diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 10 | ||||
| -rw-r--r-- | mm/backing-dev.c | 21 | ||||
| -rw-r--r-- | mm/cleancache.c | 2 | ||||
| -rw-r--r-- | mm/cma.c | 83 | ||||
| -rw-r--r-- | mm/compaction.c | 4 | ||||
| -rw-r--r-- | mm/frontswap.c | 2 | ||||
| -rw-r--r-- | mm/gup.c | 3 | ||||
| -rw-r--r-- | mm/hmm.c | 2 | ||||
| -rw-r--r-- | mm/huge_memory.c | 6 | ||||
| -rw-r--r-- | mm/hugetlb.c | 4 | ||||
| -rw-r--r-- | mm/internal.h | 6 | ||||
| -rw-r--r-- | mm/kasan/kasan.c | 66 | ||||
| -rw-r--r-- | mm/ksm.c | 23 | ||||
| -rw-r--r-- | mm/memcontrol.c | 2 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 2 | ||||
| -rw-r--r-- | mm/mempool.c | 108 | ||||
| -rw-r--r-- | mm/migrate.c | 4 | ||||
| -rw-r--r-- | mm/mmap.c | 78 | ||||
| -rw-r--r-- | mm/oom_kill.c | 81 | ||||
| -rw-r--r-- | mm/page_alloc.c | 99 | ||||
| -rw-r--r-- | mm/readahead.c | 39 | ||||
| -rw-r--r-- | mm/rmap.c | 6 | ||||
| -rw-r--r-- | mm/sparse.c | 2 | ||||
| -rw-r--r-- | mm/swapfile.c | 7 | ||||
| -rw-r--r-- | mm/util.c | 2 | ||||
| -rw-r--r-- | mm/vmalloc.c | 21 | ||||
| -rw-r--r-- | mm/vmscan.c | 2 | ||||
| -rw-r--r-- | mm/vmstat.c | 62 | ||||
| -rw-r--r-- | mm/z3fold.c | 42 |
29 files changed, 439 insertions, 350 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index d5004d82a1d6..3e0b6e87f65d 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -266,7 +266,7 @@ config ARCH_ENABLE_THP_MIGRATION bool config PHYS_ADDR_T_64BIT - def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT + def_bool 64BIT config BOUNCE bool "Enable bounce buffers" @@ -305,7 +305,7 @@ config KSM the many instances by a single page with that content, so saving memory until one or another app needs to modify the content. Recommended for use with KVM, or with other duplicative applications. - See Documentation/vm/ksm.txt for more information: KSM is inactive + See Documentation/vm/ksm.rst for more information: KSM is inactive until a program has madvised that an area is MADV_MERGEABLE, and root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set). @@ -530,7 +530,7 @@ config MEM_SOFT_DIRTY into a page just as regular dirty bit, but unlike the latter it can be cleared by hands. - See Documentation/vm/soft-dirty.txt for more details. + See Documentation/admin-guide/mm/soft-dirty.rst for more details. config ZSWAP bool "Compressed cache for swap pages (EXPERIMENTAL)" @@ -636,6 +636,7 @@ config DEFERRED_STRUCT_PAGE_INIT default n depends on NO_BOOTMEM depends on !FLATMEM + depends on !NEED_PER_CPU_KM help Ordinarily all struct pages are initialised during early boot in a single thread. On very large machines this can take a considerable @@ -656,7 +657,8 @@ config IDLE_PAGE_TRACKING be useful to tune memory cgroup limits and/or for job placement within a compute cluster. - See Documentation/vm/idle_page_tracking.txt for more details. + See Documentation/admin-guide/mm/idle_page_tracking.rst for + more details. # arch_add_memory() comprehends device memory config ARCH_HAS_ZONE_DEVICE diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 023190c69dce..8fe3ebd6ac00 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -115,6 +115,7 @@ static int bdi_debug_register(struct backing_dev_info *bdi, const char *name) bdi, &bdi_debug_stats_fops); if (!bdi->debug_stats) { debugfs_remove(bdi->debug_dir); + bdi->debug_dir = NULL; return -ENOMEM; } @@ -383,7 +384,7 @@ static void wb_shutdown(struct bdi_writeback *wb) * the barrier provided by test_and_clear_bit() above. */ smp_wmb(); - clear_bit(WB_shutting_down, &wb->state); + clear_and_wake_up_bit(WB_shutting_down, &wb->state); } static void wb_exit(struct bdi_writeback *wb) @@ -411,6 +412,7 @@ static void wb_exit(struct bdi_writeback *wb) * protected. */ static DEFINE_SPINLOCK(cgwb_lock); +static struct workqueue_struct *cgwb_release_wq; /** * wb_congested_get_create - get or create a wb_congested @@ -521,7 +523,7 @@ static void cgwb_release(struct percpu_ref *refcnt) { struct bdi_writeback *wb = container_of(refcnt, struct bdi_writeback, refcnt); - schedule_work(&wb->release_work); + queue_work(cgwb_release_wq, &wb->release_work); } static void cgwb_kill(struct bdi_writeback *wb) @@ -783,6 +785,21 @@ static void cgwb_bdi_register(struct backing_dev_info *bdi) spin_unlock_irq(&cgwb_lock); } +static int __init cgwb_init(void) +{ + /* + * There can be many concurrent release work items overwhelming + * system_wq. Put them in a separate wq and limit concurrency. + * There's no point in executing many of these in parallel. + */ + cgwb_release_wq = alloc_workqueue("cgwb_release", 0, 1); + if (!cgwb_release_wq) + return -ENOMEM; + + return 0; +} +subsys_initcall(cgwb_init); + #else /* CONFIG_CGROUP_WRITEBACK */ static int cgwb_bdi_init(struct backing_dev_info *bdi) diff --git a/mm/cleancache.c b/mm/cleancache.c index f7b9fdc79d97..126548b5a292 100644 --- a/mm/cleancache.c +++ b/mm/cleancache.c @@ -3,7 +3,7 @@ * * This code provides the generic "frontend" layer to call a matching * "backend" driver implementation of cleancache. See - * Documentation/vm/cleancache.txt for more information. + * Documentation/vm/cleancache.rst for more information. * * Copyright (C) 2009-2010 Oracle Corp. All rights reserved. * Author: Dan Magenheimer @@ -39,7 +39,6 @@ #include <trace/events/cma.h> #include "cma.h" -#include "internal.h" struct cma cma_areas[MAX_CMA_AREAS]; unsigned cma_area_count; @@ -110,25 +109,23 @@ static int __init cma_activate_area(struct cma *cma) if (!cma->bitmap) return -ENOMEM; + WARN_ON_ONCE(!pfn_valid(pfn)); + zone = page_zone(pfn_to_page(pfn)); + do { unsigned j; base_pfn = pfn; - if (!pfn_valid(base_pfn)) - goto err; - - zone = page_zone(pfn_to_page(base_pfn)); for (j = pageblock_nr_pages; j; --j, pfn++) { - if (!pfn_valid(pfn)) - goto err; - + WARN_ON_ONCE(!pfn_valid(pfn)); /* - * In init_cma_reserved_pageblock(), present_pages - * is adjusted with assumption that all pages in - * the pageblock come from a single zone. + * alloc_contig_range requires the pfn range + * specified to be in the same zone. Make this + * simple by forcing the entire CMA resv range + * to be in the same zone. */ if (page_zone(pfn_to_page(pfn)) != zone) - goto err; + goto not_in_zone; } init_cma_reserved_pageblock(pfn_to_page(base_pfn)); } while (--i); @@ -142,7 +139,7 @@ static int __init cma_activate_area(struct cma *cma) return 0; -err: +not_in_zone: pr_err("CMA area %s could not be activated\n", cma->name); kfree(cma->bitmap); cma->count = 0; @@ -152,41 +149,6 @@ err: static int __init cma_init_reserved_areas(void) { int i; - struct zone *zone; - pg_data_t *pgdat; - - if (!cma_area_count) - return 0; - - for_each_online_pgdat(pgdat) { - unsigned long start_pfn = UINT_MAX, end_pfn = 0; - - zone = &pgdat->node_zones[ZONE_MOVABLE]; - - /* - * In this case, we cannot adjust the zone range - * since it is now maximum node span and we don't - * know original zone range. - */ - if (populated_zone(zone)) - continue; - - for (i = 0; i < cma_area_count; i++) { - if (pfn_to_nid(cma_areas[i].base_pfn) != - pgdat->node_id) - continue; - - start_pfn = min(start_pfn, cma_areas[i].base_pfn); - end_pfn = max(end_pfn, cma_areas[i].base_pfn + - cma_areas[i].count); - } - - if (!end_pfn) - continue; - - zone->zone_start_pfn = start_pfn; - zone->spanned_pages = end_pfn - start_pfn; - } for (i = 0; i < cma_area_count; i++) { int ret = cma_activate_area(&cma_areas[i]); @@ -195,32 +157,9 @@ static int __init cma_init_reserved_areas(void) return ret; } - /* - * Reserved pages for ZONE_MOVABLE are now activated and - * this would change ZONE_MOVABLE's managed page counter and - * the other zones' present counter. We need to re-calculate - * various zone information that depends on this initialization. - */ - build_all_zonelists(NULL); - for_each_populated_zone(zone) { - if (zone_idx(zone) == ZONE_MOVABLE) { - zone_pcp_reset(zone); - setup_zone_pageset(zone); - } else - zone_pcp_update(zone); - - set_zone_contiguous(zone); - } - - /* - * We need to re-init per zone wmark by calling - * init_per_zone_wmark_min() but doesn't call here because it is - * registered on core_initcall and it will be called later than us. - */ - return 0; } -pure_initcall(cma_init_reserved_areas); +core_initcall(cma_init_reserved_areas); /** * cma_init_reserved_mem() - create custom contiguous area from reserved memory diff --git a/mm/compaction.c b/mm/compaction.c index 028b7210a669..29bd1df18b98 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1450,12 +1450,14 @@ static enum compact_result __compaction_suitable(struct zone *zone, int order, * if compaction succeeds. * For costly orders, we require low watermark instead of min for * compaction to proceed to increase its chances. + * ALLOC_CMA is used, as pages in CMA pageblocks are considered + * suitable migration targets */ watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ? low_wmark_pages(zone) : min_wmark_pages(zone); watermark += compact_gap(order); if (!__zone_watermark_ok(zone, 0, watermark, classzone_idx, - 0, wmark_target)) + ALLOC_CMA, wmark_target)) return COMPACT_SKIPPED; return COMPACT_CONTINUE; diff --git a/mm/frontswap.c b/mm/frontswap.c index fec8b5044040..4f5476a0f955 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -3,7 +3,7 @@ * * This code provides the generic "frontend" layer to call a matching * "backend" driver implementation of frontswap. See - * Documentation/vm/frontswap.txt for more information. + * Documentation/vm/frontswap.rst for more information. * * Copyright (C) 2009-2012 Oracle Corp. All rights reserved. * Author: Dan Magenheimer @@ -544,6 +544,9 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) if (vm_flags & (VM_IO | VM_PFNMAP)) return -EFAULT; + if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma)) + return -EFAULT; + if (write) { if (!(vm_flags & VM_WRITE)) { if (!(gup_flags & FOLL_FORCE)) @@ -37,7 +37,7 @@ #if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC) /* - * Device private memory see HMM (Documentation/vm/hmm.txt) or hmm.h + * Device private memory see HMM (Documentation/vm/hmm.rst) or hmm.h */ DEFINE_STATIC_KEY_FALSE(device_private_key); EXPORT_SYMBOL(device_private_key); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index a3a1815f8e11..ac5591d8622c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1185,7 +1185,7 @@ static int do_huge_pmd_wp_page_fallback(struct vm_fault *vmf, pmd_t orig_pmd, * mmu_notifier_invalidate_range_end() happens which can lead to a * device seeing memory write in different order than CPU. * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ pmdp_huge_clear_flush_notify(vma, haddr, vmf->pmd); @@ -2037,7 +2037,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, * replacing a zero pmd write protected page with a zero pte write * protected page. * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ pmdp_huge_clear_flush(vma, haddr, pmd); @@ -2431,7 +2431,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, __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); + ClearPageDirty(head + i); __delete_from_page_cache(head + i, NULL); if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head)) shmem_uncharge(head->mapping->host, 1); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 218679138255..129088710510 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3291,7 +3291,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, * table protection not changing it to point * to a new page. * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ huge_ptep_set_wrprotect(src, addr, src_pte); } @@ -4357,7 +4357,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, * No need to call mmu_notifier_invalidate_range() we are downgrading * page table protection not changing it to point to a new page. * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ i_mmap_unlock_write(vma->vm_file->f_mapping); mmu_notifier_invalidate_range_end(mm, start, end); diff --git a/mm/internal.h b/mm/internal.h index 62d8c34e63d5..9e3654d70289 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -53,7 +53,7 @@ void unmap_page_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, struct zap_details *details); -extern int __do_page_cache_readahead(struct address_space *mapping, +extern unsigned int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, pgoff_t offset, unsigned long nr_to_read, unsigned long lookahead_size); @@ -168,9 +168,6 @@ extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern int user_min_free_kbytes; -extern void set_zone_contiguous(struct zone *zone); -extern void clear_zone_contiguous(struct zone *zone); - #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* @@ -498,6 +495,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, #define ALLOC_HARDER 0x10 /* try to alloc harder */ #define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ +#define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ enum ttu_flags; struct tlbflush_unmap_batch; diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index bc0e68f7dc75..f185455b3406 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -792,6 +792,40 @@ DEFINE_ASAN_SET_SHADOW(f5); DEFINE_ASAN_SET_SHADOW(f8); #ifdef CONFIG_MEMORY_HOTPLUG +static bool shadow_mapped(unsigned long addr) +{ + pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + if (pgd_none(*pgd)) + return false; + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) + return false; + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) + return false; + + /* + * We can't use pud_large() or pud_huge(), the first one is + * arch-specific, the last one depends on HUGETLB_PAGE. So let's abuse + * pud_bad(), if pud is bad then it's bad because it's huge. + */ + if (pud_bad(*pud)) + return true; + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return false; + + if (pmd_bad(*pmd)) + return true; + pte = pte_offset_kernel(pmd, addr); + return !pte_none(*pte); +} + static int __meminit kasan_mem_notifier(struct notifier_block *nb, unsigned long action, void *data) { @@ -813,6 +847,14 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb, case MEM_GOING_ONLINE: { void *ret; + /* + * If shadow is mapped already than it must have been mapped + * during the boot. This could happen if we onlining previously + * offlined memory. + */ + if (shadow_mapped(shadow_start)) + return NOTIFY_OK; + ret = __vmalloc_node_range(shadow_size, PAGE_SIZE, shadow_start, shadow_end, GFP_KERNEL, PAGE_KERNEL, VM_NO_GUARD, @@ -824,8 +866,26 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb, kmemleak_ignore(ret); return NOTIFY_OK; } - case MEM_OFFLINE: - vfree((void *)shadow_start); + case MEM_CANCEL_ONLINE: + case MEM_OFFLINE: { + struct vm_struct *vm; + + /* + * shadow_start was either mapped during boot by kasan_init() + * or during memory online by __vmalloc_node_range(). + * In the latter case we can use vfree() to free shadow. + * Non-NULL result of the find_vm_area() will tell us if + * that was the second case. + * + * Currently it's not possible to free shadow mapped + * during boot by kasan_init(). It's because the code + * to do that hasn't been written yet. So we'll just + * leak the memory. + */ + vm = find_vm_area((void *)shadow_start); + if (vm) + vfree((void *)shadow_start); + } } return NOTIFY_OK; @@ -838,5 +898,5 @@ static int __init kasan_memhotplug_init(void) return 0; } -module_init(kasan_memhotplug_init); +core_initcall(kasan_memhotplug_init); #endif @@ -51,7 +51,9 @@ #define DO_NUMA(x) do { } while (0) #endif -/* +/** + * DOC: Overview + * * A few notes about the KSM scanning process, * to make it easier to understand the data structures below: * @@ -67,6 +69,21 @@ * this tree is fully assured to be working (except when pages are unmapped), * and therefore this tree is called the stable tree. * + * The stable tree node includes information required for reverse + * mapping from a KSM page to virtual addresses that map this page. + * + * In order to avoid large latencies of the rmap walks on KSM pages, + * KSM maintains two types of nodes in the stable tree: + * + * * the regular nodes that keep the reverse mapping structures in a + * linked list + * * the "chains" that link nodes ("dups") that represent the same + * write protected memory content, but each "dup" corresponds to a + * different KSM page copy of that content + * + * Internally, the regular nodes, "dups" and "chains" are represented + * using the same :c:type:`struct stable_node` structure. + * * In addition to the stable tree, KSM uses a second data structure called the * unstable tree: this tree holds pointers to pages which have been found to * be "unchanged for a period of time". The unstable tree sorts these pages @@ -1049,7 +1066,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, * No need to notify as we are downgrading page table to read * only not changing it to point to a new page. * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ entry = ptep_clear_flush(vma, pvmw.address, pvmw.pte); /* @@ -1145,7 +1162,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, * No need to notify as we are replacing a read only page with another * read only page with the same content. * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ ptep_clear_flush(vma, addr, ptep); set_pte_at_notify(mm, addr, ptep, newpte); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2bd3df3d101a..1695f38630f1 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3849,7 +3849,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, if (ret) goto out_put_css; - efile.file->f_op->poll(efile.file, &event->pt); + vfs_poll(efile.file, &event->pt); spin_lock(&memcg->event_list_lock); list_add(&event->list, &memcg->event_list); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index f74826cdceea..25982467800b 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1158,7 +1158,7 @@ int __ref add_memory_resource(int nid, struct resource *res, bool online) * nodes have to go through register_node. * TODO clean up this mess. */ - ret = link_mem_sections(nid, start_pfn, nr_pages); + ret = link_mem_sections(nid, start_pfn, nr_pages, false); register_fail: /* * If sysfs file of new node can't create, cpu on the node diff --git a/mm/mempool.c b/mm/mempool.c index 5c9dce34719b..b54f2c20e5e0 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -138,6 +138,28 @@ static void *remove_element(mempool_t *pool, gfp_t flags) } /** + * mempool_exit - exit a mempool initialized with mempool_init() + * @pool: pointer to the memory pool which was initialized with + * mempool_init(). + * + * Free all reserved elements in @pool and @pool itself. This function + * only sleeps if the free_fn() function sleeps. + * + * May be called on a zeroed but uninitialized mempool (i.e. allocated with + * kzalloc()). + */ +void mempool_exit(mempool_t *pool) +{ + while (pool->curr_nr) { + void *element = remove_element(pool, GFP_KERNEL); + pool->free(element, pool->pool_data); + } + kfree(pool->elements); + pool->elements = NULL; +} +EXPORT_SYMBOL(mempool_exit); + +/** * mempool_destroy - deallocate a memory pool * @pool: pointer to the memory pool which was allocated via * mempool_create(). @@ -150,15 +172,65 @@ void mempool_destroy(mempool_t *pool) if (unlikely(!pool)) return; - while (pool->curr_nr) { - void *element = remove_element(pool, GFP_KERNEL); - pool->free(element, pool->pool_data); - } - kfree(pool->elements); + mempool_exit(pool); kfree(pool); } EXPORT_SYMBOL(mempool_destroy); +int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, + mempool_free_t *free_fn, void *pool_data, + gfp_t gfp_mask, int node_id) +{ + spin_lock_init(&pool->lock); + pool->min_nr = min_nr; + pool->pool_data = pool_data; + pool->alloc = alloc_fn; + pool->free = free_fn; + init_waitqueue_head(&pool->wait); + + pool->elements = kmalloc_array_node(min_nr, sizeof(void *), + gfp_mask, node_id); + if (!pool->elements) + return -ENOMEM; + + /* + * First pre-allocate the guaranteed number of buffers. + */ + while (pool->curr_nr < pool->min_nr) { + void *element; + + element = pool->alloc(gfp_mask, pool->pool_data); + if (unlikely(!element)) { + mempool_exit(pool); + return -ENOMEM; + } + add_element(pool, element); + } + + return 0; +} +EXPORT_SYMBOL(mempool_init_node); + +/** + * mempool_init - initialize a memory pool + * @min_nr: the minimum number of elements guaranteed to be + * allocated for this pool. + * @alloc_fn: user-defined element-allocation function. + * @free_fn: user-defined element-freeing function. + * @pool_data: optional private data available to the user-defined functions. + * + * Like mempool_create(), but initializes the pool in (i.e. embedded in another + * structure). + */ +int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, + mempool_free_t *free_fn, void *pool_data) +{ + return mempool_init_node(pool, min_nr, alloc_fn, free_fn, + pool_data, GFP_KERNEL, NUMA_NO_NODE); + +} +EXPORT_SYMBOL(mempool_init); + /** * mempool_create - create a memory pool * @min_nr: the minimum number of elements guaranteed to be @@ -186,35 +258,17 @@ mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn, gfp_t gfp_mask, int node_id) { mempool_t *pool; + pool = kzalloc_node(sizeof(*pool), gfp_mask, node_id); if (!pool) return NULL; - pool->elements = kmalloc_array_node(min_nr, sizeof(void *), - gfp_mask, node_id); - if (!pool->elements) { + + if (mempool_init_node(pool, min_nr, alloc_fn, free_fn, pool_data, + gfp_mask, node_id)) { kfree(pool); return NULL; } - spin_lock_init(&pool->lock); - pool->min_nr = min_nr; - pool->pool_data = pool_data; - init_waitqueue_head(&pool->wait); - pool->alloc = alloc_fn; - pool->free = free_fn; - /* - * First pre-allocate the guaranteed number of buffers. - */ - while (pool->curr_nr < pool->min_nr) { - void *element; - - element = pool->alloc(gfp_mask, pool->pool_data); - if (unlikely(!element)) { - mempool_destroy(pool); - return NULL; - } - add_element(pool, element); - } return pool; } EXPORT_SYMBOL(mempool_create_node); diff --git a/mm/migrate.c b/mm/migrate.c index 568433023831..8c0af0f7cab1 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -528,14 +528,12 @@ int migrate_page_move_mapping(struct address_space *mapping, int i; int index = page_index(page); - for (i = 0; i < HPAGE_PMD_NR; i++) { + for (i = 1; i < HPAGE_PMD_NR; i++) { pslot = radix_tree_lookup_slot(&mapping->i_pages, index + i); radix_tree_replace_slot(&mapping->i_pages, pslot, newpage + i); } - } else { - radix_tree_replace_slot(&mapping->i_pages, pslot, newpage); } /* diff --git a/mm/mmap.c b/mm/mmap.c index 9d5968d1e8e3..d817764a9974 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1324,6 +1324,35 @@ static inline int mlock_future_check(struct mm_struct *mm, return 0; } +static inline u64 file_mmap_size_max(struct file *file, struct inode *inode) +{ + if (S_ISREG(inode->i_mode)) + return MAX_LFS_FILESIZE; + + if (S_ISBLK(inode->i_mode)) + return MAX_LFS_FILESIZE; + + /* Special "we do even unsigned file positions" case */ + if (file->f_mode & FMODE_UNSIGNED_OFFSET) + return 0; + + /* Yes, random drivers might want more. But I'm tired of buggy drivers */ + return ULONG_MAX; +} + +static inline bool file_mmap_ok(struct file *file, struct inode *inode, + unsigned long pgoff, unsigned long len) +{ + u64 maxsize = file_mmap_size_max(file, inode); + + if (maxsize && len > maxsize) + return false; + maxsize -= len; + if (pgoff > maxsize >> PAGE_SHIFT) + return false; + return true; +} + /* * The caller must hold down_write(¤t->mm->mmap_sem). */ @@ -1409,6 +1438,9 @@ unsigned long do_mmap(struct file *file, unsigned long addr, struct inode *inode = file_inode(file); unsigned long flags_mask; + if (!file_mmap_ok(file, inode, pgoff, len)) + return -EOVERFLOW; + flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags; switch (flags & MAP_TYPE) { @@ -2796,7 +2828,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long ret = -EINVAL; struct file *file; - pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.txt.\n", + pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.rst.\n", current->comm, current->pid); if (prot) @@ -3024,6 +3056,32 @@ void exit_mmap(struct mm_struct *mm) /* mm's last user has gone, and its about to be pulled down */ mmu_notifier_release(mm); + if (unlikely(mm_is_oom_victim(mm))) { + /* + * Manually reap the mm to free as much memory as possible. + * Then, as the oom reaper does, set MMF_OOM_SKIP to disregard + * this mm from further consideration. Taking mm->mmap_sem for + * write after setting MMF_OOM_SKIP will guarantee that the oom + * reaper will not run on this mm again after mmap_sem is + * dropped. + * + * Nothing can be holding mm->mmap_sem here and the above call + * to mmu_notifier_release(mm) ensures mmu notifier callbacks in + * __oom_reap_task_mm() will not block. + * + * This needs to be done before calling munlock_vma_pages_all(), + * which clears VM_LOCKED, otherwise the oom reaper cannot + * reliably test it. + */ + mutex_lock(&oom_lock); + __oom_reap_task_mm(mm); + mutex_unlock(&oom_lock); + + set_bit(MMF_OOM_SKIP, &mm->flags); + down_write(&mm->mmap_sem); + up_write(&mm->mmap_sem); + } + if (mm->locked_vm) { vma = mm->mmap; while (vma) { @@ -3045,24 +3103,6 @@ void exit_mmap(struct mm_struct *mm) /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use -1 here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, vma, 0, -1); - - if (unlikely(mm_is_oom_victim(mm))) { - /* - * Wait for oom_reap_task() to stop working on this - * mm. Because MMF_OOM_SKIP is already set before - * calling down_read(), oom_reap_task() will not run - * on this "mm" post up_write(). - * - * mm_is_oom_victim() cannot be set from under us - * either because victim->mm is already set to NULL - * under task_lock before calling mmput and oom_mm is - * set not NULL by the OOM killer only if victim->mm - * is found not NULL while holding the task_lock. - */ - set_bit(MMF_OOM_SKIP, &mm->flags); - down_write(&mm->mmap_sem); - up_write(&mm->mmap_sem); - } free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, 0, -1); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index ff992fa8760a..8ba6cb88cf58 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -469,7 +469,6 @@ bool process_shares_mm(struct task_struct *p, struct mm_struct *mm) return false; } - #ifdef CONFIG_MMU /* * OOM Reaper kernel thread which tries to reap the memory used by the OOM @@ -480,16 +479,54 @@ 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_mm(struct task_struct *tsk, struct mm_struct *mm) +void __oom_reap_task_mm(struct mm_struct *mm) { - struct mmu_gather tlb; struct vm_area_struct *vma; + + /* + * Tell all users of get_user/copy_from_user etc... that the content + * is no longer stable. No barriers really needed because unmapping + * should imply barriers already and the reader would hit a page fault + * if it stumbled over a reaped memory. + */ + set_bit(MMF_UNSTABLE, &mm->flags); + + for (vma = mm->mmap ; vma; vma = vma->vm_next) { + if (!can_madv_dontneed_vma(vma)) + continue; + + /* + * Only anonymous pages have a good chance to be dropped + * without additional steps which we cannot afford as we + * are OOM already. + * + * We do not even care about fs backed pages because all + * which are reclaimable have already been reclaimed and + * we do not want to block exit_mmap by keeping mm ref + * count elevated without a good reason. + */ + if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) { + const unsigned long start = vma->vm_start; + const unsigned long end = vma->vm_end; + struct mmu_gather tlb; + + tlb_gather_mmu(&tlb, mm, start, end); + mmu_notifier_invalidate_range_start(mm, start, end); + unmap_page_range(&tlb, vma, start, end, NULL); + mmu_notifier_invalidate_range_end(mm, start, end); + tlb_finish_mmu(&tlb, start, end); + } + } +} + +static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) +{ 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_mm exit_mm + * oom_reap_task_mm exit_mm * mmget_not_zero * mmput * atomic_dec_and_test @@ -534,39 +571,8 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) trace_start_task_reaping(tsk->pid); - /* - * Tell all users of get_user/copy_from_user etc... that the content - * is no longer stable. No barriers really needed because unmapping - * should imply barriers already and the reader would hit a page fault - * if it stumbled over a reaped memory. - */ - set_bit(MMF_UNSTABLE, &mm->flags); - - for (vma = mm->mmap ; vma; vma = vma->vm_next) { - if (!can_madv_dontneed_vma(vma)) - continue; + __oom_reap_task_mm(mm); - /* - * Only anonymous pages have a good chance to be dropped - * without additional steps which we cannot afford as we - * are OOM already. - * - * We do not even care about fs backed pages because all - * which are reclaimable have already been reclaimed and - * we do not want to block exit_mmap by keeping mm ref - * count elevated without a good reason. - */ - if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) { - const unsigned long start = vma->vm_start; - const unsigned long end = vma->vm_end; - - tlb_gather_mmu(&tlb, mm, start, end); - mmu_notifier_invalidate_range_start(mm, start, end); - unmap_page_range(&tlb, vma, start, end, NULL); - mmu_notifier_invalidate_range_end(mm, start, end); - tlb_finish_mmu(&tlb, start, end); - } - } pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n", task_pid_nr(tsk), tsk->comm, K(get_mm_counter(mm, MM_ANONPAGES)), @@ -587,14 +593,13 @@ static void oom_reap_task(struct task_struct *tsk) struct mm_struct *mm = tsk->signal->oom_mm; /* Retry the down_read_trylock(mmap_sem) a few times */ - while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task_mm(tsk, mm)) + while (attempts++ < MAX_OOM_REAP_RETRIES && !oom_reap_task_mm(tsk, mm)) schedule_timeout_idle(HZ/10); if (attempts <= MAX_OOM_REAP_RETRIES || test_bit(MMF_OOM_SKIP, &mm->flags)) goto done; - pr_info("oom_reaper: unable to reap pid:%d (%s)\n", task_pid_nr(tsk), tsk->comm); debug_show_all_locks(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 905db9d7962f..22320ea27489 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1743,38 +1743,16 @@ void __init page_alloc_init_late(void) } #ifdef CONFIG_CMA -static void __init adjust_present_page_count(struct page *page, long count) -{ - struct zone *zone = page_zone(page); - - /* We don't need to hold a lock since it is boot-up process */ - zone->present_pages += count; -} - /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void __init init_cma_reserved_pageblock(struct page *page) { unsigned i = pageblock_nr_pages; - unsigned long pfn = page_to_pfn(page); struct page *p = page; - int nid = page_to_nid(page); - - /* - * ZONE_MOVABLE will steal present pages from other zones by - * changing page links so page_zone() is changed. Before that, - * we need to adjust previous zone's page count first. - */ - adjust_present_page_count(page, -pageblock_nr_pages); do { __ClearPageReserved(p); set_page_count(p, 0); - - /* Steal pages from other zones */ - set_page_links(p, ZONE_MOVABLE, nid, pfn); - } while (++p, ++pfn, --i); - - adjust_present_page_count(page, pageblock_nr_pages); + } while (++p, --i); set_pageblock_migratetype(page, MIGRATE_CMA); @@ -2889,7 +2867,7 @@ int __isolate_free_page(struct page *page, unsigned int order) * exists. */ watermark = min_wmark_pages(zone) + (1UL << order); - if (!zone_watermark_ok(zone, 0, watermark, 0, 0)) + if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA)) return 0; __mod_zone_freepage_state(zone, -(1UL << order), mt); @@ -3165,6 +3143,12 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, } +#ifdef CONFIG_CMA + /* If allocation can't use CMA areas don't use free CMA pages */ + if (!(alloc_flags & ALLOC_CMA)) + free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES); +#endif + /* * Check watermarks for an order-0 allocation request. If these * are not met, then a high-order request also cannot go ahead @@ -3191,8 +3175,10 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, } #ifdef CONFIG_CMA - if (!list_empty(&area->free_list[MIGRATE_CMA])) + if ((alloc_flags & ALLOC_CMA) && + !list_empty(&area->free_list[MIGRATE_CMA])) { return true; + } #endif if (alloc_harder && !list_empty(&area->free_list[MIGRATE_HIGHATOMIC])) @@ -3212,6 +3198,13 @@ 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 @@ -3220,7 +3213,7 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order, * 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 > mark + z->lowmem_reserve[classzone_idx]) + 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, @@ -3856,6 +3849,10 @@ gfp_to_alloc_flags(gfp_t gfp_mask) } else if (unlikely(rt_task(current)) && !in_interrupt()) alloc_flags |= ALLOC_HARDER; +#ifdef CONFIG_CMA + if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE) + alloc_flags |= ALLOC_CMA; +#endif return alloc_flags; } @@ -4322,6 +4319,9 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order, if (should_fail_alloc_page(gfp_mask, order)) return false; + if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE) + *alloc_flags |= ALLOC_CMA; + return true; } @@ -6204,7 +6204,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) { enum zone_type j; int nid = pgdat->node_id; - unsigned long node_end_pfn = 0; pgdat_resize_init(pgdat); #ifdef CONFIG_NUMA_BALANCING @@ -6232,13 +6231,9 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) struct zone *zone = pgdat->node_zones + j; unsigned long size, realsize, freesize, memmap_pages; unsigned long zone_start_pfn = zone->zone_start_pfn; - unsigned long movable_size = 0; size = zone->spanned_pages; realsize = freesize = zone->present_pages; - if (zone_end_pfn(zone) > node_end_pfn) - node_end_pfn = zone_end_pfn(zone); - /* * Adjust freesize so that it accounts for how much memory @@ -6287,30 +6282,12 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) zone_seqlock_init(zone); zone_pcp_init(zone); - /* - * The size of the CMA area is unknown now so we need to - * prepare the memory for the usemap at maximum. - */ - if (IS_ENABLED(CONFIG_CMA) && j == ZONE_MOVABLE && - pgdat->node_spanned_pages) { - movable_size = node_end_pfn - pgdat->node_start_pfn; - } - - if (!size && !movable_size) + if (!size) continue; set_pageblock_order(); - if (movable_size) { - zone->zone_start_pfn = pgdat->node_start_pfn; - zone->spanned_pages = movable_size; - setup_usemap(pgdat, zone, - pgdat->node_start_pfn, movable_size); - init_currently_empty_zone(zone, - pgdat->node_start_pfn, movable_size); - } else { - setup_usemap(pgdat, zone, zone_start_pfn, size); - init_currently_empty_zone(zone, zone_start_pfn, size); - } + setup_usemap(pgdat, zone, zone_start_pfn, size); + init_currently_empty_zone(zone, zone_start_pfn, size); memmap_init(size, nid, j, zone_start_pfn); } } @@ -7621,11 +7598,12 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, unsigned long pfn, iter, found; /* - * For avoiding noise data, lru_add_drain_all() should be called - * If ZONE_MOVABLE, the zone never contains unmovable pages + * TODO we could make this much more efficient by not checking every + * page in the range if we know all of them are in MOVABLE_ZONE and + * that the movable zone guarantees that pages are migratable but + * the later is not the case right now unfortunatelly. E.g. movablecore + * can still lead to having bootmem allocations in zone_movable. */ - if (zone_idx(zone) == ZONE_MOVABLE) - return false; /* * CMA allocations (alloc_contig_range) really need to mark isolate @@ -7646,7 +7624,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, page = pfn_to_page(check); if (PageReserved(page)) - return true; + goto unmovable; /* * Hugepages are not in LRU lists, but they're movable. @@ -7696,9 +7674,12 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * page at boot. */ if (found > count) - return true; + goto unmovable; } return false; +unmovable: + WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE); + return true; } bool is_pageblock_removable_nolock(struct page *page) @@ -7951,7 +7932,7 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages) } #endif -#if defined CONFIG_MEMORY_HOTPLUG || defined CONFIG_CMA +#ifdef CONFIG_MEMORY_HOTPLUG /* * The zone indicated has a new number of managed_pages; batch sizes and percpu * page high values need to be recalulated. diff --git a/mm/readahead.c b/mm/readahead.c index 539bbb6c1fad..e273f0de3376 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -140,23 +140,23 @@ out: } /* - * __do_page_cache_readahead() actually reads a chunk of disk. It allocates all - * the pages first, then submits them all for I/O. This avoids the very bad + * __do_page_cache_readahead() actually reads a chunk of disk. It allocates + * the pages first, then submits them for I/O. This avoids the very bad * behaviour which would occur if page allocations are causing VM writeback. * We really don't want to intermingle reads and writes like that. * * Returns the number of pages requested, or the maximum amount of I/O allowed. */ -int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, - pgoff_t offset, unsigned long nr_to_read, - unsigned long lookahead_size) +unsigned int __do_page_cache_readahead(struct address_space *mapping, + struct file *filp, pgoff_t offset, unsigned long nr_to_read, + unsigned long lookahead_size) { struct inode *inode = mapping->host; struct page *page; unsigned long end_index; /* The last page we want to read */ LIST_HEAD(page_pool); int page_idx; - int ret = 0; + unsigned int nr_pages = 0; loff_t isize = i_size_read(inode); gfp_t gfp_mask = readahead_gfp_mask(mapping); @@ -177,8 +177,18 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, rcu_read_lock(); page = radix_tree_lookup(&mapping->i_pages, page_offset); rcu_read_unlock(); - if (page && !radix_tree_exceptional_entry(page)) + if (page && !radix_tree_exceptional_entry(page)) { + /* + * Page already present? Kick off the current batch of + * contiguous pages before continuing with the next + * batch. + */ + if (nr_pages) + read_pages(mapping, filp, &page_pool, nr_pages, + gfp_mask); + nr_pages = 0; continue; + } page = __page_cache_alloc(gfp_mask); if (!page) @@ -187,7 +197,7 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, list_add(&page->lru, &page_pool); if (page_idx == nr_to_read - lookahead_size) SetPageReadahead(page); - ret++; + nr_pages++; } /* @@ -195,11 +205,11 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, * uptodate then the caller will launch readpage again, and * will then handle the error. */ - if (ret) - read_pages(mapping, filp, &page_pool, ret, gfp_mask); + if (nr_pages) + read_pages(mapping, filp, &page_pool, nr_pages, gfp_mask); BUG_ON(!list_empty(&page_pool)); out: - return ret; + return nr_pages; } /* @@ -223,16 +233,11 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp, max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages); nr_to_read = min(nr_to_read, max_pages); while (nr_to_read) { - int err; - unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE; if (this_chunk > nr_to_read) this_chunk = nr_to_read; - err = __do_page_cache_readahead(mapping, filp, - offset, this_chunk, 0); - if (err < 0) - return err; + __do_page_cache_readahead(mapping, filp, offset, this_chunk, 0); offset += this_chunk; nr_to_read -= this_chunk; diff --git a/mm/rmap.c b/mm/rmap.c index 8d5337fed37b..6db729dc4c50 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -942,7 +942,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, * downgrading page table protection not changing it to point * to a new page. * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ if (ret) (*cleaned)++; @@ -1599,7 +1599,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * point at new page while a device still is using this * page. * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ dec_mm_counter(mm, mm_counter_file(page)); } @@ -1609,7 +1609,7 @@ discard: * done above for all cases requiring it to happen under page * table lock before mmu_notifier_invalidate_range_end() * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ page_remove_rmap(subpage, PageHuge(page)); put_page(page); diff --git a/mm/sparse.c b/mm/sparse.c index 62eef264a7bd..73dc2fcc0eab 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -629,7 +629,7 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn) unsigned long pfn; for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { - unsigned long section_nr = pfn_to_section_nr(start_pfn); + unsigned long section_nr = pfn_to_section_nr(pfn); struct mem_section *ms; /* diff --git a/mm/swapfile.c b/mm/swapfile.c index cc2cf04d9018..78a015fcec3b 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3112,6 +3112,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) unsigned long *frontswap_map = NULL; struct page *page = NULL; struct inode *inode = NULL; + bool inced_nr_rotate_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; @@ -3215,8 +3216,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) cluster = per_cpu_ptr(p->percpu_cluster, cpu); cluster_set_null(&cluster->index); } - } else + } else { atomic_inc(&nr_rotate_swap); + inced_nr_rotate_swap = true; + } error = swap_cgroup_swapon(p->type, maxpages); if (error) @@ -3307,6 +3310,8 @@ bad_swap: vfree(swap_map); kvfree(cluster_info); kvfree(frontswap_map); + if (inced_nr_rotate_swap) + atomic_dec(&nr_rotate_swap); if (swap_file) { if (inode && S_ISREG(inode->i_mode)) { inode_unlock(inode); diff --git a/mm/util.c b/mm/util.c index 45fc3169e7b0..c2d0a7cdb189 100644 --- a/mm/util.c +++ b/mm/util.c @@ -621,7 +621,7 @@ EXPORT_SYMBOL_GPL(vm_memory_committed); * succeed and -ENOMEM implies there is not. * * We currently support three overcommit policies, which are set via the - * vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting + * vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting.rst * * Strict overcommit modes added 2002 Feb 26 by Alan Cox. * Additional code 2002 Jul 20 by Robert Love. diff --git a/mm/vmalloc.c b/mm/vmalloc.c index ebff729cc956..63a5f502da08 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2751,25 +2751,14 @@ static const struct seq_operations vmalloc_op = { .show = s_show, }; -static int vmalloc_open(struct inode *inode, struct file *file) +static int __init proc_vmalloc_init(void) { if (IS_ENABLED(CONFIG_NUMA)) - return seq_open_private(file, &vmalloc_op, - nr_node_ids * sizeof(unsigned int)); + proc_create_seq_private("vmallocinfo", S_IRUSR, NULL, + &vmalloc_op, + nr_node_ids * sizeof(unsigned int), NULL); else - return seq_open(file, &vmalloc_op); -} - -static const struct file_operations proc_vmalloc_operations = { - .open = vmalloc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_private, -}; - -static int __init proc_vmalloc_init(void) -{ - proc_create("vmallocinfo", S_IRUSR, NULL, &proc_vmalloc_operations); + proc_create_seq("vmallocinfo", S_IRUSR, NULL, &vmalloc_op); return 0; } module_init(proc_vmalloc_init); diff --git a/mm/vmscan.c b/mm/vmscan.c index 9b697323a88c..9270a4370d54 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1418,7 +1418,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode) return ret; mapping = page_mapping(page); - migrate_dirty = mapping && mapping->a_ops->migratepage; + migrate_dirty = !mapping || mapping->a_ops->migratepage; unlock_page(page); if (!migrate_dirty) return ret; diff --git a/mm/vmstat.c b/mm/vmstat.c index 536332e988b8..75eda9c2b260 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1161,7 +1161,7 @@ const char * const vmstat_text[] = { "nr_vmscan_immediate_reclaim", "nr_dirtied", "nr_written", - "nr_indirectly_reclaimable", + "", /* nr_indirectly_reclaimable */ /* enum writeback_stat_item counters */ "nr_dirty_threshold", @@ -1516,18 +1516,6 @@ static const struct seq_operations fragmentation_op = { .show = frag_show, }; -static int fragmentation_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &fragmentation_op); -} - -static const struct file_operations buddyinfo_file_operations = { - .open = fragmentation_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - static const struct seq_operations pagetypeinfo_op = { .start = frag_start, .next = frag_next, @@ -1535,18 +1523,6 @@ static const struct seq_operations pagetypeinfo_op = { .show = pagetypeinfo_show, }; -static int pagetypeinfo_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &pagetypeinfo_op); -} - -static const struct file_operations pagetypeinfo_file_operations = { - .open = pagetypeinfo_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - static bool is_zone_first_populated(pg_data_t *pgdat, struct zone *zone) { int zid; @@ -1663,18 +1639,6 @@ static const struct seq_operations zoneinfo_op = { .show = zoneinfo_show, }; -static int zoneinfo_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &zoneinfo_op); -} - -static const struct file_operations zoneinfo_file_operations = { - .open = zoneinfo_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - enum writeback_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, @@ -1740,6 +1704,10 @@ static int vmstat_show(struct seq_file *m, void *arg) unsigned long *l = arg; unsigned long off = l - (unsigned long *)m->private; + /* Skip hidden vmstat items. */ + if (*vmstat_text[off] == '\0') + return 0; + seq_puts(m, vmstat_text[off]); seq_put_decimal_ull(m, " ", *l); seq_putc(m, '\n'); @@ -1758,18 +1726,6 @@ static const struct seq_operations vmstat_op = { .stop = vmstat_stop, .show = vmstat_show, }; - -static int vmstat_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &vmstat_op); -} - -static const struct file_operations vmstat_file_operations = { - .open = vmstat_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SMP @@ -2016,10 +1972,10 @@ void __init init_mm_internals(void) start_shepherd_timer(); #endif #ifdef CONFIG_PROC_FS - proc_create("buddyinfo", 0444, NULL, &buddyinfo_file_operations); - proc_create("pagetypeinfo", 0444, NULL, &pagetypeinfo_file_operations); - proc_create("vmstat", 0444, NULL, &vmstat_file_operations); - proc_create("zoneinfo", 0444, NULL, &zoneinfo_file_operations); + proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op); + proc_create_seq("pagetypeinfo", 0444, NULL, &pagetypeinfo_op); + proc_create_seq("vmstat", 0444, NULL, &vmstat_op); + proc_create_seq("zoneinfo", 0444, NULL, &zoneinfo_op); #endif } diff --git a/mm/z3fold.c b/mm/z3fold.c index c0bca6153b95..4b366d181f35 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -144,7 +144,8 @@ enum z3fold_page_flags { PAGE_HEADLESS = 0, MIDDLE_CHUNK_MAPPED, NEEDS_COMPACTING, - PAGE_STALE + PAGE_STALE, + UNDER_RECLAIM }; /***************** @@ -173,6 +174,7 @@ static struct z3fold_header *init_z3fold_page(struct page *page, clear_bit(MIDDLE_CHUNK_MAPPED, &page->private); clear_bit(NEEDS_COMPACTING, &page->private); clear_bit(PAGE_STALE, &page->private); + clear_bit(UNDER_RECLAIM, &page->private); spin_lock_init(&zhdr->page_lock); kref_init(&zhdr->refcount); @@ -756,6 +758,10 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) atomic64_dec(&pool->pages_nr); return; } + if (test_bit(UNDER_RECLAIM, &page->private)) { + z3fold_page_unlock(zhdr); + return; + } if (test_and_set_bit(NEEDS_COMPACTING, &page->private)) { z3fold_page_unlock(zhdr); return; @@ -840,6 +846,8 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) kref_get(&zhdr->refcount); list_del_init(&zhdr->buddy); zhdr->cpu = -1; + set_bit(UNDER_RECLAIM, &page->private); + break; } list_del_init(&page->lru); @@ -887,25 +895,35 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) goto next; } next: - spin_lock(&pool->lock); if (test_bit(PAGE_HEADLESS, &page->private)) { if (ret == 0) { - spin_unlock(&pool->lock); free_z3fold_page(page); return 0; } - } else if (kref_put(&zhdr->refcount, release_z3fold_page)) { - atomic64_dec(&pool->pages_nr); + spin_lock(&pool->lock); + list_add(&page->lru, &pool->lru); + spin_unlock(&pool->lock); + } else { + z3fold_page_lock(zhdr); + clear_bit(UNDER_RECLAIM, &page->private); + if (kref_put(&zhdr->refcount, + release_z3fold_page_locked)) { + atomic64_dec(&pool->pages_nr); + return 0; + } + /* + * if we are here, the page is still not completely + * free. Take the global pool lock then to be able + * to add it back to the lru list + */ + spin_lock(&pool->lock); + list_add(&page->lru, &pool->lru); spin_unlock(&pool->lock); - return 0; + z3fold_page_unlock(zhdr); } - /* - * Add to the beginning of LRU. - * Pool lock has to be kept here to ensure the page has - * not already been released - */ - list_add(&page->lru, &pool->lru); + /* We started off locked to we need to lock the pool back */ + spin_lock(&pool->lock); } spin_unlock(&pool->lock); return -EAGAIN; |