diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-04-16 01:39:15 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-04-16 01:39:15 +0200 |
commit | eea3a00264cf243a28e4331566ce67b86059339d (patch) | |
tree | 487f16389e0dfa32e9caa7604d1274a7dcda8f04 /mm | |
parent | Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/cool... (diff) | |
parent | parisc: remove use of seq_printf return value (diff) | |
download | linux-eea3a00264cf243a28e4331566ce67b86059339d.tar.xz linux-eea3a00264cf243a28e4331566ce67b86059339d.zip |
Merge branch 'akpm' (patches from Andrew)
Merge second patchbomb from Andrew Morton:
- the rest of MM
- various misc bits
- add ability to run /sbin/reboot at reboot time
- printk/vsprintf changes
- fiddle with seq_printf() return value
* akpm: (114 commits)
parisc: remove use of seq_printf return value
lru_cache: remove use of seq_printf return value
tracing: remove use of seq_printf return value
cgroup: remove use of seq_printf return value
proc: remove use of seq_printf return value
s390: remove use of seq_printf return value
cris fasttimer: remove use of seq_printf return value
cris: remove use of seq_printf return value
openrisc: remove use of seq_printf return value
ARM: plat-pxa: remove use of seq_printf return value
nios2: cpuinfo: remove use of seq_printf return value
microblaze: mb: remove use of seq_printf return value
ipc: remove use of seq_printf return value
rtc: remove use of seq_printf return value
power: wakeup: remove use of seq_printf return value
x86: mtrr: if: remove use of seq_printf return value
linux/bitmap.h: improve BITMAP_{LAST,FIRST}_WORD_MASK
MAINTAINERS: CREDITS: remove Stefano Brivio from B43
.mailmap: add Ricardo Ribalda
CREDITS: add Ricardo Ribalda Delgado
...
Diffstat (limited to 'mm')
-rw-r--r-- | mm/cma.c | 5 | ||||
-rw-r--r-- | mm/cma_debug.c | 41 | ||||
-rw-r--r-- | mm/compaction.c | 60 | ||||
-rw-r--r-- | mm/gup.c | 4 | ||||
-rw-r--r-- | mm/huge_memory.c | 86 | ||||
-rw-r--r-- | mm/hugetlb.c | 234 | ||||
-rw-r--r-- | mm/internal.h | 4 | ||||
-rw-r--r-- | mm/kasan/kasan.c | 13 | ||||
-rw-r--r-- | mm/ksm.c | 10 | ||||
-rw-r--r-- | mm/memblock.c | 18 | ||||
-rw-r--r-- | mm/memcontrol.c | 47 | ||||
-rw-r--r-- | mm/memory-failure.c | 122 | ||||
-rw-r--r-- | mm/memory.c | 56 | ||||
-rw-r--r-- | mm/memory_hotplug.c | 2 | ||||
-rw-r--r-- | mm/mempool.c | 117 | ||||
-rw-r--r-- | mm/migrate.c | 3 | ||||
-rw-r--r-- | mm/mmap.c | 21 | ||||
-rw-r--r-- | mm/mremap.c | 25 | ||||
-rw-r--r-- | mm/oom_kill.c | 2 | ||||
-rw-r--r-- | mm/page-writeback.c | 3 | ||||
-rw-r--r-- | mm/page_alloc.c | 6 | ||||
-rw-r--r-- | mm/rmap.c | 6 | ||||
-rw-r--r-- | mm/slub.c | 4 | ||||
-rw-r--r-- | mm/swap.c | 34 | ||||
-rw-r--r-- | mm/swap_state.c | 2 | ||||
-rw-r--r-- | mm/swapfile.c | 2 | ||||
-rw-r--r-- | mm/truncate.c | 2 | ||||
-rw-r--r-- | mm/util.c | 41 | ||||
-rw-r--r-- | mm/vmalloc.c | 95 | ||||
-rw-r--r-- | mm/zsmalloc.c | 971 |
30 files changed, 1453 insertions, 583 deletions
@@ -23,6 +23,7 @@ # define DEBUG #endif #endif +#define CREATE_TRACE_POINTS #include <linux/memblock.h> #include <linux/err.h> @@ -34,6 +35,7 @@ #include <linux/cma.h> #include <linux/highmem.h> #include <linux/io.h> +#include <trace/events/cma.h> #include "cma.h" @@ -414,6 +416,8 @@ struct page *cma_alloc(struct cma *cma, unsigned int count, unsigned int align) start = bitmap_no + mask + 1; } + trace_cma_alloc(page ? pfn : -1UL, page, count, align); + pr_debug("%s(): returned %p\n", __func__, page); return page; } @@ -446,6 +450,7 @@ bool cma_release(struct cma *cma, const struct page *pages, unsigned int count) free_contig_range(pfn, count); cma_clear_bitmap(cma, pfn, count); + trace_cma_release(pfn, pages, count); return true; } diff --git a/mm/cma_debug.c b/mm/cma_debug.c index 0b377536ccde..7621ee34daa0 100644 --- a/mm/cma_debug.c +++ b/mm/cma_debug.c @@ -30,9 +30,44 @@ static int cma_debugfs_get(void *data, u64 *val) return 0; } - DEFINE_SIMPLE_ATTRIBUTE(cma_debugfs_fops, cma_debugfs_get, NULL, "%llu\n"); +static int cma_used_get(void *data, u64 *val) +{ + struct cma *cma = data; + unsigned long used; + + mutex_lock(&cma->lock); + /* pages counter is smaller than sizeof(int) */ + used = bitmap_weight(cma->bitmap, (int)cma->count); + mutex_unlock(&cma->lock); + *val = (u64)used << cma->order_per_bit; + + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(cma_used_fops, cma_used_get, NULL, "%llu\n"); + +static int cma_maxchunk_get(void *data, u64 *val) +{ + struct cma *cma = data; + unsigned long maxchunk = 0; + unsigned long start, end = 0; + + mutex_lock(&cma->lock); + for (;;) { + start = find_next_zero_bit(cma->bitmap, cma->count, end); + if (start >= cma->count) + break; + end = find_next_bit(cma->bitmap, cma->count, start); + maxchunk = max(end - start, maxchunk); + } + mutex_unlock(&cma->lock); + *val = (u64)maxchunk << cma->order_per_bit; + + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(cma_maxchunk_fops, cma_maxchunk_get, NULL, "%llu\n"); + static void cma_add_to_cma_mem_list(struct cma *cma, struct cma_mem *mem) { spin_lock(&cma->mem_head_lock); @@ -91,7 +126,6 @@ static int cma_free_write(void *data, u64 val) return cma_free_mem(cma, pages); } - DEFINE_SIMPLE_ATTRIBUTE(cma_free_fops, NULL, cma_free_write, "%llu\n"); static int cma_alloc_mem(struct cma *cma, int count) @@ -124,7 +158,6 @@ static int cma_alloc_write(void *data, u64 val) return cma_alloc_mem(cma, pages); } - DEFINE_SIMPLE_ATTRIBUTE(cma_alloc_fops, NULL, cma_alloc_write, "%llu\n"); static void cma_debugfs_add_one(struct cma *cma, int idx) @@ -149,6 +182,8 @@ static void cma_debugfs_add_one(struct cma *cma, int idx) &cma->count, &cma_debugfs_fops); debugfs_create_file("order_per_bit", S_IRUGO, tmp, &cma->order_per_bit, &cma_debugfs_fops); + debugfs_create_file("used", S_IRUGO, tmp, cma, &cma_used_fops); + debugfs_create_file("maxchunk", S_IRUGO, tmp, cma, &cma_maxchunk_fops); u32s = DIV_ROUND_UP(cma_bitmap_maxno(cma), BITS_PER_BYTE * sizeof(u32)); debugfs_create_u32_array("bitmap", S_IRUGO, tmp, (u32*)cma->bitmap, u32s); diff --git a/mm/compaction.c b/mm/compaction.c index a18201a8124e..018f08da99a2 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -391,28 +391,6 @@ static inline bool compact_should_abort(struct compact_control *cc) return false; } -/* Returns true if the page is within a block suitable for migration to */ -static bool suitable_migration_target(struct page *page) -{ - /* If the page is a large free page, then disallow migration */ - if (PageBuddy(page)) { - /* - * We are checking page_order without zone->lock taken. But - * the only small danger is that we skip a potentially suitable - * pageblock, so it's not worth to check order for valid range. - */ - if (page_order_unsafe(page) >= pageblock_order) - return false; - } - - /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ - if (migrate_async_suitable(get_pageblock_migratetype(page))) - return true; - - /* Otherwise skip the block */ - return false; -} - /* * Isolate free pages onto a private freelist. If @strict is true, will abort * returning 0 on any invalid PFNs or non-free pages inside of the pageblock @@ -896,6 +874,29 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, #endif /* CONFIG_COMPACTION || CONFIG_CMA */ #ifdef CONFIG_COMPACTION + +/* Returns true if the page is within a block suitable for migration to */ +static bool suitable_migration_target(struct page *page) +{ + /* If the page is a large free page, then disallow migration */ + if (PageBuddy(page)) { + /* + * We are checking page_order without zone->lock taken. But + * the only small danger is that we skip a potentially suitable + * pageblock, so it's not worth to check order for valid range. + */ + if (page_order_unsafe(page) >= pageblock_order) + return false; + } + + /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ + if (migrate_async_suitable(get_pageblock_migratetype(page))) + return true; + + /* Otherwise skip the block */ + return false; +} + /* * Based on information in the current compact_control, find blocks * suitable for isolating free pages from and then isolate them. @@ -1047,6 +1048,12 @@ typedef enum { } isolate_migrate_t; /* + * Allow userspace to control policy on scanning the unevictable LRU for + * compactable pages. + */ +int sysctl_compact_unevictable_allowed __read_mostly = 1; + +/* * Isolate all pages that can be migrated from the first suitable block, * starting at the block pointed to by the migrate scanner pfn within * compact_control. @@ -1057,6 +1064,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, unsigned long low_pfn, end_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); /* @@ -1598,6 +1606,14 @@ static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) INIT_LIST_HEAD(&cc->freepages); INIT_LIST_HEAD(&cc->migratepages); + /* + * When called via /proc/sys/vm/compact_memory + * this makes sure we compact the whole zone regardless of + * cached scanner positions. + */ + if (cc->order == -1) + __reset_isolation_suitable(zone); + if (cc->order == -1 || !compaction_deferred(zone, cc->order)) compact_zone(zone, cc); @@ -1019,7 +1019,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, * * for an example see gup_get_pte in arch/x86/mm/gup.c */ - pte_t pte = ACCESS_ONCE(*ptep); + pte_t pte = READ_ONCE(*ptep); struct page *page; /* @@ -1309,7 +1309,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, local_irq_save(flags); pgdp = pgd_offset(mm, addr); do { - pgd_t pgd = ACCESS_ONCE(*pgdp); + pgd_t pgd = READ_ONCE(*pgdp); next = pgd_addr_end(addr, end); if (pgd_none(pgd)) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 3afb5cbe1312..078832cf3636 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -67,6 +67,7 @@ static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1; 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); @@ -109,9 +110,6 @@ static int set_recommended_min_free_kbytes(void) int nr_zones = 0; unsigned long recommended_min; - if (!khugepaged_enabled()) - return 0; - for_each_populated_zone(zone) nr_zones++; @@ -143,9 +141,8 @@ static int set_recommended_min_free_kbytes(void) setup_per_zone_wmarks(); return 0; } -late_initcall(set_recommended_min_free_kbytes); -static int start_khugepaged(void) +static int start_stop_khugepaged(void) { int err = 0; if (khugepaged_enabled()) { @@ -156,6 +153,7 @@ static int start_khugepaged(void) 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)) @@ -166,7 +164,7 @@ static int start_khugepaged(void) kthread_stop(khugepaged_thread); khugepaged_thread = NULL; } - +fail: return err; } @@ -183,7 +181,7 @@ static struct page *get_huge_zero_page(void) struct page *zero_page; retry: if (likely(atomic_inc_not_zero(&huge_zero_refcount))) - return ACCESS_ONCE(huge_zero_page); + return READ_ONCE(huge_zero_page); zero_page = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE, HPAGE_PMD_ORDER); @@ -202,7 +200,7 @@ retry: /* We take additional reference here. It will be put back by shrinker */ atomic_set(&huge_zero_refcount, 2); preempt_enable(); - return ACCESS_ONCE(huge_zero_page); + return READ_ONCE(huge_zero_page); } static void put_huge_zero_page(void) @@ -300,7 +298,7 @@ static ssize_t enabled_store(struct kobject *kobj, int err; mutex_lock(&khugepaged_mutex); - err = start_khugepaged(); + err = start_stop_khugepaged(); mutex_unlock(&khugepaged_mutex); if (err) @@ -634,27 +632,38 @@ static int __init hugepage_init(void) err = hugepage_init_sysfs(&hugepage_kobj); if (err) - return err; + goto err_sysfs; err = khugepaged_slab_init(); if (err) - goto out; + goto err_slab; - register_shrinker(&huge_zero_page_shrinker); + err = register_shrinker(&huge_zero_page_shrinker); + if (err) + goto err_hzp_shrinker; /* * By default disable transparent hugepages on smaller systems, * where the extra memory used could hurt more than TLB overhead * is likely to save. The admin can still enable it through /sys. */ - if (totalram_pages < (512 << (20 - PAGE_SHIFT))) + if (totalram_pages < (512 << (20 - PAGE_SHIFT))) { transparent_hugepage_flags = 0; + return 0; + } - start_khugepaged(); + err = start_stop_khugepaged(); + if (err) + goto err_khugepaged; return 0; -out: +err_khugepaged: + unregister_shrinker(&huge_zero_page_shrinker); +err_hzp_shrinker: + khugepaged_slab_exit(); +err_slab: hugepage_exit_sysfs(hugepage_kobj); +err_sysfs: return err; } subsys_initcall(hugepage_init); @@ -708,7 +717,7 @@ static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot) static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, - struct page *page) + struct page *page, gfp_t gfp) { struct mem_cgroup *memcg; pgtable_t pgtable; @@ -716,7 +725,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_try_charge(page, mm, GFP_TRANSHUGE, &memcg)) + if (mem_cgroup_try_charge(page, mm, gfp, &memcg)) return VM_FAULT_OOM; pgtable = pte_alloc_one(mm, haddr); @@ -822,7 +831,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; } - if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page))) { + if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page, gfp))) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1080,6 +1089,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr; unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ + gfp_t huge_gfp; /* for allocation and charge */ ptl = pmd_lockptr(mm, pmd); VM_BUG_ON_VMA(!vma->anon_vma, vma); @@ -1106,10 +1116,8 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, alloc: if (transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) { - gfp_t gfp; - - gfp = alloc_hugepage_gfpmask(transparent_hugepage_defrag(vma), 0); - new_page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); + huge_gfp = alloc_hugepage_gfpmask(transparent_hugepage_defrag(vma), 0); + new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER); } else new_page = NULL; @@ -1130,8 +1138,7 @@ alloc: goto out; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, - GFP_TRANSHUGE, &memcg))) { + if (unlikely(mem_cgroup_try_charge(new_page, mm, huge_gfp, &memcg))) { put_page(new_page); if (page) { split_huge_page(page); @@ -1976,6 +1983,11 @@ static int __init khugepaged_slab_init(void) 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 */ @@ -2323,19 +2335,13 @@ static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) return true; } -static struct page -*khugepaged_alloc_page(struct page **hpage, struct mm_struct *mm, +static struct page * +khugepaged_alloc_page(struct page **hpage, gfp_t gfp, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int node) { - gfp_t flags; - VM_BUG_ON_PAGE(*hpage, *hpage); - /* Only allocate from the target node */ - flags = alloc_hugepage_gfpmask(khugepaged_defrag(), __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 @@ -2344,7 +2350,7 @@ static struct page */ up_read(&mm->mmap_sem); - *hpage = alloc_pages_exact_node(node, flags, HPAGE_PMD_ORDER); + *hpage = alloc_pages_exact_node(node, gfp, HPAGE_PMD_ORDER); if (unlikely(!*hpage)) { count_vm_event(THP_COLLAPSE_ALLOC_FAILED); *hpage = ERR_PTR(-ENOMEM); @@ -2397,13 +2403,14 @@ static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) return true; } -static struct page -*khugepaged_alloc_page(struct page **hpage, struct mm_struct *mm, +static struct page * +khugepaged_alloc_page(struct page **hpage, gfp_t gfp, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int node) { up_read(&mm->mmap_sem); VM_BUG_ON(!*hpage); + return *hpage; } #endif @@ -2438,16 +2445,21 @@ static void collapse_huge_page(struct mm_struct *mm, 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_gfpmask(khugepaged_defrag(), __GFP_OTHER_NODE) | + __GFP_THISNODE; + /* release the mmap_sem read lock. */ - new_page = khugepaged_alloc_page(hpage, mm, vma, address, node); + new_page = khugepaged_alloc_page(hpage, gfp, mm, vma, address, node); if (!new_page) return; if (unlikely(mem_cgroup_try_charge(new_page, mm, - GFP_TRANSHUGE, &memcg))) + gfp, &memcg))) return; /* diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 8874c8ad55aa..271e4432734c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -61,6 +61,9 @@ DEFINE_SPINLOCK(hugetlb_lock); static int num_fault_mutexes; static struct mutex *htlb_fault_mutex_table ____cacheline_aligned_in_smp; +/* Forward declaration */ +static int hugetlb_acct_memory(struct hstate *h, long delta); + static inline void unlock_or_release_subpool(struct hugepage_subpool *spool) { bool free = (spool->count == 0) && (spool->used_hpages == 0); @@ -68,23 +71,36 @@ static inline void unlock_or_release_subpool(struct hugepage_subpool *spool) spin_unlock(&spool->lock); /* If no pages are used, and no other handles to the subpool - * remain, free the subpool the subpool remain */ - if (free) + * remain, give up any reservations mased on minimum size and + * free the subpool */ + if (free) { + if (spool->min_hpages != -1) + hugetlb_acct_memory(spool->hstate, + -spool->min_hpages); kfree(spool); + } } -struct hugepage_subpool *hugepage_new_subpool(long nr_blocks) +struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, + long min_hpages) { struct hugepage_subpool *spool; - spool = kmalloc(sizeof(*spool), GFP_KERNEL); + spool = kzalloc(sizeof(*spool), GFP_KERNEL); if (!spool) return NULL; spin_lock_init(&spool->lock); spool->count = 1; - spool->max_hpages = nr_blocks; - spool->used_hpages = 0; + spool->max_hpages = max_hpages; + spool->hstate = h; + spool->min_hpages = min_hpages; + + if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) { + kfree(spool); + return NULL; + } + spool->rsv_hpages = min_hpages; return spool; } @@ -97,36 +113,89 @@ void hugepage_put_subpool(struct hugepage_subpool *spool) unlock_or_release_subpool(spool); } -static int hugepage_subpool_get_pages(struct hugepage_subpool *spool, +/* + * Subpool accounting for allocating and reserving pages. + * Return -ENOMEM if there are not enough resources to satisfy the + * the request. Otherwise, return the number of pages by which the + * global pools must be adjusted (upward). The returned value may + * only be different than the passed value (delta) in the case where + * a subpool minimum size must be manitained. + */ +static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, long delta) { - int ret = 0; + long ret = delta; if (!spool) - return 0; + return ret; spin_lock(&spool->lock); - if ((spool->used_hpages + delta) <= spool->max_hpages) { - spool->used_hpages += delta; - } else { - ret = -ENOMEM; + + if (spool->max_hpages != -1) { /* maximum size accounting */ + if ((spool->used_hpages + delta) <= spool->max_hpages) + spool->used_hpages += delta; + else { + ret = -ENOMEM; + goto unlock_ret; + } + } + + if (spool->min_hpages != -1) { /* minimum size accounting */ + if (delta > spool->rsv_hpages) { + /* + * Asking for more reserves than those already taken on + * behalf of subpool. Return difference. + */ + ret = delta - spool->rsv_hpages; + spool->rsv_hpages = 0; + } else { + ret = 0; /* reserves already accounted for */ + spool->rsv_hpages -= delta; + } } - spin_unlock(&spool->lock); +unlock_ret: + spin_unlock(&spool->lock); return ret; } -static void hugepage_subpool_put_pages(struct hugepage_subpool *spool, +/* + * Subpool accounting for freeing and unreserving pages. + * Return the number of global page reservations that must be dropped. + * The return value may only be different than the passed value (delta) + * in the case where a subpool minimum size must be maintained. + */ +static long hugepage_subpool_put_pages(struct hugepage_subpool *spool, long delta) { + long ret = delta; + if (!spool) - return; + return delta; spin_lock(&spool->lock); - spool->used_hpages -= delta; - /* If hugetlbfs_put_super couldn't free spool due to - * an outstanding quota reference, free it now. */ + + if (spool->max_hpages != -1) /* maximum size accounting */ + spool->used_hpages -= delta; + + if (spool->min_hpages != -1) { /* minimum size accounting */ + if (spool->rsv_hpages + delta <= spool->min_hpages) + ret = 0; + else + ret = spool->rsv_hpages + delta - spool->min_hpages; + + spool->rsv_hpages += delta; + if (spool->rsv_hpages > spool->min_hpages) + spool->rsv_hpages = spool->min_hpages; + } + + /* + * If hugetlbfs_put_super couldn't free spool due to an outstanding + * quota reference, free it now. + */ unlock_or_release_subpool(spool); + + return ret; } static inline struct hugepage_subpool *subpool_inode(struct inode *inode) @@ -855,6 +924,31 @@ struct hstate *size_to_hstate(unsigned long size) return NULL; } +/* + * Test to determine whether the hugepage is "active/in-use" (i.e. being linked + * to hstate->hugepage_activelist.) + * + * This function can be called for tail pages, but never returns true for them. + */ +bool page_huge_active(struct page *page) +{ + VM_BUG_ON_PAGE(!PageHuge(page), page); + return PageHead(page) && PagePrivate(&page[1]); +} + +/* never called for tail page */ +static void set_page_huge_active(struct page *page) +{ + VM_BUG_ON_PAGE(!PageHeadHuge(page), page); + SetPagePrivate(&page[1]); +} + +static void clear_page_huge_active(struct page *page) +{ + VM_BUG_ON_PAGE(!PageHeadHuge(page), page); + ClearPagePrivate(&page[1]); +} + void free_huge_page(struct page *page) { /* @@ -874,7 +968,16 @@ void free_huge_page(struct page *page) restore_reserve = PagePrivate(page); ClearPagePrivate(page); + /* + * A return code of zero implies that the subpool will be under its + * minimum size if the reservation is not restored after page is free. + * Therefore, force restore_reserve operation. + */ + if (hugepage_subpool_put_pages(spool, 1) == 0) + restore_reserve = true; + spin_lock(&hugetlb_lock); + clear_page_huge_active(page); hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h), page); if (restore_reserve) @@ -891,7 +994,6 @@ void free_huge_page(struct page *page) enqueue_huge_page(h, page); } spin_unlock(&hugetlb_lock); - hugepage_subpool_put_pages(spool, 1); } static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) @@ -1386,7 +1488,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, if (chg < 0) return ERR_PTR(-ENOMEM); if (chg || avoid_reserve) - if (hugepage_subpool_get_pages(spool, 1)) + if (hugepage_subpool_get_pages(spool, 1) < 0) return ERR_PTR(-ENOSPC); ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); @@ -2454,6 +2556,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma) struct resv_map *resv = vma_resv_map(vma); struct hugepage_subpool *spool = subpool_vma(vma); unsigned long reserve, start, end; + long gbl_reserve; if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return; @@ -2466,8 +2569,12 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma) kref_put(&resv->refs, resv_map_release); if (reserve) { - hugetlb_acct_memory(h, -reserve); - hugepage_subpool_put_pages(spool, reserve); + /* + * Decrement reserve counts. The global reserve count may be + * adjusted if the subpool has a minimum size. + */ + gbl_reserve = hugepage_subpool_put_pages(spool, reserve); + hugetlb_acct_memory(h, -gbl_reserve); } } @@ -2891,6 +2998,7 @@ retry_avoidcopy: copy_user_huge_page(new_page, old_page, address, vma, pages_per_huge_page(h)); __SetPageUptodate(new_page); + set_page_huge_active(new_page); mmun_start = address & huge_page_mask(h); mmun_end = mmun_start + huge_page_size(h); @@ -3003,6 +3111,7 @@ retry: } clear_huge_page(page, address, pages_per_huge_page(h)); __SetPageUptodate(page); + set_page_huge_active(page); if (vma->vm_flags & VM_MAYSHARE) { int err; @@ -3447,6 +3556,7 @@ int hugetlb_reserve_pages(struct inode *inode, struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; + long gbl_reserve; /* * Only apply hugepage reservation if asked. At fault time, an @@ -3483,8 +3593,13 @@ int hugetlb_reserve_pages(struct inode *inode, goto out_err; } - /* There must be enough pages in the subpool for the mapping */ - if (hugepage_subpool_get_pages(spool, chg)) { + /* + * There must be enough pages in the subpool for the mapping. If + * the subpool has a minimum size, there may be some global + * reservations already in place (gbl_reserve). + */ + gbl_reserve = hugepage_subpool_get_pages(spool, chg); + if (gbl_reserve < 0) { ret = -ENOSPC; goto out_err; } @@ -3493,9 +3608,10 @@ int hugetlb_reserve_pages(struct inode *inode, * Check enough hugepages are available for the reservation. * Hand the pages back to the subpool if there are not */ - ret = hugetlb_acct_memory(h, chg); + ret = hugetlb_acct_memory(h, gbl_reserve); if (ret < 0) { - hugepage_subpool_put_pages(spool, chg); + /* put back original number of pages, chg */ + (void)hugepage_subpool_put_pages(spool, chg); goto out_err; } @@ -3525,6 +3641,7 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) struct resv_map *resv_map = inode_resv_map(inode); long chg = 0; struct hugepage_subpool *spool = subpool_inode(inode); + long gbl_reserve; if (resv_map) chg = region_truncate(resv_map, offset); @@ -3532,8 +3649,12 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); - hugepage_subpool_put_pages(spool, (chg - freed)); - hugetlb_acct_memory(h, -(chg - freed)); + /* + * If the subpool has a minimum size, the number of global + * reservations to be released may be adjusted. + */ + gbl_reserve = hugepage_subpool_put_pages(spool, (chg - freed)); + hugetlb_acct_memory(h, -gbl_reserve); } #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE @@ -3775,20 +3896,6 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address, #ifdef CONFIG_MEMORY_FAILURE -/* Should be called in hugetlb_lock */ -static int is_hugepage_on_freelist(struct page *hpage) -{ - struct page *page; - struct page *tmp; - struct hstate *h = page_hstate(hpage); - int nid = page_to_nid(hpage); - - list_for_each_entry_safe(page, tmp, &h->hugepage_freelists[nid], lru) - if (page == hpage) - return 1; - return 0; -} - /* * This function is called from memory failure code. * Assume the caller holds page lock of the head page. @@ -3800,7 +3907,11 @@ int dequeue_hwpoisoned_huge_page(struct page *hpage) int ret = -EBUSY; spin_lock(&hugetlb_lock); - if (is_hugepage_on_freelist(hpage)) { + /* + * Just checking !page_huge_active is not enough, because that could be + * an isolated/hwpoisoned hugepage (which have >0 refcount). + */ + if (!page_huge_active(hpage) && !page_count(hpage)) { /* * Hwpoisoned hugepage isn't linked to activelist or freelist, * but dangling hpage->lru can trigger list-debug warnings @@ -3820,42 +3931,27 @@ int dequeue_hwpoisoned_huge_page(struct page *hpage) bool isolate_huge_page(struct page *page, struct list_head *list) { + bool ret = true; + VM_BUG_ON_PAGE(!PageHead(page), page); - if (!get_page_unless_zero(page)) - return false; spin_lock(&hugetlb_lock); + if (!page_huge_active(page) || !get_page_unless_zero(page)) { + ret = false; + goto unlock; + } + clear_page_huge_active(page); list_move_tail(&page->lru, list); +unlock: spin_unlock(&hugetlb_lock); - return true; + return ret; } void putback_active_hugepage(struct page *page) { VM_BUG_ON_PAGE(!PageHead(page), page); spin_lock(&hugetlb_lock); + set_page_huge_active(page); list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist); spin_unlock(&hugetlb_lock); put_page(page); } - -bool is_hugepage_active(struct page *page) -{ - VM_BUG_ON_PAGE(!PageHuge(page), page); - /* - * This function can be called for a tail page because the caller, - * scan_movable_pages, scans through a given pfn-range which typically - * covers one memory block. In systems using gigantic hugepage (1GB - * for x86_64,) a hugepage is larger than a memory block, and we don't - * support migrating such large hugepages for now, so return false - * when called for tail pages. - */ - if (PageTail(page)) - return false; - /* - * Refcount of a hwpoisoned hugepages is 1, but they are not active, - * so we should return false for them. - */ - if (unlikely(PageHWPoison(page))) - return false; - return page_count(page) > 0; -} diff --git a/mm/internal.h b/mm/internal.h index edaab69a9c35..a25e359a4039 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -224,13 +224,13 @@ static inline unsigned long page_order(struct page *page) * PageBuddy() should be checked first by the caller to minimize race window, * and invalid values must be handled gracefully. * - * ACCESS_ONCE is used so that if the caller assigns the result into a local + * READ_ONCE is used so that if the caller assigns the result into a local * variable and e.g. tests it for valid range before using, the compiler cannot * decide to remove the variable and inline the page_private(page) multiple * times, potentially observing different values in the tests and the actual * use of the result. */ -#define page_order_unsafe(page) ACCESS_ONCE(page_private(page)) +#define page_order_unsafe(page) READ_ONCE(page_private(page)) static inline bool is_cow_mapping(vm_flags_t flags) { diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index 936d81661c47..6c513a63ea84 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -389,6 +389,19 @@ void kasan_krealloc(const void *object, size_t size) kasan_kmalloc(page->slab_cache, object, size); } +void kasan_kfree(void *ptr) +{ + struct page *page; + + page = virt_to_head_page(ptr); + + if (unlikely(!PageSlab(page))) + kasan_poison_shadow(ptr, PAGE_SIZE << compound_order(page), + KASAN_FREE_PAGE); + else + kasan_slab_free(page->slab_cache, ptr); +} + void kasan_kfree_large(const void *ptr) { struct page *page = virt_to_page(ptr); @@ -542,7 +542,7 @@ static struct page *get_ksm_page(struct stable_node *stable_node, bool lock_it) expected_mapping = (void *)stable_node + (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM); again: - kpfn = ACCESS_ONCE(stable_node->kpfn); + kpfn = READ_ONCE(stable_node->kpfn); page = pfn_to_page(kpfn); /* @@ -551,7 +551,7 @@ again: * but on Alpha we need to be more careful. */ smp_read_barrier_depends(); - if (ACCESS_ONCE(page->mapping) != expected_mapping) + if (READ_ONCE(page->mapping) != expected_mapping) goto stale; /* @@ -577,14 +577,14 @@ again: cpu_relax(); } - if (ACCESS_ONCE(page->mapping) != expected_mapping) { + if (READ_ONCE(page->mapping) != expected_mapping) { put_page(page); goto stale; } if (lock_it) { lock_page(page); - if (ACCESS_ONCE(page->mapping) != expected_mapping) { + if (READ_ONCE(page->mapping) != expected_mapping) { unlock_page(page); put_page(page); goto stale; @@ -600,7 +600,7 @@ stale: * before checking whether node->kpfn has been changed. */ smp_rmb(); - if (ACCESS_ONCE(stable_node->kpfn) != kpfn) + if (READ_ONCE(stable_node->kpfn) != kpfn) goto again; remove_node_from_stable_tree(stable_node); return NULL; diff --git a/mm/memblock.c b/mm/memblock.c index 3f37a0bca5d5..9318b567ed79 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -580,10 +580,24 @@ 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) +{ + struct memblock_type *_rgn = &memblock.memory; + + memblock_dbg("memblock_add: [%#016llx-%#016llx] flags %#02lx %pF\n", + (unsigned long long)base, + (unsigned long long)base + size - 1, + flags, (void *)_RET_IP_); + + return memblock_add_range(_rgn, base, size, nid, flags); +} + int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) { - return memblock_add_range(&memblock.memory, base, size, - MAX_NUMNODES, 0); + return memblock_add_region(base, size, MAX_NUMNODES, 0); } /** diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c3f09b2dda5f..14c2f2017e37 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -259,11 +259,6 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg); * page cache and RSS per cgroup. We would eventually like to provide * statistics based on the statistics developed by Rik Van Riel for clock-pro, * to help the administrator determine what knobs to tune. - * - * TODO: Add a water mark for the memory controller. Reclaim will begin when - * we hit the water mark. May be even add a low water mark, such that - * no reclaim occurs from a cgroup at it's low water mark, this is - * a feature that will be implemented much later in the future. */ struct mem_cgroup { struct cgroup_subsys_state css; @@ -460,6 +455,12 @@ static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) return memcg->css.id; } +/* + * A helper function to get mem_cgroup from ID. must be called under + * rcu_read_lock(). The caller is responsible for calling + * css_tryget_online() if the mem_cgroup is used for charging. (dropping + * refcnt from swap can be called against removed memcg.) + */ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) { struct cgroup_subsys_state *css; @@ -673,7 +674,7 @@ static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, static unsigned long soft_limit_excess(struct mem_cgroup *memcg) { unsigned long nr_pages = page_counter_read(&memcg->memory); - unsigned long soft_limit = ACCESS_ONCE(memcg->soft_limit); + unsigned long soft_limit = READ_ONCE(memcg->soft_limit); unsigned long excess = 0; if (nr_pages > soft_limit) @@ -1041,7 +1042,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, goto out_unlock; do { - pos = ACCESS_ONCE(iter->position); + pos = READ_ONCE(iter->position); /* * A racing update may change the position and * put the last reference, hence css_tryget(), @@ -1358,13 +1359,13 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) unsigned long limit; count = page_counter_read(&memcg->memory); - limit = ACCESS_ONCE(memcg->memory.limit); + limit = READ_ONCE(memcg->memory.limit); if (count < limit) margin = limit - count; if (do_swap_account) { count = page_counter_read(&memcg->memsw); - limit = ACCESS_ONCE(memcg->memsw.limit); + limit = READ_ONCE(memcg->memsw.limit); if (count <= limit) margin = min(margin, limit - count); } @@ -2349,20 +2350,6 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) } /* - * A helper function to get mem_cgroup from ID. must be called under - * rcu_read_lock(). The caller is responsible for calling - * css_tryget_online() if the mem_cgroup is used for charging. (dropping - * refcnt from swap can be called against removed memcg.) - */ -static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) -{ - /* ID 0 is unused ID */ - if (!id) - return NULL; - return mem_cgroup_from_id(id); -} - -/* * try_get_mem_cgroup_from_page - look up page's memcg association * @page: the page * @@ -2388,7 +2375,7 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) ent.val = page_private(page); id = lookup_swap_cgroup_id(ent); rcu_read_lock(); - memcg = mem_cgroup_lookup(id); + memcg = mem_cgroup_from_id(id); if (memcg && !css_tryget_online(&memcg->css)) memcg = NULL; rcu_read_unlock(); @@ -2650,7 +2637,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep) return cachep; memcg = get_mem_cgroup_from_mm(current->mm); - kmemcg_id = ACCESS_ONCE(memcg->kmemcg_id); + kmemcg_id = READ_ONCE(memcg->kmemcg_id); if (kmemcg_id < 0) goto out; @@ -5020,7 +5007,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, * tunable will only affect upcoming migrations, not the current one. * So we need to save it, and keep it going. */ - move_flags = ACCESS_ONCE(memcg->move_charge_at_immigrate); + move_flags = READ_ONCE(memcg->move_charge_at_immigrate); if (move_flags) { struct mm_struct *mm; struct mem_cgroup *from = mem_cgroup_from_task(p); @@ -5254,7 +5241,7 @@ static u64 memory_current_read(struct cgroup_subsys_state *css, static int memory_low_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - unsigned long low = ACCESS_ONCE(memcg->low); + unsigned long low = READ_ONCE(memcg->low); if (low == PAGE_COUNTER_MAX) seq_puts(m, "max\n"); @@ -5284,7 +5271,7 @@ static ssize_t memory_low_write(struct kernfs_open_file *of, static int memory_high_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - unsigned long high = ACCESS_ONCE(memcg->high); + unsigned long high = READ_ONCE(memcg->high); if (high == PAGE_COUNTER_MAX) seq_puts(m, "max\n"); @@ -5314,7 +5301,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, static int memory_max_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - unsigned long max = ACCESS_ONCE(memcg->memory.limit); + unsigned long max = READ_ONCE(memcg->memory.limit); if (max == PAGE_COUNTER_MAX) seq_puts(m, "max\n"); @@ -5869,7 +5856,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry) id = swap_cgroup_record(entry, 0); rcu_read_lock(); - memcg = mem_cgroup_lookup(id); + memcg = mem_cgroup_from_id(id); if (memcg) { if (!mem_cgroup_is_root(memcg)) page_counter_uncharge(&memcg->memsw, 1); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index d487f8dc6d39..d9359b770cd9 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -521,6 +521,52 @@ static const char *action_name[] = { [RECOVERED] = "Recovered", }; +enum action_page_type { + MSG_KERNEL, + MSG_KERNEL_HIGH_ORDER, + MSG_SLAB, + MSG_DIFFERENT_COMPOUND, + MSG_POISONED_HUGE, + MSG_HUGE, + MSG_FREE_HUGE, + MSG_UNMAP_FAILED, + MSG_DIRTY_SWAPCACHE, + MSG_CLEAN_SWAPCACHE, + MSG_DIRTY_MLOCKED_LRU, + MSG_CLEAN_MLOCKED_LRU, + MSG_DIRTY_UNEVICTABLE_LRU, + MSG_CLEAN_UNEVICTABLE_LRU, + MSG_DIRTY_LRU, + MSG_CLEAN_LRU, + MSG_TRUNCATED_LRU, + MSG_BUDDY, + MSG_BUDDY_2ND, + MSG_UNKNOWN, +}; + +static const char * const action_page_types[] = { + [MSG_KERNEL] = "reserved kernel page", + [MSG_KERNEL_HIGH_ORDER] = "high-order kernel page", + [MSG_SLAB] = "kernel slab page", + [MSG_DIFFERENT_COMPOUND] = "different compound page after locking", + [MSG_POISONED_HUGE] = "huge page already hardware poisoned", + [MSG_HUGE] = "huge page", + [MSG_FREE_HUGE] = "free huge page", + [MSG_UNMAP_FAILED] = "unmapping failed page", + [MSG_DIRTY_SWAPCACHE] = "dirty swapcache page", + [MSG_CLEAN_SWAPCACHE] = "clean swapcache page", + [MSG_DIRTY_MLOCKED_LRU] = "dirty mlocked LRU page", + [MSG_CLEAN_MLOCKED_LRU] = "clean mlocked LRU page", + [MSG_DIRTY_UNEVICTABLE_LRU] = "dirty unevictable LRU page", + [MSG_CLEAN_UNEVICTABLE_LRU] = "clean unevictable LRU page", + [MSG_DIRTY_LRU] = "dirty LRU page", + [MSG_CLEAN_LRU] = "clean LRU page", + [MSG_TRUNCATED_LRU] = "already truncated LRU page", + [MSG_BUDDY] = "free buddy page", + [MSG_BUDDY_2ND] = "free buddy page (2nd try)", + [MSG_UNKNOWN] = "unknown page", +}; + /* * XXX: It is possible that a page is isolated from LRU cache, * and then kept in swap cache or failed to remove from page cache. @@ -777,10 +823,10 @@ static int me_huge_page(struct page *p, unsigned long pfn) static struct page_state { unsigned long mask; unsigned long res; - char *msg; + enum action_page_type type; int (*action)(struct page *p, unsigned long pfn); } error_states[] = { - { reserved, reserved, "reserved kernel", me_kernel }, + { reserved, reserved, MSG_KERNEL, me_kernel }, /* * free pages are specially detected outside this table: * PG_buddy pages only make a small fraction of all free pages. @@ -791,31 +837,31 @@ static struct page_state { * currently unused objects without touching them. But just * treat it as standard kernel for now. */ - { slab, slab, "kernel slab", me_kernel }, + { slab, slab, MSG_SLAB, me_kernel }, #ifdef CONFIG_PAGEFLAGS_EXTENDED - { head, head, "huge", me_huge_page }, - { tail, tail, "huge", me_huge_page }, + { head, head, MSG_HUGE, me_huge_page }, + { tail, tail, MSG_HUGE, me_huge_page }, #else - { compound, compound, "huge", me_huge_page }, + { compound, compound, MSG_HUGE, me_huge_page }, #endif - { sc|dirty, sc|dirty, "dirty swapcache", me_swapcache_dirty }, - { sc|dirty, sc, "clean swapcache", me_swapcache_clean }, + { sc|dirty, sc|dirty, MSG_DIRTY_SWAPCACHE, me_swapcache_dirty }, + { sc|dirty, sc, MSG_CLEAN_SWAPCACHE, me_swapcache_clean }, - { mlock|dirty, mlock|dirty, "dirty mlocked LRU", me_pagecache_dirty }, - { mlock|dirty, mlock, "clean mlocked LRU", me_pagecache_clean }, + { mlock|dirty, mlock|dirty, MSG_DIRTY_MLOCKED_LRU, me_pagecache_dirty }, + { mlock|dirty, mlock, MSG_CLEAN_MLOCKED_LRU, me_pagecache_clean }, - { unevict|dirty, unevict|dirty, "dirty unevictable LRU", me_pagecache_dirty }, - { unevict|dirty, unevict, "clean unevictable LRU", me_pagecache_clean }, + { unevict|dirty, unevict|dirty, MSG_DIRTY_UNEVICTABLE_LRU, me_pagecache_dirty }, + { unevict|dirty, unevict, MSG_CLEAN_UNEVICTABLE_LRU, me_pagecache_clean }, - { lru|dirty, lru|dirty, "dirty LRU", me_pagecache_dirty }, - { lru|dirty, lru, "clean LRU", me_pagecache_clean }, + { lru|dirty, lru|dirty, MSG_DIRTY_LRU, me_pagecache_dirty }, + { lru|dirty, lru, MSG_CLEAN_LRU, me_pagecache_clean }, /* * Catchall entry: must be at end. */ - { 0, 0, "unknown page state", me_unknown }, + { 0, 0, MSG_UNKNOWN, me_unknown }, }; #undef dirty @@ -835,10 +881,10 @@ static struct page_state { * "Dirty/Clean" indication is not 100% accurate due to the possibility of * setting PG_dirty outside page lock. See also comment above set_page_dirty(). */ -static void action_result(unsigned long pfn, char *msg, int result) +static void action_result(unsigned long pfn, enum action_page_type type, int result) { - pr_err("MCE %#lx: %s page recovery: %s\n", - pfn, msg, action_name[result]); + pr_err("MCE %#lx: recovery action for %s: %s\n", + pfn, action_page_types[type], action_name[result]); } static int page_action(struct page_state *ps, struct page *p, @@ -854,11 +900,11 @@ static int page_action(struct page_state *ps, struct page *p, count--; if (count != 0) { printk(KERN_ERR - "MCE %#lx: %s page still referenced by %d users\n", - pfn, ps->msg, count); + "MCE %#lx: %s still referenced by %d users\n", + pfn, action_page_types[ps->type], count); result = FAILED; } - action_result(pfn, ps->msg, result); + action_result(pfn, ps->type, result); /* Could do more checks here if page looks ok */ /* @@ -1106,7 +1152,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) if (!(flags & MF_COUNT_INCREASED) && !get_page_unless_zero(hpage)) { if (is_free_buddy_page(p)) { - action_result(pfn, "free buddy", DELAYED); + action_result(pfn, MSG_BUDDY, DELAYED); return 0; } else if (PageHuge(hpage)) { /* @@ -1123,12 +1169,12 @@ int memory_failure(unsigned long pfn, int trapno, int flags) } set_page_hwpoison_huge_page(hpage); res = dequeue_hwpoisoned_huge_page(hpage); - action_result(pfn, "free huge", + action_result(pfn, MSG_FREE_HUGE, res ? IGNORED : DELAYED); unlock_page(hpage); return res; } else { - action_result(pfn, "high order kernel", IGNORED); + action_result(pfn, MSG_KERNEL_HIGH_ORDER, IGNORED); return -EBUSY; } } @@ -1150,9 +1196,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags) */ if (is_free_buddy_page(p)) { if (flags & MF_COUNT_INCREASED) - action_result(pfn, "free buddy", DELAYED); + action_result(pfn, MSG_BUDDY, DELAYED); else - action_result(pfn, "free buddy, 2nd try", DELAYED); + action_result(pfn, MSG_BUDDY_2ND, + DELAYED); return 0; } } @@ -1165,7 +1212,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * If this happens just bail out. */ if (compound_head(p) != hpage) { - action_result(pfn, "different compound page after locking", IGNORED); + action_result(pfn, MSG_DIFFERENT_COMPOUND, IGNORED); res = -EBUSY; goto out; } @@ -1205,8 +1252,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * on the head page to show that the hugepage is hwpoisoned */ if (PageHuge(p) && PageTail(p) && TestSetPageHWPoison(hpage)) { - action_result(pfn, "hugepage already hardware poisoned", - IGNORED); + action_result(pfn, MSG_POISONED_HUGE, IGNORED); unlock_page(hpage); put_page(hpage); return 0; @@ -1235,7 +1281,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) */ if (hwpoison_user_mappings(p, pfn, trapno, flags, &hpage) != SWAP_SUCCESS) { - action_result(pfn, "unmapping failed", IGNORED); + action_result(pfn, MSG_UNMAP_FAILED, IGNORED); res = -EBUSY; goto out; } @@ -1244,7 +1290,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * Torn down by someone else? */ if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) { - action_result(pfn, "already truncated LRU", IGNORED); + action_result(pfn, MSG_TRUNCATED_LRU, IGNORED); res = -EBUSY; goto out; } @@ -1540,8 +1586,18 @@ static int soft_offline_huge_page(struct page *page, int flags) } unlock_page(hpage); - /* Keep page count to indicate a given hugepage is isolated. */ - list_move(&hpage->lru, &pagelist); + ret = isolate_huge_page(hpage, &pagelist); + if (ret) { + /* + * get_any_page() and isolate_huge_page() takes a refcount each, + * so need to drop one here. + */ + put_page(hpage); + } else { + pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn); + return -EBUSY; + } + ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { diff --git a/mm/memory.c b/mm/memory.c index ac20b2a6a0c3..22e037e3364e 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -690,12 +690,11 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, /* * Choose text because data symbols depend on CONFIG_KALLSYMS_ALL=y */ - if (vma->vm_ops) - printk(KERN_ALERT "vma->vm_ops->fault: %pSR\n", - vma->vm_ops->fault); - if (vma->vm_file) - printk(KERN_ALERT "vma->vm_file->f_op->mmap: %pSR\n", - vma->vm_file->f_op->mmap); + pr_alert("file:%pD fault:%pf mmap:%pf readpage:%pf\n", + vma->vm_file, + vma->vm_ops ? vma->vm_ops->fault : NULL, + vma->vm_file ? vma->vm_file->f_op->mmap : NULL, + mapping ? mapping->a_ops->readpage : NULL); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } @@ -2181,6 +2180,42 @@ oom: return VM_FAULT_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) +{ + 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), + .flags = FAULT_FLAG_WRITE | FAULT_FLAG_MKWRITE, + }; + int ret; + + pte_unmap_unlock(page_table, 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); + /* + * 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); + return 0; + } + } + return wp_page_reuse(mm, vma, address, page_table, ptl, 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, @@ -2259,13 +2294,12 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, * VM_PFNMAP VMA. * * We should not cow pages in a shared writeable mapping. - * Just mark the pages writable as we can't do any dirty - * accounting on raw pfn maps. + * Just mark the pages writable and/or call ops->pfn_mkwrite. */ if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED)) - return wp_page_reuse(mm, vma, address, page_table, ptl, - orig_pte, old_page, 0, 0); + return wp_pfn_shared(mm, vma, address, page_table, ptl, + orig_pte, pmd); pte_unmap_unlock(page_table, ptl); return wp_page_copy(mm, vma, address, page_table, pmd, @@ -2845,7 +2879,7 @@ static void do_fault_around(struct vm_area_struct *vma, unsigned long address, struct vm_fault vmf; int off; - nr_pages = ACCESS_ONCE(fault_around_bytes) >> PAGE_SHIFT; + 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); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index e2e8014fb755..457bde530cbe 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1373,7 +1373,7 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end) if (PageLRU(page)) return pfn; if (PageHuge(page)) { - if (is_hugepage_active(page)) + if (page_huge_active(page)) return pfn; else pfn = round_up(pfn + 1, diff --git a/mm/mempool.c b/mm/mempool.c index 949970db2874..2cc08de8b1db 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -6,26 +6,138 @@ * extreme VM load. * * started by Ingo Molnar, Copyright (C) 2001 + * debugging by David Rientjes, Copyright (C) 2015 */ #include <linux/mm.h> #include <linux/slab.h> +#include <linux/highmem.h> +#include <linux/kasan.h> #include <linux/kmemleak.h> #include <linux/export.h> #include <linux/mempool.h> #include <linux/blkdev.h> #include <linux/writeback.h> +#include "slab.h" + +#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB_DEBUG_ON) +static void poison_error(mempool_t *pool, void *element, size_t size, + size_t byte) +{ + const int nr = pool->curr_nr; + const int start = max_t(int, byte - (BITS_PER_LONG / 8), 0); + const int end = min_t(int, byte + (BITS_PER_LONG / 8), size); + int i; + + pr_err("BUG: mempool element poison mismatch\n"); + pr_err("Mempool %p size %zu\n", pool, size); + pr_err(" nr=%d @ %p: %s0x", nr, element, start > 0 ? "... " : ""); + for (i = start; i < end; i++) + pr_cont("%x ", *(u8 *)(element + i)); + pr_cont("%s\n", end < size ? "..." : ""); + dump_stack(); +} + +static void __check_element(mempool_t *pool, void *element, size_t size) +{ + u8 *obj = element; + size_t i; + + for (i = 0; i < size; i++) { + u8 exp = (i < size - 1) ? POISON_FREE : POISON_END; + + if (obj[i] != exp) { + poison_error(pool, element, size, i); + return; + } + } + memset(obj, POISON_INUSE, size); +} + +static void check_element(mempool_t *pool, void *element) +{ + /* Mempools backed by slab allocator */ + if (pool->free == mempool_free_slab || pool->free == mempool_kfree) + __check_element(pool, element, ksize(element)); + + /* Mempools backed by page allocator */ + if (pool->free == mempool_free_pages) { + int order = (int)(long)pool->pool_data; + void *addr = kmap_atomic((struct page *)element); + + __check_element(pool, addr, 1UL << (PAGE_SHIFT + order)); + kunmap_atomic(addr); + } +} + +static void __poison_element(void *element, size_t size) +{ + u8 *obj = element; + + memset(obj, POISON_FREE, size - 1); + obj[size - 1] = POISON_END; +} + +static void poison_element(mempool_t *pool, void *element) +{ + /* Mempools backed by slab allocator */ + if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc) + __poison_element(element, ksize(element)); + + /* Mempools backed by page allocator */ + if (pool->alloc == mempool_alloc_pages) { + int order = (int)(long)pool->pool_data; + void *addr = kmap_atomic((struct page *)element); + + __poison_element(addr, 1UL << (PAGE_SHIFT + order)); + kunmap_atomic(addr); + } +} +#else /* CONFIG_DEBUG_SLAB || CONFIG_SLUB_DEBUG_ON */ +static inline void check_element(mempool_t *pool, void *element) +{ +} +static inline void poison_element(mempool_t *pool, void *element) +{ +} +#endif /* CONFIG_DEBUG_SLAB || CONFIG_SLUB_DEBUG_ON */ + +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_pages) + kasan_free_pages(element, (unsigned long)pool->pool_data); +} + +static void kasan_unpoison_element(mempool_t *pool, void *element) +{ + if (pool->alloc == mempool_alloc_slab) + kasan_slab_alloc(pool->pool_data, element); + if (pool->alloc == mempool_kmalloc) + kasan_krealloc(element, (size_t)pool->pool_data); + if (pool->alloc == mempool_alloc_pages) + kasan_alloc_pages(element, (unsigned long)pool->pool_data); +} static void add_element(mempool_t *pool, void *element) { BUG_ON(pool->curr_nr >= pool->min_nr); + poison_element(pool, element); + kasan_poison_element(pool, element); pool->elements[pool->curr_nr++] = element; } static void *remove_element(mempool_t *pool) { - BUG_ON(pool->curr_nr <= 0); - return pool->elements[--pool->curr_nr]; + void *element = pool->elements[--pool->curr_nr]; + + BUG_ON(pool->curr_nr < 0); + check_element(pool, element); + kasan_unpoison_element(pool, element); + return element; } /** @@ -334,6 +446,7 @@ EXPORT_SYMBOL(mempool_free); void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data) { struct kmem_cache *mem = pool_data; + VM_BUG_ON(mem->ctor); return kmem_cache_alloc(mem, gfp_mask); } EXPORT_SYMBOL(mempool_alloc_slab); diff --git a/mm/migrate.c b/mm/migrate.c index a65ff72ab739..f53838fe3dfe 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -537,7 +537,8 @@ void migrate_page_copy(struct page *newpage, struct page *page) * Please do not reorder this without considering how mm/ksm.c's * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache(). */ - ClearPageSwapCache(page); + if (PageSwapCache(page)) + ClearPageSwapCache(page); ClearPagePrivate(page); set_page_private(page, 0); diff --git a/mm/mmap.c b/mm/mmap.c index 06a6076c92e5..bb50cacc3ea5 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1133,7 +1133,7 @@ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct * * by another page fault trying to merge _that_. But that's ok: if it * is being set up, that automatically means that it will be a singleton * acceptable for merging, so we can do all of this optimistically. But - * we do that ACCESS_ONCE() to make sure that we never re-load the pointer. + * we do that READ_ONCE() to make sure that we never re-load the pointer. * * IOW: that the "list_is_singular()" test on the anon_vma_chain only * matters for the 'stable anon_vma' case (ie the thing we want to avoid @@ -1147,7 +1147,7 @@ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct * static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) { if (anon_vma_compatible(a, b)) { - struct anon_vma *anon_vma = ACCESS_ONCE(old->anon_vma); + struct anon_vma *anon_vma = READ_ONCE(old->anon_vma); if (anon_vma && list_is_singular(&old->anon_vma_chain)) return anon_vma; @@ -1551,11 +1551,10 @@ unsigned long mmap_region(struct file *file, unsigned long addr, /* Clear old maps */ error = -ENOMEM; -munmap_back: - if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) { + while (find_vma_links(mm, addr, addr + len, &prev, &rb_link, + &rb_parent)) { if (do_munmap(mm, addr, len)) return -ENOMEM; - goto munmap_back; } /* @@ -1571,7 +1570,8 @@ munmap_back: /* * Can we just expand an old mapping? */ - vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL); + vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, + NULL); if (vma) goto out; @@ -2100,7 +2100,7 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns actual_size = size; if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN))) actual_size -= PAGE_SIZE; - if (actual_size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur)) + if (actual_size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur)) return -ENOMEM; /* mlock limit tests */ @@ -2108,7 +2108,7 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns unsigned long locked; unsigned long limit; locked = mm->locked_vm + grow; - limit = ACCESS_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur); + limit = READ_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur); limit >>= PAGE_SHIFT; if (locked > limit && !capable(CAP_IPC_LOCK)) return -ENOMEM; @@ -2739,11 +2739,10 @@ static unsigned long do_brk(unsigned long addr, unsigned long len) /* * Clear old maps. this also does some error checking for us */ - munmap_back: - if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) { + while (find_vma_links(mm, addr, addr + len, &prev, &rb_link, + &rb_parent)) { if (do_munmap(mm, addr, len)) return -ENOMEM; - goto munmap_back; } /* Check against address space limits *after* clearing old maps... */ diff --git a/mm/mremap.c b/mm/mremap.c index 2dc44b1cb1df..034e2d360652 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -345,25 +345,25 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, struct vm_area_struct *vma = find_vma(mm, addr); if (!vma || vma->vm_start > addr) - goto Efault; + return ERR_PTR(-EFAULT); if (is_vm_hugetlb_page(vma)) - goto Einval; + return ERR_PTR(-EINVAL); /* We can't remap across vm area boundaries */ if (old_len > vma->vm_end - addr) - goto Efault; + return ERR_PTR(-EFAULT); /* Need to be careful about a growing mapping */ if (new_len > old_len) { unsigned long pgoff; if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) - goto Efault; + return ERR_PTR(-EFAULT); pgoff = (addr - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; if (pgoff + (new_len >> PAGE_SHIFT) < pgoff) - goto Einval; + return ERR_PTR(-EINVAL); } if (vma->vm_flags & VM_LOCKED) { @@ -372,29 +372,20 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, lock_limit = rlimit(RLIMIT_MEMLOCK); locked += new_len - old_len; if (locked > lock_limit && !capable(CAP_IPC_LOCK)) - goto Eagain; + return ERR_PTR(-EAGAIN); } if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT)) - goto Enomem; + return ERR_PTR(-ENOMEM); if (vma->vm_flags & VM_ACCOUNT) { unsigned long charged = (new_len - old_len) >> PAGE_SHIFT; if (security_vm_enough_memory_mm(mm, charged)) - goto Efault; + return ERR_PTR(-ENOMEM); *p = charged; } return vma; - -Efault: /* very odd choice for most of the cases, but... */ - return ERR_PTR(-EFAULT); -Einval: - return ERR_PTR(-EINVAL); -Enomem: - return ERR_PTR(-ENOMEM); -Eagain: - return ERR_PTR(-EAGAIN); } static unsigned long mremap_to(unsigned long addr, unsigned long old_len, diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 52628c819bf7..2b665da1b3c9 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -408,7 +408,7 @@ bool oom_killer_disabled __read_mostly; static DECLARE_RWSEM(oom_sem); /** - * mark_tsk_oom_victim - marks the given taks as OOM victim. + * mark_tsk_oom_victim - marks the given task as OOM victim. * @tsk: task to mark * * Has to be called with oom_sem taken for read and never after diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0372411f38fc..5daf5568b9e1 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2228,7 +2228,8 @@ int set_page_dirty(struct page *page) * it will confuse readahead and make it restart the size rampup * process. But it's a trivial problem. */ - ClearPageReclaim(page); + if (PageReclaim(page)) + ClearPageReclaim(page); #ifdef CONFIG_BLOCK if (!spd) spd = __set_page_dirty_buffers; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 1b849500640c..ebffa0e4a9c0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1371,7 +1371,7 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) int to_drain, batch; local_irq_save(flags); - batch = ACCESS_ONCE(pcp->batch); + batch = READ_ONCE(pcp->batch); to_drain = min(pcp->count, batch); if (to_drain > 0) { free_pcppages_bulk(zone, to_drain, pcp); @@ -1570,7 +1570,7 @@ void free_hot_cold_page(struct page *page, bool cold) list_add_tail(&page->lru, &pcp->lists[migratetype]); pcp->count++; if (pcp->count >= pcp->high) { - unsigned long batch = ACCESS_ONCE(pcp->batch); + unsigned long batch = READ_ONCE(pcp->batch); free_pcppages_bulk(zone, batch, pcp); pcp->count -= batch; } @@ -6207,7 +6207,7 @@ void set_pfnblock_flags_mask(struct page *page, unsigned long flags, mask <<= (BITS_PER_LONG - bitidx - 1); flags <<= (BITS_PER_LONG - bitidx - 1); - word = ACCESS_ONCE(bitmap[word_bitidx]); + word = READ_ONCE(bitmap[word_bitidx]); for (;;) { old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags); if (word == old_word) diff --git a/mm/rmap.c b/mm/rmap.c index c161a14b6a8f..24dd3f9fee27 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -456,7 +456,7 @@ struct anon_vma *page_get_anon_vma(struct page *page) unsigned long anon_mapping; rcu_read_lock(); - anon_mapping = (unsigned long) ACCESS_ONCE(page->mapping); + anon_mapping = (unsigned long)READ_ONCE(page->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!page_mapped(page)) @@ -500,14 +500,14 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page) unsigned long anon_mapping; rcu_read_lock(); - anon_mapping = (unsigned long) ACCESS_ONCE(page->mapping); + anon_mapping = (unsigned long)READ_ONCE(page->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!page_mapped(page)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); - root_anon_vma = ACCESS_ONCE(anon_vma->root); + root_anon_vma = READ_ONCE(anon_vma->root); if (down_read_trylock(&root_anon_vma->rwsem)) { /* * If the page is still mapped, then this anon_vma is still diff --git a/mm/slub.c b/mm/slub.c index 0fdd6c1e1f82..54c0876b43d5 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4277,7 +4277,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s, int node; struct page *page; - page = ACCESS_ONCE(c->page); + page = READ_ONCE(c->page); if (!page) continue; @@ -4292,7 +4292,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s, total += x; nodes[node] += x; - page = ACCESS_ONCE(c->partial); + page = READ_ONCE(c->partial); if (page) { node = page_to_nid(page); if (flags & SO_TOTAL) diff --git a/mm/swap.c b/mm/swap.c index cd3a5e64cea9..a7251a8ed532 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -31,6 +31,7 @@ #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> +#include <linux/hugetlb.h> #include "internal.h" @@ -42,7 +43,7 @@ int page_cluster; 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_pvecs); +static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs); /* * This path almost never happens for VM activity - pages are normally @@ -75,7 +76,14 @@ static void __put_compound_page(struct page *page) { compound_page_dtor *dtor; - __page_cache_release(page); + /* + * __page_cache_release() is supposed to be called for thp, not for + * hugetlb. This is because hugetlb page does never have PageLRU set + * (it's never listed to any LRU lists) and no memcg routines should + * be called for hugetlb (it has a separate hugetlb_cgroup.) + */ + if (!PageHuge(page)) + __page_cache_release(page); dtor = get_compound_page_dtor(page); (*dtor)(page); } @@ -743,7 +751,7 @@ void lru_cache_add_active_or_unevictable(struct page *page, * be write it out by flusher threads as this is much more effective * than the single-page writeout from reclaim. */ -static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, +static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, void *arg) { int lru, file; @@ -811,36 +819,36 @@ void lru_add_drain_cpu(int cpu) local_irq_restore(flags); } - pvec = &per_cpu(lru_deactivate_pvecs, cpu); + pvec = &per_cpu(lru_deactivate_file_pvecs, cpu); if (pagevec_count(pvec)) - pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); + pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); activate_page_drain(cpu); } /** - * deactivate_page - forcefully deactivate a page + * deactivate_file_page - forcefully deactivate a file page * @page: page to deactivate * * This function hints the VM that @page is a good reclaim candidate, * for example if its invalidation fails due to the page being dirty * or under writeback. */ -void deactivate_page(struct page *page) +void deactivate_file_page(struct page *page) { /* - * In a workload with many unevictable page such as mprotect, unevictable - * page deactivation for accelerating reclaim is pointless. + * In a workload with many unevictable page such as mprotect, + * unevictable page deactivation for accelerating reclaim is pointless. */ if (PageUnevictable(page)) return; if (likely(get_page_unless_zero(page))) { - struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs); + struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs); if (!pagevec_add(pvec, page)) - pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); - put_cpu_var(lru_deactivate_pvecs); + pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); + put_cpu_var(lru_deactivate_file_pvecs); } } @@ -872,7 +880,7 @@ void lru_add_drain_all(void) if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) || pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) || - pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) || + pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) || need_activate_page_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); schedule_work_on(cpu, work); diff --git a/mm/swap_state.c b/mm/swap_state.c index 405923f77334..8bc8e66138da 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -390,7 +390,7 @@ static unsigned long swapin_nr_pages(unsigned long offset) unsigned int pages, max_pages, last_ra; static atomic_t last_readahead_pages; - max_pages = 1 << ACCESS_ONCE(page_cluster); + max_pages = 1 << READ_ONCE(page_cluster); if (max_pages <= 1) return 1; diff --git a/mm/swapfile.c b/mm/swapfile.c index 63f55ccb9b26..a7e72103f23b 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1312,7 +1312,7 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, else continue; } - count = ACCESS_ONCE(si->swap_map[i]); + count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) break; } diff --git a/mm/truncate.c b/mm/truncate.c index 7a9d8a3cb143..66af9031fae8 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -490,7 +490,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, * of interest and try to speed up its reclaim. */ if (!ret) - deactivate_page(page); + deactivate_file_page(page); count += ret; } pagevec_remove_exceptionals(&pvec); diff --git a/mm/util.c b/mm/util.c index 3981ae9d1b15..68ff8a5361e7 100644 --- a/mm/util.c +++ b/mm/util.c @@ -325,9 +325,37 @@ void kvfree(const void *addr) } EXPORT_SYMBOL(kvfree); +static inline void *__page_rmapping(struct page *page) +{ + unsigned long mapping; + + mapping = (unsigned long)page->mapping; + mapping &= ~PAGE_MAPPING_FLAGS; + + return (void *)mapping; +} + +/* Neutral page->mapping pointer to address_space or anon_vma or other */ +void *page_rmapping(struct page *page) +{ + page = compound_head(page); + return __page_rmapping(page); +} + +struct anon_vma *page_anon_vma(struct page *page) +{ + unsigned long mapping; + + page = compound_head(page); + mapping = (unsigned long)page->mapping; + if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) + return NULL; + return __page_rmapping(page); +} + struct address_space *page_mapping(struct page *page) { - struct address_space *mapping = page->mapping; + unsigned long mapping; /* This happens if someone calls flush_dcache_page on slab page */ if (unlikely(PageSlab(page))) @@ -337,10 +365,13 @@ struct address_space *page_mapping(struct page *page) swp_entry_t entry; entry.val = page_private(page); - mapping = swap_address_space(entry); - } else if ((unsigned long)mapping & PAGE_MAPPING_ANON) - mapping = NULL; - return mapping; + return swap_address_space(entry); + } + + mapping = (unsigned long)page->mapping; + if (mapping & PAGE_MAPPING_FLAGS) + return NULL; + return page->mapping; } int overcommit_ratio_handler(struct ctl_table *table, int write, diff --git a/mm/vmalloc.c b/mm/vmalloc.c index a5bbdd3b5d67..2faaa2976447 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -765,7 +765,7 @@ struct vmap_block { spinlock_t lock; struct vmap_area *va; unsigned long free, dirty; - DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS); + unsigned long dirty_min, dirty_max; /*< dirty range */ struct list_head free_list; struct rcu_head rcu_head; struct list_head purge; @@ -796,13 +796,31 @@ static unsigned long addr_to_vb_idx(unsigned long addr) return addr; } -static struct vmap_block *new_vmap_block(gfp_t gfp_mask) +static void *vmap_block_vaddr(unsigned long va_start, unsigned long pages_off) +{ + unsigned long addr; + + addr = va_start + (pages_off << PAGE_SHIFT); + BUG_ON(addr_to_vb_idx(addr) != addr_to_vb_idx(va_start)); + return (void *)addr; +} + +/** + * new_vmap_block - allocates new vmap_block and occupies 2^order pages in this + * block. Of course pages number can't exceed VMAP_BBMAP_BITS + * @order: how many 2^order pages should be occupied in newly allocated block + * @gfp_mask: flags for the page level allocator + * + * Returns: virtual address in a newly allocated block or ERR_PTR(-errno) + */ +static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; struct vmap_area *va; unsigned long vb_idx; int node, err; + void *vaddr; node = numa_node_id(); @@ -826,11 +844,15 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask) return ERR_PTR(err); } + vaddr = vmap_block_vaddr(va->va_start, 0); spin_lock_init(&vb->lock); vb->va = va; - vb->free = VMAP_BBMAP_BITS; + /* At least something should be left free */ + BUG_ON(VMAP_BBMAP_BITS <= (1UL << order)); + vb->free = VMAP_BBMAP_BITS - (1UL << order); vb->dirty = 0; - bitmap_zero(vb->dirty_map, VMAP_BBMAP_BITS); + vb->dirty_min = VMAP_BBMAP_BITS; + vb->dirty_max = 0; INIT_LIST_HEAD(&vb->free_list); vb_idx = addr_to_vb_idx(va->va_start); @@ -842,11 +864,11 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask) vbq = &get_cpu_var(vmap_block_queue); spin_lock(&vbq->lock); - list_add_rcu(&vb->free_list, &vbq->free); + list_add_tail_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); put_cpu_var(vmap_block_queue); - return vb; + return vaddr; } static void free_vmap_block(struct vmap_block *vb) @@ -881,7 +903,8 @@ static void purge_fragmented_blocks(int cpu) if (vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS) { vb->free = 0; /* prevent further allocs after releasing lock */ vb->dirty = VMAP_BBMAP_BITS; /* prevent purging it again */ - bitmap_fill(vb->dirty_map, VMAP_BBMAP_BITS); + vb->dirty_min = 0; + vb->dirty_max = VMAP_BBMAP_BITS; spin_lock(&vbq->lock); list_del_rcu(&vb->free_list); spin_unlock(&vbq->lock); @@ -910,7 +933,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; - unsigned long addr = 0; + void *vaddr = NULL; unsigned int order; BUG_ON(size & ~PAGE_MASK); @@ -925,43 +948,38 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) } order = get_order(size); -again: rcu_read_lock(); vbq = &get_cpu_var(vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { - int i; + unsigned long pages_off; spin_lock(&vb->lock); - if (vb->free < 1UL << order) - goto next; + if (vb->free < (1UL << order)) { + spin_unlock(&vb->lock); + continue; + } - i = VMAP_BBMAP_BITS - vb->free; - addr = vb->va->va_start + (i << PAGE_SHIFT); - BUG_ON(addr_to_vb_idx(addr) != - addr_to_vb_idx(vb->va->va_start)); + pages_off = VMAP_BBMAP_BITS - vb->free; + vaddr = vmap_block_vaddr(vb->va->va_start, pages_off); vb->free -= 1UL << order; if (vb->free == 0) { spin_lock(&vbq->lock); list_del_rcu(&vb->free_list); spin_unlock(&vbq->lock); } + spin_unlock(&vb->lock); break; -next: - spin_unlock(&vb->lock); } put_cpu_var(vmap_block_queue); rcu_read_unlock(); - if (!addr) { - vb = new_vmap_block(gfp_mask); - if (IS_ERR(vb)) - return vb; - goto again; - } + /* Allocate new block if nothing was found */ + if (!vaddr) + vaddr = new_vmap_block(order, gfp_mask); - return (void *)addr; + return vaddr; } static void vb_free(const void *addr, unsigned long size) @@ -979,6 +997,7 @@ static void vb_free(const void *addr, unsigned long size) order = get_order(size); offset = (unsigned long)addr & (VMAP_BLOCK_SIZE - 1); + offset >>= PAGE_SHIFT; vb_idx = addr_to_vb_idx((unsigned long)addr); rcu_read_lock(); @@ -989,7 +1008,10 @@ static void vb_free(const void *addr, unsigned long size) vunmap_page_range((unsigned long)addr, (unsigned long)addr + size); spin_lock(&vb->lock); - BUG_ON(bitmap_allocate_region(vb->dirty_map, offset >> PAGE_SHIFT, order)); + + /* Expand dirty range */ + vb->dirty_min = min(vb->dirty_min, offset); + vb->dirty_max = max(vb->dirty_max, offset + (1UL << order)); vb->dirty += 1UL << order; if (vb->dirty == VMAP_BBMAP_BITS) { @@ -1028,25 +1050,18 @@ void vm_unmap_aliases(void) rcu_read_lock(); list_for_each_entry_rcu(vb, &vbq->free, free_list) { - int i, j; - spin_lock(&vb->lock); - i = find_first_bit(vb->dirty_map, VMAP_BBMAP_BITS); - if (i < VMAP_BBMAP_BITS) { + if (vb->dirty) { + unsigned long va_start = vb->va->va_start; unsigned long s, e; - j = find_last_bit(vb->dirty_map, - VMAP_BBMAP_BITS); - j = j + 1; /* need exclusive index */ + s = va_start + (vb->dirty_min << PAGE_SHIFT); + e = va_start + (vb->dirty_max << PAGE_SHIFT); - s = vb->va->va_start + (i << PAGE_SHIFT); - e = vb->va->va_start + (j << PAGE_SHIFT); - flush = 1; + start = min(s, start); + end = max(e, end); - if (s < start) - start = s; - if (e > end) - end = e; + flush = 1; } spin_unlock(&vb->lock); } diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 0dec1fa5f656..08bd7a3d464a 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -12,35 +12,6 @@ */ /* - * This allocator is designed for use with zram. Thus, the allocator is - * supposed to work well under low memory conditions. In particular, it - * never attempts higher order page allocation which is very likely to - * fail under memory pressure. On the other hand, if we just use single - * (0-order) pages, it would suffer from very high fragmentation -- - * any object of size PAGE_SIZE/2 or larger would occupy an entire page. - * This was one of the major issues with its predecessor (xvmalloc). - * - * To overcome these issues, zsmalloc allocates a bunch of 0-order pages - * and links them together using various 'struct page' fields. These linked - * pages act as a single higher-order page i.e. an object can span 0-order - * page boundaries. The code refers to these linked pages as a single entity - * called zspage. - * - * For simplicity, zsmalloc can only allocate objects of size up to PAGE_SIZE - * since this satisfies the requirements of all its current users (in the - * worst case, page is incompressible and is thus stored "as-is" i.e. in - * uncompressed form). For allocation requests larger than this size, failure - * is returned (see zs_malloc). - * - * Additionally, zs_malloc() does not return a dereferenceable pointer. - * Instead, it returns an opaque handle (unsigned long) which encodes actual - * location of the allocated object. The reason for this indirection is that - * zsmalloc does not keep zspages permanently mapped since that would cause - * issues on 32-bit systems where the VA region for kernel space mappings - * is very small. So, before using the allocating memory, the object has to - * be mapped using zs_map_object() to get a usable pointer and subsequently - * unmapped using zs_unmap_object(). - * * Following is how we use various fields and flags of underlying * struct page(s) to form a zspage. * @@ -57,6 +28,8 @@ * * page->private (union with page->first_page): 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. @@ -78,6 +51,7 @@ #include <linux/module.h> #include <linux/kernel.h> +#include <linux/sched.h> #include <linux/bitops.h> #include <linux/errno.h> #include <linux/highmem.h> @@ -110,6 +84,8 @@ #define ZS_MAX_ZSPAGE_ORDER 2 #define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER) +#define ZS_HANDLE_SIZE (sizeof(unsigned long)) + /* * Object location (<PFN>, <obj_idx>) is encoded as * as single (unsigned long) handle value. @@ -133,13 +109,33 @@ #endif #endif #define _PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) -#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS) + +/* + * Memory for allocating for handle keeps object position by + * encoding <page, obj_idx> and the encoded value has a room + * in least bit(ie, look at obj_to_location). + * We use the bit to synchronize between object access by + * user and migration. + */ +#define HANDLE_PIN_BIT 0 + +/* + * Head in allocated object should have OBJ_ALLOCATED_TAG + * to identify the object was allocated or not. + * It's okay to add the status bit in the least bit because + * header keeps handle which is 4byte-aligned address so we + * have room for two bit at least. + */ +#define OBJ_ALLOCATED_TAG 1 +#define OBJ_TAG_BITS 1 +#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS - OBJ_TAG_BITS) #define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1) #define MAX(a, b) ((a) >= (b) ? (a) : (b)) /* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */ #define ZS_MIN_ALLOC_SIZE \ MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS)) +/* each chunk includes extra space to keep handle */ #define ZS_MAX_ALLOC_SIZE PAGE_SIZE /* @@ -172,6 +168,8 @@ enum fullness_group { enum zs_stat_type { OBJ_ALLOCATED, OBJ_USED, + CLASS_ALMOST_FULL, + CLASS_ALMOST_EMPTY, NR_ZS_STAT_TYPE, }; @@ -216,6 +214,8 @@ struct size_class { /* 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; #ifdef CONFIG_ZSMALLOC_STAT struct zs_size_stat stats; @@ -233,14 +233,24 @@ struct size_class { * This must be power of 2 and less than or equal to ZS_ALIGN */ struct link_free { - /* Handle of next free chunk (encodes <PFN, obj_idx>) */ - void *next; + union { + /* + * Position of next free chunk (encodes <PFN, obj_idx>) + * It's valid for non-allocated object + */ + void *next; + /* + * Handle of allocated object. + */ + unsigned long handle; + }; }; struct zs_pool { char *name; struct size_class **size_class; + struct kmem_cache *handle_cachep; gfp_t flags; /* allocation flags used when growing pool */ atomic_long_t pages_allocated; @@ -267,8 +277,37 @@ struct mapping_area { #endif char *vm_addr; /* address of kmap_atomic()'ed pages */ enum zs_mapmode vm_mm; /* mapping mode */ + bool huge; }; +static int create_handle_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; +} + +static void destroy_handle_cache(struct zs_pool *pool) +{ + kmem_cache_destroy(pool->handle_cachep); +} + +static unsigned long alloc_handle(struct zs_pool *pool) +{ + return (unsigned long)kmem_cache_alloc(pool->handle_cachep, + pool->flags & ~__GFP_HIGHMEM); +} + +static void free_handle(struct zs_pool *pool, unsigned long handle) +{ + kmem_cache_free(pool->handle_cachep, (void *)handle); +} + +static void record_obj(unsigned long handle, unsigned long obj) +{ + *(unsigned long *)handle = obj; +} + /* zpool driver */ #ifdef CONFIG_ZPOOL @@ -346,6 +385,11 @@ 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); @@ -396,9 +440,182 @@ static int get_size_class_index(int size) idx = DIV_ROUND_UP(size - ZS_MIN_ALLOC_SIZE, ZS_SIZE_CLASS_DELTA); - return idx; + return min(zs_size_classes - 1, idx); +} + +#ifdef CONFIG_ZSMALLOC_STAT + +static inline void zs_stat_inc(struct size_class *class, + enum zs_stat_type type, unsigned long cnt) +{ + class->stats.objs[type] += cnt; +} + +static inline void zs_stat_dec(struct size_class *class, + enum zs_stat_type type, unsigned long cnt) +{ + class->stats.objs[type] -= cnt; +} + +static inline unsigned long zs_stat_get(struct size_class *class, + enum zs_stat_type type) +{ + return class->stats.objs[type]; +} + +static int __init zs_stat_init(void) +{ + if (!debugfs_initialized()) + return -ENODEV; + + zs_stat_root = debugfs_create_dir("zsmalloc", NULL); + if (!zs_stat_root) + return -ENOMEM; + + return 0; +} + +static void __exit zs_stat_exit(void) +{ + debugfs_remove_recursive(zs_stat_root); +} + +static int zs_stats_size_show(struct seq_file *s, void *v) +{ + int i; + struct zs_pool *pool = s->private; + struct size_class *class; + int objs_per_zspage; + unsigned long class_almost_full, class_almost_empty; + unsigned long obj_allocated, obj_used, pages_used; + unsigned long total_class_almost_full = 0, total_class_almost_empty = 0; + unsigned long total_objs = 0, total_used_objs = 0, total_pages = 0; + + seq_printf(s, " %5s %5s %11s %12s %13s %10s %10s %16s\n", + "class", "size", "almost_full", "almost_empty", + "obj_allocated", "obj_used", "pages_used", + "pages_per_zspage"); + + for (i = 0; i < zs_size_classes; i++) { + class = pool->size_class[i]; + + if (class->index != i) + continue; + + spin_lock(&class->lock); + class_almost_full = zs_stat_get(class, CLASS_ALMOST_FULL); + class_almost_empty = zs_stat_get(class, CLASS_ALMOST_EMPTY); + obj_allocated = zs_stat_get(class, OBJ_ALLOCATED); + obj_used = zs_stat_get(class, OBJ_USED); + spin_unlock(&class->lock); + + objs_per_zspage = get_maxobj_per_zspage(class->size, + class->pages_per_zspage); + pages_used = obj_allocated / objs_per_zspage * + class->pages_per_zspage; + + seq_printf(s, " %5u %5u %11lu %12lu %13lu %10lu %10lu %16d\n", + i, class->size, class_almost_full, class_almost_empty, + obj_allocated, obj_used, pages_used, + class->pages_per_zspage); + + total_class_almost_full += class_almost_full; + total_class_almost_empty += class_almost_empty; + total_objs += obj_allocated; + total_used_objs += obj_used; + total_pages += pages_used; + } + + seq_puts(s, "\n"); + seq_printf(s, " %5s %5s %11lu %12lu %13lu %10lu %10lu\n", + "Total", "", total_class_almost_full, + total_class_almost_empty, total_objs, + total_used_objs, total_pages); + + return 0; +} + +static int zs_stats_size_open(struct inode *inode, struct file *file) +{ + return single_open(file, zs_stats_size_show, inode->i_private); +} + +static const struct file_operations zs_stat_size_ops = { + .open = zs_stats_size_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int zs_pool_stat_create(char *name, struct zs_pool *pool) +{ + struct dentry *entry; + + if (!zs_stat_root) + return -ENODEV; + + entry = debugfs_create_dir(name, zs_stat_root); + if (!entry) { + pr_warn("debugfs dir <%s> creation failed\n", name); + return -ENOMEM; + } + pool->stat_dentry = entry; + + entry = debugfs_create_file("classes", S_IFREG | S_IRUGO, + pool->stat_dentry, pool, &zs_stat_size_ops); + if (!entry) { + pr_warn("%s: debugfs file entry <%s> creation failed\n", + name, "classes"); + return -ENOMEM; + } + + return 0; +} + +static void zs_pool_stat_destroy(struct zs_pool *pool) +{ + debugfs_remove_recursive(pool->stat_dentry); +} + +#else /* CONFIG_ZSMALLOC_STAT */ + +static inline void zs_stat_inc(struct size_class *class, + enum zs_stat_type type, unsigned long cnt) +{ +} + +static inline void zs_stat_dec(struct size_class *class, + enum zs_stat_type type, unsigned long cnt) +{ +} + +static inline unsigned long zs_stat_get(struct size_class *class, + enum zs_stat_type type) +{ + return 0; +} + +static int __init zs_stat_init(void) +{ + return 0; +} + +static void __exit zs_stat_exit(void) +{ +} + +static inline int zs_pool_stat_create(char *name, struct zs_pool *pool) +{ + return 0; +} + +static inline void zs_pool_stat_destroy(struct zs_pool *pool) +{ } +#endif + + /* * For each size class, zspages are divided into different groups * depending on how "full" they are. This was done so that we could @@ -419,7 +636,7 @@ static enum fullness_group get_fullness_group(struct page *page) fg = ZS_EMPTY; else if (inuse == max_objects) fg = ZS_FULL; - else if (inuse <= max_objects / fullness_threshold_frac) + else if (inuse <= 3 * max_objects / fullness_threshold_frac) fg = ZS_ALMOST_EMPTY; else fg = ZS_ALMOST_FULL; @@ -448,6 +665,8 @@ static void insert_zspage(struct page *page, struct size_class *class, list_add_tail(&page->lru, &(*head)->lru); *head = page; + zs_stat_inc(class, fullness == ZS_ALMOST_EMPTY ? + CLASS_ALMOST_EMPTY : CLASS_ALMOST_FULL, 1); } /* @@ -473,6 +692,8 @@ static void remove_zspage(struct page *page, struct size_class *class, struct page, lru); list_del_init(&page->lru); + zs_stat_dec(class, fullness == ZS_ALMOST_EMPTY ? + CLASS_ALMOST_EMPTY : CLASS_ALMOST_FULL, 1); } /* @@ -484,11 +705,10 @@ static void remove_zspage(struct page *page, struct size_class *class, * page from the freelist of the old fullness group to that of the new * fullness group. */ -static enum fullness_group fix_fullness_group(struct zs_pool *pool, +static enum fullness_group fix_fullness_group(struct size_class *class, struct page *page) { int class_idx; - struct size_class *class; enum fullness_group currfg, newfg; BUG_ON(!is_first_page(page)); @@ -498,7 +718,6 @@ static enum fullness_group fix_fullness_group(struct zs_pool *pool, if (newfg == currfg) goto out; - class = pool->size_class[class_idx]; remove_zspage(page, class, currfg); insert_zspage(page, class, newfg); set_zspage_mapping(page, class_idx, newfg); @@ -512,7 +731,8 @@ out: * to form a zspage for each size class. This is important * to reduce wastage due to unusable space left at end of * each zspage which is given as: - * wastage = Zp - Zp % size_class + * wastage = Zp % class_size + * usage = Zp - wastage * where Zp = zspage size = k * PAGE_SIZE where k = 1, 2, ... * * For example, for size class of 3/8 * PAGE_SIZE, we should @@ -571,35 +791,50 @@ static struct page *get_next_page(struct page *page) /* * Encode <page, obj_idx> as a single handle value. - * On hardware platforms with physical memory starting at 0x0 the pfn - * could be 0 so we ensure that the handle will never be 0 by adjusting the - * encoded obj_idx value before encoding. + * We use the least bit of handle for tagging. */ -static void *obj_location_to_handle(struct page *page, unsigned long obj_idx) +static void *location_to_obj(struct page *page, unsigned long obj_idx) { - unsigned long handle; + unsigned long obj; if (!page) { BUG_ON(obj_idx); return NULL; } - handle = page_to_pfn(page) << OBJ_INDEX_BITS; - handle |= ((obj_idx + 1) & OBJ_INDEX_MASK); + obj = page_to_pfn(page) << OBJ_INDEX_BITS; + obj |= ((obj_idx) & OBJ_INDEX_MASK); + obj <<= OBJ_TAG_BITS; - return (void *)handle; + 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 - * obj_location_to_handle(). + * location_to_obj(). */ -static void obj_handle_to_location(unsigned long handle, struct page **page, +static void obj_to_location(unsigned long obj, struct page **page, unsigned long *obj_idx) { - *page = pfn_to_page(handle >> OBJ_INDEX_BITS); - *obj_idx = (handle & OBJ_INDEX_MASK) - 1; + obj >>= OBJ_TAG_BITS; + *page = pfn_to_page(obj >> OBJ_INDEX_BITS); + *obj_idx = (obj & OBJ_INDEX_MASK); +} + +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) +{ + if (class->huge) { + VM_BUG_ON(!is_first_page(page)); + return *(unsigned long *)page_private(page); + } else + return *(unsigned long *)obj; } static unsigned long obj_idx_to_offset(struct page *page, @@ -613,6 +848,25 @@ static unsigned long obj_idx_to_offset(struct page *page, return off + obj_idx * class_size; } +static inline int trypin_tag(unsigned long handle) +{ + unsigned long *ptr = (unsigned long *)handle; + + return !test_and_set_bit_lock(HANDLE_PIN_BIT, ptr); +} + +static void pin_tag(unsigned long handle) +{ + while (!trypin_tag(handle)); +} + +static void unpin_tag(unsigned long handle) +{ + unsigned long *ptr = (unsigned long *)handle; + + clear_bit_unlock(HANDLE_PIN_BIT, ptr); +} + static void reset_page(struct page *page) { clear_bit(PG_private, &page->flags); @@ -674,7 +928,7 @@ static void init_zspage(struct page *first_page, struct size_class *class) link = (struct link_free *)vaddr + off / sizeof(*link); while ((off += class->size) < PAGE_SIZE) { - link->next = obj_location_to_handle(page, i++); + link->next = location_to_obj(page, i++); link += class->size / sizeof(*link); } @@ -684,7 +938,7 @@ static void init_zspage(struct page *first_page, struct size_class *class) * page (if present) */ next_page = get_next_page(page); - link->next = obj_location_to_handle(next_page, 0); + link->next = location_to_obj(next_page, 0); kunmap_atomic(vaddr); page = next_page; off %= PAGE_SIZE; @@ -738,7 +992,7 @@ static struct page *alloc_zspage(struct size_class *class, gfp_t flags) init_zspage(first_page, class); - first_page->freelist = obj_location_to_handle(first_page, 0); + 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; @@ -860,12 +1114,19 @@ static void __zs_unmap_object(struct mapping_area *area, { int sizes[2]; void *addr; - char *buf = area->vm_buf; + char *buf; /* no write fastpath */ if (area->vm_mm == ZS_MM_RO) goto out; + buf = area->vm_buf; + if (!area->huge) { + buf = buf + ZS_HANDLE_SIZE; + size -= ZS_HANDLE_SIZE; + off += ZS_HANDLE_SIZE; + } + sizes[0] = PAGE_SIZE - off; sizes[1] = size - sizes[0]; @@ -952,11 +1213,6 @@ static void init_zs_size_classes(void) zs_size_classes = nr; } -static unsigned int get_maxobj_per_zspage(int size, int pages_per_zspage) -{ - return pages_per_zspage * PAGE_SIZE / size; -} - static bool can_merge(struct size_class *prev, int size, int pages_per_zspage) { if (prev->pages_per_zspage != pages_per_zspage) @@ -969,166 +1225,13 @@ static bool can_merge(struct size_class *prev, int size, int pages_per_zspage) return true; } -#ifdef CONFIG_ZSMALLOC_STAT - -static inline void zs_stat_inc(struct size_class *class, - enum zs_stat_type type, unsigned long cnt) -{ - class->stats.objs[type] += cnt; -} - -static inline void zs_stat_dec(struct size_class *class, - enum zs_stat_type type, unsigned long cnt) -{ - class->stats.objs[type] -= cnt; -} - -static inline unsigned long zs_stat_get(struct size_class *class, - enum zs_stat_type type) -{ - return class->stats.objs[type]; -} - -static int __init zs_stat_init(void) -{ - if (!debugfs_initialized()) - return -ENODEV; - - zs_stat_root = debugfs_create_dir("zsmalloc", NULL); - if (!zs_stat_root) - return -ENOMEM; - - return 0; -} - -static void __exit zs_stat_exit(void) -{ - debugfs_remove_recursive(zs_stat_root); -} - -static int zs_stats_size_show(struct seq_file *s, void *v) +static bool zspage_full(struct page *page) { - int i; - struct zs_pool *pool = s->private; - struct size_class *class; - int objs_per_zspage; - unsigned long obj_allocated, obj_used, pages_used; - unsigned long total_objs = 0, total_used_objs = 0, total_pages = 0; - - seq_printf(s, " %5s %5s %13s %10s %10s\n", "class", "size", - "obj_allocated", "obj_used", "pages_used"); - - for (i = 0; i < zs_size_classes; i++) { - class = pool->size_class[i]; - - if (class->index != i) - continue; - - spin_lock(&class->lock); - obj_allocated = zs_stat_get(class, OBJ_ALLOCATED); - obj_used = zs_stat_get(class, OBJ_USED); - spin_unlock(&class->lock); - - objs_per_zspage = get_maxobj_per_zspage(class->size, - class->pages_per_zspage); - pages_used = obj_allocated / objs_per_zspage * - class->pages_per_zspage; - - seq_printf(s, " %5u %5u %10lu %10lu %10lu\n", i, - class->size, obj_allocated, obj_used, pages_used); - - total_objs += obj_allocated; - total_used_objs += obj_used; - total_pages += pages_used; - } - - seq_puts(s, "\n"); - seq_printf(s, " %5s %5s %10lu %10lu %10lu\n", "Total", "", - total_objs, total_used_objs, total_pages); - - return 0; -} - -static int zs_stats_size_open(struct inode *inode, struct file *file) -{ - return single_open(file, zs_stats_size_show, inode->i_private); -} - -static const struct file_operations zs_stat_size_ops = { - .open = zs_stats_size_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static int zs_pool_stat_create(char *name, struct zs_pool *pool) -{ - struct dentry *entry; - - if (!zs_stat_root) - return -ENODEV; - - entry = debugfs_create_dir(name, zs_stat_root); - if (!entry) { - pr_warn("debugfs dir <%s> creation failed\n", name); - return -ENOMEM; - } - pool->stat_dentry = entry; - - entry = debugfs_create_file("obj_in_classes", S_IFREG | S_IRUGO, - pool->stat_dentry, pool, &zs_stat_size_ops); - if (!entry) { - pr_warn("%s: debugfs file entry <%s> creation failed\n", - name, "obj_in_classes"); - return -ENOMEM; - } - - return 0; -} - -static void zs_pool_stat_destroy(struct zs_pool *pool) -{ - debugfs_remove_recursive(pool->stat_dentry); -} - -#else /* CONFIG_ZSMALLOC_STAT */ - -static inline void zs_stat_inc(struct size_class *class, - enum zs_stat_type type, unsigned long cnt) -{ -} - -static inline void zs_stat_dec(struct size_class *class, - enum zs_stat_type type, unsigned long cnt) -{ -} - -static inline unsigned long zs_stat_get(struct size_class *class, - enum zs_stat_type type) -{ - return 0; -} - -static int __init zs_stat_init(void) -{ - return 0; -} - -static void __exit zs_stat_exit(void) -{ -} - -static inline int zs_pool_stat_create(char *name, struct zs_pool *pool) -{ - return 0; -} + BUG_ON(!is_first_page(page)); -static inline void zs_pool_stat_destroy(struct zs_pool *pool) -{ + return page->inuse == page->objects; } -#endif - unsigned long zs_get_total_pages(struct zs_pool *pool) { return atomic_long_read(&pool->pages_allocated); @@ -1153,13 +1256,14 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, enum zs_mapmode mm) { struct page *page; - unsigned long obj_idx, off; + unsigned long obj, obj_idx, off; unsigned int class_idx; enum fullness_group fg; struct size_class *class; struct mapping_area *area; struct page *pages[2]; + void *ret; BUG_ON(!handle); @@ -1170,7 +1274,11 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, */ BUG_ON(in_interrupt()); - obj_handle_to_location(handle, &page, &obj_idx); + /* 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); class = pool->size_class[class_idx]; off = obj_idx_to_offset(page, obj_idx, class->size); @@ -1180,7 +1288,8 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, if (off + class->size <= PAGE_SIZE) { /* this object is contained entirely within a page */ area->vm_addr = kmap_atomic(page); - return area->vm_addr + off; + ret = area->vm_addr + off; + goto out; } /* this object spans two pages */ @@ -1188,14 +1297,19 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, pages[1] = get_next_page(page); BUG_ON(!pages[1]); - return __zs_map_object(area, pages, off, class->size); + ret = __zs_map_object(area, pages, off, class->size); +out: + if (!class->huge) + ret += ZS_HANDLE_SIZE; + + return ret; } EXPORT_SYMBOL_GPL(zs_map_object); void zs_unmap_object(struct zs_pool *pool, unsigned long handle) { struct page *page; - unsigned long obj_idx, off; + unsigned long obj, obj_idx, off; unsigned int class_idx; enum fullness_group fg; @@ -1204,7 +1318,8 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) BUG_ON(!handle); - obj_handle_to_location(handle, &page, &obj_idx); + obj = handle_to_obj(handle); + obj_to_location(obj, &page, &obj_idx); get_zspage_mapping(get_first_page(page), &class_idx, &fg); class = pool->size_class[class_idx]; off = obj_idx_to_offset(page, obj_idx, class->size); @@ -1222,9 +1337,42 @@ 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); + 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) +{ + unsigned long obj; + struct link_free *link; + + struct page *m_page; + unsigned long m_objidx, 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); + + vaddr = kmap_atomic(m_page); + link = (struct link_free *)vaddr + m_offset / sizeof(*link); + first_page->freelist = link->next; + if (!class->huge) + /* record handle in the header of allocated chunk */ + link->handle = handle; + else + /* record handle in first_page->private */ + set_page_private(first_page, handle); + kunmap_atomic(vaddr); + first_page->inuse++; + zs_stat_inc(class, OBJ_USED, 1); + + return obj; +} + + /** * zs_malloc - Allocate block of given size from pool. * @pool: pool to allocate from @@ -1236,17 +1384,19 @@ EXPORT_SYMBOL_GPL(zs_unmap_object); */ unsigned long zs_malloc(struct zs_pool *pool, size_t size) { - unsigned long obj; - struct link_free *link; + unsigned long handle, obj; struct size_class *class; - void *vaddr; - - struct page *first_page, *m_page; - unsigned long m_objidx, m_offset; + struct page *first_page; if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE)) return 0; + handle = alloc_handle(pool); + if (!handle) + return 0; + + /* extra space in chunk to keep the handle */ + size += ZS_HANDLE_SIZE; class = pool->size_class[get_size_class_index(size)]; spin_lock(&class->lock); @@ -1255,8 +1405,10 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size) if (!first_page) { spin_unlock(&class->lock); first_page = alloc_zspage(class, pool->flags); - if (unlikely(!first_page)) + 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, @@ -1267,73 +1419,360 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size) class->size, class->pages_per_zspage)); } - obj = (unsigned long)first_page->freelist; - obj_handle_to_location(obj, &m_page, &m_objidx); - m_offset = obj_idx_to_offset(m_page, m_objidx, class->size); - - vaddr = kmap_atomic(m_page); - link = (struct link_free *)vaddr + m_offset / sizeof(*link); - first_page->freelist = link->next; - memset(link, POISON_INUSE, sizeof(*link)); - kunmap_atomic(vaddr); - - first_page->inuse++; - zs_stat_inc(class, OBJ_USED, 1); + obj = obj_malloc(first_page, class, handle); /* Now move the zspage to another fullness group, if required */ - fix_fullness_group(pool, first_page); + fix_fullness_group(class, first_page); + record_obj(handle, obj); spin_unlock(&class->lock); - return obj; + return handle; } EXPORT_SYMBOL_GPL(zs_malloc); -void zs_free(struct zs_pool *pool, unsigned long obj) +static void obj_free(struct zs_pool *pool, struct size_class *class, + unsigned long obj) { struct link_free *link; struct page *first_page, *f_page; unsigned long f_objidx, f_offset; void *vaddr; - int class_idx; - struct size_class *class; enum fullness_group fullness; - if (unlikely(!obj)) - return; + BUG_ON(!obj); - obj_handle_to_location(obj, &f_page, &f_objidx); + obj &= ~OBJ_ALLOCATED_TAG; + obj_to_location(obj, &f_page, &f_objidx); first_page = get_first_page(f_page); get_zspage_mapping(first_page, &class_idx, &fullness); - class = pool->size_class[class_idx]; f_offset = obj_idx_to_offset(f_page, f_objidx, class->size); - spin_lock(&class->lock); + vaddr = kmap_atomic(f_page); /* Insert this object in containing zspage's freelist */ - vaddr = kmap_atomic(f_page); link = (struct link_free *)(vaddr + f_offset); link->next = first_page->freelist; + if (class->huge) + set_page_private(first_page, 0); kunmap_atomic(vaddr); first_page->freelist = (void *)obj; - first_page->inuse--; - fullness = fix_fullness_group(pool, first_page); - zs_stat_dec(class, OBJ_USED, 1); - if (fullness == ZS_EMPTY) +} + +void zs_free(struct zs_pool *pool, unsigned long handle) +{ + struct page *first_page, *f_page; + unsigned long obj, f_objidx; + int class_idx; + struct size_class *class; + enum fullness_group fullness; + + if (unlikely(!handle)) + return; + + pin_tag(handle); + obj = handle_to_obj(handle); + obj_to_location(obj, &f_page, &f_objidx); + first_page = get_first_page(f_page); + + get_zspage_mapping(first_page, &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); + } spin_unlock(&class->lock); + unpin_tag(handle); + + free_handle(pool, handle); +} +EXPORT_SYMBOL_GPL(zs_free); + +static void zs_object_copy(unsigned long src, unsigned long dst, + struct size_class *class) +{ + struct page *s_page, *d_page; + unsigned long s_objidx, d_objidx; + unsigned long s_off, d_off; + void *s_addr, *d_addr; + int s_size, d_size, size; + int written = 0; + + s_size = d_size = class->size; + + 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); + + if (s_off + class->size > PAGE_SIZE) + s_size = PAGE_SIZE - s_off; + + if (d_off + class->size > PAGE_SIZE) + d_size = PAGE_SIZE - d_off; + + s_addr = kmap_atomic(s_page); + d_addr = kmap_atomic(d_page); + + while (1) { + size = min(s_size, d_size); + memcpy(d_addr + d_off, s_addr + s_off, size); + written += size; + + if (written == class->size) + break; + + s_off += size; + s_size -= size; + d_off += size; + d_size -= size; + + if (s_off >= PAGE_SIZE) { + 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; + s_off = 0; + } + + 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; + } + } + + kunmap_atomic(d_addr); + kunmap_atomic(s_addr); +} + +/* + * 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) +{ + unsigned long head; + int offset = 0; + unsigned long handle = 0; + void *addr = kmap_atomic(page); + + if (!is_first_page(page)) + offset = page->index; + offset += class->size * index; + + while (offset < PAGE_SIZE) { + head = obj_to_head(class, page, addr + offset); + if (head & OBJ_ALLOCATED_TAG) { + handle = head & ~OBJ_ALLOCATED_TAG; + if (trypin_tag(handle)) + break; + handle = 0; + } + + offset += class->size; + index++; + } + + kunmap_atomic(addr); + return handle; +} + +struct zs_compact_control { + /* Source page 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; + /* how many of objects are migrated */ + int nr_migrated; +}; + +static int migrate_zspage(struct zs_pool *pool, struct size_class *class, + struct zs_compact_control *cc) +{ + unsigned long used_obj, free_obj; + unsigned long handle; + struct page *s_page = cc->s_page; + struct page *d_page = cc->d_page; + unsigned long index = cc->index; + int nr_migrated = 0; + int ret = 0; + + while (1) { + handle = find_alloced_obj(s_page, index, class); + if (!handle) { + s_page = get_next_page(s_page); + if (!s_page) + break; + index = 0; + continue; + } + + /* Stop if there is no more space */ + if (zspage_full(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(used_obj, free_obj, class); + index++; + record_obj(handle, free_obj); + unpin_tag(handle); + obj_free(pool, class, used_obj); + nr_migrated++; + } + + /* Remember last position in this iteration */ + cc->s_page = s_page; + cc->index = index; + cc->nr_migrated = nr_migrated; + + return ret; +} + +static struct page *alloc_target_page(struct size_class *class) +{ + int i; + struct page *page; + + for (i = 0; i < _ZS_NR_FULLNESS_GROUPS; i++) { + page = class->fullness_list[i]; + if (page) { + remove_zspage(page, class, i); + break; + } + } + + return page; +} + +static void putback_zspage(struct zs_pool *pool, struct size_class *class, + struct page *first_page) +{ + enum fullness_group fullness; + + BUG_ON(!is_first_page(first_page)); + + fullness = get_fullness_group(first_page); + insert_zspage(first_page, class, fullness); + set_zspage_mapping(first_page, 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); + free_zspage(first_page); } } -EXPORT_SYMBOL_GPL(zs_free); + +static struct page *isolate_source_page(struct size_class *class) +{ + struct page *page; + + page = class->fullness_list[ZS_ALMOST_EMPTY]; + if (page) + remove_zspage(page, class, ZS_ALMOST_EMPTY); + + return page; +} + +static unsigned long __zs_compact(struct zs_pool *pool, + struct size_class *class) +{ + int nr_to_migrate; + struct zs_compact_control cc; + struct page *src_page; + struct page *dst_page = NULL; + unsigned long nr_total_migrated = 0; + + spin_lock(&class->lock); + while ((src_page = isolate_source_page(class))) { + + BUG_ON(!is_first_page(src_page)); + + /* The goal is to migrate all live objects in source page */ + nr_to_migrate = src_page->inuse; + cc.index = 0; + cc.s_page = src_page; + + while ((dst_page = alloc_target_page(class))) { + cc.d_page = dst_page; + /* + * If there is no more space in dst_page, try to + * allocate another zspage. + */ + if (!migrate_zspage(pool, class, &cc)) + break; + + putback_zspage(pool, class, dst_page); + nr_total_migrated += cc.nr_migrated; + nr_to_migrate -= cc.nr_migrated; + } + + /* Stop if we couldn't find slot */ + if (dst_page == NULL) + break; + + putback_zspage(pool, class, dst_page); + putback_zspage(pool, class, src_page); + spin_unlock(&class->lock); + nr_total_migrated += cc.nr_migrated; + cond_resched(); + spin_lock(&class->lock); + } + + if (src_page) + putback_zspage(pool, class, src_page); + + spin_unlock(&class->lock); + + return nr_total_migrated; +} + +unsigned long zs_compact(struct zs_pool *pool) +{ + int i; + unsigned long nr_migrated = 0; + struct size_class *class; + + for (i = zs_size_classes - 1; i >= 0; i--) { + class = pool->size_class[i]; + if (!class) + continue; + if (class->index != i) + continue; + nr_migrated += __zs_compact(pool, class); + } + + return nr_migrated; +} +EXPORT_SYMBOL_GPL(zs_compact); /** * zs_create_pool - Creates an allocation pool to work from. @@ -1355,20 +1794,20 @@ struct zs_pool *zs_create_pool(char *name, gfp_t flags) if (!pool) return NULL; - pool->name = kstrdup(name, GFP_KERNEL); - if (!pool->name) { - kfree(pool); - return NULL; - } - pool->size_class = kcalloc(zs_size_classes, sizeof(struct size_class *), GFP_KERNEL); if (!pool->size_class) { - kfree(pool->name); kfree(pool); return NULL; } + pool->name = kstrdup(name, GFP_KERNEL); + if (!pool->name) + goto err; + + if (create_handle_cache(pool)) + goto err; + /* * Iterate reversly, because, size of size_class that we want to use * for merging should be larger or equal to current size. @@ -1406,6 +1845,9 @@ struct zs_pool *zs_create_pool(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; spin_lock_init(&class->lock); pool->size_class[i] = class; @@ -1450,6 +1892,7 @@ void zs_destroy_pool(struct zs_pool *pool) kfree(class); } + destroy_handle_cache(pool); kfree(pool->size_class); kfree(pool->name); kfree(pool); |