diff options
Diffstat (limited to 'mm')
90 files changed, 6185 insertions, 3243 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 02d44e3420f5..a02498c0e13d 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -19,7 +19,7 @@ choice config FLATMEM_MANUAL bool "Flat Memory" - depends on !(ARCH_DISCONTIGMEM_ENABLE || ARCH_SPARSEMEM_ENABLE) || ARCH_FLATMEM_ENABLE + depends on !ARCH_SPARSEMEM_ENABLE || ARCH_FLATMEM_ENABLE help This option is best suited for non-NUMA systems with flat address space. The FLATMEM is the most efficient @@ -32,21 +32,6 @@ config FLATMEM_MANUAL If unsure, choose this option (Flat Memory) over any other. -config DISCONTIGMEM_MANUAL - bool "Discontiguous Memory" - depends on ARCH_DISCONTIGMEM_ENABLE - help - This option provides enhanced support for discontiguous - memory systems, over FLATMEM. These systems have holes - in their physical address spaces, and this option provides - more efficient handling of these holes. - - Although "Discontiguous Memory" is still used by several - architectures, it is considered deprecated in favor of - "Sparse Memory". - - If unsure, choose "Sparse Memory" over this option. - config SPARSEMEM_MANUAL bool "Sparse Memory" depends on ARCH_SPARSEMEM_ENABLE @@ -62,30 +47,13 @@ config SPARSEMEM_MANUAL endchoice -config DISCONTIGMEM - def_bool y - depends on (!SELECT_MEMORY_MODEL && ARCH_DISCONTIGMEM_ENABLE) || DISCONTIGMEM_MANUAL - config SPARSEMEM def_bool y depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL config FLATMEM def_bool y - depends on (!DISCONTIGMEM && !SPARSEMEM) || FLATMEM_MANUAL - -config FLAT_NODE_MEM_MAP - def_bool y - depends on !SPARSEMEM - -# -# Both the NUMA code and DISCONTIGMEM use arrays of pg_data_t's -# to represent different areas of memory. This variable allows -# those dependencies to exist individually. -# -config NEED_MULTIPLE_NODES - def_bool y - depends on DISCONTIGMEM || NUMA + depends on !SPARSEMEM || FLATMEM_MANUAL # # SPARSEMEM_EXTREME (which is the default) does some bootmem @@ -128,6 +96,9 @@ config HAVE_FAST_GUP depends on MMU bool +config HOLES_IN_ZONE + bool + # Don't discard allocated memory used to track "memory" and "reserved" memblocks # after early boot, so it can still be used to test for validity of memory. # Also, memblocks are updated with memory hot(un)plug. @@ -703,6 +674,7 @@ config ZPOOL config ZBUD tristate "Low (Up to 2x) density storage for compressed pages" + depends on ZPOOL help A special purpose allocator for storing compressed pages. It is designed to store up to two compressed pages per physical @@ -789,6 +761,18 @@ config ARCH_HAS_CACHE_LINE_SIZE config ARCH_HAS_PTE_DEVMAP bool +config ARCH_HAS_ZONE_DMA_SET + bool + +config ZONE_DMA + bool "Support DMA zone" if ARCH_HAS_ZONE_DMA_SET + default y if ARM64 || X86 + +config ZONE_DMA32 + bool "Support DMA32 zone" if ARCH_HAS_ZONE_DMA_SET + depends on !X86_32 + default y if ARM64 + config ZONE_DEVICE bool "Device memory (pmem, HMM, etc...) hotplug support" depends on MEMORY_HOTPLUG diff --git a/mm/Makefile b/mm/Makefile index bf71e295e9f6..74b47c354682 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -75,6 +75,7 @@ obj-$(CONFIG_FRONTSWAP) += frontswap.o obj-$(CONFIG_ZSWAP) += zswap.o obj-$(CONFIG_HAS_DMA) += dmapool.o obj-$(CONFIG_HUGETLBFS) += hugetlb.o +obj-$(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP) += hugetlb_vmemmap.o obj-$(CONFIG_NUMA) += mempolicy.o obj-$(CONFIG_SPARSEMEM) += sparse.o obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o @@ -125,3 +126,4 @@ obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o obj-$(CONFIG_PTDUMP_CORE) += ptdump.o obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o obj-$(CONFIG_IO_MAPPING) += io-mapping.o +obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 576220acd686..271f2ca862c8 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -371,12 +371,16 @@ static void wb_exit(struct bdi_writeback *wb) #include <linux/memcontrol.h> /* - * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, and memcg->cgwb_list. - * bdi->cgwb_tree is also RCU protected. + * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, offline_cgwbs and + * memcg->cgwb_list. bdi->cgwb_tree is also RCU protected. */ static DEFINE_SPINLOCK(cgwb_lock); static struct workqueue_struct *cgwb_release_wq; +static LIST_HEAD(offline_cgwbs); +static void cleanup_offline_cgwbs_workfn(struct work_struct *work); +static DECLARE_WORK(cleanup_offline_cgwbs_work, cleanup_offline_cgwbs_workfn); + static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, @@ -395,7 +399,13 @@ static void cgwb_release_workfn(struct work_struct *work) fprop_local_destroy_percpu(&wb->memcg_completions); percpu_ref_exit(&wb->refcnt); + + spin_lock_irq(&cgwb_lock); + list_del(&wb->offline_node); + spin_unlock_irq(&cgwb_lock); + wb_exit(wb); + WARN_ON_ONCE(!list_empty(&wb->b_attached)); kfree_rcu(wb, rcu); } @@ -413,6 +423,7 @@ static void cgwb_kill(struct bdi_writeback *wb) WARN_ON(!radix_tree_delete(&wb->bdi->cgwb_tree, wb->memcg_css->id)); list_del(&wb->memcg_node); list_del(&wb->blkcg_node); + list_add(&wb->offline_node, &offline_cgwbs); percpu_ref_kill(&wb->refcnt); } @@ -472,6 +483,7 @@ static int cgwb_create(struct backing_dev_info *bdi, wb->memcg_css = memcg_css; wb->blkcg_css = blkcg_css; + INIT_LIST_HEAD(&wb->b_attached); INIT_WORK(&wb->release_work, cgwb_release_workfn); set_bit(WB_registered, &wb->state); @@ -633,6 +645,54 @@ static void cgwb_bdi_unregister(struct backing_dev_info *bdi) mutex_unlock(&bdi->cgwb_release_mutex); } +/* + * cleanup_offline_cgwbs_workfn - try to release dying cgwbs + * + * Try to release dying cgwbs by switching attached inodes to the nearest + * living ancestor's writeback. Processed wbs are placed at the end + * of the list to guarantee the forward progress. + */ +static void cleanup_offline_cgwbs_workfn(struct work_struct *work) +{ + struct bdi_writeback *wb; + LIST_HEAD(processed); + + spin_lock_irq(&cgwb_lock); + + while (!list_empty(&offline_cgwbs)) { + wb = list_first_entry(&offline_cgwbs, struct bdi_writeback, + offline_node); + list_move(&wb->offline_node, &processed); + + /* + * If wb is dirty, cleaning up the writeback by switching + * attached inodes will result in an effective removal of any + * bandwidth restrictions, which isn't the goal. Instead, + * it can be postponed until the next time, when all io + * will be likely completed. If in the meantime some inodes + * will get re-dirtied, they should be eventually switched to + * a new cgwb. + */ + if (wb_has_dirty_io(wb)) + continue; + + if (!wb_tryget(wb)) + continue; + + spin_unlock_irq(&cgwb_lock); + while (cleanup_offline_cgwb(wb)) + cond_resched(); + spin_lock_irq(&cgwb_lock); + + wb_put(wb); + } + + if (!list_empty(&processed)) + list_splice_tail(&processed, &offline_cgwbs); + + spin_unlock_irq(&cgwb_lock); +} + /** * wb_memcg_offline - kill all wb's associated with a memcg being offlined * @memcg: memcg being offlined @@ -649,6 +709,8 @@ void wb_memcg_offline(struct mem_cgroup *memcg) cgwb_kill(wb); memcg_cgwb_list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); + + queue_work(system_unbound_wq, &cleanup_offline_cgwbs_work); } /** diff --git a/mm/bootmem_info.c b/mm/bootmem_info.c new file mode 100644 index 000000000000..5b152dba7344 --- /dev/null +++ b/mm/bootmem_info.c @@ -0,0 +1,127 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Bootmem core functions. + * + * Copyright (c) 2020, Bytedance. + * + * Author: Muchun Song <songmuchun@bytedance.com> + * + */ +#include <linux/mm.h> +#include <linux/compiler.h> +#include <linux/memblock.h> +#include <linux/bootmem_info.h> +#include <linux/memory_hotplug.h> + +void get_page_bootmem(unsigned long info, struct page *page, unsigned long type) +{ + page->freelist = (void *)type; + SetPagePrivate(page); + set_page_private(page, info); + page_ref_inc(page); +} + +void put_page_bootmem(struct page *page) +{ + unsigned long type; + + type = (unsigned long) page->freelist; + BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE || + type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE); + + if (page_ref_dec_return(page) == 1) { + page->freelist = NULL; + ClearPagePrivate(page); + set_page_private(page, 0); + INIT_LIST_HEAD(&page->lru); + free_reserved_page(page); + } +} + +#ifndef CONFIG_SPARSEMEM_VMEMMAP +static void register_page_bootmem_info_section(unsigned long start_pfn) +{ + unsigned long mapsize, section_nr, i; + struct mem_section *ms; + struct page *page, *memmap; + struct mem_section_usage *usage; + + section_nr = pfn_to_section_nr(start_pfn); + ms = __nr_to_section(section_nr); + + /* Get section's memmap address */ + memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); + + /* + * Get page for the memmap's phys address + * XXX: need more consideration for sparse_vmemmap... + */ + page = virt_to_page(memmap); + mapsize = sizeof(struct page) * PAGES_PER_SECTION; + mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT; + + /* remember memmap's page */ + for (i = 0; i < mapsize; i++, page++) + get_page_bootmem(section_nr, page, SECTION_INFO); + + usage = ms->usage; + page = virt_to_page(usage); + + mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT; + + for (i = 0; i < mapsize; i++, page++) + get_page_bootmem(section_nr, page, MIX_SECTION_INFO); + +} +#else /* CONFIG_SPARSEMEM_VMEMMAP */ +static void register_page_bootmem_info_section(unsigned long start_pfn) +{ + unsigned long mapsize, section_nr, i; + struct mem_section *ms; + struct page *page, *memmap; + struct mem_section_usage *usage; + + section_nr = pfn_to_section_nr(start_pfn); + ms = __nr_to_section(section_nr); + + memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); + + register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION); + + usage = ms->usage; + page = virt_to_page(usage); + + mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT; + + for (i = 0; i < mapsize; i++, page++) + get_page_bootmem(section_nr, page, MIX_SECTION_INFO); +} +#endif /* !CONFIG_SPARSEMEM_VMEMMAP */ + +void __init register_page_bootmem_info_node(struct pglist_data *pgdat) +{ + unsigned long i, pfn, end_pfn, nr_pages; + int node = pgdat->node_id; + struct page *page; + + nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT; + page = virt_to_page(pgdat); + + for (i = 0; i < nr_pages; i++, page++) + get_page_bootmem(node, page, NODE_INFO); + + pfn = pgdat->node_start_pfn; + end_pfn = pgdat_end_pfn(pgdat); + + /* register section info */ + for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { + /* + * Some platforms can assign the same pfn to multiple nodes - on + * node0 as well as nodeN. To avoid registering a pfn against + * multiple nodes we check that this pfn does not already + * reside in some other nodes. + */ + if (pfn_valid(pfn) && (early_pfn_to_nid(pfn) == node)) + register_page_bootmem_info_section(pfn); + } +} diff --git a/mm/compaction.c b/mm/compaction.c index 84fde270ae74..621508e0ecd5 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1028,7 +1028,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (!TestClearPageLRU(page)) goto isolate_fail_put; - lruvec = mem_cgroup_page_lruvec(page, pgdat); + lruvec = mem_cgroup_page_lruvec(page); /* If we already hold the lock, we can skip some rechecking */ if (lruvec != locked) { @@ -1297,8 +1297,7 @@ move_freelist_head(struct list_head *freelist, struct page *freepage) if (!list_is_last(freelist, &freepage->lru)) { list_cut_before(&sublist, freelist, &freepage->lru); - if (!list_empty(&sublist)) - list_splice_tail(&sublist, freelist); + list_splice_tail(&sublist, freelist); } } @@ -1315,8 +1314,7 @@ move_freelist_tail(struct list_head *freelist, struct page *freepage) if (!list_is_first(freelist, &freepage->lru)) { list_cut_position(&sublist, freelist, &freepage->lru); - if (!list_empty(&sublist)) - list_splice_tail(&sublist, freelist); + list_splice_tail(&sublist, freelist); } } @@ -1380,7 +1378,7 @@ static int next_search_order(struct compact_control *cc, int order) static unsigned long fast_isolate_freepages(struct compact_control *cc) { - unsigned int limit = min(1U, freelist_scan_limit(cc) >> 1); + unsigned int limit = max(1U, freelist_scan_limit(cc) >> 1); unsigned int nr_scanned = 0; unsigned long low_pfn, min_pfn, highest = 0; unsigned long nr_isolated = 0; @@ -1492,11 +1490,11 @@ fast_isolate_freepages(struct compact_control *cc) spin_unlock_irqrestore(&cc->zone->lock, flags); /* - * Smaller scan on next order so the total scan ig related + * Smaller scan on next order so the total scan is related * to freelist_scan_limit. */ if (order_scanned >= limit) - limit = min(1U, limit >> 1); + limit = max(1U, limit >> 1); } if (!page) { @@ -1955,7 +1953,7 @@ static inline bool is_via_compact_memory(int order) static bool kswapd_is_running(pg_data_t *pgdat) { - return pgdat->kswapd && (pgdat->kswapd->state == TASK_RUNNING); + return pgdat->kswapd && task_is_running(pgdat->kswapd); } /* @@ -2722,9 +2720,9 @@ int sysctl_compaction_handler(struct ctl_table *table, int write, } #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) -static ssize_t sysfs_compact_node(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t compact_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { int nid = dev->id; @@ -2737,7 +2735,7 @@ static ssize_t sysfs_compact_node(struct device *dev, return count; } -static DEVICE_ATTR(compact, 0200, NULL, sysfs_compact_node); +static DEVICE_ATTR_WO(compact); int compaction_register_node(struct node *node) { diff --git a/mm/debug.c b/mm/debug.c index 0bdda8407f71..e73fe0a8ec3d 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -42,11 +42,10 @@ const struct trace_print_flags vmaflag_names[] = { {0, NULL} }; -void __dump_page(struct page *page, const char *reason) +static void __dump_page(struct page *page) { struct page *head = compound_head(page); struct address_space *mapping; - bool page_poisoned = PagePoisoned(page); bool compound = PageCompound(page); /* * Accessing the pageblock without the zone lock. It could change to @@ -58,16 +57,6 @@ void __dump_page(struct page *page, const char *reason) int mapcount; char *type = ""; - /* - * If struct page is poisoned don't access Page*() functions as that - * leads to recursive loop. Page*() check for poisoned pages, and calls - * dump_page() when detected. - */ - if (page_poisoned) { - pr_warn("page:%px is uninitialized and poisoned", page); - goto hex_only; - } - if (page < head || (page >= head + MAX_ORDER_NR_PAGES)) { /* * Corrupt page, so we cannot call page_mapping. Instead, do a @@ -173,8 +162,6 @@ out_mapping: pr_warn("%sflags: %#lx(%pGp)%s\n", type, head->flags, &head->flags, page_cma ? " CMA" : ""); - -hex_only: print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32, sizeof(unsigned long), page, sizeof(struct page), false); @@ -182,14 +169,16 @@ hex_only: print_hex_dump(KERN_WARNING, "head: ", DUMP_PREFIX_NONE, 32, sizeof(unsigned long), head, sizeof(struct page), false); - - if (reason) - pr_warn("page dumped because: %s\n", reason); } void dump_page(struct page *page, const char *reason) { - __dump_page(page, reason); + if (PagePoisoned(page)) + pr_warn("page:%p is uninitialized and poisoned", page); + else + __dump_page(page); + if (reason) + pr_warn("page dumped because: %s\n", reason); dump_page_owner(page); } EXPORT_SYMBOL(dump_page); diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index 05efe98a9ac2..1c922691aa61 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -91,7 +91,7 @@ static void __init pte_advanced_tests(struct mm_struct *mm, unsigned long pfn, unsigned long vaddr, pgprot_t prot) { - pte_t pte = pfn_pte(pfn, prot); + pte_t pte; /* * Architectures optimize set_pte_at by avoiding TLB flush. @@ -146,13 +146,14 @@ static void __init pte_savedwrite_tests(unsigned long pfn, pgprot_t prot) static void __init pmd_basic_tests(unsigned long pfn, int idx) { pgprot_t prot = protection_map[idx]; - pmd_t pmd = pfn_pmd(pfn, prot); unsigned long val = idx, *ptr = &val; + pmd_t pmd; if (!has_transparent_hugepage()) return; pr_debug("Validating PMD basic (%pGv)\n", ptr); + pmd = pfn_pmd(pfn, prot); /* * This test needs to be executed after the given page table entry @@ -185,14 +186,14 @@ static void __init pmd_advanced_tests(struct mm_struct *mm, unsigned long pfn, unsigned long vaddr, pgprot_t prot, pgtable_t pgtable) { - pmd_t pmd = pfn_pmd(pfn, prot); + pmd_t pmd; if (!has_transparent_hugepage()) return; pr_debug("Validating PMD advanced\n"); /* Align the address wrt HPAGE_PMD_SIZE */ - vaddr = (vaddr & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE; + vaddr &= HPAGE_PMD_MASK; pgtable_trans_huge_deposit(mm, pmdp, pgtable); @@ -232,9 +233,14 @@ static void __init pmd_advanced_tests(struct mm_struct *mm, static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot) { - pmd_t pmd = pfn_pmd(pfn, prot); + pmd_t pmd; + + if (!has_transparent_hugepage()) + return; pr_debug("Validating PMD leaf\n"); + pmd = pfn_pmd(pfn, prot); + /* * PMD based THP is a leaf entry. */ @@ -242,37 +248,18 @@ static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot) WARN_ON(!pmd_leaf(pmd)); } -#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP -static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) +static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot) { pmd_t pmd; - if (!arch_vmap_pmd_supported(prot)) + if (!IS_ENABLED(CONFIG_NUMA_BALANCING)) return; - pr_debug("Validating PMD huge\n"); - /* - * X86 defined pmd_set_huge() verifies that the given - * PMD is not a populated non-leaf entry. - */ - WRITE_ONCE(*pmdp, __pmd(0)); - WARN_ON(!pmd_set_huge(pmdp, __pfn_to_phys(pfn), prot)); - WARN_ON(!pmd_clear_huge(pmdp)); - pmd = READ_ONCE(*pmdp); - WARN_ON(!pmd_none(pmd)); -} -#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */ -static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) { } -#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ - -static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot) -{ - pmd_t pmd = pfn_pmd(pfn, prot); - - if (!IS_ENABLED(CONFIG_NUMA_BALANCING)) + if (!has_transparent_hugepage()) return; pr_debug("Validating PMD saved write\n"); + pmd = pfn_pmd(pfn, prot); WARN_ON(!pmd_savedwrite(pmd_mk_savedwrite(pmd_clear_savedwrite(pmd)))); WARN_ON(pmd_savedwrite(pmd_clear_savedwrite(pmd_mk_savedwrite(pmd)))); } @@ -281,13 +268,14 @@ static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot) static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) { pgprot_t prot = protection_map[idx]; - pud_t pud = pfn_pud(pfn, prot); unsigned long val = idx, *ptr = &val; + pud_t pud; if (!has_transparent_hugepage()) return; pr_debug("Validating PUD basic (%pGv)\n", ptr); + pud = pfn_pud(pfn, prot); /* * This test needs to be executed after the given page table entry @@ -323,15 +311,16 @@ static void __init pud_advanced_tests(struct mm_struct *mm, unsigned long pfn, unsigned long vaddr, pgprot_t prot) { - pud_t pud = pfn_pud(pfn, prot); + pud_t pud; if (!has_transparent_hugepage()) return; pr_debug("Validating PUD advanced\n"); /* Align the address wrt HPAGE_PUD_SIZE */ - vaddr = (vaddr & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE; + vaddr &= HPAGE_PUD_MASK; + pud = pfn_pud(pfn, prot); set_pud_at(mm, vaddr, pudp, pud); pudp_set_wrprotect(mm, vaddr, pudp); pud = READ_ONCE(*pudp); @@ -370,39 +359,19 @@ static void __init pud_advanced_tests(struct mm_struct *mm, static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) { - pud_t pud = pfn_pud(pfn, prot); + pud_t pud; + + if (!has_transparent_hugepage()) + return; pr_debug("Validating PUD leaf\n"); + pud = pfn_pud(pfn, prot); /* * PUD based THP is a leaf entry. */ pud = pud_mkhuge(pud); WARN_ON(!pud_leaf(pud)); } - -#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP -static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) -{ - pud_t pud; - - if (!arch_vmap_pud_supported(prot)) - return; - - pr_debug("Validating PUD huge\n"); - /* - * X86 defined pud_set_huge() verifies that the given - * PUD is not a populated non-leaf entry. - */ - WRITE_ONCE(*pudp, __pud(0)); - WARN_ON(!pud_set_huge(pudp, __pfn_to_phys(pfn), prot)); - WARN_ON(!pud_clear_huge(pudp)); - pud = READ_ONCE(*pudp); - WARN_ON(!pud_none(pud)); -} -#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ -static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) { } -#endif /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ - #else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) { } static void __init pud_advanced_tests(struct mm_struct *mm, @@ -412,9 +381,6 @@ static void __init pud_advanced_tests(struct mm_struct *mm, { } static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) { } -static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) -{ -} #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ #else /* !CONFIG_TRANSPARENT_HUGEPAGE */ static void __init pmd_basic_tests(unsigned long pfn, int idx) { } @@ -433,14 +399,51 @@ static void __init pud_advanced_tests(struct mm_struct *mm, } static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot) { } static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot) { } +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) { + pmd_t pmd; + + if (!arch_vmap_pmd_supported(prot)) + return; + + pr_debug("Validating PMD huge\n"); + /* + * X86 defined pmd_set_huge() verifies that the given + * PMD is not a populated non-leaf entry. + */ + WRITE_ONCE(*pmdp, __pmd(0)); + WARN_ON(!pmd_set_huge(pmdp, __pfn_to_phys(pfn), prot)); + WARN_ON(!pmd_clear_huge(pmdp)); + pmd = READ_ONCE(*pmdp); + WARN_ON(!pmd_none(pmd)); } + static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) { + pud_t pud; + + if (!arch_vmap_pud_supported(prot)) + return; + + pr_debug("Validating PUD huge\n"); + /* + * X86 defined pud_set_huge() verifies that the given + * PUD is not a populated non-leaf entry. + */ + WRITE_ONCE(*pudp, __pud(0)); + WARN_ON(!pud_set_huge(pudp, __pfn_to_phys(pfn), prot)); + WARN_ON(!pud_clear_huge(pudp)); + pud = READ_ONCE(*pudp); + WARN_ON(!pud_none(pud)); } -static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot) { } -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ +static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) { } +static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) { } +#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ static void __init p4d_basic_tests(unsigned long pfn, pgprot_t prot) { @@ -654,12 +657,16 @@ static void __init pte_protnone_tests(unsigned long pfn, pgprot_t prot) #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void __init pmd_protnone_tests(unsigned long pfn, pgprot_t prot) { - pmd_t pmd = pmd_mkhuge(pfn_pmd(pfn, prot)); + pmd_t pmd; if (!IS_ENABLED(CONFIG_NUMA_BALANCING)) return; + if (!has_transparent_hugepage()) + return; + pr_debug("Validating PMD protnone\n"); + pmd = pmd_mkhuge(pfn_pmd(pfn, prot)); WARN_ON(!pmd_protnone(pmd)); WARN_ON(!pmd_present(pmd)); } @@ -679,18 +686,26 @@ static void __init pte_devmap_tests(unsigned long pfn, pgprot_t prot) #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void __init pmd_devmap_tests(unsigned long pfn, pgprot_t prot) { - pmd_t pmd = pfn_pmd(pfn, prot); + pmd_t pmd; + + if (!has_transparent_hugepage()) + return; pr_debug("Validating PMD devmap\n"); + pmd = pfn_pmd(pfn, prot); WARN_ON(!pmd_devmap(pmd_mkdevmap(pmd))); } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static void __init pud_devmap_tests(unsigned long pfn, pgprot_t prot) { - pud_t pud = pfn_pud(pfn, prot); + pud_t pud; + + if (!has_transparent_hugepage()) + return; pr_debug("Validating PUD devmap\n"); + pud = pfn_pud(pfn, prot); WARN_ON(!pud_devmap(pud_mkdevmap(pud))); } #else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ @@ -733,34 +748,42 @@ static void __init pte_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot) #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void __init pmd_soft_dirty_tests(unsigned long pfn, pgprot_t prot) { - pmd_t pmd = pfn_pmd(pfn, prot); + pmd_t pmd; if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) return; + if (!has_transparent_hugepage()) + return; + pr_debug("Validating PMD soft dirty\n"); + pmd = pfn_pmd(pfn, prot); WARN_ON(!pmd_soft_dirty(pmd_mksoft_dirty(pmd))); WARN_ON(pmd_soft_dirty(pmd_clear_soft_dirty(pmd))); } static void __init pmd_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot) { - pmd_t pmd = pfn_pmd(pfn, prot); + pmd_t pmd; if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) || !IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION)) return; + if (!has_transparent_hugepage()) + return; + pr_debug("Validating PMD swap soft dirty\n"); + pmd = pfn_pmd(pfn, prot); WARN_ON(!pmd_swp_soft_dirty(pmd_swp_mksoft_dirty(pmd))); WARN_ON(pmd_swp_soft_dirty(pmd_swp_clear_soft_dirty(pmd))); } -#else /* !CONFIG_ARCH_HAS_PTE_DEVMAP */ +#else /* !CONFIG_TRANSPARENT_HUGEPAGE */ static void __init pmd_soft_dirty_tests(unsigned long pfn, pgprot_t prot) { } static void __init pmd_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot) { } -#endif /* CONFIG_ARCH_HAS_PTE_DEVMAP */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static void __init pte_swap_tests(unsigned long pfn, pgprot_t prot) { @@ -780,6 +803,9 @@ static void __init pmd_swap_tests(unsigned long pfn, pgprot_t prot) swp_entry_t swp; pmd_t pmd; + if (!has_transparent_hugepage()) + return; + pr_debug("Validating PMD swap\n"); pmd = pfn_pmd(pfn, prot); swp = __pmd_to_swp_entry(pmd); @@ -817,17 +843,17 @@ static void __init swap_migration_tests(void) * locked, otherwise it stumbles upon a BUG_ON(). */ __SetPageLocked(page); - swp = make_migration_entry(page, 1); + swp = make_writable_migration_entry(page_to_pfn(page)); WARN_ON(!is_migration_entry(swp)); - WARN_ON(!is_write_migration_entry(swp)); + WARN_ON(!is_writable_migration_entry(swp)); - make_migration_entry_read(&swp); + swp = make_readable_migration_entry(swp_offset(swp)); WARN_ON(!is_migration_entry(swp)); - WARN_ON(is_write_migration_entry(swp)); + WARN_ON(is_writable_migration_entry(swp)); - swp = make_migration_entry(page, 0); + swp = make_readable_migration_entry(page_to_pfn(page)); WARN_ON(!is_migration_entry(swp)); - WARN_ON(is_write_migration_entry(swp)); + WARN_ON(is_writable_migration_entry(swp)); __ClearPageLocked(page); __free_page(page); } diff --git a/mm/dmapool.c b/mm/dmapool.c index 16483f86360e..64b537b3ccb0 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -62,8 +62,7 @@ struct dma_page { /* cacheable header for 'allocation' bytes */ static DEFINE_MUTEX(pools_lock); static DEFINE_MUTEX(pools_reg_lock); -static ssize_t -show_pools(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t pools_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned temp; unsigned size; @@ -103,7 +102,7 @@ show_pools(struct device *dev, struct device_attribute *attr, char *buf) return PAGE_SIZE - size; } -static DEVICE_ATTR(pools, 0444, show_pools, NULL); +static DEVICE_ATTR_RO(pools); /** * dma_pool_create - Creates a pool of consistent memory blocks, for dma. diff --git a/mm/filemap.c b/mm/filemap.c index 66f7e9fdfbc4..d1458ecf2f51 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -872,7 +872,7 @@ noinline int __add_to_page_cache_locked(struct page *page, page->index = offset; if (!huge) { - error = mem_cgroup_charge(page, current->mm, gfp); + error = mem_cgroup_charge(page, NULL, gfp); if (error) goto error; charged = true; @@ -3642,10 +3642,6 @@ again: * Otherwise there's a nasty deadlock on copying from the * same page as we're writing to, without it being marked * up-to-date. - * - * Not only is this an optimisation, but it is also required - * to check that the address is actually valid, when atomic - * usercopies are used, below. */ if (unlikely(iov_iter_fault_in_readable(i, bytes))) { status = -EFAULT; @@ -3665,33 +3661,31 @@ again: if (mapping_writably_mapped(mapping)) flush_dcache_page(page); - copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); + copied = copy_page_from_iter_atomic(page, offset, bytes, i); flush_dcache_page(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); - if (unlikely(status < 0)) - break; - copied = status; - + if (unlikely(status != copied)) { + iov_iter_revert(i, copied - max(status, 0L)); + if (unlikely(status < 0)) + break; + } cond_resched(); - iov_iter_advance(i, copied); - if (unlikely(copied == 0)) { + if (unlikely(status == 0)) { /* - * If we were unable to copy any data at all, we must - * fall back to a single segment length write. - * - * If we didn't fallback here, we could livelock - * because not all segments in the iov can be copied at - * once without a pagefault. + * A short copy made ->write_end() reject the + * thing entirely. Might be memory poisoning + * halfway through, might be a race with munmap, + * might be severe memory pressure. */ - bytes = min_t(unsigned long, PAGE_SIZE - offset, - iov_iter_single_seg_count(i)); + if (copied) + bytes = copied; goto again; } - pos += copied; - written += copied; + pos += status; + written += status; balance_dirty_pages_ratelimited(mapping); } while (iov_iter_count(i)); @@ -44,6 +44,23 @@ static void hpage_pincount_sub(struct page *page, int refs) atomic_sub(refs, compound_pincount_ptr(page)); } +/* Equivalent to calling put_page() @refs times. */ +static void put_page_refs(struct page *page, int refs) +{ +#ifdef CONFIG_DEBUG_VM + if (VM_WARN_ON_ONCE_PAGE(page_ref_count(page) < refs, page)) + return; +#endif + + /* + * Calling put_page() for each ref is unnecessarily slow. Only the last + * ref needs a put_page(). + */ + if (refs > 1) + page_ref_sub(page, refs - 1); + put_page(page); +} + /* * Return the compound head page with ref appropriately incremented, * or NULL if that failed. @@ -56,6 +73,21 @@ static inline struct page *try_get_compound_head(struct page *page, int refs) return NULL; if (unlikely(!page_cache_add_speculative(head, refs))) return NULL; + + /* + * At this point we have a stable reference to the head page; but it + * could be that between the compound_head() lookup and the refcount + * increment, the compound page was split, in which case we'd end up + * holding a reference on a page that has nothing to do with the page + * we were given anymore. + * So now that the head page is stable, recheck that the pages still + * belong together. + */ + if (unlikely(compound_head(page) != head)) { + put_page_refs(head, refs); + return NULL; + } + return head; } @@ -96,6 +128,14 @@ __maybe_unused struct page *try_grab_compound_head(struct page *page, return NULL; /* + * CAUTION: Don't use compound_head() on the page before this + * point, the result won't be stable. + */ + page = try_get_compound_head(page, refs); + if (!page) + return NULL; + + /* * When pinning a compound page of order > 1 (which is what * hpage_pincount_available() checks for), use an exact count to * track it, via hpage_pincount_add/_sub(). @@ -103,15 +143,10 @@ __maybe_unused struct page *try_grab_compound_head(struct page *page, * However, be sure to *also* increment the normal page refcount * field at least once, so that the page really is pinned. */ - if (!hpage_pincount_available(page)) - refs *= GUP_PIN_COUNTING_BIAS; - - page = try_get_compound_head(page, refs); - if (!page) - return NULL; - if (hpage_pincount_available(page)) hpage_pincount_add(page, refs); + else + page_ref_add(page, refs * (GUP_PIN_COUNTING_BIAS - 1)); mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED, orig_refs); @@ -135,14 +170,7 @@ static void put_compound_head(struct page *page, int refs, unsigned int flags) refs *= GUP_PIN_COUNTING_BIAS; } - VM_BUG_ON_PAGE(page_ref_count(page) < refs, page); - /* - * Calling put_page() for each ref is unnecessarily slow. Only the last - * ref needs a put_page(). - */ - if (refs > 1) - page_ref_sub(page, refs - 1); - put_page(page); + put_page_refs(page, refs); } /** @@ -392,6 +420,17 @@ void unpin_user_pages(struct page **pages, unsigned long npages) } EXPORT_SYMBOL(unpin_user_pages); +/* + * Set the MMF_HAS_PINNED if not set yet; after set it'll be there for the mm's + * lifecycle. Avoid setting the bit unless necessary, or it might cause write + * cache bouncing on large SMP machines for concurrent pinned gups. + */ +static inline void mm_set_has_pinned_flag(unsigned long *mm_flags) +{ + if (!test_bit(MMF_HAS_PINNED, mm_flags)) + set_bit(MMF_HAS_PINNED, mm_flags); +} + #ifdef CONFIG_MMU static struct page *no_page_table(struct vm_area_struct *vma, unsigned int flags) @@ -1293,7 +1332,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, } if (flags & FOLL_PIN) - atomic_set(&mm->has_pinned, 1); + mm_set_has_pinned_flag(&mm->flags); /* * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior @@ -1462,6 +1501,64 @@ long populate_vma_page_range(struct vm_area_struct *vma, } /* + * faultin_vma_page_range() - populate (prefault) page tables inside the + * given VMA range readable/writable + * + * This takes care of mlocking the pages, too, if VM_LOCKED is set. + * + * @vma: target vma + * @start: start address + * @end: end address + * @write: whether to prefault readable or writable + * @locked: whether the mmap_lock is still held + * + * Returns either number of processed pages in the vma, or a negative error + * code on error (see __get_user_pages()). + * + * vma->vm_mm->mmap_lock must be held. The range must be page-aligned and + * covered by the VMA. + * + * If @locked is NULL, it may be held for read or write and will be unperturbed. + * + * If @locked is non-NULL, it must held for read only and may be released. If + * it's released, *@locked will be set to 0. + */ +long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end, bool write, int *locked) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned long nr_pages = (end - start) / PAGE_SIZE; + int gup_flags; + + VM_BUG_ON(!PAGE_ALIGNED(start)); + VM_BUG_ON(!PAGE_ALIGNED(end)); + VM_BUG_ON_VMA(start < vma->vm_start, vma); + VM_BUG_ON_VMA(end > vma->vm_end, vma); + mmap_assert_locked(mm); + + /* + * FOLL_TOUCH: Mark page accessed and thereby young; will also mark + * the page dirty with FOLL_WRITE -- which doesn't make a + * difference with !FOLL_FORCE, because the page is writable + * in the page table. + * FOLL_HWPOISON: Return -EHWPOISON instead of -EFAULT when we hit + * a poisoned page. + * FOLL_POPULATE: Always populate memory with VM_LOCKONFAULT. + * !FOLL_FORCE: Require proper access permissions. + */ + gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK | FOLL_HWPOISON; + if (write) + gup_flags |= FOLL_WRITE; + + /* + * See check_vma_flags(): Will return -EFAULT on incompatible mappings + * or with insufficient permissions. + */ + return __get_user_pages(mm, start, nr_pages, gup_flags, + NULL, NULL, locked); +} + +/* * __mm_populate - populate and/or mlock pages within a range of address space. * * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap @@ -1593,10 +1690,6 @@ struct page *get_dump_page(unsigned long addr) FOLL_FORCE | FOLL_DUMP | FOLL_GET); if (locked) mmap_read_unlock(mm); - - if (ret == 1 && is_page_poisoned(page)) - return NULL; - return (ret == 1) ? page : NULL; } #endif /* CONFIG_ELF_CORE */ @@ -2618,7 +2711,7 @@ static int internal_get_user_pages_fast(unsigned long start, return -EINVAL; if (gup_flags & FOLL_PIN) - atomic_set(¤t->mm->has_pinned, 1); + mm_set_has_pinned_flag(¤t->mm->flags); if (!(gup_flags & FOLL_FAST_ONLY)) might_lock_read(¤t->mm->mmap_lock); @@ -26,6 +26,8 @@ #include <linux/mmu_notifier.h> #include <linux/memory_hotplug.h> +#include "internal.h" + struct hmm_vma_walk { struct hmm_range *range; unsigned long last; @@ -214,7 +216,7 @@ static inline bool hmm_is_device_private_entry(struct hmm_range *range, swp_entry_t entry) { return is_device_private_entry(entry) && - device_private_entry_to_page(entry)->pgmap->owner == + pfn_swap_entry_to_page(entry)->pgmap->owner == range->dev_private_owner; } @@ -255,10 +257,9 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, */ if (hmm_is_device_private_entry(range, entry)) { cpu_flags = HMM_PFN_VALID; - if (is_write_device_private_entry(entry)) + if (is_writable_device_private_entry(entry)) cpu_flags |= HMM_PFN_WRITE; - *hmm_pfn = device_private_entry_to_pfn(entry) | - cpu_flags; + *hmm_pfn = swp_offset(entry) | cpu_flags; return 0; } @@ -272,6 +273,9 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, if (!non_swap_entry(entry)) goto fault; + if (is_device_exclusive_entry(entry)) + goto fault; + if (is_migration_entry(entry)) { pte_unmap(ptep); hmm_vma_walk->last = addr; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 63ed6b25deaa..8b731d53e9f4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -62,8 +62,16 @@ static struct shrinker deferred_split_shrinker; static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; +unsigned long huge_zero_pfn __read_mostly = ~0UL; -bool transparent_hugepage_enabled(struct vm_area_struct *vma) +static inline bool file_thp_enabled(struct vm_area_struct *vma) +{ + return transhuge_vma_enabled(vma, vma->vm_flags) && vma->vm_file && + !inode_is_open_for_write(vma->vm_file->f_inode) && + (vma->vm_flags & VM_EXEC); +} + +bool transparent_hugepage_active(struct vm_area_struct *vma) { /* The addr is used to check if the vma size fits */ unsigned long addr = (vma->vm_end & HPAGE_PMD_MASK) - HPAGE_PMD_SIZE; @@ -74,6 +82,8 @@ bool transparent_hugepage_enabled(struct vm_area_struct *vma) return __transparent_hugepage_enabled(vma); if (vma_is_shmem(vma)) return shmem_huge_enabled(vma); + if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) + return file_thp_enabled(vma); return false; } @@ -98,6 +108,7 @@ retry: __free_pages(zero_page, compound_order(zero_page)); goto retry; } + WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page)); /* We take additional reference here. It will be put back by shrinker */ atomic_set(&huge_zero_refcount, 2); @@ -147,6 +158,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { struct page *zero_page = xchg(&huge_zero_page, NULL); BUG_ON(zero_page == NULL); + WRITE_ONCE(huge_zero_pfn, ~0UL); __free_pages(zero_page, compound_order(zero_page)); return HPAGE_PMD_NR; } @@ -1014,7 +1026,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, - struct vm_area_struct *vma) + struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { spinlock_t *dst_ptl, *src_ptl; struct page *src_page; @@ -1023,7 +1035,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, int ret = -ENOMEM; /* Skip if can be re-fill on fault */ - if (!vma_is_anonymous(vma)) + if (!vma_is_anonymous(dst_vma)) return 0; pgtable = pte_alloc_one(dst_mm); @@ -1037,29 +1049,26 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, ret = -EAGAIN; pmd = *src_pmd; - /* - * Make sure the _PAGE_UFFD_WP bit is cleared if the new VMA - * does not have the VM_UFFD_WP, which means that the uffd - * fork event is not enabled. - */ - if (!(vma->vm_flags & VM_UFFD_WP)) - pmd = pmd_clear_uffd_wp(pmd); - #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION if (unlikely(is_swap_pmd(pmd))) { swp_entry_t entry = pmd_to_swp_entry(pmd); VM_BUG_ON(!is_pmd_migration_entry(pmd)); - if (is_write_migration_entry(entry)) { - make_migration_entry_read(&entry); + if (is_writable_migration_entry(entry)) { + entry = make_readable_migration_entry( + swp_offset(entry)); pmd = swp_entry_to_pmd(entry); if (pmd_swp_soft_dirty(*src_pmd)) pmd = pmd_swp_mksoft_dirty(pmd); + if (pmd_swp_uffd_wp(*src_pmd)) + pmd = pmd_swp_mkuffd_wp(pmd); set_pmd_at(src_mm, addr, src_pmd, pmd); } add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); mm_inc_nr_ptes(dst_mm); pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); + if (!userfaultfd_wp(dst_vma)) + pmd = pmd_swp_clear_uffd_wp(pmd); set_pmd_at(dst_mm, addr, dst_pmd, pmd); ret = 0; goto out_unlock; @@ -1076,17 +1085,13 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, * a page table. */ if (is_huge_zero_pmd(pmd)) { - struct page *zero_page; /* * get_huge_zero_page() will never allocate a new page here, * since we already have a zero page to copy. It just takes a * reference. */ - zero_page = mm_get_huge_zero_page(dst_mm); - set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd, - zero_page); - ret = 0; - goto out_unlock; + mm_get_huge_zero_page(dst_mm); + goto out_zero_page; } src_page = pmd_page(pmd); @@ -1099,21 +1104,23 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, * best effort that the pinned pages won't be replaced by another * random page during the coming copy-on-write. */ - if (unlikely(page_needs_cow_for_dma(vma, src_page))) { + if (unlikely(page_needs_cow_for_dma(src_vma, src_page))) { pte_free(dst_mm, pgtable); spin_unlock(src_ptl); spin_unlock(dst_ptl); - __split_huge_pmd(vma, src_pmd, addr, false, NULL); + __split_huge_pmd(src_vma, src_pmd, addr, false, NULL); return -EAGAIN; } get_page(src_page); page_dup_rmap(src_page, true); add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); +out_zero_page: mm_inc_nr_ptes(dst_mm); pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); - pmdp_set_wrprotect(src_mm, addr, src_pmd); + if (!userfaultfd_wp(dst_vma)) + pmd = pmd_clear_uffd_wp(pmd); pmd = pmd_mkold(pmd_wrprotect(pmd)); set_pmd_at(dst_mm, addr, dst_pmd, pmd); @@ -1251,11 +1258,12 @@ unlock: } #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ -void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd) +void huge_pmd_set_accessed(struct vm_fault *vmf) { pmd_t entry; unsigned long haddr; bool write = vmf->flags & FAULT_FLAG_WRITE; + pmd_t orig_pmd = vmf->orig_pmd; vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) @@ -1272,11 +1280,12 @@ unlock: spin_unlock(vmf->ptl); } -vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) +vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + pmd_t orig_pmd = vmf->orig_pmd; vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd); VM_BUG_ON_VMA(!vma->anon_vma, vma); @@ -1412,94 +1421,23 @@ out: } /* NUMA hinting page fault entry point for trans huge pmds */ -vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) +vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; - struct anon_vma *anon_vma = NULL; + pmd_t oldpmd = vmf->orig_pmd; + pmd_t pmd; struct page *page; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; - int page_nid = NUMA_NO_NODE, this_nid = numa_node_id(); + int page_nid = NUMA_NO_NODE; int target_nid, last_cpupid = -1; - bool page_locked; bool migrated = false; - bool was_writable; + bool was_writable = pmd_savedwrite(oldpmd); int flags = 0; vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); - if (unlikely(!pmd_same(pmd, *vmf->pmd))) - goto out_unlock; - - /* - * If there are potential migrations, wait for completion and retry - * without disrupting NUMA hinting information. Do not relock and - * check_same as the page may no longer be mapped. - */ - if (unlikely(pmd_trans_migrating(*vmf->pmd))) { - page = pmd_page(*vmf->pmd); - if (!get_page_unless_zero(page)) - goto out_unlock; - spin_unlock(vmf->ptl); - put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE); - goto out; - } - - page = pmd_page(pmd); - BUG_ON(is_huge_zero_page(page)); - page_nid = page_to_nid(page); - last_cpupid = page_cpupid_last(page); - count_vm_numa_event(NUMA_HINT_FAULTS); - if (page_nid == this_nid) { - count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); - flags |= TNF_FAULT_LOCAL; - } - - /* See similar comment in do_numa_page for explanation */ - if (!pmd_savedwrite(pmd)) - flags |= TNF_NO_GROUP; - - /* - * Acquire the page lock to serialise THP migrations but avoid dropping - * page_table_lock if at all possible - */ - page_locked = trylock_page(page); - target_nid = mpol_misplaced(page, vma, haddr); - /* Migration could have started since the pmd_trans_migrating check */ - if (!page_locked) { - page_nid = NUMA_NO_NODE; - if (!get_page_unless_zero(page)) - goto out_unlock; + if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { spin_unlock(vmf->ptl); - put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE); goto out; - } else if (target_nid == NUMA_NO_NODE) { - /* There are no parallel migrations and page is in the right - * node. Clear the numa hinting info in this pmd. - */ - goto clear_pmdnuma; - } - - /* - * Page is misplaced. Page lock serialises migrations. Acquire anon_vma - * to serialises splits - */ - get_page(page); - spin_unlock(vmf->ptl); - anon_vma = page_lock_anon_vma_read(page); - - /* Confirm the PMD did not change while page_table_lock was released */ - spin_lock(vmf->ptl); - if (unlikely(!pmd_same(pmd, *vmf->pmd))) { - unlock_page(page); - put_page(page); - page_nid = NUMA_NO_NODE; - goto out_unlock; - } - - /* Bail if we fail to protect against THP splits for any reason */ - if (unlikely(!anon_vma)) { - put_page(page); - page_nid = NUMA_NO_NODE; - goto clear_pmdnuma; } /* @@ -1528,43 +1466,58 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) haddr + HPAGE_PMD_SIZE); } - /* - * Migrate the THP to the requested node, returns with page unlocked - * and access rights restored. - */ + pmd = pmd_modify(oldpmd, vma->vm_page_prot); + page = vm_normal_page_pmd(vma, haddr, pmd); + if (!page) + goto out_map; + + /* See similar comment in do_numa_page for explanation */ + if (!was_writable) + flags |= TNF_NO_GROUP; + + page_nid = page_to_nid(page); + last_cpupid = page_cpupid_last(page); + target_nid = numa_migrate_prep(page, vma, haddr, page_nid, + &flags); + + if (target_nid == NUMA_NO_NODE) { + put_page(page); + goto out_map; + } + spin_unlock(vmf->ptl); - migrated = migrate_misplaced_transhuge_page(vma->vm_mm, vma, - vmf->pmd, pmd, vmf->address, page, target_nid); + migrated = migrate_misplaced_page(page, vma, target_nid); if (migrated) { flags |= TNF_MIGRATED; page_nid = target_nid; - } else + } else { flags |= TNF_MIGRATE_FAIL; - - goto out; -clear_pmdnuma: - BUG_ON(!PageLocked(page)); - was_writable = pmd_savedwrite(pmd); - pmd = pmd_modify(pmd, vma->vm_page_prot); - pmd = pmd_mkyoung(pmd); - if (was_writable) - pmd = pmd_mkwrite(pmd); - set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd); - update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); - unlock_page(page); -out_unlock: - spin_unlock(vmf->ptl); + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { + spin_unlock(vmf->ptl); + goto out; + } + goto out_map; + } out: - if (anon_vma) - page_unlock_anon_vma_read(anon_vma); - if (page_nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, flags); return 0; + +out_map: + /* Restore the PMD */ + pmd = pmd_modify(oldpmd, vma->vm_page_prot); + pmd = pmd_mkyoung(pmd); + if (was_writable) + pmd = pmd_mkwrite(pmd); + set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd); + update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); + spin_unlock(vmf->ptl); + goto out; } /* @@ -1601,7 +1554,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, * If other processes are mapping this page, we couldn't discard * the page unless they all do MADV_FREE so let's skip the page. */ - if (page_mapcount(page) != 1) + if (total_mapcount(page) != 1) goto out; if (!trylock_page(page)) @@ -1674,12 +1627,9 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (arch_needs_pgtable_deposit()) zap_deposited_table(tlb->mm, pmd); spin_unlock(ptl); - if (is_huge_zero_pmd(orig_pmd)) - tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE); } else if (is_huge_zero_pmd(orig_pmd)) { zap_deposited_table(tlb->mm, pmd); spin_unlock(ptl); - tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE); } else { struct page *page = NULL; int flush_needed = 1; @@ -1694,7 +1644,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, VM_BUG_ON(!is_pmd_migration_entry(orig_pmd)); entry = pmd_to_swp_entry(orig_pmd); - page = migration_entry_to_page(entry); + page = pfn_swap_entry_to_page(entry); flush_needed = 0; } else WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!"); @@ -1793,6 +1743,7 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, * Returns * - 0 if PMD could not be locked * - 1 if PMD was locked but protections unchanged and TLB flush unnecessary + * or if prot_numa but THP migration is not supported * - HPAGE_PMD_NR if protections changed and TLB flush necessary */ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, @@ -1807,6 +1758,9 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; + if (prot_numa && !thp_migration_supported()) + return 1; + ptl = __pmd_trans_huge_lock(pmd, vma); if (!ptl) return 0; @@ -1819,16 +1773,19 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, swp_entry_t entry = pmd_to_swp_entry(*pmd); VM_BUG_ON(!is_pmd_migration_entry(*pmd)); - if (is_write_migration_entry(entry)) { + if (is_writable_migration_entry(entry)) { pmd_t newpmd; /* * A protection check is difficult so * just be safe and disable write */ - make_migration_entry_read(&entry); + entry = make_readable_migration_entry( + swp_offset(entry)); newpmd = swp_entry_to_pmd(entry); if (pmd_swp_soft_dirty(*pmd)) newpmd = pmd_swp_mksoft_dirty(newpmd); + if (pmd_swp_uffd_wp(*pmd)) + newpmd = pmd_swp_mkuffd_wp(newpmd); set_pmd_at(mm, addr, pmd, newpmd); } goto unlock; @@ -2044,7 +2001,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, count_vm_event(THP_SPLIT_PMD); if (!vma_is_anonymous(vma)) { - _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); + old_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); /* * We are going to unmap this huge page. So * just go ahead and zap it @@ -2053,16 +2010,25 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, zap_deposited_table(mm, pmd); if (vma_is_special_huge(vma)) return; - page = pmd_page(_pmd); - if (!PageDirty(page) && pmd_dirty(_pmd)) - set_page_dirty(page); - if (!PageReferenced(page) && pmd_young(_pmd)) - SetPageReferenced(page); - page_remove_rmap(page, true); - put_page(page); + if (unlikely(is_pmd_migration_entry(old_pmd))) { + swp_entry_t entry; + + entry = pmd_to_swp_entry(old_pmd); + page = pfn_swap_entry_to_page(entry); + } else { + page = pmd_page(old_pmd); + if (!PageDirty(page) && pmd_dirty(old_pmd)) + set_page_dirty(page); + if (!PageReferenced(page) && pmd_young(old_pmd)) + SetPageReferenced(page); + page_remove_rmap(page, true); + put_page(page); + } add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR); return; - } else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) { + } + + if (is_huge_zero_pmd(*pmd)) { /* * FIXME: Do we want to invalidate secondary mmu by calling * mmu_notifier_invalidate_range() see comments below inside @@ -2102,8 +2068,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, swp_entry_t entry; entry = pmd_to_swp_entry(old_pmd); - page = migration_entry_to_page(entry); - write = is_write_migration_entry(entry); + page = pfn_swap_entry_to_page(entry); + write = is_writable_migration_entry(entry); young = false; soft_dirty = pmd_swp_soft_dirty(old_pmd); uffd_wp = pmd_swp_uffd_wp(old_pmd); @@ -2135,7 +2101,12 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, */ if (freeze || pmd_migration) { swp_entry_t swp_entry; - swp_entry = make_migration_entry(page + i, write); + if (write) + swp_entry = make_writable_migration_entry( + page_to_pfn(page + i)); + else + swp_entry = make_readable_migration_entry( + page_to_pfn(page + i)); entry = swp_entry_to_pte(swp_entry); if (soft_dirty) entry = pte_swp_mksoft_dirty(entry); @@ -2338,22 +2309,31 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, static void unmap_page(struct page *page) { - enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | - TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD; - bool unmap_success; + enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | + TTU_SYNC; VM_BUG_ON_PAGE(!PageHead(page), page); + /* + * Anon pages need migration entries to preserve them, but file + * pages can simply be left unmapped, then faulted back on demand. + * If that is ever changed (perhaps for mlock), update remap_page(). + */ if (PageAnon(page)) - ttu_flags |= TTU_SPLIT_FREEZE; + try_to_migrate(page, ttu_flags); + else + try_to_unmap(page, ttu_flags | TTU_IGNORE_MLOCK); - unmap_success = try_to_unmap(page, ttu_flags); - VM_BUG_ON_PAGE(!unmap_success, page); + VM_WARN_ON_ONCE_PAGE(page_mapped(page), page); } static void remap_page(struct page *page, unsigned int nr) { int i; + + /* If TTU_SPLIT_FREEZE is ever extended to file, remove this check */ + if (!PageAnon(page)) + return; if (PageTransHuge(page)) { remove_migration_ptes(page, page, true); } else { @@ -2659,7 +2639,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) struct deferred_split *ds_queue = get_deferred_split_queue(head); struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; - int count, mapcount, extra_pins, ret; + int extra_pins, ret; pgoff_t end; VM_BUG_ON_PAGE(is_huge_zero_page(head), head); @@ -2718,7 +2698,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) } unmap_page(head); - VM_BUG_ON_PAGE(compound_mapcount(head), head); /* block interrupt reentry in xa_lock and spinlock */ local_irq_disable(); @@ -2736,9 +2715,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) /* Prevent deferred_split_scan() touching ->_refcount */ spin_lock(&ds_queue->split_queue_lock); - count = page_count(head); - mapcount = total_mapcount(head); - if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) { + if (page_ref_freeze(head, 1 + extra_pins)) { if (!list_empty(page_deferred_list(head))) { ds_queue->split_queue_len--; list_del(page_deferred_list(head)); @@ -2758,16 +2735,9 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) __split_huge_page(page, list, end); ret = 0; } else { - if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) { - pr_alert("total_mapcount: %u, page_count(): %u\n", - mapcount, count); - if (PageTail(page)) - dump_page(head, NULL); - dump_page(page, "total_mapcount(head) > 0"); - BUG(); - } spin_unlock(&ds_queue->split_queue_lock); -fail: if (mapping) +fail: + if (mapping) xa_unlock(&mapping->i_pages); local_irq_enable(); remap_page(head, thp_nr_pages(head)); @@ -2868,7 +2838,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, spin_lock_irqsave(&ds_queue->split_queue_lock, flags); /* Take pin on all head pages to avoid freeing them under us */ list_for_each_safe(pos, next, &ds_queue->split_queue) { - page = list_entry((void *)pos, struct page, mapping); + page = list_entry((void *)pos, struct page, deferred_list); page = compound_head(page); if (get_page_unless_zero(page)) { list_move(page_deferred_list(page), &list); @@ -2883,7 +2853,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); list_for_each_safe(pos, next, &list) { - page = list_entry((void *)pos, struct page, mapping); + page = list_entry((void *)pos, struct page, deferred_list); if (!trylock_page(page)) goto next; /* split_huge_page() removes page from list on success */ @@ -3142,7 +3112,7 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf, tok = strsep(&buf, ","); if (tok) { - strncpy(file_path, tok, MAX_INPUT_BUF_SZ); + strcpy(file_path, tok); } else { ret = -EINVAL; goto out; @@ -3212,7 +3182,10 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, pmdval = pmdp_invalidate(vma, address, pvmw->pmd); if (pmd_dirty(pmdval)) set_page_dirty(page); - entry = make_migration_entry(page, pmd_write(pmdval)); + if (pmd_write(pmdval)) + entry = make_writable_migration_entry(page_to_pfn(page)); + else + entry = make_readable_migration_entry(page_to_pfn(page)); pmdswp = swp_entry_to_pmd(entry); if (pmd_soft_dirty(pmdval)) pmdswp = pmd_swp_mksoft_dirty(pmdswp); @@ -3238,8 +3211,10 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) pmde = pmd_mkold(mk_huge_pmd(new, vma->vm_page_prot)); if (pmd_swp_soft_dirty(*pvmw->pmd)) pmde = pmd_mksoft_dirty(pmde); - if (is_write_migration_entry(entry)) + if (is_writable_migration_entry(entry)) pmde = maybe_pmd_mkwrite(pmde, vma); + if (pmd_swp_uffd_wp(*pvmw->pmd)) + pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde)); flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE); if (PageAnon(new)) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3db405dea3dc..924553aa8f78 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -30,6 +30,7 @@ #include <linux/numa.h> #include <linux/llist.h> #include <linux/cma.h> +#include <linux/migrate.h> #include <asm/page.h> #include <asm/pgalloc.h> @@ -41,6 +42,7 @@ #include <linux/node.h> #include <linux/page_owner.h> #include "internal.h" +#include "hugetlb_vmemmap.h" int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; @@ -1318,8 +1320,6 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask); } -static void prep_new_huge_page(struct hstate *h, struct page *page, int nid); -static void prep_compound_gigantic_page(struct page *page, unsigned int order); #else /* !CONFIG_CONTIG_ALLOC */ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) @@ -1375,7 +1375,40 @@ static void remove_hugetlb_page(struct hstate *h, struct page *page, h->nr_huge_pages_node[nid]--; } -static void update_and_free_page(struct hstate *h, struct page *page) +static void add_hugetlb_page(struct hstate *h, struct page *page, + bool adjust_surplus) +{ + int zeroed; + int nid = page_to_nid(page); + + VM_BUG_ON_PAGE(!HPageVmemmapOptimized(page), page); + + lockdep_assert_held(&hugetlb_lock); + + INIT_LIST_HEAD(&page->lru); + h->nr_huge_pages++; + h->nr_huge_pages_node[nid]++; + + if (adjust_surplus) { + h->surplus_huge_pages++; + h->surplus_huge_pages_node[nid]++; + } + + set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); + set_page_private(page, 0); + SetHPageVmemmapOptimized(page); + + /* + * This page is now managed by the hugetlb allocator and has + * no users -- drop the last reference. + */ + zeroed = put_page_testzero(page); + VM_BUG_ON_PAGE(!zeroed, page); + arch_clear_hugepage_flags(page); + enqueue_huge_page(h, page); +} + +static void __update_and_free_page(struct hstate *h, struct page *page) { int i; struct page *subpage = page; @@ -1383,6 +1416,18 @@ static void update_and_free_page(struct hstate *h, struct page *page) if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; + if (alloc_huge_page_vmemmap(h, page)) { + spin_lock_irq(&hugetlb_lock); + /* + * If we cannot allocate vmemmap pages, just refuse to free the + * page and put the page back on the hugetlb free list and treat + * as a surplus page. + */ + add_hugetlb_page(h, page, true); + spin_unlock_irq(&hugetlb_lock); + return; + } + for (i = 0; i < pages_per_huge_page(h); i++, subpage = mem_map_next(subpage, page, i)) { subpage->flags &= ~(1 << PG_locked | 1 << PG_error | @@ -1398,12 +1443,79 @@ static void update_and_free_page(struct hstate *h, struct page *page) } } +/* + * As update_and_free_page() can be called under any context, so we cannot + * use GFP_KERNEL to allocate vmemmap pages. However, we can defer the + * actual freeing in a workqueue to prevent from using GFP_ATOMIC to allocate + * the vmemmap pages. + * + * free_hpage_workfn() locklessly retrieves the linked list of pages to be + * freed and frees them one-by-one. As the page->mapping pointer is going + * to be cleared in free_hpage_workfn() anyway, it is reused as the llist_node + * structure of a lockless linked list of huge pages to be freed. + */ +static LLIST_HEAD(hpage_freelist); + +static void free_hpage_workfn(struct work_struct *work) +{ + struct llist_node *node; + + node = llist_del_all(&hpage_freelist); + + while (node) { + struct page *page; + struct hstate *h; + + page = container_of((struct address_space **)node, + struct page, mapping); + node = node->next; + page->mapping = NULL; + /* + * The VM_BUG_ON_PAGE(!PageHuge(page), page) in page_hstate() + * is going to trigger because a previous call to + * remove_hugetlb_page() will set_compound_page_dtor(page, + * NULL_COMPOUND_DTOR), so do not use page_hstate() directly. + */ + h = size_to_hstate(page_size(page)); + + __update_and_free_page(h, page); + + cond_resched(); + } +} +static DECLARE_WORK(free_hpage_work, free_hpage_workfn); + +static inline void flush_free_hpage_work(struct hstate *h) +{ + if (free_vmemmap_pages_per_hpage(h)) + flush_work(&free_hpage_work); +} + +static void update_and_free_page(struct hstate *h, struct page *page, + bool atomic) +{ + if (!HPageVmemmapOptimized(page) || !atomic) { + __update_and_free_page(h, page); + return; + } + + /* + * Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap pages. + * + * Only call schedule_work() if hpage_freelist is previously + * empty. Otherwise, schedule_work() had been called but the workfn + * hasn't retrieved the list yet. + */ + if (llist_add((struct llist_node *)&page->mapping, &hpage_freelist)) + schedule_work(&free_hpage_work); +} + static void update_and_free_pages_bulk(struct hstate *h, struct list_head *list) { struct page *page, *t_page; list_for_each_entry_safe(page, t_page, list, lru) { - update_and_free_page(h, page); + update_and_free_page(h, page, false); cond_resched(); } } @@ -1470,12 +1582,12 @@ void free_huge_page(struct page *page) if (HPageTemporary(page)) { remove_hugetlb_page(h, page, false); spin_unlock_irqrestore(&hugetlb_lock, flags); - update_and_free_page(h, page); + update_and_free_page(h, page, true); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ remove_hugetlb_page(h, page, true); spin_unlock_irqrestore(&hugetlb_lock, flags); - update_and_free_page(h, page); + update_and_free_page(h, page, true); } else { arch_clear_hugepage_flags(page); enqueue_huge_page(h, page); @@ -1493,8 +1605,9 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid) h->nr_huge_pages_node[nid]++; } -static void __prep_new_huge_page(struct page *page) +static void __prep_new_huge_page(struct hstate *h, struct page *page) { + free_huge_page_vmemmap(h, page); INIT_LIST_HEAD(&page->lru); set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); hugetlb_set_page_subpool(page, NULL); @@ -1504,15 +1617,15 @@ static void __prep_new_huge_page(struct page *page) static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) { - __prep_new_huge_page(page); + __prep_new_huge_page(h, page); spin_lock_irq(&hugetlb_lock); __prep_account_new_huge_page(h, nid); spin_unlock_irq(&hugetlb_lock); } -static void prep_compound_gigantic_page(struct page *page, unsigned int order) +static bool prep_compound_gigantic_page(struct page *page, unsigned int order) { - int i; + int i, j; int nr_pages = 1 << order; struct page *p = page + 1; @@ -1534,11 +1647,48 @@ static void prep_compound_gigantic_page(struct page *page, unsigned int order) * after get_user_pages(). */ __ClearPageReserved(p); + /* + * Subtle and very unlikely + * + * Gigantic 'page allocators' such as memblock or cma will + * return a set of pages with each page ref counted. We need + * to turn this set of pages into a compound page with tail + * page ref counts set to zero. Code such as speculative page + * cache adding could take a ref on a 'to be' tail page. + * We need to respect any increased ref count, and only set + * the ref count to zero if count is currently 1. If count + * is not 1, we call synchronize_rcu in the hope that a rcu + * grace period will cause ref count to drop and then retry. + * If count is still inflated on retry we return an error and + * must discard the pages. + */ + if (!page_ref_freeze(p, 1)) { + pr_info("HugeTLB unexpected inflated ref count on freshly allocated page\n"); + synchronize_rcu(); + if (!page_ref_freeze(p, 1)) + goto out_error; + } set_page_count(p, 0); set_compound_head(p, page); } atomic_set(compound_mapcount_ptr(page), -1); atomic_set(compound_pincount_ptr(page), 0); + return true; + +out_error: + /* undo tail page modifications made above */ + p = page + 1; + for (j = 1; j < i; j++, p = mem_map_next(p, page, j)) { + clear_compound_head(p); + set_page_refcounted(p); + } + /* need to clear PG_reserved on remaining tail pages */ + for (; j < nr_pages; j++, p = mem_map_next(p, page, j)) + __ClearPageReserved(p); + set_compound_order(page, 0); + page[1].compound_nr = 0; + __ClearPageHead(page); + return false; } /* @@ -1588,15 +1738,12 @@ struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage) return NULL; } -pgoff_t __basepage_index(struct page *page) +pgoff_t hugetlb_basepage_index(struct page *page) { struct page *page_head = compound_head(page); pgoff_t index = page_index(page_head); unsigned long compound_idx; - if (!PageHuge(page_head)) - return page_index(page); - if (compound_order(page_head) >= MAX_ORDER) compound_idx = page_to_pfn(page) - page_to_pfn(page_head); else @@ -1661,7 +1808,9 @@ static struct page *alloc_fresh_huge_page(struct hstate *h, nodemask_t *node_alloc_noretry) { struct page *page; + bool retry = false; +retry: if (hstate_is_gigantic(h)) page = alloc_gigantic_page(h, gfp_mask, nid, nmask); else @@ -1670,8 +1819,21 @@ static struct page *alloc_fresh_huge_page(struct hstate *h, if (!page) return NULL; - if (hstate_is_gigantic(h)) - prep_compound_gigantic_page(page, huge_page_order(h)); + if (hstate_is_gigantic(h)) { + if (!prep_compound_gigantic_page(page, huge_page_order(h))) { + /* + * Rare failure to convert pages to compound page. + * Free pages and try again - ONCE! + */ + free_gigantic_page(page, huge_page_order(h)); + if (!retry) { + retry = true; + goto retry; + } + pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n"); + return NULL; + } + } prep_new_huge_page(h, page, page_to_nid(page)); return page; @@ -1740,10 +1902,14 @@ static struct page *remove_pool_huge_page(struct hstate *h, * nothing for in-use hugepages and non-hugepages. * This function returns values like below: * - * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use - * (allocated or reserved.) - * 0: successfully dissolved free hugepages or the page is not a - * hugepage (considered as already dissolved) + * -ENOMEM: failed to allocate vmemmap pages to free the freed hugepages + * when the system is under memory pressure and the feature of + * freeing unused vmemmap pages associated with each hugetlb page + * is enabled. + * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use + * (allocated or reserved.) + * 0: successfully dissolved free hugepages or the page is not a + * hugepage (considered as already dissolved) */ int dissolve_free_huge_page(struct page *page) { @@ -1785,19 +1951,38 @@ retry: goto retry; } + remove_hugetlb_page(h, head, false); + h->max_huge_pages--; + spin_unlock_irq(&hugetlb_lock); + /* - * Move PageHWPoison flag from head page to the raw error page, - * which makes any subpages rather than the error page reusable. + * Normally update_and_free_page will allocate required vmemmmap + * before freeing the page. update_and_free_page will fail to + * free the page if it can not allocate required vmemmap. We + * need to adjust max_huge_pages if the page is not freed. + * Attempt to allocate vmemmmap here so that we can take + * appropriate action on failure. */ - if (PageHWPoison(head) && page != head) { - SetPageHWPoison(page); - ClearPageHWPoison(head); + rc = alloc_huge_page_vmemmap(h, head); + if (!rc) { + /* + * Move PageHWPoison flag from head page to the raw + * error page, which makes any subpages rather than + * the error page reusable. + */ + if (PageHWPoison(head) && page != head) { + SetPageHWPoison(page); + ClearPageHWPoison(head); + } + update_and_free_page(h, head, false); + } else { + spin_lock_irq(&hugetlb_lock); + add_hugetlb_page(h, head, false); + h->max_huge_pages++; + spin_unlock_irq(&hugetlb_lock); } - remove_hugetlb_page(h, page, false); - h->max_huge_pages--; - spin_unlock_irq(&hugetlb_lock); - update_and_free_page(h, head); - return 0; + + return rc; } out: spin_unlock_irq(&hugetlb_lock); @@ -2121,12 +2306,18 @@ out: * be restored when a newly allocated huge page must be freed. It is * to be called after calling vma_needs_reservation to determine if a * reservation exists. + * + * vma_del_reservation is used in error paths where an entry in the reserve + * map was created during huge page allocation and must be removed. It is to + * be called after calling vma_needs_reservation to determine if a reservation + * exists. */ enum vma_resv_mode { VMA_NEEDS_RESV, VMA_COMMIT_RESV, VMA_END_RESV, VMA_ADD_RESV, + VMA_DEL_RESV, }; static long __vma_reservation_common(struct hstate *h, struct vm_area_struct *vma, unsigned long addr, @@ -2170,11 +2361,21 @@ static long __vma_reservation_common(struct hstate *h, ret = region_del(resv, idx, idx + 1); } break; + case VMA_DEL_RESV: + if (vma->vm_flags & VM_MAYSHARE) { + region_abort(resv, idx, idx + 1, 1); + ret = region_del(resv, idx, idx + 1); + } else { + ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); + /* region_add calls of range 1 should never fail. */ + VM_BUG_ON(ret < 0); + } + break; default: BUG(); } - if (vma->vm_flags & VM_MAYSHARE) + if (vma->vm_flags & VM_MAYSHARE || mode == VMA_DEL_RESV) return ret; /* * We know private mapping must have HPAGE_RESV_OWNER set. @@ -2222,25 +2423,39 @@ static long vma_add_reservation(struct hstate *h, return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV); } +static long vma_del_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) +{ + return __vma_reservation_common(h, vma, addr, VMA_DEL_RESV); +} + /* - * This routine is called to restore a reservation on error paths. In the - * specific error paths, a huge page was allocated (via alloc_huge_page) - * and is about to be freed. If a reservation for the page existed, - * alloc_huge_page would have consumed the reservation and set - * HPageRestoreReserve in the newly allocated page. When the page is freed - * via free_huge_page, the global reservation count will be incremented if - * HPageRestoreReserve is set. However, free_huge_page can not adjust the - * reserve map. Adjust the reserve map here to be consistent with global - * reserve count adjustments to be made by free_huge_page. + * This routine is called to restore reservation information on error paths. + * It should ONLY be called for pages allocated via alloc_huge_page(), and + * the hugetlb mutex should remain held when calling this routine. + * + * It handles two specific cases: + * 1) A reservation was in place and the page consumed the reservation. + * HPageRestoreReserve is set in the page. + * 2) No reservation was in place for the page, so HPageRestoreReserve is + * not set. However, alloc_huge_page always updates the reserve map. + * + * In case 1, free_huge_page later in the error path will increment the + * global reserve count. But, free_huge_page does not have enough context + * to adjust the reservation map. This case deals primarily with private + * mappings. Adjust the reserve map here to be consistent with global + * reserve count adjustments to be made by free_huge_page. Make sure the + * reserve map indicates there is a reservation present. + * + * In case 2, simply undo reserve map modifications done by alloc_huge_page. */ -static void restore_reserve_on_error(struct hstate *h, - struct vm_area_struct *vma, unsigned long address, - struct page *page) +void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, + unsigned long address, struct page *page) { - if (unlikely(HPageRestoreReserve(page))) { - long rc = vma_needs_reservation(h, vma, address); + long rc = vma_needs_reservation(h, vma, address); - if (unlikely(rc < 0)) { + if (HPageRestoreReserve(page)) { + if (unlikely(rc < 0)) /* * Rare out of memory condition in reserve map * manipulation. Clear HPageRestoreReserve so that @@ -2253,16 +2468,57 @@ static void restore_reserve_on_error(struct hstate *h, * accounting of reserve counts. */ ClearHPageRestoreReserve(page); - } else if (rc) { - rc = vma_add_reservation(h, vma, address); - if (unlikely(rc < 0)) + else if (rc) + (void)vma_add_reservation(h, vma, address); + else + vma_end_reservation(h, vma, address); + } else { + if (!rc) { + /* + * This indicates there is an entry in the reserve map + * added by alloc_huge_page. We know it was added + * before the alloc_huge_page call, otherwise + * HPageRestoreReserve would be set on the page. + * Remove the entry so that a subsequent allocation + * does not consume a reservation. + */ + rc = vma_del_reservation(h, vma, address); + if (rc < 0) /* - * See above comment about rare out of - * memory condition. + * VERY rare out of memory condition. Since + * we can not delete the entry, set + * HPageRestoreReserve so that the reserve + * count will be incremented when the page + * is freed. This reserve will be consumed + * on a subsequent allocation. */ - ClearHPageRestoreReserve(page); + SetHPageRestoreReserve(page); + } else if (rc < 0) { + /* + * Rare out of memory condition from + * vma_needs_reservation call. Memory allocation is + * only attempted if a new entry is needed. Therefore, + * this implies there is not an entry in the + * reserve map. + * + * For shared mappings, no entry in the map indicates + * no reservation. We are done. + */ + if (!(vma->vm_flags & VM_MAYSHARE)) + /* + * For private mappings, no entry indicates + * a reservation is present. Since we can + * not add an entry, set SetHPageRestoreReserve + * on the page so reserve count will be + * incremented when freed. This reserve will + * be consumed on a subsequent allocation. + */ + SetHPageRestoreReserve(page); } else - vma_end_reservation(h, vma, address); + /* + * No reservation present, do nothing + */ + vma_end_reservation(h, vma, address); } } @@ -2283,14 +2539,15 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page, /* * Before dissolving the page, we need to allocate a new one for the - * pool to remain stable. Using alloc_buddy_huge_page() allows us to - * not having to deal with prep_new_huge_page() and avoids dealing of any - * counters. This simplifies and let us do the whole thing under the - * lock. + * pool to remain stable. Here, we allocate the page and 'prep' it + * by doing everything but actually updating counters and adding to + * the pool. This simplifies and let us do most of the processing + * under the lock. */ new_page = alloc_buddy_huge_page(h, gfp_mask, nid, NULL, NULL); if (!new_page) return -ENOMEM; + __prep_new_huge_page(h, new_page); retry: spin_lock_irq(&hugetlb_lock); @@ -2329,14 +2586,9 @@ retry: remove_hugetlb_page(h, old_page, false); /* - * new_page needs to be initialized with the standard hugetlb - * state. This is normally done by prep_new_huge_page() but - * that takes hugetlb_lock which is already held so we need to - * open code it here. * Reference count trick is needed because allocator gives us * referenced page but the pool requires pages with 0 refcount. */ - __prep_new_huge_page(new_page); __prep_account_new_huge_page(h, nid); page_ref_dec(new_page); enqueue_huge_page(h, new_page); @@ -2345,14 +2597,14 @@ retry: * Pages have been replaced, we can safely free the old one. */ spin_unlock_irq(&hugetlb_lock); - update_and_free_page(h, old_page); + update_and_free_page(h, old_page, false); } return ret; free_new: spin_unlock_irq(&hugetlb_lock); - __free_pages(new_page, huge_page_order(h)); + update_and_free_page(h, new_page, false); return ret; } @@ -2557,16 +2809,10 @@ found: return 1; } -static void __init prep_compound_huge_page(struct page *page, - unsigned int order) -{ - if (unlikely(order > (MAX_ORDER - 1))) - prep_compound_gigantic_page(page, order); - else - prep_compound_page(page, order); -} - -/* Put bootmem huge pages into the standard lists after mem_map is up */ +/* + * Put bootmem huge pages into the standard lists after mem_map is up. + * Note: This only applies to gigantic (order > MAX_ORDER) pages. + */ static void __init gather_bootmem_prealloc(void) { struct huge_bootmem_page *m; @@ -2575,20 +2821,23 @@ static void __init gather_bootmem_prealloc(void) struct page *page = virt_to_page(m); struct hstate *h = m->hstate; + VM_BUG_ON(!hstate_is_gigantic(h)); WARN_ON(page_count(page) != 1); - prep_compound_huge_page(page, huge_page_order(h)); - WARN_ON(PageReserved(page)); - prep_new_huge_page(h, page, page_to_nid(page)); - put_page(page); /* free it into the hugepage allocator */ + if (prep_compound_gigantic_page(page, huge_page_order(h))) { + WARN_ON(PageReserved(page)); + prep_new_huge_page(h, page, page_to_nid(page)); + put_page(page); /* add to the hugepage allocator */ + } else { + free_gigantic_page(page, huge_page_order(h)); + pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n"); + } /* - * If we had gigantic hugepages allocated at boot time, we need - * to restore the 'stolen' pages to totalram_pages in order to - * fix confusing memory reports from free(1) and another - * side-effects, like CommitLimit going negative. + * We need to restore the 'stolen' pages to totalram_pages + * in order to fix confusing memory reports from free(1) and + * other side-effects, like CommitLimit going negative. */ - if (hstate_is_gigantic(h)) - adjust_managed_page_count(page, pages_per_huge_page(h)); + adjust_managed_page_count(page, pages_per_huge_page(h)); cond_resched(); } } @@ -2766,6 +3015,7 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, * pages in hstate via the proc/sysfs interfaces. */ mutex_lock(&h->resize_lock); + flush_free_hpage_work(h); spin_lock_irq(&hugetlb_lock); /* @@ -2875,6 +3125,7 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, /* free the pages after dropping lock */ spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); + flush_free_hpage_work(h); spin_lock_irq(&hugetlb_lock); while (count < persistent_huge_pages(h)) { @@ -3382,6 +3633,7 @@ void __init hugetlb_add_hstate(unsigned int order) h->next_nid_to_free = first_memory_node; snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", huge_page_size(h)/1024); + hugetlb_vmemmap_init(h); parsed_hstate = h; } @@ -3856,6 +4108,7 @@ static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, int writable) { pte_t entry; + unsigned int shift = huge_page_shift(hstate_vma(vma)); if (writable) { entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page, @@ -3866,7 +4119,7 @@ static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, } entry = pte_mkyoung(entry); entry = pte_mkhuge(entry); - entry = arch_make_huge_pte(entry, vma, page, writable); + entry = arch_make_huge_pte(entry, shift, vma->vm_flags); return entry; } @@ -3989,12 +4242,13 @@ again: is_hugetlb_entry_hwpoisoned(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); - if (is_write_migration_entry(swp_entry) && cow) { + if (is_writable_migration_entry(swp_entry) && cow) { /* * COW mappings require pages in both * parent and child to be set to read. */ - make_migration_entry_read(&swp_entry); + swp_entry = make_readable_migration_entry( + swp_offset(swp_entry)); entry = swp_entry_to_pte(swp_entry); set_huge_swap_pte_at(src, addr, src_pte, entry, sz); @@ -4037,6 +4291,8 @@ again: spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); if (!pte_same(src_pte_old, entry)) { + restore_reserve_on_error(h, vma, addr, + new); put_page(new); /* dst_entry won't change as in child */ goto again; @@ -4056,6 +4312,7 @@ again: * See Documentation/vm/mmu_notifier.rst */ huge_ptep_set_wrprotect(src, addr, src_pte); + entry = huge_pte_wrprotect(entry); } page_dup_rmap(ptepage, true); @@ -4868,30 +5125,37 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, struct page **pagep) { bool is_continue = (mode == MCOPY_ATOMIC_CONTINUE); - struct address_space *mapping; - pgoff_t idx; + struct hstate *h = hstate_vma(dst_vma); + struct address_space *mapping = dst_vma->vm_file->f_mapping; + pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr); unsigned long size; int vm_shared = dst_vma->vm_flags & VM_SHARED; - struct hstate *h = hstate_vma(dst_vma); pte_t _dst_pte; spinlock_t *ptl; - int ret; + int ret = -ENOMEM; struct page *page; int writable; - mapping = dst_vma->vm_file->f_mapping; - idx = vma_hugecache_offset(h, dst_vma, dst_addr); - if (is_continue) { ret = -EFAULT; page = find_lock_page(mapping, idx); if (!page) goto out; } else if (!*pagep) { - ret = -ENOMEM; + /* If a page already exists, then it's UFFDIO_COPY for + * a non-missing case. Return -EEXIST. + */ + if (vm_shared && + hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { + ret = -EEXIST; + goto out; + } + page = alloc_huge_page(dst_vma, dst_addr, 0); - if (IS_ERR(page)) + if (IS_ERR(page)) { + ret = -ENOMEM; goto out; + } ret = copy_huge_page_from_user(page, (const void __user *) src_addr, @@ -4900,12 +5164,44 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; + /* Free the allocated page which may have + * consumed a reservation. + */ + restore_reserve_on_error(h, dst_vma, dst_addr, page); + put_page(page); + + /* Allocate a temporary page to hold the copied + * contents. + */ + page = alloc_huge_page_vma(h, dst_vma, dst_addr); + if (!page) { + ret = -ENOMEM; + goto out; + } *pagep = page; - /* don't free the page */ + /* Set the outparam pagep and return to the caller to + * copy the contents outside the lock. Don't free the + * page. + */ goto out; } } else { - page = *pagep; + if (vm_shared && + hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { + put_page(*pagep); + ret = -EEXIST; + *pagep = NULL; + goto out; + } + + page = alloc_huge_page(dst_vma, dst_addr, 0); + if (IS_ERR(page)) { + ret = -ENOMEM; + *pagep = NULL; + goto out; + } + copy_huge_page(page, *pagep); + put_page(*pagep); *pagep = NULL; } @@ -4995,6 +5291,7 @@ out_release_unlock: if (vm_shared || is_continue) unlock_page(page); out_release_nounlock: + restore_reserve_on_error(h, dst_vma, dst_addr, page); put_page(page); goto out; } @@ -5236,10 +5533,11 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, if (unlikely(is_hugetlb_entry_migration(pte))) { swp_entry_t entry = pte_to_swp_entry(pte); - if (is_write_migration_entry(entry)) { + if (is_writable_migration_entry(entry)) { pte_t newpte; - make_migration_entry_read(&entry); + entry = make_readable_migration_entry( + swp_offset(entry)); newpte = swp_entry_to_pte(entry); set_huge_swap_pte_at(mm, address, ptep, newpte, huge_page_size(h)); @@ -5250,10 +5548,11 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, } if (!huge_pte_none(pte)) { pte_t old_pte; + unsigned int shift = huge_page_shift(hstate_vma(vma)); old_pte = huge_ptep_modify_prot_start(vma, address, ptep); pte = pte_mkhuge(huge_pte_modify(old_pte, newprot)); - pte = arch_make_huge_pte(pte, vma, NULL, 0); + pte = arch_make_huge_pte(pte, shift, vma->vm_flags); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; } @@ -5846,6 +6145,23 @@ unlock: return ret; } +int get_hwpoison_huge_page(struct page *page, bool *hugetlb) +{ + int ret = 0; + + *hugetlb = false; + spin_lock_irq(&hugetlb_lock); + if (PageHeadHuge(page)) { + *hugetlb = true; + if (HPageFreed(page) || HPageMigratable(page)) + ret = get_page_unless_zero(page); + else + ret = -EBUSY; + } + spin_unlock_irq(&hugetlb_lock); + return ret; +} + void putback_active_hugepage(struct page *page) { spin_lock_irq(&hugetlb_lock); diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c new file mode 100644 index 000000000000..c540c21e26f5 --- /dev/null +++ b/mm/hugetlb_vmemmap.c @@ -0,0 +1,298 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Free some vmemmap pages of HugeTLB + * + * Copyright (c) 2020, Bytedance. All rights reserved. + * + * Author: Muchun Song <songmuchun@bytedance.com> + * + * The struct page structures (page structs) are used to describe a physical + * page frame. By default, there is a one-to-one mapping from a page frame to + * it's corresponding page struct. + * + * HugeTLB pages consist of multiple base page size pages and is supported by + * many architectures. See hugetlbpage.rst in the Documentation directory for + * more details. On the x86-64 architecture, HugeTLB pages of size 2MB and 1GB + * are currently supported. Since the base page size on x86 is 4KB, a 2MB + * HugeTLB page consists of 512 base pages and a 1GB HugeTLB page consists of + * 4096 base pages. For each base page, there is a corresponding page struct. + * + * Within the HugeTLB subsystem, only the first 4 page structs are used to + * contain unique information about a HugeTLB page. __NR_USED_SUBPAGE provides + * this upper limit. The only 'useful' information in the remaining page structs + * is the compound_head field, and this field is the same for all tail pages. + * + * By removing redundant page structs for HugeTLB pages, memory can be returned + * to the buddy allocator for other uses. + * + * Different architectures support different HugeTLB pages. For example, the + * following table is the HugeTLB page size supported by x86 and arm64 + * architectures. Because arm64 supports 4k, 16k, and 64k base pages and + * supports contiguous entries, so it supports many kinds of sizes of HugeTLB + * page. + * + * +--------------+-----------+-----------------------------------------------+ + * | Architecture | Page Size | HugeTLB Page Size | + * +--------------+-----------+-----------+-----------+-----------+-----------+ + * | x86-64 | 4KB | 2MB | 1GB | | | + * +--------------+-----------+-----------+-----------+-----------+-----------+ + * | | 4KB | 64KB | 2MB | 32MB | 1GB | + * | +-----------+-----------+-----------+-----------+-----------+ + * | arm64 | 16KB | 2MB | 32MB | 1GB | | + * | +-----------+-----------+-----------+-----------+-----------+ + * | | 64KB | 2MB | 512MB | 16GB | | + * +--------------+-----------+-----------+-----------+-----------+-----------+ + * + * When the system boot up, every HugeTLB page has more than one struct page + * structs which size is (unit: pages): + * + * struct_size = HugeTLB_Size / PAGE_SIZE * sizeof(struct page) / PAGE_SIZE + * + * Where HugeTLB_Size is the size of the HugeTLB page. We know that the size + * of the HugeTLB page is always n times PAGE_SIZE. So we can get the following + * relationship. + * + * HugeTLB_Size = n * PAGE_SIZE + * + * Then, + * + * struct_size = n * PAGE_SIZE / PAGE_SIZE * sizeof(struct page) / PAGE_SIZE + * = n * sizeof(struct page) / PAGE_SIZE + * + * We can use huge mapping at the pud/pmd level for the HugeTLB page. + * + * For the HugeTLB page of the pmd level mapping, then + * + * struct_size = n * sizeof(struct page) / PAGE_SIZE + * = PAGE_SIZE / sizeof(pte_t) * sizeof(struct page) / PAGE_SIZE + * = sizeof(struct page) / sizeof(pte_t) + * = 64 / 8 + * = 8 (pages) + * + * Where n is how many pte entries which one page can contains. So the value of + * n is (PAGE_SIZE / sizeof(pte_t)). + * + * This optimization only supports 64-bit system, so the value of sizeof(pte_t) + * is 8. And this optimization also applicable only when the size of struct page + * is a power of two. In most cases, the size of struct page is 64 bytes (e.g. + * x86-64 and arm64). So if we use pmd level mapping for a HugeTLB page, the + * size of struct page structs of it is 8 page frames which size depends on the + * size of the base page. + * + * For the HugeTLB page of the pud level mapping, then + * + * struct_size = PAGE_SIZE / sizeof(pmd_t) * struct_size(pmd) + * = PAGE_SIZE / 8 * 8 (pages) + * = PAGE_SIZE (pages) + * + * Where the struct_size(pmd) is the size of the struct page structs of a + * HugeTLB page of the pmd level mapping. + * + * E.g.: A 2MB HugeTLB page on x86_64 consists in 8 page frames while 1GB + * HugeTLB page consists in 4096. + * + * Next, we take the pmd level mapping of the HugeTLB page as an example to + * show the internal implementation of this optimization. There are 8 pages + * struct page structs associated with a HugeTLB page which is pmd mapped. + * + * Here is how things look before optimization. + * + * HugeTLB struct pages(8 pages) page frame(8 pages) + * +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ + * | | | 0 | -------------> | 0 | + * | | +-----------+ +-----------+ + * | | | 1 | -------------> | 1 | + * | | +-----------+ +-----------+ + * | | | 2 | -------------> | 2 | + * | | +-----------+ +-----------+ + * | | | 3 | -------------> | 3 | + * | | +-----------+ +-----------+ + * | | | 4 | -------------> | 4 | + * | PMD | +-----------+ +-----------+ + * | level | | 5 | -------------> | 5 | + * | mapping | +-----------+ +-----------+ + * | | | 6 | -------------> | 6 | + * | | +-----------+ +-----------+ + * | | | 7 | -------------> | 7 | + * | | +-----------+ +-----------+ + * | | + * | | + * | | + * +-----------+ + * + * The value of page->compound_head is the same for all tail pages. The first + * page of page structs (page 0) associated with the HugeTLB page contains the 4 + * page structs necessary to describe the HugeTLB. The only use of the remaining + * pages of page structs (page 1 to page 7) is to point to page->compound_head. + * Therefore, we can remap pages 2 to 7 to page 1. Only 2 pages of page structs + * will be used for each HugeTLB page. This will allow us to free the remaining + * 6 pages to the buddy allocator. + * + * Here is how things look after remapping. + * + * HugeTLB struct pages(8 pages) page frame(8 pages) + * +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ + * | | | 0 | -------------> | 0 | + * | | +-----------+ +-----------+ + * | | | 1 | -------------> | 1 | + * | | +-----------+ +-----------+ + * | | | 2 | ----------------^ ^ ^ ^ ^ ^ + * | | +-----------+ | | | | | + * | | | 3 | ------------------+ | | | | + * | | +-----------+ | | | | + * | | | 4 | --------------------+ | | | + * | PMD | +-----------+ | | | + * | level | | 5 | ----------------------+ | | + * | mapping | +-----------+ | | + * | | | 6 | ------------------------+ | + * | | +-----------+ | + * | | | 7 | --------------------------+ + * | | +-----------+ + * | | + * | | + * | | + * +-----------+ + * + * When a HugeTLB is freed to the buddy system, we should allocate 6 pages for + * vmemmap pages and restore the previous mapping relationship. + * + * For the HugeTLB page of the pud level mapping. It is similar to the former. + * We also can use this approach to free (PAGE_SIZE - 2) vmemmap pages. + * + * Apart from the HugeTLB page of the pmd/pud level mapping, some architectures + * (e.g. aarch64) provides a contiguous bit in the translation table entries + * that hints to the MMU to indicate that it is one of a contiguous set of + * entries that can be cached in a single TLB entry. + * + * The contiguous bit is used to increase the mapping size at the pmd and pte + * (last) level. So this type of HugeTLB page can be optimized only when its + * size of the struct page structs is greater than 2 pages. + */ +#define pr_fmt(fmt) "HugeTLB: " fmt + +#include "hugetlb_vmemmap.h" + +/* + * There are a lot of struct page structures associated with each HugeTLB page. + * For tail pages, the value of compound_head is the same. So we can reuse first + * page of tail page structures. We map the virtual addresses of the remaining + * pages of tail page structures to the first tail page struct, and then free + * these page frames. Therefore, we need to reserve two pages as vmemmap areas. + */ +#define RESERVE_VMEMMAP_NR 2U +#define RESERVE_VMEMMAP_SIZE (RESERVE_VMEMMAP_NR << PAGE_SHIFT) + +bool hugetlb_free_vmemmap_enabled = IS_ENABLED(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON); + +static int __init early_hugetlb_free_vmemmap_param(char *buf) +{ + /* We cannot optimize if a "struct page" crosses page boundaries. */ + if ((!is_power_of_2(sizeof(struct page)))) { + pr_warn("cannot free vmemmap pages because \"struct page\" crosses page boundaries\n"); + return 0; + } + + if (!buf) + return -EINVAL; + + if (!strcmp(buf, "on")) + hugetlb_free_vmemmap_enabled = true; + else if (!strcmp(buf, "off")) + hugetlb_free_vmemmap_enabled = false; + else + return -EINVAL; + + return 0; +} +early_param("hugetlb_free_vmemmap", early_hugetlb_free_vmemmap_param); + +static inline unsigned long free_vmemmap_pages_size_per_hpage(struct hstate *h) +{ + return (unsigned long)free_vmemmap_pages_per_hpage(h) << PAGE_SHIFT; +} + +/* + * Previously discarded vmemmap pages will be allocated and remapping + * after this function returns zero. + */ +int alloc_huge_page_vmemmap(struct hstate *h, struct page *head) +{ + int ret; + unsigned long vmemmap_addr = (unsigned long)head; + unsigned long vmemmap_end, vmemmap_reuse; + + if (!HPageVmemmapOptimized(head)) + return 0; + + vmemmap_addr += RESERVE_VMEMMAP_SIZE; + vmemmap_end = vmemmap_addr + free_vmemmap_pages_size_per_hpage(h); + vmemmap_reuse = vmemmap_addr - PAGE_SIZE; + /* + * The pages which the vmemmap virtual address range [@vmemmap_addr, + * @vmemmap_end) are mapped to are freed to the buddy allocator, and + * the range is mapped to the page which @vmemmap_reuse is mapped to. + * When a HugeTLB page is freed to the buddy allocator, previously + * discarded vmemmap pages must be allocated and remapping. + */ + ret = vmemmap_remap_alloc(vmemmap_addr, vmemmap_end, vmemmap_reuse, + GFP_KERNEL | __GFP_NORETRY | __GFP_THISNODE); + + if (!ret) + ClearHPageVmemmapOptimized(head); + + return ret; +} + +void free_huge_page_vmemmap(struct hstate *h, struct page *head) +{ + unsigned long vmemmap_addr = (unsigned long)head; + unsigned long vmemmap_end, vmemmap_reuse; + + if (!free_vmemmap_pages_per_hpage(h)) + return; + + vmemmap_addr += RESERVE_VMEMMAP_SIZE; + vmemmap_end = vmemmap_addr + free_vmemmap_pages_size_per_hpage(h); + vmemmap_reuse = vmemmap_addr - PAGE_SIZE; + + /* + * Remap the vmemmap virtual address range [@vmemmap_addr, @vmemmap_end) + * to the page which @vmemmap_reuse is mapped to, then free the pages + * which the range [@vmemmap_addr, @vmemmap_end] is mapped to. + */ + if (!vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse)) + SetHPageVmemmapOptimized(head); +} + +void __init hugetlb_vmemmap_init(struct hstate *h) +{ + unsigned int nr_pages = pages_per_huge_page(h); + unsigned int vmemmap_pages; + + /* + * There are only (RESERVE_VMEMMAP_SIZE / sizeof(struct page)) struct + * page structs that can be used when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP, + * so add a BUILD_BUG_ON to catch invalid usage of the tail struct page. + */ + BUILD_BUG_ON(__NR_USED_SUBPAGE >= + RESERVE_VMEMMAP_SIZE / sizeof(struct page)); + + if (!hugetlb_free_vmemmap_enabled) + return; + + vmemmap_pages = (nr_pages * sizeof(struct page)) >> PAGE_SHIFT; + /* + * The head page and the first tail page are not to be freed to buddy + * allocator, the other pages will map to the first tail page, so they + * can be freed. + * + * Could RESERVE_VMEMMAP_NR be greater than @vmemmap_pages? It is true + * on some architectures (e.g. aarch64). See Documentation/arm64/ + * hugetlbpage.rst for more details. + */ + if (likely(vmemmap_pages > RESERVE_VMEMMAP_NR)) + h->nr_free_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR; + + pr_info("can free %d vmemmap pages for %s\n", h->nr_free_vmemmap_pages, + h->name); +} diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h new file mode 100644 index 000000000000..cb2bef8f9e73 --- /dev/null +++ b/mm/hugetlb_vmemmap.h @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Free some vmemmap pages of HugeTLB + * + * Copyright (c) 2020, Bytedance. All rights reserved. + * + * Author: Muchun Song <songmuchun@bytedance.com> + */ +#ifndef _LINUX_HUGETLB_VMEMMAP_H +#define _LINUX_HUGETLB_VMEMMAP_H +#include <linux/hugetlb.h> + +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP +int alloc_huge_page_vmemmap(struct hstate *h, struct page *head); +void free_huge_page_vmemmap(struct hstate *h, struct page *head); +void hugetlb_vmemmap_init(struct hstate *h); + +/* + * How many vmemmap pages associated with a HugeTLB page that can be freed + * to the buddy allocator. + */ +static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h) +{ + return h->nr_free_vmemmap_pages; +} +#else +static inline int alloc_huge_page_vmemmap(struct hstate *h, struct page *head) +{ + return 0; +} + +static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head) +{ +} + +static inline void hugetlb_vmemmap_init(struct hstate *h) +{ +} + +static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h) +{ + return 0; +} +#endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */ +#endif /* _LINUX_HUGETLB_VMEMMAP_H */ diff --git a/mm/internal.h b/mm/internal.h index 54bd0dc2c23c..2d7c9a2e0118 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -96,26 +96,6 @@ static inline void set_page_refcounted(struct page *page) set_page_count(page, 1); } -/* - * When kernel touch the user page, the user page may be have been marked - * poison but still mapped in user space, if without this page, the kernel - * can guarantee the data integrity and operation success, the kernel is - * better to check the posion status and avoid touching it, be good not to - * panic, coredump for process fatal signal is a sample case matching this - * scenario. Or if kernel can't guarantee the data integrity, it's better - * not to call this function, let kernel touch the poison page and get to - * panic. - */ -static inline bool is_page_poisoned(struct page *page) -{ - if (PageHWPoison(page)) - return true; - else if (PageHuge(page) && PageHWPoison(compound_head(page))) - return true; - - return false; -} - extern unsigned long highest_memmap_pfn; /* @@ -136,6 +116,11 @@ extern void putback_lru_page(struct page *page); extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); /* + * in mm/memcontrol.c: + */ +extern bool cgroup_memory_nokmem; + +/* * in mm/page_alloc.c */ @@ -218,10 +203,10 @@ extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern int user_min_free_kbytes; -extern void free_unref_page(struct page *page); +extern void free_unref_page(struct page *page, unsigned int order); extern void free_unref_page_list(struct list_head *list); -extern void zone_pcp_update(struct zone *zone); +extern void zone_pcp_update(struct zone *zone, int cpu_online); extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); extern void zone_pcp_enable(struct zone *zone); @@ -289,11 +274,10 @@ isolate_freepages_range(struct compact_control *cc, int isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); +#endif int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool only_stealable, bool *can_steal); -#endif - /* * This function returns the order of a free page in the buddy system. In * general, page_zone(page)->lock must be held by the caller to prevent the @@ -359,7 +343,10 @@ void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma); #ifdef CONFIG_MMU extern long populate_vma_page_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, int *nonblocking); + unsigned long start, unsigned long end, int *locked); +extern long faultin_vma_page_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, + bool write, int *locked); extern void munlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); static inline void munlock_vma_pages_all(struct vm_area_struct *vma) @@ -384,47 +371,55 @@ extern unsigned int munlock_vma_page(struct page *page); */ extern void clear_page_mlock(struct page *page); -/* - * mlock_migrate_page - called only from migrate_misplaced_transhuge_page() - * (because that does not go through the full procedure of migration ptes): - * to migrate the Mlocked page flag; update statistics. - */ -static inline void mlock_migrate_page(struct page *newpage, struct page *page) -{ - if (TestClearPageMlocked(page)) { - int nr_pages = thp_nr_pages(page); - - /* Holding pmd lock, no change in irq context: __mod is safe */ - __mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages); - SetPageMlocked(newpage); - __mod_zone_page_state(page_zone(newpage), NR_MLOCK, nr_pages); - } -} - extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /* - * At what user virtual address is page expected in @vma? + * At what user virtual address is page expected in vma? + * Returns -EFAULT if all of the page is outside the range of vma. + * If page is a compound head, the entire compound page is considered. */ static inline unsigned long -__vma_address(struct page *page, struct vm_area_struct *vma) +vma_address(struct page *page, struct vm_area_struct *vma) { - pgoff_t pgoff = page_to_pgoff(page); - return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + pgoff_t pgoff; + unsigned long address; + + VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ + pgoff = page_to_pgoff(page); + if (pgoff >= vma->vm_pgoff) { + address = vma->vm_start + + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + /* Check for address beyond vma (or wrapped through 0?) */ + if (address < vma->vm_start || address >= vma->vm_end) + address = -EFAULT; + } else if (PageHead(page) && + pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) { + /* Test above avoids possibility of wrap to 0 on 32-bit */ + address = vma->vm_start; + } else { + address = -EFAULT; + } + return address; } +/* + * Then at what user virtual address will none of the page be found in vma? + * Assumes that vma_address() already returned a good starting address. + * If page is a compound head, the entire compound page is considered. + */ static inline unsigned long -vma_address(struct page *page, struct vm_area_struct *vma) +vma_address_end(struct page *page, struct vm_area_struct *vma) { - unsigned long start, end; - - start = __vma_address(page, vma); - end = start + thp_size(page) - PAGE_SIZE; - - /* page should be within @vma mapping range */ - VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma); - - return max(start, vma->vm_start); + pgoff_t pgoff; + unsigned long address; + + VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ + pgoff = page_to_pgoff(page) + compound_nr(page); + address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + /* Check for address beyond vma (or wrapped through 0?) */ + if (address < vma->vm_start || address > vma->vm_end) + address = vma->vm_end; + return address; } static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, @@ -451,7 +446,6 @@ static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, #else /* !CONFIG_MMU */ static inline void clear_page_mlock(struct page *page) { } static inline void mlock_vma_page(struct page *page) { } -static inline void mlock_migrate_page(struct page *new, struct page *old) { } static inline void vunmap_range_noflush(unsigned long start, unsigned long end) { } @@ -662,4 +656,7 @@ int vmap_pages_range_noflush(unsigned long addr, unsigned long end, void vunmap_range_noflush(unsigned long start, unsigned long end); +int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, + unsigned long addr, int page_nid, int *flags); + #endif /* __MM_INTERNAL_H */ diff --git a/mm/ioremap.c b/mm/ioremap.c index d1dcc7e744ac..8ee0136f8cb0 100644 --- a/mm/ioremap.c +++ b/mm/ioremap.c @@ -16,16 +16,16 @@ #include "pgalloc-track.h" #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP -static bool __ro_after_init iomap_max_page_shift = PAGE_SHIFT; +static unsigned int __ro_after_init iomap_max_page_shift = BITS_PER_LONG - 1; static int __init set_nohugeiomap(char *str) { - iomap_max_page_shift = P4D_SHIFT; + iomap_max_page_shift = PAGE_SHIFT; return 0; } early_param("nohugeiomap", set_nohugeiomap); #else /* CONFIG_HAVE_ARCH_HUGE_VMAP */ -static const bool iomap_max_page_shift = PAGE_SHIFT; +static const unsigned int iomap_max_page_shift = PAGE_SHIFT; #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ int ioremap_page_range(unsigned long addr, diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile index 9fe39a66388a..adcd9acaef61 100644 --- a/mm/kasan/Makefile +++ b/mm/kasan/Makefile @@ -37,5 +37,5 @@ CFLAGS_sw_tags.o := $(CC_FLAGS_KASAN_RUNTIME) obj-$(CONFIG_KASAN) := common.o report.o obj-$(CONFIG_KASAN_GENERIC) += init.o generic.o report_generic.o shadow.o quarantine.o -obj-$(CONFIG_KASAN_HW_TAGS) += hw_tags.o report_hw_tags.o -obj-$(CONFIG_KASAN_SW_TAGS) += init.o report_sw_tags.o shadow.o sw_tags.o +obj-$(CONFIG_KASAN_HW_TAGS) += hw_tags.o report_hw_tags.o tags.o report_tags.o +obj-$(CONFIG_KASAN_SW_TAGS) += init.o report_sw_tags.o shadow.o sw_tags.o tags.o report_tags.o diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 6bb87f2acd4e..2baf121fb8c5 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -51,11 +51,14 @@ void kasan_enable_current(void) { current->kasan_depth++; } +EXPORT_SYMBOL(kasan_enable_current); void kasan_disable_current(void) { current->kasan_depth--; } +EXPORT_SYMBOL(kasan_disable_current); + #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ void __kasan_unpoison_range(const void *address, size_t size) @@ -97,7 +100,7 @@ slab_flags_t __kasan_never_merge(void) return 0; } -void __kasan_alloc_pages(struct page *page, unsigned int order, bool init) +void __kasan_unpoison_pages(struct page *page, unsigned int order, bool init) { u8 tag; unsigned long i; @@ -111,7 +114,7 @@ void __kasan_alloc_pages(struct page *page, unsigned int order, bool init) kasan_unpoison(page_address(page), PAGE_SIZE << order, init); } -void __kasan_free_pages(struct page *page, unsigned int order, bool init) +void __kasan_poison_pages(struct page *page, unsigned int order, bool init) { if (likely(!PageHighMem(page))) kasan_poison(page_address(page), PAGE_SIZE << order, @@ -328,6 +331,9 @@ static inline bool ____kasan_slab_free(struct kmem_cache *cache, void *object, u8 tag; void *tagged_object; + if (!kasan_arch_is_ready()) + return false; + tag = get_tag(object); tagged_object = object; object = kasan_reset_tag(object); diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c index 53cbf28859b5..c3f5ba7a294a 100644 --- a/mm/kasan/generic.c +++ b/mm/kasan/generic.c @@ -163,6 +163,9 @@ static __always_inline bool check_region_inline(unsigned long addr, size_t size, bool write, unsigned long ret_ip) { + if (!kasan_arch_is_ready()) + return true; + if (unlikely(size == 0)) return true; diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index 4004388b4e4b..4ea8c368b5b8 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -216,26 +216,36 @@ void __init kasan_init_hw_tags(void) pr_info("KernelAddressSanitizer initialized\n"); } -void kasan_set_free_info(struct kmem_cache *cache, - void *object, u8 tag) +void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags) { - struct kasan_alloc_meta *alloc_meta; + /* + * This condition should match the one in post_alloc_hook() in + * page_alloc.c. + */ + bool init = !want_init_on_free() && want_init_on_alloc(flags); + + if (flags & __GFP_SKIP_KASAN_POISON) + SetPageSkipKASanPoison(page); + + if (flags & __GFP_ZEROTAGS) { + int i; - alloc_meta = kasan_get_alloc_meta(cache, object); - if (alloc_meta) - kasan_set_track(&alloc_meta->free_track[0], GFP_NOWAIT); + for (i = 0; i != 1 << order; ++i) + tag_clear_highpage(page + i); + } else { + kasan_unpoison_pages(page, order, init); + } } -struct kasan_track *kasan_get_free_track(struct kmem_cache *cache, - void *object, u8 tag) +void kasan_free_pages(struct page *page, unsigned int order) { - struct kasan_alloc_meta *alloc_meta; - - alloc_meta = kasan_get_alloc_meta(cache, object); - if (!alloc_meta) - return NULL; + /* + * This condition should match the one in free_pages_prepare() in + * page_alloc.c. + */ + bool init = want_init_on_free(); - return &alloc_meta->free_track[0]; + kasan_poison_pages(page, order, init); } #if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) diff --git a/mm/kasan/init.c b/mm/kasan/init.c index c4605ac9837b..cc64ed6858c6 100644 --- a/mm/kasan/init.c +++ b/mm/kasan/init.c @@ -41,7 +41,7 @@ static inline bool kasan_p4d_table(pgd_t pgd) } #endif #if CONFIG_PGTABLE_LEVELS > 3 -pud_t kasan_early_shadow_pud[PTRS_PER_PUD] __page_aligned_bss; +pud_t kasan_early_shadow_pud[MAX_PTRS_PER_PUD] __page_aligned_bss; static inline bool kasan_pud_table(p4d_t p4d) { return p4d_page(p4d) == virt_to_page(lm_alias(kasan_early_shadow_pud)); @@ -53,7 +53,7 @@ static inline bool kasan_pud_table(p4d_t p4d) } #endif #if CONFIG_PGTABLE_LEVELS > 2 -pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD] __page_aligned_bss; +pmd_t kasan_early_shadow_pmd[MAX_PTRS_PER_PMD] __page_aligned_bss; static inline bool kasan_pmd_table(pud_t pud) { return pud_page(pud) == virt_to_page(lm_alias(kasan_early_shadow_pmd)); @@ -64,7 +64,7 @@ static inline bool kasan_pmd_table(pud_t pud) return false; } #endif -pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS] +pte_t kasan_early_shadow_pte[MAX_PTRS_PER_PTE + PTE_HWTABLE_PTRS] __page_aligned_bss; static inline bool kasan_pte_table(pmd_t pmd) @@ -220,8 +220,8 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr, /** * kasan_populate_early_shadow - populate shadow memory region with * kasan_early_shadow_page - * @shadow_start - start of the memory range to populate - * @shadow_end - end of the memory range to populate + * @shadow_start: start of the memory range to populate + * @shadow_end: end of the memory range to populate */ int __ref kasan_populate_early_shadow(const void *shadow_start, const void *shadow_end) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 8f450bc28045..98e3059bfea4 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -153,7 +153,7 @@ struct kasan_track { depot_stack_handle_t stack; }; -#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY +#if defined(CONFIG_KASAN_TAGS_IDENTIFY) && defined(CONFIG_KASAN_SW_TAGS) #define KASAN_NR_FREE_STACKS 5 #else #define KASAN_NR_FREE_STACKS 1 @@ -170,7 +170,7 @@ struct kasan_alloc_meta { #else struct kasan_track free_track[KASAN_NR_FREE_STACKS]; #endif -#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY +#ifdef CONFIG_KASAN_TAGS_IDENTIFY u8 free_pointer_tag[KASAN_NR_FREE_STACKS]; u8 free_track_idx; #endif @@ -449,6 +449,12 @@ static inline void kasan_poison_last_granule(const void *address, size_t size) { #endif /* CONFIG_KASAN_GENERIC */ +#ifndef kasan_arch_is_ready +static inline bool kasan_arch_is_ready(void) { return true; } +#elif !defined(CONFIG_KASAN_GENERIC) || !defined(CONFIG_KASAN_OUTLINE) +#error kasan_arch_is_ready only works in KASAN generic outline mode! +#endif + /* * Exported functions for interfaces called from assembly or from generated * code. Declarations here to avoid warning about missing declarations. diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 14bd51ea2348..8fff1825b22c 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -230,7 +230,7 @@ static void print_address_description(void *addr, u8 tag) { struct page *page = kasan_addr_to_page(addr); - dump_stack(); + dump_stack_lvl(KERN_ERR); pr_err("\n"); if (page && PageSlab(page)) { @@ -375,7 +375,7 @@ void kasan_report_async(void) pr_err("BUG: KASAN: invalid-access\n"); pr_err("Asynchronous mode enabled: no access details available\n"); pr_err("\n"); - dump_stack(); + dump_stack_lvl(KERN_ERR); end_report(&flags, 0); } #endif /* CONFIG_KASAN_HW_TAGS */ @@ -420,7 +420,7 @@ static void __kasan_report(unsigned long addr, size_t size, bool is_write, pr_err("\n"); print_memory_metadata(info.first_bad_addr); } else { - dump_stack(); + dump_stack_lvl(KERN_ERR); } end_report(&flags, addr); diff --git a/mm/kasan/report_hw_tags.c b/mm/kasan/report_hw_tags.c index 42b2168755d6..5dbbbb930e7a 100644 --- a/mm/kasan/report_hw_tags.c +++ b/mm/kasan/report_hw_tags.c @@ -15,11 +15,6 @@ #include "kasan.h" -const char *kasan_get_bug_type(struct kasan_access_info *info) -{ - return "invalid-access"; -} - void *kasan_find_first_bad_addr(void *addr, size_t size) { return kasan_reset_tag(addr); diff --git a/mm/kasan/report_sw_tags.c b/mm/kasan/report_sw_tags.c index 3d20d3451d9e..d2298c357834 100644 --- a/mm/kasan/report_sw_tags.c +++ b/mm/kasan/report_sw_tags.c @@ -29,49 +29,6 @@ #include "kasan.h" #include "../slab.h" -const char *kasan_get_bug_type(struct kasan_access_info *info) -{ -#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY - struct kasan_alloc_meta *alloc_meta; - struct kmem_cache *cache; - struct page *page; - const void *addr; - void *object; - u8 tag; - int i; - - tag = get_tag(info->access_addr); - addr = kasan_reset_tag(info->access_addr); - page = kasan_addr_to_page(addr); - if (page && PageSlab(page)) { - cache = page->slab_cache; - object = nearest_obj(cache, page, (void *)addr); - alloc_meta = kasan_get_alloc_meta(cache, object); - - if (alloc_meta) { - for (i = 0; i < KASAN_NR_FREE_STACKS; i++) { - if (alloc_meta->free_pointer_tag[i] == tag) - return "use-after-free"; - } - } - return "out-of-bounds"; - } - -#endif - /* - * If access_size is a negative number, then it has reason to be - * defined as out-of-bounds bug type. - * - * Casting negative numbers to size_t would indeed turn up as - * a large size_t and its value will be larger than ULONG_MAX/2, - * so that this can qualify as out-of-bounds. - */ - if (info->access_addr + info->access_size < info->access_addr) - return "out-of-bounds"; - - return "invalid-access"; -} - void *kasan_find_first_bad_addr(void *addr, size_t size) { u8 tag = get_tag(addr); diff --git a/mm/kasan/report_tags.c b/mm/kasan/report_tags.c new file mode 100644 index 000000000000..8a319fc16dab --- /dev/null +++ b/mm/kasan/report_tags.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * Copyright (c) 2020 Google, Inc. + */ + +#include "kasan.h" +#include "../slab.h" + +const char *kasan_get_bug_type(struct kasan_access_info *info) +{ +#ifdef CONFIG_KASAN_TAGS_IDENTIFY + struct kasan_alloc_meta *alloc_meta; + struct kmem_cache *cache; + struct page *page; + const void *addr; + void *object; + u8 tag; + int i; + + tag = get_tag(info->access_addr); + addr = kasan_reset_tag(info->access_addr); + page = kasan_addr_to_page(addr); + if (page && PageSlab(page)) { + cache = page->slab_cache; + object = nearest_obj(cache, page, (void *)addr); + alloc_meta = kasan_get_alloc_meta(cache, object); + + if (alloc_meta) { + for (i = 0; i < KASAN_NR_FREE_STACKS; i++) { + if (alloc_meta->free_pointer_tag[i] == tag) + return "use-after-free"; + } + } + return "out-of-bounds"; + } +#endif + + /* + * If access_size is a negative number, then it has reason to be + * defined as out-of-bounds bug type. + * + * Casting negative numbers to size_t would indeed turn up as + * a large size_t and its value will be larger than ULONG_MAX/2, + * so that this can qualify as out-of-bounds. + */ + if (info->access_addr + info->access_size < info->access_addr) + return "out-of-bounds"; + + return "invalid-access"; +} diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 082ee5b6d9a1..8d95ee52d019 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -73,6 +73,9 @@ void kasan_poison(const void *addr, size_t size, u8 value, bool init) { void *shadow_start, *shadow_end; + if (!kasan_arch_is_ready()) + return; + /* * Perform shadow offset calculation based on untagged address, as * some of the callers (e.g. kasan_poison_object_data) pass tagged @@ -99,6 +102,9 @@ EXPORT_SYMBOL(kasan_poison); #ifdef CONFIG_KASAN_GENERIC void kasan_poison_last_granule(const void *addr, size_t size) { + if (!kasan_arch_is_ready()) + return; + if (size & KASAN_GRANULE_MASK) { u8 *shadow = (u8 *)kasan_mem_to_shadow(addr + size); *shadow = size & KASAN_GRANULE_MASK; diff --git a/mm/kasan/sw_tags.c b/mm/kasan/sw_tags.c index 9df8e7f69e87..bd3f540feb47 100644 --- a/mm/kasan/sw_tags.c +++ b/mm/kasan/sw_tags.c @@ -167,43 +167,9 @@ void __hwasan_tag_memory(unsigned long addr, u8 tag, unsigned long size) } EXPORT_SYMBOL(__hwasan_tag_memory); -void kasan_set_free_info(struct kmem_cache *cache, - void *object, u8 tag) +void kasan_tag_mismatch(unsigned long addr, unsigned long access_info, + unsigned long ret_ip) { - struct kasan_alloc_meta *alloc_meta; - u8 idx = 0; - - alloc_meta = kasan_get_alloc_meta(cache, object); - if (!alloc_meta) - return; - -#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY - idx = alloc_meta->free_track_idx; - alloc_meta->free_pointer_tag[idx] = tag; - alloc_meta->free_track_idx = (idx + 1) % KASAN_NR_FREE_STACKS; -#endif - - kasan_set_track(&alloc_meta->free_track[idx], GFP_NOWAIT); -} - -struct kasan_track *kasan_get_free_track(struct kmem_cache *cache, - void *object, u8 tag) -{ - struct kasan_alloc_meta *alloc_meta; - int i = 0; - - alloc_meta = kasan_get_alloc_meta(cache, object); - if (!alloc_meta) - return NULL; - -#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY - for (i = 0; i < KASAN_NR_FREE_STACKS; i++) { - if (alloc_meta->free_pointer_tag[i] == tag) - break; - } - if (i == KASAN_NR_FREE_STACKS) - i = alloc_meta->free_track_idx; -#endif - - return &alloc_meta->free_track[i]; + kasan_report(addr, 1 << (access_info & 0xf), access_info & 0x10, + ret_ip); } diff --git a/mm/kasan/tags.c b/mm/kasan/tags.c new file mode 100644 index 000000000000..8f48b9502a17 --- /dev/null +++ b/mm/kasan/tags.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This file contains common tag-based KASAN code. + * + * Copyright (c) 2018 Google, Inc. + * Copyright (c) 2020 Google, Inc. + */ + +#include <linux/init.h> +#include <linux/kasan.h> +#include <linux/kernel.h> +#include <linux/memory.h> +#include <linux/mm.h> +#include <linux/static_key.h> +#include <linux/string.h> +#include <linux/types.h> + +#include "kasan.h" + +void kasan_set_free_info(struct kmem_cache *cache, + void *object, u8 tag) +{ + struct kasan_alloc_meta *alloc_meta; + u8 idx = 0; + + alloc_meta = kasan_get_alloc_meta(cache, object); + if (!alloc_meta) + return; + +#ifdef CONFIG_KASAN_TAGS_IDENTIFY + idx = alloc_meta->free_track_idx; + alloc_meta->free_pointer_tag[idx] = tag; + alloc_meta->free_track_idx = (idx + 1) % KASAN_NR_FREE_STACKS; +#endif + + kasan_set_track(&alloc_meta->free_track[idx], GFP_NOWAIT); +} + +struct kasan_track *kasan_get_free_track(struct kmem_cache *cache, + void *object, u8 tag) +{ + struct kasan_alloc_meta *alloc_meta; + int i = 0; + + alloc_meta = kasan_get_alloc_meta(cache, object); + if (!alloc_meta) + return NULL; + +#ifdef CONFIG_KASAN_TAGS_IDENTIFY + for (i = 0; i < KASAN_NR_FREE_STACKS; i++) { + if (alloc_meta->free_pointer_tag[i] == tag) + break; + } + if (i == KASAN_NR_FREE_STACKS) + i = alloc_meta->free_track_idx; +#endif + + return &alloc_meta->free_track[i]; +} diff --git a/mm/kfence/core.c b/mm/kfence/core.c index e18fbbd5d9b4..d7666ace9d2e 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -627,16 +627,16 @@ static void toggle_allocation_gate(struct work_struct *work) * During low activity with no allocations we might wait a * while; let's avoid the hung task warning. */ - wait_event_timeout(allocation_wait, atomic_read(&kfence_allocation_gate), - sysctl_hung_task_timeout_secs * HZ / 2); + wait_event_idle_timeout(allocation_wait, atomic_read(&kfence_allocation_gate), + sysctl_hung_task_timeout_secs * HZ / 2); } else { - wait_event(allocation_wait, atomic_read(&kfence_allocation_gate)); + wait_event_idle(allocation_wait, atomic_read(&kfence_allocation_gate)); } /* Disable static key and reset timer. */ static_branch_disable(&kfence_allocation_key); #endif - queue_delayed_work(system_power_efficient_wq, &kfence_timer, + queue_delayed_work(system_unbound_wq, &kfence_timer, msecs_to_jiffies(kfence_sample_interval)); } static DECLARE_DELAYED_WORK(kfence_timer, toggle_allocation_gate); @@ -666,7 +666,7 @@ void __init kfence_init(void) } WRITE_ONCE(kfence_enabled, true); - queue_delayed_work(system_power_efficient_wq, &kfence_timer, 0); + queue_delayed_work(system_unbound_wq, &kfence_timer, 0); pr_info("initialized - using %lu bytes for %d objects at 0x%p-0x%p\n", KFENCE_POOL_SIZE, CONFIG_KFENCE_NUM_OBJECTS, (void *)__kfence_pool, (void *)(__kfence_pool + KFENCE_POOL_SIZE)); diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c index 4acf4251ee04..7f24b9bcb2ec 100644 --- a/mm/kfence/kfence_test.c +++ b/mm/kfence/kfence_test.c @@ -197,7 +197,7 @@ static void test_cache_destroy(void) static inline size_t kmalloc_cache_alignment(size_t size) { - return kmalloc_caches[kmalloc_type(GFP_KERNEL)][kmalloc_index(size)]->align; + return kmalloc_caches[kmalloc_type(GFP_KERNEL)][__kmalloc_index(size, false)]->align; } /* Must always inline to match stack trace against caller. */ @@ -267,7 +267,8 @@ static void *test_alloc(struct kunit *test, size_t size, gfp_t gfp, enum allocat if (is_kfence_address(alloc)) { struct page *page = virt_to_head_page(alloc); - struct kmem_cache *s = test_cache ?: kmalloc_caches[kmalloc_type(GFP_KERNEL)][kmalloc_index(size)]; + struct kmem_cache *s = test_cache ?: + kmalloc_caches[kmalloc_type(GFP_KERNEL)][__kmalloc_index(size, false)]; /* * Verify that various helpers return the right values diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 6c0185fdd815..b0412be08fa2 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -442,9 +442,7 @@ static inline int khugepaged_test_exit(struct mm_struct *mm) static bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags) { - /* Explicitly disabled through madvise. */ - if ((vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + if (!transhuge_vma_enabled(vma, vm_flags)) return false; /* Enabled via shmem mount options or sysfs settings. */ @@ -459,7 +457,8 @@ static bool hugepage_vma_check(struct vm_area_struct *vma, /* Read-only file mappings need to be aligned for THP to work. */ if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && vma->vm_file && - (vm_flags & VM_DENYWRITE)) { + !inode_is_open_for_write(vma->vm_file->f_inode) && + (vm_flags & VM_EXEC)) { return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, HPAGE_PMD_NR); } @@ -1864,6 +1863,19 @@ out_unlock: else { __mod_lruvec_page_state(new_page, NR_FILE_THPS, nr); filemap_nr_thps_inc(mapping); + /* + * Paired with smp_mb() in do_dentry_open() to ensure + * i_writecount is up to date and the update to nr_thps is + * visible. Ensures the page cache will be truncated if the + * file is opened writable. + */ + smp_mb(); + if (inode_is_open_for_write(mapping->host)) { + result = SCAN_FAIL; + __mod_lruvec_page_state(new_page, NR_FILE_THPS, -nr); + filemap_nr_thps_dec(mapping); + goto xa_locked; + } } if (nr_none) { diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 92a2d4885808..228a2fbe0657 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -219,7 +219,7 @@ static struct task_struct *scan_thread; static unsigned long jiffies_min_age; static unsigned long jiffies_last_scan; /* delay between automatic memory scannings */ -static signed long jiffies_scan_wait; +static unsigned long jiffies_scan_wait; /* enables or disables the task stacks scanning */ static int kmemleak_stack_scan = 1; /* protects the memory scanning, parameters and debug/kmemleak file access */ @@ -1567,7 +1567,7 @@ static int kmemleak_scan_thread(void *arg) } while (!kthread_should_stop()) { - signed long timeout = jiffies_scan_wait; + signed long timeout = READ_ONCE(jiffies_scan_wait); mutex_lock(&scan_mutex); kmemleak_scan(); @@ -1807,14 +1807,20 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, else if (strncmp(buf, "scan=off", 8) == 0) stop_scan_thread(); else if (strncmp(buf, "scan=", 5) == 0) { - unsigned long secs; + unsigned secs; + unsigned long msecs; - ret = kstrtoul(buf + 5, 0, &secs); + ret = kstrtouint(buf + 5, 0, &secs); if (ret < 0) goto out; + + msecs = secs * MSEC_PER_SEC; + if (msecs > UINT_MAX) + msecs = UINT_MAX; + stop_scan_thread(); - if (secs) { - jiffies_scan_wait = msecs_to_jiffies(secs * 1000); + if (msecs) { + WRITE_ONCE(jiffies_scan_wait, msecs_to_jiffies(msecs)); start_scan_thread(); } } else if (strncmp(buf, "scan", 4) == 0) @@ -521,10 +521,8 @@ static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm, struct vm_area_struct *vma; if (ksm_test_exit(mm)) return NULL; - vma = find_vma(mm, addr); - if (!vma || vma->vm_start > addr) - return NULL; - if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) + vma = vma_lookup(mm, addr); + if (!vma || !(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) return NULL; return vma; } @@ -776,11 +774,12 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item) struct page *page; stable_node = rmap_item->head; - page = get_ksm_page(stable_node, GET_KSM_PAGE_NOLOCK); + page = get_ksm_page(stable_node, GET_KSM_PAGE_LOCK); if (!page) goto out; hlist_del(&rmap_item->hlist); + unlock_page(page); put_page(page); if (!hlist_empty(&stable_node->hlist)) diff --git a/mm/madvise.c b/mm/madvise.c index 63e489e5bfdb..6d3d348b17f4 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -53,6 +53,8 @@ static int madvise_need_mmap_write(int behavior) case MADV_COLD: case MADV_PAGEOUT: case MADV_FREE: + case MADV_POPULATE_READ: + case MADV_POPULATE_WRITE: return 0; default: /* be safe, default to 1. list exceptions explicitly */ @@ -822,6 +824,61 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, return -EINVAL; } +static long madvise_populate(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end, + int behavior) +{ + const bool write = behavior == MADV_POPULATE_WRITE; + struct mm_struct *mm = vma->vm_mm; + unsigned long tmp_end; + int locked = 1; + long pages; + + *prev = vma; + + while (start < end) { + /* + * We might have temporarily dropped the lock. For example, + * our VMA might have been split. + */ + if (!vma || start >= vma->vm_end) { + vma = find_vma(mm, start); + if (!vma || start < vma->vm_start) + return -ENOMEM; + } + + tmp_end = min_t(unsigned long, end, vma->vm_end); + /* Populate (prefault) page tables readable/writable. */ + pages = faultin_vma_page_range(vma, start, tmp_end, write, + &locked); + if (!locked) { + mmap_read_lock(mm); + locked = 1; + *prev = NULL; + vma = NULL; + } + if (pages < 0) { + switch (pages) { + case -EINTR: + return -EINTR; + case -EFAULT: /* Incompatible mappings / permissions. */ + return -EINVAL; + case -EHWPOISON: + return -EHWPOISON; + default: + pr_warn_once("%s: unhandled return value: %ld\n", + __func__, pages); + fallthrough; + case -ENOMEM: + return -ENOMEM; + } + } + start += pages * PAGE_SIZE; + } + return 0; +} + /* * Application wants to free up the pages and associated backing store. * This is effectively punching a hole into the middle of a file. @@ -935,6 +992,9 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, case MADV_FREE: case MADV_DONTNEED: return madvise_dontneed_free(vma, prev, start, end, behavior); + case MADV_POPULATE_READ: + case MADV_POPULATE_WRITE: + return madvise_populate(vma, prev, start, end, behavior); default: return madvise_behavior(vma, prev, start, end, behavior); } @@ -955,6 +1015,8 @@ madvise_behavior_valid(int behavior) case MADV_FREE: case MADV_COLD: case MADV_PAGEOUT: + case MADV_POPULATE_READ: + case MADV_POPULATE_WRITE: #ifdef CONFIG_KSM case MADV_MERGEABLE: case MADV_UNMERGEABLE: @@ -1042,6 +1104,10 @@ process_madvise_behavior_valid(int behavior) * easily if memory pressure happens. * MADV_PAGEOUT - the application is not expected to use this memory soon, * page out the pages in this range immediately. + * MADV_POPULATE_READ - populate (prefault) page tables readable by + * triggering read faults if required + * MADV_POPULATE_WRITE - populate (prefault) page tables writable by + * triggering write faults if required * * return values: * zero - success diff --git a/mm/mapping_dirty_helpers.c b/mm/mapping_dirty_helpers.c index b890854ec761..ea734f248fce 100644 --- a/mm/mapping_dirty_helpers.c +++ b/mm/mapping_dirty_helpers.c @@ -317,7 +317,7 @@ EXPORT_SYMBOL_GPL(wp_shared_mapping_range); * pfn_mkwrite(). And then after a TLB flush following the write-protection * pick up all dirty bits. * - * Note: This function currently skips transhuge page-table entries, since + * This function currently skips transhuge page-table entries, since * it's intended for dirty-tracking on the PTE level. It will warn on * encountering transhuge dirty entries, though, and can easily be extended * to handle them as well. diff --git a/mm/memblock.c b/mm/memblock.c index afaefa8fc6ab..0041ff62c584 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -92,7 +92,7 @@ * system initialization completes. */ -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA struct pglist_data __refdata contig_page_data; EXPORT_SYMBOL(contig_page_data); #endif @@ -182,6 +182,8 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type, { unsigned long i; + memblock_cap_size(base, &size); + for (i = 0; i < type->cnt; i++) if (memblock_addrs_overlap(base, size, type->regions[i].base, type->regions[i].size)) @@ -607,7 +609,7 @@ repeat: * area, insert that portion. */ if (rbase > base) { -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA WARN_ON(nid != memblock_get_region_node(rgn)); #endif WARN_ON(flags != rgn->flags); @@ -906,6 +908,11 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) * @base: the base phys addr of the region * @size: the size of the region * + * The memory regions marked with %MEMBLOCK_NOMAP will not be added to the + * direct mapping of the physical memory. These regions will still be + * covered by the memory map. The struct page representing NOMAP memory + * frames in the memory map will be PageReserved() + * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) @@ -1205,7 +1212,7 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid, int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, struct memblock_type *type, int nid) { -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA int start_rgn, end_rgn; int i, ret; @@ -1794,7 +1801,6 @@ bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t siz */ bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size) { - memblock_cap_size(base, &size); return memblock_overlaps_region(&memblock.reserved, base, size); } @@ -1849,7 +1855,7 @@ static void __init_memblock memblock_dump(struct memblock_type *type) size = rgn->size; end = base + size - 1; flags = rgn->flags; -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA if (memblock_get_region_node(rgn) != MAX_NUMNODES) snprintf(nid_buf, sizeof(nid_buf), " on node %d", memblock_get_region_node(rgn)); @@ -1941,14 +1947,13 @@ static void __init free_unused_memmap(void) * due to SPARSEMEM sections which aren't present. */ start = min(start, ALIGN(prev_end, PAGES_PER_SECTION)); -#else +#endif /* - * Align down here since the VM subsystem insists that the - * memmap entries are valid from the bank start aligned to - * MAX_ORDER_NR_PAGES. + * Align down here since many operations in VM subsystem + * presume that there are no holes in the memory map inside + * a pageblock */ - start = round_down(start, MAX_ORDER_NR_PAGES); -#endif + start = round_down(start, pageblock_nr_pages); /* * If we had a previous bank, and there is a space @@ -1958,16 +1963,18 @@ static void __init free_unused_memmap(void) free_memmap(prev_end, start); /* - * Align up here since the VM subsystem insists that the - * memmap entries are valid from the bank end aligned to - * MAX_ORDER_NR_PAGES. + * Align up here since many operations in VM subsystem + * presume that there are no holes in the memory map inside + * a pageblock */ - prev_end = ALIGN(end, MAX_ORDER_NR_PAGES); + prev_end = ALIGN(end, pageblock_nr_pages); } #ifdef CONFIG_SPARSEMEM - if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION)) + if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION)) { + prev_end = ALIGN(end, pageblock_nr_pages); free_memmap(prev_end, ALIGN(prev_end, PAGES_PER_SECTION)); + } #endif } @@ -2002,6 +2009,26 @@ static unsigned long __init __free_memory_core(phys_addr_t start, return end_pfn - start_pfn; } +static void __init memmap_init_reserved_pages(void) +{ + struct memblock_region *region; + phys_addr_t start, end; + u64 i; + + /* initialize struct pages for the reserved regions */ + for_each_reserved_mem_range(i, &start, &end) + reserve_bootmem_region(start, end); + + /* and also treat struct pages for the NOMAP regions as PageReserved */ + for_each_mem_region(region) { + if (memblock_is_nomap(region)) { + start = region->base; + end = start + region->size; + reserve_bootmem_region(start, end); + } + } +} + static unsigned long __init free_low_memory_core_early(void) { unsigned long count = 0; @@ -2010,8 +2037,7 @@ static unsigned long __init free_low_memory_core_early(void) memblock_clear_hotplug(0, -1); - for_each_reserved_mem_range(i, &start, &end) - reserve_bootmem_region(start, end); + memmap_init_reserved_pages(); /* * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 64ada9e650a5..ae1f5d0cb581 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -78,16 +78,17 @@ struct mem_cgroup *root_mem_cgroup __read_mostly; /* Active memory cgroup to use from an interrupt context */ DEFINE_PER_CPU(struct mem_cgroup *, int_active_memcg); +EXPORT_PER_CPU_SYMBOL_GPL(int_active_memcg); /* Socket memory accounting disabled? */ -static bool cgroup_memory_nosocket; +static bool cgroup_memory_nosocket __ro_after_init; /* Kernel memory accounting disabled? */ -static bool cgroup_memory_nokmem; +bool cgroup_memory_nokmem __ro_after_init; /* Whether the swap controller is active */ #ifdef CONFIG_MEMCG_SWAP -bool cgroup_memory_noswap __read_mostly; +bool cgroup_memory_noswap __ro_after_init; #else #define cgroup_memory_noswap 1 #endif @@ -255,13 +256,17 @@ struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr) #ifdef CONFIG_MEMCG_KMEM extern spinlock_t css_set_lock; +bool mem_cgroup_kmem_disabled(void) +{ + return cgroup_memory_nokmem; +} + static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg, unsigned int nr_pages); static void obj_cgroup_release(struct percpu_ref *ref) { struct obj_cgroup *objcg = container_of(ref, struct obj_cgroup, refcnt); - struct mem_cgroup *memcg; unsigned int nr_bytes; unsigned int nr_pages; unsigned long flags; @@ -290,12 +295,11 @@ static void obj_cgroup_release(struct percpu_ref *ref) WARN_ON_ONCE(nr_bytes & (PAGE_SIZE - 1)); nr_pages = nr_bytes >> PAGE_SHIFT; - spin_lock_irqsave(&css_set_lock, flags); - memcg = obj_cgroup_memcg(objcg); if (nr_pages) obj_cgroup_uncharge_pages(objcg, nr_pages); + + spin_lock_irqsave(&css_set_lock, flags); list_del(&objcg->list); - mem_cgroup_put(memcg); spin_unlock_irqrestore(&css_set_lock, flags); percpu_ref_exit(ref); @@ -330,17 +334,12 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg, spin_lock_irq(&css_set_lock); - /* Move active objcg to the parent's list */ - xchg(&objcg->memcg, parent); - css_get(&parent->css); - list_add(&objcg->list, &parent->objcg_list); - - /* Move already reparented objcgs to the parent's list */ - list_for_each_entry(iter, &memcg->objcg_list, list) { - css_get(&parent->css); - xchg(&iter->memcg, parent); - css_put(&memcg->css); - } + /* 1) Ready to reparent active objcg. */ + list_add(&objcg->list, &memcg->objcg_list); + /* 2) Reparent active objcg and already reparented objcgs to parent. */ + list_for_each_entry(iter, &memcg->objcg_list, list) + WRITE_ONCE(iter->memcg, parent); + /* 3) Move already reparented objcgs to the parent's list */ list_splice(&memcg->objcg_list, &parent->objcg_list); spin_unlock_irq(&css_set_lock); @@ -782,6 +781,24 @@ void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) rcu_read_unlock(); } +/* + * mod_objcg_mlstate() may be called with irq enabled, so + * mod_memcg_lruvec_state() should be used. + */ +static inline void mod_objcg_mlstate(struct obj_cgroup *objcg, + struct pglist_data *pgdat, + enum node_stat_item idx, int nr) +{ + struct mem_cgroup *memcg; + struct lruvec *lruvec; + + rcu_read_lock(); + memcg = obj_cgroup_memcg(objcg); + lruvec = mem_cgroup_lruvec(memcg, pgdat); + mod_memcg_lruvec_state(lruvec, idx, nr); + rcu_read_unlock(); +} + /** * __count_memcg_events - account VM events in a cgroup * @memcg: the memory cgroup @@ -886,13 +903,24 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) } EXPORT_SYMBOL(mem_cgroup_from_task); +static __always_inline struct mem_cgroup *active_memcg(void) +{ + if (in_interrupt()) + return this_cpu_read(int_active_memcg); + else + return current->active_memcg; +} + /** * get_mem_cgroup_from_mm: Obtain a reference on given mm_struct's memcg. * @mm: mm from which memcg should be extracted. It can be NULL. * - * Obtain a reference on mm->memcg and returns it if successful. Otherwise - * root_mem_cgroup is returned. However if mem_cgroup is disabled, NULL is - * returned. + * Obtain a reference on mm->memcg and returns it if successful. If mm + * is NULL, then the memcg is chosen as follows: + * 1) The active memcg, if set. + * 2) current->mm->memcg, if available + * 3) root memcg + * If mem_cgroup is disabled, NULL is returned. */ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { @@ -901,34 +929,38 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) if (mem_cgroup_disabled()) return NULL; + /* + * Page cache insertions can happen without an + * actual mm context, e.g. during disk probing + * on boot, loopback IO, acct() writes etc. + * + * No need to css_get on root memcg as the reference + * counting is disabled on the root level in the + * cgroup core. See CSS_NO_REF. + */ + if (unlikely(!mm)) { + memcg = active_memcg(); + if (unlikely(memcg)) { + /* remote memcg must hold a ref */ + css_get(&memcg->css); + return memcg; + } + mm = current->mm; + if (unlikely(!mm)) + return root_mem_cgroup; + } + rcu_read_lock(); do { - /* - * Page cache insertions can happen without an - * actual mm context, e.g. during disk probing - * on boot, loopback IO, acct() writes etc. - */ - if (unlikely(!mm)) + memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (unlikely(!memcg)) memcg = root_mem_cgroup; - else { - memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); - if (unlikely(!memcg)) - memcg = root_mem_cgroup; - } } while (!css_tryget(&memcg->css)); rcu_read_unlock(); return memcg; } EXPORT_SYMBOL(get_mem_cgroup_from_mm); -static __always_inline struct mem_cgroup *active_memcg(void) -{ - if (in_interrupt()) - return this_cpu_read(int_active_memcg); - else - return current->active_memcg; -} - static __always_inline bool memcg_kmem_bypass(void) { /* Allow remote memcg charging from any context. */ @@ -1178,9 +1210,8 @@ void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) struct lruvec *lock_page_lruvec(struct page *page) { struct lruvec *lruvec; - struct pglist_data *pgdat = page_pgdat(page); - lruvec = mem_cgroup_page_lruvec(page, pgdat); + lruvec = mem_cgroup_page_lruvec(page); spin_lock(&lruvec->lru_lock); lruvec_memcg_debug(lruvec, page); @@ -1191,9 +1222,8 @@ struct lruvec *lock_page_lruvec(struct page *page) struct lruvec *lock_page_lruvec_irq(struct page *page) { struct lruvec *lruvec; - struct pglist_data *pgdat = page_pgdat(page); - lruvec = mem_cgroup_page_lruvec(page, pgdat); + lruvec = mem_cgroup_page_lruvec(page); spin_lock_irq(&lruvec->lru_lock); lruvec_memcg_debug(lruvec, page); @@ -1204,9 +1234,8 @@ struct lruvec *lock_page_lruvec_irq(struct page *page) struct lruvec *lock_page_lruvec_irqsave(struct page *page, unsigned long *flags) { struct lruvec *lruvec; - struct pglist_data *pgdat = page_pgdat(page); - lruvec = mem_cgroup_page_lruvec(page, pgdat); + lruvec = mem_cgroup_page_lruvec(page); spin_lock_irqsave(&lruvec->lru_lock, *flags); lruvec_memcg_debug(lruvec, page); @@ -2040,14 +2069,23 @@ void unlock_page_memcg(struct page *page) } EXPORT_SYMBOL(unlock_page_memcg); -struct memcg_stock_pcp { - struct mem_cgroup *cached; /* this never be root cgroup */ - unsigned int nr_pages; - +struct obj_stock { #ifdef CONFIG_MEMCG_KMEM struct obj_cgroup *cached_objcg; + struct pglist_data *cached_pgdat; unsigned int nr_bytes; + int nr_slab_reclaimable_b; + int nr_slab_unreclaimable_b; +#else + int dummy[0]; #endif +}; + +struct memcg_stock_pcp { + struct mem_cgroup *cached; /* this never be root cgroup */ + unsigned int nr_pages; + struct obj_stock task_obj; + struct obj_stock irq_obj; struct work_struct work; unsigned long flags; @@ -2057,12 +2095,12 @@ static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock); static DEFINE_MUTEX(percpu_charge_mutex); #ifdef CONFIG_MEMCG_KMEM -static void drain_obj_stock(struct memcg_stock_pcp *stock); +static void drain_obj_stock(struct obj_stock *stock); static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, struct mem_cgroup *root_memcg); #else -static inline void drain_obj_stock(struct memcg_stock_pcp *stock) +static inline void drain_obj_stock(struct obj_stock *stock) { } static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, @@ -2072,6 +2110,41 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, } #endif +/* + * Most kmem_cache_alloc() calls are from user context. The irq disable/enable + * sequence used in this case to access content from object stock is slow. + * To optimize for user context access, there are now two object stocks for + * task context and interrupt context access respectively. + * + * The task context object stock can be accessed by disabling preemption only + * which is cheap in non-preempt kernel. The interrupt context object stock + * can only be accessed after disabling interrupt. User context code can + * access interrupt object stock, but not vice versa. + */ +static inline struct obj_stock *get_obj_stock(unsigned long *pflags) +{ + struct memcg_stock_pcp *stock; + + if (likely(in_task())) { + *pflags = 0UL; + preempt_disable(); + stock = this_cpu_ptr(&memcg_stock); + return &stock->task_obj; + } + + local_irq_save(*pflags); + stock = this_cpu_ptr(&memcg_stock); + return &stock->irq_obj; +} + +static inline void put_obj_stock(unsigned long flags) +{ + if (likely(in_task())) + preempt_enable(); + else + local_irq_restore(flags); +} + /** * consume_stock: Try to consume stocked charge on this cpu. * @memcg: memcg to consume from. @@ -2138,7 +2211,9 @@ static void drain_local_stock(struct work_struct *dummy) local_irq_save(flags); stock = this_cpu_ptr(&memcg_stock); - drain_obj_stock(stock); + drain_obj_stock(&stock->irq_obj); + if (in_task()) + drain_obj_stock(&stock->task_obj); drain_stock(stock); clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); @@ -2504,8 +2579,8 @@ out: css_put(&memcg->css); } -static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, - unsigned int nr_pages) +static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask, + unsigned int nr_pages) { unsigned int batch = max(MEMCG_CHARGE_BATCH, nr_pages); int nr_retries = MAX_RECLAIM_RETRIES; @@ -2517,8 +2592,6 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, bool drained = false; unsigned long pflags; - if (mem_cgroup_is_root(memcg)) - return 0; retry: if (consume_stock(memcg, nr_pages)) return 0; @@ -2698,6 +2771,15 @@ done_restock: return 0; } +static inline int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, + unsigned int nr_pages) +{ + if (mem_cgroup_is_root(memcg)) + return 0; + + return try_charge_memcg(memcg, gfp_mask, nr_pages); +} + #if defined(CONFIG_MEMCG_KMEM) || defined(CONFIG_MMU) static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) { @@ -2739,6 +2821,13 @@ retry: } #ifdef CONFIG_MEMCG_KMEM +/* + * The allocated objcg pointers array is not accounted directly. + * Moreover, it should not come from DMA buffer and is not readily + * reclaimable. So those GFP bits should be masked off. + */ +#define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT) + int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, gfp_t gfp, bool new_page) { @@ -2746,6 +2835,7 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, unsigned long memcg_data; void *vec; + gfp &= ~OBJCGS_CLEAR_MASK; vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp, page_to_nid(page)); if (!vec) @@ -2925,7 +3015,7 @@ static int obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp, memcg = get_mem_cgroup_from_objcg(objcg); - ret = try_charge(memcg, gfp, nr_pages); + ret = try_charge_memcg(memcg, gfp, nr_pages); if (ret) goto out; @@ -2995,26 +3085,81 @@ void __memcg_kmem_uncharge_page(struct page *page, int order) obj_cgroup_put(objcg); } +void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, + enum node_stat_item idx, int nr) +{ + unsigned long flags; + struct obj_stock *stock = get_obj_stock(&flags); + int *bytes; + + /* + * Save vmstat data in stock and skip vmstat array update unless + * accumulating over a page of vmstat data or when pgdat or idx + * changes. + */ + if (stock->cached_objcg != objcg) { + drain_obj_stock(stock); + obj_cgroup_get(objcg); + stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes) + ? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0; + stock->cached_objcg = objcg; + stock->cached_pgdat = pgdat; + } else if (stock->cached_pgdat != pgdat) { + /* Flush the existing cached vmstat data */ + if (stock->nr_slab_reclaimable_b) { + mod_objcg_mlstate(objcg, pgdat, NR_SLAB_RECLAIMABLE_B, + stock->nr_slab_reclaimable_b); + stock->nr_slab_reclaimable_b = 0; + } + if (stock->nr_slab_unreclaimable_b) { + mod_objcg_mlstate(objcg, pgdat, NR_SLAB_UNRECLAIMABLE_B, + stock->nr_slab_unreclaimable_b); + stock->nr_slab_unreclaimable_b = 0; + } + stock->cached_pgdat = pgdat; + } + + bytes = (idx == NR_SLAB_RECLAIMABLE_B) ? &stock->nr_slab_reclaimable_b + : &stock->nr_slab_unreclaimable_b; + /* + * Even for large object >= PAGE_SIZE, the vmstat data will still be + * cached locally at least once before pushing it out. + */ + if (!*bytes) { + *bytes = nr; + nr = 0; + } else { + *bytes += nr; + if (abs(*bytes) > PAGE_SIZE) { + nr = *bytes; + *bytes = 0; + } else { + nr = 0; + } + } + if (nr) + mod_objcg_mlstate(objcg, pgdat, idx, nr); + + put_obj_stock(flags); +} + static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) { - struct memcg_stock_pcp *stock; unsigned long flags; + struct obj_stock *stock = get_obj_stock(&flags); bool ret = false; - local_irq_save(flags); - - stock = this_cpu_ptr(&memcg_stock); if (objcg == stock->cached_objcg && stock->nr_bytes >= nr_bytes) { stock->nr_bytes -= nr_bytes; ret = true; } - local_irq_restore(flags); + put_obj_stock(flags); return ret; } -static void drain_obj_stock(struct memcg_stock_pcp *stock) +static void drain_obj_stock(struct obj_stock *stock) { struct obj_cgroup *old = stock->cached_objcg; @@ -3042,6 +3187,25 @@ static void drain_obj_stock(struct memcg_stock_pcp *stock) stock->nr_bytes = 0; } + /* + * Flush the vmstat data in current stock + */ + if (stock->nr_slab_reclaimable_b || stock->nr_slab_unreclaimable_b) { + if (stock->nr_slab_reclaimable_b) { + mod_objcg_mlstate(old, stock->cached_pgdat, + NR_SLAB_RECLAIMABLE_B, + stock->nr_slab_reclaimable_b); + stock->nr_slab_reclaimable_b = 0; + } + if (stock->nr_slab_unreclaimable_b) { + mod_objcg_mlstate(old, stock->cached_pgdat, + NR_SLAB_UNRECLAIMABLE_B, + stock->nr_slab_unreclaimable_b); + stock->nr_slab_unreclaimable_b = 0; + } + stock->cached_pgdat = NULL; + } + obj_cgroup_put(old); stock->cached_objcg = NULL; } @@ -3051,8 +3215,13 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, { struct mem_cgroup *memcg; - if (stock->cached_objcg) { - memcg = obj_cgroup_memcg(stock->cached_objcg); + if (in_task() && stock->task_obj.cached_objcg) { + memcg = obj_cgroup_memcg(stock->task_obj.cached_objcg); + if (memcg && mem_cgroup_is_descendant(memcg, root_memcg)) + return true; + } + if (stock->irq_obj.cached_objcg) { + memcg = obj_cgroup_memcg(stock->irq_obj.cached_objcg); if (memcg && mem_cgroup_is_descendant(memcg, root_memcg)) return true; } @@ -3060,26 +3229,32 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, return false; } -static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) +static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes, + bool allow_uncharge) { - struct memcg_stock_pcp *stock; unsigned long flags; + struct obj_stock *stock = get_obj_stock(&flags); + unsigned int nr_pages = 0; - local_irq_save(flags); - - stock = this_cpu_ptr(&memcg_stock); if (stock->cached_objcg != objcg) { /* reset if necessary */ drain_obj_stock(stock); obj_cgroup_get(objcg); stock->cached_objcg = objcg; - stock->nr_bytes = atomic_xchg(&objcg->nr_charged_bytes, 0); + stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes) + ? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0; + allow_uncharge = true; /* Allow uncharge when objcg changes */ } stock->nr_bytes += nr_bytes; - if (stock->nr_bytes > PAGE_SIZE) - drain_obj_stock(stock); + if (allow_uncharge && (stock->nr_bytes > PAGE_SIZE)) { + nr_pages = stock->nr_bytes >> PAGE_SHIFT; + stock->nr_bytes &= (PAGE_SIZE - 1); + } - local_irq_restore(flags); + put_obj_stock(flags); + + if (nr_pages) + obj_cgroup_uncharge_pages(objcg, nr_pages); } int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size) @@ -3091,14 +3266,27 @@ int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size) return 0; /* - * In theory, memcg->nr_charged_bytes can have enough + * In theory, objcg->nr_charged_bytes can have enough * pre-charged bytes to satisfy the allocation. However, - * flushing memcg->nr_charged_bytes requires two atomic - * operations, and memcg->nr_charged_bytes can't be big, - * so it's better to ignore it and try grab some new pages. - * memcg->nr_charged_bytes will be flushed in - * refill_obj_stock(), called from this function or - * independently later. + * flushing objcg->nr_charged_bytes requires two atomic + * operations, and objcg->nr_charged_bytes can't be big. + * The shared objcg->nr_charged_bytes can also become a + * performance bottleneck if all tasks of the same memcg are + * trying to update it. So it's better to ignore it and try + * grab some new pages. The stock's nr_bytes will be flushed to + * objcg->nr_charged_bytes later on when objcg changes. + * + * The stock's nr_bytes may contain enough pre-charged bytes + * to allow one less page from being charged, but we can't rely + * on the pre-charged bytes not being changed outside of + * consume_obj_stock() or refill_obj_stock(). So ignore those + * pre-charged bytes as well when charging pages. To avoid a + * page uncharge right after a page charge, we set the + * allow_uncharge flag to false when calling refill_obj_stock() + * to temporarily allow the pre-charged bytes to exceed the page + * size limit. The maximum reachable value of the pre-charged + * bytes is (sizeof(object) + PAGE_SIZE - 2) if there is no data + * race. */ nr_pages = size >> PAGE_SHIFT; nr_bytes = size & (PAGE_SIZE - 1); @@ -3108,14 +3296,14 @@ int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size) ret = obj_cgroup_charge_pages(objcg, gfp, nr_pages); if (!ret && nr_bytes) - refill_obj_stock(objcg, PAGE_SIZE - nr_bytes); + refill_obj_stock(objcg, PAGE_SIZE - nr_bytes, false); return ret; } void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size) { - refill_obj_stock(objcg, size); + refill_obj_stock(objcg, size, true); } #endif /* CONFIG_MEMCG_KMEM */ @@ -5349,7 +5537,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, * as special swap entry in the CPU page table. */ if (is_device_private_entry(ent)) { - page = device_private_entry_to_page(ent); + page = pfn_swap_entry_to_page(ent); /* * MEMORY_DEVICE_PRIVATE means ZONE_DEVICE page and which have * a refcount of 1 when free (unlike normal page) @@ -6456,7 +6644,7 @@ static unsigned long effective_protection(unsigned long usage, } /** - * mem_cgroup_protected - check if memory consumption is in the normal range + * mem_cgroup_calculate_protection - check if memory consumption is in the normal range * @root: the top ancestor of the sub-tree being checked * @memcg: the memory cgroup to check * @@ -6541,7 +6729,8 @@ out: * @gfp_mask: reclaim mode * * Try to charge @page to the memcg that @mm belongs to, reclaiming - * pages according to @gfp_mask if necessary. + * pages according to @gfp_mask if necessary. if @mm is NULL, try to + * charge to the active memcg. * * Do not use this for pages allocated for swapin. * @@ -6671,6 +6860,7 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) unsigned long nr_pages; struct mem_cgroup *memcg; struct obj_cgroup *objcg; + bool use_objcg = PageMemcgKmem(page); VM_BUG_ON_PAGE(PageLRU(page), page); @@ -6679,7 +6869,7 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) * page memcg or objcg at this point, we have fully * exclusive access to the page. */ - if (PageMemcgKmem(page)) { + if (use_objcg) { objcg = __page_objcg(page); /* * This get matches the put at the end of the function and @@ -6707,7 +6897,7 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) nr_pages = compound_nr(page); - if (PageMemcgKmem(page)) { + if (use_objcg) { ug->nr_memory += nr_pages; ug->nr_kmem += nr_pages; @@ -6806,9 +6996,11 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) /* Force-charge the new page. The old one will be freed soon */ nr_pages = thp_nr_pages(newpage); - page_counter_charge(&memcg->memory, nr_pages); - if (do_memsw_account()) - page_counter_charge(&memcg->memsw, nr_pages); + if (!mem_cgroup_is_root(memcg)) { + page_counter_charge(&memcg->memory, nr_pages); + if (do_memsw_account()) + page_counter_charge(&memcg->memsw, nr_pages); + } css_get(&memcg->css); commit_charge(newpage, memcg); diff --git a/mm/memfd.c b/mm/memfd.c index 2647c898990c..081dd33e6a61 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -297,9 +297,9 @@ SYSCALL_DEFINE2(memfd_create, } if (flags & MFD_HUGETLB) { - struct user_struct *user = NULL; + struct ucounts *ucounts = NULL; - file = hugetlb_file_setup(name, 0, VM_NORESERVE, &user, + file = hugetlb_file_setup(name, 0, VM_NORESERVE, &ucounts, HUGETLB_ANONHUGE_INODE, (flags >> MFD_HUGE_SHIFT) & MFD_HUGE_MASK); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 85ad98c00fd9..eefd823deb67 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -56,6 +56,7 @@ #include <linux/kfifo.h> #include <linux/ratelimit.h> #include <linux/page-isolation.h> +#include <linux/pagewalk.h> #include "internal.h" #include "ras/ras_event.h" @@ -65,6 +66,19 @@ int sysctl_memory_failure_recovery __read_mostly = 1; atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0); +static bool __page_handle_poison(struct page *page) +{ + bool ret; + + zone_pcp_disable(page_zone(page)); + ret = dissolve_free_huge_page(page); + if (!ret) + ret = take_page_off_buddy(page); + zone_pcp_enable(page_zone(page)); + + return ret; +} + static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, bool release) { if (hugepage_or_freepage) { @@ -72,7 +86,7 @@ static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, boo * Doing this check for free pages is also fine since dissolve_free_huge_page * returns 0 for non-hugetlb pages as well. */ - if (dissolve_free_huge_page(page) || !take_page_off_buddy(page)) + if (!__page_handle_poison(page)) /* * We could fail to take off the target page from buddy * for example due to racy page allocation, but that's @@ -554,6 +568,148 @@ static void collect_procs(struct page *page, struct list_head *tokill, collect_procs_file(page, tokill, force_early); } +struct hwp_walk { + struct to_kill tk; + unsigned long pfn; + int flags; +}; + +static void set_to_kill(struct to_kill *tk, unsigned long addr, short shift) +{ + tk->addr = addr; + tk->size_shift = shift; +} + +static int check_hwpoisoned_entry(pte_t pte, unsigned long addr, short shift, + unsigned long poisoned_pfn, struct to_kill *tk) +{ + unsigned long pfn = 0; + + if (pte_present(pte)) { + pfn = pte_pfn(pte); + } else { + swp_entry_t swp = pte_to_swp_entry(pte); + + if (is_hwpoison_entry(swp)) + pfn = hwpoison_entry_to_pfn(swp); + } + + if (!pfn || pfn != poisoned_pfn) + return 0; + + set_to_kill(tk, addr, shift); + return 1; +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr, + struct hwp_walk *hwp) +{ + pmd_t pmd = *pmdp; + unsigned long pfn; + unsigned long hwpoison_vaddr; + + if (!pmd_present(pmd)) + return 0; + pfn = pmd_pfn(pmd); + if (pfn <= hwp->pfn && hwp->pfn < pfn + HPAGE_PMD_NR) { + hwpoison_vaddr = addr + ((hwp->pfn - pfn) << PAGE_SHIFT); + set_to_kill(&hwp->tk, hwpoison_vaddr, PAGE_SHIFT); + return 1; + } + return 0; +} +#else +static int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr, + struct hwp_walk *hwp) +{ + return 0; +} +#endif + +static int hwpoison_pte_range(pmd_t *pmdp, unsigned long addr, + unsigned long end, struct mm_walk *walk) +{ + struct hwp_walk *hwp = (struct hwp_walk *)walk->private; + int ret = 0; + pte_t *ptep; + spinlock_t *ptl; + + ptl = pmd_trans_huge_lock(pmdp, walk->vma); + if (ptl) { + ret = check_hwpoisoned_pmd_entry(pmdp, addr, hwp); + spin_unlock(ptl); + goto out; + } + + if (pmd_trans_unstable(pmdp)) + goto out; + + ptep = pte_offset_map_lock(walk->vma->vm_mm, pmdp, addr, &ptl); + for (; addr != end; ptep++, addr += PAGE_SIZE) { + ret = check_hwpoisoned_entry(*ptep, addr, PAGE_SHIFT, + hwp->pfn, &hwp->tk); + if (ret == 1) + break; + } + pte_unmap_unlock(ptep - 1, ptl); +out: + cond_resched(); + return ret; +} + +#ifdef CONFIG_HUGETLB_PAGE +static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask, + unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct hwp_walk *hwp = (struct hwp_walk *)walk->private; + pte_t pte = huge_ptep_get(ptep); + struct hstate *h = hstate_vma(walk->vma); + + return check_hwpoisoned_entry(pte, addr, huge_page_shift(h), + hwp->pfn, &hwp->tk); +} +#else +#define hwpoison_hugetlb_range NULL +#endif + +static struct mm_walk_ops hwp_walk_ops = { + .pmd_entry = hwpoison_pte_range, + .hugetlb_entry = hwpoison_hugetlb_range, +}; + +/* + * Sends SIGBUS to the current process with error info. + * + * This function is intended to handle "Action Required" MCEs on already + * hardware poisoned pages. They could happen, for example, when + * memory_failure() failed to unmap the error page at the first call, or + * when multiple local machine checks happened on different CPUs. + * + * MCE handler currently has no easy access to the error virtual address, + * so this function walks page table to find it. The returned virtual address + * is proper in most cases, but it could be wrong when the application + * process has multiple entries mapping the error page. + */ +static int kill_accessing_process(struct task_struct *p, unsigned long pfn, + int flags) +{ + int ret; + struct hwp_walk priv = { + .pfn = pfn, + }; + priv.tk.tsk = p; + + mmap_read_lock(p->mm); + ret = walk_page_range(p->mm, 0, TASK_SIZE, &hwp_walk_ops, + (void *)&priv); + if (ret == 1 && priv.tk.addr) + kill_proc(&priv.tk, pfn, flags); + mmap_read_unlock(p->mm); + return ret ? -EFAULT : -EHWPOISON; +} + static const char *action_name[] = { [MF_IGNORED] = "Ignored", [MF_FAILED] = "Failed", @@ -658,6 +814,7 @@ static int truncate_error_page(struct page *p, unsigned long pfn, */ static int me_kernel(struct page *p, unsigned long pfn) { + unlock_page(p); return MF_IGNORED; } @@ -667,6 +824,7 @@ static int me_kernel(struct page *p, unsigned long pfn) static int me_unknown(struct page *p, unsigned long pfn) { pr_err("Memory failure: %#lx: Unknown page state\n", pfn); + unlock_page(p); return MF_FAILED; } @@ -675,6 +833,7 @@ static int me_unknown(struct page *p, unsigned long pfn) */ static int me_pagecache_clean(struct page *p, unsigned long pfn) { + int ret; struct address_space *mapping; delete_from_lru_cache(p); @@ -683,8 +842,10 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * For anonymous pages we're done the only reference left * should be the one m_f() holds. */ - if (PageAnon(p)) - return MF_RECOVERED; + if (PageAnon(p)) { + ret = MF_RECOVERED; + goto out; + } /* * Now truncate the page in the page cache. This is really @@ -698,7 +859,8 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) /* * Page has been teared down in the meanwhile */ - return MF_FAILED; + ret = MF_FAILED; + goto out; } /* @@ -706,7 +868,10 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * * Open: to take i_mutex or not for this? Right now we don't. */ - return truncate_error_page(p, pfn, mapping); + ret = truncate_error_page(p, pfn, mapping); +out: + unlock_page(p); + return ret; } /* @@ -782,24 +947,26 @@ static int me_pagecache_dirty(struct page *p, unsigned long pfn) */ static int me_swapcache_dirty(struct page *p, unsigned long pfn) { + int ret; + ClearPageDirty(p); /* Trigger EIO in shmem: */ ClearPageUptodate(p); - if (!delete_from_lru_cache(p)) - return MF_DELAYED; - else - return MF_FAILED; + ret = delete_from_lru_cache(p) ? MF_FAILED : MF_DELAYED; + unlock_page(p); + return ret; } static int me_swapcache_clean(struct page *p, unsigned long pfn) { + int ret; + delete_from_swap_cache(p); - if (!delete_from_lru_cache(p)) - return MF_RECOVERED; - else - return MF_FAILED; + ret = delete_from_lru_cache(p) ? MF_FAILED : MF_RECOVERED; + unlock_page(p); + return ret; } /* @@ -820,6 +987,7 @@ static int me_huge_page(struct page *p, unsigned long pfn) mapping = page_mapping(hpage); if (mapping) { res = truncate_error_page(hpage, pfn, mapping); + unlock_page(hpage); } else { res = MF_FAILED; unlock_page(hpage); @@ -830,11 +998,10 @@ static int me_huge_page(struct page *p, unsigned long pfn) */ if (PageAnon(hpage)) put_page(hpage); - if (!dissolve_free_huge_page(p) && take_page_off_buddy(p)) { + if (__page_handle_poison(p)) { page_ref_inc(p); res = MF_RECOVERED; } - lock_page(hpage); } return res; @@ -866,6 +1033,8 @@ static struct page_state { unsigned long mask; unsigned long res; enum mf_action_page_type type; + + /* Callback ->action() has to unlock the relevant page inside it. */ int (*action)(struct page *p, unsigned long pfn); } error_states[] = { { reserved, reserved, MF_MSG_KERNEL, me_kernel }, @@ -929,6 +1098,7 @@ static int page_action(struct page_state *ps, struct page *p, int result; int count; + /* page p should be unlocked after returning from ps->action(). */ result = ps->action(p, pfn); count = page_count(p) - 1; @@ -949,18 +1119,36 @@ static int page_action(struct page_state *ps, struct page *p, return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY; } -/** - * __get_hwpoison_page() - Get refcount for memory error handling: - * @page: raw error page (hit by memory error) - * - * Return: return 0 if failed to grab the refcount, otherwise true (some - * non-zero value.) +/* + * Return true if a page type of a given page is supported by hwpoison + * mechanism (while handling could fail), otherwise false. This function + * does not return true for hugetlb or device memory pages, so it's assumed + * to be called only in the context where we never have such pages. */ +static inline bool HWPoisonHandlable(struct page *page) +{ + return PageLRU(page) || __PageMovable(page); +} + static int __get_hwpoison_page(struct page *page) { struct page *head = compound_head(page); + int ret = 0; + bool hugetlb = false; + + ret = get_hwpoison_huge_page(head, &hugetlb); + if (hugetlb) + return ret; + + /* + * This check prevents from calling get_hwpoison_unless_zero() + * for any unsupported type of page in order to reduce the risk of + * unexpected races caused by taking a page refcount. + */ + if (!HWPoisonHandlable(head)) + return 0; - if (!PageHuge(head) && PageTransHuge(head)) { + if (PageTransHuge(head)) { /* * Non anonymous thp exists only in allocation/free time. We * can't handle such a case correctly, so let's give it up. @@ -986,15 +1174,6 @@ static int __get_hwpoison_page(struct page *page) return 0; } -/* - * Safely get reference count of an arbitrary page. - * - * Returns 0 for a free page, 1 for an in-use page, - * -EIO for a page-type we cannot handle and -EBUSY if we raced with an - * allocation. - * We only incremented refcount in case the page was already in-use and it - * is a known type we can handle. - */ static int get_any_page(struct page *p, unsigned long flags) { int ret = 0, pass = 0; @@ -1004,50 +1183,77 @@ static int get_any_page(struct page *p, unsigned long flags) count_increased = true; try_again: - if (!count_increased && !__get_hwpoison_page(p)) { - if (page_count(p)) { - /* We raced with an allocation, retry. */ - if (pass++ < 3) - goto try_again; - ret = -EBUSY; - } else if (!PageHuge(p) && !is_free_buddy_page(p)) { - /* We raced with put_page, retry. */ + if (!count_increased) { + ret = __get_hwpoison_page(p); + if (!ret) { + if (page_count(p)) { + /* We raced with an allocation, retry. */ + if (pass++ < 3) + goto try_again; + ret = -EBUSY; + } else if (!PageHuge(p) && !is_free_buddy_page(p)) { + /* We raced with put_page, retry. */ + if (pass++ < 3) + goto try_again; + ret = -EIO; + } + goto out; + } else if (ret == -EBUSY) { + /* We raced with freeing huge page to buddy, retry. */ if (pass++ < 3) goto try_again; - ret = -EIO; + goto out; } + } + + if (PageHuge(p) || HWPoisonHandlable(p)) { + ret = 1; } else { - if (PageHuge(p) || PageLRU(p) || __PageMovable(p)) { - ret = 1; - } else { - /* - * A page we cannot handle. Check whether we can turn - * it into something we can handle. - */ - if (pass++ < 3) { - put_page(p); - shake_page(p, 1); - count_increased = false; - goto try_again; - } + /* + * A page we cannot handle. Check whether we can turn + * it into something we can handle. + */ + if (pass++ < 3) { put_page(p); - ret = -EIO; + shake_page(p, 1); + count_increased = false; + goto try_again; } + put_page(p); + ret = -EIO; } - +out: return ret; } -static int get_hwpoison_page(struct page *p, unsigned long flags, - enum mf_flags ctxt) +/** + * get_hwpoison_page() - Get refcount for memory error handling + * @p: Raw error page (hit by memory error) + * @flags: Flags controlling behavior of error handling + * + * get_hwpoison_page() takes a page refcount of an error page to handle memory + * error on it, after checking that the error page is in a well-defined state + * (defined as a page-type we can successfully handle the memor error on it, + * such as LRU page and hugetlb page). + * + * Memory error handling could be triggered at any time on any type of page, + * so it's prone to race with typical memory management lifecycle (like + * allocation and free). So to avoid such races, get_hwpoison_page() takes + * extra care for the error page's state (as done in __get_hwpoison_page()), + * and has some retry logic in get_any_page(). + * + * Return: 0 on failure, + * 1 on success for in-use pages in a well-defined state, + * -EIO for pages on which we can not handle memory errors, + * -EBUSY when get_hwpoison_page() has raced with page lifecycle + * operations like allocation and free. + */ +static int get_hwpoison_page(struct page *p, unsigned long flags) { int ret; zone_pcp_disable(page_zone(p)); - if (ctxt == MF_SOFT_OFFLINE) - ret = get_any_page(p, flags); - else - ret = __get_hwpoison_page(p); + ret = get_any_page(p, flags); zone_pcp_enable(page_zone(p)); return ret; @@ -1060,10 +1266,10 @@ static int get_hwpoison_page(struct page *p, unsigned long flags, static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, int flags, struct page **hpagep) { - enum ttu_flags ttu = TTU_IGNORE_MLOCK; + enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC; struct address_space *mapping; LIST_HEAD(tokill); - bool unmap_success = true; + bool unmap_success; int kill = 1, forcekill; struct page *hpage = *hpagep; bool mlocked = PageMlocked(hpage); @@ -1126,7 +1332,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED); if (!PageHuge(hpage)) { - unmap_success = try_to_unmap(hpage, ttu); + try_to_unmap(hpage, ttu); } else { if (!PageAnon(hpage)) { /* @@ -1134,21 +1340,20 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * could potentially call huge_pmd_unshare. Because of * this, take semaphore in write mode here and set * TTU_RMAP_LOCKED to indicate we have taken the lock - * at this higer level. + * at this higher level. */ mapping = hugetlb_page_mapping_lock_write(hpage); if (mapping) { - unmap_success = try_to_unmap(hpage, - ttu|TTU_RMAP_LOCKED); + try_to_unmap(hpage, ttu|TTU_RMAP_LOCKED); i_mmap_unlock_write(mapping); - } else { + } else pr_info("Memory failure: %#lx: could not lock mapping for mapped huge page\n", pfn); - unmap_success = false; - } } else { - unmap_success = try_to_unmap(hpage, ttu); + try_to_unmap(hpage, ttu); } } + + unmap_success = !page_mapped(hpage); if (!unmap_success) pr_err("Memory failure: %#lx: failed to unmap page (mapcount=%d)\n", pfn, page_mapcount(hpage)); @@ -1228,32 +1433,41 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags) if (TestSetPageHWPoison(head)) { pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn); - return 0; + res = -EHWPOISON; + if (flags & MF_ACTION_REQUIRED) + res = kill_accessing_process(current, page_to_pfn(head), flags); + return res; } num_poisoned_pages_inc(); - if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p, flags, 0)) { - /* - * Check "filter hit" and "race with other subpage." - */ - lock_page(head); - if (PageHWPoison(head)) { - if ((hwpoison_filter(p) && TestClearPageHWPoison(p)) - || (p != head && TestSetPageHWPoison(head))) { - num_poisoned_pages_dec(); - unlock_page(head); - return 0; + if (!(flags & MF_COUNT_INCREASED)) { + res = get_hwpoison_page(p, flags); + if (!res) { + /* + * Check "filter hit" and "race with other subpage." + */ + lock_page(head); + if (PageHWPoison(head)) { + if ((hwpoison_filter(p) && TestClearPageHWPoison(p)) + || (p != head && TestSetPageHWPoison(head))) { + num_poisoned_pages_dec(); + unlock_page(head); + return 0; + } } + unlock_page(head); + res = MF_FAILED; + if (__page_handle_poison(p)) { + page_ref_inc(p); + res = MF_RECOVERED; + } + action_result(pfn, MF_MSG_FREE_HUGE, res); + return res == MF_RECOVERED ? 0 : -EBUSY; + } else if (res < 0) { + action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED); + return -EBUSY; } - unlock_page(head); - res = MF_FAILED; - if (!dissolve_free_huge_page(p) && take_page_off_buddy(p)) { - page_ref_inc(p); - res = MF_RECOVERED; - } - action_result(pfn, MF_MSG_FREE_HUGE, res); - return res == MF_RECOVERED ? 0 : -EBUSY; } lock_page(head); @@ -1288,7 +1502,7 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags) goto out; } - res = identify_page_state(pfn, p, page_flags); + return identify_page_state(pfn, p, page_flags); out: unlock_page(head); return res; @@ -1404,9 +1618,10 @@ int memory_failure(unsigned long pfn, int flags) struct page *hpage; struct page *orig_head; struct dev_pagemap *pgmap; - int res; + int res = 0; unsigned long page_flags; bool retry = true; + static DEFINE_MUTEX(mf_mutex); if (!sysctl_memory_failure_recovery) panic("Memory failure on page %lx", pfn); @@ -1424,13 +1639,21 @@ int memory_failure(unsigned long pfn, int flags) return -ENXIO; } + mutex_lock(&mf_mutex); + try_again: - if (PageHuge(p)) - return memory_failure_hugetlb(pfn, flags); + if (PageHuge(p)) { + res = memory_failure_hugetlb(pfn, flags); + goto unlock_mutex; + } + if (TestSetPageHWPoison(p)) { pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn); - return 0; + res = -EHWPOISON; + if (flags & MF_ACTION_REQUIRED) + res = kill_accessing_process(current, pfn, flags); + goto unlock_mutex; } orig_head = hpage = compound_head(p); @@ -1447,33 +1670,42 @@ try_again: * In fact it's dangerous to directly bump up page count from 0, * that may make page_ref_freeze()/page_ref_unfreeze() mismatch. */ - if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p, flags, 0)) { - if (is_free_buddy_page(p)) { - if (take_page_off_buddy(p)) { - page_ref_inc(p); - res = MF_RECOVERED; - } else { - /* We lost the race, try again */ - if (retry) { - ClearPageHWPoison(p); - num_poisoned_pages_dec(); - retry = false; - goto try_again; + if (!(flags & MF_COUNT_INCREASED)) { + res = get_hwpoison_page(p, flags); + if (!res) { + if (is_free_buddy_page(p)) { + if (take_page_off_buddy(p)) { + page_ref_inc(p); + res = MF_RECOVERED; + } else { + /* We lost the race, try again */ + if (retry) { + ClearPageHWPoison(p); + num_poisoned_pages_dec(); + retry = false; + goto try_again; + } + res = MF_FAILED; } - res = MF_FAILED; + action_result(pfn, MF_MSG_BUDDY, res); + res = res == MF_RECOVERED ? 0 : -EBUSY; + } else { + action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED); + res = -EBUSY; } - action_result(pfn, MF_MSG_BUDDY, res); - return res == MF_RECOVERED ? 0 : -EBUSY; - } else { - action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED); - return -EBUSY; + goto unlock_mutex; + } else if (res < 0) { + action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED); + res = -EBUSY; + goto unlock_mutex; } } if (PageTransHuge(hpage)) { if (try_to_split_thp_page(p, "Memory Failure") < 0) { action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED); - return -EBUSY; + res = -EBUSY; + goto unlock_mutex; } VM_BUG_ON_PAGE(!page_count(p), p); } @@ -1497,7 +1729,7 @@ try_again: if (PageCompound(p) && compound_head(p) != orig_head) { action_result(pfn, MF_MSG_DIFFERENT_COMPOUND, MF_IGNORED); res = -EBUSY; - goto out; + goto unlock_page; } /* @@ -1517,17 +1749,22 @@ try_again: num_poisoned_pages_dec(); unlock_page(p); put_page(p); - return 0; + goto unlock_mutex; } if (hwpoison_filter(p)) { if (TestClearPageHWPoison(p)) num_poisoned_pages_dec(); unlock_page(p); put_page(p); - return 0; + goto unlock_mutex; } - if (!PageTransTail(p) && !PageLRU(p)) + /* + * __munlock_pagevec may clear a writeback page's LRU flag without + * page_lock. We need wait writeback completion for this page or it + * may trigger vfs BUG while evict inode. + */ + if (!PageTransTail(p) && !PageLRU(p) && !PageWriteback(p)) goto identify_page_state; /* @@ -1543,7 +1780,7 @@ try_again: if (!hwpoison_user_mappings(p, pfn, flags, &p)) { action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED); res = -EBUSY; - goto out; + goto unlock_page; } /* @@ -1552,13 +1789,17 @@ try_again: if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) { action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED); res = -EBUSY; - goto out; + goto unlock_page; } identify_page_state: res = identify_page_state(pfn, p, page_flags); -out: + mutex_unlock(&mf_mutex); + return res; +unlock_page: unlock_page(p); +unlock_mutex: + mutex_unlock(&mf_mutex); return res; } EXPORT_SYMBOL_GPL(memory_failure); @@ -1735,7 +1976,7 @@ int unpoison_memory(unsigned long pfn) return 0; } - if (!get_hwpoison_page(p, flags, 0)) { + if (!get_hwpoison_page(p, flags)) { if (TestClearPageHWPoison(p)) num_poisoned_pages_dec(); unpoison_pr_info("Unpoison: Software-unpoisoned free page %#lx\n", @@ -1951,7 +2192,7 @@ int soft_offline_page(unsigned long pfn, int flags) retry: get_online_mems(); - ret = get_hwpoison_page(page, flags, MF_SOFT_OFFLINE); + ret = get_hwpoison_page(page, flags); put_online_mems(); if (ret > 0) { diff --git a/mm/memory.c b/mm/memory.c index 730daa00952b..747a01d495f2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -90,8 +90,7 @@ #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif -#ifndef CONFIG_NEED_MULTIPLE_NODES -/* use the per-pgdat data instead for discontigmem - mbligh */ +#ifndef CONFIG_NUMA unsigned long max_mapnr; EXPORT_SYMBOL(max_mapnr); @@ -700,6 +699,68 @@ out: } #endif +static void restore_exclusive_pte(struct vm_area_struct *vma, + struct page *page, unsigned long address, + pte_t *ptep) +{ + pte_t pte; + swp_entry_t entry; + + pte = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot))); + if (pte_swp_soft_dirty(*ptep)) + pte = pte_mksoft_dirty(pte); + + entry = pte_to_swp_entry(*ptep); + if (pte_swp_uffd_wp(*ptep)) + pte = pte_mkuffd_wp(pte); + else if (is_writable_device_exclusive_entry(entry)) + pte = maybe_mkwrite(pte_mkdirty(pte), vma); + + set_pte_at(vma->vm_mm, address, ptep, pte); + + /* + * No need to take a page reference as one was already + * created when the swap entry was made. + */ + if (PageAnon(page)) + page_add_anon_rmap(page, vma, address, false); + else + /* + * Currently device exclusive access only supports anonymous + * memory so the entry shouldn't point to a filebacked page. + */ + WARN_ON_ONCE(!PageAnon(page)); + + if (vma->vm_flags & VM_LOCKED) + mlock_vma_page(page); + + /* + * No need to invalidate - it was non-present before. However + * secondary CPUs may have mappings that need invalidating. + */ + update_mmu_cache(vma, address, ptep); +} + +/* + * Tries to restore an exclusive pte if the page lock can be acquired without + * sleeping. + */ +static int +try_restore_exclusive_pte(pte_t *src_pte, struct vm_area_struct *vma, + unsigned long addr) +{ + swp_entry_t entry = pte_to_swp_entry(*src_pte); + struct page *page = pfn_swap_entry_to_page(entry); + + if (trylock_page(page)) { + restore_exclusive_pte(vma, page, addr, src_pte); + unlock_page(page); + return 0; + } + + return -EBUSY; +} + /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range @@ -708,17 +769,17 @@ out: static unsigned long copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma, - unsigned long addr, int *rss) + pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma, unsigned long addr, int *rss) { - unsigned long vm_flags = vma->vm_flags; + unsigned long vm_flags = dst_vma->vm_flags; pte_t pte = *src_pte; struct page *page; swp_entry_t entry = pte_to_swp_entry(pte); if (likely(!non_swap_entry(entry))) { if (swap_duplicate(entry) < 0) - return entry.val; + return -EIO; /* make sure dst_mm is on swapoff's mmlist. */ if (unlikely(list_empty(&dst_mm->mmlist))) { @@ -730,17 +791,18 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, } rss[MM_SWAPENTS]++; } else if (is_migration_entry(entry)) { - page = migration_entry_to_page(entry); + page = pfn_swap_entry_to_page(entry); rss[mm_counter(page)]++; - if (is_write_migration_entry(entry) && + if (is_writable_migration_entry(entry) && is_cow_mapping(vm_flags)) { /* * COW mappings require pages in both * parent and child to be set to read. */ - make_migration_entry_read(&entry); + entry = make_readable_migration_entry( + swp_offset(entry)); pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(*src_pte)) pte = pte_swp_mksoft_dirty(pte); @@ -749,7 +811,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, set_pte_at(src_mm, addr, src_pte, pte); } } else if (is_device_private_entry(entry)) { - page = device_private_entry_to_page(entry); + page = pfn_swap_entry_to_page(entry); /* * Update rss count even for unaddressable pages, as @@ -771,15 +833,29 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, * when a device driver is involved (you cannot easily * save and restore device driver state). */ - if (is_write_device_private_entry(entry) && + if (is_writable_device_private_entry(entry) && is_cow_mapping(vm_flags)) { - make_device_private_entry_read(&entry); + entry = make_readable_device_private_entry( + swp_offset(entry)); pte = swp_entry_to_pte(entry); if (pte_swp_uffd_wp(*src_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } + } else if (is_device_exclusive_entry(entry)) { + /* + * Make device exclusive entries present by restoring the + * original entry then copying as for a present pte. Device + * exclusive entries currently only support private writable + * (ie. COW) mappings. + */ + VM_BUG_ON(!is_cow_mapping(src_vma->vm_flags)); + if (try_restore_exclusive_pte(src_pte, src_vma, addr)) + return -EBUSY; + return -ENOENT; } + if (!userfaultfd_wp(dst_vma)) + pte = pte_swp_clear_uffd_wp(pte); set_pte_at(dst_mm, addr, dst_pte, pte); return 0; } @@ -845,6 +921,9 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma /* All done, just insert the new page copy in the child */ pte = mk_pte(new_page, dst_vma->vm_page_prot); pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma); + if (userfaultfd_pte_wp(dst_vma, *src_pte)) + /* Uffd-wp needs to be delivered to dest pte as well */ + pte = pte_wrprotect(pte_mkuffd_wp(pte)); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } @@ -894,12 +973,7 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte = pte_mkclean(pte); pte = pte_mkold(pte); - /* - * Make sure the _PAGE_UFFD_WP bit is cleared if the new VMA - * does not have the VM_UFFD_WP, which means that the uffd - * fork event is not enabled. - */ - if (!(vm_flags & VM_UFFD_WP)) + if (!userfaultfd_wp(dst_vma)) pte = pte_clear_uffd_wp(pte); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); @@ -972,13 +1046,25 @@ again: continue; } if (unlikely(!pte_present(*src_pte))) { - entry.val = copy_nonpresent_pte(dst_mm, src_mm, - dst_pte, src_pte, - src_vma, addr, rss); - if (entry.val) + ret = copy_nonpresent_pte(dst_mm, src_mm, + dst_pte, src_pte, + dst_vma, src_vma, + addr, rss); + if (ret == -EIO) { + entry = pte_to_swp_entry(*src_pte); break; - progress += 8; - continue; + } else if (ret == -EBUSY) { + break; + } else if (!ret) { + progress += 8; + continue; + } + + /* + * Device exclusive entry restored, continue by copying + * the now present pte. + */ + WARN_ON_ONCE(ret != -ENOENT); } /* copy_present_pte() will clear `*prealloc' if consumed */ ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte, @@ -1009,20 +1095,26 @@ again: pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); - if (entry.val) { + if (ret == -EIO) { + VM_WARN_ON_ONCE(!entry.val); if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) { ret = -ENOMEM; goto out; } entry.val = 0; - } else if (ret) { - WARN_ON_ONCE(ret != -EAGAIN); + } else if (ret == -EBUSY) { + goto out; + } else if (ret == -EAGAIN) { prealloc = page_copy_prealloc(src_mm, src_vma, addr); if (!prealloc) return -ENOMEM; - /* We've captured and resolved the error. Reset, try again. */ - ret = 0; + } else if (ret) { + VM_WARN_ON_ONCE(1); } + + /* We've captured and resolved the error. Reset, try again. */ + ret = 0; + if (addr != end) goto again; out: @@ -1051,8 +1143,8 @@ copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, || pmd_devmap(*src_pmd)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma); - err = copy_huge_pmd(dst_mm, src_mm, - dst_pmd, src_pmd, addr, src_vma); + err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd, + addr, dst_vma, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) @@ -1279,8 +1371,9 @@ again: } entry = pte_to_swp_entry(ptent); - if (is_device_private_entry(entry)) { - struct page *page = device_private_entry_to_page(entry); + if (is_device_private_entry(entry) || + is_device_exclusive_entry(entry)) { + struct page *page = pfn_swap_entry_to_page(entry); if (unlikely(details && details->check_mapping)) { /* @@ -1295,7 +1388,10 @@ again: pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); rss[mm_counter(page)]--; - page_remove_rmap(page, false); + + if (is_device_private_entry(entry)) + page_remove_rmap(page, false); + put_page(page); continue; } @@ -1309,7 +1405,7 @@ again: else if (is_migration_entry(entry)) { struct page *page; - page = migration_entry_to_page(entry); + page = pfn_swap_entry_to_page(entry); rss[mm_counter(page)]--; } if (unlikely(!free_swap_and_cache(entry))) @@ -1361,7 +1457,18 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ + } else if (details && details->single_page && + PageTransCompound(details->single_page) && + next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { + spinlock_t *ptl = pmd_lock(tlb->mm, pmd); + /* + * Take and drop THP pmd lock so that we cannot return + * prematurely, while zap_huge_pmd() has cleared *pmd, + * but not yet decremented compound_mapcount(). + */ + spin_unlock(ptl); } + /* * Here there can be other concurrent MADV_DONTNEED or * trans huge page faults running, and if the pmd is @@ -2939,6 +3046,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); + entry = pte_sw_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* @@ -3011,6 +3119,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) munlock_vma_page(old_page); unlock_page(old_page); } + if (page_copied) + free_swap_cache(old_page); put_page(old_page); } return page_copied ? VM_FAULT_WRITE : 0; @@ -3035,7 +3145,7 @@ oom: * The function expects the page to be locked or other protection against * concurrent faults / writeback (such as DAX radix tree locks). * - * Return: %VM_FAULT_WRITE on success, %0 when PTE got changed before + * Return: %0 on success, %VM_FAULT_NOPAGE when PTE got changed before * we acquired PTE lock. */ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf) @@ -3236,6 +3346,36 @@ static inline void unmap_mapping_range_tree(struct rb_root_cached *root, } /** + * unmap_mapping_page() - Unmap single page from processes. + * @page: The locked page to be unmapped. + * + * Unmap this page from any userspace process which still has it mmaped. + * Typically, for efficiency, the range of nearby pages has already been + * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once + * truncation or invalidation holds the lock on a page, it may find that + * the page has been remapped again: and then uses unmap_mapping_page() + * to unmap it finally. + */ +void unmap_mapping_page(struct page *page) +{ + struct address_space *mapping = page->mapping; + struct zap_details details = { }; + + VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON(PageTail(page)); + + details.check_mapping = mapping; + details.first_index = page->index; + details.last_index = page->index + thp_nr_pages(page) - 1; + details.single_page = page; + + i_mmap_lock_write(mapping); + if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) + unmap_mapping_range_tree(&mapping->i_mmap, &details); + i_mmap_unlock_write(mapping); +} + +/** * unmap_mapping_pages() - Unmap pages from processes. * @mapping: The address space containing pages to be unmapped. * @start: Index of first page to be unmapped. @@ -3300,6 +3440,34 @@ void unmap_mapping_range(struct address_space *mapping, EXPORT_SYMBOL(unmap_mapping_range); /* + * Restore a potential device exclusive pte to a working pte entry + */ +static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf) +{ + struct page *page = vmf->page; + struct vm_area_struct *vma = vmf->vma; + struct mmu_notifier_range range; + + if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) + return VM_FAULT_RETRY; + mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma, + vma->vm_mm, vmf->address & PAGE_MASK, + (vmf->address & PAGE_MASK) + PAGE_SIZE, NULL); + mmu_notifier_invalidate_range_start(&range); + + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, + &vmf->ptl); + if (likely(pte_same(*vmf->pte, vmf->orig_pte))) + restore_exclusive_pte(vma, page, vmf->address, vmf->pte); + + pte_unmap_unlock(vmf->pte, vmf->ptl); + unlock_page(page); + + mmu_notifier_invalidate_range_end(&range); + return 0; +} + +/* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with pte unmapped and unlocked. @@ -3311,6 +3479,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL, *swapcache; + struct swap_info_struct *si = NULL; swp_entry_t entry; pte_t pte; int locked; @@ -3326,8 +3495,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (is_migration_entry(entry)) { migration_entry_wait(vma->vm_mm, vmf->pmd, vmf->address); + } else if (is_device_exclusive_entry(entry)) { + vmf->page = pfn_swap_entry_to_page(entry); + ret = remove_device_exclusive_entry(vmf); } else if (is_device_private_entry(entry)) { - vmf->page = device_private_entry_to_page(entry); + vmf->page = pfn_swap_entry_to_page(entry); ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; @@ -3338,14 +3510,16 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) goto out; } + /* Prevent swapoff from happening to us. */ + si = get_swap_device(entry); + if (unlikely(!si)) + goto out; delayacct_set_flag(current, DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry, vma, vmf->address); swapcache = page; if (!page) { - struct swap_info_struct *si = swp_swap_info(entry); - if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { /* skip swapcache */ @@ -3514,6 +3688,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); out: + if (si) + put_swap_device(si); return ret; out_nomap: pte_unmap_unlock(vmf->pte, vmf->ptl); @@ -3525,6 +3701,8 @@ out_release: unlock_page(swapcache); put_page(swapcache); } + if (si) + put_swap_device(si); return ret; } @@ -3602,6 +3780,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) __SetPageUptodate(page); entry = mk_pte(page, vma->vm_page_prot); + entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry)); @@ -3786,6 +3965,8 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr) if (prefault && arch_wants_old_prefaulted_pte()) entry = pte_mkold(entry); + else + entry = pte_sw_mkyoung(entry); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); @@ -3972,9 +4153,11 @@ static vm_fault_t do_read_fault(struct vm_fault *vmf) * something). */ if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { - ret = do_fault_around(vmf); - if (ret) - return ret; + if (likely(!userfaultfd_minor(vmf->vma))) { + ret = do_fault_around(vmf); + if (ret) + return ret; + } } ret = __do_fault(vmf); @@ -4119,9 +4302,8 @@ static vm_fault_t do_fault(struct vm_fault *vmf) return ret; } -static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, - unsigned long addr, int page_nid, - int *flags) +int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, + unsigned long addr, int page_nid, int *flags) { get_page(page); @@ -4242,12 +4424,12 @@ static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) } /* `inline' is required to avoid gcc 4.1.2 build error */ -static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd) +static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) { if (vma_is_anonymous(vmf->vma)) { - if (userfaultfd_huge_pmd_wp(vmf->vma, orig_pmd)) + if (userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd)) return handle_userfault(vmf, VM_UFFD_WP); - return do_huge_pmd_wp_page(vmf, orig_pmd); + return do_huge_pmd_wp_page(vmf); } if (vmf->vma->vm_ops->huge_fault) { vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); @@ -4474,26 +4656,26 @@ retry_pud: if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { - pmd_t orig_pmd = *vmf.pmd; + vmf.orig_pmd = *vmf.pmd; barrier(); - if (unlikely(is_swap_pmd(orig_pmd))) { + if (unlikely(is_swap_pmd(vmf.orig_pmd))) { VM_BUG_ON(thp_migration_supported() && - !is_pmd_migration_entry(orig_pmd)); - if (is_pmd_migration_entry(orig_pmd)) + !is_pmd_migration_entry(vmf.orig_pmd)); + if (is_pmd_migration_entry(vmf.orig_pmd)) pmd_migration_entry_wait(mm, vmf.pmd); return 0; } - if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) { - if (pmd_protnone(orig_pmd) && vma_is_accessible(vma)) - return do_huge_pmd_numa_page(&vmf, orig_pmd); + if (pmd_trans_huge(vmf.orig_pmd) || pmd_devmap(vmf.orig_pmd)) { + if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma)) + return do_huge_pmd_numa_page(&vmf); - if (dirty && !pmd_write(orig_pmd)) { - ret = wp_huge_pmd(&vmf, orig_pmd); + if (dirty && !pmd_write(vmf.orig_pmd)) { + ret = wp_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { - huge_pmd_set_accessed(&vmf, orig_pmd); + huge_pmd_set_accessed(&vmf); return 0; } } @@ -4940,8 +5122,8 @@ int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, * Check if this is a VM_IO | VM_PFNMAP VMA, which * we can access using slightly different code. */ - vma = find_vma(mm, addr); - if (!vma || vma->vm_start > addr) + vma = vma_lookup(mm, addr); + if (!vma) break; if (vma->vm_ops && vma->vm_ops->access) ret = vma->vm_ops->access(vma, addr, buf, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 70620d0dd923..8cb75b26ea4f 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -154,122 +154,6 @@ static void release_memory_resource(struct resource *res) } #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE -void get_page_bootmem(unsigned long info, struct page *page, - unsigned long type) -{ - page->freelist = (void *)type; - SetPagePrivate(page); - set_page_private(page, info); - page_ref_inc(page); -} - -void put_page_bootmem(struct page *page) -{ - unsigned long type; - - type = (unsigned long) page->freelist; - BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE || - type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE); - - if (page_ref_dec_return(page) == 1) { - page->freelist = NULL; - ClearPagePrivate(page); - set_page_private(page, 0); - INIT_LIST_HEAD(&page->lru); - free_reserved_page(page); - } -} - -#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE -#ifndef CONFIG_SPARSEMEM_VMEMMAP -static void register_page_bootmem_info_section(unsigned long start_pfn) -{ - unsigned long mapsize, section_nr, i; - struct mem_section *ms; - struct page *page, *memmap; - struct mem_section_usage *usage; - - section_nr = pfn_to_section_nr(start_pfn); - ms = __nr_to_section(section_nr); - - /* Get section's memmap address */ - memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); - - /* - * Get page for the memmap's phys address - * XXX: need more consideration for sparse_vmemmap... - */ - page = virt_to_page(memmap); - mapsize = sizeof(struct page) * PAGES_PER_SECTION; - mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT; - - /* remember memmap's page */ - for (i = 0; i < mapsize; i++, page++) - get_page_bootmem(section_nr, page, SECTION_INFO); - - usage = ms->usage; - page = virt_to_page(usage); - - mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT; - - for (i = 0; i < mapsize; i++, page++) - get_page_bootmem(section_nr, page, MIX_SECTION_INFO); - -} -#else /* CONFIG_SPARSEMEM_VMEMMAP */ -static void register_page_bootmem_info_section(unsigned long start_pfn) -{ - unsigned long mapsize, section_nr, i; - struct mem_section *ms; - struct page *page, *memmap; - struct mem_section_usage *usage; - - section_nr = pfn_to_section_nr(start_pfn); - ms = __nr_to_section(section_nr); - - memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); - - register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION); - - usage = ms->usage; - page = virt_to_page(usage); - - mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT; - - for (i = 0; i < mapsize; i++, page++) - get_page_bootmem(section_nr, page, MIX_SECTION_INFO); -} -#endif /* !CONFIG_SPARSEMEM_VMEMMAP */ - -void __init register_page_bootmem_info_node(struct pglist_data *pgdat) -{ - unsigned long i, pfn, end_pfn, nr_pages; - int node = pgdat->node_id; - struct page *page; - - nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT; - page = virt_to_page(pgdat); - - for (i = 0; i < nr_pages; i++, page++) - get_page_bootmem(node, page, NODE_INFO); - - pfn = pgdat->node_start_pfn; - end_pfn = pgdat_end_pfn(pgdat); - - /* register section info */ - for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { - /* - * Some platforms can assign the same pfn to multiple nodes - on - * node0 as well as nodeN. To avoid registering a pfn against - * multiple nodes we check that this pfn does not already - * reside in some other nodes. - */ - if (pfn_valid(pfn) && (early_pfn_to_nid(pfn) == node)) - register_page_bootmem_info_section(pfn); - } -} -#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */ - static int check_pfn_span(unsigned long pfn, unsigned long nr_pages, const char *reason) { @@ -445,7 +329,6 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, unsigned long pfn; int nid = zone_to_nid(zone); - zone_span_writelock(zone); if (zone->zone_start_pfn == start_pfn) { /* * If the section is smallest section in the zone, it need @@ -478,7 +361,6 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, zone->spanned_pages = 0; } } - zone_span_writeunlock(zone); } static void update_pgdat_span(struct pglist_data *pgdat) @@ -515,7 +397,7 @@ void __ref remove_pfn_range_from_zone(struct zone *zone, { const unsigned long end_pfn = start_pfn + nr_pages; struct pglist_data *pgdat = zone->zone_pgdat; - unsigned long pfn, cur_nr_pages, flags; + unsigned long pfn, cur_nr_pages; /* Poison struct pages because they are now uninitialized again. */ for (pfn = start_pfn; pfn < end_pfn; pfn += cur_nr_pages) { @@ -540,10 +422,8 @@ void __ref remove_pfn_range_from_zone(struct zone *zone, clear_zone_contiguous(zone); - pgdat_resize_lock(zone->zone_pgdat, &flags); shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); update_pgdat_span(pgdat); - pgdat_resize_unlock(zone->zone_pgdat, &flags); set_zone_contiguous(zone); } @@ -750,19 +630,13 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, { struct pglist_data *pgdat = zone->zone_pgdat; int nid = pgdat->node_id; - unsigned long flags; clear_zone_contiguous(zone); - /* TODO Huh pgdat is irqsave while zone is not. It used to be like that before */ - pgdat_resize_lock(pgdat, &flags); - zone_span_writelock(zone); if (zone_is_empty(zone)) init_currently_empty_zone(zone, start_pfn, nr_pages); resize_zone_range(zone, start_pfn, nr_pages); - zone_span_writeunlock(zone); resize_pgdat_range(pgdat, start_pfn, nr_pages); - pgdat_resize_unlock(pgdat, &flags); /* * Subsection population requires care in pfn_to_online_page(). @@ -852,12 +726,8 @@ struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, */ void adjust_present_page_count(struct zone *zone, long nr_pages) { - unsigned long flags; - zone->present_pages += nr_pages; - pgdat_resize_lock(zone->zone_pgdat, &flags); zone->zone_pgdat->node_present_pages += nr_pages; - pgdat_resize_unlock(zone->zone_pgdat, &flags); } int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, @@ -913,7 +783,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *z /* * {on,off}lining is constrained to full memory sections (or more - * precisly to memory blocks from the user space POV). + * precisely to memory blocks from the user space POV). * memmap_on_memory is an exception because it reserves initial part * of the physical memory space for vmemmaps. That space is pageblock * aligned. @@ -961,7 +831,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *z node_states_set_node(nid, &arg); if (need_zonelists_rebuild) build_all_zonelists(NULL); - zone_pcp_update(zone); /* Basic onlining is complete, allow allocation of onlined pages. */ undo_isolate_page_range(pfn, pfn + nr_pages, MIGRATE_MOVABLE); @@ -974,6 +843,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *z */ shuffle_zone(zone); + /* reinitialise watermarks and update pcp limits */ init_per_zone_wmark_min(); kswapd_run(nid); @@ -1072,8 +942,8 @@ static void rollback_node_hotadd(int nid) } -/** - * try_online_node - online a node if offlined +/* + * __try_online_node - online a node if offlined * @nid: the node ID * @set_node_online: Whether we want to online the node * called by cpu_up() to online a node without onlined memory. @@ -1172,6 +1042,7 @@ bool mhp_supports_memmap_on_memory(unsigned long size) * populate a single PMD. */ return memmap_on_memory && + !hugetlb_free_vmemmap_enabled && IS_ENABLED(CONFIG_MHP_MEMMAP_ON_MEMORY) && size == memory_block_size_bytes() && IS_ALIGNED(vmemmap_size, PMD_SIZE) && @@ -1521,6 +1392,8 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) struct page *page, *head; int ret = 0; LIST_HEAD(source); + static DEFINE_RATELIMIT_STATE(migrate_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); for (pfn = start_pfn; pfn < end_pfn; pfn++) { if (!pfn_valid(pfn)) @@ -1567,8 +1440,10 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) page_is_file_lru(page)); } else { - pr_warn("failed to isolate pfn %lx\n", pfn); - dump_page(page, "isolation failed"); + if (__ratelimit(&migrate_rs)) { + pr_warn("failed to isolate pfn %lx\n", pfn); + dump_page(page, "isolation failed"); + } } put_page(page); } @@ -1597,9 +1472,11 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); if (ret) { list_for_each_entry(page, &source, lru) { - pr_warn("migrating pfn %lx failed ret:%d ", - page_to_pfn(page), ret); - dump_page(page, "migration failure"); + if (__ratelimit(&migrate_rs)) { + pr_warn("migrating pfn %lx failed ret:%d\n", + page_to_pfn(page), ret); + dump_page(page, "migration failure"); + } } putback_movable_pages(&source); } @@ -1703,7 +1580,7 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) /* * {on,off}lining is constrained to full memory sections (or more - * precisly to memory blocks from the user space POV). + * precisely to memory blocks from the user space POV). * memmap_on_memory is an exception because it reserves initial part * of the physical memory space for vmemmaps. That space is pageblock * aligned. @@ -1829,13 +1706,13 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages); adjust_present_page_count(zone, -nr_pages); + /* reinitialise watermarks and update pcp limits */ init_per_zone_wmark_min(); if (!populated_zone(zone)) { zone_pcp_reset(zone); build_all_zonelists(NULL); - } else - zone_pcp_update(zone); + } node_states_clear_node(node, &arg); if (arg.status_change_nid >= 0) { @@ -2031,7 +1908,7 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) } /** - * remove_memory + * __remove_memory - Remove memory if every memory block is offline * @nid: the node ID * @start: physical address of the region to remove * @size: size of the region to remove diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d79fa299b70c..e32360e90274 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -121,8 +121,7 @@ enum zone_type policy_zone = 0; */ static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ - .mode = MPOL_PREFERRED, - .flags = MPOL_F_LOCAL, + .mode = MPOL_LOCAL, }; static struct mempolicy preferred_node_policy[MAX_NUMNODES]; @@ -194,18 +193,17 @@ static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; - pol->v.nodes = *nodes; + pol->nodes = *nodes; return 0; } static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { - if (!nodes) - pol->flags |= MPOL_F_LOCAL; /* local allocation */ - else if (nodes_empty(*nodes)) - return -EINVAL; /* no allowed nodes */ - else - pol->v.preferred_node = first_node(*nodes); + if (nodes_empty(*nodes)) + return -EINVAL; + + nodes_clear(pol->nodes); + node_set(first_node(*nodes), pol->nodes); return 0; } @@ -213,15 +211,14 @@ static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; - pol->v.nodes = *nodes; + pol->nodes = *nodes; return 0; } /* * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if * any, for the new policy. mpol_new() has already validated the nodes - * parameter with respect to the policy mode and flags. But, we need to - * handle an empty nodemask with MPOL_PREFERRED here. + * parameter with respect to the policy mode and flags. * * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_lock for write. @@ -231,33 +228,31 @@ static int mpol_set_nodemask(struct mempolicy *pol, { int ret; - /* if mode is MPOL_DEFAULT, pol is NULL. This is right. */ - if (pol == NULL) + /* + * Default (pol==NULL) resp. local memory policies are not a + * subject of any remapping. They also do not need any special + * constructor. + */ + if (!pol || pol->mode == MPOL_LOCAL) return 0; + /* Check N_MEMORY */ nodes_and(nsc->mask1, cpuset_current_mems_allowed, node_states[N_MEMORY]); VM_BUG_ON(!nodes); - if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes)) - nodes = NULL; /* explicit local allocation */ - else { - if (pol->flags & MPOL_F_RELATIVE_NODES) - mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); - else - nodes_and(nsc->mask2, *nodes, nsc->mask1); - if (mpol_store_user_nodemask(pol)) - pol->w.user_nodemask = *nodes; - else - pol->w.cpuset_mems_allowed = - cpuset_current_mems_allowed; - } + if (pol->flags & MPOL_F_RELATIVE_NODES) + mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); + else + nodes_and(nsc->mask2, *nodes, nsc->mask1); - if (nodes) - ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); + if (mpol_store_user_nodemask(pol)) + pol->w.user_nodemask = *nodes; else - ret = mpol_ops[pol->mode].create(pol, NULL); + pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed; + + ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); return ret; } @@ -290,13 +285,14 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); + + mode = MPOL_LOCAL; } } else if (mode == MPOL_LOCAL) { if (!nodes_empty(*nodes) || (flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES)) return ERR_PTR(-EINVAL); - mode = MPOL_PREFERRED; } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); @@ -330,7 +326,7 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) else if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); else { - nodes_remap(tmp, pol->v.nodes, pol->w.cpuset_mems_allowed, + nodes_remap(tmp, pol->nodes, pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } @@ -338,31 +334,13 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) if (nodes_empty(tmp)) tmp = *nodes; - pol->v.nodes = tmp; + pol->nodes = tmp; } static void mpol_rebind_preferred(struct mempolicy *pol, const nodemask_t *nodes) { - nodemask_t tmp; - - if (pol->flags & MPOL_F_STATIC_NODES) { - int node = first_node(pol->w.user_nodemask); - - if (node_isset(node, *nodes)) { - pol->v.preferred_node = node; - pol->flags &= ~MPOL_F_LOCAL; - } else - pol->flags |= MPOL_F_LOCAL; - } else if (pol->flags & MPOL_F_RELATIVE_NODES) { - mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); - pol->v.preferred_node = first_node(tmp); - } else if (!(pol->flags & MPOL_F_LOCAL)) { - pol->v.preferred_node = node_remap(pol->v.preferred_node, - pol->w.cpuset_mems_allowed, - *nodes); - pol->w.cpuset_mems_allowed = *nodes; - } + pol->w.cpuset_mems_allowed = *nodes; } /* @@ -376,7 +354,7 @@ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { if (!pol) return; - if (!mpol_store_user_nodemask(pol) && !(pol->flags & MPOL_F_LOCAL) && + if (!mpol_store_user_nodemask(pol) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; @@ -427,6 +405,9 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { .create = mpol_new_bind, .rebind = mpol_rebind_nodemask, }, + [MPOL_LOCAL] = { + .rebind = mpol_rebind_default, + }, }; static int migrate_page_add(struct page *page, struct list_head *pagelist, @@ -458,7 +439,8 @@ static inline bool queue_pages_required(struct page *page, /* * queue_pages_pmd() has four possible return values: - * 0 - pages are placed on the right node or queued successfully. + * 0 - pages are placed on the right node or queued successfully, or + * special page is met, i.e. huge zero page. * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * 2 - THP was split. @@ -482,8 +464,7 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, page = pmd_page(*pmd); if (is_huge_zero_page(page)) { spin_unlock(ptl); - __split_huge_pmd(walk->vma, pmd, addr, false, NULL); - ret = 2; + walk->action = ACTION_CONTINUE; goto out; } if (!queue_pages_required(page, qp)) @@ -510,7 +491,8 @@ out: * and move them to the pagelist if they do. * * queue_pages_pte_range() has three possible return values: - * 0 - pages are placed on the right node or queued successfully. + * 0 - pages are placed on the right node or queued successfully, or + * special page is met, i.e. zero page. * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * -EIO - only MPOL_MF_STRICT was specified and an existing page was already @@ -917,12 +899,11 @@ static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes) switch (p->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: - *nodes = p->v.nodes; - break; case MPOL_PREFERRED: - if (!(p->flags & MPOL_F_LOCAL)) - node_set(p->v.preferred_node, *nodes); - /* else return empty node mask for local allocation */ + *nodes = p->nodes; + break; + case MPOL_LOCAL: + /* return empty node mask for local allocation */ break; default: BUG(); @@ -975,7 +956,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, * want to return MPOL_DEFAULT in this case. */ mmap_read_lock(mm); - vma = find_vma_intersection(mm, addr, addr+1); + vma = vma_lookup(mm, addr); if (!vma) { mmap_read_unlock(mm); return -EFAULT; @@ -1007,7 +988,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, *policy = err; } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { - *policy = next_node_in(current->il_prev, pol->v.nodes); + *policy = next_node_in(current->il_prev, pol->nodes); } else { err = -EINVAL; goto out; @@ -1460,26 +1441,38 @@ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } +/* Basic parameter sanity check used by both mbind() and set_mempolicy() */ +static inline int sanitize_mpol_flags(int *mode, unsigned short *flags) +{ + *flags = *mode & MPOL_MODE_FLAGS; + *mode &= ~MPOL_MODE_FLAGS; + if ((unsigned int)(*mode) >= MPOL_MAX) + return -EINVAL; + if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES)) + return -EINVAL; + + return 0; +} + static long kernel_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, unsigned long maxnode, unsigned int flags) { + unsigned short mode_flags; nodemask_t nodes; + int lmode = mode; int err; - unsigned short mode_flags; start = untagged_addr(start); - mode_flags = mode & MPOL_MODE_FLAGS; - mode &= ~MPOL_MODE_FLAGS; - if (mode >= MPOL_MAX) - return -EINVAL; - if ((mode_flags & MPOL_F_STATIC_NODES) && - (mode_flags & MPOL_F_RELATIVE_NODES)) - return -EINVAL; + err = sanitize_mpol_flags(&lmode, &mode_flags); + if (err) + return err; + err = get_nodes(&nodes, nmask, maxnode); if (err) return err; - return do_mbind(start, len, mode, mode_flags, &nodes, flags); + + return do_mbind(start, len, lmode, mode_flags, &nodes, flags); } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, @@ -1493,20 +1486,20 @@ SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask, unsigned long maxnode) { - int err; + unsigned short mode_flags; nodemask_t nodes; - unsigned short flags; + int lmode = mode; + int err; + + err = sanitize_mpol_flags(&lmode, &mode_flags); + if (err) + return err; - flags = mode & MPOL_MODE_FLAGS; - mode &= ~MPOL_MODE_FLAGS; - if ((unsigned int)mode >= MPOL_MAX) - return -EINVAL; - if ((flags & MPOL_F_STATIC_NODES) && (flags & MPOL_F_RELATIVE_NODES)) - return -EINVAL; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; - return do_set_mempolicy(mode, flags, &nodes); + + return do_set_mempolicy(lmode, mode_flags, &nodes); } SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, @@ -1863,14 +1856,14 @@ static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone) BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); /* - * if policy->v.nodes has movable memory only, + * if policy->nodes has movable memory only, * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. * - * policy->v.nodes is intersect with node_states[N_MEMORY]. + * policy->nodes is intersect with node_states[N_MEMORY]. * so if the following test fails, it implies - * policy->v.nodes has movable memory only. + * policy->nodes has movable memory only. */ - if (!nodes_intersects(policy->v.nodes, node_states[N_HIGH_MEMORY])) + if (!nodes_intersects(policy->nodes, node_states[N_HIGH_MEMORY])) dynamic_policy_zone = ZONE_MOVABLE; return zone >= dynamic_policy_zone; @@ -1885,8 +1878,8 @@ nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) /* Lower zones don't get a nodemask applied for MPOL_BIND */ if (unlikely(policy->mode == MPOL_BIND) && apply_policy_zone(policy, gfp_zone(gfp)) && - cpuset_nodemask_valid_mems_allowed(&policy->v.nodes)) - return &policy->v.nodes; + cpuset_nodemask_valid_mems_allowed(&policy->nodes)) + return &policy->nodes; return NULL; } @@ -1894,9 +1887,9 @@ nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) /* Return the node id preferred by the given mempolicy, or the given id */ static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd) { - if (policy->mode == MPOL_PREFERRED && !(policy->flags & MPOL_F_LOCAL)) - nd = policy->v.preferred_node; - else { + if (policy->mode == MPOL_PREFERRED) { + nd = first_node(policy->nodes); + } else { /* * __GFP_THISNODE shouldn't even be used with the bind policy * because we might easily break the expectation to stay on the @@ -1914,7 +1907,7 @@ static unsigned interleave_nodes(struct mempolicy *policy) unsigned next; struct task_struct *me = current; - next = next_node_in(me->il_prev, policy->v.nodes); + next = next_node_in(me->il_prev, policy->nodes); if (next < MAX_NUMNODES) me->il_prev = next; return next; @@ -1933,15 +1926,12 @@ unsigned int mempolicy_slab_node(void) return node; policy = current->mempolicy; - if (!policy || policy->flags & MPOL_F_LOCAL) + if (!policy) return node; switch (policy->mode) { case MPOL_PREFERRED: - /* - * handled MPOL_F_LOCAL above - */ - return policy->v.preferred_node; + return first_node(policy->nodes); case MPOL_INTERLEAVE: return interleave_nodes(policy); @@ -1957,9 +1947,11 @@ unsigned int mempolicy_slab_node(void) enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, - &policy->v.nodes); + &policy->nodes); return z->zone ? zone_to_nid(z->zone) : node; } + case MPOL_LOCAL: + return node; default: BUG(); @@ -1968,12 +1960,12 @@ unsigned int mempolicy_slab_node(void) /* * Do static interleaving for a VMA with known offset @n. Returns the n'th - * node in pol->v.nodes (starting from n=0), wrapping around if n exceeds the + * node in pol->nodes (starting from n=0), wrapping around if n exceeds the * number of present nodes. */ static unsigned offset_il_node(struct mempolicy *pol, unsigned long n) { - unsigned nnodes = nodes_weight(pol->v.nodes); + unsigned nnodes = nodes_weight(pol->nodes); unsigned target; int i; int nid; @@ -1981,9 +1973,9 @@ static unsigned offset_il_node(struct mempolicy *pol, unsigned long n) if (!nnodes) return numa_node_id(); target = (unsigned int)n % nnodes; - nid = first_node(pol->v.nodes); + nid = first_node(pol->nodes); for (i = 0; i < target; i++) - nid = next_node(nid, pol->v.nodes); + nid = next_node(nid, pol->nodes); return nid; } @@ -2039,7 +2031,7 @@ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, } else { nid = policy_node(gfp_flags, *mpol, numa_node_id()); if ((*mpol)->mode == MPOL_BIND) - *nodemask = &(*mpol)->v.nodes; + *nodemask = &(*mpol)->nodes; } return nid; } @@ -2063,7 +2055,6 @@ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, bool init_nodemask_of_mempolicy(nodemask_t *mask) { struct mempolicy *mempolicy; - int nid; if (!(mask && current->mempolicy)) return false; @@ -2072,16 +2063,13 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask) mempolicy = current->mempolicy; switch (mempolicy->mode) { case MPOL_PREFERRED: - if (mempolicy->flags & MPOL_F_LOCAL) - nid = numa_node_id(); - else - nid = mempolicy->v.preferred_node; - init_nodemask_of_node(mask, nid); - break; - case MPOL_BIND: case MPOL_INTERLEAVE: - *mask = mempolicy->v.nodes; + *mask = mempolicy->nodes; + break; + + case MPOL_LOCAL: + init_nodemask_of_node(mask, numa_node_id()); break; default: @@ -2094,16 +2082,16 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask) #endif /* - * mempolicy_nodemask_intersects + * mempolicy_in_oom_domain * - * If tsk's mempolicy is "default" [NULL], return 'true' to indicate default - * policy. Otherwise, check for intersection between mask and the policy - * nodemask for 'bind' or 'interleave' policy. For 'preferred' or 'local' - * policy, always return true since it may allocate elsewhere on fallback. + * If tsk's mempolicy is "bind", check for intersection between mask and + * the policy nodemask. Otherwise, return true for all other policies + * including "interleave", as a tsk with "interleave" policy may have + * memory allocated from all nodes in system. * * Takes task_lock(tsk) to prevent freeing of its mempolicy. */ -bool mempolicy_nodemask_intersects(struct task_struct *tsk, +bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask) { struct mempolicy *mempolicy; @@ -2111,29 +2099,13 @@ bool mempolicy_nodemask_intersects(struct task_struct *tsk, if (!mask) return ret; + task_lock(tsk); mempolicy = tsk->mempolicy; - if (!mempolicy) - goto out; - - switch (mempolicy->mode) { - case MPOL_PREFERRED: - /* - * MPOL_PREFERRED and MPOL_F_LOCAL are only preferred nodes to - * allocate from, they may fallback to other nodes when oom. - * Thus, it's possible for tsk to have allocated memory from - * nodes in mask. - */ - break; - case MPOL_BIND: - case MPOL_INTERLEAVE: - ret = nodes_intersects(mempolicy->v.nodes, *mask); - break; - default: - BUG(); - } -out: + if (mempolicy && mempolicy->mode == MPOL_BIND) + ret = nodes_intersects(mempolicy->nodes, *mask); task_unlock(tsk); + return ret; } @@ -2150,7 +2122,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, return page; if (page && page_to_nid(page) == nid) { preempt_disable(); - __inc_numa_state(page_zone(page), NUMA_INTERLEAVE_HIT); + __count_numa_event(page_zone(page), NUMA_INTERLEAVE_HIT); preempt_enable(); } return page; @@ -2204,8 +2176,8 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, * If the policy is interleave, or does not allow the current * node in its nodemask, we allocate the standard way. */ - if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL)) - hpage_node = pol->v.preferred_node; + if (pol->mode == MPOL_PREFERRED) + hpage_node = first_node(pol->nodes); nmask = policy_nodemask(gfp, pol); if (!nmask || node_isset(hpage_node, *nmask)) { @@ -2338,12 +2310,10 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) switch (a->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: - return !!nodes_equal(a->v.nodes, b->v.nodes); case MPOL_PREFERRED: - /* a's ->flags is the same as b's */ - if (a->flags & MPOL_F_LOCAL) - return true; - return a->v.preferred_node == b->v.preferred_node; + return !!nodes_equal(a->nodes, b->nodes); + case MPOL_LOCAL: + return true; default: BUG(); return false; @@ -2481,16 +2451,17 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long break; case MPOL_PREFERRED: - if (pol->flags & MPOL_F_LOCAL) - polnid = numa_node_id(); - else - polnid = pol->v.preferred_node; + polnid = first_node(pol->nodes); + break; + + case MPOL_LOCAL: + polnid = numa_node_id(); break; case MPOL_BIND: /* Optimize placement among multiple nodes via NUMA balancing */ if (pol->flags & MPOL_F_MORON) { - if (node_isset(thisnid, pol->v.nodes)) + if (node_isset(thisnid, pol->nodes)) break; goto out; } @@ -2501,12 +2472,12 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long * else select nearest allowed node, if any. * If no allowed nodes, use current [!misplaced]. */ - if (node_isset(curnid, pol->v.nodes)) + if (node_isset(curnid, pol->nodes)) goto out; z = first_zones_zonelist( node_zonelist(numa_node_id(), GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), - &pol->v.nodes); + &pol->nodes); polnid = zone_to_nid(z->zone); break; @@ -2709,7 +2680,7 @@ int mpol_set_shared_policy(struct shared_policy *info, vma->vm_pgoff, sz, npol ? npol->mode : -1, npol ? npol->flags : -1, - npol ? nodes_addr(npol->v.nodes)[0] : NUMA_NO_NODE); + npol ? nodes_addr(npol->nodes)[0] : NUMA_NO_NODE); if (npol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol); @@ -2807,7 +2778,7 @@ void __init numa_policy_init(void) .refcnt = ATOMIC_INIT(1), .mode = MPOL_PREFERRED, .flags = MPOL_F_MOF | MPOL_F_MORON, - .v = { .preferred_node = nid, }, + .nodes = nodemask_of_node(nid), }; } @@ -2851,9 +2822,6 @@ void numa_default_policy(void) * Parse and format mempolicy from/to strings */ -/* - * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag. - */ static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", @@ -2931,7 +2899,6 @@ int mpol_parse_str(char *str, struct mempolicy **mpol) */ if (nodelist) goto out; - mode = MPOL_PREFERRED; break; case MPOL_DEFAULT: /* @@ -2970,12 +2937,14 @@ int mpol_parse_str(char *str, struct mempolicy **mpol) * Save nodes for mpol_to_str() to show the tmpfs mount options * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo. */ - if (mode != MPOL_PREFERRED) - new->v.nodes = nodes; - else if (nodelist) - new->v.preferred_node = first_node(nodes); - else - new->flags |= MPOL_F_LOCAL; + if (mode != MPOL_PREFERRED) { + new->nodes = nodes; + } else if (nodelist) { + nodes_clear(new->nodes); + node_set(first_node(nodes), new->nodes); + } else { + new->mode = MPOL_LOCAL; + } /* * Save nodes for contextualization: this will be used to "clone" @@ -3021,16 +2990,12 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) switch (mode) { case MPOL_DEFAULT: + case MPOL_LOCAL: break; case MPOL_PREFERRED: - if (flags & MPOL_F_LOCAL) - mode = MPOL_LOCAL; - else - node_set(pol->v.preferred_node, nodes); - break; case MPOL_BIND: case MPOL_INTERLEAVE: - nodes = pol->v.nodes; + nodes = pol->nodes; break; default: WARN_ON_ONCE(1); diff --git a/mm/mempool.c b/mm/mempool.c index a258cf4de575..0b8afbec3e35 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -106,7 +106,8 @@ static __always_inline void kasan_poison_element(mempool_t *pool, void *element) if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc) kasan_slab_free_mempool(element); else if (pool->alloc == mempool_alloc_pages) - kasan_free_pages(element, (unsigned long)pool->pool_data, false); + kasan_poison_pages(element, (unsigned long)pool->pool_data, + false); } static void kasan_unpoison_element(mempool_t *pool, void *element) @@ -114,7 +115,8 @@ static void kasan_unpoison_element(mempool_t *pool, void *element) if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc) kasan_unpoison_range(element, __ksize(element)); else if (pool->alloc == mempool_alloc_pages) - kasan_alloc_pages(element, (unsigned long)pool->pool_data, false); + kasan_unpoison_pages(element, (unsigned long)pool->pool_data, + false); } static __always_inline void add_element(mempool_t *pool, void *element) diff --git a/mm/migrate.c b/mm/migrate.c index b234c3f3acb7..23cbd9de030b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -210,13 +210,18 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, * Recheck VMA as permissions can change since migration started */ entry = pte_to_swp_entry(*pvmw.pte); - if (is_write_migration_entry(entry)) + if (is_writable_migration_entry(entry)) pte = maybe_mkwrite(pte, vma); else if (pte_swp_uffd_wp(*pvmw.pte)) pte = pte_mkuffd_wp(pte); if (unlikely(is_device_private_page(new))) { - entry = make_device_private_entry(new, pte_write(pte)); + if (pte_write(pte)) + entry = make_writable_device_private_entry( + page_to_pfn(new)); + else + entry = make_readable_device_private_entry( + page_to_pfn(new)); pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(*pvmw.pte)) pte = pte_swp_mksoft_dirty(pte); @@ -226,8 +231,10 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, #ifdef CONFIG_HUGETLB_PAGE if (PageHuge(new)) { + unsigned int shift = huge_page_shift(hstate_vma(vma)); + pte = pte_mkhuge(pte); - pte = arch_make_huge_pte(pte, vma, new, 0); + pte = arch_make_huge_pte(pte, shift, vma->vm_flags); set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); if (PageAnon(new)) hugepage_add_anon_rmap(new, vma, pvmw.address); @@ -294,7 +301,8 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, if (!is_migration_entry(entry)) goto out; - page = migration_entry_to_page(entry); + page = pfn_swap_entry_to_page(entry); + page = compound_head(page); /* * Once page cache replacement of page migration started, page_count @@ -334,7 +342,7 @@ void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd) ptl = pmd_lock(mm, pmd); if (!is_pmd_migration_entry(*pmd)) goto unlock; - page = migration_entry_to_page(pmd_to_swp_entry(*pmd)); + page = pfn_swap_entry_to_page(pmd_to_swp_entry(*pmd)); if (!get_page_unless_zero(page)) goto unlock; spin_unlock(ptl); @@ -550,7 +558,7 @@ static void __copy_gigantic_page(struct page *dst, struct page *src, } } -static void copy_huge_page(struct page *dst, struct page *src) +void copy_huge_page(struct page *dst, struct page *src) { int i; int nr_pages; @@ -625,7 +633,10 @@ void migrate_page_states(struct page *newpage, struct page *page) if (PageSwapCache(page)) ClearPageSwapCache(page); ClearPagePrivate(page); - set_page_private(page, 0); + + /* page->private contains hugetlb specific flags */ + if (!PageHuge(page)) + set_page_private(page, 0); /* * If any waiters have accumulated on the new page then @@ -1098,7 +1109,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, /* Establish migration ptes */ VM_BUG_ON_PAGE(PageAnon(page) && !PageKsm(page) && !anon_vma, page); - try_to_unmap(page, TTU_MIGRATION|TTU_IGNORE_MLOCK); + try_to_migrate(page, 0); page_was_mapped = 1; } @@ -1287,7 +1298,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, * page_mapping() set, hugetlbfs specific move page routine will not * be called and we could leak usage counts for subpools. */ - if (page_private(hpage) && !page_mapping(hpage)) { + if (hugetlb_page_subpool(hpage) && !page_mapping(hpage)) { rc = -EBUSY; goto out_unlock; } @@ -1300,7 +1311,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (page_mapped(hpage)) { bool mapping_locked = false; - enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK; + enum ttu_flags ttu = 0; if (!PageAnon(hpage)) { /* @@ -1317,7 +1328,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, ttu |= TTU_RMAP_LOCKED; } - try_to_unmap(hpage, ttu); + try_to_migrate(hpage, ttu); page_was_mapped = 1; if (mapping_locked) @@ -1417,6 +1428,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, int swapwrite = current->flags & PF_SWAPWRITE; int rc, nr_subpages; LIST_HEAD(ret_pages); + bool nosplit = (reason == MR_NUMA_MISPLACED); trace_mm_migrate_pages_start(mode, reason); @@ -1488,8 +1500,9 @@ retry: /* * When memory is low, don't bother to try to migrate * other pages, just exit. + * THP NUMA faulting doesn't split THP to retry. */ - if (is_thp) { + if (is_thp && !nosplit) { if (!try_split_thp(page, &page2, from)) { nr_thp_split++; goto retry; @@ -1833,8 +1846,8 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages, struct page *page; int err = -EFAULT; - vma = find_vma(mm, addr); - if (!vma || addr < vma->vm_start) + vma = vma_lookup(mm, addr); + if (!vma) goto set_status; /* FOLL_DUMP to ignore special (like zero) pages */ @@ -2042,12 +2055,33 @@ static struct page *alloc_misplaced_dst_page(struct page *page, return newpage; } +static struct page *alloc_misplaced_dst_page_thp(struct page *page, + unsigned long data) +{ + int nid = (int) data; + struct page *newpage; + + newpage = alloc_pages_node(nid, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), + HPAGE_PMD_ORDER); + if (!newpage) + goto out; + + prep_transhuge_page(newpage); + +out: + return newpage; +} + static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) { int page_lru; VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page); + /* Do not migrate THP mapped by multiple processes */ + if (PageTransHuge(page) && total_mapcount(page) > 1) + return 0; + /* Avoid migrating to a node that is nearly full */ if (!migrate_balanced_pgdat(pgdat, compound_nr(page))) return 0; @@ -2055,18 +2089,6 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) if (isolate_lru_page(page)) return 0; - /* - * migrate_misplaced_transhuge_page() skips page migration's usual - * check on page_count(), so we must do it here, now that the page - * has been isolated: a GUP pin, or any other pin, prevents migration. - * The expected page count is 3: 1 for page's mapcount and 1 for the - * caller's pin and 1 for the reference taken by isolate_lru_page(). - */ - if (PageTransHuge(page) && page_count(page) != 3) { - putback_lru_page(page); - return 0; - } - page_lru = page_is_file_lru(page); mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru, thp_nr_pages(page)); @@ -2080,12 +2102,6 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) return 1; } -bool pmd_trans_migrating(pmd_t pmd) -{ - struct page *page = pmd_page(pmd); - return PageLocked(page); -} - /* * Attempt to migrate a misplaced page to the specified destination * node. Caller is expected to have an elevated reference count on @@ -2098,6 +2114,21 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int isolated; int nr_remaining; LIST_HEAD(migratepages); + new_page_t *new; + bool compound; + unsigned int nr_pages = thp_nr_pages(page); + + /* + * PTE mapped THP or HugeTLB page can't reach here so the page could + * be either base page or THP. And it must be head page if it is + * THP. + */ + compound = PageTransHuge(page); + + if (compound) + new = alloc_misplaced_dst_page_thp; + else + new = alloc_misplaced_dst_page; /* * Don't migrate file pages that are mapped in multiple processes @@ -2119,19 +2150,18 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, goto out; list_add(&page->lru, &migratepages); - nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, - NULL, node, MIGRATE_ASYNC, - MR_NUMA_MISPLACED); + nr_remaining = migrate_pages(&migratepages, *new, NULL, node, + MIGRATE_ASYNC, MR_NUMA_MISPLACED); if (nr_remaining) { if (!list_empty(&migratepages)) { list_del(&page->lru); - dec_node_page_state(page, NR_ISOLATED_ANON + - page_is_file_lru(page)); + mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + + page_is_file_lru(page), -nr_pages); putback_lru_page(page); } isolated = 0; } else - count_vm_numa_event(NUMA_PAGE_MIGRATE); + count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_pages); BUG_ON(!list_empty(&migratepages)); return isolated; @@ -2140,141 +2170,6 @@ out: return 0; } #endif /* CONFIG_NUMA_BALANCING */ - -#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE) -/* - * Migrates a THP to a given target node. page must be locked and is unlocked - * before returning. - */ -int migrate_misplaced_transhuge_page(struct mm_struct *mm, - struct vm_area_struct *vma, - pmd_t *pmd, pmd_t entry, - unsigned long address, - struct page *page, int node) -{ - spinlock_t *ptl; - pg_data_t *pgdat = NODE_DATA(node); - int isolated = 0; - struct page *new_page = NULL; - int page_lru = page_is_file_lru(page); - unsigned long start = address & HPAGE_PMD_MASK; - - new_page = alloc_pages_node(node, - (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), - HPAGE_PMD_ORDER); - if (!new_page) - goto out_fail; - prep_transhuge_page(new_page); - - isolated = numamigrate_isolate_page(pgdat, page); - if (!isolated) { - put_page(new_page); - goto out_fail; - } - - /* Prepare a page as a migration target */ - __SetPageLocked(new_page); - if (PageSwapBacked(page)) - __SetPageSwapBacked(new_page); - - /* anon mapping, we can simply copy page->mapping to the new page: */ - new_page->mapping = page->mapping; - new_page->index = page->index; - /* flush the cache before copying using the kernel virtual address */ - flush_cache_range(vma, start, start + HPAGE_PMD_SIZE); - migrate_page_copy(new_page, page); - WARN_ON(PageLRU(new_page)); - - /* Recheck the target PMD */ - ptl = pmd_lock(mm, pmd); - if (unlikely(!pmd_same(*pmd, entry) || !page_ref_freeze(page, 2))) { - spin_unlock(ptl); - - /* Reverse changes made by migrate_page_copy() */ - if (TestClearPageActive(new_page)) - SetPageActive(page); - if (TestClearPageUnevictable(new_page)) - SetPageUnevictable(page); - - unlock_page(new_page); - put_page(new_page); /* Free it */ - - /* Retake the callers reference and putback on LRU */ - get_page(page); - putback_lru_page(page); - mod_node_page_state(page_pgdat(page), - NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR); - - goto out_unlock; - } - - entry = mk_huge_pmd(new_page, vma->vm_page_prot); - entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - - /* - * Overwrite the old entry under pagetable lock and establish - * the new PTE. Any parallel GUP will either observe the old - * page blocking on the page lock, block on the page table - * lock or observe the new page. The SetPageUptodate on the - * new page and page_add_new_anon_rmap guarantee the copy is - * visible before the pagetable update. - */ - page_add_anon_rmap(new_page, vma, start, true); - /* - * At this point the pmd is numa/protnone (i.e. non present) and the TLB - * has already been flushed globally. So no TLB can be currently - * caching this non present pmd mapping. There's no need to clear the - * pmd before doing set_pmd_at(), nor to flush the TLB after - * set_pmd_at(). Clearing the pmd here would introduce a race - * condition against MADV_DONTNEED, because MADV_DONTNEED only holds the - * mmap_lock for reading. If the pmd is set to NULL at any given time, - * MADV_DONTNEED won't wait on the pmd lock and it'll skip clearing this - * pmd. - */ - set_pmd_at(mm, start, pmd, entry); - update_mmu_cache_pmd(vma, address, &entry); - - page_ref_unfreeze(page, 2); - mlock_migrate_page(new_page, page); - page_remove_rmap(page, true); - set_page_owner_migrate_reason(new_page, MR_NUMA_MISPLACED); - - spin_unlock(ptl); - - /* Take an "isolate" reference and put new page on the LRU. */ - get_page(new_page); - putback_lru_page(new_page); - - unlock_page(new_page); - unlock_page(page); - put_page(page); /* Drop the rmap reference */ - put_page(page); /* Drop the LRU isolation reference */ - - count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR); - count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR); - - mod_node_page_state(page_pgdat(page), - NR_ISOLATED_ANON + page_lru, - -HPAGE_PMD_NR); - return isolated; - -out_fail: - count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); - ptl = pmd_lock(mm, pmd); - if (pmd_same(*pmd, entry)) { - entry = pmd_modify(entry, vma->vm_page_prot); - set_pmd_at(mm, start, pmd, entry); - update_mmu_cache_pmd(vma, address, &entry); - } - spin_unlock(ptl); - -out_unlock: - unlock_page(page); - put_page(page); - return 0; -} -#endif /* CONFIG_NUMA_BALANCING */ - #endif /* CONFIG_NUMA */ #ifdef CONFIG_DEVICE_PRIVATE @@ -2399,7 +2294,7 @@ again: if (!is_device_private_entry(entry)) goto next; - page = device_private_entry_to_page(entry); + page = pfn_swap_entry_to_page(entry); if (!(migrate->flags & MIGRATE_VMA_SELECT_DEVICE_PRIVATE) || page->pgmap->owner != migrate->pgmap_owner) @@ -2407,7 +2302,7 @@ again: mpfn = migrate_pfn(page_to_pfn(page)) | MIGRATE_PFN_MIGRATE; - if (is_write_device_private_entry(entry)) + if (is_writable_device_private_entry(entry)) mpfn |= MIGRATE_PFN_WRITE; } else { if (!(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM)) @@ -2453,8 +2348,12 @@ again: ptep_get_and_clear(mm, addr, ptep); /* Setup special migration page table entry */ - entry = make_migration_entry(page, mpfn & - MIGRATE_PFN_WRITE); + if (mpfn & MIGRATE_PFN_WRITE) + entry = make_writable_migration_entry( + page_to_pfn(page)); + else + entry = make_readable_migration_entry( + page_to_pfn(page)); swp_pte = swp_entry_to_pte(entry); if (pte_present(pte)) { if (pte_soft_dirty(pte)) @@ -2517,8 +2416,8 @@ static void migrate_vma_collect(struct migrate_vma *migrate) * that the registered device driver can skip invalidating device * private page mappings that won't be migrated. */ - mmu_notifier_range_init_migrate(&range, 0, migrate->vma, - migrate->vma->vm_mm, migrate->start, migrate->end, + mmu_notifier_range_init_owner(&range, MMU_NOTIFY_MIGRATE, 0, + migrate->vma, migrate->vma->vm_mm, migrate->start, migrate->end, migrate->pgmap_owner); mmu_notifier_invalidate_range_start(&range); @@ -2703,7 +2602,6 @@ static void migrate_vma_prepare(struct migrate_vma *migrate) */ static void migrate_vma_unmap(struct migrate_vma *migrate) { - int flags = TTU_MIGRATION | TTU_IGNORE_MLOCK; const unsigned long npages = migrate->npages; const unsigned long start = migrate->start; unsigned long addr, i, restore = 0; @@ -2715,7 +2613,7 @@ static void migrate_vma_unmap(struct migrate_vma *migrate) continue; if (page_mapped(page)) { - try_to_unmap(page, flags); + try_to_migrate(page, 0); if (page_mapped(page)) goto restore; } @@ -2927,7 +2825,12 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, if (is_device_private_page(page)) { swp_entry_t swp_entry; - swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE); + if (vma->vm_flags & VM_WRITE) + swp_entry = make_writable_device_private_entry( + page_to_pfn(page)); + else + swp_entry = make_readable_device_private_entry( + page_to_pfn(page)); entry = swp_entry_to_pte(swp_entry); } else { /* @@ -3024,9 +2927,9 @@ void migrate_vma_pages(struct migrate_vma *migrate) if (!notified) { notified = true; - mmu_notifier_range_init_migrate(&range, 0, - migrate->vma, migrate->vma->vm_mm, - addr, migrate->end, + mmu_notifier_range_init_owner(&range, + MMU_NOTIFY_MIGRATE, 0, migrate->vma, + migrate->vma->vm_mm, addr, migrate->end, migrate->pgmap_owner); mmu_notifier_invalidate_range_start(&range); } diff --git a/mm/mlock.c b/mm/mlock.c index df590fda5688..0d639bf48794 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -108,7 +108,7 @@ void mlock_vma_page(struct page *page) /* * Finish munlock after successful page isolation * - * Page must be locked. This is a wrapper for try_to_munlock() + * Page must be locked. This is a wrapper for page_mlock() * and putback_lru_page() with munlock accounting. */ static void __munlock_isolated_page(struct page *page) @@ -118,7 +118,7 @@ static void __munlock_isolated_page(struct page *page) * and we don't need to check all the other vmas. */ if (page_mapcount(page) > 1) - try_to_munlock(page); + page_mlock(page); /* Did try_to_unlock() succeed or punt? */ if (!PageMlocked(page)) @@ -158,7 +158,7 @@ static void __munlock_isolation_failed(struct page *page) * munlock()ed or munmap()ed, we want to check whether other vmas hold the * page locked so that we can leave it on the unevictable lru list and not * bother vmscan with it. However, to walk the page's rmap list in - * try_to_munlock() we must isolate the page from the LRU. If some other + * page_mlock() we must isolate the page from the LRU. If some other * task has removed the page from the LRU, we won't be able to do that. * So we clear the PageMlocked as we might not get another chance. If we * can't isolate the page, we leave it for putback_lru_page() and vmscan @@ -168,7 +168,7 @@ unsigned int munlock_vma_page(struct page *page) { int nr_pages; - /* For try_to_munlock() and to serialize with page migration */ + /* For page_mlock() and to serialize with page migration */ BUG_ON(!PageLocked(page)); VM_BUG_ON_PAGE(PageTail(page), page); @@ -205,7 +205,7 @@ static int __mlock_posix_error_return(long retval) * * The fast path is available only for evictable pages with single mapping. * Then we can bypass the per-cpu pvec and get better performance. - * when mapcount > 1 we need try_to_munlock() which can fail. + * when mapcount > 1 we need page_mlock() which can fail. * when !page_evictable(), we need the full redo logic of putback_lru_page to * avoid leaving evictable page in unevictable list. * @@ -414,7 +414,7 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec, * * We don't save and restore VM_LOCKED here because pages are * still on lru. In unmap path, pages might be scanned by reclaim - * and re-mlocked by try_to_{munlock|unmap} before we unmap and + * and re-mlocked by page_mlock/try_to_unmap before we unmap and * free them. This will result in freeing mlocked pages. */ void munlock_vma_pages_range(struct vm_area_struct *vma, @@ -817,9 +817,10 @@ SYSCALL_DEFINE0(munlockall) */ static DEFINE_SPINLOCK(shmlock_user_lock); -int user_shm_lock(size_t size, struct user_struct *user) +int user_shm_lock(size_t size, struct ucounts *ucounts) { unsigned long lock_limit, locked; + long memlock; int allowed = 0; locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; @@ -828,21 +829,26 @@ int user_shm_lock(size_t size, struct user_struct *user) allowed = 1; lock_limit >>= PAGE_SHIFT; spin_lock(&shmlock_user_lock); - if (!allowed && - locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK)) + memlock = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); + + if (!allowed && (memlock == LONG_MAX || memlock > lock_limit) && !capable(CAP_IPC_LOCK)) { + dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); + goto out; + } + if (!get_ucounts(ucounts)) { + dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); goto out; - get_uid(user); - user->locked_shm += locked; + } allowed = 1; out: spin_unlock(&shmlock_user_lock); return allowed; } -void user_shm_unlock(size_t size, struct user_struct *user) +void user_shm_unlock(size_t size, struct ucounts *ucounts) { spin_lock(&shmlock_user_lock); - user->locked_shm -= (size + PAGE_SIZE - 1) >> PAGE_SHIFT; + dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, (size + PAGE_SIZE - 1) >> PAGE_SHIFT); spin_unlock(&shmlock_user_lock); - free_uid(user); + put_ucounts(ucounts); } diff --git a/mm/mmap.c b/mm/mmap.c index 0584e540246e..aa9de981b659 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1457,9 +1457,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, return addr; if (flags & MAP_FIXED_NOREPLACE) { - struct vm_area_struct *vma = find_vma(mm, addr); - - if (vma && vma->vm_start < addr + len) + if (find_vma_intersection(mm, addr, addr + len)) return -EEXIST; } @@ -1611,7 +1609,7 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, goto out_fput; } } else if (flags & MAP_HUGETLB) { - struct user_struct *user = NULL; + struct ucounts *ucounts = NULL; struct hstate *hs; hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); @@ -1627,13 +1625,13 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, */ file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, - &user, HUGETLB_ANONHUGE_INODE, + &ucounts, HUGETLB_ANONHUGE_INODE, (flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (IS_ERR(file)) return PTR_ERR(file); } - flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); + flags &= ~MAP_DENYWRITE; retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); out_fput: @@ -2802,6 +2800,22 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, return __split_vma(mm, vma, addr, new_below); } +static inline void +unlock_range(struct vm_area_struct *start, unsigned long limit) +{ + struct mm_struct *mm = start->vm_mm; + struct vm_area_struct *tmp = start; + + while (tmp && tmp->vm_start < limit) { + if (tmp->vm_flags & VM_LOCKED) { + mm->locked_vm -= vma_pages(tmp); + munlock_vma_pages_all(tmp); + } + + tmp = tmp->vm_next; + } +} + /* Munmap is split into 2 main parts -- this part which finds * what needs doing, and the areas themselves, which do the * work. This now handles partial unmappings. @@ -2828,16 +2842,11 @@ int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, */ arch_unmap(mm, start, end); - /* Find the first overlapping VMA */ - vma = find_vma(mm, start); + /* Find the first overlapping VMA where start < vma->vm_end */ + vma = find_vma_intersection(mm, start, end); if (!vma) return 0; prev = vma->vm_prev; - /* we have start < vma->vm_end */ - - /* if it doesn't overlap, we have nothing.. */ - if (vma->vm_start >= end) - return 0; /* * If we need to split any vma, do it now to save pain later. @@ -2890,17 +2899,8 @@ int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, /* * unlock any mlock()ed ranges before detaching vmas */ - if (mm->locked_vm) { - struct vm_area_struct *tmp = vma; - while (tmp && tmp->vm_start < end) { - if (tmp->vm_flags & VM_LOCKED) { - mm->locked_vm -= vma_pages(tmp); - munlock_vma_pages_all(tmp); - } - - tmp = tmp->vm_next; - } - } + if (mm->locked_vm) + unlock_range(vma, end); /* Detach vmas from rbtree */ if (!detach_vmas_to_be_unmapped(mm, vma, prev, end)) @@ -3185,14 +3185,8 @@ void exit_mmap(struct mm_struct *mm) mmap_write_unlock(mm); } - if (mm->locked_vm) { - vma = mm->mmap; - while (vma) { - if (vma->vm_flags & VM_LOCKED) - munlock_vma_pages_all(vma); - vma = vma->vm_next; - } - } + if (mm->locked_vm) + unlock_range(mm->mmap, ULONG_MAX); arch_exit_mmap(mm); diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c index dcdde4f722a4..f5852a058ce0 100644 --- a/mm/mmap_lock.c +++ b/mm/mmap_lock.c @@ -11,6 +11,7 @@ #include <linux/rcupdate.h> #include <linux/smp.h> #include <linux/trace_events.h> +#include <linux/local_lock.h> EXPORT_TRACEPOINT_SYMBOL(mmap_lock_start_locking); EXPORT_TRACEPOINT_SYMBOL(mmap_lock_acquire_returned); @@ -39,21 +40,30 @@ static int reg_refcount; /* Protected by reg_lock. */ */ #define CONTEXT_COUNT 4 -static DEFINE_PER_CPU(char __rcu *, memcg_path_buf); +struct memcg_path { + local_lock_t lock; + char __rcu *buf; + local_t buf_idx; +}; +static DEFINE_PER_CPU(struct memcg_path, memcg_paths) = { + .lock = INIT_LOCAL_LOCK(lock), + .buf_idx = LOCAL_INIT(0), +}; + static char **tmp_bufs; -static DEFINE_PER_CPU(int, memcg_path_buf_idx); /* Called with reg_lock held. */ static void free_memcg_path_bufs(void) { + struct memcg_path *memcg_path; int cpu; char **old = tmp_bufs; for_each_possible_cpu(cpu) { - *(old++) = rcu_dereference_protected( - per_cpu(memcg_path_buf, cpu), + memcg_path = per_cpu_ptr(&memcg_paths, cpu); + *(old++) = rcu_dereference_protected(memcg_path->buf, lockdep_is_held(®_lock)); - rcu_assign_pointer(per_cpu(memcg_path_buf, cpu), NULL); + rcu_assign_pointer(memcg_path->buf, NULL); } /* Wait for inflight memcg_path_buf users to finish. */ @@ -88,7 +98,7 @@ int trace_mmap_lock_reg(void) new = kmalloc(MEMCG_PATH_BUF_SIZE * CONTEXT_COUNT, GFP_KERNEL); if (new == NULL) goto out_fail_free; - rcu_assign_pointer(per_cpu(memcg_path_buf, cpu), new); + rcu_assign_pointer(per_cpu_ptr(&memcg_paths, cpu)->buf, new); /* Don't need to wait for inflights, they'd have gotten NULL. */ } @@ -122,26 +132,58 @@ out: static inline char *get_memcg_path_buf(void) { + struct memcg_path *memcg_path = this_cpu_ptr(&memcg_paths); char *buf; int idx; rcu_read_lock(); - buf = rcu_dereference(*this_cpu_ptr(&memcg_path_buf)); + buf = rcu_dereference(memcg_path->buf); if (buf == NULL) { rcu_read_unlock(); return NULL; } - idx = this_cpu_add_return(memcg_path_buf_idx, MEMCG_PATH_BUF_SIZE) - + idx = local_add_return(MEMCG_PATH_BUF_SIZE, &memcg_path->buf_idx) - MEMCG_PATH_BUF_SIZE; return &buf[idx]; } static inline void put_memcg_path_buf(void) { - this_cpu_sub(memcg_path_buf_idx, MEMCG_PATH_BUF_SIZE); + local_sub(MEMCG_PATH_BUF_SIZE, &this_cpu_ptr(&memcg_paths)->buf_idx); rcu_read_unlock(); } +#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ + do { \ + const char *memcg_path; \ + preempt_disable(); \ + memcg_path = get_mm_memcg_path(mm); \ + trace_mmap_lock_##type(mm, \ + memcg_path != NULL ? memcg_path : "", \ + ##__VA_ARGS__); \ + if (likely(memcg_path != NULL)) \ + put_memcg_path_buf(); \ + preempt_enable(); \ + } while (0) + +#else /* !CONFIG_MEMCG */ + +int trace_mmap_lock_reg(void) +{ + return 0; +} + +void trace_mmap_lock_unreg(void) +{ +} + +#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ + trace_mmap_lock_##type(mm, "", ##__VA_ARGS__) + +#endif /* CONFIG_MEMCG */ + +#ifdef CONFIG_TRACING +#ifdef CONFIG_MEMCG /* * Write the given mm_struct's memcg path to a percpu buffer, and return a * pointer to it. If the path cannot be determined, or no buffer was available @@ -176,33 +218,6 @@ out: return buf; } -#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ - do { \ - const char *memcg_path; \ - preempt_disable(); \ - memcg_path = get_mm_memcg_path(mm); \ - trace_mmap_lock_##type(mm, \ - memcg_path != NULL ? memcg_path : "", \ - ##__VA_ARGS__); \ - if (likely(memcg_path != NULL)) \ - put_memcg_path_buf(); \ - preempt_enable(); \ - } while (0) - -#else /* !CONFIG_MEMCG */ - -int trace_mmap_lock_reg(void) -{ - return 0; -} - -void trace_mmap_lock_unreg(void) -{ -} - -#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ - trace_mmap_lock_##type(mm, "", ##__VA_ARGS__) - #endif /* CONFIG_MEMCG */ /* @@ -228,3 +243,4 @@ void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write) TRACE_MMAP_LOCK_EVENT(released, mm, write); } EXPORT_SYMBOL(__mmap_lock_do_trace_released); +#endif /* CONFIG_TRACING */ diff --git a/mm/mprotect.c b/mm/mprotect.c index e7a443157988..883e2cc85cad 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -143,26 +143,36 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, swp_entry_t entry = pte_to_swp_entry(oldpte); pte_t newpte; - if (is_write_migration_entry(entry)) { + if (is_writable_migration_entry(entry)) { /* * A protection check is difficult so * just be safe and disable write */ - make_migration_entry_read(&entry); + entry = make_readable_migration_entry( + swp_offset(entry)); newpte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(oldpte)) newpte = pte_swp_mksoft_dirty(newpte); if (pte_swp_uffd_wp(oldpte)) newpte = pte_swp_mkuffd_wp(newpte); - } else if (is_write_device_private_entry(entry)) { + } else if (is_writable_device_private_entry(entry)) { /* * We do not preserve soft-dirtiness. See * copy_one_pte() for explanation. */ - make_device_private_entry_read(&entry); + entry = make_readable_device_private_entry( + swp_offset(entry)); newpte = swp_entry_to_pte(entry); if (pte_swp_uffd_wp(oldpte)) newpte = pte_swp_mkuffd_wp(newpte); + } else if (is_writable_device_exclusive_entry(entry)) { + entry = make_readable_device_exclusive_entry( + swp_offset(entry)); + newpte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(oldpte)) + newpte = pte_swp_mksoft_dirty(newpte); + if (pte_swp_uffd_wp(oldpte)) + newpte = pte_swp_mkuffd_wp(newpte); } else { newpte = oldpte; } diff --git a/mm/mremap.c b/mm/mremap.c index 47c255b60150..a369a6100698 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -634,10 +634,11 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, unsigned long *p) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma = find_vma(mm, addr); + struct vm_area_struct *vma; unsigned long pgoff; - if (!vma || vma->vm_start > addr) + vma = vma_lookup(mm, addr); + if (!vma) return ERR_PTR(-EFAULT); /* diff --git a/mm/nommu.c b/mm/nommu.c index 85a3a68dffb6..3a93d4054810 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -223,7 +223,7 @@ long vread(char *buf, char *addr, unsigned long count) */ void *vmalloc(unsigned long size) { - return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM); + return __vmalloc(size, GFP_KERNEL); } EXPORT_SYMBOL(vmalloc); @@ -241,7 +241,7 @@ EXPORT_SYMBOL(vmalloc); */ void *vzalloc(unsigned long size) { - return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); + return __vmalloc(size, GFP_KERNEL | __GFP_ZERO); } EXPORT_SYMBOL(vzalloc); @@ -1296,7 +1296,7 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, goto out; } - flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); + flags &= ~MAP_DENYWRITE; retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); @@ -1501,7 +1501,6 @@ erase_whole_vma: delete_vma(mm, vma); return 0; } -EXPORT_SYMBOL(do_munmap); int vm_munmap(unsigned long addr, size_t len) { diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 54527de9cd2d..c729a4c4a1ac 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -104,7 +104,7 @@ static bool oom_cpuset_eligible(struct task_struct *start, * mempolicy intersects current, otherwise it may be * needlessly killed. */ - ret = mempolicy_nodemask_intersects(tsk, mask); + ret = mempolicy_in_oom_domain(tsk, mask); } else { /* * This is not a mempolicy constrained oom, so only diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0062d5c57d41..9f63548f247c 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -32,7 +32,6 @@ #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/syscalls.h> -#include <linux/buffer_head.h> /* __set_page_dirty_buffers */ #include <linux/pagevec.h> #include <linux/timer.h> #include <linux/sched/rt.h> @@ -109,11 +108,6 @@ EXPORT_SYMBOL_GPL(dirty_writeback_interval); unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */ /* - * Flag that makes the machine dump writes/reads and block dirtyings. - */ -int block_dump; - -/* * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies: * a full sync is triggered after this time elapses without any disk activity. */ @@ -845,7 +839,7 @@ static long long pos_ratio_polynom(unsigned long setpoint, * ^ pos_ratio * | * | |<===== global dirty control scope ======>| - * 2.0 .............* + * 2.0 * * * * * * * * | .* * | . * * | . * @@ -1869,10 +1863,9 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * - * On really big machines, get_writeback_state is expensive, so try to avoid - * calling it too often (ratelimiting). But once we're over the dirty memory - * limit we decrease the ratelimiting by a lot, to prevent individual processes - * from overshooting the limit by (ratelimit_pages) each. + * Once we're over the dirty memory limit we decrease the ratelimiting + * by a lot, to prevent individual processes from overshooting the limit + * by (ratelimit_pages) each. */ void balance_dirty_pages_ratelimited(struct address_space *mapping) { @@ -1945,6 +1938,8 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; + unsigned long reclaimable; + unsigned long thresh; /* * Similar to balance_dirty_pages() but ignores pages being written @@ -1957,8 +1952,13 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) if (gdtc->dirty > gdtc->bg_thresh) return true; - if (wb_stat(wb, WB_RECLAIMABLE) > - wb_calc_thresh(gdtc->wb, gdtc->bg_thresh)) + thresh = wb_calc_thresh(gdtc->wb, gdtc->bg_thresh); + if (thresh < 2 * wb_stat_error()) + reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); + else + reclaimable = wb_stat(wb, WB_RECLAIMABLE); + + if (reclaimable > thresh) return true; if (mdtc) { @@ -1972,8 +1972,13 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) if (mdtc->dirty > mdtc->bg_thresh) return true; - if (wb_stat(wb, WB_RECLAIMABLE) > - wb_calc_thresh(mdtc->wb, mdtc->bg_thresh)) + thresh = wb_calc_thresh(mdtc->wb, mdtc->bg_thresh); + if (thresh < 2 * wb_stat_error()) + reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); + else + reclaimable = wb_stat(wb, WB_RECLAIMABLE); + + if (reclaimable > thresh) return true; } @@ -2045,8 +2050,6 @@ void laptop_sync_completion(void) /* * If ratelimit_pages is too high then we can get into dirty-data overload * if a large number of processes all perform writes at the same time. - * If it is too low then SMP machines will call the (expensive) - * get_writeback_state too often. * * Here we set ratelimit_pages to a level which ensures that when all CPUs are * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory @@ -2409,6 +2412,7 @@ int __set_page_dirty_no_writeback(struct page *page) return !TestSetPageDirty(page); return 0; } +EXPORT_SYMBOL(__set_page_dirty_no_writeback); /* * Helper function for set_page_dirty family. @@ -2417,7 +2421,8 @@ int __set_page_dirty_no_writeback(struct page *page) * * NOTE: This relies on being atomic wrt interrupts. */ -void account_page_dirtied(struct page *page, struct address_space *mapping) +static void account_page_dirtied(struct page *page, + struct address_space *mapping) { struct inode *inode = mapping->host; @@ -2436,7 +2441,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) inc_wb_stat(wb, WB_DIRTIED); task_io_account_write(PAGE_SIZE); current->nr_dirtied++; - this_cpu_inc(bdp_ratelimits); + __this_cpu_inc(bdp_ratelimits); mem_cgroup_track_foreign_dirty(page, wb); } @@ -2459,6 +2464,30 @@ void account_page_cleaned(struct page *page, struct address_space *mapping, } /* + * Mark the page dirty, and set it dirty in the page cache, and mark the inode + * dirty. + * + * If warn is true, then emit a warning if the page is not uptodate and has + * not been truncated. + * + * The caller must hold lock_page_memcg(). + */ +void __set_page_dirty(struct page *page, struct address_space *mapping, + int warn) +{ + unsigned long flags; + + xa_lock_irqsave(&mapping->i_pages, flags); + if (page->mapping) { /* Race with truncate? */ + WARN_ON_ONCE(warn && !PageUptodate(page)); + account_page_dirtied(page, mapping); + __xa_set_mark(&mapping->i_pages, page_index(page), + PAGECACHE_TAG_DIRTY); + } + xa_unlock_irqrestore(&mapping->i_pages, flags); +} + +/* * For address_spaces which do not use buffers. Just tag the page as dirty in * the xarray. * @@ -2475,20 +2504,12 @@ int __set_page_dirty_nobuffers(struct page *page) lock_page_memcg(page); if (!TestSetPageDirty(page)) { struct address_space *mapping = page_mapping(page); - unsigned long flags; if (!mapping) { unlock_page_memcg(page); return 1; } - - xa_lock_irqsave(&mapping->i_pages, flags); - BUG_ON(page_mapping(page) != mapping); - WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); - account_page_dirtied(page, mapping); - __xa_set_mark(&mapping->i_pages, page_index(page), - PAGECACHE_TAG_DIRTY); - xa_unlock_irqrestore(&mapping->i_pages, flags); + __set_page_dirty(page, mapping, !PagePrivate(page)); unlock_page_memcg(page); if (mapping->host) { @@ -2546,13 +2567,9 @@ EXPORT_SYMBOL(redirty_page_for_writepage); /* * Dirty a page. * - * For pages with a mapping this should be done under the page lock - * for the benefit of asynchronous memory errors who prefer a consistent - * dirty state. This rule can be broken in some special cases, - * but should be better not to. - * - * If the mapping doesn't provide a set_page_dirty a_op, then - * just fall through and assume that it wants buffer_heads. + * For pages with a mapping this should be done under the page lock for the + * benefit of asynchronous memory errors who prefer a consistent dirty state. + * This rule can be broken in some special cases, but should be better not to. */ int set_page_dirty(struct page *page) { @@ -2560,7 +2577,6 @@ int set_page_dirty(struct page *page) page = compound_head(page); if (likely(mapping)) { - int (*spd)(struct page *) = mapping->a_ops->set_page_dirty; /* * readahead/lru_deactivate_page could remain * PG_readahead/PG_reclaim due to race with end_page_writeback @@ -2573,11 +2589,7 @@ int set_page_dirty(struct page *page) */ if (PageReclaim(page)) ClearPageReclaim(page); -#ifdef CONFIG_BLOCK - if (!spd) - spd = __set_page_dirty_buffers; -#endif - return (*spd)(page); + return mapping->a_ops->set_page_dirty(page); } if (!PageDirty(page)) { if (!TestSetPageDirty(page)) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index aaa1655cf682..d6e94cc8066c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -120,7 +120,25 @@ typedef int __bitwise fpi_t; /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */ static DEFINE_MUTEX(pcp_batch_high_lock); -#define MIN_PERCPU_PAGELIST_FRACTION (8) +#define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8) + +struct pagesets { + local_lock_t lock; +#if defined(CONFIG_DEBUG_INFO_BTF) && \ + !defined(CONFIG_DEBUG_LOCK_ALLOC) && \ + !defined(CONFIG_PAHOLE_HAS_ZEROSIZE_PERCPU_SUPPORT) + /* + * pahole 1.21 and earlier gets confused by zero-sized per-CPU + * variables and produces invalid BTF. Ensure that + * sizeof(struct pagesets) != 0 for older versions of pahole. + */ + char __pahole_hack; + #warning "pahole too old to support zero-sized struct pagesets" +#endif +}; +static DEFINE_PER_CPU(struct pagesets, pagesets) = { + .lock = INIT_LOCAL_LOCK(lock), +}; #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); @@ -175,7 +193,7 @@ EXPORT_SYMBOL(_totalram_pages); unsigned long totalreserve_pages __read_mostly; unsigned long totalcma_pages __read_mostly; -int percpu_pagelist_fraction; +int percpu_pagelist_high_fraction; gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc); EXPORT_SYMBOL(init_on_alloc); @@ -331,20 +349,7 @@ compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS] = { int min_free_kbytes = 1024; int user_min_free_kbytes = -1; -#ifdef CONFIG_DISCONTIGMEM -/* - * DiscontigMem defines memory ranges as separate pg_data_t even if the ranges - * are not on separate NUMA nodes. Functionally this works but with - * watermark_boost_factor, it can reclaim prematurely as the ranges can be - * quite small. By default, do not boost watermarks on discontigmem as in - * many cases very high-order allocations like THP are likely to be - * unsupported and the premature reclaim offsets the advantage of long-term - * fragmentation avoidance. - */ -int watermark_boost_factor __read_mostly; -#else int watermark_boost_factor __read_mostly = 15000; -#endif int watermark_scale_factor = 10; static unsigned long nr_kernel_pages __initdata; @@ -382,7 +387,7 @@ int page_group_by_mobility_disabled __read_mostly; static DEFINE_STATIC_KEY_TRUE(deferred_pages); /* - * Calling kasan_free_pages() only after deferred memory initialization + * Calling kasan_poison_pages() only after deferred memory initialization * has completed. Poisoning pages during deferred memory init will greatly * lengthen the process and cause problem in large memory systems as the * deferred pages initialization is done with interrupt disabled. @@ -394,15 +399,12 @@ static DEFINE_STATIC_KEY_TRUE(deferred_pages); * on-demand allocation and then freed again before the deferred pages * initialization is done, but this is not likely to happen. */ -static inline void kasan_free_nondeferred_pages(struct page *page, int order, - bool init, fpi_t fpi_flags) +static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags) { - if (static_branch_unlikely(&deferred_pages)) - return; - if (!IS_ENABLED(CONFIG_KASAN_GENERIC) && - (fpi_flags & FPI_SKIP_KASAN_POISON)) - return; - kasan_free_pages(page, order, init); + return static_branch_unlikely(&deferred_pages) || + (!IS_ENABLED(CONFIG_KASAN_GENERIC) && + (fpi_flags & FPI_SKIP_KASAN_POISON)) || + PageSkipKASanPoison(page); } /* Returns true if the struct page for the pfn is uninitialised */ @@ -453,13 +455,11 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn) return false; } #else -static inline void kasan_free_nondeferred_pages(struct page *page, int order, - bool init, fpi_t fpi_flags) +static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags) { - if (!IS_ENABLED(CONFIG_KASAN_GENERIC) && - (fpi_flags & FPI_SKIP_KASAN_POISON)) - return; - kasan_free_pages(page, order, init); + return (!IS_ENABLED(CONFIG_KASAN_GENERIC) && + (fpi_flags & FPI_SKIP_KASAN_POISON)) || + PageSkipKASanPoison(page); } static inline bool early_page_uninitialised(unsigned long pfn) @@ -474,7 +474,7 @@ static inline bool defer_init(int nid, unsigned long pfn, unsigned long end_pfn) #endif /* Return a pointer to the bitmap storing bits affecting a block of pages */ -static inline unsigned long *get_pageblock_bitmap(struct page *page, +static inline unsigned long *get_pageblock_bitmap(const struct page *page, unsigned long pfn) { #ifdef CONFIG_SPARSEMEM @@ -484,7 +484,7 @@ static inline unsigned long *get_pageblock_bitmap(struct page *page, #endif /* CONFIG_SPARSEMEM */ } -static inline int pfn_to_bitidx(struct page *page, unsigned long pfn) +static inline int pfn_to_bitidx(const struct page *page, unsigned long pfn) { #ifdef CONFIG_SPARSEMEM pfn &= (PAGES_PER_SECTION-1); @@ -495,7 +495,7 @@ static inline int pfn_to_bitidx(struct page *page, unsigned long pfn) } static __always_inline -unsigned long __get_pfnblock_flags_mask(struct page *page, +unsigned long __get_pfnblock_flags_mask(const struct page *page, unsigned long pfn, unsigned long mask) { @@ -520,13 +520,14 @@ unsigned long __get_pfnblock_flags_mask(struct page *page, * * Return: pageblock_bits flags */ -unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, - unsigned long mask) +unsigned long get_pfnblock_flags_mask(const struct page *page, + unsigned long pfn, unsigned long mask) { return __get_pfnblock_flags_mask(page, pfn, mask); } -static __always_inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn) +static __always_inline int get_pfnblock_migratetype(const struct page *page, + unsigned long pfn) { return __get_pfnblock_flags_mask(page, pfn, MIGRATETYPE_MASK); } @@ -658,8 +659,7 @@ static void bad_page(struct page *page, const char *reason) pr_alert("BUG: Bad page state in process %s pfn:%05lx\n", current->comm, page_to_pfn(page)); - __dump_page(page, reason); - dump_page_owner(page); + dump_page(page, reason); print_modules(); dump_stack(); @@ -669,6 +669,57 @@ out: add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } +static inline unsigned int order_to_pindex(int migratetype, int order) +{ + int base = order; + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (order > PAGE_ALLOC_COSTLY_ORDER) { + VM_BUG_ON(order != pageblock_order); + base = PAGE_ALLOC_COSTLY_ORDER + 1; + } +#else + VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); +#endif + + return (MIGRATE_PCPTYPES * base) + migratetype; +} + +static inline int pindex_to_order(unsigned int pindex) +{ + int order = pindex / MIGRATE_PCPTYPES; + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (order > PAGE_ALLOC_COSTLY_ORDER) { + order = pageblock_order; + VM_BUG_ON(order != pageblock_order); + } +#else + VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); +#endif + + return order; +} + +static inline bool pcp_allowed_order(unsigned int order) +{ + if (order <= PAGE_ALLOC_COSTLY_ORDER) + return true; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (order == pageblock_order) + return true; +#endif + return false; +} + +static inline void free_the_page(struct page *page, unsigned int order) +{ + if (pcp_allowed_order(order)) /* Via pcp? */ + free_unref_page(page, order); + else + __free_pages_ok(page, order, FPI_NONE); +} + /* * Higher-order pages are called "compound pages". They are structured thusly: * @@ -687,7 +738,7 @@ out: void free_compound_page(struct page *page) { mem_cgroup_uncharge(page); - __free_pages_ok(page, compound_order(page), FPI_NONE); + free_the_page(page, compound_order(page)); } void prep_compound_page(struct page *page, unsigned int order) @@ -698,7 +749,6 @@ void prep_compound_page(struct page *page, unsigned int order) __SetPageHead(page); for (i = 1; i < nr_pages; i++) { struct page *p = page + i; - set_page_count(p, 0); p->mapping = TAIL_MAPPING; set_compound_head(p, page); } @@ -1226,10 +1276,16 @@ out: return ret; } -static void kernel_init_free_pages(struct page *page, int numpages) +static void kernel_init_free_pages(struct page *page, int numpages, bool zero_tags) { int i; + if (zero_tags) { + for (i = 0; i < numpages; i++) + tag_clear_highpage(page + i); + return; + } + /* s390's use of memset() could override KASAN redzones. */ kasan_disable_current(); for (i = 0; i < numpages; i++) { @@ -1245,7 +1301,7 @@ static __always_inline bool free_pages_prepare(struct page *page, unsigned int order, bool check_free, fpi_t fpi_flags) { int bad = 0; - bool init; + bool skip_kasan_poison = should_skip_kasan_poison(page, fpi_flags); VM_BUG_ON_PAGE(PageTail(page), page); @@ -1314,10 +1370,17 @@ static __always_inline bool free_pages_prepare(struct page *page, * With hardware tag-based KASAN, memory tags must be set before the * page becomes unavailable via debug_pagealloc or arch_free_page. */ - init = want_init_on_free(); - if (init && !kasan_has_integrated_init()) - kernel_init_free_pages(page, 1 << order); - kasan_free_nondeferred_pages(page, order, init, fpi_flags); + if (kasan_has_integrated_init()) { + if (!skip_kasan_poison) + kasan_free_pages(page, order); + } else { + bool init = want_init_on_free(); + + if (init) + kernel_init_free_pages(page, 1 << order, false); + if (!skip_kasan_poison) + kasan_poison_pages(page, order, init); + } /* * arch_free_page() can make the page's contents inaccessible. s390 @@ -1337,9 +1400,9 @@ static __always_inline bool free_pages_prepare(struct page *page, * to pcp lists. With debug_pagealloc also enabled, they are also rechecked when * moved from pcp lists to free lists. */ -static bool free_pcp_prepare(struct page *page) +static bool free_pcp_prepare(struct page *page, unsigned int order) { - return free_pages_prepare(page, 0, true, FPI_NONE); + return free_pages_prepare(page, order, true, FPI_NONE); } static bool bulkfree_pcp_prepare(struct page *page) @@ -1356,12 +1419,12 @@ static bool bulkfree_pcp_prepare(struct page *page) * debug_pagealloc enabled, they are checked also immediately when being freed * to the pcp lists. */ -static bool free_pcp_prepare(struct page *page) +static bool free_pcp_prepare(struct page *page, unsigned int order) { if (debug_pagealloc_enabled_static()) - return free_pages_prepare(page, 0, true, FPI_NONE); + return free_pages_prepare(page, order, true, FPI_NONE); else - return free_pages_prepare(page, 0, false, FPI_NONE); + return free_pages_prepare(page, order, false, FPI_NONE); } static bool bulkfree_pcp_prepare(struct page *page) @@ -1393,8 +1456,10 @@ static inline void prefetch_buddy(struct page *page) static void free_pcppages_bulk(struct zone *zone, int count, struct per_cpu_pages *pcp) { - int migratetype = 0; + int pindex = 0; int batch_free = 0; + int nr_freed = 0; + unsigned int order; int prefetch_nr = READ_ONCE(pcp->batch); bool isolated_pageblocks; struct page *page, *tmp; @@ -1405,7 +1470,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, * below while (list_empty(list)) loop. */ count = min(pcp->count, count); - while (count) { + while (count > 0) { struct list_head *list; /* @@ -1417,24 +1482,31 @@ static void free_pcppages_bulk(struct zone *zone, int count, */ do { batch_free++; - if (++migratetype == MIGRATE_PCPTYPES) - migratetype = 0; - list = &pcp->lists[migratetype]; + if (++pindex == NR_PCP_LISTS) + pindex = 0; + list = &pcp->lists[pindex]; } while (list_empty(list)); /* This is the only non-empty list. Free them all. */ - if (batch_free == MIGRATE_PCPTYPES) + if (batch_free == NR_PCP_LISTS) batch_free = count; + order = pindex_to_order(pindex); + BUILD_BUG_ON(MAX_ORDER >= (1<<NR_PCP_ORDER_WIDTH)); do { page = list_last_entry(list, struct page, lru); /* must delete to avoid corrupting pcp list */ list_del(&page->lru); - pcp->count--; + nr_freed += 1 << order; + count -= 1 << order; if (bulkfree_pcp_prepare(page)) continue; + /* Encode order with the migratetype */ + page->index <<= NR_PCP_ORDER_WIDTH; + page->index |= order; + list_add_tail(&page->lru, &head); /* @@ -1450,9 +1522,14 @@ static void free_pcppages_bulk(struct zone *zone, int count, prefetch_buddy(page); prefetch_nr--; } - } while (--count && --batch_free && !list_empty(list)); + } while (count > 0 && --batch_free && !list_empty(list)); } + pcp->count -= nr_freed; + /* + * local_lock_irq held so equivalent to spin_lock_irqsave for + * both PREEMPT_RT and non-PREEMPT_RT configurations. + */ spin_lock(&zone->lock); isolated_pageblocks = has_isolate_pageblock(zone); @@ -1462,14 +1539,19 @@ static void free_pcppages_bulk(struct zone *zone, int count, */ list_for_each_entry_safe(page, tmp, &head, lru) { int mt = get_pcppage_migratetype(page); + + /* mt has been encoded with the order (see above) */ + order = mt & NR_PCP_ORDER_MASK; + mt >>= NR_PCP_ORDER_WIDTH; + /* MIGRATE_ISOLATE page should not go to pcplists */ VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); /* Pageblock could have been isolated meanwhile */ if (unlikely(isolated_pageblocks)) mt = get_pageblock_migratetype(page); - __free_one_page(page, page_to_pfn(page), zone, 0, mt, FPI_NONE); - trace_mm_page_pcpu_drain(page, 0, mt); + __free_one_page(page, page_to_pfn(page), zone, order, mt, FPI_NONE); + trace_mm_page_pcpu_drain(page, order, mt); } spin_unlock(&zone->lock); } @@ -1479,13 +1561,15 @@ static void free_one_page(struct zone *zone, unsigned int order, int migratetype, fpi_t fpi_flags) { - spin_lock(&zone->lock); + unsigned long flags; + + spin_lock_irqsave(&zone->lock, flags); if (unlikely(has_isolate_pageblock(zone) || is_migrate_isolate(migratetype))) { migratetype = get_pfnblock_migratetype(page, pfn); } __free_one_page(page, pfn, zone, order, migratetype, fpi_flags); - spin_unlock(&zone->lock); + spin_unlock_irqrestore(&zone->lock, flags); } static void __meminit __init_single_page(struct page *page, unsigned long pfn, @@ -1568,16 +1652,22 @@ static void __free_pages_ok(struct page *page, unsigned int order, unsigned long flags; int migratetype; unsigned long pfn = page_to_pfn(page); + struct zone *zone = page_zone(page); if (!free_pages_prepare(page, order, true, fpi_flags)) return; migratetype = get_pfnblock_migratetype(page, pfn); - local_irq_save(flags); + + spin_lock_irqsave(&zone->lock, flags); + if (unlikely(has_isolate_pageblock(zone) || + is_migrate_isolate(migratetype))) { + migratetype = get_pfnblock_migratetype(page, pfn); + } + __free_one_page(page, pfn, zone, order, migratetype, fpi_flags); + spin_unlock_irqrestore(&zone->lock, flags); + __count_vm_events(PGFREE, 1 << order); - free_one_page(page_zone(page), page, pfn, order, migratetype, - fpi_flags); - local_irq_restore(flags); } void __free_pages_core(struct page *page, unsigned int order) @@ -1609,7 +1699,7 @@ void __free_pages_core(struct page *page, unsigned int order) __free_pages_ok(page, order, FPI_TO_TAIL | FPI_SKIP_KASAN_POISON); } -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA /* * During memory init memblocks map pfns to nids. The search is expensive and @@ -1659,7 +1749,7 @@ int __meminit early_pfn_to_nid(unsigned long pfn) return nid; } -#endif /* CONFIG_NEED_MULTIPLE_NODES */ +#endif /* CONFIG_NUMA */ void __init memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order) @@ -2147,14 +2237,6 @@ void __init page_alloc_init_late(void) wait_for_completion(&pgdat_init_all_done_comp); /* - * The number of managed pages has changed due to the initialisation - * so the pcpu batch and high limits needs to be updated or the limits - * will be artificially small. - */ - for_each_populated_zone(zone) - zone_pcp_update(zone); - - /* * We initialized the rest of the deferred pages. Permanently disable * on-demand struct page initialization. */ @@ -2324,8 +2406,6 @@ static bool check_new_pages(struct page *page, unsigned int order) inline void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags) { - bool init; - set_page_private(page, 0); set_page_refcounted(page); @@ -2344,10 +2424,16 @@ inline void post_alloc_hook(struct page *page, unsigned int order, * kasan_alloc_pages and kernel_init_free_pages must be * kept together to avoid discrepancies in behavior. */ - init = !want_init_on_free() && want_init_on_alloc(gfp_flags); - kasan_alloc_pages(page, order, init); - if (init && !kasan_has_integrated_init()) - kernel_init_free_pages(page, 1 << order); + if (kasan_has_integrated_init()) { + kasan_alloc_pages(page, order, gfp_flags); + } else { + bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags); + + kasan_unpoison_pages(page, order, init); + if (init) + kernel_init_free_pages(page, 1 << order, + gfp_flags & __GFP_ZEROTAGS); + } set_page_owner(page, order, gfp_flags); } @@ -2955,6 +3041,10 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, { int i, allocated = 0; + /* + * local_lock_irq held so equivalent to spin_lock_irqsave for + * both PREEMPT_RT and non-PREEMPT_RT configurations. + */ spin_lock(&zone->lock); for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype, @@ -3007,12 +3097,12 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) unsigned long flags; int to_drain, batch; - local_irq_save(flags); + local_lock_irqsave(&pagesets.lock, flags); batch = READ_ONCE(pcp->batch); to_drain = min(pcp->count, batch); if (to_drain > 0) free_pcppages_bulk(zone, to_drain, pcp); - local_irq_restore(flags); + local_unlock_irqrestore(&pagesets.lock, flags); } #endif @@ -3026,16 +3116,15 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) static void drain_pages_zone(unsigned int cpu, struct zone *zone) { unsigned long flags; - struct per_cpu_pageset *pset; struct per_cpu_pages *pcp; - local_irq_save(flags); - pset = per_cpu_ptr(zone->pageset, cpu); + local_lock_irqsave(&pagesets.lock, flags); - pcp = &pset->pcp; + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); if (pcp->count) free_pcppages_bulk(zone, pcp->count, pcp); - local_irq_restore(flags); + + local_unlock_irqrestore(&pagesets.lock, flags); } /* @@ -3103,7 +3192,7 @@ static void __drain_all_pages(struct zone *zone, bool force_all_cpus) int cpu; /* - * Allocate in the BSS so we wont require allocation in + * Allocate in the BSS so we won't require allocation in * direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y */ static cpumask_t cpus_with_pcps; @@ -3133,7 +3222,7 @@ static void __drain_all_pages(struct zone *zone, bool force_all_cpus) * disables preemption as part of its processing */ for_each_online_cpu(cpu) { - struct per_cpu_pageset *pcp; + struct per_cpu_pages *pcp; struct zone *z; bool has_pcps = false; @@ -3144,13 +3233,13 @@ static void __drain_all_pages(struct zone *zone, bool force_all_cpus) */ has_pcps = true; } else if (zone) { - pcp = per_cpu_ptr(zone->pageset, cpu); - if (pcp->pcp.count) + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + if (pcp->count) has_pcps = true; } else { for_each_populated_zone(z) { - pcp = per_cpu_ptr(z->pageset, cpu); - if (pcp->pcp.count) { + pcp = per_cpu_ptr(z->per_cpu_pageset, cpu); + if (pcp->count) { has_pcps = true; break; } @@ -3243,11 +3332,12 @@ void mark_free_pages(struct zone *zone) } #endif /* CONFIG_PM */ -static bool free_unref_page_prepare(struct page *page, unsigned long pfn) +static bool free_unref_page_prepare(struct page *page, unsigned long pfn, + unsigned int order) { int migratetype; - if (!free_pcp_prepare(page)) + if (!free_pcp_prepare(page, order)) return false; migratetype = get_pfnblock_migratetype(page, pfn); @@ -3255,52 +3345,99 @@ static bool free_unref_page_prepare(struct page *page, unsigned long pfn) return true; } -static void free_unref_page_commit(struct page *page, unsigned long pfn) +static int nr_pcp_free(struct per_cpu_pages *pcp, int high, int batch) +{ + int min_nr_free, max_nr_free; + + /* Check for PCP disabled or boot pageset */ + if (unlikely(high < batch)) + return 1; + + /* Leave at least pcp->batch pages on the list */ + min_nr_free = batch; + max_nr_free = high - batch; + + /* + * Double the number of pages freed each time there is subsequent + * freeing of pages without any allocation. + */ + batch <<= pcp->free_factor; + if (batch < max_nr_free) + pcp->free_factor++; + batch = clamp(batch, min_nr_free, max_nr_free); + + return batch; +} + +static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone) +{ + int high = READ_ONCE(pcp->high); + + if (unlikely(!high)) + return 0; + + if (!test_bit(ZONE_RECLAIM_ACTIVE, &zone->flags)) + return high; + + /* + * If reclaim is active, limit the number of pages that can be + * stored on pcp lists + */ + return min(READ_ONCE(pcp->batch) << 2, high); +} + +static void free_unref_page_commit(struct page *page, unsigned long pfn, + int migratetype, unsigned int order) { struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; - int migratetype; + int high; + int pindex; - migratetype = get_pcppage_migratetype(page); __count_vm_event(PGFREE); + pcp = this_cpu_ptr(zone->per_cpu_pageset); + pindex = order_to_pindex(migratetype, order); + list_add(&page->lru, &pcp->lists[pindex]); + pcp->count += 1 << order; + high = nr_pcp_high(pcp, zone); + if (pcp->count >= high) { + int batch = READ_ONCE(pcp->batch); + + free_pcppages_bulk(zone, nr_pcp_free(pcp, high, batch), pcp); + } +} + +/* + * Free a pcp page + */ +void free_unref_page(struct page *page, unsigned int order) +{ + unsigned long flags; + unsigned long pfn = page_to_pfn(page); + int migratetype; + + if (!free_unref_page_prepare(page, pfn, order)) + return; /* * We only track unmovable, reclaimable and movable on pcp lists. - * Free ISOLATE pages back to the allocator because they are being + * Place ISOLATE pages on the isolated list because they are being * offlined but treat HIGHATOMIC as movable pages so we can get those * areas back if necessary. Otherwise, we may have to free * excessively into the page allocator */ - if (migratetype >= MIGRATE_PCPTYPES) { + migratetype = get_pcppage_migratetype(page); + if (unlikely(migratetype >= MIGRATE_PCPTYPES)) { if (unlikely(is_migrate_isolate(migratetype))) { - free_one_page(zone, page, pfn, 0, migratetype, - FPI_NONE); + free_one_page(page_zone(page), page, pfn, order, migratetype, FPI_NONE); return; } migratetype = MIGRATE_MOVABLE; } - pcp = &this_cpu_ptr(zone->pageset)->pcp; - list_add(&page->lru, &pcp->lists[migratetype]); - pcp->count++; - if (pcp->count >= READ_ONCE(pcp->high)) - free_pcppages_bulk(zone, READ_ONCE(pcp->batch), pcp); -} - -/* - * Free a 0-order page - */ -void free_unref_page(struct page *page) -{ - unsigned long flags; - unsigned long pfn = page_to_pfn(page); - - if (!free_unref_page_prepare(page, pfn)) - return; - - local_irq_save(flags); - free_unref_page_commit(page, pfn); - local_irq_restore(flags); + local_lock_irqsave(&pagesets.lock, flags); + free_unref_page_commit(page, pfn, migratetype, order); + local_unlock_irqrestore(&pagesets.lock, flags); } /* @@ -3311,34 +3448,56 @@ void free_unref_page_list(struct list_head *list) struct page *page, *next; unsigned long flags, pfn; int batch_count = 0; + int migratetype; /* Prepare pages for freeing */ list_for_each_entry_safe(page, next, list, lru) { pfn = page_to_pfn(page); - if (!free_unref_page_prepare(page, pfn)) + if (!free_unref_page_prepare(page, pfn, 0)) list_del(&page->lru); + + /* + * Free isolated pages directly to the allocator, see + * comment in free_unref_page. + */ + migratetype = get_pcppage_migratetype(page); + if (unlikely(migratetype >= MIGRATE_PCPTYPES)) { + if (unlikely(is_migrate_isolate(migratetype))) { + list_del(&page->lru); + free_one_page(page_zone(page), page, pfn, 0, + migratetype, FPI_NONE); + continue; + } + + /* + * Non-isolated types over MIGRATE_PCPTYPES get added + * to the MIGRATE_MOVABLE pcp list. + */ + set_pcppage_migratetype(page, MIGRATE_MOVABLE); + } + set_page_private(page, pfn); } - local_irq_save(flags); + local_lock_irqsave(&pagesets.lock, flags); list_for_each_entry_safe(page, next, list, lru) { - unsigned long pfn = page_private(page); - + pfn = page_private(page); set_page_private(page, 0); + migratetype = get_pcppage_migratetype(page); trace_mm_page_free_batched(page); - free_unref_page_commit(page, pfn); + free_unref_page_commit(page, pfn, migratetype, 0); /* * Guard against excessive IRQ disabled times when we get * a large list of pages to free. */ if (++batch_count == SWAP_CLUSTER_MAX) { - local_irq_restore(flags); + local_unlock_irqrestore(&pagesets.lock, flags); batch_count = 0; - local_irq_save(flags); + local_lock_irqsave(&pagesets.lock, flags); } } - local_irq_restore(flags); + local_unlock_irqrestore(&pagesets.lock, flags); } /* @@ -3437,7 +3596,8 @@ void __putback_isolated_page(struct page *page, unsigned int order, int mt) * * Must be called with interrupts disabled. */ -static inline void zone_statistics(struct zone *preferred_zone, struct zone *z) +static inline void zone_statistics(struct zone *preferred_zone, struct zone *z, + long nr_account) { #ifdef CONFIG_NUMA enum numa_stat_item local_stat = NUMA_LOCAL; @@ -3450,18 +3610,19 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z) local_stat = NUMA_OTHER; if (zone_to_nid(z) == zone_to_nid(preferred_zone)) - __inc_numa_state(z, NUMA_HIT); + __count_numa_events(z, NUMA_HIT, nr_account); else { - __inc_numa_state(z, NUMA_MISS); - __inc_numa_state(preferred_zone, NUMA_FOREIGN); + __count_numa_events(z, NUMA_MISS, nr_account); + __count_numa_events(preferred_zone, NUMA_FOREIGN, nr_account); } - __inc_numa_state(z, local_stat); + __count_numa_events(z, local_stat, nr_account); #endif } /* Remove page from the per-cpu list, caller must protect the list */ static inline -struct page *__rmqueue_pcplist(struct zone *zone, int migratetype, +struct page *__rmqueue_pcplist(struct zone *zone, unsigned int order, + int migratetype, unsigned int alloc_flags, struct per_cpu_pages *pcp, struct list_head *list) @@ -3470,16 +3631,30 @@ struct page *__rmqueue_pcplist(struct zone *zone, int migratetype, do { if (list_empty(list)) { - pcp->count += rmqueue_bulk(zone, 0, - READ_ONCE(pcp->batch), list, + int batch = READ_ONCE(pcp->batch); + int alloced; + + /* + * Scale batch relative to order if batch implies + * free pages can be stored on the PCP. Batch can + * be 1 for small zones or for boot pagesets which + * should never store free pages as the pages may + * belong to arbitrary zones. + */ + if (batch > 1) + batch = max(batch >> order, 2); + alloced = rmqueue_bulk(zone, order, + batch, list, migratetype, alloc_flags); + + pcp->count += alloced << order; if (unlikely(list_empty(list))) return NULL; } page = list_first_entry(list, struct page, lru); list_del(&page->lru); - pcp->count--; + pcp->count -= 1 << order; } while (check_new_pcp(page)); return page; @@ -3487,23 +3662,31 @@ struct page *__rmqueue_pcplist(struct zone *zone, int migratetype, /* Lock and remove page from the per-cpu list */ static struct page *rmqueue_pcplist(struct zone *preferred_zone, - struct zone *zone, gfp_t gfp_flags, - int migratetype, unsigned int alloc_flags) + struct zone *zone, unsigned int order, + gfp_t gfp_flags, int migratetype, + unsigned int alloc_flags) { struct per_cpu_pages *pcp; struct list_head *list; struct page *page; unsigned long flags; - local_irq_save(flags); - pcp = &this_cpu_ptr(zone->pageset)->pcp; - list = &pcp->lists[migratetype]; - page = __rmqueue_pcplist(zone, migratetype, alloc_flags, pcp, list); + local_lock_irqsave(&pagesets.lock, flags); + + /* + * On allocation, reduce the number of pages that are batch freed. + * See nr_pcp_free() where free_factor is increased for subsequent + * frees. + */ + pcp = this_cpu_ptr(zone->per_cpu_pageset); + pcp->free_factor >>= 1; + list = &pcp->lists[order_to_pindex(migratetype, order)]; + page = __rmqueue_pcplist(zone, order, migratetype, alloc_flags, pcp, list); + local_unlock_irqrestore(&pagesets.lock, flags); if (page) { __count_zid_vm_events(PGALLOC, page_zonenum(page), 1); - zone_statistics(preferred_zone, zone); + zone_statistics(preferred_zone, zone, 1); } - local_irq_restore(flags); return page; } @@ -3519,15 +3702,15 @@ struct page *rmqueue(struct zone *preferred_zone, unsigned long flags; struct page *page; - if (likely(order == 0)) { + if (likely(pcp_allowed_order(order))) { /* * MIGRATE_MOVABLE pcplist could have the pages on CMA area and * we need to skip it when CMA area isn't allowed. */ if (!IS_ENABLED(CONFIG_CMA) || alloc_flags & ALLOC_CMA || migratetype != MIGRATE_MOVABLE) { - page = rmqueue_pcplist(preferred_zone, zone, gfp_flags, - migratetype, alloc_flags); + page = rmqueue_pcplist(preferred_zone, zone, order, + gfp_flags, migratetype, alloc_flags); goto out; } } @@ -3555,15 +3738,15 @@ struct page *rmqueue(struct zone *preferred_zone, if (!page) page = __rmqueue(zone, order, migratetype, alloc_flags); } while (page && check_new_pages(page, order)); - spin_unlock(&zone->lock); if (!page) goto failed; + __mod_zone_freepage_state(zone, -(1 << order), get_pcppage_migratetype(page)); + spin_unlock_irqrestore(&zone->lock, flags); __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); - zone_statistics(preferred_zone, zone); - local_irq_restore(flags); + zone_statistics(preferred_zone, zone, 1); out: /* Separate test+clear to avoid unnecessary atomics */ @@ -3576,7 +3759,7 @@ out: return page; failed: - local_irq_restore(flags); + spin_unlock_irqrestore(&zone->lock, flags); return NULL; } @@ -3648,7 +3831,7 @@ static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) #endif /* CONFIG_FAIL_PAGE_ALLOC */ -noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +static noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { return __should_fail_alloc_page(gfp_mask, order); } @@ -4252,6 +4435,9 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, if (!order) return false; + if (fatal_signal_pending(current)) + return false; + if (compaction_made_progress(compact_result)) (*compaction_retries)++; @@ -5044,7 +5230,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, struct alloc_context ac; gfp_t alloc_gfp; unsigned int alloc_flags = ALLOC_WMARK_LOW; - int nr_populated = 0; + int nr_populated = 0, nr_account = 0; if (unlikely(nr_pages <= 0)) return 0; @@ -5053,9 +5239,13 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, * Skip populated array elements to determine if any pages need * to be allocated before disabling IRQs. */ - while (page_array && page_array[nr_populated] && nr_populated < nr_pages) + while (page_array && nr_populated < nr_pages && page_array[nr_populated]) nr_populated++; + /* Already populated array? */ + if (unlikely(page_array && nr_pages - nr_populated == 0)) + return nr_populated; + /* Use the single page allocator for one page. */ if (nr_pages - nr_populated == 1) goto failed; @@ -5097,9 +5287,9 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, goto failed; /* Attempt the batch allocation */ - local_irq_save(flags); - pcp = &this_cpu_ptr(zone->pageset)->pcp; - pcp_list = &pcp->lists[ac.migratetype]; + local_lock_irqsave(&pagesets.lock, flags); + pcp = this_cpu_ptr(zone->per_cpu_pageset); + pcp_list = &pcp->lists[order_to_pindex(ac.migratetype, 0)]; while (nr_populated < nr_pages) { @@ -5109,7 +5299,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, continue; } - page = __rmqueue_pcplist(zone, ac.migratetype, alloc_flags, + page = __rmqueue_pcplist(zone, 0, ac.migratetype, alloc_flags, pcp, pcp_list); if (unlikely(!page)) { /* Try and get at least one page */ @@ -5117,15 +5307,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, goto failed_irq; break; } - - /* - * Ideally this would be batched but the best way to do - * that cheaply is to first convert zone_statistics to - * be inaccurate per-cpu counter like vm_events to avoid - * a RMW cycle then do the accounting with IRQs enabled. - */ - __count_zid_vm_events(PGALLOC, zone_idx(zone), 1); - zone_statistics(ac.preferred_zoneref->zone, zone); + nr_account++; prep_new_page(page, 0, gfp, 0); if (page_list) @@ -5135,12 +5317,15 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, nr_populated++; } - local_irq_restore(flags); + local_unlock_irqrestore(&pagesets.lock, flags); + + __count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account); + zone_statistics(ac.preferred_zoneref->zone, zone, nr_account); return nr_populated; failed_irq: - local_irq_restore(flags); + local_unlock_irqrestore(&pagesets.lock, flags); failed: page = __alloc_pages(gfp, 0, preferred_nid, nodemask); @@ -5247,14 +5432,6 @@ unsigned long get_zeroed_page(gfp_t gfp_mask) } EXPORT_SYMBOL(get_zeroed_page); -static inline void free_the_page(struct page *page, unsigned int order) -{ - if (order == 0) /* Via pcp? */ - free_unref_page(page); - else - __free_pages_ok(page, order, FPI_NONE); -} - /** * __free_pages - Free pages allocated with alloc_pages(). * @page: The page pointer returned from alloc_pages(). @@ -5713,7 +5890,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) continue; for_each_online_cpu(cpu) - free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count; + free_pcp += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count; } printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n" @@ -5805,7 +5982,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) free_pcp = 0; for_each_online_cpu(cpu) - free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count; + free_pcp += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count; show_node(zone); printk(KERN_CONT @@ -5846,7 +6023,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) K(zone_page_state(zone, NR_MLOCK)), K(zone_page_state(zone, NR_BOUNCE)), K(free_pcp), - K(this_cpu_read(zone->pageset->pcp.count)), + K(this_cpu_read(zone->per_cpu_pageset->count)), K(zone_page_state(zone, NR_FREE_CMA_PAGES))); printk("lowmem_reserve[]:"); for (i = 0; i < MAX_NR_ZONES; i++) @@ -6173,11 +6350,12 @@ static void build_zonelists(pg_data_t *pgdat) * not check if the processor is online before following the pageset pointer. * Other parts of the kernel may not check if the zone is available. */ -static void pageset_init(struct per_cpu_pageset *p); +static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonestat *pzstats); /* These effectively disable the pcplists in the boot pageset completely */ #define BOOT_PAGESET_HIGH 0 #define BOOT_PAGESET_BATCH 1 -static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset); +static DEFINE_PER_CPU(struct per_cpu_pages, boot_pageset); +static DEFINE_PER_CPU(struct per_cpu_zonestat, boot_zonestats); static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats); static void __build_all_zonelists(void *data) @@ -6244,7 +6422,7 @@ build_all_zonelists_init(void) * (a chicken-egg dilemma). */ for_each_possible_cpu(cpu) - pageset_init(&per_cpu(boot_pageset, cpu)); + per_cpu_pages_init(&per_cpu(boot_pageset, cpu), &per_cpu(boot_zonestats, cpu)); mminit_verify_zonelist(); cpuset_init_current_mems_allowed(); @@ -6396,7 +6574,7 @@ void __ref memmap_init_zone_device(struct zone *zone, return; /* - * The call to memmap_init_zone should have already taken care + * The call to memmap_init should have already taken care * of the pages reserved for the memmap, so we can just jump to * the end of that region and start processing the device pages. */ @@ -6457,11 +6635,11 @@ static void __meminit zone_init_free_lists(struct zone *zone) } } -#if !defined(CONFIG_FLAT_NODE_MEM_MAP) +#if !defined(CONFIG_FLATMEM) /* * Only struct pages that correspond to ranges defined by memblock.memory * are zeroed and initialized by going through __init_single_page() during - * memmap_init_zone(). + * memmap_init_zone_range(). * * But, there could be struct pages that correspond to holes in * memblock.memory. This can happen because of the following reasons: @@ -6480,9 +6658,9 @@ static void __meminit zone_init_free_lists(struct zone *zone) * zone/node above the hole except for the trailing pages in the last * section that will be appended to the zone/node below. */ -static u64 __meminit init_unavailable_range(unsigned long spfn, - unsigned long epfn, - int zone, int node) +static void __init init_unavailable_range(unsigned long spfn, + unsigned long epfn, + int zone, int node) { unsigned long pfn; u64 pgcnt = 0; @@ -6498,56 +6676,77 @@ static u64 __meminit init_unavailable_range(unsigned long spfn, pgcnt++; } - return pgcnt; + if (pgcnt) + pr_info("On node %d, zone %s: %lld pages in unavailable ranges", + node, zone_names[zone], pgcnt); } #else -static inline u64 init_unavailable_range(unsigned long spfn, unsigned long epfn, - int zone, int node) +static inline void init_unavailable_range(unsigned long spfn, + unsigned long epfn, + int zone, int node) { - return 0; } #endif -void __meminit __weak memmap_init_zone(struct zone *zone) +static void __init memmap_init_zone_range(struct zone *zone, + unsigned long start_pfn, + unsigned long end_pfn, + unsigned long *hole_pfn) { unsigned long zone_start_pfn = zone->zone_start_pfn; unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages; - int i, nid = zone_to_nid(zone), zone_id = zone_idx(zone); - static unsigned long hole_pfn; + int nid = zone_to_nid(zone), zone_id = zone_idx(zone); + + start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn); + end_pfn = clamp(end_pfn, zone_start_pfn, zone_end_pfn); + + if (start_pfn >= end_pfn) + return; + + memmap_init_range(end_pfn - start_pfn, nid, zone_id, start_pfn, + zone_end_pfn, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); + + if (*hole_pfn < start_pfn) + init_unavailable_range(*hole_pfn, start_pfn, zone_id, nid); + + *hole_pfn = end_pfn; +} + +static void __init memmap_init(void) +{ unsigned long start_pfn, end_pfn; - u64 pgcnt = 0; + unsigned long hole_pfn = 0; + int i, j, zone_id, nid; - for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { - start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn); - end_pfn = clamp(end_pfn, zone_start_pfn, zone_end_pfn); + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + struct pglist_data *node = NODE_DATA(nid); - if (end_pfn > start_pfn) - memmap_init_range(end_pfn - start_pfn, nid, - zone_id, start_pfn, zone_end_pfn, - MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); + for (j = 0; j < MAX_NR_ZONES; j++) { + struct zone *zone = node->node_zones + j; - if (hole_pfn < start_pfn) - pgcnt += init_unavailable_range(hole_pfn, start_pfn, - zone_id, nid); - hole_pfn = end_pfn; + if (!populated_zone(zone)) + continue; + + memmap_init_zone_range(zone, start_pfn, end_pfn, + &hole_pfn); + zone_id = j; + } } #ifdef CONFIG_SPARSEMEM /* - * Initialize the hole in the range [zone_end_pfn, section_end]. - * If zone boundary falls in the middle of a section, this hole - * will be re-initialized during the call to this function for the - * higher zone. + * Initialize the memory map for hole in the range [memory_end, + * section_end]. + * Append the pages in this hole to the highest zone in the last + * node. + * The call to init_unavailable_range() is outside the ifdef to + * silence the compiler warining about zone_id set but not used; + * for FLATMEM it is a nop anyway */ - end_pfn = round_up(zone_end_pfn, PAGES_PER_SECTION); + end_pfn = round_up(end_pfn, PAGES_PER_SECTION); if (hole_pfn < end_pfn) - pgcnt += init_unavailable_range(hole_pfn, end_pfn, - zone_id, nid); #endif - - if (pgcnt) - pr_info(" %s zone: %llu pages in unavailable ranges\n", - zone->name, pgcnt); + init_unavailable_range(hole_pfn, end_pfn, zone_id, nid); } static int zone_batchsize(struct zone *zone) @@ -6556,13 +6755,12 @@ static int zone_batchsize(struct zone *zone) int batch; /* - * The per-cpu-pages pools are set to around 1000th of the - * size of the zone. + * The number of pages to batch allocate is either ~0.1% + * of the zone or 1MB, whichever is smaller. The batch + * size is striking a balance between allocation latency + * and zone lock contention. */ - batch = zone_managed_pages(zone) / 1024; - /* But no more than a meg. */ - if (batch * PAGE_SIZE > 1024 * 1024) - batch = (1024 * 1024) / PAGE_SIZE; + batch = min(zone_managed_pages(zone) >> 10, (1024 * 1024) / PAGE_SIZE); batch /= 4; /* We effectively *= 4 below */ if (batch < 1) batch = 1; @@ -6599,6 +6797,54 @@ static int zone_batchsize(struct zone *zone) #endif } +static int zone_highsize(struct zone *zone, int batch, int cpu_online) +{ +#ifdef CONFIG_MMU + int high; + int nr_split_cpus; + unsigned long total_pages; + + if (!percpu_pagelist_high_fraction) { + /* + * By default, the high value of the pcp is based on the zone + * low watermark so that if they are full then background + * reclaim will not be started prematurely. + */ + total_pages = low_wmark_pages(zone); + } else { + /* + * If percpu_pagelist_high_fraction is configured, the high + * value is based on a fraction of the managed pages in the + * zone. + */ + total_pages = zone_managed_pages(zone) / percpu_pagelist_high_fraction; + } + + /* + * Split the high value across all online CPUs local to the zone. Note + * that early in boot that CPUs may not be online yet and that during + * CPU hotplug that the cpumask is not yet updated when a CPU is being + * onlined. For memory nodes that have no CPUs, split pcp->high across + * all online CPUs to mitigate the risk that reclaim is triggered + * prematurely due to pages stored on pcp lists. + */ + nr_split_cpus = cpumask_weight(cpumask_of_node(zone_to_nid(zone))) + cpu_online; + if (!nr_split_cpus) + nr_split_cpus = num_online_cpus(); + high = total_pages / nr_split_cpus; + + /* + * Ensure high is at least batch*4. The multiple is based on the + * historical relationship between high and batch. + */ + high = max(high, batch << 2); + + return high; +#else + return 0; +#endif +} + /* * pcp->high and pcp->batch values are related and generally batch is lower * than high. They are also related to pcp->count such that count is lower @@ -6622,16 +6868,15 @@ static void pageset_update(struct per_cpu_pages *pcp, unsigned long high, WRITE_ONCE(pcp->high, high); } -static void pageset_init(struct per_cpu_pageset *p) +static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonestat *pzstats) { - struct per_cpu_pages *pcp; - int migratetype; + int pindex; - memset(p, 0, sizeof(*p)); + memset(pcp, 0, sizeof(*pcp)); + memset(pzstats, 0, sizeof(*pzstats)); - pcp = &p->pcp; - for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++) - INIT_LIST_HEAD(&pcp->lists[migratetype]); + for (pindex = 0; pindex < NR_PCP_LISTS; pindex++) + INIT_LIST_HEAD(&pcp->lists[pindex]); /* * Set batch and high values safe for a boot pageset. A true percpu @@ -6641,38 +6886,31 @@ static void pageset_init(struct per_cpu_pageset *p) */ pcp->high = BOOT_PAGESET_HIGH; pcp->batch = BOOT_PAGESET_BATCH; + pcp->free_factor = 0; } static void __zone_set_pageset_high_and_batch(struct zone *zone, unsigned long high, unsigned long batch) { - struct per_cpu_pageset *p; + struct per_cpu_pages *pcp; int cpu; for_each_possible_cpu(cpu) { - p = per_cpu_ptr(zone->pageset, cpu); - pageset_update(&p->pcp, high, batch); + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + pageset_update(pcp, high, batch); } } /* * Calculate and set new high and batch values for all per-cpu pagesets of a - * zone, based on the zone's size and the percpu_pagelist_fraction sysctl. + * zone based on the zone's size. */ -static void zone_set_pageset_high_and_batch(struct zone *zone) +static void zone_set_pageset_high_and_batch(struct zone *zone, int cpu_online) { - unsigned long new_high, new_batch; + int new_high, new_batch; - if (percpu_pagelist_fraction) { - new_high = zone_managed_pages(zone) / percpu_pagelist_fraction; - new_batch = max(1UL, new_high / 4); - if ((new_high / 4) > (PAGE_SHIFT * 8)) - new_batch = PAGE_SHIFT * 8; - } else { - new_batch = zone_batchsize(zone); - new_high = 6 * new_batch; - new_batch = max(1UL, 1 * new_batch); - } + new_batch = max(1, zone_batchsize(zone)); + new_high = zone_highsize(zone, new_batch, cpu_online); if (zone->pageset_high == new_high && zone->pageset_batch == new_batch) @@ -6686,16 +6924,23 @@ static void zone_set_pageset_high_and_batch(struct zone *zone) void __meminit setup_zone_pageset(struct zone *zone) { - struct per_cpu_pageset *p; int cpu; - zone->pageset = alloc_percpu(struct per_cpu_pageset); + /* Size may be 0 on !SMP && !NUMA */ + if (sizeof(struct per_cpu_zonestat) > 0) + zone->per_cpu_zonestats = alloc_percpu(struct per_cpu_zonestat); + + zone->per_cpu_pageset = alloc_percpu(struct per_cpu_pages); for_each_possible_cpu(cpu) { - p = per_cpu_ptr(zone->pageset, cpu); - pageset_init(p); + struct per_cpu_pages *pcp; + struct per_cpu_zonestat *pzstats; + + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); + per_cpu_pages_init(pcp, pzstats); } - zone_set_pageset_high_and_batch(zone); + zone_set_pageset_high_and_batch(zone, 0); } /* @@ -6719,9 +6964,9 @@ void __init setup_per_cpu_pageset(void) * the nodes these zones are associated with. */ for_each_possible_cpu(cpu) { - struct per_cpu_pageset *pcp = &per_cpu(boot_pageset, cpu); - memset(pcp->vm_numa_stat_diff, 0, - sizeof(pcp->vm_numa_stat_diff)); + struct per_cpu_zonestat *pzstats = &per_cpu(boot_zonestats, cpu); + memset(pzstats->vm_numa_event, 0, + sizeof(pzstats->vm_numa_event)); } #endif @@ -6737,14 +6982,14 @@ static __meminit void zone_pcp_init(struct zone *zone) * relies on the ability of the linker to provide the * offset of a (static) per cpu variable into the per cpu area. */ - zone->pageset = &boot_pageset; + zone->per_cpu_pageset = &boot_pageset; + zone->per_cpu_zonestats = &boot_zonestats; zone->pageset_high = BOOT_PAGESET_HIGH; zone->pageset_batch = BOOT_PAGESET_BATCH; if (populated_zone(zone)) - printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%u\n", - zone->name, zone->present_pages, - zone_batchsize(zone)); + pr_debug(" %s zone: %lu pages, LIFO batch:%u\n", zone->name, + zone->present_pages, zone_batchsize(zone)); } void __meminit init_currently_empty_zone(struct zone *zone, @@ -7014,8 +7259,7 @@ static void __init calculate_node_totalpages(struct pglist_data *pgdat, pgdat->node_spanned_pages = totalpages; pgdat->node_present_pages = realtotalpages; - printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, - realtotalpages); + pr_debug("On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages); } #ifndef CONFIG_SPARSEMEM @@ -7215,19 +7459,17 @@ static void __init free_area_init_core(struct pglist_data *pgdat) if (freesize >= memmap_pages) { freesize -= memmap_pages; if (memmap_pages) - printk(KERN_DEBUG - " %s zone: %lu pages used for memmap\n", - zone_names[j], memmap_pages); + pr_debug(" %s zone: %lu pages used for memmap\n", + zone_names[j], memmap_pages); } else - pr_warn(" %s zone: %lu pages exceeds freesize %lu\n", + pr_warn(" %s zone: %lu memmap pages exceeds freesize %lu\n", zone_names[j], memmap_pages, freesize); } /* Account for reserved pages */ if (j == 0 && freesize > dma_reserve) { freesize -= dma_reserve; - printk(KERN_DEBUG " %s zone: %lu pages reserved\n", - zone_names[0], dma_reserve); + pr_debug(" %s zone: %lu pages reserved\n", zone_names[0], dma_reserve); } if (!is_highmem_idx(j)) @@ -7250,11 +7492,10 @@ static void __init free_area_init_core(struct pglist_data *pgdat) set_pageblock_order(); setup_usemap(zone); init_currently_empty_zone(zone, zone->zone_start_pfn, size); - memmap_init_zone(zone); } } -#ifdef CONFIG_FLAT_NODE_MEM_MAP +#ifdef CONFIG_FLATMEM static void __ref alloc_node_mem_map(struct pglist_data *pgdat) { unsigned long __maybe_unused start = 0; @@ -7289,7 +7530,7 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat) pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n", __func__, pgdat->node_id, (unsigned long)pgdat, (unsigned long)pgdat->node_mem_map); -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA /* * With no DISCONTIG, the global mem_map is just set as node 0's */ @@ -7302,7 +7543,7 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat) } #else static void __ref alloc_node_mem_map(struct pglist_data *pgdat) { } -#endif /* CONFIG_FLAT_NODE_MEM_MAP */ +#endif /* CONFIG_FLATMEM */ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT static inline void pgdat_set_deferred_range(pg_data_t *pgdat) @@ -7776,6 +8017,8 @@ void __init free_area_init(unsigned long *max_zone_pfn) node_set_state(nid, N_MEMORY); check_for_memory(pgdat, nid); } + + memmap_init(); } static int __init cmdline_parse_core(char *p, unsigned long *core, @@ -7952,6 +8195,7 @@ void __init set_dma_reserve(unsigned long new_dma_reserve) static int page_alloc_cpu_dead(unsigned int cpu) { + struct zone *zone; lru_add_drain_cpu(cpu); drain_pages(cpu); @@ -7972,6 +8216,19 @@ static int page_alloc_cpu_dead(unsigned int cpu) * race with what we are doing. */ cpu_vm_stats_fold(cpu); + + for_each_populated_zone(zone) + zone_pcp_update(zone, 0); + + return 0; +} + +static int page_alloc_cpu_online(unsigned int cpu) +{ + struct zone *zone; + + for_each_populated_zone(zone) + zone_pcp_update(zone, 1); return 0; } @@ -7997,8 +8254,9 @@ void __init page_alloc_init(void) hashdist = 0; #endif - ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC_DEAD, - "mm/page_alloc:dead", NULL, + ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC, + "mm/page_alloc:pcp", + page_alloc_cpu_online, page_alloc_cpu_dead); WARN_ON(ret < 0); } @@ -8061,14 +8319,14 @@ static void setup_per_zone_lowmem_reserve(void) unsigned long managed_pages = 0; for (j = i + 1; j < MAX_NR_ZONES; j++) { - if (clear) { - zone->lowmem_reserve[j] = 0; - } else { - struct zone *upper_zone = &pgdat->node_zones[j]; + struct zone *upper_zone = &pgdat->node_zones[j]; - managed_pages += zone_managed_pages(upper_zone); + managed_pages += zone_managed_pages(upper_zone); + + if (clear) + zone->lowmem_reserve[j] = 0; + else zone->lowmem_reserve[j] = managed_pages / ratio; - } } } } @@ -8148,11 +8406,19 @@ static void __setup_per_zone_wmarks(void) */ void setup_per_zone_wmarks(void) { + struct zone *zone; static DEFINE_SPINLOCK(lock); spin_lock(&lock); __setup_per_zone_wmarks(); spin_unlock(&lock); + + /* + * The watermark size have changed so update the pcpu batch + * and high limits or the limits may be inappropriate. + */ + for_each_zone(zone) + zone_pcp_update(zone, 0); } /* @@ -8331,38 +8597,38 @@ int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write, } /* - * percpu_pagelist_fraction - changes the pcp->high for each zone on each - * cpu. It is the fraction of total pages in each zone that a hot per cpu + * percpu_pagelist_high_fraction - changes the pcp->high for each zone on each + * cpu. It is the fraction of total pages in each zone that a hot per cpu * pagelist can have before it gets flushed back to buddy allocator. */ -int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write, - void *buffer, size_t *length, loff_t *ppos) +int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *table, + int write, void *buffer, size_t *length, loff_t *ppos) { struct zone *zone; - int old_percpu_pagelist_fraction; + int old_percpu_pagelist_high_fraction; int ret; mutex_lock(&pcp_batch_high_lock); - old_percpu_pagelist_fraction = percpu_pagelist_fraction; + old_percpu_pagelist_high_fraction = percpu_pagelist_high_fraction; ret = proc_dointvec_minmax(table, write, buffer, length, ppos); if (!write || ret < 0) goto out; /* Sanity checking to avoid pcp imbalance */ - if (percpu_pagelist_fraction && - percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) { - percpu_pagelist_fraction = old_percpu_pagelist_fraction; + if (percpu_pagelist_high_fraction && + percpu_pagelist_high_fraction < MIN_PERCPU_PAGELIST_HIGH_FRACTION) { + percpu_pagelist_high_fraction = old_percpu_pagelist_high_fraction; ret = -EINVAL; goto out; } /* No change? */ - if (percpu_pagelist_fraction == old_percpu_pagelist_fraction) + if (percpu_pagelist_high_fraction == old_percpu_pagelist_high_fraction) goto out; for_each_populated_zone(zone) - zone_set_pageset_high_and_batch(zone); + zone_set_pageset_high_and_batch(zone, 0); out: mutex_unlock(&pcp_batch_high_lock); return ret; @@ -8717,7 +8983,8 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, lru_cache_enable(); if (ret < 0) { - alloc_contig_dump_pages(&cc->migratepages); + if (ret == -EBUSY) + alloc_contig_dump_pages(&cc->migratepages); putback_movable_pages(&cc->migratepages); return ret; } @@ -8990,10 +9257,10 @@ EXPORT_SYMBOL(free_contig_range); * The zone indicated has a new number of managed_pages; batch sizes and percpu * page high values need to be recalculated. */ -void __meminit zone_pcp_update(struct zone *zone) +void zone_pcp_update(struct zone *zone, int cpu_online) { mutex_lock(&pcp_batch_high_lock); - zone_set_pageset_high_and_batch(zone); + zone_set_pageset_high_and_batch(zone, cpu_online); mutex_unlock(&pcp_batch_high_lock); } @@ -9021,15 +9288,17 @@ void zone_pcp_enable(struct zone *zone) void zone_pcp_reset(struct zone *zone) { int cpu; - struct per_cpu_pageset *pset; + struct per_cpu_zonestat *pzstats; - if (zone->pageset != &boot_pageset) { + if (zone->per_cpu_pageset != &boot_pageset) { for_each_online_cpu(cpu) { - pset = per_cpu_ptr(zone->pageset, cpu); - drain_zonestat(zone, pset); + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); + drain_zonestat(zone, pzstats); } - free_percpu(zone->pageset); - zone->pageset = &boot_pageset; + free_percpu(zone->per_cpu_pageset); + free_percpu(zone->per_cpu_zonestats); + zone->per_cpu_pageset = &boot_pageset; + zone->per_cpu_zonestats = &boot_zonestats; } } @@ -9158,6 +9427,8 @@ bool take_page_off_buddy(struct page *page) del_page_from_free_list(page_head, zone, page_order); break_down_buddy_pages(zone, page_head, page, 0, page_order, migratetype); + if (!is_migrate_isolate(migratetype)) + __mod_zone_freepage_state(zone, -1, migratetype); ret = true; break; } diff --git a/mm/page_ext.c b/mm/page_ext.c index df6f74aac8e1..293b2685fc48 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -191,7 +191,7 @@ fail: panic("Out of memory"); } -#else /* CONFIG_FLAT_NODE_MEM_MAP */ +#else /* CONFIG_FLATMEM */ struct page_ext *lookup_page_ext(const struct page *page) { diff --git a/mm/page_owner.c b/mm/page_owner.c index adfabb560eb9..f51a57e92aa3 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -392,7 +392,7 @@ err: return -ENOMEM; } -void __dump_page_owner(struct page *page) +void __dump_page_owner(const struct page *page) { struct page_ext *page_ext = lookup_page_ext(page); struct page_owner *page_owner; diff --git a/mm/page_reporting.c b/mm/page_reporting.c index c50d93ffa252..382958eef8a9 100644 --- a/mm/page_reporting.c +++ b/mm/page_reporting.c @@ -4,12 +4,17 @@ #include <linux/page_reporting.h> #include <linux/gfp.h> #include <linux/export.h> +#include <linux/module.h> #include <linux/delay.h> #include <linux/scatterlist.h> #include "page_reporting.h" #include "internal.h" +unsigned int page_reporting_order = MAX_ORDER; +module_param(page_reporting_order, uint, 0644); +MODULE_PARM_DESC(page_reporting_order, "Set page reporting order"); + #define PAGE_REPORTING_DELAY (2 * HZ) static struct page_reporting_dev_info __rcu *pr_dev_info __read_mostly; @@ -31,8 +36,8 @@ __page_reporting_request(struct page_reporting_dev_info *prdev) return; /* - * If reporting is already active there is nothing we need to do. - * Test against 0 as that represents PAGE_REPORTING_IDLE. + * If reporting is already active there is nothing we need to do. + * Test against 0 as that represents PAGE_REPORTING_IDLE. */ state = atomic_xchg(&prdev->state, PAGE_REPORTING_REQUESTED); if (state != PAGE_REPORTING_IDLE) @@ -229,7 +234,7 @@ page_reporting_process_zone(struct page_reporting_dev_info *prdev, /* Generate minimum watermark to be able to guarantee progress */ watermark = low_wmark_pages(zone) + - (PAGE_REPORTING_CAPACITY << PAGE_REPORTING_MIN_ORDER); + (PAGE_REPORTING_CAPACITY << page_reporting_order); /* * Cancel request if insufficient free memory or if we failed @@ -239,7 +244,7 @@ page_reporting_process_zone(struct page_reporting_dev_info *prdev, return err; /* Process each free list starting from lowest order/mt */ - for (order = PAGE_REPORTING_MIN_ORDER; order < MAX_ORDER; order++) { + for (order = page_reporting_order; order < MAX_ORDER; order++) { for (mt = 0; mt < MIGRATE_TYPES; mt++) { /* We do not pull pages from the isolate free list */ if (is_migrate_isolate(mt)) @@ -324,6 +329,12 @@ int page_reporting_register(struct page_reporting_dev_info *prdev) goto err_out; } + /* + * Update the page reporting order if it's specified by driver. + * Otherwise, it falls back to @pageblock_order. + */ + page_reporting_order = prdev->order ? : pageblock_order; + /* initialize state and work structures */ atomic_set(&prdev->state, PAGE_REPORTING_IDLE); INIT_DELAYED_WORK(&prdev->work, &page_reporting_process); diff --git a/mm/page_reporting.h b/mm/page_reporting.h index 2c385dd4ddbd..c51dbc228b94 100644 --- a/mm/page_reporting.h +++ b/mm/page_reporting.h @@ -10,10 +10,9 @@ #include <linux/pgtable.h> #include <linux/scatterlist.h> -#define PAGE_REPORTING_MIN_ORDER pageblock_order - #ifdef CONFIG_PAGE_REPORTING DECLARE_STATIC_KEY_FALSE(page_reporting_enabled); +extern unsigned int page_reporting_order; void __page_reporting_notify(void); static inline bool page_reported(struct page *page) @@ -38,7 +37,7 @@ static inline void page_reporting_notify_free(unsigned int order) return; /* Determine if we have crossed reporting threshold */ - if (order < PAGE_REPORTING_MIN_ORDER) + if (order < page_reporting_order) return; /* This will add a few cycles, but should be called infrequently */ diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 2cf01d933f13..f7b331081791 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -41,7 +41,8 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw) /* Handle un-addressable ZONE_DEVICE memory */ entry = pte_to_swp_entry(*pvmw->pte); - if (!is_device_private_entry(entry)) + if (!is_device_private_entry(entry) && + !is_device_exclusive_entry(entry)) return false; } else if (!pte_present(*pvmw->pte)) return false; @@ -93,19 +94,21 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) return false; entry = pte_to_swp_entry(*pvmw->pte); - if (!is_migration_entry(entry)) + if (!is_migration_entry(entry) && + !is_device_exclusive_entry(entry)) return false; - pfn = migration_entry_to_pfn(entry); + pfn = swp_offset(entry); } else if (is_swap_pte(*pvmw->pte)) { swp_entry_t entry; /* Handle un-addressable ZONE_DEVICE memory */ entry = pte_to_swp_entry(*pvmw->pte); - if (!is_device_private_entry(entry)) + if (!is_device_private_entry(entry) && + !is_device_exclusive_entry(entry)) return false; - pfn = device_private_entry_to_pfn(entry); + pfn = swp_offset(entry); } else { if (!pte_present(*pvmw->pte)) return false; @@ -116,6 +119,13 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) return pfn_is_match(pvmw->page, pfn); } +static void step_forward(struct page_vma_mapped_walk *pvmw, unsigned long size) +{ + pvmw->address = (pvmw->address + size) & ~(size - 1); + if (!pvmw->address) + pvmw->address = ULONG_MAX; +} + /** * page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at * @pvmw->address @@ -144,6 +154,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) { struct mm_struct *mm = pvmw->vma->vm_mm; struct page *page = pvmw->page; + unsigned long end; pgd_t *pgd; p4d_t *p4d; pud_t *pud; @@ -153,10 +164,11 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (pvmw->pmd && !pvmw->pte) return not_found(pvmw); - if (pvmw->pte) - goto next_pte; + if (unlikely(PageHuge(page))) { + /* The only possible mapping was handled on last iteration */ + if (pvmw->pte) + return not_found(pvmw); - if (unlikely(PageHuge(pvmw->page))) { /* when pud is not present, pte will be NULL */ pvmw->pte = huge_pte_offset(mm, pvmw->address, page_size(page)); if (!pvmw->pte) @@ -168,78 +180,108 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) return not_found(pvmw); return true; } -restart: - pgd = pgd_offset(mm, pvmw->address); - if (!pgd_present(*pgd)) - return false; - p4d = p4d_offset(pgd, pvmw->address); - if (!p4d_present(*p4d)) - return false; - pud = pud_offset(p4d, pvmw->address); - if (!pud_present(*pud)) - return false; - pvmw->pmd = pmd_offset(pud, pvmw->address); + /* - * Make sure the pmd value isn't cached in a register by the - * compiler and used as a stale value after we've observed a - * subsequent update. + * Seek to next pte only makes sense for THP. + * But more important than that optimization, is to filter out + * any PageKsm page: whose page->index misleads vma_address() + * and vma_address_end() to disaster. */ - pmde = READ_ONCE(*pvmw->pmd); - if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) { - pvmw->ptl = pmd_lock(mm, pvmw->pmd); - if (likely(pmd_trans_huge(*pvmw->pmd))) { - if (pvmw->flags & PVMW_MIGRATION) - return not_found(pvmw); - if (pmd_page(*pvmw->pmd) != page) - return not_found(pvmw); - return true; - } else if (!pmd_present(*pvmw->pmd)) { - if (thp_migration_supported()) { - if (!(pvmw->flags & PVMW_MIGRATION)) + end = PageTransCompound(page) ? + vma_address_end(page, pvmw->vma) : + pvmw->address + PAGE_SIZE; + if (pvmw->pte) + goto next_pte; +restart: + do { + pgd = pgd_offset(mm, pvmw->address); + if (!pgd_present(*pgd)) { + step_forward(pvmw, PGDIR_SIZE); + continue; + } + p4d = p4d_offset(pgd, pvmw->address); + if (!p4d_present(*p4d)) { + step_forward(pvmw, P4D_SIZE); + continue; + } + pud = pud_offset(p4d, pvmw->address); + if (!pud_present(*pud)) { + step_forward(pvmw, PUD_SIZE); + continue; + } + + pvmw->pmd = pmd_offset(pud, pvmw->address); + /* + * Make sure the pmd value isn't cached in a register by the + * compiler and used as a stale value after we've observed a + * subsequent update. + */ + pmde = READ_ONCE(*pvmw->pmd); + + if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) { + pvmw->ptl = pmd_lock(mm, pvmw->pmd); + pmde = *pvmw->pmd; + if (likely(pmd_trans_huge(pmde))) { + if (pvmw->flags & PVMW_MIGRATION) return not_found(pvmw); - if (is_migration_entry(pmd_to_swp_entry(*pvmw->pmd))) { - swp_entry_t entry = pmd_to_swp_entry(*pvmw->pmd); + if (pmd_page(pmde) != page) + return not_found(pvmw); + return true; + } + if (!pmd_present(pmde)) { + swp_entry_t entry; - if (migration_entry_to_page(entry) != page) - return not_found(pvmw); - return true; - } + if (!thp_migration_supported() || + !(pvmw->flags & PVMW_MIGRATION)) + return not_found(pvmw); + entry = pmd_to_swp_entry(pmde); + if (!is_migration_entry(entry) || + pfn_swap_entry_to_page(entry) != page) + return not_found(pvmw); + return true; } - return not_found(pvmw); - } else { /* THP pmd was split under us: handle on pte level */ spin_unlock(pvmw->ptl); pvmw->ptl = NULL; + } else if (!pmd_present(pmde)) { + /* + * If PVMW_SYNC, take and drop THP pmd lock so that we + * cannot return prematurely, while zap_huge_pmd() has + * cleared *pmd but not decremented compound_mapcount(). + */ + if ((pvmw->flags & PVMW_SYNC) && + PageTransCompound(page)) { + spinlock_t *ptl = pmd_lock(mm, pvmw->pmd); + + spin_unlock(ptl); + } + step_forward(pvmw, PMD_SIZE); + continue; } - } else if (!pmd_present(pmde)) { - return false; - } - if (!map_pte(pvmw)) - goto next_pte; - while (1) { + if (!map_pte(pvmw)) + goto next_pte; +this_pte: if (check_pte(pvmw)) return true; next_pte: - /* Seek to next pte only makes sense for THP */ - if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page)) - return not_found(pvmw); do { pvmw->address += PAGE_SIZE; - if (pvmw->address >= pvmw->vma->vm_end || - pvmw->address >= - __vma_address(pvmw->page, pvmw->vma) + - thp_size(pvmw->page)) + if (pvmw->address >= end) return not_found(pvmw); /* Did we cross page table boundary? */ - if (pvmw->address % PMD_SIZE == 0) { - pte_unmap(pvmw->pte); + if ((pvmw->address & (PMD_SIZE - PAGE_SIZE)) == 0) { if (pvmw->ptl) { spin_unlock(pvmw->ptl); pvmw->ptl = NULL; } + pte_unmap(pvmw->pte); + pvmw->pte = NULL; goto restart; - } else { - pvmw->pte++; + } + pvmw->pte++; + if ((pvmw->flags & PVMW_SYNC) && !pvmw->ptl) { + pvmw->ptl = pte_lockptr(mm, pvmw->pmd); + spin_lock(pvmw->ptl); } } while (pte_none(*pvmw->pte)); @@ -247,7 +289,10 @@ next_pte: pvmw->ptl = pte_lockptr(mm, pvmw->pmd); spin_lock(pvmw->ptl); } - } + goto this_pte; + } while (pvmw->address < end); + + return false; } /** @@ -266,14 +311,10 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) .vma = vma, .flags = PVMW_SYNC, }; - unsigned long start, end; - - start = __vma_address(page, vma); - end = start + thp_size(page) - PAGE_SIZE; - if (unlikely(end < vma->vm_start || start >= vma->vm_end)) + pvmw.address = vma_address(page, vma); + if (pvmw.address == -EFAULT) return 0; - pvmw.address = max(start, vma->vm_start); if (!page_vma_mapped_walk(&pvmw)) return 0; page_vma_mapped_walk_done(&pvmw); diff --git a/mm/pagewalk.c b/mm/pagewalk.c index e81640d9f177..9b3db11a4d1d 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -58,6 +58,45 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, return err; } +#ifdef CONFIG_ARCH_HAS_HUGEPD +static int walk_hugepd_range(hugepd_t *phpd, unsigned long addr, + unsigned long end, struct mm_walk *walk, int pdshift) +{ + int err = 0; + const struct mm_walk_ops *ops = walk->ops; + int shift = hugepd_shift(*phpd); + int page_size = 1 << shift; + + if (!ops->pte_entry) + return 0; + + if (addr & (page_size - 1)) + return 0; + + for (;;) { + pte_t *pte; + + spin_lock(&walk->mm->page_table_lock); + pte = hugepte_offset(*phpd, addr, pdshift); + err = ops->pte_entry(pte, addr, addr + page_size, walk); + spin_unlock(&walk->mm->page_table_lock); + + if (err) + break; + if (addr >= end - page_size) + break; + addr += page_size; + } + return err; +} +#else +static int walk_hugepd_range(hugepd_t *phpd, unsigned long addr, + unsigned long end, struct mm_walk *walk, int pdshift) +{ + return 0; +} +#endif + static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -108,7 +147,10 @@ again: goto again; } - err = walk_pte_range(pmd, addr, next, walk); + if (is_hugepd(__hugepd(pmd_val(*pmd)))) + err = walk_hugepd_range((hugepd_t *)pmd, addr, next, walk, PMD_SHIFT); + else + err = walk_pte_range(pmd, addr, next, walk); if (err) break; } while (pmd++, addr = next, addr != end); @@ -157,7 +199,10 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, if (pud_none(*pud)) goto again; - err = walk_pmd_range(pud, addr, next, walk); + if (is_hugepd(__hugepd(pud_val(*pud)))) + err = walk_hugepd_range((hugepd_t *)pud, addr, next, walk, PUD_SHIFT); + else + err = walk_pmd_range(pud, addr, next, walk); if (err) break; } while (pud++, addr = next, addr != end); @@ -189,7 +234,9 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, if (err) break; } - if (ops->pud_entry || ops->pmd_entry || ops->pte_entry) + if (is_hugepd(__hugepd(p4d_val(*p4d)))) + err = walk_hugepd_range((hugepd_t *)p4d, addr, next, walk, P4D_SHIFT); + else if (ops->pud_entry || ops->pmd_entry || ops->pte_entry) err = walk_pud_range(p4d, addr, next, walk); if (err) break; @@ -224,8 +271,9 @@ static int walk_pgd_range(unsigned long addr, unsigned long end, if (err) break; } - if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry || - ops->pte_entry) + if (is_hugepd(__hugepd(pgd_val(*pgd)))) + err = walk_hugepd_range((hugepd_t *)pgd, addr, next, walk, PGDIR_SHIFT); + else if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry || ops->pte_entry) err = walk_p4d_range(pgd, addr, next, walk); if (err) break; diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h index ae26b118e246..639662c20c82 100644 --- a/mm/percpu-internal.h +++ b/mm/percpu-internal.h @@ -6,25 +6,6 @@ #include <linux/percpu.h> /* - * There are two chunk types: root and memcg-aware. - * Chunks of each type have separate slots list. - * - * Memcg-aware chunks have an attached vector of obj_cgroup pointers, which is - * used to store memcg membership data of a percpu object. Obj_cgroups are - * ref-counted pointers to a memory cgroup with an ability to switch dynamically - * to the parent memory cgroup. This allows to reclaim a deleted memory cgroup - * without reclaiming of all outstanding objects, which hold a reference at it. - */ -enum pcpu_chunk_type { - PCPU_CHUNK_ROOT, -#ifdef CONFIG_MEMCG_KMEM - PCPU_CHUNK_MEMCG, -#endif - PCPU_NR_CHUNK_TYPES, - PCPU_FAIL_ALLOC = PCPU_NR_CHUNK_TYPES -}; - -/* * pcpu_block_md is the metadata block struct. * Each chunk's bitmap is split into a number of full blocks. * All units are in terms of bits. @@ -67,6 +48,8 @@ struct pcpu_chunk { void *data; /* chunk data */ bool immutable; /* no [de]population allowed */ + bool isolated; /* isolated from active chunk + slots */ int start_offset; /* the overlap with the previous region to have a page aligned base_addr */ @@ -87,7 +70,9 @@ extern spinlock_t pcpu_lock; extern struct list_head *pcpu_chunk_lists; extern int pcpu_nr_slots; -extern int pcpu_nr_empty_pop_pages[]; +extern int pcpu_sidelined_slot; +extern int pcpu_to_depopulate_slot; +extern int pcpu_nr_empty_pop_pages; extern struct pcpu_chunk *pcpu_first_chunk; extern struct pcpu_chunk *pcpu_reserved_chunk; @@ -128,37 +113,6 @@ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk) return pcpu_nr_pages_to_map_bits(chunk->nr_pages); } -#ifdef CONFIG_MEMCG_KMEM -static inline enum pcpu_chunk_type pcpu_chunk_type(struct pcpu_chunk *chunk) -{ - if (chunk->obj_cgroups) - return PCPU_CHUNK_MEMCG; - return PCPU_CHUNK_ROOT; -} - -static inline bool pcpu_is_memcg_chunk(enum pcpu_chunk_type chunk_type) -{ - return chunk_type == PCPU_CHUNK_MEMCG; -} - -#else -static inline enum pcpu_chunk_type pcpu_chunk_type(struct pcpu_chunk *chunk) -{ - return PCPU_CHUNK_ROOT; -} - -static inline bool pcpu_is_memcg_chunk(enum pcpu_chunk_type chunk_type) -{ - return false; -} -#endif - -static inline struct list_head *pcpu_chunk_list(enum pcpu_chunk_type chunk_type) -{ - return &pcpu_chunk_lists[pcpu_nr_slots * - pcpu_is_memcg_chunk(chunk_type)]; -} - #ifdef CONFIG_PERCPU_STATS #include <linux/spinlock.h> diff --git a/mm/percpu-km.c b/mm/percpu-km.c index 35c9941077ee..c9d529dc7651 100644 --- a/mm/percpu-km.c +++ b/mm/percpu-km.c @@ -44,8 +44,7 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, /* nada */ } -static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type, - gfp_t gfp) +static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp) { const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT; struct pcpu_chunk *chunk; @@ -53,7 +52,7 @@ static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type, unsigned long flags; int i; - chunk = pcpu_alloc_chunk(type, gfp); + chunk = pcpu_alloc_chunk(gfp); if (!chunk) return NULL; @@ -118,3 +117,8 @@ static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai) return 0; } + +static bool pcpu_should_reclaim_chunk(struct pcpu_chunk *chunk) +{ + return false; +} diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c index f6026dbcdf6b..c6bd092ff7a3 100644 --- a/mm/percpu-stats.c +++ b/mm/percpu-stats.c @@ -34,15 +34,11 @@ static int find_max_nr_alloc(void) { struct pcpu_chunk *chunk; int slot, max_nr_alloc; - enum pcpu_chunk_type type; max_nr_alloc = 0; - for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) - for (slot = 0; slot < pcpu_nr_slots; slot++) - list_for_each_entry(chunk, &pcpu_chunk_list(type)[slot], - list) - max_nr_alloc = max(max_nr_alloc, - chunk->nr_alloc); + for (slot = 0; slot < pcpu_nr_slots; slot++) + list_for_each_entry(chunk, &pcpu_chunk_lists[slot], list) + max_nr_alloc = max(max_nr_alloc, chunk->nr_alloc); return max_nr_alloc; } @@ -133,9 +129,6 @@ static void chunk_map_stats(struct seq_file *m, struct pcpu_chunk *chunk, P("cur_min_alloc", cur_min_alloc); P("cur_med_alloc", cur_med_alloc); P("cur_max_alloc", cur_max_alloc); -#ifdef CONFIG_MEMCG_KMEM - P("memcg_aware", pcpu_is_memcg_chunk(pcpu_chunk_type(chunk))); -#endif seq_putc(m, '\n'); } @@ -144,8 +137,6 @@ static int percpu_stats_show(struct seq_file *m, void *v) struct pcpu_chunk *chunk; int slot, max_nr_alloc; int *buffer; - enum pcpu_chunk_type type; - int nr_empty_pop_pages; alloc_buffer: spin_lock_irq(&pcpu_lock); @@ -166,10 +157,6 @@ alloc_buffer: goto alloc_buffer; } - nr_empty_pop_pages = 0; - for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) - nr_empty_pop_pages += pcpu_nr_empty_pop_pages[type]; - #define PL(X) \ seq_printf(m, " %-20s: %12lld\n", #X, (long long int)pcpu_stats_ai.X) @@ -201,7 +188,7 @@ alloc_buffer: PU(nr_max_chunks); PU(min_alloc_size); PU(max_alloc_size); - P("empty_pop_pages", nr_empty_pop_pages); + P("empty_pop_pages", pcpu_nr_empty_pop_pages); seq_putc(m, '\n'); #undef PU @@ -215,18 +202,17 @@ alloc_buffer: chunk_map_stats(m, pcpu_reserved_chunk, buffer); } - for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) { - for (slot = 0; slot < pcpu_nr_slots; slot++) { - list_for_each_entry(chunk, &pcpu_chunk_list(type)[slot], - list) { - if (chunk == pcpu_first_chunk) { - seq_puts(m, "Chunk: <- First Chunk\n"); - chunk_map_stats(m, chunk, buffer); - } else { - seq_puts(m, "Chunk:\n"); - chunk_map_stats(m, chunk, buffer); - } - } + for (slot = 0; slot < pcpu_nr_slots; slot++) { + list_for_each_entry(chunk, &pcpu_chunk_lists[slot], list) { + if (chunk == pcpu_first_chunk) + seq_puts(m, "Chunk: <- First Chunk\n"); + else if (slot == pcpu_to_depopulate_slot) + seq_puts(m, "Chunk (to_depopulate)\n"); + else if (slot == pcpu_sidelined_slot) + seq_puts(m, "Chunk (sidelined):\n"); + else + seq_puts(m, "Chunk:\n"); + chunk_map_stats(m, chunk, buffer); } } diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index 8d3844bc0c7c..ee5d89fcd66f 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -329,13 +329,12 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, pcpu_free_pages(chunk, pages, page_start, page_end); } -static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type, - gfp_t gfp) +static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp) { struct pcpu_chunk *chunk; struct vm_struct **vms; - chunk = pcpu_alloc_chunk(type, gfp); + chunk = pcpu_alloc_chunk(gfp); if (!chunk) return NULL; @@ -378,3 +377,33 @@ static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai) /* no extra restriction */ return 0; } + +/** + * pcpu_should_reclaim_chunk - determine if a chunk should go into reclaim + * @chunk: chunk of interest + * + * This is the entry point for percpu reclaim. If a chunk qualifies, it is then + * isolated and managed in separate lists at the back of pcpu_slot: sidelined + * and to_depopulate respectively. The to_depopulate list holds chunks slated + * for depopulation. They no longer contribute to pcpu_nr_empty_pop_pages once + * they are on this list. Once depopulated, they are moved onto the sidelined + * list which enables them to be pulled back in for allocation if no other chunk + * can suffice the allocation. + */ +static bool pcpu_should_reclaim_chunk(struct pcpu_chunk *chunk) +{ + /* do not reclaim either the first chunk or reserved chunk */ + if (chunk == pcpu_first_chunk || chunk == pcpu_reserved_chunk) + return false; + + /* + * If it is isolated, it may be on the sidelined list so move it back to + * the to_depopulate list. If we hit at least 1/4 pages empty pages AND + * there is no system-wide shortage of empty pages aside from this + * chunk, move it to the to_depopulate list. + */ + return ((chunk->isolated && chunk->nr_empty_pop_pages) || + (pcpu_nr_empty_pop_pages > + (PCPU_EMPTY_POP_PAGES_HIGH + chunk->nr_empty_pop_pages) && + chunk->nr_empty_pop_pages >= chunk->nr_pages / 4)); +} diff --git a/mm/percpu.c b/mm/percpu.c index f99e9306b939..b4cebeca4c0c 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -99,7 +99,10 @@ #include "percpu-internal.h" -/* the slots are sorted by free bytes left, 1-31 bytes share the same slot */ +/* + * The slots are sorted by the size of the biggest continuous free area. + * 1-31 bytes share the same slot. + */ #define PCPU_SLOT_BASE_SHIFT 5 /* chunks in slots below this are subject to being sidelined on failed alloc */ #define PCPU_SLOT_FAIL_THRESHOLD 3 @@ -132,6 +135,9 @@ static int pcpu_unit_size __ro_after_init; static int pcpu_nr_units __ro_after_init; static int pcpu_atom_size __ro_after_init; int pcpu_nr_slots __ro_after_init; +static int pcpu_free_slot __ro_after_init; +int pcpu_sidelined_slot __ro_after_init; +int pcpu_to_depopulate_slot __ro_after_init; static size_t pcpu_chunk_struct_size __ro_after_init; /* cpus with the lowest and highest unit addresses */ @@ -173,10 +179,10 @@ struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */ static LIST_HEAD(pcpu_map_extend_chunks); /* - * The number of empty populated pages by chunk type, protected by pcpu_lock. + * The number of empty populated pages, protected by pcpu_lock. * The reserved chunk doesn't contribute to the count. */ -int pcpu_nr_empty_pop_pages[PCPU_NR_CHUNK_TYPES]; +int pcpu_nr_empty_pop_pages; /* * The number of populated pages in use by the allocator, protected by @@ -234,7 +240,7 @@ static int __pcpu_size_to_slot(int size) static int pcpu_size_to_slot(int size) { if (size == pcpu_unit_size) - return pcpu_nr_slots - 1; + return pcpu_free_slot; return __pcpu_size_to_slot(size); } @@ -303,6 +309,25 @@ static unsigned long pcpu_block_off_to_off(int index, int off) return index * PCPU_BITMAP_BLOCK_BITS + off; } +/** + * pcpu_check_block_hint - check against the contig hint + * @block: block of interest + * @bits: size of allocation + * @align: alignment of area (max PAGE_SIZE) + * + * Check to see if the allocation can fit in the block's contig hint. + * Note, a chunk uses the same hints as a block so this can also check against + * the chunk's contig hint. + */ +static bool pcpu_check_block_hint(struct pcpu_block_md *block, int bits, + size_t align) +{ + int bit_off = ALIGN(block->contig_hint_start, align) - + block->contig_hint_start; + + return bit_off + bits <= block->contig_hint; +} + /* * pcpu_next_hint - determine which hint to use * @block: block of interest @@ -507,13 +532,10 @@ static void __pcpu_chunk_move(struct pcpu_chunk *chunk, int slot, bool move_front) { if (chunk != pcpu_reserved_chunk) { - struct list_head *pcpu_slot; - - pcpu_slot = pcpu_chunk_list(pcpu_chunk_type(chunk)); if (move_front) - list_move(&chunk->list, &pcpu_slot[slot]); + list_move(&chunk->list, &pcpu_chunk_lists[slot]); else - list_move_tail(&chunk->list, &pcpu_slot[slot]); + list_move_tail(&chunk->list, &pcpu_chunk_lists[slot]); } } @@ -539,10 +561,36 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) { int nslot = pcpu_chunk_slot(chunk); + /* leave isolated chunks in-place */ + if (chunk->isolated) + return; + if (oslot != nslot) __pcpu_chunk_move(chunk, nslot, oslot < nslot); } +static void pcpu_isolate_chunk(struct pcpu_chunk *chunk) +{ + lockdep_assert_held(&pcpu_lock); + + if (!chunk->isolated) { + chunk->isolated = true; + pcpu_nr_empty_pop_pages -= chunk->nr_empty_pop_pages; + } + list_move(&chunk->list, &pcpu_chunk_lists[pcpu_to_depopulate_slot]); +} + +static void pcpu_reintegrate_chunk(struct pcpu_chunk *chunk) +{ + lockdep_assert_held(&pcpu_lock); + + if (chunk->isolated) { + chunk->isolated = false; + pcpu_nr_empty_pop_pages += chunk->nr_empty_pop_pages; + pcpu_chunk_relocate(chunk, -1); + } +} + /* * pcpu_update_empty_pages - update empty page counters * @chunk: chunk of interest @@ -555,8 +603,8 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr) { chunk->nr_empty_pop_pages += nr; - if (chunk != pcpu_reserved_chunk) - pcpu_nr_empty_pop_pages[pcpu_chunk_type(chunk)] += nr; + if (chunk != pcpu_reserved_chunk && !chunk->isolated) + pcpu_nr_empty_pop_pages += nr; } /* @@ -1063,14 +1111,11 @@ static int pcpu_find_block_fit(struct pcpu_chunk *chunk, int alloc_bits, int bit_off, bits, next_off; /* - * Check to see if the allocation can fit in the chunk's contig hint. - * This is an optimization to prevent scanning by assuming if it - * cannot fit in the global hint, there is memory pressure and creating - * a new chunk would happen soon. + * This is an optimization to prevent scanning by assuming if the + * allocation cannot fit in the global hint, there is memory pressure + * and creating a new chunk would happen soon. */ - bit_off = ALIGN(chunk_md->contig_hint_start, align) - - chunk_md->contig_hint_start; - if (bit_off + alloc_bits > chunk_md->contig_hint) + if (!pcpu_check_block_hint(chunk_md, alloc_bits, align)) return -1; bit_off = pcpu_next_hint(chunk_md, alloc_bits); @@ -1352,7 +1397,7 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, alloc_size); #ifdef CONFIG_MEMCG_KMEM - /* first chunk isn't memcg-aware */ + /* first chunk is free to use */ chunk->obj_cgroups = NULL; #endif pcpu_init_md_blocks(chunk); @@ -1394,7 +1439,7 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, return chunk; } -static struct pcpu_chunk *pcpu_alloc_chunk(enum pcpu_chunk_type type, gfp_t gfp) +static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp) { struct pcpu_chunk *chunk; int region_bits; @@ -1423,7 +1468,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(enum pcpu_chunk_type type, gfp_t gfp) goto md_blocks_fail; #ifdef CONFIG_MEMCG_KMEM - if (pcpu_is_memcg_chunk(type)) { + if (!mem_cgroup_kmem_disabled()) { chunk->obj_cgroups = pcpu_mem_zalloc(pcpu_chunk_map_bits(chunk) * sizeof(struct obj_cgroup *), gfp); @@ -1536,8 +1581,7 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end, gfp_t gfp); static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end); -static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type, - gfp_t gfp); +static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp); static void pcpu_destroy_chunk(struct pcpu_chunk *chunk); static struct page *pcpu_addr_to_page(void *addr); static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai); @@ -1580,25 +1624,25 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) } #ifdef CONFIG_MEMCG_KMEM -static enum pcpu_chunk_type pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, - struct obj_cgroup **objcgp) +static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, + struct obj_cgroup **objcgp) { struct obj_cgroup *objcg; if (!memcg_kmem_enabled() || !(gfp & __GFP_ACCOUNT)) - return PCPU_CHUNK_ROOT; + return true; objcg = get_obj_cgroup_from_current(); if (!objcg) - return PCPU_CHUNK_ROOT; + return true; if (obj_cgroup_charge(objcg, gfp, size * num_possible_cpus())) { obj_cgroup_put(objcg); - return PCPU_FAIL_ALLOC; + return false; } *objcgp = objcg; - return PCPU_CHUNK_MEMCG; + return true; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, @@ -1608,7 +1652,7 @@ static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, if (!objcg) return; - if (chunk) { + if (likely(chunk && chunk->obj_cgroups)) { chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = objcg; rcu_read_lock(); @@ -1625,10 +1669,12 @@ static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { struct obj_cgroup *objcg; - if (!pcpu_is_memcg_chunk(pcpu_chunk_type(chunk))) + if (unlikely(!chunk->obj_cgroups)) return; objcg = chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT]; + if (!objcg) + return; chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = NULL; obj_cgroup_uncharge(objcg, size * num_possible_cpus()); @@ -1642,10 +1688,10 @@ static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) } #else /* CONFIG_MEMCG_KMEM */ -static enum pcpu_chunk_type +static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { - return PCPU_CHUNK_ROOT; + return true; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, @@ -1680,8 +1726,6 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, gfp_t pcpu_gfp; bool is_atomic; bool do_warn; - enum pcpu_chunk_type type; - struct list_head *pcpu_slot; struct obj_cgroup *objcg = NULL; static int warn_limit = 10; struct pcpu_chunk *chunk, *next; @@ -1717,10 +1761,8 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, return NULL; } - type = pcpu_memcg_pre_alloc_hook(size, gfp, &objcg); - if (unlikely(type == PCPU_FAIL_ALLOC)) + if (unlikely(!pcpu_memcg_pre_alloc_hook(size, gfp, &objcg))) return NULL; - pcpu_slot = pcpu_chunk_list(type); if (!is_atomic) { /* @@ -1758,8 +1800,9 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, restart: /* search through normal chunks */ - for (slot = pcpu_size_to_slot(size); slot < pcpu_nr_slots; slot++) { - list_for_each_entry_safe(chunk, next, &pcpu_slot[slot], list) { + for (slot = pcpu_size_to_slot(size); slot <= pcpu_free_slot; slot++) { + list_for_each_entry_safe(chunk, next, &pcpu_chunk_lists[slot], + list) { off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); if (off < 0) { @@ -1769,9 +1812,10 @@ restart: } off = pcpu_alloc_area(chunk, bits, bit_align, off); - if (off >= 0) + if (off >= 0) { + pcpu_reintegrate_chunk(chunk); goto area_found; - + } } } @@ -1787,8 +1831,8 @@ restart: goto fail; } - if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) { - chunk = pcpu_create_chunk(type, pcpu_gfp); + if (list_empty(&pcpu_chunk_lists[pcpu_free_slot])) { + chunk = pcpu_create_chunk(pcpu_gfp); if (!chunk) { err = "failed to allocate new chunk"; goto fail; @@ -1832,7 +1876,7 @@ area_found: mutex_unlock(&pcpu_alloc_mutex); } - if (pcpu_nr_empty_pop_pages[type] < PCPU_EMPTY_POP_PAGES_LOW) + if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW) pcpu_schedule_balance_work(); /* clear the areas and return address relative to base address */ @@ -1930,33 +1974,28 @@ void __percpu *__alloc_reserved_percpu(size_t size, size_t align) } /** - * __pcpu_balance_workfn - manage the amount of free chunks and populated pages - * @type: chunk type + * pcpu_balance_free - manage the amount of free chunks + * @empty_only: free chunks only if there are no populated pages * - * Reclaim all fully free chunks except for the first one. This is also - * responsible for maintaining the pool of empty populated pages. However, - * it is possible that this is called when physical memory is scarce causing - * OOM killer to be triggered. We should avoid doing so until an actual - * allocation causes the failure as it is possible that requests can be - * serviced from already backed regions. + * If empty_only is %false, reclaim all fully free chunks regardless of the + * number of populated pages. Otherwise, only reclaim chunks that have no + * populated pages. + * + * CONTEXT: + * pcpu_lock (can be dropped temporarily) */ -static void __pcpu_balance_workfn(enum pcpu_chunk_type type) +static void pcpu_balance_free(bool empty_only) { - /* gfp flags passed to underlying allocators */ - const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; LIST_HEAD(to_free); - struct list_head *pcpu_slot = pcpu_chunk_list(type); - struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1]; + struct list_head *free_head = &pcpu_chunk_lists[pcpu_free_slot]; struct pcpu_chunk *chunk, *next; - int slot, nr_to_pop, ret; + + lockdep_assert_held(&pcpu_lock); /* * There's no reason to keep around multiple unused chunks and VM * areas can be scarce. Destroy all free chunks except for one. */ - mutex_lock(&pcpu_alloc_mutex); - spin_lock_irq(&pcpu_lock); - list_for_each_entry_safe(chunk, next, free_head, list) { WARN_ON(chunk->immutable); @@ -1964,11 +2003,14 @@ static void __pcpu_balance_workfn(enum pcpu_chunk_type type) if (chunk == list_first_entry(free_head, struct pcpu_chunk, list)) continue; - list_move(&chunk->list, &to_free); + if (!empty_only || chunk->nr_empty_pop_pages == 0) + list_move(&chunk->list, &to_free); } - spin_unlock_irq(&pcpu_lock); + if (list_empty(&to_free)) + return; + spin_unlock_irq(&pcpu_lock); list_for_each_entry_safe(chunk, next, &to_free, list) { unsigned int rs, re; @@ -1982,6 +2024,29 @@ static void __pcpu_balance_workfn(enum pcpu_chunk_type type) pcpu_destroy_chunk(chunk); cond_resched(); } + spin_lock_irq(&pcpu_lock); +} + +/** + * pcpu_balance_populated - manage the amount of populated pages + * + * Maintain a certain amount of populated pages to satisfy atomic allocations. + * It is possible that this is called when physical memory is scarce causing + * OOM killer to be triggered. We should avoid doing so until an actual + * allocation causes the failure as it is possible that requests can be + * serviced from already backed regions. + * + * CONTEXT: + * pcpu_lock (can be dropped temporarily) + */ +static void pcpu_balance_populated(void) +{ + /* gfp flags passed to underlying allocators */ + const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; + struct pcpu_chunk *chunk; + int slot, nr_to_pop, ret; + + lockdep_assert_held(&pcpu_lock); /* * Ensure there are certain number of free populated pages for @@ -2000,23 +2065,21 @@ retry_pop: pcpu_atomic_alloc_failed = false; } else { nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH - - pcpu_nr_empty_pop_pages[type], + pcpu_nr_empty_pop_pages, 0, PCPU_EMPTY_POP_PAGES_HIGH); } - for (slot = pcpu_size_to_slot(PAGE_SIZE); slot < pcpu_nr_slots; slot++) { + for (slot = pcpu_size_to_slot(PAGE_SIZE); slot <= pcpu_free_slot; slot++) { unsigned int nr_unpop = 0, rs, re; if (!nr_to_pop) break; - spin_lock_irq(&pcpu_lock); - list_for_each_entry(chunk, &pcpu_slot[slot], list) { + list_for_each_entry(chunk, &pcpu_chunk_lists[slot], list) { nr_unpop = chunk->nr_pages - chunk->nr_populated; if (nr_unpop) break; } - spin_unlock_irq(&pcpu_lock); if (!nr_unpop) continue; @@ -2026,12 +2089,13 @@ retry_pop: chunk->nr_pages) { int nr = min_t(int, re - rs, nr_to_pop); + spin_unlock_irq(&pcpu_lock); ret = pcpu_populate_chunk(chunk, rs, rs + nr, gfp); + cond_resched(); + spin_lock_irq(&pcpu_lock); if (!ret) { nr_to_pop -= nr; - spin_lock_irq(&pcpu_lock); pcpu_chunk_populated(chunk, rs, rs + nr); - spin_unlock_irq(&pcpu_lock); } else { nr_to_pop = 0; } @@ -2043,30 +2107,133 @@ retry_pop: if (nr_to_pop) { /* ran out of chunks to populate, create a new one and retry */ - chunk = pcpu_create_chunk(type, gfp); + spin_unlock_irq(&pcpu_lock); + chunk = pcpu_create_chunk(gfp); + cond_resched(); + spin_lock_irq(&pcpu_lock); if (chunk) { - spin_lock_irq(&pcpu_lock); pcpu_chunk_relocate(chunk, -1); - spin_unlock_irq(&pcpu_lock); goto retry_pop; } } +} - mutex_unlock(&pcpu_alloc_mutex); +/** + * pcpu_reclaim_populated - scan over to_depopulate chunks and free empty pages + * + * Scan over chunks in the depopulate list and try to release unused populated + * pages back to the system. Depopulated chunks are sidelined to prevent + * repopulating these pages unless required. Fully free chunks are reintegrated + * and freed accordingly (1 is kept around). If we drop below the empty + * populated pages threshold, reintegrate the chunk if it has empty free pages. + * Each chunk is scanned in the reverse order to keep populated pages close to + * the beginning of the chunk. + * + * CONTEXT: + * pcpu_lock (can be dropped temporarily) + * + */ +static void pcpu_reclaim_populated(void) +{ + struct pcpu_chunk *chunk; + struct pcpu_block_md *block; + int i, end; + + lockdep_assert_held(&pcpu_lock); + +restart: + /* + * Once a chunk is isolated to the to_depopulate list, the chunk is no + * longer discoverable to allocations whom may populate pages. The only + * other accessor is the free path which only returns area back to the + * allocator not touching the populated bitmap. + */ + while (!list_empty(&pcpu_chunk_lists[pcpu_to_depopulate_slot])) { + chunk = list_first_entry(&pcpu_chunk_lists[pcpu_to_depopulate_slot], + struct pcpu_chunk, list); + WARN_ON(chunk->immutable); + + /* + * Scan chunk's pages in the reverse order to keep populated + * pages close to the beginning of the chunk. + */ + for (i = chunk->nr_pages - 1, end = -1; i >= 0; i--) { + /* no more work to do */ + if (chunk->nr_empty_pop_pages == 0) + break; + + /* reintegrate chunk to prevent atomic alloc failures */ + if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_HIGH) { + pcpu_reintegrate_chunk(chunk); + goto restart; + } + + /* + * If the page is empty and populated, start or + * extend the (i, end) range. If i == 0, decrease + * i and perform the depopulation to cover the last + * (first) page in the chunk. + */ + block = chunk->md_blocks + i; + if (block->contig_hint == PCPU_BITMAP_BLOCK_BITS && + test_bit(i, chunk->populated)) { + if (end == -1) + end = i; + if (i > 0) + continue; + i--; + } + + /* depopulate if there is an active range */ + if (end == -1) + continue; + + spin_unlock_irq(&pcpu_lock); + pcpu_depopulate_chunk(chunk, i + 1, end + 1); + cond_resched(); + spin_lock_irq(&pcpu_lock); + + pcpu_chunk_depopulated(chunk, i + 1, end + 1); + + /* reset the range and continue */ + end = -1; + } + + if (chunk->free_bytes == pcpu_unit_size) + pcpu_reintegrate_chunk(chunk); + else + list_move(&chunk->list, + &pcpu_chunk_lists[pcpu_sidelined_slot]); + } } /** * pcpu_balance_workfn - manage the amount of free chunks and populated pages * @work: unused * - * Call __pcpu_balance_workfn() for each chunk type. + * For each chunk type, manage the number of fully free chunks and the number of + * populated pages. An important thing to consider is when pages are freed and + * how they contribute to the global counts. */ static void pcpu_balance_workfn(struct work_struct *work) { - enum pcpu_chunk_type type; + /* + * pcpu_balance_free() is called twice because the first time we may + * trim pages in the active pcpu_nr_empty_pop_pages which may cause us + * to grow other chunks. This then gives pcpu_reclaim_populated() time + * to move fully free chunks to the active list to be freed if + * appropriate. + */ + mutex_lock(&pcpu_alloc_mutex); + spin_lock_irq(&pcpu_lock); + + pcpu_balance_free(false); + pcpu_reclaim_populated(); + pcpu_balance_populated(); + pcpu_balance_free(true); - for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) - __pcpu_balance_workfn(type); + spin_unlock_irq(&pcpu_lock); + mutex_unlock(&pcpu_alloc_mutex); } /** @@ -2085,7 +2252,6 @@ void free_percpu(void __percpu *ptr) unsigned long flags; int size, off; bool need_balance = false; - struct list_head *pcpu_slot; if (!ptr) return; @@ -2101,19 +2267,24 @@ void free_percpu(void __percpu *ptr) size = pcpu_free_area(chunk, off); - pcpu_slot = pcpu_chunk_list(pcpu_chunk_type(chunk)); - pcpu_memcg_free_hook(chunk, off, size); - /* if there are more than one fully free chunks, wake up grim reaper */ - if (chunk->free_bytes == pcpu_unit_size) { + /* + * If there are more than one fully free chunks, wake up grim reaper. + * If the chunk is isolated, it may be in the process of being + * reclaimed. Let reclaim manage cleaning up of that chunk. + */ + if (!chunk->isolated && chunk->free_bytes == pcpu_unit_size) { struct pcpu_chunk *pos; - list_for_each_entry(pos, &pcpu_slot[pcpu_nr_slots - 1], list) + list_for_each_entry(pos, &pcpu_chunk_lists[pcpu_free_slot], list) if (pos != chunk) { need_balance = true; break; } + } else if (pcpu_should_reclaim_chunk(chunk)) { + pcpu_isolate_chunk(chunk); + need_balance = true; } trace_percpu_free_percpu(chunk->base_addr, off, ptr); @@ -2414,7 +2585,6 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, int map_size; unsigned long tmp_addr; size_t alloc_size; - enum pcpu_chunk_type type; #define PCPU_SETUP_BUG_ON(cond) do { \ if (unlikely(cond)) { \ @@ -2528,22 +2698,24 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, pcpu_stats_save_ai(ai); /* - * Allocate chunk slots. The additional last slot is for - * empty chunks. + * Allocate chunk slots. The slots after the active slots are: + * sidelined_slot - isolated, depopulated chunks + * free_slot - fully free chunks + * to_depopulate_slot - isolated, chunks to depopulate */ - pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2; + pcpu_sidelined_slot = __pcpu_size_to_slot(pcpu_unit_size) + 1; + pcpu_free_slot = pcpu_sidelined_slot + 1; + pcpu_to_depopulate_slot = pcpu_free_slot + 1; + pcpu_nr_slots = pcpu_to_depopulate_slot + 1; pcpu_chunk_lists = memblock_alloc(pcpu_nr_slots * - sizeof(pcpu_chunk_lists[0]) * - PCPU_NR_CHUNK_TYPES, + sizeof(pcpu_chunk_lists[0]), SMP_CACHE_BYTES); if (!pcpu_chunk_lists) panic("%s: Failed to allocate %zu bytes\n", __func__, - pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]) * - PCPU_NR_CHUNK_TYPES); + pcpu_nr_slots * sizeof(pcpu_chunk_lists[0])); - for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) - for (i = 0; i < pcpu_nr_slots; i++) - INIT_LIST_HEAD(&pcpu_chunk_list(type)[i]); + for (i = 0; i < pcpu_nr_slots; i++) + INIT_LIST_HEAD(&pcpu_chunk_lists[i]); /* * The end of the static region needs to be aligned with the @@ -2580,7 +2752,7 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, /* link the first chunk in */ pcpu_first_chunk = chunk; - pcpu_nr_empty_pop_pages[PCPU_CHUNK_ROOT] = pcpu_first_chunk->nr_empty_pop_pages; + pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages; pcpu_chunk_relocate(pcpu_first_chunk, -1); /* include all regions of the first chunk */ @@ -2733,6 +2905,7 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( * Related to atom_size, which could be much larger than the unit_size. */ last_allocs = INT_MAX; + best_upa = 0; for (upa = max_upa; upa; upa--) { int allocs = 0, wasted = 0; @@ -2759,6 +2932,7 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( last_allocs = allocs; best_upa = upa; } + BUG_ON(!best_upa); upa = best_upa; /* allocate and fill alloc_info */ diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index c2210e1cdb51..4e640baf9794 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -135,9 +135,8 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, { pmd_t pmd; VM_BUG_ON(address & ~HPAGE_PMD_MASK); - VM_BUG_ON(!pmd_present(*pmdp)); - /* Below assumes pmd_present() is true */ - VM_BUG_ON(!pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp)); + VM_BUG_ON(pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) && + !pmd_devmap(*pmdp)); pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; diff --git a/mm/rmap.c b/mm/rmap.c index 693a610e181d..37c24672125c 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -707,7 +707,6 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { - unsigned long address; if (PageAnon(page)) { struct anon_vma *page__anon_vma = page_anon_vma(page); /* @@ -717,15 +716,13 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; - } else if (page->mapping) { - if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping) - return -EFAULT; - } else + } else if (!vma->vm_file) { return -EFAULT; - address = __vma_address(page, vma); - if (unlikely(address < vma->vm_start || address >= vma->vm_end)) + } else if (vma->vm_file->f_mapping != compound_head(page)->mapping) { return -EFAULT; - return address; + } + + return vma_address(page, vma); } pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) @@ -919,7 +916,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma, vma->vm_mm, address, - min(vma->vm_end, address + page_size(page))); + vma_address_end(page, vma)); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { @@ -1405,18 +1402,17 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; - /* munlock has nothing to gain from examining un-locked vmas */ - if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED)) - return true; - - if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && - is_zone_device_page(page) && !is_device_private_page(page)) - return true; + /* + * When racing against e.g. zap_pte_range() on another cpu, + * in between its ptep_get_and_clear_full() and page_remove_rmap(), + * try_to_unmap() may return before page_mapped() has become false, + * if page table locking is skipped: use TTU_SYNC to wait for that. + */ + if (flags & TTU_SYNC) + pvmw.flags = PVMW_SYNC; - if (flags & TTU_SPLIT_HUGE_PMD) { - split_huge_pmd_address(vma, address, - flags & TTU_SPLIT_FREEZE, page); - } + if (flags & TTU_SPLIT_HUGE_PMD) + split_huge_pmd_address(vma, address, false, page); /* * For THP, we have to assume the worse case ie pmd for invalidation. @@ -1426,9 +1422,10 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ + range.end = PageKsm(page) ? + address + PAGE_SIZE : vma_address_end(page, vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, - address, - min(vma->vm_end, address + page_size(page))); + address, range.end); if (PageHuge(page)) { /* * If sharing is possible, start and end will be adjusted @@ -1440,16 +1437,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { -#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION - /* PMD-mapped THP migration entry */ - if (!pvmw.pte && (flags & TTU_MIGRATION)) { - VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page); - - set_pmd_migration_entry(&pvmw, page); - continue; - } -#endif - /* * If the page is mlock()d, we cannot swap it out. * If it's recently referenced (perhaps page_referenced @@ -1469,8 +1456,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, page_vma_mapped_walk_done(&pvmw); break; } - if (flags & TTU_MUNLOCK) - continue; } /* Unexpected PMD-mapped THP? */ @@ -1513,46 +1498,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } } - if (IS_ENABLED(CONFIG_MIGRATION) && - (flags & TTU_MIGRATION) && - is_zone_device_page(page)) { - swp_entry_t entry; - pte_t swp_pte; - - pteval = ptep_get_and_clear(mm, pvmw.address, pvmw.pte); - - /* - * Store the pfn of the page in a special migration - * pte. do_swap_page() will wait until the migration - * pte is removed and then restart fault handling. - */ - entry = make_migration_entry(page, 0); - swp_pte = swp_entry_to_pte(entry); - - /* - * pteval maps a zone device page and is therefore - * a swap pte. - */ - if (pte_swp_soft_dirty(pteval)) - swp_pte = pte_swp_mksoft_dirty(swp_pte); - if (pte_swp_uffd_wp(pteval)) - swp_pte = pte_swp_mkuffd_wp(swp_pte); - set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); - /* - * No need to invalidate here it will synchronize on - * against the special swap migration pte. - * - * The assignment to subpage above was computed from a - * swap PTE which results in an invalid pointer. - * Since only PAGE_SIZE pages can currently be - * migrated, just set it to page. This will need to be - * changed when hugepage migrations to device private - * memory are supported. - */ - subpage = page; - goto discard; - } - /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); if (should_defer_flush(mm, flags)) { @@ -1605,35 +1550,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, /* We have to invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); - } else if (IS_ENABLED(CONFIG_MIGRATION) && - (flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE))) { - swp_entry_t entry; - pte_t swp_pte; - - if (arch_unmap_one(mm, vma, address, pteval) < 0) { - set_pte_at(mm, address, pvmw.pte, pteval); - ret = false; - page_vma_mapped_walk_done(&pvmw); - break; - } - - /* - * Store the pfn of the page in a special migration - * pte. do_swap_page() will wait until the migration - * pte is removed and then restart fault handling. - */ - entry = make_migration_entry(subpage, - pte_write(pteval)); - swp_pte = swp_entry_to_pte(entry); - if (pte_soft_dirty(pteval)) - swp_pte = pte_swp_mksoft_dirty(swp_pte); - if (pte_uffd_wp(pteval)) - swp_pte = pte_swp_mkuffd_wp(swp_pte); - set_pte_at(mm, address, pvmw.pte, swp_pte); - /* - * No need to invalidate here it will synchronize on - * against the special swap migration pte. - */ } else if (PageAnon(page)) { swp_entry_t entry = { .val = page_private(subpage) }; pte_t swp_pte; @@ -1749,9 +1665,10 @@ static int page_not_mapped(struct page *page) * Tries to remove all the page table entries which are mapping this * page, used in the pageout path. Caller must hold the page lock. * - * If unmap is successful, return true. Otherwise, false. + * It is the caller's responsibility to check if the page is still + * mapped when needed (use TTU_SYNC to prevent accounting races). */ -bool try_to_unmap(struct page *page, enum ttu_flags flags) +void try_to_unmap(struct page *page, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, @@ -1760,6 +1677,277 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags) .anon_lock = page_lock_anon_vma_read, }; + if (flags & TTU_RMAP_LOCKED) + rmap_walk_locked(page, &rwc); + else + rmap_walk(page, &rwc); +} + +/* + * @arg: enum ttu_flags will be passed to this argument. + * + * If TTU_SPLIT_HUGE_PMD is specified any PMD mappings will be split into PTEs + * containing migration entries. This and TTU_RMAP_LOCKED are the only supported + * flags. + */ +static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, + unsigned long address, void *arg) +{ + struct mm_struct *mm = vma->vm_mm; + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = address, + }; + pte_t pteval; + struct page *subpage; + bool ret = true; + struct mmu_notifier_range range; + enum ttu_flags flags = (enum ttu_flags)(long)arg; + + if (is_zone_device_page(page) && !is_device_private_page(page)) + return true; + + /* + * When racing against e.g. zap_pte_range() on another cpu, + * in between its ptep_get_and_clear_full() and page_remove_rmap(), + * try_to_migrate() may return before page_mapped() has become false, + * if page table locking is skipped: use TTU_SYNC to wait for that. + */ + if (flags & TTU_SYNC) + pvmw.flags = PVMW_SYNC; + + /* + * unmap_page() in mm/huge_memory.c is the only user of migration with + * TTU_SPLIT_HUGE_PMD and it wants to freeze. + */ + if (flags & TTU_SPLIT_HUGE_PMD) + split_huge_pmd_address(vma, address, true, page); + + /* + * For THP, we have to assume the worse case ie pmd for invalidation. + * For hugetlb, it could be much worse if we need to do pud + * invalidation in the case of pmd sharing. + * + * Note that the page can not be free in this function as call of + * try_to_unmap() must hold a reference on the page. + */ + range.end = PageKsm(page) ? + address + PAGE_SIZE : vma_address_end(page, vma); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, + address, range.end); + if (PageHuge(page)) { + /* + * If sharing is possible, start and end will be adjusted + * accordingly. + */ + adjust_range_if_pmd_sharing_possible(vma, &range.start, + &range.end); + } + mmu_notifier_invalidate_range_start(&range); + + while (page_vma_mapped_walk(&pvmw)) { +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION + /* PMD-mapped THP migration entry */ + if (!pvmw.pte) { + VM_BUG_ON_PAGE(PageHuge(page) || + !PageTransCompound(page), page); + + set_pmd_migration_entry(&pvmw, page); + continue; + } +#endif + + /* Unexpected PMD-mapped THP? */ + VM_BUG_ON_PAGE(!pvmw.pte, page); + + subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); + address = pvmw.address; + + if (PageHuge(page) && !PageAnon(page)) { + /* + * To call huge_pmd_unshare, i_mmap_rwsem must be + * held in write mode. Caller needs to explicitly + * do this outside rmap routines. + */ + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); + if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) { + /* + * huge_pmd_unshare unmapped an entire PMD + * page. There is no way of knowing exactly + * which PMDs may be cached for this mm, so + * we must flush them all. start/end were + * already adjusted above to cover this range. + */ + flush_cache_range(vma, range.start, range.end); + flush_tlb_range(vma, range.start, range.end); + mmu_notifier_invalidate_range(mm, range.start, + range.end); + + /* + * The ref count of the PMD page was dropped + * which is part of the way map counting + * is done for shared PMDs. Return 'true' + * here. When there is no other sharing, + * huge_pmd_unshare returns false and we will + * unmap the actual page and drop map count + * to zero. + */ + page_vma_mapped_walk_done(&pvmw); + break; + } + } + + /* Nuke the page table entry. */ + flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); + pteval = ptep_clear_flush(vma, address, pvmw.pte); + + /* Move the dirty bit to the page. Now the pte is gone. */ + if (pte_dirty(pteval)) + set_page_dirty(page); + + /* Update high watermark before we lower rss */ + update_hiwater_rss(mm); + + if (is_zone_device_page(page)) { + swp_entry_t entry; + pte_t swp_pte; + + /* + * Store the pfn of the page in a special migration + * pte. do_swap_page() will wait until the migration + * pte is removed and then restart fault handling. + */ + entry = make_readable_migration_entry( + page_to_pfn(page)); + swp_pte = swp_entry_to_pte(entry); + + /* + * pteval maps a zone device page and is therefore + * a swap pte. + */ + if (pte_swp_soft_dirty(pteval)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + if (pte_swp_uffd_wp(pteval)) + swp_pte = pte_swp_mkuffd_wp(swp_pte); + set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); + /* + * No need to invalidate here it will synchronize on + * against the special swap migration pte. + * + * The assignment to subpage above was computed from a + * swap PTE which results in an invalid pointer. + * Since only PAGE_SIZE pages can currently be + * migrated, just set it to page. This will need to be + * changed when hugepage migrations to device private + * memory are supported. + */ + subpage = page; + } else if (PageHWPoison(page)) { + pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); + if (PageHuge(page)) { + hugetlb_count_sub(compound_nr(page), mm); + set_huge_swap_pte_at(mm, address, + pvmw.pte, pteval, + vma_mmu_pagesize(vma)); + } else { + dec_mm_counter(mm, mm_counter(page)); + set_pte_at(mm, address, pvmw.pte, pteval); + } + + } else if (pte_unused(pteval) && !userfaultfd_armed(vma)) { + /* + * The guest indicated that the page content is of no + * interest anymore. Simply discard the pte, vmscan + * will take care of the rest. + * A future reference will then fault in a new zero + * page. When userfaultfd is active, we must not drop + * this page though, as its main user (postcopy + * migration) will not expect userfaults on already + * copied pages. + */ + dec_mm_counter(mm, mm_counter(page)); + /* We have to invalidate as we cleared the pte */ + mmu_notifier_invalidate_range(mm, address, + address + PAGE_SIZE); + } else { + swp_entry_t entry; + pte_t swp_pte; + + if (arch_unmap_one(mm, vma, address, pteval) < 0) { + set_pte_at(mm, address, pvmw.pte, pteval); + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } + + /* + * Store the pfn of the page in a special migration + * pte. do_swap_page() will wait until the migration + * pte is removed and then restart fault handling. + */ + if (pte_write(pteval)) + entry = make_writable_migration_entry( + page_to_pfn(subpage)); + else + entry = make_readable_migration_entry( + page_to_pfn(subpage)); + + swp_pte = swp_entry_to_pte(entry); + if (pte_soft_dirty(pteval)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + if (pte_uffd_wp(pteval)) + swp_pte = pte_swp_mkuffd_wp(swp_pte); + set_pte_at(mm, address, pvmw.pte, swp_pte); + /* + * No need to invalidate here it will synchronize on + * against the special swap migration pte. + */ + } + + /* + * No need to call mmu_notifier_invalidate_range() it has be + * done above for all cases requiring it to happen under page + * table lock before mmu_notifier_invalidate_range_end() + * + * See Documentation/vm/mmu_notifier.rst + */ + page_remove_rmap(subpage, PageHuge(page)); + put_page(page); + } + + mmu_notifier_invalidate_range_end(&range); + + return ret; +} + +/** + * try_to_migrate - try to replace all page table mappings with swap entries + * @page: the page to replace page table entries for + * @flags: action and flags + * + * Tries to remove all the page table entries which are mapping this page and + * replace them with special swap entries. Caller must hold the page lock. + * + * If is successful, return true. Otherwise, false. + */ +void try_to_migrate(struct page *page, enum ttu_flags flags) +{ + struct rmap_walk_control rwc = { + .rmap_one = try_to_migrate_one, + .arg = (void *)flags, + .done = page_not_mapped, + .anon_lock = page_lock_anon_vma_read, + }; + + /* + * Migration always ignores mlock and only supports TTU_RMAP_LOCKED and + * TTU_SPLIT_HUGE_PMD and TTU_SYNC flags. + */ + if (WARN_ON_ONCE(flags & ~(TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | + TTU_SYNC))) + return; + /* * During exec, a temporary VMA is setup and later moved. * The VMA is moved under the anon_vma lock but not the @@ -1768,32 +1956,67 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags) * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ - if ((flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE)) - && !PageKsm(page) && PageAnon(page)) + if (!PageKsm(page) && PageAnon(page)) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(page, &rwc); else rmap_walk(page, &rwc); +} + +/* + * Walks the vma's mapping a page and mlocks the page if any locked vma's are + * found. Once one is found the page is locked and the scan can be terminated. + */ +static bool page_mlock_one(struct page *page, struct vm_area_struct *vma, + unsigned long address, void *unused) +{ + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = address, + }; - return !page_mapcount(page) ? true : false; + /* An un-locked vma doesn't have any pages to lock, continue the scan */ + if (!(vma->vm_flags & VM_LOCKED)) + return true; + + while (page_vma_mapped_walk(&pvmw)) { + /* + * Need to recheck under the ptl to serialise with + * __munlock_pagevec_fill() after VM_LOCKED is cleared in + * munlock_vma_pages_range(). + */ + if (vma->vm_flags & VM_LOCKED) { + /* PTE-mapped THP are never mlocked */ + if (!PageTransCompound(page)) + mlock_vma_page(page); + page_vma_mapped_walk_done(&pvmw); + } + + /* + * no need to continue scanning other vma's if the page has + * been locked. + */ + return false; + } + + return true; } /** - * try_to_munlock - try to munlock a page - * @page: the page to be munlocked + * page_mlock - try to mlock a page + * @page: the page to be mlocked * - * Called from munlock code. Checks all of the VMAs mapping the page - * to make sure nobody else has this page mlocked. The page will be - * returned with PG_mlocked cleared if no other vmas have it mlocked. + * Called from munlock code. Checks all of the VMAs mapping the page and mlocks + * the page if any are found. The page will be returned with PG_mlocked cleared + * if it is not mapped by any locked vmas. */ - -void try_to_munlock(struct page *page) +void page_mlock(struct page *page) { struct rmap_walk_control rwc = { - .rmap_one = try_to_unmap_one, - .arg = (void *)TTU_MUNLOCK, + .rmap_one = page_mlock_one, .done = page_not_mapped, .anon_lock = page_lock_anon_vma_read, @@ -1805,6 +2028,192 @@ void try_to_munlock(struct page *page) rmap_walk(page, &rwc); } +#ifdef CONFIG_DEVICE_PRIVATE +struct make_exclusive_args { + struct mm_struct *mm; + unsigned long address; + void *owner; + bool valid; +}; + +static bool page_make_device_exclusive_one(struct page *page, + struct vm_area_struct *vma, unsigned long address, void *priv) +{ + struct mm_struct *mm = vma->vm_mm; + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = address, + }; + struct make_exclusive_args *args = priv; + pte_t pteval; + struct page *subpage; + bool ret = true; + struct mmu_notifier_range range; + swp_entry_t entry; + pte_t swp_pte; + + mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma, + vma->vm_mm, address, min(vma->vm_end, + address + page_size(page)), args->owner); + mmu_notifier_invalidate_range_start(&range); + + while (page_vma_mapped_walk(&pvmw)) { + /* Unexpected PMD-mapped THP? */ + VM_BUG_ON_PAGE(!pvmw.pte, page); + + if (!pte_present(*pvmw.pte)) { + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } + + subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); + address = pvmw.address; + + /* Nuke the page table entry. */ + flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); + pteval = ptep_clear_flush(vma, address, pvmw.pte); + + /* Move the dirty bit to the page. Now the pte is gone. */ + if (pte_dirty(pteval)) + set_page_dirty(page); + + /* + * Check that our target page is still mapped at the expected + * address. + */ + if (args->mm == mm && args->address == address && + pte_write(pteval)) + args->valid = true; + + /* + * Store the pfn of the page in a special migration + * pte. do_swap_page() will wait until the migration + * pte is removed and then restart fault handling. + */ + if (pte_write(pteval)) + entry = make_writable_device_exclusive_entry( + page_to_pfn(subpage)); + else + entry = make_readable_device_exclusive_entry( + page_to_pfn(subpage)); + swp_pte = swp_entry_to_pte(entry); + if (pte_soft_dirty(pteval)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + if (pte_uffd_wp(pteval)) + swp_pte = pte_swp_mkuffd_wp(swp_pte); + + set_pte_at(mm, address, pvmw.pte, swp_pte); + + /* + * There is a reference on the page for the swap entry which has + * been removed, so shouldn't take another. + */ + page_remove_rmap(subpage, false); + } + + mmu_notifier_invalidate_range_end(&range); + + return ret; +} + +/** + * page_make_device_exclusive - mark the page exclusively owned by a device + * @page: the page to replace page table entries for + * @mm: the mm_struct where the page is expected to be mapped + * @address: address where the page is expected to be mapped + * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier callbacks + * + * Tries to remove all the page table entries which are mapping this page and + * replace them with special device exclusive swap entries to grant a device + * exclusive access to the page. Caller must hold the page lock. + * + * Returns false if the page is still mapped, or if it could not be unmapped + * from the expected address. Otherwise returns true (success). + */ +static bool page_make_device_exclusive(struct page *page, struct mm_struct *mm, + unsigned long address, void *owner) +{ + struct make_exclusive_args args = { + .mm = mm, + .address = address, + .owner = owner, + .valid = false, + }; + struct rmap_walk_control rwc = { + .rmap_one = page_make_device_exclusive_one, + .done = page_not_mapped, + .anon_lock = page_lock_anon_vma_read, + .arg = &args, + }; + + /* + * Restrict to anonymous pages for now to avoid potential writeback + * issues. Also tail pages shouldn't be passed to rmap_walk so skip + * those. + */ + if (!PageAnon(page) || PageTail(page)) + return false; + + rmap_walk(page, &rwc); + + return args.valid && !page_mapcount(page); +} + +/** + * make_device_exclusive_range() - Mark a range for exclusive use by a device + * @mm: mm_struct of assoicated target process + * @start: start of the region to mark for exclusive device access + * @end: end address of region + * @pages: returns the pages which were successfully marked for exclusive access + * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier to allow filtering + * + * Returns: number of pages found in the range by GUP. A page is marked for + * exclusive access only if the page pointer is non-NULL. + * + * This function finds ptes mapping page(s) to the given address range, locks + * them and replaces mappings with special swap entries preventing userspace CPU + * access. On fault these entries are replaced with the original mapping after + * calling MMU notifiers. + * + * A driver using this to program access from a device must use a mmu notifier + * critical section to hold a device specific lock during programming. Once + * programming is complete it should drop the page lock and reference after + * which point CPU access to the page will revoke the exclusive access. + */ +int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, + unsigned long end, struct page **pages, + void *owner) +{ + long npages = (end - start) >> PAGE_SHIFT; + long i; + + npages = get_user_pages_remote(mm, start, npages, + FOLL_GET | FOLL_WRITE | FOLL_SPLIT_PMD, + pages, NULL, NULL); + if (npages < 0) + return npages; + + for (i = 0; i < npages; i++, start += PAGE_SIZE) { + if (!trylock_page(pages[i])) { + put_page(pages[i]); + pages[i] = NULL; + continue; + } + + if (!page_make_device_exclusive(pages[i], mm, start, owner)) { + unlock_page(pages[i]); + put_page(pages[i]); + pages[i] = NULL; + } + } + + return npages; +} +EXPORT_SYMBOL_GPL(make_device_exclusive_range); +#endif + void __put_anon_vma(struct anon_vma *anon_vma) { struct anon_vma *root = anon_vma->root; @@ -1845,7 +2254,7 @@ static struct anon_vma *rmap_walk_anon_lock(struct page *page, * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the anon_vma struct it points to. * - * When called from try_to_munlock(), the mmap_lock of the mm containing the vma + * When called from page_mlock(), the mmap_lock of the mm containing the vma * where the page was found will be held for write. So, we won't recheck * vm_flags for that VMA. That should be OK, because that vma shouldn't be * LOCKED. @@ -1874,6 +2283,7 @@ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); + VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) @@ -1897,7 +2307,7 @@ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the address_space struct it points to. * - * When called from try_to_munlock(), the mmap_lock of the mm containing the vma + * When called from page_mlock(), the mmap_lock of the mm containing the vma * where the page was found will be held for write. So, we won't recheck * vm_flags for that VMA. That should be OK, because that vma shouldn't be * LOCKED. @@ -1928,6 +2338,7 @@ static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, pgoff_start, pgoff_end) { unsigned long address = vma_address(page, vma); + VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) diff --git a/mm/shmem.c b/mm/shmem.c index a08cedefbfaa..70d9ce294bb4 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1695,8 +1695,9 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); - struct mm_struct *charge_mm = vma ? vma->vm_mm : current->mm; - struct page *page; + struct mm_struct *charge_mm = vma ? vma->vm_mm : NULL; + struct swap_info_struct *si; + struct page *page = NULL; swp_entry_t swap; int error; @@ -1704,6 +1705,12 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, swap = radix_to_swp_entry(*pagep); *pagep = NULL; + /* Prevent swapoff from happening to us. */ + si = get_swap_device(swap); + if (!si) { + error = EINVAL; + goto failed; + } /* Look it up and read it in.. */ page = lookup_swap_cache(swap, NULL, 0); if (!page) { @@ -1765,6 +1772,8 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, swap_free(swap); *pagep = page; + if (si) + put_swap_device(si); return 0; failed: if (!shmem_confirm_swap(mapping, index, swap)) @@ -1775,6 +1784,9 @@ unlock: put_page(page); } + if (si) + put_swap_device(si); + return error; } @@ -1785,7 +1797,7 @@ unlock: * vm. If we swap it in we mark it dirty since we also free the swap * entry since a page cannot live in both the swap and page cache. * - * vmf and fault_type are only supplied by shmem_fault: + * vma, vmf, and fault_type are only supplied by shmem_fault: * otherwise they are NULL. */ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, @@ -1816,10 +1828,20 @@ repeat: } sbinfo = SHMEM_SB(inode->i_sb); - charge_mm = vma ? vma->vm_mm : current->mm; + charge_mm = vma ? vma->vm_mm : NULL; page = pagecache_get_page(mapping, index, FGP_ENTRY | FGP_HEAD | FGP_LOCK, 0); + + if (page && vma && userfaultfd_minor(vma)) { + if (!xa_is_value(page)) { + unlock_page(page); + put_page(page); + } + *fault_type = handle_userfault(vmf, VM_UFFD_MINOR); + return 0; + } + if (xa_is_value(page)) { error = shmem_swapin_page(inode, index, &page, sgp, gfp, vma, fault_type); @@ -2227,7 +2249,7 @@ static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma, } #endif -int shmem_lock(struct file *file, int lock, struct user_struct *user) +int shmem_lock(struct file *file, int lock, struct ucounts *ucounts) { struct inode *inode = file_inode(file); struct shmem_inode_info *info = SHMEM_I(inode); @@ -2239,13 +2261,13 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) * no serialization needed when called from shm_destroy(). */ if (lock && !(info->flags & VM_LOCKED)) { - if (!user_shm_lock(inode->i_size, user)) + if (!user_shm_lock(inode->i_size, ucounts)) goto out_nomem; info->flags |= VM_LOCKED; mapping_set_unevictable(file->f_mapping); } - if (!lock && (info->flags & VM_LOCKED) && user) { - user_shm_unlock(inode->i_size, user); + if (!lock && (info->flags & VM_LOCKED) && ucounts) { + user_shm_unlock(inode->i_size, ucounts); info->flags &= ~VM_LOCKED; mapping_clear_unevictable(file->f_mapping); } @@ -2258,25 +2280,11 @@ out_nomem: static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { struct shmem_inode_info *info = SHMEM_I(file_inode(file)); + int ret; - if (info->seals & F_SEAL_FUTURE_WRITE) { - /* - * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * "future write" seal active. - */ - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) - return -EPERM; - - /* - * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (vma->vm_flags & VM_SHARED) - vma->vm_flags &= ~(VM_MAYWRITE); - } + ret = seal_check_future_write(info->seals, vma); + if (ret) + return ret; /* arm64 - allow memory tagging on RAM-based files */ vma->vm_flags |= VM_MTE_ALLOWED; @@ -2354,36 +2362,45 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode return inode; } -static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - bool zeropage, - struct page **pagep) +#ifdef CONFIG_USERFAULTFD +int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + bool zeropage, + struct page **pagep) { struct inode *inode = file_inode(dst_vma->vm_file); struct shmem_inode_info *info = SHMEM_I(inode); struct address_space *mapping = inode->i_mapping; gfp_t gfp = mapping_gfp_mask(mapping); pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); - spinlock_t *ptl; void *page_kaddr; struct page *page; - pte_t _dst_pte, *dst_pte; int ret; - pgoff_t offset, max_off; + pgoff_t max_off; - ret = -ENOMEM; - if (!shmem_inode_acct_block(inode, 1)) - goto out; + if (!shmem_inode_acct_block(inode, 1)) { + /* + * We may have got a page, returned -ENOENT triggering a retry, + * and now we find ourselves with -ENOMEM. Release the page, to + * avoid a BUG_ON in our caller. + */ + if (unlikely(*pagep)) { + put_page(*pagep); + *pagep = NULL; + } + return -ENOMEM; + } if (!*pagep) { + ret = -ENOMEM; page = shmem_alloc_page(gfp, info, pgoff); if (!page) goto out_unacct_blocks; - if (!zeropage) { /* mcopy_atomic */ + if (!zeropage) { /* COPY */ page_kaddr = kmap_atomic(page); ret = copy_from_user(page_kaddr, (const void __user *)src_addr, @@ -2393,11 +2410,11 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { *pagep = page; - shmem_inode_unacct_blocks(inode, 1); + ret = -ENOENT; /* don't free the page */ - return -ENOENT; + goto out_unacct_blocks; } - } else { /* mfill_zeropage_atomic */ + } else { /* ZEROPAGE */ clear_highpage(page); } } else { @@ -2405,15 +2422,15 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, *pagep = NULL; } - VM_BUG_ON(PageLocked(page) || PageSwapBacked(page)); + VM_BUG_ON(PageLocked(page)); + VM_BUG_ON(PageSwapBacked(page)); __SetPageLocked(page); __SetPageSwapBacked(page); __SetPageUptodate(page); ret = -EFAULT; - offset = linear_page_index(dst_vma, dst_addr); max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); - if (unlikely(offset >= max_off)) + if (unlikely(pgoff >= max_off)) goto out_release; ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL, @@ -2421,32 +2438,10 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (ret) goto out_release; - _dst_pte = mk_pte(page, dst_vma->vm_page_prot); - if (dst_vma->vm_flags & VM_WRITE) - _dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte)); - else { - /* - * We don't set the pte dirty if the vma has no - * VM_WRITE permission, so mark the page dirty or it - * could be freed from under us. We could do it - * unconditionally before unlock_page(), but doing it - * only if VM_WRITE is not set is faster. - */ - set_page_dirty(page); - } - - dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); - - ret = -EFAULT; - max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); - if (unlikely(offset >= max_off)) - goto out_release_unlock; - - ret = -EEXIST; - if (!pte_none(*dst_pte)) - goto out_release_unlock; - - lru_cache_add(page); + ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, + page, true, false); + if (ret) + goto out_delete_from_cache; spin_lock_irq(&info->lock); info->alloced++; @@ -2454,50 +2449,19 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); - inc_mm_counter(dst_mm, mm_counter_file(page)); - page_add_file_rmap(page, false); - set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); - - /* No need to invalidate - it was non-present before */ - update_mmu_cache(dst_vma, dst_addr, dst_pte); - pte_unmap_unlock(dst_pte, ptl); + SetPageDirty(page); unlock_page(page); - ret = 0; -out: - return ret; -out_release_unlock: - pte_unmap_unlock(dst_pte, ptl); - ClearPageDirty(page); + return 0; +out_delete_from_cache: delete_from_page_cache(page); out_release: unlock_page(page); put_page(page); out_unacct_blocks: shmem_inode_unacct_blocks(inode, 1); - goto out; -} - -int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - struct page **pagep) -{ - return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, - dst_addr, src_addr, false, pagep); -} - -int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr) -{ - struct page *page = NULL; - - return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, - dst_addr, 0, true, &page); + return ret; } +#endif /* CONFIG_USERFAULTFD */ #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; @@ -4032,8 +3996,7 @@ bool shmem_huge_enabled(struct vm_area_struct *vma) loff_t i_size; pgoff_t off; - if ((vma->vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + if (!transhuge_vma_enabled(vma, vma->vm_flags)) return false; if (shmem_huge == SHMEM_HUGE_FORCE) return true; @@ -4096,7 +4059,7 @@ int shmem_unuse(unsigned int type, bool frontswap, return 0; } -int shmem_lock(struct file *file, int lock, struct user_struct *user) +int shmem_lock(struct file *file, int lock, struct ucounts *ucounts) { return 0; } diff --git a/mm/shuffle.h b/mm/shuffle.h index 71b784f0b7c3..cec62984f7d3 100644 --- a/mm/shuffle.h +++ b/mm/shuffle.h @@ -10,7 +10,7 @@ DECLARE_STATIC_KEY_FALSE(page_alloc_shuffle_key); extern void __shuffle_free_memory(pg_data_t *pgdat); extern bool shuffle_pick_tail(void); -static inline void shuffle_free_memory(pg_data_t *pgdat) +static inline void __meminit shuffle_free_memory(pg_data_t *pgdat) { if (!static_branch_unlikely(&page_alloc_shuffle_key)) return; @@ -18,7 +18,7 @@ static inline void shuffle_free_memory(pg_data_t *pgdat) } extern void __shuffle_zone(struct zone *z); -static inline void shuffle_zone(struct zone *z) +static inline void __meminit shuffle_zone(struct zone *z) { if (!static_branch_unlikely(&page_alloc_shuffle_key)) return; diff --git a/mm/slab.h b/mm/slab.h index 7189daa0c586..67e06637ff2e 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -215,6 +215,7 @@ DECLARE_STATIC_KEY_TRUE(slub_debug_enabled); DECLARE_STATIC_KEY_FALSE(slub_debug_enabled); #endif extern void print_tracking(struct kmem_cache *s, void *object); +long validate_slab_cache(struct kmem_cache *s); #else static inline void print_tracking(struct kmem_cache *s, void *object) { @@ -239,6 +240,8 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla #ifdef CONFIG_MEMCG_KMEM int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, gfp_t gfp, bool new_page); +void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, + enum node_stat_item idx, int nr); static inline void memcg_free_page_obj_cgroups(struct page *page) { @@ -283,20 +286,6 @@ static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, return true; } -static inline void mod_objcg_state(struct obj_cgroup *objcg, - struct pglist_data *pgdat, - enum node_stat_item idx, int nr) -{ - struct mem_cgroup *memcg; - struct lruvec *lruvec; - - rcu_read_lock(); - memcg = obj_cgroup_memcg(objcg); - lruvec = mem_cgroup_lruvec(memcg, pgdat); - mod_memcg_lruvec_state(lruvec, idx, nr); - rcu_read_unlock(); -} - static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, struct obj_cgroup *objcg, gfp_t flags, size_t size, @@ -309,7 +298,6 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, if (!memcg_kmem_enabled() || !objcg) return; - flags &= ~__GFP_ACCOUNT; for (i = 0; i < size; i++) { if (likely(p[i])) { page = virt_to_head_page(p[i]); @@ -630,6 +618,12 @@ static inline bool slab_want_init_on_free(struct kmem_cache *c) return false; } +#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_SLUB_DEBUG) +void debugfs_slab_release(struct kmem_cache *); +#else +static inline void debugfs_slab_release(struct kmem_cache *s) { } +#endif + #ifdef CONFIG_PRINTK #define KS_ADDRS_COUNT 16 struct kmem_obj_info { diff --git a/mm/slab_common.c b/mm/slab_common.c index 92e3aa78bb4d..1c673c323baf 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -97,8 +97,7 @@ EXPORT_SYMBOL(kmem_cache_size); #ifdef CONFIG_DEBUG_VM static int kmem_cache_sanity_check(const char *name, unsigned int size) { - if (!name || in_interrupt() || size < sizeof(void *) || - size > KMALLOC_MAX_SIZE) { + if (!name || in_interrupt() || size > KMALLOC_MAX_SIZE) { pr_err("kmem_cache_create(%s) integrity check failed\n", name); return -EINVAL; } @@ -318,6 +317,16 @@ kmem_cache_create_usercopy(const char *name, const char *cache_name; int err; +#ifdef CONFIG_SLUB_DEBUG + /* + * If no slub_debug was enabled globally, the static key is not yet + * enabled by setup_slub_debug(). Enable it if the cache is being + * created with any of the debugging flags passed explicitly. + */ + if (flags & SLAB_DEBUG_FLAGS) + static_branch_enable(&slub_debug_enabled); +#endif + mutex_lock(&slab_mutex); err = kmem_cache_sanity_check(name, size); @@ -368,11 +377,11 @@ out_unlock: if (err) { if (flags & SLAB_PANIC) - panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n", - name, err); + panic("%s: Failed to create slab '%s'. Error %d\n", + __func__, name, err); else { - pr_warn("kmem_cache_create(%s) failed with error %d\n", - name, err); + pr_warn("%s(%s) failed with error %d\n", + __func__, name, err); dump_stack(); } return NULL; @@ -439,6 +448,7 @@ static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work) rcu_barrier(); list_for_each_entry_safe(s, s2, &to_destroy, list) { + debugfs_slab_release(s); kfence_shutdown_cache(s); #ifdef SLAB_SUPPORTS_SYSFS sysfs_slab_release(s); @@ -466,6 +476,7 @@ static int shutdown_cache(struct kmem_cache *s) schedule_work(&slab_caches_to_rcu_destroy_work); } else { kfence_shutdown_cache(s); + debugfs_slab_release(s); #ifdef SLAB_SUPPORTS_SYSFS sysfs_slab_unlink(s); sysfs_slab_release(s); @@ -499,8 +510,8 @@ void kmem_cache_destroy(struct kmem_cache *s) err = shutdown_cache(s); if (err) { - pr_err("kmem_cache_destroy %s: Slab cache still has objects\n", - s->name); + pr_err("%s %s: Slab cache still has objects\n", + __func__, s->name); dump_stack(); } out_unlock: @@ -737,26 +748,30 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags) } #ifdef CONFIG_ZONE_DMA -#define INIT_KMALLOC_INFO(__size, __short_size) \ -{ \ - .name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \ - .name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #__short_size, \ - .name[KMALLOC_DMA] = "dma-kmalloc-" #__short_size, \ - .size = __size, \ -} +#define KMALLOC_DMA_NAME(sz) .name[KMALLOC_DMA] = "dma-kmalloc-" #sz, #else +#define KMALLOC_DMA_NAME(sz) +#endif + +#ifdef CONFIG_MEMCG_KMEM +#define KMALLOC_CGROUP_NAME(sz) .name[KMALLOC_CGROUP] = "kmalloc-cg-" #sz, +#else +#define KMALLOC_CGROUP_NAME(sz) +#endif + #define INIT_KMALLOC_INFO(__size, __short_size) \ { \ .name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \ .name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #__short_size, \ + KMALLOC_CGROUP_NAME(__short_size) \ + KMALLOC_DMA_NAME(__short_size) \ .size = __size, \ } -#endif /* * kmalloc_info[] is to make slub_debug=,kmalloc-xx option work at boot time. - * kmalloc_index() supports up to 2^26=64MB, so the final entry of the table is - * kmalloc-67108864. + * kmalloc_index() supports up to 2^25=32MB, so the final entry of the table is + * kmalloc-32M. */ const struct kmalloc_info_struct kmalloc_info[] __initconst = { INIT_KMALLOC_INFO(0, 0), @@ -784,8 +799,7 @@ const struct kmalloc_info_struct kmalloc_info[] __initconst = { INIT_KMALLOC_INFO(4194304, 4M), INIT_KMALLOC_INFO(8388608, 8M), INIT_KMALLOC_INFO(16777216, 16M), - INIT_KMALLOC_INFO(33554432, 32M), - INIT_KMALLOC_INFO(67108864, 64M) + INIT_KMALLOC_INFO(33554432, 32M) }; /* @@ -838,13 +852,27 @@ void __init setup_kmalloc_cache_index_table(void) static void __init new_kmalloc_cache(int idx, enum kmalloc_cache_type type, slab_flags_t flags) { - if (type == KMALLOC_RECLAIM) + if (type == KMALLOC_RECLAIM) { flags |= SLAB_RECLAIM_ACCOUNT; + } else if (IS_ENABLED(CONFIG_MEMCG_KMEM) && (type == KMALLOC_CGROUP)) { + if (cgroup_memory_nokmem) { + kmalloc_caches[type][idx] = kmalloc_caches[KMALLOC_NORMAL][idx]; + return; + } + flags |= SLAB_ACCOUNT; + } kmalloc_caches[type][idx] = create_kmalloc_cache( kmalloc_info[idx].name[type], kmalloc_info[idx].size, flags, 0, kmalloc_info[idx].size); + + /* + * If CONFIG_MEMCG_KMEM is enabled, disable cache merging for + * KMALLOC_NORMAL caches. + */ + if (IS_ENABLED(CONFIG_MEMCG_KMEM) && (type == KMALLOC_NORMAL)) + kmalloc_caches[type][idx]->refcount = -1; } /* @@ -857,6 +885,9 @@ void __init create_kmalloc_caches(slab_flags_t flags) int i; enum kmalloc_cache_type type; + /* + * Including KMALLOC_CGROUP if CONFIG_MEMCG_KMEM defined + */ for (type = KMALLOC_NORMAL; type <= KMALLOC_RECLAIM; type++) { for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) { if (!kmalloc_caches[type][i]) diff --git a/mm/slub.c b/mm/slub.c index deec894a1345..2ee43ff667a5 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -15,6 +15,7 @@ #include <linux/module.h> #include <linux/bit_spinlock.h> #include <linux/interrupt.h> +#include <linux/swab.h> #include <linux/bitops.h> #include <linux/slab.h> #include "slab.h" @@ -35,7 +36,9 @@ #include <linux/prefetch.h> #include <linux/memcontrol.h> #include <linux/random.h> +#include <kunit/test.h> +#include <linux/debugfs.h> #include <trace/events/kmem.h> #include "internal.h" @@ -116,12 +119,26 @@ */ #ifdef CONFIG_SLUB_DEBUG + #ifdef CONFIG_SLUB_DEBUG_ON DEFINE_STATIC_KEY_TRUE(slub_debug_enabled); #else DEFINE_STATIC_KEY_FALSE(slub_debug_enabled); #endif -#endif + +static inline bool __slub_debug_enabled(void) +{ + return static_branch_unlikely(&slub_debug_enabled); +} + +#else /* CONFIG_SLUB_DEBUG */ + +static inline bool __slub_debug_enabled(void) +{ + return false; +} + +#endif /* CONFIG_SLUB_DEBUG */ static inline bool kmem_cache_debug(struct kmem_cache *s) { @@ -153,9 +170,6 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s) * - Variable sizing of the per node arrays */ -/* Enable to test recovery from slab corruption on boot */ -#undef SLUB_RESILIENCY_TEST - /* Enable to log cmpxchg failures */ #undef SLUB_DEBUG_CMPXCHG @@ -225,6 +239,12 @@ static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p) { return 0; } #endif +#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_SLUB_DEBUG) +static void debugfs_slab_add(struct kmem_cache *); +#else +static inline void debugfs_slab_add(struct kmem_cache *s) { } +#endif + static inline void stat(const struct kmem_cache *s, enum stat_item si) { #ifdef CONFIG_SLUB_STATS @@ -301,6 +321,7 @@ static inline void *get_freepointer_safe(struct kmem_cache *s, void *object) if (!debug_pagealloc_enabled_static()) return get_freepointer(s, object); + object = kasan_reset_tag(object); freepointer_addr = (unsigned long)object + s->offset; copy_from_kernel_nofault(&p, (void **)freepointer_addr, sizeof(p)); return freelist_ptr(s, p, freepointer_addr); @@ -447,6 +468,26 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, static unsigned long object_map[BITS_TO_LONGS(MAX_OBJS_PER_PAGE)]; static DEFINE_SPINLOCK(object_map_lock); +#if IS_ENABLED(CONFIG_KUNIT) +static bool slab_add_kunit_errors(void) +{ + struct kunit_resource *resource; + + if (likely(!current->kunit_test)) + return false; + + resource = kunit_find_named_resource(current->kunit_test, "slab_errors"); + if (!resource) + return false; + + (*(int *)resource->data)++; + kunit_put_resource(resource); + return true; +} +#else +static inline bool slab_add_kunit_errors(void) { return false; } +#endif + /* * Determine a map of object in use on a page. * @@ -667,16 +708,18 @@ static void slab_bug(struct kmem_cache *s, char *fmt, ...) pr_err("=============================================================================\n"); pr_err("BUG %s (%s): %pV\n", s->name, print_tainted(), &vaf); pr_err("-----------------------------------------------------------------------------\n\n"); - - add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); va_end(args); } +__printf(2, 3) static void slab_fix(struct kmem_cache *s, char *fmt, ...) { struct va_format vaf; va_list args; + if (slab_add_kunit_errors()) + return; + va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; @@ -711,15 +754,15 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) p, p - addr, get_freepointer(s, p)); if (s->flags & SLAB_RED_ZONE) - print_section(KERN_ERR, "Redzone ", p - s->red_left_pad, + print_section(KERN_ERR, "Redzone ", p - s->red_left_pad, s->red_left_pad); else if (p > addr + 16) print_section(KERN_ERR, "Bytes b4 ", p - 16, 16); - print_section(KERN_ERR, "Object ", p, + print_section(KERN_ERR, "Object ", p, min_t(unsigned int, s->object_size, PAGE_SIZE)); if (s->flags & SLAB_RED_ZONE) - print_section(KERN_ERR, "Redzone ", p + s->object_size, + print_section(KERN_ERR, "Redzone ", p + s->object_size, s->inuse - s->object_size); off = get_info_end(s); @@ -731,7 +774,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) if (off != size_from_object(s)) /* Beginning of the filler is the free pointer */ - print_section(KERN_ERR, "Padding ", p + off, + print_section(KERN_ERR, "Padding ", p + off, size_from_object(s) - off); dump_stack(); @@ -740,8 +783,12 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) void object_err(struct kmem_cache *s, struct page *page, u8 *object, char *reason) { + if (slab_add_kunit_errors()) + return; + slab_bug(s, "%s", reason); print_trailer(s, page, object); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } static __printf(3, 4) void slab_err(struct kmem_cache *s, struct page *page, @@ -750,12 +797,16 @@ static __printf(3, 4) void slab_err(struct kmem_cache *s, struct page *page, va_list args; char buf[100]; + if (slab_add_kunit_errors()) + return; + va_start(args, fmt); vsnprintf(buf, sizeof(buf), fmt, args); va_end(args); slab_bug(s, "%s", buf); print_page_info(page); dump_stack(); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } static void init_object(struct kmem_cache *s, void *object, u8 val) @@ -777,7 +828,7 @@ static void init_object(struct kmem_cache *s, void *object, u8 val) static void restore_bytes(struct kmem_cache *s, char *message, u8 data, void *from, void *to) { - slab_fix(s, "Restoring 0x%p-0x%p=0x%x\n", from, to - 1, data); + slab_fix(s, "Restoring %s 0x%p-0x%p=0x%x", message, from, to - 1, data); memset(from, data, to - from); } @@ -799,12 +850,17 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, while (end > fault && end[-1] == value) end--; + if (slab_add_kunit_errors()) + goto skip_bug_print; + slab_bug(s, "%s overwritten", what); pr_err("0x%p-0x%p @offset=%tu. First byte 0x%x instead of 0x%x\n", fault, end - 1, fault - addr, fault[0], value); print_trailer(s, page, object); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); +skip_bug_print: restore_bytes(s, what, value, fault, end); return 0; } @@ -908,11 +964,11 @@ static int check_object(struct kmem_cache *s, struct page *page, u8 *endobject = object + s->object_size; if (s->flags & SLAB_RED_ZONE) { - if (!check_bytes_and_report(s, page, object, "Redzone", + if (!check_bytes_and_report(s, page, object, "Left Redzone", object - s->red_left_pad, val, s->red_left_pad)) return 0; - if (!check_bytes_and_report(s, page, object, "Redzone", + if (!check_bytes_and_report(s, page, object, "Right Redzone", endobject, val, s->inuse - s->object_size)) return 0; } else { @@ -927,7 +983,7 @@ static int check_object(struct kmem_cache *s, struct page *page, if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) && (!check_bytes_and_report(s, page, p, "Poison", p, POISON_FREE, s->object_size - 1) || - !check_bytes_and_report(s, page, p, "Poison", + !check_bytes_and_report(s, page, p, "End Poison", p + s->object_size - 1, POISON_END, 1))) return 0; /* @@ -1026,13 +1082,13 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search) slab_err(s, page, "Wrong number of objects. Found %d but should be %d", page->objects, max_objects); page->objects = max_objects; - slab_fix(s, "Number of objects adjusted."); + slab_fix(s, "Number of objects adjusted"); } if (page->inuse != page->objects - nr) { slab_err(s, page, "Wrong object count. Counter is %d but counted were %d", page->inuse, page->objects - nr); page->inuse = page->objects - nr; - slab_fix(s, "Object count adjusted."); + slab_fix(s, "Object count adjusted"); } return search == NULL; } @@ -1396,6 +1452,8 @@ static int __init setup_slub_debug(char *str) out: if (slub_debug != 0 || slub_debug_string) static_branch_enable(&slub_debug_enabled); + else + static_branch_disable(&slub_debug_enabled); if ((static_branch_unlikely(&init_on_alloc) || static_branch_unlikely(&init_on_free)) && (slub_debug & SLAB_POISON)) @@ -3688,7 +3746,6 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) { slab_flags_t flags = s->flags; unsigned int size = s->object_size; - unsigned int freepointer_area; unsigned int order; /* @@ -3697,13 +3754,6 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * the possible location of the free pointer. */ size = ALIGN(size, sizeof(void *)); - /* - * This is the area of the object where a freepointer can be - * safely written. If redzoning adds more to the inuse size, we - * can't use that portion for writing the freepointer, so - * s->offset must be limited within this for the general case. - */ - freepointer_area = size; #ifdef CONFIG_SLUB_DEBUG /* @@ -3729,19 +3779,21 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) /* * With that we have determined the number of bytes in actual use - * by the object. This is the potential offset to the free pointer. + * by the object and redzoning. */ s->inuse = size; - if (((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) || - s->ctor)) { + if ((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) || + ((flags & SLAB_RED_ZONE) && s->object_size < sizeof(void *)) || + s->ctor) { /* * Relocate free pointer after the object if it is not * permitted to overwrite the first word of the object on * kmem_cache_free. * * This is the case if we do RCU, have a constructor or - * destructor or are poisoning the objects. + * destructor, are poisoning the objects, or are + * redzoning an object smaller than sizeof(void *). * * The assumption that s->offset >= s->inuse means free * pointer is outside of the object is used in the @@ -3750,13 +3802,13 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) */ s->offset = size; size += sizeof(void *); - } else if (freepointer_area > sizeof(void *)) { + } else { /* * Store freelist pointer near middle of object to keep * it away from the edges of the object to avoid small * sized over/underflows from neighboring allocations. */ - s->offset = ALIGN(freepointer_area / 2, sizeof(void *)); + s->offset = ALIGN_DOWN(s->object_size / 2, sizeof(void *)); } #ifdef CONFIG_SLUB_DEBUG @@ -3828,15 +3880,6 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags) { -#ifdef CONFIG_SLUB_DEBUG - /* - * If no slub_debug was enabled globally, the static key is not yet - * enabled by setup_slub_debug(). Enable it if the cache is being - * created with any of the debugging flags passed explicitly. - */ - if (flags & SLAB_DEBUG_FLAGS) - static_branch_enable(&slub_debug_enabled); -#endif s->flags = kmem_cache_flags(s->size, flags, s->name); #ifdef CONFIG_SLAB_FREELIST_HARDENED s->random = get_random_long(); @@ -4474,6 +4517,10 @@ void __init kmem_cache_init(void) if (debug_guardpage_minorder()) slub_max_order = 0; + /* Print slub debugging pointers without hashing */ + if (__slub_debug_enabled()) + no_hash_pointers_enable(NULL); + kmem_cache_node = &boot_kmem_cache_node; kmem_cache = &boot_kmem_cache; @@ -4562,6 +4609,9 @@ int __kmem_cache_create(struct kmem_cache *s, slab_flags_t flags) if (err) __kmem_cache_release(s); + if (s->flags & SLAB_STORE_USER) + debugfs_slab_add(s); + return err; } @@ -4670,9 +4720,11 @@ static int validate_slab_node(struct kmem_cache *s, validate_slab(s, page); count++; } - if (count != n->nr_partial) + if (count != n->nr_partial) { pr_err("SLUB %s: %ld partial slabs counted but counter=%ld\n", s->name, count, n->nr_partial); + slab_add_kunit_errors(); + } if (!(s->flags & SLAB_STORE_USER)) goto out; @@ -4681,16 +4733,18 @@ static int validate_slab_node(struct kmem_cache *s, validate_slab(s, page); count++; } - if (count != atomic_long_read(&n->nr_slabs)) + if (count != atomic_long_read(&n->nr_slabs)) { pr_err("SLUB: %s %ld slabs counted but counter=%ld\n", s->name, count, atomic_long_read(&n->nr_slabs)); + slab_add_kunit_errors(); + } out: spin_unlock_irqrestore(&n->list_lock, flags); return count; } -static long validate_slab_cache(struct kmem_cache *s) +long validate_slab_cache(struct kmem_cache *s) { int node; unsigned long count = 0; @@ -4702,6 +4756,9 @@ static long validate_slab_cache(struct kmem_cache *s) return count; } +EXPORT_SYMBOL(validate_slab_cache); + +#ifdef CONFIG_DEBUG_FS /* * Generate lists of code addresses where slabcache objects are allocated * and freed. @@ -4725,6 +4782,8 @@ struct loc_track { struct location *loc; }; +static struct dentry *slab_debugfs_root; + static void free_loc_track(struct loc_track *t) { if (t->max) @@ -4841,144 +4900,9 @@ static void process_slab(struct loc_track *t, struct kmem_cache *s, add_location(t, s, get_track(s, p, alloc)); put_map(map); } - -static int list_locations(struct kmem_cache *s, char *buf, - enum track_item alloc) -{ - int len = 0; - unsigned long i; - struct loc_track t = { 0, 0, NULL }; - int node; - struct kmem_cache_node *n; - - if (!alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location), - GFP_KERNEL)) { - return sysfs_emit(buf, "Out of memory\n"); - } - /* Push back cpu slabs */ - flush_all(s); - - for_each_kmem_cache_node(s, node, n) { - unsigned long flags; - struct page *page; - - if (!atomic_long_read(&n->nr_slabs)) - continue; - - spin_lock_irqsave(&n->list_lock, flags); - list_for_each_entry(page, &n->partial, slab_list) - process_slab(&t, s, page, alloc); - list_for_each_entry(page, &n->full, slab_list) - process_slab(&t, s, page, alloc); - spin_unlock_irqrestore(&n->list_lock, flags); - } - - for (i = 0; i < t.count; i++) { - struct location *l = &t.loc[i]; - - len += sysfs_emit_at(buf, len, "%7ld ", l->count); - - if (l->addr) - len += sysfs_emit_at(buf, len, "%pS", (void *)l->addr); - else - len += sysfs_emit_at(buf, len, "<not-available>"); - - if (l->sum_time != l->min_time) - len += sysfs_emit_at(buf, len, " age=%ld/%ld/%ld", - l->min_time, - (long)div_u64(l->sum_time, - l->count), - l->max_time); - else - len += sysfs_emit_at(buf, len, " age=%ld", l->min_time); - - if (l->min_pid != l->max_pid) - len += sysfs_emit_at(buf, len, " pid=%ld-%ld", - l->min_pid, l->max_pid); - else - len += sysfs_emit_at(buf, len, " pid=%ld", - l->min_pid); - - if (num_online_cpus() > 1 && - !cpumask_empty(to_cpumask(l->cpus))) - len += sysfs_emit_at(buf, len, " cpus=%*pbl", - cpumask_pr_args(to_cpumask(l->cpus))); - - if (nr_online_nodes > 1 && !nodes_empty(l->nodes)) - len += sysfs_emit_at(buf, len, " nodes=%*pbl", - nodemask_pr_args(&l->nodes)); - - len += sysfs_emit_at(buf, len, "\n"); - } - - free_loc_track(&t); - if (!t.count) - len += sysfs_emit_at(buf, len, "No data\n"); - - return len; -} +#endif /* CONFIG_DEBUG_FS */ #endif /* CONFIG_SLUB_DEBUG */ -#ifdef SLUB_RESILIENCY_TEST -static void __init resiliency_test(void) -{ - u8 *p; - int type = KMALLOC_NORMAL; - - BUILD_BUG_ON(KMALLOC_MIN_SIZE > 16 || KMALLOC_SHIFT_HIGH < 10); - - pr_err("SLUB resiliency testing\n"); - pr_err("-----------------------\n"); - pr_err("A. Corruption after allocation\n"); - - p = kzalloc(16, GFP_KERNEL); - p[16] = 0x12; - pr_err("\n1. kmalloc-16: Clobber Redzone/next pointer 0x12->0x%p\n\n", - p + 16); - - validate_slab_cache(kmalloc_caches[type][4]); - - /* Hmmm... The next two are dangerous */ - p = kzalloc(32, GFP_KERNEL); - p[32 + sizeof(void *)] = 0x34; - pr_err("\n2. kmalloc-32: Clobber next pointer/next slab 0x34 -> -0x%p\n", - p); - pr_err("If allocated object is overwritten then not detectable\n\n"); - - validate_slab_cache(kmalloc_caches[type][5]); - p = kzalloc(64, GFP_KERNEL); - p += 64 + (get_cycles() & 0xff) * sizeof(void *); - *p = 0x56; - pr_err("\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n", - p); - pr_err("If allocated object is overwritten then not detectable\n\n"); - validate_slab_cache(kmalloc_caches[type][6]); - - pr_err("\nB. Corruption after free\n"); - p = kzalloc(128, GFP_KERNEL); - kfree(p); - *p = 0x78; - pr_err("1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p); - validate_slab_cache(kmalloc_caches[type][7]); - - p = kzalloc(256, GFP_KERNEL); - kfree(p); - p[50] = 0x9a; - pr_err("\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n", p); - validate_slab_cache(kmalloc_caches[type][8]); - - p = kzalloc(512, GFP_KERNEL); - kfree(p); - p[512] = 0xab; - pr_err("\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p); - validate_slab_cache(kmalloc_caches[type][9]); -} -#else -#ifdef CONFIG_SYSFS -static void resiliency_test(void) {}; -#endif -#endif /* SLUB_RESILIENCY_TEST */ - #ifdef CONFIG_SYSFS enum slab_stat_type { SL_ALL, /* All slabs */ @@ -5366,21 +5290,6 @@ static ssize_t validate_store(struct kmem_cache *s, } SLAB_ATTR(validate); -static ssize_t alloc_calls_show(struct kmem_cache *s, char *buf) -{ - if (!(s->flags & SLAB_STORE_USER)) - return -ENOSYS; - return list_locations(s, buf, TRACK_ALLOC); -} -SLAB_ATTR_RO(alloc_calls); - -static ssize_t free_calls_show(struct kmem_cache *s, char *buf) -{ - if (!(s->flags & SLAB_STORE_USER)) - return -ENOSYS; - return list_locations(s, buf, TRACK_FREE); -} -SLAB_ATTR_RO(free_calls); #endif /* CONFIG_SLUB_DEBUG */ #ifdef CONFIG_FAILSLAB @@ -5544,8 +5453,6 @@ static struct attribute *slab_attrs[] = { &poison_attr.attr, &store_user_attr.attr, &validate_attr.attr, - &alloc_calls_attr.attr, - &free_calls_attr.attr, #endif #ifdef CONFIG_ZONE_DMA &cache_dma_attr.attr, @@ -5827,13 +5734,179 @@ static int __init slab_sysfs_init(void) } mutex_unlock(&slab_mutex); - resiliency_test(); return 0; } __initcall(slab_sysfs_init); #endif /* CONFIG_SYSFS */ +#if defined(CONFIG_SLUB_DEBUG) && defined(CONFIG_DEBUG_FS) +static int slab_debugfs_show(struct seq_file *seq, void *v) +{ + + struct location *l; + unsigned int idx = *(unsigned int *)v; + struct loc_track *t = seq->private; + + if (idx < t->count) { + l = &t->loc[idx]; + + seq_printf(seq, "%7ld ", l->count); + + if (l->addr) + seq_printf(seq, "%pS", (void *)l->addr); + else + seq_puts(seq, "<not-available>"); + + if (l->sum_time != l->min_time) { + seq_printf(seq, " age=%ld/%llu/%ld", + l->min_time, div_u64(l->sum_time, l->count), + l->max_time); + } else + seq_printf(seq, " age=%ld", l->min_time); + + if (l->min_pid != l->max_pid) + seq_printf(seq, " pid=%ld-%ld", l->min_pid, l->max_pid); + else + seq_printf(seq, " pid=%ld", + l->min_pid); + + if (num_online_cpus() > 1 && !cpumask_empty(to_cpumask(l->cpus))) + seq_printf(seq, " cpus=%*pbl", + cpumask_pr_args(to_cpumask(l->cpus))); + + if (nr_online_nodes > 1 && !nodes_empty(l->nodes)) + seq_printf(seq, " nodes=%*pbl", + nodemask_pr_args(&l->nodes)); + + seq_puts(seq, "\n"); + } + + if (!idx && !t->count) + seq_puts(seq, "No data\n"); + + return 0; +} + +static void slab_debugfs_stop(struct seq_file *seq, void *v) +{ +} + +static void *slab_debugfs_next(struct seq_file *seq, void *v, loff_t *ppos) +{ + struct loc_track *t = seq->private; + + v = ppos; + ++*ppos; + if (*ppos <= t->count) + return v; + + return NULL; +} + +static void *slab_debugfs_start(struct seq_file *seq, loff_t *ppos) +{ + return ppos; +} + +static const struct seq_operations slab_debugfs_sops = { + .start = slab_debugfs_start, + .next = slab_debugfs_next, + .stop = slab_debugfs_stop, + .show = slab_debugfs_show, +}; + +static int slab_debug_trace_open(struct inode *inode, struct file *filep) +{ + + struct kmem_cache_node *n; + enum track_item alloc; + int node; + struct loc_track *t = __seq_open_private(filep, &slab_debugfs_sops, + sizeof(struct loc_track)); + struct kmem_cache *s = file_inode(filep)->i_private; + + if (strcmp(filep->f_path.dentry->d_name.name, "alloc_traces") == 0) + alloc = TRACK_ALLOC; + else + alloc = TRACK_FREE; + + if (!alloc_loc_track(t, PAGE_SIZE / sizeof(struct location), GFP_KERNEL)) + return -ENOMEM; + + /* Push back cpu slabs */ + flush_all(s); + + for_each_kmem_cache_node(s, node, n) { + unsigned long flags; + struct page *page; + + if (!atomic_long_read(&n->nr_slabs)) + continue; + + spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->partial, slab_list) + process_slab(t, s, page, alloc); + list_for_each_entry(page, &n->full, slab_list) + process_slab(t, s, page, alloc); + spin_unlock_irqrestore(&n->list_lock, flags); + } + + return 0; +} + +static int slab_debug_trace_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct loc_track *t = seq->private; + + free_loc_track(t); + return seq_release_private(inode, file); +} + +static const struct file_operations slab_debugfs_fops = { + .open = slab_debug_trace_open, + .read = seq_read, + .llseek = seq_lseek, + .release = slab_debug_trace_release, +}; + +static void debugfs_slab_add(struct kmem_cache *s) +{ + struct dentry *slab_cache_dir; + + if (unlikely(!slab_debugfs_root)) + return; + + slab_cache_dir = debugfs_create_dir(s->name, slab_debugfs_root); + + debugfs_create_file("alloc_traces", 0400, + slab_cache_dir, s, &slab_debugfs_fops); + + debugfs_create_file("free_traces", 0400, + slab_cache_dir, s, &slab_debugfs_fops); +} + +void debugfs_slab_release(struct kmem_cache *s) +{ + debugfs_remove_recursive(debugfs_lookup(s->name, slab_debugfs_root)); +} + +static int __init slab_debugfs_init(void) +{ + struct kmem_cache *s; + + slab_debugfs_root = debugfs_create_dir("slab", NULL); + + list_for_each_entry(s, &slab_caches, list) + if (s->flags & SLAB_STORE_USER) + debugfs_slab_add(s); + + return 0; + +} +__initcall(slab_debugfs_init); +#endif /* * The /proc/slabinfo ABI */ diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 16183d85a7d5..bdce883f9286 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -27,8 +27,362 @@ #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <linux/sched.h> +#include <linux/pgtable.h> +#include <linux/bootmem_info.h> + #include <asm/dma.h> #include <asm/pgalloc.h> +#include <asm/tlbflush.h> + +/** + * struct vmemmap_remap_walk - walk vmemmap page table + * + * @remap_pte: called for each lowest-level entry (PTE). + * @nr_walked: the number of walked pte. + * @reuse_page: the page which is reused for the tail vmemmap pages. + * @reuse_addr: the virtual address of the @reuse_page page. + * @vmemmap_pages: the list head of the vmemmap pages that can be freed + * or is mapped from. + */ +struct vmemmap_remap_walk { + void (*remap_pte)(pte_t *pte, unsigned long addr, + struct vmemmap_remap_walk *walk); + unsigned long nr_walked; + struct page *reuse_page; + unsigned long reuse_addr; + struct list_head *vmemmap_pages; +}; + +static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start, + struct vmemmap_remap_walk *walk) +{ + pmd_t __pmd; + int i; + unsigned long addr = start; + struct page *page = pmd_page(*pmd); + pte_t *pgtable = pte_alloc_one_kernel(&init_mm); + + if (!pgtable) + return -ENOMEM; + + pmd_populate_kernel(&init_mm, &__pmd, pgtable); + + for (i = 0; i < PMD_SIZE / PAGE_SIZE; i++, addr += PAGE_SIZE) { + pte_t entry, *pte; + pgprot_t pgprot = PAGE_KERNEL; + + entry = mk_pte(page + i, pgprot); + pte = pte_offset_kernel(&__pmd, addr); + set_pte_at(&init_mm, addr, pte, entry); + } + + /* Make pte visible before pmd. See comment in __pte_alloc(). */ + smp_wmb(); + pmd_populate_kernel(&init_mm, pmd, pgtable); + + flush_tlb_kernel_range(start, start + PMD_SIZE); + + return 0; +} + +static void vmemmap_pte_range(pmd_t *pmd, unsigned long addr, + unsigned long end, + struct vmemmap_remap_walk *walk) +{ + pte_t *pte = pte_offset_kernel(pmd, addr); + + /* + * The reuse_page is found 'first' in table walk before we start + * remapping (which is calling @walk->remap_pte). + */ + if (!walk->reuse_page) { + walk->reuse_page = pte_page(*pte); + /* + * Because the reuse address is part of the range that we are + * walking, skip the reuse address range. + */ + addr += PAGE_SIZE; + pte++; + walk->nr_walked++; + } + + for (; addr != end; addr += PAGE_SIZE, pte++) { + walk->remap_pte(pte, addr, walk); + walk->nr_walked++; + } +} + +static int vmemmap_pmd_range(pud_t *pud, unsigned long addr, + unsigned long end, + struct vmemmap_remap_walk *walk) +{ + pmd_t *pmd; + unsigned long next; + + pmd = pmd_offset(pud, addr); + do { + if (pmd_leaf(*pmd)) { + int ret; + + ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK, walk); + if (ret) + return ret; + } + next = pmd_addr_end(addr, end); + vmemmap_pte_range(pmd, addr, next, walk); + } while (pmd++, addr = next, addr != end); + + return 0; +} + +static int vmemmap_pud_range(p4d_t *p4d, unsigned long addr, + unsigned long end, + struct vmemmap_remap_walk *walk) +{ + pud_t *pud; + unsigned long next; + + pud = pud_offset(p4d, addr); + do { + int ret; + + next = pud_addr_end(addr, end); + ret = vmemmap_pmd_range(pud, addr, next, walk); + if (ret) + return ret; + } while (pud++, addr = next, addr != end); + + return 0; +} + +static int vmemmap_p4d_range(pgd_t *pgd, unsigned long addr, + unsigned long end, + struct vmemmap_remap_walk *walk) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_offset(pgd, addr); + do { + int ret; + + next = p4d_addr_end(addr, end); + ret = vmemmap_pud_range(p4d, addr, next, walk); + if (ret) + return ret; + } while (p4d++, addr = next, addr != end); + + return 0; +} + +static int vmemmap_remap_range(unsigned long start, unsigned long end, + struct vmemmap_remap_walk *walk) +{ + unsigned long addr = start; + unsigned long next; + pgd_t *pgd; + + VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE)); + VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE)); + + pgd = pgd_offset_k(addr); + do { + int ret; + + next = pgd_addr_end(addr, end); + ret = vmemmap_p4d_range(pgd, addr, next, walk); + if (ret) + return ret; + } while (pgd++, addr = next, addr != end); + + /* + * We only change the mapping of the vmemmap virtual address range + * [@start + PAGE_SIZE, end), so we only need to flush the TLB which + * belongs to the range. + */ + flush_tlb_kernel_range(start + PAGE_SIZE, end); + + return 0; +} + +/* + * Free a vmemmap page. A vmemmap page can be allocated from the memblock + * allocator or buddy allocator. If the PG_reserved flag is set, it means + * that it allocated from the memblock allocator, just free it via the + * free_bootmem_page(). Otherwise, use __free_page(). + */ +static inline void free_vmemmap_page(struct page *page) +{ + if (PageReserved(page)) + free_bootmem_page(page); + else + __free_page(page); +} + +/* Free a list of the vmemmap pages */ +static void free_vmemmap_page_list(struct list_head *list) +{ + struct page *page, *next; + + list_for_each_entry_safe(page, next, list, lru) { + list_del(&page->lru); + free_vmemmap_page(page); + } +} + +static void vmemmap_remap_pte(pte_t *pte, unsigned long addr, + struct vmemmap_remap_walk *walk) +{ + /* + * Remap the tail pages as read-only to catch illegal write operation + * to the tail pages. + */ + pgprot_t pgprot = PAGE_KERNEL_RO; + pte_t entry = mk_pte(walk->reuse_page, pgprot); + struct page *page = pte_page(*pte); + + list_add_tail(&page->lru, walk->vmemmap_pages); + set_pte_at(&init_mm, addr, pte, entry); +} + +static void vmemmap_restore_pte(pte_t *pte, unsigned long addr, + struct vmemmap_remap_walk *walk) +{ + pgprot_t pgprot = PAGE_KERNEL; + struct page *page; + void *to; + + BUG_ON(pte_page(*pte) != walk->reuse_page); + + page = list_first_entry(walk->vmemmap_pages, struct page, lru); + list_del(&page->lru); + to = page_to_virt(page); + copy_page(to, (void *)walk->reuse_addr); + + set_pte_at(&init_mm, addr, pte, mk_pte(page, pgprot)); +} + +/** + * vmemmap_remap_free - remap the vmemmap virtual address range [@start, @end) + * to the page which @reuse is mapped to, then free vmemmap + * which the range are mapped to. + * @start: start address of the vmemmap virtual address range that we want + * to remap. + * @end: end address of the vmemmap virtual address range that we want to + * remap. + * @reuse: reuse address. + * + * Return: %0 on success, negative error code otherwise. + */ +int vmemmap_remap_free(unsigned long start, unsigned long end, + unsigned long reuse) +{ + int ret; + LIST_HEAD(vmemmap_pages); + struct vmemmap_remap_walk walk = { + .remap_pte = vmemmap_remap_pte, + .reuse_addr = reuse, + .vmemmap_pages = &vmemmap_pages, + }; + + /* + * In order to make remapping routine most efficient for the huge pages, + * the routine of vmemmap page table walking has the following rules + * (see more details from the vmemmap_pte_range()): + * + * - The range [@start, @end) and the range [@reuse, @reuse + PAGE_SIZE) + * should be continuous. + * - The @reuse address is part of the range [@reuse, @end) that we are + * walking which is passed to vmemmap_remap_range(). + * - The @reuse address is the first in the complete range. + * + * So we need to make sure that @start and @reuse meet the above rules. + */ + BUG_ON(start - reuse != PAGE_SIZE); + + mmap_write_lock(&init_mm); + ret = vmemmap_remap_range(reuse, end, &walk); + mmap_write_downgrade(&init_mm); + + if (ret && walk.nr_walked) { + end = reuse + walk.nr_walked * PAGE_SIZE; + /* + * vmemmap_pages contains pages from the previous + * vmemmap_remap_range call which failed. These + * are pages which were removed from the vmemmap. + * They will be restored in the following call. + */ + walk = (struct vmemmap_remap_walk) { + .remap_pte = vmemmap_restore_pte, + .reuse_addr = reuse, + .vmemmap_pages = &vmemmap_pages, + }; + + vmemmap_remap_range(reuse, end, &walk); + } + mmap_read_unlock(&init_mm); + + free_vmemmap_page_list(&vmemmap_pages); + + return ret; +} + +static int alloc_vmemmap_page_list(unsigned long start, unsigned long end, + gfp_t gfp_mask, struct list_head *list) +{ + unsigned long nr_pages = (end - start) >> PAGE_SHIFT; + int nid = page_to_nid((struct page *)start); + struct page *page, *next; + + while (nr_pages--) { + page = alloc_pages_node(nid, gfp_mask, 0); + if (!page) + goto out; + list_add_tail(&page->lru, list); + } + + return 0; +out: + list_for_each_entry_safe(page, next, list, lru) + __free_pages(page, 0); + return -ENOMEM; +} + +/** + * vmemmap_remap_alloc - remap the vmemmap virtual address range [@start, end) + * to the page which is from the @vmemmap_pages + * respectively. + * @start: start address of the vmemmap virtual address range that we want + * to remap. + * @end: end address of the vmemmap virtual address range that we want to + * remap. + * @reuse: reuse address. + * @gfp_mask: GFP flag for allocating vmemmap pages. + * + * Return: %0 on success, negative error code otherwise. + */ +int vmemmap_remap_alloc(unsigned long start, unsigned long end, + unsigned long reuse, gfp_t gfp_mask) +{ + LIST_HEAD(vmemmap_pages); + struct vmemmap_remap_walk walk = { + .remap_pte = vmemmap_restore_pte, + .reuse_addr = reuse, + .vmemmap_pages = &vmemmap_pages, + }; + + /* See the comment in the vmemmap_remap_free(). */ + BUG_ON(start - reuse != PAGE_SIZE); + + if (alloc_vmemmap_page_list(start, end, gfp_mask, &vmemmap_pages)) + return -ENOMEM; + + mmap_read_lock(&init_mm); + vmemmap_remap_range(reuse, end, &walk); + mmap_read_unlock(&init_mm); + + return 0; +} /* * Allocate a block of memory to be used to back the virtual memory map diff --git a/mm/sparse.c b/mm/sparse.c index b2ada9dc00cb..6326cdf36c4f 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -13,6 +13,7 @@ #include <linux/vmalloc.h> #include <linux/swap.h> #include <linux/swapops.h> +#include <linux/bootmem_info.h> #include "internal.h" #include <asm/dma.h> @@ -344,6 +345,15 @@ size_t mem_section_usage_size(void) return sizeof(struct mem_section_usage) + usemap_size(); } +static inline phys_addr_t pgdat_to_phys(struct pglist_data *pgdat) +{ +#ifndef CONFIG_NUMA + return __pa_symbol(pgdat); +#else + return __pa(pgdat); +#endif +} + #ifdef CONFIG_MEMORY_HOTREMOVE static struct mem_section_usage * __init sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, @@ -362,7 +372,7 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, * from the same section as the pgdat where possible to avoid * this problem. */ - goal = __pa(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT); + goal = pgdat_to_phys(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT); limit = goal + (1UL << PA_SECTION_SHIFT); nid = early_pfn_to_nid(goal >> PAGE_SHIFT); again: @@ -390,7 +400,7 @@ static void __init check_usemap_section_nr(int nid, } usemap_snr = pfn_to_section_nr(__pa(usage) >> PAGE_SHIFT); - pgdat_snr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT); + pgdat_snr = pfn_to_section_nr(pgdat_to_phys(pgdat) >> PAGE_SHIFT); if (usemap_snr == pgdat_snr) return; diff --git a/mm/swap.c b/mm/swap.c index dfb48cf9c2c9..19600430e536 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -95,7 +95,7 @@ static void __put_single_page(struct page *page) { __page_cache_release(page); mem_cgroup_uncharge(page); - free_unref_page(page); + free_unref_page(page, 0); } static void __put_compound_page(struct page *page) @@ -313,7 +313,7 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) void lru_note_cost_page(struct page *page) { - lru_note_cost(mem_cgroup_page_lruvec(page, page_pgdat(page)), + lru_note_cost(mem_cgroup_page_lruvec(page), page_is_file_lru(page), thp_nr_pages(page)); } @@ -554,7 +554,7 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec) } else { /* * The page's writeback ends up during pagevec - * We moves tha page into tail of inactive. + * We move that page into tail of inactive. */ add_page_to_lru_list_tail(page, lruvec); __count_vm_events(PGROTATED, nr_pages); diff --git a/mm/swap_slots.c b/mm/swap_slots.c index 6248d1030a9b..a66f3e0ec973 100644 --- a/mm/swap_slots.c +++ b/mm/swap_slots.c @@ -43,8 +43,6 @@ static DEFINE_MUTEX(swap_slots_cache_mutex); static DEFINE_MUTEX(swap_slots_cache_enable_mutex); static void __drain_swap_slots_cache(unsigned int type); -static void deactivate_swap_slots_cache(void); -static void reactivate_swap_slots_cache(void); #define use_swap_slot_cache (swap_slot_cache_active && swap_slot_cache_enabled) #define SLOTS_CACHE 0x1 diff --git a/mm/swap_state.c b/mm/swap_state.c index 272ea2108c9d..c56aa9ac050d 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -114,8 +114,6 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, SetPageSwapCache(page); do { - unsigned long nr_shadows = 0; - xas_lock_irq(&xas); xas_create_range(&xas); if (xas_error(&xas)) @@ -124,7 +122,6 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, VM_BUG_ON_PAGE(xas.xa_index != idx + i, page); old = xas_load(&xas); if (xa_is_value(old)) { - nr_shadows++; if (shadowp) *shadowp = old; } @@ -260,7 +257,6 @@ void clear_shadow_from_swap_cache(int type, unsigned long begin, void *old; for (;;) { - unsigned long nr_shadows = 0; swp_entry_t entry = swp_entry(type, curr); struct address_space *address_space = swap_address_space(entry); XA_STATE(xas, &address_space->i_pages, curr); @@ -270,7 +266,6 @@ void clear_shadow_from_swap_cache(int type, unsigned long begin, if (!xa_is_value(old)) continue; xas_store(&xas, NULL); - nr_shadows++; } xa_unlock_irq(&address_space->i_pages); @@ -291,7 +286,7 @@ void clear_shadow_from_swap_cache(int type, unsigned long begin, * try_to_free_swap() _with_ the lock. * - Marcelo */ -static inline void free_swap_cache(struct page *page) +void free_swap_cache(struct page *page) { if (PageSwapCache(page) && !page_mapped(page) && trylock_page(page)) { try_to_free_swap(page); @@ -698,7 +693,12 @@ int init_swap_address_space(unsigned int type, unsigned long nr_pages) void exit_swap_address_space(unsigned int type) { - kvfree(swapper_spaces[type]); + int i; + struct address_space *spaces = swapper_spaces[type]; + + for (i = 0; i < nr_swapper_spaces[type]; i++) + VM_WARN_ON_ONCE(!mapping_empty(&spaces[i])); + kvfree(spaces); nr_swapper_spaces[type] = 0; swapper_spaces[type] = NULL; } @@ -721,7 +721,6 @@ static void swap_ra_info(struct vm_fault *vmf, { struct vm_area_struct *vma = vmf->vma; unsigned long ra_val; - swp_entry_t entry; unsigned long faddr, pfn, fpfn; unsigned long start, end; pte_t *pte, *orig_pte; @@ -739,11 +738,6 @@ static void swap_ra_info(struct vm_fault *vmf, faddr = vmf->address; orig_pte = pte = pte_offset_map(vmf->pmd, faddr); - entry = pte_to_swp_entry(*pte); - if ((unlikely(non_swap_entry(entry)))) { - pte_unmap(orig_pte); - return; - } fpfn = PFN_DOWN(faddr); ra_val = GET_SWAP_RA_VAL(vma); diff --git a/mm/swapfile.c b/mm/swapfile.c index 149e77454e3c..1e07d1c776f2 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -39,6 +39,7 @@ #include <linux/export.h> #include <linux/swap_slots.h> #include <linux/sort.h> +#include <linux/completion.h> #include <asm/tlbflush.h> #include <linux/swapops.h> @@ -99,11 +100,10 @@ atomic_t nr_rotate_swap = ATOMIC_INIT(0); static struct swap_info_struct *swap_type_to_swap_info(int type) { - if (type >= READ_ONCE(nr_swapfiles)) + if (type >= MAX_SWAPFILES) return NULL; - smp_rmb(); /* Pairs with smp_wmb in alloc_swap_info. */ - return READ_ONCE(swap_info[type]); + return READ_ONCE(swap_info[type]); /* rcu_dereference() */ } static inline unsigned char swap_count(unsigned char ent) @@ -452,10 +452,10 @@ static void swap_cluster_schedule_discard(struct swap_info_struct *si, unsigned int idx) { /* - * If scan_swap_map() can't find a free cluster, it will check + * If scan_swap_map_slots() can't find a free cluster, it will check * si->swap_map directly. To make sure the discarding cluster isn't - * taken by scan_swap_map(), mark the swap entries bad (occupied). It - * will be cleared after discard + * taken by scan_swap_map_slots(), mark the swap entries bad (occupied). + * It will be cleared after discard */ memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); @@ -511,6 +511,14 @@ static void swap_discard_work(struct work_struct *work) spin_unlock(&si->lock); } +static void swap_users_ref_free(struct percpu_ref *ref) +{ + struct swap_info_struct *si; + + si = container_of(ref, struct swap_info_struct, users); + complete(&si->comp); +} + static void alloc_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info; @@ -580,7 +588,7 @@ static void dec_cluster_info_page(struct swap_info_struct *p, } /* - * It's possible scan_swap_map() uses a free cluster in the middle of free + * It's possible scan_swap_map_slots() uses a free cluster in the middle of free * cluster list. Avoiding such abuse to avoid list corruption. */ static bool @@ -1028,21 +1036,6 @@ static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx) swap_range_free(si, offset, SWAPFILE_CLUSTER); } -static unsigned long scan_swap_map(struct swap_info_struct *si, - unsigned char usage) -{ - swp_entry_t entry; - int n_ret; - - n_ret = scan_swap_map_slots(si, usage, 1, &entry); - - if (n_ret) - return swp_offset(entry); - else - return 0; - -} - int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size) { unsigned long size = swap_entry_size(entry_size); @@ -1105,14 +1098,14 @@ start_over: nextsi: /* * if we got here, it's likely that si was almost full before, - * and since scan_swap_map() can drop the si->lock, multiple - * callers probably all tried to get a page from the same si - * and it filled up before we could get one; or, the si filled - * up between us dropping swap_avail_lock and taking si->lock. - * Since we dropped the swap_avail_lock, the swap_avail_head - * list may have been modified; so if next is still in the - * swap_avail_head list then try it, otherwise start over - * if we have not gotten any slots. + * and since scan_swap_map_slots() can drop the si->lock, + * multiple callers probably all tried to get a page from the + * same si and it filled up before we could get one; or, the si + * filled up between us dropping swap_avail_lock and taking + * si->lock. Since we dropped the swap_avail_lock, the + * swap_avail_head list may have been modified; so if next is + * still in the swap_avail_head list then try it, otherwise + * start over if we have not gotten any slots. */ if (plist_node_empty(&next->avail_lists[node])) goto start_over; @@ -1128,30 +1121,6 @@ noswap: return n_ret; } -/* The only caller of this function is now suspend routine */ -swp_entry_t get_swap_page_of_type(int type) -{ - struct swap_info_struct *si = swap_type_to_swap_info(type); - pgoff_t offset; - - if (!si) - goto fail; - - spin_lock(&si->lock); - if (si->flags & SWP_WRITEOK) { - /* This is called for allocating swap entry, not cache */ - offset = scan_swap_map(si, 1); - if (offset) { - atomic_long_dec(&nr_swap_pages); - spin_unlock(&si->lock); - return swp_entry(type, offset); - } - } - spin_unlock(&si->lock); -fail: - return (swp_entry_t) {0}; -} - static struct swap_info_struct *__swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; @@ -1270,18 +1239,12 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * - * The entirety of the RCU read critical section must come before the - * return from or after the call to synchronize_rcu() in - * enable_swap_info() or swapoff(). So if "si->flags & SWP_VALID" is - * true, the si->map, si->cluster_info, etc. must be valid in the - * critical section. - * * Notice that swapoff or swapoff+swapon can still happen before the - * rcu_read_lock() in get_swap_device() or after the rcu_read_unlock() - * in put_swap_device() if there isn't any other way to prevent - * swapoff, such as page lock, page table lock, etc. The caller must - * be prepared for that. For example, the following situation is - * possible. + * percpu_ref_tryget_live() in get_swap_device() or after the + * percpu_ref_put() in put_swap_device() if there isn't any other way + * to prevent swapoff, such as page lock, page table lock, etc. The + * caller must be prepared for that. For example, the following + * situation is possible. * * CPU1 CPU2 * do_swap_page() @@ -1309,21 +1272,27 @@ struct swap_info_struct *get_swap_device(swp_entry_t entry) si = swp_swap_info(entry); if (!si) goto bad_nofile; - - rcu_read_lock(); - if (data_race(!(si->flags & SWP_VALID))) - goto unlock_out; + if (!percpu_ref_tryget_live(&si->users)) + goto out; + /* + * Guarantee the si->users are checked before accessing other + * fields of swap_info_struct. + * + * Paired with the spin_unlock() after setup_swap_info() in + * enable_swap_info(). + */ + smp_rmb(); offset = swp_offset(entry); if (offset >= si->max) - goto unlock_out; + goto put_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; -unlock_out: - rcu_read_unlock(); +put_out: + percpu_ref_put(&si->users); return NULL; } @@ -1803,6 +1772,24 @@ int free_swap_and_cache(swp_entry_t entry) } #ifdef CONFIG_HIBERNATION + +swp_entry_t get_swap_page_of_type(int type) +{ + struct swap_info_struct *si = swap_type_to_swap_info(type); + swp_entry_t entry = {0}; + + if (!si) + goto fail; + + /* This is called for allocating swap entry, not cache */ + spin_lock(&si->lock); + if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry)) + atomic_long_dec(&nr_swap_pages); + spin_unlock(&si->lock); +fail: + return entry; +} + /* * Find the swap type that corresponds to given device (if any). * @@ -1900,7 +1887,7 @@ unsigned int count_swap_pages(int type, int free) static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { - return pte_same(pte_swp_clear_soft_dirty(pte), swp_pte); + return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* @@ -2466,7 +2453,7 @@ static void setup_swap_info(struct swap_info_struct *p, int prio, static void _enable_swap_info(struct swap_info_struct *p) { - p->flags |= SWP_WRITEOK | SWP_VALID; + p->flags |= SWP_WRITEOK; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; @@ -2497,10 +2484,9 @@ static void enable_swap_info(struct swap_info_struct *p, int prio, spin_unlock(&p->lock); spin_unlock(&swap_lock); /* - * Guarantee swap_map, cluster_info, etc. fields are valid - * between get/put_swap_device() if SWP_VALID bit is set + * Finished initializing swap device, now it's safe to reference it. */ - synchronize_rcu(); + percpu_ref_resurrect(&p->users); spin_lock(&swap_lock); spin_lock(&p->lock); _enable_swap_info(p); @@ -2616,16 +2602,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) reenable_swap_slots_cache_unlock(); - spin_lock(&swap_lock); - spin_lock(&p->lock); - p->flags &= ~SWP_VALID; /* mark swap device as invalid */ - spin_unlock(&p->lock); - spin_unlock(&swap_lock); /* - * wait for swap operations protected by get/put_swap_device() - * to complete + * Wait for swap operations protected by get/put_swap_device() + * to complete. + * + * We need synchronize_rcu() here to protect the accessing to + * the swap cache data structure. */ + percpu_ref_kill(&p->users); synchronize_rcu(); + wait_for_completion(&p->comp); flush_work(&p->discard_work); @@ -2641,7 +2627,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_lock(&p->lock); drain_mmlist(); - /* wait for anyone still in scan_swap_map */ + /* wait for anyone still in scan_swap_map_slots */ p->highest_bit = 0; /* cuts scans short */ while (p->flags >= SWP_SCANNING) { spin_unlock(&p->lock); @@ -2857,6 +2843,12 @@ static struct swap_info_struct *alloc_swap_info(void) if (!p) return ERR_PTR(-ENOMEM); + if (percpu_ref_init(&p->users, swap_users_ref_free, + PERCPU_REF_INIT_DEAD, GFP_KERNEL)) { + kvfree(p); + return ERR_PTR(-ENOMEM); + } + spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) @@ -2864,19 +2856,18 @@ static struct swap_info_struct *alloc_swap_info(void) } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); + percpu_ref_exit(&p->users); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; - WRITE_ONCE(swap_info[type], p); /* - * Write swap_info[type] before nr_swapfiles, in case a - * racing procfs swap_start() or swap_next() is reading them. - * (We never shrink nr_swapfiles, we never free this entry.) + * Publish the swap_info_struct after initializing it. + * Note that kvzalloc() above zeroes all its fields. */ - smp_wmb(); - WRITE_ONCE(nr_swapfiles, nr_swapfiles + 1); + smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ + nr_swapfiles++; } else { defer = p; p = swap_info[type]; @@ -2891,9 +2882,13 @@ static struct swap_info_struct *alloc_swap_info(void) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); - kvfree(defer); + if (defer) { + percpu_ref_exit(&defer->users); + kvfree(defer); + } spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); + init_completion(&p->comp); return p; } @@ -2972,7 +2967,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p, return 0; } - /* swap partition endianess hack... */ + /* swap partition endianness hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); diff --git a/mm/truncate.c b/mm/truncate.c index 95af244b112a..234ddd879caa 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -167,13 +167,10 @@ void do_invalidatepage(struct page *page, unsigned int offset, * its lock, b) when a concurrent invalidate_mapping_pages got there first and * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. */ -static void -truncate_cleanup_page(struct address_space *mapping, struct page *page) +static void truncate_cleanup_page(struct page *page) { - if (page_mapped(page)) { - unsigned int nr = thp_nr_pages(page); - unmap_mapping_pages(mapping, page->index, nr, false); - } + if (page_mapped(page)) + unmap_mapping_page(page); if (page_has_private(page)) do_invalidatepage(page, 0, thp_size(page)); @@ -218,7 +215,7 @@ int truncate_inode_page(struct address_space *mapping, struct page *page) if (page->mapping != mapping) return -EIO; - truncate_cleanup_page(mapping, page); + truncate_cleanup_page(page); delete_from_page_cache(page); return 0; } @@ -325,7 +322,7 @@ void truncate_inode_pages_range(struct address_space *mapping, index = indices[pagevec_count(&pvec) - 1] + 1; truncate_exceptional_pvec_entries(mapping, &pvec, indices); for (i = 0; i < pagevec_count(&pvec); i++) - truncate_cleanup_page(mapping, pvec.pages[i]); + truncate_cleanup_page(pvec.pages[i]); delete_from_page_cache_batch(mapping, &pvec); for (i = 0; i < pagevec_count(&pvec); i++) unlock_page(pvec.pages[i]); @@ -639,6 +636,16 @@ int invalidate_inode_pages2_range(struct address_space *mapping, continue; } + if (!did_range_unmap && page_mapped(page)) { + /* + * If page is mapped, before taking its lock, + * zap the rest of the file in one hit. + */ + unmap_mapping_pages(mapping, index, + (1 + end - index), false); + did_range_unmap = 1; + } + lock_page(page); WARN_ON(page_to_index(page) != index); if (page->mapping != mapping) { @@ -646,23 +653,11 @@ int invalidate_inode_pages2_range(struct address_space *mapping, continue; } wait_on_page_writeback(page); - if (page_mapped(page)) { - if (!did_range_unmap) { - /* - * Zap the rest of the file in one hit. - */ - unmap_mapping_pages(mapping, index, - (1 + end - index), false); - did_range_unmap = 1; - } else { - /* - * Just zap this page - */ - unmap_mapping_pages(mapping, index, - 1, false); - } - } + + if (page_mapped(page)) + unmap_mapping_page(page); BUG_ON(page_mapped(page)); + ret2 = do_launder_page(mapping, page); if (ret2 == 0) { if (!invalidate_complete_page2(mapping, page)) diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index e14b3820c6a8..0e2132834bc7 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -48,6 +48,78 @@ struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm, return dst_vma; } +/* + * Install PTEs, to map dst_addr (within dst_vma) to page. + * + * This function handles both MCOPY_ATOMIC_NORMAL and _CONTINUE for both shmem + * and anon, and for both shared and private VMAs. + */ +int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, struct page *page, + bool newly_allocated, bool wp_copy) +{ + int ret; + pte_t _dst_pte, *dst_pte; + bool writable = dst_vma->vm_flags & VM_WRITE; + bool vm_shared = dst_vma->vm_flags & VM_SHARED; + bool page_in_cache = page->mapping; + spinlock_t *ptl; + struct inode *inode; + pgoff_t offset, max_off; + + _dst_pte = mk_pte(page, dst_vma->vm_page_prot); + if (page_in_cache && !vm_shared) + writable = false; + if (writable || !page_in_cache) + _dst_pte = pte_mkdirty(_dst_pte); + if (writable) { + if (wp_copy) + _dst_pte = pte_mkuffd_wp(_dst_pte); + else + _dst_pte = pte_mkwrite(_dst_pte); + } + + dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); + + if (vma_is_shmem(dst_vma)) { + /* serialize against truncate with the page table lock */ + inode = dst_vma->vm_file->f_inode; + offset = linear_page_index(dst_vma, dst_addr); + max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + ret = -EFAULT; + if (unlikely(offset >= max_off)) + goto out_unlock; + } + + ret = -EEXIST; + if (!pte_none(*dst_pte)) + goto out_unlock; + + if (page_in_cache) + page_add_file_rmap(page, false); + else + page_add_new_anon_rmap(page, dst_vma, dst_addr, false); + + /* + * Must happen after rmap, as mm_counter() checks mapping (via + * PageAnon()), which is set by __page_set_anon_rmap(). + */ + inc_mm_counter(dst_mm, mm_counter(page)); + + if (newly_allocated) + lru_cache_add_inactive_or_unevictable(page, dst_vma); + + set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); + + /* No need to invalidate - it was non-present before */ + update_mmu_cache(dst_vma, dst_addr, dst_pte); + ret = 0; +out_unlock: + pte_unmap_unlock(dst_pte, ptl); + return ret; +} + static int mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, @@ -56,13 +128,9 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, struct page **pagep, bool wp_copy) { - pte_t _dst_pte, *dst_pte; - spinlock_t *ptl; void *page_kaddr; int ret; struct page *page; - pgoff_t offset, max_off; - struct inode *inode; if (!*pagep) { ret = -ENOMEM; @@ -99,43 +167,12 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL)) goto out_release; - _dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot)); - if (dst_vma->vm_flags & VM_WRITE) { - if (wp_copy) - _dst_pte = pte_mkuffd_wp(_dst_pte); - else - _dst_pte = pte_mkwrite(_dst_pte); - } - - dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); - if (dst_vma->vm_file) { - /* the shmem MAP_PRIVATE case requires checking the i_size */ - inode = dst_vma->vm_file->f_inode; - offset = linear_page_index(dst_vma, dst_addr); - max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); - ret = -EFAULT; - if (unlikely(offset >= max_off)) - goto out_release_uncharge_unlock; - } - ret = -EEXIST; - if (!pte_none(*dst_pte)) - goto out_release_uncharge_unlock; - - inc_mm_counter(dst_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, dst_vma, dst_addr, false); - lru_cache_add_inactive_or_unevictable(page, dst_vma); - - set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); - - /* No need to invalidate - it was non-present before */ - update_mmu_cache(dst_vma, dst_addr, dst_pte); - - pte_unmap_unlock(dst_pte, ptl); - ret = 0; + ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, + page, true, wp_copy); + if (ret) + goto out_release; out: return ret; -out_release_uncharge_unlock: - pte_unmap_unlock(dst_pte, ptl); out_release: put_page(page); goto out; @@ -176,6 +213,41 @@ out_unlock: return ret; } +/* Handles UFFDIO_CONTINUE for all shmem VMAs (shared or private). */ +static int mcontinue_atomic_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + bool wp_copy) +{ + struct inode *inode = file_inode(dst_vma->vm_file); + pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); + struct page *page; + int ret; + + ret = shmem_getpage(inode, pgoff, &page, SGP_READ); + if (ret) + goto out; + if (!page) { + ret = -EFAULT; + goto out; + } + + ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, + page, false, wp_copy); + if (ret) + goto out_release; + + unlock_page(page); + ret = 0; +out: + return ret; +out_release: + unlock_page(page); + put_page(page); + goto out; +} + static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; @@ -209,7 +281,6 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, unsigned long len, enum mcopy_atomic_mode mode) { - int vm_alloc_shared = dst_vma->vm_flags & VM_SHARED; int vm_shared = dst_vma->vm_flags & VM_SHARED; ssize_t err; pte_t *dst_pte; @@ -308,7 +379,6 @@ retry: mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); - vm_alloc_shared = vm_shared; cond_resched(); @@ -346,54 +416,8 @@ retry: out_unlock: mmap_read_unlock(dst_mm); out: - if (page) { - /* - * We encountered an error and are about to free a newly - * allocated huge page. - * - * Reservation handling is very subtle, and is different for - * private and shared mappings. See the routine - * restore_reserve_on_error for details. Unfortunately, we - * can not call restore_reserve_on_error now as it would - * require holding mmap_lock. - * - * If a reservation for the page existed in the reservation - * map of a private mapping, the map was modified to indicate - * the reservation was consumed when the page was allocated. - * We clear the PagePrivate flag now so that the global - * reserve count will not be incremented in free_huge_page. - * The reservation map will still indicate the reservation - * was consumed and possibly prevent later page allocation. - * This is better than leaking a global reservation. If no - * reservation existed, it is still safe to clear PagePrivate - * as no adjustments to reservation counts were made during - * allocation. - * - * The reservation map for shared mappings indicates which - * pages have reservations. When a huge page is allocated - * for an address with a reservation, no change is made to - * the reserve map. In this case PagePrivate will be set - * to indicate that the global reservation count should be - * incremented when the page is freed. This is the desired - * behavior. However, when a huge page is allocated for an - * address without a reservation a reservation entry is added - * to the reservation map, and PagePrivate will not be set. - * When the page is freed, the global reserve count will NOT - * be incremented and it will appear as though we have leaked - * reserved page. In this case, set PagePrivate so that the - * global reserve count will be incremented to match the - * reservation map entry which was created. - * - * Note that vm_alloc_shared is based on the flags of the vma - * for which the page was originally allocated. dst_vma could - * be different or NULL on error. - */ - if (vm_alloc_shared) - SetPagePrivate(page); - else - ClearPagePrivate(page); + if (page) put_page(page); - } BUG_ON(copied < 0); BUG_ON(err > 0); BUG_ON(!copied && !err); @@ -415,11 +439,16 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, unsigned long dst_addr, unsigned long src_addr, struct page **page, - bool zeropage, + enum mcopy_atomic_mode mode, bool wp_copy) { ssize_t err; + if (mode == MCOPY_ATOMIC_CONTINUE) { + return mcontinue_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, + wp_copy); + } + /* * The normal page fault path for a shmem will invoke the * fault, fill the hole in the file and COW it right away. The @@ -431,7 +460,7 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, * and not in the radix tree. */ if (!(dst_vma->vm_flags & VM_SHARED)) { - if (!zeropage) + if (mode == MCOPY_ATOMIC_NORMAL) err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, src_addr, page, wp_copy); @@ -440,13 +469,10 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, dst_vma, dst_addr); } else { VM_WARN_ON_ONCE(wp_copy); - if (!zeropage) - err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd, - dst_vma, dst_addr, - src_addr, page); - else - err = shmem_mfill_zeropage_pte(dst_mm, dst_pmd, - dst_vma, dst_addr); + err = shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, + dst_addr, src_addr, + mode != MCOPY_ATOMIC_NORMAL, + page); } return err; @@ -467,7 +493,6 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm, long copied; struct page *page; bool wp_copy; - bool zeropage = (mcopy_mode == MCOPY_ATOMIC_ZEROPAGE); /* * Sanitize the command parameters: @@ -530,7 +555,7 @@ retry: if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; - if (mcopy_mode == MCOPY_ATOMIC_CONTINUE) + if (!vma_is_shmem(dst_vma) && mcopy_mode == MCOPY_ATOMIC_CONTINUE) goto out_unlock; /* @@ -578,7 +603,7 @@ retry: BUG_ON(pmd_trans_huge(*dst_pmd)); err = mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, - src_addr, &page, zeropage, wp_copy); + src_addr, &page, mcopy_mode, wp_copy); cond_resched(); if (unlikely(err == -ENOENT)) { diff --git a/mm/util.c b/mm/util.c index 0b6dd9d81da7..99c6cc77de9e 100644 --- a/mm/util.c +++ b/mm/util.c @@ -1010,3 +1010,43 @@ void mem_dump_obj(void *object) } EXPORT_SYMBOL_GPL(mem_dump_obj); #endif + +/* + * A driver might set a page logically offline -- PageOffline() -- and + * turn the page inaccessible in the hypervisor; after that, access to page + * content can be fatal. + * + * Some special PFN walkers -- i.e., /proc/kcore -- read content of random + * pages after checking PageOffline(); however, these PFN walkers can race + * with drivers that set PageOffline(). + * + * page_offline_freeze()/page_offline_thaw() allows for a subsystem to + * synchronize with such drivers, achieving that a page cannot be set + * PageOffline() while frozen. + * + * page_offline_begin()/page_offline_end() is used by drivers that care about + * such races when setting a page PageOffline(). + */ +static DECLARE_RWSEM(page_offline_rwsem); + +void page_offline_freeze(void) +{ + down_read(&page_offline_rwsem); +} + +void page_offline_thaw(void) +{ + up_read(&page_offline_rwsem); +} + +void page_offline_begin(void) +{ + down_write(&page_offline_rwsem); +} +EXPORT_SYMBOL(page_offline_begin); + +void page_offline_end(void) +{ + up_write(&page_offline_rwsem); +} +EXPORT_SYMBOL(page_offline_end); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index a13ac524f6ff..d5cd52805149 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -25,6 +25,7 @@ #include <linux/notifier.h> #include <linux/rbtree.h> #include <linux/xarray.h> +#include <linux/io.h> #include <linux/rcupdate.h> #include <linux/pfn.h> #include <linux/kmemleak.h> @@ -36,6 +37,7 @@ #include <linux/overflow.h> #include <linux/pgtable.h> #include <linux/uaccess.h> +#include <linux/hugetlb.h> #include <asm/tlbflush.h> #include <asm/shmparam.h> @@ -83,10 +85,11 @@ static void free_work(struct work_struct *w) /*** Page table manipulation functions ***/ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, - pgtbl_mod_mask *mask) + unsigned int max_page_shift, pgtbl_mod_mask *mask) { pte_t *pte; u64 pfn; + unsigned long size = PAGE_SIZE; pfn = phys_addr >> PAGE_SHIFT; pte = pte_alloc_kernel_track(pmd, addr, mask); @@ -94,9 +97,22 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, return -ENOMEM; do { BUG_ON(!pte_none(*pte)); + +#ifdef CONFIG_HUGETLB_PAGE + size = arch_vmap_pte_range_map_size(addr, end, pfn, max_page_shift); + if (size != PAGE_SIZE) { + pte_t entry = pfn_pte(pfn, prot); + + entry = pte_mkhuge(entry); + entry = arch_make_huge_pte(entry, ilog2(size), 0); + set_huge_pte_at(&init_mm, addr, pte, entry); + pfn += PFN_DOWN(size); + continue; + } +#endif set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot)); pfn++; - } while (pte++, addr += PAGE_SIZE, addr != end); + } while (pte += PFN_DOWN(size), addr += size, addr != end); *mask |= PGTBL_PTE_MODIFIED; return 0; } @@ -145,7 +161,7 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, continue; } - if (vmap_pte_range(pmd, addr, next, phys_addr, prot, mask)) + if (vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask)) return -ENOMEM; } while (pmd++, phys_addr += (next - addr), addr = next, addr != end); return 0; @@ -1592,6 +1608,7 @@ static DEFINE_MUTEX(vmap_purge_lock); /* for per-CPU blocks */ static void purge_fragmented_blocks_allcpus(void); +#ifdef CONFIG_X86_64 /* * called before a call to iounmap() if the caller wants vm_area_struct's * immediately freed. @@ -1600,6 +1617,7 @@ void set_iounmap_nonlazy(void) { atomic_long_set(&vmap_lazy_nr, lazy_max_pages()+1); } +#endif /* CONFIG_X86_64 */ /* * Purges all lazily-freed vmap areas. @@ -2344,15 +2362,16 @@ static void clear_vm_uninitialized_flag(struct vm_struct *vm) } static struct vm_struct *__get_vm_area_node(unsigned long size, - unsigned long align, unsigned long flags, unsigned long start, - unsigned long end, int node, gfp_t gfp_mask, const void *caller) + unsigned long align, unsigned long shift, unsigned long flags, + unsigned long start, unsigned long end, int node, + gfp_t gfp_mask, const void *caller) { struct vmap_area *va; struct vm_struct *area; unsigned long requested_size = size; BUG_ON(in_interrupt()); - size = PAGE_ALIGN(size); + size = ALIGN(size, 1ul << shift); if (unlikely(!size)) return NULL; @@ -2384,8 +2403,8 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, const void *caller) { - return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE, - GFP_KERNEL, caller); + return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, start, end, + NUMA_NO_NODE, GFP_KERNEL, caller); } /** @@ -2401,7 +2420,8 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, */ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) { - return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, + return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, + VMALLOC_START, VMALLOC_END, NUMA_NO_NODE, GFP_KERNEL, __builtin_return_address(0)); } @@ -2409,7 +2429,8 @@ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller) { - return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, + return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, + VMALLOC_START, VMALLOC_END, NUMA_NO_NODE, GFP_KERNEL, caller); } @@ -2564,6 +2585,7 @@ static void __vunmap(const void *addr, int deallocate_pages) BUG_ON(!page); __free_pages(page, page_order); + cond_resched(); } atomic_long_sub(area->nr_pages, &nr_vmalloc_pages); @@ -2755,6 +2777,54 @@ void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot) EXPORT_SYMBOL_GPL(vmap_pfn); #endif /* CONFIG_VMAP_PFN */ +static inline unsigned int +vm_area_alloc_pages(gfp_t gfp, int nid, + unsigned int order, unsigned long nr_pages, struct page **pages) +{ + unsigned int nr_allocated = 0; + + /* + * For order-0 pages we make use of bulk allocator, if + * the page array is partly or not at all populated due + * to fails, fallback to a single page allocator that is + * more permissive. + */ + if (!order) + nr_allocated = alloc_pages_bulk_array_node( + gfp, nid, nr_pages, pages); + else + /* + * Compound pages required for remap_vmalloc_page if + * high-order pages. + */ + gfp |= __GFP_COMP; + + /* High-order pages or fallback path if "bulk" fails. */ + while (nr_allocated < nr_pages) { + struct page *page; + int i; + + page = alloc_pages_node(nid, gfp, order); + if (unlikely(!page)) + break; + + /* + * Careful, we allocate and map page-order pages, but + * tracking is done per PAGE_SIZE page so as to keep the + * vm_struct APIs independent of the physical/mapped size. + */ + for (i = 0; i < (1U << order); i++) + pages[nr_allocated + i] = page + i; + + if (gfpflags_allow_blocking(gfp)) + cond_resched(); + + nr_allocated += 1U << order; + } + + return nr_allocated; +} + static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot, unsigned int page_shift, int node) @@ -2765,8 +2835,6 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, unsigned long array_size; unsigned int nr_small_pages = size >> PAGE_SHIFT; unsigned int page_order; - struct page **pages; - unsigned int i; array_size = (unsigned long)nr_small_pages * sizeof(struct page *); gfp_mask |= __GFP_NOWARN; @@ -2775,62 +2843,44 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, /* Please note that the recursion is strictly bounded. */ if (array_size > PAGE_SIZE) { - pages = __vmalloc_node(array_size, 1, nested_gfp, node, + area->pages = __vmalloc_node(array_size, 1, nested_gfp, node, area->caller); } else { - pages = kmalloc_node(array_size, nested_gfp, node); + area->pages = kmalloc_node(array_size, nested_gfp, node); } - if (!pages) { - free_vm_area(area); + if (!area->pages) { warn_alloc(gfp_mask, NULL, - "vmalloc size %lu allocation failure: " - "page array size %lu allocation failed", - nr_small_pages * PAGE_SIZE, array_size); + "vmalloc error: size %lu, failed to allocated page array size %lu", + nr_small_pages * PAGE_SIZE, array_size); + free_vm_area(area); return NULL; } - area->pages = pages; - area->nr_pages = nr_small_pages; set_vm_area_page_order(area, page_shift - PAGE_SHIFT); - page_order = vm_area_page_order(area); - /* - * Careful, we allocate and map page_order pages, but tracking is done - * per PAGE_SIZE page so as to keep the vm_struct APIs independent of - * the physical/mapped size. - */ - for (i = 0; i < area->nr_pages; i += 1U << page_order) { - struct page *page; - int p; - - /* Compound pages required for remap_vmalloc_page */ - page = alloc_pages_node(node, gfp_mask | __GFP_COMP, page_order); - if (unlikely(!page)) { - /* Successfully allocated i pages, free them in __vfree() */ - area->nr_pages = i; - atomic_long_add(area->nr_pages, &nr_vmalloc_pages); - warn_alloc(gfp_mask, NULL, - "vmalloc size %lu allocation failure: " - "page order %u allocation failed", - area->nr_pages * PAGE_SIZE, page_order); - goto fail; - } + area->nr_pages = vm_area_alloc_pages(gfp_mask, node, + page_order, nr_small_pages, area->pages); - for (p = 0; p < (1U << page_order); p++) - area->pages[i + p] = page + p; + atomic_long_add(area->nr_pages, &nr_vmalloc_pages); - if (gfpflags_allow_blocking(gfp_mask)) - cond_resched(); + /* + * If not enough pages were obtained to accomplish an + * allocation request, free them via __vfree() if any. + */ + if (area->nr_pages != nr_small_pages) { + warn_alloc(gfp_mask, NULL, + "vmalloc error: size %lu, page order %u, failed to allocate pages", + area->nr_pages * PAGE_SIZE, page_order); + goto fail; } - atomic_long_add(area->nr_pages, &nr_vmalloc_pages); - if (vmap_pages_range(addr, addr + size, prot, pages, page_shift) < 0) { + if (vmap_pages_range(addr, addr + size, prot, area->pages, + page_shift) < 0) { warn_alloc(gfp_mask, NULL, - "vmalloc size %lu allocation failure: " - "failed to map pages", - area->nr_pages * PAGE_SIZE); + "vmalloc error: size %lu, failed to map pages", + area->nr_pages * PAGE_SIZE); goto fail; } @@ -2875,13 +2925,12 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, if ((size >> PAGE_SHIFT) > totalram_pages()) { warn_alloc(gfp_mask, NULL, - "vmalloc size %lu allocation failure: " - "exceeds total pages", real_size); + "vmalloc error: size %lu, exceeds total pages", + real_size); return NULL; } - if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP) && - arch_vmap_pmd_supported(prot)) { + if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP)) { unsigned long size_per_node; /* @@ -2894,21 +2943,23 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, size_per_node = size; if (node == NUMA_NO_NODE) size_per_node /= num_online_nodes(); - if (size_per_node >= PMD_SIZE) { + if (arch_vmap_pmd_supported(prot) && size_per_node >= PMD_SIZE) shift = PMD_SHIFT; - align = max(real_align, 1UL << shift); - size = ALIGN(real_size, 1UL << shift); - } + else + shift = arch_vmap_pte_supported_shift(size_per_node); + + align = max(real_align, 1UL << shift); + size = ALIGN(real_size, 1UL << shift); } again: - size = PAGE_ALIGN(size); - area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED | - vm_flags, start, end, node, gfp_mask, caller); + area = __get_vm_area_node(real_size, align, shift, VM_ALLOC | + VM_UNINITIALIZED | vm_flags, start, end, node, + gfp_mask, caller); if (!area) { warn_alloc(gfp_mask, NULL, - "vmalloc size %lu allocation failure: " - "vm_struct allocation failed", real_size); + "vmalloc error: size %lu, vm_struct allocation failed", + real_size); goto fail; } @@ -2923,6 +2974,7 @@ again: */ clear_vm_uninitialized_flag(area); + size = PAGE_ALIGN(size); kmemleak_vmalloc(area, size, gfp_mask); return addr; @@ -2999,6 +3051,23 @@ void *vmalloc(unsigned long size) EXPORT_SYMBOL(vmalloc); /** + * vmalloc_no_huge - allocate virtually contiguous memory using small pages + * @size: allocation size + * + * Allocate enough non-huge pages to cover @size from the page level + * allocator and map them into contiguous kernel virtual space. + * + * Return: pointer to the allocated memory or %NULL on error + */ +void *vmalloc_no_huge(unsigned long size) +{ + return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, + GFP_KERNEL, PAGE_KERNEL, VM_NO_HUGE_VMAP, + NUMA_NO_NODE, __builtin_return_address(0)); +} +EXPORT_SYMBOL(vmalloc_no_huge); + +/** * vzalloc - allocate virtually contiguous memory with zero fill * @size: allocation size * diff --git a/mm/vmscan.c b/mm/vmscan.c index 5199b9696bab..4620df62f0ff 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1499,7 +1499,8 @@ static unsigned int shrink_page_list(struct list_head *page_list, if (unlikely(PageTransHuge(page))) flags |= TTU_SPLIT_HUGE_PMD; - if (!try_to_unmap(page, flags)) { + try_to_unmap(page, flags); + if (page_mapped(page)) { stat->nr_unmap_fail += nr_pages; if (!was_swapbacked && PageSwapBacked(page)) stat->nr_lazyfree_fail += nr_pages; @@ -1701,6 +1702,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone, unsigned int nr_reclaimed; struct page *page, *next; LIST_HEAD(clean_pages); + unsigned int noreclaim_flag; list_for_each_entry_safe(page, next, page_list, lru) { if (!PageHuge(page) && page_is_file_lru(page) && @@ -1711,8 +1713,17 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone, } } + /* + * We should be safe here since we are only dealing with file pages and + * we are not kswapd and therefore cannot write dirty file pages. But + * call memalloc_noreclaim_save() anyway, just in case these conditions + * change in the future. + */ + noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, &stat, true); + memalloc_noreclaim_restore(noreclaim_flag); + list_splice(&clean_pages, page_list); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)nr_reclaimed); @@ -1810,7 +1821,7 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec, } -/** +/* * Isolating page from the lruvec to fill in @dst list by nr_to_scan times. * * lruvec->lru_lock is heavily contended. Some of the functions that @@ -2015,8 +2026,8 @@ static int too_many_isolated(struct pglist_data *pgdat, int file, * * Returns the number of pages moved to the given lruvec. */ -static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec, - struct list_head *list) +static unsigned int move_pages_to_lru(struct lruvec *lruvec, + struct list_head *list) { int nr_pages, nr_moved = 0; LIST_HEAD(pages_to_free); @@ -2063,7 +2074,7 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec, * All pages were isolated from the same lruvec (and isolation * inhibits memcg migration). */ - VM_BUG_ON_PAGE(!lruvec_holds_page_lru_lock(page, lruvec), page); + VM_BUG_ON_PAGE(!page_matches_lruvec(page, lruvec), page); add_page_to_lru_list(page, lruvec); nr_pages = thp_nr_pages(page); nr_moved += nr_pages; @@ -2096,7 +2107,7 @@ static int current_may_throttle(void) * shrink_inactive_list() is a helper for shrink_node(). It returns the number * of reclaimed pages */ -static noinline_for_stack unsigned long +static unsigned long shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { @@ -2306,6 +2317,7 @@ unsigned long reclaim_pages(struct list_head *page_list) LIST_HEAD(node_page_list); struct reclaim_stat dummy_stat; struct page *page; + unsigned int noreclaim_flag; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .priority = DEF_PRIORITY, @@ -2314,6 +2326,8 @@ unsigned long reclaim_pages(struct list_head *page_list) .may_swap = 1, }; + noreclaim_flag = memalloc_noreclaim_save(); + while (!list_empty(page_list)) { page = lru_to_page(page_list); if (nid == NUMA_NO_NODE) { @@ -2350,6 +2364,8 @@ unsigned long reclaim_pages(struct list_head *page_list) } } + memalloc_noreclaim_restore(noreclaim_flag); + return nr_reclaimed; } @@ -3722,6 +3738,38 @@ static bool kswapd_shrink_node(pg_data_t *pgdat, return sc->nr_scanned >= sc->nr_to_reclaim; } +/* Page allocator PCP high watermark is lowered if reclaim is active. */ +static inline void +update_reclaim_active(pg_data_t *pgdat, int highest_zoneidx, bool active) +{ + int i; + struct zone *zone; + + for (i = 0; i <= highest_zoneidx; i++) { + zone = pgdat->node_zones + i; + + if (!managed_zone(zone)) + continue; + + if (active) + set_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); + else + clear_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); + } +} + +static inline void +set_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) +{ + update_reclaim_active(pgdat, highest_zoneidx, true); +} + +static inline void +clear_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) +{ + update_reclaim_active(pgdat, highest_zoneidx, false); +} + /* * For kswapd, balance_pgdat() will reclaim pages across a node from zones * that are eligible for use by the caller until at least one zone is @@ -3774,6 +3822,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) boosted = nr_boost_reclaim; restart: + set_reclaim_active(pgdat, highest_zoneidx); sc.priority = DEF_PRIORITY; do { unsigned long nr_reclaimed = sc.nr_reclaimed; @@ -3907,6 +3956,8 @@ restart: pgdat->kswapd_failures++; out: + clear_reclaim_active(pgdat, highest_zoneidx); + /* If reclaim was boosted, account for the reclaim done in this pass */ if (boosted) { unsigned long flags; diff --git a/mm/vmstat.c b/mm/vmstat.c index cccee36b289c..b0534e068166 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -31,8 +31,6 @@ #include "internal.h" -#define NUMA_STATS_THRESHOLD (U16_MAX - 2) - #ifdef CONFIG_NUMA int sysctl_vm_numa_stat = ENABLE_NUMA_STAT; @@ -41,11 +39,12 @@ static void zero_zone_numa_counters(struct zone *zone) { int item, cpu; - for (item = 0; item < NR_VM_NUMA_STAT_ITEMS; item++) { - atomic_long_set(&zone->vm_numa_stat[item], 0); - for_each_online_cpu(cpu) - per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item] + for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) { + atomic_long_set(&zone->vm_numa_event[item], 0); + for_each_online_cpu(cpu) { + per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_numa_event[item] = 0; + } } } @@ -63,8 +62,8 @@ static void zero_global_numa_counters(void) { int item; - for (item = 0; item < NR_VM_NUMA_STAT_ITEMS; item++) - atomic_long_set(&vm_numa_stat[item], 0); + for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) + atomic_long_set(&vm_numa_event[item], 0); } static void invalid_numa_statistics(void) @@ -161,10 +160,9 @@ void vm_events_fold_cpu(int cpu) * vm_stat contains the global counters */ atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp; -atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS] __cacheline_aligned_in_smp; atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS] __cacheline_aligned_in_smp; +atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS] __cacheline_aligned_in_smp; EXPORT_SYMBOL(vm_zone_stat); -EXPORT_SYMBOL(vm_numa_stat); EXPORT_SYMBOL(vm_node_stat); #ifdef CONFIG_SMP @@ -266,7 +264,7 @@ void refresh_zone_stat_thresholds(void) for_each_online_cpu(cpu) { int pgdat_threshold; - per_cpu_ptr(zone->pageset, cpu)->stat_threshold + per_cpu_ptr(zone->per_cpu_zonestats, cpu)->stat_threshold = threshold; /* Base nodestat threshold on the largest populated zone. */ @@ -303,7 +301,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, threshold = (*calculate_pressure)(zone); for_each_online_cpu(cpu) - per_cpu_ptr(zone->pageset, cpu)->stat_threshold + per_cpu_ptr(zone->per_cpu_zonestats, cpu)->stat_threshold = threshold; } } @@ -316,7 +314,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long delta) { - struct per_cpu_pageset __percpu *pcp = zone->pageset; + struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats; s8 __percpu *p = pcp->vm_stat_diff + item; long x; long t; @@ -389,7 +387,7 @@ EXPORT_SYMBOL(__mod_node_page_state); */ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { - struct per_cpu_pageset __percpu *pcp = zone->pageset; + struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats; s8 __percpu *p = pcp->vm_stat_diff + item; s8 v, t; @@ -435,7 +433,7 @@ EXPORT_SYMBOL(__inc_node_page_state); void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { - struct per_cpu_pageset __percpu *pcp = zone->pageset; + struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats; s8 __percpu *p = pcp->vm_stat_diff + item; s8 v, t; @@ -495,7 +493,7 @@ EXPORT_SYMBOL(__dec_node_page_state); static inline void mod_zone_state(struct zone *zone, enum zone_stat_item item, long delta, int overstep_mode) { - struct per_cpu_pageset __percpu *pcp = zone->pageset; + struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats; s8 __percpu *p = pcp->vm_stat_diff + item; long o, n, t, z; @@ -706,8 +704,7 @@ EXPORT_SYMBOL(dec_node_page_state); * Fold a differential into the global counters. * Returns the number of counters updated. */ -#ifdef CONFIG_NUMA -static int fold_diff(int *zone_diff, int *numa_diff, int *node_diff) +static int fold_diff(int *zone_diff, int *node_diff) { int i; int changes = 0; @@ -718,12 +715,6 @@ static int fold_diff(int *zone_diff, int *numa_diff, int *node_diff) changes++; } - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - if (numa_diff[i]) { - atomic_long_add(numa_diff[i], &vm_numa_stat[i]); - changes++; - } - for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) if (node_diff[i]) { atomic_long_add(node_diff[i], &vm_node_stat[i]); @@ -731,26 +722,34 @@ static int fold_diff(int *zone_diff, int *numa_diff, int *node_diff) } return changes; } -#else -static int fold_diff(int *zone_diff, int *node_diff) + +#ifdef CONFIG_NUMA +static void fold_vm_zone_numa_events(struct zone *zone) { - int i; - int changes = 0; + unsigned long zone_numa_events[NR_VM_NUMA_EVENT_ITEMS] = { 0, }; + int cpu; + enum numa_stat_item item; - for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - if (zone_diff[i]) { - atomic_long_add(zone_diff[i], &vm_zone_stat[i]); - changes++; - } + for_each_online_cpu(cpu) { + struct per_cpu_zonestat *pzstats; - for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) - if (node_diff[i]) { - atomic_long_add(node_diff[i], &vm_node_stat[i]); - changes++; + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); + for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) + zone_numa_events[item] += xchg(&pzstats->vm_numa_event[item], 0); } - return changes; + + for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) + zone_numa_event_add(zone_numa_events[item], zone, item); +} + +void fold_vm_numa_events(void) +{ + struct zone *zone; + + for_each_populated_zone(zone) + fold_vm_zone_numa_events(zone); } -#endif /* CONFIG_NUMA */ +#endif /* * Update the zone counters for the current cpu. @@ -774,41 +773,30 @@ static int refresh_cpu_vm_stats(bool do_pagesets) struct zone *zone; int i; int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; -#ifdef CONFIG_NUMA - int global_numa_diff[NR_VM_NUMA_STAT_ITEMS] = { 0, }; -#endif int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, }; int changes = 0; for_each_populated_zone(zone) { - struct per_cpu_pageset __percpu *p = zone->pageset; + struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; +#ifdef CONFIG_NUMA + struct per_cpu_pages __percpu *pcp = zone->per_cpu_pageset; +#endif for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { int v; - v = this_cpu_xchg(p->vm_stat_diff[i], 0); + v = this_cpu_xchg(pzstats->vm_stat_diff[i], 0); if (v) { atomic_long_add(v, &zone->vm_stat[i]); global_zone_diff[i] += v; #ifdef CONFIG_NUMA /* 3 seconds idle till flush */ - __this_cpu_write(p->expire, 3); + __this_cpu_write(pcp->expire, 3); #endif } } #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) { - int v; - - v = this_cpu_xchg(p->vm_numa_stat_diff[i], 0); - if (v) { - - atomic_long_add(v, &zone->vm_numa_stat[i]); - global_numa_diff[i] += v; - __this_cpu_write(p->expire, 3); - } - } if (do_pagesets) { cond_resched(); @@ -819,23 +807,23 @@ static int refresh_cpu_vm_stats(bool do_pagesets) * Check if there are pages remaining in this pageset * if not then there is nothing to expire. */ - if (!__this_cpu_read(p->expire) || - !__this_cpu_read(p->pcp.count)) + if (!__this_cpu_read(pcp->expire) || + !__this_cpu_read(pcp->count)) continue; /* * We never drain zones local to this processor. */ if (zone_to_nid(zone) == numa_node_id()) { - __this_cpu_write(p->expire, 0); + __this_cpu_write(pcp->expire, 0); continue; } - if (__this_cpu_dec_return(p->expire)) + if (__this_cpu_dec_return(pcp->expire)) continue; - if (__this_cpu_read(p->pcp.count)) { - drain_zone_pages(zone, this_cpu_ptr(&p->pcp)); + if (__this_cpu_read(pcp->count)) { + drain_zone_pages(zone, this_cpu_ptr(pcp)); changes++; } } @@ -856,12 +844,7 @@ static int refresh_cpu_vm_stats(bool do_pagesets) } } -#ifdef CONFIG_NUMA - changes += fold_diff(global_zone_diff, global_numa_diff, - global_node_diff); -#else changes += fold_diff(global_zone_diff, global_node_diff); -#endif return changes; } @@ -876,36 +859,33 @@ void cpu_vm_stats_fold(int cpu) struct zone *zone; int i; int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; -#ifdef CONFIG_NUMA - int global_numa_diff[NR_VM_NUMA_STAT_ITEMS] = { 0, }; -#endif int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, }; for_each_populated_zone(zone) { - struct per_cpu_pageset *p; + struct per_cpu_zonestat *pzstats; - p = per_cpu_ptr(zone->pageset, cpu); + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); - for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - if (p->vm_stat_diff[i]) { + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { + if (pzstats->vm_stat_diff[i]) { int v; - v = p->vm_stat_diff[i]; - p->vm_stat_diff[i] = 0; + v = pzstats->vm_stat_diff[i]; + pzstats->vm_stat_diff[i] = 0; atomic_long_add(v, &zone->vm_stat[i]); global_zone_diff[i] += v; } - + } #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - if (p->vm_numa_stat_diff[i]) { - int v; + for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) { + if (pzstats->vm_numa_event[i]) { + unsigned long v; - v = p->vm_numa_stat_diff[i]; - p->vm_numa_stat_diff[i] = 0; - atomic_long_add(v, &zone->vm_numa_stat[i]); - global_numa_diff[i] += v; + v = pzstats->vm_numa_event[i]; + pzstats->vm_numa_event[i] = 0; + zone_numa_event_add(v, zone, i); } + } #endif } @@ -925,58 +905,39 @@ void cpu_vm_stats_fold(int cpu) } } -#ifdef CONFIG_NUMA - fold_diff(global_zone_diff, global_numa_diff, global_node_diff); -#else fold_diff(global_zone_diff, global_node_diff); -#endif } /* * this is only called if !populated_zone(zone), which implies no other users of * pset->vm_stat_diff[] exist. */ -void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) +void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *pzstats) { + unsigned long v; int i; - for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - if (pset->vm_stat_diff[i]) { - int v = pset->vm_stat_diff[i]; - pset->vm_stat_diff[i] = 0; - atomic_long_add(v, &zone->vm_stat[i]); - atomic_long_add(v, &vm_zone_stat[i]); + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { + if (pzstats->vm_stat_diff[i]) { + v = pzstats->vm_stat_diff[i]; + pzstats->vm_stat_diff[i] = 0; + zone_page_state_add(v, zone, i); } + } #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - if (pset->vm_numa_stat_diff[i]) { - int v = pset->vm_numa_stat_diff[i]; - - pset->vm_numa_stat_diff[i] = 0; - atomic_long_add(v, &zone->vm_numa_stat[i]); - atomic_long_add(v, &vm_numa_stat[i]); + for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) { + if (pzstats->vm_numa_event[i]) { + v = pzstats->vm_numa_event[i]; + pzstats->vm_numa_event[i] = 0; + zone_numa_event_add(v, zone, i); } + } #endif } #endif #ifdef CONFIG_NUMA -void __inc_numa_state(struct zone *zone, - enum numa_stat_item item) -{ - struct per_cpu_pageset __percpu *pcp = zone->pageset; - u16 __percpu *p = pcp->vm_numa_stat_diff + item; - u16 v; - - v = __this_cpu_inc_return(*p); - - if (unlikely(v > NUMA_STATS_THRESHOLD)) { - zone_numa_state_add(v, zone, item); - __this_cpu_write(*p, 0); - } -} - /* * Determine the per node value of a stat item. This function * is called frequently in a NUMA machine, so try to be as @@ -995,19 +956,16 @@ unsigned long sum_zone_node_page_state(int node, return count; } -/* - * Determine the per node value of a numa stat item. To avoid deviation, - * the per cpu stat number in vm_numa_stat_diff[] is also included. - */ -unsigned long sum_zone_numa_state(int node, +/* Determine the per node value of a numa stat item. */ +unsigned long sum_zone_numa_event_state(int node, enum numa_stat_item item) { struct zone *zones = NODE_DATA(node)->node_zones; - int i; unsigned long count = 0; + int i; for (i = 0; i < MAX_NR_ZONES; i++) - count += zone_numa_state_snapshot(zones + i, item); + count += zone_numa_event_state(zones + i, item); return count; } @@ -1686,28 +1644,30 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, zone_page_state(zone, i)); #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) + for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) seq_printf(m, "\n %-12s %lu", numa_stat_name(i), - zone_numa_state_snapshot(zone, i)); + zone_numa_event_state(zone, i)); #endif seq_printf(m, "\n pagesets"); for_each_online_cpu(i) { - struct per_cpu_pageset *pageset; + struct per_cpu_pages *pcp; + struct per_cpu_zonestat __maybe_unused *pzstats; - pageset = per_cpu_ptr(zone->pageset, i); + pcp = per_cpu_ptr(zone->per_cpu_pageset, i); seq_printf(m, "\n cpu: %i" "\n count: %i" "\n high: %i" "\n batch: %i", i, - pageset->pcp.count, - pageset->pcp.high, - pageset->pcp.batch); + pcp->count, + pcp->high, + pcp->batch); #ifdef CONFIG_SMP + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, i); seq_printf(m, "\n vm stats threshold: %d", - pageset->stat_threshold); + pzstats->stat_threshold); #endif } seq_printf(m, @@ -1740,7 +1700,7 @@ static const struct seq_operations zoneinfo_op = { }; #define NR_VMSTAT_ITEMS (NR_VM_ZONE_STAT_ITEMS + \ - NR_VM_NUMA_STAT_ITEMS + \ + NR_VM_NUMA_EVENT_ITEMS + \ NR_VM_NODE_STAT_ITEMS + \ NR_VM_WRITEBACK_STAT_ITEMS + \ (IS_ENABLED(CONFIG_VM_EVENT_COUNTERS) ? \ @@ -1755,6 +1715,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) return NULL; BUILD_BUG_ON(ARRAY_SIZE(vmstat_text) < NR_VMSTAT_ITEMS); + fold_vm_numa_events(); v = kmalloc_array(NR_VMSTAT_ITEMS, sizeof(unsigned long), GFP_KERNEL); m->private = v; if (!v) @@ -1764,9 +1725,9 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) v += NR_VM_ZONE_STAT_ITEMS; #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - v[i] = global_numa_state(i); - v += NR_VM_NUMA_STAT_ITEMS; + for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) + v[i] = global_numa_event_state(i); + v += NR_VM_NUMA_EVENT_ITEMS; #endif for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { @@ -1927,19 +1888,16 @@ static bool need_update(int cpu) struct zone *zone; for_each_populated_zone(zone) { - struct per_cpu_pageset *p = per_cpu_ptr(zone->pageset, cpu); + struct per_cpu_zonestat *pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); struct per_cpu_nodestat *n; + /* * The fast way of checking if there are any vmstat diffs. */ - if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS * - sizeof(p->vm_stat_diff[0]))) - return true; -#ifdef CONFIG_NUMA - if (memchr_inv(p->vm_numa_stat_diff, 0, NR_VM_NUMA_STAT_ITEMS * - sizeof(p->vm_numa_stat_diff[0]))) + if (memchr_inv(pzstats->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS * + sizeof(pzstats->vm_stat_diff[0]))) return true; -#endif + if (last_pgdat == zone->zone_pgdat) continue; last_pgdat = zone->zone_pgdat; diff --git a/mm/workingset.c b/mm/workingset.c index b7cdeca5a76d..5ba3e42446fa 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -168,8 +168,10 @@ * refault distance will immediately activate the refaulting page. */ +#define WORKINGSET_SHIFT 1 #define EVICTION_SHIFT ((BITS_PER_LONG - BITS_PER_XA_VALUE) + \ - 1 + NODES_SHIFT + MEM_CGROUP_ID_SHIFT) + WORKINGSET_SHIFT + NODES_SHIFT + \ + MEM_CGROUP_ID_SHIFT) #define EVICTION_MASK (~0UL >> EVICTION_SHIFT) /* @@ -189,7 +191,7 @@ static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction, eviction &= EVICTION_MASK; eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; eviction = (eviction << NODES_SHIFT) | pgdat->node_id; - eviction = (eviction << 1) | workingset; + eviction = (eviction << WORKINGSET_SHIFT) | workingset; return xa_mk_value(eviction); } @@ -201,8 +203,8 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, int memcgid, nid; bool workingset; - workingset = entry & 1; - entry >>= 1; + workingset = entry & ((1UL << WORKINGSET_SHIFT) - 1); + entry >>= WORKINGSET_SHIFT; nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); @@ -408,7 +410,7 @@ void workingset_activation(struct page *page) memcg = page_memcg_rcu(page); if (!mem_cgroup_disabled() && !memcg) goto out; - lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); + lruvec = mem_cgroup_page_lruvec(page); workingset_age_nonresident(lruvec, thp_nr_pages(page)); out: rcu_read_unlock(); diff --git a/mm/z3fold.c b/mm/z3fold.c index 7fe7adaaad01..b3c0577b8095 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -62,7 +62,7 @@ #define ZHDR_SIZE_ALIGNED round_up(sizeof(struct z3fold_header), CHUNK_SIZE) #define ZHDR_CHUNKS (ZHDR_SIZE_ALIGNED >> CHUNK_SHIFT) #define TOTAL_CHUNKS (PAGE_SIZE >> CHUNK_SHIFT) -#define NCHUNKS ((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT) +#define NCHUNKS (TOTAL_CHUNKS - ZHDR_CHUNKS) #define BUDDY_MASK (0x3) #define BUDDY_SHIFT 2 @@ -144,6 +144,8 @@ struct z3fold_header { * @c_handle: cache for z3fold_buddy_slots allocation * @ops: pointer to a structure of user defined operations specified at * pool creation time. + * @zpool: zpool driver + * @zpool_ops: zpool operations structure with an evict callback * @compact_wq: workqueue for page layout background optimization * @release_wq: workqueue for safe page release * @work: work_struct for safe page release @@ -253,9 +255,8 @@ static inline void z3fold_page_unlock(struct z3fold_header *zhdr) spin_unlock(&zhdr->page_lock); } - -static inline struct z3fold_header *__get_z3fold_header(unsigned long handle, - bool lock) +/* return locked z3fold page if it's not headless */ +static inline struct z3fold_header *get_z3fold_header(unsigned long handle) { struct z3fold_buddy_slots *slots; struct z3fold_header *zhdr; @@ -269,13 +270,12 @@ static inline struct z3fold_header *__get_z3fold_header(unsigned long handle, read_lock(&slots->lock); addr = *(unsigned long *)handle; zhdr = (struct z3fold_header *)(addr & PAGE_MASK); - if (lock) - locked = z3fold_page_trylock(zhdr); + locked = z3fold_page_trylock(zhdr); read_unlock(&slots->lock); if (locked) break; cpu_relax(); - } while (lock); + } while (true); } else { zhdr = (struct z3fold_header *)(handle & PAGE_MASK); } @@ -283,18 +283,6 @@ static inline struct z3fold_header *__get_z3fold_header(unsigned long handle, return zhdr; } -/* Returns the z3fold page where a given handle is stored */ -static inline struct z3fold_header *handle_to_z3fold_header(unsigned long h) -{ - return __get_z3fold_header(h, false); -} - -/* return locked z3fold page if it's not headless */ -static inline struct z3fold_header *get_z3fold_header(unsigned long h) -{ - return __get_z3fold_header(h, true); -} - static inline void put_z3fold_header(struct z3fold_header *zhdr) { struct page *page = virt_to_page(zhdr); @@ -998,7 +986,8 @@ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp, goto out_c; spin_lock_init(&pool->lock); spin_lock_init(&pool->stale_lock); - pool->unbuddied = __alloc_percpu(sizeof(struct list_head)*NCHUNKS, 2); + pool->unbuddied = __alloc_percpu(sizeof(struct list_head) * NCHUNKS, + __alignof__(struct list_head)); if (!pool->unbuddied) goto out_pool; for_each_possible_cpu(cpu) { @@ -1059,6 +1048,7 @@ static void z3fold_destroy_pool(struct z3fold_pool *pool) destroy_workqueue(pool->compact_wq); destroy_workqueue(pool->release_wq); z3fold_unregister_migration(pool); + free_percpu(pool->unbuddied); kfree(pool); } @@ -1382,7 +1372,7 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) if (zhdr->foreign_handles || test_and_set_bit(PAGE_CLAIMED, &page->private)) { if (kref_put(&zhdr->refcount, - release_z3fold_page)) + release_z3fold_page_locked)) atomic64_dec(&pool->pages_nr); else z3fold_page_unlock(zhdr); @@ -1803,8 +1793,11 @@ static int __init init_z3fold(void) { int ret; - /* Make sure the z3fold header is not larger than the page size */ - BUILD_BUG_ON(ZHDR_SIZE_ALIGNED > PAGE_SIZE); + /* + * Make sure the z3fold header is not larger than the page size and + * there has remaining spaces for its buddy. + */ + BUILD_BUG_ON(ZHDR_SIZE_ALIGNED > PAGE_SIZE - CHUNK_SIZE); ret = z3fold_mount(); if (ret) return ret; diff --git a/mm/zbud.c b/mm/zbud.c index 7ec5f27a68b0..6348932430b8 100644 --- a/mm/zbud.c +++ b/mm/zbud.c @@ -51,7 +51,6 @@ #include <linux/preempt.h> #include <linux/slab.h> #include <linux/spinlock.h> -#include <linux/zbud.h> #include <linux/zpool.h> /***************** @@ -73,6 +72,12 @@ #define ZHDR_SIZE_ALIGNED CHUNK_SIZE #define NCHUNKS ((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT) +struct zbud_pool; + +struct zbud_ops { + int (*evict)(struct zbud_pool *pool, unsigned long handle); +}; + /** * struct zbud_pool - stores metadata for each zbud pool * @lock: protects all pool fields and first|last_chunk fields of any @@ -87,21 +92,27 @@ * @pages_nr: number of zbud pages in the pool. * @ops: pointer to a structure of user defined operations specified at * pool creation time. + * @zpool: zpool driver + * @zpool_ops: zpool operations structure with an evict callback * * This structure is allocated at pool creation time and maintains metadata * pertaining to a particular zbud pool. */ struct zbud_pool { spinlock_t lock; - struct list_head unbuddied[NCHUNKS]; - struct list_head buddied; + union { + /* + * Reuse unbuddied[0] as buddied on the ground that + * unbuddied[0] is unused. + */ + struct list_head buddied; + struct list_head unbuddied[NCHUNKS]; + }; struct list_head lru; u64 pages_nr; const struct zbud_ops *ops; -#ifdef CONFIG_ZPOOL struct zpool *zpool; const struct zpool_ops *zpool_ops; -#endif }; /* @@ -121,104 +132,6 @@ struct zbud_header { }; /***************** - * zpool - ****************/ - -#ifdef CONFIG_ZPOOL - -static int zbud_zpool_evict(struct zbud_pool *pool, unsigned long handle) -{ - if (pool->zpool && pool->zpool_ops && pool->zpool_ops->evict) - return pool->zpool_ops->evict(pool->zpool, handle); - else - return -ENOENT; -} - -static const struct zbud_ops zbud_zpool_ops = { - .evict = zbud_zpool_evict -}; - -static void *zbud_zpool_create(const char *name, gfp_t gfp, - const struct zpool_ops *zpool_ops, - struct zpool *zpool) -{ - struct zbud_pool *pool; - - pool = zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL); - if (pool) { - pool->zpool = zpool; - pool->zpool_ops = zpool_ops; - } - return pool; -} - -static void zbud_zpool_destroy(void *pool) -{ - zbud_destroy_pool(pool); -} - -static int zbud_zpool_malloc(void *pool, size_t size, gfp_t gfp, - unsigned long *handle) -{ - return zbud_alloc(pool, size, gfp, handle); -} -static void zbud_zpool_free(void *pool, unsigned long handle) -{ - zbud_free(pool, handle); -} - -static int zbud_zpool_shrink(void *pool, unsigned int pages, - unsigned int *reclaimed) -{ - unsigned int total = 0; - int ret = -EINVAL; - - while (total < pages) { - ret = zbud_reclaim_page(pool, 8); - if (ret < 0) - break; - total++; - } - - if (reclaimed) - *reclaimed = total; - - return ret; -} - -static void *zbud_zpool_map(void *pool, unsigned long handle, - enum zpool_mapmode mm) -{ - return zbud_map(pool, handle); -} -static void zbud_zpool_unmap(void *pool, unsigned long handle) -{ - zbud_unmap(pool, handle); -} - -static u64 zbud_zpool_total_size(void *pool) -{ - return zbud_get_pool_size(pool) * PAGE_SIZE; -} - -static struct zpool_driver zbud_zpool_driver = { - .type = "zbud", - .sleep_mapped = true, - .owner = THIS_MODULE, - .create = zbud_zpool_create, - .destroy = zbud_zpool_destroy, - .malloc = zbud_zpool_malloc, - .free = zbud_zpool_free, - .shrink = zbud_zpool_shrink, - .map = zbud_zpool_map, - .unmap = zbud_zpool_unmap, - .total_size = zbud_zpool_total_size, -}; - -MODULE_ALIAS("zpool-zbud"); -#endif /* CONFIG_ZPOOL */ - -/***************** * Helpers *****************/ /* Just to make the code easier to read */ @@ -304,7 +217,7 @@ static int num_free_chunks(struct zbud_header *zhdr) * Return: pointer to the new zbud pool or NULL if the metadata allocation * failed. */ -struct zbud_pool *zbud_create_pool(gfp_t gfp, const struct zbud_ops *ops) +static struct zbud_pool *zbud_create_pool(gfp_t gfp, const struct zbud_ops *ops) { struct zbud_pool *pool; int i; @@ -328,7 +241,7 @@ struct zbud_pool *zbud_create_pool(gfp_t gfp, const struct zbud_ops *ops) * * The pool should be emptied before this function is called. */ -void zbud_destroy_pool(struct zbud_pool *pool) +static void zbud_destroy_pool(struct zbud_pool *pool) { kfree(pool); } @@ -352,7 +265,7 @@ void zbud_destroy_pool(struct zbud_pool *pool) * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate * a new page. */ -int zbud_alloc(struct zbud_pool *pool, size_t size, gfp_t gfp, +static int zbud_alloc(struct zbud_pool *pool, size_t size, gfp_t gfp, unsigned long *handle) { int chunks, i, freechunks; @@ -427,7 +340,7 @@ found: * only sets the first|last_chunks to 0. The page is actually freed * once both buddies are evicted (see zbud_reclaim_page() below). */ -void zbud_free(struct zbud_pool *pool, unsigned long handle) +static void zbud_free(struct zbud_pool *pool, unsigned long handle) { struct zbud_header *zhdr; int freechunks; @@ -499,7 +412,7 @@ void zbud_free(struct zbud_pool *pool, unsigned long handle) * no pages to evict or an eviction handler is not registered, -EAGAIN if * the retry limit was hit. */ -int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries) +static int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries) { int i, ret, freechunks; struct zbud_header *zhdr; @@ -581,7 +494,7 @@ next: * * Returns: a pointer to the mapped allocation */ -void *zbud_map(struct zbud_pool *pool, unsigned long handle) +static void *zbud_map(struct zbud_pool *pool, unsigned long handle) { return (void *)(handle); } @@ -591,7 +504,7 @@ void *zbud_map(struct zbud_pool *pool, unsigned long handle) * @pool: pool in which the allocation resides * @handle: handle associated with the allocation to be unmapped */ -void zbud_unmap(struct zbud_pool *pool, unsigned long handle) +static void zbud_unmap(struct zbud_pool *pool, unsigned long handle) { } @@ -602,30 +515,120 @@ void zbud_unmap(struct zbud_pool *pool, unsigned long handle) * Returns: size in pages of the given pool. The pool lock need not be * taken to access pages_nr. */ -u64 zbud_get_pool_size(struct zbud_pool *pool) +static u64 zbud_get_pool_size(struct zbud_pool *pool) { return pool->pages_nr; } +/***************** + * zpool + ****************/ + +static int zbud_zpool_evict(struct zbud_pool *pool, unsigned long handle) +{ + if (pool->zpool && pool->zpool_ops && pool->zpool_ops->evict) + return pool->zpool_ops->evict(pool->zpool, handle); + else + return -ENOENT; +} + +static const struct zbud_ops zbud_zpool_ops = { + .evict = zbud_zpool_evict +}; + +static void *zbud_zpool_create(const char *name, gfp_t gfp, + const struct zpool_ops *zpool_ops, + struct zpool *zpool) +{ + struct zbud_pool *pool; + + pool = zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL); + if (pool) { + pool->zpool = zpool; + pool->zpool_ops = zpool_ops; + } + return pool; +} + +static void zbud_zpool_destroy(void *pool) +{ + zbud_destroy_pool(pool); +} + +static int zbud_zpool_malloc(void *pool, size_t size, gfp_t gfp, + unsigned long *handle) +{ + return zbud_alloc(pool, size, gfp, handle); +} +static void zbud_zpool_free(void *pool, unsigned long handle) +{ + zbud_free(pool, handle); +} + +static int zbud_zpool_shrink(void *pool, unsigned int pages, + unsigned int *reclaimed) +{ + unsigned int total = 0; + int ret = -EINVAL; + + while (total < pages) { + ret = zbud_reclaim_page(pool, 8); + if (ret < 0) + break; + total++; + } + + if (reclaimed) + *reclaimed = total; + + return ret; +} + +static void *zbud_zpool_map(void *pool, unsigned long handle, + enum zpool_mapmode mm) +{ + return zbud_map(pool, handle); +} +static void zbud_zpool_unmap(void *pool, unsigned long handle) +{ + zbud_unmap(pool, handle); +} + +static u64 zbud_zpool_total_size(void *pool) +{ + return zbud_get_pool_size(pool) * PAGE_SIZE; +} + +static struct zpool_driver zbud_zpool_driver = { + .type = "zbud", + .sleep_mapped = true, + .owner = THIS_MODULE, + .create = zbud_zpool_create, + .destroy = zbud_zpool_destroy, + .malloc = zbud_zpool_malloc, + .free = zbud_zpool_free, + .shrink = zbud_zpool_shrink, + .map = zbud_zpool_map, + .unmap = zbud_zpool_unmap, + .total_size = zbud_zpool_total_size, +}; + +MODULE_ALIAS("zpool-zbud"); + static int __init init_zbud(void) { /* Make sure the zbud header will fit in one chunk */ BUILD_BUG_ON(sizeof(struct zbud_header) > ZHDR_SIZE_ALIGNED); pr_info("loaded\n"); -#ifdef CONFIG_ZPOOL zpool_register_driver(&zbud_zpool_driver); -#endif return 0; } static void __exit exit_zbud(void) { -#ifdef CONFIG_ZPOOL zpool_unregister_driver(&zbud_zpool_driver); -#endif - pr_info("unloaded\n"); } diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 19b563bc6c48..68e8831068f4 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1471,7 +1471,6 @@ static void obj_free(struct size_class *class, unsigned long obj) unsigned int f_objidx; void *vaddr; - obj &= ~OBJ_ALLOCATED_TAG; obj_to_location(obj, &f_page, &f_objidx); f_offset = (class->size * f_objidx) & ~PAGE_MASK; zspage = get_zspage(f_page); @@ -2163,7 +2162,7 @@ static void async_free_zspage(struct work_struct *work) VM_BUG_ON(fullness != ZS_EMPTY); class = pool->size_class[class_idx]; spin_lock(&class->lock); - __free_zspage(pool, pool->size_class[class_idx], zspage); + __free_zspage(pool, class, zspage); spin_unlock(&class->lock); } }; diff --git a/mm/zswap.c b/mm/zswap.c index 20763267a219..7944e3e57e78 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -967,6 +967,13 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) spin_unlock(&tree->lock); BUG_ON(offset != entry->offset); + src = (u8 *)zhdr + sizeof(struct zswap_header); + if (!zpool_can_sleep_mapped(pool)) { + memcpy(tmp, src, entry->length); + src = tmp; + zpool_unmap_handle(pool, handle); + } + /* try to allocate swap cache page */ switch (zswap_get_swap_cache_page(swpentry, &page)) { case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */ @@ -982,17 +989,7 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) case ZSWAP_SWAPCACHE_NEW: /* page is locked */ /* decompress */ acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); - dlen = PAGE_SIZE; - src = (u8 *)zhdr + sizeof(struct zswap_header); - - if (!zpool_can_sleep_mapped(pool)) { - - memcpy(tmp, src, entry->length); - src = tmp; - - zpool_unmap_handle(pool, handle); - } mutex_lock(acomp_ctx->mutex); sg_init_one(&input, src, entry->length); @@ -1203,7 +1200,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, zswap_reject_alloc_fail++; goto put_dstmem; } - buf = zpool_map_handle(entry->pool->zpool, handle, ZPOOL_MM_RW); + buf = zpool_map_handle(entry->pool->zpool, handle, ZPOOL_MM_WO); memcpy(buf, &zhdr, hlen); memcpy(buf + hlen, dst, dlen); zpool_unmap_handle(entry->pool->zpool, handle); @@ -1427,18 +1424,11 @@ static int __init zswap_debugfs_init(void) return 0; } - -static void __exit zswap_debugfs_exit(void) -{ - debugfs_remove_recursive(zswap_debugfs_root); -} #else static int __init zswap_debugfs_init(void) { return 0; } - -static void __exit zswap_debugfs_exit(void) { } #endif /********************************* |