermark check. + */ + available = zone_reclaimable_pages(zone) / order; + available += zone_page_state_snapshot(zone, NR_FREE_PAGES); + compact_result = __compaction_suitable(zone, order, alloc_flags, + ac_classzone_idx(ac), available); + if (compact_result != COMPACT_SKIPPED && + compact_result != COMPACT_NOT_SUITABLE_ZONE) + return true; + } + + return false; +} + +static enum compact_result compact_zone(struct zone *zone, struct compact_control *cc) +{ + enum compact_result ret; unsigned long start_pfn = zone->zone_start_pfn; unsigned long end_pfn = zone_end_pfn(zone); const int migratetype = gfpflags_to_migratetype(cc->gfp_mask); @@ -1326,15 +1476,12 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) ret = compaction_suitable(zone, cc->order, cc->alloc_flags, cc->classzone_idx); - switch (ret) { - case COMPACT_PARTIAL: - case COMPACT_SKIPPED: - /* Compaction is likely to fail */ + /* Compaction is likely to fail */ + if (ret == COMPACT_PARTIAL || ret == COMPACT_SKIPPED) return ret; - case COMPACT_CONTINUE: - /* Fall through to compaction */ - ; - } + + /* huh, compaction_suitable is returning something unexpected */ + VM_BUG_ON(ret != COMPACT_CONTINUE); /* * Clear pageblock skip if there were failures recently and compaction @@ -1351,7 +1498,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync]; cc->free_pfn = zone->compact_cached_free_pfn; if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) { - cc->free_pfn = round_down(end_pfn - 1, pageblock_nr_pages); + cc->free_pfn = pageblock_start_pfn(end_pfn - 1); zone->compact_cached_free_pfn = cc->free_pfn; } if (cc->migrate_pfn < start_pfn || cc->migrate_pfn >= end_pfn) { @@ -1359,6 +1506,10 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn; zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; } + + if (cc->migrate_pfn == start_pfn) + cc->whole_zone = true; + cc->last_migrated_pfn = 0; trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, @@ -1406,6 +1557,18 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) ret = COMPACT_CONTENDED; goto out; } + /* + * We failed to migrate at least one page in the current + * order-aligned block, so skip the rest of it. + */ + if (cc->direct_compaction && + (cc->mode == MIGRATE_ASYNC)) { + cc->migrate_pfn = block_end_pfn( + cc->migrate_pfn - 1, cc->order); + /* Draining pcplists is useless in this case */ + cc->last_migrated_pfn = 0; + + } } check_drain: @@ -1419,7 +1582,7 @@ check_drain: if (cc->order > 0 && cc->last_migrated_pfn) { int cpu; unsigned long current_block_start = - cc->migrate_pfn & ~((1UL << cc->order) - 1); + block_start_pfn(cc->migrate_pfn, cc->order); if (cc->last_migrated_pfn < current_block_start) { cpu = get_cpu(); @@ -1444,7 +1607,7 @@ out: cc->nr_freepages = 0; VM_BUG_ON(free_pfn == 0); /* The cached pfn is always the first in a pageblock */ - free_pfn &= ~(pageblock_nr_pages-1); + free_pfn = pageblock_start_pfn(free_pfn); /* * Only go back, not forward. The cached pfn might have been * already reset to zone end in compact_finished() @@ -1456,24 +1619,22 @@ out: trace_mm_compaction_end(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn, sync, ret); - if (ret == COMPACT_CONTENDED) - ret = COMPACT_PARTIAL; - return ret; } -static unsigned long compact_zone_order(struct zone *zone, int order, - gfp_t gfp_mask, enum migrate_mode mode, int *contended, - int alloc_flags, int classzone_idx) +static enum compact_result compact_zone_order(struct zone *zone, int order, + gfp_t gfp_mask, enum compact_priority prio, + unsigned int alloc_flags, int classzone_idx) { - unsigned long ret; + enum compact_result ret; struct compact_control cc = { .nr_freepages = 0, .nr_migratepages = 0, .order = order, .gfp_mask = gfp_mask, .zone = zone, - .mode = mode, + .mode = (prio == COMPACT_PRIO_ASYNC) ? + MIGRATE_ASYNC : MIGRATE_SYNC_LIGHT, .alloc_flags = alloc_flags, .classzone_idx = classzone_idx, .direct_compaction = true, @@ -1486,7 +1647,6 @@ static unsigned long compact_zone_order(struct zone *zone, int order, VM_BUG_ON(!list_empty(&cc.freepages)); VM_BUG_ON(!list_empty(&cc.migratepages)); - *contended = cc.contended; return ret; } @@ -1499,52 +1659,42 @@ int sysctl_extfrag_threshold = 500; * @alloc_flags: The allocation flags of the current allocation * @ac: The context of current allocation * @mode: The migration mode for async, sync light, or sync migration - * @contended: Return value that determines if compaction was aborted due to - * need_resched() or lock contention * * This is the main entry point for direct page compaction. */ -unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order, - int alloc_flags, const struct alloc_context *ac, - enum migrate_mode mode, int *contended) +enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, + unsigned int alloc_flags, const struct alloc_context *ac, + enum compact_priority prio) { int may_enter_fs = gfp_mask & __GFP_FS; int may_perform_io = gfp_mask & __GFP_IO; struct zoneref *z; struct zone *zone; - int rc = COMPACT_DEFERRED; - int all_zones_contended = COMPACT_CONTENDED_LOCK; /* init for &= op */ - - *contended = COMPACT_CONTENDED_NONE; + enum compact_result rc = COMPACT_SKIPPED; /* Check if the GFP flags allow compaction */ - if (!order || !may_enter_fs || !may_perform_io) + if (!may_enter_fs || !may_perform_io) return COMPACT_SKIPPED; - trace_mm_compaction_try_to_compact_pages(order, gfp_mask, mode); + trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio); /* Compact each zone in the list */ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, ac->nodemask) { - int status; - int zone_contended; + enum compact_result status; - if (compaction_deferred(zone, order)) + if (compaction_deferred(zone, order)) { + rc = max_t(enum compact_result, COMPACT_DEFERRED, rc); continue; + } - status = compact_zone_order(zone, order, gfp_mask, mode, - &zone_contended, alloc_flags, - ac->classzone_idx); + status = compact_zone_order(zone, order, gfp_mask, prio, + alloc_flags, ac_classzone_idx(ac)); rc = max(status, rc); - /* - * It takes at least one zone that wasn't lock contended - * to clear all_zones_contended. - */ - all_zones_contended &= zone_contended; /* If a normal allocation would succeed, stop compacting */ if (zone_watermark_ok(zone, order, low_wmark_pages(zone), - ac->classzone_idx, alloc_flags)) { + ac_classzone_idx(ac), alloc_flags)) { /* * We think the allocation will succeed in this zone, * but it is not certain, hence the false. The caller @@ -1552,58 +1702,29 @@ unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order, * succeeds in this zone. */ compaction_defer_reset(zone, order, false); - /* - * It is possible that async compaction aborted due to - * need_resched() and the watermarks were ok thanks to - * somebody else freeing memory. The allocation can - * however still fail so we better signal the - * need_resched() contention anyway (this will not - * prevent the allocation attempt). - */ - if (zone_contended == COMPACT_CONTENDED_SCHED) - *contended = COMPACT_CONTENDED_SCHED; - goto break_loop; + break; } - if (mode != MIGRATE_ASYNC && status == COMPACT_COMPLETE) { + if (prio != COMPACT_PRIO_ASYNC && (status == COMPACT_COMPLETE || + status == COMPACT_PARTIAL_SKIPPED)) /* * We think that allocation won't succeed in this zone * so we defer compaction there. If it ends up * succeeding after all, it will be reset. */ defer_compaction(zone, order); - } /* * We might have stopped compacting due to need_resched() in * async compaction, or due to a fatal signal detected. In that - * case do not try further zones and signal need_resched() - * contention. + * case do not try further zones */ - if ((zone_contended == COMPACT_CONTENDED_SCHED) - || fatal_signal_pending(current)) { - *contended = COMPACT_CONTENDED_SCHED; - goto break_loop; - } - - continue; -break_loop: - /* - * We might not have tried all the zones, so be conservative - * and assume they are not all lock contended. - */ - all_zones_contended = 0; - break; + if ((prio == COMPACT_PRIO_ASYNC && need_resched()) + || fatal_signal_pending(current)) + break; } - /* - * If at least one zone wasn't deferred or skipped, we report if all - * zones that were tried were lock contended. - */ - if (rc > COMPACT_SKIPPED && all_zones_contended) - *contended = COMPACT_CONTENDED_LOCK; - return rc; } @@ -1741,7 +1862,7 @@ void compaction_unregister_node(struct node *node) static inline bool kcompactd_work_requested(pg_data_t *pgdat) { - return pgdat->kcompactd_max_order > 0; + return pgdat->kcompactd_max_order > 0 || kthread_should_stop(); } static bool kcompactd_node_suitable(pg_data_t *pgdat) @@ -1750,7 +1871,7 @@ static bool kcompactd_node_suitable(pg_data_t *pgdat) struct zone *zone; enum zone_type classzone_idx = pgdat->kcompactd_classzone_idx; - for (zoneid = 0; zoneid < classzone_idx; zoneid++) { + for (zoneid = 0; zoneid <= classzone_idx; zoneid++) { zone = &pgdat->node_zones[zoneid]; if (!populated_zone(zone)) @@ -1785,7 +1906,7 @@ static void kcompactd_do_work(pg_data_t *pgdat) cc.classzone_idx); count_vm_event(KCOMPACTD_WAKE); - for (zoneid = 0; zoneid < cc.classzone_idx; zoneid++) { + for (zoneid = 0; zoneid <= cc.classzone_idx; zoneid++) { int status; zone = &pgdat->node_zones[zoneid]; @@ -1805,13 +1926,15 @@ static void kcompactd_do_work(pg_data_t *pgdat) INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); + if (kthread_should_stop()) + return; status = compact_zone(zone, &cc); if (zone_watermark_ok(zone, cc.order, low_wmark_pages(zone), cc.classzone_idx, 0)) { success = true; compaction_defer_reset(zone, cc.order, false); - } else if (status == COMPACT_COMPLETE) { + } else if (status == COMPACT_PARTIAL_SKIPPED || status == COMPACT_COMPLETE) { /* * We use sync migration mode here, so we defer like * sync direct compaction does. diff --git a/mm/fadvise.c b/mm/fadvise.c index b8a5bc66b0c0..6c707bfe02fd 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -97,8 +97,8 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) break; case POSIX_FADV_WILLNEED: /* First and last PARTIAL page! */ - start_index = offset >> PAGE_CACHE_SHIFT; - end_index = endbyte >> PAGE_CACHE_SHIFT; + start_index = offset >> PAGE_SHIFT; + end_index = endbyte >> PAGE_SHIFT; /* Careful about overflow on the "+1" */ nrpages = end_index - start_index + 1; @@ -124,8 +124,19 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) * preserved on the expectation that it is better to preserve * needed memory than to discard unneeded memory. */ - start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT; - end_index = (endbyte >> PAGE_CACHE_SHIFT); + start_index = (offset+(PAGE_SIZE-1)) >> PAGE_SHIFT; + end_index = (endbyte >> PAGE_SHIFT); + if ((endbyte & ~PAGE_MASK) != ~PAGE_MASK) { + /* First page is tricky as 0 - 1 = -1, but pgoff_t + * is unsigned, so the end_index >= start_index + * check below would be true and we'll discard the whole + * file cache which is not what was asked. + */ + if (end_index == 0) + break; + + end_index--; + } if (end_index >= start_index) { unsigned long count = invalidate_mapping_pages(mapping, diff --git a/mm/filemap.c b/mm/filemap.c index a8c69c8c0a90..daef091d4c50 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -95,8 +95,8 @@ * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->tree_lock (try_to_unmap_one) - * ->zone.lru_lock (follow_page->mark_page_accessed) - * ->zone.lru_lock (check_pte_range->isolate_lru_page) + * ->zone_lru_lock(zone) (follow_page->mark_page_accessed) + * ->zone_lru_lock(zone) (check_pte_range->isolate_lru_page) * ->private_lock (page_remove_rmap->set_page_dirty) * ->tree_lock (page_remove_rmap->set_page_dirty) * bdi.wb->list_lock (page_remove_rmap->set_page_dirty) @@ -114,17 +114,14 @@ static void page_cache_tree_delete(struct address_space *mapping, struct page *page, void *shadow) { struct radix_tree_node *node; - unsigned long index; - unsigned int offset; - unsigned int tag; - void **slot; - - VM_BUG_ON(!PageLocked(page)); + int i, nr = PageHuge(page) ? 1 : hpage_nr_pages(page); - __radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageTail(page), page); + VM_BUG_ON_PAGE(nr != 1 && shadow, page); if (shadow) { - mapping->nrexceptional++; + mapping->nrexceptional += nr; /* * Make sure the nrexceptional update is committed before * the nrpages update so that final truncate racing @@ -133,43 +130,38 @@ static void page_cache_tree_delete(struct address_space *mapping, */ smp_wmb(); } - mapping->nrpages--; - - if (!node) { - /* Clear direct pointer tags in root node */ - mapping->page_tree.gfp_mask &= __GFP_BITS_MASK; - radix_tree_replace_slot(slot, shadow); - return; - } + mapping->nrpages -= nr; - /* Clear tree tags for the removed page */ - index = page->index; - offset = index & RADIX_TREE_MAP_MASK; - for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { - if (test_bit(offset, node->tags[tag])) - radix_tree_tag_clear(&mapping->page_tree, index, tag); - } - - /* Delete page, swap shadow entry */ - radix_tree_replace_slot(slot, shadow); - workingset_node_pages_dec(node); - if (shadow) - workingset_node_shadows_inc(node); - else - if (__radix_tree_delete_node(&mapping->page_tree, node)) + for (i = 0; i < nr; i++) { + node = radix_tree_replace_clear_tags(&mapping->page_tree, + page->index + i, shadow); + if (!node) { + VM_BUG_ON_PAGE(nr != 1, page); return; + } - /* - * Track node that only contains shadow entries. - * - * Avoid acquiring the list_lru lock if already tracked. The - * list_empty() test is safe as node->private_list is - * protected by mapping->tree_lock. - */ - if (!workingset_node_pages(node) && - list_empty(&node->private_list)) { - node->private_data = mapping; - list_lru_add(&workingset_shadow_nodes, &node->private_list); + workingset_node_pages_dec(node); + if (shadow) + workingset_node_shadows_inc(node); + else + if (__radix_tree_delete_node(&mapping->page_tree, node)) + continue; + + /* + * Track node that only contains shadow entries. DAX mappings + * contain no shadow entries and may contain other exceptional + * entries so skip those. + * + * Avoid acquiring the list_lru lock if already tracked. + * The list_empty() test is safe as node->private_list is + * protected by mapping->tree_lock. + */ + if (!dax_mapping(mapping) && !workingset_node_pages(node) && + list_empty(&node->private_list)) { + node->private_data = mapping; + list_lru_add(&workingset_shadow_nodes, + &node->private_list); + } } } @@ -181,6 +173,7 @@ static void page_cache_tree_delete(struct address_space *mapping, void __delete_from_page_cache(struct page *page, void *shadow) { struct address_space *mapping = page->mapping; + int nr = hpage_nr_pages(page); trace_mm_filemap_delete_from_page_cache(page); /* @@ -193,6 +186,7 @@ void __delete_from_page_cache(struct page *page, void *shadow) else cleancache_invalidate_page(mapping, page); + VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_mapped(page), page); if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) { int mapcount; @@ -213,7 +207,7 @@ void __delete_from_page_cache(struct page *page, void *shadow) * some other bad page check should catch it later. */ page_mapcount_reset(page); - atomic_sub(mapcount, &page->_count); + page_ref_sub(page, mapcount); } } @@ -224,9 +218,14 @@ void __delete_from_page_cache(struct page *page, void *shadow) /* hugetlb pages do not participate in page cache accounting. */ if (!PageHuge(page)) - __dec_zone_page_state(page, NR_FILE_PAGES); - if (PageSwapBacked(page)) - __dec_zone_page_state(page, NR_SHMEM); + __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr); + if (PageSwapBacked(page)) { + __mod_node_page_state(page_pgdat(page), NR_SHMEM, -nr); + if (PageTransHuge(page)) + __dec_node_page_state(page, NR_SHMEM_THPS); + } else { + VM_BUG_ON_PAGE(PageTransHuge(page) && !PageHuge(page), page); + } /* * At this point page must be either written or cleaned by truncate. @@ -250,9 +249,8 @@ void __delete_from_page_cache(struct page *page, void *shadow) */ void delete_from_page_cache(struct page *page) { - struct address_space *mapping = page->mapping; + struct address_space *mapping = page_mapping(page); unsigned long flags; - void (*freepage)(struct page *); BUG_ON(!PageLocked(page)); @@ -265,11 +263,17 @@ void delete_from_page_cache(struct page *page) if (freepage) freepage(page); - page_cache_release(page); + + if (PageTransHuge(page) && !PageHuge(page)) { + page_ref_sub(page, HPAGE_PMD_NR); + VM_BUG_ON_PAGE(page_count(page) <= 0, page); + } else { + put_page(page); + } } EXPORT_SYMBOL(delete_from_page_cache); -static int filemap_check_errors(struct address_space *mapping) +int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ @@ -281,6 +285,7 @@ static int filemap_check_errors(struct address_space *mapping) ret = -EIO; return ret; } +EXPORT_SYMBOL(filemap_check_errors); /** * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range @@ -352,8 +357,8 @@ EXPORT_SYMBOL(filemap_flush); static int __filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { - pgoff_t index = start_byte >> PAGE_CACHE_SHIFT; - pgoff_t end = end_byte >> PAGE_CACHE_SHIFT; + pgoff_t index = start_byte >> PAGE_SHIFT; + pgoff_t end = end_byte >> PAGE_SHIFT; struct pagevec pvec; int nr_pages; int ret = 0; @@ -550,7 +555,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) pgoff_t offset = old->index; freepage = mapping->a_ops->freepage; - page_cache_get(new); + get_page(new); new->mapping = mapping; new->index = offset; @@ -564,15 +569,15 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) * hugetlb pages do not participate in page cache accounting. */ if (!PageHuge(new)) - __inc_zone_page_state(new, NR_FILE_PAGES); + __inc_node_page_state(new, NR_FILE_PAGES); if (PageSwapBacked(new)) - __inc_zone_page_state(new, NR_SHMEM); + __inc_node_page_state(new, NR_SHMEM); spin_unlock_irqrestore(&mapping->tree_lock, flags); mem_cgroup_migrate(old, new); radix_tree_preload_end(); if (freepage) freepage(old); - page_cache_release(old); + put_page(old); } return error; @@ -597,14 +602,24 @@ static int page_cache_tree_insert(struct address_space *mapping, if (!radix_tree_exceptional_entry(p)) return -EEXIST; - if (WARN_ON(dax_mapping(mapping))) - return -EINVAL; - - if (shadowp) - *shadowp = p; mapping->nrexceptional--; - if (node) - workingset_node_shadows_dec(node); + if (!dax_mapping(mapping)) { + if (shadowp) + *shadowp = p; + if (node) + workingset_node_shadows_dec(node); + } else { + /* DAX can replace empty locked entry with a hole */ + WARN_ON_ONCE(p != + (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | + RADIX_DAX_ENTRY_LOCK)); + /* DAX accounts exceptional entries as normal pages */ + if (node) + workingset_node_pages_dec(node); + /* Wakeup waiters for exceptional entry lock */ + dax_wake_mapping_entry_waiter(mapping, page->index, + false); + } } radix_tree_replace_slot(slot, page); mapping->nrpages++; @@ -651,7 +666,7 @@ static int __add_to_page_cache_locked(struct page *page, return error; } - page_cache_get(page); + get_page(page); page->mapping = mapping; page->index = offset; @@ -663,7 +678,7 @@ static int __add_to_page_cache_locked(struct page *page, /* hugetlb pages do not participate in page cache accounting. */ if (!huge) - __inc_zone_page_state(page, NR_FILE_PAGES); + __inc_node_page_state(page, NR_FILE_PAGES); spin_unlock_irq(&mapping->tree_lock); if (!huge) mem_cgroup_commit_charge(page, memcg, false, false); @@ -675,7 +690,7 @@ err_insert: spin_unlock_irq(&mapping->tree_lock); if (!huge) mem_cgroup_cancel_charge(page, memcg, false); - page_cache_release(page); + put_page(page); return error; } @@ -713,8 +728,12 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, * The page might have been evicted from cache only * recently, in which case it should be activated like * any other repeatedly accessed page. + * The exception is pages getting rewritten; evicting other + * data from the working set, only to cache data that will + * get overwritten with something else, is a waste of memory. */ - if (shadow && workingset_refault(shadow)) { + if (!(gfp_mask & __GFP_WRITE) && + shadow && workingset_refault(shadow)) { SetPageActive(page); workingset_activation(page); } else @@ -868,9 +887,9 @@ EXPORT_SYMBOL(end_page_writeback); * After completing I/O on a page, call this routine to update the page * flags appropriately */ -void page_endio(struct page *page, int rw, int err) +void page_endio(struct page *page, int op, int err) { - if (rw == READ) { + if (!op_is_write(op)) { if (!err) { SetPageUptodate(page); } else { @@ -878,7 +897,7 @@ void page_endio(struct page *page, int rw, int err) SetPageError(page); } unlock_page(page); - } else { /* rw == WRITE */ + } else { if (err) { SetPageError(page); if (page->mapping) @@ -1054,7 +1073,7 @@ EXPORT_SYMBOL(page_cache_prev_hole); struct page *find_get_entry(struct address_space *mapping, pgoff_t offset) { void **pagep; - struct page *page; + struct page *head, *page; rcu_read_lock(); repeat: @@ -1074,8 +1093,16 @@ repeat: */ goto out; } - if (!page_cache_get_speculative(page)) + + head = compound_head(page); + if (!page_cache_get_speculative(head)) + goto repeat; + + /* The page was split under us? */ + if (compound_head(page) != head) { + put_page(head); goto repeat; + } /* * Has the page moved? @@ -1083,7 +1110,7 @@ repeat: * include/linux/pagemap.h for details. */ if (unlikely(page != *pagep)) { - page_cache_release(page); + put_page(head); goto repeat; } } @@ -1119,12 +1146,12 @@ repeat: if (page && !radix_tree_exception(page)) { lock_page(page); /* Has the page been truncated? */ - if (unlikely(page->mapping != mapping)) { + if (unlikely(page_mapping(page) != mapping)) { unlock_page(page); - page_cache_release(page); + put_page(page); goto repeat; } - VM_BUG_ON_PAGE(page->index != offset, page); + VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page); } return page; } @@ -1168,7 +1195,7 @@ repeat: if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { if (!trylock_page(page)) { - page_cache_release(page); + put_page(page); return NULL; } } else { @@ -1178,7 +1205,7 @@ repeat: /* Has the page been truncated? */ if (unlikely(page->mapping != mapping)) { unlock_page(page); - page_cache_release(page); + put_page(page); goto repeat; } VM_BUG_ON_PAGE(page->index != offset, page); @@ -1209,7 +1236,7 @@ no_page: err = add_to_page_cache_lru(page, mapping, offset, gfp_mask & GFP_RECLAIM_MASK); if (unlikely(err)) { - page_cache_release(page); + put_page(page); page = NULL; if (err == -EEXIST) goto repeat; @@ -1256,7 +1283,7 @@ unsigned find_get_entries(struct address_space *mapping, rcu_read_lock(); radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { - struct page *page; + struct page *head, *page; repeat: page = radix_tree_deref_slot(slot); if (unlikely(!page)) @@ -1273,12 +1300,20 @@ repeat: */ goto export; } - if (!page_cache_get_speculative(page)) + + head = compound_head(page); + if (!page_cache_get_speculative(head)) goto repeat; + /* The page was split under us? */ + if (compound_head(page) != head) { + put_page(head); + goto repeat; + } + /* Has the page moved? */ if (unlikely(page != *slot)) { - page_cache_release(page); + put_page(head); goto repeat; } export: @@ -1319,7 +1354,7 @@ unsigned find_get_pages(struct address_space *mapping, pgoff_t start, rcu_read_lock(); radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { - struct page *page; + struct page *head, *page; repeat: page = radix_tree_deref_slot(slot); if (unlikely(!page)) @@ -1338,12 +1373,19 @@ repeat: continue; } - if (!page_cache_get_speculative(page)) + head = compound_head(page); + if (!page_cache_get_speculative(head)) + goto repeat; + + /* The page was split under us? */ + if (compound_head(page) != head) { + put_page(head); goto repeat; + } /* Has the page moved? */ if (unlikely(page != *slot)) { - page_cache_release(page); + put_page(head); goto repeat; } @@ -1380,7 +1422,7 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, rcu_read_lock(); radix_tree_for_each_contig(slot, &mapping->page_tree, &iter, index) { - struct page *page; + struct page *head, *page; repeat: page = radix_tree_deref_slot(slot); /* The hole, there no reason to continue */ @@ -1400,12 +1442,19 @@ repeat: break; } - if (!page_cache_get_speculative(page)) + head = compound_head(page); + if (!page_cache_get_speculative(head)) + goto repeat; + + /* The page was split under us? */ + if (compound_head(page) != head) { + put_page(head); goto repeat; + } /* Has the page moved? */ if (unlikely(page != *slot)) { - page_cache_release(page); + put_page(head); goto repeat; } @@ -1414,8 +1463,8 @@ repeat: * otherwise we can get both false positives and false * negatives, which is just confusing to the caller. */ - if (page->mapping == NULL || page->index != iter.index) { - page_cache_release(page); + if (page->mapping == NULL || page_to_pgoff(page) != iter.index) { + put_page(page); break; } @@ -1452,7 +1501,7 @@ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, rcu_read_lock(); radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter, *index, tag) { - struct page *page; + struct page *head, *page; repeat: page = radix_tree_deref_slot(slot); if (unlikely(!page)) @@ -1477,12 +1526,19 @@ repeat: continue; } - if (!page_cache_get_speculative(page)) + head = compound_head(page); + if (!page_cache_get_speculative(head)) goto repeat; + /* The page was split under us? */ + if (compound_head(page) != head) { + put_page(head); + goto repeat; + } + /* Has the page moved? */ if (unlikely(page != *slot)) { - page_cache_release(page); + put_page(head); goto repeat; } @@ -1526,7 +1582,7 @@ unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start, rcu_read_lock(); radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter, start, tag) { - struct page *page; + struct page *head, *page; repeat: page = radix_tree_deref_slot(slot); if (unlikely(!page)) @@ -1544,12 +1600,20 @@ repeat: */ goto export; } - if (!page_cache_get_speculative(page)) + + head = compound_head(page); + if (!page_cache_get_speculative(head)) goto repeat; + /* The page was split under us? */ + if (compound_head(page) != head) { + put_page(head); + goto repeat; + } + /* Has the page moved? */ if (unlikely(page != *slot)) { - page_cache_release(page); + put_page(head); goto repeat; } export: @@ -1610,11 +1674,11 @@ static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos, unsigned int prev_offset; int error = 0; - index = *ppos >> PAGE_CACHE_SHIFT; - prev_index = ra->prev_pos >> PAGE_CACHE_SHIFT; - prev_offset = ra->prev_pos & (PAGE_CACHE_SIZE-1); - last_index = (*ppos + iter->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT; - offset = *ppos & ~PAGE_CACHE_MASK; + index = *ppos >> PAGE_SHIFT; + prev_index = ra->prev_pos >> PAGE_SHIFT; + prev_offset = ra->prev_pos & (PAGE_SIZE-1); + last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT; + offset = *ppos & ~PAGE_MASK; for (;;) { struct page *page; @@ -1648,7 +1712,7 @@ find_page: if (PageUptodate(page)) goto page_ok; - if (inode->i_blkbits == PAGE_CACHE_SHIFT || + if (inode->i_blkbits == PAGE_SHIFT || !mapping->a_ops->is_partially_uptodate) goto page_not_up_to_date; if (!trylock_page(page)) @@ -1672,18 +1736,18 @@ page_ok: */ isize = i_size_read(inode); - end_index = (isize - 1) >> PAGE_CACHE_SHIFT; + end_index = (isize - 1) >> PAGE_SHIFT; if (unlikely(!isize || index > end_index)) { - page_cache_release(page); + put_page(page); goto out; } /* nr is the maximum number of bytes to copy from this page */ - nr = PAGE_CACHE_SIZE; + nr = PAGE_SIZE; if (index == end_index) { - nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1; + nr = ((isize - 1) & ~PAGE_MASK) + 1; if (nr <= offset) { - page_cache_release(page); + put_page(page); goto out; } } @@ -1711,11 +1775,11 @@ page_ok: ret = copy_page_to_iter(page, offset, nr, iter); offset += ret; - index += offset >> PAGE_CACHE_SHIFT; - offset &= ~PAGE_CACHE_MASK; + index += offset >> PAGE_SHIFT; + offset &= ~PAGE_MASK; prev_offset = offset; - page_cache_release(page); + put_page(page); written += ret; if (!iov_iter_count(iter)) goto out; @@ -1735,7 +1799,7 @@ page_not_up_to_date_locked: /* Did it get truncated before we got the lock? */ if (!page->mapping) { unlock_page(page); - page_cache_release(page); + put_page(page); continue; } @@ -1757,7 +1821,7 @@ readpage: if (unlikely(error)) { if (error == AOP_TRUNCATED_PAGE) { - page_cache_release(page); + put_page(page); error = 0; goto find_page; } @@ -1774,7 +1838,7 @@ readpage: * invalidate_mapping_pages got it */ unlock_page(page); - page_cache_release(page); + put_page(page); goto find_page; } unlock_page(page); @@ -1789,7 +1853,7 @@ readpage: readpage_error: /* UHHUH! A synchronous read error occurred. Report it */ - page_cache_release(page); + put_page(page); goto out; no_cached_page: @@ -1805,7 +1869,7 @@ no_cached_page: error = add_to_page_cache_lru(page, mapping, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error) { - page_cache_release(page); + put_page(page); if (error == -EEXIST) { error = 0; goto find_page; @@ -1817,10 +1881,10 @@ no_cached_page: out: ra->prev_pos = prev_index; - ra->prev_pos <<= PAGE_CACHE_SHIFT; + ra->prev_pos <<= PAGE_SHIFT; ra->prev_pos |= prev_offset; - *ppos = ((loff_t)index << PAGE_CACHE_SHIFT) + offset; + *ppos = ((loff_t)index << PAGE_SHIFT) + offset; file_accessed(filp); return written ? written : error; } @@ -1838,8 +1902,6 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; ssize_t retval = 0; - loff_t *ppos = &iocb->ki_pos; - loff_t pos = *ppos; size_t count = iov_iter_count(iter); if (!count) @@ -1851,15 +1913,15 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) loff_t size; size = i_size_read(inode); - retval = filemap_write_and_wait_range(mapping, pos, - pos + count - 1); + retval = filemap_write_and_wait_range(mapping, iocb->ki_pos, + iocb->ki_pos + count - 1); if (!retval) { struct iov_iter data = *iter; - retval = mapping->a_ops->direct_IO(iocb, &data, pos); + retval = mapping->a_ops->direct_IO(iocb, &data); } if (retval > 0) { - *ppos = pos + retval; + iocb->ki_pos += retval; iov_iter_advance(iter, retval); } @@ -1872,14 +1934,14 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) * the rest of the read. Buffered reads will not work for * DAX files, so don't bother trying. */ - if (retval < 0 || !iov_iter_count(iter) || *ppos >= size || + if (retval < 0 || !iov_iter_count(iter) || iocb->ki_pos >= size || IS_DAX(inode)) { file_accessed(file); goto out; } } - retval = do_generic_file_read(file, ppos, iter, retval); + retval = do_generic_file_read(file, &iocb->ki_pos, iter, retval); out: return retval; } @@ -1912,7 +1974,7 @@ static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask) else if (ret == -EEXIST) ret = 0; /* losing race to add is OK */ - page_cache_release(page); + put_page(page); } while (ret == AOP_TRUNCATED_PAGE); @@ -2022,8 +2084,8 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) loff_t size; int ret = 0; - size = round_up(i_size_read(inode), PAGE_CACHE_SIZE); - if (offset >= size >> PAGE_CACHE_SHIFT) + size = round_up(i_size_read(inode), PAGE_SIZE); + if (offset >= size >> PAGE_SHIFT) return VM_FAULT_SIGBUS; /* @@ -2049,7 +2111,7 @@ retry_find: } if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) { - page_cache_release(page); + put_page(page); return ret | VM_FAULT_RETRY; } @@ -2072,10 +2134,10 @@ retry_find: * Found the page and have a reference on it. * We must recheck i_size under page lock. */ - size = round_up(i_size_read(inode), PAGE_CACHE_SIZE); - if (unlikely(offset >= size >> PAGE_CACHE_SHIFT)) { + size = round_up(i_size_read(inode), PAGE_SIZE); + if (unlikely(offset >= size >> PAGE_SHIFT)) { unlock_page(page); - page_cache_release(page); + put_page(page); return VM_FAULT_SIGBUS; } @@ -2120,7 +2182,7 @@ page_not_uptodate: if (!PageUptodate(page)) error = -EIO; } - page_cache_release(page); + put_page(page); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; @@ -2131,21 +2193,21 @@ page_not_uptodate: } EXPORT_SYMBOL(filemap_fault); -void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf) +void filemap_map_pages(struct fault_env *fe, + pgoff_t start_pgoff, pgoff_t end_pgoff) { struct radix_tree_iter iter; void **slot; - struct file *file = vma->vm_file; + struct file *file = fe->vma->vm_file; struct address_space *mapping = file->f_mapping; + pgoff_t last_pgoff = start_pgoff; loff_t size; - struct page *page; - unsigned long address = (unsigned long) vmf->virtual_address; - unsigned long addr; - pte_t *pte; + struct page *head, *page; rcu_read_lock(); - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, vmf->pgoff) { - if (iter.index > vmf->max_pgoff) + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, + start_pgoff) { + if (iter.index > end_pgoff) break; repeat: page = radix_tree_deref_slot(slot); @@ -2159,12 +2221,19 @@ repeat: goto next; } - if (!page_cache_get_speculative(page)) + head = compound_head(page); + if (!page_cache_get_speculative(head)) goto repeat; + /* The page was split under us? */ + if (compound_head(page) != head) { + put_page(head); + goto repeat; + } + /* Has the page moved? */ if (unlikely(page != *slot)) { - page_cache_release(page); + put_page(head); goto repeat; } @@ -2178,26 +2247,30 @@ repeat: if (page->mapping != mapping || !PageUptodate(page)) goto unlock; - size = round_up(i_size_read(mapping->host), PAGE_CACHE_SIZE); - if (page->index >= size >> PAGE_CACHE_SHIFT) - goto unlock; - - pte = vmf->pte + page->index - vmf->pgoff; - if (!pte_none(*pte)) + size = round_up(i_size_read(mapping->host), PAGE_SIZE); + if (page->index >= size >> PAGE_SHIFT) goto unlock; if (file->f_ra.mmap_miss > 0) file->f_ra.mmap_miss--; - addr = address + (page->index - vmf->pgoff) * PAGE_SIZE; - do_set_pte(vma, addr, page, pte, false, false); + + fe->address += (iter.index - last_pgoff) << PAGE_SHIFT; + if (fe->pte) + fe->pte += iter.index - last_pgoff; + last_pgoff = iter.index; + if (alloc_set_pte(fe, NULL, page)) + goto unlock; unlock_page(page); goto next; unlock: unlock_page(page); skip: - page_cache_release(page); + put_page(page); next: - if (iter.index == vmf->max_pgoff) + /* Huge page is mapped? No need to proceed. */ + if (pmd_trans_huge(*fe->pmd)) + break; + if (iter.index == end_pgoff) break; } rcu_read_unlock(); @@ -2278,7 +2351,7 @@ static struct page *wait_on_page_read(struct page *page) if (!IS_ERR(page)) { wait_on_page_locked(page); if (!PageUptodate(page)) { - page_cache_release(page); + put_page(page); page = ERR_PTR(-EIO); } } @@ -2301,7 +2374,7 @@ repeat: return ERR_PTR(-ENOMEM); err = add_to_page_cache_lru(page, mapping, index, gfp); if (unlikely(err)) { - page_cache_release(page); + put_page(page); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for radix tree node */ @@ -2311,7 +2384,7 @@ repeat: filler: err = filler(data, page); if (err < 0) { - page_cache_release(page); + put_page(page); return ERR_PTR(err); } @@ -2364,7 +2437,7 @@ filler: /* Case c or d, restart the operation */ if (!page->mapping) { unlock_page(page); - page_cache_release(page); + put_page(page); goto repeat; } @@ -2500,18 +2573,19 @@ int pagecache_write_end(struct file *file, struct address_space *mapping, EXPORT_SYMBOL(pagecache_write_end); ssize_t -generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos) +generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; + loff_t pos = iocb->ki_pos; ssize_t written; size_t write_len; pgoff_t end; struct iov_iter data; write_len = iov_iter_count(from); - end = (pos + write_len - 1) >> PAGE_CACHE_SHIFT; + end = (pos + write_len - 1) >> PAGE_SHIFT; written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1); if (written) @@ -2525,7 +2599,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos) */ if (mapping->nrpages) { written = invalidate_inode_pages2_range(mapping, - pos >> PAGE_CACHE_SHIFT, end); + pos >> PAGE_SHIFT, end); /* * If a page can not be invalidated, return 0 to fall back * to buffered write. @@ -2538,7 +2612,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos) } data = *from; - written = mapping->a_ops->direct_IO(iocb, &data, pos); + written = mapping->a_ops->direct_IO(iocb, &data); /* * Finally, try again to invalidate clean pages which might have been @@ -2550,7 +2624,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos) */ if (mapping->nrpages) { invalidate_inode_pages2_range(mapping, - pos >> PAGE_CACHE_SHIFT, end); + pos >> PAGE_SHIFT, end); } if (written > 0) { @@ -2575,7 +2649,7 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags) { struct page *page; - int fgp_flags = FGP_LOCK|FGP_ACCESSED|FGP_WRITE|FGP_CREAT; + int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT; if (flags & AOP_FLAG_NOFS) fgp_flags |= FGP_NOFS; @@ -2611,8 +2685,8 @@ ssize_t generic_perform_write(struct file *file, size_t copied; /* Bytes copied from user */ void *fsdata; - offset = (pos & (PAGE_CACHE_SIZE - 1)); - bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset, + offset = (pos & (PAGE_SIZE - 1)); + bytes = min_t(unsigned long, PAGE_SIZE - offset, iov_iter_count(i)); again: @@ -2665,7 +2739,7 @@ again: * because not all segments in the iov can be copied at * once without a pagefault. */ - bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset, + bytes = min_t(unsigned long, PAGE_SIZE - offset, iov_iter_single_seg_count(i)); goto again; } @@ -2718,7 +2792,7 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_flags & IOCB_DIRECT) { loff_t pos, endbyte; - written = generic_file_direct_write(iocb, from, iocb->ki_pos); + written = generic_file_direct_write(iocb, from); /* * If the write stopped short of completing, fall back to * buffered writes. Some filesystems do this for writes to @@ -2752,8 +2826,8 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) iocb->ki_pos = endbyte + 1; written += status; invalidate_mapping_pages(mapping, - pos >> PAGE_CACHE_SHIFT, - endbyte >> PAGE_CACHE_SHIFT); + pos >> PAGE_SHIFT, + endbyte >> PAGE_SHIFT); } else { /* * We don't know how much we wrote, so just return @@ -2792,13 +2866,8 @@ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) ret = __generic_file_write_iter(iocb, from); inode_unlock(inode); - if (ret > 0) { - ssize_t err; - - err = generic_write_sync(file, iocb->ki_pos - ret, ret); - if (err < 0) - ret = err; - } + if (ret > 0) + ret = generic_write_sync(iocb, ret); return ret; } EXPORT_SYMBOL(generic_file_write_iter); diff --git a/mm/frontswap.c b/mm/frontswap.c index 27a9924caf61..fec8b5044040 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -20,6 +20,8 @@ #include <linux/frontswap.h> #include <linux/swapfile.h> +DEFINE_STATIC_KEY_FALSE(frontswap_enabled_key); + /* * frontswap_ops are added by frontswap_register_ops, and provide the * frontswap "backend" implementation functions. Multiple implementations @@ -139,6 +141,8 @@ void frontswap_register_ops(struct frontswap_ops *ops) ops->next = frontswap_ops; } while (cmpxchg(&frontswap_ops, ops->next, ops) != ops->next); + static_branch_inc(&frontswap_enabled_key); + spin_lock(&swap_lock); plist_for_each_entry(si, &swap_active_head, list) { if (si->frontswap_map) @@ -189,7 +193,7 @@ void __frontswap_init(unsigned type, unsigned long *map) struct swap_info_struct *sis = swap_info[type]; struct frontswap_ops *ops; - BUG_ON(sis == NULL); + VM_BUG_ON(sis == NULL); /* * p->frontswap is a bitmap that we MUST have to figure out which page @@ -248,15 +252,9 @@ int __frontswap_store(struct page *page) pgoff_t offset = swp_offset(entry); struct frontswap_ops *ops; - /* - * Return if no backend registed. - * Don't need to inc frontswap_failed_stores here. - */ - if (!frontswap_ops) - return -1; - - BUG_ON(!PageLocked(page)); - BUG_ON(sis == NULL); + VM_BUG_ON(!frontswap_ops); + VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON(sis == NULL); /* * If a dup, we must remove the old page first; we can't leave the @@ -303,11 +301,10 @@ int __frontswap_load(struct page *page) pgoff_t offset = swp_offset(entry); struct frontswap_ops *ops; - if (!frontswap_ops) - return -1; + VM_BUG_ON(!frontswap_ops); + VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON(sis == NULL); - BUG_ON(!PageLocked(page)); - BUG_ON(sis == NULL); if (!__frontswap_test(sis, offset)) return -1; @@ -337,10 +334,9 @@ void __frontswap_invalidate_page(unsigned type, pgoff_t offset) struct swap_info_struct *sis = swap_info[type]; struct frontswap_ops *ops; - if (!frontswap_ops) - return; + VM_BUG_ON(!frontswap_ops); + VM_BUG_ON(sis == NULL); - BUG_ON(sis == NULL); if (!__frontswap_test(sis, offset)) return; @@ -360,10 +356,9 @@ void __frontswap_invalidate_area(unsigned type) struct swap_info_struct *sis = swap_info[type]; struct frontswap_ops *ops; - if (!frontswap_ops) - return; + VM_BUG_ON(!frontswap_ops); + VM_BUG_ON(sis == NULL); - BUG_ON(sis == NULL); if (sis->frontswap_map == NULL) return; @@ -1,4 +1,3 @@ -#define __DISABLE_GUP_DEPRECATED 1 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/err.h> @@ -280,6 +279,8 @@ struct page *follow_page_mask(struct vm_area_struct *vma, spin_unlock(ptl); ret = 0; split_huge_pmd(vma, pmd, address); + if (pmd_trans_unstable(pmd)) + ret = -EBUSY; } else { get_page(page); spin_unlock(ptl); @@ -287,6 +288,8 @@ struct page *follow_page_mask(struct vm_area_struct *vma, ret = split_huge_page(page); unlock_page(page); put_page(page); + if (pmd_none(*pmd)) + return no_page_table(vma, flags); } return ret ? ERR_PTR(ret) : @@ -351,7 +354,6 @@ unmap: static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, unsigned long address, unsigned int *flags, int *nonblocking) { - struct mm_struct *mm = vma->vm_mm; unsigned int fault_flags = 0; int ret; @@ -376,7 +378,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, fault_flags |= FAULT_FLAG_TRIED; } - ret = handle_mm_fault(mm, vma, address, fault_flags); + ret = handle_mm_fault(vma, address, fault_flags); if (ret & VM_FAULT_ERROR) { if (ret & VM_FAULT_OOM) return -ENOMEM; @@ -691,7 +693,7 @@ retry: if (!vma_permits_fault(vma, fault_flags)) return -EFAULT; - ret = handle_mm_fault(mm, vma, address, fault_flags); + ret = handle_mm_fault(vma, address, fault_flags); major |= ret & VM_FAULT_MAJOR; if (ret & VM_FAULT_ERROR) { if (ret & VM_FAULT_OOM) @@ -721,6 +723,7 @@ retry: } return 0; } +EXPORT_SYMBOL_GPL(fixup_user_fault); static __always_inline long __get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, @@ -839,7 +842,7 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk, * if (locked) * up_read(&mm->mmap_sem); */ -long get_user_pages_locked6(unsigned long start, unsigned long nr_pages, +long get_user_pages_locked(unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, int *locked) { @@ -847,7 +850,7 @@ long get_user_pages_locked6(unsigned long start, unsigned long nr_pages, write, force, pages, NULL, locked, true, FOLL_TOUCH); } -EXPORT_SYMBOL(get_user_pages_locked6); +EXPORT_SYMBOL(get_user_pages_locked); /* * Same as get_user_pages_unlocked(...., FOLL_TOUCH) but it allows to @@ -892,13 +895,13 @@ EXPORT_SYMBOL(__get_user_pages_unlocked); * or if "force" shall be set to 1 (get_user_pages_fast misses the * "force" parameter). */ -long get_user_pages_unlocked5(unsigned long start, unsigned long nr_pages, +long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages) { return __get_user_pages_unlocked(current, current->mm, start, nr_pages, write, force, pages, FOLL_TOUCH); } -EXPORT_SYMBOL(get_user_pages_unlocked5); +EXPORT_SYMBOL(get_user_pages_unlocked); /* * get_user_pages_remote() - pin user pages in memory @@ -972,7 +975,7 @@ EXPORT_SYMBOL(get_user_pages_remote); * and mm being operated on are the current task's. We also * obviously don't pass FOLL_REMOTE in here. */ -long get_user_pages6(unsigned long start, unsigned long nr_pages, +long get_user_pages(unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas) { @@ -980,7 +983,7 @@ long get_user_pages6(unsigned long start, unsigned long nr_pages, write, force, pages, vmas, NULL, false, FOLL_TOUCH); } -EXPORT_SYMBOL(get_user_pages6); +EXPORT_SYMBOL(get_user_pages); /** * populate_vma_page_range() - populate a range of pages in the vma. @@ -1107,7 +1110,7 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) * @addr: user address * * Returns struct page pointer of user page pinned for dump, - * to be freed afterwards by page_cache_release() or put_page(). + * to be freed afterwards by put_page(). * * 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 @@ -1491,7 +1494,6 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { - struct mm_struct *mm = current->mm; int nr, ret; start &= PAGE_MASK; @@ -1503,8 +1505,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write, start += nr << PAGE_SHIFT; pages += nr; - ret = get_user_pages_unlocked(current, mm, start, - nr_pages - nr, write, 0, pages); + ret = get_user_pages_unlocked(start, nr_pages - nr, write, 0, pages); /* Have to be a bit careful with return values */ if (nr > 0) { @@ -1519,38 +1520,3 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write, } #endif /* CONFIG_HAVE_GENERIC_RCU_GUP */ - -long get_user_pages8(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages, - struct vm_area_struct **vmas) -{ - WARN_ONCE(tsk != current, "get_user_pages() called on remote task"); - WARN_ONCE(mm != current->mm, "get_user_pages() called on remote mm"); - - return get_user_pages6(start, nr_pages, write, force, pages, vmas); -} -EXPORT_SYMBOL(get_user_pages8); - -long get_user_pages_locked8(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages, int *locked) -{ - WARN_ONCE(tsk != current, "get_user_pages_locked() called on remote task"); - WARN_ONCE(mm != current->mm, "get_user_pages_locked() called on remote mm"); - - return get_user_pages_locked6(start, nr_pages, write, force, pages, locked); -} -EXPORT_SYMBOL(get_user_pages_locked8); - -long get_user_pages_unlocked7(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages) -{ - WARN_ONCE(tsk != current, "get_user_pages_unlocked() called on remote task"); - WARN_ONCE(mm != current->mm, "get_user_pages_unlocked() called on remote mm"); - - return get_user_pages_unlocked5(start, nr_pages, write, force, pages); -} -EXPORT_SYMBOL(get_user_pages_unlocked7); - diff --git a/mm/highmem.c b/mm/highmem.c index 123bcd3ed4f2..50b4ca6787f0 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -112,16 +112,12 @@ EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx); unsigned int nr_free_highpages (void) { - pg_data_t *pgdat; + struct zone *zone; unsigned int pages = 0; - for_each_online_pgdat(pgdat) { - pages += zone_page_state(&pgdat->node_zones[ZONE_HIGHMEM], - NR_FREE_PAGES); - if (zone_movable_is_highmem()) - pages += zone_page_state( - &pgdat->node_zones[ZONE_MOVABLE], - NR_FREE_PAGES); + for_each_populated_zone(zone) { + if (is_highmem(zone)) + pages += zone_page_state(zone, NR_FREE_PAGES); } return pages; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 86f9f8b82f8e..2373f0a7d340 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -18,7 +18,6 @@ #include <linux/mm_inline.h> #include <linux/swapops.h> #include <linux/dax.h> -#include <linux/kthread.h> #include <linux/khugepaged.h> #include <linux/freezer.h> #include <linux/pfn_t.h> @@ -30,39 +29,12 @@ #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> +#include <linux/shmem_fs.h> #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" -enum scan_result { - SCAN_FAIL, - SCAN_SUCCEED, - SCAN_PMD_NULL, - SCAN_EXCEED_NONE_PTE, - SCAN_PTE_NON_PRESENT, - SCAN_PAGE_RO, - SCAN_NO_REFERENCED_PAGE, - SCAN_PAGE_NULL, - SCAN_SCAN_ABORT, - SCAN_PAGE_COUNT, - SCAN_PAGE_LRU, - SCAN_PAGE_LOCK, - SCAN_PAGE_ANON, - SCAN_PAGE_COMPOUND, - SCAN_ANY_PROCESS, - SCAN_VMA_NULL, - SCAN_VMA_CHECK, - SCAN_ADDRESS_RANGE, - SCAN_SWAP_CACHE_PAGE, - SCAN_DEL_PAGE_LRU, - SCAN_ALLOC_HUGE_PAGE_FAIL, - SCAN_CGROUP_CHARGE_FAIL -}; - -#define CREATE_TRACE_POINTS -#include <trace/events/huge_memory.h> - /* * By default transparent hugepage support is disabled in order that avoid * to risk increase the memory footprint of applications without a guaranteed @@ -82,126 +54,8 @@ unsigned long transparent_hugepage_flags __read_mostly = (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)| (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); -/* default scan 8*512 pte (or vmas) every 30 second */ -static unsigned int khugepaged_pages_to_scan __read_mostly; -static unsigned int khugepaged_pages_collapsed; -static unsigned int khugepaged_full_scans; -static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000; -/* during fragmentation poll the hugepage allocator once every minute */ -static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000; -static struct task_struct *khugepaged_thread __read_mostly; -static DEFINE_MUTEX(khugepaged_mutex); -static DEFINE_SPINLOCK(khugepaged_mm_lock); -static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); -/* - * default collapse hugepages if there is at least one pte mapped like - * it would have happened if the vma was large enough during page - * fault. - */ -static unsigned int khugepaged_max_ptes_none __read_mostly; - -static int khugepaged(void *none); -static int khugepaged_slab_init(void); -static void khugepaged_slab_exit(void); - -#define MM_SLOTS_HASH_BITS 10 -static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); - -static struct kmem_cache *mm_slot_cache __read_mostly; - -/** - * struct mm_slot - hash lookup from mm to mm_slot - * @hash: hash collision list - * @mm_node: khugepaged scan list headed in khugepaged_scan.mm_head - * @mm: the mm that this information is valid for - */ -struct mm_slot { - struct hlist_node hash; - struct list_head mm_node; - struct mm_struct *mm; -}; - -/** - * struct khugepaged_scan - cursor for scanning - * @mm_head: the head of the mm list to scan - * @mm_slot: the current mm_slot we are scanning - * @address: the next address inside that to be scanned - * - * There is only the one khugepaged_scan instance of this cursor structure. - */ -struct khugepaged_scan { - struct list_head mm_head; - struct mm_slot *mm_slot; - unsigned long address; -}; -static struct khugepaged_scan khugepaged_scan = { - .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), -}; - static struct shrinker deferred_split_shrinker; -static void set_recommended_min_free_kbytes(void) -{ - struct zone *zone; - int nr_zones = 0; - unsigned long recommended_min; - - for_each_populated_zone(zone) - nr_zones++; - - /* Ensure 2 pageblocks are free to assist fragmentation avoidance */ - recommended_min = pageblock_nr_pages * nr_zones * 2; - - /* - * Make sure that on average at least two pageblocks are almost free - * of another type, one for a migratetype to fall back to and a - * second to avoid subsequent fallbacks of other types There are 3 - * MIGRATE_TYPES we care about. - */ - recommended_min += pageblock_nr_pages * nr_zones * - MIGRATE_PCPTYPES * MIGRATE_PCPTYPES; - - /* don't ever allow to reserve more than 5% of the lowmem */ - recommended_min = min(recommended_min, - (unsigned long) nr_free_buffer_pages() / 20); - recommended_min <<= (PAGE_SHIFT-10); - - if (recommended_min > min_free_kbytes) { - if (user_min_free_kbytes >= 0) - pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n", - min_free_kbytes, recommended_min); - - min_free_kbytes = recommended_min; - } - setup_per_zone_wmarks(); -} - -static int start_stop_khugepaged(void) -{ - int err = 0; - if (khugepaged_enabled()) { - if (!khugepaged_thread) - khugepaged_thread = kthread_run(khugepaged, NULL, - "khugepaged"); - if (IS_ERR(khugepaged_thread)) { - pr_err("khugepaged: kthread_run(khugepaged) failed\n"); - err = PTR_ERR(khugepaged_thread); - khugepaged_thread = NULL; - goto fail; - } - - if (!list_empty(&khugepaged_scan.mm_head)) - wake_up_interruptible(&khugepaged_wait); - - set_recommended_min_free_kbytes(); - } else if (khugepaged_thread) { - kthread_stop(khugepaged_thread); - khugepaged_thread = NULL; - } -fail: - return err; -} - static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; @@ -232,7 +86,7 @@ retry: return READ_ONCE(huge_zero_page); } -static void put_huge_zero_page(void) +void put_huge_zero_page(void) { /* * Counter should never go to zero here. Only shrinker can put @@ -327,12 +181,7 @@ static ssize_t enabled_store(struct kobject *kobj, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG); if (ret > 0) { - int err; - - mutex_lock(&khugepaged_mutex); - err = start_stop_khugepaged(); - mutex_unlock(&khugepaged_mutex); - + int err = start_stop_khugepaged(); if (err) ret = err; } @@ -342,7 +191,7 @@ static ssize_t enabled_store(struct kobject *kobj, static struct kobj_attribute enabled_attr = __ATTR(enabled, 0644, enabled_show, enabled_store); -static ssize_t single_flag_show(struct kobject *kobj, +ssize_t single_hugepage_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, enum transparent_hugepage_flag flag) { @@ -350,7 +199,7 @@ static ssize_t single_flag_show(struct kobject *kobj, !!test_bit(flag, &transparent_hugepage_flags)); } -static ssize_t single_flag_store(struct kobject *kobj, +ssize_t single_hugepage_flag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count, enum transparent_hugepage_flag flag) @@ -405,13 +254,13 @@ static struct kobj_attribute defrag_attr = static ssize_t use_zero_page_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return single_flag_show(kobj, attr, buf, + return single_hugepage_flag_show(kobj, attr, buf, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); } static ssize_t use_zero_page_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - return single_flag_store(kobj, attr, buf, count, + return single_hugepage_flag_store(kobj, attr, buf, count, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); } static struct kobj_attribute use_zero_page_attr = @@ -420,14 +269,14 @@ static struct kobj_attribute use_zero_page_attr = static ssize_t debug_cow_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return single_flag_show(kobj, attr, buf, + return single_hugepage_flag_show(kobj, attr, buf, TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG); } static ssize_t debug_cow_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - return single_flag_store(kobj, attr, buf, count, + return single_hugepage_flag_store(kobj, attr, buf, count, TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG); } static struct kobj_attribute debug_cow_attr = @@ -438,6 +287,9 @@ static struct attribute *hugepage_attr[] = { &enabled_attr.attr, &defrag_attr.attr, &use_zero_page_attr.attr, +#if defined(CONFIG_SHMEM) && defined(CONFIG_TRANSPARENT_HUGE_PAGECACHE) + &shmem_enabled_attr.attr, +#endif #ifdef CONFIG_DEBUG_VM &debug_cow_attr.attr, #endif @@ -448,169 +300,6 @@ static struct attribute_group hugepage_attr_group = { .attrs = hugepage_attr, }; -static ssize_t scan_sleep_millisecs_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", khugepaged_scan_sleep_millisecs); -} - -static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - unsigned long msecs; - int err; - - err = kstrtoul(buf, 10, &msecs); - if (err || msecs > UINT_MAX) - return -EINVAL; - - khugepaged_scan_sleep_millisecs = msecs; - wake_up_interruptible(&khugepaged_wait); - - return count; -} -static struct kobj_attribute scan_sleep_millisecs_attr = - __ATTR(scan_sleep_millisecs, 0644, scan_sleep_millisecs_show, - scan_sleep_millisecs_store); - -static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", khugepaged_alloc_sleep_millisecs); -} - -static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - unsigned long msecs; - int err; - - err = kstrtoul(buf, 10, &msecs); - if (err || msecs > UINT_MAX) - return -EINVAL; - - khugepaged_alloc_sleep_millisecs = msecs; - wake_up_interruptible(&khugepaged_wait); - - return count; -} -static struct kobj_attribute alloc_sleep_millisecs_attr = - __ATTR(alloc_sleep_millisecs, 0644, alloc_sleep_millisecs_show, - alloc_sleep_millisecs_store); - -static ssize_t pages_to_scan_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", khugepaged_pages_to_scan); -} -static ssize_t pages_to_scan_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - int err; - unsigned long pages; - - err = kstrtoul(buf, 10, &pages); - if (err || !pages || pages > UINT_MAX) - return -EINVAL; - - khugepaged_pages_to_scan = pages; - - return count; -} -static struct kobj_attribute pages_to_scan_attr = - __ATTR(pages_to_scan, 0644, pages_to_scan_show, - pages_to_scan_store); - -static ssize_t pages_collapsed_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", khugepaged_pages_collapsed); -} -static struct kobj_attribute pages_collapsed_attr = - __ATTR_RO(pages_collapsed); - -static ssize_t full_scans_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", khugepaged_full_scans); -} -static struct kobj_attribute full_scans_attr = - __ATTR_RO(full_scans); - -static ssize_t khugepaged_defrag_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - return single_flag_show(kobj, attr, buf, - TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); -} -static ssize_t khugepaged_defrag_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - return single_flag_store(kobj, attr, buf, count, - TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); -} -static struct kobj_attribute khugepaged_defrag_attr = - __ATTR(defrag, 0644, khugepaged_defrag_show, - khugepaged_defrag_store); - -/* - * max_ptes_none controls if khugepaged should collapse hugepages over - * any unmapped ptes in turn potentially increasing the memory - * footprint of the vmas. When max_ptes_none is 0 khugepaged will not - * reduce the available free memory in the system as it - * runs. Increasing max_ptes_none will instead potentially reduce the - * free memory in the system during the khugepaged scan. - */ -static ssize_t khugepaged_max_ptes_none_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", khugepaged_max_ptes_none); -} -static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - int err; - unsigned long max_ptes_none; - - err = kstrtoul(buf, 10, &max_ptes_none); - if (err || max_ptes_none > HPAGE_PMD_NR-1) - return -EINVAL; - - khugepaged_max_ptes_none = max_ptes_none; - - return count; -} -static struct kobj_attribute khugepaged_max_ptes_none_attr = - __ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show, - khugepaged_max_ptes_none_store); - -static struct attribute *khugepaged_attr[] = { - &khugepaged_defrag_attr.attr, - &khugepaged_max_ptes_none_attr.attr, - &pages_to_scan_attr.attr, - &pages_collapsed_attr.attr, - &full_scans_attr.attr, - &scan_sleep_millisecs_attr.attr, - &alloc_sleep_millisecs_attr.attr, - NULL, -}; - -static struct attribute_group khugepaged_attr_group = { - .attrs = khugepaged_attr, - .name = "khugepaged", -}; - static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj) { int err; @@ -669,8 +358,6 @@ static int __init hugepage_init(void) return -EINVAL; } - khugepaged_pages_to_scan = HPAGE_PMD_NR * 8; - khugepaged_max_ptes_none = HPAGE_PMD_NR - 1; /* * hugepages can't be allocated by the buddy allocator */ @@ -685,7 +372,7 @@ static int __init hugepage_init(void) if (err) goto err_sysfs; - err = khugepaged_slab_init(); + err = khugepaged_init(); if (err) goto err_slab; @@ -716,7 +403,7 @@ err_khugepaged: err_split_shrinker: unregister_shrinker(&huge_zero_page_shrinker); err_hzp_shrinker: - khugepaged_slab_exit(); + khugepaged_destroy(); err_slab: hugepage_exit_sysfs(hugepage_kobj); err_sysfs: @@ -762,14 +449,6 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) return pmd; } -static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot) -{ - pmd_t entry; - entry = mk_pmd(page, prot); - entry = pmd_mkhuge(entry); - return entry; -} - static inline struct list_head *page_deferred_list(struct page *page) { /* @@ -790,26 +469,23 @@ void prep_transhuge_page(struct page *page) set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR); } -static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, - struct page *page, gfp_t gfp, - unsigned int flags) +static int __do_huge_pmd_anonymous_page(struct fault_env *fe, struct page *page, + gfp_t gfp) { + struct vm_area_struct *vma = fe->vma; struct mem_cgroup *memcg; pgtable_t pgtable; - spinlock_t *ptl; - unsigned long haddr = address & HPAGE_PMD_MASK; + unsigned long haddr = fe->address & HPAGE_PMD_MASK; VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_try_charge(page, mm, gfp, &memcg, true)) { + if (mem_cgroup_try_charge(page, vma->vm_mm, gfp, &memcg, true)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; } - pgtable = pte_alloc_one(mm, haddr); + pgtable = pte_alloc_one(vma->vm_mm, haddr); if (unlikely(!pgtable)) { mem_cgroup_cancel_charge(page, memcg, true); put_page(page); @@ -824,12 +500,12 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, */ __SetPageUptodate(page); - ptl = pmd_lock(mm, pmd); - if (unlikely(!pmd_none(*pmd))) { - spin_unlock(ptl); + fe->ptl = pmd_lock(vma->vm_mm, fe->pmd); + if (unlikely(!pmd_none(*fe->pmd))) { + spin_unlock(fe->ptl); mem_cgroup_cancel_charge(page, memcg, true); put_page(page); - pte_free(mm, pgtable); + pte_free(vma->vm_mm, pgtable); } else { pmd_t entry; @@ -837,12 +513,11 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, if (userfaultfd_missing(vma)) { int ret; - spin_unlock(ptl); + spin_unlock(fe->ptl); mem_cgroup_cancel_charge(page, memcg, true); put_page(page); - pte_free(mm, pgtable); - ret = handle_userfault(vma, address, flags, - VM_UFFD_MISSING); + pte_free(vma->vm_mm, pgtable); + ret = handle_userfault(fe, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); return ret; } @@ -852,11 +527,11 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, page_add_new_anon_rmap(page, vma, haddr, true); mem_cgroup_commit_charge(page, memcg, false, true); lru_cache_add_active_or_unevictable(page, vma); - pgtable_trans_huge_deposit(mm, pmd, pgtable); - set_pmd_at(mm, haddr, pmd, entry); - add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR); - atomic_long_inc(&mm->nr_ptes); - spin_unlock(ptl); + pgtable_trans_huge_deposit(vma->vm_mm, fe->pmd, pgtable); + set_pmd_at(vma->vm_mm, haddr, fe->pmd, entry); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); + atomic_long_inc(&vma->vm_mm->nr_ptes); + spin_unlock(fe->ptl); count_vm_event(THP_FAULT_ALLOC); } @@ -864,29 +539,26 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, } /* - * If THP is set to always then directly reclaim/compact as necessary - * If set to defer then do no reclaim and defer to khugepaged + * If THP defrag is set to always then directly reclaim/compact as necessary + * If set to defer then do only background reclaim/compact and defer to khugepaged * If set to madvise and the VMA is flagged then directly reclaim/compact + * When direct reclaim/compact is allowed, don't retry except for flagged VMA's */ static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma) { - gfp_t reclaim_flags = 0; + bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); - if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags) && - (vma->vm_flags & VM_HUGEPAGE)) - reclaim_flags = __GFP_DIRECT_RECLAIM; - else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) - reclaim_flags = __GFP_KSWAPD_RECLAIM; - else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) - reclaim_flags = __GFP_DIRECT_RECLAIM; + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, + &transparent_hugepage_flags) && vma_madvised) + return GFP_TRANSHUGE; + else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, + &transparent_hugepage_flags)) + return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; + else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, + &transparent_hugepage_flags)) + return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); - return GFP_TRANSHUGE | reclaim_flags; -} - -/* Defrag for khugepaged will enter direct reclaim/compaction if necessary */ -static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void) -{ - return GFP_TRANSHUGE | (khugepaged_defrag() ? __GFP_DIRECT_RECLAIM : 0); + return GFP_TRANSHUGE_LIGHT; } /* Caller must hold page table lock. */ @@ -906,13 +578,12 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, return true; } -int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, - unsigned int flags) +int do_huge_pmd_anonymous_page(struct fault_env *fe) { + struct vm_area_struct *vma = fe->vma; gfp_t gfp; struct page *page; - unsigned long haddr = address & HPAGE_PMD_MASK; + unsigned long haddr = fe->address & HPAGE_PMD_MASK; if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) return VM_FAULT_FALLBACK; @@ -920,42 +591,40 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, return VM_FAULT_OOM; if (unlikely(khugepaged_enter(vma, vma->vm_flags))) return VM_FAULT_OOM; - if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm) && + if (!(fe->flags & FAULT_FLAG_WRITE) && + !mm_forbids_zeropage(vma->vm_mm) && transparent_hugepage_use_zero_page()) { - spinlock_t *ptl; pgtable_t pgtable; struct page *zero_page; bool set; int ret; - pgtable = pte_alloc_one(mm, haddr); + pgtable = pte_alloc_one(vma->vm_mm, haddr); if (unlikely(!pgtable)) return VM_FAULT_OOM; zero_page = get_huge_zero_page(); if (unlikely(!zero_page)) { - pte_free(mm, pgtable); + pte_free(vma->vm_mm, pgtable); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; } - ptl = pmd_lock(mm, pmd); + fe->ptl = pmd_lock(vma->vm_mm, fe->pmd); ret = 0; set = false; - if (pmd_none(*pmd)) { + if (pmd_none(*fe->pmd)) { if (userfaultfd_missing(vma)) { - spin_unlock(ptl); - ret = handle_userfault(vma, address, flags, - VM_UFFD_MISSING); + spin_unlock(fe->ptl); + ret = handle_userfault(fe, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); } else { - set_huge_zero_page(pgtable, mm, vma, - haddr, pmd, - zero_page); - spin_unlock(ptl); + set_huge_zero_page(pgtable, vma->vm_mm, vma, + haddr, fe->pmd, zero_page); + spin_unlock(fe->ptl); set = true; } } else - spin_unlock(ptl); + spin_unlock(fe->ptl); if (!set) { - pte_free(mm, pgtable); + pte_free(vma->vm_mm, pgtable); put_huge_zero_page(); } return ret; @@ -967,8 +636,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, return VM_FAULT_FALLBACK; } prep_transhuge_page(page); - return __do_huge_pmd_anonymous_page(mm, vma, address, pmd, page, gfp, - flags); + return __do_huge_pmd_anonymous_page(fe, page, gfp); } static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, @@ -1013,6 +681,7 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write); return VM_FAULT_NOPAGE; } +EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd); static void touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd) @@ -1079,14 +748,15 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, struct page *src_page; pmd_t pmd; pgtable_t pgtable = NULL; - int ret; + int ret = -ENOMEM; - if (!vma_is_dax(vma)) { - ret = -ENOMEM; - pgtable = pte_alloc_one(dst_mm, addr); - if (unlikely(!pgtable)) - goto out; - } + /* Skip if can be re-fill on fault */ + if (!vma_is_anonymous(vma)) + return 0; + + pgtable = pte_alloc_one(dst_mm, addr); + if (unlikely(!pgtable)) + goto out; dst_ptl = pmd_lock(dst_mm, dst_pmd); src_ptl = pmd_lockptr(src_mm, src_pmd); @@ -1094,7 +764,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, ret = -EAGAIN; pmd = *src_pmd; - if (unlikely(!pmd_trans_huge(pmd) && !pmd_devmap(pmd))) { + if (unlikely(!pmd_trans_huge(pmd))) { pte_free(dst_mm, pgtable); goto out_unlock; } @@ -1117,16 +787,13 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, goto out_unlock; } - if (!vma_is_dax(vma)) { - /* thp accounting separate from pmd_devmap accounting */ - src_page = pmd_page(pmd); - VM_BUG_ON_PAGE(!PageHead(src_page), src_page); - get_page(src_page); - page_dup_rmap(src_page, true); - add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); - atomic_long_inc(&dst_mm->nr_ptes); - pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); - } + src_page = pmd_page(pmd); + VM_BUG_ON_PAGE(!PageHead(src_page), src_page); + get_page(src_page); + page_dup_rmap(src_page, true); + add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); + atomic_long_inc(&dst_mm->nr_ptes); + pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); pmdp_set_wrprotect(src_mm, addr, src_pmd); pmd = pmd_mkold(pmd_wrprotect(pmd)); @@ -1140,38 +807,31 @@ out: return ret; } -void huge_pmd_set_accessed(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long address, - pmd_t *pmd, pmd_t orig_pmd, - int dirty) +void huge_pmd_set_accessed(struct fault_env *fe, pmd_t orig_pmd) { - spinlock_t *ptl; pmd_t entry; unsigned long haddr; - ptl = pmd_lock(mm, pmd); - if (unlikely(!pmd_same(*pmd, orig_pmd))) + fe->ptl = pmd_lock(fe->vma->vm_mm, fe->pmd); + if (unlikely(!pmd_same(*fe->pmd, orig_pmd))) goto unlock; entry = pmd_mkyoung(orig_pmd); - haddr = address & HPAGE_PMD_MASK; - if (pmdp_set_access_flags(vma, haddr, pmd, entry, dirty)) - update_mmu_cache_pmd(vma, address, pmd); + haddr = fe->address & HPAGE_PMD_MASK; + if (pmdp_set_access_flags(fe->vma, haddr, fe->pmd, entry, + fe->flags & FAULT_FLAG_WRITE)) + update_mmu_cache_pmd(fe->vma, fe->address, fe->pmd); unlock: - spin_unlock(ptl); + spin_unlock(fe->ptl); } -static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long address, - pmd_t *pmd, pmd_t orig_pmd, - struct page *page, - unsigned long haddr) +static int do_huge_pmd_wp_page_fallback(struct fault_env *fe, pmd_t orig_pmd, + struct page *page) { + struct vm_area_struct *vma = fe->vma; + unsigned long haddr = fe->address & HPAGE_PMD_MASK; struct mem_cgroup *memcg; - spinlock_t *ptl; pgtable_t pgtable; pmd_t _pmd; int ret = 0, i; @@ -1188,11 +848,11 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, for (i = 0; i < HPAGE_PMD_NR; i++) { pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE | - __GFP_OTHER_NODE, - vma, address, page_to_nid(page)); + __GFP_OTHER_NODE, vma, + fe->address, page_to_nid(page)); if (unlikely(!pages[i] || - mem_cgroup_try_charge(pages[i], mm, GFP_KERNEL, - &memcg, false))) { + mem_cgroup_try_charge(pages[i], vma->vm_mm, + GFP_KERNEL, &memcg, false))) { if (pages[i]) put_page(pages[i]); while (--i >= 0) { @@ -1218,41 +878,41 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, mmun_start = haddr; mmun_end = haddr + HPAGE_PMD_SIZE; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); + mmu_notifier_invalidate_range_start(vma->vm_mm, mmun_start, mmun_end); - ptl = pmd_lock(mm, pmd); - if (unlikely(!pmd_same(*pmd, orig_pmd))) + fe->ptl = pmd_lock(vma->vm_mm, fe->pmd); + if (unlikely(!pmd_same(*fe->pmd, orig_pmd))) goto out_free_pages; VM_BUG_ON_PAGE(!PageHead(page), page); - pmdp_huge_clear_flush_notify(vma, haddr, pmd); + pmdp_huge_clear_flush_notify(vma, haddr, fe->pmd); /* leave pmd empty until pte is filled */ - pgtable = pgtable_trans_huge_withdraw(mm, pmd); - pmd_populate(mm, &_pmd, pgtable); + pgtable = pgtable_trans_huge_withdraw(vma->vm_mm, fe->pmd); + pmd_populate(vma->vm_mm, &_pmd, pgtable); for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { - pte_t *pte, entry; + pte_t entry; entry = mk_pte(pages[i], vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); memcg = (void *)page_private(pages[i]); set_page_private(pages[i], 0); - page_add_new_anon_rmap(pages[i], vma, haddr, false); + page_add_new_anon_rmap(pages[i], fe->vma, haddr, false); mem_cgroup_commit_charge(pages[i], memcg, false, false); lru_cache_add_active_or_unevictable(pages[i], vma); - pte = pte_offset_map(&_pmd, haddr); - VM_BUG_ON(!pte_none(*pte)); - set_pte_at(mm, haddr, pte, entry); - pte_unmap(pte); + fe->pte = pte_offset_map(&_pmd, haddr); + VM_BUG_ON(!pte_none(*fe->pte)); + set_pte_at(vma->vm_mm, haddr, fe->pte, entry); + pte_unmap(fe->pte); } kfree(pages); smp_wmb(); /* make pte visible before pmd */ - pmd_populate(mm, pmd, pgtable); + pmd_populate(vma->vm_mm, fe->pmd, pgtable); page_remove_rmap(page, true); - spin_unlock(ptl); + spin_unlock(fe->ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end); ret |= VM_FAULT_WRITE; put_page(page); @@ -1261,8 +921,8 @@ out: return ret; out_free_pages: - spin_unlock(ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + spin_unlock(fe->ptl); + mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end); for (i = 0; i < HPAGE_PMD_NR; i++) { memcg = (void *)page_private(pages[i]); set_page_private(pages[i], 0); @@ -1273,50 +933,42 @@ out_free_pages: goto out; } -int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, pmd_t orig_pmd) +int do_huge_pmd_wp_page(struct fault_env *fe, pmd_t orig_pmd) { - spinlock_t *ptl; - int ret = 0; + struct vm_area_struct *vma = fe->vma; struct page *page = NULL, *new_page; struct mem_cgroup *memcg; - unsigned long haddr; + unsigned long haddr = fe->address & HPAGE_PMD_MASK; unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ gfp_t huge_gfp; /* for allocation and charge */ + int ret = 0; - ptl = pmd_lockptr(mm, pmd); + fe->ptl = pmd_lockptr(vma->vm_mm, fe->pmd); VM_BUG_ON_VMA(!vma->anon_vma, vma); - haddr = address & HPAGE_PMD_MASK; if (is_huge_zero_pmd(orig_pmd)) goto alloc; - spin_lock(ptl); - if (unlikely(!pmd_same(*pmd, orig_pmd))) + spin_lock(fe->ptl); + if (unlikely(!pmd_same(*fe->pmd, orig_pmd))) goto out_unlock; page = pmd_page(orig_pmd); VM_BUG_ON_PAGE(!PageCompound(page) || !PageHead(page), page); /* * We can only reuse the page if nobody else maps the huge page or it's - * part. We can do it by checking page_mapcount() on each sub-page, but - * it's expensive. - * The cheaper way is to check page_count() to be equal 1: every - * mapcount takes page reference reference, so this way we can - * guarantee, that the PMD is the only mapping. - * This can give false negative if somebody pinned the page, but that's - * fine. + * part. */ - if (page_mapcount(page) == 1 && page_count(page) == 1) { + if (page_trans_huge_mapcount(page, NULL) == 1) { pmd_t entry; entry = pmd_mkyoung(orig_pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - if (pmdp_set_access_flags(vma, haddr, pmd, entry, 1)) - update_mmu_cache_pmd(vma, address, pmd); + if (pmdp_set_access_flags(vma, haddr, fe->pmd, entry, 1)) + update_mmu_cache_pmd(vma, fe->address, fe->pmd); ret |= VM_FAULT_WRITE; goto out_unlock; } get_page(page); - spin_unlock(ptl); + spin_unlock(fe->ptl); alloc: if (transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) { @@ -1329,13 +981,12 @@ alloc: prep_transhuge_page(new_page); } else { if (!page) { - split_huge_pmd(vma, pmd, address); + split_huge_pmd(vma, fe->pmd, fe->address); ret |= VM_FAULT_FALLBACK; } else { - ret = do_huge_pmd_wp_page_fallback(mm, vma, address, - pmd, orig_pmd, page, haddr); + ret = do_huge_pmd_wp_page_fallback(fe, orig_pmd, page); if (ret & VM_FAULT_OOM) { - split_huge_pmd(vma, pmd, address); + split_huge_pmd(vma, fe->pmd, fe->address); ret |= VM_FAULT_FALLBACK; } put_page(page); @@ -1344,14 +995,12 @@ alloc: goto out; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, huge_gfp, &memcg, - true))) { + if (unlikely(mem_cgroup_try_charge(new_page, vma->vm_mm, + huge_gfp, &memcg, true))) { put_page(new_page); - if (page) { - split_huge_pmd(vma, pmd, address); + split_huge_pmd(vma, fe->pmd, fe->address); + if (page) put_page(page); - } else - split_huge_pmd(vma, pmd, address); ret |= VM_FAULT_FALLBACK; count_vm_event(THP_FAULT_FALLBACK); goto out; @@ -1367,13 +1016,13 @@ alloc: mmun_start = haddr; mmun_end = haddr + HPAGE_PMD_SIZE; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); + mmu_notifier_invalidate_range_start(vma->vm_mm, mmun_start, mmun_end); - spin_lock(ptl); + spin_lock(fe->ptl); if (page) put_page(page); - if (unlikely(!pmd_same(*pmd, orig_pmd))) { - spin_unlock(ptl); + if (unlikely(!pmd_same(*fe->pmd, orig_pmd))) { + spin_unlock(fe->ptl); mem_cgroup_cancel_charge(new_page, memcg, true); put_page(new_page); goto out_mn; @@ -1381,14 +1030,14 @@ alloc: pmd_t entry; entry = mk_huge_pmd(new_page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - pmdp_huge_clear_flush_notify(vma, haddr, pmd); + pmdp_huge_clear_flush_notify(vma, haddr, fe->pmd); page_add_new_anon_rmap(new_page, vma, haddr, true); mem_cgroup_commit_charge(new_page, memcg, false, true); lru_cache_add_active_or_unevictable(new_page, vma); - set_pmd_at(mm, haddr, pmd, entry); - update_mmu_cache_pmd(vma, address, pmd); + set_pmd_at(vma->vm_mm, haddr, fe->pmd, entry); + update_mmu_cache_pmd(vma, fe->address, fe->pmd); if (!page) { - add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); put_huge_zero_page(); } else { VM_BUG_ON_PAGE(!PageHead(page), page); @@ -1397,13 +1046,13 @@ alloc: } ret |= VM_FAULT_WRITE; } - spin_unlock(ptl); + spin_unlock(fe->ptl); out_mn: - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end); out: return ret; out_unlock: - spin_unlock(ptl); + spin_unlock(fe->ptl); return ret; } @@ -1437,6 +1086,8 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, * We don't mlock() pte-mapped THPs. This way we can avoid * leaking mlocked pages into non-VM_LOCKED VMAs. * + * For anon THP: + * * In most cases the pmd is the only mapping of the page as we * break COW for the mlock() -- see gup_flags |= FOLL_WRITE for * writable private mappings in populate_vma_page_range(). @@ -1444,15 +1095,26 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, * The only scenario when we have the page shared here is if we * mlocking read-only mapping shared over fork(). We skip * mlocking such pages. + * + * For file THP: + * + * We can expect PageDoubleMap() to be stable under page lock: + * for file pages we set it in page_add_file_rmap(), which + * requires page to be locked. */ - if (compound_mapcount(page) == 1 && !PageDoubleMap(page) && - page->mapping && trylock_page(page)) { - lru_add_drain(); - if (page->mapping) - mlock_vma_page(page); - unlock_page(page); - } + + if (PageAnon(page) && compound_mapcount(page) != 1) + goto skip_mlock; + if (PageDoubleMap(page) || !page->mapping) + goto skip_mlock; + if (!trylock_page(page)) + goto skip_mlock; + lru_add_drain(); + if (page->mapping && !PageDoubleMap(page)) + mlock_vma_page(page); + unlock_page(page); } +skip_mlock: page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; VM_BUG_ON_PAGE(!PageCompound(page), page); if (flags & FOLL_GET) @@ -1463,13 +1125,12 @@ out: } /* NUMA hinting page fault entry point for trans huge pmds */ -int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pmd_t pmd, pmd_t *pmdp) +int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t pmd) { - spinlock_t *ptl; + struct vm_area_struct *vma = fe->vma; struct anon_vma *anon_vma = NULL; struct page *page; - unsigned long haddr = addr & HPAGE_PMD_MASK; + unsigned long haddr = fe->address & HPAGE_PMD_MASK; int page_nid = -1, this_nid = numa_node_id(); int target_nid, last_cpupid = -1; bool page_locked; @@ -1480,8 +1141,8 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* A PROT_NONE fault should not end up here */ BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))); - ptl = pmd_lock(mm, pmdp); - if (unlikely(!pmd_same(pmd, *pmdp))) + fe->ptl = pmd_lock(vma->vm_mm, fe->pmd); + if (unlikely(!pmd_same(pmd, *fe->pmd))) goto out_unlock; /* @@ -1489,9 +1150,9 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, * without disrupting NUMA hinting information. Do not relock and * check_same as the page may no longer be mapped. */ - if (unlikely(pmd_trans_migrating(*pmdp))) { - page = pmd_page(*pmdp); - spin_unlock(ptl); + if (unlikely(pmd_trans_migrating(*fe->pmd))) { + page = pmd_page(*fe->pmd); + spin_unlock(fe->ptl); wait_on_page_locked(page); goto out; } @@ -1524,7 +1185,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Migration could have started since the pmd_trans_migrating check */ if (!page_locked) { - spin_unlock(ptl); + spin_unlock(fe->ptl); wait_on_page_locked(page); page_nid = -1; goto out; @@ -1535,12 +1196,12 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, * to serialises splits */ get_page(page); - spin_unlock(ptl); + spin_unlock(fe->ptl); anon_vma = page_lock_anon_vma_read(page); /* Confirm the PMD did not change while page_table_lock was released */ - spin_lock(ptl); - if (unlikely(!pmd_same(pmd, *pmdp))) { + spin_lock(fe->ptl); + if (unlikely(!pmd_same(pmd, *fe->pmd))) { unlock_page(page); put_page(page); page_nid = -1; @@ -1558,9 +1219,9 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, * Migrate the THP to the requested node, returns with page unlocked * and access rights restored. */ - spin_unlock(ptl); - migrated = migrate_misplaced_transhuge_page(mm, vma, - pmdp, pmd, addr, page, target_nid); + spin_unlock(fe->ptl); + migrated = migrate_misplaced_transhuge_page(vma->vm_mm, vma, + fe->pmd, pmd, fe->address, page, target_nid); if (migrated) { flags |= TNF_MIGRATED; page_nid = target_nid; @@ -1575,41 +1236,42 @@ clear_pmdnuma: pmd = pmd_mkyoung(pmd); if (was_writable) pmd = pmd_mkwrite(pmd); - set_pmd_at(mm, haddr, pmdp, pmd); - update_mmu_cache_pmd(vma, addr, pmdp); + set_pmd_at(vma->vm_mm, haddr, fe->pmd, pmd); + update_mmu_cache_pmd(vma, fe->address, fe->pmd); unlock_page(page); out_unlock: - spin_unlock(ptl); + spin_unlock(fe->ptl); out: if (anon_vma) page_unlock_anon_vma_read(anon_vma); if (page_nid != -1) - task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, flags); + task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, fe->flags); return 0; } -int madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, +/* + * Return true if we do MADV_FREE successfully on entire pmd page. + * Otherwise, return false. + */ +bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long next) - { spinlock_t *ptl; pmd_t orig_pmd; struct page *page; struct mm_struct *mm = tlb->mm; - int ret = 0; + bool ret = false; ptl = pmd_trans_huge_lock(pmd, vma); if (!ptl) goto out_unlocked; orig_pmd = *pmd; - if (is_huge_zero_pmd(orig_pmd)) { - ret = 1; + if (is_huge_zero_pmd(orig_pmd)) goto out; - } page = pmd_page(orig_pmd); /* @@ -1629,14 +1291,9 @@ int madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (next - addr != HPAGE_PMD_SIZE) { get_page(page); spin_unlock(ptl); - if (split_huge_page(page)) { - put_page(page); - unlock_page(page); - goto out_unlocked; - } + split_huge_page(page); put_page(page); unlock_page(page); - ret = 1; goto out_unlocked; } @@ -1656,7 +1313,7 @@ int madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, set_pmd_at(mm, addr, pmd, orig_pmd); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); } - ret = 1; + ret = true; out: spin_unlock(ptl); out_unlocked: @@ -1684,40 +1341,43 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (vma_is_dax(vma)) { spin_unlock(ptl); if (is_huge_zero_pmd(orig_pmd)) - put_huge_zero_page(); + tlb_remove_page(tlb, pmd_page(orig_pmd)); } else if (is_huge_zero_pmd(orig_pmd)) { pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd)); atomic_long_dec(&tlb->mm->nr_ptes); spin_unlock(ptl); - put_huge_zero_page(); + tlb_remove_page(tlb, pmd_page(orig_pmd)); } else { struct page *page = pmd_page(orig_pmd); page_remove_rmap(page, true); VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); - add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); VM_BUG_ON_PAGE(!PageHead(page), page); - pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd)); - atomic_long_dec(&tlb->mm->nr_ptes); + if (PageAnon(page)) { + pgtable_t pgtable; + pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd); + pte_free(tlb->mm, pgtable); + atomic_long_dec(&tlb->mm->nr_ptes); + add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); + } else { + add_mm_counter(tlb->mm, MM_FILEPAGES, -HPAGE_PMD_NR); + } spin_unlock(ptl); - tlb_remove_page(tlb, page); + tlb_remove_page_size(tlb, page, HPAGE_PMD_SIZE); } return 1; } -bool move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, - unsigned long old_addr, +bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, unsigned long old_end, pmd_t *old_pmd, pmd_t *new_pmd) { spinlock_t *old_ptl, *new_ptl; pmd_t pmd; - struct mm_struct *mm = vma->vm_mm; if ((old_addr & ~HPAGE_PMD_MASK) || (new_addr & ~HPAGE_PMD_MASK) || - old_end - old_addr < HPAGE_PMD_SIZE || - (new_vma->vm_flags & VM_NOHUGEPAGE)) + old_end - old_addr < HPAGE_PMD_SIZE) return false; /* @@ -1792,7 +1452,8 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, entry = pmd_mkwrite(entry); ret = HPAGE_PMD_NR; set_pmd_at(mm, addr, pmd, entry); - BUG_ON(!preserve_write && pmd_write(entry)); + BUG_ON(vma_is_anonymous(vma) && !preserve_write && + pmd_write(entry)); } spin_unlock(ptl); } @@ -1801,10 +1462,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, } /* - * Returns true if a given pmd maps a thp, false otherwise. + * Returns page table lock pointer if a given pmd maps a thp, NULL otherwise. * - * Note that if it returns true, this routine returns without unlocking page - * table lock. So callers must unlock it. + * Note that if it returns page table lock pointer, this routine returns without + * unlocking page table lock. So callers must unlock it. */ spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { @@ -1816,1031 +1477,6 @@ spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) return NULL; } -#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE) - -int hugepage_madvise(struct vm_area_struct *vma, - unsigned long *vm_flags, int advice) -{ - switch (advice) { - case MADV_HUGEPAGE: -#ifdef CONFIG_S390 - /* - * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390 - * can't handle this properly after s390_enable_sie, so we simply - * ignore the madvise to prevent qemu from causing a SIGSEGV. - */ - if (mm_has_pgste(vma->vm_mm)) - return 0; -#endif - /* - * Be somewhat over-protective like KSM for now! - */ - if (*vm_flags & VM_NO_THP) - return -EINVAL; - *vm_flags &= ~VM_NOHUGEPAGE; - *vm_flags |= VM_HUGEPAGE; - /* - * If the vma become good for khugepaged to scan, - * register it here without waiting a page fault that - * may not happen any time soon. - */ - if (unlikely(khugepaged_enter_vma_merge(vma, *vm_flags))) - return -ENOMEM; - break; - case MADV_NOHUGEPAGE: - /* - * Be somewhat over-protective like KSM for now! - */ - if (*vm_flags & VM_NO_THP) - return -EINVAL; - *vm_flags &= ~VM_HUGEPAGE; - *vm_flags |= VM_NOHUGEPAGE; - /* - * Setting VM_NOHUGEPAGE will prevent khugepaged from scanning - * this vma even if we leave the mm registered in khugepaged if - * it got registered before VM_NOHUGEPAGE was set. - */ - break; - } - - return 0; -} - -static int __init khugepaged_slab_init(void) -{ - mm_slot_cache = kmem_cache_create("khugepaged_mm_slot", - sizeof(struct mm_slot), - __alignof__(struct mm_slot), 0, NULL); - if (!mm_slot_cache) - return -ENOMEM; - - return 0; -} - -static void __init khugepaged_slab_exit(void) -{ - kmem_cache_destroy(mm_slot_cache); -} - -static inline struct mm_slot *alloc_mm_slot(void) -{ - if (!mm_slot_cache) /* initialization failed */ - return NULL; - return kmem_cache_zalloc(mm_slot_cache, GFP_KERNEL); -} - -static inline void free_mm_slot(struct mm_slot *mm_slot) -{ - kmem_cache_free(mm_slot_cache, mm_slot); -} - -static struct mm_slot *get_mm_slot(struct mm_struct *mm) -{ - struct mm_slot *mm_slot; - - hash_for_each_possible(mm_slots_hash, mm_slot, hash, (unsigned long)mm) - if (mm == mm_slot->mm) - return mm_slot; - - return NULL; -} - -static void insert_to_mm_slots_hash(struct mm_struct *mm, - struct mm_slot *mm_slot) -{ - mm_slot->mm = mm; - hash_add(mm_slots_hash, &mm_slot->hash, (long)mm); -} - -static inline int khugepaged_test_exit(struct mm_struct *mm) -{ - return atomic_read(&mm->mm_users) == 0; -} - -int __khugepaged_enter(struct mm_struct *mm) -{ - struct mm_slot *mm_slot; - int wakeup; - - mm_slot = alloc_mm_slot(); - if (!mm_slot) - return -ENOMEM; - - /* __khugepaged_exit() must not run from under us */ - 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; - } - - spin_lock(&khugepaged_mm_lock); - insert_to_mm_slots_hash(mm, mm_slot); - /* - * Insert just behind the scanning cursor, to let the area settle - * down a little. - */ - wakeup = list_empty(&khugepaged_scan.mm_head); - list_add_tail(&mm_slot->mm_node, &khugepaged_scan.mm_head); - spin_unlock(&khugepaged_mm_lock); - - atomic_inc(&mm->mm_count); - if (wakeup) - wake_up_interruptible(&khugepaged_wait); - - return 0; -} - -int khugepaged_enter_vma_merge(struct vm_area_struct *vma, - unsigned long vm_flags) -{ - unsigned long hstart, hend; - if (!vma->anon_vma) - /* - * Not yet faulted in so we will register later in the - * page fault if needed. - */ - return 0; - if (vma->vm_ops) - /* khugepaged not yet working on file or special mappings */ - return 0; - VM_BUG_ON_VMA(vm_flags & VM_NO_THP, vma); - hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; - hend = vma->vm_end & HPAGE_PMD_MASK; - if (hstart < hend) - return khugepaged_enter(vma, vm_flags); - return 0; -} - -void __khugepaged_exit(struct mm_struct *mm) -{ - struct mm_slot *mm_slot; - int free = 0; - - spin_lock(&khugepaged_mm_lock); - mm_slot = get_mm_slot(mm); - if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { - hash_del(&mm_slot->hash); - list_del(&mm_slot->mm_node); - free = 1; - } - spin_unlock(&khugepaged_mm_lock); - - if (free) { - clear_bit(MMF_VM_HUGEPAGE, &mm->flags); - free_mm_slot(mm_slot); - mmdrop(mm); - } else if (mm_slot) { - /* - * This is required to serialize against - * khugepaged_test_exit() (which is guaranteed to run - * under mmap sem read mode). Stop here (after we - * return all pagetables will be destroyed) until - * khugepaged has finished working on the pagetables - * under the mmap_sem. - */ - down_write(&mm->mmap_sem); - up_write(&mm->mmap_sem); - } -} - -static void release_pte_page(struct page *page) -{ - /* 0 stands for page_is_file_cache(page) == false */ - dec_zone_page_state(page, NR_ISOLATED_ANON + 0); - unlock_page(page); - putback_lru_page(page); -} - -static void release_pte_pages(pte_t *pte, pte_t *_pte) -{ - while (--_pte >= pte) { - pte_t pteval = *_pte; - if (!pte_none(pteval) && !is_zero_pfn(pte_pfn(pteval))) - release_pte_page(pte_page(pteval)); - } -} - -static int __collapse_huge_page_isolate(struct vm_area_struct *vma, - unsigned long address, - pte_t *pte) -{ - struct page *page = NULL; - pte_t *_pte; - int none_or_zero = 0, result = 0; - bool referenced = false, writable = false; - - for (_pte = pte; _pte < pte+HPAGE_PMD_NR; - _pte++, address += PAGE_SIZE) { - pte_t pteval = *_pte; - if (pte_none(pteval) || (pte_present(pteval) && - is_zero_pfn(pte_pfn(pteval)))) { - if (!userfaultfd_armed(vma) && - ++none_or_zero <= khugepaged_max_ptes_none) { - continue; - } else { - result = SCAN_EXCEED_NONE_PTE; - goto out; - } - } - if (!pte_present(pteval)) { - result = SCAN_PTE_NON_PRESENT; - goto out; - } - page = vm_normal_page(vma, address, pteval); - if (unlikely(!page)) { - result = SCAN_PAGE_NULL; - goto out; - } - - VM_BUG_ON_PAGE(PageCompound(page), page); - VM_BUG_ON_PAGE(!PageAnon(page), page); - VM_BUG_ON_PAGE(!PageSwapBacked(page), page); - - /* - * We can do it before isolate_lru_page because the - * page can't be freed from under us. NOTE: PG_lock - * is needed to serialize against split_huge_page - * when invoked from the VM. - */ - if (!trylock_page(page)) { - result = SCAN_PAGE_LOCK; - goto out; - } - - /* - * cannot use mapcount: can't collapse if there's a gup pin. - * The page must only be referenced by the scanned process - * and page swap cache. - */ - if (page_count(page) != 1 + !!PageSwapCache(page)) { - unlock_page(page); - result = SCAN_PAGE_COUNT; - goto out; - } - if (pte_write(pteval)) { - writable = true; - } else { - if (PageSwapCache(page) && !reuse_swap_page(page)) { - unlock_page(page); - result = SCAN_SWAP_CACHE_PAGE; - goto out; - } - /* - * Page is not in the swap cache. It can be collapsed - * into a THP. - */ - } - - /* - * Isolate the page to avoid collapsing an hugepage - * currently in use by the VM. - */ - if (isolate_lru_page(page)) { - unlock_page(page); - result = SCAN_DEL_PAGE_LRU; - goto out; - } - /* 0 stands for page_is_file_cache(page) == false */ - inc_zone_page_state(page, NR_ISOLATED_ANON + 0); - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(PageLRU(page), page); - - /* If there is no mapped pte young don't collapse the page */ - if (pte_young(pteval) || - page_is_young(page) || PageReferenced(page) || - mmu_notifier_test_young(vma->vm_mm, address)) - referenced = 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 { - result = SCAN_PAGE_RO; - } - -out: - release_pte_pages(pte, _pte); - trace_mm_collapse_huge_page_isolate(page, none_or_zero, - referenced, writable, result); - return 0; -} - -static void __collapse_huge_page_copy(pte_t *pte, struct page *page, - struct vm_area_struct *vma, - unsigned long address, - spinlock_t *ptl) -{ - pte_t *_pte; - for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++) { - pte_t pteval = *_pte; - struct page *src_page; - - if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { - clear_user_highpage(page, address); - add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); - if (is_zero_pfn(pte_pfn(pteval))) { - /* - * ptl mostly unnecessary. - */ - spin_lock(ptl); - /* - * paravirt calls inside pte_clear here are - * superfluous. - */ - pte_clear(vma->vm_mm, address, _pte); - spin_unlock(ptl); - } - } else { - src_page = pte_page(pteval); - copy_user_highpage(page, src_page, address, vma); - VM_BUG_ON_PAGE(page_mapcount(src_page) != 1, src_page); - release_pte_page(src_page); - /* - * ptl mostly unnecessary, but preempt has to - * be disabled to update the per-cpu stats - * inside page_remove_rmap(). - */ - spin_lock(ptl); - /* - * paravirt calls inside pte_clear here are - * superfluous. - */ - pte_clear(vma->vm_mm, address, _pte); - page_remove_rmap(src_page, false); - spin_unlock(ptl); - free_page_and_swap_cache(src_page); - } - - address += PAGE_SIZE; - page++; - } -} - -static void khugepaged_alloc_sleep(void) -{ - DEFINE_WAIT(wait); - - add_wait_queue(&khugepaged_wait, &wait); - freezable_schedule_timeout_interruptible( - msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); - remove_wait_queue(&khugepaged_wait, &wait); -} - -static int khugepaged_node_load[MAX_NUMNODES]; - -static bool khugepaged_scan_abort(int nid) -{ - int i; - - /* - * If zone_reclaim_mode is disabled, then no extra effort is made to - * allocate memory locally. - */ - if (!zone_reclaim_mode) - return false; - - /* If there is a count for this node already, it must be acceptable */ - if (khugepaged_node_load[nid]) - return false; - - for (i = 0; i < MAX_NUMNODES; i++) { - if (!khugepaged_node_load[i]) - continue; - if (node_distance(nid, i) > RECLAIM_DISTANCE) - return true; - } - return false; -} - -#ifdef CONFIG_NUMA -static int khugepaged_find_target_node(void) -{ - static int last_khugepaged_target_node = NUMA_NO_NODE; - int nid, target_node = 0, max_value = 0; - - /* find first node with max normal pages hit */ - for (nid = 0; nid < MAX_NUMNODES; nid++) - if (khugepaged_node_load[nid] > max_value) { - max_value = khugepaged_node_load[nid]; - target_node = nid; - } - - /* do some balance if several nodes have the same hit record */ - if (target_node <= last_khugepaged_target_node) - for (nid = last_khugepaged_target_node + 1; nid < MAX_NUMNODES; - nid++) - if (max_value == khugepaged_node_load[nid]) { - target_node = nid; - break; - } - - last_khugepaged_target_node = target_node; - return target_node; -} - -static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) -{ - if (IS_ERR(*hpage)) { - if (!*wait) - return false; - - *wait = false; - *hpage = NULL; - khugepaged_alloc_sleep(); - } else if (*hpage) { - put_page(*hpage); - *hpage = NULL; - } - - return true; -} - -static struct page * -khugepaged_alloc_page(struct page **hpage, gfp_t gfp, struct mm_struct *mm, - unsigned long address, int node) -{ - VM_BUG_ON_PAGE(*hpage, *hpage); - - /* - * Before allocating the hugepage, release the mmap_sem read lock. - * The allocation can take potentially a long time if it involves - * sync compaction, and we do not need to hold the mmap_sem during - * that. We will recheck the vma after taking it again in write mode. - */ - up_read(&mm->mmap_sem); - - *hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER); - if (unlikely(!*hpage)) { - count_vm_event(THP_COLLAPSE_ALLOC_FAILED); - *hpage = ERR_PTR(-ENOMEM); - return NULL; - } - - prep_transhuge_page(*hpage); - count_vm_event(THP_COLLAPSE_ALLOC); - return *hpage; -} -#else -static int khugepaged_find_target_node(void) -{ - return 0; -} - -static inline struct page *alloc_khugepaged_hugepage(void) -{ - struct page *page; - - page = alloc_pages(alloc_hugepage_khugepaged_gfpmask(), - HPAGE_PMD_ORDER); - if (page) - prep_transhuge_page(page); - return page; -} - -static struct page *khugepaged_alloc_hugepage(bool *wait) -{ - struct page *hpage; - - do { - hpage = alloc_khugepaged_hugepage(); - if (!hpage) { - count_vm_event(THP_COLLAPSE_ALLOC_FAILED); - if (!*wait) - return NULL; - - *wait = false; - khugepaged_alloc_sleep(); - } else - count_vm_event(THP_COLLAPSE_ALLOC); - } while (unlikely(!hpage) && likely(khugepaged_enabled())); - - return hpage; -} - -static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) -{ - if (!*hpage) - *hpage = khugepaged_alloc_hugepage(wait); - - if (unlikely(!*hpage)) - return false; - - return true; -} - -static struct page * -khugepaged_alloc_page(struct page **hpage, gfp_t gfp, struct mm_struct *mm, - unsigned long address, int node) -{ - up_read(&mm->mmap_sem); - VM_BUG_ON(!*hpage); - - return *hpage; -} -#endif - -static bool hugepage_vma_check(struct vm_area_struct *vma) -{ - if ((!(vma->vm_flags & VM_HUGEPAGE) && !khugepaged_always()) || - (vma->vm_flags & VM_NOHUGEPAGE)) - return false; - if (!vma->anon_vma || vma->vm_ops) - return false; - if (is_vma_temporary_stack(vma)) - return false; - VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma); - return true; -} - -static void collapse_huge_page(struct mm_struct *mm, - unsigned long address, - struct page **hpage, - struct vm_area_struct *vma, - int node) -{ - pmd_t *pmd, _pmd; - pte_t *pte; - pgtable_t pgtable; - struct page *new_page; - spinlock_t *pmd_ptl, *pte_ptl; - int isolated = 0, result = 0; - unsigned long hstart, hend; - struct mem_cgroup *memcg; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ - gfp_t gfp; - - VM_BUG_ON(address & ~HPAGE_PMD_MASK); - - /* Only allocate from the target node */ - gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_OTHER_NODE | __GFP_THISNODE; - - /* release the mmap_sem read lock. */ - new_page = khugepaged_alloc_page(hpage, gfp, mm, address, node); - if (!new_page) { - result = SCAN_ALLOC_HUGE_PAGE_FAIL; - goto out_nolock; - } - - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { - result = SCAN_CGROUP_CHARGE_FAIL; - goto out_nolock; - } - - /* - * Prevent all access to pagetables with the exception of - * gup_fast later hanlded by the ptep_clear_flush and the VM - * handled by the anon_vma lock + PG_lock. - */ - down_write(&mm->mmap_sem); - if (unlikely(khugepaged_test_exit(mm))) { - result = SCAN_ANY_PROCESS; - goto out; - } - - vma = find_vma(mm, address); - if (!vma) { - result = SCAN_VMA_NULL; - goto out; - } - hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; - hend = vma->vm_end & HPAGE_PMD_MASK; - if (address < hstart || address + HPAGE_PMD_SIZE > hend) { - result = SCAN_ADDRESS_RANGE; - goto out; - } - if (!hugepage_vma_check(vma)) { - result = SCAN_VMA_CHECK; - goto out; - } - pmd = mm_find_pmd(mm, address); - if (!pmd) { - result = SCAN_PMD_NULL; - goto out; - } - - anon_vma_lock_write(vma->anon_vma); - - pte = pte_offset_map(pmd, address); - pte_ptl = pte_lockptr(mm, pmd); - - mmun_start = address; - mmun_end = address + HPAGE_PMD_SIZE; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ - /* - * After this gup_fast can't run anymore. This also removes - * any huge TLB entry from the CPU so we won't allow - * huge and small TLB entries for the same virtual address - * to avoid the risk of CPU bugs in that area. - */ - _pmd = pmdp_collapse_flush(vma, address, pmd); - spin_unlock(pmd_ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - - spin_lock(pte_ptl); - isolated = __collapse_huge_page_isolate(vma, address, pte); - spin_unlock(pte_ptl); - - if (unlikely(!isolated)) { - pte_unmap(pte); - spin_lock(pmd_ptl); - BUG_ON(!pmd_none(*pmd)); - /* - * We can only use set_pmd_at when establishing - * hugepmds and never for establishing regular pmds that - * points to regular pagetables. Use pmd_populate for that - */ - pmd_populate(mm, pmd, pmd_pgtable(_pmd)); - spin_unlock(pmd_ptl); - anon_vma_unlock_write(vma->anon_vma); - result = SCAN_FAIL; - goto out; - } - - /* - * All pages are isolated and locked so anon_vma rmap - * can't run anymore. - */ - anon_vma_unlock_write(vma->anon_vma); - - __collapse_huge_page_copy(pte, new_page, vma, address, pte_ptl); - pte_unmap(pte); - __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); - mem_cgroup_commit_charge(new_page, memcg, false, true); - lru_cache_add_active_or_unevictable(new_page, vma); - pgtable_trans_huge_deposit(mm, pmd, pgtable); - set_pmd_at(mm, address, pmd, _pmd); - update_mmu_cache_pmd(vma, address, pmd); - spin_unlock(pmd_ptl); - - *hpage = NULL; - - khugepaged_pages_collapsed++; - result = SCAN_SUCCEED; -out_up_write: - up_write(&mm->mmap_sem); - trace_mm_collapse_huge_page(mm, isolated, result); - return; - -out_nolock: - trace_mm_collapse_huge_page(mm, isolated, result); - return; -out: - mem_cgroup_cancel_charge(new_page, memcg, true); - goto out_up_write; -} - -static int khugepaged_scan_pmd(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long address, - struct page **hpage) -{ - pmd_t *pmd; - pte_t *pte, *_pte; - int ret = 0, none_or_zero = 0, result = 0; - struct page *page = NULL; - unsigned long _address; - spinlock_t *ptl; - int node = NUMA_NO_NODE; - bool writable = false, referenced = false; - - VM_BUG_ON(address & ~HPAGE_PMD_MASK); - - pmd = mm_find_pmd(mm, address); - if (!pmd) { - result = SCAN_PMD_NULL; - goto out; - } - - memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); - pte = pte_offset_map_lock(mm, pmd, address, &ptl); - for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR; - _pte++, _address += PAGE_SIZE) { - pte_t pteval = *_pte; - if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { - if (!userfaultfd_armed(vma) && - ++none_or_zero <= khugepaged_max_ptes_none) { - continue; - } else { - result = SCAN_EXCEED_NONE_PTE; - goto out_unmap; - } - } - if (!pte_present(pteval)) { - result = SCAN_PTE_NON_PRESENT; - goto out_unmap; - } - if (pte_write(pteval)) - writable = true; - - page = vm_normal_page(vma, _address, pteval); - if (unlikely(!page)) { - result = SCAN_PAGE_NULL; - goto out_unmap; - } - - /* TODO: teach khugepaged to collapse THP mapped with pte */ - if (PageCompound(page)) { - result = SCAN_PAGE_COMPOUND; - goto out_unmap; - } - - /* - * Record which node the original page is from and save this - * information to khugepaged_node_load[]. - * Khupaged will allocate hugepage from the node has the max - * hit record. - */ - node = page_to_nid(page); - if (khugepaged_scan_abort(node)) { - result = SCAN_SCAN_ABORT; - goto out_unmap; - } - khugepaged_node_load[node]++; - if (!PageLRU(page)) { - result = SCAN_PAGE_LRU; - goto out_unmap; - } - if (PageLocked(page)) { - result = SCAN_PAGE_LOCK; - goto out_unmap; - } - if (!PageAnon(page)) { - result = SCAN_PAGE_ANON; - goto out_unmap; - } - - /* - * cannot use mapcount: can't collapse if there's a gup pin. - * The page must only be referenced by the scanned process - * and page swap cache. - */ - if (page_count(page) != 1 + !!PageSwapCache(page)) { - result = SCAN_PAGE_COUNT; - goto out_unmap; - } - if (pte_young(pteval) || - page_is_young(page) || PageReferenced(page) || - mmu_notifier_test_young(vma->vm_mm, address)) - referenced = true; - } - if (writable) { - if (referenced) { - result = SCAN_SUCCEED; - ret = 1; - } else { - result = SCAN_NO_REFERENCED_PAGE; - } - } else { - result = SCAN_PAGE_RO; - } -out_unmap: - pte_unmap_unlock(pte, ptl); - if (ret) { - node = khugepaged_find_target_node(); - /* collapse_huge_page will return with the mmap_sem released */ - collapse_huge_page(mm, address, hpage, vma, node); - } -out: - trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced, - none_or_zero, result); - return ret; -} - -static void collect_mm_slot(struct mm_slot *mm_slot) -{ - struct mm_struct *mm = mm_slot->mm; - - VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock)); - - if (khugepaged_test_exit(mm)) { - /* free mm_slot */ - hash_del(&mm_slot->hash); - list_del(&mm_slot->mm_node); - - /* - * Not strictly needed because the mm exited already. - * - * clear_bit(MMF_VM_HUGEPAGE, &mm->flags); - */ - - /* khugepaged_mm_lock actually not necessary for the below */ - free_mm_slot(mm_slot); - mmdrop(mm); - } -} - -static unsigned int khugepaged_scan_mm_slot(unsigned int pages, - struct page **hpage) - __releases(&khugepaged_mm_lock) - __acquires(&khugepaged_mm_lock) -{ - struct mm_slot *mm_slot; - struct mm_struct *mm; - struct vm_area_struct *vma; - int progress = 0; - - VM_BUG_ON(!pages); - VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock)); - - if (khugepaged_scan.mm_slot) - mm_slot = khugepaged_scan.mm_slot; - else { - mm_slot = list_entry(khugepaged_scan.mm_head.next, - struct mm_slot, mm_node); - khugepaged_scan.address = 0; - khugepaged_scan.mm_slot = mm_slot; - } - spin_unlock(&khugepaged_mm_lock); - - mm = mm_slot->mm; - down_read(&mm->mmap_sem); - if (unlikely(khugepaged_test_exit(mm))) - vma = NULL; - else - vma = find_vma(mm, khugepaged_scan.address); - - progress++; - for (; vma; vma = vma->vm_next) { - unsigned long hstart, hend; - - cond_resched(); - if (unlikely(khugepaged_test_exit(mm))) { - progress++; - break; - } - if (!hugepage_vma_check(vma)) { -skip: - progress++; - continue; - } - hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; - hend = vma->vm_end & HPAGE_PMD_MASK; - if (hstart >= hend) - goto skip; - if (khugepaged_scan.address > hend) - goto skip; - if (khugepaged_scan.address < hstart) - khugepaged_scan.address = hstart; - VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); - - while (khugepaged_scan.address < hend) { - int ret; - cond_resched(); - if (unlikely(khugepaged_test_exit(mm))) - goto breakouterloop; - - VM_BUG_ON(khugepaged_scan.address < hstart || - khugepaged_scan.address + HPAGE_PMD_SIZE > - hend); - ret = khugepaged_scan_pmd(mm, vma, - khugepaged_scan.address, - hpage); - /* move to next address */ - khugepaged_scan.address += HPAGE_PMD_SIZE; - progress += HPAGE_PMD_NR; - if (ret) - /* we released mmap_sem so break loop */ - goto breakouterloop_mmap_sem; - if (progress >= pages) - goto breakouterloop; - } - } -breakouterloop: - up_read(&mm->mmap_sem); /* exit_mmap will destroy ptes after this */ -breakouterloop_mmap_sem: - - spin_lock(&khugepaged_mm_lock); - VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot); - /* - * Release the current mm_slot if this mm is about to die, or - * if we scanned all vmas of this mm. - */ - if (khugepaged_test_exit(mm) || !vma) { - /* - * Make sure that if mm_users is reaching zero while - * khugepaged runs here, khugepaged_exit will find - * mm_slot not pointing to the exiting mm. - */ - if (mm_slot->mm_node.next != &khugepaged_scan.mm_head) { - khugepaged_scan.mm_slot = list_entry( - mm_slot->mm_node.next, - struct mm_slot, mm_node); - khugepaged_scan.address = 0; - } else { - khugepaged_scan.mm_slot = NULL; - khugepaged_full_scans++; - } - - collect_mm_slot(mm_slot); - } - - return progress; -} - -static int khugepaged_has_work(void) -{ - return !list_empty(&khugepaged_scan.mm_head) && - khugepaged_enabled(); -} - -static int khugepaged_wait_event(void) -{ - return !list_empty(&khugepaged_scan.mm_head) || - kthread_should_stop(); -} - -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; - bool wait = true; - - barrier(); /* write khugepaged_pages_to_scan to local stack */ - - while (progress < pages) { - if (!khugepaged_prealloc_page(&hpage, &wait)) - break; - - cond_resched(); - - if (unlikely(kthread_should_stop() || try_to_freeze())) - break; - - spin_lock(&khugepaged_mm_lock); - if (!khugepaged_scan.mm_slot) - pass_through_head++; - if (khugepaged_has_work() && - pass_through_head < 2) - progress += khugepaged_scan_mm_slot(pages - progress, - &hpage); - else - progress = pages; - spin_unlock(&khugepaged_mm_lock); - } - - if (!IS_ERR_OR_NULL(hpage)) - put_page(hpage); -} - -static void khugepaged_wait_work(void) -{ - if (khugepaged_has_work()) { - if (!khugepaged_scan_sleep_millisecs) - return; - - wait_event_freezable_timeout(khugepaged_wait, - kthread_should_stop(), - msecs_to_jiffies(khugepaged_scan_sleep_millisecs)); - return; - } - - if (khugepaged_enabled()) - wait_event_freezable(khugepaged_wait, khugepaged_wait_event()); -} - -static int khugepaged(void *none) -{ - struct mm_slot *mm_slot; - - set_freezable(); - set_user_nice(current, MAX_NICE); - - while (!kthread_should_stop()) { - khugepaged_do_scan(); - khugepaged_wait_work(); - } - - spin_lock(&khugepaged_mm_lock); - mm_slot = khugepaged_scan.mm_slot; - khugepaged_scan.mm_slot = NULL; - if (mm_slot) - collect_mm_slot(mm_slot); - spin_unlock(&khugepaged_mm_lock); - return 0; -} - static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd) { @@ -2887,10 +1523,18 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, count_vm_event(THP_SPLIT_PMD); - if (vma_is_dax(vma)) { - pmd_t _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); + if (!vma_is_anonymous(vma)) { + _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); if (is_huge_zero_pmd(_pmd)) put_huge_zero_page(); + if (vma_is_dax(vma)) + return; + page = pmd_page(_pmd); + if (!PageReferenced(page) && pmd_young(_pmd)) + SetPageReferenced(page); + page_remove_rmap(page, true); + put_page(page); + add_mm_counter(mm, MM_FILEPAGES, -HPAGE_PMD_NR); return; } else if (is_huge_zero_pmd(*pmd)) { return __split_huge_zero_page_pmd(vma, haddr, pmd); @@ -2946,7 +1590,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { /* Last compound_mapcount is gone. */ - __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + __dec_node_page_state(page, NR_ANON_THPS); if (TestClearPageDoubleMap(page)) { /* No need in mapcount reference anymore */ for (i = 0; i < HPAGE_PMD_NR; i++) @@ -2988,7 +1632,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, } void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze) + unsigned long address, bool freeze, struct page *page) { spinlock_t *ptl; struct mm_struct *mm = vma->vm_mm; @@ -2996,8 +1640,17 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE); ptl = pmd_lock(mm, pmd); + + /* + * If caller asks to setup a migration entries, we need a page to check + * pmd against. Otherwise we can end up replacing wrong page. + */ + VM_BUG_ON(freeze && !page); + if (page && page != pmd_page(*pmd)) + goto out; + if (pmd_trans_huge(*pmd)) { - struct page *page = pmd_page(*pmd); + page = pmd_page(*pmd); if (PageMlocked(page)) clear_page_mlock(page); } else if (!pmd_devmap(*pmd)) @@ -3024,22 +1677,8 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, return; pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd) || (!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd))) - return; - - /* - * If caller asks to setup a migration entries, we need a page to check - * pmd against. Otherwise we can end up replacing wrong page. - */ - VM_BUG_ON(freeze && !page); - if (page && page != pmd_page(*pmd)) - return; - /* - * Caller holds the mmap_sem write mode, so a huge pmd cannot - * materialize from under us. - */ - __split_huge_pmd(vma, pmd, address, freeze); + __split_huge_pmd(vma, pmd, address, freeze, page); } void vma_adjust_trans_huge(struct vm_area_struct *vma, @@ -3085,12 +1724,15 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, static void freeze_page(struct page *page) { - enum ttu_flags ttu_flags = TTU_MIGRATION | TTU_IGNORE_MLOCK | - TTU_IGNORE_ACCESS | TTU_RMAP_LOCKED; + enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS | + TTU_RMAP_LOCKED; int i, ret; VM_BUG_ON_PAGE(!PageHead(page), page); + if (PageAnon(page)) + ttu_flags |= TTU_MIGRATION; + /* We only need TTU_SPLIT_HUGE_PMD once */ ret = try_to_unmap(page, ttu_flags | TTU_SPLIT_HUGE_PMD); for (i = 1; !ret && i < HPAGE_PMD_NR; i++) { @@ -3100,7 +1742,7 @@ static void freeze_page(struct page *page) ret = try_to_unmap(page + i, ttu_flags); } - VM_BUG_ON(ret); + VM_BUG_ON_PAGE(ret, page + i - 1); } static void unfreeze_page(struct page *page) @@ -3120,17 +1762,22 @@ static void __split_huge_page_tail(struct page *head, int tail, VM_BUG_ON_PAGE(page_ref_count(page_tail) != 0, page_tail); /* - * tail_page->_count is zero and not changing from under us. But + * tail_page->_refcount is zero and not changing from under us. But * get_page_unless_zero() may be running from under us on the - * tail_page. If we used atomic_set() below instead of atomic_inc(), we - * would then run atomic_set() concurrently with + * tail_page. If we used atomic_set() below instead of atomic_inc() or + * atomic_add(), we would then run atomic_set() concurrently with * get_page_unless_zero(), and atomic_set() is implemented in C not * using locked ops. spin_unlock on x86 sometime uses locked ops * because of PPro errata 66, 92, so unless somebody can guarantee * atomic_set() here would be safe on all archs (and not only on x86), - * it's safer to use atomic_inc(). + * it's safer to use atomic_inc()/atomic_add(). */ - page_ref_inc(page_tail); + if (PageAnon(head)) { + page_ref_inc(page_tail); + } else { + /* Additional pin to radix tree */ + page_ref_add(page_tail, 2); + } page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; page_tail->flags |= (head->flags & @@ -3166,25 +1813,46 @@ static void __split_huge_page_tail(struct page *head, int tail, lru_add_page_tail(head, page_tail, lruvec, list); } -static void __split_huge_page(struct page *page, struct list_head *list) +static void __split_huge_page(struct page *page, struct list_head *list, + unsigned long flags) { struct page *head = compound_head(page); struct zone *zone = page_zone(head); struct lruvec *lruvec; + pgoff_t end = -1; int i; - /* prevent PageLRU to go away from under us, and freeze lru stats */ - spin_lock_irq(&zone->lru_lock); - lruvec = mem_cgroup_page_lruvec(head, zone); + lruvec = mem_cgroup_page_lruvec(head, zone->zone_pgdat); /* complete memcg works before add pages to LRU */ mem_cgroup_split_huge_fixup(head); - for (i = HPAGE_PMD_NR - 1; i >= 1; i--) + if (!PageAnon(page)) + end = DIV_ROUND_UP(i_size_read(head->mapping->host), PAGE_SIZE); + + for (i = HPAGE_PMD_NR - 1; i >= 1; i--) { __split_huge_page_tail(head, i, lruvec, list); + /* Some pages can be beyond i_size: drop them from page cache */ + if (head[i].index >= end) { + __ClearPageDirty(head + i); + __delete_from_page_cache(head + i, NULL); + if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head)) + shmem_uncharge(head->mapping->host, 1); + put_page(head + i); + } + } ClearPageCompound(head); - spin_unlock_irq(&zone->lru_lock); + /* See comment in __split_huge_page_tail() */ + if (PageAnon(head)) { + page_ref_inc(head); + } else { + /* Additional pin to radix tree */ + page_ref_add(head, 2); + spin_unlock(&head->mapping->tree_lock); + } + + spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags); unfreeze_page(head); @@ -3207,24 +1875,86 @@ static void __split_huge_page(struct page *page, struct list_head *list) int total_mapcount(struct page *page) { - int i, ret; + int i, compound, ret; VM_BUG_ON_PAGE(PageTail(page), page); if (likely(!PageCompound(page))) return atomic_read(&page->_mapcount) + 1; - ret = compound_mapcount(page); + compound = compound_mapcount(page); if (PageHuge(page)) - return ret; + return compound; + ret = compound; for (i = 0; i < HPAGE_PMD_NR; i++) ret += atomic_read(&page[i]._mapcount) + 1; + /* File pages has compound_mapcount included in _mapcount */ + if (!PageAnon(page)) + return ret - compound * HPAGE_PMD_NR; if (PageDoubleMap(page)) ret -= HPAGE_PMD_NR; return ret; } /* + * This calculates accurately how many mappings a transparent hugepage + * has (unlike page_mapcount() which isn't fully accurate). This full + * accuracy is primarily needed to know if copy-on-write faults can + * reuse the page and change the mapping to read-write instead of + * copying them. At the same time this returns the total_mapcount too. + * + * The function returns the highest mapcount any one of the subpages + * has. If the return value is one, even if different processes are + * mapping different subpages of the transparent hugepage, they can + * all reuse it, because each process is reusing a different subpage. + * + * The total_mapcount is instead counting all virtual mappings of the + * subpages. If the total_mapcount is equal to "one", it tells the + * caller all mappings belong to the same "mm" and in turn the + * anon_vma of the transparent hugepage can become the vma->anon_vma + * local one as no other process may be mapping any of the subpages. + * + * It would be more accurate to replace page_mapcount() with + * page_trans_huge_mapcount(), however we only use + * page_trans_huge_mapcount() in the copy-on-write faults where we + * need full accuracy to avoid breaking page pinning, because + * page_trans_huge_mapcount() is slower than page_mapcount(). + */ +int page_trans_huge_mapcount(struct page *page, int *total_mapcount) +{ + int i, ret, _total_mapcount, mapcount; + + /* hugetlbfs shouldn't call it */ + VM_BUG_ON_PAGE(PageHuge(page), page); + + if (likely(!PageTransCompound(page))) { + mapcount = atomic_read(&page->_mapcount) + 1; + if (total_mapcount) + *total_mapcount = mapcount; + return mapcount; + } + + page = compound_head(page); + + _total_mapcount = ret = 0; + for (i = 0; i < HPAGE_PMD_NR; i++) { + mapcount = atomic_read(&page[i]._mapcount) + 1; + ret = max(ret, mapcount); + _total_mapcount += mapcount; + } + if (PageDoubleMap(page)) { + ret -= 1; + _total_mapcount -= HPAGE_PMD_NR; + } + mapcount = compound_mapcount(page); + ret += mapcount; + _total_mapcount += mapcount; + if (total_mapcount) + *total_mapcount = _total_mapcount; + return ret; +} + +/* * This function splits huge page into normal pages. @page can point to any * subpage of huge page to split. Split doesn't change the position of @page. * @@ -3247,36 +1977,54 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) { struct page *head = compound_head(page); struct pglist_data *pgdata = NODE_DATA(page_to_nid(head)); - struct anon_vma *anon_vma; - int count, mapcount, ret; + struct anon_vma *anon_vma = NULL; + struct address_space *mapping = NULL; + int count, mapcount, extra_pins, ret; bool mlocked; unsigned long flags; VM_BUG_ON_PAGE(is_huge_zero_page(page), page); - VM_BUG_ON_PAGE(!PageAnon(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageSwapBacked(page), page); VM_BUG_ON_PAGE(!PageCompound(page), page); - /* - * The caller does not necessarily hold an mmap_sem that would prevent - * the anon_vma disappearing so we first we take a reference to it - * and then lock the anon_vma for write. This is similar to - * page_lock_anon_vma_read except the write lock is taken to serialise - * against parallel split or collapse operations. - */ - anon_vma = page_get_anon_vma(head); - if (!anon_vma) { - ret = -EBUSY; - goto out; + if (PageAnon(head)) { + /* + * The caller does not necessarily hold an mmap_sem that would + * prevent the anon_vma disappearing so we first we take a + * reference to it and then lock the anon_vma for write. This + * is similar to page_lock_anon_vma_read except the write lock + * is taken to serialise against parallel split or collapse + * operations. + */ + anon_vma = page_get_anon_vma(head); + if (!anon_vma) { + ret = -EBUSY; + goto out; + } + extra_pins = 0; + mapping = NULL; + anon_vma_lock_write(anon_vma); + } else { + mapping = head->mapping; + + /* Truncated ? */ + if (!mapping) { + ret = -EBUSY; + goto out; + } + + /* Addidional pins from radix tree */ + extra_pins = HPAGE_PMD_NR; + anon_vma = NULL; + i_mmap_lock_read(mapping); } - anon_vma_lock_write(anon_vma); /* * Racy check if we can split the page, before freeze_page() will * split PMDs */ - if (total_mapcount(head) != page_count(head) - 1) { + if (total_mapcount(head) != page_count(head) - extra_pins - 1) { ret = -EBUSY; goto out_unlock; } @@ -3289,35 +2037,62 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) if (mlocked) lru_add_drain(); - /* Prevent deferred_split_scan() touching ->_count */ - spin_lock_irqsave(&pgdata->split_queue_lock, flags); + /* prevent PageLRU to go away from under us, and freeze lru stats */ + spin_lock_irqsave(zone_lru_lock(page_zone(head)), flags); + + if (mapping) { + void **pslot; + + spin_lock(&mapping->tree_lock); + pslot = radix_tree_lookup_slot(&mapping->page_tree, + page_index(head)); + /* + * Check if the head page is present in radix tree. + * We assume all tail are present too, if head is there. + */ + if (radix_tree_deref_slot_protected(pslot, + &mapping->tree_lock) != head) + goto fail; + } + + /* Prevent deferred_split_scan() touching ->_refcount */ + spin_lock(&pgdata->split_queue_lock); count = page_count(head); mapcount = total_mapcount(head); - if (!mapcount && count == 1) { + if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) { if (!list_empty(page_deferred_list(head))) { pgdata->split_queue_len--; list_del(page_deferred_list(head)); } - spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); - __split_huge_page(page, list); + if (mapping) + __dec_node_page_state(page, NR_SHMEM_THPS); + spin_unlock(&pgdata->split_queue_lock); + __split_huge_page(page, list, flags); ret = 0; - } else if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) { - spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); - pr_alert("total_mapcount: %u, page_count(): %u\n", - mapcount, count); - if (PageTail(page)) - dump_page(head, NULL); - dump_page(page, "total_mapcount(head) > 0"); - BUG(); } else { - spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); + if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) { + pr_alert("total_mapcount: %u, page_count(): %u\n", + mapcount, count); + if (PageTail(page)) + dump_page(head, NULL); + dump_page(page, "total_mapcount(head) > 0"); + BUG(); + } + spin_unlock(&pgdata->split_queue_lock); +fail: if (mapping) + spin_unlock(&mapping->tree_lock); + spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags); unfreeze_page(head); ret = -EBUSY; } out_unlock: - anon_vma_unlock_write(anon_vma); - put_anon_vma(anon_vma); + if (anon_vma) { + anon_vma_unlock_write(anon_vma); + put_anon_vma(anon_vma); + } + if (mapping) + i_mmap_unlock_read(mapping); out: count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); return ret; @@ -3440,8 +2215,7 @@ static int split_huge_pages_set(void *data, u64 val) if (zone != page_zone(page)) goto next; - if (!PageHead(page) || !PageAnon(page) || - PageHuge(page)) + if (!PageHead(page) || PageHuge(page) || !PageLRU(page)) goto next; total++; @@ -3454,7 +2228,7 @@ next: } } - pr_info("%lu of %lu THP split", split, total); + pr_info("%lu of %lu THP split\n", split, total); return 0; } @@ -3465,7 +2239,7 @@ static int __init split_huge_pages_debugfs(void) { void *ret; - ret = debugfs_create_file("split_huge_pages", 0644, NULL, NULL, + ret = debugfs_create_file("split_huge_pages", 0200, NULL, NULL, &split_huge_pages_fops); if (!ret) pr_warn("Failed to create split_huge_pages in debugfs"); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 06058eaa173b..b9aa1b0b38b0 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -51,6 +51,7 @@ __initdata LIST_HEAD(huge_boot_pages); static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; static unsigned long __initdata default_hstate_size; +static bool __initdata parsed_valid_hugepagesz = true; /* * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, @@ -144,7 +145,8 @@ static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, } } - if (spool->min_hpages != -1) { /* minimum size accounting */ + /* minimum size accounting */ + if (spool->min_hpages != -1 && spool->rsv_hpages) { if (delta > spool->rsv_hpages) { /* * Asking for more reserves than those already taken on @@ -182,7 +184,8 @@ static long hugepage_subpool_put_pages(struct hugepage_subpool *spool, if (spool->max_hpages != -1) /* maximum size accounting */ spool->used_hpages -= delta; - if (spool->min_hpages != -1) { /* minimum size accounting */ + /* minimum size accounting */ + if (spool->min_hpages != -1 && spool->used_hpages < spool->min_hpages) { if (spool->rsv_hpages + delta <= spool->min_hpages) ret = 0; else @@ -624,6 +627,7 @@ pgoff_t linear_hugepage_index(struct vm_area_struct *vma, { return vma_hugecache_offset(hstate_vma(vma), vma, address); } +EXPORT_SYMBOL_GPL(linear_hugepage_index); /* * Return the size of the pages allocated when backing a VMA. In the majority @@ -828,8 +832,27 @@ static bool vma_has_reserves(struct vm_area_struct *vma, long chg) * Only the process that called mmap() has reserves for * private mappings. */ - if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) - return true; + if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { + /* + * Like the shared case above, a hole punch or truncate + * could have been performed on the private mapping. + * Examine the value of chg to determine if reserves + * actually exist or were previously consumed. + * Very Subtle - The value of chg comes from a previous + * call to vma_needs_reserves(). The reserve map for + * private mappings has different (opposite) semantics + * than that of shared mappings. vma_needs_reserves() + * has already taken this difference in semantics into + * account. Therefore, the meaning of chg is the same + * as in the shared case above. Code could easily be + * combined, but keeping it separate draws attention to + * subtle differences. + */ + if (chg) + return false; + else + return true; + } return false; } @@ -937,9 +960,7 @@ err: */ static int next_node_allowed(int nid, nodemask_t *nodes_allowed) { - nid = next_node(nid, *nodes_allowed); - if (nid == MAX_NUMNODES) - nid = first_node(*nodes_allowed); + nid = next_node_in(nid, *nodes_allowed); VM_BUG_ON(nid >= MAX_NUMNODES); return nid; @@ -1001,7 +1022,9 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) ((node = hstate_next_node_to_free(hs, mask)) || 1); \ nr_nodes--) -#if defined(CONFIG_X86_64) && ((defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)) +#if (defined(CONFIG_X86_64) || defined(CONFIG_S390)) && \ + ((defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || \ + defined(CONFIG_CMA)) static void destroy_compound_gigantic_page(struct page *page, unsigned int order) { @@ -1009,6 +1032,7 @@ static void destroy_compound_gigantic_page(struct page *page, int nr_pages = 1 << order; struct page *p = page + 1; + atomic_set(compound_mapcount_ptr(page), 0); for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { clear_compound_head(p); set_page_refcounted(p); @@ -1030,8 +1054,8 @@ static int __alloc_gigantic_page(unsigned long start_pfn, return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE); } -static bool pfn_range_valid_gigantic(unsigned long start_pfn, - unsigned long nr_pages) +static bool pfn_range_valid_gigantic(struct zone *z, + unsigned long start_pfn, unsigned long nr_pages) { unsigned long i, end_pfn = start_pfn + nr_pages; struct page *page; @@ -1042,6 +1066,9 @@ static bool pfn_range_valid_gigantic(unsigned long start_pfn, page = pfn_to_page(i); + if (page_zone(page) != z) + return false; + if (PageReserved(page)) return false; @@ -1074,7 +1101,7 @@ static struct page *alloc_gigantic_page(int nid, unsigned int order) pfn = ALIGN(z->zone_start_pfn, nr_pages); while (zone_spans_last_pfn(z, pfn, nr_pages)) { - if (pfn_range_valid_gigantic(pfn, nr_pages)) { + if (pfn_range_valid_gigantic(z, pfn, nr_pages)) { /* * We release the zone lock here because * alloc_contig_range() will also lock the zone @@ -1811,6 +1838,25 @@ 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; } @@ -2170,6 +2216,10 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count, * and reducing the surplus. */ spin_unlock(&hugetlb_lock); + + /* yield cpu to avoid soft lockup */ + cond_resched(); + if (hstate_is_gigantic(h)) ret = alloc_fresh_gigantic_page(h, nodes_allowed); else @@ -2659,6 +2709,11 @@ static int __init hugetlb_init(void) subsys_initcall(hugetlb_init); /* Should be called on processing a hugepagesz=... option */ +void __init hugetlb_bad_size(void) +{ + parsed_valid_hugepagesz = false; +} + void __init hugetlb_add_hstate(unsigned int order) { struct hstate *h; @@ -2678,8 +2733,8 @@ void __init hugetlb_add_hstate(unsigned int order) for (i = 0; i < MAX_NUMNODES; ++i) INIT_LIST_HEAD(&h->hugepage_freelists[i]); INIT_LIST_HEAD(&h->hugepage_activelist); - h->next_nid_to_alloc = first_node(node_states[N_MEMORY]); - h->next_nid_to_free = first_node(node_states[N_MEMORY]); + h->next_nid_to_alloc = first_memory_node; + h->next_nid_to_free = first_memory_node; snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", huge_page_size(h)/1024); @@ -2691,11 +2746,17 @@ static int __init hugetlb_nrpages_setup(char *s) unsigned long *mhp; static unsigned long *last_mhp; + if (!parsed_valid_hugepagesz) { + pr_warn("hugepages = %s preceded by " + "an unsupported hugepagesz, ignoring\n", s); + parsed_valid_hugepagesz = true; + return 1; + } /* * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter yet, * so this hugepages= parameter goes to the "default hstate". */ - if (!hugetlb_max_hstate) + else if (!hugetlb_max_hstate) mhp = &default_hstate_max_huge_pages; else mhp = &parsed_hstate->max_huge_pages; @@ -3122,7 +3183,6 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page) { - int force_flush = 0; struct mm_struct *mm = vma->vm_mm; unsigned long address; pte_t *ptep; @@ -3141,19 +3201,22 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, tlb_start_vma(tlb, vma); mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); address = start; -again: for (; address < end; address += sz) { ptep = huge_pte_offset(mm, address); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, &address, ptep)) - goto unlock; + if (huge_pmd_unshare(mm, &address, ptep)) { + spin_unlock(ptl); + continue; + } pte = huge_ptep_get(ptep); - if (huge_pte_none(pte)) - goto unlock; + if (huge_pte_none(pte)) { + spin_unlock(ptl); + continue; + } /* * Migrating hugepage or HWPoisoned hugepage is already @@ -3161,7 +3224,8 @@ again: */ if (unlikely(!pte_present(pte))) { huge_pte_clear(mm, address, ptep); - goto unlock; + spin_unlock(ptl); + continue; } page = pte_page(pte); @@ -3171,9 +3235,10 @@ again: * are about to unmap is the actual page of interest. */ if (ref_page) { - if (page != ref_page) - goto unlock; - + if (page != ref_page) { + spin_unlock(ptl); + continue; + } /* * Mark the VMA as having unmapped its page so that * future faults in this VMA will fail rather than @@ -3189,30 +3254,14 @@ again: hugetlb_count_sub(pages_per_huge_page(h), mm); page_remove_rmap(page, true); - force_flush = !__tlb_remove_page(tlb, page); - if (force_flush) { - address += sz; - spin_unlock(ptl); - break; - } - /* Bail out after unmapping reference page if supplied */ - if (ref_page) { - spin_unlock(ptl); - break; - } -unlock: + spin_unlock(ptl); - } - /* - * mmu_gather ran out of room to batch pages, we break out of - * the PTE lock to avoid doing the potential expensive TLB invalidate - * and page-free while holding it. - */ - if (force_flush) { - force_flush = 0; - tlb_flush_mmu(tlb); - if (address < end && !ref_page) - goto again; + tlb_remove_page_size(tlb, page, huge_page_size(h)); + /* + * Bail out after unmapping reference page if supplied + */ + if (ref_page) + break; } mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); tlb_end_vma(tlb, vma); @@ -3271,7 +3320,7 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, address = address & huge_page_mask(h); pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - mapping = file_inode(vma->vm_file)->i_mapping; + mapping = vma->vm_file->f_mapping; /* * Take the mapping lock for the duration of the table walk. As @@ -3328,7 +3377,7 @@ retry_avoidcopy: /* If no-one else is actually using this page, avoid the copy * and just make the page writable */ if (page_mapcount(old_page) == 1 && PageAnon(old_page)) { - page_move_anon_rmap(old_page, vma, address); + page_move_anon_rmap(old_page, vma); set_huge_ptep_writable(vma, address, ptep); return 0; } @@ -3346,7 +3395,7 @@ retry_avoidcopy: old_page != pagecache_page) outside_reserve = 1; - page_cache_get(old_page); + get_page(old_page); /* * Drop page table lock as buddy allocator may be called. It will @@ -3364,7 +3413,7 @@ retry_avoidcopy: * may get SIGKILLed if it later faults. */ if (outside_reserve) { - page_cache_release(old_page); + put_page(old_page); BUG_ON(huge_pte_none(pte)); unmap_ref_private(mm, vma, old_page, address); BUG_ON(huge_pte_none(pte)); @@ -3425,9 +3474,9 @@ retry_avoidcopy: spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); out_release_all: - page_cache_release(new_page); + put_page(new_page); out_release_old: - page_cache_release(old_page); + put_page(old_page); spin_lock(ptl); /* Caller expects lock to be held */ return ret; @@ -3893,6 +3942,14 @@ same_page: return i ? i : -EFAULT; } +#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) { @@ -3953,7 +4010,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, * once we release i_mmap_rwsem, another task can do the final put_page * and that page table be reused and filled with junk. */ - flush_tlb_range(vma, start, end); + flush_hugetlb_tlb_range(vma, start, end); mmu_notifier_invalidate_range(mm, start, end); i_mmap_unlock_write(vma->vm_file->f_mapping); mmu_notifier_invalidate_range_end(mm, start, end); @@ -4174,7 +4231,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) if (saddr) { spte = huge_pte_offset(svma->vm_mm, saddr); if (spte) { - mm_inc_nr_pmds(mm); get_page(virt_to_page(spte)); break; } @@ -4189,9 +4245,9 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) if (pud_none(*pud)) { pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); + mm_inc_nr_pmds(mm); } else { put_page(virt_to_page(spte)); - mm_inc_nr_pmds(mm); } spin_unlock(ptl); out: @@ -4262,7 +4318,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, pte = (pte_t *)pmd_alloc(mm, pud, addr); } } - BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte)); + BUG_ON(pte && pte_present(*pte) && !pte_huge(*pte)); return pte; } @@ -4347,7 +4403,6 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address, /* * This function is called from memory failure code. - * Assume the caller holds page lock of the head page. */ int dequeue_hwpoisoned_huge_page(struct page *hpage) { diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index d8fb10de0f14..eec1150125b9 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -67,26 +67,42 @@ static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg) return false; } +static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup, + struct hugetlb_cgroup *parent_h_cgroup) +{ + int idx; + + for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) { + struct page_counter *counter = &h_cgroup->hugepage[idx]; + struct page_counter *parent = NULL; + unsigned long limit; + int ret; + + if (parent_h_cgroup) + parent = &parent_h_cgroup->hugepage[idx]; + page_counter_init(counter, parent); + + limit = round_down(PAGE_COUNTER_MAX, + 1 << huge_page_order(&hstates[idx])); + ret = page_counter_limit(counter, limit); + VM_BUG_ON(ret); + } +} + static struct cgroup_subsys_state * hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { struct hugetlb_cgroup *parent_h_cgroup = hugetlb_cgroup_from_css(parent_css); struct hugetlb_cgroup *h_cgroup; - int idx; h_cgroup = kzalloc(sizeof(*h_cgroup), GFP_KERNEL); if (!h_cgroup) return ERR_PTR(-ENOMEM); - if (parent_h_cgroup) { - for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) - page_counter_init(&h_cgroup->hugepage[idx], - &parent_h_cgroup->hugepage[idx]); - } else { + if (!parent_h_cgroup) root_h_cgroup = h_cgroup; - for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) - page_counter_init(&h_cgroup->hugepage[idx], NULL); - } + + hugetlb_cgroup_init(h_cgroup, parent_h_cgroup); return &h_cgroup->css; } @@ -285,6 +301,7 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, return ret; idx = MEMFILE_IDX(of_cft(of)->private); + nr_pages = round_down(nr_pages, 1 << huge_page_order(&hstates[idx])); switch (MEMFILE_ATTR(of_cft(of)->private)) { case RES_LIMIT: diff --git a/mm/internal.h b/mm/internal.h index b79abb6721cf..1501304f87a4 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -24,7 +24,8 @@ */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\ - __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC) + __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ + __GFP_ATOMIC) /* The GFP flags allowed during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) @@ -35,6 +36,8 @@ /* Do not use these with a slab allocator */ #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) +int do_swap_page(struct fault_env *fe, pte_t orig_pte); + void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); @@ -58,7 +61,7 @@ static inline unsigned long ra_submit(struct file_ra_state *ra, } /* - * Turn a non-refcounted page (->_count == 0) into refcounted with + * Turn a non-refcounted page (->_refcount == 0) into refcounted with * a count of one. */ static inline void set_page_refcounted(struct page *page) @@ -75,7 +78,7 @@ extern unsigned long highest_memmap_pfn; */ extern int isolate_lru_page(struct page *page); extern void putback_lru_page(struct page *page); -extern bool zone_reclaimable(struct zone *zone); +extern bool pgdat_reclaimable(struct pglist_data *pgdat); /* * in mm/rmap.c: @@ -102,13 +105,14 @@ extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); struct alloc_context { struct zonelist *zonelist; nodemask_t *nodemask; - struct zone *preferred_zone; - int classzone_idx; + struct zoneref *preferred_zoneref; int migratetype; enum zone_type high_zoneidx; bool spread_dirty_pages; }; +#define ac_classzone_idx(ac) zonelist_zone_idx(ac->preferred_zoneref) + /* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). @@ -148,6 +152,8 @@ extern int __isolate_free_page(struct page *page, unsigned int order); extern void __free_pages_bootmem(struct page *page, unsigned long pfn, unsigned int order); extern void prep_compound_page(struct page *page, unsigned int order); +extern void post_alloc_hook(struct page *page, unsigned int order, + gfp_t gfp_flags); extern int user_min_free_kbytes; #if defined CONFIG_COMPACTION || defined CONFIG_CMA @@ -173,15 +179,13 @@ struct compact_control { enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool direct_compaction; /* False from kcompactd or /proc/... */ + bool whole_zone; /* Whole zone has been scanned */ int order; /* order a direct compactor needs */ const gfp_t gfp_mask; /* gfp mask of a direct compactor */ - const int alloc_flags; /* alloc flags of a direct compactor */ + const unsigned int alloc_flags; /* alloc flags of a direct compactor */ const int classzone_idx; /* zone index of a direct compactor */ struct zone *zone; - int contended; /* Signal need_sched() or lock - * contention detected during - * compaction - */ + bool contended; /* Signal lock or sched contention */ }; unsigned long @@ -426,10 +430,10 @@ static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn, } #endif /* CONFIG_SPARSEMEM */ -#define ZONE_RECLAIM_NOSCAN -2 -#define ZONE_RECLAIM_FULL -1 -#define ZONE_RECLAIM_SOME 0 -#define ZONE_RECLAIM_SUCCESS 1 +#define NODE_RECLAIM_NOSCAN -2 +#define NODE_RECLAIM_FULL -1 +#define NODE_RECLAIM_SOME 0 +#define NODE_RECLAIM_SUCCESS 1 extern int hwpoison_filter(struct page *p); @@ -440,7 +444,7 @@ extern u64 hwpoison_filter_flags_value; extern u64 hwpoison_filter_memcg; extern u32 hwpoison_filter_enable; -extern unsigned long vm_mmap_pgoff(struct file *, unsigned long, +extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); @@ -460,7 +464,6 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, #define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ #define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ -#define ALLOC_FAIR 0x100 /* fair zone allocation */ enum ttu_flags; struct tlbflush_unmap_batch; diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile index 131daadf40e4..2976a9ee104f 100644 --- a/mm/kasan/Makefile +++ b/mm/kasan/Makefile @@ -7,4 +7,4 @@ CFLAGS_REMOVE_kasan.o = -pg # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533 CFLAGS_kasan.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) -obj-y := kasan.o report.o kasan_init.o +obj-y := kasan.o report.o kasan_init.o quarantine.o diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index acb3b6c4dd89..88af13c00d3c 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -273,32 +273,48 @@ static __always_inline bool memory_is_poisoned(unsigned long addr, size_t size) return memory_is_poisoned_n(addr, size); } - -static __always_inline void check_memory_region(unsigned long addr, - size_t size, bool write) +static __always_inline void check_memory_region_inline(unsigned long addr, + size_t size, bool write, + unsigned long ret_ip) { if (unlikely(size == 0)) return; if (unlikely((void *)addr < kasan_shadow_to_mem((void *)KASAN_SHADOW_START))) { - kasan_report(addr, size, write, _RET_IP_); + kasan_report(addr, size, write, ret_ip); return; } if (likely(!memory_is_poisoned(addr, size))) return; - kasan_report(addr, size, write, _RET_IP_); + kasan_report(addr, size, write, ret_ip); +} + +static void check_memory_region(unsigned long addr, + size_t size, bool write, + unsigned long ret_ip) +{ + check_memory_region_inline(addr, size, write, ret_ip); } -void __asan_loadN(unsigned long addr, size_t size); -void __asan_storeN(unsigned long addr, size_t size); +void kasan_check_read(const void *p, unsigned int size) +{ + check_memory_region((unsigned long)p, size, false, _RET_IP_); +} +EXPORT_SYMBOL(kasan_check_read); + +void kasan_check_write(const void *p, unsigned int size) +{ + check_memory_region((unsigned long)p, size, true, _RET_IP_); +} +EXPORT_SYMBOL(kasan_check_write); #undef memset void *memset(void *addr, int c, size_t len) { - __asan_storeN((unsigned long)addr, len); + check_memory_region((unsigned long)addr, len, true, _RET_IP_); return __memset(addr, c, len); } @@ -306,8 +322,8 @@ void *memset(void *addr, int c, size_t len) #undef memmove void *memmove(void *dest, const void *src, size_t len) { - __asan_loadN((unsigned long)src, len); - __asan_storeN((unsigned long)dest, len); + check_memory_region((unsigned long)src, len, false, _RET_IP_); + check_memory_region((unsigned long)dest, len, true, _RET_IP_); return __memmove(dest, src, len); } @@ -315,8 +331,8 @@ void *memmove(void *dest, const void *src, size_t len) #undef memcpy void *memcpy(void *dest, const void *src, size_t len) { - __asan_loadN((unsigned long)src, len); - __asan_storeN((unsigned long)dest, len); + check_memory_region((unsigned long)src, len, false, _RET_IP_); + check_memory_region((unsigned long)dest, len, true, _RET_IP_); return __memcpy(dest, src, len); } @@ -335,7 +351,6 @@ void kasan_free_pages(struct page *page, unsigned int order) KASAN_FREE_PAGE); } -#ifdef CONFIG_SLAB /* * Adaptive redzone policy taken from the userspace AddressSanitizer runtime. * For larger allocations larger redzones are used. @@ -357,16 +372,8 @@ void kasan_cache_create(struct kmem_cache *cache, size_t *size, unsigned long *flags) { int redzone_adjust; - /* Make sure the adjusted size is still less than - * KMALLOC_MAX_CACHE_SIZE. - * TODO: this check is only useful for SLAB, but not SLUB. We'll need - * to skip it for SLUB when it starts using kasan_cache_create(). - */ - if (*size > KMALLOC_MAX_CACHE_SIZE - - sizeof(struct kasan_alloc_meta) - - sizeof(struct kasan_free_meta)) - return; - *flags |= SLAB_KASAN; + int orig_size = *size; + /* Add alloc meta. */ cache->kasan_info.alloc_meta_offset = *size; *size += sizeof(struct kasan_alloc_meta); @@ -379,14 +386,44 @@ void kasan_cache_create(struct kmem_cache *cache, size_t *size, } redzone_adjust = optimal_redzone(cache->object_size) - (*size - cache->object_size); + if (redzone_adjust > 0) *size += redzone_adjust; - *size = min(KMALLOC_MAX_CACHE_SIZE, - max(*size, - cache->object_size + - optimal_redzone(cache->object_size))); + + *size = min(KMALLOC_MAX_SIZE, max(*size, cache->object_size + + optimal_redzone(cache->object_size))); + + /* + * If the metadata doesn't fit, don't enable KASAN at all. + */ + if (*size <= cache->kasan_info.alloc_meta_offset || + *size <= cache->kasan_info.free_meta_offset) { + cache->kasan_info.alloc_meta_offset = 0; + cache->kasan_info.free_meta_offset = 0; + *size = orig_size; + return; + } + + *flags |= SLAB_KASAN; +} + +void kasan_cache_shrink(struct kmem_cache *cache) +{ + quarantine_remove_cache(cache); +} + +void kasan_cache_destroy(struct kmem_cache *cache) +{ + quarantine_remove_cache(cache); +} + +size_t kasan_metadata_size(struct kmem_cache *cache) +{ + return (cache->kasan_info.alloc_meta_offset ? + sizeof(struct kasan_alloc_meta) : 0) + + (cache->kasan_info.free_meta_offset ? + sizeof(struct kasan_free_meta) : 0); } -#endif void kasan_poison_slab(struct page *page) { @@ -405,16 +442,8 @@ void kasan_poison_object_data(struct kmem_cache *cache, void *object) kasan_poison_shadow(object, round_up(cache->object_size, KASAN_SHADOW_SCALE_SIZE), KASAN_KMALLOC_REDZONE); -#ifdef CONFIG_SLAB - if (cache->flags & SLAB_KASAN) { - struct kasan_alloc_meta *alloc_info = - get_alloc_info(cache, object); - alloc_info->state = KASAN_STATE_INIT; - } -#endif } -#ifdef CONFIG_SLAB static inline int in_irqentry_text(unsigned long ptr) { return (ptr >= (unsigned long)&__irqentry_text_start && @@ -475,14 +504,24 @@ struct kasan_free_meta *get_free_info(struct kmem_cache *cache, BUILD_BUG_ON(sizeof(struct kasan_free_meta) > 32); return (void *)object + cache->kasan_info.free_meta_offset; } -#endif + +void kasan_init_slab_obj(struct kmem_cache *cache, const void *object) +{ + struct kasan_alloc_meta *alloc_info; + + if (!(cache->flags & SLAB_KASAN)) + return; + + alloc_info = get_alloc_info(cache, object); + __memset(alloc_info, 0, sizeof(*alloc_info)); +} void kasan_slab_alloc(struct kmem_cache *cache, void *object, gfp_t flags) { kasan_kmalloc(cache, object, cache->object_size, flags); } -void kasan_slab_free(struct kmem_cache *cache, void *object) +static void kasan_poison_slab_free(struct kmem_cache *cache, void *object) { unsigned long size = cache->object_size; unsigned long rounded_up_size = round_up(size, KASAN_SHADOW_SCALE_SIZE); @@ -491,18 +530,31 @@ void kasan_slab_free(struct kmem_cache *cache, void *object) if (unlikely(cache->flags & SLAB_DESTROY_BY_RCU)) return; -#ifdef CONFIG_SLAB - if (cache->flags & SLAB_KASAN) { - struct kasan_free_meta *free_info = - get_free_info(cache, object); - struct kasan_alloc_meta *alloc_info = - get_alloc_info(cache, object); - alloc_info->state = KASAN_STATE_FREE; - set_track(&free_info->track); + kasan_poison_shadow(object, rounded_up_size, KASAN_KMALLOC_FREE); +} + +bool kasan_slab_free(struct kmem_cache *cache, void *object) +{ + s8 shadow_byte; + + /* RCU slabs could be legally used after free within the RCU period */ + if (unlikely(cache->flags & SLAB_DESTROY_BY_RCU)) + return false; + + shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(object)); + if (shadow_byte < 0 || shadow_byte >= KASAN_SHADOW_SCALE_SIZE) { + kasan_report_double_free(cache, object, shadow_byte); + return true; } -#endif - kasan_poison_shadow(object, rounded_up_size, KASAN_KMALLOC_FREE); + kasan_poison_slab_free(cache, object); + + if (unlikely(!(cache->flags & SLAB_KASAN))) + return false; + + set_track(&get_alloc_info(cache, object)->free_track, GFP_NOWAIT); + quarantine_put(get_free_info(cache, object), cache); + return true; } void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size, @@ -511,6 +563,9 @@ void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size, unsigned long redzone_start; unsigned long redzone_end; + if (gfpflags_allow_blocking(flags)) + quarantine_reduce(); + if (unlikely(object == NULL)) return; @@ -522,16 +577,9 @@ void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size, kasan_unpoison_shadow(object, size); kasan_poison_shadow((void *)redzone_start, redzone_end - redzone_start, KASAN_KMALLOC_REDZONE); -#ifdef CONFIG_SLAB - if (cache->flags & SLAB_KASAN) { - struct kasan_alloc_meta *alloc_info = - get_alloc_info(cache, object); - - alloc_info->state = KASAN_STATE_ALLOC; - alloc_info->alloc_size = size; - set_track(&alloc_info->track, flags); - } -#endif + + if (cache->flags & SLAB_KASAN) + set_track(&get_alloc_info(cache, object)->alloc_track, flags); } EXPORT_SYMBOL(kasan_kmalloc); @@ -541,6 +589,9 @@ void kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags) unsigned long redzone_start; unsigned long redzone_end; + if (gfpflags_allow_blocking(flags)) + quarantine_reduce(); + if (unlikely(ptr == NULL)) return; @@ -569,7 +620,7 @@ void kasan_krealloc(const void *object, size_t size, gfp_t flags) kasan_kmalloc(page->slab_cache, object, size, flags); } -void kasan_kfree(void *ptr) +void kasan_poison_kfree(void *ptr) { struct page *page; @@ -579,7 +630,7 @@ void kasan_kfree(void *ptr) kasan_poison_shadow(ptr, PAGE_SIZE << compound_order(page), KASAN_FREE_PAGE); else - kasan_slab_free(page->slab_cache, ptr); + kasan_poison_slab_free(page->slab_cache, ptr); } void kasan_kfree_large(const void *ptr) @@ -649,22 +700,22 @@ void __asan_unregister_globals(struct kasan_global *globals, size_t size) } EXPORT_SYMBOL(__asan_unregister_globals); -#define DEFINE_ASAN_LOAD_STORE(size) \ - void __asan_load##size(unsigned long addr) \ - { \ - check_memory_region(addr, size, false); \ - } \ - EXPORT_SYMBOL(__asan_load##size); \ - __alias(__asan_load##size) \ - void __asan_load##size##_noabort(unsigned long); \ - EXPORT_SYMBOL(__asan_load##size##_noabort); \ - void __asan_store##size(unsigned long addr) \ - { \ - check_memory_region(addr, size, true); \ - } \ - EXPORT_SYMBOL(__asan_store##size); \ - __alias(__asan_store##size) \ - void __asan_store##size##_noabort(unsigned long); \ +#define DEFINE_ASAN_LOAD_STORE(size) \ + void __asan_load##size(unsigned long addr) \ + { \ + check_memory_region_inline(addr, size, false, _RET_IP_);\ + } \ + EXPORT_SYMBOL(__asan_load##size); \ + __alias(__asan_load##size) \ + void __asan_load##size##_noabort(unsigned long); \ + EXPORT_SYMBOL(__asan_load##size##_noabort); \ + void __asan_store##size(unsigned long addr) \ + { \ + check_memory_region_inline(addr, size, true, _RET_IP_); \ + } \ + EXPORT_SYMBOL(__asan_store##size); \ + __alias(__asan_store##size) \ + void __asan_store##size##_noabort(unsigned long); \ EXPORT_SYMBOL(__asan_store##size##_noabort) DEFINE_ASAN_LOAD_STORE(1); @@ -675,7 +726,7 @@ DEFINE_ASAN_LOAD_STORE(16); void __asan_loadN(unsigned long addr, size_t size) { - check_memory_region(addr, size, false); + check_memory_region(addr, size, false, _RET_IP_); } EXPORT_SYMBOL(__asan_loadN); @@ -685,7 +736,7 @@ EXPORT_SYMBOL(__asan_loadN_noabort); void __asan_storeN(unsigned long addr, size_t size) { - check_memory_region(addr, size, true); + check_memory_region(addr, size, true, _RET_IP_); } EXPORT_SYMBOL(__asan_storeN); @@ -706,8 +757,8 @@ static int kasan_mem_notifier(struct notifier_block *nb, static int __init kasan_memhotplug_init(void) { - pr_err("WARNING: KASAN doesn't support memory hot-add\n"); - pr_err("Memory hot-add will be disabled\n"); + pr_info("WARNING: KASAN doesn't support memory hot-add\n"); + pr_info("Memory hot-add will be disabled\n"); hotplug_memory_notifier(kasan_mem_notifier, 0); diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 30a2f0ba0e09..e5c2181fee6f 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -59,12 +59,6 @@ struct kasan_global { * Structures to keep alloc and free tracks * */ -enum kasan_state { - KASAN_STATE_INIT, - KASAN_STATE_ALLOC, - KASAN_STATE_FREE -}; - #define KASAN_STACK_DEPTH 64 struct kasan_track { @@ -73,16 +67,18 @@ struct kasan_track { }; struct kasan_alloc_meta { - struct kasan_track track; - u32 state : 2; /* enum kasan_state */ - u32 alloc_size : 30; - u32 reserved; + struct kasan_track alloc_track; + struct kasan_track free_track; }; +struct qlist_node { + struct qlist_node *next; +}; struct kasan_free_meta { - /* Allocator freelist pointer, unused by KASAN. */ - void **freelist; - struct kasan_track track; + /* This field is used while the object is in the quarantine. + * Otherwise it might be used for the allocator freelist. + */ + struct qlist_node quarantine_link; }; struct kasan_alloc_meta *get_alloc_info(struct kmem_cache *cache, @@ -90,7 +86,6 @@ struct kasan_alloc_meta *get_alloc_info(struct kmem_cache *cache, struct kasan_free_meta *get_free_info(struct kmem_cache *cache, const void *object); - static inline const void *kasan_shadow_to_mem(const void *shadow_addr) { return (void *)(((unsigned long)shadow_addr - KASAN_SHADOW_OFFSET) @@ -104,5 +99,18 @@ static inline bool kasan_report_enabled(void) void kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip); +void kasan_report_double_free(struct kmem_cache *cache, void *object, + s8 shadow); + +#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB) +void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache); +void quarantine_reduce(void); +void quarantine_remove_cache(struct kmem_cache *cache); +#else +static inline void quarantine_put(struct kasan_free_meta *info, + struct kmem_cache *cache) { } +static inline void quarantine_reduce(void) { } +static inline void quarantine_remove_cache(struct kmem_cache *cache) { } +#endif #endif diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c new file mode 100644 index 000000000000..b6728a33a4ac --- /dev/null +++ b/mm/kasan/quarantine.c @@ -0,0 +1,291 @@ +/* + * KASAN quarantine. + * + * Author: Alexander Potapenko <glider@google.com> + * Copyright (C) 2016 Google, Inc. + * + * Based on code by Dmitry Chernenkov. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + */ + +#include <linux/gfp.h> +#include <linux/hash.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/percpu.h> +#include <linux/printk.h> +#include <linux/shrinker.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/types.h> + +#include "../slab.h" +#include "kasan.h" + +/* Data structure and operations for quarantine queues. */ + +/* + * Each queue is a signle-linked list, which also stores the total size of + * objects inside of it. + */ +struct qlist_head { + struct qlist_node *head; + struct qlist_node *tail; + size_t bytes; +}; + +#define QLIST_INIT { NULL, NULL, 0 } + +static bool qlist_empty(struct qlist_head *q) +{ + return !q->head; +} + +static void qlist_init(struct qlist_head *q) +{ + q->head = q->tail = NULL; + q->bytes = 0; +} + +static void qlist_put(struct qlist_head *q, struct qlist_node *qlink, + size_t size) +{ + if (unlikely(qlist_empty(q))) + q->head = qlink; + else + q->tail->next = qlink; + q->tail = qlink; + qlink->next = NULL; + q->bytes += size; +} + +static void qlist_move_all(struct qlist_head *from, struct qlist_head *to) +{ + if (unlikely(qlist_empty(from))) + return; + + if (qlist_empty(to)) { + *to = *from; + qlist_init(from); + return; + } + + to->tail->next = from->head; + to->tail = from->tail; + to->bytes += from->bytes; + + qlist_init(from); +} + +static void qlist_move(struct qlist_head *from, struct qlist_node *last, + struct qlist_head *to, size_t size) +{ + if (unlikely(last == from->tail)) { + qlist_move_all(from, to); + return; + } + if (qlist_empty(to)) + to->head = from->head; + else + to->tail->next = from->head; + to->tail = last; + from->head = last->next; + last->next = NULL; + from->bytes -= size; + to->bytes += size; +} + + +/* + * The object quarantine consists of per-cpu queues and a global queue, + * guarded by quarantine_lock. + */ +static DEFINE_PER_CPU(struct qlist_head, cpu_quarantine); + +static struct qlist_head global_quarantine; +static DEFINE_SPINLOCK(quarantine_lock); + +/* Maximum size of the global queue. */ +static unsigned long quarantine_size; + +/* + * The fraction of physical memory the quarantine is allowed to occupy. + * Quarantine doesn't support memory shrinker with SLAB allocator, so we keep + * the ratio low to avoid OOM. + */ +#define QUARANTINE_FRACTION 32 + +#define QUARANTINE_LOW_SIZE (READ_ONCE(quarantine_size) * 3 / 4) +#define QUARANTINE_PERCPU_SIZE (1 << 20) + +static struct kmem_cache *qlink_to_cache(struct qlist_node *qlink) +{ + return virt_to_head_page(qlink)->slab_cache; +} + +static void *qlink_to_object(struct qlist_node *qlink, struct kmem_cache *cache) +{ + struct kasan_free_meta *free_info = + container_of(qlink, struct kasan_free_meta, + quarantine_link); + + return ((void *)free_info) - cache->kasan_info.free_meta_offset; +} + +static void qlink_free(struct qlist_node *qlink, struct kmem_cache *cache) +{ + void *object = qlink_to_object(qlink, cache); + unsigned long flags; + + if (IS_ENABLED(CONFIG_SLAB)) + local_irq_save(flags); + + ___cache_free(cache, object, _THIS_IP_); + + if (IS_ENABLED(CONFIG_SLAB)) + local_irq_restore(flags); +} + +static void qlist_free_all(struct qlist_head *q, struct kmem_cache *cache) +{ + struct qlist_node *qlink; + + if (unlikely(qlist_empty(q))) + return; + + qlink = q->head; + while (qlink) { + struct kmem_cache *obj_cache = + cache ? cache : qlink_to_cache(qlink); + struct qlist_node *next = qlink->next; + + qlink_free(qlink, obj_cache); + qlink = next; + } + qlist_init(q); +} + +void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) +{ + unsigned long flags; + struct qlist_head *q; + struct qlist_head temp = QLIST_INIT; + + local_irq_save(flags); + + q = this_cpu_ptr(&cpu_quarantine); + qlist_put(q, &info->quarantine_link, cache->size); + if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) + qlist_move_all(q, &temp); + + local_irq_restore(flags); + + if (unlikely(!qlist_empty(&temp))) { + spin_lock_irqsave(&quarantine_lock, flags); + qlist_move_all(&temp, &global_quarantine); + spin_unlock_irqrestore(&quarantine_lock, flags); + } +} + +void quarantine_reduce(void) +{ + size_t new_quarantine_size, percpu_quarantines; + unsigned long flags; + struct qlist_head to_free = QLIST_INIT; + size_t size_to_free = 0; + struct qlist_node *last; + + if (likely(READ_ONCE(global_quarantine.bytes) <= + READ_ONCE(quarantine_size))) + return; + + spin_lock_irqsave(&quarantine_lock, flags); + + /* + * Update quarantine size in case of hotplug. Allocate a fraction of + * the installed memory to quarantine minus per-cpu queue limits. + */ + new_quarantine_size = (READ_ONCE(totalram_pages) << PAGE_SHIFT) / + QUARANTINE_FRACTION; + percpu_quarantines = QUARANTINE_PERCPU_SIZE * num_online_cpus(); + if (WARN_ONCE(new_quarantine_size < percpu_quarantines, + "Too little memory, disabling global KASAN quarantine.\n")) + new_quarantine_size = 0; + else + new_quarantine_size -= percpu_quarantines; + WRITE_ONCE(quarantine_size, new_quarantine_size); + + last = global_quarantine.head; + while (last) { + struct kmem_cache *cache = qlink_to_cache(last); + + size_to_free += cache->size; + if (!last->next || size_to_free > + global_quarantine.bytes - QUARANTINE_LOW_SIZE) + break; + last = last->next; + } + qlist_move(&global_quarantine, last, &to_free, size_to_free); + + spin_unlock_irqrestore(&quarantine_lock, flags); + + qlist_free_all(&to_free, NULL); +} + +static void qlist_move_cache(struct qlist_head *from, + struct qlist_head *to, + struct kmem_cache *cache) +{ + struct qlist_node *curr; + + if (unlikely(qlist_empty(from))) + return; + + curr = from->head; + qlist_init(from); + while (curr) { + struct qlist_node *next = curr->next; + struct kmem_cache *obj_cache = qlink_to_cache(curr); + + if (obj_cache == cache) + qlist_put(to, curr, obj_cache->size); + else + qlist_put(from, curr, obj_cache->size); + + curr = next; + } +} + +static void per_cpu_remove_cache(void *arg) +{ + struct kmem_cache *cache = arg; + struct qlist_head to_free = QLIST_INIT; + struct qlist_head *q; + + q = this_cpu_ptr(&cpu_quarantine); + qlist_move_cache(q, &to_free, cache); + qlist_free_all(&to_free, cache); +} + +void quarantine_remove_cache(struct kmem_cache *cache) +{ + unsigned long flags; + struct qlist_head to_free = QLIST_INIT; + + on_each_cpu(per_cpu_remove_cache, cache, 1); + + spin_lock_irqsave(&quarantine_lock, flags); + qlist_move_cache(&global_quarantine, &to_free, cache); + spin_unlock_irqrestore(&quarantine_lock, flags); + + qlist_free_all(&to_free, cache); +} diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 60869a5a0124..24c1211fe9d5 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -116,7 +116,26 @@ static inline bool init_task_stack_addr(const void *addr) sizeof(init_thread_union.stack)); } -#ifdef CONFIG_SLAB +static DEFINE_SPINLOCK(report_lock); + +static void kasan_start_report(unsigned long *flags) +{ + /* + * Make sure we don't end up in loop. + */ + kasan_disable_current(); + spin_lock_irqsave(&report_lock, *flags); + pr_err("==================================================================\n"); +} + +static void kasan_end_report(unsigned long *flags) +{ + pr_err("==================================================================\n"); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); + spin_unlock_irqrestore(&report_lock, *flags); + kasan_enable_current(); +} + static void print_track(struct kasan_track *track) { pr_err("PID = %u\n", track->pid); @@ -130,38 +149,34 @@ static void print_track(struct kasan_track *track) } } -static void object_err(struct kmem_cache *cache, struct page *page, - void *object, char *unused_reason) +static void kasan_object_err(struct kmem_cache *cache, void *object) { struct kasan_alloc_meta *alloc_info = get_alloc_info(cache, object); - struct kasan_free_meta *free_info; dump_stack(); - pr_err("Object at %p, in cache %s\n", object, cache->name); + pr_err("Object at %p, in cache %s size: %d\n", object, cache->name, + cache->object_size); + if (!(cache->flags & SLAB_KASAN)) return; - switch (alloc_info->state) { - case KASAN_STATE_INIT: - pr_err("Object not allocated yet\n"); - break; - case KASAN_STATE_ALLOC: - pr_err("Object allocated with size %u bytes.\n", - alloc_info->alloc_size); - pr_err("Allocation:\n"); - print_track(&alloc_info->track); - break; - case KASAN_STATE_FREE: - pr_err("Object freed, allocated with size %u bytes\n", - alloc_info->alloc_size); - free_info = get_free_info(cache, object); - pr_err("Allocation:\n"); - print_track(&alloc_info->track); - pr_err("Deallocation:\n"); - print_track(&free_info->track); - break; - } + + pr_err("Allocated:\n"); + print_track(&alloc_info->alloc_track); + pr_err("Freed:\n"); + print_track(&alloc_info->free_track); +} + +void kasan_report_double_free(struct kmem_cache *cache, void *object, + s8 shadow) +{ + unsigned long flags; + + kasan_start_report(&flags); + pr_err("BUG: Double free or freeing an invalid pointer\n"); + pr_err("Unexpected shadow byte: 0x%hhX\n", shadow); + kasan_object_err(cache, object); + kasan_end_report(&flags); } -#endif static void print_address_description(struct kasan_access_info *info) { @@ -176,8 +191,7 @@ static void print_address_description(struct kasan_access_info *info) struct kmem_cache *cache = page->slab_cache; object = nearest_obj(cache, page, (void *)info->access_addr); - object_err(cache, page, object, - "kasan: bad access detected"); + kasan_object_err(cache, object); return; } dump_page(page, "kasan: bad access detected"); @@ -242,19 +256,13 @@ static void print_shadow_for_address(const void *addr) } } -static DEFINE_SPINLOCK(report_lock); - static void kasan_report_error(struct kasan_access_info *info) { unsigned long flags; const char *bug_type; - /* - * Make sure we don't end up in loop. - */ - kasan_disable_current(); - spin_lock_irqsave(&report_lock, flags); - pr_err("==================================================================\n"); + kasan_start_report(&flags); + if (info->access_addr < kasan_shadow_to_mem((void *)KASAN_SHADOW_START)) { if ((unsigned long)info->access_addr < PAGE_SIZE) @@ -275,10 +283,8 @@ static void kasan_report_error(struct kasan_access_info *info) print_address_description(info); print_shadow_for_address(info->first_bad_addr); } - pr_err("==================================================================\n"); - add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); - spin_unlock_irqrestore(&report_lock, flags); - kasan_enable_current(); + + kasan_end_report(&flags); } void kasan_report(unsigned long addr, size_t size, diff --git a/mm/khugepaged.c b/mm/khugepaged.c new file mode 100644 index 000000000000..79c52d0061af --- /dev/null +++ b/mm/khugepaged.c @@ -0,0 +1,1922 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/mm.h> +#include <linux/sched.h> +#include <linux/mmu_notifier.h> +#include <linux/rmap.h> +#include <linux/swap.h> +#include <linux/mm_inline.h> +#include <linux/kthread.h> +#include <linux/khugepaged.h> +#include <linux/freezer.h> +#include <linux/mman.h> +#include <linux/hashtable.h> +#include <linux/userfaultfd_k.h> +#include <linux/page_idle.h> +#include <linux/swapops.h> +#include <linux/shmem_fs.h> + +#include <asm/tlb.h> +#include <asm/pgalloc.h> +#include "internal.h" + +enum scan_result { + SCAN_FAIL, + SCAN_SUCCEED, + SCAN_PMD_NULL, + SCAN_EXCEED_NONE_PTE, + SCAN_PTE_NON_PRESENT, + SCAN_PAGE_RO, + SCAN_LACK_REFERENCED_PAGE, + SCAN_PAGE_NULL, + SCAN_SCAN_ABORT, + SCAN_PAGE_COUNT, + SCAN_PAGE_LRU, + SCAN_PAGE_LOCK, + SCAN_PAGE_ANON, + SCAN_PAGE_COMPOUND, + SCAN_ANY_PROCESS, + SCAN_VMA_NULL, + SCAN_VMA_CHECK, + SCAN_ADDRESS_RANGE, + SCAN_SWAP_CACHE_PAGE, + SCAN_DEL_PAGE_LRU, + SCAN_ALLOC_HUGE_PAGE_FAIL, + SCAN_CGROUP_CHARGE_FAIL, + SCAN_EXCEED_SWAP_PTE, + SCAN_TRUNCATED, +}; + +#define CREATE_TRACE_POINTS +#include <trace/events/huge_memory.h> + +/* default scan 8*512 pte (or vmas) every 30 second */ +static unsigned int khugepaged_pages_to_scan __read_mostly; +static unsigned int khugepaged_pages_collapsed; +static unsigned int khugepaged_full_scans; +static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000; +/* during fragmentation poll the hugepage allocator once every minute */ +static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000; +static unsigned long khugepaged_sleep_expire; +static DEFINE_SPINLOCK(khugepaged_mm_lock); +static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); +/* + * default collapse hugepages if there is at least one pte mapped like + * it would have happened if the vma was large enough during page + * fault. + */ +static unsigned int khugepaged_max_ptes_none __read_mostly; +static unsigned int khugepaged_max_ptes_swap __read_mostly; + +#define MM_SLOTS_HASH_BITS 10 +static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); + +static struct kmem_cache *mm_slot_cache __read_mostly; + +/** + * struct mm_slot - hash lookup from mm to mm_slot + * @hash: hash collision list + * @mm_node: khugepaged scan list headed in khugepaged_scan.mm_head + * @mm: the mm that this information is valid for + */ +struct mm_slot { + struct hlist_node hash; + struct list_head mm_node; + struct mm_struct *mm; +}; + +/** + * struct khugepaged_scan - cursor for scanning + * @mm_head: the head of the mm list to scan + * @mm_slot: the current mm_slot we are scanning + * @address: the next address inside that to be scanned + * + * There is only the one khugepaged_scan instance of this cursor structure. + */ +struct khugepaged_scan { + struct list_head mm_head; + struct mm_slot *mm_slot; + unsigned long address; +}; + +static struct khugepaged_scan khugepaged_scan = { + .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), +}; + +static ssize_t scan_sleep_millisecs_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_scan_sleep_millisecs); +} + +static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long msecs; + int err; + + err = kstrtoul(buf, 10, &msecs); + if (err || msecs > UINT_MAX) + return -EINVAL; + + khugepaged_scan_sleep_millisecs = msecs; + khugepaged_sleep_expire = 0; + wake_up_interruptible(&khugepaged_wait); + + return count; +} +static struct kobj_attribute scan_sleep_millisecs_attr = + __ATTR(scan_sleep_millisecs, 0644, scan_sleep_millisecs_show, + scan_sleep_millisecs_store); + +static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_alloc_sleep_millisecs); +} + +static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long msecs; + int err; + + err = kstrtoul(buf, 10, &msecs); + if (err || msecs > UINT_MAX) + return -EINVAL; + + khugepaged_alloc_sleep_millisecs = msecs; + khugepaged_sleep_expire = 0; + wake_up_interruptible(&khugepaged_wait); + + return count; +} +static struct kobj_attribute alloc_sleep_millisecs_attr = + __ATTR(alloc_sleep_millisecs, 0644, alloc_sleep_millisecs_show, + alloc_sleep_millisecs_store); + +static ssize_t pages_to_scan_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_pages_to_scan); +} +static ssize_t pages_to_scan_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long pages; + + err = kstrtoul(buf, 10, &pages); + if (err || !pages || pages > UINT_MAX) + return -EINVAL; + + khugepaged_pages_to_scan = pages; + + return count; +} +static struct kobj_attribute pages_to_scan_attr = + __ATTR(pages_to_scan, 0644, pages_to_scan_show, + pages_to_scan_store); + +static ssize_t pages_collapsed_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_pages_collapsed); +} +static struct kobj_attribute pages_collapsed_attr = + __ATTR_RO(pages_collapsed); + +static ssize_t full_scans_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_full_scans); +} +static struct kobj_attribute full_scans_attr = + __ATTR_RO(full_scans); + +static ssize_t khugepaged_defrag_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return single_hugepage_flag_show(kobj, attr, buf, + TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); +} +static ssize_t khugepaged_defrag_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + return single_hugepage_flag_store(kobj, attr, buf, count, + TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); +} +static struct kobj_attribute khugepaged_defrag_attr = + __ATTR(defrag, 0644, khugepaged_defrag_show, + khugepaged_defrag_store); + +/* + * max_ptes_none controls if khugepaged should collapse hugepages over + * any unmapped ptes in turn potentially increasing the memory + * footprint of the vmas. When max_ptes_none is 0 khugepaged will not + * reduce the available free memory in the system as it + * runs. Increasing max_ptes_none will instead potentially reduce the + * free memory in the system during the khugepaged scan. + */ +static ssize_t khugepaged_max_ptes_none_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_max_ptes_none); +} +static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long max_ptes_none; + + err = kstrtoul(buf, 10, &max_ptes_none); + if (err || max_ptes_none > HPAGE_PMD_NR-1) + return -EINVAL; + + khugepaged_max_ptes_none = max_ptes_none; + + return count; +} +static struct kobj_attribute khugepaged_max_ptes_none_attr = + __ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show, + khugepaged_max_ptes_none_store); + +static ssize_t khugepaged_max_ptes_swap_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_max_ptes_swap); +} + +static ssize_t khugepaged_max_ptes_swap_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long max_ptes_swap; + + err = kstrtoul(buf, 10, &max_ptes_swap); + if (err || max_ptes_swap > HPAGE_PMD_NR-1) + return -EINVAL; + + khugepaged_max_ptes_swap = max_ptes_swap; + + return count; +} + +static struct kobj_attribute khugepaged_max_ptes_swap_attr = + __ATTR(max_ptes_swap, 0644, khugepaged_max_ptes_swap_show, + khugepaged_max_ptes_swap_store); + +static struct attribute *khugepaged_attr[] = { + &khugepaged_defrag_attr.attr, + &khugepaged_max_ptes_none_attr.attr, + &pages_to_scan_attr.attr, + &pages_collapsed_attr.attr, + &full_scans_attr.attr, + &scan_sleep_millisecs_attr.attr, + &alloc_sleep_millisecs_attr.attr, + &khugepaged_max_ptes_swap_attr.attr, + NULL, +}; + +struct attribute_group khugepaged_attr_group = { + .attrs = khugepaged_attr, + .name = "khugepaged", +}; + +#define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB) + +int hugepage_madvise(struct vm_area_struct *vma, + unsigned long *vm_flags, int advice) +{ + switch (advice) { + case MADV_HUGEPAGE: +#ifdef CONFIG_S390 + /* + * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390 + * can't handle this properly after s390_enable_sie, so we simply + * ignore the madvise to prevent qemu from causing a SIGSEGV. + */ + if (mm_has_pgste(vma->vm_mm)) + return 0; +#endif + *vm_flags &= ~VM_NOHUGEPAGE; + *vm_flags |= VM_HUGEPAGE; + /* + * If the vma become good for khugepaged to scan, + * register it here without waiting a page fault that + * may not happen any time soon. + */ + if (!(*vm_flags & VM_NO_KHUGEPAGED) && + khugepaged_enter_vma_merge(vma, *vm_flags)) + return -ENOMEM; + break; + case MADV_NOHUGEPAGE: + *vm_flags &= ~VM_HUGEPAGE; + *vm_flags |= VM_NOHUGEPAGE; + /* + * Setting VM_NOHUGEPAGE will prevent khugepaged from scanning + * this vma even if we leave the mm registered in khugepaged if + * it got registered before VM_NOHUGEPAGE was set. + */ + break; + } + + return 0; +} + +int __init khugepaged_init(void) +{ + mm_slot_cache = kmem_cache_create("khugepaged_mm_slot", + sizeof(struct mm_slot), + __alignof__(struct mm_slot), 0, NULL); + if (!mm_slot_cache) + return -ENOMEM; + + khugepaged_pages_to_scan = HPAGE_PMD_NR * 8; + khugepaged_max_ptes_none = HPAGE_PMD_NR - 1; + khugepaged_max_ptes_swap = HPAGE_PMD_NR / 8; + + return 0; +} + +void __init khugepaged_destroy(void) +{ + kmem_cache_destroy(mm_slot_cache); +} + +static inline struct mm_slot *alloc_mm_slot(void) +{ + if (!mm_slot_cache) /* initialization failed */ + return NULL; + return kmem_cache_zalloc(mm_slot_cache, GFP_KERNEL); +} + +static inline void free_mm_slot(struct mm_slot *mm_slot) +{ + kmem_cache_free(mm_slot_cache, mm_slot); +} + +static struct mm_slot *get_mm_slot(struct mm_struct *mm) +{ + struct mm_slot *mm_slot; + + hash_for_each_possible(mm_slots_hash, mm_slot, hash, (unsigned long)mm) + if (mm == mm_slot->mm) + return mm_slot; + + return NULL; +} + +static void insert_to_mm_slots_hash(struct mm_struct *mm, + struct mm_slot *mm_slot) +{ + mm_slot->mm = mm; + hash_add(mm_slots_hash, &mm_slot->hash, (long)mm); +} + +static inline int khugepaged_test_exit(struct mm_struct *mm) +{ + return atomic_read(&mm->mm_users) == 0; +} + +int __khugepaged_enter(struct mm_struct *mm) +{ + struct mm_slot *mm_slot; + int wakeup; + + mm_slot = alloc_mm_slot(); + if (!mm_slot) + return -ENOMEM; + + /* __khugepaged_exit() must not run from under us */ + 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; + } + + spin_lock(&khugepaged_mm_lock); + insert_to_mm_slots_hash(mm, mm_slot); + /* + * Insert just behind the scanning cursor, to let the area settle + * down a little. + */ + wakeup = list_empty(&khugepaged_scan.mm_head); + list_add_tail(&mm_slot->mm_node, &khugepaged_scan.mm_head); + spin_unlock(&khugepaged_mm_lock); + + atomic_inc(&mm->mm_count); + if (wakeup) + wake_up_interruptible(&khugepaged_wait); + + return 0; +} + +int khugepaged_enter_vma_merge(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + unsigned long hstart, hend; + if (!vma->anon_vma) + /* + * Not yet faulted in so we will register later in the + * page fault if needed. + */ + return 0; + if (vma->vm_ops || (vm_flags & VM_NO_KHUGEPAGED)) + /* khugepaged not yet working on file or special mappings */ + return 0; + hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; + hend = vma->vm_end & HPAGE_PMD_MASK; + if (hstart < hend) + return khugepaged_enter(vma, vm_flags); + return 0; +} + +void __khugepaged_exit(struct mm_struct *mm) +{ + struct mm_slot *mm_slot; + int free = 0; + + spin_lock(&khugepaged_mm_lock); + mm_slot = get_mm_slot(mm); + if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { + hash_del(&mm_slot->hash); + list_del(&mm_slot->mm_node); + free = 1; + } + spin_unlock(&khugepaged_mm_lock); + + if (free) { + clear_bit(MMF_VM_HUGEPAGE, &mm->flags); + free_mm_slot(mm_slot); + mmdrop(mm); + } else if (mm_slot) { + /* + * This is required to serialize against + * khugepaged_test_exit() (which is guaranteed to run + * under mmap sem read mode). Stop here (after we + * return all pagetables will be destroyed) until + * khugepaged has finished working on the pagetables + * under the mmap_sem. + */ + down_write(&mm->mmap_sem); + up_write(&mm->mmap_sem); + } +} + +static void release_pte_page(struct page *page) +{ + /* 0 stands for page_is_file_cache(page) == false */ + dec_node_page_state(page, NR_ISOLATED_ANON + 0); + unlock_page(page); + putback_lru_page(page); +} + +static void release_pte_pages(pte_t *pte, pte_t *_pte) +{ + while (--_pte >= pte) { + pte_t pteval = *_pte; + if (!pte_none(pteval) && !is_zero_pfn(pte_pfn(pteval))) + release_pte_page(pte_page(pteval)); + } +} + +static int __collapse_huge_page_isolate(struct vm_area_struct *vma, + unsigned long address, + pte_t *pte) +{ + struct page *page = NULL; + pte_t *_pte; + int none_or_zero = 0, result = 0, referenced = 0; + bool writable = false; + + for (_pte = pte; _pte < pte+HPAGE_PMD_NR; + _pte++, address += PAGE_SIZE) { + pte_t pteval = *_pte; + if (pte_none(pteval) || (pte_present(pteval) && + is_zero_pfn(pte_pfn(pteval)))) { + if (!userfaultfd_armed(vma) && + ++none_or_zero <= khugepaged_max_ptes_none) { + continue; + } else { + result = SCAN_EXCEED_NONE_PTE; + goto out; + } + } + if (!pte_present(pteval)) { + result = SCAN_PTE_NON_PRESENT; + goto out; + } + page = vm_normal_page(vma, address, pteval); + if (unlikely(!page)) { + result = SCAN_PAGE_NULL; + goto out; + } + + VM_BUG_ON_PAGE(PageCompound(page), page); + VM_BUG_ON_PAGE(!PageAnon(page), page); + VM_BUG_ON_PAGE(!PageSwapBacked(page), page); + + /* + * We can do it before isolate_lru_page because the + * page can't be freed from under us. NOTE: PG_lock + * is needed to serialize against split_huge_page + * when invoked from the VM. + */ + if (!trylock_page(page)) { + result = SCAN_PAGE_LOCK; + goto out; + } + + /* + * cannot use mapcount: can't collapse if there's a gup pin. + * The page must only be referenced by the scanned process + * and page swap cache. + */ + if (page_count(page) != 1 + !!PageSwapCache(page)) { + unlock_page(page); + result = SCAN_PAGE_COUNT; + goto out; + } + if (pte_write(pteval)) { + writable = true; + } else { + if (PageSwapCache(page) && + !reuse_swap_page(page, NULL)) { + unlock_page(page); + result = SCAN_SWAP_CACHE_PAGE; + goto out; + } + /* + * Page is not in the swap cache. It can be collapsed + * into a THP. + */ + } + + /* + * Isolate the page to avoid collapsing an hugepage + * currently in use by the VM. + */ + if (isolate_lru_page(page)) { + unlock_page(page); + result = SCAN_DEL_PAGE_LRU; + goto out; + } + /* 0 stands for page_is_file_cache(page) == false */ + inc_node_page_state(page, NR_ISOLATED_ANON + 0); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageLRU(page), page); + + /* There should be enough young pte to collapse the page */ + if (pte_young(pteval) || + page_is_young(page) || PageReferenced(page) || + mmu_notifier_test_young(vma->vm_mm, address)) + referenced++; + } + 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 { + result = SCAN_PAGE_RO; + } + +out: + release_pte_pages(pte, _pte); + trace_mm_collapse_huge_page_isolate(page, none_or_zero, + referenced, writable, result); + return 0; +} + +static void __collapse_huge_page_copy(pte_t *pte, struct page *page, + struct vm_area_struct *vma, + unsigned long address, + spinlock_t *ptl) +{ + pte_t *_pte; + for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++) { + pte_t pteval = *_pte; + struct page *src_page; + + if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { + clear_user_highpage(page, address); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); + if (is_zero_pfn(pte_pfn(pteval))) { + /* + * ptl mostly unnecessary. + */ + spin_lock(ptl); + /* + * paravirt calls inside pte_clear here are + * superfluous. + */ + pte_clear(vma->vm_mm, address, _pte); + spin_unlock(ptl); + } + } else { + src_page = pte_page(pteval); + copy_user_highpage(page, src_page, address, vma); + VM_BUG_ON_PAGE(page_mapcount(src_page) != 1, src_page); + release_pte_page(src_page); + /* + * ptl mostly unnecessary, but preempt has to + * be disabled to update the per-cpu stats + * inside page_remove_rmap(). + */ + spin_lock(ptl); + /* + * paravirt calls inside pte_clear here are + * superfluous. + */ + pte_clear(vma->vm_mm, address, _pte); + page_remove_rmap(src_page, false); + spin_unlock(ptl); + free_page_and_swap_cache(src_page); + } + + address += PAGE_SIZE; + page++; + } +} + +static void khugepaged_alloc_sleep(void) +{ + DEFINE_WAIT(wait); + + add_wait_queue(&khugepaged_wait, &wait); + freezable_schedule_timeout_interruptible( + msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); + remove_wait_queue(&khugepaged_wait, &wait); +} + +static int khugepaged_node_load[MAX_NUMNODES]; + +static bool khugepaged_scan_abort(int nid) +{ + int i; + + /* + * If node_reclaim_mode is disabled, then no extra effort is made to + * allocate memory locally. + */ + if (!node_reclaim_mode) + return false; + + /* If there is a count for this node already, it must be acceptable */ + if (khugepaged_node_load[nid]) + return false; + + for (i = 0; i < MAX_NUMNODES; i++) { + if (!khugepaged_node_load[i]) + continue; + if (node_distance(nid, i) > RECLAIM_DISTANCE) + return true; + } + return false; +} + +/* Defrag for khugepaged will enter direct reclaim/compaction if necessary */ +static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void) +{ + return khugepaged_defrag() ? GFP_TRANSHUGE : GFP_TRANSHUGE_LIGHT; +} + +#ifdef CONFIG_NUMA +static int khugepaged_find_target_node(void) +{ + static int last_khugepaged_target_node = NUMA_NO_NODE; + int nid, target_node = 0, max_value = 0; + + /* find first node with max normal pages hit */ + for (nid = 0; nid < MAX_NUMNODES; nid++) + if (khugepaged_node_load[nid] > max_value) { + max_value = khugepaged_node_load[nid]; + target_node = nid; + } + + /* do some balance if several nodes have the same hit record */ + if (target_node <= last_khugepaged_target_node) + for (nid = last_khugepaged_target_node + 1; nid < MAX_NUMNODES; + nid++) + if (max_value == khugepaged_node_load[nid]) { + target_node = nid; + break; + } + + last_khugepaged_target_node = target_node; + return target_node; +} + +static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) +{ + if (IS_ERR(*hpage)) { + if (!*wait) + return false; + + *wait = false; + *hpage = NULL; + khugepaged_alloc_sleep(); + } else if (*hpage) { + put_page(*hpage); + *hpage = NULL; + } + + return true; +} + +static struct page * +khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node) +{ + VM_BUG_ON_PAGE(*hpage, *hpage); + + *hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER); + if (unlikely(!*hpage)) { + count_vm_event(THP_COLLAPSE_ALLOC_FAILED); + *hpage = ERR_PTR(-ENOMEM); + return NULL; + } + + prep_transhuge_page(*hpage); + count_vm_event(THP_COLLAPSE_ALLOC); + return *hpage; +} +#else +static int khugepaged_find_target_node(void) +{ + return 0; +} + +static inline struct page *alloc_khugepaged_hugepage(void) +{ + struct page *page; + + page = alloc_pages(alloc_hugepage_khugepaged_gfpmask(), + HPAGE_PMD_ORDER); + if (page) + prep_transhuge_page(page); + return page; +} + +static struct page *khugepaged_alloc_hugepage(bool *wait) +{ + struct page *hpage; + + do { + hpage = alloc_khugepaged_hugepage(); + if (!hpage) { + count_vm_event(THP_COLLAPSE_ALLOC_FAILED); + if (!*wait) + return NULL; + + *wait = false; + khugepaged_alloc_sleep(); + } else + count_vm_event(THP_COLLAPSE_ALLOC); + } while (unlikely(!hpage) && likely(khugepaged_enabled())); + + return hpage; +} + +static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) +{ + if (!*hpage) + *hpage = khugepaged_alloc_hugepage(wait); + + if (unlikely(!*hpage)) + return false; + + return true; +} + +static struct page * +khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node) +{ + VM_BUG_ON(!*hpage); + + return *hpage; +} +#endif + +static bool hugepage_vma_check(struct vm_area_struct *vma) +{ + if ((!(vma->vm_flags & VM_HUGEPAGE) && !khugepaged_always()) || + (vma->vm_flags & VM_NOHUGEPAGE)) + return false; + if (shmem_file(vma->vm_file)) { + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) + return false; + return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, + HPAGE_PMD_NR); + } + if (!vma->anon_vma || vma->vm_ops) + return false; + if (is_vma_temporary_stack(vma)) + return false; + return !(vma->vm_flags & VM_NO_KHUGEPAGED); +} + +/* + * If mmap_sem temporarily dropped, revalidate vma + * before taking mmap_sem. + * Return 0 if succeeds, otherwise return none-zero + * value (scan code). + */ + +static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address) +{ + struct vm_area_struct *vma; + unsigned long hstart, hend; + + if (unlikely(khugepaged_test_exit(mm))) + return SCAN_ANY_PROCESS; + + vma = find_vma(mm, address); + if (!vma) + return SCAN_VMA_NULL; + + hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; + hend = vma->vm_end & HPAGE_PMD_MASK; + if (address < hstart || address + HPAGE_PMD_SIZE > hend) + return SCAN_ADDRESS_RANGE; + if (!hugepage_vma_check(vma)) + return SCAN_VMA_CHECK; + return 0; +} + +/* + * Bring missing pages in from swap, to complete THP collapse. + * Only done if khugepaged_scan_pmd believes it is worthwhile. + * + * Called and returns without pte mapped or spinlocks held, + * but with mmap_sem held to protect against vma changes. + */ + +static bool __collapse_huge_page_swapin(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + int referenced) +{ + pte_t pteval; + int swapped_in = 0, ret = 0; + struct fault_env fe = { + .vma = vma, + .address = address, + .flags = FAULT_FLAG_ALLOW_RETRY, + .pmd = pmd, + }; + + fe.pte = pte_offset_map(pmd, address); + for (; fe.address < address + HPAGE_PMD_NR*PAGE_SIZE; + fe.pte++, fe.address += PAGE_SIZE) { + pteval = *fe.pte; + if (!is_swap_pte(pteval)) + continue; + swapped_in++; + /* we only decide to swapin, if there is enough young ptes */ + if (referenced < HPAGE_PMD_NR/2) { + trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); + return false; + } + ret = do_swap_page(&fe, pteval); + + /* do_swap_page returns VM_FAULT_RETRY with released mmap_sem */ + if (ret & VM_FAULT_RETRY) { + down_read(&mm->mmap_sem); + if (hugepage_vma_revalidate(mm, address)) { + /* vma is no longer available, don't continue to swapin */ + trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); + return false; + } + /* check if the pmd is still valid */ + if (mm_find_pmd(mm, address) != pmd) + return false; + } + if (ret & VM_FAULT_ERROR) { + trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); + return false; + } + /* pte is unmapped now, we need to map it */ + fe.pte = pte_offset_map(pmd, fe.address); + } + fe.pte--; + pte_unmap(fe.pte); + trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 1); + return true; +} + +static void collapse_huge_page(struct mm_struct *mm, + unsigned long address, + struct page **hpage, + struct vm_area_struct *vma, + int node, int referenced) +{ + pmd_t *pmd, _pmd; + pte_t *pte; + pgtable_t pgtable; + struct page *new_page; + spinlock_t *pmd_ptl, *pte_ptl; + int isolated = 0, result = 0; + struct mem_cgroup *memcg; + unsigned long mmun_start; /* For mmu_notifiers */ + unsigned long mmun_end; /* For mmu_notifiers */ + gfp_t gfp; + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + + /* Only allocate from the target node */ + gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_OTHER_NODE | __GFP_THISNODE; + + /* + * Before allocating the hugepage, release the mmap_sem read lock. + * The allocation can take potentially a long time if it involves + * sync compaction, and we do not need to hold the mmap_sem during + * that. We will recheck the vma after taking it again in write mode. + */ + up_read(&mm->mmap_sem); + new_page = khugepaged_alloc_page(hpage, gfp, node); + if (!new_page) { + result = SCAN_ALLOC_HUGE_PAGE_FAIL; + goto out_nolock; + } + + if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { + result = SCAN_CGROUP_CHARGE_FAIL; + goto out_nolock; + } + + down_read(&mm->mmap_sem); + result = hugepage_vma_revalidate(mm, address); + if (result) { + mem_cgroup_cancel_charge(new_page, memcg, true); + up_read(&mm->mmap_sem); + goto out_nolock; + } + + pmd = mm_find_pmd(mm, address); + if (!pmd) { + result = SCAN_PMD_NULL; + mem_cgroup_cancel_charge(new_page, memcg, true); + up_read(&mm->mmap_sem); + goto out_nolock; + } + + /* + * __collapse_huge_page_swapin always returns with mmap_sem locked. + * If it fails, we release mmap_sem and jump out_nolock. + * Continuing to collapse causes inconsistency. + */ + if (!__collapse_huge_page_swapin(mm, vma, address, pmd, referenced)) { + mem_cgroup_cancel_charge(new_page, memcg, true); + up_read(&mm->mmap_sem); + goto out_nolock; + } + + up_read(&mm->mmap_sem); + /* + * Prevent all access to pagetables with the exception of + * gup_fast later handled by the ptep_clear_flush and the VM + * handled by the anon_vma lock + PG_lock. + */ + down_write(&mm->mmap_sem); + result = hugepage_vma_revalidate(mm, address); + if (result) + goto out; + /* check if the pmd is still valid */ + if (mm_find_pmd(mm, address) != pmd) + goto out; + + anon_vma_lock_write(vma->anon_vma); + + pte = pte_offset_map(pmd, address); + pte_ptl = pte_lockptr(mm, pmd); + + mmun_start = address; + mmun_end = address + HPAGE_PMD_SIZE; + mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); + pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ + /* + * After this gup_fast can't run anymore. This also removes + * any huge TLB entry from the CPU so we won't allow + * huge and small TLB entries for the same virtual address + * to avoid the risk of CPU bugs in that area. + */ + _pmd = pmdp_collapse_flush(vma, address, pmd); + spin_unlock(pmd_ptl); + mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + + spin_lock(pte_ptl); + isolated = __collapse_huge_page_isolate(vma, address, pte); + spin_unlock(pte_ptl); + + if (unlikely(!isolated)) { + pte_unmap(pte); + spin_lock(pmd_ptl); + BUG_ON(!pmd_none(*pmd)); + /* + * We can only use set_pmd_at when establishing + * hugepmds and never for establishing regular pmds that + * points to regular pagetables. Use pmd_populate for that + */ + pmd_populate(mm, pmd, pmd_pgtable(_pmd)); + spin_unlock(pmd_ptl); + anon_vma_unlock_write(vma->anon_vma); + result = SCAN_FAIL; + goto out; + } + + /* + * All pages are isolated and locked so anon_vma rmap + * can't run anymore. + */ + anon_vma_unlock_write(vma->anon_vma); + + __collapse_huge_page_copy(pte, new_page, vma, address, pte_ptl); + pte_unmap(pte); + __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); + mem_cgroup_commit_charge(new_page, memcg, false, true); + lru_cache_add_active_or_unevictable(new_page, vma); + pgtable_trans_huge_deposit(mm, pmd, pgtable); + set_pmd_at(mm, address, pmd, _pmd); + update_mmu_cache_pmd(vma, address, pmd); + spin_unlock(pmd_ptl); + + *hpage = NULL; + + khugepaged_pages_collapsed++; + result = SCAN_SUCCEED; +out_up_write: + up_write(&mm->mmap_sem); +out_nolock: + trace_mm_collapse_huge_page(mm, isolated, result); + return; +out: + mem_cgroup_cancel_charge(new_page, memcg, true); + goto out_up_write; +} + +static int khugepaged_scan_pmd(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long address, + struct page **hpage) +{ + pmd_t *pmd; + pte_t *pte, *_pte; + int ret = 0, none_or_zero = 0, result = 0, referenced = 0; + struct page *page = NULL; + unsigned long _address; + spinlock_t *ptl; + int node = NUMA_NO_NODE, unmapped = 0; + bool writable = false; + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + + pmd = mm_find_pmd(mm, address); + if (!pmd) { + result = SCAN_PMD_NULL; + goto out; + } + + memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR; + _pte++, _address += PAGE_SIZE) { + pte_t pteval = *_pte; + if (is_swap_pte(pteval)) { + if (++unmapped <= khugepaged_max_ptes_swap) { + continue; + } else { + result = SCAN_EXCEED_SWAP_PTE; + goto out_unmap; + } + } + if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { + if (!userfaultfd_armed(vma) && + ++none_or_zero <= khugepaged_max_ptes_none) { + continue; + } else { + result = SCAN_EXCEED_NONE_PTE; + goto out_unmap; + } + } + if (!pte_present(pteval)) { + result = SCAN_PTE_NON_PRESENT; + goto out_unmap; + } + if (pte_write(pteval)) + writable = true; + + page = vm_normal_page(vma, _address, pteval); + if (unlikely(!page)) { + result = SCAN_PAGE_NULL; + goto out_unmap; + } + + /* TODO: teach khugepaged to collapse THP mapped with pte */ + if (PageCompound(page)) { + result = SCAN_PAGE_COMPOUND; + goto out_unmap; + } + + /* + * Record which node the original page is from and save this + * information to khugepaged_node_load[]. + * Khupaged will allocate hugepage from the node has the max + * hit record. + */ + node = page_to_nid(page); + if (khugepaged_scan_abort(node)) { + result = SCAN_SCAN_ABORT; + goto out_unmap; + } + khugepaged_node_load[node]++; + if (!PageLRU(page)) { + result = SCAN_PAGE_LRU; + goto out_unmap; + } + if (PageLocked(page)) { + result = SCAN_PAGE_LOCK; + goto out_unmap; + } + if (!PageAnon(page)) { + result = SCAN_PAGE_ANON; + goto out_unmap; + } + + /* + * cannot use mapcount: can't collapse if there's a gup pin. + * The page must only be referenced by the scanned process + * and page swap cache. + */ + if (page_count(page) != 1 + !!PageSwapCache(page)) { + result = SCAN_PAGE_COUNT; + goto out_unmap; + } + if (pte_young(pteval) || + page_is_young(page) || PageReferenced(page) || + mmu_notifier_test_young(vma->vm_mm, address)) + referenced++; + } + if (writable) { + if (referenced) { + result = SCAN_SUCCEED; + ret = 1; + } else { + result = SCAN_LACK_REFERENCED_PAGE; + } + } else { + result = SCAN_PAGE_RO; + } +out_unmap: + pte_unmap_unlock(pte, ptl); + if (ret) { + node = khugepaged_find_target_node(); + /* collapse_huge_page will return with the mmap_sem released */ + collapse_huge_page(mm, address, hpage, vma, node, referenced); + } +out: + trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced, + none_or_zero, result, unmapped); + return ret; +} + +static void collect_mm_slot(struct mm_slot *mm_slot) +{ + struct mm_struct *mm = mm_slot->mm; + + VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock)); + + if (khugepaged_test_exit(mm)) { + /* free mm_slot */ + hash_del(&mm_slot->hash); + list_del(&mm_slot->mm_node); + + /* + * Not strictly needed because the mm exited already. + * + * clear_bit(MMF_VM_HUGEPAGE, &mm->flags); + */ + + /* khugepaged_mm_lock actually not necessary for the below */ + free_mm_slot(mm_slot); + mmdrop(mm); + } +} + +#if defined(CONFIG_SHMEM) && defined(CONFIG_TRANSPARENT_HUGE_PAGECACHE) +static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) +{ + struct vm_area_struct *vma; + unsigned long addr; + pmd_t *pmd, _pmd; + + i_mmap_lock_write(mapping); + vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { + /* probably overkill */ + if (vma->anon_vma) + continue; + addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + if (addr & ~HPAGE_PMD_MASK) + continue; + if (vma->vm_end < addr + HPAGE_PMD_SIZE) + continue; + pmd = mm_find_pmd(vma->vm_mm, addr); + if (!pmd) + continue; + /* + * We need exclusive mmap_sem to retract page table. + * If trylock fails we would end up with pte-mapped THP after + * re-fault. Not ideal, but it's more important to not disturb + * the system too much. + */ + if (down_write_trylock(&vma->vm_mm->mmap_sem)) { + spinlock_t *ptl = pmd_lock(vma->vm_mm, pmd); + /* assume page table is clear */ + _pmd = pmdp_collapse_flush(vma, addr, pmd); + spin_unlock(ptl); + up_write(&vma->vm_mm->mmap_sem); + atomic_long_dec(&vma->vm_mm->nr_ptes); + pte_free(vma->vm_mm, pmd_pgtable(_pmd)); + } + } + i_mmap_unlock_write(mapping); +} + +/** + * collapse_shmem - collapse small tmpfs/shmem pages into huge one. + * + * Basic scheme is simple, details are more complex: + * - allocate and freeze a new huge page; + * - scan over radix tree replacing old pages the new one + * + swap in pages if necessary; + * + fill in gaps; + * + keep old pages around in case if rollback is required; + * - if replacing succeed: + * + copy data over; + * + free old pages; + * + unfreeze huge page; + * - if replacing failed; + * + put all pages back and unfreeze them; + * + restore gaps in the radix-tree; + * + free huge page; + */ +static void collapse_shmem(struct mm_struct *mm, + struct address_space *mapping, pgoff_t start, + struct page **hpage, int node) +{ + gfp_t gfp; + struct page *page, *new_page, *tmp; + struct mem_cgroup *memcg; + pgoff_t index, end = start + HPAGE_PMD_NR; + LIST_HEAD(pagelist); + struct radix_tree_iter iter; + void **slot; + int nr_none = 0, result = SCAN_SUCCEED; + + VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); + + /* Only allocate from the target node */ + gfp = alloc_hugepage_khugepaged_gfpmask() | + __GFP_OTHER_NODE | __GFP_THISNODE; + + new_page = khugepaged_alloc_page(hpage, gfp, node); + if (!new_page) { + result = SCAN_ALLOC_HUGE_PAGE_FAIL; + goto out; + } + + if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { + result = SCAN_CGROUP_CHARGE_FAIL; + goto out; + } + + new_page->index = start; + new_page->mapping = mapping; + __SetPageSwapBacked(new_page); + __SetPageLocked(new_page); + BUG_ON(!page_ref_freeze(new_page, 1)); + + + /* + * At this point the new_page is 'frozen' (page_count() is zero), locked + * and not up-to-date. It's safe to insert it into radix tree, because + * nobody would be able to map it or use it in other way until we + * unfreeze it. + */ + + index = start; + spin_lock_irq(&mapping->tree_lock); + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + int n = min(iter.index, end) - index; + + /* + * Handle holes in the radix tree: charge it from shmem and + * insert relevant subpage of new_page into the radix-tree. + */ + if (n && !shmem_charge(mapping->host, n)) { + result = SCAN_FAIL; + break; + } + nr_none += n; + for (; index < min(iter.index, end); index++) { + radix_tree_insert(&mapping->page_tree, index, + new_page + (index % HPAGE_PMD_NR)); + } + + /* We are done. */ + if (index >= end) + break; + + page = radix_tree_deref_slot_protected(slot, + &mapping->tree_lock); + if (radix_tree_exceptional_entry(page) || !PageUptodate(page)) { + spin_unlock_irq(&mapping->tree_lock); + /* swap in or instantiate fallocated page */ + if (shmem_getpage(mapping->host, index, &page, + SGP_NOHUGE)) { + result = SCAN_FAIL; + goto tree_unlocked; + } + spin_lock_irq(&mapping->tree_lock); + } else if (trylock_page(page)) { + get_page(page); + } else { + result = SCAN_PAGE_LOCK; + break; + } + + /* + * The page must be locked, so we can drop the tree_lock + * without racing with truncate. + */ + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageUptodate(page), page); + VM_BUG_ON_PAGE(PageTransCompound(page), page); + + if (page_mapping(page) != mapping) { + result = SCAN_TRUNCATED; + goto out_unlock; + } + spin_unlock_irq(&mapping->tree_lock); + + if (isolate_lru_page(page)) { + result = SCAN_DEL_PAGE_LRU; + goto out_isolate_failed; + } + + if (page_mapped(page)) + unmap_mapping_range(mapping, index << PAGE_SHIFT, + PAGE_SIZE, 0); + + spin_lock_irq(&mapping->tree_lock); + + VM_BUG_ON_PAGE(page_mapped(page), page); + + /* + * The page is expected to have page_count() == 3: + * - we hold a pin on it; + * - one reference from radix tree; + * - one from isolate_lru_page; + */ + if (!page_ref_freeze(page, 3)) { + result = SCAN_PAGE_COUNT; + goto out_lru; + } + + /* + * Add the page to the list to be able to undo the collapse if + * something go wrong. + */ + list_add_tail(&page->lru, &pagelist); + + /* Finally, replace with the new page. */ + radix_tree_replace_slot(slot, + new_page + (index % HPAGE_PMD_NR)); + + index++; + continue; +out_lru: + spin_unlock_irq(&mapping->tree_lock); + putback_lru_page(page); +out_isolate_failed: + unlock_page(page); + put_page(page); + goto tree_unlocked; +out_unlock: + unlock_page(page); + put_page(page); + break; + } + + /* + * Handle hole in radix tree at the end of the range. + * This code only triggers if there's nothing in radix tree + * beyond 'end'. + */ + if (result == SCAN_SUCCEED && index < end) { + int n = end - index; + + if (!shmem_charge(mapping->host, n)) { + result = SCAN_FAIL; + goto tree_locked; + } + + for (; index < end; index++) { + radix_tree_insert(&mapping->page_tree, index, + new_page + (index % HPAGE_PMD_NR)); + } + nr_none += n; + } + +tree_locked: + spin_unlock_irq(&mapping->tree_lock); +tree_unlocked: + + if (result == SCAN_SUCCEED) { + unsigned long flags; + struct zone *zone = page_zone(new_page); + + /* + * Replacing old pages with new one has succeed, now we need to + * copy the content and free old pages. + */ + list_for_each_entry_safe(page, tmp, &pagelist, lru) { + copy_highpage(new_page + (page->index % HPAGE_PMD_NR), + page); + list_del(&page->lru); + unlock_page(page); + page_ref_unfreeze(page, 1); + page->mapping = NULL; + ClearPageActive(page); + ClearPageUnevictable(page); + put_page(page); + } + + local_irq_save(flags); + __inc_node_page_state(new_page, NR_SHMEM_THPS); + if (nr_none) { + __mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none); + __mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none); + } + local_irq_restore(flags); + + /* + * Remove pte page tables, so we can re-faulti + * the page as huge. + */ + retract_page_tables(mapping, start); + + /* Everything is ready, let's unfreeze the new_page */ + set_page_dirty(new_page); + SetPageUptodate(new_page); + page_ref_unfreeze(new_page, HPAGE_PMD_NR); + mem_cgroup_commit_charge(new_page, memcg, false, true); + lru_cache_add_anon(new_page); + unlock_page(new_page); + + *hpage = NULL; + } else { + /* Something went wrong: rollback changes to the radix-tree */ + shmem_uncharge(mapping->host, nr_none); + spin_lock_irq(&mapping->tree_lock); + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, + start) { + if (iter.index >= end) + break; + page = list_first_entry_or_null(&pagelist, + struct page, lru); + if (!page || iter.index < page->index) { + if (!nr_none) + break; + /* Put holes back where they were */ + radix_tree_replace_slot(slot, NULL); + nr_none--; + continue; + } + + VM_BUG_ON_PAGE(page->index != iter.index, page); + + /* Unfreeze the page. */ + list_del(&page->lru); + page_ref_unfreeze(page, 2); + radix_tree_replace_slot(slot, page); + spin_unlock_irq(&mapping->tree_lock); + putback_lru_page(page); + unlock_page(page); + spin_lock_irq(&mapping->tree_lock); + } + VM_BUG_ON(nr_none); + spin_unlock_irq(&mapping->tree_lock); + + /* Unfreeze new_page, caller would take care about freeing it */ + page_ref_unfreeze(new_page, 1); + mem_cgroup_cancel_charge(new_page, memcg, true); + unlock_page(new_page); + new_page->mapping = NULL; + } +out: + VM_BUG_ON(!list_empty(&pagelist)); + /* TODO: tracepoints */ +} + +static void khugepaged_scan_shmem(struct mm_struct *mm, + struct address_space *mapping, + pgoff_t start, struct page **hpage) +{ + struct page *page = NULL; + struct radix_tree_iter iter; + void **slot; + int present, swap; + int node = NUMA_NO_NODE; + int result = SCAN_SUCCEED; + + present = 0; + swap = 0; + memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); + rcu_read_lock(); + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + if (iter.index >= start + HPAGE_PMD_NR) + break; + + page = radix_tree_deref_slot(slot); + if (radix_tree_deref_retry(page)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + + if (radix_tree_exception(page)) { + if (++swap > khugepaged_max_ptes_swap) { + result = SCAN_EXCEED_SWAP_PTE; + break; + } + continue; + } + + if (PageTransCompound(page)) { + result = SCAN_PAGE_COMPOUND; + break; + } + + node = page_to_nid(page); + if (khugepaged_scan_abort(node)) { + result = SCAN_SCAN_ABORT; + break; + } + khugepaged_node_load[node]++; + + if (!PageLRU(page)) { + result = SCAN_PAGE_LRU; + break; + } + + if (page_count(page) != 1 + page_mapcount(page)) { + result = SCAN_PAGE_COUNT; + break; + } + + /* + * We probably should check if the page is referenced here, but + * nobody would transfer pte_young() to PageReferenced() for us. + * And rmap walk here is just too costly... + */ + + present++; + + if (need_resched()) { + cond_resched_rcu(); + slot = radix_tree_iter_next(&iter); + } + } + rcu_read_unlock(); + + if (result == SCAN_SUCCEED) { + if (present < HPAGE_PMD_NR - khugepaged_max_ptes_none) { + result = SCAN_EXCEED_NONE_PTE; + } else { + node = khugepaged_find_target_node(); + collapse_shmem(mm, mapping, start, hpage, node); + } + } + + /* TODO: tracepoints */ +} +#else +static void khugepaged_scan_shmem(struct mm_struct *mm, + struct address_space *mapping, + pgoff_t start, struct page **hpage) +{ + BUILD_BUG(); +} +#endif + +static unsigned int khugepaged_scan_mm_slot(unsigned int pages, + struct page **hpage) + __releases(&khugepaged_mm_lock) + __acquires(&khugepaged_mm_lock) +{ + struct mm_slot *mm_slot; + struct mm_struct *mm; + struct vm_area_struct *vma; + int progress = 0; + + VM_BUG_ON(!pages); + VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock)); + + if (khugepaged_scan.mm_slot) + mm_slot = khugepaged_scan.mm_slot; + else { + mm_slot = list_entry(khugepaged_scan.mm_head.next, + struct mm_slot, mm_node); + khugepaged_scan.address = 0; + khugepaged_scan.mm_slot = mm_slot; + } + spin_unlock(&khugepaged_mm_lock); + + mm = mm_slot->mm; + down_read(&mm->mmap_sem); + if (unlikely(khugepaged_test_exit(mm))) + vma = NULL; + else + vma = find_vma(mm, khugepaged_scan.address); + + progress++; + for (; vma; vma = vma->vm_next) { + unsigned long hstart, hend; + + cond_resched(); + if (unlikely(khugepaged_test_exit(mm))) { + progress++; + break; + } + if (!hugepage_vma_check(vma)) { +skip: + progress++; + continue; + } + hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; + hend = vma->vm_end & HPAGE_PMD_MASK; + if (hstart >= hend) + goto skip; + if (khugepaged_scan.address > hend) + goto skip; + if (khugepaged_scan.address < hstart) + khugepaged_scan.address = hstart; + VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); + + while (khugepaged_scan.address < hend) { + int ret; + cond_resched(); + if (unlikely(khugepaged_test_exit(mm))) + goto breakouterloop; + + VM_BUG_ON(khugepaged_scan.address < hstart || + khugepaged_scan.address + HPAGE_PMD_SIZE > + hend); + if (shmem_file(vma->vm_file)) { + struct file *file; + pgoff_t pgoff = linear_page_index(vma, + khugepaged_scan.address); + if (!shmem_huge_enabled(vma)) + goto skip; + file = get_file(vma->vm_file); + up_read(&mm->mmap_sem); + ret = 1; + khugepaged_scan_shmem(mm, file->f_mapping, + pgoff, hpage); + fput(file); + } else { + ret = khugepaged_scan_pmd(mm, vma, + khugepaged_scan.address, + hpage); + } + /* move to next address */ + khugepaged_scan.address += HPAGE_PMD_SIZE; + progress += HPAGE_PMD_NR; + if (ret) + /* we released mmap_sem so break loop */ + goto breakouterloop_mmap_sem; + if (progress >= pages) + goto breakouterloop; + } + } +breakouterloop: + up_read(&mm->mmap_sem); /* exit_mmap will destroy ptes after this */ +breakouterloop_mmap_sem: + + spin_lock(&khugepaged_mm_lock); + VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot); + /* + * Release the current mm_slot if this mm is about to die, or + * if we scanned all vmas of this mm. + */ + if (khugepaged_test_exit(mm) || !vma) { + /* + * Make sure that if mm_users is reaching zero while + * khugepaged runs here, khugepaged_exit will find + * mm_slot not pointing to the exiting mm. + */ + if (mm_slot->mm_node.next != &khugepaged_scan.mm_head) { + khugepaged_scan.mm_slot = list_entry( + mm_slot->mm_node.next, + struct mm_slot, mm_node); + khugepaged_scan.address = 0; + } else { + khugepaged_scan.mm_slot = NULL; + khugepaged_full_scans++; + } + + collect_mm_slot(mm_slot); + } + + return progress; +} + +static int khugepaged_has_work(void) +{ + return !list_empty(&khugepaged_scan.mm_head) && + khugepaged_enabled(); +} + +static int khugepaged_wait_event(void) +{ + return !list_empty(&khugepaged_scan.mm_head) || + kthread_should_stop(); +} + +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; + bool wait = true; + + barrier(); /* write khugepaged_pages_to_scan to local stack */ + + while (progress < pages) { + if (!khugepaged_prealloc_page(&hpage, &wait)) + break; + + cond_resched(); + + if (unlikely(kthread_should_stop() || try_to_freeze())) + break; + + spin_lock(&khugepaged_mm_lock); + if (!khugepaged_scan.mm_slot) + pass_through_head++; + if (khugepaged_has_work() && + pass_through_head < 2) + progress += khugepaged_scan_mm_slot(pages - progress, + &hpage); + else + progress = pages; + spin_unlock(&khugepaged_mm_lock); + } + + if (!IS_ERR_OR_NULL(hpage)) + put_page(hpage); +} + +static bool khugepaged_should_wakeup(void) +{ + return kthread_should_stop() || + time_after_eq(jiffies, khugepaged_sleep_expire); +} + +static void khugepaged_wait_work(void) +{ + if (khugepaged_has_work()) { + const unsigned long scan_sleep_jiffies = + msecs_to_jiffies(khugepaged_scan_sleep_millisecs); + + if (!scan_sleep_jiffies) + return; + + khugepaged_sleep_expire = jiffies + scan_sleep_jiffies; + wait_event_freezable_timeout(khugepaged_wait, + khugepaged_should_wakeup(), + scan_sleep_jiffies); + return; + } + + if (khugepaged_enabled()) + wait_event_freezable(khugepaged_wait, khugepaged_wait_event()); +} + +static int khugepaged(void *none) +{ + struct mm_slot *mm_slot; + + set_freezable(); + set_user_nice(current, MAX_NICE); + + while (!kthread_should_stop()) { + khugepaged_do_scan(); + khugepaged_wait_work(); + } + + spin_lock(&khugepaged_mm_lock); + mm_slot = khugepaged_scan.mm_slot; + khugepaged_scan.mm_slot = NULL; + if (mm_slot) + collect_mm_slot(mm_slot); + spin_unlock(&khugepaged_mm_lock); + return 0; +} + +static void set_recommended_min_free_kbytes(void) +{ + struct zone *zone; + int nr_zones = 0; + unsigned long recommended_min; + + for_each_populated_zone(zone) + nr_zones++; + + /* Ensure 2 pageblocks are free to assist fragmentation avoidance */ + recommended_min = pageblock_nr_pages * nr_zones * 2; + + /* + * Make sure that on average at least two pageblocks are almost free + * of another type, one for a migratetype to fall back to and a + * second to avoid subsequent fallbacks of other types There are 3 + * MIGRATE_TYPES we care about. + */ + recommended_min += pageblock_nr_pages * nr_zones * + MIGRATE_PCPTYPES * MIGRATE_PCPTYPES; + + /* don't ever allow to reserve more than 5% of the lowmem */ + recommended_min = min(recommended_min, + (unsigned long) nr_free_buffer_pages() / 20); + recommended_min <<= (PAGE_SHIFT-10); + + if (recommended_min > min_free_kbytes) { + if (user_min_free_kbytes >= 0) + pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n", + min_free_kbytes, recommended_min); + + min_free_kbytes = recommended_min; + } + setup_per_zone_wmarks(); +} + +int start_stop_khugepaged(void) +{ + static struct task_struct *khugepaged_thread __read_mostly; + static DEFINE_MUTEX(khugepaged_mutex); + int err = 0; + + mutex_lock(&khugepaged_mutex); + if (khugepaged_enabled()) { + if (!khugepaged_thread) + khugepaged_thread = kthread_run(khugepaged, NULL, + "khugepaged"); + if (IS_ERR(khugepaged_thread)) { + pr_err("khugepaged: kthread_run(khugepaged) failed\n"); + err = PTR_ERR(khugepaged_thread); + khugepaged_thread = NULL; + goto fail; + } + + if (!list_empty(&khugepaged_scan.mm_head)) + wake_up_interruptible(&khugepaged_wait); + + set_recommended_min_free_kbytes(); + } else if (khugepaged_thread) { + kthread_stop(khugepaged_thread); + khugepaged_thread = NULL; + } +fail: + mutex_unlock(&khugepaged_mutex); + return err; +} diff --git a/mm/kmemleak.c b/mm/kmemleak.c index e6429926e957..086292f7c59d 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -307,8 +307,10 @@ static void hex_dump_object(struct seq_file *seq, len = min_t(size_t, object->size, HEX_MAX_LINES * HEX_ROW_SIZE); seq_printf(seq, " hex dump (first %zu bytes):\n", len); + kasan_disable_current(); seq_hex_dump(seq, " ", DUMP_PREFIX_NONE, HEX_ROW_SIZE, HEX_GROUP_SIZE, ptr, len, HEX_ASCII); + kasan_enable_current(); } /* @@ -1483,8 +1485,10 @@ static int kmemleak_scan_thread(void *arg) * Wait before the first scan to allow the system to fully initialize. */ if (first_run) { + signed long timeout = msecs_to_jiffies(SECS_FIRST_SCAN * 1000); first_run = 0; - ssleep(SECS_FIRST_SCAN); + while (timeout && !kthread_should_stop()) + timeout = schedule_timeout_interruptible(timeout); } while (!kthread_should_stop()) { @@ -376,9 +376,8 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) if (IS_ERR_OR_NULL(page)) break; if (PageKsm(page)) - ret = handle_mm_fault(vma->vm_mm, vma, addr, - FAULT_FLAG_WRITE | - FAULT_FLAG_REMOTE); + ret = handle_mm_fault(vma, addr, + FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE); else ret = VM_FAULT_WRITE; put_page(page); @@ -532,8 +531,8 @@ static struct page *get_ksm_page(struct stable_node *stable_node, bool lock_it) void *expected_mapping; unsigned long kpfn; - expected_mapping = (void *)stable_node + - (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM); + expected_mapping = (void *)((unsigned long)stable_node | + PAGE_MAPPING_KSM); again: kpfn = READ_ONCE(stable_node->kpfn); page = pfn_to_page(kpfn); @@ -783,6 +782,7 @@ static int unmerge_and_remove_all_rmap_items(void) } remove_trailing_rmap_items(mm_slot, &mm_slot->rmap_list); + up_read(&mm->mmap_sem); spin_lock(&ksm_mmlist_lock); ksm_scan.mm_slot = list_entry(mm_slot->mm_list.next, @@ -794,12 +794,9 @@ static int unmerge_and_remove_all_rmap_items(void) free_mm_slot(mm_slot); clear_bit(MMF_VM_MERGEABLE, &mm->flags); - up_read(&mm->mmap_sem); mmdrop(mm); - } else { + } else spin_unlock(&ksm_mmlist_lock); - up_read(&mm->mmap_sem); - } } /* Clean up stable nodes, but don't worry if some are still busy */ @@ -1663,8 +1660,15 @@ next_mm: up_read(&mm->mmap_sem); mmdrop(mm); } else { - spin_unlock(&ksm_mmlist_lock); up_read(&mm->mmap_sem); + /* + * up_read(&mm->mmap_sem) first because after + * spin_unlock(&ksm_mmlist_lock) run, the "mm" may + * already have been freed under us by __ksm_exit() + * because the "mm_slot" is still hashed and + * ksm_scan.mm_slot doesn't point to it anymore. + */ + spin_unlock(&ksm_mmlist_lock); } /* Repeat until we've completed scanning the whole list */ diff --git a/mm/maccess.c b/mm/maccess.c index d159b1c96e48..78f9274dd49d 100644 --- a/mm/maccess.c +++ b/mm/maccess.c @@ -96,8 +96,7 @@ long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count) pagefault_disable(); do { - ret = __copy_from_user_inatomic(dst++, - (const void __user __force *)src++, 1); + ret = __get_user(*dst++, (const char __user __force *)src++); } while (dst[-1] && ret == 0 && src - unsafe_addr < count); dst[-1] = '\0'; diff --git a/mm/madvise.c b/mm/madvise.c index a01147359f3b..93fb63e88b5e 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -170,7 +170,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE, vma, index); if (page) - page_cache_release(page); + put_page(page); } return 0; @@ -204,14 +204,14 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma, page = find_get_entry(mapping, index); if (!radix_tree_exceptional_entry(page)) { if (page) - page_cache_release(page); + put_page(page); continue; } swap = radix_to_swp_entry(page); page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE, NULL, 0); if (page) - page_cache_release(page); + put_page(page); } lru_add_drain(); /* Push any new pages onto the LRU now */ @@ -707,10 +707,12 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) return error; write = madvise_need_mmap_write(behavior); - if (write) - down_write(¤t->mm->mmap_sem); - else + if (write) { + if (down_write_killable(¤t->mm->mmap_sem)) + return -EINTR; + } else { down_read(¤t->mm->mmap_sem); + } /* * If the interval [start,end) covers some unmapped address diff --git a/mm/memblock.c b/mm/memblock.c index b570dddb4cb9..483197ef613f 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -20,7 +20,7 @@ #include <linux/seq_file.h> #include <linux/memblock.h> -#include <asm-generic/sections.h> +#include <asm/sections.h> #include <linux/io.h> #include "internal.h" @@ -482,7 +482,7 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type) * @flags: flags of the new region * * Insert new memblock region [@base,@base+@size) into @type at @idx. - * @type must already have extra room to accomodate the new region. + * @type must already have extra room to accommodate the new region. */ static void __init_memblock memblock_insert_region(struct memblock_type *type, int idx, phys_addr_t base, @@ -544,7 +544,7 @@ repeat: /* * The following is executed twice. Once with %false @insert and * then with %true. The first counts the number of regions needed - * to accomodate the new area. The second actually inserts them. + * to accommodate the new area. The second actually inserts them. */ base = obase; nr_new = 0; @@ -584,6 +584,9 @@ repeat: nid, flags); } + if (!nr_new) + return 0; + /* * If this was the first round, resize array and repeat for actual * insertions; otherwise, merge and return. @@ -606,22 +609,14 @@ int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, return memblock_add_range(&memblock.memory, base, size, nid, 0); } -static int __init_memblock memblock_add_region(phys_addr_t base, - phys_addr_t size, - int nid, - unsigned long flags) +int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) { memblock_dbg("memblock_add: [%#016llx-%#016llx] flags %#02lx %pF\n", (unsigned long long)base, (unsigned long long)base + size - 1, - flags, (void *)_RET_IP_); + 0UL, (void *)_RET_IP_); - return memblock_add_range(&memblock.memory, base, size, nid, flags); -} - -int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) -{ - return memblock_add_region(base, size, MAX_NUMNODES, 0); + return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0); } /** @@ -732,22 +727,14 @@ int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) return memblock_remove_range(&memblock.reserved, base, size); } -static int __init_memblock memblock_reserve_region(phys_addr_t base, - phys_addr_t size, - int nid, - unsigned long flags) +int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) { memblock_dbg("memblock_reserve: [%#016llx-%#016llx] flags %#02lx %pF\n", (unsigned long long)base, (unsigned long long)base + size - 1, - flags, (void *)_RET_IP_); - - return memblock_add_range(&memblock.reserved, base, size, nid, flags); -} + 0UL, (void *)_RET_IP_); -int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) -{ - return memblock_reserve_region(base, size, MAX_NUMNODES, 0); + return memblock_add_range(&memblock.reserved, base, size, MAX_NUMNODES, 0); } /** @@ -840,7 +827,7 @@ void __init_memblock __next_reserved_mem_region(u64 *idx, { struct memblock_type *type = &memblock.reserved; - if (*idx >= 0 && *idx < type->cnt) { + if (*idx < type->cnt) { struct memblock_region *r = &type->regions[*idx]; phys_addr_t base = r->base; phys_addr_t size = r->size; @@ -1007,7 +994,10 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, ulong flags, if (*idx == (u64)ULLONG_MAX) { idx_a = type_a->cnt - 1; - idx_b = type_b->cnt; + if (type_b != NULL) + idx_b = type_b->cnt; + else + idx_b = 0; } for (; idx_a >= 0; idx_a--) { @@ -1040,7 +1030,7 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, ulong flags, *out_end = m_end; if (out_nid) *out_nid = m_nid; - idx_a++; + idx_a--; *idx = (u32)idx_a | (u64)idx_b << 32; return; } @@ -1478,15 +1468,16 @@ phys_addr_t __init_memblock memblock_end_of_DRAM(void) return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size); } -void __init memblock_enforce_memory_limit(phys_addr_t limit) +static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit) { phys_addr_t max_addr = (phys_addr_t)ULLONG_MAX; struct memblock_region *r; - if (!limit) - return; - - /* find out max address */ + /* + * translate the memory @limit size into the max address within one of + * the memory memblock regions, if the @limit exceeds the total size + * of those regions, max_addr will keep original value ULLONG_MAX + */ for_each_memblock(memory, r) { if (limit <= r->size) { max_addr = r->base + limit; @@ -1495,6 +1486,22 @@ void __init memblock_enforce_memory_limit(phys_addr_t limit) limit -= r->size; } + return max_addr; +} + +void __init memblock_enforce_memory_limit(phys_addr_t limit) +{ + phys_addr_t max_addr = (phys_addr_t)ULLONG_MAX; + + if (!limit) + return; + + max_addr = __find_max_addr(limit); + + /* @limit exceeds the total size of the memory, do nothing */ + if (max_addr == (phys_addr_t)ULLONG_MAX) + return; + /* truncate both memory and reserved regions */ memblock_remove_range(&memblock.memory, max_addr, (phys_addr_t)ULLONG_MAX); @@ -1502,6 +1509,36 @@ void __init memblock_enforce_memory_limit(phys_addr_t limit) (phys_addr_t)ULLONG_MAX); } +void __init memblock_mem_limit_remove_map(phys_addr_t limit) +{ + struct memblock_type *type = &memblock.memory; + phys_addr_t max_addr; + int i, ret, start_rgn, end_rgn; + + if (!limit) + return; + + max_addr = __find_max_addr(limit); + + /* @limit exceeds the total size of the memory, do nothing */ + if (max_addr == (phys_addr_t)ULLONG_MAX) + return; + + ret = memblock_isolate_range(type, max_addr, (phys_addr_t)ULLONG_MAX, + &start_rgn, &end_rgn); + if (ret) + return; + + /* remove all the MAP regions above the limit */ + for (i = end_rgn - 1; i >= start_rgn; i--) { + if (!memblock_is_nomap(&type->regions[i])) + memblock_remove_region(type, i); + } + /* truncate the reserved regions */ + memblock_remove_range(&memblock.reserved, max_addr, + (phys_addr_t)ULLONG_MAX); +} + static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr) { unsigned int left = 0, right = type->cnt; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 36db05fa8acb..66beca1ad92f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -132,15 +132,11 @@ static const char * const mem_cgroup_lru_names[] = { * their hierarchy representation */ -struct mem_cgroup_tree_per_zone { +struct mem_cgroup_tree_per_node { struct rb_root rb_root; spinlock_t lock; }; -struct mem_cgroup_tree_per_node { - struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES]; -}; - struct mem_cgroup_tree { struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES]; }; @@ -207,6 +203,7 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg); /* "mc" and its members are protected by cgroup_mutex */ static struct move_charge_struct { spinlock_t lock; /* for from, to */ + struct mm_struct *mm; struct mem_cgroup *from; struct mem_cgroup *to; unsigned long flags; @@ -322,15 +319,6 @@ EXPORT_SYMBOL(memcg_kmem_enabled_key); #endif /* !CONFIG_SLOB */ -static struct mem_cgroup_per_zone * -mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) -{ - int nid = zone_to_nid(zone); - int zid = zone_idx(zone); - - return &memcg->nodeinfo[nid]->zoneinfo[zid]; -} - /** * mem_cgroup_css_from_page - css of the memcg associated with a page * @page: page of interest @@ -382,37 +370,35 @@ ino_t page_cgroup_ino(struct page *page) return ino; } -static struct mem_cgroup_per_zone * -mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page) +static struct mem_cgroup_per_node * +mem_cgroup_page_nodeinfo(struct mem_cgroup *memcg, struct page *page) { int nid = page_to_nid(page); - int zid = page_zonenum(page); - return &memcg->nodeinfo[nid]->zoneinfo[zid]; + return memcg->nodeinfo[nid]; } -static struct mem_cgroup_tree_per_zone * -soft_limit_tree_node_zone(int nid, int zid) +static struct mem_cgroup_tree_per_node * +soft_limit_tree_node(int nid) { - return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; + return soft_limit_tree.rb_tree_per_node[nid]; } -static struct mem_cgroup_tree_per_zone * +static struct mem_cgroup_tree_per_node * soft_limit_tree_from_page(struct page *page) { int nid = page_to_nid(page); - int zid = page_zonenum(page); - return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; + return soft_limit_tree.rb_tree_per_node[nid]; } -static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz, +static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz, + struct mem_cgroup_tree_per_node *mctz, unsigned long new_usage_in_excess) { struct rb_node **p = &mctz->rb_root.rb_node; struct rb_node *parent = NULL; - struct mem_cgroup_per_zone *mz_node; + struct mem_cgroup_per_node *mz_node; if (mz->on_tree) return; @@ -422,7 +408,7 @@ static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz, return; while (*p) { parent = *p; - mz_node = rb_entry(parent, struct mem_cgroup_per_zone, + mz_node = rb_entry(parent, struct mem_cgroup_per_node, tree_node); if (mz->usage_in_excess < mz_node->usage_in_excess) p = &(*p)->rb_left; @@ -438,8 +424,8 @@ static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz, mz->on_tree = true; } -static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz) +static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz, + struct mem_cgroup_tree_per_node *mctz) { if (!mz->on_tree) return; @@ -447,8 +433,8 @@ static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, mz->on_tree = false; } -static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz) +static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz, + struct mem_cgroup_tree_per_node *mctz) { unsigned long flags; @@ -472,8 +458,8 @@ static unsigned long soft_limit_excess(struct mem_cgroup *memcg) static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) { unsigned long excess; - struct mem_cgroup_per_zone *mz; - struct mem_cgroup_tree_per_zone *mctz; + struct mem_cgroup_per_node *mz; + struct mem_cgroup_tree_per_node *mctz; mctz = soft_limit_tree_from_page(page); /* @@ -481,7 +467,7 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) * because their event counter is not touched. */ for (; memcg; memcg = parent_mem_cgroup(memcg)) { - mz = mem_cgroup_page_zoneinfo(memcg, page); + mz = mem_cgroup_page_nodeinfo(memcg, page); excess = soft_limit_excess(memcg); /* * We have to update the tree if mz is on RB-tree or @@ -506,24 +492,22 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) { - struct mem_cgroup_tree_per_zone *mctz; - struct mem_cgroup_per_zone *mz; - int nid, zid; + struct mem_cgroup_tree_per_node *mctz; + struct mem_cgroup_per_node *mz; + int nid; for_each_node(nid) { - for (zid = 0; zid < MAX_NR_ZONES; zid++) { - mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; - mctz = soft_limit_tree_node_zone(nid, zid); - mem_cgroup_remove_exceeded(mz, mctz); - } + mz = mem_cgroup_nodeinfo(memcg, nid); + mctz = soft_limit_tree_node(nid); + mem_cgroup_remove_exceeded(mz, mctz); } } -static struct mem_cgroup_per_zone * -__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) +static struct mem_cgroup_per_node * +__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz) { struct rb_node *rightmost = NULL; - struct mem_cgroup_per_zone *mz; + struct mem_cgroup_per_node *mz; retry: mz = NULL; @@ -531,7 +515,7 @@ retry: if (!rightmost) goto done; /* Nothing to reclaim from */ - mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node); + mz = rb_entry(rightmost, struct mem_cgroup_per_node, tree_node); /* * Remove the node now but someone else can add it back, * we will to add it back at the end of reclaim to its correct @@ -545,10 +529,10 @@ done: return mz; } -static struct mem_cgroup_per_zone * -mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) +static struct mem_cgroup_per_node * +mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz) { - struct mem_cgroup_per_zone *mz; + struct mem_cgroup_per_node *mz; spin_lock_irq(&mctz->lock); mz = __mem_cgroup_largest_soft_limit_node(mctz); @@ -642,20 +626,16 @@ unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, int nid, unsigned int lru_mask) { unsigned long nr = 0; - int zid; + struct mem_cgroup_per_node *mz; + enum lru_list lru; VM_BUG_ON((unsigned)nid >= nr_node_ids); - for (zid = 0; zid < MAX_NR_ZONES; zid++) { - struct mem_cgroup_per_zone *mz; - enum lru_list lru; - - for_each_lru(lru) { - if (!(BIT(lru) & lru_mask)) - continue; - mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; - nr += mz->lru_size[lru]; - } + for_each_lru(lru) { + if (!(BIT(lru) & lru_mask)) + continue; + mz = mem_cgroup_nodeinfo(memcg, nid); + nr += mz->lru_size[lru]; } return nr; } @@ -808,9 +788,9 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, rcu_read_lock(); if (reclaim) { - struct mem_cgroup_per_zone *mz; + struct mem_cgroup_per_node *mz; - mz = mem_cgroup_zone_zoneinfo(root, reclaim->zone); + mz = mem_cgroup_nodeinfo(root, reclaim->pgdat->node_id); iter = &mz->iter[reclaim->priority]; if (prev && reclaim->generation != iter->generation) @@ -909,19 +889,17 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) { struct mem_cgroup *memcg = dead_memcg; struct mem_cgroup_reclaim_iter *iter; - struct mem_cgroup_per_zone *mz; - int nid, zid; + struct mem_cgroup_per_node *mz; + int nid; int i; while ((memcg = parent_mem_cgroup(memcg))) { for_each_node(nid) { - for (zid = 0; zid < MAX_NR_ZONES; zid++) { - mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; - for (i = 0; i <= DEF_PRIORITY; i++) { - iter = &mz->iter[i]; - cmpxchg(&iter->position, - dead_memcg, NULL); - } + mz = mem_cgroup_nodeinfo(memcg, nid); + for (i = 0; i <= DEF_PRIORITY; i++) { + iter = &mz->iter[i]; + cmpxchg(&iter->position, + dead_memcg, NULL); } } } @@ -943,39 +921,6 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) iter = mem_cgroup_iter(NULL, iter, NULL)) /** - * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg - * @zone: zone of the wanted lruvec - * @memcg: memcg of the wanted lruvec - * - * Returns the lru list vector holding pages for the given @zone and - * @mem. This can be the global zone lruvec, if the memory controller - * is disabled. - */ -struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, - struct mem_cgroup *memcg) -{ - struct mem_cgroup_per_zone *mz; - struct lruvec *lruvec; - - if (mem_cgroup_disabled()) { - lruvec = &zone->lruvec; - goto out; - } - - mz = mem_cgroup_zone_zoneinfo(memcg, zone); - lruvec = &mz->lruvec; -out: - /* - * Since a node can be onlined after the mem_cgroup was created, - * we have to be prepared to initialize lruvec->zone here; - * and if offlined then reonlined, we need to reinitialize it. - */ - if (unlikely(lruvec->zone != zone)) - lruvec->zone = zone; - return lruvec; -} - -/** * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page * @page: the page * @zone: zone of the page @@ -984,14 +929,14 @@ out: * and putback protocol: the LRU lock must be held, and the page must * either be PageLRU() or the caller must have isolated/allocated it. */ -struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone) +struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat) { - struct mem_cgroup_per_zone *mz; + struct mem_cgroup_per_node *mz; struct mem_cgroup *memcg; struct lruvec *lruvec; if (mem_cgroup_disabled()) { - lruvec = &zone->lruvec; + lruvec = &pgdat->lruvec; goto out; } @@ -1003,7 +948,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone) if (!memcg) memcg = root_mem_cgroup; - mz = mem_cgroup_page_zoneinfo(memcg, page); + mz = mem_cgroup_page_nodeinfo(memcg, page); lruvec = &mz->lruvec; out: /* @@ -1011,8 +956,8 @@ out: * we have to be prepared to initialize lruvec->zone here; * and if offlined then reonlined, we need to reinitialize it. */ - if (unlikely(lruvec->zone != zone)) - lruvec->zone = zone; + if (unlikely(lruvec->pgdat != pgdat)) + lruvec->pgdat = pgdat; return lruvec; } @@ -1022,22 +967,38 @@ out: * @lru: index of lru list the page is sitting on * @nr_pages: positive when adding or negative when removing * - * This function must be called when a page is added to or removed from an - * lru list. + * This function must be called under lru_lock, just before a page is added + * to or just after a page is removed from an lru list (that ordering being + * so as to allow it to check that lru_size 0 is consistent with list_empty). */ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, int nr_pages) { - struct mem_cgroup_per_zone *mz; + struct mem_cgroup_per_node *mz; unsigned long *lru_size; + long size; + bool empty; if (mem_cgroup_disabled()) return; - mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); + mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); lru_size = mz->lru_size + lru; - *lru_size += nr_pages; - VM_BUG_ON((long)(*lru_size) < 0); + empty = list_empty(lruvec->lists + lru); + + if (nr_pages < 0) + *lru_size += nr_pages; + + size = *lru_size; + if (WARN_ONCE(size < 0 || empty != !size, + "%s(%p, %d, %d): lru_size %ld but %sempty\n", + __func__, lruvec, lru, nr_pages, size, empty ? "" : "not ")) { + VM_BUG_ON(1); + *lru_size = 0; + } + + if (nr_pages > 0) + *lru_size += nr_pages; } bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg) @@ -1089,6 +1050,8 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) limit = READ_ONCE(memcg->memsw.limit); if (count <= limit) margin = min(margin, limit - count); + else + margin = 0; } return margin; @@ -1238,6 +1201,7 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, struct oom_control oc = { .zonelist = NULL, .nodemask = NULL, + .memcg = memcg, .gfp_mask = gfp_mask, .order = order, }; @@ -1254,12 +1218,13 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, * select it. The goal is to allow it to allocate so that it may * quickly exit and free its memory. */ - if (fatal_signal_pending(current) || task_will_free_mem(current)) { + if (task_will_free_mem(current)) { mark_oom_victim(current); + wake_oom_reaper(current); goto unlock; } - check_panic_on_oom(&oc, CONSTRAINT_MEMCG, memcg); + check_panic_on_oom(&oc, CONSTRAINT_MEMCG); totalpages = mem_cgroup_get_limit(memcg) ? : 1; for_each_mem_cgroup_tree(iter, memcg) { struct css_task_iter it; @@ -1267,7 +1232,7 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, css_task_iter_start(&iter->css, &it); while ((task = css_task_iter_next(&it))) { - switch (oom_scan_process_thread(&oc, task, totalpages)) { + switch (oom_scan_process_thread(&oc, task)) { case OOM_SCAN_SELECT: if (chosen) put_task_struct(chosen); @@ -1282,6 +1247,8 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, mem_cgroup_iter_break(memcg, iter); if (chosen) put_task_struct(chosen); + /* Set a dummy value to return "true". */ + chosen = (void *) 1; goto unlock; case OOM_SCAN_OK: break; @@ -1305,7 +1272,7 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, if (chosen) { points = chosen_points * 1000 / totalpages; - oom_kill_process(&oc, chosen, points, totalpages, memcg, + oom_kill_process(&oc, chosen, points, totalpages, "Memory cgroup out of memory"); } unlock: @@ -1388,14 +1355,11 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) mem_cgroup_may_update_nodemask(memcg); node = memcg->last_scanned_node; - node = next_node(node, memcg->scan_nodes); - if (node == MAX_NUMNODES) - node = first_node(memcg->scan_nodes); + node = next_node_in(node, memcg->scan_nodes); /* - * We call this when we hit limit, not when pages are added to LRU. - * No LRU may hold pages because all pages are UNEVICTABLE or - * memcg is too small and all pages are not on LRU. In that case, - * we use curret node. + * mem_cgroup_may_update_nodemask might have seen no reclaimmable pages + * last time it really checked all the LRUs due to rate limiting. + * Fallback to the current node in that case for simplicity. */ if (unlikely(node == MAX_NUMNODES)) node = numa_node_id(); @@ -1411,7 +1375,7 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) #endif static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, - struct zone *zone, + pg_data_t *pgdat, gfp_t gfp_mask, unsigned long *total_scanned) { @@ -1421,7 +1385,7 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, unsigned long excess; unsigned long nr_scanned; struct mem_cgroup_reclaim_cookie reclaim = { - .zone = zone, + .pgdat = pgdat, .priority = 0, }; @@ -1451,8 +1415,8 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, } continue; } - total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false, - zone, &nr_scanned); + total += mem_cgroup_shrink_node(victim, gfp_mask, false, + pgdat, &nr_scanned); *total_scanned += nr_scanned; if (!soft_limit_excess(root_memcg)) break; @@ -2085,11 +2049,11 @@ static void lock_page_lru(struct page *page, int *isolated) { struct zone *zone = page_zone(page); - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); if (PageLRU(page)) { struct lruvec *lruvec; - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_lru(page)); *isolated = 1; @@ -2104,12 +2068,12 @@ static void unlock_page_lru(struct page *page, int isolated) if (isolated) { struct lruvec *lruvec; - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); VM_BUG_ON_PAGE(PageLRU(page), page); SetPageLRU(page); add_page_to_lru_list(page, lruvec, page_lru(page)); } - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); } static void commit_charge(struct page *page, struct mem_cgroup *memcg, @@ -2251,20 +2215,30 @@ static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, current->memcg_kmem_skip_account = 0; } -/* +static inline bool memcg_kmem_bypass(void) +{ + if (in_interrupt() || !current->mm || (current->flags & PF_KTHREAD)) + return true; + return false; +} + +/** + * memcg_kmem_get_cache: select the correct per-memcg cache for allocation + * @cachep: the original global kmem cache + * * Return the kmem_cache we're supposed to use for a slab allocation. * We try to use the current memcg's version of the cache. * - * If the cache does not exist yet, if we are the first user of it, - * we either create it immediately, if possible, or create it asynchronously - * in a workqueue. - * In the latter case, we will let the current allocation go through with - * the original cache. + * If the cache does not exist yet, if we are the first user of it, we + * create it asynchronously in a workqueue and let the current allocation + * go through with the original cache. * - * Can't be called in interrupt context or from kernel threads. - * This function needs to be called with rcu_read_lock() held. + * This function takes a reference to the cache it returns to assure it + * won't get destroyed while we are working with it. Once the caller is + * done with it, memcg_kmem_put_cache() must be called to release the + * reference. */ -struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) +struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep) { struct mem_cgroup *memcg; struct kmem_cache *memcg_cachep; @@ -2272,10 +2246,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) VM_BUG_ON(!is_root_cache(cachep)); - if (cachep->flags & SLAB_ACCOUNT) - gfp |= __GFP_ACCOUNT; - - if (!(gfp & __GFP_ACCOUNT)) + if (memcg_kmem_bypass()) return cachep; if (current->memcg_kmem_skip_account) @@ -2308,14 +2279,27 @@ out: return cachep; } -void __memcg_kmem_put_cache(struct kmem_cache *cachep) +/** + * memcg_kmem_put_cache: drop reference taken by memcg_kmem_get_cache + * @cachep: the cache returned by memcg_kmem_get_cache + */ +void memcg_kmem_put_cache(struct kmem_cache *cachep) { if (!is_root_cache(cachep)) css_put(&cachep->memcg_params.memcg->css); } -int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, - struct mem_cgroup *memcg) +/** + * memcg_kmem_charge: charge a kmem page + * @page: page to charge + * @gfp: reclaim mode + * @order: allocation order + * @memcg: memory cgroup to charge + * + * Returns 0 on success, an error code on failure. + */ +int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, + struct mem_cgroup *memcg) { unsigned int nr_pages = 1 << order; struct page_counter *counter; @@ -2336,19 +2320,34 @@ int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, return 0; } -int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order) +/** + * memcg_kmem_charge: charge a kmem page to the current memory cgroup + * @page: page to charge + * @gfp: reclaim mode + * @order: allocation order + * + * Returns 0 on success, an error code on failure. + */ +int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) { struct mem_cgroup *memcg; int ret = 0; + if (memcg_kmem_bypass()) + return 0; + memcg = get_mem_cgroup_from_mm(current->mm); if (!mem_cgroup_is_root(memcg)) - ret = __memcg_kmem_charge_memcg(page, gfp, order, memcg); + ret = memcg_kmem_charge_memcg(page, gfp, order, memcg); css_put(&memcg->css); return ret; } - -void __memcg_kmem_uncharge(struct page *page, int order) +/** + * memcg_kmem_uncharge: uncharge a kmem page + * @page: page to uncharge + * @order: allocation order + */ +void memcg_kmem_uncharge(struct page *page, int order) { struct mem_cgroup *memcg = page->mem_cgroup; unsigned int nr_pages = 1 << order; @@ -2374,7 +2373,7 @@ void __memcg_kmem_uncharge(struct page *page, int order) /* * Because tail pages are not marked as "used", set it. We're under - * zone->lru_lock and migration entries setup in all page mappings. + * zone_lru_lock and migration entries setup in all page mappings. */ void mem_cgroup_split_huge_fixup(struct page *head) { @@ -2544,22 +2543,31 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, return ret; } -unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, +unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned) { unsigned long nr_reclaimed = 0; - struct mem_cgroup_per_zone *mz, *next_mz = NULL; + struct mem_cgroup_per_node *mz, *next_mz = NULL; unsigned long reclaimed; int loop = 0; - struct mem_cgroup_tree_per_zone *mctz; + struct mem_cgroup_tree_per_node *mctz; unsigned long excess; unsigned long nr_scanned; if (order > 0) return 0; - mctz = soft_limit_tree_node_zone(zone_to_nid(zone), zone_idx(zone)); + mctz = soft_limit_tree_node(pgdat->node_id); + + /* + * Do not even bother to check the largest node if the root + * is empty. Do it lockless to prevent lock bouncing. Races + * are acceptable as soft limit is best effort anyway. + */ + if (RB_EMPTY_ROOT(&mctz->rb_root)) + return 0; + /* * This loop can run a while, specially if mem_cgroup's continuously * keep exceeding their soft limit and putting the system under @@ -2574,7 +2582,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, break; nr_scanned = 0; - reclaimed = mem_cgroup_soft_reclaim(mz->memcg, zone, + reclaimed = mem_cgroup_soft_reclaim(mz->memcg, pgdat, gfp_mask, &nr_scanned); nr_reclaimed += reclaimed; *total_scanned += nr_scanned; @@ -2635,8 +2643,7 @@ static inline bool memcg_has_children(struct mem_cgroup *memcg) } /* - * Reclaims as many pages from the given memcg as possible and moves - * the rest to the parent. + * Reclaims as many pages from the given memcg as possible. * * Caller is responsible for holding css reference for memcg. */ @@ -2876,6 +2883,7 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg) * ordering is imposed by list_lru_node->lock taken by * memcg_drain_all_list_lrus(). */ + rcu_read_lock(); /* can be called from css_free w/o cgroup_mutex */ css_for_each_descendant_pre(css, &memcg->css) { child = mem_cgroup_from_css(css); BUG_ON(child->kmemcg_id != kmemcg_id); @@ -2883,6 +2891,8 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg) if (!memcg->use_hierarchy) break; } + rcu_read_unlock(); + memcg_drain_all_list_lrus(kmemcg_id, parent->kmemcg_id); memcg_free_cache_id(kmemcg_id); @@ -3193,22 +3203,21 @@ static int memcg_stat_show(struct seq_file *m, void *v) #ifdef CONFIG_DEBUG_VM { - int nid, zid; - struct mem_cgroup_per_zone *mz; + pg_data_t *pgdat; + struct mem_cgroup_per_node *mz; struct zone_reclaim_stat *rstat; unsigned long recent_rotated[2] = {0, 0}; unsigned long recent_scanned[2] = {0, 0}; - for_each_online_node(nid) - for (zid = 0; zid < MAX_NR_ZONES; zid++) { - mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; - rstat = &mz->lruvec.reclaim_stat; + for_each_online_pgdat(pgdat) { + mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id); + rstat = &mz->lruvec.reclaim_stat; - recent_rotated[0] += rstat->recent_rotated[0]; - recent_rotated[1] += rstat->recent_rotated[1]; - recent_scanned[0] += rstat->recent_scanned[0]; - recent_scanned[1] += rstat->recent_scanned[1]; - } + recent_rotated[0] += rstat->recent_rotated[0]; + recent_rotated[1] += rstat->recent_rotated[1]; + recent_scanned[0] += rstat->recent_scanned[0]; + recent_scanned[1] += rstat->recent_scanned[1]; + } seq_printf(m, "recent_rotated_anon %lu\n", recent_rotated[0]); seq_printf(m, "recent_rotated_file %lu\n", recent_rotated[1]); seq_printf(m, "recent_scanned_anon %lu\n", recent_scanned[0]); @@ -4034,11 +4043,64 @@ static struct cftype mem_cgroup_legacy_files[] = { { }, /* terminate */ }; -static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) +/* + * Private memory cgroup IDR + * + * Swap-out records and page cache shadow entries need to store memcg + * references in constrained space, so we maintain an ID space that is + * limited to 16 bit (MEM_CGROUP_ID_MAX), limiting the total number of + * memory-controlled cgroups to 64k. + * + * However, there usually are many references to the oflline CSS after + * the cgroup has been destroyed, such as page cache or reclaimable + * slab objects, that don't need to hang on to the ID. We want to keep + * those dead CSS from occupying IDs, or we might quickly exhaust the + * relatively small ID space and prevent the creation of new cgroups + * even when there are much fewer than 64k cgroups - possibly none. + * + * Maintain a private 16-bit ID space for memcg, and allow the ID to + * be freed and recycled when it's no longer needed, which is usually + * when the CSS is offlined. + * + * The only exception to that are records of swapped out tmpfs/shmem + * pages that need to be attributed to live ancestors on swapin. But + * those references are manageable from userspace. + */ + +static DEFINE_IDR(mem_cgroup_idr); + +static void mem_cgroup_id_get(struct mem_cgroup *memcg) +{ + atomic_inc(&memcg->id.ref); +} + +static void mem_cgroup_id_put(struct mem_cgroup *memcg) +{ + if (atomic_dec_and_test(&memcg->id.ref)) { + idr_remove(&mem_cgroup_idr, memcg->id.id); + memcg->id.id = 0; + + /* Memcg ID pins CSS */ + css_put(&memcg->css); + } +} + +/** + * mem_cgroup_from_id - look up a memcg from a memcg id + * @id: the memcg id to look up + * + * Caller must hold rcu_read_lock(). + */ +struct mem_cgroup *mem_cgroup_from_id(unsigned short id) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return idr_find(&mem_cgroup_idr, id); +} + +static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn; - struct mem_cgroup_per_zone *mz; - int zone, tmp = node; + int tmp = node; /* * This routine is called against possible nodes. * But it's BUG to call kmalloc() against offline node. @@ -4053,18 +4115,16 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) if (!pn) return 1; - for (zone = 0; zone < MAX_NR_ZONES; zone++) { - mz = &pn->zoneinfo[zone]; - lruvec_init(&mz->lruvec); - mz->usage_in_excess = 0; - mz->on_tree = false; - mz->memcg = memcg; - } + lruvec_init(&pn->lruvec); + pn->usage_in_excess = 0; + pn->on_tree = false; + pn->memcg = memcg; + memcg->nodeinfo[node] = pn; return 0; } -static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) +static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) { kfree(memcg->nodeinfo[node]); } @@ -4075,7 +4135,7 @@ static void mem_cgroup_free(struct mem_cgroup *memcg) memcg_wb_domain_exit(memcg); for_each_node(node) - free_mem_cgroup_per_zone_info(memcg, node); + free_mem_cgroup_per_node_info(memcg, node); free_percpu(memcg->stat); kfree(memcg); } @@ -4093,12 +4153,18 @@ static struct mem_cgroup *mem_cgroup_alloc(void) if (!memcg) return NULL; + memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, + 1, MEM_CGROUP_ID_MAX, + GFP_KERNEL); + if (memcg->id.id < 0) + goto fail; + memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu); if (!memcg->stat) goto fail; for_each_node(node) - if (alloc_mem_cgroup_per_zone_info(memcg, node)) + if (alloc_mem_cgroup_per_node_info(memcg, node)) goto fail; if (memcg_wb_domain_init(memcg, GFP_KERNEL)) @@ -4119,8 +4185,11 @@ static struct mem_cgroup *mem_cgroup_alloc(void) #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&memcg->cgwb_list); #endif + idr_replace(&mem_cgroup_idr, memcg, memcg->id.id); return memcg; fail: + if (memcg->id.id > 0) + idr_remove(&mem_cgroup_idr, memcg->id.id); mem_cgroup_free(memcg); return NULL; } @@ -4180,15 +4249,14 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) return &memcg->css; fail: mem_cgroup_free(memcg); - return NULL; + return ERR_PTR(-ENOMEM); } -static int -mem_cgroup_css_online(struct cgroup_subsys_state *css) +static int mem_cgroup_css_online(struct cgroup_subsys_state *css) { - if (css->id > MEM_CGROUP_ID_MAX) - return -ENOSPC; - + /* Online state pins memcg ID, memcg ID pins CSS */ + mem_cgroup_id_get(mem_cgroup_from_css(css)); + css_get(css); return 0; } @@ -4211,6 +4279,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) memcg_offline_kmem(memcg); wb_memcg_offline(memcg); + + mem_cgroup_id_put(memcg); } static void mem_cgroup_css_released(struct cgroup_subsys_state *css) @@ -4289,24 +4359,6 @@ static int mem_cgroup_do_precharge(unsigned long count) return 0; } -/** - * get_mctgt_type - get target type of moving charge - * @vma: the vma the pte to be checked belongs - * @addr: the address corresponding to the pte to be checked - * @ptent: the pte to be checked - * @target: the pointer the target page or swap ent will be stored(can be NULL) - * - * Returns - * 0(MC_TARGET_NONE): if the pte is not a target for move charge. - * 1(MC_TARGET_PAGE): if the page corresponding to this pte is a target for - * move charge. if @target is not NULL, the page is stored in target->page - * with extra refcnt got(Callers should handle it). - * 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a - * target for charge migration. if @target is not NULL, the entry is stored - * in target->ent. - * - * Called with pte lock held. - */ union mc_target { struct page *page; swp_entry_t ent; @@ -4340,7 +4392,7 @@ static struct page *mc_handle_present_pte(struct vm_area_struct *vma, #ifdef CONFIG_SWAP static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, - unsigned long addr, pte_t ptent, swp_entry_t *entry) + pte_t ptent, swp_entry_t *entry) { struct page *page = NULL; swp_entry_t ent = pte_to_swp_entry(ptent); @@ -4359,7 +4411,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, } #else static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, - unsigned long addr, pte_t ptent, swp_entry_t *entry) + pte_t ptent, swp_entry_t *entry) { return NULL; } @@ -4402,7 +4454,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, /** * mem_cgroup_move_account - move account of the page * @page: the page - * @nr_pages: number of regular pages (>1 for huge pages) + * @compound: charge the page as compound or small page * @from: mem_cgroup which the page is moved from. * @to: mem_cgroup which the page is moved to. @from != @to. * @@ -4495,6 +4547,25 @@ out: return ret; } +/** + * get_mctgt_type - get target type of moving charge + * @vma: the vma the pte to be checked belongs + * @addr: the address corresponding to the pte to be checked + * @ptent: the pte to be checked + * @target: the pointer the target page or swap ent will be stored(can be NULL) + * + * Returns + * 0(MC_TARGET_NONE): if the pte is not a target for move charge. + * 1(MC_TARGET_PAGE): if the page corresponding to this pte is a target for + * move charge. if @target is not NULL, the page is stored in target->page + * with extra refcnt got(Callers should handle it). + * 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a + * target for charge migration. if @target is not NULL, the entry is stored + * in target->ent. + * + * Called with pte lock held. + */ + static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, unsigned long addr, pte_t ptent, union mc_target *target) { @@ -4505,7 +4576,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, if (pte_present(ptent)) page = mc_handle_present_pte(vma, addr, ptent); else if (is_swap_pte(ptent)) - page = mc_handle_swap_pte(vma, addr, ptent, &ent); + page = mc_handle_swap_pte(vma, ptent, &ent); else if (pte_none(ptent)) page = mc_handle_file_pte(vma, addr, ptent, &ent); @@ -4667,6 +4738,8 @@ static void __mem_cgroup_clear_mc(void) static void mem_cgroup_clear_mc(void) { + struct mm_struct *mm = mc.mm; + /* * we must clear moving_task before waking up waiters at the end of * task migration. @@ -4676,7 +4749,10 @@ static void mem_cgroup_clear_mc(void) spin_lock(&mc.lock); mc.from = NULL; mc.to = NULL; + mc.mm = NULL; spin_unlock(&mc.lock); + + mmput(mm); } static int mem_cgroup_can_attach(struct cgroup_taskset *tset) @@ -4733,6 +4809,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) VM_BUG_ON(mc.moved_swap); spin_lock(&mc.lock); + mc.mm = mm; mc.from = from; mc.to = memcg; mc.flags = move_flags; @@ -4742,8 +4819,9 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) ret = mem_cgroup_precharge_mc(mm); if (ret) mem_cgroup_clear_mc(); + } else { + mmput(mm); } - mmput(mm); return ret; } @@ -4852,11 +4930,11 @@ put: /* get_mctgt_type() gets the page */ return ret; } -static void mem_cgroup_move_charge(struct mm_struct *mm) +static void mem_cgroup_move_charge(void) { struct mm_walk mem_cgroup_move_charge_walk = { .pmd_entry = mem_cgroup_move_charge_pte_range, - .mm = mm, + .mm = mc.mm, }; lru_add_drain_all(); @@ -4868,7 +4946,7 @@ static void mem_cgroup_move_charge(struct mm_struct *mm) atomic_inc(&mc.from->moving_account); synchronize_rcu(); retry: - if (unlikely(!down_read_trylock(&mm->mmap_sem))) { + if (unlikely(!down_read_trylock(&mc.mm->mmap_sem))) { /* * Someone who are holding the mmap_sem might be waiting in * waitq. So we cancel all extra charges, wake up all waiters, @@ -4885,23 +4963,16 @@ retry: * additional charge, the page walk just aborts. */ walk_page_range(0, ~0UL, &mem_cgroup_move_charge_walk); - up_read(&mm->mmap_sem); + up_read(&mc.mm->mmap_sem); atomic_dec(&mc.from->moving_account); } -static void mem_cgroup_move_task(struct cgroup_taskset *tset) +static void mem_cgroup_move_task(void) { - struct cgroup_subsys_state *css; - struct task_struct *p = cgroup_taskset_first(tset, &css); - struct mm_struct *mm = get_task_mm(p); - - if (mm) { - if (mc.to) - mem_cgroup_move_charge(mm); - mmput(mm); - } - if (mc.to) + if (mc.to) { + mem_cgroup_move_charge(); mem_cgroup_clear_mc(); + } } #else /* !CONFIG_MMU */ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) @@ -4911,7 +4982,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { } -static void mem_cgroup_move_task(struct cgroup_taskset *tset) +static void mem_cgroup_move_task(void) { } #endif @@ -5109,7 +5180,7 @@ static int memory_stat_show(struct seq_file *m, void *v) seq_printf(m, "file %llu\n", (u64)stat[MEM_CGROUP_STAT_CACHE] * PAGE_SIZE); seq_printf(m, "kernel_stack %llu\n", - (u64)stat[MEMCG_KERNEL_STACK] * PAGE_SIZE); + (u64)stat[MEMCG_KERNEL_STACK_KB] * 1024); seq_printf(m, "slab %llu\n", (u64)(stat[MEMCG_SLAB_RECLAIMABLE] + stat[MEMCG_SLAB_UNRECLAIMABLE]) * PAGE_SIZE); @@ -5195,7 +5266,7 @@ struct cgroup_subsys memory_cgrp_subsys = { .css_reset = mem_cgroup_css_reset, .can_attach = mem_cgroup_can_attach, .cancel_attach = mem_cgroup_cancel_attach, - .attach = mem_cgroup_move_task, + .post_attach = mem_cgroup_move_task, .bind = mem_cgroup_bind, .dfl_cftypes = memory_files, .legacy_cftypes = mem_cgroup_legacy_files, @@ -5245,6 +5316,7 @@ bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg) * @mm: mm context of the victim * @gfp_mask: reclaim mode * @memcgp: charged memcg return + * @compound: charge the page as compound or small page * * Try to charge @page to the memcg that @mm belongs to, reclaiming * pages according to @gfp_mask if necessary. @@ -5307,6 +5379,7 @@ out: * @page: page to charge * @memcg: memcg to charge the page to * @lrucare: page might be on LRU already + * @compound: charge the page as compound or small page * * Finalize a charge transaction started by mem_cgroup_try_charge(), * after page->mapping has been set up. This must happen atomically @@ -5358,6 +5431,7 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, * mem_cgroup_cancel_charge - cancel a page charge * @page: page to charge * @memcg: memcg to charge the page to + * @compound: charge the page as compound or small page * * Cancel a charge transaction started by mem_cgroup_try_charge(). */ @@ -5381,15 +5455,18 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout, unsigned long nr_anon, unsigned long nr_file, - unsigned long nr_huge, struct page *dummy_page) + unsigned long nr_huge, unsigned long nr_kmem, + struct page *dummy_page) { - unsigned long nr_pages = nr_anon + nr_file; + unsigned long nr_pages = nr_anon + nr_file + nr_kmem; unsigned long flags; if (!mem_cgroup_is_root(memcg)) { page_counter_uncharge(&memcg->memory, nr_pages); if (do_memsw_account()) page_counter_uncharge(&memcg->memsw, nr_pages); + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && nr_kmem) + page_counter_uncharge(&memcg->kmem, nr_kmem); memcg_oom_recover(memcg); } @@ -5412,6 +5489,7 @@ static void uncharge_list(struct list_head *page_list) unsigned long nr_anon = 0; unsigned long nr_file = 0; unsigned long nr_huge = 0; + unsigned long nr_kmem = 0; unsigned long pgpgout = 0; struct list_head *next; struct page *page; @@ -5422,8 +5500,6 @@ static void uncharge_list(struct list_head *page_list) */ next = page_list->next; do { - unsigned int nr_pages = 1; - page = list_entry(next, struct page, lru); next = page->lru.next; @@ -5442,31 +5518,34 @@ static void uncharge_list(struct list_head *page_list) if (memcg != page->mem_cgroup) { if (memcg) { uncharge_batch(memcg, pgpgout, nr_anon, nr_file, - nr_huge, page); - pgpgout = nr_anon = nr_file = nr_huge = 0; + nr_huge, nr_kmem, page); + pgpgout = nr_anon = nr_file = + nr_huge = nr_kmem = 0; } memcg = page->mem_cgroup; } - if (PageTransHuge(page)) { - nr_pages <<= compound_order(page); - VM_BUG_ON_PAGE(!PageTransHuge(page), page); - nr_huge += nr_pages; - } + if (!PageKmemcg(page)) { + unsigned int nr_pages = 1; - if (PageAnon(page)) - nr_anon += nr_pages; - else - nr_file += nr_pages; + if (PageTransHuge(page)) { + nr_pages <<= compound_order(page); + nr_huge += nr_pages; + } + if (PageAnon(page)) + nr_anon += nr_pages; + else + nr_file += nr_pages; + pgpgout++; + } else + nr_kmem += 1 << compound_order(page); page->mem_cgroup = NULL; - - pgpgout++; } while (next != page_list); if (memcg) uncharge_batch(memcg, pgpgout, nr_anon, nr_file, - nr_huge, page); + nr_huge, nr_kmem, page); } /** @@ -5520,6 +5599,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) struct mem_cgroup *memcg; unsigned int nr_pages; bool compound; + unsigned long flags; VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); @@ -5550,10 +5630,10 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) commit_charge(newpage, memcg, false); - local_irq_disable(); + local_irq_save(flags); mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages); memcg_check_events(memcg, newpage); - local_irq_enable(); + local_irq_restore(flags); } DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key); @@ -5687,18 +5767,12 @@ static int __init mem_cgroup_init(void) for_each_node(node) { struct mem_cgroup_tree_per_node *rtpn; - int zone; rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, node_online(node) ? node : NUMA_NO_NODE); - for (zone = 0; zone < MAX_NR_ZONES; zone++) { - struct mem_cgroup_tree_per_zone *rtpz; - - rtpz = &rtpn->rb_tree_per_zone[zone]; - rtpz->rb_root = RB_ROOT; - spin_lock_init(&rtpz->lock); - } + rtpn->rb_root = RB_ROOT; + spin_lock_init(&rtpn->lock); soft_limit_tree.rb_tree_per_node[node] = rtpn; } @@ -5731,6 +5805,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) if (!memcg) return; + mem_cgroup_id_get(memcg); oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); VM_BUG_ON_PAGE(oldid, page); mem_cgroup_swap_statistics(memcg, true); @@ -5749,6 +5824,9 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) VM_BUG_ON(!irqs_disabled()); mem_cgroup_charge_statistics(memcg, page, false, -1); memcg_check_events(memcg, page); + + if (!mem_cgroup_is_root(memcg)) + css_put(&memcg->css); } /* @@ -5779,11 +5857,11 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) !page_counter_try_charge(&memcg->swap, 1, &counter)) return -ENOMEM; + mem_cgroup_id_get(memcg); oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); VM_BUG_ON_PAGE(oldid, page); mem_cgroup_swap_statistics(memcg, true); - css_get(&memcg->css); return 0; } @@ -5812,7 +5890,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry) page_counter_uncharge(&memcg->memsw, 1); } mem_cgroup_swap_statistics(memcg, false); - css_put(&memcg->css); + mem_cgroup_id_put(memcg); } rcu_read_unlock(); } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 5a544c6c0717..de88f33519c0 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -184,8 +184,8 @@ static int kill_proc(struct task_struct *t, unsigned long addr, int trapno, struct siginfo si; int ret; - pr_err("MCE %#lx: Killing %s:%d due to hardware memory corruption\n", - pfn, t->comm, t->pid); + pr_err("Memory failure: %#lx: Killing %s:%d due to hardware memory corruption\n", + pfn, t->comm, t->pid); si.si_signo = SIGBUS; si.si_errno = 0; si.si_addr = (void *)addr; @@ -208,7 +208,7 @@ static int kill_proc(struct task_struct *t, unsigned long addr, int trapno, ret = send_sig_info(SIGBUS, &si, t); /* synchronous? */ } if (ret < 0) - pr_info("MCE: Error sending signal to %s:%d: %d\n", + pr_info("Memory failure: Error sending signal to %s:%d: %d\n", t->comm, t->pid, ret); return ret; } @@ -289,7 +289,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, } else { tk = kmalloc(sizeof(struct to_kill), GFP_ATOMIC); if (!tk) { - pr_err("MCE: Out of memory while machine check handling\n"); + pr_err("Memory failure: Out of memory while machine check handling\n"); return; } } @@ -303,7 +303,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, * a SIGKILL because the error is not contained anymore. */ if (tk->addr == -EFAULT) { - pr_info("MCE: Unable to find user space address %lx in %s\n", + pr_info("Memory failure: Unable to find user space address %lx in %s\n", page_to_pfn(p), tsk->comm); tk->addr_valid = 0; } @@ -334,7 +334,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, int trapno, * signal and then access the memory. Just kill it. */ if (fail || tk->addr_valid == 0) { - pr_err("MCE %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", + pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", pfn, tk->tsk->comm, tk->tsk->pid); force_sig(SIGKILL, tk->tsk); } @@ -347,7 +347,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, int trapno, */ else if (kill_proc(tk->tsk, tk->addr, trapno, pfn, page, flags) < 0) - pr_err("MCE %#lx: Cannot send advisory machine check signal to %s:%d\n", + pr_err("Memory failure: %#lx: Cannot send advisory machine check signal to %s:%d\n", pfn, tk->tsk->comm, tk->tsk->pid); } put_task_struct(tk->tsk); @@ -538,7 +538,7 @@ static int delete_from_lru_cache(struct page *p) /* * drop the page count elevated by isolate_lru_page() */ - page_cache_release(p); + put_page(p); return 0; } return -EIO; @@ -559,7 +559,7 @@ static int me_kernel(struct page *p, unsigned long pfn) */ static int me_unknown(struct page *p, unsigned long pfn) { - pr_err("MCE %#lx: Unknown page state\n", pfn); + pr_err("Memory failure: %#lx: Unknown page state\n", pfn); return MF_FAILED; } @@ -604,11 +604,12 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) if (mapping->a_ops->error_remove_page) { err = mapping->a_ops->error_remove_page(mapping, p); if (err != 0) { - pr_info("MCE %#lx: Failed to punch page: %d\n", + pr_info("Memory failure: %#lx: Failed to punch page: %d\n", pfn, err); } else if (page_has_private(p) && !try_to_release_page(p, GFP_NOIO)) { - pr_info("MCE %#lx: failed to release buffers\n", pfn); + pr_info("Memory failure: %#lx: failed to release buffers\n", + pfn); } else { ret = MF_RECOVERED; } @@ -620,7 +621,8 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) if (invalidate_inode_page(p)) ret = MF_RECOVERED; else - pr_info("MCE %#lx: Failed to invalidate\n", pfn); + pr_info("Memory failure: %#lx: Failed to invalidate\n", + pfn); } return ret; } @@ -739,8 +741,6 @@ static int me_huge_page(struct page *p, unsigned long pfn) * page->lru because it can be used in other hugepage operations, * such as __unmap_hugepage_range() and gather_surplus_pages(). * So instead we use page_mapping() and PageAnon(). - * We assume that this function is called with page lock held, - * so there is no race between isolation and mapping/unmapping. */ if (!(page_mapping(hpage) || PageAnon(hpage))) { res = dequeue_hwpoisoned_huge_page(hpage); @@ -833,7 +833,7 @@ static void action_result(unsigned long pfn, enum mf_action_page_type type, { trace_memory_failure_event(pfn, type, result); - pr_err("MCE %#lx: recovery action for %s: %s\n", + pr_err("Memory failure: %#lx: recovery action for %s: %s\n", pfn, action_page_types[type], action_name[result]); } @@ -849,7 +849,7 @@ static int page_action(struct page_state *ps, struct page *p, if (ps->action == me_swapcache_dirty && result == MF_DELAYED) count--; if (count != 0) { - pr_err("MCE %#lx: %s still referenced by %d users\n", + pr_err("Memory failure: %#lx: %s still referenced by %d users\n", pfn, action_page_types[ps->type], count); result = MF_FAILED; } @@ -882,13 +882,22 @@ int get_hwpoison_page(struct page *page) * tries to touch the "partially handled" page. */ if (!PageAnon(head)) { - pr_err("MCE: %#lx: non anonymous thp\n", + pr_err("Memory failure: %#lx: non anonymous thp\n", page_to_pfn(page)); return 0; } } - return get_page_unless_zero(head); + if (get_page_unless_zero(head)) { + if (head == compound_head(page)) + return 1; + + pr_info("Memory failure: %#lx cannot catch tail\n", + page_to_pfn(page)); + put_page(head); + } + + return 0; } EXPORT_SYMBOL_GPL(get_hwpoison_page); @@ -923,12 +932,13 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, return SWAP_SUCCESS; if (PageKsm(p)) { - pr_err("MCE %#lx: can't handle KSM pages.\n", pfn); + pr_err("Memory failure: %#lx: can't handle KSM pages.\n", pfn); return SWAP_FAIL; } if (PageSwapCache(p)) { - pr_err("MCE %#lx: keeping poisoned page in swap cache\n", pfn); + pr_err("Memory failure: %#lx: keeping poisoned page in swap cache\n", + pfn); ttu |= TTU_IGNORE_HWPOISON; } @@ -946,7 +956,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, } else { kill = 0; ttu |= TTU_IGNORE_HWPOISON; - pr_info("MCE %#lx: corrupted page was clean: dropped without side effects\n", + pr_info("Memory failure: %#lx: corrupted page was clean: dropped without side effects\n", pfn); } } @@ -964,7 +974,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, ret = try_to_unmap(hpage, ttu); if (ret != SWAP_SUCCESS) - pr_err("MCE %#lx: failed to unmap page (mapcount=%d)\n", + pr_err("Memory failure: %#lx: failed to unmap page (mapcount=%d)\n", pfn, page_mapcount(hpage)); /* @@ -1032,14 +1042,16 @@ int memory_failure(unsigned long pfn, int trapno, int flags) panic("Memory failure from trap %d on page %lx", trapno, pfn); if (!pfn_valid(pfn)) { - pr_err("MCE %#lx: memory outside kernel control\n", pfn); + pr_err("Memory failure: %#lx: memory outside kernel control\n", + pfn); return -ENXIO; } p = pfn_to_page(pfn); orig_head = hpage = compound_head(p); if (TestSetPageHWPoison(p)) { - pr_err("MCE %#lx: already hardware poisoned\n", pfn); + pr_err("Memory failure: %#lx: already hardware poisoned\n", + pfn); return 0; } @@ -1104,9 +1116,11 @@ int memory_failure(unsigned long pfn, int trapno, int flags) if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) { unlock_page(hpage); if (!PageAnon(hpage)) - pr_err("MCE: %#lx: non anonymous thp\n", pfn); + pr_err("Memory failure: %#lx: non anonymous thp\n", + pfn); else - pr_err("MCE: %#lx: thp split failed\n", pfn); + pr_err("Memory failure: %#lx: thp split failed\n", + pfn); if (TestClearPageHWPoison(p)) num_poisoned_pages_sub(nr_pages); put_hwpoison_page(p); @@ -1170,7 +1184,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * unpoison always clear PG_hwpoison inside page lock */ if (!PageHWPoison(p)) { - pr_err("MCE %#lx: just unpoisoned\n", pfn); + pr_err("Memory failure: %#lx: just unpoisoned\n", pfn); num_poisoned_pages_sub(nr_pages); unlock_page(hpage); put_hwpoison_page(hpage); @@ -1387,25 +1401,25 @@ int unpoison_memory(unsigned long pfn) page = compound_head(p); if (!PageHWPoison(p)) { - unpoison_pr_info("MCE: Page was already unpoisoned %#lx\n", + unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n", pfn, &unpoison_rs); return 0; } if (page_count(page) > 1) { - unpoison_pr_info("MCE: Someone grabs the hwpoison page %#lx\n", + unpoison_pr_info("Unpoison: Someone grabs the hwpoison page %#lx\n", pfn, &unpoison_rs); return 0; } if (page_mapped(page)) { - unpoison_pr_info("MCE: Someone maps the hwpoison page %#lx\n", + unpoison_pr_info("Unpoison: Someone maps the hwpoison page %#lx\n", pfn, &unpoison_rs); return 0; } if (page_mapping(page)) { - unpoison_pr_info("MCE: the hwpoison page has non-NULL mapping %#lx\n", + unpoison_pr_info("Unpoison: the hwpoison page has non-NULL mapping %#lx\n", pfn, &unpoison_rs); return 0; } @@ -1416,7 +1430,7 @@ int unpoison_memory(unsigned long pfn) * In such case, we yield to memory_failure() and make unpoison fail. */ if (!PageHuge(page) && PageTransHuge(page)) { - unpoison_pr_info("MCE: Memory failure is now running on %#lx\n", + unpoison_pr_info("Unpoison: Memory failure is now running on %#lx\n", pfn, &unpoison_rs); return 0; } @@ -1431,13 +1445,13 @@ int unpoison_memory(unsigned long pfn) * to the end. */ if (PageHuge(page)) { - unpoison_pr_info("MCE: Memory failure is now running on free hugepage %#lx\n", + unpoison_pr_info("Unpoison: Memory failure is now running on free hugepage %#lx\n", pfn, &unpoison_rs); return 0; } if (TestClearPageHWPoison(p)) num_poisoned_pages_dec(); - unpoison_pr_info("MCE: Software-unpoisoned free page %#lx\n", + unpoison_pr_info("Unpoison: Software-unpoisoned free page %#lx\n", pfn, &unpoison_rs); return 0; } @@ -1450,7 +1464,7 @@ int unpoison_memory(unsigned long pfn) * the free buddy page pool. */ if (TestClearPageHWPoison(page)) { - unpoison_pr_info("MCE: Software-unpoisoned page %#lx\n", + unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n", pfn, &unpoison_rs); num_poisoned_pages_sub(nr_pages); freeit = 1; @@ -1647,7 +1661,7 @@ static int __soft_offline_page(struct page *page, int flags) put_hwpoison_page(page); if (!ret) { LIST_HEAD(pagelist); - inc_zone_page_state(page, NR_ISOLATED_ANON + + inc_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); list_add(&page->lru, &pagelist); ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, @@ -1655,7 +1669,7 @@ static int __soft_offline_page(struct page *page, int flags) if (ret) { if (!list_empty(&pagelist)) { list_del(&page->lru); - dec_zone_page_state(page, NR_ISOLATED_ANON + + dec_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); putback_lru_page(page); } diff --git a/mm/memory.c b/mm/memory.c index 098f00d05461..83be99d9d8a1 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -63,6 +63,7 @@ #include <linux/dma-debug.h> #include <linux/debugfs.h> #include <linux/userfaultfd_k.h> +#include <linux/dax.h> #include <asm/io.h> #include <asm/mmu_context.h> @@ -232,6 +233,7 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long #ifdef CONFIG_HAVE_RCU_TABLE_FREE tlb->batch = NULL; #endif + tlb->page_size = 0; __tlb_reset_range(tlb); } @@ -291,23 +293,31 @@ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long e * handling the additional races in SMP caused by other CPUs caching valid * mappings in their TLBs. Returns the number of free page slots left. * When out of page slots we must call tlb_flush_mmu(). + *returns true if the caller should flush. */ -int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) +bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size) { struct mmu_gather_batch *batch; VM_BUG_ON(!tlb->end); + if (!tlb->page_size) + tlb->page_size = page_size; + else { + if (page_size != tlb->page_size) + return true; + } + batch = tlb->active; - batch->pages[batch->nr++] = page; if (batch->nr == batch->max) { if (!tlb_next_batch(tlb)) - return 0; + return true; batch = tlb->active; } VM_BUG_ON_PAGE(batch->nr > batch->max, page); - return batch->max - batch->nr; + batch->pages[batch->nr++] = page; + return false; } #endif /* HAVE_GENERIC_MMU_GATHER */ @@ -789,6 +799,46 @@ out: return pfn_to_page(pfn); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t pmd) +{ + unsigned long pfn = pmd_pfn(pmd); + + /* + * There is no pmd_special() but there may be special pmds, e.g. + * in a direct-access (dax) mapping, so let's just replicate the + * !HAVE_PTE_SPECIAL case from vm_normal_page() here. + */ + if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { + if (vma->vm_flags & VM_MIXEDMAP) { + if (!pfn_valid(pfn)) + return NULL; + goto out; + } else { + unsigned long off; + off = (addr - vma->vm_start) >> PAGE_SHIFT; + if (pfn == vma->vm_pgoff + off) + return NULL; + if (!is_cow_mapping(vma->vm_flags)) + return NULL; + } + } + + if (is_zero_pfn(pfn)) + return NULL; + if (unlikely(pfn > highest_memmap_pfn)) + return NULL; + + /* + * NOTE! We still have PageReserved() pages in the page tables. + * eg. VDSO mappings can cause them to exist. + */ +out: + return pfn_to_page(pfn); +} +#endif + /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range @@ -1068,6 +1118,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, pte_t *start_pte; pte_t *pte; swp_entry_t entry; + struct page *pending_page = NULL; again: init_rss_vec(rss); @@ -1091,7 +1142,7 @@ again: * unmap shared but keep private pages. */ if (details->check_mapping && - details->check_mapping != page->mapping) + details->check_mapping != page_rmapping(page)) continue; } ptent = ptep_get_and_clear_full(mm, addr, pte, @@ -1119,8 +1170,9 @@ again: page_remove_rmap(page, false); if (unlikely(page_mapcount(page) < 0)) print_bad_pte(vma, addr, ptent, page); - if (unlikely(!__tlb_remove_page(tlb, page))) { + if (unlikely(__tlb_remove_page(tlb, page))) { force_flush = 1; + pending_page = page; addr += PAGE_SIZE; break; } @@ -1161,7 +1213,11 @@ again: if (force_flush) { force_flush = 0; tlb_flush_mmu_free(tlb); - + if (pending_page) { + /* remove the page with new size */ + __tlb_remove_pte_page(tlb, pending_page); + pending_page = NULL; + } if (addr != end) goto again; } @@ -1182,15 +1238,8 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, next = pmd_addr_end(addr, end); if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) { -#ifdef CONFIG_DEBUG_VM - if (!rwsem_is_locked(&tlb->mm->mmap_sem)) { - pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n", - __func__, addr, end, - vma->vm_start, - vma->vm_end); - BUG(); - } -#endif + VM_BUG_ON_VMA(vma_is_anonymous(vma) && + !rwsem_is_locked(&tlb->mm->mmap_sem), vma); split_huge_pmd(vma, pmd, addr); } else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; @@ -1445,7 +1494,7 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr, /* Ok, finally just insert the thing.. */ get_page(page); inc_mm_counter_fast(mm, mm_counter_file(page)); - page_add_file_rmap(page); + page_add_file_rmap(page, false); set_pte_at(mm, addr, pte, mk_pte(page, prot)); retval = 0; @@ -1711,6 +1760,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long next; unsigned long end = addr + PAGE_ALIGN(size); struct mm_struct *mm = vma->vm_mm; + unsigned long remap_pfn = pfn; int err; /* @@ -1737,7 +1787,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, vma->vm_pgoff = pfn; } - err = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size)); + err = track_pfn_remap(vma, &prot, remap_pfn, addr, PAGE_ALIGN(size)); if (err) return -EINVAL; @@ -1756,7 +1806,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, } while (pgd++, addr = next, addr != end); if (err) - untrack_pfn(vma, pfn, PAGE_ALIGN(size)); + untrack_pfn(vma, remap_pfn, PAGE_ALIGN(size)); return err; } @@ -2020,13 +2070,11 @@ static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page, * case, all we need to do here is to mark the page as writable and update * any related book-keeping. */ -static inline int wp_page_reuse(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long address, - pte_t *page_table, spinlock_t *ptl, pte_t orig_pte, - struct page *page, int page_mkwrite, - int dirty_shared) - __releases(ptl) +static inline int wp_page_reuse(struct fault_env *fe, pte_t orig_pte, + struct page *page, int page_mkwrite, int dirty_shared) + __releases(fe->ptl) { + struct vm_area_struct *vma = fe->vma; pte_t entry; /* * Clear the pages cpupid information as the existing @@ -2036,12 +2084,12 @@ static inline int wp_page_reuse(struct mm_struct *mm, if (page) page_cpupid_xchg_last(page, (1 << LAST_CPUPID_SHIFT) - 1); - flush_cache_page(vma, address, pte_pfn(orig_pte)); + flush_cache_page(vma, fe->address, pte_pfn(orig_pte)); entry = pte_mkyoung(orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); - if (ptep_set_access_flags(vma, address, page_table, entry, 1)) - update_mmu_cache(vma, address, page_table); - pte_unmap_unlock(page_table, ptl); + if (ptep_set_access_flags(vma, fe->address, fe->pte, entry, 1)) + update_mmu_cache(vma, fe->address, fe->pte); + pte_unmap_unlock(fe->pte, fe->ptl); if (dirty_shared) { struct address_space *mapping; @@ -2054,7 +2102,7 @@ static inline int wp_page_reuse(struct mm_struct *mm, VM_BUG_ON_PAGE(PageAnon(page), page); mapping = page->mapping; unlock_page(page); - page_cache_release(page); + put_page(page); if ((dirtied || page_mkwrite) && mapping) { /* @@ -2087,30 +2135,31 @@ static inline int wp_page_reuse(struct mm_struct *mm, * held to the old page, as well as updating the rmap. * - In any case, unlock the PTL and drop the reference we took to the old page. */ -static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - pte_t orig_pte, struct page *old_page) +static int wp_page_copy(struct fault_env *fe, pte_t orig_pte, + struct page *old_page) { + struct vm_area_struct *vma = fe->vma; + struct mm_struct *mm = vma->vm_mm; struct page *new_page = NULL; - spinlock_t *ptl = NULL; pte_t entry; int page_copied = 0; - const unsigned long mmun_start = address & PAGE_MASK; /* For mmu_notifiers */ - const unsigned long mmun_end = mmun_start + PAGE_SIZE; /* For mmu_notifiers */ + const unsigned long mmun_start = fe->address & PAGE_MASK; + const unsigned long mmun_end = mmun_start + PAGE_SIZE; struct mem_cgroup *memcg; if (unlikely(anon_vma_prepare(vma))) goto oom; if (is_zero_pfn(pte_pfn(orig_pte))) { - new_page = alloc_zeroed_user_highpage_movable(vma, address); + new_page = alloc_zeroed_user_highpage_movable(vma, fe->address); if (!new_page) goto oom; } else { - new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, + fe->address); if (!new_page) goto oom; - cow_user_page(new_page, old_page, address, vma); + cow_user_page(new_page, old_page, fe->address, vma); } if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false)) @@ -2123,8 +2172,8 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, /* * Re-check the pte - we dropped the lock */ - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); - if (likely(pte_same(*page_table, orig_pte))) { + fe->pte = pte_offset_map_lock(mm, fe->pmd, fe->address, &fe->ptl); + if (likely(pte_same(*fe->pte, orig_pte))) { if (old_page) { if (!PageAnon(old_page)) { dec_mm_counter_fast(mm, @@ -2134,7 +2183,7 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, } else { inc_mm_counter_fast(mm, MM_ANONPAGES); } - flush_cache_page(vma, address, pte_pfn(orig_pte)); + flush_cache_page(vma, fe->address, pte_pfn(orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* @@ -2143,8 +2192,8 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, * seen in the presence of one thread doing SMC and another * thread doing COW. */ - ptep_clear_flush_notify(vma, address, page_table); - page_add_new_anon_rmap(new_page, vma, address, false); + ptep_clear_flush_notify(vma, fe->address, fe->pte); + page_add_new_anon_rmap(new_page, vma, fe->address, false); mem_cgroup_commit_charge(new_page, memcg, false, false); lru_cache_add_active_or_unevictable(new_page, vma); /* @@ -2152,8 +2201,8 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, * mmu page tables (such as kvm shadow page tables), we want the * new page to be mapped directly into the secondary page table. */ - set_pte_at_notify(mm, address, page_table, entry); - update_mmu_cache(vma, address, page_table); + set_pte_at_notify(mm, fe->address, fe->pte, entry); + update_mmu_cache(vma, fe->address, fe->pte); if (old_page) { /* * Only after switching the pte to the new page may @@ -2188,9 +2237,9 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, } if (new_page) - page_cache_release(new_page); + put_page(new_page); - pte_unmap_unlock(page_table, ptl); + pte_unmap_unlock(fe->pte, fe->ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); if (old_page) { /* @@ -2203,14 +2252,14 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, munlock_vma_page(old_page); unlock_page(old_page); } - page_cache_release(old_page); + put_page(old_page); } return page_copied ? VM_FAULT_WRITE : 0; oom_free_new: - page_cache_release(new_page); + put_page(new_page); oom: if (old_page) - page_cache_release(old_page); + put_page(old_page); return VM_FAULT_OOM; } @@ -2218,56 +2267,55 @@ oom: * Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED * mapping */ -static int wp_pfn_shared(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long address, - pte_t *page_table, spinlock_t *ptl, pte_t orig_pte, - pmd_t *pmd) +static int wp_pfn_shared(struct fault_env *fe, pte_t orig_pte) { + struct vm_area_struct *vma = fe->vma; + if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) { struct vm_fault vmf = { .page = NULL, - .pgoff = linear_page_index(vma, address), - .virtual_address = (void __user *)(address & PAGE_MASK), + .pgoff = linear_page_index(vma, fe->address), + .virtual_address = + (void __user *)(fe->address & PAGE_MASK), .flags = FAULT_FLAG_WRITE | FAULT_FLAG_MKWRITE, }; int ret; - pte_unmap_unlock(page_table, ptl); + pte_unmap_unlock(fe->pte, fe->ptl); ret = vma->vm_ops->pfn_mkwrite(vma, &vmf); if (ret & VM_FAULT_ERROR) return ret; - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); + fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd, fe->address, + &fe->ptl); /* * We might have raced with another page fault while we * released the pte_offset_map_lock. */ - if (!pte_same(*page_table, orig_pte)) { - pte_unmap_unlock(page_table, ptl); + if (!pte_same(*fe->pte, orig_pte)) { + pte_unmap_unlock(fe->pte, fe->ptl); return 0; } } - return wp_page_reuse(mm, vma, address, page_table, ptl, orig_pte, - NULL, 0, 0); + return wp_page_reuse(fe, orig_pte, NULL, 0, 0); } -static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, - pmd_t *pmd, spinlock_t *ptl, pte_t orig_pte, - struct page *old_page) - __releases(ptl) +static int wp_page_shared(struct fault_env *fe, pte_t orig_pte, + struct page *old_page) + __releases(fe->ptl) { + struct vm_area_struct *vma = fe->vma; int page_mkwrite = 0; - page_cache_get(old_page); + get_page(old_page); if (vma->vm_ops && vma->vm_ops->page_mkwrite) { int tmp; - pte_unmap_unlock(page_table, ptl); - tmp = do_page_mkwrite(vma, old_page, address); + pte_unmap_unlock(fe->pte, fe->ptl); + tmp = do_page_mkwrite(vma, old_page, fe->address); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { - page_cache_release(old_page); + put_page(old_page); return tmp; } /* @@ -2276,19 +2324,18 @@ static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma, * they did, we just return, as we can count on the * MMU to tell us if they didn't also make it writable. */ - page_table = pte_offset_map_lock(mm, pmd, address, - &ptl); - if (!pte_same(*page_table, orig_pte)) { + fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd, fe->address, + &fe->ptl); + if (!pte_same(*fe->pte, orig_pte)) { unlock_page(old_page); - pte_unmap_unlock(page_table, ptl); - page_cache_release(old_page); + pte_unmap_unlock(fe->pte, fe->ptl); + put_page(old_page); return 0; } page_mkwrite = 1; } - return wp_page_reuse(mm, vma, address, page_table, ptl, - orig_pte, old_page, page_mkwrite, 1); + return wp_page_reuse(fe, orig_pte, old_page, page_mkwrite, 1); } /* @@ -2309,14 +2356,13 @@ static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma, * but allow concurrent faults), with pte both mapped and locked. * We return with mmap_sem still held, but pte unmapped and unlocked. */ -static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - spinlock_t *ptl, pte_t orig_pte) - __releases(ptl) +static int do_wp_page(struct fault_env *fe, pte_t orig_pte) + __releases(fe->ptl) { + struct vm_area_struct *vma = fe->vma; struct page *old_page; - old_page = vm_normal_page(vma, address, orig_pte); + old_page = vm_normal_page(vma, fe->address, orig_pte); if (!old_page) { /* * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a @@ -2327,12 +2373,10 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, */ if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED)) - return wp_pfn_shared(mm, vma, address, page_table, ptl, - orig_pte, pmd); + return wp_pfn_shared(fe, orig_pte); - pte_unmap_unlock(page_table, ptl); - return wp_page_copy(mm, vma, address, page_table, pmd, - orig_pte, old_page); + pte_unmap_unlock(fe->pte, fe->ptl); + return wp_page_copy(fe, orig_pte, old_page); } /* @@ -2340,46 +2384,48 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, * not dirty accountable. */ if (PageAnon(old_page) && !PageKsm(old_page)) { + int total_mapcount; if (!trylock_page(old_page)) { - page_cache_get(old_page); - pte_unmap_unlock(page_table, ptl); + get_page(old_page); + pte_unmap_unlock(fe->pte, fe->ptl); lock_page(old_page); - page_table = pte_offset_map_lock(mm, pmd, address, - &ptl); - if (!pte_same(*page_table, orig_pte)) { + fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd, + fe->address, &fe->ptl); + if (!pte_same(*fe->pte, orig_pte)) { unlock_page(old_page); - pte_unmap_unlock(page_table, ptl); - page_cache_release(old_page); + pte_unmap_unlock(fe->pte, fe->ptl); + put_page(old_page); return 0; } - page_cache_release(old_page); + put_page(old_page); } - if (reuse_swap_page(old_page)) { - /* - * The page is all ours. Move it to our anon_vma so - * the rmap code will not search our parent or siblings. - * Protected against the rmap code by the page lock. - */ - page_move_anon_rmap(old_page, vma, address); + if (reuse_swap_page(old_page, &total_mapcount)) { + if (total_mapcount == 1) { + /* + * The page is all ours. Move it to + * our anon_vma so the rmap code will + * not search our parent or siblings. + * Protected against the rmap code by + * the page lock. + */ + page_move_anon_rmap(old_page, vma); + } unlock_page(old_page); - return wp_page_reuse(mm, vma, address, page_table, ptl, - orig_pte, old_page, 0, 0); + return wp_page_reuse(fe, orig_pte, old_page, 0, 0); } unlock_page(old_page); } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { - return wp_page_shared(mm, vma, address, page_table, pmd, - ptl, orig_pte, old_page); + return wp_page_shared(fe, orig_pte, old_page); } /* * Ok, we need to copy. Oh, well.. */ - page_cache_get(old_page); + get_page(old_page); - pte_unmap_unlock(page_table, ptl); - return wp_page_copy(mm, vma, address, page_table, pmd, - orig_pte, old_page); + pte_unmap_unlock(fe->pte, fe->ptl); + return wp_page_copy(fe, orig_pte, old_page); } static void unmap_mapping_range_vma(struct vm_area_struct *vma, @@ -2400,7 +2446,6 @@ static inline void unmap_mapping_range_tree(struct rb_root *root, vba = vma->vm_pgoff; vea = vba + vma_pages(vma) - 1; - /* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */ zba = details->first_index; if (zba < vba) zba = vba; @@ -2453,8 +2498,6 @@ void unmap_mapping_range(struct address_space *mapping, if (details.last_index < details.first_index) details.last_index = ULONG_MAX; - - /* DAX uses i_mmap_lock to serialise file truncate vs page fault */ i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap))) unmap_mapping_range_tree(&mapping->i_mmap, &details); @@ -2470,11 +2513,9 @@ EXPORT_SYMBOL(unmap_mapping_range); * We return with the mmap_sem locked or unlocked in the same cases * as does filemap_fault(). */ -static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - unsigned int flags, pte_t orig_pte) +int do_swap_page(struct fault_env *fe, pte_t orig_pte) { - spinlock_t *ptl; + struct vm_area_struct *vma = fe->vma; struct page *page, *swapcache; struct mem_cgroup *memcg; swp_entry_t entry; @@ -2483,17 +2524,17 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, int exclusive = 0; int ret = 0; - if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) + if (!pte_unmap_same(vma->vm_mm, fe->pmd, fe->pte, orig_pte)) goto out; entry = pte_to_swp_entry(orig_pte); if (unlikely(non_swap_entry(entry))) { if (is_migration_entry(entry)) { - migration_entry_wait(mm, pmd, address); + migration_entry_wait(vma->vm_mm, fe->pmd, fe->address); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; } else { - print_bad_pte(vma, address, orig_pte, NULL); + print_bad_pte(vma, fe->address, orig_pte, NULL); ret = VM_FAULT_SIGBUS; } goto out; @@ -2502,14 +2543,15 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, page = lookup_swap_cache(entry); if (!page) { page = swapin_readahead(entry, - GFP_HIGHUSER_MOVABLE, vma, address); + GFP_HIGHUSER_MOVABLE, vma, fe->address); if (!page) { /* * Back out if somebody else faulted in this pte * while we released the pte lock. */ - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); - if (likely(pte_same(*page_table, orig_pte))) + fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd, + fe->address, &fe->ptl); + if (likely(pte_same(*fe->pte, orig_pte))) ret = VM_FAULT_OOM; delayacct_clear_flag(DELAYACCT_PF_SWAPIN); goto unlock; @@ -2518,7 +2560,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Had to read the page from swap area: Major fault */ ret = VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); - mem_cgroup_count_vm_event(mm, PGMAJFAULT); + mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); } else if (PageHWPoison(page)) { /* * hwpoisoned dirty swapcache pages are kept for killing @@ -2531,7 +2573,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, } swapcache = page; - locked = lock_page_or_retry(page, mm, flags); + locked = lock_page_or_retry(page, vma->vm_mm, fe->flags); delayacct_clear_flag(DELAYACCT_PF_SWAPIN); if (!locked) { @@ -2548,14 +2590,15 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(!PageSwapCache(page) || page_private(page) != entry.val)) goto out_page; - page = ksm_might_need_to_copy(page, vma, address); + page = ksm_might_need_to_copy(page, vma, fe->address); if (unlikely(!page)) { ret = VM_FAULT_OOM; page = swapcache; goto out_page; } - if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg, false)) { + if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, + &memcg, false)) { ret = VM_FAULT_OOM; goto out_page; } @@ -2563,8 +2606,9 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, /* * Back out if somebody else already faulted in this pte. */ - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); - if (unlikely(!pte_same(*page_table, orig_pte))) + fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd, fe->address, + &fe->ptl); + if (unlikely(!pte_same(*fe->pte, orig_pte))) goto out_nomap; if (unlikely(!PageUptodate(page))) { @@ -2582,24 +2626,25 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, * must be called after the swap_free(), or it will never succeed. */ - inc_mm_counter_fast(mm, MM_ANONPAGES); - dec_mm_counter_fast(mm, MM_SWAPENTS); + inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); + dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS); pte = mk_pte(page, vma->vm_page_prot); - if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) { + if ((fe->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); - flags &= ~FAULT_FLAG_WRITE; + fe->flags &= ~FAULT_FLAG_WRITE; ret |= VM_FAULT_WRITE; exclusive = RMAP_EXCLUSIVE; } flush_icache_page(vma, page); if (pte_swp_soft_dirty(orig_pte)) pte = pte_mksoft_dirty(pte); - set_pte_at(mm, address, page_table, pte); + set_pte_at(vma->vm_mm, fe->address, fe->pte, pte); if (page == swapcache) { - do_page_add_anon_rmap(page, vma, address, exclusive); + do_page_add_anon_rmap(page, vma, fe->address, exclusive); mem_cgroup_commit_charge(page, memcg, true, false); + activate_page(page); } else { /* ksm created a completely new copy */ - page_add_new_anon_rmap(page, vma, address, false); + page_add_new_anon_rmap(page, vma, fe->address, false); mem_cgroup_commit_charge(page, memcg, false, false); lru_cache_add_active_or_unevictable(page, vma); } @@ -2619,32 +2664,32 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, * parallel locked swapcache. */ unlock_page(swapcache); - page_cache_release(swapcache); + put_page(swapcache); } - if (flags & FAULT_FLAG_WRITE) { - ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte); + if (fe->flags & FAULT_FLAG_WRITE) { + ret |= do_wp_page(fe, pte); if (ret & VM_FAULT_ERROR) ret &= VM_FAULT_ERROR; goto out; } /* No need to invalidate - it was non-present before */ - update_mmu_cache(vma, address, page_table); + update_mmu_cache(vma, fe->address, fe->pte); unlock: - pte_unmap_unlock(page_table, ptl); + pte_unmap_unlock(fe->pte, fe->ptl); out: return ret; out_nomap: mem_cgroup_cancel_charge(page, memcg, false); - pte_unmap_unlock(page_table, ptl); + pte_unmap_unlock(fe->pte, fe->ptl); out_page: unlock_page(page); out_release: - page_cache_release(page); + put_page(page); if (page != swapcache) { unlock_page(swapcache); - page_cache_release(swapcache); + put_page(swapcache); } return ret; } @@ -2688,37 +2733,51 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_sem still held, but pte unmapped and unlocked. */ -static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - unsigned int flags) +static int do_anonymous_page(struct fault_env *fe) { + struct vm_area_struct *vma = fe->vma; struct mem_cgroup *memcg; struct page *page; - spinlock_t *ptl; pte_t entry; - pte_unmap(page_table); - /* File mapping without ->vm_ops ? */ if (vma->vm_flags & VM_SHARED) return VM_FAULT_SIGBUS; /* Check if we need to add a guard page to the stack */ - if (check_stack_guard_page(vma, address) < 0) + if (check_stack_guard_page(vma, fe->address) < 0) return VM_FAULT_SIGSEGV; + /* + * Use pte_alloc() instead of pte_alloc_map(). We can't run + * pte_offset_map() on pmds where a huge pmd might be created + * from a different thread. + * + * pte_alloc_map() is safe to use under down_write(mmap_sem) or when + * parallel threads are excluded by other means. + * + * Here we only have down_read(mmap_sem). + */ + if (pte_alloc(vma->vm_mm, fe->pmd, fe->address)) + return VM_FAULT_OOM; + + /* See the comment in pte_alloc_one_map() */ + if (unlikely(pmd_trans_unstable(fe->pmd))) + return 0; + /* Use the zero-page for reads */ - if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm)) { - entry = pte_mkspecial(pfn_pte(my_zero_pfn(address), + if (!(fe->flags & FAULT_FLAG_WRITE) && + !mm_forbids_zeropage(vma->vm_mm)) { + entry = pte_mkspecial(pfn_pte(my_zero_pfn(fe->address), vma->vm_page_prot)); - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); - if (!pte_none(*page_table)) + fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd, fe->address, + &fe->ptl); + if (!pte_none(*fe->pte)) goto unlock; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { - pte_unmap_unlock(page_table, ptl); - return handle_userfault(vma, address, flags, - VM_UFFD_MISSING); + pte_unmap_unlock(fe->pte, fe->ptl); + return handle_userfault(fe, VM_UFFD_MISSING); } goto setpte; } @@ -2726,11 +2785,11 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Allocate our own private page. */ if (unlikely(anon_vma_prepare(vma))) goto oom; - page = alloc_zeroed_user_highpage_movable(vma, address); + page = alloc_zeroed_user_highpage_movable(vma, fe->address); if (!page) goto oom; - if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg, false)) + if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg, false)) goto oom_free_page; /* @@ -2744,37 +2803,37 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry)); - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); - if (!pte_none(*page_table)) + fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd, fe->address, + &fe->ptl); + if (!pte_none(*fe->pte)) goto release; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { - pte_unmap_unlock(page_table, ptl); + pte_unmap_unlock(fe->pte, fe->ptl); mem_cgroup_cancel_charge(page, memcg, false); - page_cache_release(page); - return handle_userfault(vma, address, flags, - VM_UFFD_MISSING); + put_page(page); + return handle_userfault(fe, VM_UFFD_MISSING); } - inc_mm_counter_fast(mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, address, false); + inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); + page_add_new_anon_rmap(page, vma, fe->address, false); mem_cgroup_commit_charge(page, memcg, false, false); lru_cache_add_active_or_unevictable(page, vma); setpte: - set_pte_at(mm, address, page_table, entry); + set_pte_at(vma->vm_mm, fe->address, fe->pte, entry); /* No need to invalidate - it was non-present before */ - update_mmu_cache(vma, address, page_table); + update_mmu_cache(vma, fe->address, fe->pte); unlock: - pte_unmap_unlock(page_table, ptl); + pte_unmap_unlock(fe->pte, fe->ptl); return 0; release: mem_cgroup_cancel_charge(page, memcg, false); - page_cache_release(page); + put_page(page); goto unlock; oom_free_page: - page_cache_release(page); + put_page(page); oom: return VM_FAULT_OOM; } @@ -2784,16 +2843,16 @@ oom: * released depending on flags and vma->vm_ops->fault() return value. * See filemap_fault() and __lock_page_retry(). */ -static int __do_fault(struct vm_area_struct *vma, unsigned long address, - pgoff_t pgoff, unsigned int flags, - struct page *cow_page, struct page **page) +static int __do_fault(struct fault_env *fe, pgoff_t pgoff, + struct page *cow_page, struct page **page, void **entry) { + struct vm_area_struct *vma = fe->vma; struct vm_fault vmf; int ret; - vmf.virtual_address = (void __user *)(address & PAGE_MASK); + vmf.virtual_address = (void __user *)(fe->address & PAGE_MASK); vmf.pgoff = pgoff; - vmf.flags = flags; + vmf.flags = fe->flags; vmf.page = NULL; vmf.gfp_mask = __get_fault_gfp_mask(vma); vmf.cow_page = cow_page; @@ -2801,13 +2860,15 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address, ret = vma->vm_ops->fault(vma, &vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; - if (!vmf.page) - goto out; + if (ret & VM_FAULT_DAX_LOCKED) { + *entry = vmf.entry; + return ret; + } if (unlikely(PageHWPoison(vmf.page))) { if (ret & VM_FAULT_LOCKED) unlock_page(vmf.page); - page_cache_release(vmf.page); + put_page(vmf.page); return VM_FAULT_HWPOISON; } @@ -2816,46 +2877,172 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address, else VM_BUG_ON_PAGE(!PageLocked(vmf.page), vmf.page); - out: *page = vmf.page; return ret; } +static int pte_alloc_one_map(struct fault_env *fe) +{ + struct vm_area_struct *vma = fe->vma; + + if (!pmd_none(*fe->pmd)) + goto map_pte; + if (fe->prealloc_pte) { + fe->ptl = pmd_lock(vma->vm_mm, fe->pmd); + if (unlikely(!pmd_none(*fe->pmd))) { + spin_unlock(fe->ptl); + goto map_pte; + } + + atomic_long_inc(&vma->vm_mm->nr_ptes); + pmd_populate(vma->vm_mm, fe->pmd, fe->prealloc_pte); + spin_unlock(fe->ptl); + fe->prealloc_pte = 0; + } else if (unlikely(pte_alloc(vma->vm_mm, fe->pmd, fe->address))) { + return VM_FAULT_OOM; + } +map_pte: + /* + * If a huge pmd materialized under us just retry later. Use + * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd + * didn't become pmd_trans_huge under us and then back to pmd_none, as + * a result of MADV_DONTNEED running immediately after a huge pmd fault + * in a different thread of this mm, in turn leading to a misleading + * pmd_trans_huge() retval. All we have to ensure is that it is a + * regular pmd that we can walk with pte_offset_map() and we can do that + * through an atomic read in C, which is what pmd_trans_unstable() + * provides. + */ + if (pmd_trans_unstable(fe->pmd) || pmd_devmap(*fe->pmd)) + return VM_FAULT_NOPAGE; + + fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd, fe->address, + &fe->ptl); + return 0; +} + +#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE + +#define HPAGE_CACHE_INDEX_MASK (HPAGE_PMD_NR - 1) +static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, + unsigned long haddr) +{ + if (((vma->vm_start >> PAGE_SHIFT) & HPAGE_CACHE_INDEX_MASK) != + (vma->vm_pgoff & HPAGE_CACHE_INDEX_MASK)) + return false; + if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) + return false; + return true; +} + +static int do_set_pmd(struct fault_env *fe, struct page *page) +{ + struct vm_area_struct *vma = fe->vma; + bool write = fe->flags & FAULT_FLAG_WRITE; + unsigned long haddr = fe->address & HPAGE_PMD_MASK; + pmd_t entry; + int i, ret; + + if (!transhuge_vma_suitable(vma, haddr)) + return VM_FAULT_FALLBACK; + + ret = VM_FAULT_FALLBACK; + page = compound_head(page); + + fe->ptl = pmd_lock(vma->vm_mm, fe->pmd); + if (unlikely(!pmd_none(*fe->pmd))) + goto out; + + for (i = 0; i < HPAGE_PMD_NR; i++) + flush_icache_page(vma, page + i); + + entry = mk_huge_pmd(page, vma->vm_page_prot); + if (write) + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + + add_mm_counter(vma->vm_mm, MM_FILEPAGES, HPAGE_PMD_NR); + page_add_file_rmap(page, true); + + set_pmd_at(vma->vm_mm, haddr, fe->pmd, entry); + + update_mmu_cache_pmd(vma, haddr, fe->pmd); + + /* fault is handled */ + ret = 0; + count_vm_event(THP_FILE_MAPPED); +out: + spin_unlock(fe->ptl); + return ret; +} +#else +static int do_set_pmd(struct fault_env *fe, struct page *page) +{ + BUILD_BUG(); + return 0; +} +#endif + /** - * do_set_pte - setup new PTE entry for given page and add reverse page mapping. + * alloc_set_pte - setup new PTE entry for given page and add reverse page + * mapping. If needed, the fucntion allocates page table or use pre-allocated. * - * @vma: virtual memory area - * @address: user virtual address + * @fe: fault environment + * @memcg: memcg to charge page (only for private mappings) * @page: page to map - * @pte: pointer to target page table entry - * @write: true, if new entry is writable - * @anon: true, if it's anonymous page * - * Caller must hold page table lock relevant for @pte. + * Caller must take care of unlocking fe->ptl, if fe->pte is non-NULL on return. * * Target users are page handler itself and implementations of * vm_ops->map_pages. */ -void do_set_pte(struct vm_area_struct *vma, unsigned long address, - struct page *page, pte_t *pte, bool write, bool anon) +int alloc_set_pte(struct fault_env *fe, struct mem_cgroup *memcg, + struct page *page) { + struct vm_area_struct *vma = fe->vma; + bool write = fe->flags & FAULT_FLAG_WRITE; pte_t entry; + int ret; + + if (pmd_none(*fe->pmd) && PageTransCompound(page) && + IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) { + /* THP on COW? */ + VM_BUG_ON_PAGE(memcg, page); + + ret = do_set_pmd(fe, page); + if (ret != VM_FAULT_FALLBACK) + return ret; + } + + if (!fe->pte) { + ret = pte_alloc_one_map(fe); + if (ret) + return ret; + } + + /* Re-check under ptl */ + if (unlikely(!pte_none(*fe->pte))) + return VM_FAULT_NOPAGE; flush_icache_page(vma, page); entry = mk_pte(page, vma->vm_page_prot); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); - if (anon) { + /* copy-on-write page */ + if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, address, false); + page_add_new_anon_rmap(page, vma, fe->address, false); + mem_cgroup_commit_charge(page, memcg, false, false); + lru_cache_add_active_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); - page_add_file_rmap(page); + page_add_file_rmap(page, false); } - set_pte_at(vma->vm_mm, address, pte, entry); + set_pte_at(vma->vm_mm, fe->address, fe->pte, entry); /* no need to invalidate: a not-present page won't be cached */ - update_mmu_cache(vma, address, pte); + update_mmu_cache(vma, fe->address, fe->pte); + + return 0; } static unsigned long fault_around_bytes __read_mostly = @@ -2922,57 +3109,68 @@ late_initcall(fault_around_debugfs); * fault_around_pages() value (and therefore to page order). This way it's * easier to guarantee that we don't cross page table boundaries. */ -static void do_fault_around(struct vm_area_struct *vma, unsigned long address, - pte_t *pte, pgoff_t pgoff, unsigned int flags) +static int do_fault_around(struct fault_env *fe, pgoff_t start_pgoff) { - unsigned long start_addr, nr_pages, mask; - pgoff_t max_pgoff; - struct vm_fault vmf; - int off; + unsigned long address = fe->address, nr_pages, mask; + pgoff_t end_pgoff; + int off, ret = 0; nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT; mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK; - start_addr = max(address & mask, vma->vm_start); - off = ((address - start_addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); - pte -= off; - pgoff -= off; + fe->address = max(address & mask, fe->vma->vm_start); + off = ((address - fe->address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); + start_pgoff -= off; /* - * max_pgoff is either end of page table or end of vma - * or fault_around_pages() from pgoff, depending what is nearest. + * end_pgoff is either end of page table or end of vma + * or fault_around_pages() from start_pgoff, depending what is nearest. */ - max_pgoff = pgoff - ((start_addr >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + + end_pgoff = start_pgoff - + ((fe->address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + PTRS_PER_PTE - 1; - max_pgoff = min3(max_pgoff, vma_pages(vma) + vma->vm_pgoff - 1, - pgoff + nr_pages - 1); + end_pgoff = min3(end_pgoff, vma_pages(fe->vma) + fe->vma->vm_pgoff - 1, + start_pgoff + nr_pages - 1); - /* Check if it makes any sense to call ->map_pages */ - while (!pte_none(*pte)) { - if (++pgoff > max_pgoff) - return; - start_addr += PAGE_SIZE; - if (start_addr >= vma->vm_end) - return; - pte++; + if (pmd_none(*fe->pmd)) { + fe->prealloc_pte = pte_alloc_one(fe->vma->vm_mm, fe->address); + if (!fe->prealloc_pte) + goto out; + smp_wmb(); /* See comment in __pte_alloc() */ } - vmf.virtual_address = (void __user *) start_addr; - vmf.pte = pte; - vmf.pgoff = pgoff; - vmf.max_pgoff = max_pgoff; - vmf.flags = flags; - vmf.gfp_mask = __get_fault_gfp_mask(vma); - vma->vm_ops->map_pages(vma, &vmf); + fe->vma->vm_ops->map_pages(fe, start_pgoff, end_pgoff); + + /* preallocated pagetable is unused: free it */ + if (fe->prealloc_pte) { + pte_free(fe->vma->vm_mm, fe->prealloc_pte); + fe->prealloc_pte = 0; + } + /* Huge page is mapped? Page fault is solved */ + if (pmd_trans_huge(*fe->pmd)) { + ret = VM_FAULT_NOPAGE; + goto out; + } + + /* ->map_pages() haven't done anything useful. Cold page cache? */ + if (!fe->pte) + goto out; + + /* check if the page fault is solved */ + fe->pte -= (fe->address >> PAGE_SHIFT) - (address >> PAGE_SHIFT); + if (!pte_none(*fe->pte)) + ret = VM_FAULT_NOPAGE; + pte_unmap_unlock(fe->pte, fe->ptl); +out: + fe->address = address; + fe->pte = NULL; + return ret; } -static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, - pgoff_t pgoff, unsigned int flags, pte_t orig_pte) +static int do_read_fault(struct fault_env *fe, pgoff_t pgoff) { + struct vm_area_struct *vma = fe->vma; struct page *fault_page; - spinlock_t *ptl; - pte_t *pte; int ret = 0; /* @@ -2981,109 +3179,80 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, * something). */ if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { - pte = pte_offset_map_lock(mm, pmd, address, &ptl); - do_fault_around(vma, address, pte, pgoff, flags); - if (!pte_same(*pte, orig_pte)) - goto unlock_out; - pte_unmap_unlock(pte, ptl); + ret = do_fault_around(fe, pgoff); + if (ret) + return ret; } - ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page); + ret = __do_fault(fe, pgoff, NULL, &fault_page, NULL); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; - pte = pte_offset_map_lock(mm, pmd, address, &ptl); - if (unlikely(!pte_same(*pte, orig_pte))) { - pte_unmap_unlock(pte, ptl); - unlock_page(fault_page); - page_cache_release(fault_page); - return ret; - } - do_set_pte(vma, address, fault_page, pte, false, false); + ret |= alloc_set_pte(fe, NULL, fault_page); + if (fe->pte) + pte_unmap_unlock(fe->pte, fe->ptl); unlock_page(fault_page); -unlock_out: - pte_unmap_unlock(pte, ptl); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + put_page(fault_page); return ret; } -static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, - pgoff_t pgoff, unsigned int flags, pte_t orig_pte) +static int do_cow_fault(struct fault_env *fe, pgoff_t pgoff) { + struct vm_area_struct *vma = fe->vma; struct page *fault_page, *new_page; + void *fault_entry; struct mem_cgroup *memcg; - spinlock_t *ptl; - pte_t *pte; int ret; if (unlikely(anon_vma_prepare(vma))) return VM_FAULT_OOM; - new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, fe->address); if (!new_page) return VM_FAULT_OOM; - if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false)) { - page_cache_release(new_page); + if (mem_cgroup_try_charge(new_page, vma->vm_mm, GFP_KERNEL, + &memcg, false)) { + put_page(new_page); return VM_FAULT_OOM; } - ret = __do_fault(vma, address, pgoff, flags, new_page, &fault_page); + ret = __do_fault(fe, pgoff, new_page, &fault_page, &fault_entry); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; - if (fault_page) - copy_user_highpage(new_page, fault_page, address, vma); + if (!(ret & VM_FAULT_DAX_LOCKED)) + copy_user_highpage(new_page, fault_page, fe->address, vma); __SetPageUptodate(new_page); - pte = pte_offset_map_lock(mm, pmd, address, &ptl); - if (unlikely(!pte_same(*pte, orig_pte))) { - pte_unmap_unlock(pte, ptl); - if (fault_page) { - unlock_page(fault_page); - page_cache_release(fault_page); - } else { - /* - * The fault handler has no page to lock, so it holds - * i_mmap_lock for read to protect against truncate. - */ - i_mmap_unlock_read(vma->vm_file->f_mapping); - } - goto uncharge_out; - } - do_set_pte(vma, address, new_page, pte, true, true); - mem_cgroup_commit_charge(new_page, memcg, false, false); - lru_cache_add_active_or_unevictable(new_page, vma); - pte_unmap_unlock(pte, ptl); - if (fault_page) { + ret |= alloc_set_pte(fe, memcg, new_page); + if (fe->pte) + pte_unmap_unlock(fe->pte, fe->ptl); + if (!(ret & VM_FAULT_DAX_LOCKED)) { unlock_page(fault_page); - page_cache_release(fault_page); + put_page(fault_page); } else { - /* - * The fault handler has no page to lock, so it holds - * i_mmap_lock for read to protect against truncate. - */ - i_mmap_unlock_read(vma->vm_file->f_mapping); + dax_unlock_mapping_entry(vma->vm_file->f_mapping, pgoff); } + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + goto uncharge_out; return ret; uncharge_out: mem_cgroup_cancel_charge(new_page, memcg, false); - page_cache_release(new_page); + put_page(new_page); return ret; } -static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, - pgoff_t pgoff, unsigned int flags, pte_t orig_pte) +static int do_shared_fault(struct fault_env *fe, pgoff_t pgoff) { + struct vm_area_struct *vma = fe->vma; struct page *fault_page; struct address_space *mapping; - spinlock_t *ptl; - pte_t *pte; int dirtied = 0; int ret, tmp; - ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page); + ret = __do_fault(fe, pgoff, NULL, &fault_page, NULL); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; @@ -3093,23 +3262,23 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, */ if (vma->vm_ops->page_mkwrite) { unlock_page(fault_page); - tmp = do_page_mkwrite(vma, fault_page, address); + tmp = do_page_mkwrite(vma, fault_page, fe->address); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { - page_cache_release(fault_page); + put_page(fault_page); return tmp; } } - pte = pte_offset_map_lock(mm, pmd, address, &ptl); - if (unlikely(!pte_same(*pte, orig_pte))) { - pte_unmap_unlock(pte, ptl); + ret |= alloc_set_pte(fe, NULL, fault_page); + if (fe->pte) + pte_unmap_unlock(fe->pte, fe->ptl); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | + VM_FAULT_RETRY))) { unlock_page(fault_page); - page_cache_release(fault_page); + put_page(fault_page); return ret; } - do_set_pte(vma, address, fault_page, pte, true, false); - pte_unmap_unlock(pte, ptl); if (set_page_dirty(fault_page)) dirtied = 1; @@ -3141,23 +3310,19 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, * The mmap_sem may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ -static int do_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - unsigned int flags, pte_t orig_pte) +static int do_fault(struct fault_env *fe) { - pgoff_t pgoff = linear_page_index(vma, address); + struct vm_area_struct *vma = fe->vma; + pgoff_t pgoff = linear_page_index(vma, fe->address); - pte_unmap(page_table); /* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */ if (!vma->vm_ops->fault) return VM_FAULT_SIGBUS; - if (!(flags & FAULT_FLAG_WRITE)) - return do_read_fault(mm, vma, address, pmd, pgoff, flags, - orig_pte); + if (!(fe->flags & FAULT_FLAG_WRITE)) + return do_read_fault(fe, pgoff); if (!(vma->vm_flags & VM_SHARED)) - return do_cow_fault(mm, vma, address, pmd, pgoff, flags, - orig_pte); - return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); + return do_cow_fault(fe, pgoff); + return do_shared_fault(fe, pgoff); } static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, @@ -3175,11 +3340,10 @@ static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, return mpol_misplaced(page, vma, addr); } -static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t pte, pte_t *ptep, pmd_t *pmd) +static int do_numa_page(struct fault_env *fe, pte_t pte) { + struct vm_area_struct *vma = fe->vma; struct page *page = NULL; - spinlock_t *ptl; int page_nid = -1; int last_cpupid; int target_nid; @@ -3199,10 +3363,10 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, * page table entry is not accessible, so there would be no * concurrent hardware modifications to the PTE. */ - ptl = pte_lockptr(mm, pmd); - spin_lock(ptl); - if (unlikely(!pte_same(*ptep, pte))) { - pte_unmap_unlock(ptep, ptl); + fe->ptl = pte_lockptr(vma->vm_mm, fe->pmd); + spin_lock(fe->ptl); + if (unlikely(!pte_same(*fe->pte, pte))) { + pte_unmap_unlock(fe->pte, fe->ptl); goto out; } @@ -3211,18 +3375,18 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, pte = pte_mkyoung(pte); if (was_writable) pte = pte_mkwrite(pte); - set_pte_at(mm, addr, ptep, pte); - update_mmu_cache(vma, addr, ptep); + set_pte_at(vma->vm_mm, fe->address, fe->pte, pte); + update_mmu_cache(vma, fe->address, fe->pte); - page = vm_normal_page(vma, addr, pte); + page = vm_normal_page(vma, fe->address, pte); if (!page) { - pte_unmap_unlock(ptep, ptl); + pte_unmap_unlock(fe->pte, fe->ptl); return 0; } /* TODO: handle PTE-mapped THP */ if (PageCompound(page)) { - pte_unmap_unlock(ptep, ptl); + pte_unmap_unlock(fe->pte, fe->ptl); return 0; } @@ -3246,8 +3410,9 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, last_cpupid = page_cpupid_last(page); page_nid = page_to_nid(page); - target_nid = numa_migrate_prep(page, vma, addr, page_nid, &flags); - pte_unmap_unlock(ptep, ptl); + target_nid = numa_migrate_prep(page, vma, fe->address, page_nid, + &flags); + pte_unmap_unlock(fe->pte, fe->ptl); if (target_nid == -1) { put_page(page); goto out; @@ -3267,24 +3432,29 @@ out: return 0; } -static int create_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, unsigned int flags) +static int create_huge_pmd(struct fault_env *fe) { + struct vm_area_struct *vma = fe->vma; if (vma_is_anonymous(vma)) - return do_huge_pmd_anonymous_page(mm, vma, address, pmd, flags); + return do_huge_pmd_anonymous_page(fe); if (vma->vm_ops->pmd_fault) - return vma->vm_ops->pmd_fault(vma, address, pmd, flags); + return vma->vm_ops->pmd_fault(vma, fe->address, fe->pmd, + fe->flags); return VM_FAULT_FALLBACK; } -static int wp_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, pmd_t orig_pmd, - unsigned int flags) +static int wp_huge_pmd(struct fault_env *fe, pmd_t orig_pmd) { - if (vma_is_anonymous(vma)) - return do_huge_pmd_wp_page(mm, vma, address, pmd, orig_pmd); - if (vma->vm_ops->pmd_fault) - return vma->vm_ops->pmd_fault(vma, address, pmd, flags); + if (vma_is_anonymous(fe->vma)) + return do_huge_pmd_wp_page(fe, orig_pmd); + if (fe->vma->vm_ops->pmd_fault) + return fe->vma->vm_ops->pmd_fault(fe->vma, fe->address, fe->pmd, + fe->flags); + + /* COW handled on pte level: split pmd */ + VM_BUG_ON_VMA(fe->vma->vm_flags & VM_SHARED, fe->vma); + split_huge_pmd(fe->vma, fe->pmd, fe->address); + return VM_FAULT_FALLBACK; } @@ -3297,59 +3467,79 @@ static int wp_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma, * with external mmu caches can use to update those (ie the Sparc or * PowerPC hashed page tables that act as extended TLBs). * - * We enter with non-exclusive mmap_sem (to exclude vma changes, - * but allow concurrent faults), and pte mapped but not yet locked. - * We return with pte unmapped and unlocked. + * We enter with non-exclusive mmap_sem (to exclude vma changes, but allow + * concurrent faults). * - * The mmap_sem may have been released depending on flags and our - * return value. See filemap_fault() and __lock_page_or_retry(). + * The mmap_sem may have been released depending on flags and our return value. + * See filemap_fault() and __lock_page_or_retry(). */ -static int handle_pte_fault(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long address, - pte_t *pte, pmd_t *pmd, unsigned int flags) +static int handle_pte_fault(struct fault_env *fe) { pte_t entry; - spinlock_t *ptl; - /* - * some architectures can have larger ptes than wordsize, - * e.g.ppc44x-defconfig has CONFIG_PTE_64BIT=y and CONFIG_32BIT=y, - * so READ_ONCE or ACCESS_ONCE cannot guarantee atomic accesses. - * The code below just needs a consistent view for the ifs and - * we later double check anyway with the ptl lock held. So here - * a barrier will do. - */ - entry = *pte; - barrier(); - if (!pte_present(entry)) { + if (unlikely(pmd_none(*fe->pmd))) { + /* + * Leave __pte_alloc() until later: because vm_ops->fault may + * want to allocate huge page, and if we expose page table + * for an instant, it will be difficult to retract from + * concurrent faults and from rmap lookups. + */ + fe->pte = NULL; + } else { + /* See comment in pte_alloc_one_map() */ + if (pmd_trans_unstable(fe->pmd) || pmd_devmap(*fe->pmd)) + return 0; + /* + * A regular pmd is established and it can't morph into a huge + * pmd from under us anymore at this point because we hold the + * mmap_sem read mode and khugepaged takes it in write mode. + * So now it's safe to run pte_offset_map(). + */ + fe->pte = pte_offset_map(fe->pmd, fe->address); + + entry = *fe->pte; + + /* + * some architectures can have larger ptes than wordsize, + * e.g.ppc44x-defconfig has CONFIG_PTE_64BIT=y and + * CONFIG_32BIT=y, so READ_ONCE or ACCESS_ONCE cannot guarantee + * atomic accesses. The code below just needs a consistent + * view for the ifs and we later double check anyway with the + * ptl lock held. So here a barrier will do. + */ + barrier(); if (pte_none(entry)) { - if (vma_is_anonymous(vma)) - return do_anonymous_page(mm, vma, address, - pte, pmd, flags); - else - return do_fault(mm, vma, address, pte, pmd, - flags, entry); + pte_unmap(fe->pte); + fe->pte = NULL; } - return do_swap_page(mm, vma, address, - pte, pmd, flags, entry); } + if (!fe->pte) { + if (vma_is_anonymous(fe->vma)) + return do_anonymous_page(fe); + else + return do_fault(fe); + } + + if (!pte_present(entry)) + return do_swap_page(fe, entry); + if (pte_protnone(entry)) - return do_numa_page(mm, vma, address, entry, pte, pmd); + return do_numa_page(fe, entry); - ptl = pte_lockptr(mm, pmd); - spin_lock(ptl); - if (unlikely(!pte_same(*pte, entry))) + fe->ptl = pte_lockptr(fe->vma->vm_mm, fe->pmd); + spin_lock(fe->ptl); + if (unlikely(!pte_same(*fe->pte, entry))) goto unlock; - if (flags & FAULT_FLAG_WRITE) { + if (fe->flags & FAULT_FLAG_WRITE) { if (!pte_write(entry)) - return do_wp_page(mm, vma, address, - pte, pmd, ptl, entry); + return do_wp_page(fe, entry); entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); - if (ptep_set_access_flags(vma, address, pte, entry, flags & FAULT_FLAG_WRITE)) { - update_mmu_cache(vma, address, pte); + if (ptep_set_access_flags(fe->vma, fe->address, fe->pte, entry, + fe->flags & FAULT_FLAG_WRITE)) { + update_mmu_cache(fe->vma, fe->address, fe->pte); } else { /* * This is needed only for protection faults but the arch code @@ -3357,11 +3547,11 @@ static int handle_pte_fault(struct mm_struct *mm, * This still avoids useless tlb flushes for .text page faults * with threads. */ - if (flags & FAULT_FLAG_WRITE) - flush_tlb_fix_spurious_fault(vma, address); + if (fe->flags & FAULT_FLAG_WRITE) + flush_tlb_fix_spurious_fault(fe->vma, fe->address); } unlock: - pte_unmap_unlock(pte, ptl); + pte_unmap_unlock(fe->pte, fe->ptl); return 0; } @@ -3371,87 +3561,51 @@ unlock: * The mmap_sem may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ -static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, unsigned int flags) +static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, + unsigned int flags) { + struct fault_env fe = { + .vma = vma, + .address = address, + .flags = flags, + }; + struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE, - flags & FAULT_FLAG_INSTRUCTION, - flags & FAULT_FLAG_REMOTE)) - return VM_FAULT_SIGSEGV; - - if (unlikely(is_vm_hugetlb_page(vma))) - return hugetlb_fault(mm, vma, address, flags); pgd = pgd_offset(mm, address); pud = pud_alloc(mm, pgd, address); if (!pud) return VM_FAULT_OOM; - pmd = pmd_alloc(mm, pud, address); - if (!pmd) + fe.pmd = pmd_alloc(mm, pud, address); + if (!fe.pmd) return VM_FAULT_OOM; - if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) { - int ret = create_huge_pmd(mm, vma, address, pmd, flags); + if (pmd_none(*fe.pmd) && transparent_hugepage_enabled(vma)) { + int ret = create_huge_pmd(&fe); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { - pmd_t orig_pmd = *pmd; + pmd_t orig_pmd = *fe.pmd; int ret; barrier(); if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) { - unsigned int dirty = flags & FAULT_FLAG_WRITE; - if (pmd_protnone(orig_pmd)) - return do_huge_pmd_numa_page(mm, vma, address, - orig_pmd, pmd); + return do_huge_pmd_numa_page(&fe, orig_pmd); - if (dirty && !pmd_write(orig_pmd)) { - ret = wp_huge_pmd(mm, vma, address, pmd, - orig_pmd, flags); + if ((fe.flags & FAULT_FLAG_WRITE) && + !pmd_write(orig_pmd)) { + ret = wp_huge_pmd(&fe, orig_pmd); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { - huge_pmd_set_accessed(mm, vma, address, pmd, - orig_pmd, dirty); + huge_pmd_set_accessed(&fe, orig_pmd); return 0; } } } - /* - * Use pte_alloc() instead of pte_alloc_map, because we can't - * run pte_offset_map on the pmd, if an huge pmd could - * materialize from under us from a different thread. - */ - if (unlikely(pte_alloc(mm, pmd, address))) - return VM_FAULT_OOM; - /* - * If a huge pmd materialized under us just retry later. Use - * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd - * didn't become pmd_trans_huge under us and then back to pmd_none, as - * a result of MADV_DONTNEED running immediately after a huge pmd fault - * in a different thread of this mm, in turn leading to a misleading - * pmd_trans_huge() retval. All we have to ensure is that it is a - * regular pmd that we can walk with pte_offset_map() and we can do that - * through an atomic read in C, which is what pmd_trans_unstable() - * provides. - */ - if (unlikely(pmd_trans_unstable(pmd) || pmd_devmap(*pmd))) - return 0; - /* - * A regular pmd is established and it can't morph into a huge pmd - * from under us anymore at this point because we hold the mmap_sem - * read mode and khugepaged takes it in write mode. So now it's - * safe to run pte_offset_map(). - */ - pte = pte_offset_map(pmd, address); - - return handle_pte_fault(mm, vma, address, pte, pmd, flags); + return handle_pte_fault(&fe); } /* @@ -3460,15 +3614,15 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, * The mmap_sem may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ -int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, unsigned int flags) +int handle_mm_fault(struct vm_area_struct *vma, unsigned long address, + unsigned int flags) { int ret; __set_current_state(TASK_RUNNING); count_vm_event(PGFAULT); - mem_cgroup_count_vm_event(mm, PGFAULT); + mem_cgroup_count_vm_event(vma->vm_mm, PGFAULT); /* do counter updates before entering really critical section. */ check_sync_rss_stat(current); @@ -3480,7 +3634,15 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (flags & FAULT_FLAG_USER) mem_cgroup_oom_enable(); - ret = __handle_mm_fault(mm, vma, address, flags); + if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE, + flags & FAULT_FLAG_INSTRUCTION, + flags & FAULT_FLAG_REMOTE)) + return VM_FAULT_SIGSEGV; + + if (unlikely(is_vm_hugetlb_page(vma))) + ret = hugetlb_fault(vma->vm_mm, vma, address, flags); + else + ret = __handle_mm_fault(vma, address, flags); if (flags & FAULT_FLAG_USER) { mem_cgroup_oom_disable(); @@ -3736,7 +3898,7 @@ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, buf, maddr + offset, bytes); } kunmap(page); - page_cache_release(page); + put_page(page); } len -= bytes; buf += bytes; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index aa34431c3f31..3894b65b1555 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -78,9 +78,24 @@ static struct { #define memhp_lock_acquire() lock_map_acquire(&mem_hotplug.dep_map) #define memhp_lock_release() lock_map_release(&mem_hotplug.dep_map) +#ifndef CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE bool memhp_auto_online; +#else +bool memhp_auto_online = true; +#endif EXPORT_SYMBOL_GPL(memhp_auto_online); +static int __init setup_memhp_default_state(char *str) +{ + if (!strcmp(str, "online")) + memhp_auto_online = true; + else if (!strcmp(str, "offline")) + memhp_auto_online = false; + + return 1; +} +__setup("memhp_default_state=", setup_memhp_default_state); + void get_online_mems(void) { might_sleep(); @@ -248,7 +263,7 @@ static void register_page_bootmem_info_section(unsigned long start_pfn) } #endif /* !CONFIG_SPARSEMEM_VMEMMAP */ -void register_page_bootmem_info_node(struct pglist_data *pgdat) +void __init register_page_bootmem_info_node(struct pglist_data *pgdat) { unsigned long i, pfn, end_pfn, nr_pages; int node = pgdat->node_id; @@ -285,7 +300,7 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat) * multiple nodes we check that this pfn does not already * reside in some other nodes. */ - if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node)) + if (pfn_valid(pfn) && (early_pfn_to_nid(pfn) == node)) register_page_bootmem_info_section(pfn); } } @@ -434,6 +449,25 @@ out_fail: return -1; } +static struct zone * __meminit move_pfn_range(int zone_shift, + unsigned long start_pfn, unsigned long end_pfn) +{ + struct zone *zone = page_zone(pfn_to_page(start_pfn)); + int ret = 0; + + if (zone_shift < 0) + ret = move_pfn_range_left(zone + zone_shift, zone, + start_pfn, end_pfn); + else if (zone_shift) + ret = move_pfn_range_right(zone, zone + zone_shift, + start_pfn, end_pfn); + + if (ret) + return NULL; + + return zone + zone_shift; +} + static void __meminit grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn, unsigned long end_pfn) { @@ -1013,6 +1047,37 @@ static void node_states_set_node(int node, struct memory_notify *arg) node_set_state(node, N_MEMORY); } +int zone_can_shift(unsigned long pfn, unsigned long nr_pages, + enum zone_type target) +{ + struct zone *zone = page_zone(pfn_to_page(pfn)); + enum zone_type idx = zone_idx(zone); + int i; + + if (idx < target) { + /* pages must be at end of current zone */ + if (pfn + nr_pages != zone_end_pfn(zone)) + return 0; + + /* no zones in use between current zone and target */ + for (i = idx + 1; i < target; i++) + if (zone_is_initialized(zone - idx + i)) + return 0; + } + + if (target < idx) { + /* pages must be at beginning of current zone */ + if (pfn != zone->zone_start_pfn) + return 0; + + /* no zones in use between current zone and target */ + for (i = target + 1; i < idx; i++) + if (zone_is_initialized(zone - idx + i)) + return 0; + } + + return target - idx; +} /* Must be protected by mem_hotplug_begin() */ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type) @@ -1024,6 +1089,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ int nid; int ret; struct memory_notify arg; + int zone_shift = 0; /* * This doesn't need a lock to do pfn_to_page(). @@ -1037,19 +1103,14 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ !can_online_high_movable(zone)) return -EINVAL; - if (online_type == MMOP_ONLINE_KERNEL && - zone_idx(zone) == ZONE_MOVABLE) { - if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages)) - return -EINVAL; - } - if (online_type == MMOP_ONLINE_MOVABLE && - zone_idx(zone) == ZONE_MOVABLE - 1) { - if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages)) - return -EINVAL; - } + if (online_type == MMOP_ONLINE_KERNEL) + zone_shift = zone_can_shift(pfn, nr_pages, ZONE_NORMAL); + else if (online_type == MMOP_ONLINE_MOVABLE) + zone_shift = zone_can_shift(pfn, nr_pages, ZONE_MOVABLE); - /* Previous code may changed the zone of the pfn range */ - zone = page_zone(pfn_to_page(pfn)); + zone = move_pfn_range(zone_shift, pfn, pfn + nr_pages); + if (!zone) + return -EINVAL; arg.start_pfn = pfn; arg.nr_pages = nr_pages; @@ -1148,9 +1209,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) arch_refresh_nodedata(nid, pgdat); } else { - /* Reset the nr_zones and classzone_idx to 0 before reuse */ + /* Reset the nr_zones, order and classzone_idx before reuse */ pgdat->nr_zones = 0; - pgdat->classzone_idx = 0; + pgdat->kswapd_order = 0; + pgdat->kswapd_classzone_idx = 0; } /* we can use NODE_DATA(nid) from here */ @@ -1410,7 +1472,7 @@ static struct page *next_active_pageblock(struct page *page) } /* Checks if this range of memory is likely to be hot-removable. */ -int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) +bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) { struct page *page = pfn_to_page(start_pfn); struct page *end_page = page + nr_pages; @@ -1418,12 +1480,12 @@ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) /* Check the starting page of each pageblock within the range */ for (; page < end_page; page = next_active_pageblock(page)) { if (!is_pageblock_removable_nolock(page)) - return 0; + return false; cond_resched(); } /* All pageblocks in the memory block are likely to be hot-removable */ - return 1; + return true; } /* @@ -1486,6 +1548,37 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end) return 0; } +static struct page *new_node_page(struct page *page, unsigned long private, + int **result) +{ + gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE; + int nid = page_to_nid(page); + nodemask_t nmask = node_online_map; + struct page *new_page; + + /* + * TODO: allocate a destination hugepage from a nearest neighbor node, + * accordance with memory policy of the user process if possible. For + * now as a simple work-around, we use the next node for destination. + */ + if (PageHuge(page)) + return alloc_huge_page_node(page_hstate(compound_head(page)), + next_node_in(nid, nmask)); + + node_clear(nid, nmask); + if (PageHighMem(page) + || (zone_idx(page_zone(page)) == ZONE_MOVABLE)) + gfp_mask |= __GFP_HIGHMEM; + + new_page = __alloc_pages_nodemask(gfp_mask, 0, + node_zonelist(nid, gfp_mask), &nmask); + if (!new_page) + new_page = __alloc_pages(gfp_mask, 0, + node_zonelist(nid, gfp_mask)); + + return new_page; +} + #define NR_OFFLINE_AT_ONCE_PAGES (256) static int do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) @@ -1525,7 +1618,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) put_page(page); list_add_tail(&page->lru, &source); move_pages--; - inc_zone_page_state(page, NR_ISOLATED_ANON + + inc_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); } else { @@ -1549,11 +1642,8 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) goto out; } - /* - * alloc_migrate_target should be improooooved!! - * migrate_pages returns # of failed pages. - */ - ret = migrate_pages(&source, alloc_migrate_target, NULL, 0, + /* Allocate a new page from the nearest neighbor node */ + ret = migrate_pages(&source, new_node_page, NULL, 0, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); if (ret) putback_movable_pages(&source); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 36cc01bc950a..d8c4e38fb5f4 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -97,7 +97,6 @@ #include <asm/tlbflush.h> #include <asm/uaccess.h> -#include <linux/random.h> #include "internal.h" @@ -347,9 +346,7 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes, BUG(); if (!node_isset(current->il_next, tmp)) { - current->il_next = next_node(current->il_next, tmp); - if (current->il_next >= MAX_NUMNODES) - current->il_next = first_node(tmp); + current->il_next = next_node_in(current->il_next, tmp); if (current->il_next >= MAX_NUMNODES) current->il_next = numa_node_id(); } @@ -515,6 +512,8 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, } } + if (pmd_trans_unstable(pmd)) + return 0; retry: pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) { @@ -532,7 +531,7 @@ retry: nid = page_to_nid(page); if (node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT)) continue; - if (PageTransCompound(page) && PageAnon(page)) { + if (PageTransCompound(page)) { get_page(page); pte_unmap_unlock(pte, ptl); lock_page(page); @@ -963,7 +962,7 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist, if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) { if (!isolate_lru_page(page)) { list_add_tail(&page->lru, pagelist); - inc_zone_page_state(page, NR_ISOLATED_ANON + + inc_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); } } @@ -1709,9 +1708,7 @@ static unsigned interleave_nodes(struct mempolicy *policy) struct task_struct *me = current; nid = me->il_next; - next = next_node(nid, policy->v.nodes); - if (next >= MAX_NUMNODES) - next = first_node(policy->v.nodes); + next = next_node_in(nid, policy->v.nodes); if (next < MAX_NUMNODES) me->il_next = next; return nid; @@ -1744,18 +1741,18 @@ unsigned int mempolicy_slab_node(void) return interleave_nodes(policy); case MPOL_BIND: { + struct zoneref *z; + /* * Follow bind policy behavior and start allocation at the * first node. */ struct zonelist *zonelist; - struct zone *zone; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); zonelist = &NODE_DATA(node)->node_zonelists[0]; - (void)first_zones_zonelist(zonelist, highest_zoneidx, - &policy->v.nodes, - &zone); - return zone ? zone->node : node; + z = first_zones_zonelist(zonelist, highest_zoneidx, + &policy->v.nodes); + return z->zone ? z->zone->node : node; } default: @@ -1763,23 +1760,25 @@ unsigned int mempolicy_slab_node(void) } } -/* Do static interleaving for a VMA with known offset. */ +/* + * Do static interleaving for a VMA with known offset @n. Returns the n'th + * node in pol->v.nodes (starting from n=0), wrapping around if n exceeds the + * number of present nodes. + */ static unsigned offset_il_node(struct mempolicy *pol, - struct vm_area_struct *vma, unsigned long off) + struct vm_area_struct *vma, unsigned long n) { unsigned nnodes = nodes_weight(pol->v.nodes); unsigned target; - int c; - int nid = NUMA_NO_NODE; + int i; + int nid; if (!nnodes) return numa_node_id(); - target = (unsigned int)off % nnodes; - c = 0; - do { + target = (unsigned int)n % nnodes; + nid = first_node(pol->v.nodes); + for (i = 0; i < target; i++) nid = next_node(nid, pol->v.nodes); - c++; - } while (c <= target); return nid; } @@ -1805,21 +1804,6 @@ static inline unsigned interleave_nid(struct mempolicy *pol, return interleave_nodes(pol); } -/* - * Return the bit number of a random bit set in the nodemask. - * (returns NUMA_NO_NODE if nodemask is empty) - */ -int node_random(const nodemask_t *maskp) -{ - int w, bit = NUMA_NO_NODE; - - w = nodes_weight(*maskp); - if (w) - bit = bitmap_ord_to_pos(maskp->bits, - get_random_int() % w, MAX_NUMNODES); - return bit; -} - #ifdef CONFIG_HUGETLBFS /* * huge_zonelist(@vma, @addr, @gfp_flags, @mpol) @@ -2284,7 +2268,7 @@ static void sp_free(struct sp_node *n) int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol; - struct zone *zone; + struct zoneref *z; int curnid = page_to_nid(page); unsigned long pgoff; int thiscpu = raw_smp_processor_id(); @@ -2316,6 +2300,7 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long break; case MPOL_BIND: + /* * allows binding to multiple nodes. * use current page if in policy nodemask, @@ -2324,11 +2309,11 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long */ if (node_isset(curnid, pol->v.nodes)) goto out; - (void)first_zones_zonelist( + z = first_zones_zonelist( node_zonelist(numa_node_id(), GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), - &pol->v.nodes, &zone); - polnid = zone->node; + &pol->v.nodes); + polnid = z->zone->node; break; default: diff --git a/mm/mempool.c b/mm/mempool.c index 9b7a14a791cc..47a659dedd44 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -104,20 +104,16 @@ static inline void poison_element(mempool_t *pool, void *element) static void kasan_poison_element(mempool_t *pool, void *element) { - if (pool->alloc == mempool_alloc_slab) - kasan_slab_free(pool->pool_data, element); - if (pool->alloc == mempool_kmalloc) - kasan_kfree(element); + if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc) + kasan_poison_kfree(element); if (pool->alloc == mempool_alloc_pages) kasan_free_pages(element, (unsigned long)pool->pool_data); } static void kasan_unpoison_element(mempool_t *pool, void *element, gfp_t flags) { - if (pool->alloc == mempool_alloc_slab) - kasan_slab_alloc(pool->pool_data, element, flags); - if (pool->alloc == mempool_kmalloc) - kasan_krealloc(element, (size_t)pool->pool_data, flags); + if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc) + kasan_unpoison_slab(element); if (pool->alloc == mempool_alloc_pages) kasan_alloc_pages(element, (unsigned long)pool->pool_data); } @@ -310,7 +306,7 @@ EXPORT_SYMBOL(mempool_resize); * returns NULL. Note that due to preallocation, this function * *never* fails when called from process contexts. (it might * fail if called from an IRQ context.) - * Note: neither __GFP_NOMEMALLOC nor __GFP_ZERO are supported. + * Note: using __GFP_ZERO is not supported. */ void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) { @@ -319,27 +315,16 @@ void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) wait_queue_t wait; gfp_t gfp_temp; - /* If oom killed, memory reserves are essential to prevent livelock */ - VM_WARN_ON_ONCE(gfp_mask & __GFP_NOMEMALLOC); - /* No element size to zero on allocation */ VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO); - might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM); + gfp_mask |= __GFP_NOMEMALLOC; /* don't allocate emergency reserves */ gfp_mask |= __GFP_NORETRY; /* don't loop in __alloc_pages */ gfp_mask |= __GFP_NOWARN; /* failures are OK */ gfp_temp = gfp_mask & ~(__GFP_DIRECT_RECLAIM|__GFP_IO); repeat_alloc: - if (likely(pool->curr_nr)) { - /* - * Don't allocate from emergency reserves if there are - * elements available. This check is racy, but it will - * be rechecked each loop. - */ - gfp_temp |= __GFP_NOMEMALLOC; - } element = pool->alloc(gfp_temp, pool->pool_data); if (likely(element != NULL)) @@ -363,12 +348,11 @@ repeat_alloc: * We use gfp mask w/o direct reclaim or IO for the first round. If * alloc failed with that and @pool was empty, retry immediately. */ - if ((gfp_temp & ~__GFP_NOMEMALLOC) != gfp_mask) { + if (gfp_temp != gfp_mask) { spin_unlock_irqrestore(&pool->lock, flags); gfp_temp = gfp_mask; goto repeat_alloc; } - gfp_temp = gfp_mask; /* We must not sleep if !__GFP_DIRECT_RECLAIM */ if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) { diff --git a/mm/migrate.c b/mm/migrate.c index 6c822a7b27e0..f7ee04a5ae27 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -31,6 +31,7 @@ #include <linux/vmalloc.h> #include <linux/security.h> #include <linux/backing-dev.h> +#include <linux/compaction.h> #include <linux/syscalls.h> #include <linux/hugetlb.h> #include <linux/hugetlb_cgroup.h> @@ -73,6 +74,81 @@ int migrate_prep_local(void) return 0; } +bool isolate_movable_page(struct page *page, isolate_mode_t mode) +{ + struct address_space *mapping; + + /* + * Avoid burning cycles with pages that are yet under __free_pages(), + * or just got freed under us. + * + * In case we 'win' a race for a movable page being freed under us and + * raise its refcount preventing __free_pages() from doing its job + * the put_page() at the end of this block will take care of + * release this page, thus avoiding a nasty leakage. + */ + if (unlikely(!get_page_unless_zero(page))) + goto out; + + /* + * Check PageMovable before holding a PG_lock because page's owner + * assumes anybody doesn't touch PG_lock of newly allocated page + * so unconditionally grapping the lock ruins page's owner side. + */ + if (unlikely(!__PageMovable(page))) + goto out_putpage; + /* + * As movable pages are not isolated from LRU lists, concurrent + * compaction threads can race against page migration functions + * as well as race against the releasing a page. + * + * In order to avoid having an already isolated movable page + * being (wrongly) re-isolated while it is under migration, + * or to avoid attempting to isolate pages being released, + * lets be sure we have the page lock + * before proceeding with the movable page isolation steps. + */ + if (unlikely(!trylock_page(page))) + goto out_putpage; + + if (!PageMovable(page) || PageIsolated(page)) + goto out_no_isolated; + + mapping = page_mapping(page); + VM_BUG_ON_PAGE(!mapping, page); + + if (!mapping->a_ops->isolate_page(page, mode)) + goto out_no_isolated; + + /* Driver shouldn't use PG_isolated bit of page->flags */ + WARN_ON_ONCE(PageIsolated(page)); + __SetPageIsolated(page); + unlock_page(page); + + return true; + +out_no_isolated: + unlock_page(page); +out_putpage: + put_page(page); +out: + return false; +} + +/* It should be called on page which is PG_movable */ +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); +} + /* * Put previously isolated pages back onto the appropriate lists * from where they were once taken off for compaction/migration. @@ -92,12 +168,25 @@ void putback_movable_pages(struct list_head *l) continue; } list_del(&page->lru); - dec_zone_page_state(page, NR_ISOLATED_ANON + + dec_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); - if (unlikely(isolated_balloon_page(page))) - balloon_page_putback(page); - else + /* + * We isolated non-lru movable page so here we can use + * __PageMovable because LRU page's mapping cannot have + * PAGE_MAPPING_MOVABLE. + */ + if (unlikely(__PageMovable(page))) { + VM_BUG_ON_PAGE(!PageIsolated(page), page); + lock_page(page); + if (PageMovable(page)) + putback_movable_page(page); + else + __ClearPageIsolated(page); + unlock_page(page); + put_page(page); + } else { putback_lru_page(page); + } } } @@ -170,7 +259,7 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, } else if (PageAnon(new)) page_add_anon_rmap(new, vma, addr, false); else - page_add_file_rmap(new); + page_add_file_rmap(new, false); if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new)) mlock_vma_page(new); @@ -332,7 +421,7 @@ int migrate_page_move_mapping(struct address_space *mapping, newpage->index = page->index; newpage->mapping = page->mapping; if (PageSwapBacked(page)) - SetPageSwapBacked(newpage); + __SetPageSwapBacked(newpage); return MIGRATEPAGE_SUCCESS; } @@ -378,7 +467,7 @@ int migrate_page_move_mapping(struct address_space *mapping, newpage->index = page->index; newpage->mapping = page->mapping; if (PageSwapBacked(page)) - SetPageSwapBacked(newpage); + __SetPageSwapBacked(newpage); get_page(newpage); /* add cache reference */ if (PageSwapCache(page)) { @@ -412,25 +501,28 @@ int migrate_page_move_mapping(struct address_space *mapping, * new page and drop references to the old page. * * Note that anonymous pages are accounted for - * via NR_FILE_PAGES and NR_ANON_PAGES if they + * via NR_FILE_PAGES and NR_ANON_MAPPED if they * are mapped to swap space. */ if (newzone != oldzone) { - __dec_zone_state(oldzone, NR_FILE_PAGES); - __inc_zone_state(newzone, NR_FILE_PAGES); + __dec_node_state(oldzone->zone_pgdat, NR_FILE_PAGES); + __inc_node_state(newzone->zone_pgdat, NR_FILE_PAGES); if (PageSwapBacked(page) && !PageSwapCache(page)) { - __dec_zone_state(oldzone, NR_SHMEM); - __inc_zone_state(newzone, NR_SHMEM); + __dec_node_state(oldzone->zone_pgdat, NR_SHMEM); + __inc_node_state(newzone->zone_pgdat, NR_SHMEM); } if (dirty && mapping_cap_account_dirty(mapping)) { - __dec_zone_state(oldzone, NR_FILE_DIRTY); - __inc_zone_state(newzone, NR_FILE_DIRTY); + __dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY); + __dec_zone_state(oldzone, NR_ZONE_WRITE_PENDING); + __inc_node_state(newzone->zone_pgdat, NR_FILE_DIRTY); + __inc_zone_state(newzone, NR_ZONE_WRITE_PENDING); } } local_irq_enable(); return MIGRATEPAGE_SUCCESS; } +EXPORT_SYMBOL(migrate_page_move_mapping); /* * The expected number of remaining references is the same as that @@ -586,13 +678,14 @@ void migrate_page_copy(struct page *newpage, struct page *page) mem_cgroup_migrate(page, newpage); } +EXPORT_SYMBOL(migrate_page_copy); /************************************************************ * Migration functions ***********************************************************/ /* - * Common logic to directly migrate a single page suitable for + * Common logic to directly migrate a single LRU page suitable for * pages that do not use PagePrivate/PagePrivate2. * * Pages are locked upon entry and exit. @@ -755,33 +848,72 @@ static int move_to_new_page(struct page *newpage, struct page *page, enum migrate_mode mode) { struct address_space *mapping; - int rc; + int rc = -EAGAIN; + bool is_lru = !__PageMovable(page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); mapping = page_mapping(page); - if (!mapping) - rc = migrate_page(mapping, newpage, page, mode); - else if (mapping->a_ops->migratepage) + + if (likely(is_lru)) { + if (!mapping) + rc = migrate_page(mapping, newpage, page, mode); + else if (mapping->a_ops->migratepage) + /* + * Most pages have a mapping and most filesystems + * provide a migratepage callback. Anonymous pages + * are part of swap space which also has its own + * migratepage callback. This is the most common path + * for page migration. + */ + rc = mapping->a_ops->migratepage(mapping, newpage, + page, mode); + else + rc = fallback_migrate_page(mapping, newpage, + page, mode); + } else { /* - * Most pages have a mapping and most filesystems provide a - * migratepage callback. Anonymous pages are part of swap - * space which also has its own migratepage callback. This - * is the most common path for page migration. + * In case of non-lru page, it could be released after + * isolation step. In that case, we shouldn't try migration. */ - rc = mapping->a_ops->migratepage(mapping, newpage, page, mode); - else - rc = fallback_migrate_page(mapping, newpage, page, mode); + VM_BUG_ON_PAGE(!PageIsolated(page), page); + if (!PageMovable(page)) { + rc = MIGRATEPAGE_SUCCESS; + __ClearPageIsolated(page); + goto out; + } + + rc = mapping->a_ops->migratepage(mapping, newpage, + page, mode); + WARN_ON_ONCE(rc == MIGRATEPAGE_SUCCESS && + !PageIsolated(page)); + } /* * When successful, old pagecache page->mapping must be cleared before * page is freed; but stats require that PageAnon be left as PageAnon. */ if (rc == MIGRATEPAGE_SUCCESS) { - if (!PageAnon(page)) + if (__PageMovable(page)) { + VM_BUG_ON_PAGE(!PageIsolated(page), page); + + /* + * We clear PG_movable under page_lock so any compactor + * cannot try to migrate this page. + */ + __ClearPageIsolated(page); + } + + /* + * Anonymous and movable page->mapping will be cleard by + * free_pages_prepare so don't reset it here for keeping + * the type to work PageAnon, for example. + */ + if (!PageMappingFlags(page)) page->mapping = NULL; } +out: return rc; } @@ -791,6 +923,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, int rc = -EAGAIN; int page_was_mapped = 0; struct anon_vma *anon_vma = NULL; + bool is_lru = !__PageMovable(page); if (!trylock_page(page)) { if (!force || mode == MIGRATE_ASYNC) @@ -859,15 +992,8 @@ static int __unmap_and_move(struct page *page, struct page *newpage, if (unlikely(!trylock_page(newpage))) goto out_unlock; - if (unlikely(isolated_balloon_page(page))) { - /* - * A ballooned page does not need any special attention from - * physical to virtual reverse mapping procedures. - * Skip any attempt to unmap PTEs or to remap swap cache, - * in order to avoid burning cycles at rmap level, and perform - * the page migration right away (proteced by page lock). - */ - rc = balloon_page_migrate(newpage, page, mode); + if (unlikely(!is_lru)) { + rc = move_to_new_page(newpage, page, mode); goto out_unlock_both; } @@ -913,6 +1039,19 @@ out_unlock: put_anon_vma(anon_vma); unlock_page(page); out: + /* + * If migration is successful, decrease refcount of the newpage + * which will not free the page because new page owner increased + * refcounter. As well, if it is LRU page, add the page to LRU + * list in here. + */ + if (rc == MIGRATEPAGE_SUCCESS) { + if (unlikely(__PageMovable(newpage))) + put_page(newpage); + else + putback_lru_page(newpage); + } + return rc; } @@ -946,6 +1085,18 @@ static ICE_noinline int unmap_and_move(new_page_t get_new_page, if (page_count(page) == 1) { /* page was freed from under us. So we are done. */ + ClearPageActive(page); + ClearPageUnevictable(page); + if (unlikely(__PageMovable(page))) { + lock_page(page); + if (!PageMovable(page)) + __ClearPageIsolated(page); + unlock_page(page); + } + if (put_new_page) + put_new_page(newpage, private); + else + put_page(newpage); goto out; } @@ -958,10 +1109,8 @@ static ICE_noinline int unmap_and_move(new_page_t get_new_page, } rc = __unmap_and_move(page, newpage, force, mode); - if (rc == MIGRATEPAGE_SUCCESS) { - put_new_page = NULL; + if (rc == MIGRATEPAGE_SUCCESS) set_page_owner_migrate_reason(newpage, reason); - } out: if (rc != -EAGAIN) { @@ -972,29 +1121,47 @@ out: * restored. */ list_del(&page->lru); - dec_zone_page_state(page, NR_ISOLATED_ANON + + dec_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); - /* Soft-offlined page shouldn't go through lru cache list */ - if (reason == MR_MEMORY_FAILURE) { - put_page(page); - if (!test_set_page_hwpoison(page)) - num_poisoned_pages_inc(); - } else - putback_lru_page(page); } /* - * If migration was not successful and there's a freeing callback, use - * it. Otherwise, putback_lru_page() will drop the reference grabbed - * during isolation. + * If migration is successful, releases reference grabbed during + * isolation. Otherwise, restore the page to right list unless + * we want to retry. */ - if (put_new_page) - put_new_page(newpage, private); - else if (unlikely(__is_movable_balloon_page(newpage))) { - /* drop our reference, page already in the balloon */ - put_page(newpage); - } else - putback_lru_page(newpage); + if (rc == MIGRATEPAGE_SUCCESS) { + put_page(page); + if (reason == MR_MEMORY_FAILURE) { + /* + * Set PG_HWPoison on just freed page + * intentionally. Although it's rather weird, + * it's how HWPoison flag works at the moment. + */ + if (!test_set_page_hwpoison(page)) + num_poisoned_pages_inc(); + } + } else { + if (rc != -EAGAIN) { + if (likely(!__PageMovable(page))) { + putback_lru_page(page); + goto put_new; + } + + lock_page(page); + if (PageMovable(page)) + putback_movable_page(page); + else + __ClearPageIsolated(page); + unlock_page(page); + put_page(page); + } +put_new: + if (put_new_page) + put_new_page(newpage, private); + else + put_page(newpage); + } if (result) { if (rc) @@ -1165,6 +1332,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, switch(rc) { case -ENOMEM: + nr_failed++; goto out; case -EAGAIN: retry++; @@ -1294,7 +1462,7 @@ static int do_move_page_to_node_array(struct mm_struct *mm, err = isolate_lru_page(page); if (!err) { list_add_tail(&page->lru, &pagelist); - inc_zone_page_state(page, NR_ISOLATED_ANON + + inc_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); } put_and_set: @@ -1560,15 +1728,16 @@ static bool migrate_balanced_pgdat(struct pglist_data *pgdat, unsigned long nr_migrate_pages) { int z; + + if (!pgdat_reclaimable(pgdat)) + return false; + for (z = pgdat->nr_zones - 1; z >= 0; z--) { struct zone *zone = pgdat->node_zones + z; if (!populated_zone(zone)) continue; - if (!zone_reclaimable(zone)) - continue; - /* Avoid waking kswapd by allocating pages_to_migrate pages. */ if (!zone_watermark_ok(zone, 0, high_wmark_pages(zone) + @@ -1662,7 +1831,7 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) } page_lru = page_is_file_cache(page); - mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru, + mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru, hpage_nr_pages(page)); /* @@ -1720,7 +1889,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, if (nr_remaining) { if (!list_empty(&migratepages)) { list_del(&page->lru); - dec_zone_page_state(page, NR_ISOLATED_ANON + + dec_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); putback_lru_page(page); } @@ -1765,7 +1934,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, goto out_dropref; new_page = alloc_pages_node(node, - (GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_RECLAIM, + (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), HPAGE_PMD_ORDER); if (!new_page) goto out_fail; @@ -1785,7 +1954,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, /* Prepare a page as a migration target */ __SetPageLocked(new_page); - SetPageSwapBacked(new_page); + __SetPageSwapBacked(new_page); /* anon mapping, we can simply copy page->mapping to the new page: */ new_page->mapping = page->mapping; @@ -1813,15 +1982,14 @@ fail_putback: /* Retake the callers reference and putback on LRU */ get_page(page); putback_lru_page(page); - mod_zone_page_state(page_zone(page), + mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR); goto out_unlock; } orig_entry = *pmd; - entry = mk_pmd(new_page, vma->vm_page_prot); - entry = pmd_mkhuge(entry); + entry = mk_huge_pmd(new_page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); /* @@ -1865,7 +2033,7 @@ fail_putback: count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR); count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR); - mod_zone_page_state(page_zone(page), + mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR); return isolated; diff --git a/mm/mincore.c b/mm/mincore.c index 563f32045490..c0b5ba965200 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -75,7 +75,7 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) #endif if (page) { present = PageUptodate(page); - page_cache_release(page); + put_page(page); } return present; @@ -211,7 +211,7 @@ static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *v * return values: * zero - success * -EFAULT - vec points to an illegal address - * -EINVAL - addr is not a multiple of PAGE_CACHE_SIZE + * -EINVAL - addr is not a multiple of PAGE_SIZE * -ENOMEM - Addresses in the range [addr, addr + len] are * invalid for the address space of this process, or * specify one or more pages which are not currently @@ -226,14 +226,14 @@ SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len, unsigned char *tmp; /* Check the start address: needs to be page-aligned.. */ - if (start & ~PAGE_CACHE_MASK) + if (start & ~PAGE_MASK) return -EINVAL; /* ..and we need to be passed a valid user-space range */ if (!access_ok(VERIFY_READ, (void __user *) start, len)) return -ENOMEM; - /* This also avoids any overflows on PAGE_CACHE_ALIGN */ + /* This also avoids any overflows on PAGE_ALIGN */ pages = len >> PAGE_SHIFT; pages += (offset_in_page(len)) != 0; diff --git a/mm/mlock.c b/mm/mlock.c index 96f001041928..14645be06e30 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -103,7 +103,7 @@ static bool __munlock_isolate_lru_page(struct page *page, bool getpage) if (PageLRU(page)) { struct lruvec *lruvec; - lruvec = mem_cgroup_page_lruvec(page, page_zone(page)); + lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); if (getpage) get_page(page); ClearPageLRU(page); @@ -188,7 +188,7 @@ unsigned int munlock_vma_page(struct page *page) * might otherwise copy PageMlocked to part of the tail pages before * we clear it in the head page. It also stabilizes hpage_nr_pages(). */ - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); nr_pages = hpage_nr_pages(page); if (!TestClearPageMlocked(page)) @@ -197,14 +197,14 @@ unsigned int munlock_vma_page(struct page *page) __mod_zone_page_state(zone, NR_MLOCK, -nr_pages); if (__munlock_isolate_lru_page(page, true)) { - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); __munlock_isolated_page(page); goto out; } __munlock_isolation_failed(page); unlock_out: - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); out: return nr_pages - 1; @@ -289,7 +289,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) pagevec_init(&pvec_putback, 0); /* Phase 1: page isolation */ - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); for (i = 0; i < nr; i++) { struct page *page = pvec->pages[i]; @@ -315,7 +315,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) } delta_munlocked = -nr + pagevec_count(&pvec_putback); __mod_zone_page_state(zone, NR_MLOCK, delta_munlocked); - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); /* Now we can release pins of pages that we are not munlocking */ pagevec_release(&pvec_putback); @@ -617,7 +617,7 @@ static int apply_vma_lock_flags(unsigned long start, size_t len, return error; } -static int do_mlock(unsigned long start, size_t len, vm_flags_t flags) +static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags) { unsigned long locked; unsigned long lock_limit; @@ -635,7 +635,8 @@ static int do_mlock(unsigned long start, size_t len, vm_flags_t flags) lock_limit >>= PAGE_SHIFT; locked = len >> PAGE_SHIFT; - down_write(¤t->mm->mmap_sem); + if (down_write_killable(¤t->mm->mmap_sem)) + return -EINTR; locked += current->mm->locked_vm; @@ -678,7 +679,8 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; - down_write(¤t->mm->mmap_sem); + if (down_write_killable(¤t->mm->mmap_sem)) + return -EINTR; ret = apply_vma_lock_flags(start, len, 0); up_write(¤t->mm->mmap_sem); @@ -748,9 +750,10 @@ SYSCALL_DEFINE1(mlockall, int, flags) lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; - ret = -ENOMEM; - down_write(¤t->mm->mmap_sem); + if (down_write_killable(¤t->mm->mmap_sem)) + return -EINTR; + ret = -ENOMEM; if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) || capable(CAP_IPC_LOCK)) ret = apply_mlockall_flags(flags); @@ -765,7 +768,8 @@ SYSCALL_DEFINE0(munlockall) { int ret; - down_write(¤t->mm->mmap_sem); + if (down_write_killable(¤t->mm->mmap_sem)) + return -EINTR; ret = apply_mlockall_flags(0); up_write(¤t->mm->mmap_sem); return ret; diff --git a/mm/mmap.c b/mm/mmap.c index bd2e1a533bc1..ca9d91bca0d6 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -25,6 +25,7 @@ #include <linux/personality.h> #include <linux/security.h> #include <linux/hugetlb.h> +#include <linux/shmem_fs.h> #include <linux/profile.h> #include <linux/export.h> #include <linux/mount.h> @@ -55,10 +56,6 @@ #define arch_mmap_check(addr, len, flags) (0) #endif -#ifndef arch_rebalance_pgtables -#define arch_rebalance_pgtables(addr, len) (addr) -#endif - #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN; const int mmap_rnd_bits_max = CONFIG_ARCH_MMAP_RND_BITS_MAX; @@ -70,7 +67,7 @@ const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX; int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS; #endif -static bool ignore_rlimit_data = true; +static bool ignore_rlimit_data; core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644); static void unmap_region(struct mm_struct *mm, @@ -172,7 +169,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) return next; } -static unsigned long do_brk(unsigned long addr, unsigned long len); +static int do_brk(unsigned long addr, unsigned long len); SYSCALL_DEFINE1(brk, unsigned long, brk) { @@ -182,7 +179,8 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) unsigned long min_brk; bool populate; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; #ifdef CONFIG_COMPAT_BRK /* @@ -227,7 +225,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) goto out; /* Ok, looks good - let it rip. */ - if (do_brk(oldbrk, newbrk-oldbrk) != oldbrk) + if (do_brk(oldbrk, newbrk-oldbrk) < 0) goto out; set_brk: @@ -623,7 +621,6 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start, { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next = vma->vm_next; - struct vm_area_struct *importer = NULL; struct address_space *mapping = NULL; struct rb_root *root = NULL; struct anon_vma *anon_vma = NULL; @@ -633,17 +630,25 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start, int remove_next = 0; if (next && !insert) { - struct vm_area_struct *exporter = NULL; + struct vm_area_struct *exporter = NULL, *importer = NULL; if (end >= next->vm_end) { /* * vma expands, overlapping all the next, and * perhaps the one after too (mprotect case 6). */ -again: remove_next = 1 + (end > next->vm_end); + remove_next = 1 + (end > next->vm_end); end = next->vm_end; exporter = next; importer = vma; + + /* + * If next doesn't have anon_vma, import from vma after + * next, if the vma overlaps with it. + */ + if (remove_next == 2 && next && !next->anon_vma) + exporter = next->vm_next; + } else if (end > next->vm_start) { /* * vma expands, overlapping part of the next: @@ -677,6 +682,8 @@ again: remove_next = 1 + (end > next->vm_end); return error; } } +again: + vma_adjust_trans_huge(vma, start, end, adjust_next); if (file) { mapping = file->f_mapping; @@ -698,8 +705,6 @@ again: remove_next = 1 + (end > next->vm_end); } } - vma_adjust_trans_huge(vma, start, end, adjust_next); - anon_vma = vma->anon_vma; if (!anon_vma && adjust_next) anon_vma = next->anon_vma; @@ -798,8 +803,11 @@ again: remove_next = 1 + (end > next->vm_end); * up the code too much to do both in one go. */ next = vma->vm_next; - if (remove_next == 2) + if (remove_next == 2) { + remove_next = 1; + end = next->vm_end; goto again; + } else if (next) vma_gap_update(next); else @@ -1900,8 +1908,19 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, return -ENOMEM; get_area = current->mm->get_unmapped_area; - if (file && file->f_op->get_unmapped_area) - get_area = file->f_op->get_unmapped_area; + if (file) { + if (file->f_op->get_unmapped_area) + get_area = file->f_op->get_unmapped_area; + } else if (flags & MAP_SHARED) { + /* + * mmap_region() will call shmem_zero_setup() to create a file, + * so use shmem's get_unmapped_area in case it can be huge. + * do_mmap_pgoff() will clear pgoff, so match alignment. + */ + pgoff = 0; + get_area = shmem_get_unmapped_area; + } + addr = get_area(file, addr, len, pgoff, flags); if (IS_ERR_VALUE(addr)) return addr; @@ -1911,7 +1930,6 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, if (offset_in_page(addr)) return -EINVAL; - addr = arch_rebalance_pgtables(addr, len); error = security_mmap_addr(addr); return error ? error : addr; } @@ -2498,7 +2516,9 @@ int vm_munmap(unsigned long start, size_t len) int ret; struct mm_struct *mm = current->mm; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; + ret = do_munmap(mm, start, len); up_write(&mm->mmap_sem); return ret; @@ -2507,8 +2527,15 @@ EXPORT_SYMBOL(vm_munmap); SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) { + int ret; + struct mm_struct *mm = current->mm; + profile_munmap(addr); - return vm_munmap(addr, len); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; + ret = do_munmap(mm, addr, len); + up_write(&mm->mmap_sem); + return ret; } @@ -2540,7 +2567,9 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, if (pgoff + (size >> PAGE_SHIFT) < pgoff) return ret; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; + vma = find_vma(mm, start); if (!vma || !(vma->vm_flags & VM_SHARED)) @@ -2584,6 +2613,12 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, /* 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)); @@ -2618,18 +2653,20 @@ static inline void verify_mm_writelocked(struct mm_struct *mm) * anonymous maps. eventually we may be able to do some * brk-specific accounting here. */ -static unsigned long do_brk(unsigned long addr, unsigned long len) +static int do_brk(unsigned long addr, unsigned long request) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; - unsigned long flags; + unsigned long flags, len; struct rb_node **rb_link, *rb_parent; pgoff_t pgoff = addr >> PAGE_SHIFT; int error; - len = PAGE_ALIGN(len); + len = PAGE_ALIGN(request); + if (len < request) + return -ENOMEM; if (!len) - return addr; + return 0; flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; @@ -2696,20 +2733,22 @@ out: if (flags & VM_LOCKED) mm->locked_vm += (len >> PAGE_SHIFT); vma->vm_flags |= VM_SOFTDIRTY; - return addr; + return 0; } -unsigned long vm_brk(unsigned long addr, unsigned long len) +int vm_brk(unsigned long addr, unsigned long len) { struct mm_struct *mm = current->mm; - unsigned long ret; + int ret; bool populate; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; + ret = do_brk(addr, len); populate = ((mm->def_flags & VM_LOCKED) != 0); up_write(&mm->mmap_sem); - if (populate) + if (populate && !ret) mm_populate(addr, len); return ret; } @@ -2891,13 +2930,17 @@ bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages) if (is_data_mapping(flags) && mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) { - if (ignore_rlimit_data) - pr_warn_once("%s (%d): VmData %lu exceed data ulimit %lu. Will be forbidden soon.\n", + /* Workaround for Valgrind */ + if (rlimit(RLIMIT_DATA) == 0 && + mm->data_vm + npages <= rlimit_max(RLIMIT_DATA) >> PAGE_SHIFT) + return true; + if (!ignore_rlimit_data) { + pr_warn_once("%s (%d): VmData %lu exceed data ulimit %lu. Update limits or use boot option ignore_rlimit_data.\n", current->comm, current->pid, (mm->data_vm + npages) << PAGE_SHIFT, rlimit(RLIMIT_DATA)); - else return false; + } } return true; @@ -2930,9 +2973,19 @@ static const char *special_mapping_name(struct vm_area_struct *vma) return ((struct vm_special_mapping *)vma->vm_private_data)->name; } +static int special_mapping_mremap(struct vm_area_struct *new_vma) +{ + struct vm_special_mapping *sm = new_vma->vm_private_data; + + if (sm->mremap) + return sm->mremap(sm, new_vma); + return 0; +} + static const struct vm_operations_struct special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, + .mremap = special_mapping_mremap, .name = special_mapping_name, }; diff --git a/mm/mmu_context.c b/mm/mmu_context.c index f802c2d216a7..6f4d27c5bb32 100644 --- a/mm/mmu_context.c +++ b/mm/mmu_context.c @@ -4,9 +4,9 @@ */ #include <linux/mm.h> +#include <linux/sched.h> #include <linux/mmu_context.h> #include <linux/export.h> -#include <linux/sched.h> #include <asm/mmu_context.h> diff --git a/mm/mmzone.c b/mm/mmzone.c index 52687fb4de6f..5652be858e5e 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -52,7 +52,7 @@ static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes) } /* Returns the next zone at or below highest_zoneidx in a zonelist */ -struct zoneref *next_zones_zonelist(struct zoneref *z, +struct zoneref *__next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes) { diff --git a/mm/mprotect.c b/mm/mprotect.c index b650c5412f58..a4830f0325fe 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -163,7 +163,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) { split_huge_pmd(vma, pmd, addr); - if (pmd_none(*pmd)) + if (pmd_trans_unstable(pmd)) continue; } else { int nr_ptes = change_huge_pmd(vma, pmd, addr, @@ -379,7 +379,8 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len, reqprot = prot; - down_write(¤t->mm->mmap_sem); + if (down_write_killable(¤t->mm->mmap_sem)) + return -EINTR; vma = find_vma(current->mm, start); error = -ENOMEM; diff --git a/mm/mremap.c b/mm/mremap.c index 3fa0a467df66..da22ad2a5678 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -70,6 +70,22 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma, return pmd; } +static void take_rmap_locks(struct vm_area_struct *vma) +{ + if (vma->vm_file) + i_mmap_lock_write(vma->vm_file->f_mapping); + if (vma->anon_vma) + anon_vma_lock_write(vma->anon_vma); +} + +static void drop_rmap_locks(struct vm_area_struct *vma) +{ + if (vma->anon_vma) + anon_vma_unlock_write(vma->anon_vma); + if (vma->vm_file) + i_mmap_unlock_write(vma->vm_file->f_mapping); +} + static pte_t move_soft_dirty_pte(pte_t pte) { /* @@ -90,8 +106,6 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, struct vm_area_struct *new_vma, pmd_t *new_pmd, unsigned long new_addr, bool need_rmap_locks) { - struct address_space *mapping = NULL; - struct anon_vma *anon_vma = NULL; struct mm_struct *mm = vma->vm_mm; pte_t *old_pte, *new_pte, pte; spinlock_t *old_ptl, *new_ptl; @@ -114,16 +128,8 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, * serialize access to individual ptes, but only rmap traversal * order guarantees that we won't miss both the old and new ptes). */ - if (need_rmap_locks) { - if (vma->vm_file) { - mapping = vma->vm_file->f_mapping; - i_mmap_lock_write(mapping); - } - if (vma->anon_vma) { - anon_vma = vma->anon_vma; - anon_vma_lock_write(anon_vma); - } - } + if (need_rmap_locks) + take_rmap_locks(vma); /* * We don't have to worry about the ordering of src and dst @@ -151,10 +157,8 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, spin_unlock(new_ptl); pte_unmap(new_pte - 1); pte_unmap_unlock(old_pte - 1, old_ptl); - if (anon_vma) - anon_vma_unlock_write(anon_vma); - if (mapping) - i_mmap_unlock_write(mapping); + if (need_rmap_locks) + drop_rmap_locks(vma); } #define LATENCY_LIMIT (64 * PAGE_SIZE) @@ -193,25 +197,21 @@ unsigned long move_page_tables(struct vm_area_struct *vma, if (pmd_trans_huge(*old_pmd)) { if (extent == HPAGE_PMD_SIZE) { bool moved; - VM_BUG_ON_VMA(vma->vm_file || !vma->anon_vma, - vma); /* See comment in move_ptes() */ if (need_rmap_locks) - anon_vma_lock_write(vma->anon_vma); - moved = move_huge_pmd(vma, new_vma, old_addr, - new_addr, old_end, - old_pmd, new_pmd); + take_rmap_locks(vma); + moved = move_huge_pmd(vma, old_addr, new_addr, + old_end, old_pmd, new_pmd); if (need_rmap_locks) - anon_vma_unlock_write(vma->anon_vma); + drop_rmap_locks(vma); if (moved) { need_flush = true; continue; } } split_huge_pmd(vma, old_pmd, old_addr); - if (pmd_none(*old_pmd)) + if (pmd_trans_unstable(old_pmd)) continue; - VM_BUG_ON(pmd_trans_huge(*old_pmd)); } if (pte_alloc(new_vma->vm_mm, new_pmd, new_addr)) break; @@ -502,7 +502,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, if (!new_len) return ret; - down_write(¤t->mm->mmap_sem); + if (down_write_killable(¤t->mm->mmap_sem)) + return -EINTR; if (flags & MREMAP_FIXED) { ret = mremap_to(addr, old_len, new_addr, new_len, diff --git a/mm/nommu.c b/mm/nommu.c index de8b6b6580c1..95daf81a4855 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -15,8 +15,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#define __DISABLE_GUP_DEPRECATED - #include <linux/export.h> #include <linux/mm.h> #include <linux/vmacache.h> @@ -141,7 +139,7 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, if (pages) { pages[i] = virt_to_page(start); if (pages[i]) - page_cache_get(pages[i]); + get_page(pages[i]); } if (vmas) vmas[i] = vma; @@ -161,7 +159,7 @@ finish_or_fault: * slab page or a secondary page from a compound page * - don't permit access to VMAs that don't support it, such as I/O mappings */ -long get_user_pages6(unsigned long start, unsigned long nr_pages, +long get_user_pages(unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas) { @@ -175,15 +173,15 @@ long get_user_pages6(unsigned long start, unsigned long nr_pages, return __get_user_pages(current, current->mm, start, nr_pages, flags, pages, vmas, NULL); } -EXPORT_SYMBOL(get_user_pages6); +EXPORT_SYMBOL(get_user_pages); -long get_user_pages_locked6(unsigned long start, unsigned long nr_pages, +long get_user_pages_locked(unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, int *locked) { - return get_user_pages6(start, nr_pages, write, force, pages, NULL); + return get_user_pages(start, nr_pages, write, force, pages, NULL); } -EXPORT_SYMBOL(get_user_pages_locked6); +EXPORT_SYMBOL(get_user_pages_locked); long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, @@ -199,13 +197,13 @@ long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, } EXPORT_SYMBOL(__get_user_pages_unlocked); -long get_user_pages_unlocked5(unsigned long start, unsigned long nr_pages, +long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages) { return __get_user_pages_unlocked(current, current->mm, start, nr_pages, write, force, pages, 0); } -EXPORT_SYMBOL(get_user_pages_unlocked5); +EXPORT_SYMBOL(get_user_pages_unlocked); /** * follow_pfn - look up PFN at a user virtual address @@ -1684,7 +1682,7 @@ void exit_mmap(struct mm_struct *mm) } } -unsigned long vm_brk(unsigned long addr, unsigned long len) +int vm_brk(unsigned long addr, unsigned long len) { return -ENOMEM; } @@ -1811,7 +1809,8 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } EXPORT_SYMBOL(filemap_fault); -void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf) +void filemap_map_pages(struct fault_env *fe, + pgoff_t start_pgoff, pgoff_t end_pgoff) { BUG(); } @@ -1989,31 +1988,3 @@ static int __meminit init_admin_reserve(void) return 0; } subsys_initcall(init_admin_reserve); - -long get_user_pages8(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages, - struct vm_area_struct **vmas) -{ - return get_user_pages6(start, nr_pages, write, force, pages, vmas); -} -EXPORT_SYMBOL(get_user_pages8); - -long get_user_pages_locked8(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages, - int *locked) -{ - return get_user_pages_locked6(start, nr_pages, write, - force, pages, locked); -} -EXPORT_SYMBOL(get_user_pages_locked8); - -long get_user_pages_unlocked7(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages) -{ - return get_user_pages_unlocked5(start, nr_pages, write, force, pages); -} -EXPORT_SYMBOL(get_user_pages_unlocked7); - diff --git a/mm/oom_kill.c b/mm/oom_kill.c index b34d279a7ee6..7d0a275df822 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -174,8 +174,15 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, if (!p) return 0; + /* + * Do not even consider tasks which are explicitly marked oom + * unkillable or have been already oom reaped or the are in + * the middle of vfork + */ adj = (long)p->signal->oom_score_adj; - if (adj == OOM_SCORE_ADJ_MIN) { + if (adj == OOM_SCORE_ADJ_MIN || + test_bit(MMF_OOM_REAPED, &p->mm->flags) || + in_vfork(p)) { task_unlock(p); return 0; } @@ -269,21 +276,29 @@ static enum oom_constraint constrained_alloc(struct oom_control *oc, #endif enum oom_scan_t oom_scan_process_thread(struct oom_control *oc, - struct task_struct *task, unsigned long totalpages) + struct task_struct *task) { if (oom_unkillable_task(task, NULL, oc->nodemask)) return OOM_SCAN_CONTINUE; /* * This task already has access to memory reserves and is being killed. - * Don't allow any other task to have access to the reserves. + * Don't allow any other task to have access to the reserves unless + * the task has MMF_OOM_REAPED because chances that it would release + * any memory is quite low. */ - if (test_tsk_thread_flag(task, TIF_MEMDIE)) { - if (!is_sysrq_oom(oc)) - return OOM_SCAN_ABORT; + if (!is_sysrq_oom(oc) && atomic_read(&task->signal->oom_victims)) { + struct task_struct *p = find_lock_task_mm(task); + enum oom_scan_t ret = OOM_SCAN_ABORT; + + if (p) { + if (test_bit(MMF_OOM_REAPED, &p->mm->flags)) + ret = OOM_SCAN_CONTINUE; + task_unlock(p); + } + + return ret; } - if (!task->mm) - return OOM_SCAN_CONTINUE; /* * If task is allocating a lot of memory and has been marked to be @@ -302,15 +317,15 @@ enum oom_scan_t oom_scan_process_thread(struct oom_control *oc, static struct task_struct *select_bad_process(struct oom_control *oc, unsigned int *ppoints, unsigned long totalpages) { - struct task_struct *g, *p; + struct task_struct *p; struct task_struct *chosen = NULL; unsigned long chosen_points = 0; rcu_read_lock(); - for_each_process_thread(g, p) { + for_each_process(p) { unsigned int points; - switch (oom_scan_process_thread(oc, p, totalpages)) { + switch (oom_scan_process_thread(oc, p)) { case OOM_SCAN_SELECT: chosen = p; chosen_points = ULONG_MAX; @@ -326,9 +341,6 @@ static struct task_struct *select_bad_process(struct oom_control *oc, points = oom_badness(p, NULL, oc->nodemask, totalpages); if (!points || points < chosen_points) continue; - /* Prefer thread group leaders for display purposes */ - if (points == chosen_points && thread_group_leader(chosen)) - continue; chosen = p; chosen_points = points; @@ -385,8 +397,7 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask) rcu_read_unlock(); } -static void dump_header(struct oom_control *oc, struct task_struct *p, - struct mem_cgroup *memcg) +static void dump_header(struct oom_control *oc, struct task_struct *p) { pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), order=%d, oom_score_adj=%hd\n", current->comm, oc->gfp_mask, &oc->gfp_mask, oc->order, @@ -394,12 +405,12 @@ static void dump_header(struct oom_control *oc, struct task_struct *p, cpuset_print_current_mems_allowed(); dump_stack(); - if (memcg) - mem_cgroup_print_oom_info(memcg, p); + if (oc->memcg) + mem_cgroup_print_oom_info(oc->memcg, p); else show_mem(SHOW_MEM_FILTER_NODES); if (sysctl_oom_dump_tasks) - dump_tasks(memcg, oc->nodemask); + dump_tasks(oc->memcg, oc->nodemask); } /* @@ -412,6 +423,25 @@ bool oom_killer_disabled __read_mostly; #define K(x) ((x) << (PAGE_SHIFT-10)) +/* + * task->mm can be NULL if the task is the exited group leader. So to + * determine whether the task is using a particular mm, we examine all the + * task's threads: if one of those is using this mm then this task was also + * using it. + */ +bool process_shares_mm(struct task_struct *p, struct mm_struct *mm) +{ + struct task_struct *t; + + for_each_thread(p, t) { + struct mm_struct *t_mm = READ_ONCE(t->mm); + if (t_mm) + return t_mm == mm; + } + return false; +} + + #ifdef CONFIG_MMU /* * OOM Reaper kernel thread which tries to reap the memory used by the OOM @@ -422,18 +452,33 @@ static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait); static struct task_struct *oom_reaper_list; static DEFINE_SPINLOCK(oom_reaper_lock); - static bool __oom_reap_task(struct task_struct *tsk) { struct mmu_gather tlb; struct vm_area_struct *vma; - struct mm_struct *mm; + struct mm_struct *mm = NULL; struct task_struct *p; struct zap_details details = {.check_swap_entries = true, .ignore_dirty = true}; bool ret = true; /* + * We have to make sure to not race with the victim exit path + * and cause premature new oom victim selection: + * __oom_reap_task exit_mm + * mmget_not_zero + * mmput + * atomic_dec_and_test + * exit_oom_victim + * [...] + * out_of_memory + * select_bad_process + * # no TIF_MEMDIE task selects new victim + * unmap_page_range # frees some memory + */ + mutex_lock(&oom_lock); + + /* * Make sure we find the associated mm_struct even when the particular * thread has already terminated and cleared its mm. * We might have race with exit path so consider our work done if there @@ -441,19 +486,24 @@ static bool __oom_reap_task(struct task_struct *tsk) */ p = find_lock_task_mm(tsk); if (!p) - return true; - + goto unlock_oom; mm = p->mm; - if (!atomic_inc_not_zero(&mm->mm_users)) { - task_unlock(p); - return true; - } - + atomic_inc(&mm->mm_count); task_unlock(p); if (!down_read_trylock(&mm->mmap_sem)) { ret = false; - goto out; + goto mm_drop; + } + + /* + * increase mm_users only after we know we will reap something so + * that the mmput_async is called only when we have reaped something + * and delayed __mmput doesn't matter that much + */ + if (!mmget_not_zero(mm)) { + up_read(&mm->mmap_sem); + goto mm_drop; } tlb_gather_mmu(&tlb, mm, 0, -1); @@ -491,16 +541,20 @@ static bool __oom_reap_task(struct task_struct *tsk) up_read(&mm->mmap_sem); /* - * Clear TIF_MEMDIE because the task shouldn't be sitting on a - * reasonably reclaimable memory anymore. OOM killer can continue - * by selecting other victim if unmapping hasn't led to any - * improvements. This also means that selecting this task doesn't - * make any sense. + * This task can be safely ignored because we cannot do much more + * to release its memory. */ - tsk->signal->oom_score_adj = OOM_SCORE_ADJ_MIN; - exit_oom_victim(tsk); -out: - mmput(mm); + set_bit(MMF_OOM_REAPED, &mm->flags); + /* + * Drop our reference but make sure the mmput slow path is called from a + * different context because we shouldn't risk we get stuck there and + * put the oom_reaper out of the way. + */ + mmput_async(mm); +mm_drop: + mmdrop(mm); +unlock_oom: + mutex_unlock(&oom_lock); return ret; } @@ -514,11 +568,39 @@ static void oom_reap_task(struct task_struct *tsk) schedule_timeout_idle(HZ/10); if (attempts > MAX_OOM_REAP_RETRIES) { + struct task_struct *p; + pr_info("oom_reaper: unable to reap pid:%d (%s)\n", task_pid_nr(tsk), tsk->comm); + + /* + * If we've already tried to reap this task in the past and + * failed it probably doesn't make much sense to try yet again + * so hide the mm from the oom killer so that it can move on + * to another task with a different mm struct. + */ + p = find_lock_task_mm(tsk); + if (p) { + if (test_and_set_bit(MMF_OOM_NOT_REAPABLE, &p->mm->flags)) { + pr_info("oom_reaper: giving up pid:%d (%s)\n", + task_pid_nr(tsk), tsk->comm); + set_bit(MMF_OOM_REAPED, &p->mm->flags); + } + task_unlock(p); + } + debug_show_all_locks(); } + /* + * Clear TIF_MEMDIE because the task shouldn't be sitting on a + * reasonably reclaimable memory anymore or it is not a good candidate + * for the oom victim right now because it cannot release its memory + * itself nor by the oom reaper. + */ + tsk->oom_reaper_list = NULL; + exit_oom_victim(tsk); + /* Drop a reference taken by wake_oom_reaper */ put_task_struct(tsk); } @@ -545,9 +627,13 @@ static int oom_reaper(void *unused) return 0; } -static void wake_oom_reaper(struct task_struct *tsk) +void wake_oom_reaper(struct task_struct *tsk) { - if (!oom_reaper_th || tsk->oom_reaper_list) + if (!oom_reaper_th) + return; + + /* tsk is already queued? */ + if (tsk == oom_reaper_list || tsk->oom_reaper_list) return; get_task_struct(tsk); @@ -570,10 +656,6 @@ static int __init oom_init(void) return 0; } subsys_initcall(oom_init) -#else -static void wake_oom_reaper(struct task_struct *tsk) -{ -} #endif /** @@ -589,6 +671,7 @@ void mark_oom_victim(struct task_struct *tsk) /* OOM killer might race with memcg OOM */ if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE)) return; + atomic_inc(&tsk->signal->oom_victims); /* * Make sure that the task is woken up from uninterruptible sleep * if it is frozen because OOM killer wouldn't be able to free @@ -606,6 +689,7 @@ void exit_oom_victim(struct task_struct *tsk) { if (!test_and_clear_tsk_thread_flag(tsk, TIF_MEMDIE)) return; + atomic_dec(&tsk->signal->oom_victims); if (!atomic_dec_return(&oom_victims)) wake_up_all(&oom_victims_wait); @@ -648,22 +732,78 @@ void oom_killer_enable(void) oom_killer_disabled = false; } +static inline bool __task_will_free_mem(struct task_struct *task) +{ + struct signal_struct *sig = task->signal; + + /* + * A coredumping process may sleep for an extended period in exit_mm(), + * so the oom killer cannot assume that the process will promptly exit + * and release memory. + */ + if (sig->flags & SIGNAL_GROUP_COREDUMP) + return false; + + if (sig->flags & SIGNAL_GROUP_EXIT) + return true; + + if (thread_group_empty(task) && (task->flags & PF_EXITING)) + return true; + + return false; +} + /* - * task->mm can be NULL if the task is the exited group leader. So to - * determine whether the task is using a particular mm, we examine all the - * task's threads: if one of those is using this mm then this task was also - * using it. + * Checks whether the given task is dying or exiting and likely to + * release its address space. This means that all threads and processes + * sharing the same mm have to be killed or exiting. + * Caller has to make sure that task->mm is stable (hold task_lock or + * it operates on the current). */ -static bool process_shares_mm(struct task_struct *p, struct mm_struct *mm) +bool task_will_free_mem(struct task_struct *task) { - struct task_struct *t; + struct mm_struct *mm = task->mm; + struct task_struct *p; + bool ret; - for_each_thread(p, t) { - struct mm_struct *t_mm = READ_ONCE(t->mm); - if (t_mm) - return t_mm == mm; + /* + * Skip tasks without mm because it might have passed its exit_mm and + * exit_oom_victim. oom_reaper could have rescued that but do not rely + * on that for now. We can consider find_lock_task_mm in future. + */ + if (!mm) + return false; + + if (!__task_will_free_mem(task)) + return false; + + /* + * This task has already been drained by the oom reaper so there are + * only small chances it will free some more + */ + if (test_bit(MMF_OOM_REAPED, &mm->flags)) + return false; + + if (atomic_read(&mm->mm_users) <= 1) + return true; + + /* + * This is really pessimistic but we do not have any reliable way + * to check that external processes share with our mm + */ + rcu_read_lock(); + for_each_process(p) { + if (!process_shares_mm(p, mm)) + continue; + if (same_thread_group(task, p)) + continue; + ret = __task_will_free_mem(p); + if (!ret) + break; } - return false; + rcu_read_unlock(); + + return ret; } /* @@ -672,7 +812,7 @@ static bool process_shares_mm(struct task_struct *p, struct mm_struct *mm) */ void oom_kill_process(struct oom_control *oc, struct task_struct *p, unsigned int points, unsigned long totalpages, - struct mem_cgroup *memcg, const char *message) + const char *message) { struct task_struct *victim = p; struct task_struct *child; @@ -688,8 +828,9 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, * its children or threads, just set TIF_MEMDIE so it can die quickly */ task_lock(p); - if (p->mm && task_will_free_mem(p)) { + if (task_will_free_mem(p)) { mark_oom_victim(p); + wake_oom_reaper(p); task_unlock(p); put_task_struct(p); return; @@ -697,7 +838,7 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, task_unlock(p); if (__ratelimit(&oom_rs)) - dump_header(oc, p, memcg); + dump_header(oc, p); pr_err("%s: Kill process %d (%s) score %u or sacrifice child\n", message, task_pid_nr(p), p->comm, points); @@ -718,8 +859,8 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, /* * oom_badness() returns 0 if the thread is unkillable */ - child_points = oom_badness(child, memcg, oc->nodemask, - totalpages); + child_points = oom_badness(child, + oc->memcg, oc->nodemask, totalpages); if (child_points > victim_points) { put_task_struct(victim); victim = child; @@ -772,14 +913,18 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, continue; if (same_thread_group(p, victim)) continue; - if (unlikely(p->flags & PF_KTHREAD) || is_global_init(p) || - p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) { + if (unlikely(p->flags & PF_KTHREAD) || is_global_init(p)) { /* * We cannot use oom_reaper for the mm shared by this * process because it wouldn't get killed and so the - * memory might be still used. + * memory might be still used. Hide the mm from the oom + * killer to guarantee OOM forward progress. */ can_oom_reap = false; + set_bit(MMF_OOM_REAPED, &mm->flags); + pr_info("oom killer %d (%s) has mm pinned by %d (%s)\n", + task_pid_nr(victim), victim->comm, + task_pid_nr(p), p->comm); continue; } do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true); @@ -797,8 +942,7 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, /* * Determines whether the kernel must panic because of the panic_on_oom sysctl. */ -void check_panic_on_oom(struct oom_control *oc, enum oom_constraint constraint, - struct mem_cgroup *memcg) +void check_panic_on_oom(struct oom_control *oc, enum oom_constraint constraint) { if (likely(!sysctl_panic_on_oom)) return; @@ -814,7 +958,7 @@ void check_panic_on_oom(struct oom_control *oc, enum oom_constraint constraint, /* Do not panic for oom kills triggered by sysrq */ if (is_sysrq_oom(oc)) return; - dump_header(oc, NULL, memcg); + dump_header(oc, NULL); panic("Out of memory: %s panic_on_oom is enabled\n", sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); } @@ -862,30 +1006,36 @@ bool out_of_memory(struct oom_control *oc) * If current has a pending SIGKILL or is exiting, then automatically * select it. The goal is to allow it to allocate so that it may * quickly exit and free its memory. - * - * But don't select if current has already released its mm and cleared - * TIF_MEMDIE flag at exit_mm(), otherwise an OOM livelock may occur. */ - if (current->mm && - (fatal_signal_pending(current) || task_will_free_mem(current))) { + if (task_will_free_mem(current)) { mark_oom_victim(current); + wake_oom_reaper(current); return true; } /* + * The OOM killer does not compensate for IO-less reclaim. + * pagefault_out_of_memory lost its gfp context so we have to + * make sure exclude 0 mask - all other users should have at least + * ___GFP_DIRECT_RECLAIM to get here. + */ + if (oc->gfp_mask && !(oc->gfp_mask & (__GFP_FS|__GFP_NOFAIL))) + return true; + + /* * Check if there were limitations on the allocation (only relevant for * NUMA) that may require different handling. */ constraint = constrained_alloc(oc, &totalpages); if (constraint != CONSTRAINT_MEMORY_POLICY) oc->nodemask = NULL; - check_panic_on_oom(oc, constraint, NULL); + check_panic_on_oom(oc, constraint); if (sysctl_oom_kill_allocating_task && current->mm && !oom_unkillable_task(current, NULL, oc->nodemask) && current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) { get_task_struct(current); - oom_kill_process(oc, current, 0, totalpages, NULL, + oom_kill_process(oc, current, 0, totalpages, "Out of memory (oom_kill_allocating_task)"); return true; } @@ -893,12 +1043,11 @@ bool out_of_memory(struct oom_control *oc) p = select_bad_process(oc, &points, totalpages); /* Found nothing?!?! Either we hang forever, or we panic. */ if (!p && !is_sysrq_oom(oc)) { - dump_header(oc, NULL, NULL); + dump_header(oc, NULL); panic("Out of memory and no killable processes...\n"); } if (p && p != (void *)-1UL) { - oom_kill_process(oc, p, points, totalpages, NULL, - "Out of memory"); + oom_kill_process(oc, p, points, totalpages, "Out of memory"); /* * Give the killed process a good chance to exit before trying * to allocate memory again. @@ -910,14 +1059,15 @@ bool out_of_memory(struct oom_control *oc) /* * The pagefault handler calls here because it is out of memory, so kill a - * memory-hogging task. If any populated zone has ZONE_OOM_LOCKED set, a - * parallel oom killing is already in progress so do nothing. + * memory-hogging task. If oom_lock is held by somebody else, a parallel oom + * killing is already in progress so do nothing. */ void pagefault_out_of_memory(void) { struct oom_control oc = { .zonelist = NULL, .nodemask = NULL, + .memcg = NULL, .gfp_mask = 0, .order = 0, }; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 11ff8f758631..f4cd7d8005c9 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -267,26 +267,35 @@ static void wb_min_max_ratio(struct bdi_writeback *wb, */ /** - * zone_dirtyable_memory - number of dirtyable pages in a zone - * @zone: the zone + * node_dirtyable_memory - number of dirtyable pages in a node + * @pgdat: the node * - * Returns the zone's number of pages potentially available for dirty - * page cache. This is the base value for the per-zone dirty limits. + * Returns the node's number of pages potentially available for dirty + * page cache. This is the base value for the per-node dirty limits. */ -static unsigned long zone_dirtyable_memory(struct zone *zone) +static unsigned long node_dirtyable_memory(struct pglist_data *pgdat) { - unsigned long nr_pages; + unsigned long nr_pages = 0; + int z; + + for (z = 0; z < MAX_NR_ZONES; z++) { + struct zone *zone = pgdat->node_zones + z; + + if (!populated_zone(zone)) + continue; + + nr_pages += zone_page_state(zone, NR_FREE_PAGES); + } - nr_pages = zone_page_state(zone, NR_FREE_PAGES); /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ - nr_pages -= min(nr_pages, zone->totalreserve_pages); + nr_pages -= min(nr_pages, pgdat->totalreserve_pages); - nr_pages += zone_page_state(zone, NR_INACTIVE_FILE); - nr_pages += zone_page_state(zone, NR_ACTIVE_FILE); + nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE); + nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE); return nr_pages; } @@ -296,12 +305,29 @@ static unsigned long highmem_dirtyable_memory(unsigned long total) #ifdef CONFIG_HIGHMEM int node; unsigned long x = 0; + int i; for_each_node_state(node, N_HIGH_MEMORY) { - struct zone *z = &NODE_DATA(node)->node_zones[ZONE_HIGHMEM]; + for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) { + struct zone *z; + unsigned long nr_pages; - x += zone_dirtyable_memory(z); + if (!is_highmem_idx(i)) + continue; + + z = &NODE_DATA(node)->node_zones[i]; + if (!populated_zone(z)) + continue; + + nr_pages = zone_page_state(z, NR_FREE_PAGES); + /* watch for underflows */ + nr_pages -= min(nr_pages, high_wmark_pages(z)); + nr_pages += zone_page_state(z, NR_ZONE_INACTIVE_FILE); + nr_pages += zone_page_state(z, NR_ZONE_ACTIVE_FILE); + x += nr_pages; + } } + /* * Unreclaimable memory (kernel memory or anonymous memory * without swap) can bring down the dirtyable pages below @@ -344,8 +370,8 @@ static unsigned long global_dirtyable_memory(void) */ x -= min(x, totalreserve_pages); - x += global_page_state(NR_INACTIVE_FILE); - x += global_page_state(NR_ACTIVE_FILE); + x += global_node_page_state(NR_INACTIVE_FILE); + x += global_node_page_state(NR_ACTIVE_FILE); if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); @@ -369,8 +395,9 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc) struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc); unsigned long bytes = vm_dirty_bytes; unsigned long bg_bytes = dirty_background_bytes; - unsigned long ratio = vm_dirty_ratio; - unsigned long bg_ratio = dirty_background_ratio; + /* convert ratios to per-PAGE_SIZE for higher precision */ + unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100; + unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100; unsigned long thresh; unsigned long bg_thresh; struct task_struct *tsk; @@ -382,33 +409,35 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc) /* * The byte settings can't be applied directly to memcg * domains. Convert them to ratios by scaling against - * globally available memory. + * globally available memory. As the ratios are in + * per-PAGE_SIZE, they can be obtained by dividing bytes by + * number of pages. */ if (bytes) - ratio = min(DIV_ROUND_UP(bytes, PAGE_SIZE) * 100 / - global_avail, 100UL); + ratio = min(DIV_ROUND_UP(bytes, global_avail), + PAGE_SIZE); if (bg_bytes) - bg_ratio = min(DIV_ROUND_UP(bg_bytes, PAGE_SIZE) * 100 / - global_avail, 100UL); + bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail), + PAGE_SIZE); bytes = bg_bytes = 0; } if (bytes) thresh = DIV_ROUND_UP(bytes, PAGE_SIZE); else - thresh = (ratio * available_memory) / 100; + thresh = (ratio * available_memory) / PAGE_SIZE; if (bg_bytes) bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE); else - bg_thresh = (bg_ratio * available_memory) / 100; + bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE; if (bg_thresh >= thresh) bg_thresh = thresh / 2; tsk = current; if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) { - bg_thresh += bg_thresh / 4; - thresh += thresh / 4; + bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32; + thresh += thresh / 4 + global_wb_domain.dirty_limit / 32; } dtc->thresh = thresh; dtc->bg_thresh = bg_thresh; @@ -438,23 +467,23 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) } /** - * zone_dirty_limit - maximum number of dirty pages allowed in a zone - * @zone: the zone + * node_dirty_limit - maximum number of dirty pages allowed in a node + * @pgdat: the node * - * Returns the maximum number of dirty pages allowed in a zone, based - * on the zone's dirtyable memory. + * Returns the maximum number of dirty pages allowed in a node, based + * on the node's dirtyable memory. */ -static unsigned long zone_dirty_limit(struct zone *zone) +static unsigned long node_dirty_limit(struct pglist_data *pgdat) { - unsigned long zone_memory = zone_dirtyable_memory(zone); + unsigned long node_memory = node_dirtyable_memory(pgdat); struct task_struct *tsk = current; unsigned long dirty; if (vm_dirty_bytes) dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) * - zone_memory / global_dirtyable_memory(); + node_memory / global_dirtyable_memory(); else - dirty = vm_dirty_ratio * zone_memory / 100; + dirty = vm_dirty_ratio * node_memory / 100; if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) dirty += dirty / 4; @@ -463,19 +492,22 @@ static unsigned long zone_dirty_limit(struct zone *zone) } /** - * zone_dirty_ok - tells whether a zone is within its dirty limits - * @zone: the zone to check + * node_dirty_ok - tells whether a node is within its dirty limits + * @pgdat: the node to check * - * Returns %true when the dirty pages in @zone are within the zone's + * Returns %true when the dirty pages in @pgdat are within the node's * dirty limit, %false if the limit is exceeded. */ -bool zone_dirty_ok(struct zone *zone) +bool node_dirty_ok(struct pglist_data *pgdat) { - unsigned long limit = zone_dirty_limit(zone); + unsigned long limit = node_dirty_limit(pgdat); + unsigned long nr_pages = 0; + + nr_pages += node_page_state(pgdat, NR_FILE_DIRTY); + nr_pages += node_page_state(pgdat, NR_UNSTABLE_NFS); + nr_pages += node_page_state(pgdat, NR_WRITEBACK); - return zone_page_state(zone, NR_FILE_DIRTY) + - zone_page_state(zone, NR_UNSTABLE_NFS) + - zone_page_state(zone, NR_WRITEBACK) <= limit; + return nr_pages <= limit; } int dirty_background_ratio_handler(struct ctl_table *table, int write, @@ -1563,10 +1595,10 @@ static void balance_dirty_pages(struct address_space *mapping, * written to the server's write cache, but has not yet * been flushed to permanent storage. */ - nr_reclaimable = global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS); + nr_reclaimable = global_node_page_state(NR_FILE_DIRTY) + + global_node_page_state(NR_UNSTABLE_NFS); gdtc->avail = global_dirtyable_memory(); - gdtc->dirty = nr_reclaimable + global_page_state(NR_WRITEBACK); + gdtc->dirty = nr_reclaimable + global_node_page_state(NR_WRITEBACK); domain_dirty_limits(gdtc); @@ -1903,14 +1935,15 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) * as we're trying to decide whether to put more under writeback. */ gdtc->avail = global_dirtyable_memory(); - gdtc->dirty = global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS); + gdtc->dirty = global_node_page_state(NR_FILE_DIRTY) + + global_node_page_state(NR_UNSTABLE_NFS); domain_dirty_limits(gdtc); if (gdtc->dirty > gdtc->bg_thresh) return true; - if (wb_stat(wb, WB_RECLAIMABLE) > __wb_calc_thresh(gdtc)) + if (wb_stat(wb, WB_RECLAIMABLE) > + wb_calc_thresh(gdtc->wb, gdtc->bg_thresh)) return true; if (mdtc) { @@ -1924,7 +1957,8 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) if (mdtc->dirty > mdtc->bg_thresh) return true; - if (wb_stat(wb, WB_RECLAIMABLE) > __wb_calc_thresh(mdtc)) + if (wb_stat(wb, WB_RECLAIMABLE) > + wb_calc_thresh(mdtc->wb, mdtc->bg_thresh)) return true; } @@ -1946,8 +1980,8 @@ void throttle_vm_writeout(gfp_t gfp_mask) */ dirty_thresh += dirty_thresh / 10; /* wheeee... */ - if (global_page_state(NR_UNSTABLE_NFS) + - global_page_state(NR_WRITEBACK) <= dirty_thresh) + if (global_node_page_state(NR_UNSTABLE_NFS) + + global_node_page_state(NR_WRITEBACK) <= dirty_thresh) break; congestion_wait(BLK_RW_ASYNC, HZ/10); @@ -1975,8 +2009,8 @@ int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, void laptop_mode_timer_fn(unsigned long data) { struct request_queue *q = (struct request_queue *)data; - int nr_pages = global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS); + int nr_pages = global_node_page_state(NR_FILE_DIRTY) + + global_node_page_state(NR_UNSTABLE_NFS); struct bdi_writeback *wb; /* @@ -2176,8 +2210,8 @@ int write_cache_pages(struct address_space *mapping, cycled = 0; end = -1; } else { - index = wbc->range_start >> PAGE_CACHE_SHIFT; - end = wbc->range_end >> PAGE_CACHE_SHIFT; + index = wbc->range_start >> PAGE_SHIFT; + end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; cycled = 1; /* ignore range_cyclic tests */ @@ -2382,14 +2416,14 @@ int write_one_page(struct page *page, int wait) wait_on_page_writeback(page); if (clear_page_dirty_for_io(page)) { - page_cache_get(page); + get_page(page); ret = mapping->a_ops->writepage(page, &wbc); if (ret == 0 && wait) { wait_on_page_writeback(page); if (PageError(page)) ret = -EIO; } - page_cache_release(page); + put_page(page); } else { unlock_page(page); } @@ -2427,11 +2461,12 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) wb = inode_to_wb(inode); mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_DIRTY); - __inc_zone_page_state(page, NR_FILE_DIRTY); - __inc_zone_page_state(page, NR_DIRTIED); + __inc_node_page_state(page, NR_FILE_DIRTY); + __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); + __inc_node_page_state(page, NR_DIRTIED); __inc_wb_stat(wb, WB_RECLAIMABLE); __inc_wb_stat(wb, WB_DIRTIED); - task_io_account_write(PAGE_CACHE_SIZE); + task_io_account_write(PAGE_SIZE); current->nr_dirtied++; this_cpu_inc(bdp_ratelimits); } @@ -2448,9 +2483,10 @@ void account_page_cleaned(struct page *page, struct address_space *mapping, { if (mapping_cap_account_dirty(mapping)) { mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY); - dec_zone_page_state(page, NR_FILE_DIRTY); + dec_node_page_state(page, NR_FILE_DIRTY); + dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); dec_wb_stat(wb, WB_RECLAIMABLE); - task_io_account_cancelled_write(PAGE_CACHE_SIZE); + task_io_account_cancelled_write(PAGE_SIZE); } } @@ -2516,7 +2552,7 @@ void account_page_redirty(struct page *page) wb = unlocked_inode_to_wb_begin(inode, &locked); current->nr_dirtied--; - dec_zone_page_state(page, NR_DIRTIED); + dec_node_page_state(page, NR_DIRTIED); dec_wb_stat(wb, WB_DIRTIED); unlocked_inode_to_wb_end(inode, locked); } @@ -2554,6 +2590,7 @@ int set_page_dirty(struct page *page) { struct address_space *mapping = page_mapping(page); + page = compound_head(page); if (likely(mapping)) { int (*spd)(struct page *) = mapping->a_ops->set_page_dirty; /* @@ -2703,7 +2740,8 @@ int clear_page_dirty_for_io(struct page *page) wb = unlocked_inode_to_wb_begin(inode, &locked); if (TestClearPageDirty(page)) { mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY); - dec_zone_page_state(page, NR_FILE_DIRTY); + dec_node_page_state(page, NR_FILE_DIRTY); + dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); dec_wb_stat(wb, WB_RECLAIMABLE); ret = 1; } @@ -2738,14 +2776,20 @@ int test_clear_page_writeback(struct page *page) __wb_writeout_inc(wb); } } + + if (mapping->host && !mapping_tagged(mapping, + PAGECACHE_TAG_WRITEBACK)) + sb_clear_inode_writeback(mapping->host); + spin_unlock_irqrestore(&mapping->tree_lock, flags); } else { ret = TestClearPageWriteback(page); } if (ret) { mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK); - dec_zone_page_state(page, NR_WRITEBACK); - inc_zone_page_state(page, NR_WRITTEN); + dec_node_page_state(page, NR_WRITEBACK); + dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); + inc_node_page_state(page, NR_WRITTEN); } unlock_page_memcg(page); return ret; @@ -2765,11 +2809,24 @@ int __test_set_page_writeback(struct page *page, bool keep_write) spin_lock_irqsave(&mapping->tree_lock, flags); ret = TestSetPageWriteback(page); if (!ret) { + bool on_wblist; + + on_wblist = mapping_tagged(mapping, + PAGECACHE_TAG_WRITEBACK); + radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_WRITEBACK); if (bdi_cap_account_writeback(bdi)) __inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK); + + /* + * We can come through here when swapping anonymous + * pages, so we don't necessarily have an inode to track + * for sync. + */ + if (mapping->host && !on_wblist) + sb_mark_inode_writeback(mapping->host); } if (!PageDirty(page)) radix_tree_tag_clear(&mapping->page_tree, @@ -2785,7 +2842,8 @@ int __test_set_page_writeback(struct page *page, bool keep_write) } if (!ret) { mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK); - inc_zone_page_state(page, NR_WRITEBACK); + inc_node_page_state(page, NR_WRITEBACK); + inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); } unlock_page_memcg(page); return ret; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 59de90d5d3a3..fb975cec3518 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -63,6 +63,7 @@ #include <linux/sched/rt.h> #include <linux/page_owner.h> #include <linux/kthread.h> +#include <linux/memcontrol.h> #include <asm/sections.h> #include <asm/tlbflush.h> @@ -286,15 +287,9 @@ static inline void reset_deferred_meminit(pg_data_t *pgdat) /* Returns true if the struct page for the pfn is uninitialised */ static inline bool __meminit early_page_uninitialised(unsigned long pfn) { - if (pfn >= NODE_DATA(early_pfn_to_nid(pfn))->first_deferred_pfn) - return true; - - return false; -} + int nid = early_pfn_to_nid(pfn); -static inline bool early_page_nid_uninitialised(unsigned long pfn, int nid) -{ - if (pfn >= NODE_DATA(nid)->first_deferred_pfn) + if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn) return true; return false; @@ -339,11 +334,6 @@ static inline bool early_page_uninitialised(unsigned long pfn) return false; } -static inline bool early_page_nid_uninitialised(unsigned long pfn, int nid) -{ - return false; -} - static inline bool update_defer_init(pg_data_t *pgdat, unsigned long pfn, unsigned long zone_end, unsigned long *nr_initialised) @@ -352,6 +342,106 @@ static inline bool update_defer_init(pg_data_t *pgdat, } #endif +/* Return a pointer to the bitmap storing bits affecting a block of pages */ +static inline unsigned long *get_pageblock_bitmap(struct page *page, + unsigned long pfn) +{ +#ifdef CONFIG_SPARSEMEM + return __pfn_to_section(pfn)->pageblock_flags; +#else + return page_zone(page)->pageblock_flags; +#endif /* CONFIG_SPARSEMEM */ +} + +static inline int pfn_to_bitidx(struct page *page, unsigned long pfn) +{ +#ifdef CONFIG_SPARSEMEM + pfn &= (PAGES_PER_SECTION-1); + return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS; +#else + pfn = pfn - round_down(page_zone(page)->zone_start_pfn, pageblock_nr_pages); + return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS; +#endif /* CONFIG_SPARSEMEM */ +} + +/** + * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages + * @page: The page within the block of interest + * @pfn: The target page frame number + * @end_bitidx: The last bit of interest to retrieve + * @mask: mask of bits that the caller is interested in + * + * Return: pageblock_bits flags + */ +static __always_inline unsigned long __get_pfnblock_flags_mask(struct page *page, + unsigned long pfn, + unsigned long end_bitidx, + unsigned long mask) +{ + unsigned long *bitmap; + unsigned long bitidx, word_bitidx; + unsigned long word; + + bitmap = get_pageblock_bitmap(page, pfn); + bitidx = pfn_to_bitidx(page, pfn); + word_bitidx = bitidx / BITS_PER_LONG; + bitidx &= (BITS_PER_LONG-1); + + word = bitmap[word_bitidx]; + bitidx += end_bitidx; + return (word >> (BITS_PER_LONG - bitidx - 1)) & mask; +} + +unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, + unsigned long end_bitidx, + unsigned long mask) +{ + return __get_pfnblock_flags_mask(page, pfn, end_bitidx, mask); +} + +static __always_inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn) +{ + return __get_pfnblock_flags_mask(page, pfn, PB_migrate_end, MIGRATETYPE_MASK); +} + +/** + * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages + * @page: The page within the block of interest + * @flags: The flags to set + * @pfn: The target page frame number + * @end_bitidx: The last bit of interest + * @mask: mask of bits that the caller is interested in + */ +void set_pfnblock_flags_mask(struct page *page, unsigned long flags, + unsigned long pfn, + unsigned long end_bitidx, + unsigned long mask) +{ + unsigned long *bitmap; + unsigned long bitidx, word_bitidx; + unsigned long old_word, word; + + BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); + + bitmap = get_pageblock_bitmap(page, pfn); + bitidx = pfn_to_bitidx(page, pfn); + word_bitidx = bitidx / BITS_PER_LONG; + bitidx &= (BITS_PER_LONG-1); + + VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page); + + bitidx += end_bitidx; + mask <<= (BITS_PER_LONG - bitidx - 1); + flags <<= (BITS_PER_LONG - bitidx - 1); + + word = READ_ONCE(bitmap[word_bitidx]); + for (;;) { + old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags); + if (word == old_word) + break; + word = old_word; + } +} void set_pageblock_migratetype(struct page *page, int migratetype) { @@ -422,12 +512,6 @@ static void bad_page(struct page *page, const char *reason, static unsigned long nr_shown; static unsigned long nr_unshown; - /* Don't complain about poisoned pages */ - if (PageHWPoison(page)) { - page_mapcount_reset(page); /* remove PageBuddy */ - return; - } - /* * Allow a burst of 60 reports, then keep quiet for that minute; * or allow a steady drip of one report per second. @@ -513,14 +597,7 @@ static int __init early_debug_pagealloc(char *buf) { if (!buf) return -EINVAL; - - if (strcmp(buf, "on") == 0) - _debug_pagealloc_enabled = true; - - if (strcmp(buf, "off") == 0) - _debug_pagealloc_enabled = false; - - return 0; + return kstrtobool(buf, &_debug_pagealloc_enabled); } early_param("debug_pagealloc", early_debug_pagealloc); @@ -569,6 +646,9 @@ static inline void set_page_guard(struct zone *zone, struct page *page, return; page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + return; + __set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags); INIT_LIST_HEAD(&page->lru); @@ -586,6 +666,9 @@ static inline void clear_page_guard(struct zone *zone, struct page *page, return; page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + return; + __clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags); set_page_private(page, 0); @@ -784,17 +867,42 @@ out: zone->free_area[order].nr_free++; } -static inline int free_pages_check(struct page *page) +/* + * A bad page could be due to a number of fields. Instead of multiple branches, + * try and check multiple fields with one check. The caller must do a detailed + * check if necessary. + */ +static inline bool page_expected_state(struct page *page, + unsigned long check_flags) { - const char *bad_reason = NULL; - unsigned long bad_flags = 0; + if (unlikely(atomic_read(&page->_mapcount) != -1)) + return false; + + if (unlikely((unsigned long)page->mapping | + page_ref_count(page) | +#ifdef CONFIG_MEMCG + (unsigned long)page->mem_cgroup | +#endif + (page->flags & check_flags))) + return false; + + return true; +} + +static void free_pages_check_bad(struct page *page) +{ + const char *bad_reason; + unsigned long bad_flags; + + bad_reason = NULL; + bad_flags = 0; if (unlikely(atomic_read(&page->_mapcount) != -1)) bad_reason = "nonzero mapcount"; if (unlikely(page->mapping != NULL)) bad_reason = "non-NULL mapping"; if (unlikely(page_ref_count(page) != 0)) - bad_reason = "nonzero _count"; + bad_reason = "nonzero _refcount"; if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_FREE)) { bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set"; bad_flags = PAGE_FLAGS_CHECK_AT_FREE; @@ -803,16 +911,152 @@ static inline int free_pages_check(struct page *page) if (unlikely(page->mem_cgroup)) bad_reason = "page still charged to cgroup"; #endif - if (unlikely(bad_reason)) { - bad_page(page, bad_reason, bad_flags); - return 1; + bad_page(page, bad_reason, bad_flags); +} + +static inline int free_pages_check(struct page *page) +{ + if (likely(page_expected_state(page, PAGE_FLAGS_CHECK_AT_FREE))) + return 0; + + /* Something has gone sideways, find it */ + free_pages_check_bad(page); + return 1; +} + +static int free_tail_pages_check(struct page *head_page, struct page *page) +{ + int ret = 1; + + /* + * We rely page->lru.next never has bit 0 set, unless the page + * is PageTail(). Let's make sure that's true even for poisoned ->lru. + */ + BUILD_BUG_ON((unsigned long)LIST_POISON1 & 1); + + if (!IS_ENABLED(CONFIG_DEBUG_VM)) { + ret = 0; + goto out; } + switch (page - head_page) { + case 1: + /* the first tail page: ->mapping is compound_mapcount() */ + if (unlikely(compound_mapcount(page))) { + bad_page(page, "nonzero compound_mapcount", 0); + goto out; + } + break; + case 2: + /* + * the second tail page: ->mapping is + * page_deferred_list().next -- ignore value. + */ + break; + default: + if (page->mapping != TAIL_MAPPING) { + bad_page(page, "corrupted mapping in tail page", 0); + goto out; + } + break; + } + if (unlikely(!PageTail(page))) { + bad_page(page, "PageTail not set", 0); + goto out; + } + if (unlikely(compound_head(page) != head_page)) { + bad_page(page, "compound_head not consistent", 0); + goto out; + } + ret = 0; +out: + page->mapping = NULL; + clear_compound_head(page); + return ret; +} + +static __always_inline bool free_pages_prepare(struct page *page, + unsigned int order, bool check_free) +{ + int bad = 0; + + VM_BUG_ON_PAGE(PageTail(page), page); + + trace_mm_page_free(page, order); + kmemcheck_free_shadow(page, order); + + /* + * Check tail pages before head page information is cleared to + * avoid checking PageCompound for order-0 pages. + */ + if (unlikely(order)) { + bool compound = PageCompound(page); + int i; + + VM_BUG_ON_PAGE(compound && compound_order(page) != order, page); + + if (compound) + ClearPageDoubleMap(page); + for (i = 1; i < (1 << order); i++) { + if (compound) + bad += free_tail_pages_check(page, page + i); + if (unlikely(free_pages_check(page + i))) { + bad++; + continue; + } + (page + i)->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; + } + } + if (PageMappingFlags(page)) + page->mapping = NULL; + if (memcg_kmem_enabled() && PageKmemcg(page)) { + memcg_kmem_uncharge(page, order); + __ClearPageKmemcg(page); + } + if (check_free) + bad += free_pages_check(page); + if (bad) + return false; + page_cpupid_reset_last(page); - if (page->flags & PAGE_FLAGS_CHECK_AT_PREP) - page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; - return 0; + page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; + reset_page_owner(page, order); + + if (!PageHighMem(page)) { + debug_check_no_locks_freed(page_address(page), + PAGE_SIZE << order); + debug_check_no_obj_freed(page_address(page), + PAGE_SIZE << order); + } + arch_free_page(page, order); + kernel_poison_pages(page, 1 << order, 0); + kernel_map_pages(page, 1 << order, 0); + kasan_free_pages(page, order); + + return true; } +#ifdef CONFIG_DEBUG_VM +static inline bool free_pcp_prepare(struct page *page) +{ + return free_pages_prepare(page, 0, true); +} + +static inline bool bulkfree_pcp_prepare(struct page *page) +{ + return false; +} +#else +static bool free_pcp_prepare(struct page *page) +{ + return free_pages_prepare(page, 0, false); +} + +static bool bulkfree_pcp_prepare(struct page *page) +{ + return free_pages_check(page); +} +#endif /* CONFIG_DEBUG_VM */ + /* * Frees a number of pages from the PCP lists * Assumes all pages on list are in same zone, and of same order. @@ -829,15 +1073,16 @@ static void free_pcppages_bulk(struct zone *zone, int count, { int migratetype = 0; int batch_free = 0; - int to_free = count; unsigned long nr_scanned; + bool isolated_pageblocks; spin_lock(&zone->lock); - nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + isolated_pageblocks = has_isolate_pageblock(zone); + nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED); if (nr_scanned) - __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); + __mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned); - while (to_free) { + while (count) { struct page *page; struct list_head *list; @@ -857,7 +1102,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, /* This is the only non-empty list. Free them all. */ if (batch_free == MIGRATE_PCPTYPES) - batch_free = to_free; + batch_free = count; do { int mt; /* migratetype of the to-be-freed page */ @@ -870,12 +1115,15 @@ static void free_pcppages_bulk(struct zone *zone, int count, /* MIGRATE_ISOLATE page should not go to pcplists */ VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); /* Pageblock could have been isolated meanwhile */ - if (unlikely(has_isolate_pageblock(zone))) + if (unlikely(isolated_pageblocks)) mt = get_pageblock_migratetype(page); + if (bulkfree_pcp_prepare(page)) + continue; + __free_one_page(page, page_to_pfn(page), zone, 0, mt); trace_mm_page_pcpu_drain(page, 0, mt); - } while (--to_free && --batch_free && !list_empty(list)); + } while (--count && --batch_free && !list_empty(list)); } spin_unlock(&zone->lock); } @@ -887,9 +1135,9 @@ static void free_one_page(struct zone *zone, { unsigned long nr_scanned; spin_lock(&zone->lock); - nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED); if (nr_scanned) - __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); + __mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned); if (unlikely(has_isolate_pageblock(zone) || is_migrate_isolate(migratetype))) { @@ -899,56 +1147,6 @@ static void free_one_page(struct zone *zone, spin_unlock(&zone->lock); } -static int free_tail_pages_check(struct page *head_page, struct page *page) -{ - int ret = 1; - - /* - * We rely page->lru.next never has bit 0 set, unless the page - * is PageTail(). Let's make sure that's true even for poisoned ->lru. - */ - BUILD_BUG_ON((unsigned long)LIST_POISON1 & 1); - - if (!IS_ENABLED(CONFIG_DEBUG_VM)) { - ret = 0; - goto out; - } - switch (page - head_page) { - case 1: - /* the first tail page: ->mapping is compound_mapcount() */ - if (unlikely(compound_mapcount(page))) { - bad_page(page, "nonzero compound_mapcount", 0); - goto out; - } - break; - case 2: - /* - * the second tail page: ->mapping is - * page_deferred_list().next -- ignore value. - */ - break; - default: - if (page->mapping != TAIL_MAPPING) { - bad_page(page, "corrupted mapping in tail page", 0); - goto out; - } - break; - } - if (unlikely(!PageTail(page))) { - bad_page(page, "PageTail not set", 0); - goto out; - } - if (unlikely(compound_head(page) != head_page)) { - bad_page(page, "compound_head not consistent", 0); - goto out; - } - ret = 0; -out: - page->mapping = NULL; - clear_compound_head(page); - return ret; -} - static void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long zone, int nid) { @@ -1003,7 +1201,7 @@ static inline void init_reserved_page(unsigned long pfn) * marks the pages PageReserved. The remaining valid pages are later * sent to the buddy page allocator. */ -void __meminit reserve_bootmem_region(unsigned long start, unsigned long end) +void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end) { unsigned long start_pfn = PFN_DOWN(start); unsigned long end_pfn = PFN_UP(end); @@ -1022,51 +1220,13 @@ void __meminit reserve_bootmem_region(unsigned long start, unsigned long end) } } -static bool free_pages_prepare(struct page *page, unsigned int order) -{ - bool compound = PageCompound(page); - int i, bad = 0; - - VM_BUG_ON_PAGE(PageTail(page), page); - VM_BUG_ON_PAGE(compound && compound_order(page) != order, page); - - trace_mm_page_free(page, order); - kmemcheck_free_shadow(page, order); - kasan_free_pages(page, order); - - if (PageAnon(page)) - page->mapping = NULL; - bad += free_pages_check(page); - for (i = 1; i < (1 << order); i++) { - if (compound) - bad += free_tail_pages_check(page, page + i); - bad += free_pages_check(page + i); - } - if (bad) - return false; - - reset_page_owner(page, order); - - if (!PageHighMem(page)) { - debug_check_no_locks_freed(page_address(page), - PAGE_SIZE << order); - debug_check_no_obj_freed(page_address(page), - PAGE_SIZE << order); - } - arch_free_page(page, order); - kernel_poison_pages(page, 1 << order, 0); - kernel_map_pages(page, 1 << order, 0); - - return true; -} - static void __free_pages_ok(struct page *page, unsigned int order) { unsigned long flags; int migratetype; unsigned long pfn = page_to_pfn(page); - if (!free_pages_prepare(page, order)) + if (!free_pages_prepare(page, order, true)) return; migratetype = get_pfnblock_migratetype(page, pfn); @@ -1076,8 +1236,7 @@ static void __free_pages_ok(struct page *page, unsigned int order) local_irq_restore(flags); } -static void __init __free_pages_boot_core(struct page *page, - unsigned long pfn, unsigned int order) +static void __init __free_pages_boot_core(struct page *page, unsigned int order) { unsigned int nr_pages = 1 << order; struct page *p = page; @@ -1110,7 +1269,7 @@ int __meminit early_pfn_to_nid(unsigned long pfn) spin_lock(&early_pfn_lock); nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache); if (nid < 0) - nid = 0; + nid = first_online_node; spin_unlock(&early_pfn_lock); return nid; @@ -1154,7 +1313,7 @@ void __init __free_pages_bootmem(struct page *page, unsigned long pfn, { if (early_page_uninitialised(pfn)) return; - return __free_pages_boot_core(page, pfn, order); + return __free_pages_boot_core(page, order); } /* @@ -1239,12 +1398,12 @@ static void __init deferred_free_range(struct page *page, if (nr_pages == MAX_ORDER_NR_PAGES && (pfn & (MAX_ORDER_NR_PAGES-1)) == 0) { set_pageblock_migratetype(page, MIGRATE_MOVABLE); - __free_pages_boot_core(page, pfn, MAX_ORDER-1); + __free_pages_boot_core(page, MAX_ORDER-1); return; } - for (i = 0; i < nr_pages; i++, page++, pfn++) - __free_pages_boot_core(page, pfn, 0); + for (i = 0; i < nr_pages; i++, page++) + __free_pages_boot_core(page, 0); } /* Completion tracking for deferred_init_memmap() threads */ @@ -1477,10 +1636,7 @@ static inline void expand(struct zone *zone, struct page *page, } } -/* - * This page is about to be returned from the page allocator - */ -static inline int check_new_page(struct page *page) +static void check_new_page_bad(struct page *page) { const char *bad_reason = NULL; unsigned long bad_flags = 0; @@ -1494,6 +1650,9 @@ static inline int check_new_page(struct page *page) if (unlikely(page->flags & __PG_HWPOISON)) { bad_reason = "HWPoisoned (hardware-corrupted)"; bad_flags = __PG_HWPOISON; + /* Don't complain about hwpoisoned pages */ + page_mapcount_reset(page); /* remove PageBuddy */ + return; } if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) { bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set"; @@ -1503,11 +1662,20 @@ static inline int check_new_page(struct page *page) if (unlikely(page->mem_cgroup)) bad_reason = "page still charged to cgroup"; #endif - if (unlikely(bad_reason)) { - bad_page(page, bad_reason, bad_flags); - return 1; - } - return 0; + bad_page(page, bad_reason, bad_flags); +} + +/* + * This page is about to be returned from the page allocator + */ +static inline int check_new_page(struct page *page) +{ + if (likely(page_expected_state(page, + PAGE_FLAGS_CHECK_AT_PREP|__PG_HWPOISON))) + return 0; + + check_new_page_bad(page); + return 1; } static inline bool free_pages_prezeroed(bool poisoned) @@ -1516,20 +1684,43 @@ static inline bool free_pages_prezeroed(bool poisoned) page_poisoning_enabled() && poisoned; } -static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, - int alloc_flags) +#ifdef CONFIG_DEBUG_VM +static bool check_pcp_refill(struct page *page) { - int i; - bool poisoned = true; + return false; +} + +static bool check_new_pcp(struct page *page) +{ + return check_new_page(page); +} +#else +static bool check_pcp_refill(struct page *page) +{ + return check_new_page(page); +} +static bool check_new_pcp(struct page *page) +{ + return false; +} +#endif /* CONFIG_DEBUG_VM */ +static bool check_new_pages(struct page *page, unsigned int order) +{ + int i; for (i = 0; i < (1 << order); i++) { struct page *p = page + i; + if (unlikely(check_new_page(p))) - return 1; - if (poisoned) - poisoned &= page_is_poisoned(p); + return true; } + return false; +} + +inline void post_alloc_hook(struct page *page, unsigned int order, + gfp_t gfp_flags) +{ set_page_private(page, 0); set_page_refcounted(page); @@ -1537,6 +1728,22 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, kernel_map_pages(page, 1 << order, 1); kernel_poison_pages(page, 1 << order, 1); kasan_alloc_pages(page, order); + set_page_owner(page, order, gfp_flags); +} + +static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, + unsigned int alloc_flags) +{ + int i; + bool poisoned = true; + + for (i = 0; i < (1 << order); i++) { + struct page *p = page + i; + if (poisoned) + poisoned &= page_is_poisoned(p); + } + + post_alloc_hook(page, order, gfp_flags); if (!free_pages_prezeroed(poisoned) && (gfp_flags & __GFP_ZERO)) for (i = 0; i < (1 << order); i++) @@ -1545,8 +1752,6 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, if (order && (gfp_flags & __GFP_COMP)) prep_compound_page(page, order); - set_page_owner(page, order, gfp_flags); - /* * page is set pfmemalloc when ALLOC_NO_WATERMARKS was necessary to * allocate the page. The expectation is that the caller is taking @@ -1557,8 +1762,6 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, set_page_pfmemalloc(page); else clear_page_pfmemalloc(page); - - return 0; } /* @@ -1980,6 +2183,9 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, if (unlikely(page == NULL)) break; + if (unlikely(check_pcp_refill(page))) + continue; + /* * Split buddy pages returned by expand() are received here * in physical page order. The page is added to the callers and @@ -2157,6 +2363,10 @@ void mark_free_pages(struct zone *zone) for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) if (pfn_valid(pfn)) { page = pfn_to_page(pfn); + + if (page_zone(page) != zone) + continue; + if (!swsusp_page_is_forbidden(page)) swsusp_unset_page_free(page); } @@ -2187,7 +2397,7 @@ void free_hot_cold_page(struct page *page, bool cold) unsigned long pfn = page_to_pfn(page); int migratetype; - if (!free_pages_prepare(page, 0)) + if (!free_pcp_prepare(page)) return; migratetype = get_pfnblock_migratetype(page, pfn); @@ -2250,7 +2460,6 @@ void free_hot_cold_page_list(struct list_head *list, bool cold) void split_page(struct page *page, unsigned int order) { int i; - gfp_t gfp_mask; VM_BUG_ON_PAGE(PageCompound(page), page); VM_BUG_ON_PAGE(!page_count(page), page); @@ -2264,12 +2473,9 @@ void split_page(struct page *page, unsigned int order) split_page(virt_to_page(page[0].shadow), order); #endif - gfp_mask = get_page_owner_gfp(page); - set_page_owner(page, 0, gfp_mask); - for (i = 1; i < (1 << order); i++) { + for (i = 1; i < (1 << order); i++) set_page_refcounted(page + i); - set_page_owner(page + i, 0, gfp_mask); - } + split_page_owner(page, order); } EXPORT_SYMBOL_GPL(split_page); @@ -2298,9 +2504,10 @@ int __isolate_free_page(struct page *page, unsigned int order) zone->free_area[order].nr_free--; rmv_page_order(page); - set_page_owner(page, order, __GFP_MOVABLE); - - /* Set the pageblock if the isolated page is at least a pageblock */ + /* + * Set the pageblock if the isolated page is at least half of a + * pageblock + */ if (order >= pageblock_order - 1) { struct page *endpage = page + (1 << order) - 1; for (; page < endpage; page += pageblock_nr_pages) { @@ -2316,30 +2523,34 @@ int __isolate_free_page(struct page *page, unsigned int order) } /* - * Similar to split_page except the page is already free. As this is only - * being used for migration, the migratetype of the block also changes. - * As this is called with interrupts disabled, the caller is responsible - * for calling arch_alloc_page() and kernel_map_page() after interrupts - * are enabled. + * Update NUMA hit/miss statistics * - * Note: this is probably too low level an operation for use in drivers. - * Please consult with lkml before using this in your driver. + * Must be called with interrupts disabled. + * + * When __GFP_OTHER_NODE is set assume the node of the preferred + * zone is the local node. This is useful for daemons who allocate + * memory on behalf of other processes. */ -int split_free_page(struct page *page) +static inline void zone_statistics(struct zone *preferred_zone, struct zone *z, + gfp_t flags) { - unsigned int order; - int nr_pages; - - order = page_order(page); +#ifdef CONFIG_NUMA + int local_nid = numa_node_id(); + enum zone_stat_item local_stat = NUMA_LOCAL; - nr_pages = __isolate_free_page(page, order); - if (!nr_pages) - return 0; + if (unlikely(flags & __GFP_OTHER_NODE)) { + local_stat = NUMA_OTHER; + local_nid = preferred_zone->node; + } - /* Split into individual pages */ - set_page_refcounted(page); - split_page(page, order); - return nr_pages; + if (z->node == local_nid) { + __inc_zone_state(z, NUMA_HIT); + __inc_zone_state(z, local_stat); + } else { + __inc_zone_state(z, NUMA_MISS); + __inc_zone_state(preferred_zone, NUMA_FOREIGN); + } +#endif } /* @@ -2348,7 +2559,8 @@ int split_free_page(struct page *page) static inline struct page *buffered_rmqueue(struct zone *preferred_zone, struct zone *zone, unsigned int order, - gfp_t gfp_flags, int alloc_flags, int migratetype) + gfp_t gfp_flags, unsigned int alloc_flags, + int migratetype) { unsigned long flags; struct page *page; @@ -2359,23 +2571,26 @@ struct page *buffered_rmqueue(struct zone *preferred_zone, struct list_head *list; local_irq_save(flags); - pcp = &this_cpu_ptr(zone->pageset)->pcp; - list = &pcp->lists[migratetype]; - if (list_empty(list)) { - pcp->count += rmqueue_bulk(zone, 0, - pcp->batch, list, - migratetype, cold); - if (unlikely(list_empty(list))) - goto failed; - } + do { + pcp = &this_cpu_ptr(zone->pageset)->pcp; + list = &pcp->lists[migratetype]; + if (list_empty(list)) { + pcp->count += rmqueue_bulk(zone, 0, + pcp->batch, list, + migratetype, cold); + if (unlikely(list_empty(list))) + goto failed; + } - if (cold) - page = list_last_entry(list, struct page, lru); - else - page = list_first_entry(list, struct page, lru); + if (cold) + page = list_last_entry(list, struct page, lru); + else + page = list_first_entry(list, struct page, lru); - list_del(&page->lru); - pcp->count--; + list_del(&page->lru); + pcp->count--; + + } while (check_new_pcp(page)); } else { /* * We most definitely don't want callers attempting to @@ -2384,14 +2599,16 @@ struct page *buffered_rmqueue(struct zone *preferred_zone, WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1)); spin_lock_irqsave(&zone->lock, flags); - page = NULL; - if (alloc_flags & ALLOC_HARDER) { - page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); - if (page) - trace_mm_page_alloc_zone_locked(page, order, migratetype); - } - if (!page) - page = __rmqueue(zone, order, migratetype); + do { + page = NULL; + if (alloc_flags & ALLOC_HARDER) { + page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); + if (page) + trace_mm_page_alloc_zone_locked(page, order, migratetype); + } + if (!page) + page = __rmqueue(zone, order, migratetype); + } while (page && check_new_pages(page, order)); spin_unlock(&zone->lock); if (!page) goto failed; @@ -2399,12 +2616,7 @@ struct page *buffered_rmqueue(struct zone *preferred_zone, get_pcppage_migratetype(page)); } - __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); - if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0 && - !test_bit(ZONE_FAIR_DEPLETED, &zone->flags)) - set_bit(ZONE_FAIR_DEPLETED, &zone->flags); - - __count_zone_vm_events(PGALLOC, zone, 1 << order); + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); zone_statistics(preferred_zone, zone, gfp_flags); local_irq_restore(flags); @@ -2500,13 +2712,13 @@ static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) * one free page of a suitable size. Checking now avoids taking the zone lock * to check in the allocation paths if no pages are free. */ -static bool __zone_watermark_ok(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx, int alloc_flags, - long free_pages) +bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, + int classzone_idx, unsigned int alloc_flags, + long free_pages) { long min = mark; int o; - const int alloc_harder = (alloc_flags & ALLOC_HARDER); + const bool alloc_harder = (alloc_flags & ALLOC_HARDER); /* free_pages may go negative - that's OK */ free_pages -= (1 << order) - 1; @@ -2569,12 +2781,38 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order, } bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, - int classzone_idx, int alloc_flags) + int classzone_idx, unsigned int alloc_flags) { return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, zone_page_state(z, NR_FREE_PAGES)); } +static inline bool zone_watermark_fast(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, unsigned int alloc_flags) +{ + long free_pages = zone_page_state(z, NR_FREE_PAGES); + long cma_pages = 0; + +#ifdef CONFIG_CMA + /* If allocation can't use CMA areas don't use free CMA pages */ + if (!(alloc_flags & ALLOC_CMA)) + cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES); +#endif + + /* + * Fast check for order-0 only. If this fails then the reserves + * need to be calculated. There is a corner case where the check + * passes but only the high-order atomic reserve are free. If + * the caller is !atomic then it'll uselessly search the free + * list. That corner case is then slower but it is harmless. + */ + if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx]) + return true; + + return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, + free_pages); +} + bool zone_watermark_ok_safe(struct zone *z, unsigned int order, unsigned long mark, int classzone_idx) { @@ -2588,40 +2826,18 @@ bool zone_watermark_ok_safe(struct zone *z, unsigned int order, } #ifdef CONFIG_NUMA -static bool zone_local(struct zone *local_zone, struct zone *zone) -{ - return local_zone->node == zone->node; -} - static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) < RECLAIM_DISTANCE; } #else /* CONFIG_NUMA */ -static bool zone_local(struct zone *local_zone, struct zone *zone) -{ - return true; -} - static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { return true; } #endif /* CONFIG_NUMA */ -static void reset_alloc_batches(struct zone *preferred_zone) -{ - struct zone *zone = preferred_zone->zone_pgdat->node_zones; - - do { - mod_zone_page_state(zone, NR_ALLOC_BATCH, - high_wmark_pages(zone) - low_wmark_pages(zone) - - atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); - clear_bit(ZONE_FAIR_DEPLETED, &zone->flags); - } while (zone++ != preferred_zone); -} - /* * get_page_from_freelist goes through the zonelist trying to allocate * a page. @@ -2630,74 +2846,55 @@ static struct page * get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, const struct alloc_context *ac) { - struct zonelist *zonelist = ac->zonelist; - struct zoneref *z; - struct page *page = NULL; + struct zoneref *z = ac->preferred_zoneref; struct zone *zone; - int nr_fair_skipped = 0; - bool zonelist_rescan; - -zonelist_scan: - zonelist_rescan = false; + struct pglist_data *last_pgdat_dirty_limit = NULL; /* * Scan zonelist, looking for a zone with enough free. * See also __cpuset_node_allowed() comment in kernel/cpuset.c. */ - for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->high_zoneidx, + for_next_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, ac->nodemask) { + struct page *page; unsigned long mark; if (cpusets_enabled() && (alloc_flags & ALLOC_CPUSET) && - !cpuset_zone_allowed(zone, gfp_mask)) + !__cpuset_zone_allowed(zone, gfp_mask)) continue; /* - * Distribute pages in proportion to the individual - * zone size to ensure fair page aging. The zone a - * page was allocated in should have no effect on the - * time the page has in memory before being reclaimed. - */ - if (alloc_flags & ALLOC_FAIR) { - if (!zone_local(ac->preferred_zone, zone)) - break; - if (test_bit(ZONE_FAIR_DEPLETED, &zone->flags)) { - nr_fair_skipped++; - continue; - } - } - /* * When allocating a page cache page for writing, we - * want to get it from a zone that is within its dirty - * limit, such that no single zone holds more than its + * want to get it from a node that is within its dirty + * limit, such that no single node holds more than its * proportional share of globally allowed dirty pages. - * The dirty limits take into account the zone's + * The dirty limits take into account the node's * lowmem reserves and high watermark so that kswapd * should be able to balance it without having to * write pages from its LRU list. * - * This may look like it could increase pressure on - * lower zones by failing allocations in higher zones - * before they are full. But the pages that do spill - * over are limited as the lower zones are protected - * by this very same mechanism. It should not become - * a practical burden to them. - * * XXX: For now, allow allocations to potentially - * exceed the per-zone dirty limit in the slowpath + * exceed the per-node dirty limit in the slowpath * (spread_dirty_pages unset) before going into reclaim, * which is important when on a NUMA setup the allowed - * zones are together not big enough to reach the + * nodes are together not big enough to reach the * global limit. The proper fix for these situations - * will require awareness of zones in the + * will require awareness of nodes in the * dirty-throttling and the flusher threads. */ - if (ac->spread_dirty_pages && !zone_dirty_ok(zone)) - continue; + if (ac->spread_dirty_pages) { + if (last_pgdat_dirty_limit == zone->zone_pgdat) + continue; + + if (!node_dirty_ok(zone->zone_pgdat)) { + last_pgdat_dirty_limit = zone->zone_pgdat; + continue; + } + } mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; - if (!zone_watermark_ok(zone, order, mark, - ac->classzone_idx, alloc_flags)) { + if (!zone_watermark_fast(zone, order, mark, + ac_classzone_idx(ac), alloc_flags)) { int ret; /* Checked here to keep the fast path fast */ @@ -2705,22 +2902,22 @@ zonelist_scan: if (alloc_flags & ALLOC_NO_WATERMARKS) goto try_this_zone; - if (zone_reclaim_mode == 0 || - !zone_allows_reclaim(ac->preferred_zone, zone)) + if (node_reclaim_mode == 0 || + !zone_allows_reclaim(ac->preferred_zoneref->zone, zone)) continue; - ret = zone_reclaim(zone, gfp_mask, order); + ret = node_reclaim(zone->zone_pgdat, gfp_mask, order); switch (ret) { - case ZONE_RECLAIM_NOSCAN: + case NODE_RECLAIM_NOSCAN: /* did not scan */ continue; - case ZONE_RECLAIM_FULL: + case NODE_RECLAIM_FULL: /* scanned but unreclaimable */ continue; default: /* did we reclaim enough */ if (zone_watermark_ok(zone, order, mark, - ac->classzone_idx, alloc_flags)) + ac_classzone_idx(ac), alloc_flags)) goto try_this_zone; continue; @@ -2728,11 +2925,10 @@ zonelist_scan: } try_this_zone: - page = buffered_rmqueue(ac->preferred_zone, zone, order, + page = buffered_rmqueue(ac->preferred_zoneref->zone, zone, order, gfp_mask, alloc_flags, ac->migratetype); if (page) { - if (prep_new_page(page, order, gfp_mask, alloc_flags)) - goto try_this_zone; + prep_new_page(page, order, gfp_mask, alloc_flags); /* * If this is a high-order atomic allocation then check @@ -2745,27 +2941,6 @@ try_this_zone: } } - /* - * The first pass makes sure allocations are spread fairly within the - * local node. However, the local node might have free pages left - * after the fairness batches are exhausted, and remote zones haven't - * even been considered yet. Try once more without fairness, and - * include remote zones now, before entering the slowpath and waking - * kswapd: prefer spilling to a remote zone over swapping locally. - */ - if (alloc_flags & ALLOC_FAIR) { - alloc_flags &= ~ALLOC_FAIR; - if (nr_fair_skipped) { - zonelist_rescan = true; - reset_alloc_batches(ac->preferred_zone); - } - if (nr_online_nodes > 1) - zonelist_rescan = true; - } - - if (zonelist_rescan) - goto zonelist_scan; - return NULL; } @@ -2835,6 +3010,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, struct oom_control oc = { .zonelist = ac->zonelist, .nodemask = ac->nodemask, + .memcg = NULL, .gfp_mask = gfp_mask, .order = order, }; @@ -2872,22 +3048,18 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, /* The OOM killer does not needlessly kill tasks for lowmem */ if (ac->high_zoneidx < ZONE_NORMAL) goto out; - /* The OOM killer does not compensate for IO-less reclaim */ - if (!(gfp_mask & __GFP_FS)) { - /* - * XXX: Page reclaim didn't yield anything, - * and the OOM killer can't be invoked, but - * keep looping as per tradition. - * - * But do not keep looping if oom_killer_disable() - * was already called, for the system is trying to - * enter a quiescent state during suspend. - */ - *did_some_progress = !oom_killer_disabled; - goto out; - } if (pm_suspended_storage()) goto out; + /* + * XXX: GFP_NOFS allocations should rather fail than rely on + * other request to make a forward progress. + * We are in an unfortunate situation where out_of_memory cannot + * do much for this context but let's try it to at least get + * access to memory reserved if the current task is killed (see + * out_of_memory). Once filesystems are ready to handle allocation + * failures more gracefully we should just bail out here. + */ + /* The OOM killer may not free memory on a specific node */ if (gfp_mask & __GFP_THISNODE) goto out; @@ -2913,34 +3085,31 @@ out: return page; } +/* + * Maximum number of compaction retries wit a progress before OOM + * killer is consider as the only way to move forward. + */ +#define MAX_COMPACT_RETRIES 16 + #ifdef CONFIG_COMPACTION /* Try memory compaction for high-order allocations before reclaim */ static struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, - int alloc_flags, const struct alloc_context *ac, - enum migrate_mode mode, int *contended_compaction, - bool *deferred_compaction) + unsigned int alloc_flags, const struct alloc_context *ac, + enum compact_priority prio, enum compact_result *compact_result) { - unsigned long compact_result; struct page *page; if (!order) return NULL; current->flags |= PF_MEMALLOC; - compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, - mode, contended_compaction); + *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, + prio); current->flags &= ~PF_MEMALLOC; - switch (compact_result) { - case COMPACT_DEFERRED: - *deferred_compaction = true; - /* fall-through */ - case COMPACT_SKIPPED: + if (*compact_result <= COMPACT_INACTIVE) return NULL; - default: - break; - } /* * At least in one zone compaction wasn't deferred or skipped, so let's @@ -2948,8 +3117,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, */ count_vm_event(COMPACTSTALL); - page = get_page_from_freelist(gfp_mask, order, - alloc_flags & ~ALLOC_NO_WATERMARKS, ac); + page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); if (page) { struct zone *zone = page_zone(page); @@ -2970,15 +3138,91 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, return NULL; } + +static inline bool +should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, + enum compact_result compact_result, + enum compact_priority *compact_priority, + int compaction_retries) +{ + int max_retries = MAX_COMPACT_RETRIES; + + if (!order) + return false; + + /* + * compaction considers all the zone as desperately out of memory + * so it doesn't really make much sense to retry except when the + * failure could be caused by insufficient priority + */ + if (compaction_failed(compact_result)) { + if (*compact_priority > MIN_COMPACT_PRIORITY) { + (*compact_priority)--; + return true; + } + return false; + } + + /* + * make sure the compaction wasn't deferred or didn't bail out early + * due to locks contention before we declare that we should give up. + * But do not retry if the given zonelist is not suitable for + * compaction. + */ + if (compaction_withdrawn(compact_result)) + return compaction_zonelist_suitable(ac, order, alloc_flags); + + /* + * !costly requests are much more important than __GFP_REPEAT + * costly ones because they are de facto nofail and invoke OOM + * killer to move on while costly can fail and users are ready + * to cope with that. 1/4 retries is rather arbitrary but we + * would need much more detailed feedback from compaction to + * make a better decision. + */ + if (order > PAGE_ALLOC_COSTLY_ORDER) + max_retries /= 4; + if (compaction_retries <= max_retries) + return true; + + return false; +} #else static inline struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, - int alloc_flags, const struct alloc_context *ac, - enum migrate_mode mode, int *contended_compaction, - bool *deferred_compaction) + unsigned int alloc_flags, const struct alloc_context *ac, + enum compact_priority prio, enum compact_result *compact_result) { + *compact_result = COMPACT_SKIPPED; return NULL; } + +static inline bool +should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_flags, + enum compact_result compact_result, + enum compact_priority *compact_priority, + int compaction_retries) +{ + struct zone *zone; + struct zoneref *z; + + if (!order || order > PAGE_ALLOC_COSTLY_ORDER) + return false; + + /* + * There are setups with compaction disabled which would prefer to loop + * inside the allocator rather than hit the oom killer prematurely. + * Let's give them a good hope and keep retrying while the order-0 + * watermarks are OK. + */ + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, + ac->nodemask) { + if (zone_watermark_ok(zone, 0, min_wmark_pages(zone), + ac_classzone_idx(ac), alloc_flags)) + return true; + } + return false; +} #endif /* CONFIG_COMPACTION */ /* Perform direct synchronous page reclaim */ @@ -3013,7 +3257,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, /* The really slow allocator path where we enter direct reclaim */ static inline struct page * __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, - int alloc_flags, const struct alloc_context *ac, + unsigned int alloc_flags, const struct alloc_context *ac, unsigned long *did_some_progress) { struct page *page = NULL; @@ -3024,8 +3268,7 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, return NULL; retry: - page = get_page_from_freelist(gfp_mask, order, - alloc_flags & ~ALLOC_NO_WATERMARKS, ac); + page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); /* * If an allocation failed after direct reclaim, it could be because @@ -3046,16 +3289,20 @@ static void wake_all_kswapds(unsigned int order, const struct alloc_context *ac) { struct zoneref *z; struct zone *zone; + pg_data_t *last_pgdat = NULL; for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, - ac->high_zoneidx, ac->nodemask) - wakeup_kswapd(zone, order, zone_idx(ac->preferred_zone)); + ac->high_zoneidx, ac->nodemask) { + if (last_pgdat != zone->zone_pgdat) + wakeup_kswapd(zone, order, ac->high_zoneidx); + last_pgdat = zone->zone_pgdat; + } } -static inline int +static inline unsigned int gfp_to_alloc_flags(gfp_t gfp_mask) { - int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; + unsigned int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */ BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH); @@ -3083,16 +3330,6 @@ gfp_to_alloc_flags(gfp_t gfp_mask) } else if (unlikely(rt_task(current)) && !in_interrupt()) alloc_flags |= ALLOC_HARDER; - if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) { - if (gfp_mask & __GFP_MEMALLOC) - alloc_flags |= ALLOC_NO_WATERMARKS; - else if (in_serving_softirq() && (current->flags & PF_MEMALLOC)) - alloc_flags |= ALLOC_NO_WATERMARKS; - else if (!in_interrupt() && - ((current->flags & PF_MEMALLOC) || - unlikely(test_thread_flag(TIF_MEMDIE)))) - alloc_flags |= ALLOC_NO_WATERMARKS; - } #ifdef CONFIG_CMA if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE) alloc_flags |= ALLOC_CMA; @@ -3102,12 +3339,112 @@ gfp_to_alloc_flags(gfp_t gfp_mask) bool gfp_pfmemalloc_allowed(gfp_t gfp_mask) { - return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS); + if (unlikely(gfp_mask & __GFP_NOMEMALLOC)) + return false; + + if (gfp_mask & __GFP_MEMALLOC) + return true; + if (in_serving_softirq() && (current->flags & PF_MEMALLOC)) + return true; + if (!in_interrupt() && + ((current->flags & PF_MEMALLOC) || + unlikely(test_thread_flag(TIF_MEMDIE)))) + return true; + + return false; } -static inline bool is_thp_gfp_mask(gfp_t gfp_mask) +/* + * Maximum number of reclaim retries without any progress before OOM killer + * is consider as the only way to move forward. + */ +#define MAX_RECLAIM_RETRIES 16 + +/* + * Checks whether it makes sense to retry the reclaim to make a forward progress + * for the given allocation request. + * The reclaim feedback represented by did_some_progress (any progress during + * the last reclaim round) and no_progress_loops (number of reclaim rounds without + * any progress in a row) is considered as well as the reclaimable pages on the + * applicable zone list (with a backoff mechanism which is a function of + * no_progress_loops). + * + * Returns true if a retry is viable or false to enter the oom path. + */ +static inline bool +should_reclaim_retry(gfp_t gfp_mask, unsigned order, + struct alloc_context *ac, int alloc_flags, + bool did_some_progress, int no_progress_loops) { - return (gfp_mask & (GFP_TRANSHUGE | __GFP_KSWAPD_RECLAIM)) == GFP_TRANSHUGE; + struct zone *zone; + struct zoneref *z; + + /* + * Make sure we converge to OOM if we cannot make any progress + * several times in the row. + */ + if (no_progress_loops > MAX_RECLAIM_RETRIES) + return false; + + /* + * Keep reclaiming pages while there is a chance this will lead + * somewhere. If none of the target zones can satisfy our allocation + * request even if all reclaimable pages are considered then we are + * screwed and have to go OOM. + */ + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, + ac->nodemask) { + unsigned long available; + unsigned long reclaimable; + + available = reclaimable = zone_reclaimable_pages(zone); + available -= DIV_ROUND_UP(no_progress_loops * available, + MAX_RECLAIM_RETRIES); + available += zone_page_state_snapshot(zone, NR_FREE_PAGES); + + /* + * Would the allocation succeed if we reclaimed the whole + * available? + */ + if (__zone_watermark_ok(zone, order, min_wmark_pages(zone), + ac_classzone_idx(ac), alloc_flags, available)) { + /* + * If we didn't make any progress and have a lot of + * dirty + writeback pages then we should wait for + * an IO to complete to slow down the reclaim and + * prevent from pre mature OOM + */ + if (!did_some_progress) { + unsigned long write_pending; + + write_pending = zone_page_state_snapshot(zone, + NR_ZONE_WRITE_PENDING); + + if (2 * write_pending > reclaimable) { + congestion_wait(BLK_RW_ASYNC, HZ/10); + return true; + } + } + + /* + * Memory allocation/reclaim might be called from a WQ + * context and the current implementation of the WQ + * concurrency control doesn't recognize that + * a particular WQ is congested if the worker thread is + * looping without ever sleeping. Therefore we have to + * do a short sleep here rather than calling + * cond_resched(). + */ + if (current->flags & PF_WQ_WORKER) + schedule_timeout_uninterruptible(1); + else + cond_resched(); + + return true; + } + } + + return false; } static inline struct page * @@ -3116,12 +3453,12 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, { bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM; struct page *page = NULL; - int alloc_flags; - unsigned long pages_reclaimed = 0; + unsigned int alloc_flags; unsigned long did_some_progress; - enum migrate_mode migration_mode = MIGRATE_ASYNC; - bool deferred_compaction = false; - int contended_compaction = COMPACT_CONTENDED_NONE; + enum compact_priority compact_priority = DEF_COMPACT_PRIORITY; + enum compact_result compact_result; + int compaction_retries = 0; + int no_progress_loops = 0; /* * In the slowpath, we sanity check order to avoid ever trying to @@ -3142,48 +3479,88 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM))) gfp_mask &= ~__GFP_ATOMIC; -retry: - if (gfp_mask & __GFP_KSWAPD_RECLAIM) - wake_all_kswapds(order, ac); - /* - * OK, we're below the kswapd watermark and have kicked background - * reclaim. Now things get more complex, so set up alloc_flags according - * to how we want to proceed. + * The fast path uses conservative alloc_flags to succeed only until + * kswapd needs to be woken up, and to avoid the cost of setting up + * alloc_flags precisely. So we do that now. */ alloc_flags = gfp_to_alloc_flags(gfp_mask); + if (gfp_mask & __GFP_KSWAPD_RECLAIM) + wake_all_kswapds(order, ac); + /* - * Find the true preferred zone if the allocation is unconstrained by - * cpusets. + * The adjusted alloc_flags might result in immediate success, so try + * that first */ - if (!(alloc_flags & ALLOC_CPUSET) && !ac->nodemask) { - struct zoneref *preferred_zoneref; - preferred_zoneref = first_zones_zonelist(ac->zonelist, - ac->high_zoneidx, NULL, &ac->preferred_zone); - ac->classzone_idx = zonelist_zone_idx(preferred_zoneref); - } - - /* This is the last chance, in general, before the goto nopage. */ - page = get_page_from_freelist(gfp_mask, order, - alloc_flags & ~ALLOC_NO_WATERMARKS, ac); + page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); if (page) goto got_pg; - /* Allocate without watermarks if the context allows */ - if (alloc_flags & ALLOC_NO_WATERMARKS) { + /* + * For costly allocations, try direct compaction first, as it's likely + * that we have enough base pages and don't need to reclaim. Don't try + * that for allocations that are allowed to ignore watermarks, as the + * ALLOC_NO_WATERMARKS attempt didn't yet happen. + */ + if (can_direct_reclaim && order > PAGE_ALLOC_COSTLY_ORDER && + !gfp_pfmemalloc_allowed(gfp_mask)) { + page = __alloc_pages_direct_compact(gfp_mask, order, + alloc_flags, ac, + INIT_COMPACT_PRIORITY, + &compact_result); + if (page) + goto got_pg; + /* - * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds - * the allocation is high priority and these type of - * allocations are system rather than user orientated + * Checks for costly allocations with __GFP_NORETRY, which + * includes THP page fault allocations */ + if (gfp_mask & __GFP_NORETRY) { + /* + * If compaction is deferred for high-order allocations, + * it is because sync compaction recently failed. If + * this is the case and the caller requested a THP + * allocation, we do not want to heavily disrupt the + * system, so we fail the allocation instead of entering + * direct reclaim. + */ + if (compact_result == COMPACT_DEFERRED) + goto nopage; + + /* + * Looks like reclaim/compaction is worth trying, but + * sync compaction could be very expensive, so keep + * using async compaction. + */ + compact_priority = INIT_COMPACT_PRIORITY; + } + } + +retry: + /* Ensure kswapd doesn't accidentally go to sleep as long as we loop */ + if (gfp_mask & __GFP_KSWAPD_RECLAIM) + wake_all_kswapds(order, ac); + + if (gfp_pfmemalloc_allowed(gfp_mask)) + alloc_flags = ALLOC_NO_WATERMARKS; + + /* + * Reset the zonelist iterators if memory policies can be ignored. + * These allocations are high priority and system rather than user + * orientated. + */ + if (!(alloc_flags & ALLOC_CPUSET) || (alloc_flags & ALLOC_NO_WATERMARKS)) { ac->zonelist = node_zonelist(numa_node_id(), gfp_mask); - page = get_page_from_freelist(gfp_mask, order, - ALLOC_NO_WATERMARKS, ac); - if (page) - goto got_pg; + ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, + ac->high_zoneidx, ac->nodemask); } + /* Attempt with potentially adjusted zonelist and alloc_flags */ + page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); + if (page) + goto got_pg; + /* Caller is not willing to reclaim, we can't balance anything */ if (!can_direct_reclaim) { /* @@ -3213,74 +3590,58 @@ retry: if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL)) goto nopage; - /* - * Try direct compaction. The first pass is asynchronous. Subsequent - * attempts after direct reclaim are synchronous - */ + + /* Try direct reclaim and then allocating */ + page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac, + &did_some_progress); + if (page) + goto got_pg; + + /* Try direct compaction and then allocating */ page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags, ac, - migration_mode, - &contended_compaction, - &deferred_compaction); + compact_priority, &compact_result); if (page) goto got_pg; - /* Checks for THP-specific high-order allocations */ - if (is_thp_gfp_mask(gfp_mask)) { - /* - * If compaction is deferred for high-order allocations, it is - * because sync compaction recently failed. If this is the case - * and the caller requested a THP allocation, we do not want - * to heavily disrupt the system, so we fail the allocation - * instead of entering direct reclaim. - */ - if (deferred_compaction) - goto nopage; + if (order && compaction_made_progress(compact_result)) + compaction_retries++; - /* - * In all zones where compaction was attempted (and not - * deferred or skipped), lock contention has been detected. - * For THP allocation we do not want to disrupt the others - * so we fallback to base pages instead. - */ - if (contended_compaction == COMPACT_CONTENDED_LOCK) - goto nopage; + /* Do not loop if specifically requested */ + if (gfp_mask & __GFP_NORETRY) + goto nopage; - /* - * If compaction was aborted due to need_resched(), we do not - * want to further increase allocation latency, unless it is - * khugepaged trying to collapse. - */ - if (contended_compaction == COMPACT_CONTENDED_SCHED - && !(current->flags & PF_KTHREAD)) - goto nopage; - } + /* + * Do not retry costly high order allocations unless they are + * __GFP_REPEAT + */ + if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_REPEAT)) + goto nopage; /* - * It can become very expensive to allocate transparent hugepages at - * fault, so use asynchronous memory compaction for THP unless it is - * khugepaged trying to collapse. + * Costly allocations might have made a progress but this doesn't mean + * their order will become available due to high fragmentation so + * always increment the no progress counter for them */ - if (!is_thp_gfp_mask(gfp_mask) || (current->flags & PF_KTHREAD)) - migration_mode = MIGRATE_SYNC_LIGHT; + if (did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER) + no_progress_loops = 0; + else + no_progress_loops++; - /* Try direct reclaim and then allocating */ - page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac, - &did_some_progress); - if (page) - goto got_pg; + if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags, + did_some_progress > 0, no_progress_loops)) + goto retry; - /* Do not loop if specifically requested */ - if (gfp_mask & __GFP_NORETRY) - goto noretry; - - /* Keep reclaiming pages as long as there is reasonable progress */ - pages_reclaimed += did_some_progress; - if ((did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER) || - ((gfp_mask & __GFP_REPEAT) && pages_reclaimed < (1 << order))) { - /* Wait for some write requests to complete then retry */ - wait_iff_congested(ac->preferred_zone, BLK_RW_ASYNC, HZ/50); + /* + * It doesn't make any sense to retry for the compaction if the order-0 + * reclaim is not able to make any progress because the current + * implementation of the compaction depends on the sufficient amount + * of free memory (see __compaction_suitable) + */ + if (did_some_progress > 0 && + should_compact_retry(ac, order, alloc_flags, + compact_result, &compact_priority, + compaction_retries)) goto retry; - } /* Reclaim has failed us, start killing things */ page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress); @@ -3288,21 +3649,11 @@ retry: goto got_pg; /* Retry as long as the OOM killer is making progress */ - if (did_some_progress) + if (did_some_progress) { + no_progress_loops = 0; goto retry; + } -noretry: - /* - * High-order allocations do not necessarily loop after - * direct reclaim and reclaim/compaction depends on compaction - * being called after reclaim so call directly if necessary - */ - page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags, - ac, migration_mode, - &contended_compaction, - &deferred_compaction); - if (page) - goto got_pg; nopage: warn_alloc_failed(gfp_mask, order, NULL); got_pg: @@ -3316,17 +3667,24 @@ struct page * __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, nodemask_t *nodemask) { - struct zoneref *preferred_zoneref; - struct page *page = NULL; + struct page *page; unsigned int cpuset_mems_cookie; - int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR; - gfp_t alloc_mask; /* The gfp_t that was actually used for allocation */ + unsigned int alloc_flags = ALLOC_WMARK_LOW; + gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */ struct alloc_context ac = { .high_zoneidx = gfp_zone(gfp_mask), + .zonelist = zonelist, .nodemask = nodemask, .migratetype = gfpflags_to_migratetype(gfp_mask), }; + if (cpusets_enabled()) { + alloc_mask |= __GFP_HARDWALL; + alloc_flags |= ALLOC_CPUSET; + if (!ac.nodemask) + ac.nodemask = &cpuset_current_mems_allowed; + } + gfp_mask &= gfp_allowed_mask; lockdep_trace_alloc(gfp_mask); @@ -3350,49 +3708,66 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, retry_cpuset: cpuset_mems_cookie = read_mems_allowed_begin(); - /* We set it here, as __alloc_pages_slowpath might have changed it */ - ac.zonelist = zonelist; - /* Dirty zone balancing only done in the fast path */ ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE); - /* The preferred zone is used for statistics later */ - preferred_zoneref = first_zones_zonelist(ac.zonelist, ac.high_zoneidx, - ac.nodemask ? : &cpuset_current_mems_allowed, - &ac.preferred_zone); - if (!ac.preferred_zone) - goto out; - ac.classzone_idx = zonelist_zone_idx(preferred_zoneref); + /* + * The preferred zone is used for statistics but crucially it is + * also used as the starting point for the zonelist iterator. It + * may get reset for allocations that ignore memory policies. + */ + ac.preferred_zoneref = first_zones_zonelist(ac.zonelist, + ac.high_zoneidx, ac.nodemask); + if (!ac.preferred_zoneref) { + page = NULL; + goto no_zone; + } /* First allocation attempt */ - alloc_mask = gfp_mask|__GFP_HARDWALL; page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac); - if (unlikely(!page)) { - /* - * Runtime PM, block IO and its error handling path - * can deadlock because I/O on the device might not - * complete. - */ - alloc_mask = memalloc_noio_flags(gfp_mask); - ac.spread_dirty_pages = false; - - page = __alloc_pages_slowpath(alloc_mask, order, &ac); - } + if (likely(page)) + goto out; - if (kmemcheck_enabled && page) - kmemcheck_pagealloc_alloc(page, order, gfp_mask); + /* + * Runtime PM, block IO and its error handling path can deadlock + * because I/O on the device might not complete. + */ + alloc_mask = memalloc_noio_flags(gfp_mask); + ac.spread_dirty_pages = false; - trace_mm_page_alloc(page, order, alloc_mask, ac.migratetype); + /* + * Restore the original nodemask if it was potentially replaced with + * &cpuset_current_mems_allowed to optimize the fast-path attempt. + */ + if (cpusets_enabled()) + ac.nodemask = nodemask; + page = __alloc_pages_slowpath(alloc_mask, order, &ac); -out: +no_zone: /* * When updating a task's mems_allowed, it is possible to race with * parallel threads in such a way that an allocation can fail while * the mask is being updated. If a page allocation is about to fail, * check if the cpuset changed during allocation and if so, retry. */ - if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) { + alloc_mask = gfp_mask; goto retry_cpuset; + } + +out: + if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page) { + if (unlikely(memcg_kmem_charge(page, gfp_mask, order))) { + __free_pages(page, order); + page = NULL; + } else + __SetPageKmemcg(page); + } + + if (kmemcheck_enabled && page) + kmemcheck_pagealloc_alloc(page, order, gfp_mask); + + trace_mm_page_alloc(page, order, alloc_mask, ac.migratetype); return page; } @@ -3544,56 +3919,6 @@ void __free_page_frag(void *addr) } EXPORT_SYMBOL(__free_page_frag); -/* - * alloc_kmem_pages charges newly allocated pages to the kmem resource counter - * of the current memory cgroup if __GFP_ACCOUNT is set, other than that it is - * equivalent to alloc_pages. - * - * It should be used when the caller would like to use kmalloc, but since the - * allocation is large, it has to fall back to the page allocator. - */ -struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order) -{ - struct page *page; - - page = alloc_pages(gfp_mask, order); - if (page && memcg_kmem_charge(page, gfp_mask, order) != 0) { - __free_pages(page, order); - page = NULL; - } - return page; -} - -struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, unsigned int order) -{ - struct page *page; - - page = alloc_pages_node(nid, gfp_mask, order); - if (page && memcg_kmem_charge(page, gfp_mask, order) != 0) { - __free_pages(page, order); - page = NULL; - } - return page; -} - -/* - * __free_kmem_pages and free_kmem_pages will free pages allocated with - * alloc_kmem_pages. - */ -void __free_kmem_pages(struct page *page, unsigned int order) -{ - memcg_kmem_uncharge(page, order); - __free_pages(page, order); -} - -void free_kmem_pages(unsigned long addr, unsigned int order) -{ - if (addr != 0) { - VM_BUG_ON(!virt_addr_valid((void *)addr)); - __free_kmem_pages(virt_to_page((void *)addr), order); - } -} - static void *make_alloc_exact(unsigned long addr, unsigned int order, size_t size) { @@ -3775,7 +4100,7 @@ EXPORT_SYMBOL_GPL(si_mem_available); void si_meminfo(struct sysinfo *val) { val->totalram = totalram_pages; - val->sharedram = global_page_state(NR_SHMEM); + val->sharedram = global_node_page_state(NR_SHMEM); val->freeram = global_page_state(NR_FREE_PAGES); val->bufferram = nr_blockdev_pages(); val->totalhigh = totalhigh_pages; @@ -3790,20 +4115,29 @@ void si_meminfo_node(struct sysinfo *val, int nid) { int zone_type; /* needs to be signed */ unsigned long managed_pages = 0; + unsigned long managed_highpages = 0; + unsigned long free_highpages = 0; pg_data_t *pgdat = NODE_DATA(nid); for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) managed_pages += pgdat->node_zones[zone_type].managed_pages; val->totalram = managed_pages; - val->sharedram = node_page_state(nid, NR_SHMEM); - val->freeram = node_page_state(nid, NR_FREE_PAGES); + val->sharedram = node_page_state(pgdat, NR_SHMEM); + val->freeram = sum_zone_node_page_state(nid, NR_FREE_PAGES); #ifdef CONFIG_HIGHMEM - val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].managed_pages; - val->freehigh = zone_page_state(&pgdat->node_zones[ZONE_HIGHMEM], - NR_FREE_PAGES); + for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) { + struct zone *zone = &pgdat->node_zones[zone_type]; + + if (is_highmem(zone)) { + managed_highpages += zone->managed_pages; + free_highpages += zone_page_state(zone, NR_FREE_PAGES); + } + } + val->totalhigh = managed_highpages; + val->freehigh = free_highpages; #else - val->totalhigh = 0; - val->freehigh = 0; + val->totalhigh = managed_highpages; + val->freehigh = free_highpages; #endif val->mem_unit = PAGE_SIZE; } @@ -3872,6 +4206,7 @@ void show_free_areas(unsigned int filter) unsigned long free_pcp = 0; int cpu; struct zone *zone; + pg_data_t *pgdat; for_each_populated_zone(zone) { if (skip_free_areas_node(filter, zone_to_nid(zone))) @@ -3887,26 +4222,73 @@ void show_free_areas(unsigned int filter) " slab_reclaimable:%lu slab_unreclaimable:%lu\n" " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n" " free:%lu free_pcp:%lu free_cma:%lu\n", - global_page_state(NR_ACTIVE_ANON), - global_page_state(NR_INACTIVE_ANON), - global_page_state(NR_ISOLATED_ANON), - global_page_state(NR_ACTIVE_FILE), - global_page_state(NR_INACTIVE_FILE), - global_page_state(NR_ISOLATED_FILE), - global_page_state(NR_UNEVICTABLE), - global_page_state(NR_FILE_DIRTY), - global_page_state(NR_WRITEBACK), - global_page_state(NR_UNSTABLE_NFS), + global_node_page_state(NR_ACTIVE_ANON), + global_node_page_state(NR_INACTIVE_ANON), + global_node_page_state(NR_ISOLATED_ANON), + global_node_page_state(NR_ACTIVE_FILE), + global_node_page_state(NR_INACTIVE_FILE), + global_node_page_state(NR_ISOLATED_FILE), + global_node_page_state(NR_UNEVICTABLE), + global_node_page_state(NR_FILE_DIRTY), + global_node_page_state(NR_WRITEBACK), + global_node_page_state(NR_UNSTABLE_NFS), global_page_state(NR_SLAB_RECLAIMABLE), global_page_state(NR_SLAB_UNRECLAIMABLE), - global_page_state(NR_FILE_MAPPED), - global_page_state(NR_SHMEM), + global_node_page_state(NR_FILE_MAPPED), + global_node_page_state(NR_SHMEM), global_page_state(NR_PAGETABLE), global_page_state(NR_BOUNCE), global_page_state(NR_FREE_PAGES), free_pcp, global_page_state(NR_FREE_CMA_PAGES)); + for_each_online_pgdat(pgdat) { + printk("Node %d" + " active_anon:%lukB" + " inactive_anon:%lukB" + " active_file:%lukB" + " inactive_file:%lukB" + " unevictable:%lukB" + " isolated(anon):%lukB" + " isolated(file):%lukB" + " mapped:%lukB" + " dirty:%lukB" + " writeback:%lukB" + " shmem:%lukB" +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + " shmem_thp: %lukB" + " shmem_pmdmapped: %lukB" + " anon_thp: %lukB" +#endif + " writeback_tmp:%lukB" + " unstable:%lukB" + " pages_scanned:%lu" + " all_unreclaimable? %s" + "\n", + pgdat->node_id, + K(node_page_state(pgdat, NR_ACTIVE_ANON)), + K(node_page_state(pgdat, NR_INACTIVE_ANON)), + K(node_page_state(pgdat, NR_ACTIVE_FILE)), + K(node_page_state(pgdat, NR_INACTIVE_FILE)), + K(node_page_state(pgdat, NR_UNEVICTABLE)), + K(node_page_state(pgdat, NR_ISOLATED_ANON)), + K(node_page_state(pgdat, NR_ISOLATED_FILE)), + K(node_page_state(pgdat, NR_FILE_MAPPED)), + K(node_page_state(pgdat, NR_FILE_DIRTY)), + K(node_page_state(pgdat, NR_WRITEBACK)), +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR), + K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) + * HPAGE_PMD_NR), + K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR), +#endif + K(node_page_state(pgdat, NR_SHMEM)), + K(node_page_state(pgdat, NR_WRITEBACK_TEMP)), + K(node_page_state(pgdat, NR_UNSTABLE_NFS)), + node_page_state(pgdat, NR_PAGES_SCANNED), + !pgdat_reclaimable(pgdat) ? "yes" : "no"); + } + for_each_populated_zone(zone) { int i; @@ -3928,61 +4310,41 @@ void show_free_areas(unsigned int filter) " active_file:%lukB" " inactive_file:%lukB" " unevictable:%lukB" - " isolated(anon):%lukB" - " isolated(file):%lukB" + " writepending:%lukB" " present:%lukB" " managed:%lukB" " mlocked:%lukB" - " dirty:%lukB" - " writeback:%lukB" - " mapped:%lukB" - " shmem:%lukB" " slab_reclaimable:%lukB" " slab_unreclaimable:%lukB" " kernel_stack:%lukB" " pagetables:%lukB" - " unstable:%lukB" " bounce:%lukB" " free_pcp:%lukB" " local_pcp:%ukB" " free_cma:%lukB" - " writeback_tmp:%lukB" - " pages_scanned:%lu" - " all_unreclaimable? %s" "\n", zone->name, K(zone_page_state(zone, NR_FREE_PAGES)), K(min_wmark_pages(zone)), K(low_wmark_pages(zone)), K(high_wmark_pages(zone)), - K(zone_page_state(zone, NR_ACTIVE_ANON)), - K(zone_page_state(zone, NR_INACTIVE_ANON)), - K(zone_page_state(zone, NR_ACTIVE_FILE)), - K(zone_page_state(zone, NR_INACTIVE_FILE)), - K(zone_page_state(zone, NR_UNEVICTABLE)), - K(zone_page_state(zone, NR_ISOLATED_ANON)), - K(zone_page_state(zone, NR_ISOLATED_FILE)), + K(zone_page_state(zone, NR_ZONE_ACTIVE_ANON)), + K(zone_page_state(zone, NR_ZONE_INACTIVE_ANON)), + K(zone_page_state(zone, NR_ZONE_ACTIVE_FILE)), + K(zone_page_state(zone, NR_ZONE_INACTIVE_FILE)), + K(zone_page_state(zone, NR_ZONE_UNEVICTABLE)), + K(zone_page_state(zone, NR_ZONE_WRITE_PENDING)), K(zone->present_pages), K(zone->managed_pages), K(zone_page_state(zone, NR_MLOCK)), - K(zone_page_state(zone, NR_FILE_DIRTY)), - K(zone_page_state(zone, NR_WRITEBACK)), - K(zone_page_state(zone, NR_FILE_MAPPED)), - K(zone_page_state(zone, NR_SHMEM)), K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)), K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)), - zone_page_state(zone, NR_KERNEL_STACK) * - THREAD_SIZE / 1024, + zone_page_state(zone, NR_KERNEL_STACK_KB), K(zone_page_state(zone, NR_PAGETABLE)), - K(zone_page_state(zone, NR_UNSTABLE_NFS)), K(zone_page_state(zone, NR_BOUNCE)), K(free_pcp), K(this_cpu_read(zone->pageset->pcp.count)), - K(zone_page_state(zone, NR_FREE_CMA_PAGES)), - K(zone_page_state(zone, NR_WRITEBACK_TEMP)), - K(zone_page_state(zone, NR_PAGES_SCANNED)), - (!zone_reclaimable(zone) ? "yes" : "no") - ); + K(zone_page_state(zone, NR_FREE_CMA_PAGES))); printk("lowmem_reserve[]:"); for (i = 0; i < MAX_NR_ZONES; i++) printk(" %ld", zone->lowmem_reserve[i]); @@ -4024,7 +4386,7 @@ void show_free_areas(unsigned int filter) hugetlb_show_meminfo(); - printk("%ld total pagecache pages\n", global_page_state(NR_FILE_PAGES)); + printk("%ld total pagecache pages\n", global_node_page_state(NR_FILE_PAGES)); show_swap_cache_info(); } @@ -4390,13 +4752,12 @@ static void build_zonelists(pg_data_t *pgdat) */ int local_memory_node(int node) { - struct zone *zone; + struct zoneref *z; - (void)first_zones_zonelist(node_zonelist(node, GFP_KERNEL), + z = first_zones_zonelist(node_zonelist(node, GFP_KERNEL), gfp_zone(GFP_KERNEL), - NULL, - &zone); - return zone->node; + NULL); + return z->zone->node; } #endif @@ -4904,13 +5265,18 @@ static void __meminit setup_zone_pageset(struct zone *zone) */ void __init setup_per_cpu_pageset(void) { + struct pglist_data *pgdat; struct zone *zone; for_each_populated_zone(zone) setup_zone_pageset(zone); + + for_each_online_pgdat(pgdat) + pgdat->per_cpu_nodestats = + alloc_percpu(struct per_cpu_nodestat); } -static noinline __init_refok +static noinline __ref int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) { int i; @@ -5465,6 +5831,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) init_waitqueue_head(&pgdat->kcompactd_wait); #endif pgdat_page_ext_init(pgdat); + spin_lock_init(&pgdat->lru_lock); + lruvec_init(node_lruvec(pgdat)); for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; @@ -5514,21 +5882,16 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) zone->managed_pages = is_highmem_idx(j) ? realsize : freesize; #ifdef CONFIG_NUMA zone->node = nid; - zone->min_unmapped_pages = (freesize*sysctl_min_unmapped_ratio) + pgdat->min_unmapped_pages += (freesize*sysctl_min_unmapped_ratio) / 100; - zone->min_slab_pages = (freesize * sysctl_min_slab_ratio) / 100; + pgdat->min_slab_pages += (freesize * sysctl_min_slab_ratio) / 100; #endif zone->name = zone_names[j]; + zone->zone_pgdat = pgdat; spin_lock_init(&zone->lock); - spin_lock_init(&zone->lru_lock); zone_seqlock_init(zone); - zone->zone_pgdat = pgdat; zone_pcp_init(zone); - /* For bootup, initialized properly in watermark setup */ - mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages); - - lruvec_init(&zone->lruvec); if (!size) continue; @@ -5540,7 +5903,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) } } -static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat) +static void __ref alloc_node_mem_map(struct pglist_data *pgdat) { unsigned long __maybe_unused start = 0; unsigned long __maybe_unused offset = 0; @@ -5594,11 +5957,12 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, unsigned long end_pfn = 0; /* pg_data_t should be reset to zero when it's allocated */ - WARN_ON(pgdat->nr_zones || pgdat->classzone_idx); + WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx); reset_deferred_meminit(pgdat); pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; + pgdat->per_cpu_nodestats = NULL; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid, @@ -5980,15 +6344,18 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) sizeof(arch_zone_lowest_possible_pfn)); memset(arch_zone_highest_possible_pfn, 0, sizeof(arch_zone_highest_possible_pfn)); - arch_zone_lowest_possible_pfn[0] = find_min_pfn_with_active_regions(); - arch_zone_highest_possible_pfn[0] = max_zone_pfn[0]; - for (i = 1; i < MAX_NR_ZONES; i++) { + + start_pfn = find_min_pfn_with_active_regions(); + + for (i = 0; i < MAX_NR_ZONES; i++) { if (i == ZONE_MOVABLE) continue; - arch_zone_lowest_possible_pfn[i] = - arch_zone_highest_possible_pfn[i-1]; - arch_zone_highest_possible_pfn[i] = - max(max_zone_pfn[i], arch_zone_lowest_possible_pfn[i]); + + end_pfn = max(max_zone_pfn[i], start_pfn); + arch_zone_lowest_possible_pfn[i] = start_pfn; + arch_zone_highest_possible_pfn[i] = end_pfn; + + start_pfn = end_pfn; } arch_zone_lowest_possible_pfn[ZONE_MOVABLE] = 0; arch_zone_highest_possible_pfn[ZONE_MOVABLE] = 0; @@ -6252,6 +6619,9 @@ static void calculate_totalreserve_pages(void) enum zone_type i, j; for_each_online_pgdat(pgdat) { + + pgdat->totalreserve_pages = 0; + for (i = 0; i < MAX_NR_ZONES; i++) { struct zone *zone = pgdat->node_zones + i; long max = 0; @@ -6268,7 +6638,7 @@ static void calculate_totalreserve_pages(void) if (max > zone->managed_pages) max = zone->managed_pages; - zone->totalreserve_pages = max; + pgdat->totalreserve_pages += max; reserve_pages += max; } @@ -6369,10 +6739,6 @@ static void __setup_per_zone_wmarks(void) zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp; zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2; - __mod_zone_page_state(zone, NR_ALLOC_BATCH, - high_wmark_pages(zone) - low_wmark_pages(zone) - - atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); - spin_unlock_irqrestore(&zone->lock, flags); } @@ -6395,49 +6761,6 @@ void setup_per_zone_wmarks(void) } /* - * The inactive anon list should be small enough that the VM never has to - * do too much work, but large enough that each inactive page has a chance - * to be referenced again before it is swapped out. - * - * The inactive_anon ratio is the target ratio of ACTIVE_ANON to - * INACTIVE_ANON pages on this zone's LRU, maintained by the - * pageout code. A zone->inactive_ratio of 3 means 3:1 or 25% of - * the anonymous pages are kept on the inactive list. - * - * total target max - * memory ratio inactive anon - * ------------------------------------- - * 10MB 1 5MB - * 100MB 1 50MB - * 1GB 3 250MB - * 10GB 10 0.9GB - * 100GB 31 3GB - * 1TB 101 10GB - * 10TB 320 32GB - */ -static void __meminit calculate_zone_inactive_ratio(struct zone *zone) -{ - unsigned int gb, ratio; - - /* Zone size in gigabytes */ - gb = zone->managed_pages >> (30 - PAGE_SHIFT); - if (gb) - ratio = int_sqrt(10 * gb); - else - ratio = 1; - - zone->inactive_ratio = ratio; -} - -static void __meminit setup_per_zone_inactive_ratio(void) -{ - struct zone *zone; - - for_each_zone(zone) - calculate_zone_inactive_ratio(zone); -} - -/* * Initialise min_free_kbytes. * * For small machines we want it small (128k min). For large machines @@ -6482,10 +6805,9 @@ int __meminit init_per_zone_wmark_min(void) setup_per_zone_wmarks(); refresh_zone_stat_thresholds(); setup_per_zone_lowmem_reserve(); - setup_per_zone_inactive_ratio(); return 0; } -module_init(init_per_zone_wmark_min) +core_initcall(init_per_zone_wmark_min) /* * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so @@ -6527,6 +6849,7 @@ int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write, int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { + struct pglist_data *pgdat; struct zone *zone; int rc; @@ -6534,8 +6857,11 @@ int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write, if (rc) return rc; + for_each_online_pgdat(pgdat) + pgdat->min_slab_pages = 0; + for_each_zone(zone) - zone->min_unmapped_pages = (zone->managed_pages * + zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages * sysctl_min_unmapped_ratio) / 100; return 0; } @@ -6543,6 +6869,7 @@ int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write, int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { + struct pglist_data *pgdat; struct zone *zone; int rc; @@ -6550,8 +6877,11 @@ int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write, if (rc) return rc; + for_each_online_pgdat(pgdat) + pgdat->min_slab_pages = 0; + for_each_zone(zone) - zone->min_slab_pages = (zone->managed_pages * + zone->zone_pgdat->min_slab_pages += (zone->managed_pages * sysctl_min_slab_ratio) / 100; return 0; } @@ -6725,98 +7055,6 @@ void *__init alloc_large_system_hash(const char *tablename, return table; } -/* Return a pointer to the bitmap storing bits affecting a block of pages */ -static inline unsigned long *get_pageblock_bitmap(struct zone *zone, - unsigned long pfn) -{ -#ifdef CONFIG_SPARSEMEM - return __pfn_to_section(pfn)->pageblock_flags; -#else - return zone->pageblock_flags; -#endif /* CONFIG_SPARSEMEM */ -} - -static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn) -{ -#ifdef CONFIG_SPARSEMEM - pfn &= (PAGES_PER_SECTION-1); - return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS; -#else - pfn = pfn - round_down(zone->zone_start_pfn, pageblock_nr_pages); - return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS; -#endif /* CONFIG_SPARSEMEM */ -} - -/** - * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages - * @page: The page within the block of interest - * @pfn: The target page frame number - * @end_bitidx: The last bit of interest to retrieve - * @mask: mask of bits that the caller is interested in - * - * Return: pageblock_bits flags - */ -unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, - unsigned long end_bitidx, - unsigned long mask) -{ - struct zone *zone; - unsigned long *bitmap; - unsigned long bitidx, word_bitidx; - unsigned long word; - - zone = page_zone(page); - bitmap = get_pageblock_bitmap(zone, pfn); - bitidx = pfn_to_bitidx(zone, pfn); - word_bitidx = bitidx / BITS_PER_LONG; - bitidx &= (BITS_PER_LONG-1); - - word = bitmap[word_bitidx]; - bitidx += end_bitidx; - return (word >> (BITS_PER_LONG - bitidx - 1)) & mask; -} - -/** - * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages - * @page: The page within the block of interest - * @flags: The flags to set - * @pfn: The target page frame number - * @end_bitidx: The last bit of interest - * @mask: mask of bits that the caller is interested in - */ -void set_pfnblock_flags_mask(struct page *page, unsigned long flags, - unsigned long pfn, - unsigned long end_bitidx, - unsigned long mask) -{ - struct zone *zone; - unsigned long *bitmap; - unsigned long bitidx, word_bitidx; - unsigned long old_word, word; - - BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); - - zone = page_zone(page); - bitmap = get_pageblock_bitmap(zone, pfn); - bitidx = pfn_to_bitidx(zone, pfn); - word_bitidx = bitidx / BITS_PER_LONG; - bitidx &= (BITS_PER_LONG-1); - - VM_BUG_ON_PAGE(!zone_spans_pfn(zone, pfn), page); - - bitidx += end_bitidx; - mask <<= (BITS_PER_LONG - bitidx - 1); - flags <<= (BITS_PER_LONG - bitidx - 1); - - word = READ_ONCE(bitmap[word_bitidx]); - for (;;) { - old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags); - if (word == old_word) - break; - word = old_word; - } -} - /* * This function checks whether pageblock includes unmovable pages or not. * If @count is not zero, it is okay to include less @count unmovable pages @@ -6864,7 +7102,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * We can't use page_count without pin a page * because another CPU can free compound page. * This check already skips compound tails of THP - * because their page->_count is zero at all time. + * because their page->_refcount is zero at all time. */ if (!page_ref_count(page)) { if (PageBuddy(page)) @@ -7177,7 +7415,8 @@ void zone_pcp_reset(struct zone *zone) #ifdef CONFIG_MEMORY_HOTREMOVE /* - * All pages in the range must be isolated before calling this. + * All pages in the range must be in a single zone and isolated + * before calling this. */ void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) diff --git a/mm/page_ext.c b/mm/page_ext.c index 2d864e64f7fe..44a4c029c8e7 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -390,8 +390,10 @@ void __init page_ext_init(void) * We know some arch can have a nodes layout such as * -------------pfn--------------> * N0 | N1 | N2 | N0 | N1 | N2|.... + * + * Take into account DEFERRED_STRUCT_PAGE_INIT. */ - if (pfn_to_nid(pfn) != nid) + if (early_pfn_to_nid(pfn) != nid) continue; if (init_section_page_ext(pfn, nid)) goto oom; diff --git a/mm/page_idle.c b/mm/page_idle.c index 4ea9c4ef5146..ae11aa914e55 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -41,12 +41,12 @@ static struct page *page_idle_get_page(unsigned long pfn) return NULL; zone = page_zone(page); - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(zone_lru_lock(zone)); if (unlikely(!PageLRU(page))) { put_page(page); page = NULL; } - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); return page; } diff --git a/mm/page_io.c b/mm/page_io.c index 18aac7819cc9..fb1fa269d3a0 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -166,6 +166,8 @@ int generic_swapfile_activate(struct swap_info_struct *sis, unsigned block_in_page; sector_t first_block; + cond_resched(); + first_block = bmap(inode, probe_block); if (first_block == 0) goto bad_bmap; @@ -252,14 +254,14 @@ out: static sector_t swap_page_sector(struct page *page) { - return (sector_t)__page_file_index(page) << (PAGE_CACHE_SHIFT - 9); + return (sector_t)__page_file_index(page) << (PAGE_SHIFT - 9); } int __swap_writepage(struct page *page, struct writeback_control *wbc, bio_end_io_t end_write_func) { struct bio *bio; - int ret, rw = WRITE; + int ret; struct swap_info_struct *sis = page_swap_info(page); if (sis->flags & SWP_FILE) { @@ -279,7 +281,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, set_page_writeback(page); unlock_page(page); - ret = mapping->a_ops->direct_IO(&kiocb, &from, kiocb.ki_pos); + ret = mapping->a_ops->direct_IO(&kiocb, &from); if (ret == PAGE_SIZE) { count_vm_event(PSWPOUT); ret = 0; @@ -317,12 +319,13 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, ret = -ENOMEM; goto out; } + bio_set_op_attrs(bio, REQ_OP_WRITE, 0); if (wbc->sync_mode == WB_SYNC_ALL) - rw |= REQ_SYNC; + bio->bi_rw |= REQ_SYNC; count_vm_event(PSWPOUT); set_page_writeback(page); unlock_page(page); - submit_bio(rw, bio); + submit_bio(bio); out: return ret; } @@ -353,7 +356,11 @@ int swap_readpage(struct page *page) ret = bdev_read_page(sis->bdev, swap_page_sector(page), page); if (!ret) { - swap_slot_free_notify(page); + if (trylock_page(page)) { + swap_slot_free_notify(page); + unlock_page(page); + } + count_vm_event(PSWPIN); return 0; } @@ -365,8 +372,9 @@ int swap_readpage(struct page *page) ret = -ENOMEM; goto out; } + bio_set_op_attrs(bio, REQ_OP_READ, 0); count_vm_event(PSWPIN); - submit_bio(READ, bio); + submit_bio(bio); out: return ret; } diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 92c4c36501e7..064b7fb6e0b5 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -7,6 +7,7 @@ #include <linux/pageblock-flags.h> #include <linux/memory.h> #include <linux/hugetlb.h> +#include <linux/page_owner.h> #include "internal.h" #define CREATE_TRACE_POINTS @@ -80,7 +81,7 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype) { struct zone *zone; unsigned long flags, nr_pages; - struct page *isolated_page = NULL; + bool isolated_page = false; unsigned int order; unsigned long page_idx, buddy_idx; struct page *buddy; @@ -108,9 +109,7 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype) if (pfn_valid_within(page_to_pfn(buddy)) && !is_migrate_isolate_page(buddy)) { __isolate_free_page(page, order); - kernel_map_pages(page, (1 << order), 1); - set_page_refcounted(page); - isolated_page = page; + isolated_page = true; } } } @@ -128,8 +127,10 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype) zone->nr_isolate_pageblock--; out: spin_unlock_irqrestore(&zone->lock, flags); - if (isolated_page) - __free_pages(isolated_page, order); + if (isolated_page) { + post_alloc_hook(page, order, __GFP_MOVABLE); + __free_pages(page, order); + } } static inline struct page * @@ -215,7 +216,7 @@ int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, * all pages in [start_pfn...end_pfn) must be in the same zone. * zone->lock must be held before call this. * - * Returns 1 if all pages in the range are isolated. + * Returns the last tested pfn. */ static unsigned long __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn, @@ -246,6 +247,7 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn, return pfn; } +/* Caller should ensure that requested range is in a single zone */ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, bool skip_hwpoisoned_pages) { @@ -288,13 +290,10 @@ struct page *alloc_migrate_target(struct page *page, unsigned long private, * accordance with memory policy of the user process if possible. For * now as a simple work-around, we use the next node for destination. */ - if (PageHuge(page)) { - nodemask_t src = nodemask_of_node(page_to_nid(page)); - nodemask_t dst; - nodes_complement(dst, src); + if (PageHuge(page)) return alloc_huge_page_node(page_hstate(compound_head(page)), - next_node(page_to_nid(page), dst)); - } + next_node_in(page_to_nid(page), + node_online_map)); if (PageHighMem(page)) gfp_mask |= __GFP_HIGHMEM; diff --git a/mm/page_owner.c b/mm/page_owner.c index ac3d8d129974..ec6dc1886f71 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -7,11 +7,22 @@ #include <linux/page_owner.h> #include <linux/jump_label.h> #include <linux/migrate.h> +#include <linux/stackdepot.h> + #include "internal.h" +/* + * TODO: teach PAGE_OWNER_STACK_DEPTH (__dump_page_owner and save_stack) + * to use off stack temporal storage + */ +#define PAGE_OWNER_STACK_DEPTH (16) + static bool page_owner_disabled = true; DEFINE_STATIC_KEY_FALSE(page_owner_inited); +static depot_stack_handle_t dummy_handle; +static depot_stack_handle_t failure_handle; + static void init_early_allocated_pages(void); static int early_page_owner_param(char *buf) @@ -34,11 +45,41 @@ static bool need_page_owner(void) return true; } +static noinline void register_dummy_stack(void) +{ + unsigned long entries[4]; + struct stack_trace dummy; + + dummy.nr_entries = 0; + dummy.max_entries = ARRAY_SIZE(entries); + dummy.entries = &entries[0]; + dummy.skip = 0; + + save_stack_trace(&dummy); + dummy_handle = depot_save_stack(&dummy, GFP_KERNEL); +} + +static noinline void register_failure_stack(void) +{ + unsigned long entries[4]; + struct stack_trace failure; + + failure.nr_entries = 0; + failure.max_entries = ARRAY_SIZE(entries); + failure.entries = &entries[0]; + failure.skip = 0; + + save_stack_trace(&failure); + failure_handle = depot_save_stack(&failure, GFP_KERNEL); +} + static void init_page_owner(void) { if (page_owner_disabled) return; + register_dummy_stack(); + register_failure_stack(); static_branch_enable(&page_owner_inited); init_early_allocated_pages(); } @@ -55,25 +96,72 @@ void __reset_page_owner(struct page *page, unsigned int order) for (i = 0; i < (1 << order); i++) { page_ext = lookup_page_ext(page + i); + if (unlikely(!page_ext)) + continue; __clear_bit(PAGE_EXT_OWNER, &page_ext->flags); } } -void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) +static inline bool check_recursive_alloc(struct stack_trace *trace, + unsigned long ip) { - struct page_ext *page_ext = lookup_page_ext(page); + int i, count; + + if (!trace->nr_entries) + return false; + + for (i = 0, count = 0; i < trace->nr_entries; i++) { + if (trace->entries[i] == ip && ++count == 2) + return true; + } + + return false; +} + +static noinline depot_stack_handle_t save_stack(gfp_t flags) +{ + unsigned long entries[PAGE_OWNER_STACK_DEPTH]; struct stack_trace trace = { .nr_entries = 0, - .max_entries = ARRAY_SIZE(page_ext->trace_entries), - .entries = &page_ext->trace_entries[0], - .skip = 3, + .entries = entries, + .max_entries = PAGE_OWNER_STACK_DEPTH, + .skip = 0 }; + depot_stack_handle_t handle; save_stack_trace(&trace); + if (trace.nr_entries != 0 && + trace.entries[trace.nr_entries-1] == ULONG_MAX) + trace.nr_entries--; + /* + * We need to check recursion here because our request to stackdepot + * could trigger memory allocation to save new entry. New memory + * allocation would reach here and call depot_save_stack() again + * if we don't catch it. There is still not enough memory in stackdepot + * so it would try to allocate memory again and loop forever. + */ + if (check_recursive_alloc(&trace, _RET_IP_)) + return dummy_handle; + + handle = depot_save_stack(&trace, flags); + if (!handle) + handle = failure_handle; + + return handle; +} + +noinline void __set_page_owner(struct page *page, unsigned int order, + gfp_t gfp_mask) +{ + struct page_ext *page_ext = lookup_page_ext(page); + + if (unlikely(!page_ext)) + return; + + page_ext->handle = save_stack(gfp_mask); page_ext->order = order; page_ext->gfp_mask = gfp_mask; - page_ext->nr_entries = trace.nr_entries; page_ext->last_migrate_reason = -1; __set_bit(PAGE_EXT_OWNER, &page_ext->flags); @@ -82,29 +170,37 @@ void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) void __set_page_owner_migrate_reason(struct page *page, int reason) { struct page_ext *page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + return; page_ext->last_migrate_reason = reason; } -gfp_t __get_page_owner_gfp(struct page *page) +void __split_page_owner(struct page *page, unsigned int order) { + int i; struct page_ext *page_ext = lookup_page_ext(page); - return page_ext->gfp_mask; + if (unlikely(!page_ext)) + return; + + page_ext->order = 0; + for (i = 1; i < (1 << order); i++) + __copy_page_owner(page, page + i); } void __copy_page_owner(struct page *oldpage, struct page *newpage) { struct page_ext *old_ext = lookup_page_ext(oldpage); struct page_ext *new_ext = lookup_page_ext(newpage); - int i; + + if (unlikely(!old_ext || !new_ext)) + return; new_ext->order = old_ext->order; new_ext->gfp_mask = old_ext->gfp_mask; - new_ext->nr_entries = old_ext->nr_entries; - - for (i = 0; i < ARRAY_SIZE(new_ext->trace_entries); i++) - new_ext->trace_entries[i] = old_ext->trace_entries[i]; + new_ext->last_migrate_reason = old_ext->last_migrate_reason; + new_ext->handle = old_ext->handle; /* * We don't clear the bit on the oldpage as it's going to be freed @@ -120,14 +216,18 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage) static ssize_t print_page_owner(char __user *buf, size_t count, unsigned long pfn, - struct page *page, struct page_ext *page_ext) + struct page *page, struct page_ext *page_ext, + depot_stack_handle_t handle) { int ret; int pageblock_mt, page_mt; char *kbuf; + unsigned long entries[PAGE_OWNER_STACK_DEPTH]; struct stack_trace trace = { - .nr_entries = page_ext->nr_entries, - .entries = &page_ext->trace_entries[0], + .nr_entries = 0, + .entries = entries, + .max_entries = PAGE_OWNER_STACK_DEPTH, + .skip = 0 }; kbuf = kmalloc(count, GFP_KERNEL); @@ -143,7 +243,7 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn, goto err; /* Print information relevant to grouping pages by mobility */ - pageblock_mt = get_pfnblock_migratetype(page, pfn); + pageblock_mt = get_pageblock_migratetype(page); page_mt = gfpflags_to_migratetype(page_ext->gfp_mask); ret += snprintf(kbuf + ret, count - ret, "PFN %lu type %s Block %lu type %s Flags %#lx(%pGp)\n", @@ -156,6 +256,7 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn, if (ret >= count) goto err; + depot_fetch_stack(handle, &trace); ret += snprint_stack_trace(kbuf + ret, count - ret, &trace, 0); if (ret >= count) goto err; @@ -186,18 +287,36 @@ err: void __dump_page_owner(struct page *page) { struct page_ext *page_ext = lookup_page_ext(page); + unsigned long entries[PAGE_OWNER_STACK_DEPTH]; struct stack_trace trace = { - .nr_entries = page_ext->nr_entries, - .entries = &page_ext->trace_entries[0], + .nr_entries = 0, + .entries = entries, + .max_entries = PAGE_OWNER_STACK_DEPTH, + .skip = 0 }; - gfp_t gfp_mask = page_ext->gfp_mask; - int mt = gfpflags_to_migratetype(gfp_mask); + depot_stack_handle_t handle; + gfp_t gfp_mask; + int mt; + + if (unlikely(!page_ext)) { + pr_alert("There is not page extension available.\n"); + return; + } + gfp_mask = page_ext->gfp_mask; + mt = gfpflags_to_migratetype(gfp_mask); if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) { pr_alert("page_owner info is not active (free page?)\n"); return; } + handle = READ_ONCE(page_ext->handle); + if (!handle) { + pr_alert("page_owner info is not active (free page?)\n"); + return; + } + + depot_fetch_stack(handle, &trace); pr_alert("page allocated via order %u, migratetype %s, gfp_mask %#x(%pGg)\n", page_ext->order, migratetype_names[mt], gfp_mask, &gfp_mask); print_stack_trace(&trace, 0); @@ -213,6 +332,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) unsigned long pfn; struct page *page; struct page_ext *page_ext; + depot_stack_handle_t handle; if (!static_branch_unlikely(&page_owner_inited)) return -EINVAL; @@ -251,6 +371,8 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) } page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + continue; /* * Some pages could be missed by concurrent allocation or free, @@ -259,10 +381,19 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) continue; + /* + * Access to page_ext->handle isn't synchronous so we should + * be careful to access it. + */ + handle = READ_ONCE(page_ext->handle); + if (!handle) + continue; + /* Record the next PFN to read in the file offset */ *ppos = (pfn - min_low_pfn) + 1; - return print_page_owner(buf, count, pfn, page, page_ext); + return print_page_owner(buf, count, pfn, page, + page_ext, handle); } return 0; @@ -301,6 +432,9 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) page = pfn_to_page(pfn); + if (page_zone(page) != zone) + continue; + /* * We are safe to check buddy flag and order, because * this is init stage and only single thread runs. @@ -314,6 +448,8 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) continue; page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + continue; /* Maybe overraping zone */ if (test_bit(PAGE_EXT_OWNER, &page_ext->flags)) diff --git a/mm/page_poison.c b/mm/page_poison.c index 479e7ea2bea6..2e647c65916b 100644 --- a/mm/page_poison.c +++ b/mm/page_poison.c @@ -13,13 +13,7 @@ static int early_page_poison_param(char *buf) { if (!buf) return -EINVAL; - - if (strcmp(buf, "on") == 0) - want_page_poisoning = true; - else if (strcmp(buf, "off") == 0) - want_page_poisoning = false; - - return 0; + return strtobool(buf, &want_page_poisoning); } early_param("page_poison", early_page_poison_param); @@ -60,6 +54,9 @@ static inline void set_page_poison(struct page *page) struct page_ext *page_ext; page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + return; + __set_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags); } @@ -68,6 +65,9 @@ static inline void clear_page_poison(struct page *page) struct page_ext *page_ext; page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + return; + __clear_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags); } @@ -76,7 +76,7 @@ bool page_is_poisoned(struct page *page) struct page_ext *page_ext; page_ext = lookup_page_ext(page); - if (!page_ext) + if (unlikely(!page_ext)) return false; return test_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags); diff --git a/mm/percpu.c b/mm/percpu.c index 0c59684f1ff2..9903830aaebb 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -112,7 +112,7 @@ struct pcpu_chunk { int map_used; /* # of map entries used before the sentry */ int map_alloc; /* # of map entries allocated */ int *map; /* allocation map */ - struct work_struct map_extend_work;/* async ->map[] extension */ + struct list_head map_extend_list;/* on pcpu_map_extend_chunks */ void *data; /* chunk data */ int first_free; /* no free below this */ @@ -162,10 +162,13 @@ static struct pcpu_chunk *pcpu_reserved_chunk; static int pcpu_reserved_chunk_limit; static DEFINE_SPINLOCK(pcpu_lock); /* all internal data structures */ -static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop */ +static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop, map ext */ static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */ +/* chunks which need their map areas extended, protected by pcpu_lock */ +static LIST_HEAD(pcpu_map_extend_chunks); + /* * The number of empty populated pages, protected by pcpu_lock. The * reserved chunk doesn't contribute to the count. @@ -395,13 +398,19 @@ static int pcpu_need_to_extend(struct pcpu_chunk *chunk, bool is_atomic) { int margin, new_alloc; + lockdep_assert_held(&pcpu_lock); + if (is_atomic) { margin = 3; if (chunk->map_alloc < - chunk->map_used + PCPU_ATOMIC_MAP_MARGIN_LOW && - pcpu_async_enabled) - schedule_work(&chunk->map_extend_work); + chunk->map_used + PCPU_ATOMIC_MAP_MARGIN_LOW) { + if (list_empty(&chunk->map_extend_list)) { + list_add_tail(&chunk->map_extend_list, + &pcpu_map_extend_chunks); + pcpu_schedule_balance_work(); + } + } } else { margin = PCPU_ATOMIC_MAP_MARGIN_HIGH; } @@ -435,6 +444,8 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc) size_t old_size = 0, new_size = new_alloc * sizeof(new[0]); unsigned long flags; + lockdep_assert_held(&pcpu_alloc_mutex); + new = pcpu_mem_zalloc(new_size); if (!new) return -ENOMEM; @@ -467,20 +478,6 @@ out_unlock: return 0; } -static void pcpu_map_extend_workfn(struct work_struct *work) -{ - struct pcpu_chunk *chunk = container_of(work, struct pcpu_chunk, - map_extend_work); - int new_alloc; - - spin_lock_irq(&pcpu_lock); - new_alloc = pcpu_need_to_extend(chunk, false); - spin_unlock_irq(&pcpu_lock); - - if (new_alloc) - pcpu_extend_area_map(chunk, new_alloc); -} - /** * pcpu_fit_in_area - try to fit the requested allocation in a candidate area * @chunk: chunk the candidate area belongs to @@ -740,7 +737,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void) chunk->map_used = 1; INIT_LIST_HEAD(&chunk->list); - INIT_WORK(&chunk->map_extend_work, pcpu_map_extend_workfn); + INIT_LIST_HEAD(&chunk->map_extend_list); chunk->free_size = pcpu_unit_size; chunk->contig_hint = pcpu_unit_size; @@ -895,6 +892,9 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, return NULL; } + if (!is_atomic) + mutex_lock(&pcpu_alloc_mutex); + spin_lock_irqsave(&pcpu_lock, flags); /* serve reserved allocations from the reserved chunk if available */ @@ -967,12 +967,9 @@ restart: if (is_atomic) goto fail; - mutex_lock(&pcpu_alloc_mutex); - if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) { chunk = pcpu_create_chunk(); if (!chunk) { - mutex_unlock(&pcpu_alloc_mutex); err = "failed to allocate new chunk"; goto fail; } @@ -983,7 +980,6 @@ restart: spin_lock_irqsave(&pcpu_lock, flags); } - mutex_unlock(&pcpu_alloc_mutex); goto restart; area_found: @@ -993,8 +989,6 @@ area_found: if (!is_atomic) { int page_start, page_end, rs, re; - mutex_lock(&pcpu_alloc_mutex); - page_start = PFN_DOWN(off); page_end = PFN_UP(off + size); @@ -1005,7 +999,6 @@ area_found: spin_lock_irqsave(&pcpu_lock, flags); if (ret) { - mutex_unlock(&pcpu_alloc_mutex); pcpu_free_area(chunk, off, &occ_pages); err = "failed to populate"; goto fail_unlock; @@ -1045,6 +1038,8 @@ fail: /* see the flag handling in pcpu_blance_workfn() */ pcpu_atomic_alloc_failed = true; pcpu_schedule_balance_work(); + } else { + mutex_unlock(&pcpu_alloc_mutex); } return NULL; } @@ -1129,6 +1124,7 @@ static void pcpu_balance_workfn(struct work_struct *work) if (chunk == list_first_entry(free_head, struct pcpu_chunk, list)) continue; + list_del_init(&chunk->map_extend_list); list_move(&chunk->list, &to_free); } @@ -1146,6 +1142,25 @@ static void pcpu_balance_workfn(struct work_struct *work) pcpu_destroy_chunk(chunk); } + /* service chunks which requested async area map extension */ + do { + int new_alloc = 0; + + spin_lock_irq(&pcpu_lock); + + chunk = list_first_entry_or_null(&pcpu_map_extend_chunks, + struct pcpu_chunk, map_extend_list); + if (chunk) { + list_del_init(&chunk->map_extend_list); + new_alloc = pcpu_need_to_extend(chunk, false); + } + + spin_unlock_irq(&pcpu_lock); + + if (new_alloc) + pcpu_extend_area_map(chunk, new_alloc); + } while (chunk); + /* * Ensure there are certain number of free populated pages for * atomic allocs. Fill up from the most packed so that atomic @@ -1644,7 +1659,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, */ schunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0); INIT_LIST_HEAD(&schunk->list); - INIT_WORK(&schunk->map_extend_work, pcpu_map_extend_workfn); + INIT_LIST_HEAD(&schunk->map_extend_list); schunk->base_addr = base_addr; schunk->map = smap; schunk->map_alloc = ARRAY_SIZE(smap); @@ -1673,7 +1688,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, if (dyn_size) { dchunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0); INIT_LIST_HEAD(&dchunk->list); - INIT_WORK(&dchunk->map_extend_work, pcpu_map_extend_workfn); + INIT_LIST_HEAD(&dchunk->map_extend_list); dchunk->base_addr = base_addr; dchunk->map = dmap; dchunk->map_alloc = ARRAY_SIZE(dmap); diff --git a/mm/readahead.c b/mm/readahead.c index 20e58e820e44..65ec288dc057 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -47,11 +47,11 @@ static void read_cache_pages_invalidate_page(struct address_space *mapping, if (!trylock_page(page)) BUG(); page->mapping = mapping; - do_invalidatepage(page, 0, PAGE_CACHE_SIZE); + do_invalidatepage(page, 0, PAGE_SIZE); page->mapping = NULL; unlock_page(page); } - page_cache_release(page); + put_page(page); } /* @@ -89,18 +89,18 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages, page = lru_to_page(pages); list_del(&page->lru); if (add_to_page_cache_lru(page, mapping, page->index, - mapping_gfp_constraint(mapping, GFP_KERNEL))) { + readahead_gfp_mask(mapping))) { read_cache_pages_invalidate_page(mapping, page); continue; } - page_cache_release(page); + put_page(page); ret = filler(data, page); if (unlikely(ret)) { read_cache_pages_invalidate_pages(mapping, pages); break; } - task_io_account_read(PAGE_CACHE_SIZE); + task_io_account_read(PAGE_SIZE); } return ret; } @@ -108,7 +108,7 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages, EXPORT_SYMBOL(read_cache_pages); static int read_pages(struct address_space *mapping, struct file *filp, - struct list_head *pages, unsigned nr_pages) + struct list_head *pages, unsigned int nr_pages, gfp_t gfp) { struct blk_plug plug; unsigned page_idx; @@ -126,11 +126,9 @@ static int read_pages(struct address_space *mapping, struct file *filp, for (page_idx = 0; page_idx < nr_pages; page_idx++) { struct page *page = lru_to_page(pages); list_del(&page->lru); - if (!add_to_page_cache_lru(page, mapping, page->index, - mapping_gfp_constraint(mapping, GFP_KERNEL))) { + if (!add_to_page_cache_lru(page, mapping, page->index, gfp)) mapping->a_ops->readpage(filp, page); - } - page_cache_release(page); + put_page(page); } ret = 0; @@ -159,11 +157,12 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, int page_idx; int ret = 0; loff_t isize = i_size_read(inode); + gfp_t gfp_mask = readahead_gfp_mask(mapping); if (isize == 0) goto out; - end_index = ((isize - 1) >> PAGE_CACHE_SHIFT); + end_index = ((isize - 1) >> PAGE_SHIFT); /* * Preallocate as many pages as we will need. @@ -180,7 +179,7 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, if (page && !radix_tree_exceptional_entry(page)) continue; - page = page_cache_alloc_readahead(mapping); + page = __page_cache_alloc(gfp_mask); if (!page) break; page->index = page_offset; @@ -196,7 +195,7 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, * will then handle the error. */ if (ret) - read_pages(mapping, filp, &page_pool, ret); + read_pages(mapping, filp, &page_pool, ret, gfp_mask); BUG_ON(!list_empty(&page_pool)); out: return ret; @@ -216,7 +215,7 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp, while (nr_to_read) { int err; - unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_CACHE_SIZE; + unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE; if (this_chunk > nr_to_read) this_chunk = nr_to_read; @@ -425,7 +424,7 @@ ondemand_readahead(struct address_space *mapping, * trivial case: (offset - prev_offset) == 1 * unaligned reads: (offset - prev_offset) == 0 */ - prev_offset = (unsigned long long)ra->prev_pos >> PAGE_CACHE_SHIFT; + prev_offset = (unsigned long long)ra->prev_pos >> PAGE_SHIFT; if (offset - prev_offset <= 1UL) goto initial_readahead; @@ -558,8 +557,8 @@ SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) if (f.file) { if (f.file->f_mode & FMODE_READ) { struct address_space *mapping = f.file->f_mapping; - pgoff_t start = offset >> PAGE_CACHE_SHIFT; - pgoff_t end = (offset + count - 1) >> PAGE_CACHE_SHIFT; + pgoff_t start = offset >> PAGE_SHIFT; + pgoff_t end = (offset + count - 1) >> PAGE_SHIFT; unsigned long len = end - start + 1; ret = do_readahead(mapping, f.file, start, len); } diff --git a/mm/rmap.c b/mm/rmap.c index c399a0d41b31..709bc83703b1 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -27,7 +27,7 @@ * mapping->i_mmap_rwsem * anon_vma->rwsem * mm->page_table_lock or pte_lock - * zone->lru_lock (in mark_page_accessed, isolate_lru_page) + * zone_lru_lock (in mark_page_accessed, isolate_lru_page) * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in __set_page_dirty_buffers) @@ -409,7 +409,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma) list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; - BUG_ON(anon_vma->degree); + VM_WARN_ON(anon_vma->degree); put_anon_vma(anon_vma); list_del(&avc->same_vma); @@ -569,19 +569,6 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma) } #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH -static void percpu_flush_tlb_batch_pages(void *data) -{ - /* - * All TLB entries are flushed on the assumption that it is - * cheaper to flush all TLBs and let them be refilled than - * flushing individual PFNs. Note that we do not track mm's - * to flush as that might simply be multiple full TLB flushes - * for no gain. - */ - count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); - flush_tlb_local(); -} - /* * Flush TLB entries for recently unmapped pages from remote CPUs. It is * important if a PTE was dirty when it was unmapped that it's flushed @@ -598,15 +585,14 @@ void try_to_unmap_flush(void) cpu = get_cpu(); - trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, -1UL); - - if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) - percpu_flush_tlb_batch_pages(&tlb_ubc->cpumask); - - if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids) { - smp_call_function_many(&tlb_ubc->cpumask, - percpu_flush_tlb_batch_pages, (void *)tlb_ubc, true); + if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) { + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + local_flush_tlb(); + trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); } + + if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids) + flush_tlb_others(&tlb_ubc->cpumask, NULL, 0, TLB_FLUSH_ALL); cpumask_clear(&tlb_ubc->cpumask); tlb_ubc->flush_required = false; tlb_ubc->writable = false; @@ -1098,21 +1084,20 @@ EXPORT_SYMBOL_GPL(page_mkclean); * page_move_anon_rmap - move a page to our anon_vma * @page: the page to move to our anon_vma * @vma: the vma the page belongs to - * @address: the user virtual address mapped * * When a page belongs exclusively to one process after a COW event, * that page can be moved into the anon_vma that belongs to just that * process, so the rmap code will not search the parent or sibling * processes. */ -void page_move_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address) +void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; + page = compound_head(page); + VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_VMA(!anon_vma, vma); - VM_BUG_ON_PAGE(page->index != linear_page_index(vma, address), page); anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; /* @@ -1227,11 +1212,9 @@ void do_page_add_anon_rmap(struct page *page, * pte lock(a spinlock) is held, which implies preemption * disabled. */ - if (compound) { - __inc_zone_page_state(page, - NR_ANON_TRANSPARENT_HUGEPAGES); - } - __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, nr); + if (compound) + __inc_node_page_state(page, NR_ANON_THPS); + __mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, nr); } if (unlikely(PageKsm(page))) return; @@ -1263,19 +1246,19 @@ void page_add_new_anon_rmap(struct page *page, int nr = compound ? hpage_nr_pages(page) : 1; VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); - SetPageSwapBacked(page); + __SetPageSwapBacked(page); if (compound) { VM_BUG_ON_PAGE(!PageTransHuge(page), page); /* increment count (starts at -1) */ atomic_set(compound_mapcount_ptr(page), 0); - __inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + __inc_node_page_state(page, NR_ANON_THPS); } else { /* Anon THP always mapped first with PMD */ VM_BUG_ON_PAGE(PageTransCompound(page), page); /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); } - __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, nr); + __mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, nr); __page_set_anon_rmap(page, vma, address, 1); } @@ -1285,18 +1268,42 @@ void page_add_new_anon_rmap(struct page *page, * * The caller needs to hold the pte lock. */ -void page_add_file_rmap(struct page *page) +void page_add_file_rmap(struct page *page, bool compound) { + int i, nr = 1; + + VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page); lock_page_memcg(page); - if (atomic_inc_and_test(&page->_mapcount)) { - __inc_zone_page_state(page, NR_FILE_MAPPED); - mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); + if (compound && PageTransHuge(page)) { + for (i = 0, nr = 0; i < HPAGE_PMD_NR; i++) { + if (atomic_inc_and_test(&page[i]._mapcount)) + nr++; + } + if (!atomic_inc_and_test(compound_mapcount_ptr(page))) + goto out; + VM_BUG_ON_PAGE(!PageSwapBacked(page), page); + __inc_node_page_state(page, NR_SHMEM_PMDMAPPED); + } else { + if (PageTransCompound(page)) { + VM_BUG_ON_PAGE(!PageLocked(page), page); + SetPageDoubleMap(compound_head(page)); + if (PageMlocked(page)) + clear_page_mlock(compound_head(page)); + } + if (!atomic_inc_and_test(&page->_mapcount)) + goto out; } + __mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, nr); + mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); +out: unlock_page_memcg(page); } -static void page_remove_file_rmap(struct page *page) +static void page_remove_file_rmap(struct page *page, bool compound) { + int i, nr = 1; + + VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page); lock_page_memcg(page); /* Hugepages are not counted in NR_FILE_MAPPED for now. */ @@ -1307,15 +1314,26 @@ static void page_remove_file_rmap(struct page *page) } /* page still mapped by someone else? */ - if (!atomic_add_negative(-1, &page->_mapcount)) - goto out; + if (compound && PageTransHuge(page)) { + for (i = 0, nr = 0; i < HPAGE_PMD_NR; i++) { + if (atomic_add_negative(-1, &page[i]._mapcount)) + nr++; + } + if (!atomic_add_negative(-1, compound_mapcount_ptr(page))) + goto out; + VM_BUG_ON_PAGE(!PageSwapBacked(page), page); + __dec_node_page_state(page, NR_SHMEM_PMDMAPPED); + } else { + if (!atomic_add_negative(-1, &page->_mapcount)) + goto out; + } /* - * We use the irq-unsafe __{inc|mod}_zone_page_stat because + * We use the irq-unsafe __{inc|mod}_zone_page_state because * these counters are not modified in interrupt context, and * pte lock(a spinlock) is held, which implies preemption disabled. */ - __dec_zone_page_state(page, NR_FILE_MAPPED); + __mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, -nr); mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); if (unlikely(PageMlocked(page))) @@ -1338,7 +1356,7 @@ static void page_remove_anon_compound_rmap(struct page *page) if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return; - __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + __dec_node_page_state(page, NR_ANON_THPS); if (TestClearPageDoubleMap(page)) { /* @@ -1357,7 +1375,7 @@ static void page_remove_anon_compound_rmap(struct page *page) clear_page_mlock(page); if (nr) { - __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, -nr); + __mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, -nr); deferred_split_huge_page(page); } } @@ -1371,11 +1389,8 @@ static void page_remove_anon_compound_rmap(struct page *page) */ void page_remove_rmap(struct page *page, bool compound) { - if (!PageAnon(page)) { - VM_BUG_ON_PAGE(compound && !PageHuge(page), page); - page_remove_file_rmap(page); - return; - } + if (!PageAnon(page)) + return page_remove_file_rmap(page, compound); if (compound) return page_remove_anon_compound_rmap(page); @@ -1389,7 +1404,7 @@ void page_remove_rmap(struct page *page, bool compound) * these counters are not modified in interrupt context, and * pte lock(a spinlock) is held, which implies preemption disabled. */ - __dec_zone_page_state(page, NR_ANON_PAGES); + __dec_node_page_state(page, NR_ANON_MAPPED); if (unlikely(PageMlocked(page))) clear_page_mlock(page); @@ -1439,7 +1454,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, goto out; } - pte = page_check_address(page, mm, address, &ptl, 0); + pte = page_check_address(page, mm, address, &ptl, + PageTransCompound(page)); if (!pte) goto out; @@ -1450,8 +1466,14 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, */ if (!(flags & TTU_IGNORE_MLOCK)) { if (vma->vm_flags & VM_LOCKED) { - /* Holding pte lock, we do *not* need mmap_sem here */ - mlock_vma_page(page); + /* PTE-mapped THP are never mlocked */ + if (!PageTransCompound(page)) { + /* + * Holding pte lock, we do *not* need + * mmap_sem here + */ + mlock_vma_page(page); + } ret = SWAP_MLOCK; goto out_unmap; } @@ -1555,7 +1577,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, discard: page_remove_rmap(page, PageHuge(page)); - page_cache_release(page); + put_page(page); out_unmap: pte_unmap_unlock(pte, ptl); diff --git a/mm/shmem.c b/mm/shmem.c index 9428c51ab2d6..7f7748a0f9e1 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -32,6 +32,7 @@ #include <linux/export.h> #include <linux/swap.h> #include <linux/uio.h> +#include <linux/khugepaged.h> static struct vfsmount *shm_mnt; @@ -75,8 +76,8 @@ static struct vfsmount *shm_mnt; #include "internal.h" -#define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512) -#define VM_ACCT(size) (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT) +#define BLOCKS_PER_PAGE (PAGE_SIZE/512) +#define VM_ACCT(size) (PAGE_ALIGN(size) >> PAGE_SHIFT) /* Pretend that each entry is of this size in directory's i_size */ #define BOGO_DIRENT_SIZE 20 @@ -97,15 +98,6 @@ struct shmem_falloc { pgoff_t nr_unswapped; /* how often writepage refused to swap out */ }; -/* Flag allocation requirements to shmem_getpage */ -enum sgp_type { - SGP_READ, /* don't exceed i_size, don't allocate page */ - SGP_CACHE, /* don't exceed i_size, may allocate page */ - SGP_DIRTY, /* like SGP_CACHE, but set new page dirty */ - SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */ - SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */ -}; - #ifdef CONFIG_TMPFS static unsigned long shmem_default_max_blocks(void) { @@ -122,13 +114,14 @@ static bool shmem_should_replace_page(struct page *page, gfp_t gfp); static int shmem_replace_page(struct page **pagep, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index); static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, - struct page **pagep, enum sgp_type sgp, gfp_t gfp, int *fault_type); + struct page **pagep, enum sgp_type sgp, + gfp_t gfp, struct mm_struct *fault_mm, int *fault_type); -static inline int shmem_getpage(struct inode *inode, pgoff_t index, - struct page **pagep, enum sgp_type sgp, int *fault_type) +int shmem_getpage(struct inode *inode, pgoff_t index, + struct page **pagep, enum sgp_type sgp) { return shmem_getpage_gfp(inode, index, pagep, sgp, - mapping_gfp_mask(inode->i_mapping), fault_type); + mapping_gfp_mask(inode->i_mapping), NULL, NULL); } static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) @@ -169,20 +162,23 @@ static inline int shmem_reacct_size(unsigned long flags, /* * ... whereas tmpfs objects are accounted incrementally as - * pages are allocated, in order to allow huge sparse files. + * pages are allocated, in order to allow large sparse files. * shmem_getpage reports shmem_acct_block failure as -ENOSPC not -ENOMEM, * so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM. */ -static inline int shmem_acct_block(unsigned long flags) +static inline int shmem_acct_block(unsigned long flags, long pages) { - return (flags & VM_NORESERVE) ? - security_vm_enough_memory_mm(current->mm, VM_ACCT(PAGE_CACHE_SIZE)) : 0; + if (!(flags & VM_NORESERVE)) + return 0; + + return security_vm_enough_memory_mm(current->mm, + pages * VM_ACCT(PAGE_SIZE)); } static inline void shmem_unacct_blocks(unsigned long flags, long pages) { if (flags & VM_NORESERVE) - vm_unacct_memory(pages * VM_ACCT(PAGE_CACHE_SIZE)); + vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE)); } static const struct super_operations shmem_ops; @@ -192,6 +188,7 @@ static const struct inode_operations shmem_inode_operations; static const struct inode_operations shmem_dir_inode_operations; static const struct inode_operations shmem_special_inode_operations; static const struct vm_operations_struct shmem_vm_ops; +static struct file_system_type shmem_fs_type; static LIST_HEAD(shmem_swaplist); static DEFINE_MUTEX(shmem_swaplist_mutex); @@ -249,6 +246,53 @@ static void shmem_recalc_inode(struct inode *inode) } } +bool shmem_charge(struct inode *inode, long pages) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + unsigned long flags; + + if (shmem_acct_block(info->flags, pages)) + return false; + spin_lock_irqsave(&info->lock, flags); + info->alloced += pages; + inode->i_blocks += pages * BLOCKS_PER_PAGE; + shmem_recalc_inode(inode); + spin_unlock_irqrestore(&info->lock, flags); + inode->i_mapping->nrpages += pages; + + if (!sbinfo->max_blocks) + return true; + if (percpu_counter_compare(&sbinfo->used_blocks, + sbinfo->max_blocks - pages) > 0) { + inode->i_mapping->nrpages -= pages; + spin_lock_irqsave(&info->lock, flags); + info->alloced -= pages; + shmem_recalc_inode(inode); + spin_unlock_irqrestore(&info->lock, flags); + + return false; + } + percpu_counter_add(&sbinfo->used_blocks, pages); + return true; +} + +void shmem_uncharge(struct inode *inode, long pages) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + unsigned long flags; + + spin_lock_irqsave(&info->lock, flags); + info->alloced -= pages; + inode->i_blocks -= pages * BLOCKS_PER_PAGE; + shmem_recalc_inode(inode); + spin_unlock_irqrestore(&info->lock, flags); + + if (sbinfo->max_blocks) + percpu_counter_sub(&sbinfo->used_blocks, pages); +} + /* * Replace item expected in radix tree by a new item, while holding tree lock. */ @@ -289,36 +333,256 @@ static bool shmem_confirm_swap(struct address_space *mapping, } /* + * Definitions for "huge tmpfs": tmpfs mounted with the huge= option + * + * SHMEM_HUGE_NEVER: + * disables huge pages for the mount; + * SHMEM_HUGE_ALWAYS: + * enables huge pages for the mount; + * SHMEM_HUGE_WITHIN_SIZE: + * only allocate huge pages if the page will be fully within i_size, + * also respect fadvise()/madvise() hints; + * SHMEM_HUGE_ADVISE: + * only allocate huge pages if requested with fadvise()/madvise(); + */ + +#define SHMEM_HUGE_NEVER 0 +#define SHMEM_HUGE_ALWAYS 1 +#define SHMEM_HUGE_WITHIN_SIZE 2 +#define SHMEM_HUGE_ADVISE 3 + +/* + * Special values. + * Only can be set via /sys/kernel/mm/transparent_hugepage/shmem_enabled: + * + * SHMEM_HUGE_DENY: + * disables huge on shm_mnt and all mounts, for emergency use; + * SHMEM_HUGE_FORCE: + * enables huge on shm_mnt and all mounts, w/o needing option, for testing; + * + */ +#define SHMEM_HUGE_DENY (-1) +#define SHMEM_HUGE_FORCE (-2) + +#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE +/* ifdef here to avoid bloating shmem.o when not necessary */ + +int shmem_huge __read_mostly; + +static int shmem_parse_huge(const char *str) +{ + if (!strcmp(str, "never")) + return SHMEM_HUGE_NEVER; + if (!strcmp(str, "always")) + return SHMEM_HUGE_ALWAYS; + if (!strcmp(str, "within_size")) + return SHMEM_HUGE_WITHIN_SIZE; + if (!strcmp(str, "advise")) + return SHMEM_HUGE_ADVISE; + if (!strcmp(str, "deny")) + return SHMEM_HUGE_DENY; + if (!strcmp(str, "force")) + return SHMEM_HUGE_FORCE; + return -EINVAL; +} + +static const char *shmem_format_huge(int huge) +{ + switch (huge) { + case SHMEM_HUGE_NEVER: + return "never"; + case SHMEM_HUGE_ALWAYS: + return "always"; + case SHMEM_HUGE_WITHIN_SIZE: + return "within_size"; + case SHMEM_HUGE_ADVISE: + return "advise"; + case SHMEM_HUGE_DENY: + return "deny"; + case SHMEM_HUGE_FORCE: + return "force"; + default: + VM_BUG_ON(1); + return "bad_val"; + } +} + +static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, + struct shrink_control *sc, unsigned long nr_to_split) +{ + LIST_HEAD(list), *pos, *next; + struct inode *inode; + struct shmem_inode_info *info; + struct page *page; + unsigned long batch = sc ? sc->nr_to_scan : 128; + int removed = 0, split = 0; + + if (list_empty(&sbinfo->shrinklist)) + return SHRINK_STOP; + + spin_lock(&sbinfo->shrinklist_lock); + list_for_each_safe(pos, next, &sbinfo->shrinklist) { + info = list_entry(pos, struct shmem_inode_info, shrinklist); + + /* pin the inode */ + inode = igrab(&info->vfs_inode); + + /* inode is about to be evicted */ + if (!inode) { + list_del_init(&info->shrinklist); + removed++; + goto next; + } + + /* Check if there's anything to gain */ + if (round_up(inode->i_size, PAGE_SIZE) == + round_up(inode->i_size, HPAGE_PMD_SIZE)) { + list_del_init(&info->shrinklist); + removed++; + iput(inode); + goto next; + } + + list_move(&info->shrinklist, &list); +next: + if (!--batch) + break; + } + spin_unlock(&sbinfo->shrinklist_lock); + + list_for_each_safe(pos, next, &list) { + int ret; + + info = list_entry(pos, struct shmem_inode_info, shrinklist); + inode = &info->vfs_inode; + + if (nr_to_split && split >= nr_to_split) { + iput(inode); + continue; + } + + page = find_lock_page(inode->i_mapping, + (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT); + if (!page) + goto drop; + + if (!PageTransHuge(page)) { + unlock_page(page); + put_page(page); + goto drop; + } + + ret = split_huge_page(page); + unlock_page(page); + put_page(page); + + if (ret) { + /* split failed: leave it on the list */ + iput(inode); + continue; + } + + split++; +drop: + list_del_init(&info->shrinklist); + removed++; + iput(inode); + } + + spin_lock(&sbinfo->shrinklist_lock); + list_splice_tail(&list, &sbinfo->shrinklist); + sbinfo->shrinklist_len -= removed; + spin_unlock(&sbinfo->shrinklist_lock); + + return split; +} + +static long shmem_unused_huge_scan(struct super_block *sb, + struct shrink_control *sc) +{ + struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + + if (!READ_ONCE(sbinfo->shrinklist_len)) + return SHRINK_STOP; + + return shmem_unused_huge_shrink(sbinfo, sc, 0); +} + +static long shmem_unused_huge_count(struct super_block *sb, + struct shrink_control *sc) +{ + struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + return READ_ONCE(sbinfo->shrinklist_len); +} +#else /* !CONFIG_TRANSPARENT_HUGE_PAGECACHE */ + +#define shmem_huge SHMEM_HUGE_DENY + +static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, + struct shrink_control *sc, unsigned long nr_to_split) +{ + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE */ + +/* * Like add_to_page_cache_locked, but error if expected item has gone. */ static int shmem_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t index, void *expected) { - int error; + int error, nr = hpage_nr_pages(page); + VM_BUG_ON_PAGE(PageTail(page), page); + VM_BUG_ON_PAGE(index != round_down(index, nr), page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageSwapBacked(page), page); + VM_BUG_ON(expected && PageTransHuge(page)); - page_cache_get(page); + page_ref_add(page, nr); page->mapping = mapping; page->index = index; spin_lock_irq(&mapping->tree_lock); - if (!expected) + if (PageTransHuge(page)) { + void __rcu **results; + pgoff_t idx; + int i; + + error = 0; + if (radix_tree_gang_lookup_slot(&mapping->page_tree, + &results, &idx, index, 1) && + idx < index + HPAGE_PMD_NR) { + error = -EEXIST; + } + + if (!error) { + for (i = 0; i < HPAGE_PMD_NR; i++) { + error = radix_tree_insert(&mapping->page_tree, + index + i, page + i); + VM_BUG_ON(error); + } + count_vm_event(THP_FILE_ALLOC); + } + } else if (!expected) { error = radix_tree_insert(&mapping->page_tree, index, page); - else + } else { error = shmem_radix_tree_replace(mapping, index, expected, page); + } + if (!error) { - mapping->nrpages++; - __inc_zone_page_state(page, NR_FILE_PAGES); - __inc_zone_page_state(page, NR_SHMEM); + mapping->nrpages += nr; + if (PageTransHuge(page)) + __inc_node_page_state(page, NR_SHMEM_THPS); + __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr); + __mod_node_page_state(page_pgdat(page), NR_SHMEM, nr); spin_unlock_irq(&mapping->tree_lock); } else { page->mapping = NULL; spin_unlock_irq(&mapping->tree_lock); - page_cache_release(page); + page_ref_sub(page, nr); } return error; } @@ -331,14 +595,16 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap) struct address_space *mapping = page->mapping; int error; + VM_BUG_ON_PAGE(PageCompound(page), page); + spin_lock_irq(&mapping->tree_lock); error = shmem_radix_tree_replace(mapping, page->index, page, radswap); page->mapping = NULL; mapping->nrpages--; - __dec_zone_page_state(page, NR_FILE_PAGES); - __dec_zone_page_state(page, NR_SHMEM); + __dec_node_page_state(page, NR_FILE_PAGES); + __dec_node_page_state(page, NR_SHMEM); spin_unlock_irq(&mapping->tree_lock); - page_cache_release(page); + put_page(page); BUG_ON(error); } @@ -474,10 +740,10 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); - pgoff_t start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - pgoff_t end = (lend + 1) >> PAGE_CACHE_SHIFT; - unsigned int partial_start = lstart & (PAGE_CACHE_SIZE - 1); - unsigned int partial_end = (lend + 1) & (PAGE_CACHE_SIZE - 1); + pgoff_t start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; + pgoff_t end = (lend + 1) >> PAGE_SHIFT; + unsigned int partial_start = lstart & (PAGE_SIZE - 1); + unsigned int partial_end = (lend + 1) & (PAGE_SIZE - 1); struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; long nr_swaps_freed = 0; @@ -510,10 +776,33 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, continue; } + VM_BUG_ON_PAGE(page_to_pgoff(page) != index, page); + if (!trylock_page(page)) continue; + + if (PageTransTail(page)) { + /* Middle of THP: zero out the page */ + clear_highpage(page); + unlock_page(page); + continue; + } else if (PageTransHuge(page)) { + if (index == round_down(end, HPAGE_PMD_NR)) { + /* + * Range ends in the middle of THP: + * zero out the page + */ + clear_highpage(page); + unlock_page(page); + continue; + } + index += HPAGE_PMD_NR - 1; + i += HPAGE_PMD_NR - 1; + } + if (!unfalloc || !PageUptodate(page)) { - if (page->mapping == mapping) { + VM_BUG_ON_PAGE(PageTail(page), page); + if (page_mapping(page) == mapping) { VM_BUG_ON_PAGE(PageWriteback(page), page); truncate_inode_page(mapping, page); } @@ -528,9 +817,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (partial_start) { struct page *page = NULL; - shmem_getpage(inode, start - 1, &page, SGP_READ, NULL); + shmem_getpage(inode, start - 1, &page, SGP_READ); if (page) { - unsigned int top = PAGE_CACHE_SIZE; + unsigned int top = PAGE_SIZE; if (start > end) { top = partial_end; partial_end = 0; @@ -538,17 +827,17 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, zero_user_segment(page, partial_start, top); set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); } } if (partial_end) { struct page *page = NULL; - shmem_getpage(inode, end, &page, SGP_READ, NULL); + shmem_getpage(inode, end, &page, SGP_READ); if (page) { zero_user_segment(page, 0, partial_end); set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); } } if (start >= end) @@ -589,8 +878,36 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } lock_page(page); + + if (PageTransTail(page)) { + /* Middle of THP: zero out the page */ + clear_highpage(page); + unlock_page(page); + /* + * Partial thp truncate due 'start' in middle + * of THP: don't need to look on these pages + * again on !pvec.nr restart. + */ + if (index != round_down(end, HPAGE_PMD_NR)) + start++; + continue; + } else if (PageTransHuge(page)) { + if (index == round_down(end, HPAGE_PMD_NR)) { + /* + * Range ends in the middle of THP: + * zero out the page + */ + clear_highpage(page); + unlock_page(page); + continue; + } + index += HPAGE_PMD_NR - 1; + i += HPAGE_PMD_NR - 1; + } + if (!unfalloc || !PageUptodate(page)) { - if (page->mapping == mapping) { + VM_BUG_ON_PAGE(PageTail(page), page); + if (page_mapping(page) == mapping) { VM_BUG_ON_PAGE(PageWriteback(page), page); truncate_inode_page(mapping, page); } else { @@ -607,10 +924,10 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, index++; } - spin_lock(&info->lock); + spin_lock_irq(&info->lock); info->swapped -= nr_swaps_freed; shmem_recalc_inode(inode); - spin_unlock(&info->lock); + spin_unlock_irq(&info->lock); } void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) @@ -627,9 +944,9 @@ static int shmem_getattr(struct vfsmount *mnt, struct dentry *dentry, struct shmem_inode_info *info = SHMEM_I(inode); if (info->alloced - info->swapped != inode->i_mapping->nrpages) { - spin_lock(&info->lock); + spin_lock_irq(&info->lock); shmem_recalc_inode(inode); - spin_unlock(&info->lock); + spin_unlock_irq(&info->lock); } generic_fillattr(inode, stat); return 0; @@ -639,6 +956,7 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); int error; error = inode_change_ok(inode, attr); @@ -674,6 +992,20 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) if (oldsize > holebegin) unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); + + /* + * Part of the huge page can be beyond i_size: subject + * to shrink under memory pressure. + */ + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) { + spin_lock(&sbinfo->shrinklist_lock); + if (list_empty(&info->shrinklist)) { + list_add_tail(&info->shrinklist, + &sbinfo->shrinklist); + sbinfo->shrinklist_len++; + } + spin_unlock(&sbinfo->shrinklist_lock); + } } } @@ -686,11 +1018,20 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) static void shmem_evict_inode(struct inode *inode) { struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); if (inode->i_mapping->a_ops == &shmem_aops) { shmem_unacct_size(info->flags, inode->i_size); inode->i_size = 0; shmem_truncate_range(inode, 0, (loff_t)-1); + if (!list_empty(&info->shrinklist)) { + spin_lock(&sbinfo->shrinklist_lock); + if (!list_empty(&info->shrinklist)) { + list_del_init(&info->shrinklist); + sbinfo->shrinklist_len--; + } + spin_unlock(&sbinfo->shrinklist_lock); + } if (!list_empty(&info->swaplist)) { mutex_lock(&shmem_swaplist_mutex); list_del_init(&info->swaplist); @@ -773,9 +1114,9 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, delete_from_swap_cache(*pagep); set_page_dirty(*pagep); if (!error) { - spin_lock(&info->lock); + spin_lock_irq(&info->lock); info->swapped--; - spin_unlock(&info->lock); + spin_unlock_irq(&info->lock); swap_free(swap); } } @@ -833,7 +1174,7 @@ int shmem_unuse(swp_entry_t swap, struct page *page) mem_cgroup_commit_charge(page, memcg, true, false); out: unlock_page(page); - page_cache_release(page); + put_page(page); return error; } @@ -848,6 +1189,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) swp_entry_t swap; pgoff_t index; + VM_BUG_ON_PAGE(PageCompound(page), page); BUG_ON(!PageLocked(page)); mapping = page->mapping; index = page->index; @@ -922,10 +1264,10 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) list_add_tail(&info->swaplist, &shmem_swaplist); if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) { - spin_lock(&info->lock); + spin_lock_irq(&info->lock); shmem_recalc_inode(inode); info->swapped++; - spin_unlock(&info->lock); + spin_unlock_irq(&info->lock); swap_shmem_alloc(swap); shmem_delete_from_page_cache(page, swp_to_radix_entry(swap)); @@ -947,8 +1289,7 @@ redirty: return 0; } -#ifdef CONFIG_NUMA -#ifdef CONFIG_TMPFS +#if defined(CONFIG_NUMA) && defined(CONFIG_TMPFS) static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) { char buffer[64]; @@ -972,7 +1313,35 @@ static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) } return mpol; } -#endif /* CONFIG_TMPFS */ +#else /* !CONFIG_NUMA || !CONFIG_TMPFS */ +static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) +{ +} +static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) +{ + return NULL; +} +#endif /* CONFIG_NUMA && CONFIG_TMPFS */ +#ifndef CONFIG_NUMA +#define vm_policy vm_private_data +#endif + +static void shmem_pseudo_vma_init(struct vm_area_struct *vma, + struct shmem_inode_info *info, pgoff_t index) +{ + /* Create a pseudo vma that just contains the policy */ + vma->vm_start = 0; + /* Bias interleave by inode number to distribute better across nodes */ + vma->vm_pgoff = index + info->vfs_inode.i_ino; + vma->vm_ops = NULL; + vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index); +} + +static void shmem_pseudo_vma_destroy(struct vm_area_struct *vma) +{ + /* Drop reference taken by mpol_shared_policy_lookup() */ + mpol_cond_put(vma->vm_policy); +} static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) @@ -980,67 +1349,96 @@ static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, struct vm_area_struct pvma; struct page *page; - /* Create a pseudo vma that just contains the policy */ - pvma.vm_start = 0; - /* Bias interleave by inode number to distribute better across nodes */ - pvma.vm_pgoff = index + info->vfs_inode.i_ino; - pvma.vm_ops = NULL; - pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index); - + shmem_pseudo_vma_init(&pvma, info, index); page = swapin_readahead(swap, gfp, &pvma, 0); - - /* Drop reference taken by mpol_shared_policy_lookup() */ - mpol_cond_put(pvma.vm_policy); + shmem_pseudo_vma_destroy(&pvma); return page; } -static struct page *shmem_alloc_page(gfp_t gfp, - struct shmem_inode_info *info, pgoff_t index) +static struct page *shmem_alloc_hugepage(gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; + struct inode *inode = &info->vfs_inode; + struct address_space *mapping = inode->i_mapping; + pgoff_t idx, hindex; + void __rcu **results; struct page *page; - /* Create a pseudo vma that just contains the policy */ - pvma.vm_start = 0; - /* Bias interleave by inode number to distribute better across nodes */ - pvma.vm_pgoff = index + info->vfs_inode.i_ino; - pvma.vm_ops = NULL; - pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index); - - page = alloc_page_vma(gfp, &pvma, 0); + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) + return NULL; - /* Drop reference taken by mpol_shared_policy_lookup() */ - mpol_cond_put(pvma.vm_policy); + hindex = round_down(index, HPAGE_PMD_NR); + rcu_read_lock(); + if (radix_tree_gang_lookup_slot(&mapping->page_tree, &results, &idx, + hindex, 1) && idx < hindex + HPAGE_PMD_NR) { + rcu_read_unlock(); + return NULL; + } + rcu_read_unlock(); + shmem_pseudo_vma_init(&pvma, info, hindex); + page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, + HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true); + shmem_pseudo_vma_destroy(&pvma); + if (page) + prep_transhuge_page(page); return page; } -#else /* !CONFIG_NUMA */ -#ifdef CONFIG_TMPFS -static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) -{ -} -#endif /* CONFIG_TMPFS */ -static inline struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, +static struct page *shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { - return swapin_readahead(swap, gfp, NULL, 0); -} + struct vm_area_struct pvma; + struct page *page; -static inline struct page *shmem_alloc_page(gfp_t gfp, - struct shmem_inode_info *info, pgoff_t index) -{ - return alloc_page(gfp); + shmem_pseudo_vma_init(&pvma, info, index); + page = alloc_page_vma(gfp, &pvma, 0); + shmem_pseudo_vma_destroy(&pvma); + + return page; } -#endif /* CONFIG_NUMA */ -#if !defined(CONFIG_NUMA) || !defined(CONFIG_TMPFS) -static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) +static struct page *shmem_alloc_and_acct_page(gfp_t gfp, + struct shmem_inode_info *info, struct shmem_sb_info *sbinfo, + pgoff_t index, bool huge) { - return NULL; + struct page *page; + int nr; + int err = -ENOSPC; + + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) + huge = false; + nr = huge ? HPAGE_PMD_NR : 1; + + if (shmem_acct_block(info->flags, nr)) + goto failed; + if (sbinfo->max_blocks) { + if (percpu_counter_compare(&sbinfo->used_blocks, + sbinfo->max_blocks - nr) > 0) + goto unacct; + percpu_counter_add(&sbinfo->used_blocks, nr); + } + + if (huge) + page = shmem_alloc_hugepage(gfp, info, index); + else + page = shmem_alloc_page(gfp, info, index); + if (page) { + __SetPageLocked(page); + __SetPageSwapBacked(page); + return page; + } + + err = -ENOMEM; + if (sbinfo->max_blocks) + percpu_counter_add(&sbinfo->used_blocks, -nr); +unacct: + shmem_unacct_blocks(info->flags, nr); +failed: + return ERR_PTR(err); } -#endif /* * When a page is moved from swapcache to shmem filecache (either by the @@ -1080,13 +1478,11 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, if (!newpage) return -ENOMEM; - page_cache_get(newpage); + get_page(newpage); copy_highpage(newpage, oldpage); flush_dcache_page(newpage); - __SetPageLocked(newpage); SetPageUptodate(newpage); - SetPageSwapBacked(newpage); set_page_private(newpage, swap_index); SetPageSwapCache(newpage); @@ -1098,8 +1494,8 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage, newpage); if (!error) { - __inc_zone_page_state(newpage, NR_FILE_PAGES); - __dec_zone_page_state(oldpage, NR_FILE_PAGES); + __inc_node_page_state(newpage, NR_FILE_PAGES); + __dec_node_page_state(oldpage, NR_FILE_PAGES); } spin_unlock_irq(&swap_mapping->tree_lock); @@ -1120,8 +1516,8 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, set_page_private(oldpage, 0); unlock_page(oldpage); - page_cache_release(oldpage); - page_cache_release(oldpage); + put_page(oldpage); + put_page(oldpage); return error; } @@ -1130,23 +1526,32 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, * * If we allocate a new one we do not mark it dirty. That's up to the * vm. If we swap it in we mark it dirty since we also free the swap - * entry since a page cannot live in both the swap and page cache + * entry since a page cannot live in both the swap and page cache. + * + * fault_mm and fault_type are only supplied by shmem_fault: + * otherwise they are NULL. */ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, - struct page **pagep, enum sgp_type sgp, gfp_t gfp, int *fault_type) + struct page **pagep, enum sgp_type sgp, gfp_t gfp, + struct mm_struct *fault_mm, int *fault_type) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info; struct shmem_sb_info *sbinfo; + struct mm_struct *charge_mm; struct mem_cgroup *memcg; struct page *page; swp_entry_t swap; + enum sgp_type sgp_huge = sgp; + pgoff_t hindex = index; int error; int once = 0; int alloced = 0; - if (index > (MAX_LFS_FILESIZE >> PAGE_CACHE_SHIFT)) + if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT)) return -EFBIG; + if (sgp == SGP_NOHUGE || sgp == SGP_HUGE) + sgp = SGP_CACHE; repeat: swap.val = 0; page = find_lock_entry(mapping, index); @@ -1155,8 +1560,8 @@ repeat: page = NULL; } - if (sgp != SGP_WRITE && sgp != SGP_FALLOC && - ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { + if (sgp <= SGP_CACHE && + ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { error = -EINVAL; goto unlock; } @@ -1169,7 +1574,7 @@ repeat: if (sgp != SGP_READ) goto clear; unlock_page(page); - page_cache_release(page); + put_page(page); page = NULL; } if (page || (sgp == SGP_READ && !swap.val)) { @@ -1183,14 +1588,19 @@ repeat: */ info = SHMEM_I(inode); sbinfo = SHMEM_SB(inode->i_sb); + charge_mm = fault_mm ? : current->mm; if (swap.val) { /* Look it up and read it in.. */ page = lookup_swap_cache(swap); if (!page) { - /* here we actually do the io */ - if (fault_type) + /* Or update major stats only when swapin succeeds?? */ + if (fault_type) { *fault_type |= VM_FAULT_MAJOR; + count_vm_event(PGMAJFAULT); + mem_cgroup_count_vm_event(fault_mm, PGMAJFAULT); + } + /* Here we actually start the io */ page = shmem_swapin(swap, gfp, info, index); if (!page) { error = -ENOMEM; @@ -1217,7 +1627,7 @@ repeat: goto failed; } - error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg, + error = mem_cgroup_try_charge(page, charge_mm, gfp, &memcg, false); if (!error) { error = shmem_add_to_page_cache(page, mapping, index, @@ -1244,10 +1654,10 @@ repeat: mem_cgroup_commit_charge(page, memcg, true, false); - spin_lock(&info->lock); + spin_lock_irq(&info->lock); info->swapped--; shmem_recalc_inode(inode); - spin_unlock(&info->lock); + spin_unlock_irq(&info->lock); if (sgp == SGP_WRITE) mark_page_accessed(page); @@ -1257,54 +1667,111 @@ repeat: swap_free(swap); } else { - if (shmem_acct_block(info->flags)) { - error = -ENOSPC; - goto failed; + /* shmem_symlink() */ + if (mapping->a_ops != &shmem_aops) + goto alloc_nohuge; + if (shmem_huge == SHMEM_HUGE_DENY || sgp_huge == SGP_NOHUGE) + goto alloc_nohuge; + if (shmem_huge == SHMEM_HUGE_FORCE) + goto alloc_huge; + switch (sbinfo->huge) { + loff_t i_size; + pgoff_t off; + case SHMEM_HUGE_NEVER: + goto alloc_nohuge; + case SHMEM_HUGE_WITHIN_SIZE: + off = round_up(index, HPAGE_PMD_NR); + i_size = round_up(i_size_read(inode), PAGE_SIZE); + if (i_size >= HPAGE_PMD_SIZE && + i_size >> PAGE_SHIFT >= off) + goto alloc_huge; + /* fallthrough */ + case SHMEM_HUGE_ADVISE: + if (sgp_huge == SGP_HUGE) + goto alloc_huge; + /* TODO: implement fadvise() hints */ + goto alloc_nohuge; } - if (sbinfo->max_blocks) { - if (percpu_counter_compare(&sbinfo->used_blocks, - sbinfo->max_blocks) >= 0) { - error = -ENOSPC; - goto unacct; + +alloc_huge: + page = shmem_alloc_and_acct_page(gfp, info, sbinfo, + index, true); + if (IS_ERR(page)) { +alloc_nohuge: page = shmem_alloc_and_acct_page(gfp, info, sbinfo, + index, false); + } + if (IS_ERR(page)) { + int retry = 5; + error = PTR_ERR(page); + page = NULL; + if (error != -ENOSPC) + goto failed; + /* + * Try to reclaim some spece by splitting a huge page + * beyond i_size on the filesystem. + */ + while (retry--) { + int ret; + ret = shmem_unused_huge_shrink(sbinfo, NULL, 1); + if (ret == SHRINK_STOP) + break; + if (ret) + goto alloc_nohuge; } - percpu_counter_inc(&sbinfo->used_blocks); + goto failed; } - page = shmem_alloc_page(gfp, info, index); - if (!page) { - error = -ENOMEM; - goto decused; - } + if (PageTransHuge(page)) + hindex = round_down(index, HPAGE_PMD_NR); + else + hindex = index; - __SetPageSwapBacked(page); - __SetPageLocked(page); if (sgp == SGP_WRITE) __SetPageReferenced(page); - error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg, - false); + error = mem_cgroup_try_charge(page, charge_mm, gfp, &memcg, + PageTransHuge(page)); if (error) - goto decused; - error = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK); + goto unacct; + error = radix_tree_maybe_preload_order(gfp & GFP_RECLAIM_MASK, + compound_order(page)); if (!error) { - error = shmem_add_to_page_cache(page, mapping, index, + error = shmem_add_to_page_cache(page, mapping, hindex, NULL); radix_tree_preload_end(); } if (error) { - mem_cgroup_cancel_charge(page, memcg, false); - goto decused; + mem_cgroup_cancel_charge(page, memcg, + PageTransHuge(page)); + goto unacct; } - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false, + PageTransHuge(page)); lru_cache_add_anon(page); - spin_lock(&info->lock); - info->alloced++; - inode->i_blocks += BLOCKS_PER_PAGE; + spin_lock_irq(&info->lock); + info->alloced += 1 << compound_order(page); + inode->i_blocks += BLOCKS_PER_PAGE << compound_order(page); shmem_recalc_inode(inode); - spin_unlock(&info->lock); + spin_unlock_irq(&info->lock); alloced = true; + if (PageTransHuge(page) && + DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE) < + hindex + HPAGE_PMD_NR - 1) { + /* + * Part of the huge page is beyond i_size: subject + * to shrink under memory pressure. + */ + spin_lock(&sbinfo->shrinklist_lock); + if (list_empty(&info->shrinklist)) { + list_add_tail(&info->shrinklist, + &sbinfo->shrinklist); + sbinfo->shrinklist_len++; + } + spin_unlock(&sbinfo->shrinklist_lock); + } + /* * Let SGP_FALLOC use the SGP_WRITE optimization on a new page. */ @@ -1316,52 +1783,61 @@ clear: * but SGP_FALLOC on a page fallocated earlier must initialize * it now, lest undo on failure cancel our earlier guarantee. */ - if (sgp != SGP_WRITE) { - clear_highpage(page); - flush_dcache_page(page); - SetPageUptodate(page); + if (sgp != SGP_WRITE && !PageUptodate(page)) { + struct page *head = compound_head(page); + int i; + + for (i = 0; i < (1 << compound_order(head)); i++) { + clear_highpage(head + i); + flush_dcache_page(head + i); + } + SetPageUptodate(head); } - if (sgp == SGP_DIRTY) - set_page_dirty(page); } /* Perhaps the file has been truncated since we checked */ - if (sgp != SGP_WRITE && sgp != SGP_FALLOC && - ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { + if (sgp <= SGP_CACHE && + ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { if (alloced) { ClearPageDirty(page); delete_from_page_cache(page); - spin_lock(&info->lock); + spin_lock_irq(&info->lock); shmem_recalc_inode(inode); - spin_unlock(&info->lock); + spin_unlock_irq(&info->lock); } error = -EINVAL; goto unlock; } - *pagep = page; + *pagep = page + index - hindex; return 0; /* * Error recovery. */ -decused: - if (sbinfo->max_blocks) - percpu_counter_add(&sbinfo->used_blocks, -1); unacct: - shmem_unacct_blocks(info->flags, 1); + if (sbinfo->max_blocks) + percpu_counter_sub(&sbinfo->used_blocks, + 1 << compound_order(page)); + shmem_unacct_blocks(info->flags, 1 << compound_order(page)); + + if (PageTransHuge(page)) { + unlock_page(page); + put_page(page); + goto alloc_nohuge; + } failed: if (swap.val && !shmem_confirm_swap(mapping, index, swap)) error = -EEXIST; unlock: if (page) { unlock_page(page); - page_cache_release(page); + put_page(page); } if (error == -ENOSPC && !once++) { info = SHMEM_I(inode); - spin_lock(&info->lock); + spin_lock_irq(&info->lock); shmem_recalc_inode(inode); - spin_unlock(&info->lock); + spin_unlock_irq(&info->lock); goto repeat; } if (error == -EEXIST) /* from above or from radix_tree_insert */ @@ -1372,6 +1848,8 @@ unlock: static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct inode *inode = file_inode(vma->vm_file); + gfp_t gfp = mapping_gfp_mask(inode->i_mapping); + enum sgp_type sgp; int error; int ret = VM_FAULT_LOCKED; @@ -1433,15 +1911,105 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) spin_unlock(&inode->i_lock); } - error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret); + sgp = SGP_CACHE; + if (vma->vm_flags & VM_HUGEPAGE) + sgp = SGP_HUGE; + else if (vma->vm_flags & VM_NOHUGEPAGE) + sgp = SGP_NOHUGE; + + error = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, sgp, + gfp, vma->vm_mm, &ret); if (error) return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS); + return ret; +} + +unsigned long shmem_get_unmapped_area(struct file *file, + unsigned long uaddr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + unsigned long (*get_area)(struct file *, + unsigned long, unsigned long, unsigned long, unsigned long); + unsigned long addr; + unsigned long offset; + unsigned long inflated_len; + unsigned long inflated_addr; + unsigned long inflated_offset; + + if (len > TASK_SIZE) + return -ENOMEM; + + get_area = current->mm->get_unmapped_area; + addr = get_area(file, uaddr, len, pgoff, flags); + + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) + return addr; + if (IS_ERR_VALUE(addr)) + return addr; + if (addr & ~PAGE_MASK) + return addr; + if (addr > TASK_SIZE - len) + return addr; + + if (shmem_huge == SHMEM_HUGE_DENY) + return addr; + if (len < HPAGE_PMD_SIZE) + return addr; + if (flags & MAP_FIXED) + return addr; + /* + * Our priority is to support MAP_SHARED mapped hugely; + * and support MAP_PRIVATE mapped hugely too, until it is COWed. + * But if caller specified an address hint, respect that as before. + */ + if (uaddr) + return addr; + + if (shmem_huge != SHMEM_HUGE_FORCE) { + struct super_block *sb; - if (ret & VM_FAULT_MAJOR) { - count_vm_event(PGMAJFAULT); - mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); + if (file) { + VM_BUG_ON(file->f_op != &shmem_file_operations); + sb = file_inode(file)->i_sb; + } else { + /* + * Called directly from mm/mmap.c, or drivers/char/mem.c + * for "/dev/zero", to create a shared anonymous object. + */ + if (IS_ERR(shm_mnt)) + return addr; + sb = shm_mnt->mnt_sb; + } + if (SHMEM_SB(sb)->huge != SHMEM_HUGE_NEVER) + return addr; } - return ret; + + offset = (pgoff << PAGE_SHIFT) & (HPAGE_PMD_SIZE-1); + if (offset && offset + len < 2 * HPAGE_PMD_SIZE) + return addr; + if ((addr & (HPAGE_PMD_SIZE-1)) == offset) + return addr; + + inflated_len = len + HPAGE_PMD_SIZE - PAGE_SIZE; + if (inflated_len > TASK_SIZE) + return addr; + if (inflated_len < len) + return addr; + + inflated_addr = get_area(NULL, 0, inflated_len, 0, flags); + if (IS_ERR_VALUE(inflated_addr)) + return addr; + if (inflated_addr & ~PAGE_MASK) + return addr; + + inflated_offset = inflated_addr & (HPAGE_PMD_SIZE-1); + inflated_addr += offset - inflated_offset; + if (inflated_offset > offset) + inflated_addr += HPAGE_PMD_SIZE; + + if (inflated_addr > TASK_SIZE - len) + return addr; + return inflated_addr; } #ifdef CONFIG_NUMA @@ -1468,7 +2036,7 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) struct shmem_inode_info *info = SHMEM_I(inode); int retval = -ENOMEM; - spin_lock(&info->lock); + spin_lock_irq(&info->lock); if (lock && !(info->flags & VM_LOCKED)) { if (!user_shm_lock(inode->i_size, user)) goto out_nomem; @@ -1483,7 +2051,7 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) retval = 0; out_nomem: - spin_unlock(&info->lock); + spin_unlock_irq(&info->lock); return retval; } @@ -1491,6 +2059,11 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { file_accessed(file); vma->vm_ops = &shmem_vm_ops; + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE) && + ((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) < + (vma->vm_end & HPAGE_PMD_MASK)) { + khugepaged_enter(vma, vma->vm_flags); + } return 0; } @@ -1516,6 +2089,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode spin_lock_init(&info->lock); info->seals = F_SEAL_SEAL; info->flags = flags & VM_NORESERVE; + INIT_LIST_HEAD(&info->shrinklist); INIT_LIST_HEAD(&info->swaplist); simple_xattrs_init(&info->xattrs); cache_no_acl(inode); @@ -1577,7 +2151,7 @@ shmem_write_begin(struct file *file, struct address_space *mapping, { struct inode *inode = mapping->host; struct shmem_inode_info *info = SHMEM_I(inode); - pgoff_t index = pos >> PAGE_CACHE_SHIFT; + pgoff_t index = pos >> PAGE_SHIFT; /* i_mutex is held by caller */ if (unlikely(info->seals)) { @@ -1587,7 +2161,7 @@ shmem_write_begin(struct file *file, struct address_space *mapping, return -EPERM; } - return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL); + return shmem_getpage(inode, index, pagep, SGP_WRITE); } static int @@ -1601,16 +2175,27 @@ shmem_write_end(struct file *file, struct address_space *mapping, i_size_write(inode, pos + copied); if (!PageUptodate(page)) { - if (copied < PAGE_CACHE_SIZE) { - unsigned from = pos & (PAGE_CACHE_SIZE - 1); + struct page *head = compound_head(page); + if (PageTransCompound(page)) { + int i; + + for (i = 0; i < HPAGE_PMD_NR; i++) { + if (head + i == page) + continue; + clear_highpage(head + i); + flush_dcache_page(head + i); + } + } + if (copied < PAGE_SIZE) { + unsigned from = pos & (PAGE_SIZE - 1); zero_user_segments(page, 0, from, - from + copied, PAGE_CACHE_SIZE); + from + copied, PAGE_SIZE); } - SetPageUptodate(page); + SetPageUptodate(head); } set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); return copied; } @@ -1633,10 +2218,10 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) * and even mark them dirty, so it cannot exceed the max_blocks limit. */ if (!iter_is_iovec(to)) - sgp = SGP_DIRTY; + sgp = SGP_CACHE; - index = *ppos >> PAGE_CACHE_SHIFT; - offset = *ppos & ~PAGE_CACHE_MASK; + index = *ppos >> PAGE_SHIFT; + offset = *ppos & ~PAGE_MASK; for (;;) { struct page *page = NULL; @@ -1644,36 +2229,39 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) unsigned long nr, ret; loff_t i_size = i_size_read(inode); - end_index = i_size >> PAGE_CACHE_SHIFT; + end_index = i_size >> PAGE_SHIFT; if (index > end_index) break; if (index == end_index) { - nr = i_size & ~PAGE_CACHE_MASK; + nr = i_size & ~PAGE_MASK; if (nr <= offset) break; } - error = shmem_getpage(inode, index, &page, sgp, NULL); + error = shmem_getpage(inode, index, &page, sgp); if (error) { if (error == -EINVAL) error = 0; break; } - if (page) + if (page) { + if (sgp == SGP_CACHE) + set_page_dirty(page); unlock_page(page); + } /* * We must evaluate after, since reads (unlike writes) * are called without i_mutex protection against truncate */ - nr = PAGE_CACHE_SIZE; + nr = PAGE_SIZE; i_size = i_size_read(inode); - end_index = i_size >> PAGE_CACHE_SHIFT; + end_index = i_size >> PAGE_SHIFT; if (index == end_index) { - nr = i_size & ~PAGE_CACHE_MASK; + nr = i_size & ~PAGE_MASK; if (nr <= offset) { if (page) - page_cache_release(page); + put_page(page); break; } } @@ -1694,7 +2282,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) mark_page_accessed(page); } else { page = ZERO_PAGE(0); - page_cache_get(page); + get_page(page); } /* @@ -1704,10 +2292,10 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) ret = copy_page_to_iter(page, offset, nr, to); retval += ret; offset += ret; - index += offset >> PAGE_CACHE_SHIFT; - offset &= ~PAGE_CACHE_MASK; + index += offset >> PAGE_SHIFT; + offset &= ~PAGE_MASK; - page_cache_release(page); + put_page(page); if (!iov_iter_count(to)) break; if (ret < nr) { @@ -1717,7 +2305,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) cond_resched(); } - *ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset; + *ppos = ((loff_t) index << PAGE_SHIFT) + offset; file_accessed(file); return retval ? retval : error; } @@ -1755,9 +2343,9 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, if (splice_grow_spd(pipe, &spd)) return -ENOMEM; - index = *ppos >> PAGE_CACHE_SHIFT; - loff = *ppos & ~PAGE_CACHE_MASK; - req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + index = *ppos >> PAGE_SHIFT; + loff = *ppos & ~PAGE_MASK; + req_pages = (len + loff + PAGE_SIZE - 1) >> PAGE_SHIFT; nr_pages = min(req_pages, spd.nr_pages_max); spd.nr_pages = find_get_pages_contig(mapping, index, @@ -1766,7 +2354,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, error = 0; while (spd.nr_pages < nr_pages) { - error = shmem_getpage(inode, index, &page, SGP_CACHE, NULL); + error = shmem_getpage(inode, index, &page, SGP_CACHE); if (error) break; unlock_page(page); @@ -1774,7 +2362,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, index++; } - index = *ppos >> PAGE_CACHE_SHIFT; + index = *ppos >> PAGE_SHIFT; nr_pages = spd.nr_pages; spd.nr_pages = 0; @@ -1784,28 +2372,27 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, if (!len) break; - this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff); + this_len = min_t(unsigned long, len, PAGE_SIZE - loff); page = spd.pages[page_nr]; if (!PageUptodate(page) || page->mapping != mapping) { - error = shmem_getpage(inode, index, &page, - SGP_CACHE, NULL); + error = shmem_getpage(inode, index, &page, SGP_CACHE); if (error) break; unlock_page(page); - page_cache_release(spd.pages[page_nr]); + put_page(spd.pages[page_nr]); spd.pages[page_nr] = page; } isize = i_size_read(inode); - end_index = (isize - 1) >> PAGE_CACHE_SHIFT; + end_index = (isize - 1) >> PAGE_SHIFT; if (unlikely(!isize || index > end_index)) break; if (end_index == index) { unsigned int plen; - plen = ((isize - 1) & ~PAGE_CACHE_MASK) + 1; + plen = ((isize - 1) & ~PAGE_MASK) + 1; if (plen <= loff) break; @@ -1822,7 +2409,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, } while (page_nr < nr_pages) - page_cache_release(spd.pages[page_nr++]); + put_page(spd.pages[page_nr++]); if (spd.nr_pages) error = splice_to_pipe(pipe, &spd); @@ -1904,10 +2491,10 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) else if (offset >= inode->i_size) offset = -ENXIO; else { - start = offset >> PAGE_CACHE_SHIFT; - end = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + start = offset >> PAGE_SHIFT; + end = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; new_offset = shmem_seek_hole_data(mapping, start, end, whence); - new_offset <<= PAGE_CACHE_SHIFT; + new_offset <<= PAGE_SHIFT; if (new_offset > offset) { if (new_offset < inode->i_size) offset = new_offset; @@ -2203,8 +2790,8 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, goto out; } - start = offset >> PAGE_CACHE_SHIFT; - end = (offset + len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + start = offset >> PAGE_SHIFT; + end = (offset + len + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Try to avoid a swapstorm if len is impossible to satisfy */ if (sbinfo->max_blocks && end - start > sbinfo->max_blocks) { error = -ENOSPC; @@ -2232,13 +2819,14 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, else if (shmem_falloc.nr_unswapped > shmem_falloc.nr_falloced) error = -ENOMEM; else - error = shmem_getpage(inode, index, &page, SGP_FALLOC, - NULL); + error = shmem_getpage(inode, index, &page, SGP_FALLOC); if (error) { /* Remove the !PageUptodate pages we added */ - shmem_undo_range(inode, - (loff_t)start << PAGE_CACHE_SHIFT, - (loff_t)index << PAGE_CACHE_SHIFT, true); + if (index > start) { + shmem_undo_range(inode, + (loff_t)start << PAGE_SHIFT, + ((loff_t)index << PAGE_SHIFT) - 1, true); + } goto undone; } @@ -2259,7 +2847,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, */ set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); cond_resched(); } @@ -2280,7 +2868,7 @@ static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb); buf->f_type = TMPFS_MAGIC; - buf->f_bsize = PAGE_CACHE_SIZE; + buf->f_bsize = PAGE_SIZE; buf->f_namelen = NAME_MAX; if (sbinfo->max_blocks) { buf->f_blocks = sbinfo->max_blocks; @@ -2523,7 +3111,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s struct shmem_inode_info *info; len = strlen(symname) + 1; - if (len > PAGE_CACHE_SIZE) + if (len > PAGE_SIZE) return -ENAMETOOLONG; inode = shmem_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0, VM_NORESERVE); @@ -2551,7 +3139,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s inode->i_op = &shmem_short_symlink_operations; } else { inode_nohighmem(inode); - error = shmem_getpage(inode, 0, &page, SGP_WRITE, NULL); + error = shmem_getpage(inode, 0, &page, SGP_WRITE); if (error) { iput(inode); return error; @@ -2562,7 +3150,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s SetPageUptodate(page); set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); } dir->i_size += BOGO_DIRENT_SIZE; dir->i_ctime = dir->i_mtime = CURRENT_TIME; @@ -2592,7 +3180,7 @@ static const char *shmem_get_link(struct dentry *dentry, return ERR_PTR(-ECHILD); } } else { - error = shmem_getpage(inode, 0, &page, SGP_READ, NULL); + error = shmem_getpage(inode, 0, &page, SGP_READ); if (error) return ERR_PTR(error); unlock_page(page); @@ -2646,20 +3234,21 @@ static int shmem_initxattrs(struct inode *inode, } static int shmem_xattr_handler_get(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - struct shmem_inode_info *info = SHMEM_I(d_inode(dentry)); + struct shmem_inode_info *info = SHMEM_I(inode); name = xattr_full_name(handler, name); return simple_xattr_get(&info->xattrs, name, buffer, size); } static int shmem_xattr_handler_set(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - const void *value, size_t size, int flags) + struct dentry *unused, struct inode *inode, + const char *name, const void *value, + size_t size, int flags) { - struct shmem_inode_info *info = SHMEM_I(d_inode(dentry)); + struct shmem_inode_info *info = SHMEM_I(inode); name = xattr_full_name(handler, name); return simple_xattr_set(&info->xattrs, name, value, size, flags); @@ -2835,7 +3424,7 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo, if (*rest) goto bad_val; sbinfo->max_blocks = - DIV_ROUND_UP(size, PAGE_CACHE_SIZE); + DIV_ROUND_UP(size, PAGE_SIZE); } else if (!strcmp(this_char,"nr_blocks")) { sbinfo->max_blocks = memparse(value, &rest); if (*rest) @@ -2868,11 +3457,24 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo, sbinfo->gid = make_kgid(current_user_ns(), gid); if (!gid_valid(sbinfo->gid)) goto bad_val; +#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE + } else if (!strcmp(this_char, "huge")) { + int huge; + huge = shmem_parse_huge(value); + if (huge < 0) + goto bad_val; + if (!has_transparent_hugepage() && + huge != SHMEM_HUGE_NEVER) + goto bad_val; + sbinfo->huge = huge; +#endif +#ifdef CONFIG_NUMA } else if (!strcmp(this_char,"mpol")) { mpol_put(mpol); mpol = NULL; if (mpol_parse_str(value, &mpol)) goto bad_val; +#endif } else { pr_err("tmpfs: Bad mount option %s\n", this_char); goto error; @@ -2918,6 +3520,7 @@ static int shmem_remount_fs(struct super_block *sb, int *flags, char *data) goto out; error = 0; + sbinfo->huge = config.huge; sbinfo->max_blocks = config.max_blocks; sbinfo->max_inodes = config.max_inodes; sbinfo->free_inodes = config.max_inodes - inodes; @@ -2940,7 +3543,7 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root) if (sbinfo->max_blocks != shmem_default_max_blocks()) seq_printf(seq, ",size=%luk", - sbinfo->max_blocks << (PAGE_CACHE_SHIFT - 10)); + sbinfo->max_blocks << (PAGE_SHIFT - 10)); if (sbinfo->max_inodes != shmem_default_max_inodes()) seq_printf(seq, ",nr_inodes=%lu", sbinfo->max_inodes); if (sbinfo->mode != (S_IRWXUGO | S_ISVTX)) @@ -2951,6 +3554,11 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root) if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID)) seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, sbinfo->gid)); +#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE + /* Rightly or wrongly, show huge mount option unmasked by shmem_huge */ + if (sbinfo->huge) + seq_printf(seq, ",huge=%s", shmem_format_huge(sbinfo->huge)); +#endif shmem_show_mpol(seq, sbinfo->mpol); return 0; } @@ -3080,10 +3688,12 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent) if (percpu_counter_init(&sbinfo->used_blocks, 0, GFP_KERNEL)) goto failed; sbinfo->free_inodes = sbinfo->max_inodes; + spin_lock_init(&sbinfo->shrinklist_lock); + INIT_LIST_HEAD(&sbinfo->shrinklist); sb->s_maxbytes = MAX_LFS_FILESIZE; - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = TMPFS_MAGIC; sb->s_op = &shmem_ops; sb->s_time_gran = 1; @@ -3123,7 +3733,8 @@ static struct inode *shmem_alloc_inode(struct super_block *sb) static void shmem_destroy_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); - kfree(inode->i_link); + if (S_ISLNK(inode->i_mode)) + kfree(inode->i_link); kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); } @@ -3168,6 +3779,7 @@ static const struct address_space_operations shmem_aops = { static const struct file_operations shmem_file_operations = { .mmap = shmem_mmap, + .get_unmapped_area = shmem_get_unmapped_area, #ifdef CONFIG_TMPFS .llseek = shmem_file_llseek, .read_iter = shmem_file_read_iter, @@ -3240,6 +3852,10 @@ static const struct super_operations shmem_ops = { .evict_inode = shmem_evict_inode, .drop_inode = generic_delete_inode, .put_super = shmem_put_super, +#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE + .nr_cached_objects = shmem_unused_huge_count, + .free_cached_objects = shmem_unused_huge_scan, +#endif }; static const struct vm_operations_struct shmem_vm_ops = { @@ -3289,6 +3905,13 @@ int __init shmem_init(void) pr_err("Could not kern_mount tmpfs\n"); goto out1; } + +#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE + if (has_transparent_hugepage() && shmem_huge < SHMEM_HUGE_DENY) + SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge; + else + shmem_huge = 0; /* just in case it was patched */ +#endif return 0; out1: @@ -3300,6 +3923,91 @@ out3: return error; } +#if defined(CONFIG_TRANSPARENT_HUGE_PAGECACHE) && defined(CONFIG_SYSFS) +static ssize_t shmem_enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + int values[] = { + SHMEM_HUGE_ALWAYS, + SHMEM_HUGE_WITHIN_SIZE, + SHMEM_HUGE_ADVISE, + SHMEM_HUGE_NEVER, + SHMEM_HUGE_DENY, + SHMEM_HUGE_FORCE, + }; + int i, count; + + for (i = 0, count = 0; i < ARRAY_SIZE(values); i++) { + const char *fmt = shmem_huge == values[i] ? "[%s] " : "%s "; + + count += sprintf(buf + count, fmt, + shmem_format_huge(values[i])); + } + buf[count - 1] = '\n'; + return count; +} + +static ssize_t shmem_enabled_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + char tmp[16]; + int huge; + + if (count + 1 > sizeof(tmp)) + return -EINVAL; + memcpy(tmp, buf, count); + tmp[count] = '\0'; + if (count && tmp[count - 1] == '\n') + tmp[count - 1] = '\0'; + + huge = shmem_parse_huge(tmp); + if (huge == -EINVAL) + return -EINVAL; + if (!has_transparent_hugepage() && + huge != SHMEM_HUGE_NEVER && huge != SHMEM_HUGE_DENY) + return -EINVAL; + + shmem_huge = huge; + if (shmem_huge < SHMEM_HUGE_DENY) + SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge; + return count; +} + +struct kobj_attribute shmem_enabled_attr = + __ATTR(shmem_enabled, 0644, shmem_enabled_show, shmem_enabled_store); + +bool shmem_huge_enabled(struct vm_area_struct *vma) +{ + struct inode *inode = file_inode(vma->vm_file); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + loff_t i_size; + pgoff_t off; + + if (shmem_huge == SHMEM_HUGE_FORCE) + return true; + if (shmem_huge == SHMEM_HUGE_DENY) + return false; + switch (sbinfo->huge) { + case SHMEM_HUGE_NEVER: + return false; + case SHMEM_HUGE_ALWAYS: + return true; + case SHMEM_HUGE_WITHIN_SIZE: + off = round_up(vma->vm_pgoff, HPAGE_PMD_NR); + i_size = round_up(i_size_read(inode), PAGE_SIZE); + if (i_size >= HPAGE_PMD_SIZE && + i_size >> PAGE_SHIFT >= off) + return true; + case SHMEM_HUGE_ADVISE: + /* TODO: implement fadvise() hints */ + return (vma->vm_flags & VM_HUGEPAGE); + default: + VM_BUG_ON(1); + return false; + } +} +#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE && CONFIG_SYSFS */ + #else /* !CONFIG_SHMEM */ /* @@ -3342,6 +4050,15 @@ void shmem_unlock_mapping(struct address_space *mapping) { } +#ifdef CONFIG_MMU +unsigned long shmem_get_unmapped_area(struct file *file, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); +} +#endif + void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { truncate_inode_pages_range(inode->i_mapping, lstart, lend); @@ -3468,6 +4185,13 @@ int shmem_zero_setup(struct vm_area_struct *vma) fput(vma->vm_file); vma->vm_file = file; vma->vm_ops = &shmem_vm_ops; + + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE) && + ((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) < + (vma->vm_end & HPAGE_PMD_MASK)) { + khugepaged_enter(vma, vma->vm_flags); + } + return 0; } @@ -3495,7 +4219,8 @@ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, int error; BUG_ON(mapping->a_ops != &shmem_aops); - error = shmem_getpage_gfp(inode, index, &page, SGP_CACHE, gfp, NULL); + error = shmem_getpage_gfp(inode, index, &page, SGP_CACHE, + gfp, NULL, NULL); if (error) page = ERR_PTR(error); else diff --git a/mm/slab.c b/mm/slab.c index 17e2848979c5..261147ba156f 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -213,6 +213,11 @@ static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list); static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp); static void cache_reap(struct work_struct *unused); +static inline void fixup_objfreelist_debug(struct kmem_cache *cachep, + void **list); +static inline void fixup_slab_list(struct kmem_cache *cachep, + struct kmem_cache_node *n, struct page *page, + void **list); static int slab_early_init = 1; #define INDEX_NODE kmalloc_index(sizeof(struct kmem_cache_node)) @@ -421,8 +426,6 @@ static struct kmem_cache kmem_cache_boot = { .name = "kmem_cache", }; -#define BAD_ALIEN_MAGIC 0x01020304ul - static DEFINE_PER_CPU(struct delayed_work, slab_reap_work); static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep) @@ -519,22 +522,15 @@ static DEFINE_PER_CPU(unsigned long, slab_reap_node); static void init_reap_node(int cpu) { - int node; - - node = next_node(cpu_to_mem(cpu), node_online_map); - if (node == MAX_NUMNODES) - node = first_node(node_online_map); - - per_cpu(slab_reap_node, cpu) = node; + per_cpu(slab_reap_node, cpu) = next_node_in(cpu_to_mem(cpu), + node_online_map); } static void next_reap_node(void) { int node = __this_cpu_read(slab_reap_node); - node = next_node(node, node_online_map); - if (unlikely(node >= MAX_NUMNODES)) - node = first_node(node_online_map); + node = next_node_in(node, node_online_map); __this_cpu_write(slab_reap_node, node); } @@ -644,7 +640,7 @@ static int transfer_objects(struct array_cache *to, static inline struct alien_cache **alloc_alien_cache(int node, int limit, gfp_t gfp) { - return (struct alien_cache **)BAD_ALIEN_MAGIC; + return NULL; } static inline void free_alien_cache(struct alien_cache **ac_ptr) @@ -850,6 +846,46 @@ static inline gfp_t gfp_exact_node(gfp_t flags) } #endif +static int init_cache_node(struct kmem_cache *cachep, int node, gfp_t gfp) +{ + struct kmem_cache_node *n; + + /* + * Set up the kmem_cache_node for cpu before we can + * begin anything. Make sure some other cpu on this + * node has not already allocated this + */ + n = get_node(cachep, node); + if (n) { + spin_lock_irq(&n->list_lock); + n->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount + + cachep->num; + spin_unlock_irq(&n->list_lock); + + return 0; + } + + n = kmalloc_node(sizeof(struct kmem_cache_node), gfp, node); + if (!n) + return -ENOMEM; + + kmem_cache_node_init(n); + n->next_reap = jiffies + REAPTIMEOUT_NODE + + ((unsigned long)cachep) % REAPTIMEOUT_NODE; + + n->free_limit = + (1 + nr_cpus_node(node)) * cachep->batchcount + cachep->num; + + /* + * The kmem_cache_nodes don't come and go as CPUs + * come and go. slab_mutex is sufficient + * protection here. + */ + cachep->node[node] = n; + + return 0; +} + /* * Allocates and initializes node for a node on each slab cache, used for * either memory or cpu hotplug. If memory is being hot-added, the kmem_cache_node @@ -861,46 +897,82 @@ static inline gfp_t gfp_exact_node(gfp_t flags) */ static int init_cache_node_node(int node) { + int ret; struct kmem_cache *cachep; - struct kmem_cache_node *n; - const size_t memsize = sizeof(struct kmem_cache_node); list_for_each_entry(cachep, &slab_caches, list) { - /* - * Set up the kmem_cache_node for cpu before we can - * begin anything. Make sure some other cpu on this - * node has not already allocated this - */ - n = get_node(cachep, node); - if (!n) { - n = kmalloc_node(memsize, GFP_KERNEL, node); - if (!n) - return -ENOMEM; - kmem_cache_node_init(n); - n->next_reap = jiffies + REAPTIMEOUT_NODE + - ((unsigned long)cachep) % REAPTIMEOUT_NODE; - - /* - * The kmem_cache_nodes don't come and go as CPUs - * come and go. slab_mutex is sufficient - * protection here. - */ - cachep->node[node] = n; - } - - spin_lock_irq(&n->list_lock); - n->free_limit = - (1 + nr_cpus_node(node)) * - cachep->batchcount + cachep->num; - spin_unlock_irq(&n->list_lock); + ret = init_cache_node(cachep, node, GFP_KERNEL); + if (ret) + return ret; } + return 0; } -static inline int slabs_tofree(struct kmem_cache *cachep, - struct kmem_cache_node *n) +static int setup_kmem_cache_node(struct kmem_cache *cachep, + int node, gfp_t gfp, bool force_change) { - return (n->free_objects + cachep->num - 1) / cachep->num; + int ret = -ENOMEM; + struct kmem_cache_node *n; + struct array_cache *old_shared = NULL; + struct array_cache *new_shared = NULL; + struct alien_cache **new_alien = NULL; + LIST_HEAD(list); + + if (use_alien_caches) { + new_alien = alloc_alien_cache(node, cachep->limit, gfp); + if (!new_alien) + goto fail; + } + + if (cachep->shared) { + new_shared = alloc_arraycache(node, + cachep->shared * cachep->batchcount, 0xbaadf00d, gfp); + if (!new_shared) + goto fail; + } + + ret = init_cache_node(cachep, node, gfp); + if (ret) + goto fail; + + n = get_node(cachep, node); + spin_lock_irq(&n->list_lock); + if (n->shared && force_change) { + free_block(cachep, n->shared->entry, + n->shared->avail, node, &list); + n->shared->avail = 0; + } + + if (!n->shared || force_change) { + old_shared = n->shared; + n->shared = new_shared; + new_shared = NULL; + } + + if (!n->alien) { + n->alien = new_alien; + new_alien = NULL; + } + + spin_unlock_irq(&n->list_lock); + slabs_destroy(cachep, &list); + + /* + * To protect lockless access to n->shared during irq disabled context. + * If n->shared isn't NULL in irq disabled context, accessing to it is + * guaranteed to be valid until irq is re-enabled, because it will be + * freed after synchronize_sched(). + */ + if (force_change) + synchronize_sched(); + +fail: + kfree(old_shared); + kfree(new_shared); + free_alien_cache(new_alien); + + return ret; } static void cpuup_canceled(long cpu) @@ -967,14 +1039,13 @@ free_slab: n = get_node(cachep, node); if (!n) continue; - drain_freelist(cachep, n, slabs_tofree(cachep, n)); + drain_freelist(cachep, n, INT_MAX); } } static int cpuup_prepare(long cpu) { struct kmem_cache *cachep; - struct kmem_cache_node *n = NULL; int node = cpu_to_mem(cpu); int err; @@ -993,44 +1064,9 @@ static int cpuup_prepare(long cpu) * array caches */ list_for_each_entry(cachep, &slab_caches, list) { - struct array_cache *shared = NULL; - struct alien_cache **alien = NULL; - - if (cachep->shared) { - shared = alloc_arraycache(node, - cachep->shared * cachep->batchcount, - 0xbaadf00d, GFP_KERNEL); - if (!shared) - goto bad; - } - if (use_alien_caches) { - alien = alloc_alien_cache(node, cachep->limit, GFP_KERNEL); - if (!alien) { - kfree(shared); - goto bad; - } - } - n = get_node(cachep, node); - BUG_ON(!n); - - spin_lock_irq(&n->list_lock); - if (!n->shared) { - /* - * We are serialised from CPU_DEAD or - * CPU_UP_CANCELLED by the cpucontrol lock - */ - n->shared = shared; - shared = NULL; - } -#ifdef CONFIG_NUMA - if (!n->alien) { - n->alien = alien; - alien = NULL; - } -#endif - spin_unlock_irq(&n->list_lock); - kfree(shared); - free_alien_cache(alien); + err = setup_kmem_cache_node(cachep, node, GFP_KERNEL, false); + if (err) + goto bad; } return 0; @@ -1119,7 +1155,7 @@ static int __meminit drain_cache_node_node(int node) if (!n) continue; - drain_freelist(cachep, n, slabs_tofree(cachep, n)); + drain_freelist(cachep, n, INT_MAX); if (!list_empty(&n->slabs_full) || !list_empty(&n->slabs_partial)) { @@ -1212,7 +1248,7 @@ void __init kmem_cache_init(void) sizeof(struct rcu_head)); kmem_cache = &kmem_cache_boot; - if (num_possible_nodes() == 1) + if (!IS_ENABLED(CONFIG_NUMA) || num_possible_nodes() == 1) use_alien_caches = 0; for (i = 0; i < NUM_INIT_LISTS; i++) @@ -1781,7 +1817,7 @@ static size_t calculate_slab_order(struct kmem_cache *cachep, /* * Needed to avoid possible looping condition - * in cache_grow() + * in cache_grow_begin() */ if (OFF_SLAB(freelist_cache)) continue; @@ -1841,7 +1877,7 @@ static struct array_cache __percpu *alloc_kmem_cache_cpus( return cpu_cache; } -static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) +static int __ref setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) { if (slab_state >= FULL) return enable_cpucache(cachep, gfp); @@ -2138,7 +2174,7 @@ done: cachep->freelist_size = cachep->num * sizeof(freelist_idx_t); cachep->flags = flags; cachep->allocflags = __GFP_COMP; - if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA)) + if (flags & SLAB_CACHE_DMA) cachep->allocflags |= GFP_DMA; cachep->size = size; cachep->reciprocal_buffer_size = reciprocal_value(size); @@ -2180,6 +2216,11 @@ static void check_irq_on(void) BUG_ON(irqs_disabled()); } +static void check_mutex_acquired(void) +{ + BUG_ON(!mutex_is_locked(&slab_mutex)); +} + static void check_spinlock_acquired(struct kmem_cache *cachep) { #ifdef CONFIG_SMP @@ -2199,13 +2240,27 @@ static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node) #else #define check_irq_off() do { } while(0) #define check_irq_on() do { } while(0) +#define check_mutex_acquired() do { } while(0) #define check_spinlock_acquired(x) do { } while(0) #define check_spinlock_acquired_node(x, y) do { } while(0) #endif -static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n, - struct array_cache *ac, - int force, int node); +static void drain_array_locked(struct kmem_cache *cachep, struct array_cache *ac, + int node, bool free_all, struct list_head *list) +{ + int tofree; + + if (!ac || !ac->avail) + return; + + tofree = free_all ? ac->avail : (ac->limit + 4) / 5; + if (tofree > ac->avail) + tofree = (ac->avail + 1) / 2; + + free_block(cachep, ac->entry, tofree, node, list); + ac->avail -= tofree; + memmove(ac->entry, &(ac->entry[tofree]), sizeof(void *) * ac->avail); +} static void do_drain(void *arg) { @@ -2229,6 +2284,7 @@ static void drain_cpu_caches(struct kmem_cache *cachep) { struct kmem_cache_node *n; int node; + LIST_HEAD(list); on_each_cpu(do_drain, cachep, 1); check_irq_on(); @@ -2236,8 +2292,13 @@ static void drain_cpu_caches(struct kmem_cache *cachep) if (n->alien) drain_alien_cache(cachep, n->alien); - for_each_kmem_cache_node(cachep, node, n) - drain_array(cachep, n, n->shared, 1, node); + for_each_kmem_cache_node(cachep, node, n) { + spin_lock_irq(&n->list_lock); + drain_array_locked(cachep, n->shared, node, true, &list); + spin_unlock_irq(&n->list_lock); + + slabs_destroy(cachep, &list); + } } /* @@ -2288,7 +2349,7 @@ int __kmem_cache_shrink(struct kmem_cache *cachep, bool deactivate) check_irq_on(); for_each_kmem_cache_node(cachep, node, n) { - drain_freelist(cachep, n, slabs_tofree(cachep, n)); + drain_freelist(cachep, n, INT_MAX); ret += !list_empty(&n->slabs_full) || !list_empty(&n->slabs_partial); @@ -2306,6 +2367,8 @@ void __kmem_cache_release(struct kmem_cache *cachep) int i; struct kmem_cache_node *n; + cache_random_seq_destroy(cachep); + free_percpu(cachep->cpu_cache); /* NUMA: free the node structures */ @@ -2412,39 +2475,147 @@ static void cache_init_objs_debug(struct kmem_cache *cachep, struct page *page) #endif } +#ifdef CONFIG_SLAB_FREELIST_RANDOM +/* Hold information during a freelist initialization */ +union freelist_init_state { + struct { + unsigned int pos; + unsigned int *list; + unsigned int count; + unsigned int rand; + }; + struct rnd_state rnd_state; +}; + +/* + * Initialize the state based on the randomization methode available. + * return true if the pre-computed list is available, false otherwize. + */ +static bool freelist_state_initialize(union freelist_init_state *state, + struct kmem_cache *cachep, + unsigned int count) +{ + bool ret; + unsigned int rand; + + /* Use best entropy available to define a random shift */ + rand = get_random_int(); + + /* Use a random state if the pre-computed list is not available */ + if (!cachep->random_seq) { + prandom_seed_state(&state->rnd_state, rand); + ret = false; + } else { + state->list = cachep->random_seq; + state->count = count; + state->pos = 0; + state->rand = rand; + ret = true; + } + return ret; +} + +/* Get the next entry on the list and randomize it using a random shift */ +static freelist_idx_t next_random_slot(union freelist_init_state *state) +{ + return (state->list[state->pos++] + state->rand) % state->count; +} + +/* Swap two freelist entries */ +static void swap_free_obj(struct page *page, unsigned int a, unsigned int b) +{ + swap(((freelist_idx_t *)page->freelist)[a], + ((freelist_idx_t *)page->freelist)[b]); +} + +/* + * Shuffle the freelist initialization state based on pre-computed lists. + * return true if the list was successfully shuffled, false otherwise. + */ +static bool shuffle_freelist(struct kmem_cache *cachep, struct page *page) +{ + unsigned int objfreelist = 0, i, rand, count = cachep->num; + union freelist_init_state state; + bool precomputed; + + if (count < 2) + return false; + + precomputed = freelist_state_initialize(&state, cachep, count); + + /* Take a random entry as the objfreelist */ + if (OBJFREELIST_SLAB(cachep)) { + if (!precomputed) + objfreelist = count - 1; + else + objfreelist = next_random_slot(&state); + page->freelist = index_to_obj(cachep, page, objfreelist) + + obj_offset(cachep); + count--; + } + + /* + * On early boot, generate the list dynamically. + * Later use a pre-computed list for speed. + */ + if (!precomputed) { + for (i = 0; i < count; i++) + set_free_obj(page, i, i); + + /* Fisher-Yates shuffle */ + for (i = count - 1; i > 0; i--) { + rand = prandom_u32_state(&state.rnd_state); + rand %= (i + 1); + swap_free_obj(page, i, rand); + } + } else { + for (i = 0; i < count; i++) + set_free_obj(page, i, next_random_slot(&state)); + } + + if (OBJFREELIST_SLAB(cachep)) + set_free_obj(page, cachep->num - 1, objfreelist); + + return true; +} +#else +static inline bool shuffle_freelist(struct kmem_cache *cachep, + struct page *page) +{ + return false; +} +#endif /* CONFIG_SLAB_FREELIST_RANDOM */ + static void cache_init_objs(struct kmem_cache *cachep, struct page *page) { int i; void *objp; + bool shuffled; cache_init_objs_debug(cachep, page); - if (OBJFREELIST_SLAB(cachep)) { + /* Try to randomize the freelist if enabled */ + shuffled = shuffle_freelist(cachep, page); + + if (!shuffled && OBJFREELIST_SLAB(cachep)) { page->freelist = index_to_obj(cachep, page, cachep->num - 1) + obj_offset(cachep); } for (i = 0; i < cachep->num; i++) { + objp = index_to_obj(cachep, page, i); + kasan_init_slab_obj(cachep, objp); + /* constructor could break poison info */ if (DEBUG == 0 && cachep->ctor) { - objp = index_to_obj(cachep, page, i); kasan_unpoison_object_data(cachep, objp); cachep->ctor(objp); kasan_poison_object_data(cachep, objp); } - set_free_obj(page, i, i); - } -} - -static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags) -{ - if (CONFIG_ZONE_DMA_FLAG) { - if (flags & GFP_DMA) - BUG_ON(!(cachep->allocflags & GFP_DMA)); - else - BUG_ON(cachep->allocflags & GFP_DMA); + if (!shuffled) + set_free_obj(page, i, i); } } @@ -2502,61 +2673,58 @@ static void slab_map_pages(struct kmem_cache *cache, struct page *page, * Grow (by 1) the number of slabs within a cache. This is called by * kmem_cache_alloc() when there are no active objs left in a cache. */ -static int cache_grow(struct kmem_cache *cachep, - gfp_t flags, int nodeid, struct page *page) +static struct page *cache_grow_begin(struct kmem_cache *cachep, + gfp_t flags, int nodeid) { void *freelist; size_t offset; gfp_t local_flags; + int page_node; struct kmem_cache_node *n; + struct page *page; /* * Be lazy and only check for valid flags here, keeping it out of the * critical path in kmem_cache_alloc(). */ if (unlikely(flags & GFP_SLAB_BUG_MASK)) { - pr_emerg("gfp: %u\n", flags & GFP_SLAB_BUG_MASK); - BUG(); + gfp_t invalid_mask = flags & GFP_SLAB_BUG_MASK; + flags &= ~GFP_SLAB_BUG_MASK; + pr_warn("Unexpected gfp: %#x (%pGg). Fixing up to gfp: %#x (%pGg). Fix your code!\n", + invalid_mask, &invalid_mask, flags, &flags); + dump_stack(); } local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK); - /* Take the node list lock to change the colour_next on this node */ check_irq_off(); - n = get_node(cachep, nodeid); - spin_lock(&n->list_lock); - - /* Get colour for the slab, and cal the next value. */ - offset = n->colour_next; - n->colour_next++; - if (n->colour_next >= cachep->colour) - n->colour_next = 0; - spin_unlock(&n->list_lock); - - offset *= cachep->colour_off; - if (gfpflags_allow_blocking(local_flags)) local_irq_enable(); /* - * The test for missing atomic flag is performed here, rather than - * the more obvious place, simply to reduce the critical path length - * in kmem_cache_alloc(). If a caller is seriously mis-behaving they - * will eventually be caught here (where it matters). - */ - kmem_flagcheck(cachep, flags); - - /* * Get mem for the objs. Attempt to allocate a physical page from * 'nodeid'. */ - if (!page) - page = kmem_getpages(cachep, local_flags, nodeid); + page = kmem_getpages(cachep, local_flags, nodeid); if (!page) goto failed; + page_node = page_to_nid(page); + n = get_node(cachep, page_node); + + /* Get colour for the slab, and cal the next value. */ + n->colour_next++; + if (n->colour_next >= cachep->colour) + n->colour_next = 0; + + offset = n->colour_next; + if (offset >= cachep->colour) + offset = 0; + + offset *= cachep->colour_off; + /* Get slab management. */ freelist = alloc_slabmgmt(cachep, page, offset, - local_flags & ~GFP_CONSTRAINT_MASK, nodeid); + local_flags & ~GFP_CONSTRAINT_MASK, page_node); if (OFF_SLAB(cachep) && !freelist) goto opps1; @@ -2567,21 +2735,40 @@ static int cache_grow(struct kmem_cache *cachep, if (gfpflags_allow_blocking(local_flags)) local_irq_disable(); - check_irq_off(); - spin_lock(&n->list_lock); - /* Make slab active. */ - list_add_tail(&page->lru, &(n->slabs_free)); - STATS_INC_GROWN(cachep); - n->free_objects += cachep->num; - spin_unlock(&n->list_lock); - return 1; + return page; + opps1: kmem_freepages(cachep, page); failed: if (gfpflags_allow_blocking(local_flags)) local_irq_disable(); - return 0; + return NULL; +} + +static void cache_grow_end(struct kmem_cache *cachep, struct page *page) +{ + struct kmem_cache_node *n; + void *list = NULL; + + check_irq_off(); + + if (!page) + return; + + INIT_LIST_HEAD(&page->lru); + n = get_node(cachep, page_to_nid(page)); + + spin_lock(&n->list_lock); + if (!page->active) + list_add_tail(&page->lru, &(n->slabs_free)); + else + fixup_slab_list(cachep, n, page, &list); + STATS_INC_GROWN(cachep); + n->free_objects += cachep->num - page->active; + spin_unlock(&n->list_lock); + + fixup_objfreelist_debug(cachep, &list); } #if DEBUG @@ -2785,18 +2972,42 @@ static noinline void *cache_alloc_pfmemalloc(struct kmem_cache *cachep, return obj; } +/* + * Slab list should be fixed up by fixup_slab_list() for existing slab + * or cache_grow_end() for new slab + */ +static __always_inline int alloc_block(struct kmem_cache *cachep, + struct array_cache *ac, struct page *page, int batchcount) +{ + /* + * There must be at least one object available for + * allocation. + */ + BUG_ON(page->active >= cachep->num); + + while (page->active < cachep->num && batchcount--) { + STATS_INC_ALLOCED(cachep); + STATS_INC_ACTIVE(cachep); + STATS_SET_HIGH(cachep); + + ac->entry[ac->avail++] = slab_get_obj(cachep, page); + } + + return batchcount; +} + static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags) { int batchcount; struct kmem_cache_node *n; - struct array_cache *ac; + struct array_cache *ac, *shared; int node; void *list = NULL; + struct page *page; check_irq_off(); node = numa_mem_id(); -retry: ac = cpu_cache_get(cachep); batchcount = ac->batchcount; if (!ac->touched && batchcount > BATCHREFILL_LIMIT) { @@ -2810,16 +3021,20 @@ retry: n = get_node(cachep, node); BUG_ON(ac->avail > 0 || !n); + shared = READ_ONCE(n->shared); + if (!n->free_objects && (!shared || !shared->avail)) + goto direct_grow; + spin_lock(&n->list_lock); + shared = READ_ONCE(n->shared); /* See if we can refill from the shared array */ - if (n->shared && transfer_objects(ac, n->shared, batchcount)) { - n->shared->touched = 1; + if (shared && transfer_objects(ac, shared, batchcount)) { + shared->touched = 1; goto alloc_done; } while (batchcount > 0) { - struct page *page; /* Get slab alloc is to come from. */ page = get_first_slab(n, false); if (!page) @@ -2827,21 +3042,7 @@ retry: check_spinlock_acquired(cachep); - /* - * The slab was either on partial or free list so - * there must be at least one object available for - * allocation. - */ - BUG_ON(page->active >= cachep->num); - - while (page->active < cachep->num && batchcount--) { - STATS_INC_ALLOCED(cachep); - STATS_INC_ACTIVE(cachep); - STATS_SET_HIGH(cachep); - - ac->entry[ac->avail++] = slab_get_obj(cachep, page); - } - + batchcount = alloc_block(cachep, ac, page, batchcount); fixup_slab_list(cachep, n, page, &list); } @@ -2851,9 +3052,8 @@ alloc_done: spin_unlock(&n->list_lock); fixup_objfreelist_debug(cachep, &list); +direct_grow: if (unlikely(!ac->avail)) { - int x; - /* Check if we can use obj in pfmemalloc slab */ if (sk_memalloc_socks()) { void *obj = cache_alloc_pfmemalloc(cachep, n, flags); @@ -2862,18 +3062,19 @@ alloc_done: return obj; } - x = cache_grow(cachep, gfp_exact_node(flags), node, NULL); + page = cache_grow_begin(cachep, gfp_exact_node(flags), node); - /* cache_grow can reenable interrupts, then ac could change. */ + /* + * cache_grow_begin() can reenable interrupts, + * then ac could change. + */ ac = cpu_cache_get(cachep); - node = numa_mem_id(); + if (!ac->avail && page) + alloc_block(cachep, ac, page, batchcount); + cache_grow_end(cachep, page); - /* no objects in sight? abort */ - if (!x && ac->avail == 0) + if (!ac->avail) return NULL; - - if (!ac->avail) /* objects refilled by interrupt? */ - goto retry; } ac->touched = 1; @@ -2884,9 +3085,6 @@ static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep, gfp_t flags) { might_sleep_if(gfpflags_allow_blocking(flags)); -#if DEBUG - kmem_flagcheck(cachep, flags); -#endif } #if DEBUG @@ -2998,19 +3196,17 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags) static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags) { struct zonelist *zonelist; - gfp_t local_flags; struct zoneref *z; struct zone *zone; enum zone_type high_zoneidx = gfp_zone(flags); void *obj = NULL; + struct page *page; int nid; unsigned int cpuset_mems_cookie; if (flags & __GFP_THISNODE) return NULL; - local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK); - retry_cpuset: cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = node_zonelist(mempolicy_slab_node(), flags); @@ -3040,33 +3236,19 @@ retry: * We may trigger various forms of reclaim on the allowed * set and go into memory reserves if necessary. */ - struct page *page; - - if (gfpflags_allow_blocking(local_flags)) - local_irq_enable(); - kmem_flagcheck(cache, flags); - page = kmem_getpages(cache, local_flags, numa_mem_id()); - if (gfpflags_allow_blocking(local_flags)) - local_irq_disable(); + page = cache_grow_begin(cache, flags, numa_mem_id()); + cache_grow_end(cache, page); if (page) { + nid = page_to_nid(page); + obj = ____cache_alloc_node(cache, + gfp_exact_node(flags), nid); + /* - * Insert into the appropriate per node queues + * Another processor may allocate the objects in + * the slab since we are not holding any locks. */ - nid = page_to_nid(page); - if (cache_grow(cache, flags, nid, page)) { - obj = ____cache_alloc_node(cache, - gfp_exact_node(flags), nid); - if (!obj) - /* - * Another processor may allocate the - * objects in the slab since we are - * not holding any locks. - */ - goto retry; - } else { - /* cache_grow already freed obj */ - obj = NULL; - } + if (!obj) + goto retry; } } @@ -3083,15 +3265,13 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, { struct page *page; struct kmem_cache_node *n; - void *obj; + void *obj = NULL; void *list = NULL; - int x; VM_BUG_ON(nodeid < 0 || nodeid >= MAX_NUMNODES); n = get_node(cachep, nodeid); BUG_ON(!n); -retry: check_irq_off(); spin_lock(&n->list_lock); page = get_first_slab(n, false); @@ -3113,18 +3293,18 @@ retry: spin_unlock(&n->list_lock); fixup_objfreelist_debug(cachep, &list); - goto done; + return obj; must_grow: spin_unlock(&n->list_lock); - x = cache_grow(cachep, gfp_exact_node(flags), nodeid, NULL); - if (x) - goto retry; - - return fallback_alloc(cachep, flags); + page = cache_grow_begin(cachep, gfp_exact_node(flags), nodeid); + if (page) { + /* This slab isn't counted yet so don't update free_objects */ + obj = slab_get_obj(cachep, page); + } + cache_grow_end(cachep, page); -done: - return obj; + return obj ? obj : fallback_alloc(cachep, flags); } static __always_inline void * @@ -3242,6 +3422,9 @@ static void free_block(struct kmem_cache *cachep, void **objpp, { int i; struct kmem_cache_node *n = get_node(cachep, node); + struct page *page; + + n->free_objects += nr_objects; for (i = 0; i < nr_objects; i++) { void *objp; @@ -3254,17 +3437,11 @@ static void free_block(struct kmem_cache *cachep, void **objpp, check_spinlock_acquired_node(cachep, node); slab_put_obj(cachep, page, objp); STATS_DEC_ACTIVE(cachep); - n->free_objects++; /* fixup slab chains */ - if (page->active == 0) { - if (n->free_objects > n->free_limit) { - n->free_objects -= cachep->num; - list_add_tail(&page->lru, list); - } else { - list_add(&page->lru, &n->slabs_free); - } - } else { + if (page->active == 0) + list_add(&page->lru, &n->slabs_free); + else { /* Unconditionally move a slab to the end of the * partial list on free - maximum time for the * other objects to be freed, too. @@ -3272,6 +3449,13 @@ static void free_block(struct kmem_cache *cachep, void **objpp, list_add_tail(&page->lru, &n->slabs_partial); } } + + while (n->free_objects > n->free_limit && !list_empty(&n->slabs_free)) { + n->free_objects -= cachep->num; + + page = list_last_entry(&n->slabs_free, struct page, lru); + list_move(&page->lru, list); + } } static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac) @@ -3327,9 +3511,17 @@ free_done: static inline void __cache_free(struct kmem_cache *cachep, void *objp, unsigned long caller) { - struct array_cache *ac = cpu_cache_get(cachep); + /* Put the object into the quarantine, don't touch it for now. */ + if (kasan_slab_free(cachep, objp)) + return; - kasan_slab_free(cachep, objp); + ___cache_free(cachep, objp, caller); +} + +void ___cache_free(struct kmem_cache *cachep, void *objp, + unsigned long caller) +{ + struct array_cache *ac = cpu_cache_get(cachep); check_irq_off(); kmemleak_free_recursive(objp, cachep->flags); @@ -3645,72 +3837,19 @@ EXPORT_SYMBOL(kfree); /* * This initializes kmem_cache_node or resizes various caches for all nodes. */ -static int alloc_kmem_cache_node(struct kmem_cache *cachep, gfp_t gfp) +static int setup_kmem_cache_nodes(struct kmem_cache *cachep, gfp_t gfp) { + int ret; int node; struct kmem_cache_node *n; - struct array_cache *new_shared; - struct alien_cache **new_alien = NULL; for_each_online_node(node) { - - if (use_alien_caches) { - new_alien = alloc_alien_cache(node, cachep->limit, gfp); - if (!new_alien) - goto fail; - } - - new_shared = NULL; - if (cachep->shared) { - new_shared = alloc_arraycache(node, - cachep->shared*cachep->batchcount, - 0xbaadf00d, gfp); - if (!new_shared) { - free_alien_cache(new_alien); - goto fail; - } - } - - n = get_node(cachep, node); - if (n) { - struct array_cache *shared = n->shared; - LIST_HEAD(list); - - spin_lock_irq(&n->list_lock); - - if (shared) - free_block(cachep, shared->entry, - shared->avail, node, &list); - - n->shared = new_shared; - if (!n->alien) { - n->alien = new_alien; - new_alien = NULL; - } - n->free_limit = (1 + nr_cpus_node(node)) * - cachep->batchcount + cachep->num; - spin_unlock_irq(&n->list_lock); - slabs_destroy(cachep, &list); - kfree(shared); - free_alien_cache(new_alien); - continue; - } - n = kmalloc_node(sizeof(struct kmem_cache_node), gfp, node); - if (!n) { - free_alien_cache(new_alien); - kfree(new_shared); + ret = setup_kmem_cache_node(cachep, node, gfp, true); + if (ret) goto fail; - } - kmem_cache_node_init(n); - n->next_reap = jiffies + REAPTIMEOUT_NODE + - ((unsigned long)cachep) % REAPTIMEOUT_NODE; - n->shared = new_shared; - n->alien = new_alien; - n->free_limit = (1 + nr_cpus_node(node)) * - cachep->batchcount + cachep->num; - cachep->node[node] = n; } + return 0; fail: @@ -3752,7 +3891,7 @@ static int __do_tune_cpucache(struct kmem_cache *cachep, int limit, cachep->shared = shared; if (!prev) - goto alloc_node; + goto setup_node; for_each_online_cpu(cpu) { LIST_HEAD(list); @@ -3769,8 +3908,8 @@ static int __do_tune_cpucache(struct kmem_cache *cachep, int limit, } free_percpu(prev); -alloc_node: - return alloc_kmem_cache_node(cachep, gfp); +setup_node: + return setup_kmem_cache_nodes(cachep, gfp); } static int do_tune_cpucache(struct kmem_cache *cachep, int limit, @@ -3804,6 +3943,10 @@ static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp) int shared = 0; int batchcount = 0; + err = cache_random_seq_create(cachep, cachep->num, gfp); + if (err) + goto end; + if (!is_root_cache(cachep)) { struct kmem_cache *root = memcg_root_cache(cachep); limit = root->limit; @@ -3857,6 +4000,7 @@ static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp) batchcount = (limit + 1) / 2; skip_setup: err = do_tune_cpucache(cachep, limit, batchcount, shared, gfp); +end: if (err) pr_err("enable_cpucache failed for %s, error %d\n", cachep->name, -err); @@ -3869,29 +4013,26 @@ skip_setup: * if drain_array() is used on the shared array. */ static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n, - struct array_cache *ac, int force, int node) + struct array_cache *ac, int node) { LIST_HEAD(list); - int tofree; + + /* ac from n->shared can be freed if we don't hold the slab_mutex. */ + check_mutex_acquired(); if (!ac || !ac->avail) return; - if (ac->touched && !force) { + + if (ac->touched) { ac->touched = 0; - } else { - spin_lock_irq(&n->list_lock); - if (ac->avail) { - tofree = force ? ac->avail : (ac->limit + 4) / 5; - if (tofree > ac->avail) - tofree = (ac->avail + 1) / 2; - free_block(cachep, ac->entry, tofree, node, &list); - ac->avail -= tofree; - memmove(ac->entry, &(ac->entry[tofree]), - sizeof(void *) * ac->avail); - } - spin_unlock_irq(&n->list_lock); - slabs_destroy(cachep, &list); + return; } + + spin_lock_irq(&n->list_lock); + drain_array_locked(cachep, ac, node, false, &list); + spin_unlock_irq(&n->list_lock); + + slabs_destroy(cachep, &list); } /** @@ -3929,7 +4070,7 @@ static void cache_reap(struct work_struct *w) reap_alien(searchp, n); - drain_array(searchp, n, cpu_cache_get(searchp), 0, node); + drain_array(searchp, n, cpu_cache_get(searchp), node); /* * These are racy checks but it does not matter @@ -3940,7 +4081,7 @@ static void cache_reap(struct work_struct *w) n->next_reap = jiffies + REAPTIMEOUT_NODE; - drain_array(searchp, n, n->shared, 0, node); + drain_array(searchp, n, n->shared, node); if (n->free_touched) n->free_touched = 0; @@ -4324,7 +4465,7 @@ size_t ksize(const void *objp) /* We assume that ksize callers could use the whole allocated area, * so we need to unpoison this area. */ - kasan_krealloc(objp, size, GFP_NOWAIT); + kasan_unpoison_shadow(objp, size); return size; } diff --git a/mm/slab.h b/mm/slab.h index 5969769fbee6..9653f2e2591a 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -42,6 +42,7 @@ struct kmem_cache { #include <linux/kmemcheck.h> #include <linux/kasan.h> #include <linux/kmemleak.h> +#include <linux/random.h> /* * State of the slab allocator. @@ -253,8 +254,7 @@ static __always_inline int memcg_charge_slab(struct page *page, if (is_root_cache(s)) return 0; - ret = __memcg_kmem_charge_memcg(page, gfp, order, - s->memcg_params.memcg); + ret = memcg_kmem_charge_memcg(page, gfp, order, s->memcg_params.memcg); if (ret) return ret; @@ -268,6 +268,9 @@ static __always_inline int memcg_charge_slab(struct page *page, static __always_inline void memcg_uncharge_slab(struct page *page, int order, struct kmem_cache *s) { + if (!memcg_kmem_enabled()) + return; + memcg_kmem_update_page_stat(page, (s->flags & SLAB_RECLAIM_ACCOUNT) ? MEMCG_SLAB_RECLAIMABLE : MEMCG_SLAB_UNRECLAIMABLE, @@ -366,6 +369,8 @@ static inline size_t slab_ksize(const struct kmem_cache *s) if (s->flags & (SLAB_RED_ZONE | SLAB_POISON)) return s->object_size; # endif + if (s->flags & SLAB_KASAN) + return s->object_size; /* * If we have the need to store the freelist pointer * back there or track user information then we can @@ -390,7 +395,11 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, if (should_failslab(s, flags)) return NULL; - return memcg_kmem_get_cache(s, flags); + if (memcg_kmem_enabled() && + ((flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT))) + return memcg_kmem_get_cache(s); + + return s; } static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, @@ -407,7 +416,9 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, s->flags, flags); kasan_slab_alloc(s, object, flags); } - memcg_kmem_put_cache(s); + + if (memcg_kmem_enabled()) + memcg_kmem_put_cache(s); } #ifndef CONFIG_SLOB @@ -462,4 +473,19 @@ void *slab_next(struct seq_file *m, void *p, loff_t *pos); void slab_stop(struct seq_file *m, void *p); int memcg_slab_show(struct seq_file *m, void *p); +void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr); + +#ifdef CONFIG_SLAB_FREELIST_RANDOM +int cache_random_seq_create(struct kmem_cache *cachep, unsigned int count, + gfp_t gfp); +void cache_random_seq_destroy(struct kmem_cache *cachep); +#else +static inline int cache_random_seq_create(struct kmem_cache *cachep, + unsigned int count, gfp_t gfp) +{ + return 0; +} +static inline void cache_random_seq_destroy(struct kmem_cache *cachep) { } +#endif /* CONFIG_SLAB_FREELIST_RANDOM */ + #endif /* MM_SLAB_H */ diff --git a/mm/slab_common.c b/mm/slab_common.c index 3239bfd758e6..71f0b28a1bec 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -526,8 +526,8 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg, goto out_unlock; cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf)); - cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, - css->id, memcg_name_buf); + cache_name = kasprintf(GFP_KERNEL, "%s(%llu:%s)", root_cache->name, + css->serial_nr, memcg_name_buf); if (!cache_name) goto out_unlock; @@ -715,6 +715,7 @@ void kmem_cache_destroy(struct kmem_cache *s) get_online_cpus(); get_online_mems(); + kasan_cache_destroy(s); mutex_lock(&slab_mutex); s->refcount--; @@ -753,6 +754,7 @@ int kmem_cache_shrink(struct kmem_cache *cachep) get_online_cpus(); get_online_mems(); + kasan_cache_shrink(cachep); ret = __kmem_cache_shrink(cachep, false); put_online_mems(); put_online_cpus(); @@ -1010,7 +1012,7 @@ void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) struct page *page; flags |= __GFP_COMP; - page = alloc_kmem_pages(flags, order); + page = alloc_pages(flags, order); ret = page ? page_address(page) : NULL; kmemleak_alloc(ret, size, 1, flags); kasan_kmalloc_large(ret, size, flags); @@ -1028,6 +1030,53 @@ void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) EXPORT_SYMBOL(kmalloc_order_trace); #endif +#ifdef CONFIG_SLAB_FREELIST_RANDOM +/* Randomize a generic freelist */ +static void freelist_randomize(struct rnd_state *state, unsigned int *list, + size_t count) +{ + size_t i; + unsigned int rand; + + for (i = 0; i < count; i++) + list[i] = i; + + /* Fisher-Yates shuffle */ + for (i = count - 1; i > 0; i--) { + rand = prandom_u32_state(state); + rand %= (i + 1); + swap(list[i], list[rand]); + } +} + +/* Create a random sequence per cache */ +int cache_random_seq_create(struct kmem_cache *cachep, unsigned int count, + gfp_t gfp) +{ + struct rnd_state state; + + if (count < 2 || cachep->random_seq) + return 0; + + cachep->random_seq = kcalloc(count, sizeof(unsigned int), gfp); + if (!cachep->random_seq) + return -ENOMEM; + + /* Get best entropy at this stage of boot */ + prandom_seed_state(&state, get_random_long()); + + freelist_randomize(&state, cachep->random_seq, count); + return 0; +} + +/* Destroy the per-cache random freelist sequence */ +void cache_random_seq_destroy(struct kmem_cache *cachep) +{ + kfree(cachep->random_seq); + cachep->random_seq = NULL; +} +#endif /* CONFIG_SLAB_FREELIST_RANDOM */ + #ifdef CONFIG_SLABINFO #ifdef CONFIG_SLAB diff --git a/mm/slub.c b/mm/slub.c index 4dbb109eb8cd..850737bdfbd8 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -124,7 +124,7 @@ static inline int kmem_cache_debug(struct kmem_cache *s) #endif } -static inline void *fixup_red_left(struct kmem_cache *s, void *p) +void *fixup_red_left(struct kmem_cache *s, void *p) { if (kmem_cache_debug(s) && s->flags & SLAB_RED_ZONE) p += s->red_left_pad; @@ -329,8 +329,8 @@ static inline void set_page_slub_counters(struct page *page, unsigned long count tmp.counters = counters_new; /* * page->counters can cover frozen/inuse/objects as well - * as page->_count. If we assign to ->counters directly - * we run the risk of losing updates to page->_count, so + * as page->_refcount. If we assign to ->counters directly + * we run the risk of losing updates to page->_refcount, so * be careful and only assign to the fields we need. */ page->frozen = tmp.frozen; @@ -454,8 +454,6 @@ static inline void *restore_red_left(struct kmem_cache *s, void *p) */ #if defined(CONFIG_SLUB_DEBUG_ON) static int slub_debug = DEBUG_DEFAULT_FLAGS; -#elif defined(CONFIG_KASAN) -static int slub_debug = SLAB_STORE_USER; #else static int slub_debug; #endif @@ -660,6 +658,8 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) if (s->flags & SLAB_STORE_USER) off += 2 * sizeof(struct track); + off += kasan_metadata_size(s); + if (off != size_from_object(s)) /* Beginning of the filler is the free pointer */ print_section("Padding ", p + off, size_from_object(s) - off); @@ -787,6 +787,8 @@ static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p) /* We also have user information there */ off += 2 * sizeof(struct track); + off += kasan_metadata_size(s); + if (size_from_object(s) == off) return 1; @@ -1322,8 +1324,10 @@ static inline void kfree_hook(const void *x) kasan_kfree_large(x); } -static inline void slab_free_hook(struct kmem_cache *s, void *x) +static inline void *slab_free_hook(struct kmem_cache *s, void *x) { + void *freeptr; + kmemleak_free_recursive(x, s->flags); /* @@ -1344,7 +1348,13 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) if (!(s->flags & SLAB_DEBUG_OBJECTS)) debug_check_no_obj_freed(x, s->object_size); + freeptr = get_freepointer(s, x); + /* + * kasan_slab_free() may put x into memory quarantine, delaying its + * reuse. In this case the object's freelist pointer is changed. + */ kasan_slab_free(s, x); + return freeptr; } static inline void slab_free_freelist_hook(struct kmem_cache *s, @@ -1362,11 +1372,11 @@ static inline void slab_free_freelist_hook(struct kmem_cache *s, void *object = head; void *tail_obj = tail ? : head; + void *freeptr; do { - slab_free_hook(s, object); - } while ((object != tail_obj) && - (object = get_freepointer(s, object))); + freeptr = slab_free_hook(s, object); + } while ((object != tail_obj) && (object = freeptr)); #endif } @@ -1374,6 +1384,7 @@ static void setup_object(struct kmem_cache *s, struct page *page, void *object) { setup_object_debug(s, page, object); + kasan_init_slab_obj(s, object); if (unlikely(s->ctor)) { kasan_unpoison_object_data(s, object); s->ctor(object); @@ -1405,6 +1416,109 @@ static inline struct page *alloc_slab_page(struct kmem_cache *s, return page; } +#ifdef CONFIG_SLAB_FREELIST_RANDOM +/* Pre-initialize the random sequence cache */ +static int init_cache_random_seq(struct kmem_cache *s) +{ + int err; + unsigned long i, count = oo_objects(s->oo); + + err = cache_random_seq_create(s, count, GFP_KERNEL); + if (err) { + pr_err("SLUB: Unable to initialize free list for %s\n", + s->name); + return err; + } + + /* Transform to an offset on the set of pages */ + if (s->random_seq) { + for (i = 0; i < count; i++) + s->random_seq[i] *= s->size; + } + return 0; +} + +/* Initialize each random sequence freelist per cache */ +static void __init init_freelist_randomization(void) +{ + struct kmem_cache *s; + + mutex_lock(&slab_mutex); + + list_for_each_entry(s, &slab_caches, list) + init_cache_random_seq(s); + + mutex_unlock(&slab_mutex); +} + +/* Get the next entry on the pre-computed freelist randomized */ +static void *next_freelist_entry(struct kmem_cache *s, struct page *page, + unsigned long *pos, void *start, + unsigned long page_limit, + unsigned long freelist_count) +{ + unsigned int idx; + + /* + * If the target page allocation failed, the number of objects on the + * page might be smaller than the usual size defined by the cache. + */ + do { + idx = s->random_seq[*pos]; + *pos += 1; + if (*pos >= freelist_count) + *pos = 0; + } while (unlikely(idx >= page_limit)); + + return (char *)start + idx; +} + +/* Shuffle the single linked freelist based on a random pre-computed sequence */ +static bool shuffle_freelist(struct kmem_cache *s, struct page *page) +{ + void *start; + void *cur; + void *next; + unsigned long idx, pos, page_limit, freelist_count; + + if (page->objects < 2 || !s->random_seq) + return false; + + freelist_count = oo_objects(s->oo); + pos = get_random_int() % freelist_count; + + page_limit = page->objects * s->size; + start = fixup_red_left(s, page_address(page)); + + /* First entry is used as the base of the freelist */ + cur = next_freelist_entry(s, page, &pos, start, page_limit, + freelist_count); + page->freelist = cur; + + for (idx = 1; idx < page->objects; idx++) { + setup_object(s, page, cur); + next = next_freelist_entry(s, page, &pos, start, page_limit, + freelist_count); + set_freepointer(s, cur, next); + cur = next; + } + setup_object(s, page, cur); + set_freepointer(s, cur, NULL); + + return true; +} +#else +static inline int init_cache_random_seq(struct kmem_cache *s) +{ + return 0; +} +static inline void init_freelist_randomization(void) { } +static inline bool shuffle_freelist(struct kmem_cache *s, struct page *page) +{ + return false; +} +#endif /* CONFIG_SLAB_FREELIST_RANDOM */ + static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) { struct page *page; @@ -1412,6 +1526,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) gfp_t alloc_gfp; void *start, *p; int idx, order; + bool shuffle; flags &= gfp_allowed_mask; @@ -1473,15 +1588,19 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) kasan_poison_slab(page); - for_each_object_idx(p, idx, s, start, page->objects) { - setup_object(s, page, p); - if (likely(idx < page->objects)) - set_freepointer(s, p, p + s->size); - else - set_freepointer(s, p, NULL); + shuffle = shuffle_freelist(s, page); + + if (!shuffle) { + for_each_object_idx(p, idx, s, start, page->objects) { + setup_object(s, page, p); + if (likely(idx < page->objects)) + set_freepointer(s, p, p + s->size); + else + set_freepointer(s, p, NULL); + } + page->freelist = fixup_red_left(s, start); } - page->freelist = fixup_red_left(s, start); page->inuse = page->objects; page->frozen = 1; @@ -1504,8 +1623,10 @@ out: static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) { if (unlikely(flags & GFP_SLAB_BUG_MASK)) { - pr_emerg("gfp: %u\n", flags & GFP_SLAB_BUG_MASK); - BUG(); + gfp_t invalid_mask = flags & GFP_SLAB_BUG_MASK; + flags &= ~GFP_SLAB_BUG_MASK; + pr_warn("Unexpected gfp: %#x (%pGg). Fixing up to gfp: %#x (%pGg). Fix your code!\n", + invalid_mask, &invalid_mask, flags, &flags); } return allocate_slab(s, @@ -1735,11 +1856,11 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, * may return off node objects because partial slabs are obtained * from other nodes and filled up. * - * If /sys/kernel/slab/xx/defrag_ratio is set to 100 (which makes - * defrag_ratio = 1000) then every (well almost) allocation will - * first attempt to defrag slab caches on other nodes. This means - * scanning over all nodes to look for partial slabs which may be - * expensive if we do it every time we are trying to find a slab + * If /sys/kernel/slab/xx/remote_node_defrag_ratio is set to 100 + * (which makes defrag_ratio = 1000) then every (well almost) + * allocation will first attempt to defrag slab caches on other nodes. + * This means scanning over all nodes to look for partial slabs which + * may be expensive if we do it every time we are trying to find a slab * with available objects. */ if (!s->remote_node_defrag_ratio || @@ -2768,16 +2889,13 @@ slab_empty: * same page) possible by specifying head and tail ptr, plus objects * count (cnt). Bulk free indicated by tail pointer being set. */ -static __always_inline void slab_free(struct kmem_cache *s, struct page *page, - void *head, void *tail, int cnt, - unsigned long addr) +static __always_inline void do_slab_free(struct kmem_cache *s, + struct page *page, void *head, void *tail, + int cnt, unsigned long addr) { void *tail_obj = tail ? : head; struct kmem_cache_cpu *c; unsigned long tid; - - slab_free_freelist_hook(s, head, tail); - redo: /* * Determine the currently cpus per cpu slab. @@ -2811,6 +2929,27 @@ redo: } +static __always_inline void slab_free(struct kmem_cache *s, struct page *page, + void *head, void *tail, int cnt, + unsigned long addr) +{ + slab_free_freelist_hook(s, head, tail); + /* + * slab_free_freelist_hook() could have put the items into quarantine. + * If so, no need to free them. + */ + if (s->flags & SLAB_KASAN && !(s->flags & SLAB_DESTROY_BY_RCU)) + return; + do_slab_free(s, page, head, tail, cnt, addr); +} + +#ifdef CONFIG_KASAN +void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr) +{ + do_slab_free(cache, virt_to_head_page(x), x, NULL, 1, addr); +} +#endif + void kmem_cache_free(struct kmem_cache *s, void *x) { s = cache_from_obj(s, x); @@ -2867,7 +3006,7 @@ int build_detached_freelist(struct kmem_cache *s, size_t size, if (unlikely(!PageSlab(page))) { BUG_ON(!PageCompound(page)); kfree_hook(object); - __free_kmem_pages(page, compound_order(page)); + __free_pages(page, compound_order(page)); p[size] = NULL; /* mark object processed */ return size; } @@ -3207,6 +3346,7 @@ static void free_kmem_cache_nodes(struct kmem_cache *s) void __kmem_cache_release(struct kmem_cache *s) { + cache_random_seq_destroy(s); free_percpu(s->cpu_slab); free_kmem_cache_nodes(s); } @@ -3252,7 +3392,7 @@ static void set_min_partial(struct kmem_cache *s, unsigned long min) static int calculate_sizes(struct kmem_cache *s, int forced_order) { unsigned long flags = s->flags; - unsigned long size = s->object_size; + size_t size = s->object_size; int order; /* @@ -3311,7 +3451,10 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * the object. */ size += 2 * sizeof(struct track); +#endif + kasan_cache_create(s, &size, &s->flags); +#ifdef CONFIG_SLUB_DEBUG if (flags & SLAB_RED_ZONE) { /* * Add some empty padding so that we can catch @@ -3431,6 +3574,13 @@ static int kmem_cache_open(struct kmem_cache *s, unsigned long flags) #ifdef CONFIG_NUMA s->remote_node_defrag_ratio = 1000; #endif + + /* Initialize the pre-computed randomized freelist if slab is up */ + if (slab_state >= UP) { + if (init_cache_random_seq(s)) + goto error; + } + if (!init_kmem_cache_nodes(s)) goto error; @@ -3575,7 +3725,7 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node) void *ptr = NULL; flags |= __GFP_COMP | __GFP_NOTRACK; - page = alloc_kmem_pages_node(node, flags, get_order(size)); + page = alloc_pages_node(node, flags, get_order(size)); if (page) ptr = page_address(page); @@ -3635,8 +3785,9 @@ size_t ksize(const void *object) { size_t size = __ksize(object); /* We assume that ksize callers could use whole allocated area, - so we need unpoison this area. */ - kasan_krealloc(object, size, GFP_NOWAIT); + * so we need to unpoison this area. + */ + kasan_unpoison_shadow(object, size); return size; } EXPORT_SYMBOL(ksize); @@ -3655,7 +3806,7 @@ void kfree(const void *x) if (unlikely(!PageSlab(page))) { BUG_ON(!PageCompound(page)); kfree_hook(x); - __free_kmem_pages(page, compound_order(page)); + __free_pages(page, compound_order(page)); return; } slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_); @@ -3697,7 +3848,7 @@ int __kmem_cache_shrink(struct kmem_cache *s, bool deactivate) * s->cpu_partial is checked locklessly (see put_cpu_partial), * so we have to make sure the change is visible. */ - kick_all_cpus_sync(); + synchronize_sched(); } flush_all(s); @@ -3946,6 +4097,9 @@ void __init kmem_cache_init(void) setup_kmalloc_cache_index_table(); create_kmalloc_caches(0); + /* Setup random freelists for each cache */ + init_freelist_randomization(); + #ifdef CONFIG_SMP register_cpu_notifier(&slab_notifier); #endif diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 68885dcbaf40..574c67b663fe 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -36,7 +36,7 @@ * Uses the main allocators if they are available, else bootmem. */ -static void * __init_refok __earlyonly_bootmem_alloc(int node, +static void * __ref __earlyonly_bootmem_alloc(int node, unsigned long size, unsigned long align, unsigned long goal) diff --git a/mm/sparse.c b/mm/sparse.c index 5d0cf4540364..1e168bf2779a 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -59,7 +59,7 @@ static inline void set_section_nid(unsigned long section_nr, int nid) #endif #ifdef CONFIG_SPARSEMEM_EXTREME -static struct mem_section noinline __init_refok *sparse_index_alloc(int nid) +static noinline struct mem_section __ref *sparse_index_alloc(int nid) { struct mem_section *section = NULL; unsigned long array_size = SECTIONS_PER_ROOT * @@ -100,11 +100,7 @@ static inline int sparse_index_init(unsigned long section_nr, int nid) } #endif -/* - * Although written for the SPARSEMEM_EXTREME case, this happens - * to also work for the flat array case because - * NR_SECTION_ROOTS==NR_MEM_SECTIONS. - */ +#ifdef CONFIG_SPARSEMEM_EXTREME int __section_nr(struct mem_section* ms) { unsigned long root_nr; @@ -123,6 +119,12 @@ int __section_nr(struct mem_section* ms) return (root_nr * SECTIONS_PER_ROOT) + (ms - root); } +#else +int __section_nr(struct mem_section* ms) +{ + return (int)(ms - mem_section[0]); +} +#endif /* * During early boot, before section_mem_map is used for an actual diff --git a/mm/swap.c b/mm/swap.c index 09fe5e97714a..75c63bb2a1da 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -47,6 +47,9 @@ static DEFINE_PER_CPU(struct pagevec, lru_add_pvec); static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs); static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs); +#ifdef CONFIG_SMP +static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs); +#endif /* * This path almost never happens for VM activity - pages are normally @@ -59,12 +62,12 @@ static void __page_cache_release(struct page *page) struct lruvec *lruvec; unsigned long flags; - spin_lock_irqsave(&zone->lru_lock, flags); - lruvec = mem_cgroup_page_lruvec(page, zone); + spin_lock_irqsave(zone_lru_lock(zone), flags); + lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); - spin_unlock_irqrestore(&zone->lru_lock, flags); + spin_unlock_irqrestore(zone_lru_lock(zone), flags); } mem_cgroup_uncharge(page); } @@ -114,7 +117,7 @@ void put_pages_list(struct list_head *pages) victim = list_entry(pages->prev, struct page, lru); list_del(&victim->lru); - page_cache_release(victim); + put_page(victim); } } EXPORT_SYMBOL(put_pages_list); @@ -142,7 +145,7 @@ int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write, return seg; pages[seg] = kmap_to_page(kiov[seg].iov_base); - page_cache_get(pages[seg]); + get_page(pages[seg]); } return seg; @@ -176,26 +179,26 @@ static void pagevec_lru_move_fn(struct pagevec *pvec, void *arg) { int i; - struct zone *zone = NULL; + struct pglist_data *pgdat = NULL; struct lruvec *lruvec; unsigned long flags = 0; for (i = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; - struct zone *pagezone = page_zone(page); + struct pglist_data *pagepgdat = page_pgdat(page); - if (pagezone != zone) { - if (zone) - spin_unlock_irqrestore(&zone->lru_lock, flags); - zone = pagezone; - spin_lock_irqsave(&zone->lru_lock, flags); + if (pagepgdat != pgdat) { + if (pgdat) + spin_unlock_irqrestore(&pgdat->lru_lock, flags); + pgdat = pagepgdat; + spin_lock_irqsave(&pgdat->lru_lock, flags); } - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, pgdat); (*move_fn)(page, lruvec, arg); } - if (zone) - spin_unlock_irqrestore(&zone->lru_lock, flags); + if (pgdat) + spin_unlock_irqrestore(&pgdat->lru_lock, flags); release_pages(pvec->pages, pvec->nr, pvec->cold); pagevec_reinit(pvec); } @@ -236,10 +239,10 @@ void rotate_reclaimable_page(struct page *page) struct pagevec *pvec; unsigned long flags; - page_cache_get(page); + get_page(page); local_irq_save(flags); pvec = this_cpu_ptr(&lru_rotate_pvecs); - if (!pagevec_add(pvec, page)) + if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_move_tail(pvec); local_irq_restore(flags); } @@ -274,8 +277,6 @@ static void __activate_page(struct page *page, struct lruvec *lruvec, } #ifdef CONFIG_SMP -static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs); - static void activate_page_drain(int cpu) { struct pagevec *pvec = &per_cpu(activate_page_pvecs, cpu); @@ -291,11 +292,12 @@ static bool need_activate_page_drain(int cpu) void activate_page(struct page *page) { + page = compound_head(page); if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { struct pagevec *pvec = &get_cpu_var(activate_page_pvecs); - page_cache_get(page); - if (!pagevec_add(pvec, page)) + get_page(page); + if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, __activate_page, NULL); put_cpu_var(activate_page_pvecs); } @@ -315,9 +317,10 @@ void activate_page(struct page *page) { struct zone *zone = page_zone(page); - spin_lock_irq(&zone->lru_lock); - __activate_page(page, mem_cgroup_page_lruvec(page, zone), NULL); - spin_unlock_irq(&zone->lru_lock); + page = compound_head(page); + spin_lock_irq(zone_lru_lock(zone)); + __activate_page(page, mem_cgroup_page_lruvec(page, zone->zone_pgdat), NULL); + spin_unlock_irq(zone_lru_lock(zone)); } #endif @@ -389,10 +392,9 @@ static void __lru_cache_add(struct page *page) { struct pagevec *pvec = &get_cpu_var(lru_add_pvec); - page_cache_get(page); - if (!pagevec_space(pvec)) + get_page(page); + if (!pagevec_add(pvec, page) || PageCompound(page)) __pagevec_lru_add(pvec); - pagevec_add(pvec, page); put_cpu_var(lru_add_pvec); } @@ -443,16 +445,16 @@ void lru_cache_add(struct page *page) */ void add_page_to_unevictable_list(struct page *page) { - struct zone *zone = page_zone(page); + struct pglist_data *pgdat = page_pgdat(page); struct lruvec *lruvec; - spin_lock_irq(&zone->lru_lock); - lruvec = mem_cgroup_page_lruvec(page, zone); + spin_lock_irq(&pgdat->lru_lock); + lruvec = mem_cgroup_page_lruvec(page, pgdat); ClearPageActive(page); SetPageUnevictable(page); SetPageLRU(page); add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE); - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(&pgdat->lru_lock); } /** @@ -627,7 +629,7 @@ void deactivate_file_page(struct page *page) if (likely(get_page_unless_zero(page))) { struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs); - if (!pagevec_add(pvec, page)) + if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); put_cpu_var(lru_deactivate_file_pvecs); } @@ -646,8 +648,8 @@ void deactivate_page(struct page *page) if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs); - page_cache_get(page); - if (!pagevec_add(pvec, page)) + get_page(page); + if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); put_cpu_var(lru_deactivate_pvecs); } @@ -666,6 +668,24 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy) static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); +/* + * lru_add_drain_wq is used to do lru_add_drain_all() from a WQ_MEM_RECLAIM + * workqueue, aiding in getting memory freed. + */ +static struct workqueue_struct *lru_add_drain_wq; + +static int __init lru_init(void) +{ + lru_add_drain_wq = alloc_workqueue("lru-add-drain", WQ_MEM_RECLAIM, 0); + + if (WARN(!lru_add_drain_wq, + "Failed to create workqueue lru_add_drain_wq")) + return -ENOMEM; + + return 0; +} +early_initcall(lru_init); + void lru_add_drain_all(void) { static DEFINE_MUTEX(lock); @@ -685,7 +705,7 @@ void lru_add_drain_all(void) pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) || need_activate_page_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); - schedule_work_on(cpu, work); + queue_work_on(cpu, lru_add_drain_wq, work); cpumask_set_cpu(cpu, &has_work); } } @@ -698,7 +718,7 @@ void lru_add_drain_all(void) } /** - * release_pages - batched page_cache_release() + * release_pages - batched put_page() * @pages: array of pages to release * @nr: number of pages * @cold: whether the pages are cache cold @@ -710,7 +730,7 @@ void release_pages(struct page **pages, int nr, bool cold) { int i; LIST_HEAD(pages_to_free); - struct zone *zone = NULL; + struct pglist_data *locked_pgdat = NULL; struct lruvec *lruvec; unsigned long uninitialized_var(flags); unsigned int uninitialized_var(lock_batch); @@ -721,11 +741,16 @@ void release_pages(struct page **pages, int nr, bool cold) /* * Make sure the IRQ-safe lock-holding time does not get * excessive with a continuous string of pages from the - * same zone. The lock is held only if zone != NULL. + * same pgdat. The lock is held only if pgdat != NULL. */ - if (zone && ++lock_batch == SWAP_CLUSTER_MAX) { - spin_unlock_irqrestore(&zone->lru_lock, flags); - zone = NULL; + if (locked_pgdat && ++lock_batch == SWAP_CLUSTER_MAX) { + spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); + locked_pgdat = NULL; + } + + if (is_huge_zero_page(page)) { + put_huge_zero_page(); + continue; } page = compound_head(page); @@ -733,27 +758,27 @@ void release_pages(struct page **pages, int nr, bool cold) continue; if (PageCompound(page)) { - if (zone) { - spin_unlock_irqrestore(&zone->lru_lock, flags); - zone = NULL; + if (locked_pgdat) { + spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); + locked_pgdat = NULL; } __put_compound_page(page); continue; } if (PageLRU(page)) { - struct zone *pagezone = page_zone(page); + struct pglist_data *pgdat = page_pgdat(page); - if (pagezone != zone) { - if (zone) - spin_unlock_irqrestore(&zone->lru_lock, + if (pgdat != locked_pgdat) { + if (locked_pgdat) + spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); lock_batch = 0; - zone = pagezone; - spin_lock_irqsave(&zone->lru_lock, flags); + locked_pgdat = pgdat; + spin_lock_irqsave(&locked_pgdat->lru_lock, flags); } - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, locked_pgdat); VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); @@ -764,8 +789,8 @@ void release_pages(struct page **pages, int nr, bool cold) list_add(&page->lru, &pages_to_free); } - if (zone) - spin_unlock_irqrestore(&zone->lru_lock, flags); + if (locked_pgdat) + spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); mem_cgroup_uncharge_list(&pages_to_free); free_hot_cold_page_list(&pages_to_free, cold); @@ -801,7 +826,7 @@ void lru_add_page_tail(struct page *page, struct page *page_tail, VM_BUG_ON_PAGE(PageCompound(page_tail), page); VM_BUG_ON_PAGE(PageLRU(page_tail), page); VM_BUG_ON(NR_CPUS != 1 && - !spin_is_locked(&lruvec_zone(lruvec)->lru_lock)); + !spin_is_locked(&lruvec_pgdat(lruvec)->lru_lock)); if (!list) SetPageLRU(page_tail); diff --git a/mm/swap_state.c b/mm/swap_state.c index 69cb2464e7dc..c8310a37be3a 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -85,7 +85,7 @@ int __add_to_swap_cache(struct page *page, swp_entry_t entry) VM_BUG_ON_PAGE(PageSwapCache(page), page); VM_BUG_ON_PAGE(!PageSwapBacked(page), page); - page_cache_get(page); + get_page(page); SetPageSwapCache(page); set_page_private(page, entry.val); @@ -95,7 +95,7 @@ int __add_to_swap_cache(struct page *page, swp_entry_t entry) entry.val, page); if (likely(!error)) { address_space->nrpages++; - __inc_zone_page_state(page, NR_FILE_PAGES); + __inc_node_page_state(page, NR_FILE_PAGES); INC_CACHE_INFO(add_total); } spin_unlock_irq(&address_space->tree_lock); @@ -109,7 +109,7 @@ int __add_to_swap_cache(struct page *page, swp_entry_t entry) VM_BUG_ON(error == -EEXIST); set_page_private(page, 0UL); ClearPageSwapCache(page); - page_cache_release(page); + put_page(page); } return error; @@ -147,7 +147,7 @@ void __delete_from_swap_cache(struct page *page) set_page_private(page, 0); ClearPageSwapCache(page); address_space->nrpages--; - __dec_zone_page_state(page, NR_FILE_PAGES); + __dec_node_page_state(page, NR_FILE_PAGES); INC_CACHE_INFO(del_total); } @@ -226,7 +226,7 @@ void delete_from_swap_cache(struct page *page) spin_unlock_irq(&address_space->tree_lock); swapcache_free(entry); - page_cache_release(page); + put_page(page); } /* @@ -252,7 +252,10 @@ static inline void free_swap_cache(struct page *page) void free_page_and_swap_cache(struct page *page) { free_swap_cache(page); - page_cache_release(page); + if (is_huge_zero_page(page)) + put_huge_zero_page(); + else + put_page(page); } /* @@ -358,7 +361,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, /* May fail (-ENOMEM) if radix-tree node allocation failed. */ __SetPageLocked(new_page); - SetPageSwapBacked(new_page); + __SetPageSwapBacked(new_page); err = __add_to_swap_cache(new_page, entry); if (likely(!err)) { radix_tree_preload_end(); @@ -370,7 +373,6 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, return new_page; } radix_tree_preload_end(); - ClearPageSwapBacked(new_page); __ClearPageLocked(new_page); /* * add_to_swap_cache() doesn't return -EEXIST, so we can safely @@ -380,7 +382,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, } while (err != -ENOMEM); if (new_page) - page_cache_release(new_page); + put_page(new_page); return found_page; } @@ -495,7 +497,7 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, continue; if (offset != entry_offset) SetPageReadahead(page); - page_cache_release(page); + put_page(page); } blk_finish_plug(&plug); diff --git a/mm/swapfile.c b/mm/swapfile.c index 560ad380634c..78cfa292a29a 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -119,7 +119,7 @@ __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset) ret = try_to_free_swap(page); unlock_page(page); } - page_cache_release(page); + put_page(page); return ret; } @@ -922,18 +922,19 @@ out: * to it. And as a side-effect, free up its swap: because the old content * on disk will never be read, and seeking back there to write new content * later would only waste time away from clustering. + * + * NOTE: total_mapcount should not be relied upon by the caller if + * reuse_swap_page() returns false, but it may be always overwritten + * (see the other implementation for CONFIG_SWAP=n). */ -int reuse_swap_page(struct page *page) +bool reuse_swap_page(struct page *page, int *total_mapcount) { int count; VM_BUG_ON_PAGE(!PageLocked(page), page); if (unlikely(PageKsm(page))) - return 0; - /* The page is part of THP and cannot be reused */ - if (PageTransCompound(page)) - return 0; - count = page_mapcount(page); + return false; + count = page_trans_huge_mapcount(page, total_mapcount); if (count <= 1 && PageSwapCache(page)) { count += page_swapcount(page); if (count == 1 && !PageWriteback(page)) { @@ -1000,7 +1001,7 @@ int free_swap_and_cache(swp_entry_t entry) page = find_get_page(swap_address_space(entry), entry.val); if (page && !trylock_page(page)) { - page_cache_release(page); + put_page(page); page = NULL; } } @@ -1017,7 +1018,7 @@ int free_swap_and_cache(swp_entry_t entry) SetPageDirty(page); } unlock_page(page); - page_cache_release(page); + put_page(page); } return p != NULL; } @@ -1518,7 +1519,7 @@ int try_to_unuse(unsigned int type, bool frontswap, } if (retval) { unlock_page(page); - page_cache_release(page); + put_page(page); break; } @@ -1570,7 +1571,7 @@ int try_to_unuse(unsigned int type, bool frontswap, */ SetPageDirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); /* * Make sure that we aren't completely killing @@ -2492,7 +2493,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) goto bad_swap; } /* frontswap enabled? set up bit-per-page map for frontswap */ - if (frontswap_enabled) + if (IS_ENABLED(CONFIG_FRONTSWAP)) frontswap_map = vzalloc(BITS_TO_LONGS(maxpages) * sizeof(long)); if (p->bdev &&(swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { @@ -2574,7 +2575,7 @@ bad_swap: out: if (page && !IS_ERR(page)) { kunmap(page); - page_cache_release(page); + put_page(page); } if (name) putname(name); diff --git a/mm/truncate.c b/mm/truncate.c index 7598b552ae03..a01cce450a26 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -34,40 +34,38 @@ static void clear_exceptional_entry(struct address_space *mapping, if (shmem_mapping(mapping)) return; - spin_lock_irq(&mapping->tree_lock); - if (dax_mapping(mapping)) { - if (radix_tree_delete_item(&mapping->page_tree, index, entry)) - mapping->nrexceptional--; - } else { - /* - * Regular page slots are stabilized by the page lock even - * without the tree itself locked. These unlocked entries - * need verification under the tree lock. - */ - if (!__radix_tree_lookup(&mapping->page_tree, index, &node, - &slot)) - goto unlock; - if (*slot != entry) - goto unlock; - radix_tree_replace_slot(slot, NULL); - mapping->nrexceptional--; - if (!node) - goto unlock; - workingset_node_shadows_dec(node); - /* - * Don't track node without shadow entries. - * - * Avoid acquiring the list_lru lock if already untracked. - * The list_empty() test is safe as node->private_list is - * protected by mapping->tree_lock. - */ - if (!workingset_node_shadows(node) && - !list_empty(&node->private_list)) - list_lru_del(&workingset_shadow_nodes, - &node->private_list); - __radix_tree_delete_node(&mapping->page_tree, node); + dax_delete_mapping_entry(mapping, index); + return; } + spin_lock_irq(&mapping->tree_lock); + /* + * Regular page slots are stabilized by the page lock even + * without the tree itself locked. These unlocked entries + * need verification under the tree lock. + */ + if (!__radix_tree_lookup(&mapping->page_tree, index, &node, + &slot)) + goto unlock; + if (*slot != entry) + goto unlock; + radix_tree_replace_slot(slot, NULL); + mapping->nrexceptional--; + if (!node) + goto unlock; + workingset_node_shadows_dec(node); + /* + * Don't track node without shadow entries. + * + * Avoid acquiring the list_lru lock if already untracked. + * The list_empty() test is safe as node->private_list is + * protected by mapping->tree_lock. + */ + if (!workingset_node_shadows(node) && + !list_empty(&node->private_list)) + list_lru_del(&workingset_shadow_nodes, + &node->private_list); + __radix_tree_delete_node(&mapping->page_tree, node); unlock: spin_unlock_irq(&mapping->tree_lock); } @@ -118,7 +116,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page) return -EIO; if (page_has_private(page)) - do_invalidatepage(page, 0, PAGE_CACHE_SIZE); + do_invalidatepage(page, 0, PAGE_SIZE); /* * Some filesystems seem to re-dirty the page even after @@ -157,10 +155,14 @@ invalidate_complete_page(struct address_space *mapping, struct page *page) int truncate_inode_page(struct address_space *mapping, struct page *page) { + loff_t holelen; + VM_BUG_ON_PAGE(PageTail(page), page); + + holelen = PageTransHuge(page) ? HPAGE_PMD_SIZE : PAGE_SIZE; if (page_mapped(page)) { unmap_mapping_range(mapping, - (loff_t)page->index << PAGE_CACHE_SHIFT, - PAGE_CACHE_SIZE, 0); + (loff_t)page->index << PAGE_SHIFT, + holelen, 0); } return truncate_complete_page(mapping, page); } @@ -241,8 +243,8 @@ void truncate_inode_pages_range(struct address_space *mapping, return; /* Offsets within partial pages */ - partial_start = lstart & (PAGE_CACHE_SIZE - 1); - partial_end = (lend + 1) & (PAGE_CACHE_SIZE - 1); + partial_start = lstart & (PAGE_SIZE - 1); + partial_end = (lend + 1) & (PAGE_SIZE - 1); /* * 'start' and 'end' always covers the range of pages to be fully @@ -250,7 +252,7 @@ void truncate_inode_pages_range(struct address_space *mapping, * start of the range and 'partial_end' at the end of the range. * Note that 'end' is exclusive while 'lend' is inclusive. */ - start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; if (lend == -1) /* * lend == -1 indicates end-of-file so we have to set 'end' @@ -259,7 +261,7 @@ void truncate_inode_pages_range(struct address_space *mapping, */ end = -1; else - end = (lend + 1) >> PAGE_CACHE_SHIFT; + end = (lend + 1) >> PAGE_SHIFT; pagevec_init(&pvec, 0); index = start; @@ -281,7 +283,7 @@ void truncate_inode_pages_range(struct address_space *mapping, if (!trylock_page(page)) continue; - WARN_ON(page->index != index); + WARN_ON(page_to_pgoff(page) != index); if (PageWriteback(page)) { unlock_page(page); continue; @@ -298,7 +300,7 @@ void truncate_inode_pages_range(struct address_space *mapping, if (partial_start) { struct page *page = find_lock_page(mapping, start - 1); if (page) { - unsigned int top = PAGE_CACHE_SIZE; + unsigned int top = PAGE_SIZE; if (start > end) { /* Truncation within a single page */ top = partial_end; @@ -311,7 +313,7 @@ void truncate_inode_pages_range(struct address_space *mapping, do_invalidatepage(page, partial_start, top - partial_start); unlock_page(page); - page_cache_release(page); + put_page(page); } } if (partial_end) { @@ -324,7 +326,7 @@ void truncate_inode_pages_range(struct address_space *mapping, do_invalidatepage(page, 0, partial_end); unlock_page(page); - page_cache_release(page); + put_page(page); } } /* @@ -369,7 +371,7 @@ void truncate_inode_pages_range(struct address_space *mapping, } lock_page(page); - WARN_ON(page->index != index); + WARN_ON(page_to_pgoff(page) != index); wait_on_page_writeback(page); truncate_inode_page(mapping, page); unlock_page(page); @@ -489,7 +491,21 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, if (!trylock_page(page)) continue; - WARN_ON(page->index != index); + + WARN_ON(page_to_pgoff(page) != index); + + /* Middle of THP: skip */ + if (PageTransTail(page)) { + unlock_page(page); + continue; + } else if (PageTransHuge(page)) { + index += HPAGE_PMD_NR - 1; + i += HPAGE_PMD_NR - 1; + /* 'end' is in the middle of THP */ + if (index == round_down(end, HPAGE_PMD_NR)) + continue; + } + ret = invalidate_inode_page(page); unlock_page(page); /* @@ -538,7 +554,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) if (mapping->a_ops->freepage) mapping->a_ops->freepage(page); - page_cache_release(page); /* pagecache ref */ + put_page(page); /* pagecache ref */ return 1; failed: spin_unlock_irqrestore(&mapping->tree_lock, flags); @@ -596,7 +612,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, } lock_page(page); - WARN_ON(page->index != index); + WARN_ON(page_to_pgoff(page) != index); if (page->mapping != mapping) { unlock_page(page); continue; @@ -608,18 +624,18 @@ int invalidate_inode_pages2_range(struct address_space *mapping, * Zap the rest of the file in one hit. */ unmap_mapping_range(mapping, - (loff_t)index << PAGE_CACHE_SHIFT, + (loff_t)index << PAGE_SHIFT, (loff_t)(1 + end - index) - << PAGE_CACHE_SHIFT, - 0); + << PAGE_SHIFT, + 0); did_range_unmap = 1; } else { /* * Just zap this page */ unmap_mapping_range(mapping, - (loff_t)index << PAGE_CACHE_SHIFT, - PAGE_CACHE_SIZE, 0); + (loff_t)index << PAGE_SHIFT, + PAGE_SIZE, 0); } } BUG_ON(page_mapped(page)); @@ -744,14 +760,14 @@ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) WARN_ON(to > inode->i_size); - if (from >= to || bsize == PAGE_CACHE_SIZE) + if (from >= to || bsize == PAGE_SIZE) return; /* Page straddling @from will not have any hole block created? */ rounded_from = round_up(from, bsize); - if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1))) + if (to <= rounded_from || !(rounded_from & (PAGE_SIZE - 1))) return; - index = from >> PAGE_CACHE_SHIFT; + index = from >> PAGE_SHIFT; page = find_lock_page(inode->i_mapping, index); /* Page not cached? Nothing to do */ if (!page) @@ -763,7 +779,7 @@ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) if (page_mkclean(page)) set_page_dirty(page); unlock_page(page); - page_cache_release(page); + put_page(page); } EXPORT_SYMBOL(pagecache_isize_extended); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 9f3a0290b273..af817e5060fb 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -93,7 +93,7 @@ out_release_uncharge_unlock: pte_unmap_unlock(dst_pte, ptl); mem_cgroup_cancel_charge(page, memcg, false); out_release: - page_cache_release(page); + put_page(page); goto out; } @@ -287,7 +287,7 @@ out_unlock: up_read(&dst_mm->mmap_sem); out: if (page) - page_cache_release(page); + put_page(page); BUG_ON(copied < 0); BUG_ON(err > 0); BUG_ON(!copied && !err); diff --git a/mm/util.c b/mm/util.c index 6cc81e7b8705..662cddf914af 100644 --- a/mm/util.c +++ b/mm/util.c @@ -297,7 +297,8 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, ret = security_mmap_file(file, prot, flag); if (!ret) { - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff, &populate); up_write(&mm->mmap_sem); @@ -346,6 +347,29 @@ void *page_rmapping(struct page *page) return __page_rmapping(page); } +/* + * Return true if this page is mapped into pagetables. + * For compound page it returns true if any subpage of compound page is mapped. + */ +bool page_mapped(struct page *page) +{ + int i; + + if (likely(!PageCompound(page))) + return atomic_read(&page->_mapcount) >= 0; + page = compound_head(page); + if (atomic_read(compound_mapcount_ptr(page)) >= 0) + return true; + if (PageHuge(page)) + return false; + for (i = 0; i < hpage_nr_pages(page); i++) { + if (atomic_read(&page[i]._mapcount) >= 0) + return true; + } + return false; +} +EXPORT_SYMBOL(page_mapped); + struct anon_vma *page_anon_vma(struct page *page) { unsigned long mapping; @@ -375,10 +399,12 @@ struct address_space *page_mapping(struct page *page) } mapping = page->mapping; - if ((unsigned long)mapping & PAGE_MAPPING_FLAGS) + if ((unsigned long)mapping & PAGE_MAPPING_ANON) return NULL; - return mapping; + + return (void *)((unsigned long)mapping & ~PAGE_MAPPING_FLAGS); } +EXPORT_SYMBOL(page_mapping); /* Slow path of page_mapcount() for compound pages */ int __page_mapcount(struct page *page) @@ -386,6 +412,12 @@ int __page_mapcount(struct page *page) int ret; ret = atomic_read(&page->_mapcount) + 1; + /* + * For file THP page->_mapcount contains total number of mapping + * of the page: no need to look into compound_mapcount. + */ + if (!PageAnon(page) && !PageHuge(page)) + return ret; page = compound_head(page); ret += atomic_read(compound_mapcount_ptr(page)) + 1; if (PageDoubleMap(page)) @@ -496,7 +528,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) { free = global_page_state(NR_FREE_PAGES); - free += global_page_state(NR_FILE_PAGES); + free += global_node_page_state(NR_FILE_PAGES); /* * shmem pages shouldn't be counted as free in this @@ -504,7 +536,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) * that won't affect the overall amount of available * memory in the system. */ - free -= global_page_state(NR_SHMEM); + free -= global_node_page_state(NR_SHMEM); free += get_nr_swap_pages(); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index ae7d20b447ff..91f44e78c516 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -21,6 +21,7 @@ #include <linux/debugobjects.h> #include <linux/kallsyms.h> #include <linux/list.h> +#include <linux/notifier.h> #include <linux/rbtree.h> #include <linux/radix-tree.h> #include <linux/rcupdate.h> @@ -274,13 +275,12 @@ EXPORT_SYMBOL(vmalloc_to_pfn); /*** Global kva allocator ***/ -#define VM_LAZY_FREE 0x01 -#define VM_LAZY_FREEING 0x02 #define VM_VM_AREA 0x04 static DEFINE_SPINLOCK(vmap_area_lock); /* Export for kexec only */ LIST_HEAD(vmap_area_list); +static LLIST_HEAD(vmap_purge_list); static struct rb_root vmap_area_root = RB_ROOT; /* The vmap cache globals are protected by vmap_area_lock */ @@ -344,6 +344,8 @@ static void __insert_vmap_area(struct vmap_area *va) static void purge_vmap_area_lazy(void); +static BLOCKING_NOTIFIER_HEAD(vmap_notify_list); + /* * Allocate a region of KVA of the specified size and alignment, within the * vstart and vend. @@ -363,6 +365,8 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, BUG_ON(offset_in_page(size)); BUG_ON(!is_power_of_2(align)); + might_sleep_if(gfpflags_allow_blocking(gfp_mask)); + va = kmalloc_node(sizeof(struct vmap_area), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!va)) @@ -468,6 +472,16 @@ overflow: purged = 1; goto retry; } + + if (gfpflags_allow_blocking(gfp_mask)) { + unsigned long freed = 0; + blocking_notifier_call_chain(&vmap_notify_list, 0, &freed); + if (freed > 0) { + purged = 0; + goto retry; + } + } + if (printk_ratelimit()) pr_warn("vmap allocation for size %lu failed: use vmalloc=<size> to increase size\n", size); @@ -475,6 +489,18 @@ overflow: return ERR_PTR(-EBUSY); } +int register_vmap_purge_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&vmap_notify_list, nb); +} +EXPORT_SYMBOL_GPL(register_vmap_purge_notifier); + +int unregister_vmap_purge_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&vmap_notify_list, nb); +} +EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier); + static void __free_vmap_area(struct vmap_area *va) { BUG_ON(RB_EMPTY_NODE(&va->rb_node)); @@ -601,7 +627,7 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end, int sync, int force_flush) { static DEFINE_SPINLOCK(purge_lock); - LIST_HEAD(valist); + struct llist_node *valist; struct vmap_area *va; struct vmap_area *n_va; int nr = 0; @@ -620,20 +646,14 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end, if (sync) purge_fragmented_blocks_allcpus(); - rcu_read_lock(); - list_for_each_entry_rcu(va, &vmap_area_list, list) { - if (va->flags & VM_LAZY_FREE) { - if (va->va_start < *start) - *start = va->va_start; - if (va->va_end > *end) - *end = va->va_end; - nr += (va->va_end - va->va_start) >> PAGE_SHIFT; - list_add_tail(&va->purge_list, &valist); - va->flags |= VM_LAZY_FREEING; - va->flags &= ~VM_LAZY_FREE; - } + valist = llist_del_all(&vmap_purge_list); + llist_for_each_entry(va, valist, purge_list) { + if (va->va_start < *start) + *start = va->va_start; + if (va->va_end > *end) + *end = va->va_end; + nr += (va->va_end - va->va_start) >> PAGE_SHIFT; } - rcu_read_unlock(); if (nr) atomic_sub(nr, &vmap_lazy_nr); @@ -643,7 +663,7 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end, if (nr) { spin_lock(&vmap_area_lock); - list_for_each_entry_safe(va, n_va, &valist, purge_list) + llist_for_each_entry_safe(va, n_va, valist, purge_list) __free_vmap_area(va); spin_unlock(&vmap_area_lock); } @@ -678,9 +698,15 @@ static void purge_vmap_area_lazy(void) */ static void free_vmap_area_noflush(struct vmap_area *va) { - va->flags |= VM_LAZY_FREE; - atomic_add((va->va_end - va->va_start) >> PAGE_SHIFT, &vmap_lazy_nr); - if (unlikely(atomic_read(&vmap_lazy_nr) > lazy_max_pages())) + int nr_lazy; + + nr_lazy = atomic_add_return((va->va_end - va->va_start) >> PAGE_SHIFT, + &vmap_lazy_nr); + + /* After this point, we may free va at any time */ + llist_add(&va->purge_list, &vmap_purge_list); + + if (unlikely(nr_lazy > lazy_max_pages())) try_purge_vmap_area_lazy(); } @@ -1079,7 +1105,7 @@ EXPORT_SYMBOL_GPL(vm_unmap_aliases); */ void vm_unmap_ram(const void *mem, unsigned int count) { - unsigned long size = count << PAGE_SHIFT; + unsigned long size = (unsigned long)count << PAGE_SHIFT; unsigned long addr = (unsigned long)mem; BUG_ON(!addr); @@ -1114,7 +1140,7 @@ EXPORT_SYMBOL(vm_unmap_ram); */ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot) { - unsigned long size = count << PAGE_SHIFT; + unsigned long size = (unsigned long)count << PAGE_SHIFT; unsigned long addr; void *mem; @@ -1475,7 +1501,7 @@ static void __vunmap(const void *addr, int deallocate_pages) struct page *page = area->pages[i]; BUG_ON(!page); - __free_kmem_pages(page, 0); + __free_pages(page, 0); } kvfree(area->pages); @@ -1548,14 +1574,15 @@ void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot) { struct vm_struct *area; + unsigned long size; /* In bytes */ might_sleep(); if (count > totalram_pages) return NULL; - area = get_vm_area_caller((count << PAGE_SHIFT), flags, - __builtin_return_address(0)); + size = (unsigned long)count << PAGE_SHIFT; + area = get_vm_area_caller(size, flags, __builtin_return_address(0)); if (!area) return NULL; @@ -1602,9 +1629,9 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, struct page *page; if (node == NUMA_NO_NODE) - page = alloc_kmem_pages(alloc_mask, order); + page = alloc_pages(alloc_mask, order); else - page = alloc_kmem_pages_node(node, alloc_mask, order); + page = alloc_pages_node(node, alloc_mask, order); if (unlikely(!page)) { /* Successfully allocated i pages, free them in __vunmap() */ diff --git a/mm/vmscan.c b/mm/vmscan.c index b934223eaa45..374d95d04178 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -84,6 +84,9 @@ struct scan_control { /* Scan (total_size >> priority) pages at once */ int priority; + /* The highest zone to isolate pages for reclaim from */ + enum zone_type reclaim_idx; + unsigned int may_writepage:1; /* Can mapped pages be reclaimed? */ @@ -191,26 +194,44 @@ static bool sane_reclaim(struct scan_control *sc) } #endif -static unsigned long zone_reclaimable_pages(struct zone *zone) +/* + * This misses isolated pages which are not accounted for to save counters. + * As the data only determines if reclaim or compaction continues, it is + * not expected that isolated pages will be a dominating factor. + */ +unsigned long zone_reclaimable_pages(struct zone *zone) +{ + unsigned long nr; + + nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); + if (get_nr_swap_pages() > 0) + nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); + + return nr; +} + +unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat) { unsigned long nr; - nr = zone_page_state_snapshot(zone, NR_ACTIVE_FILE) + - zone_page_state_snapshot(zone, NR_INACTIVE_FILE) + - zone_page_state_snapshot(zone, NR_ISOLATED_FILE); + nr = node_page_state_snapshot(pgdat, NR_ACTIVE_FILE) + + node_page_state_snapshot(pgdat, NR_INACTIVE_FILE) + + node_page_state_snapshot(pgdat, NR_ISOLATED_FILE); if (get_nr_swap_pages() > 0) - nr += zone_page_state_snapshot(zone, NR_ACTIVE_ANON) + - zone_page_state_snapshot(zone, NR_INACTIVE_ANON) + - zone_page_state_snapshot(zone, NR_ISOLATED_ANON); + nr += node_page_state_snapshot(pgdat, NR_ACTIVE_ANON) + + node_page_state_snapshot(pgdat, NR_INACTIVE_ANON) + + node_page_state_snapshot(pgdat, NR_ISOLATED_ANON); return nr; } -bool zone_reclaimable(struct zone *zone) +bool pgdat_reclaimable(struct pglist_data *pgdat) { - return zone_page_state_snapshot(zone, NR_PAGES_SCANNED) < - zone_reclaimable_pages(zone) * 6; + return node_page_state_snapshot(pgdat, NR_PAGES_SCANNED) < + pgdat_reclaimable_pages(pgdat) * 6; } unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru) @@ -218,7 +239,7 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru) if (!mem_cgroup_disabled()) return mem_cgroup_get_lru_size(lruvec, lru); - return zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru); + return node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru); } /* @@ -593,7 +614,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, ClearPageReclaim(page); } trace_mm_vmscan_writepage(page); - inc_zone_page_state(page, NR_VMSCAN_WRITE); + inc_node_page_state(page, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } @@ -633,7 +654,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, * * Reversing the order of the tests ensures such a situation cannot * escape unnoticed. The smp_rmb is needed to ensure the page->flags - * load is not satisfied before that of page->_count. + * load is not satisfied before that of page->_refcount. * * Note that if SetPageDirty is always performed via set_page_dirty, * and thus under tree_lock, then this ordering is not required. @@ -877,7 +898,7 @@ static void page_check_dirty_writeback(struct page *page, * shrink_page_list() returns the number of reclaimed pages */ static unsigned long shrink_page_list(struct list_head *page_list, - struct zone *zone, + struct pglist_data *pgdat, struct scan_control *sc, enum ttu_flags ttu_flags, unsigned long *ret_nr_dirty, @@ -917,7 +938,6 @@ static unsigned long shrink_page_list(struct list_head *page_list, goto keep; VM_BUG_ON_PAGE(PageActive(page), page); - VM_BUG_ON_PAGE(page_zone(page) != zone, page); sc->nr_scanned++; @@ -996,7 +1016,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, /* Case 1 above */ if (current_is_kswapd() && PageReclaim(page) && - test_bit(ZONE_WRITEBACK, &zone->flags)) { + test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { nr_immediate++; goto keep_locked; @@ -1055,8 +1075,14 @@ static unsigned long shrink_page_list(struct list_head *page_list, /* Adding to swap updated mapping */ mapping = page_mapping(page); + } else if (unlikely(PageTransHuge(page))) { + /* Split file THP */ + if (split_huge_page_to_list(page, page_list)) + goto keep_locked; } + VM_BUG_ON_PAGE(PageTransHuge(page), page); + /* * The page is mapped into the page tables of one or more * processes. Try to unmap it here. @@ -1086,14 +1112,14 @@ static unsigned long shrink_page_list(struct list_head *page_list, */ if (page_is_file_cache(page) && (!current_is_kswapd() || - !test_bit(ZONE_DIRTY, &zone->flags))) { + !test_bit(PGDAT_DIRTY, &pgdat->flags))) { /* * Immediately reclaim when written back. * Similar in principal to deactivate_page() * except we already have the page isolated * and know it's dirty */ - inc_zone_page_state(page, NR_VMSCAN_IMMEDIATE); + inc_node_page_state(page, NR_VMSCAN_IMMEDIATE); SetPageReclaim(page); goto keep_locked; @@ -1254,17 +1280,17 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, list_for_each_entry_safe(page, next, page_list, lru) { if (page_is_file_cache(page) && !PageDirty(page) && - !isolated_balloon_page(page)) { + !__PageMovable(page)) { ClearPageActive(page); list_move(&page->lru, &clean_pages); } } - ret = shrink_page_list(&clean_pages, zone, &sc, + ret = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, TTU_UNMAP|TTU_IGNORE_ACCESS, &dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true); list_splice(&clean_pages, page_list); - mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret); + mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -ret); return ret; } @@ -1342,8 +1368,31 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode) return ret; } + +/* + * Update LRU sizes after isolating pages. The LRU size updates must + * be complete before mem_cgroup_update_lru_size due to a santity check. + */ +static __always_inline void update_lru_sizes(struct lruvec *lruvec, + enum lru_list lru, unsigned long *nr_zone_taken, + unsigned long nr_taken) +{ + int zid; + + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + if (!nr_zone_taken[zid]) + continue; + + __update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); + } + +#ifdef CONFIG_MEMCG + mem_cgroup_update_lru_size(lruvec, lru, -nr_taken); +#endif +} + /* - * zone->lru_lock is heavily contended. Some of the functions that + * zone_lru_lock is heavily contended. Some of the functions that * shrink the lists perform better by taking out a batch of pages * and working on them outside the LRU lock. * @@ -1369,24 +1418,38 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, { struct list_head *src = &lruvec->lists[lru]; unsigned long nr_taken = 0; - unsigned long scan; + unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 }; + unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; + unsigned long scan, nr_pages; + LIST_HEAD(pages_skipped); for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan && - !list_empty(src); scan++) { + !list_empty(src);) { struct page *page; - int nr_pages; page = lru_to_page(src); prefetchw_prev_lru_page(page, src, flags); VM_BUG_ON_PAGE(!PageLRU(page), page); + if (page_zonenum(page) > sc->reclaim_idx) { + list_move(&page->lru, &pages_skipped); + nr_skipped[page_zonenum(page)]++; + continue; + } + + /* + * Account for scanned and skipped separetly to avoid the pgdat + * being prematurely marked unreclaimable by pgdat_reclaimable. + */ + scan++; + switch (__isolate_lru_page(page, mode)) { case 0: nr_pages = hpage_nr_pages(page); - mem_cgroup_update_lru_size(lruvec, lru, -nr_pages); - list_move(&page->lru, dst); nr_taken += nr_pages; + nr_zone_taken[page_zonenum(page)] += nr_pages; + list_move(&page->lru, dst); break; case -EBUSY: @@ -1399,9 +1462,38 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, } } + /* + * Splice any skipped pages to the start of the LRU list. Note that + * this disrupts the LRU order when reclaiming for lower zones but + * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX + * scanning would soon rescan the same pages to skip and put the + * system at risk of premature OOM. + */ + if (!list_empty(&pages_skipped)) { + int zid; + unsigned long total_skipped = 0; + + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + if (!nr_skipped[zid]) + continue; + + __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]); + total_skipped += nr_skipped[zid]; + } + + /* + * Account skipped pages as a partial scan as the pgdat may be + * close to unreclaimable. If the LRU list is empty, account + * skipped pages as a full scan. + */ + scan += list_empty(src) ? total_skipped : total_skipped >> 2; + + list_splice(&pages_skipped, src); + } *nr_scanned = scan; - trace_mm_vmscan_lru_isolate(sc->order, nr_to_scan, scan, + trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan, nr_taken, mode, is_file_lru(lru)); + update_lru_sizes(lruvec, lru, nr_zone_taken, nr_taken); return nr_taken; } @@ -1441,8 +1533,8 @@ int isolate_lru_page(struct page *page) struct zone *zone = page_zone(page); struct lruvec *lruvec; - spin_lock_irq(&zone->lru_lock); - lruvec = mem_cgroup_page_lruvec(page, zone); + spin_lock_irq(zone_lru_lock(zone)); + lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); if (PageLRU(page)) { int lru = page_lru(page); get_page(page); @@ -1450,7 +1542,7 @@ int isolate_lru_page(struct page *page) del_page_from_lru_list(page, lruvec, lru); ret = 0; } - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(zone_lru_lock(zone)); } return ret; } @@ -1462,7 +1554,7 @@ int isolate_lru_page(struct page *page) * the LRU list will go small and be scanned faster than necessary, leading to * unnecessary swapping, thrashing and OOM. */ -static int too_many_isolated(struct zone *zone, int file, +static int too_many_isolated(struct pglist_data *pgdat, int file, struct scan_control *sc) { unsigned long inactive, isolated; @@ -1474,11 +1566,11 @@ static int too_many_isolated(struct zone *zone, int file, return 0; if (file) { - inactive = zone_page_state(zone, NR_INACTIVE_FILE); - isolated = zone_page_state(zone, NR_ISOLATED_FILE); + inactive = node_page_state(pgdat, NR_INACTIVE_FILE); + isolated = node_page_state(pgdat, NR_ISOLATED_FILE); } else { - inactive = zone_page_state(zone, NR_INACTIVE_ANON); - isolated = zone_page_state(zone, NR_ISOLATED_ANON); + inactive = node_page_state(pgdat, NR_INACTIVE_ANON); + isolated = node_page_state(pgdat, NR_ISOLATED_ANON); } /* @@ -1496,7 +1588,7 @@ static noinline_for_stack void putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) { struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; - struct zone *zone = lruvec_zone(lruvec); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); LIST_HEAD(pages_to_free); /* @@ -1509,13 +1601,13 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) VM_BUG_ON_PAGE(PageLRU(page), page); list_del(&page->lru); if (unlikely(!page_evictable(page))) { - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(&pgdat->lru_lock); putback_lru_page(page); - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(&pgdat->lru_lock); continue; } - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, pgdat); SetPageLRU(page); lru = page_lru(page); @@ -1532,10 +1624,10 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list) del_page_from_lru_list(page, lruvec, lru); if (unlikely(PageCompound(page))) { - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(&pgdat->lru_lock); mem_cgroup_uncharge(page); (*get_compound_page_dtor(page))(page); - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(&pgdat->lru_lock); } else list_add(&page->lru, &pages_to_free); } @@ -1560,8 +1652,32 @@ static int current_may_throttle(void) bdi_write_congested(current->backing_dev_info); } +static bool inactive_reclaimable_pages(struct lruvec *lruvec, + struct scan_control *sc, enum lru_list lru) +{ + int zid; + struct zone *zone; + int file = is_file_lru(lru); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); + + if (!global_reclaim(sc)) + return true; + + for (zid = sc->reclaim_idx; zid >= 0; zid--) { + zone = &pgdat->node_zones[zid]; + if (!populated_zone(zone)) + continue; + + if (zone_page_state_snapshot(zone, NR_ZONE_LRU_BASE + + LRU_FILE * file) >= SWAP_CLUSTER_MAX) + return true; + } + + return false; +} + /* - * shrink_inactive_list() is a helper for shrink_zone(). It returns the number + * shrink_inactive_list() is a helper for shrink_node(). It returns the number * of reclaimed pages */ static noinline_for_stack unsigned long @@ -1579,10 +1695,13 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, unsigned long nr_immediate = 0; isolate_mode_t isolate_mode = 0; int file = is_file_lru(lru); - struct zone *zone = lruvec_zone(lruvec); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; - while (unlikely(too_many_isolated(zone, file, sc))) { + if (!inactive_reclaimable_pages(lruvec, sc, lru)) + return 0; + + while (unlikely(too_many_isolated(pgdat, file, sc))) { congestion_wait(BLK_RW_ASYNC, HZ/10); /* We are about to die and free our memory. Return now. */ @@ -1597,49 +1716,45 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, if (!sc->may_writepage) isolate_mode |= ISOLATE_CLEAN; - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(&pgdat->lru_lock); nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list, &nr_scanned, sc, isolate_mode, lru); - __mod_zone_page_state(zone, NR_LRU_BASE + lru, -nr_taken); - __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken); + __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); + reclaim_stat->recent_scanned[file] += nr_taken; if (global_reclaim(sc)) { - __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned); + __mod_node_page_state(pgdat, NR_PAGES_SCANNED, nr_scanned); if (current_is_kswapd()) - __count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scanned); + __count_vm_events(PGSCAN_KSWAPD, nr_scanned); else - __count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scanned); + __count_vm_events(PGSCAN_DIRECT, nr_scanned); } - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(&pgdat->lru_lock); if (nr_taken == 0) return 0; - nr_reclaimed = shrink_page_list(&page_list, zone, sc, TTU_UNMAP, + nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, TTU_UNMAP, &nr_dirty, &nr_unqueued_dirty, &nr_congested, &nr_writeback, &nr_immediate, false); - spin_lock_irq(&zone->lru_lock); - - reclaim_stat->recent_scanned[file] += nr_taken; + spin_lock_irq(&pgdat->lru_lock); if (global_reclaim(sc)) { if (current_is_kswapd()) - __count_zone_vm_events(PGSTEAL_KSWAPD, zone, - nr_reclaimed); + __count_vm_events(PGSTEAL_KSWAPD, nr_reclaimed); else - __count_zone_vm_events(PGSTEAL_DIRECT, zone, - nr_reclaimed); + __count_vm_events(PGSTEAL_DIRECT, nr_reclaimed); } putback_inactive_pages(lruvec, &page_list); - __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken); + __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(&pgdat->lru_lock); mem_cgroup_uncharge_list(&page_list); free_hot_cold_page_list(&page_list, true); @@ -1659,7 +1774,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * are encountered in the nr_immediate check below. */ if (nr_writeback && nr_writeback == nr_taken) - set_bit(ZONE_WRITEBACK, &zone->flags); + set_bit(PGDAT_WRITEBACK, &pgdat->flags); /* * Legacy memcg will stall in page writeback so avoid forcibly @@ -1671,16 +1786,16 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * backed by a congested BDI and wait_iff_congested will stall. */ if (nr_dirty && nr_dirty == nr_congested) - set_bit(ZONE_CONGESTED, &zone->flags); + set_bit(PGDAT_CONGESTED, &pgdat->flags); /* * If dirty pages are scanned that are not queued for IO, it * implies that flushers are not keeping up. In this case, flag - * the zone ZONE_DIRTY and kswapd will start writing pages from + * the pgdat PGDAT_DIRTY and kswapd will start writing pages from * reclaim context. */ if (nr_unqueued_dirty == nr_taken) - set_bit(ZONE_DIRTY, &zone->flags); + set_bit(PGDAT_DIRTY, &pgdat->flags); /* * If kswapd scans pages marked marked for immediate @@ -1699,9 +1814,10 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, */ if (!sc->hibernation_mode && !current_is_kswapd() && current_may_throttle()) - wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10); + wait_iff_congested(pgdat, BLK_RW_ASYNC, HZ/10); - trace_mm_vmscan_lru_shrink_inactive(zone, nr_scanned, nr_reclaimed, + trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, + nr_scanned, nr_reclaimed, sc->priority, file); return nr_reclaimed; } @@ -1713,14 +1829,14 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * processes, from rmap. * * If the pages are mostly unmapped, the processing is fast and it is - * appropriate to hold zone->lru_lock across the whole operation. But if + * appropriate to hold zone_lru_lock across the whole operation. But if * the pages are mapped, the processing is slow (page_referenced()) so we - * should drop zone->lru_lock around each page. It's impossible to balance + * should drop zone_lru_lock around each page. It's impossible to balance * this, so instead we remove the pages from the LRU while processing them. * It is safe to rely on PG_active against the non-LRU pages in here because * nobody will play with that bit on a non-LRU page. * - * The downside is that we have to touch page->_count against each page. + * The downside is that we have to touch page->_refcount against each page. * But we had to alter page->flags anyway. */ @@ -1729,20 +1845,20 @@ static void move_active_pages_to_lru(struct lruvec *lruvec, struct list_head *pages_to_free, enum lru_list lru) { - struct zone *zone = lruvec_zone(lruvec); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); unsigned long pgmoved = 0; struct page *page; int nr_pages; while (!list_empty(list)) { page = lru_to_page(list); - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, pgdat); VM_BUG_ON_PAGE(PageLRU(page), page); SetPageLRU(page); nr_pages = hpage_nr_pages(page); - mem_cgroup_update_lru_size(lruvec, lru, nr_pages); + update_lru_size(lruvec, lru, page_zonenum(page), nr_pages); list_move(&page->lru, &lruvec->lists[lru]); pgmoved += nr_pages; @@ -1752,15 +1868,15 @@ static void move_active_pages_to_lru(struct lruvec *lruvec, del_page_from_lru_list(page, lruvec, lru); if (unlikely(PageCompound(page))) { - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(&pgdat->lru_lock); mem_cgroup_uncharge(page); (*get_compound_page_dtor(page))(page); - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(&pgdat->lru_lock); } else list_add(&page->lru, pages_to_free); } } - __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved); + if (!is_active_lru(lru)) __count_vm_events(PGDEACTIVATE, pgmoved); } @@ -1781,7 +1897,7 @@ static void shrink_active_list(unsigned long nr_to_scan, unsigned long nr_rotated = 0; isolate_mode_t isolate_mode = 0; int file = is_file_lru(lru); - struct zone *zone = lruvec_zone(lruvec); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); lru_add_drain(); @@ -1790,19 +1906,19 @@ static void shrink_active_list(unsigned long nr_to_scan, if (!sc->may_writepage) isolate_mode |= ISOLATE_CLEAN; - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(&pgdat->lru_lock); nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, isolate_mode, lru); - if (global_reclaim(sc)) - __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned); + __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); reclaim_stat->recent_scanned[file] += nr_taken; - __count_zone_vm_events(PGREFILL, zone, nr_scanned); - __mod_zone_page_state(zone, NR_LRU_BASE + lru, -nr_taken); - __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken); - spin_unlock_irq(&zone->lru_lock); + if (global_reclaim(sc)) + __mod_node_page_state(pgdat, NR_PAGES_SCANNED, nr_scanned); + __count_vm_events(PGREFILL, nr_scanned); + + spin_unlock_irq(&pgdat->lru_lock); while (!list_empty(&l_hold)) { cond_resched(); @@ -1847,7 +1963,7 @@ static void shrink_active_list(unsigned long nr_to_scan, /* * Move pages back to the lru list. */ - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(&pgdat->lru_lock); /* * Count referenced pages from currently used mappings as rotated, * even though only some of them are actually re-activated. This @@ -1858,90 +1974,94 @@ static void shrink_active_list(unsigned long nr_to_scan, move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru); move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE); - __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken); - spin_unlock_irq(&zone->lru_lock); + __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); + spin_unlock_irq(&pgdat->lru_lock); mem_cgroup_uncharge_list(&l_hold); free_hot_cold_page_list(&l_hold, true); } -#ifdef CONFIG_SWAP -static bool inactive_anon_is_low_global(struct zone *zone) -{ - unsigned long active, inactive; - - active = zone_page_state(zone, NR_ACTIVE_ANON); - inactive = zone_page_state(zone, NR_INACTIVE_ANON); - - return inactive * zone->inactive_ratio < active; -} - -/** - * inactive_anon_is_low - check if anonymous pages need to be deactivated - * @lruvec: LRU vector to check +/* + * The inactive anon list should be small enough that the VM never has + * to do too much work. + * + * The inactive file list should be small enough to leave most memory + * to the established workingset on the scan-resistant active list, + * but large enough to avoid thrashing the aggregate readahead window. * - * Returns true if the zone does not have enough inactive anon pages, - * meaning some active anon pages need to be deactivated. + * Both inactive lists should also be large enough that each inactive + * page has a chance to be referenced again before it is reclaimed. + * + * The inactive_ratio is the target ratio of ACTIVE to INACTIVE pages + * on this LRU, maintained by the pageout code. A zone->inactive_ratio + * of 3 means 3:1 or 25% of the pages are kept on the inactive list. + * + * total target max + * memory ratio inactive + * ------------------------------------- + * 10MB 1 5MB + * 100MB 1 50MB + * 1GB 3 250MB + * 10GB 10 0.9GB + * 100GB 31 3GB + * 1TB 101 10GB + * 10TB 320 32GB */ -static bool inactive_anon_is_low(struct lruvec *lruvec) +static bool inactive_list_is_low(struct lruvec *lruvec, bool file, + struct scan_control *sc) { + unsigned long inactive_ratio; + unsigned long inactive; + unsigned long active; + unsigned long gb; + struct pglist_data *pgdat = lruvec_pgdat(lruvec); + int zid; + /* * If we don't have swap space, anonymous page deactivation * is pointless. */ - if (!total_swap_pages) + if (!file && !total_swap_pages) return false; - if (!mem_cgroup_disabled()) - return mem_cgroup_inactive_anon_is_low(lruvec); + inactive = lruvec_lru_size(lruvec, file * LRU_FILE); + active = lruvec_lru_size(lruvec, file * LRU_FILE + LRU_ACTIVE); - return inactive_anon_is_low_global(lruvec_zone(lruvec)); -} -#else -static inline bool inactive_anon_is_low(struct lruvec *lruvec) -{ - return false; -} -#endif + /* + * For zone-constrained allocations, it is necessary to check if + * deactivations are required for lowmem to be reclaimed. This + * calculates the inactive/active pages available in eligible zones. + */ + for (zid = sc->reclaim_idx + 1; zid < MAX_NR_ZONES; zid++) { + struct zone *zone = &pgdat->node_zones[zid]; + unsigned long inactive_zone, active_zone; -/** - * inactive_file_is_low - check if file pages need to be deactivated - * @lruvec: LRU vector to check - * - * When the system is doing streaming IO, memory pressure here - * ensures that active file pages get deactivated, until more - * than half of the file pages are on the inactive list. - * - * Once we get to that situation, protect the system's working - * set from being evicted by disabling active file page aging. - * - * This uses a different ratio than the anonymous pages, because - * the page cache uses a use-once replacement algorithm. - */ -static bool inactive_file_is_low(struct lruvec *lruvec) -{ - unsigned long inactive; - unsigned long active; + if (!populated_zone(zone)) + continue; - inactive = lruvec_lru_size(lruvec, LRU_INACTIVE_FILE); - active = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE); + inactive_zone = zone_page_state(zone, + NR_ZONE_LRU_BASE + (file * LRU_FILE)); + active_zone = zone_page_state(zone, + NR_ZONE_LRU_BASE + (file * LRU_FILE) + LRU_ACTIVE); - return active > inactive; -} + inactive -= min(inactive, inactive_zone); + active -= min(active, active_zone); + } -static bool inactive_list_is_low(struct lruvec *lruvec, enum lru_list lru) -{ - if (is_file_lru(lru)) - return inactive_file_is_low(lruvec); + gb = (inactive + active) >> (30 - PAGE_SHIFT); + if (gb) + inactive_ratio = int_sqrt(10 * gb); else - return inactive_anon_is_low(lruvec); + inactive_ratio = 1; + + return inactive * inactive_ratio < active; } static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc) { if (is_active_lru(lru)) { - if (inactive_list_is_low(lruvec, lru)) + if (inactive_list_is_low(lruvec, is_file_lru(lru), sc)) shrink_active_list(nr_to_scan, lruvec, sc, lru); return 0; } @@ -1973,7 +2093,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; u64 fraction[2]; u64 denominator = 0; /* gcc */ - struct zone *zone = lruvec_zone(lruvec); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); unsigned long anon_prio, file_prio; enum scan_balance scan_balance; unsigned long anon, file; @@ -1994,7 +2114,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, * well. */ if (current_is_kswapd()) { - if (!zone_reclaimable(zone)) + if (!pgdat_reclaimable(pgdat)) force_scan = true; if (!mem_cgroup_online(memcg)) force_scan = true; @@ -2040,14 +2160,24 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, * anon pages. Try to detect this based on file LRU size. */ if (global_reclaim(sc)) { - unsigned long zonefile; - unsigned long zonefree; + unsigned long pgdatfile; + unsigned long pgdatfree; + int z; + unsigned long total_high_wmark = 0; - zonefree = zone_page_state(zone, NR_FREE_PAGES); - zonefile = zone_page_state(zone, NR_ACTIVE_FILE) + - zone_page_state(zone, NR_INACTIVE_FILE); + pgdatfree = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); + pgdatfile = node_page_state(pgdat, NR_ACTIVE_FILE) + + node_page_state(pgdat, NR_INACTIVE_FILE); - if (unlikely(zonefile + zonefree <= high_wmark_pages(zone))) { + for (z = 0; z < MAX_NR_ZONES; z++) { + struct zone *zone = &pgdat->node_zones[z]; + if (!populated_zone(zone)) + continue; + + total_high_wmark += high_wmark_pages(zone); + } + + if (unlikely(pgdatfile + pgdatfree <= total_high_wmark)) { scan_balance = SCAN_ANON; goto out; } @@ -2062,7 +2192,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, * lruvec even if it has plenty of old anonymous pages unless the * system is under heavy pressure. */ - if (!inactive_file_is_low(lruvec) && + if (!inactive_list_is_low(lruvec, true, sc) && lruvec_lru_size(lruvec, LRU_INACTIVE_FILE) >> sc->priority) { scan_balance = SCAN_FILE; goto out; @@ -2094,7 +2224,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE) + lruvec_lru_size(lruvec, LRU_INACTIVE_FILE); - spin_lock_irq(&zone->lru_lock); + spin_lock_irq(&pgdat->lru_lock); if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) { reclaim_stat->recent_scanned[0] /= 2; reclaim_stat->recent_rotated[0] /= 2; @@ -2115,7 +2245,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, fp = file_prio * (reclaim_stat->recent_scanned[1] + 1); fp /= reclaim_stat->recent_rotated[1] + 1; - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(&pgdat->lru_lock); fraction[0] = ap; fraction[1] = fp; @@ -2191,12 +2321,12 @@ static inline void init_tlb_ubc(void) #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ /* - * This is a basic per-zone page freer. Used by both kswapd and direct reclaim. + * This is a basic per-node page freer. Used by both kswapd and direct reclaim. */ -static void shrink_zone_memcg(struct zone *zone, struct mem_cgroup *memcg, +static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memcg, struct scan_control *sc, unsigned long *lru_pages) { - struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg); + struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg); unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; unsigned long nr_to_scan; @@ -2304,7 +2434,7 @@ static void shrink_zone_memcg(struct zone *zone, struct mem_cgroup *memcg, * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ - if (inactive_anon_is_low(lruvec)) + if (inactive_list_is_low(lruvec, false, sc)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); @@ -2329,13 +2459,14 @@ static bool in_reclaim_compaction(struct scan_control *sc) * calls try_to_compact_zone() that it will have enough free pages to succeed. * It will give up earlier than that if there is difficulty reclaiming pages. */ -static inline bool should_continue_reclaim(struct zone *zone, +static inline bool should_continue_reclaim(struct pglist_data *pgdat, unsigned long nr_reclaimed, unsigned long nr_scanned, struct scan_control *sc) { unsigned long pages_for_compaction; unsigned long inactive_lru_pages; + int z; /* If not in reclaim/compaction mode, stop */ if (!in_reclaim_compaction(sc)) @@ -2369,25 +2500,32 @@ static inline bool should_continue_reclaim(struct zone *zone, * inactive lists are large enough, continue reclaiming */ pages_for_compaction = (2UL << sc->order); - inactive_lru_pages = zone_page_state(zone, NR_INACTIVE_FILE); + inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); if (get_nr_swap_pages() > 0) - inactive_lru_pages += zone_page_state(zone, NR_INACTIVE_ANON); + inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); if (sc->nr_reclaimed < pages_for_compaction && inactive_lru_pages > pages_for_compaction) return true; /* If compaction would go ahead or the allocation would succeed, stop */ - switch (compaction_suitable(zone, sc->order, 0, 0)) { - case COMPACT_PARTIAL: - case COMPACT_CONTINUE: - return false; - default: - return true; + for (z = 0; z <= sc->reclaim_idx; z++) { + struct zone *zone = &pgdat->node_zones[z]; + if (!populated_zone(zone)) + continue; + + switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) { + case COMPACT_PARTIAL: + case COMPACT_CONTINUE: + return false; + default: + /* check next zone */ + ; + } } + return true; } -static bool shrink_zone(struct zone *zone, struct scan_control *sc, - bool is_classzone) +static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct reclaim_state *reclaim_state = current->reclaim_state; unsigned long nr_reclaimed, nr_scanned; @@ -2396,10 +2534,10 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, do { struct mem_cgroup *root = sc->target_mem_cgroup; struct mem_cgroup_reclaim_cookie reclaim = { - .zone = zone, + .pgdat = pgdat, .priority = sc->priority, }; - unsigned long zone_lru_pages = 0; + unsigned long node_lru_pages = 0; struct mem_cgroup *memcg; nr_reclaimed = sc->nr_reclaimed; @@ -2420,11 +2558,11 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, reclaimed = sc->nr_reclaimed; scanned = sc->nr_scanned; - shrink_zone_memcg(zone, memcg, sc, &lru_pages); - zone_lru_pages += lru_pages; + shrink_node_memcg(pgdat, memcg, sc, &lru_pages); + node_lru_pages += lru_pages; - if (memcg && is_classzone) - shrink_slab(sc->gfp_mask, zone_to_nid(zone), + if (memcg) + shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->nr_scanned - scanned, lru_pages); @@ -2436,7 +2574,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, /* * Direct reclaim and kswapd have to scan all memory * cgroups to fulfill the overall scan target for the - * zone. + * node. * * Limit reclaim, on the other hand, only cares about * nr_to_reclaim pages to be reclaimed and it will @@ -2454,10 +2592,10 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, * Shrink the slab caches in the same proportion that * the eligible LRU pages were scanned. */ - if (global_reclaim(sc) && is_classzone) - shrink_slab(sc->gfp_mask, zone_to_nid(zone), NULL, + if (global_reclaim(sc)) + shrink_slab(sc->gfp_mask, pgdat->node_id, NULL, sc->nr_scanned - nr_scanned, - zone_lru_pages); + node_lru_pages); if (reclaim_state) { sc->nr_reclaimed += reclaim_state->reclaimed_slab; @@ -2472,7 +2610,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, if (sc->nr_reclaimed - nr_reclaimed) reclaimable = true; - } while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed, + } while (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, sc->nr_scanned - nr_scanned, sc)); return reclaimable; @@ -2482,9 +2620,9 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, * Returns true if compaction should go ahead for a high-order request, or * the high-order allocation would succeed without compaction. */ -static inline bool compaction_ready(struct zone *zone, int order) +static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) { - unsigned long balance_gap, watermark; + unsigned long watermark; bool watermark_ok; /* @@ -2493,23 +2631,21 @@ static inline bool compaction_ready(struct zone *zone, int order) * there is a buffer of free pages available to give compaction * a reasonable chance of completing and allocating the page */ - balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP( - zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO)); - watermark = high_wmark_pages(zone) + balance_gap + (2UL << order); - watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0); + watermark = high_wmark_pages(zone) + (2UL << sc->order); + watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); /* * If compaction is deferred, reclaim up to a point where * compaction will have a chance of success when re-enabled */ - if (compaction_deferred(zone, order)) + if (compaction_deferred(zone, sc->order)) return watermark_ok; /* * If compaction is not ready to start and allocation is not likely * to succeed without it, then keep reclaiming. */ - if (compaction_suitable(zone, order, 0, 0) == COMPACT_SKIPPED) + if (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx) == COMPACT_SKIPPED) return false; return watermark_ok; @@ -2520,28 +2656,17 @@ static inline bool compaction_ready(struct zone *zone, int order) * try to reclaim pages from zones which will satisfy the caller's allocation * request. * - * We reclaim from a zone even if that zone is over high_wmark_pages(zone). - * Because: - * a) The caller may be trying to free *extra* pages to satisfy a higher-order - * allocation or - * b) The target zone may be at high_wmark_pages(zone) but the lower zones - * must go *over* high_wmark_pages(zone) to satisfy the `incremental min' - * zone defense algorithm. - * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. - * - * Returns true if a zone was reclaimable. */ -static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) +static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; gfp_t orig_mask; - enum zone_type requested_highidx = gfp_zone(sc->gfp_mask); - bool reclaimable = false; + pg_data_t *last_pgdat = NULL; /* * If the number of buffer_heads in the machine exceeds the maximum @@ -2549,21 +2674,13 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) * highmem pages could be pinning lowmem pages storing buffer_heads */ orig_mask = sc->gfp_mask; - if (buffer_heads_over_limit) + if (buffer_heads_over_limit) { sc->gfp_mask |= __GFP_HIGHMEM; + sc->reclaim_idx = gfp_zone(sc->gfp_mask); + } for_each_zone_zonelist_nodemask(zone, z, zonelist, - requested_highidx, sc->nodemask) { - enum zone_type classzone_idx; - - if (!populated_zone(zone)) - continue; - - classzone_idx = requested_highidx; - while (!populated_zone(zone->zone_pgdat->node_zones + - classzone_idx)) - classzone_idx--; - + sc->reclaim_idx, sc->nodemask) { /* * Take care memory controller reclaiming has small influence * to global LRU. @@ -2574,7 +2691,7 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) continue; if (sc->priority != DEF_PRIORITY && - !zone_reclaimable(zone)) + !pgdat_reclaimable(zone->zone_pgdat)) continue; /* Let kswapd poll it */ /* @@ -2588,35 +2705,40 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) */ if (IS_ENABLED(CONFIG_COMPACTION) && sc->order > PAGE_ALLOC_COSTLY_ORDER && - zonelist_zone_idx(z) <= requested_highidx && - compaction_ready(zone, sc->order)) { + compaction_ready(zone, sc)) { sc->compaction_ready = true; continue; } /* + * Shrink each node in the zonelist once. If the + * zonelist is ordered by zone (not the default) then a + * node may be shrunk multiple times but in that case + * the user prefers lower zones being preserved. + */ + if (zone->zone_pgdat == last_pgdat) + continue; + + /* * This steals pages from memory cgroups over softlimit * and returns the number of reclaimed pages and * scanned pages. This works for global memory pressure * and balancing, not for a memcg's limit. */ nr_soft_scanned = 0; - nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone, + nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone->zone_pgdat, sc->order, sc->gfp_mask, &nr_soft_scanned); sc->nr_reclaimed += nr_soft_reclaimed; sc->nr_scanned += nr_soft_scanned; - if (nr_soft_reclaimed) - reclaimable = true; /* need some check for avoid more shrink_zone() */ } - if (shrink_zone(zone, sc, zone_idx(zone) == classzone_idx)) - reclaimable = true; - - if (global_reclaim(sc) && - !reclaimable && zone_reclaimable(zone)) - reclaimable = true; + /* See comment about same check for global reclaim above */ + if (zone->zone_pgdat == last_pgdat) + continue; + last_pgdat = zone->zone_pgdat; + shrink_node(zone->zone_pgdat, sc); } /* @@ -2624,8 +2746,6 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) * promoted it to __GFP_HIGHMEM. */ sc->gfp_mask = orig_mask; - - return reclaimable; } /* @@ -2650,18 +2770,17 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, int initial_priority = sc->priority; unsigned long total_scanned = 0; unsigned long writeback_threshold; - bool zones_reclaimable; retry: delayacct_freepages_start(); if (global_reclaim(sc)) - count_vm_event(ALLOCSTALL); + __count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1); do { vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, sc->priority); sc->nr_scanned = 0; - zones_reclaimable = shrink_zones(zonelist, sc); + shrink_zones(zonelist, sc); total_scanned += sc->nr_scanned; if (sc->nr_reclaimed >= sc->nr_to_reclaim) @@ -2708,10 +2827,6 @@ retry: goto retry; } - /* Any of the zones still reclaimable? Don't OOM. */ - if (zones_reclaimable) - return 1; - return 0; } @@ -2726,7 +2841,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; if (!populated_zone(zone) || - zone_reclaimable_pages(zone) == 0) + pgdat_reclaimable_pages(pgdat) == 0) continue; pfmemalloc_reserve += min_wmark_pages(zone); @@ -2741,7 +2856,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) /* kswapd must be awake if processes are being throttled */ if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { - pgdat->classzone_idx = min(pgdat->classzone_idx, + pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx, (enum zone_type)ZONE_NORMAL); wake_up_interruptible(&pgdat->kswapd_wait); } @@ -2849,6 +2964,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)), + .reclaim_idx = gfp_zone(gfp_mask), .order = order, .nodemask = nodemask, .priority = DEF_PRIORITY, @@ -2867,7 +2983,8 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, trace_mm_vmscan_direct_reclaim_begin(order, sc.may_writepage, - gfp_mask); + gfp_mask, + sc.reclaim_idx); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); @@ -2878,9 +2995,9 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, #ifdef CONFIG_MEMCG -unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, +unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, gfp_t gfp_mask, bool noswap, - struct zone *zone, + pg_data_t *pgdat, unsigned long *nr_scanned) { struct scan_control sc = { @@ -2888,6 +3005,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, .target_mem_cgroup = memcg, .may_writepage = !laptop_mode, .may_unmap = 1, + .reclaim_idx = MAX_NR_ZONES - 1, .may_swap = !noswap, }; unsigned long lru_pages; @@ -2897,16 +3015,17 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order, sc.may_writepage, - sc.gfp_mask); + sc.gfp_mask, + sc.reclaim_idx); /* * NOTE: Although we can get the priority field, using it * here is not a good idea, since it limits the pages we can scan. - * if we don't reclaim here, the shrink_zone from balance_pgdat + * if we don't reclaim here, the shrink_node from balance_pgdat * will pick up pages from other mem cgroup's as well. We hack * the priority and make it zero. */ - shrink_zone_memcg(zone, memcg, &sc, &lru_pages); + shrink_node_memcg(pgdat, memcg, &sc, &lru_pages); trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); @@ -2926,6 +3045,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), + .reclaim_idx = MAX_NR_ZONES - 1, .target_mem_cgroup = memcg, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, @@ -2944,7 +3064,8 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, trace_mm_vmscan_memcg_reclaim_begin(0, sc.may_writepage, - sc.gfp_mask); + sc.gfp_mask, + sc.reclaim_idx); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); @@ -2954,7 +3075,8 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, } #endif -static void age_active_anon(struct zone *zone, struct scan_control *sc) +static void age_active_anon(struct pglist_data *pgdat, + struct scan_control *sc) { struct mem_cgroup *memcg; @@ -2963,9 +3085,9 @@ static void age_active_anon(struct zone *zone, struct scan_control *sc) memcg = mem_cgroup_iter(NULL, NULL, NULL); do { - struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg); + struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg); - if (inactive_anon_is_low(lruvec)) + if (inactive_list_is_low(lruvec, false, sc)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); @@ -2973,82 +3095,21 @@ static void age_active_anon(struct zone *zone, struct scan_control *sc) } while (memcg); } -static bool zone_balanced(struct zone *zone, int order, bool highorder, - unsigned long balance_gap, int classzone_idx) +static bool zone_balanced(struct zone *zone, int order, int classzone_idx) { - unsigned long mark = high_wmark_pages(zone) + balance_gap; + unsigned long mark = high_wmark_pages(zone); + + if (!zone_watermark_ok_safe(zone, order, mark, classzone_idx)) + return false; /* - * When checking from pgdat_balanced(), kswapd should stop and sleep - * when it reaches the high order-0 watermark and let kcompactd take - * over. Other callers such as wakeup_kswapd() want to determine the - * true high-order watermark. + * If any eligible zone is balanced then the node is not considered + * to be congested or dirty */ - if (IS_ENABLED(CONFIG_COMPACTION) && !highorder) { - mark += (1UL << order); - order = 0; - } - - return zone_watermark_ok_safe(zone, order, mark, classzone_idx); -} - -/* - * pgdat_balanced() is used when checking if a node is balanced. - * - * For order-0, all zones must be balanced! - * - * For high-order allocations only zones that meet watermarks and are in a - * zone allowed by the callers classzone_idx are added to balanced_pages. The - * total of balanced pages must be at least 25% of the zones allowed by - * classzone_idx for the node to be considered balanced. Forcing all zones to - * be balanced for high orders can cause excessive reclaim when there are - * imbalanced zones. - * The choice of 25% is due to - * o a 16M DMA zone that is balanced will not balance a zone on any - * reasonable sized machine - * o On all other machines, the top zone must be at least a reasonable - * percentage of the middle zones. For example, on 32-bit x86, highmem - * would need to be at least 256M for it to be balance a whole node. - * Similarly, on x86-64 the Normal zone would need to be at least 1G - * to balance a node on its own. These seemed like reasonable ratios. - */ -static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) -{ - unsigned long managed_pages = 0; - unsigned long balanced_pages = 0; - int i; - - /* Check the watermark levels */ - for (i = 0; i <= classzone_idx; i++) { - struct zone *zone = pgdat->node_zones + i; - - if (!populated_zone(zone)) - continue; - - managed_pages += zone->managed_pages; - - /* - * A special case here: - * - * balance_pgdat() skips over all_unreclaimable after - * DEF_PRIORITY. Effectively, it considers them balanced so - * they must be considered balanced here as well! - */ - if (!zone_reclaimable(zone)) { - balanced_pages += zone->managed_pages; - continue; - } + clear_bit(PGDAT_CONGESTED, &zone->zone_pgdat->flags); + clear_bit(PGDAT_DIRTY, &zone->zone_pgdat->flags); - if (zone_balanced(zone, order, false, 0, i)) - balanced_pages += zone->managed_pages; - else if (!order) - return false; - } - - if (order) - return balanced_pages >= (managed_pages >> 2); - else - return true; + return true; } /* @@ -3057,12 +3118,9 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) * * Returns true if kswapd is ready to sleep */ -static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, - int classzone_idx) +static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx) { - /* If a direct reclaimer woke kswapd within HZ/10, it's premature */ - if (remaining) - return false; + int i; /* * The throttled processes are normally woken up in balance_pgdat() as @@ -3080,91 +3138,81 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, if (waitqueue_active(&pgdat->pfmemalloc_wait)) wake_up_all(&pgdat->pfmemalloc_wait); - return pgdat_balanced(pgdat, order, classzone_idx); + for (i = 0; i <= classzone_idx; i++) { + struct zone *zone = pgdat->node_zones + i; + + if (!populated_zone(zone)) + continue; + + if (!zone_balanced(zone, order, classzone_idx)) + return false; + } + + return true; } /* - * kswapd shrinks the zone by the number of pages required to reach - * the high watermark. + * kswapd shrinks a node of pages that are at or below the highest usable + * zone that is currently unbalanced. * * Returns true if kswapd scanned at least the requested number of pages to * reclaim or if the lack of progress was due to pages under writeback. * This is used to determine if the scanning priority needs to be raised. */ -static bool kswapd_shrink_zone(struct zone *zone, - int classzone_idx, +static bool kswapd_shrink_node(pg_data_t *pgdat, struct scan_control *sc) { - unsigned long balance_gap; - bool lowmem_pressure; + struct zone *zone; + int z; - /* Reclaim above the high watermark. */ - sc->nr_to_reclaim = max(SWAP_CLUSTER_MAX, high_wmark_pages(zone)); + /* Reclaim a number of pages proportional to the number of zones */ + sc->nr_to_reclaim = 0; + for (z = 0; z <= sc->reclaim_idx; z++) { + zone = pgdat->node_zones + z; + if (!populated_zone(zone)) + continue; - /* - * We put equal pressure on every zone, unless one zone has way too - * many pages free already. The "too many pages" is defined as the - * high wmark plus a "gap" where the gap is either the low - * watermark or 1% of the zone, whichever is smaller. - */ - balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP( - zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO)); + sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX); + } /* - * If there is no low memory pressure or the zone is balanced then no - * reclaim is necessary + * Historically care was taken to put equal pressure on all zones but + * now pressure is applied based on node LRU order. */ - lowmem_pressure = (buffer_heads_over_limit && is_highmem(zone)); - if (!lowmem_pressure && zone_balanced(zone, sc->order, false, - balance_gap, classzone_idx)) - return true; - - shrink_zone(zone, sc, zone_idx(zone) == classzone_idx); - - clear_bit(ZONE_WRITEBACK, &zone->flags); + shrink_node(pgdat, sc); /* - * If a zone reaches its high watermark, consider it to be no longer - * congested. It's possible there are dirty pages backed by congested - * BDIs but as pressure is relieved, speculatively avoid congestion - * waits. + * Fragmentation may mean that the system cannot be rebalanced for + * high-order allocations. If twice the allocation size has been + * reclaimed then recheck watermarks only at order-0 to prevent + * excessive reclaim. Assume that a process requested a high-order + * can direct reclaim/compact. */ - if (zone_reclaimable(zone) && - zone_balanced(zone, sc->order, false, 0, classzone_idx)) { - clear_bit(ZONE_CONGESTED, &zone->flags); - clear_bit(ZONE_DIRTY, &zone->flags); - } + if (sc->order && sc->nr_reclaimed >= 2UL << sc->order) + sc->order = 0; return sc->nr_scanned >= sc->nr_to_reclaim; } /* - * For kswapd, balance_pgdat() will work across all this node's zones until - * they are all at high_wmark_pages(zone). - * - * Returns the highest zone idx kswapd was reclaiming at + * For kswapd, balance_pgdat() will reclaim pages across a node from zones + * that are eligible for use by the caller until at least one zone is + * balanced. * - * There is special handling here for zones which are full of pinned pages. - * This can happen if the pages are all mlocked, or if they are all used by - * device drivers (say, ZONE_DMA). Or if they are all in use by hugetlb. - * What we do is to detect the case where all pages in the zone have been - * scanned twice and there has been zero successful reclaim. Mark the zone as - * dead and from now on, only perform a short scan. Basically we're polling - * the zone for when the problem goes away. + * Returns the order kswapd finished reclaiming at. * * kswapd scans the zones in the highmem->normal->dma direction. It skips * zones which have free_pages > high_wmark_pages(zone), but once a zone is - * found to have free_pages <= high_wmark_pages(zone), we scan that zone and the - * lower zones regardless of the number of free pages in the lower zones. This - * interoperates with the page allocator fallback scheme to ensure that aging - * of pages is balanced across the zones. + * found to have free_pages <= high_wmark_pages(zone), any page is that zone + * or lower is eligible for reclaim until at least one usable zone is + * balanced. */ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) { int i; - int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */ unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; + struct zone *zone; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .order = order, @@ -3179,100 +3227,77 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) bool raise_priority = true; sc.nr_reclaimed = 0; + sc.reclaim_idx = classzone_idx; /* - * Scan in the highmem->dma direction for the highest - * zone which needs scanning + * If the number of buffer_heads exceeds the maximum allowed + * then consider reclaiming from all zones. This has a dual + * purpose -- on 64-bit systems it is expected that + * buffer_heads are stripped during active rotation. On 32-bit + * systems, highmem pages can pin lowmem memory and shrinking + * buffers can relieve lowmem pressure. Reclaim may still not + * go ahead if all eligible zones for the original allocation + * request are balanced to avoid excessive reclaim from kswapd. */ - for (i = pgdat->nr_zones - 1; i >= 0; i--) { - struct zone *zone = pgdat->node_zones + i; - - if (!populated_zone(zone)) - continue; - - if (sc.priority != DEF_PRIORITY && - !zone_reclaimable(zone)) - continue; - - /* - * Do some background aging of the anon list, to give - * pages a chance to be referenced before reclaiming. - */ - age_active_anon(zone, &sc); + if (buffer_heads_over_limit) { + for (i = MAX_NR_ZONES - 1; i >= 0; i--) { + zone = pgdat->node_zones + i; + if (!populated_zone(zone)) + continue; - /* - * If the number of buffer_heads in the machine - * exceeds the maximum allowed level and this node - * has a highmem zone, force kswapd to reclaim from - * it to relieve lowmem pressure. - */ - if (buffer_heads_over_limit && is_highmem_idx(i)) { - end_zone = i; + sc.reclaim_idx = i; break; } + } - if (!zone_balanced(zone, order, false, 0, 0)) { - end_zone = i; - break; - } else { - /* - * If balanced, clear the dirty and congested - * flags - */ - clear_bit(ZONE_CONGESTED, &zone->flags); - clear_bit(ZONE_DIRTY, &zone->flags); - } + /* + * Only reclaim if there are no eligible zones. Check from + * high to low zone as allocations prefer higher zones. + * Scanning from low to high zone would allow congestion to be + * cleared during a very small window when a small low + * zone was balanced even under extreme pressure when the + * overall node may be congested. Note that sc.reclaim_idx + * is not used as buffer_heads_over_limit may have adjusted + * it. + */ + for (i = classzone_idx; i >= 0; i--) { + zone = pgdat->node_zones + i; + if (!populated_zone(zone)) + continue; + + if (zone_balanced(zone, sc.order, classzone_idx)) + goto out; } - if (i < 0) - goto out; + /* + * Do some background aging of the anon list, to give + * pages a chance to be referenced before reclaiming. All + * pages are rotated regardless of classzone as this is + * about consistent aging. + */ + age_active_anon(pgdat, &sc); /* * If we're getting trouble reclaiming, start doing writepage * even in laptop mode. */ - if (sc.priority < DEF_PRIORITY - 2) + if (sc.priority < DEF_PRIORITY - 2 || !pgdat_reclaimable(pgdat)) sc.may_writepage = 1; + /* Call soft limit reclaim before calling shrink_node. */ + sc.nr_scanned = 0; + nr_soft_scanned = 0; + nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(pgdat, sc.order, + sc.gfp_mask, &nr_soft_scanned); + sc.nr_reclaimed += nr_soft_reclaimed; + /* - * Now scan the zone in the dma->highmem direction, stopping - * at the last zone which needs scanning. - * - * We do this because the page allocator works in the opposite - * direction. This prevents the page allocator from allocating - * pages behind kswapd's direction of progress, which would - * cause too much scanning of the lower zones. + * There should be no need to raise the scanning priority if + * enough pages are already being scanned that that high + * watermark would be met at 100% efficiency. */ - for (i = 0; i <= end_zone; i++) { - struct zone *zone = pgdat->node_zones + i; - - if (!populated_zone(zone)) - continue; - - if (sc.priority != DEF_PRIORITY && - !zone_reclaimable(zone)) - continue; - - sc.nr_scanned = 0; - - nr_soft_scanned = 0; - /* - * Call soft limit reclaim before calling shrink_zone. - */ - nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone, - order, sc.gfp_mask, - &nr_soft_scanned); - sc.nr_reclaimed += nr_soft_reclaimed; - - /* - * There should be no need to raise the scanning - * priority if enough pages are already being scanned - * that that high watermark would be met at 100% - * efficiency. - */ - if (kswapd_shrink_zone(zone, end_zone, &sc)) - raise_priority = false; - } + if (kswapd_shrink_node(pgdat, &sc)) + raise_priority = false; /* * If the low watermark is met there is no need for processes @@ -3293,19 +3318,20 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) */ if (raise_priority || !sc.nr_reclaimed) sc.priority--; - } while (sc.priority >= 1 && - !pgdat_balanced(pgdat, order, classzone_idx)); + } while (sc.priority >= 1); out: /* - * Return the highest zone idx we were reclaiming at so - * prepare_kswapd_sleep() makes the same decisions as here. + * Return the order kswapd stopped reclaiming at as + * prepare_kswapd_sleep() takes it into account. If another caller + * entered the allocator slow path while kswapd was awake, order will + * remain at the higher level. */ - return end_zone; + return sc.order; } -static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, - int classzone_idx, int balanced_classzone_idx) +static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, + unsigned int classzone_idx) { long remaining = 0; DEFINE_WAIT(wait); @@ -3316,9 +3342,33 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); /* Try to sleep for a short interval */ - if (prepare_kswapd_sleep(pgdat, order, remaining, - balanced_classzone_idx)) { + if (prepare_kswapd_sleep(pgdat, reclaim_order, classzone_idx)) { + /* + * Compaction records what page blocks it recently failed to + * isolate pages from and skips them in the future scanning. + * When kswapd is going to sleep, it is reasonable to assume + * that pages and compaction may succeed so reset the cache. + */ + reset_isolation_suitable(pgdat); + + /* + * We have freed the memory, now we should compact it to make + * allocation of the requested order possible. + */ + wakeup_kcompactd(pgdat, alloc_order, classzone_idx); + remaining = schedule_timeout(HZ/10); + + /* + * If woken prematurely then reset kswapd_classzone_idx and + * order. The values will either be from a wakeup request or + * the previous request that slept prematurely. + */ + if (remaining) { + pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx); + pgdat->kswapd_order = max(pgdat->kswapd_order, reclaim_order); + } + finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); } @@ -3327,8 +3377,8 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, * After a short sleep, check if it was a premature sleep. If not, then * go fully to sleep until explicitly woken up. */ - if (prepare_kswapd_sleep(pgdat, order, remaining, - balanced_classzone_idx)) { + if (!remaining && + prepare_kswapd_sleep(pgdat, reclaim_order, classzone_idx)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); /* @@ -3341,20 +3391,6 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); - /* - * Compaction records what page blocks it recently failed to - * isolate pages from and skips them in the future scanning. - * When kswapd is going to sleep, it is reasonable to assume - * that pages and compaction may succeed so reset the cache. - */ - reset_isolation_suitable(pgdat); - - /* - * We have freed the memory, now we should compact it to make - * allocation of the requested order possible. - */ - wakeup_kcompactd(pgdat, order, classzone_idx); - if (!kthread_should_stop()) schedule(); @@ -3383,9 +3419,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, */ static int kswapd(void *p) { - unsigned long order, new_order; - int classzone_idx, new_classzone_idx; - int balanced_classzone_idx; + unsigned int alloc_order, reclaim_order, classzone_idx; pg_data_t *pgdat = (pg_data_t*)p; struct task_struct *tsk = current; @@ -3415,38 +3449,20 @@ static int kswapd(void *p) tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; set_freezable(); - order = new_order = 0; - classzone_idx = new_classzone_idx = pgdat->nr_zones - 1; - balanced_classzone_idx = classzone_idx; + pgdat->kswapd_order = alloc_order = reclaim_order = 0; + pgdat->kswapd_classzone_idx = classzone_idx = 0; for ( ; ; ) { bool ret; - /* - * While we were reclaiming, there might have been another - * wakeup, so check the values. - */ - new_order = pgdat->kswapd_max_order; - new_classzone_idx = pgdat->classzone_idx; - pgdat->kswapd_max_order = 0; - pgdat->classzone_idx = pgdat->nr_zones - 1; +kswapd_try_sleep: + kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, + classzone_idx); - if (order < new_order || classzone_idx > new_classzone_idx) { - /* - * Don't sleep if someone wants a larger 'order' - * allocation or has tigher zone constraints - */ - order = new_order; - classzone_idx = new_classzone_idx; - } else { - kswapd_try_to_sleep(pgdat, order, classzone_idx, - balanced_classzone_idx); - order = pgdat->kswapd_max_order; - classzone_idx = pgdat->classzone_idx; - new_order = order; - new_classzone_idx = classzone_idx; - pgdat->kswapd_max_order = 0; - pgdat->classzone_idx = pgdat->nr_zones - 1; - } + /* Read the new order and classzone_idx */ + alloc_order = reclaim_order = pgdat->kswapd_order; + classzone_idx = pgdat->kswapd_classzone_idx; + pgdat->kswapd_order = 0; + pgdat->kswapd_classzone_idx = 0; ret = try_to_freeze(); if (kthread_should_stop()) @@ -3456,11 +3472,25 @@ static int kswapd(void *p) * We can speed up thawing tasks if we don't call balance_pgdat * after returning from the refrigerator */ - if (!ret) { - trace_mm_vmscan_kswapd_wake(pgdat->node_id, order); - balanced_classzone_idx = balance_pgdat(pgdat, order, - classzone_idx); - } + if (ret) + continue; + + /* + * Reclaim begins at the requested order but if a high-order + * reclaim fails then kswapd falls back to reclaiming for + * order-0. If that happens, kswapd will consider sleeping + * for the order it finished reclaiming at (reclaim_order) + * but kcompactd is woken to compact for the original + * request (alloc_order). + */ + trace_mm_vmscan_kswapd_wake(pgdat->node_id, classzone_idx, + alloc_order); + reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx); + if (reclaim_order < alloc_order) + goto kswapd_try_sleep; + + alloc_order = reclaim_order = pgdat->kswapd_order; + classzone_idx = pgdat->kswapd_classzone_idx; } tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD); @@ -3476,6 +3506,7 @@ static int kswapd(void *p) void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) { pg_data_t *pgdat; + int z; if (!populated_zone(zone)) return; @@ -3483,14 +3514,20 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL)) return; pgdat = zone->zone_pgdat; - if (pgdat->kswapd_max_order < order) { - pgdat->kswapd_max_order = order; - pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx); - } + pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx); + pgdat->kswapd_order = max(pgdat->kswapd_order, order); if (!waitqueue_active(&pgdat->kswapd_wait)) return; - if (zone_balanced(zone, order, true, 0, 0)) - return; + + /* Only wake kswapd if all zones are unbalanced */ + for (z = 0; z <= classzone_idx; z++) { + zone = pgdat->node_zones + z; + if (!populated_zone(zone)) + continue; + + if (zone_balanced(zone, order, classzone_idx)) + return; + } trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order); wake_up_interruptible(&pgdat->kswapd_wait); @@ -3511,6 +3548,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) struct scan_control sc = { .nr_to_reclaim = nr_to_reclaim, .gfp_mask = GFP_HIGHUSER_MOVABLE, + .reclaim_idx = MAX_NR_ZONES - 1, .priority = DEF_PRIORITY, .may_writepage = 1, .may_unmap = 1, @@ -3612,12 +3650,12 @@ module_init(kswapd_init) #ifdef CONFIG_NUMA /* - * Zone reclaim mode + * Node reclaim mode * - * If non-zero call zone_reclaim when the number of free pages falls below + * If non-zero call node_reclaim when the number of free pages falls below * the watermarks. */ -int zone_reclaim_mode __read_mostly; +int node_reclaim_mode __read_mostly; #define RECLAIM_OFF 0 #define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */ @@ -3625,14 +3663,14 @@ int zone_reclaim_mode __read_mostly; #define RECLAIM_UNMAP (1<<2) /* Unmap pages during reclaim */ /* - * Priority for ZONE_RECLAIM. This determines the fraction of pages + * 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. */ -#define ZONE_RECLAIM_PRIORITY 4 +#define NODE_RECLAIM_PRIORITY 4 /* - * Percentage of pages in a zone that must be unmapped for zone_reclaim to + * Percentage of pages in a zone that must be unmapped for node_reclaim to * occur. */ int sysctl_min_unmapped_ratio = 1; @@ -3643,11 +3681,11 @@ int sysctl_min_unmapped_ratio = 1; */ int sysctl_min_slab_ratio = 5; -static inline unsigned long zone_unmapped_file_pages(struct zone *zone) +static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat) { - unsigned long file_mapped = zone_page_state(zone, NR_FILE_MAPPED); - unsigned long file_lru = zone_page_state(zone, NR_INACTIVE_FILE) + - zone_page_state(zone, NR_ACTIVE_FILE); + unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED); + unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) + + node_page_state(pgdat, NR_ACTIVE_FILE); /* * It's possible for there to be more file mapped pages than @@ -3658,7 +3696,7 @@ static inline unsigned long zone_unmapped_file_pages(struct zone *zone) } /* Work out how many page cache pages we can reclaim in this reclaim_mode */ -static unsigned long zone_pagecache_reclaimable(struct zone *zone) +static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat) { unsigned long nr_pagecache_reclaimable; unsigned long delta = 0; @@ -3666,17 +3704,17 @@ static unsigned long zone_pagecache_reclaimable(struct zone *zone) /* * If RECLAIM_UNMAP is set, then all file pages are considered * potentially reclaimable. Otherwise, we have to worry about - * pages like swapcache and zone_unmapped_file_pages() provides + * pages like swapcache and node_unmapped_file_pages() provides * a better estimate */ - if (zone_reclaim_mode & RECLAIM_UNMAP) - nr_pagecache_reclaimable = zone_page_state(zone, NR_FILE_PAGES); + if (node_reclaim_mode & RECLAIM_UNMAP) + nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES); else - nr_pagecache_reclaimable = zone_unmapped_file_pages(zone); + nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat); /* If we can't clean pages, remove dirty pages from consideration */ - if (!(zone_reclaim_mode & RECLAIM_WRITE)) - delta += zone_page_state(zone, NR_FILE_DIRTY); + if (!(node_reclaim_mode & RECLAIM_WRITE)) + delta += node_page_state(pgdat, NR_FILE_DIRTY); /* Watch for any possible underflows due to delta */ if (unlikely(delta > nr_pagecache_reclaimable)) @@ -3686,22 +3724,24 @@ static unsigned long zone_pagecache_reclaimable(struct zone *zone) } /* - * Try to free up some pages from this zone through reclaim. + * Try to free up some pages from this node through reclaim. */ -static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) +static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { /* Minimum pages needed in order to stay on node */ const unsigned long nr_pages = 1 << order; struct task_struct *p = current; struct reclaim_state reclaim_state; + int classzone_idx = gfp_zone(gfp_mask); struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)), .order = order, - .priority = ZONE_RECLAIM_PRIORITY, - .may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE), - .may_unmap = !!(zone_reclaim_mode & RECLAIM_UNMAP), + .priority = NODE_RECLAIM_PRIORITY, + .may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE), + .may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP), .may_swap = 1, + .reclaim_idx = classzone_idx, }; cond_resched(); @@ -3715,13 +3755,13 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) reclaim_state.reclaimed_slab = 0; p->reclaim_state = &reclaim_state; - if (zone_pagecache_reclaimable(zone) > zone->min_unmapped_pages) { + if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) { /* * Free memory by calling shrink zone with increasing * priorities until we have enough memory freed. */ do { - shrink_zone(zone, &sc, true); + shrink_node(pgdat, &sc); } while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0); } @@ -3731,49 +3771,47 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) return sc.nr_reclaimed >= nr_pages; } -int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) +int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { - int node_id; int ret; /* - * Zone reclaim reclaims unmapped file backed pages and + * Node reclaim reclaims unmapped file backed pages and * slab pages if we are over the defined limits. * * A small portion of unmapped file backed pages is needed for * file I/O otherwise pages read by file I/O will be immediately - * thrown out if the zone is overallocated. So we do not reclaim - * if less than a specified percentage of the zone is used by + * thrown out if the node is overallocated. So we do not reclaim + * if less than a specified percentage of the node is used by * unmapped file backed pages. */ - if (zone_pagecache_reclaimable(zone) <= zone->min_unmapped_pages && - zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages) - return ZONE_RECLAIM_FULL; + if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages && + sum_zone_node_page_state(pgdat->node_id, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages) + return NODE_RECLAIM_FULL; - if (!zone_reclaimable(zone)) - return ZONE_RECLAIM_FULL; + if (!pgdat_reclaimable(pgdat)) + return NODE_RECLAIM_FULL; /* * Do not scan if the allocation should not be delayed. */ if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC)) - return ZONE_RECLAIM_NOSCAN; + return NODE_RECLAIM_NOSCAN; /* - * Only run zone reclaim on the local zone or on zones that do not + * Only run node reclaim on the local node or on nodes that do not * have associated processors. This will favor the local processor * over remote processors and spread off node memory allocations * as wide as possible. */ - node_id = zone_to_nid(zone); - if (node_state(node_id, N_CPU) && node_id != numa_node_id()) - return ZONE_RECLAIM_NOSCAN; + if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id()) + return NODE_RECLAIM_NOSCAN; - if (test_and_set_bit(ZONE_RECLAIM_LOCKED, &zone->flags)) - return ZONE_RECLAIM_NOSCAN; + if (test_and_set_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags)) + return NODE_RECLAIM_NOSCAN; - ret = __zone_reclaim(zone, gfp_mask, order); - clear_bit(ZONE_RECLAIM_LOCKED, &zone->flags); + ret = __node_reclaim(pgdat, gfp_mask, order); + clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags); if (!ret) count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED); @@ -3812,24 +3850,23 @@ int page_evictable(struct page *page) void check_move_unevictable_pages(struct page **pages, int nr_pages) { struct lruvec *lruvec; - struct zone *zone = NULL; + struct pglist_data *pgdat = NULL; int pgscanned = 0; int pgrescued = 0; int i; for (i = 0; i < nr_pages; i++) { struct page *page = pages[i]; - struct zone *pagezone; + struct pglist_data *pagepgdat = page_pgdat(page); pgscanned++; - pagezone = page_zone(page); - if (pagezone != zone) { - if (zone) - spin_unlock_irq(&zone->lru_lock); - zone = pagezone; - spin_lock_irq(&zone->lru_lock); + if (pagepgdat != pgdat) { + if (pgdat) + spin_unlock_irq(&pgdat->lru_lock); + pgdat = pagepgdat; + spin_lock_irq(&pgdat->lru_lock); } - lruvec = mem_cgroup_page_lruvec(page, zone); + lruvec = mem_cgroup_page_lruvec(page, pgdat); if (!PageLRU(page) || !PageUnevictable(page)) continue; @@ -3845,10 +3882,10 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages) } } - if (zone) { + if (pgdat) { __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irq(&pgdat->lru_lock); } } #endif /* CONFIG_SHMEM */ diff --git a/mm/vmstat.c b/mm/vmstat.c index 5e4300482897..89cec42d19ff 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -86,8 +86,10 @@ void vm_events_fold_cpu(int cpu) * * vm_stat contains the global counters */ -atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp; -EXPORT_SYMBOL(vm_stat); +atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp; +atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS] __cacheline_aligned_in_smp; +EXPORT_SYMBOL(vm_zone_stat); +EXPORT_SYMBOL(vm_node_stat); #ifdef CONFIG_SMP @@ -167,19 +169,36 @@ int calculate_normal_threshold(struct zone *zone) */ void refresh_zone_stat_thresholds(void) { + struct pglist_data *pgdat; struct zone *zone; int cpu; int threshold; + /* Zero current pgdat thresholds */ + for_each_online_pgdat(pgdat) { + for_each_online_cpu(cpu) { + per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold = 0; + } + } + for_each_populated_zone(zone) { + struct pglist_data *pgdat = zone->zone_pgdat; unsigned long max_drift, tolerate_drift; threshold = calculate_normal_threshold(zone); - for_each_online_cpu(cpu) + for_each_online_cpu(cpu) { + int pgdat_threshold; + per_cpu_ptr(zone->pageset, cpu)->stat_threshold = threshold; + /* Base nodestat threshold on the largest populated zone. */ + pgdat_threshold = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold; + per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold + = max(threshold, pgdat_threshold); + } + /* * Only set percpu_drift_mark if there is a danger that * NR_FREE_PAGES reports the low watermark is ok when in fact @@ -238,6 +257,26 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, } EXPORT_SYMBOL(__mod_zone_page_state); +void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, + long delta) +{ + struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats; + s8 __percpu *p = pcp->vm_node_stat_diff + item; + long x; + long t; + + x = delta + __this_cpu_read(*p); + + t = __this_cpu_read(pcp->stat_threshold); + + if (unlikely(x > t || x < -t)) { + node_page_state_add(x, pgdat, item); + x = 0; + } + __this_cpu_write(*p, x); +} +EXPORT_SYMBOL(__mod_node_page_state); + /* * Optimized increment and decrement functions. * @@ -277,12 +316,34 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) } } +void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) +{ + struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats; + s8 __percpu *p = pcp->vm_node_stat_diff + item; + s8 v, t; + + v = __this_cpu_inc_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v > t)) { + s8 overstep = t >> 1; + + node_page_state_add(v + overstep, pgdat, item); + __this_cpu_write(*p, -overstep); + } +} + void __inc_zone_page_state(struct page *page, enum zone_stat_item item) { __inc_zone_state(page_zone(page), item); } EXPORT_SYMBOL(__inc_zone_page_state); +void __inc_node_page_state(struct page *page, enum node_stat_item item) +{ + __inc_node_state(page_pgdat(page), item); +} +EXPORT_SYMBOL(__inc_node_page_state); + void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { struct per_cpu_pageset __percpu *pcp = zone->pageset; @@ -299,12 +360,34 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item) } } +void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) +{ + struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats; + s8 __percpu *p = pcp->vm_node_stat_diff + item; + s8 v, t; + + v = __this_cpu_dec_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v < - t)) { + s8 overstep = t >> 1; + + node_page_state_add(v - overstep, pgdat, item); + __this_cpu_write(*p, overstep); + } +} + void __dec_zone_page_state(struct page *page, enum zone_stat_item item) { __dec_zone_state(page_zone(page), item); } EXPORT_SYMBOL(__dec_zone_page_state); +void __dec_node_page_state(struct page *page, enum node_stat_item item) +{ + __dec_node_state(page_pgdat(page), item); +} +EXPORT_SYMBOL(__dec_node_page_state); + #ifdef CONFIG_HAVE_CMPXCHG_LOCAL /* * If we have cmpxchg_local support then we do not need to incur the overhead @@ -318,8 +401,8 @@ EXPORT_SYMBOL(__dec_zone_page_state); * 1 Overstepping half of threshold * -1 Overstepping minus half of threshold */ -static inline void mod_state(struct zone *zone, enum zone_stat_item item, - long delta, int overstep_mode) +static inline void mod_zone_state(struct zone *zone, + enum zone_stat_item item, long delta, int overstep_mode) { struct per_cpu_pageset __percpu *pcp = zone->pageset; s8 __percpu *p = pcp->vm_stat_diff + item; @@ -359,26 +442,83 @@ static inline void mod_state(struct zone *zone, enum zone_stat_item item, void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long delta) { - mod_state(zone, item, delta, 0); + mod_zone_state(zone, item, delta, 0); } EXPORT_SYMBOL(mod_zone_page_state); -void inc_zone_state(struct zone *zone, enum zone_stat_item item) -{ - mod_state(zone, item, 1, 1); -} - void inc_zone_page_state(struct page *page, enum zone_stat_item item) { - mod_state(page_zone(page), item, 1, 1); + mod_zone_state(page_zone(page), item, 1, 1); } EXPORT_SYMBOL(inc_zone_page_state); void dec_zone_page_state(struct page *page, enum zone_stat_item item) { - mod_state(page_zone(page), item, -1, -1); + mod_zone_state(page_zone(page), item, -1, -1); } EXPORT_SYMBOL(dec_zone_page_state); + +static inline void mod_node_state(struct pglist_data *pgdat, + enum node_stat_item item, int delta, int overstep_mode) +{ + struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats; + s8 __percpu *p = pcp->vm_node_stat_diff + item; + long o, n, t, z; + + do { + z = 0; /* overflow to node counters */ + + /* + * The fetching of the stat_threshold is racy. We may apply + * a counter threshold to the wrong the cpu if we get + * rescheduled while executing here. However, the next + * counter update will apply the threshold again and + * therefore bring the counter under the threshold again. + * + * Most of the time the thresholds are the same anyways + * for all cpus in a node. + */ + t = this_cpu_read(pcp->stat_threshold); + + o = this_cpu_read(*p); + n = delta + o; + + if (n > t || n < -t) { + int os = overstep_mode * (t >> 1) ; + + /* Overflow must be added to node counters */ + z = n + os; + n = -os; + } + } while (this_cpu_cmpxchg(*p, o, n) != o); + + if (z) + node_page_state_add(z, pgdat, item); +} + +void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, + long delta) +{ + mod_node_state(pgdat, item, delta, 0); +} +EXPORT_SYMBOL(mod_node_page_state); + +void inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) +{ + mod_node_state(pgdat, item, 1, 1); +} + +void inc_node_page_state(struct page *page, enum node_stat_item item) +{ + mod_node_state(page_pgdat(page), item, 1, 1); +} +EXPORT_SYMBOL(inc_node_page_state); + +void dec_node_page_state(struct page *page, enum node_stat_item item) +{ + mod_node_state(page_pgdat(page), item, -1, -1); +} +EXPORT_SYMBOL(dec_node_page_state); #else /* * Use interrupt disable to serialize counter updates @@ -394,15 +534,6 @@ void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, } EXPORT_SYMBOL(mod_zone_page_state); -void inc_zone_state(struct zone *zone, enum zone_stat_item item) -{ - unsigned long flags; - - local_irq_save(flags); - __inc_zone_state(zone, item); - local_irq_restore(flags); -} - void inc_zone_page_state(struct page *page, enum zone_stat_item item) { unsigned long flags; @@ -424,21 +555,69 @@ void dec_zone_page_state(struct page *page, enum zone_stat_item item) local_irq_restore(flags); } EXPORT_SYMBOL(dec_zone_page_state); -#endif +void inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) +{ + unsigned long flags; + + local_irq_save(flags); + __inc_node_state(pgdat, item); + local_irq_restore(flags); +} +EXPORT_SYMBOL(inc_node_state); + +void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, + long delta) +{ + unsigned long flags; + + local_irq_save(flags); + __mod_node_page_state(pgdat, item, delta); + local_irq_restore(flags); +} +EXPORT_SYMBOL(mod_node_page_state); + +void inc_node_page_state(struct page *page, enum node_stat_item item) +{ + unsigned long flags; + struct pglist_data *pgdat; + + pgdat = page_pgdat(page); + local_irq_save(flags); + __inc_node_state(pgdat, item); + local_irq_restore(flags); +} +EXPORT_SYMBOL(inc_node_page_state); + +void dec_node_page_state(struct page *page, enum node_stat_item item) +{ + unsigned long flags; + + local_irq_save(flags); + __dec_node_page_state(page, item); + local_irq_restore(flags); +} +EXPORT_SYMBOL(dec_node_page_state); +#endif /* * Fold a differential into the global counters. * Returns the number of counters updated. */ -static int fold_diff(int *diff) +static int fold_diff(int *zone_diff, int *node_diff) { int i; int changes = 0; for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - if (diff[i]) { - atomic_long_add(diff[i], &vm_stat[i]); + if (zone_diff[i]) { + atomic_long_add(zone_diff[i], &vm_zone_stat[i]); + changes++; + } + + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) + if (node_diff[i]) { + atomic_long_add(node_diff[i], &vm_node_stat[i]); changes++; } return changes; @@ -462,9 +641,11 @@ static int fold_diff(int *diff) */ static int refresh_cpu_vm_stats(bool do_pagesets) { + struct pglist_data *pgdat; struct zone *zone; int i; - int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; + int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; + int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, }; int changes = 0; for_each_populated_zone(zone) { @@ -477,7 +658,7 @@ static int refresh_cpu_vm_stats(bool do_pagesets) if (v) { atomic_long_add(v, &zone->vm_stat[i]); - global_diff[i] += v; + global_zone_diff[i] += v; #ifdef CONFIG_NUMA /* 3 seconds idle till flush */ __this_cpu_write(p->expire, 3); @@ -516,7 +697,22 @@ static int refresh_cpu_vm_stats(bool do_pagesets) } #endif } - changes += fold_diff(global_diff); + + for_each_online_pgdat(pgdat) { + struct per_cpu_nodestat __percpu *p = pgdat->per_cpu_nodestats; + + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { + int v; + + v = this_cpu_xchg(p->vm_node_stat_diff[i], 0); + if (v) { + atomic_long_add(v, &pgdat->vm_stat[i]); + global_node_diff[i] += v; + } + } + } + + changes += fold_diff(global_zone_diff, global_node_diff); return changes; } @@ -527,9 +723,11 @@ static int refresh_cpu_vm_stats(bool do_pagesets) */ void cpu_vm_stats_fold(int cpu) { + struct pglist_data *pgdat; struct zone *zone; int i; - int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; + int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; + int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, }; for_each_populated_zone(zone) { struct per_cpu_pageset *p; @@ -543,11 +741,27 @@ void cpu_vm_stats_fold(int cpu) v = p->vm_stat_diff[i]; p->vm_stat_diff[i] = 0; atomic_long_add(v, &zone->vm_stat[i]); - global_diff[i] += v; + global_zone_diff[i] += v; + } + } + + for_each_online_pgdat(pgdat) { + struct per_cpu_nodestat *p; + + p = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu); + + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) + if (p->vm_node_stat_diff[i]) { + int v; + + v = p->vm_node_stat_diff[i]; + p->vm_node_stat_diff[i] = 0; + atomic_long_add(v, &pgdat->vm_stat[i]); + global_node_diff[i] += v; } } - fold_diff(global_diff); + fold_diff(global_zone_diff, global_node_diff); } /* @@ -563,58 +777,43 @@ void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) int v = pset->vm_stat_diff[i]; pset->vm_stat_diff[i] = 0; atomic_long_add(v, &zone->vm_stat[i]); - atomic_long_add(v, &vm_stat[i]); + atomic_long_add(v, &vm_zone_stat[i]); } } #endif #ifdef CONFIG_NUMA /* - * zonelist = the list of zones passed to the allocator - * z = the zone from which the allocation occurred. - * - * Must be called with interrupts disabled. - * - * When __GFP_OTHER_NODE is set assume the node of the preferred - * zone is the local node. This is useful for daemons who allocate - * memory on behalf of other processes. + * Determine the per node value of a stat item. This function + * is called frequently in a NUMA machine, so try to be as + * frugal as possible. */ -void zone_statistics(struct zone *preferred_zone, struct zone *z, gfp_t flags) +unsigned long sum_zone_node_page_state(int node, + enum zone_stat_item item) { - if (z->zone_pgdat == preferred_zone->zone_pgdat) { - __inc_zone_state(z, NUMA_HIT); - } else { - __inc_zone_state(z, NUMA_MISS); - __inc_zone_state(preferred_zone, NUMA_FOREIGN); - } - if (z->node == ((flags & __GFP_OTHER_NODE) ? - preferred_zone->node : numa_node_id())) - __inc_zone_state(z, NUMA_LOCAL); - else - __inc_zone_state(z, NUMA_OTHER); + struct zone *zones = NODE_DATA(node)->node_zones; + int i; + unsigned long count = 0; + + for (i = 0; i < MAX_NR_ZONES; i++) + count += zone_page_state(zones + i, item); + + return count; } /* * Determine the per node value of a stat item. */ -unsigned long node_page_state(int node, enum zone_stat_item item) +unsigned long node_page_state(struct pglist_data *pgdat, + enum node_stat_item item) { - struct zone *zones = NODE_DATA(node)->node_zones; - - return -#ifdef CONFIG_ZONE_DMA - zone_page_state(&zones[ZONE_DMA], item) + -#endif -#ifdef CONFIG_ZONE_DMA32 - zone_page_state(&zones[ZONE_DMA32], item) + -#endif -#ifdef CONFIG_HIGHMEM - zone_page_state(&zones[ZONE_HIGHMEM], item) + + long x = atomic_long_read(&pgdat->vm_stat[item]); +#ifdef CONFIG_SMP + if (x < 0) + x = 0; #endif - zone_page_state(&zones[ZONE_NORMAL], item) + - zone_page_state(&zones[ZONE_MOVABLE], item); + return x; } - #endif #ifdef CONFIG_COMPACTION @@ -722,34 +921,21 @@ int fragmentation_index(struct zone *zone, unsigned int order) const char * const vmstat_text[] = { /* enum zone_stat_item countes */ "nr_free_pages", - "nr_alloc_batch", - "nr_inactive_anon", - "nr_active_anon", - "nr_inactive_file", - "nr_active_file", - "nr_unevictable", + "nr_zone_inactive_anon", + "nr_zone_active_anon", + "nr_zone_inactive_file", + "nr_zone_active_file", + "nr_zone_unevictable", + "nr_zone_write_pending", "nr_mlock", - "nr_anon_pages", - "nr_mapped", - "nr_file_pages", - "nr_dirty", - "nr_writeback", "nr_slab_reclaimable", "nr_slab_unreclaimable", "nr_page_table_pages", "nr_kernel_stack", - "nr_unstable", "nr_bounce", - "nr_vmscan_write", - "nr_vmscan_immediate_reclaim", - "nr_writeback_temp", - "nr_isolated_anon", - "nr_isolated_file", - "nr_shmem", - "nr_dirtied", - "nr_written", - "nr_pages_scanned", - +#if IS_ENABLED(CONFIG_ZSMALLOC) + "nr_zspages", +#endif #ifdef CONFIG_NUMA "numa_hit", "numa_miss", @@ -758,11 +944,35 @@ const char * const vmstat_text[] = { "numa_local", "numa_other", #endif + "nr_free_cma", + + /* Node-based counters */ + "nr_inactive_anon", + "nr_active_anon", + "nr_inactive_file", + "nr_active_file", + "nr_unevictable", + "nr_isolated_anon", + "nr_isolated_file", + "nr_pages_scanned", "workingset_refault", "workingset_activate", "workingset_nodereclaim", + "nr_anon_pages", + "nr_mapped", + "nr_file_pages", + "nr_dirty", + "nr_writeback", + "nr_writeback_temp", + "nr_shmem", + "nr_shmem_hugepages", + "nr_shmem_pmdmapped", "nr_anon_transparent_hugepages", - "nr_free_cma", + "nr_unstable", + "nr_vmscan_write", + "nr_vmscan_immediate_reclaim", + "nr_dirtied", + "nr_written", /* enum writeback_stat_item counters */ "nr_dirty_threshold", @@ -776,6 +986,8 @@ const char * const vmstat_text[] = { "pswpout", TEXTS_FOR_ZONES("pgalloc") + TEXTS_FOR_ZONES("allocstall") + TEXTS_FOR_ZONES("pgskip") "pgfree", "pgactivate", @@ -785,11 +997,11 @@ const char * const vmstat_text[] = { "pgmajfault", "pglazyfreed", - TEXTS_FOR_ZONES("pgrefill") - TEXTS_FOR_ZONES("pgsteal_kswapd") - TEXTS_FOR_ZONES("pgsteal_direct") - TEXTS_FOR_ZONES("pgscan_kswapd") - TEXTS_FOR_ZONES("pgscan_direct") + "pgrefill", + "pgsteal_kswapd", + "pgsteal_direct", + "pgscan_kswapd", + "pgscan_direct", "pgscan_direct_throttle", #ifdef CONFIG_NUMA @@ -801,7 +1013,6 @@ const char * const vmstat_text[] = { "kswapd_low_wmark_hit_quickly", "kswapd_high_wmark_hit_quickly", "pageoutrun", - "allocstall", "pgrotated", @@ -846,6 +1057,8 @@ const char * const vmstat_text[] = { "thp_fault_fallback", "thp_collapse_alloc", "thp_collapse_alloc_failed", + "thp_file_alloc", + "thp_file_mapped", "thp_split_page", "thp_split_page_failed", "thp_deferred_split_page", @@ -1010,6 +1223,9 @@ static void pagetypeinfo_showblockcount_print(struct seq_file *m, if (!memmap_valid_within(pfn, page, zone)) continue; + if (page_zone(page) != zone) + continue; + mtype = get_pageblock_migratetype(page); if (mtype < MIGRATE_TYPES) @@ -1069,13 +1285,17 @@ static void pagetypeinfo_showmixedcount_print(struct seq_file *m, block_end_pfn = min(block_end_pfn, end_pfn); page = pfn_to_page(pfn); - pageblock_mt = get_pfnblock_migratetype(page, pfn); + pageblock_mt = get_pageblock_migratetype(page); for (; pfn < block_end_pfn; pfn++) { if (!pfn_valid_within(pfn)) continue; page = pfn_to_page(pfn); + + if (page_zone(page) != zone) + continue; + if (PageBuddy(page)) { pfn += (1UL << page_order(page)) - 1; continue; @@ -1085,6 +1305,8 @@ static void pagetypeinfo_showmixedcount_print(struct seq_file *m, continue; page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + continue; if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) continue; @@ -1196,17 +1418,41 @@ static const struct file_operations pagetypeinfo_file_ops = { .release = seq_release, }; +static bool is_zone_first_populated(pg_data_t *pgdat, struct zone *zone) +{ + int zid; + + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + struct zone *compare = &pgdat->node_zones[zid]; + + if (populated_zone(compare)) + return zone == compare; + } + + /* The zone must be somewhere! */ + WARN_ON_ONCE(1); + return false; +} + static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone) { int i; seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name); + if (is_zone_first_populated(pgdat, zone)) { + seq_printf(m, "\n per-node stats"); + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { + seq_printf(m, "\n %-12s %lu", + vmstat_text[i + NR_VM_ZONE_STAT_ITEMS], + node_page_state(pgdat, i)); + } + } seq_printf(m, "\n pages free %lu" "\n min %lu" "\n low %lu" "\n high %lu" - "\n scanned %lu" + "\n node_scanned %lu" "\n spanned %lu" "\n present %lu" "\n managed %lu", @@ -1214,13 +1460,13 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, min_wmark_pages(zone), low_wmark_pages(zone), high_wmark_pages(zone), - zone_page_state(zone, NR_PAGES_SCANNED), + node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED), zone->spanned_pages, zone->present_pages, zone->managed_pages); for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - seq_printf(m, "\n %-12s %lu", vmstat_text[i], + seq_printf(m, "\n %-12s %lu", vmstat_text[i], zone_page_state(zone, i)); seq_printf(m, @@ -1250,12 +1496,12 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, #endif } seq_printf(m, - "\n all_unreclaimable: %u" - "\n start_pfn: %lu" - "\n inactive_ratio: %u", - !zone_reclaimable(zone), + "\n node_unreclaimable: %u" + "\n start_pfn: %lu" + "\n node_inactive_ratio: %u", + !pgdat_reclaimable(zone->zone_pgdat), zone->zone_start_pfn, - zone->inactive_ratio); + zone->zone_pgdat->inactive_ratio); seq_putc(m, '\n'); } @@ -1303,6 +1549,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) if (*pos >= ARRAY_SIZE(vmstat_text)) return NULL; stat_items_size = NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) + + NR_VM_NODE_STAT_ITEMS * sizeof(unsigned long) + NR_VM_WRITEBACK_STAT_ITEMS * sizeof(unsigned long); #ifdef CONFIG_VM_EVENT_COUNTERS @@ -1317,6 +1564,10 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) v[i] = global_page_state(i); v += NR_VM_ZONE_STAT_ITEMS; + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) + v[i] = global_node_page_state(i); + v += NR_VM_NODE_STAT_ITEMS; + global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD, v + NR_DIRTY_THRESHOLD); v += NR_VM_WRITEBACK_STAT_ITEMS; @@ -1341,7 +1592,6 @@ static int vmstat_show(struct seq_file *m, void *arg) { unsigned long *l = arg; unsigned long off = l - (unsigned long *)m->private; - seq_printf(m, "%s %lu\n", vmstat_text[off], *l); return 0; } @@ -1376,7 +1626,65 @@ static const struct file_operations proc_vmstat_file_operations = { static struct workqueue_struct *vmstat_wq; static DEFINE_PER_CPU(struct delayed_work, vmstat_work); int sysctl_stat_interval __read_mostly = HZ; -static cpumask_var_t cpu_stat_off; + +#ifdef CONFIG_PROC_FS +static void refresh_vm_stats(struct work_struct *work) +{ + refresh_cpu_vm_stats(true); +} + +int vmstat_refresh(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + long val; + int err; + int i; + + /* + * The regular update, every sysctl_stat_interval, may come later + * than expected: leaving a significant amount in per_cpu buckets. + * This is particularly misleading when checking a quantity of HUGE + * pages, immediately after running a test. /proc/sys/vm/stat_refresh, + * which can equally be echo'ed to or cat'ted from (by root), + * can be used to update the stats just before reading them. + * + * Oh, and since global_page_state() etc. are so careful to hide + * transiently negative values, report an error here if any of + * the stats is negative, so we know to go looking for imbalance. + */ + err = schedule_on_each_cpu(refresh_vm_stats); + if (err) + return err; + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { + val = atomic_long_read(&vm_zone_stat[i]); + if (val < 0) { + switch (i) { + case NR_PAGES_SCANNED: + /* + * This is often seen to go negative in + * recent kernels, but not to go permanently + * negative. Whilst it would be nicer not to + * have exceptions, rooting them out would be + * another task, of rather low priority. + */ + break; + default: + pr_warn("%s: %s %ld\n", + __func__, vmstat_text[i], val); + err = -EINVAL; + break; + } + } + } + if (err) + return err; + if (write) + *ppos += *lenp; + else + *lenp = 0; + return 0; +} +#endif /* CONFIG_PROC_FS */ static void vmstat_update(struct work_struct *w) { @@ -1385,24 +1693,10 @@ static void vmstat_update(struct work_struct *w) * Counters were updated so we expect more updates * to occur in the future. Keep on running the * update worker thread. - * If we were marked on cpu_stat_off clear the flag - * so that vmstat_shepherd doesn't schedule us again. */ - if (!cpumask_test_and_clear_cpu(smp_processor_id(), - cpu_stat_off)) { - queue_delayed_work_on(smp_processor_id(), vmstat_wq, + queue_delayed_work_on(smp_processor_id(), vmstat_wq, this_cpu_ptr(&vmstat_work), round_jiffies_relative(sysctl_stat_interval)); - } - } else { - /* - * We did not update any counters so the app may be in - * a mode where it does not cause counter updates. - * We may be uselessly running vmstat_update. - * Defer the checking for differentials to the - * shepherd thread on a different processor. - */ - cpumask_set_cpu(smp_processor_id(), cpu_stat_off); } } @@ -1434,16 +1728,17 @@ static bool need_update(int cpu) return false; } +/* + * Switch off vmstat processing and then fold all the remaining differentials + * until the diffs stay at zero. The function is used by NOHZ and can only be + * invoked when tick processing is not active. + */ void quiet_vmstat(void) { if (system_state != SYSTEM_RUNNING) return; - /* - * If we are already in hands of the shepherd then there - * is nothing for us to do here. - */ - if (cpumask_test_and_set_cpu(smp_processor_id(), cpu_stat_off)) + if (!delayed_work_pending(this_cpu_ptr(&vmstat_work))) return; if (!need_update(smp_processor_id())) @@ -1458,7 +1753,6 @@ void quiet_vmstat(void) refresh_cpu_vm_stats(false); } - /* * Shepherd worker thread that checks the * differentials of processors that have their worker @@ -1475,20 +1769,11 @@ static void vmstat_shepherd(struct work_struct *w) get_online_cpus(); /* Check processors whose vmstat worker threads have been disabled */ - for_each_cpu(cpu, cpu_stat_off) { + for_each_online_cpu(cpu) { struct delayed_work *dw = &per_cpu(vmstat_work, cpu); - if (need_update(cpu)) { - if (cpumask_test_and_clear_cpu(cpu, cpu_stat_off)) - queue_delayed_work_on(cpu, vmstat_wq, dw, 0); - } else { - /* - * Cancel the work if quiet_vmstat has put this - * cpu on cpu_stat_off because the work item might - * be still scheduled - */ - cancel_delayed_work(dw); - } + if (!delayed_work_pending(dw) && need_update(cpu)) + queue_delayed_work_on(cpu, vmstat_wq, dw, 0); } put_online_cpus(); @@ -1504,10 +1789,6 @@ static void __init start_shepherd_timer(void) INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu), vmstat_update); - if (!alloc_cpumask_var(&cpu_stat_off, GFP_KERNEL)) - BUG(); - cpumask_copy(cpu_stat_off, cpu_online_mask); - vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); schedule_delayed_work(&shepherd, round_jiffies_relative(sysctl_stat_interval)); @@ -1542,16 +1823,13 @@ static int vmstat_cpuup_callback(struct notifier_block *nfb, case CPU_ONLINE_FROZEN: refresh_zone_stat_thresholds(); node_set_state(cpu_to_node(cpu), N_CPU); - cpumask_set_cpu(cpu, cpu_stat_off); break; case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu)); - cpumask_clear_cpu(cpu, cpu_stat_off); break; case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: - cpumask_set_cpu(cpu, cpu_stat_off); break; case CPU_DEAD: case CPU_DEAD_FROZEN: diff --git a/mm/workingset.c b/mm/workingset.c index 8a75f8d2916a..69551cfae97b 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -16,7 +16,7 @@ /* * Double CLOCK lists * - * Per zone, two clock lists are maintained for file pages: the + * Per node, two clock lists are maintained for file pages: the * inactive and the active list. Freshly faulted pages start out at * the head of the inactive list and page reclaim scans pages from the * tail. Pages that are accessed multiple times on the inactive list @@ -141,11 +141,11 @@ * * Implementation * - * For each zone's file LRU lists, a counter for inactive evictions - * and activations is maintained (zone->inactive_age). + * For each node's file LRU lists, a counter for inactive evictions + * and activations is maintained (node->inactive_age). * * On eviction, a snapshot of this counter (along with some bits to - * identify the zone) is stored in the now empty page cache radix tree + * identify the node) is stored in the now empty page cache radix tree * slot of the evicted page. This is called a shadow entry. * * On cache misses for which there are shadow entries, an eligible @@ -153,7 +153,7 @@ */ #define EVICTION_SHIFT (RADIX_TREE_EXCEPTIONAL_ENTRY + \ - ZONES_SHIFT + NODES_SHIFT + \ + NODES_SHIFT + \ MEM_CGROUP_ID_SHIFT) #define EVICTION_MASK (~0UL >> EVICTION_SHIFT) @@ -167,33 +167,30 @@ */ static unsigned int bucket_order __read_mostly; -static void *pack_shadow(int memcgid, struct zone *zone, unsigned long eviction) +static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction) { eviction >>= bucket_order; eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; - eviction = (eviction << NODES_SHIFT) | zone_to_nid(zone); - eviction = (eviction << ZONES_SHIFT) | zone_idx(zone); + eviction = (eviction << NODES_SHIFT) | pgdat->node_id; eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT); return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY); } -static void unpack_shadow(void *shadow, int *memcgidp, struct zone **zonep, +static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, unsigned long *evictionp) { unsigned long entry = (unsigned long)shadow; - int memcgid, nid, zid; + int memcgid, nid; entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT; - zid = entry & ((1UL << ZONES_SHIFT) - 1); - entry >>= ZONES_SHIFT; nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); entry >>= MEM_CGROUP_ID_SHIFT; *memcgidp = memcgid; - *zonep = NODE_DATA(nid)->node_zones + zid; + *pgdat = NODE_DATA(nid); *evictionp = entry << bucket_order; } @@ -208,7 +205,7 @@ static void unpack_shadow(void *shadow, int *memcgidp, struct zone **zonep, void *workingset_eviction(struct address_space *mapping, struct page *page) { struct mem_cgroup *memcg = page_memcg(page); - struct zone *zone = page_zone(page); + struct pglist_data *pgdat = page_pgdat(page); int memcgid = mem_cgroup_id(memcg); unsigned long eviction; struct lruvec *lruvec; @@ -218,9 +215,9 @@ void *workingset_eviction(struct address_space *mapping, struct page *page) VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); - lruvec = mem_cgroup_zone_lruvec(zone, memcg); + lruvec = mem_cgroup_lruvec(pgdat, memcg); eviction = atomic_long_inc_return(&lruvec->inactive_age); - return pack_shadow(memcgid, zone, eviction); + return pack_shadow(memcgid, pgdat, eviction); } /** @@ -228,7 +225,7 @@ void *workingset_eviction(struct address_space *mapping, struct page *page) * @shadow: shadow entry of the evicted page * * Calculates and evaluates the refault distance of the previously - * evicted page in the context of the zone it was allocated in. + * evicted page in the context of the node it was allocated in. * * Returns %true if the page should be activated, %false otherwise. */ @@ -240,10 +237,10 @@ bool workingset_refault(void *shadow) unsigned long eviction; struct lruvec *lruvec; unsigned long refault; - struct zone *zone; + struct pglist_data *pgdat; int memcgid; - unpack_shadow(shadow, &memcgid, &zone, &eviction); + unpack_shadow(shadow, &memcgid, &pgdat, &eviction); rcu_read_lock(); /* @@ -267,7 +264,7 @@ bool workingset_refault(void *shadow) rcu_read_unlock(); return false; } - lruvec = mem_cgroup_zone_lruvec(zone, memcg); + lruvec = mem_cgroup_lruvec(pgdat, memcg); refault = atomic_long_read(&lruvec->inactive_age); active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE); rcu_read_unlock(); @@ -290,10 +287,10 @@ bool workingset_refault(void *shadow) */ refault_distance = (refault - eviction) & EVICTION_MASK; - inc_zone_state(zone, WORKINGSET_REFAULT); + inc_node_state(pgdat, WORKINGSET_REFAULT); if (refault_distance <= active_file) { - inc_zone_state(zone, WORKINGSET_ACTIVATE); + inc_node_state(pgdat, WORKINGSET_ACTIVATE); return true; } return false; @@ -305,9 +302,10 @@ bool workingset_refault(void *shadow) */ void workingset_activation(struct page *page) { + struct mem_cgroup *memcg; struct lruvec *lruvec; - lock_page_memcg(page); + rcu_read_lock(); /* * Filter non-memcg pages here, e.g. unmap can call * mark_page_accessed() on VDSO pages. @@ -315,12 +313,13 @@ void workingset_activation(struct page *page) * XXX: See workingset_refault() - this should return * root_mem_cgroup even for !CONFIG_MEMCG. */ - if (!mem_cgroup_disabled() && !page_memcg(page)) + memcg = page_memcg_rcu(page); + if (!mem_cgroup_disabled() && !memcg) goto out; - lruvec = mem_cgroup_zone_lruvec(page_zone(page), page_memcg(page)); + lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg); atomic_long_inc(&lruvec->inactive_age); out: - unlock_page_memcg(page); + rcu_read_unlock(); } /* @@ -349,12 +348,13 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc); local_irq_enable(); - if (memcg_kmem_enabled()) + if (memcg_kmem_enabled()) { pages = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid, LRU_ALL_FILE); - else - pages = node_page_state(sc->nid, NR_ACTIVE_FILE) + - node_page_state(sc->nid, NR_INACTIVE_FILE); + } else { + pages = node_page_state(NODE_DATA(sc->nid), NR_ACTIVE_FILE) + + node_page_state(NODE_DATA(sc->nid), NR_INACTIVE_FILE); + } /* * Active cache pages are limited to 50% of memory, and shadow @@ -433,7 +433,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, } } BUG_ON(node->count); - inc_zone_state(page_zone(virt_to_page(node)), WORKINGSET_NODERECLAIM); + inc_node_state(page_pgdat(virt_to_page(node)), WORKINGSET_NODERECLAIM); if (!__radix_tree_delete_node(&mapping->page_tree, node)) BUG(); @@ -491,7 +491,7 @@ static int __init workingset_init(void) max_order = fls_long(totalram_pages - 1); if (max_order > timestamp_bits) bucket_order = max_order - timestamp_bits; - printk("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", + pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", timestamp_bits, max_order, bucket_order); ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key); diff --git a/mm/z3fold.c b/mm/z3fold.c new file mode 100644 index 000000000000..8f9e89ca1d31 --- /dev/null +++ b/mm/z3fold.c @@ -0,0 +1,796 @@ +/* + * z3fold.c + * + * Author: Vitaly Wool <vitaly.wool@konsulko.com> + * Copyright (C) 2016, Sony Mobile Communications Inc. + * + * This implementation is based on zbud written by Seth Jennings. + * + * z3fold is an special purpose allocator for storing compressed pages. It + * can store up to three compressed pages per page which improves the + * compression ratio of zbud while retaining its main concepts (e. g. always + * storing an integral number of objects per page) and simplicity. + * It still has simple and deterministic reclaim properties that make it + * preferable to a higher density approach (with no requirement on integral + * number of object per page) when reclaim is used. + * + * As in zbud, pages are divided into "chunks". The size of the chunks is + * fixed at compile time and is determined by NCHUNKS_ORDER below. + * + * z3fold doesn't export any API and is meant to be used via zpool API. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/atomic.h> +#include <linux/list.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/preempt.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/zpool.h> + +/***************** + * Structures +*****************/ +/* + * NCHUNKS_ORDER determines the internal allocation granularity, effectively + * adjusting internal fragmentation. It also determines the number of + * freelists maintained in each pool. NCHUNKS_ORDER of 6 means that the + * allocation granularity will be in chunks of size PAGE_SIZE/64. As one chunk + * in allocated page is occupied by z3fold header, NCHUNKS will be calculated + * to 63 which shows the max number of free chunks in z3fold page, also there + * will be 63 freelists per pool. + */ +#define NCHUNKS_ORDER 6 + +#define CHUNK_SHIFT (PAGE_SHIFT - NCHUNKS_ORDER) +#define CHUNK_SIZE (1 << CHUNK_SHIFT) +#define ZHDR_SIZE_ALIGNED CHUNK_SIZE +#define NCHUNKS ((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT) + +#define BUDDY_MASK ((1 << NCHUNKS_ORDER) - 1) + +struct z3fold_pool; +struct z3fold_ops { + int (*evict)(struct z3fold_pool *pool, unsigned long handle); +}; + +/** + * struct z3fold_pool - stores metadata for each z3fold pool + * @lock: protects all pool fields and first|last_chunk fields of any + * z3fold page in the pool + * @unbuddied: array of lists tracking z3fold pages that contain 2- buddies; + * the lists each z3fold page is added to depends on the size of + * its free region. + * @buddied: list tracking the z3fold pages that contain 3 buddies; + * these z3fold pages are full + * @lru: list tracking the z3fold pages in LRU order by most recently + * added buddy. + * @pages_nr: number of z3fold pages in the pool. + * @ops: pointer to a structure of user defined operations specified at + * pool creation time. + * + * This structure is allocated at pool creation time and maintains metadata + * pertaining to a particular z3fold pool. + */ +struct z3fold_pool { + spinlock_t lock; + struct list_head unbuddied[NCHUNKS]; + struct list_head buddied; + struct list_head lru; + u64 pages_nr; + const struct z3fold_ops *ops; + struct zpool *zpool; + const struct zpool_ops *zpool_ops; +}; + +enum buddy { + HEADLESS = 0, + FIRST, + MIDDLE, + LAST, + BUDDIES_MAX +}; + +/* + * struct z3fold_header - z3fold page metadata occupying the first chunk of each + * z3fold page, except for HEADLESS pages + * @buddy: links the z3fold page into the relevant list in the pool + * @first_chunks: the size of the first buddy in chunks, 0 if free + * @middle_chunks: the size of the middle buddy in chunks, 0 if free + * @last_chunks: the size of the last buddy in chunks, 0 if free + * @first_num: the starting number (for the first handle) + */ +struct z3fold_header { + struct list_head buddy; + unsigned short first_chunks; + unsigned short middle_chunks; + unsigned short last_chunks; + unsigned short start_middle; + unsigned short first_num:NCHUNKS_ORDER; +}; + +/* + * Internal z3fold page flags + */ +enum z3fold_page_flags { + UNDER_RECLAIM = 0, + PAGE_HEADLESS, + MIDDLE_CHUNK_MAPPED, +}; + +/***************** + * Helpers +*****************/ + +/* Converts an allocation size in bytes to size in z3fold chunks */ +static int size_to_chunks(size_t size) +{ + return (size + CHUNK_SIZE - 1) >> CHUNK_SHIFT; +} + +#define for_each_unbuddied_list(_iter, _begin) \ + for ((_iter) = (_begin); (_iter) < NCHUNKS; (_iter)++) + +/* Initializes the z3fold header of a newly allocated z3fold page */ +static struct z3fold_header *init_z3fold_page(struct page *page) +{ + struct z3fold_header *zhdr = page_address(page); + + INIT_LIST_HEAD(&page->lru); + clear_bit(UNDER_RECLAIM, &page->private); + clear_bit(PAGE_HEADLESS, &page->private); + clear_bit(MIDDLE_CHUNK_MAPPED, &page->private); + + zhdr->first_chunks = 0; + zhdr->middle_chunks = 0; + zhdr->last_chunks = 0; + zhdr->first_num = 0; + zhdr->start_middle = 0; + INIT_LIST_HEAD(&zhdr->buddy); + return zhdr; +} + +/* Resets the struct page fields and frees the page */ +static void free_z3fold_page(struct z3fold_header *zhdr) +{ + __free_page(virt_to_page(zhdr)); +} + +/* + * Encodes the handle of a particular buddy within a z3fold page + * Pool lock should be held as this function accesses first_num + */ +static unsigned long encode_handle(struct z3fold_header *zhdr, enum buddy bud) +{ + unsigned long handle; + + handle = (unsigned long)zhdr; + if (bud != HEADLESS) + handle += (bud + zhdr->first_num) & BUDDY_MASK; + return handle; +} + +/* Returns the z3fold page where a given handle is stored */ +static struct z3fold_header *handle_to_z3fold_header(unsigned long handle) +{ + return (struct z3fold_header *)(handle & PAGE_MASK); +} + +/* Returns buddy number */ +static enum buddy handle_to_buddy(unsigned long handle) +{ + struct z3fold_header *zhdr = handle_to_z3fold_header(handle); + return (handle - zhdr->first_num) & BUDDY_MASK; +} + +/* + * Returns the number of free chunks in a z3fold page. + * NB: can't be used with HEADLESS pages. + */ +static int num_free_chunks(struct z3fold_header *zhdr) +{ + int nfree; + /* + * If there is a middle object, pick up the bigger free space + * either before or after it. Otherwise just subtract the number + * of chunks occupied by the first and the last objects. + */ + if (zhdr->middle_chunks != 0) { + int nfree_before = zhdr->first_chunks ? + 0 : zhdr->start_middle - 1; + int nfree_after = zhdr->last_chunks ? + 0 : NCHUNKS - zhdr->start_middle - zhdr->middle_chunks; + nfree = max(nfree_before, nfree_after); + } else + nfree = NCHUNKS - zhdr->first_chunks - zhdr->last_chunks; + return nfree; +} + +/***************** + * API Functions +*****************/ +/** + * z3fold_create_pool() - create a new z3fold pool + * @gfp: gfp flags when allocating the z3fold pool structure + * @ops: user-defined operations for the z3fold pool + * + * Return: pointer to the new z3fold pool or NULL if the metadata allocation + * failed. + */ +static struct z3fold_pool *z3fold_create_pool(gfp_t gfp, + const struct z3fold_ops *ops) +{ + struct z3fold_pool *pool; + int i; + + pool = kzalloc(sizeof(struct z3fold_pool), gfp); + if (!pool) + return NULL; + spin_lock_init(&pool->lock); + for_each_unbuddied_list(i, 0) + INIT_LIST_HEAD(&pool->unbuddied[i]); + INIT_LIST_HEAD(&pool->buddied); + INIT_LIST_HEAD(&pool->lru); + pool->pages_nr = 0; + pool->ops = ops; + return pool; +} + +/** + * z3fold_destroy_pool() - destroys an existing z3fold pool + * @pool: the z3fold pool to be destroyed + * + * The pool should be emptied before this function is called. + */ +static void z3fold_destroy_pool(struct z3fold_pool *pool) +{ + kfree(pool); +} + +/* Has to be called with lock held */ +static int z3fold_compact_page(struct z3fold_header *zhdr) +{ + struct page *page = virt_to_page(zhdr); + void *beg = zhdr; + + + if (!test_bit(MIDDLE_CHUNK_MAPPED, &page->private) && + zhdr->middle_chunks != 0 && + zhdr->first_chunks == 0 && zhdr->last_chunks == 0) { + memmove(beg + ZHDR_SIZE_ALIGNED, + beg + (zhdr->start_middle << CHUNK_SHIFT), + zhdr->middle_chunks << CHUNK_SHIFT); + zhdr->first_chunks = zhdr->middle_chunks; + zhdr->middle_chunks = 0; + zhdr->start_middle = 0; + zhdr->first_num++; + return 1; + } + return 0; +} + +/** + * z3fold_alloc() - allocates a region of a given size + * @pool: z3fold pool from which to allocate + * @size: size in bytes of the desired allocation + * @gfp: gfp flags used if the pool needs to grow + * @handle: handle of the new allocation + * + * This function will attempt to find a free region in the pool large enough to + * satisfy the allocation request. A search of the unbuddied lists is + * performed first. If no suitable free region is found, then a new page is + * allocated and added to the pool to satisfy the request. + * + * gfp should not set __GFP_HIGHMEM as highmem pages cannot be used + * as z3fold pool pages. + * + * Return: 0 if success and handle is set, otherwise -EINVAL if the size or + * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate + * a new page. + */ +static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp, + unsigned long *handle) +{ + int chunks = 0, i, freechunks; + struct z3fold_header *zhdr = NULL; + enum buddy bud; + struct page *page; + + if (!size || (gfp & __GFP_HIGHMEM)) + return -EINVAL; + + if (size > PAGE_SIZE) + return -ENOSPC; + + if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE) + bud = HEADLESS; + else { + chunks = size_to_chunks(size); + spin_lock(&pool->lock); + + /* First, try to find an unbuddied z3fold page. */ + zhdr = NULL; + for_each_unbuddied_list(i, chunks) { + if (!list_empty(&pool->unbuddied[i])) { + zhdr = list_first_entry(&pool->unbuddied[i], + struct z3fold_header, buddy); + page = virt_to_page(zhdr); + if (zhdr->first_chunks == 0) { + if (zhdr->middle_chunks != 0 && + chunks >= zhdr->start_middle) + bud = LAST; + else + bud = FIRST; + } else if (zhdr->last_chunks == 0) + bud = LAST; + else if (zhdr->middle_chunks == 0) + bud = MIDDLE; + else { + pr_err("No free chunks in unbuddied\n"); + WARN_ON(1); + continue; + } + list_del(&zhdr->buddy); + goto found; + } + } + bud = FIRST; + spin_unlock(&pool->lock); + } + + /* Couldn't find unbuddied z3fold page, create new one */ + page = alloc_page(gfp); + if (!page) + return -ENOMEM; + spin_lock(&pool->lock); + pool->pages_nr++; + zhdr = init_z3fold_page(page); + + if (bud == HEADLESS) { + set_bit(PAGE_HEADLESS, &page->private); + goto headless; + } + +found: + if (bud == FIRST) + zhdr->first_chunks = chunks; + else if (bud == LAST) + zhdr->last_chunks = chunks; + else { + zhdr->middle_chunks = chunks; + zhdr->start_middle = zhdr->first_chunks + 1; + } + + if (zhdr->first_chunks == 0 || zhdr->last_chunks == 0 || + zhdr->middle_chunks == 0) { + /* Add to unbuddied list */ + freechunks = num_free_chunks(zhdr); + list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + } else { + /* Add to buddied list */ + list_add(&zhdr->buddy, &pool->buddied); + } + +headless: + /* Add/move z3fold page to beginning of LRU */ + if (!list_empty(&page->lru)) + list_del(&page->lru); + + list_add(&page->lru, &pool->lru); + + *handle = encode_handle(zhdr, bud); + spin_unlock(&pool->lock); + + return 0; +} + +/** + * z3fold_free() - frees the allocation associated with the given handle + * @pool: pool in which the allocation resided + * @handle: handle associated with the allocation returned by z3fold_alloc() + * + * In the case that the z3fold page in which the allocation resides is under + * reclaim, as indicated by the PG_reclaim flag being set, this function + * only sets the first|last_chunks to 0. The page is actually freed + * once both buddies are evicted (see z3fold_reclaim_page() below). + */ +static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) +{ + struct z3fold_header *zhdr; + int freechunks; + struct page *page; + enum buddy bud; + + spin_lock(&pool->lock); + zhdr = handle_to_z3fold_header(handle); + page = virt_to_page(zhdr); + + if (test_bit(PAGE_HEADLESS, &page->private)) { + /* HEADLESS page stored */ + bud = HEADLESS; + } else { + bud = handle_to_buddy(handle); + + switch (bud) { + case FIRST: + zhdr->first_chunks = 0; + break; + case MIDDLE: + zhdr->middle_chunks = 0; + zhdr->start_middle = 0; + break; + case LAST: + zhdr->last_chunks = 0; + break; + default: + pr_err("%s: unknown bud %d\n", __func__, bud); + WARN_ON(1); + spin_unlock(&pool->lock); + return; + } + } + + if (test_bit(UNDER_RECLAIM, &page->private)) { + /* z3fold page is under reclaim, reclaim will free */ + spin_unlock(&pool->lock); + return; + } + + if (bud != HEADLESS) { + /* Remove from existing buddy list */ + list_del(&zhdr->buddy); + } + + if (bud == HEADLESS || + (zhdr->first_chunks == 0 && zhdr->middle_chunks == 0 && + zhdr->last_chunks == 0)) { + /* z3fold page is empty, free */ + list_del(&page->lru); + clear_bit(PAGE_HEADLESS, &page->private); + free_z3fold_page(zhdr); + pool->pages_nr--; + } else { + z3fold_compact_page(zhdr); + /* Add to the unbuddied list */ + freechunks = num_free_chunks(zhdr); + list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + } + + spin_unlock(&pool->lock); +} + +/** + * z3fold_reclaim_page() - evicts allocations from a pool page and frees it + * @pool: pool from which a page will attempt to be evicted + * @retires: number of pages on the LRU list for which eviction will + * be attempted before failing + * + * z3fold reclaim is different from normal system reclaim in that it is done + * from the bottom, up. This is because only the bottom layer, z3fold, has + * information on how the allocations are organized within each z3fold page. + * This has the potential to create interesting locking situations between + * z3fold and the user, however. + * + * To avoid these, this is how z3fold_reclaim_page() should be called: + + * The user detects a page should be reclaimed and calls z3fold_reclaim_page(). + * z3fold_reclaim_page() will remove a z3fold page from the pool LRU list and + * call the user-defined eviction handler with the pool and handle as + * arguments. + * + * If the handle can not be evicted, the eviction handler should return + * non-zero. z3fold_reclaim_page() will add the z3fold page back to the + * appropriate list and try the next z3fold page on the LRU up to + * a user defined number of retries. + * + * If the handle is successfully evicted, the eviction handler should + * return 0 _and_ should have called z3fold_free() on the handle. z3fold_free() + * contains logic to delay freeing the page if the page is under reclaim, + * as indicated by the setting of the PG_reclaim flag on the underlying page. + * + * If all buddies in the z3fold page are successfully evicted, then the + * z3fold page can be freed. + * + * Returns: 0 if page is successfully freed, otherwise -EINVAL if there are + * no pages to evict or an eviction handler is not registered, -EAGAIN if + * the retry limit was hit. + */ +static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) +{ + int i, ret = 0, freechunks; + struct z3fold_header *zhdr; + struct page *page; + unsigned long first_handle = 0, middle_handle = 0, last_handle = 0; + + spin_lock(&pool->lock); + if (!pool->ops || !pool->ops->evict || list_empty(&pool->lru) || + retries == 0) { + spin_unlock(&pool->lock); + return -EINVAL; + } + for (i = 0; i < retries; i++) { + page = list_last_entry(&pool->lru, struct page, lru); + list_del(&page->lru); + + /* Protect z3fold page against free */ + set_bit(UNDER_RECLAIM, &page->private); + zhdr = page_address(page); + if (!test_bit(PAGE_HEADLESS, &page->private)) { + list_del(&zhdr->buddy); + /* + * We need encode the handles before unlocking, since + * we can race with free that will set + * (first|last)_chunks to 0 + */ + first_handle = 0; + last_handle = 0; + middle_handle = 0; + if (zhdr->first_chunks) + first_handle = encode_handle(zhdr, FIRST); + if (zhdr->middle_chunks) + middle_handle = encode_handle(zhdr, MIDDLE); + if (zhdr->last_chunks) + last_handle = encode_handle(zhdr, LAST); + } else { + first_handle = encode_handle(zhdr, HEADLESS); + last_handle = middle_handle = 0; + } + + spin_unlock(&pool->lock); + + /* Issue the eviction callback(s) */ + if (middle_handle) { + ret = pool->ops->evict(pool, middle_handle); + if (ret) + goto next; + } + if (first_handle) { + ret = pool->ops->evict(pool, first_handle); + if (ret) + goto next; + } + if (last_handle) { + ret = pool->ops->evict(pool, last_handle); + if (ret) + goto next; + } +next: + spin_lock(&pool->lock); + clear_bit(UNDER_RECLAIM, &page->private); + if ((test_bit(PAGE_HEADLESS, &page->private) && ret == 0) || + (zhdr->first_chunks == 0 && zhdr->last_chunks == 0 && + zhdr->middle_chunks == 0)) { + /* + * All buddies are now free, free the z3fold page and + * return success. + */ + clear_bit(PAGE_HEADLESS, &page->private); + free_z3fold_page(zhdr); + pool->pages_nr--; + spin_unlock(&pool->lock); + return 0; + } else if (!test_bit(PAGE_HEADLESS, &page->private)) { + if (zhdr->first_chunks != 0 && + zhdr->last_chunks != 0 && + zhdr->middle_chunks != 0) { + /* Full, add to buddied list */ + list_add(&zhdr->buddy, &pool->buddied); + } else { + z3fold_compact_page(zhdr); + /* add to unbuddied list */ + freechunks = num_free_chunks(zhdr); + list_add(&zhdr->buddy, + &pool->unbuddied[freechunks]); + } + } + + /* add to beginning of LRU */ + list_add(&page->lru, &pool->lru); + } + spin_unlock(&pool->lock); + return -EAGAIN; +} + +/** + * z3fold_map() - maps the allocation associated with the given handle + * @pool: pool in which the allocation resides + * @handle: handle associated with the allocation to be mapped + * + * Extracts the buddy number from handle and constructs the pointer to the + * correct starting chunk within the page. + * + * Returns: a pointer to the mapped allocation + */ +static void *z3fold_map(struct z3fold_pool *pool, unsigned long handle) +{ + struct z3fold_header *zhdr; + struct page *page; + void *addr; + enum buddy buddy; + + spin_lock(&pool->lock); + zhdr = handle_to_z3fold_header(handle); + addr = zhdr; + page = virt_to_page(zhdr); + + if (test_bit(PAGE_HEADLESS, &page->private)) + goto out; + + buddy = handle_to_buddy(handle); + switch (buddy) { + case FIRST: + addr += ZHDR_SIZE_ALIGNED; + break; + case MIDDLE: + addr += zhdr->start_middle << CHUNK_SHIFT; + set_bit(MIDDLE_CHUNK_MAPPED, &page->private); + break; + case LAST: + addr += PAGE_SIZE - (zhdr->last_chunks << CHUNK_SHIFT); + break; + default: + pr_err("unknown buddy id %d\n", buddy); + WARN_ON(1); + addr = NULL; + break; + } +out: + spin_unlock(&pool->lock); + return addr; +} + +/** + * z3fold_unmap() - unmaps the allocation associated with the given handle + * @pool: pool in which the allocation resides + * @handle: handle associated with the allocation to be unmapped + */ +static void z3fold_unmap(struct z3fold_pool *pool, unsigned long handle) +{ + struct z3fold_header *zhdr; + struct page *page; + enum buddy buddy; + + spin_lock(&pool->lock); + zhdr = handle_to_z3fold_header(handle); + page = virt_to_page(zhdr); + + if (test_bit(PAGE_HEADLESS, &page->private)) { + spin_unlock(&pool->lock); + return; + } + + buddy = handle_to_buddy(handle); + if (buddy == MIDDLE) + clear_bit(MIDDLE_CHUNK_MAPPED, &page->private); + spin_unlock(&pool->lock); +} + +/** + * z3fold_get_pool_size() - gets the z3fold pool size in pages + * @pool: pool whose size is being queried + * + * Returns: size in pages of the given pool. The pool lock need not be + * taken to access pages_nr. + */ +static u64 z3fold_get_pool_size(struct z3fold_pool *pool) +{ + return pool->pages_nr; +} + +/***************** + * zpool + ****************/ + +static int z3fold_zpool_evict(struct z3fold_pool *pool, unsigned long handle) +{ + if (pool->zpool && pool->zpool_ops && pool->zpool_ops->evict) + return pool->zpool_ops->evict(pool->zpool, handle); + else + return -ENOENT; +} + +static const struct z3fold_ops z3fold_zpool_ops = { + .evict = z3fold_zpool_evict +}; + +static void *z3fold_zpool_create(const char *name, gfp_t gfp, + const struct zpool_ops *zpool_ops, + struct zpool *zpool) +{ + struct z3fold_pool *pool; + + pool = z3fold_create_pool(gfp, zpool_ops ? &z3fold_zpool_ops : NULL); + if (pool) { + pool->zpool = zpool; + pool->zpool_ops = zpool_ops; + } + return pool; +} + +static void z3fold_zpool_destroy(void *pool) +{ + z3fold_destroy_pool(pool); +} + +static int z3fold_zpool_malloc(void *pool, size_t size, gfp_t gfp, + unsigned long *handle) +{ + return z3fold_alloc(pool, size, gfp, handle); +} +static void z3fold_zpool_free(void *pool, unsigned long handle) +{ + z3fold_free(pool, handle); +} + +static int z3fold_zpool_shrink(void *pool, unsigned int pages, + unsigned int *reclaimed) +{ + unsigned int total = 0; + int ret = -EINVAL; + + while (total < pages) { + ret = z3fold_reclaim_page(pool, 8); + if (ret < 0) + break; + total++; + } + + if (reclaimed) + *reclaimed = total; + + return ret; +} + +static void *z3fold_zpool_map(void *pool, unsigned long handle, + enum zpool_mapmode mm) +{ + return z3fold_map(pool, handle); +} +static void z3fold_zpool_unmap(void *pool, unsigned long handle) +{ + z3fold_unmap(pool, handle); +} + +static u64 z3fold_zpool_total_size(void *pool) +{ + return z3fold_get_pool_size(pool) * PAGE_SIZE; +} + +static struct zpool_driver z3fold_zpool_driver = { + .type = "z3fold", + .owner = THIS_MODULE, + .create = z3fold_zpool_create, + .destroy = z3fold_zpool_destroy, + .malloc = z3fold_zpool_malloc, + .free = z3fold_zpool_free, + .shrink = z3fold_zpool_shrink, + .map = z3fold_zpool_map, + .unmap = z3fold_zpool_unmap, + .total_size = z3fold_zpool_total_size, +}; + +MODULE_ALIAS("zpool-z3fold"); + +static int __init init_z3fold(void) +{ + /* Make sure the z3fold header will fit in one chunk */ + BUILD_BUG_ON(sizeof(struct z3fold_header) > ZHDR_SIZE_ALIGNED); + zpool_register_driver(&z3fold_zpool_driver); + + return 0; +} + +static void __exit exit_z3fold(void) +{ + zpool_unregister_driver(&z3fold_zpool_driver); +} + +module_init(init_z3fold); +module_exit(exit_z3fold); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Vitaly Wool <vitalywool@gmail.com>"); +MODULE_DESCRIPTION("3-Fold Allocator for Compressed Pages"); diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index e72efb109fde..b0bc023d25c5 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -16,35 +16,21 @@ * struct page(s) to form a zspage. * * Usage of struct page fields: - * page->private: points to the first component (0-order) page - * page->index (union with page->freelist): offset of the first object - * starting in this page. For the first page, this is - * always 0, so we use this field (aka freelist) to point - * to the first free object in zspage. - * page->lru: links together all component pages (except the first page) - * of a zspage - * - * For _first_ page only: - * - * page->private: refers to the component page after the first page - * If the page is first_page for huge object, it stores handle. - * Look at size_class->huge. - * page->freelist: points to the first free object in zspage. - * Free objects are linked together using in-place - * metadata. - * page->objects: maximum number of objects we can store in this - * zspage (class->zspage_order * PAGE_SIZE / class->size) - * page->lru: links together first pages of various zspages. - * Basically forming list of zspages in a fullness group. - * page->mapping: class index and fullness group of the zspage - * page->inuse: the number of objects that are used in this zspage + * page->private: points to zspage + * page->freelist(index): links together all component pages of a zspage + * For the huge page, this is always 0, so we use this field + * to store handle. + * page->units: first object offset in a subpage of zspage * * Usage of struct page flags: * PG_private: identifies the first component page * PG_private2: identifies the last component page + * PG_owner_priv_1: indentifies the huge component page * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/kernel.h> #include <linux/sched.h> @@ -64,6 +50,11 @@ #include <linux/debugfs.h> #include <linux/zsmalloc.h> #include <linux/zpool.h> +#include <linux/mount.h> +#include <linux/migrate.h> +#include <linux/pagemap.h> + +#define ZSPAGE_MAGIC 0x58 /* * This must be power of 2 and greater than of equal to sizeof(link_free). @@ -86,9 +77,7 @@ * Object location (<PFN>, <obj_idx>) is encoded as * as single (unsigned long) handle value. * - * Note that object index <obj_idx> is relative to system - * page <PFN> it is stored in, so for each sub-page belonging - * to a zspage, obj_idx starts with 0. + * Note that object index <obj_idx> starts from 0. * * This is made more complicated by various memory models and PAE. */ @@ -147,33 +136,26 @@ * ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN * (reason above) */ -#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> 8) +#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> CLASS_BITS) -/* - * We do not maintain any list for completely empty or full pages - */ enum fullness_group { - ZS_ALMOST_FULL, - ZS_ALMOST_EMPTY, - _ZS_NR_FULLNESS_GROUPS, - ZS_EMPTY, - ZS_FULL + ZS_ALMOST_EMPTY, + ZS_ALMOST_FULL, + ZS_FULL, + NR_ZS_FULLNESS, }; enum zs_stat_type { + CLASS_EMPTY, + CLASS_ALMOST_EMPTY, + CLASS_ALMOST_FULL, + CLASS_FULL, OBJ_ALLOCATED, OBJ_USED, - CLASS_ALMOST_FULL, - CLASS_ALMOST_EMPTY, + NR_ZS_STAT_TYPE, }; -#ifdef CONFIG_ZSMALLOC_STAT -#define NR_ZS_STAT_TYPE (CLASS_ALMOST_EMPTY + 1) -#else -#define NR_ZS_STAT_TYPE (OBJ_USED + 1) -#endif - struct zs_size_stat { unsigned long objs[NR_ZS_STAT_TYPE]; }; @@ -182,6 +164,10 @@ struct zs_size_stat { static struct dentry *zs_stat_root; #endif +#ifdef CONFIG_COMPACTION +static struct vfsmount *zsmalloc_mnt; +#endif + /* * number of size_classes */ @@ -205,35 +191,49 @@ static const int fullness_threshold_frac = 4; struct size_class { spinlock_t lock; - struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS]; + struct list_head fullness_list[NR_ZS_FULLNESS]; /* * Size of objects stored in this class. Must be multiple * of ZS_ALIGN. */ int size; - unsigned int index; - - struct zs_size_stat stats; - + int objs_per_zspage; /* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */ int pages_per_zspage; - /* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */ - bool huge; + + unsigned int index; + struct zs_size_stat stats; }; +/* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */ +static void SetPageHugeObject(struct page *page) +{ + SetPageOwnerPriv1(page); +} + +static void ClearPageHugeObject(struct page *page) +{ + ClearPageOwnerPriv1(page); +} + +static int PageHugeObject(struct page *page) +{ + return PageOwnerPriv1(page); +} + /* * Placed within free objects to form a singly linked list. - * For every zspage, first_page->freelist gives head of this list. + * For every zspage, zspage->freeobj gives head of this list. * * This must be power of 2 and less than or equal to ZS_ALIGN */ struct link_free { union { /* - * Position of next free chunk (encodes <PFN, obj_idx>) + * Free object index; * It's valid for non-allocated object */ - void *next; + unsigned long next; /* * Handle of allocated object. */ @@ -246,8 +246,8 @@ struct zs_pool { struct size_class **size_class; struct kmem_cache *handle_cachep; + struct kmem_cache *zspage_cachep; - gfp_t flags; /* allocation flags used when growing pool */ atomic_long_t pages_allocated; struct zs_pool_stats stats; @@ -262,16 +262,36 @@ struct zs_pool { #ifdef CONFIG_ZSMALLOC_STAT struct dentry *stat_dentry; #endif +#ifdef CONFIG_COMPACTION + struct inode *inode; + struct work_struct free_work; +#endif }; /* * A zspage's class index and fullness group * are encoded in its (first)page->mapping */ -#define CLASS_IDX_BITS 28 -#define FULLNESS_BITS 4 -#define CLASS_IDX_MASK ((1 << CLASS_IDX_BITS) - 1) -#define FULLNESS_MASK ((1 << FULLNESS_BITS) - 1) +#define FULLNESS_BITS 2 +#define CLASS_BITS 8 +#define ISOLATED_BITS 3 +#define MAGIC_VAL_BITS 8 + +struct zspage { + struct { + unsigned int fullness:FULLNESS_BITS; + unsigned int class:CLASS_BITS; + unsigned int isolated:ISOLATED_BITS; + unsigned int magic:MAGIC_VAL_BITS; + }; + unsigned int inuse; + unsigned int freeobj; + struct page *first_page; + struct list_head list; /* fullness list */ +#ifdef CONFIG_COMPACTION + rwlock_t lock; +#endif +}; struct mapping_area { #ifdef CONFIG_PGTABLE_MAPPING @@ -283,29 +303,74 @@ struct mapping_area { enum zs_mapmode vm_mm; /* mapping mode */ }; -static int create_handle_cache(struct zs_pool *pool) +#ifdef CONFIG_COMPACTION +static int zs_register_migration(struct zs_pool *pool); +static void zs_unregister_migration(struct zs_pool *pool); +static void migrate_lock_init(struct zspage *zspage); +static void migrate_read_lock(struct zspage *zspage); +static void migrate_read_unlock(struct zspage *zspage); +static void kick_deferred_free(struct zs_pool *pool); +static void init_deferred_free(struct zs_pool *pool); +static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage); +#else +static int zsmalloc_mount(void) { return 0; } +static void zsmalloc_unmount(void) {} +static int zs_register_migration(struct zs_pool *pool) { return 0; } +static void zs_unregister_migration(struct zs_pool *pool) {} +static void migrate_lock_init(struct zspage *zspage) {} +static void migrate_read_lock(struct zspage *zspage) {} +static void migrate_read_unlock(struct zspage *zspage) {} +static void kick_deferred_free(struct zs_pool *pool) {} +static void init_deferred_free(struct zs_pool *pool) {} +static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) {} +#endif + +static int create_cache(struct zs_pool *pool) { pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_SIZE, 0, 0, NULL); - return pool->handle_cachep ? 0 : 1; + if (!pool->handle_cachep) + return 1; + + pool->zspage_cachep = kmem_cache_create("zspage", sizeof(struct zspage), + 0, 0, NULL); + if (!pool->zspage_cachep) { + kmem_cache_destroy(pool->handle_cachep); + pool->handle_cachep = NULL; + return 1; + } + + return 0; } -static void destroy_handle_cache(struct zs_pool *pool) +static void destroy_cache(struct zs_pool *pool) { kmem_cache_destroy(pool->handle_cachep); + kmem_cache_destroy(pool->zspage_cachep); } -static unsigned long alloc_handle(struct zs_pool *pool) +static unsigned long cache_alloc_handle(struct zs_pool *pool, gfp_t gfp) { return (unsigned long)kmem_cache_alloc(pool->handle_cachep, - pool->flags & ~__GFP_HIGHMEM); + gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE)); } -static void free_handle(struct zs_pool *pool, unsigned long handle) +static void cache_free_handle(struct zs_pool *pool, unsigned long handle) { kmem_cache_free(pool->handle_cachep, (void *)handle); } +static struct zspage *cache_alloc_zspage(struct zs_pool *pool, gfp_t flags) +{ + return kmem_cache_alloc(pool->zspage_cachep, + flags & ~(__GFP_HIGHMEM|__GFP_MOVABLE)); +}; + +static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage) +{ + kmem_cache_free(pool->zspage_cachep, zspage); +} + static void record_obj(unsigned long handle, unsigned long obj) { /* @@ -324,7 +389,12 @@ static void *zs_zpool_create(const char *name, gfp_t gfp, const struct zpool_ops *zpool_ops, struct zpool *zpool) { - return zs_create_pool(name, gfp); + /* + * Ignore global gfp flags: zs_malloc() may be invoked from + * different contexts and its caller must provide a valid + * gfp mask. + */ + return zs_create_pool(name); } static void zs_zpool_destroy(void *pool) @@ -335,7 +405,7 @@ static void zs_zpool_destroy(void *pool) static int zs_zpool_malloc(void *pool, size_t size, gfp_t gfp, unsigned long *handle) { - *handle = zs_malloc(pool, size); + *handle = zs_malloc(pool, size, gfp); return *handle ? 0 : -1; } static void zs_zpool_free(void *pool, unsigned long handle) @@ -395,44 +465,79 @@ static struct zpool_driver zs_zpool_driver = { MODULE_ALIAS("zpool-zsmalloc"); #endif /* CONFIG_ZPOOL */ -static unsigned int get_maxobj_per_zspage(int size, int pages_per_zspage) -{ - return pages_per_zspage * PAGE_SIZE / size; -} - /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ static DEFINE_PER_CPU(struct mapping_area, zs_map_area); +static bool is_zspage_isolated(struct zspage *zspage) +{ + return zspage->isolated; +} + static int is_first_page(struct page *page) { return PagePrivate(page); } -static int is_last_page(struct page *page) +/* Protected by class->lock */ +static inline int get_zspage_inuse(struct zspage *zspage) +{ + return zspage->inuse; +} + +static inline void set_zspage_inuse(struct zspage *zspage, int val) +{ + zspage->inuse = val; +} + +static inline void mod_zspage_inuse(struct zspage *zspage, int val) +{ + zspage->inuse += val; +} + +static inline struct page *get_first_page(struct zspage *zspage) +{ + struct page *first_page = zspage->first_page; + + VM_BUG_ON_PAGE(!is_first_page(first_page), first_page); + return first_page; +} + +static inline int get_first_obj_offset(struct page *page) { - return PagePrivate2(page); + return page->units; } -static void get_zspage_mapping(struct page *page, unsigned int *class_idx, +static inline void set_first_obj_offset(struct page *page, int offset) +{ + page->units = offset; +} + +static inline unsigned int get_freeobj(struct zspage *zspage) +{ + return zspage->freeobj; +} + +static inline void set_freeobj(struct zspage *zspage, unsigned int obj) +{ + zspage->freeobj = obj; +} + +static void get_zspage_mapping(struct zspage *zspage, + unsigned int *class_idx, enum fullness_group *fullness) { - unsigned long m; - BUG_ON(!is_first_page(page)); + BUG_ON(zspage->magic != ZSPAGE_MAGIC); - m = (unsigned long)page->mapping; - *fullness = m & FULLNESS_MASK; - *class_idx = (m >> FULLNESS_BITS) & CLASS_IDX_MASK; + *fullness = zspage->fullness; + *class_idx = zspage->class; } -static void set_zspage_mapping(struct page *page, unsigned int class_idx, +static void set_zspage_mapping(struct zspage *zspage, + unsigned int class_idx, enum fullness_group fullness) { - unsigned long m; - BUG_ON(!is_first_page(page)); - - m = ((class_idx & CLASS_IDX_MASK) << FULLNESS_BITS) | - (fullness & FULLNESS_MASK); - page->mapping = (struct address_space *)m; + zspage->class = class_idx; + zspage->fullness = fullness; } /* @@ -456,37 +561,33 @@ static int get_size_class_index(int size) static inline void zs_stat_inc(struct size_class *class, enum zs_stat_type type, unsigned long cnt) { - if (type < NR_ZS_STAT_TYPE) - class->stats.objs[type] += cnt; + class->stats.objs[type] += cnt; } static inline void zs_stat_dec(struct size_class *class, enum zs_stat_type type, unsigned long cnt) { - if (type < NR_ZS_STAT_TYPE) - class->stats.objs[type] -= cnt; + class->stats.objs[type] -= cnt; } static inline unsigned long zs_stat_get(struct size_class *class, enum zs_stat_type type) { - if (type < NR_ZS_STAT_TYPE) - return class->stats.objs[type]; - return 0; + return class->stats.objs[type]; } #ifdef CONFIG_ZSMALLOC_STAT -static int __init zs_stat_init(void) +static void __init zs_stat_init(void) { - if (!debugfs_initialized()) - return -ENODEV; + if (!debugfs_initialized()) { + pr_warn("debugfs not available, stat dir not created\n"); + return; + } zs_stat_root = debugfs_create_dir("zsmalloc", NULL); if (!zs_stat_root) - return -ENOMEM; - - return 0; + pr_warn("debugfs 'zsmalloc' stat dir creation failed\n"); } static void __exit zs_stat_exit(void) @@ -527,8 +628,7 @@ static int zs_stats_size_show(struct seq_file *s, void *v) freeable = zs_can_compact(class); spin_unlock(&class->lock); - objs_per_zspage = get_maxobj_per_zspage(class->size, - class->pages_per_zspage); + objs_per_zspage = class->objs_per_zspage; pages_used = obj_allocated / objs_per_zspage * class->pages_per_zspage; @@ -567,17 +667,19 @@ static const struct file_operations zs_stat_size_ops = { .release = single_release, }; -static int zs_pool_stat_create(const char *name, struct zs_pool *pool) +static void zs_pool_stat_create(struct zs_pool *pool, const char *name) { struct dentry *entry; - if (!zs_stat_root) - return -ENODEV; + if (!zs_stat_root) { + pr_warn("no root stat dir, not creating <%s> stat dir\n", name); + return; + } entry = debugfs_create_dir(name, zs_stat_root); if (!entry) { pr_warn("debugfs dir <%s> creation failed\n", name); - return -ENOMEM; + return; } pool->stat_dentry = entry; @@ -586,10 +688,9 @@ static int zs_pool_stat_create(const char *name, struct zs_pool *pool) if (!entry) { pr_warn("%s: debugfs file entry <%s> creation failed\n", name, "classes"); - return -ENOMEM; + debugfs_remove_recursive(pool->stat_dentry); + pool->stat_dentry = NULL; } - - return 0; } static void zs_pool_stat_destroy(struct zs_pool *pool) @@ -598,18 +699,16 @@ static void zs_pool_stat_destroy(struct zs_pool *pool) } #else /* CONFIG_ZSMALLOC_STAT */ -static int __init zs_stat_init(void) +static void __init zs_stat_init(void) { - return 0; } static void __exit zs_stat_exit(void) { } -static inline int zs_pool_stat_create(const char *name, struct zs_pool *pool) +static inline void zs_pool_stat_create(struct zs_pool *pool, const char *name) { - return 0; } static inline void zs_pool_stat_destroy(struct zs_pool *pool) @@ -625,20 +724,20 @@ static inline void zs_pool_stat_destroy(struct zs_pool *pool) * the pool (not yet implemented). This function returns fullness * status of the given page. */ -static enum fullness_group get_fullness_group(struct page *page) +static enum fullness_group get_fullness_group(struct size_class *class, + struct zspage *zspage) { - int inuse, max_objects; + int inuse, objs_per_zspage; enum fullness_group fg; - BUG_ON(!is_first_page(page)); - inuse = page->inuse; - max_objects = page->objects; + inuse = get_zspage_inuse(zspage); + objs_per_zspage = class->objs_per_zspage; if (inuse == 0) fg = ZS_EMPTY; - else if (inuse == max_objects) + else if (inuse == objs_per_zspage) fg = ZS_FULL; - else if (inuse <= 3 * max_objects / fullness_threshold_frac) + else if (inuse <= 3 * objs_per_zspage / fullness_threshold_frac) fg = ZS_ALMOST_EMPTY; else fg = ZS_ALMOST_FULL; @@ -652,59 +751,41 @@ static enum fullness_group get_fullness_group(struct page *page) * have. This functions inserts the given zspage into the freelist * identified by <class, fullness_group>. */ -static void insert_zspage(struct page *page, struct size_class *class, +static void insert_zspage(struct size_class *class, + struct zspage *zspage, enum fullness_group fullness) { - struct page **head; - - BUG_ON(!is_first_page(page)); - - if (fullness >= _ZS_NR_FULLNESS_GROUPS) - return; - - zs_stat_inc(class, fullness == ZS_ALMOST_EMPTY ? - CLASS_ALMOST_EMPTY : CLASS_ALMOST_FULL, 1); - - head = &class->fullness_list[fullness]; - if (!*head) { - *head = page; - return; - } + struct zspage *head; + zs_stat_inc(class, fullness, 1); + head = list_first_entry_or_null(&class->fullness_list[fullness], + struct zspage, list); /* - * We want to see more ZS_FULL pages and less almost - * empty/full. Put pages with higher ->inuse first. + * We want to see more ZS_FULL pages and less almost empty/full. + * Put pages with higher ->inuse first. */ - list_add_tail(&page->lru, &(*head)->lru); - if (page->inuse >= (*head)->inuse) - *head = page; + if (head) { + if (get_zspage_inuse(zspage) < get_zspage_inuse(head)) { + list_add(&zspage->list, &head->list); + return; + } + } + list_add(&zspage->list, &class->fullness_list[fullness]); } /* * This function removes the given zspage from the freelist identified * by <class, fullness_group>. */ -static void remove_zspage(struct page *page, struct size_class *class, +static void remove_zspage(struct size_class *class, + struct zspage *zspage, enum fullness_group fullness) { - struct page **head; - - BUG_ON(!is_first_page(page)); - - if (fullness >= _ZS_NR_FULLNESS_GROUPS) - return; - - head = &class->fullness_list[fullness]; - BUG_ON(!*head); - if (list_empty(&(*head)->lru)) - *head = NULL; - else if (*head == page) - *head = (struct page *)list_entry((*head)->lru.next, - struct page, lru); + VM_BUG_ON(list_empty(&class->fullness_list[fullness])); + VM_BUG_ON(is_zspage_isolated(zspage)); - list_del_init(&page->lru); - zs_stat_dec(class, fullness == ZS_ALMOST_EMPTY ? - CLASS_ALMOST_EMPTY : CLASS_ALMOST_FULL, 1); + list_del_init(&zspage->list); + zs_stat_dec(class, fullness, 1); } /* @@ -717,21 +798,22 @@ static void remove_zspage(struct page *page, struct size_class *class, * fullness group. */ static enum fullness_group fix_fullness_group(struct size_class *class, - struct page *page) + struct zspage *zspage) { int class_idx; enum fullness_group currfg, newfg; - BUG_ON(!is_first_page(page)); - - get_zspage_mapping(page, &class_idx, &currfg); - newfg = get_fullness_group(page); + get_zspage_mapping(zspage, &class_idx, &currfg); + newfg = get_fullness_group(class, zspage); if (newfg == currfg) goto out; - remove_zspage(page, class, currfg); - insert_zspage(page, class, newfg); - set_zspage_mapping(page, class_idx, newfg); + if (!is_zspage_isolated(zspage)) { + remove_zspage(class, zspage, currfg); + insert_zspage(class, zspage, newfg); + } + + set_zspage_mapping(zspage, class_idx, newfg); out: return newfg; @@ -773,64 +855,49 @@ static int get_pages_per_zspage(int class_size) return max_usedpc_order; } -/* - * A single 'zspage' is composed of many system pages which are - * linked together using fields in struct page. This function finds - * the first/head page, given any component page of a zspage. - */ -static struct page *get_first_page(struct page *page) +static struct zspage *get_zspage(struct page *page) { - if (is_first_page(page)) - return page; - else - return (struct page *)page_private(page); + struct zspage *zspage = (struct zspage *)page->private; + + BUG_ON(zspage->magic != ZSPAGE_MAGIC); + return zspage; } static struct page *get_next_page(struct page *page) { - struct page *next; + if (unlikely(PageHugeObject(page))) + return NULL; - if (is_last_page(page)) - next = NULL; - else if (is_first_page(page)) - next = (struct page *)page_private(page); - else - next = list_entry(page->lru.next, struct page, lru); + return page->freelist; +} - return next; +/** + * obj_to_location - get (<page>, <obj_idx>) from encoded object value + * @page: page object resides in zspage + * @obj_idx: object index + */ +static void obj_to_location(unsigned long obj, struct page **page, + unsigned int *obj_idx) +{ + obj >>= OBJ_TAG_BITS; + *page = pfn_to_page(obj >> OBJ_INDEX_BITS); + *obj_idx = (obj & OBJ_INDEX_MASK); } -/* - * Encode <page, obj_idx> as a single handle value. - * We use the least bit of handle for tagging. +/** + * location_to_obj - get obj value encoded from (<page>, <obj_idx>) + * @page: page object resides in zspage + * @obj_idx: object index */ -static void *location_to_obj(struct page *page, unsigned long obj_idx) +static unsigned long location_to_obj(struct page *page, unsigned int obj_idx) { unsigned long obj; - if (!page) { - BUG_ON(obj_idx); - return NULL; - } - obj = page_to_pfn(page) << OBJ_INDEX_BITS; - obj |= ((obj_idx) & OBJ_INDEX_MASK); + obj |= obj_idx & OBJ_INDEX_MASK; obj <<= OBJ_TAG_BITS; - return (void *)obj; -} - -/* - * Decode <page, obj_idx> pair from the given object handle. We adjust the - * decoded obj_idx back to its original value since it was adjusted in - * location_to_obj(). - */ -static void obj_to_location(unsigned long obj, struct page **page, - unsigned long *obj_idx) -{ - obj >>= OBJ_TAG_BITS; - *page = pfn_to_page(obj >> OBJ_INDEX_BITS); - *obj_idx = (obj & OBJ_INDEX_MASK); + return obj; } static unsigned long handle_to_obj(unsigned long handle) @@ -838,108 +905,146 @@ static unsigned long handle_to_obj(unsigned long handle) return *(unsigned long *)handle; } -static unsigned long obj_to_head(struct size_class *class, struct page *page, - void *obj) +static unsigned long obj_to_head(struct page *page, void *obj) { - if (class->huge) { - VM_BUG_ON(!is_first_page(page)); - return page_private(page); + if (unlikely(PageHugeObject(page))) { + VM_BUG_ON_PAGE(!is_first_page(page), page); + return page->index; } else return *(unsigned long *)obj; } -static unsigned long obj_idx_to_offset(struct page *page, - unsigned long obj_idx, int class_size) +static inline int testpin_tag(unsigned long handle) { - unsigned long off = 0; - - if (!is_first_page(page)) - off = page->index; - - return off + obj_idx * class_size; + return bit_spin_is_locked(HANDLE_PIN_BIT, (unsigned long *)handle); } static inline int trypin_tag(unsigned long handle) { - unsigned long *ptr = (unsigned long *)handle; - - return !test_and_set_bit_lock(HANDLE_PIN_BIT, ptr); + return bit_spin_trylock(HANDLE_PIN_BIT, (unsigned long *)handle); } static void pin_tag(unsigned long handle) { - while (!trypin_tag(handle)); + bit_spin_lock(HANDLE_PIN_BIT, (unsigned long *)handle); } static void unpin_tag(unsigned long handle) { - unsigned long *ptr = (unsigned long *)handle; - - clear_bit_unlock(HANDLE_PIN_BIT, ptr); + bit_spin_unlock(HANDLE_PIN_BIT, (unsigned long *)handle); } static void reset_page(struct page *page) { - clear_bit(PG_private, &page->flags); - clear_bit(PG_private_2, &page->flags); + __ClearPageMovable(page); + ClearPagePrivate(page); + ClearPagePrivate2(page); set_page_private(page, 0); - page->mapping = NULL; - page->freelist = NULL; page_mapcount_reset(page); + ClearPageHugeObject(page); + page->freelist = NULL; } -static void free_zspage(struct page *first_page) +/* + * To prevent zspage destroy during migration, zspage freeing should + * hold locks of all pages in the zspage. + */ +void lock_zspage(struct zspage *zspage) { - struct page *nextp, *tmp, *head_extra; + struct page *page = get_first_page(zspage); - BUG_ON(!is_first_page(first_page)); - BUG_ON(first_page->inuse); + do { + lock_page(page); + } while ((page = get_next_page(page)) != NULL); +} - head_extra = (struct page *)page_private(first_page); +int trylock_zspage(struct zspage *zspage) +{ + struct page *cursor, *fail; + + for (cursor = get_first_page(zspage); cursor != NULL; cursor = + get_next_page(cursor)) { + if (!trylock_page(cursor)) { + fail = cursor; + goto unlock; + } + } - reset_page(first_page); - __free_page(first_page); + return 1; +unlock: + for (cursor = get_first_page(zspage); cursor != fail; cursor = + get_next_page(cursor)) + unlock_page(cursor); - /* zspage with only 1 system page */ - if (!head_extra) - return; + return 0; +} + +static void __free_zspage(struct zs_pool *pool, struct size_class *class, + struct zspage *zspage) +{ + struct page *page, *next; + enum fullness_group fg; + unsigned int class_idx; + + get_zspage_mapping(zspage, &class_idx, &fg); + + assert_spin_locked(&class->lock); + + VM_BUG_ON(get_zspage_inuse(zspage)); + VM_BUG_ON(fg != ZS_EMPTY); + + next = page = get_first_page(zspage); + do { + VM_BUG_ON_PAGE(!PageLocked(page), page); + next = get_next_page(page); + reset_page(page); + unlock_page(page); + dec_zone_page_state(page, NR_ZSPAGES); + put_page(page); + page = next; + } while (page != NULL); + + cache_free_zspage(pool, zspage); + + zs_stat_dec(class, OBJ_ALLOCATED, class->objs_per_zspage); + atomic_long_sub(class->pages_per_zspage, + &pool->pages_allocated); +} + +static void free_zspage(struct zs_pool *pool, struct size_class *class, + struct zspage *zspage) +{ + VM_BUG_ON(get_zspage_inuse(zspage)); + VM_BUG_ON(list_empty(&zspage->list)); - list_for_each_entry_safe(nextp, tmp, &head_extra->lru, lru) { - list_del(&nextp->lru); - reset_page(nextp); - __free_page(nextp); + if (!trylock_zspage(zspage)) { + kick_deferred_free(pool); + return; } - reset_page(head_extra); - __free_page(head_extra); + + remove_zspage(class, zspage, ZS_EMPTY); + __free_zspage(pool, class, zspage); } /* Initialize a newly allocated zspage */ -static void init_zspage(struct page *first_page, struct size_class *class) +static void init_zspage(struct size_class *class, struct zspage *zspage) { + unsigned int freeobj = 1; unsigned long off = 0; - struct page *page = first_page; + struct page *page = get_first_page(zspage); - BUG_ON(!is_first_page(first_page)); while (page) { struct page *next_page; struct link_free *link; - unsigned int i = 1; void *vaddr; - /* - * page->index stores offset of first object starting - * in the page. For the first page, this is always 0, - * so we use first_page->index (aka ->freelist) to store - * head of corresponding zspage's freelist. - */ - if (page != first_page) - page->index = off; + set_first_obj_offset(page, off); vaddr = kmap_atomic(page); link = (struct link_free *)vaddr + off / sizeof(*link); while ((off += class->size) < PAGE_SIZE) { - link->next = location_to_obj(page, i++); + link->next = freeobj++ << OBJ_TAG_BITS; link += class->size / sizeof(*link); } @@ -949,87 +1054,112 @@ static void init_zspage(struct page *first_page, struct size_class *class) * page (if present) */ next_page = get_next_page(page); - link->next = location_to_obj(next_page, 0); + if (next_page) { + link->next = freeobj++ << OBJ_TAG_BITS; + } else { + /* + * Reset OBJ_TAG_BITS bit to last link to tell + * whether it's allocated object or not. + */ + link->next = -1 << OBJ_TAG_BITS; + } kunmap_atomic(vaddr); page = next_page; off %= PAGE_SIZE; } + + set_freeobj(zspage, 0); } -/* - * Allocate a zspage for the given size class - */ -static struct page *alloc_zspage(struct size_class *class, gfp_t flags) +static void create_page_chain(struct size_class *class, struct zspage *zspage, + struct page *pages[]) { - int i, error; - struct page *first_page = NULL, *uninitialized_var(prev_page); + int i; + struct page *page; + struct page *prev_page = NULL; + int nr_pages = class->pages_per_zspage; /* * Allocate individual pages and link them together as: - * 1. first page->private = first sub-page - * 2. all sub-pages are linked together using page->lru - * 3. each sub-page is linked to the first page using page->private + * 1. all pages are linked together using page->freelist + * 2. each sub-page point to zspage using page->private * - * For each size class, First/Head pages are linked together using - * page->lru. Also, we set PG_private to identify the first page - * (i.e. no other sub-page has this flag set) and PG_private_2 to - * identify the last page. + * we set PG_private to identify the first page (i.e. no other sub-page + * has this flag set) and PG_private_2 to identify the last page. */ - error = -ENOMEM; - for (i = 0; i < class->pages_per_zspage; i++) { - struct page *page; - - page = alloc_page(flags); - if (!page) - goto cleanup; - - INIT_LIST_HEAD(&page->lru); - if (i == 0) { /* first page */ + for (i = 0; i < nr_pages; i++) { + page = pages[i]; + set_page_private(page, (unsigned long)zspage); + page->freelist = NULL; + if (i == 0) { + zspage->first_page = page; SetPagePrivate(page); - set_page_private(page, 0); - first_page = page; - first_page->inuse = 0; + if (unlikely(class->objs_per_zspage == 1 && + class->pages_per_zspage == 1)) + SetPageHugeObject(page); + } else { + prev_page->freelist = page; } - if (i == 1) - set_page_private(first_page, (unsigned long)page); - if (i >= 1) - set_page_private(page, (unsigned long)first_page); - if (i >= 2) - list_add(&page->lru, &prev_page->lru); - if (i == class->pages_per_zspage - 1) /* last page */ + if (i == nr_pages - 1) SetPagePrivate2(page); prev_page = page; } +} + +/* + * Allocate a zspage for the given size class + */ +static struct zspage *alloc_zspage(struct zs_pool *pool, + struct size_class *class, + gfp_t gfp) +{ + int i; + struct page *pages[ZS_MAX_PAGES_PER_ZSPAGE]; + struct zspage *zspage = cache_alloc_zspage(pool, gfp); - init_zspage(first_page, class); + if (!zspage) + return NULL; - first_page->freelist = location_to_obj(first_page, 0); - /* Maximum number of objects we can store in this zspage */ - first_page->objects = class->pages_per_zspage * PAGE_SIZE / class->size; + memset(zspage, 0, sizeof(struct zspage)); + zspage->magic = ZSPAGE_MAGIC; + migrate_lock_init(zspage); - error = 0; /* Success */ + for (i = 0; i < class->pages_per_zspage; i++) { + struct page *page; -cleanup: - if (unlikely(error) && first_page) { - free_zspage(first_page); - first_page = NULL; + page = alloc_page(gfp); + if (!page) { + while (--i >= 0) { + dec_zone_page_state(pages[i], NR_ZSPAGES); + __free_page(pages[i]); + } + cache_free_zspage(pool, zspage); + return NULL; + } + + inc_zone_page_state(page, NR_ZSPAGES); + pages[i] = page; } - return first_page; + create_page_chain(class, zspage, pages); + init_zspage(class, zspage); + + return zspage; } -static struct page *find_get_zspage(struct size_class *class) +static struct zspage *find_get_zspage(struct size_class *class) { int i; - struct page *page; + struct zspage *zspage; - for (i = 0; i < _ZS_NR_FULLNESS_GROUPS; i++) { - page = class->fullness_list[i]; - if (page) + for (i = ZS_ALMOST_FULL; i >= ZS_EMPTY; i--) { + zspage = list_first_entry_or_null(&class->fullness_list[i], + struct zspage, list); + if (zspage) break; } - return page; + return zspage; } #ifdef CONFIG_PGTABLE_MAPPING @@ -1211,7 +1341,7 @@ static void zs_unregister_cpu_notifier(void) cpu_notifier_register_done(); } -static void init_zs_size_classes(void) +static void __init init_zs_size_classes(void) { int nr; @@ -1222,23 +1352,19 @@ static void init_zs_size_classes(void) zs_size_classes = nr; } -static bool can_merge(struct size_class *prev, int size, int pages_per_zspage) +static bool can_merge(struct size_class *prev, int pages_per_zspage, + int objs_per_zspage) { - if (prev->pages_per_zspage != pages_per_zspage) - return false; + if (prev->pages_per_zspage == pages_per_zspage && + prev->objs_per_zspage == objs_per_zspage) + return true; - if (get_maxobj_per_zspage(prev->size, prev->pages_per_zspage) - != get_maxobj_per_zspage(size, pages_per_zspage)) - return false; - - return true; + return false; } -static bool zspage_full(struct page *page) +static bool zspage_full(struct size_class *class, struct zspage *zspage) { - BUG_ON(!is_first_page(page)); - - return page->inuse == page->objects; + return get_zspage_inuse(zspage) == class->objs_per_zspage; } unsigned long zs_get_total_pages(struct zs_pool *pool) @@ -1264,8 +1390,10 @@ EXPORT_SYMBOL_GPL(zs_get_total_pages); void *zs_map_object(struct zs_pool *pool, unsigned long handle, enum zs_mapmode mm) { + struct zspage *zspage; struct page *page; - unsigned long obj, obj_idx, off; + unsigned long obj, off; + unsigned int obj_idx; unsigned int class_idx; enum fullness_group fg; @@ -1274,23 +1402,26 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, struct page *pages[2]; void *ret; - BUG_ON(!handle); - /* * Because we use per-cpu mapping areas shared among the * pools/users, we can't allow mapping in interrupt context * because it can corrupt another users mappings. */ - BUG_ON(in_interrupt()); + WARN_ON_ONCE(in_interrupt()); /* From now on, migration cannot move the object */ pin_tag(handle); obj = handle_to_obj(handle); obj_to_location(obj, &page, &obj_idx); - get_zspage_mapping(get_first_page(page), &class_idx, &fg); + zspage = get_zspage(page); + + /* migration cannot move any subpage in this zspage */ + migrate_read_lock(zspage); + + get_zspage_mapping(zspage, &class_idx, &fg); class = pool->size_class[class_idx]; - off = obj_idx_to_offset(page, obj_idx, class->size); + off = (class->size * obj_idx) & ~PAGE_MASK; area = &get_cpu_var(zs_map_area); area->vm_mm = mm; @@ -1308,7 +1439,7 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, ret = __zs_map_object(area, pages, off, class->size); out: - if (!class->huge) + if (likely(!PageHugeObject(page))) ret += ZS_HANDLE_SIZE; return ret; @@ -1317,21 +1448,22 @@ EXPORT_SYMBOL_GPL(zs_map_object); void zs_unmap_object(struct zs_pool *pool, unsigned long handle) { + struct zspage *zspage; struct page *page; - unsigned long obj, obj_idx, off; + unsigned long obj, off; + unsigned int obj_idx; unsigned int class_idx; enum fullness_group fg; struct size_class *class; struct mapping_area *area; - BUG_ON(!handle); - obj = handle_to_obj(handle); obj_to_location(obj, &page, &obj_idx); - get_zspage_mapping(get_first_page(page), &class_idx, &fg); + zspage = get_zspage(page); + get_zspage_mapping(zspage, &class_idx, &fg); class = pool->size_class[class_idx]; - off = obj_idx_to_offset(page, obj_idx, class->size); + off = (class->size * obj_idx) & ~PAGE_MASK; area = this_cpu_ptr(&zs_map_area); if (off + class->size <= PAGE_SIZE) @@ -1346,38 +1478,50 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) __zs_unmap_object(area, pages, off, class->size); } put_cpu_var(zs_map_area); + + migrate_read_unlock(zspage); unpin_tag(handle); } EXPORT_SYMBOL_GPL(zs_unmap_object); -static unsigned long obj_malloc(struct page *first_page, - struct size_class *class, unsigned long handle) +static unsigned long obj_malloc(struct size_class *class, + struct zspage *zspage, unsigned long handle) { + int i, nr_page, offset; unsigned long obj; struct link_free *link; struct page *m_page; - unsigned long m_objidx, m_offset; + unsigned long m_offset; void *vaddr; handle |= OBJ_ALLOCATED_TAG; - obj = (unsigned long)first_page->freelist; - obj_to_location(obj, &m_page, &m_objidx); - m_offset = obj_idx_to_offset(m_page, m_objidx, class->size); + obj = get_freeobj(zspage); + + offset = obj * class->size; + nr_page = offset >> PAGE_SHIFT; + m_offset = offset & ~PAGE_MASK; + m_page = get_first_page(zspage); + + for (i = 0; i < nr_page; i++) + m_page = get_next_page(m_page); vaddr = kmap_atomic(m_page); link = (struct link_free *)vaddr + m_offset / sizeof(*link); - first_page->freelist = link->next; - if (!class->huge) + set_freeobj(zspage, link->next >> OBJ_TAG_BITS); + if (likely(!PageHugeObject(m_page))) /* record handle in the header of allocated chunk */ link->handle = handle; else - /* record handle in first_page->private */ - set_page_private(first_page, handle); + /* record handle to page->index */ + zspage->first_page->index = handle; + kunmap_atomic(vaddr); - first_page->inuse++; + mod_zspage_inuse(zspage, 1); zs_stat_inc(class, OBJ_USED, 1); + obj = location_to_obj(m_page, obj); + return obj; } @@ -1386,21 +1530,23 @@ static unsigned long obj_malloc(struct page *first_page, * zs_malloc - Allocate block of given size from pool. * @pool: pool to allocate from * @size: size of block to allocate + * @gfp: gfp flags when allocating object * * On success, handle to the allocated object is returned, * otherwise 0. * Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail. */ -unsigned long zs_malloc(struct zs_pool *pool, size_t size) +unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) { unsigned long handle, obj; struct size_class *class; - struct page *first_page; + enum fullness_group newfg; + struct zspage *zspage; if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE)) return 0; - handle = alloc_handle(pool); + handle = cache_alloc_handle(pool, gfp); if (!handle) return 0; @@ -1409,71 +1555,78 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size) class = pool->size_class[get_size_class_index(size)]; spin_lock(&class->lock); - first_page = find_get_zspage(class); - - if (!first_page) { + zspage = find_get_zspage(class); + if (likely(zspage)) { + obj = obj_malloc(class, zspage, handle); + /* Now move the zspage to another fullness group, if required */ + fix_fullness_group(class, zspage); + record_obj(handle, obj); spin_unlock(&class->lock); - first_page = alloc_zspage(class, pool->flags); - if (unlikely(!first_page)) { - free_handle(pool, handle); - return 0; - } - set_zspage_mapping(first_page, class->index, ZS_EMPTY); - atomic_long_add(class->pages_per_zspage, - &pool->pages_allocated); + return handle; + } - spin_lock(&class->lock); - zs_stat_inc(class, OBJ_ALLOCATED, get_maxobj_per_zspage( - class->size, class->pages_per_zspage)); + spin_unlock(&class->lock); + + zspage = alloc_zspage(pool, class, gfp); + if (!zspage) { + cache_free_handle(pool, handle); + return 0; } - obj = obj_malloc(first_page, class, handle); - /* Now move the zspage to another fullness group, if required */ - fix_fullness_group(class, first_page); + spin_lock(&class->lock); + obj = obj_malloc(class, zspage, handle); + newfg = get_fullness_group(class, zspage); + insert_zspage(class, zspage, newfg); + set_zspage_mapping(zspage, class->index, newfg); record_obj(handle, obj); + atomic_long_add(class->pages_per_zspage, + &pool->pages_allocated); + zs_stat_inc(class, OBJ_ALLOCATED, class->objs_per_zspage); + + /* We completely set up zspage so mark them as movable */ + SetZsPageMovable(pool, zspage); spin_unlock(&class->lock); return handle; } EXPORT_SYMBOL_GPL(zs_malloc); -static void obj_free(struct zs_pool *pool, struct size_class *class, - unsigned long obj) +static void obj_free(struct size_class *class, unsigned long obj) { struct link_free *link; - struct page *first_page, *f_page; - unsigned long f_objidx, f_offset; + struct zspage *zspage; + struct page *f_page; + unsigned long f_offset; + unsigned int f_objidx; void *vaddr; - BUG_ON(!obj); - obj &= ~OBJ_ALLOCATED_TAG; obj_to_location(obj, &f_page, &f_objidx); - first_page = get_first_page(f_page); - - f_offset = obj_idx_to_offset(f_page, f_objidx, class->size); + f_offset = (class->size * f_objidx) & ~PAGE_MASK; + zspage = get_zspage(f_page); vaddr = kmap_atomic(f_page); /* Insert this object in containing zspage's freelist */ link = (struct link_free *)(vaddr + f_offset); - link->next = first_page->freelist; - if (class->huge) - set_page_private(first_page, 0); + link->next = get_freeobj(zspage) << OBJ_TAG_BITS; kunmap_atomic(vaddr); - first_page->freelist = (void *)obj; - first_page->inuse--; + set_freeobj(zspage, f_objidx); + mod_zspage_inuse(zspage, -1); zs_stat_dec(class, OBJ_USED, 1); } void zs_free(struct zs_pool *pool, unsigned long handle) { - struct page *first_page, *f_page; - unsigned long obj, f_objidx; + struct zspage *zspage; + struct page *f_page; + unsigned long obj; + unsigned int f_objidx; int class_idx; struct size_class *class; enum fullness_group fullness; + bool isolated; if (unlikely(!handle)) return; @@ -1481,33 +1634,39 @@ void zs_free(struct zs_pool *pool, unsigned long handle) pin_tag(handle); obj = handle_to_obj(handle); obj_to_location(obj, &f_page, &f_objidx); - first_page = get_first_page(f_page); + zspage = get_zspage(f_page); + + migrate_read_lock(zspage); - get_zspage_mapping(first_page, &class_idx, &fullness); + get_zspage_mapping(zspage, &class_idx, &fullness); class = pool->size_class[class_idx]; spin_lock(&class->lock); - obj_free(pool, class, obj); - fullness = fix_fullness_group(class, first_page); - if (fullness == ZS_EMPTY) { - zs_stat_dec(class, OBJ_ALLOCATED, get_maxobj_per_zspage( - class->size, class->pages_per_zspage)); - atomic_long_sub(class->pages_per_zspage, - &pool->pages_allocated); - free_zspage(first_page); + obj_free(class, obj); + fullness = fix_fullness_group(class, zspage); + if (fullness != ZS_EMPTY) { + migrate_read_unlock(zspage); + goto out; } + + isolated = is_zspage_isolated(zspage); + migrate_read_unlock(zspage); + /* If zspage is isolated, zs_page_putback will free the zspage */ + if (likely(!isolated)) + free_zspage(pool, class, zspage); +out: + spin_unlock(&class->lock); unpin_tag(handle); - - free_handle(pool, handle); + cache_free_handle(pool, handle); } EXPORT_SYMBOL_GPL(zs_free); -static void zs_object_copy(unsigned long dst, unsigned long src, - struct size_class *class) +static void zs_object_copy(struct size_class *class, unsigned long dst, + unsigned long src) { struct page *s_page, *d_page; - unsigned long s_objidx, d_objidx; + unsigned int s_objidx, d_objidx; unsigned long s_off, d_off; void *s_addr, *d_addr; int s_size, d_size, size; @@ -1518,8 +1677,8 @@ static void zs_object_copy(unsigned long dst, unsigned long src, obj_to_location(src, &s_page, &s_objidx); obj_to_location(dst, &d_page, &d_objidx); - s_off = obj_idx_to_offset(s_page, s_objidx, class->size); - d_off = obj_idx_to_offset(d_page, d_objidx, class->size); + s_off = (class->size * s_objidx) & ~PAGE_MASK; + d_off = (class->size * d_objidx) & ~PAGE_MASK; if (s_off + class->size > PAGE_SIZE) s_size = PAGE_SIZE - s_off; @@ -1547,7 +1706,6 @@ static void zs_object_copy(unsigned long dst, unsigned long src, kunmap_atomic(d_addr); kunmap_atomic(s_addr); s_page = get_next_page(s_page); - BUG_ON(!s_page); s_addr = kmap_atomic(s_page); d_addr = kmap_atomic(d_page); s_size = class->size - written; @@ -1557,7 +1715,6 @@ static void zs_object_copy(unsigned long dst, unsigned long src, if (d_off >= PAGE_SIZE) { kunmap_atomic(d_addr); d_page = get_next_page(d_page); - BUG_ON(!d_page); d_addr = kmap_atomic(d_page); d_size = class->size - written; d_off = 0; @@ -1572,20 +1729,20 @@ static void zs_object_copy(unsigned long dst, unsigned long src, * Find alloced object in zspage from index object and * return handle. */ -static unsigned long find_alloced_obj(struct page *page, int index, - struct size_class *class) +static unsigned long find_alloced_obj(struct size_class *class, + struct page *page, int *obj_idx) { unsigned long head; int offset = 0; + int index = *obj_idx; unsigned long handle = 0; void *addr = kmap_atomic(page); - if (!is_first_page(page)) - offset = page->index; + offset = get_first_obj_offset(page); offset += class->size * index; while (offset < PAGE_SIZE) { - head = obj_to_head(class, page, addr + offset); + head = obj_to_head(page, addr + offset); if (head & OBJ_ALLOCATED_TAG) { handle = head & ~OBJ_ALLOCATED_TAG; if (trypin_tag(handle)) @@ -1598,18 +1755,21 @@ static unsigned long find_alloced_obj(struct page *page, int index, } kunmap_atomic(addr); + + *obj_idx = index; + return handle; } struct zs_compact_control { - /* Source page for migration which could be a subpage of zspage. */ + /* Source spage for migration which could be a subpage of zspage */ struct page *s_page; /* Destination page for migration which should be a first page * of zspage. */ struct page *d_page; /* Starting object index within @s_page which used for live object * in the subpage. */ - int index; + int obj_idx; }; static int migrate_zspage(struct zs_pool *pool, struct size_class *class, @@ -1619,30 +1779,30 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class, unsigned long handle; struct page *s_page = cc->s_page; struct page *d_page = cc->d_page; - unsigned long index = cc->index; + int obj_idx = cc->obj_idx; int ret = 0; while (1) { - handle = find_alloced_obj(s_page, index, class); + handle = find_alloced_obj(class, s_page, &obj_idx); if (!handle) { s_page = get_next_page(s_page); if (!s_page) break; - index = 0; + obj_idx = 0; continue; } /* Stop if there is no more space */ - if (zspage_full(d_page)) { + if (zspage_full(class, get_zspage(d_page))) { unpin_tag(handle); ret = -ENOMEM; break; } used_obj = handle_to_obj(handle); - free_obj = obj_malloc(d_page, class, handle); - zs_object_copy(free_obj, used_obj, class); - index++; + free_obj = obj_malloc(class, get_zspage(d_page), handle); + zs_object_copy(class, free_obj, used_obj); + obj_idx++; /* * record_obj updates handle's value to free_obj and it will * invalidate lock bit(ie, HANDLE_PIN_BIT) of handle, which @@ -1652,81 +1812,432 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class, free_obj |= BIT(HANDLE_PIN_BIT); record_obj(handle, free_obj); unpin_tag(handle); - obj_free(pool, class, used_obj); + obj_free(class, used_obj); } /* Remember last position in this iteration */ cc->s_page = s_page; - cc->index = index; + cc->obj_idx = obj_idx; return ret; } -static struct page *isolate_target_page(struct size_class *class) +static struct zspage *isolate_zspage(struct size_class *class, bool source) { int i; - struct page *page; + struct zspage *zspage; + enum fullness_group fg[2] = {ZS_ALMOST_EMPTY, ZS_ALMOST_FULL}; - for (i = 0; i < _ZS_NR_FULLNESS_GROUPS; i++) { - page = class->fullness_list[i]; - if (page) { - remove_zspage(page, class, i); - break; + if (!source) { + fg[0] = ZS_ALMOST_FULL; + fg[1] = ZS_ALMOST_EMPTY; + } + + for (i = 0; i < 2; i++) { + zspage = list_first_entry_or_null(&class->fullness_list[fg[i]], + struct zspage, list); + if (zspage) { + VM_BUG_ON(is_zspage_isolated(zspage)); + remove_zspage(class, zspage, fg[i]); + return zspage; } } - return page; + return zspage; } /* - * putback_zspage - add @first_page into right class's fullness list - * @pool: target pool + * putback_zspage - add @zspage into right class's fullness list * @class: destination class - * @first_page: target page + * @zspage: target page * - * Return @fist_page's fullness_group + * Return @zspage's fullness_group */ -static enum fullness_group putback_zspage(struct zs_pool *pool, - struct size_class *class, - struct page *first_page) +static enum fullness_group putback_zspage(struct size_class *class, + struct zspage *zspage) { enum fullness_group fullness; - BUG_ON(!is_first_page(first_page)); + VM_BUG_ON(is_zspage_isolated(zspage)); - fullness = get_fullness_group(first_page); - insert_zspage(first_page, class, fullness); - set_zspage_mapping(first_page, class->index, fullness); + fullness = get_fullness_group(class, zspage); + insert_zspage(class, zspage, fullness); + set_zspage_mapping(zspage, class->index, fullness); - if (fullness == ZS_EMPTY) { - zs_stat_dec(class, OBJ_ALLOCATED, get_maxobj_per_zspage( - class->size, class->pages_per_zspage)); - atomic_long_sub(class->pages_per_zspage, - &pool->pages_allocated); + return fullness; +} + +#ifdef CONFIG_COMPACTION +static struct dentry *zs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) +{ + static const struct dentry_operations ops = { + .d_dname = simple_dname, + }; + + return mount_pseudo(fs_type, "zsmalloc:", NULL, &ops, ZSMALLOC_MAGIC); +} + +static struct file_system_type zsmalloc_fs = { + .name = "zsmalloc", + .mount = zs_mount, + .kill_sb = kill_anon_super, +}; + +static int zsmalloc_mount(void) +{ + int ret = 0; + + zsmalloc_mnt = kern_mount(&zsmalloc_fs); + if (IS_ERR(zsmalloc_mnt)) + ret = PTR_ERR(zsmalloc_mnt); + + return ret; +} + +static void zsmalloc_unmount(void) +{ + kern_unmount(zsmalloc_mnt); +} + +static void migrate_lock_init(struct zspage *zspage) +{ + rwlock_init(&zspage->lock); +} + +static void migrate_read_lock(struct zspage *zspage) +{ + read_lock(&zspage->lock); +} + +static void migrate_read_unlock(struct zspage *zspage) +{ + read_unlock(&zspage->lock); +} + +static void migrate_write_lock(struct zspage *zspage) +{ + write_lock(&zspage->lock); +} + +static void migrate_write_unlock(struct zspage *zspage) +{ + write_unlock(&zspage->lock); +} + +/* Number of isolated subpage for *page migration* in this zspage */ +static void inc_zspage_isolation(struct zspage *zspage) +{ + zspage->isolated++; +} + +static void dec_zspage_isolation(struct zspage *zspage) +{ + zspage->isolated--; +} - free_zspage(first_page); +static void replace_sub_page(struct size_class *class, struct zspage *zspage, + struct page *newpage, struct page *oldpage) +{ + struct page *page; + struct page *pages[ZS_MAX_PAGES_PER_ZSPAGE] = {NULL, }; + int idx = 0; + + page = get_first_page(zspage); + do { + if (page == oldpage) + pages[idx] = newpage; + else + pages[idx] = page; + idx++; + } while ((page = get_next_page(page)) != NULL); + + create_page_chain(class, zspage, pages); + set_first_obj_offset(newpage, get_first_obj_offset(oldpage)); + if (unlikely(PageHugeObject(oldpage))) + newpage->index = oldpage->index; + __SetPageMovable(newpage, page_mapping(oldpage)); +} + +bool zs_page_isolate(struct page *page, isolate_mode_t mode) +{ + struct zs_pool *pool; + struct size_class *class; + int class_idx; + enum fullness_group fullness; + struct zspage *zspage; + struct address_space *mapping; + + /* + * Page is locked so zspage couldn't be destroyed. For detail, look at + * lock_zspage in free_zspage. + */ + VM_BUG_ON_PAGE(!PageMovable(page), page); + VM_BUG_ON_PAGE(PageIsolated(page), page); + + zspage = get_zspage(page); + + /* + * Without class lock, fullness could be stale while class_idx is okay + * because class_idx is constant unless page is freed so we should get + * fullness again under class lock. + */ + get_zspage_mapping(zspage, &class_idx, &fullness); + mapping = page_mapping(page); + pool = mapping->private_data; + class = pool->size_class[class_idx]; + + spin_lock(&class->lock); + if (get_zspage_inuse(zspage) == 0) { + spin_unlock(&class->lock); + return false; } - return fullness; + /* zspage is isolated for object migration */ + if (list_empty(&zspage->list) && !is_zspage_isolated(zspage)) { + spin_unlock(&class->lock); + return false; + } + + /* + * If this is first time isolation for the zspage, isolate zspage from + * size_class to prevent further object allocation from the zspage. + */ + if (!list_empty(&zspage->list) && !is_zspage_isolated(zspage)) { + get_zspage_mapping(zspage, &class_idx, &fullness); + remove_zspage(class, zspage, fullness); + } + + inc_zspage_isolation(zspage); + spin_unlock(&class->lock); + + return true; +} + +int zs_page_migrate(struct address_space *mapping, struct page *newpage, + struct page *page, enum migrate_mode mode) +{ + struct zs_pool *pool; + struct size_class *class; + int class_idx; + enum fullness_group fullness; + struct zspage *zspage; + struct page *dummy; + void *s_addr, *d_addr, *addr; + int offset, pos; + unsigned long handle, head; + unsigned long old_obj, new_obj; + unsigned int obj_idx; + int ret = -EAGAIN; + + VM_BUG_ON_PAGE(!PageMovable(page), page); + VM_BUG_ON_PAGE(!PageIsolated(page), page); + + zspage = get_zspage(page); + + /* Concurrent compactor cannot migrate any subpage in zspage */ + migrate_write_lock(zspage); + get_zspage_mapping(zspage, &class_idx, &fullness); + pool = mapping->private_data; + class = pool->size_class[class_idx]; + offset = get_first_obj_offset(page); + + spin_lock(&class->lock); + if (!get_zspage_inuse(zspage)) { + ret = -EBUSY; + goto unlock_class; + } + + pos = offset; + s_addr = kmap_atomic(page); + while (pos < PAGE_SIZE) { + head = obj_to_head(page, s_addr + pos); + if (head & OBJ_ALLOCATED_TAG) { + handle = head & ~OBJ_ALLOCATED_TAG; + if (!trypin_tag(handle)) + goto unpin_objects; + } + pos += class->size; + } + + /* + * Here, any user cannot access all objects in the zspage so let's move. + */ + d_addr = kmap_atomic(newpage); + memcpy(d_addr, s_addr, PAGE_SIZE); + kunmap_atomic(d_addr); + + for (addr = s_addr + offset; addr < s_addr + pos; + addr += class->size) { + head = obj_to_head(page, addr); + if (head & OBJ_ALLOCATED_TAG) { + handle = head & ~OBJ_ALLOCATED_TAG; + if (!testpin_tag(handle)) + BUG(); + + old_obj = handle_to_obj(handle); + obj_to_location(old_obj, &dummy, &obj_idx); + new_obj = (unsigned long)location_to_obj(newpage, + obj_idx); + new_obj |= BIT(HANDLE_PIN_BIT); + record_obj(handle, new_obj); + } + } + + replace_sub_page(class, zspage, newpage, page); + get_page(newpage); + + dec_zspage_isolation(zspage); + + /* + * Page migration is done so let's putback isolated zspage to + * the list if @page is final isolated subpage in the zspage. + */ + if (!is_zspage_isolated(zspage)) + putback_zspage(class, zspage); + + reset_page(page); + put_page(page); + page = newpage; + + ret = MIGRATEPAGE_SUCCESS; +unpin_objects: + for (addr = s_addr + offset; addr < s_addr + pos; + addr += class->size) { + head = obj_to_head(page, addr); + if (head & OBJ_ALLOCATED_TAG) { + handle = head & ~OBJ_ALLOCATED_TAG; + if (!testpin_tag(handle)) + BUG(); + unpin_tag(handle); + } + } + kunmap_atomic(s_addr); +unlock_class: + spin_unlock(&class->lock); + migrate_write_unlock(zspage); + + return ret; +} + +void zs_page_putback(struct page *page) +{ + struct zs_pool *pool; + struct size_class *class; + int class_idx; + enum fullness_group fg; + struct address_space *mapping; + struct zspage *zspage; + + VM_BUG_ON_PAGE(!PageMovable(page), page); + VM_BUG_ON_PAGE(!PageIsolated(page), page); + + zspage = get_zspage(page); + get_zspage_mapping(zspage, &class_idx, &fg); + mapping = page_mapping(page); + pool = mapping->private_data; + class = pool->size_class[class_idx]; + + spin_lock(&class->lock); + dec_zspage_isolation(zspage); + if (!is_zspage_isolated(zspage)) { + fg = putback_zspage(class, zspage); + /* + * Due to page_lock, we cannot free zspage immediately + * so let's defer. + */ + if (fg == ZS_EMPTY) + schedule_work(&pool->free_work); + } + spin_unlock(&class->lock); +} + +const struct address_space_operations zsmalloc_aops = { + .isolate_page = zs_page_isolate, + .migratepage = zs_page_migrate, + .putback_page = zs_page_putback, +}; + +static int zs_register_migration(struct zs_pool *pool) +{ + pool->inode = alloc_anon_inode(zsmalloc_mnt->mnt_sb); + if (IS_ERR(pool->inode)) { + pool->inode = NULL; + return 1; + } + + pool->inode->i_mapping->private_data = pool; + pool->inode->i_mapping->a_ops = &zsmalloc_aops; + return 0; +} + +static void zs_unregister_migration(struct zs_pool *pool) +{ + flush_work(&pool->free_work); + iput(pool->inode); } -static struct page *isolate_source_page(struct size_class *class) +/* + * Caller should hold page_lock of all pages in the zspage + * In here, we cannot use zspage meta data. + */ +static void async_free_zspage(struct work_struct *work) { int i; - struct page *page = NULL; + struct size_class *class; + unsigned int class_idx; + enum fullness_group fullness; + struct zspage *zspage, *tmp; + LIST_HEAD(free_pages); + struct zs_pool *pool = container_of(work, struct zs_pool, + free_work); - for (i = ZS_ALMOST_EMPTY; i >= ZS_ALMOST_FULL; i--) { - page = class->fullness_list[i]; - if (!page) + for (i = 0; i < zs_size_classes; i++) { + class = pool->size_class[i]; + if (class->index != i) continue; - remove_zspage(page, class, i); - break; + spin_lock(&class->lock); + list_splice_init(&class->fullness_list[ZS_EMPTY], &free_pages); + spin_unlock(&class->lock); } - return page; + + list_for_each_entry_safe(zspage, tmp, &free_pages, list) { + list_del(&zspage->list); + lock_zspage(zspage); + + get_zspage_mapping(zspage, &class_idx, &fullness); + VM_BUG_ON(fullness != ZS_EMPTY); + class = pool->size_class[class_idx]; + spin_lock(&class->lock); + __free_zspage(pool, pool->size_class[class_idx], zspage); + spin_unlock(&class->lock); + } +}; + +static void kick_deferred_free(struct zs_pool *pool) +{ + schedule_work(&pool->free_work); +} + +static void init_deferred_free(struct zs_pool *pool) +{ + INIT_WORK(&pool->free_work, async_free_zspage); } +static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) +{ + struct page *page = get_first_page(zspage); + + do { + WARN_ON(!trylock_page(page)); + __SetPageMovable(page, pool->inode->i_mapping); + unlock_page(page); + } while ((page = get_next_page(page)) != NULL); +} +#endif + /* * * Based on the number of unused allocated objects calculate @@ -1735,12 +2246,14 @@ static struct page *isolate_source_page(struct size_class *class) static unsigned long zs_can_compact(struct size_class *class) { unsigned long obj_wasted; + unsigned long obj_allocated = zs_stat_get(class, OBJ_ALLOCATED); + unsigned long obj_used = zs_stat_get(class, OBJ_USED); - obj_wasted = zs_stat_get(class, OBJ_ALLOCATED) - - zs_stat_get(class, OBJ_USED); + if (obj_allocated <= obj_used) + return 0; - obj_wasted /= get_maxobj_per_zspage(class->size, - class->pages_per_zspage); + obj_wasted = obj_allocated - obj_used; + obj_wasted /= class->objs_per_zspage; return obj_wasted * class->pages_per_zspage; } @@ -1748,22 +2261,20 @@ static unsigned long zs_can_compact(struct size_class *class) static void __zs_compact(struct zs_pool *pool, struct size_class *class) { struct zs_compact_control cc; - struct page *src_page; - struct page *dst_page = NULL; + struct zspage *src_zspage; + struct zspage *dst_zspage = NULL; spin_lock(&class->lock); - while ((src_page = isolate_source_page(class))) { - - BUG_ON(!is_first_page(src_page)); + while ((src_zspage = isolate_zspage(class, true))) { if (!zs_can_compact(class)) break; - cc.index = 0; - cc.s_page = src_page; + cc.obj_idx = 0; + cc.s_page = get_first_page(src_zspage); - while ((dst_page = isolate_target_page(class))) { - cc.d_page = dst_page; + while ((dst_zspage = isolate_zspage(class, false))) { + cc.d_page = get_first_page(dst_zspage); /* * If there is no more space in dst_page, resched * and see if anyone had allocated another zspage. @@ -1771,23 +2282,25 @@ static void __zs_compact(struct zs_pool *pool, struct size_class *class) if (!migrate_zspage(pool, class, &cc)) break; - putback_zspage(pool, class, dst_page); + putback_zspage(class, dst_zspage); } /* Stop if we couldn't find slot */ - if (dst_page == NULL) + if (dst_zspage == NULL) break; - putback_zspage(pool, class, dst_page); - if (putback_zspage(pool, class, src_page) == ZS_EMPTY) + putback_zspage(class, dst_zspage); + if (putback_zspage(class, src_zspage) == ZS_EMPTY) { + free_zspage(pool, class, src_zspage); pool->stats.pages_compacted += class->pages_per_zspage; + } spin_unlock(&class->lock); cond_resched(); spin_lock(&class->lock); } - if (src_page) - putback_zspage(pool, class, src_page); + if (src_zspage) + putback_zspage(class, src_zspage); spin_unlock(&class->lock); } @@ -1876,7 +2389,7 @@ static int zs_register_shrinker(struct zs_pool *pool) /** * zs_create_pool - Creates an allocation pool to work from. - * @flags: allocation flags used to allocate pool metadata + * @name: pool name to be created * * This function must be called before anything when using * the zsmalloc allocator. @@ -1884,7 +2397,7 @@ static int zs_register_shrinker(struct zs_pool *pool) * On success, a pointer to the newly created pool is returned, * otherwise NULL. */ -struct zs_pool *zs_create_pool(const char *name, gfp_t flags) +struct zs_pool *zs_create_pool(const char *name) { int i; struct zs_pool *pool; @@ -1894,6 +2407,7 @@ struct zs_pool *zs_create_pool(const char *name, gfp_t flags) if (!pool) return NULL; + init_deferred_free(pool); pool->size_class = kcalloc(zs_size_classes, sizeof(struct size_class *), GFP_KERNEL); if (!pool->size_class) { @@ -1905,7 +2419,7 @@ struct zs_pool *zs_create_pool(const char *name, gfp_t flags) if (!pool->name) goto err; - if (create_handle_cache(pool)) + if (create_cache(pool)) goto err; /* @@ -1915,12 +2429,15 @@ struct zs_pool *zs_create_pool(const char *name, gfp_t flags) for (i = zs_size_classes - 1; i >= 0; i--) { int size; int pages_per_zspage; + int objs_per_zspage; struct size_class *class; + int fullness = 0; size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA; if (size > ZS_MAX_ALLOC_SIZE) size = ZS_MAX_ALLOC_SIZE; pages_per_zspage = get_pages_per_zspage(size); + objs_per_zspage = pages_per_zspage * PAGE_SIZE / size; /* * size_class is used for normal zsmalloc operation such @@ -1932,7 +2449,7 @@ struct zs_pool *zs_create_pool(const char *name, gfp_t flags) * previous size_class if possible. */ if (prev_class) { - if (can_merge(prev_class, size, pages_per_zspage)) { + if (can_merge(prev_class, pages_per_zspage, objs_per_zspage)) { pool->size_class[i] = prev_class; continue; } @@ -1945,18 +2462,20 @@ struct zs_pool *zs_create_pool(const char *name, gfp_t flags) class->size = size; class->index = i; class->pages_per_zspage = pages_per_zspage; - if (pages_per_zspage == 1 && - get_maxobj_per_zspage(size, pages_per_zspage) == 1) - class->huge = true; + class->objs_per_zspage = objs_per_zspage; spin_lock_init(&class->lock); pool->size_class[i] = class; + for (fullness = ZS_EMPTY; fullness < NR_ZS_FULLNESS; + fullness++) + INIT_LIST_HEAD(&class->fullness_list[fullness]); prev_class = class; } - pool->flags = flags; + /* debug only, don't abort if it fails */ + zs_pool_stat_create(pool, name); - if (zs_pool_stat_create(name, pool)) + if (zs_register_migration(pool)) goto err; /* @@ -1978,6 +2497,7 @@ void zs_destroy_pool(struct zs_pool *pool) int i; zs_unregister_shrinker(pool); + zs_unregister_migration(pool); zs_pool_stat_destroy(pool); for (i = 0; i < zs_size_classes; i++) { @@ -1990,8 +2510,8 @@ void zs_destroy_pool(struct zs_pool *pool) if (class->index != i) continue; - for (fg = 0; fg < _ZS_NR_FULLNESS_GROUPS; fg++) { - if (class->fullness_list[fg]) { + for (fg = ZS_EMPTY; fg < NR_ZS_FULLNESS; fg++) { + if (!list_empty(&class->fullness_list[fg])) { pr_info("Freeing non-empty class with size %db, fullness group %d\n", class->size, fg); } @@ -1999,7 +2519,7 @@ void zs_destroy_pool(struct zs_pool *pool) kfree(class); } - destroy_handle_cache(pool); + destroy_cache(pool); kfree(pool->size_class); kfree(pool->name); kfree(pool); @@ -2008,7 +2528,13 @@ EXPORT_SYMBOL_GPL(zs_destroy_pool); static int __init zs_init(void) { - int ret = zs_register_cpu_notifier(); + int ret; + + ret = zsmalloc_mount(); + if (ret) + goto out; + + ret = zs_register_cpu_notifier(); if (ret) goto notifier_fail; @@ -2019,20 +2545,14 @@ static int __init zs_init(void) zpool_register_driver(&zs_zpool_driver); #endif - ret = zs_stat_init(); - if (ret) { - pr_err("zs stat initialization failed\n"); - goto stat_fail; - } + zs_stat_init(); + return 0; -stat_fail: -#ifdef CONFIG_ZPOOL - zpool_unregister_driver(&zs_zpool_driver); -#endif notifier_fail: zs_unregister_cpu_notifier(); - + zsmalloc_unmount(); +out: return ret; } @@ -2041,6 +2561,7 @@ static void __exit zs_exit(void) #ifdef CONFIG_ZPOOL zpool_unregister_driver(&zs_zpool_driver); #endif + zsmalloc_unmount(); zs_unregister_cpu_notifier(); zs_stat_exit(); diff --git a/mm/zswap.c b/mm/zswap.c index bf14508afd64..275b22cc8df4 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -117,7 +117,7 @@ struct zswap_pool { struct crypto_comp * __percpu *tfm; struct kref kref; struct list_head list; - struct rcu_head rcu_head; + struct work_struct work; struct notifier_block notifier; char tfm_name[CRYPTO_MAX_ALG_NAME]; }; @@ -170,6 +170,8 @@ static struct zswap_tree *zswap_trees[MAX_SWAPFILES]; static LIST_HEAD(zswap_pools); /* protects zswap_pools list modification */ static DEFINE_SPINLOCK(zswap_pools_lock); +/* pool counter to provide unique names to zpool */ +static atomic_t zswap_pools_count = ATOMIC_INIT(0); /* used by param callback function */ static bool zswap_init_started; @@ -565,6 +567,7 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor) static struct zswap_pool *zswap_pool_create(char *type, char *compressor) { struct zswap_pool *pool; + char name[38]; /* 'zswap' + 32 char (max) num + \0 */ gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; pool = kzalloc(sizeof(*pool), GFP_KERNEL); @@ -573,7 +576,10 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) return NULL; } - pool->zpool = zpool_create_pool(type, "zswap", gfp, &zswap_zpool_ops); + /* unique name for each pool specifically required by zsmalloc */ + snprintf(name, 38, "zswap%x", atomic_inc_return(&zswap_pools_count)); + + pool->zpool = zpool_create_pool(type, name, gfp, &zswap_zpool_ops); if (!pool->zpool) { pr_err("%s zpool not available\n", type); goto error; @@ -652,9 +658,11 @@ static int __must_check zswap_pool_get(struct zswap_pool *pool) return kref_get_unless_zero(&pool->kref); } -static void __zswap_pool_release(struct rcu_head *head) +static void __zswap_pool_release(struct work_struct *work) { - struct zswap_pool *pool = container_of(head, typeof(*pool), rcu_head); + struct zswap_pool *pool = container_of(work, typeof(*pool), work); + + synchronize_rcu(); /* nobody should have been able to get a kref... */ WARN_ON(kref_get_unless_zero(&pool->kref)); @@ -674,7 +682,9 @@ static void __zswap_pool_empty(struct kref *kref) WARN_ON(pool == zswap_pool_current()); list_del_rcu(&pool->list); - call_rcu(&pool->rcu_head, __zswap_pool_release); + + INIT_WORK(&pool->work, __zswap_pool_release); + schedule_work(&pool->work); spin_unlock(&zswap_pools_lock); } @@ -869,7 +879,7 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) case ZSWAP_SWAPCACHE_EXIST: /* page is already in the swap cache, ignore for now */ - page_cache_release(page); + put_page(page); ret = -EEXIST; goto fail; @@ -897,7 +907,7 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) /* start writeback */ __swap_writepage(page, &wbc, end_swap_bio_write); - page_cache_release(page); + put_page(page); zswap_written_back_pages++; spin_lock(&tree->lock); |