diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig.debug | 10 | ||||
| -rw-r--r-- | mm/Makefile | 2 | ||||
| -rw-r--r-- | mm/cma.c | 25 | ||||
| -rw-r--r-- | mm/debug-pagealloc.c | 45 | ||||
| -rw-r--r-- | mm/fadvise.c | 6 | ||||
| -rw-r--r-- | mm/filemap.c | 10 | ||||
| -rw-r--r-- | mm/filemap_xip.c | 23 | ||||
| -rw-r--r-- | mm/fremap.c | 4 | ||||
| -rw-r--r-- | mm/hugetlb.c | 26 | ||||
| -rw-r--r-- | mm/memblock.c | 43 | ||||
| -rw-r--r-- | mm/memcontrol.c | 180 | ||||
| -rw-r--r-- | mm/memory-failure.c | 15 | ||||
| -rw-r--r-- | mm/memory.c | 9 | ||||
| -rw-r--r-- | mm/migrate.c | 28 | ||||
| -rw-r--r-- | mm/mincore.c | 7 | ||||
| -rw-r--r-- | mm/mmap.c | 24 | ||||
| -rw-r--r-- | mm/mremap.c | 6 | ||||
| -rw-r--r-- | mm/nommu.c | 50 | ||||
| -rw-r--r-- | mm/oom_kill.c | 15 | ||||
| -rw-r--r-- | mm/page_alloc.c | 137 | ||||
| -rw-r--r-- | mm/page_ext.c | 403 | ||||
| -rw-r--r-- | mm/page_owner.c | 311 | ||||
| -rw-r--r-- | mm/rmap.c | 18 | ||||
| -rw-r--r-- | mm/slab.c | 4 | ||||
| -rw-r--r-- | mm/slub.c | 17 | ||||
| -rw-r--r-- | mm/vmacache.c | 2 | ||||
| -rw-r--r-- | mm/vmalloc.c | 4 | ||||
| -rw-r--r-- | mm/vmscan.c | 216 | ||||
| -rw-r--r-- | mm/vmstat.c | 102 | ||||
| -rw-r--r-- | mm/zbud.c | 2 | ||||
| -rw-r--r-- | mm/zsmalloc.c | 180 | ||||
| -rw-r--r-- | mm/zswap.c | 9 |
32 files changed, 1409 insertions, 524 deletions
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index 4b24432..56badfc 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -1,8 +1,18 @@ +config PAGE_EXTENSION + bool "Extend memmap on extra space for more information on page" + ---help--- + Extend memmap on extra space for more information on page. This + could be used for debugging features that need to insert extra + field for every page. This extension enables us to save memory + by not allocating this extra memory according to boottime + configuration. + config DEBUG_PAGEALLOC bool "Debug page memory allocations" depends on DEBUG_KERNEL depends on !HIBERNATION || ARCH_SUPPORTS_DEBUG_PAGEALLOC && !PPC && !SPARC depends on !KMEMCHECK + select PAGE_EXTENSION select PAGE_POISONING if !ARCH_SUPPORTS_DEBUG_PAGEALLOC select PAGE_GUARD if ARCH_SUPPORTS_DEBUG_PAGEALLOC ---help--- diff --git a/mm/Makefile b/mm/Makefile index b3c6ce9..4bf586e 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -63,6 +63,7 @@ obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o +obj-$(CONFIG_PAGE_OWNER) += page_owner.o obj-$(CONFIG_CLEANCACHE) += cleancache.o obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o obj-$(CONFIG_ZPOOL) += zpool.o @@ -71,3 +72,4 @@ obj-$(CONFIG_ZSMALLOC) += zsmalloc.o obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o obj-$(CONFIG_CMA) += cma.o obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o +obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o @@ -33,6 +33,7 @@ #include <linux/log2.h> #include <linux/cma.h> #include <linux/highmem.h> +#include <linux/io.h> struct cma { unsigned long base_pfn; @@ -63,6 +64,17 @@ static unsigned long cma_bitmap_aligned_mask(struct cma *cma, int align_order) return (1UL << (align_order - cma->order_per_bit)) - 1; } +static unsigned long cma_bitmap_aligned_offset(struct cma *cma, int align_order) +{ + unsigned int alignment; + + if (align_order <= cma->order_per_bit) + return 0; + alignment = 1UL << (align_order - cma->order_per_bit); + return ALIGN(cma->base_pfn, alignment) - + (cma->base_pfn >> cma->order_per_bit); +} + static unsigned long cma_bitmap_maxno(struct cma *cma) { return cma->count >> cma->order_per_bit; @@ -313,6 +325,11 @@ int __init cma_declare_contiguous(phys_addr_t base, } } + /* + * kmemleak scans/reads tracked objects for pointers to other + * objects but this address isn't mapped and accessible + */ + kmemleak_ignore(phys_to_virt(addr)); base = addr; } @@ -340,7 +357,7 @@ err: */ struct page *cma_alloc(struct cma *cma, int count, unsigned int align) { - unsigned long mask, pfn, start = 0; + unsigned long mask, offset, pfn, start = 0; unsigned long bitmap_maxno, bitmap_no, bitmap_count; struct page *page = NULL; int ret; @@ -355,13 +372,15 @@ struct page *cma_alloc(struct cma *cma, int count, unsigned int align) return NULL; mask = cma_bitmap_aligned_mask(cma, align); + offset = cma_bitmap_aligned_offset(cma, align); bitmap_maxno = cma_bitmap_maxno(cma); bitmap_count = cma_bitmap_pages_to_bits(cma, count); for (;;) { mutex_lock(&cma->lock); - bitmap_no = bitmap_find_next_zero_area(cma->bitmap, - bitmap_maxno, start, bitmap_count, mask); + bitmap_no = bitmap_find_next_zero_area_off(cma->bitmap, + bitmap_maxno, start, bitmap_count, mask, + offset); if (bitmap_no >= bitmap_maxno) { mutex_unlock(&cma->lock); break; diff --git a/mm/debug-pagealloc.c b/mm/debug-pagealloc.c index 789ff70..5bf5906 100644 --- a/mm/debug-pagealloc.c +++ b/mm/debug-pagealloc.c @@ -2,23 +2,55 @@ #include <linux/string.h> #include <linux/mm.h> #include <linux/highmem.h> -#include <linux/page-debug-flags.h> +#include <linux/page_ext.h> #include <linux/poison.h> #include <linux/ratelimit.h> +static bool page_poisoning_enabled __read_mostly; + +static bool need_page_poisoning(void) +{ + if (!debug_pagealloc_enabled()) + return false; + + return true; +} + +static void init_page_poisoning(void) +{ + if (!debug_pagealloc_enabled()) + return; + + page_poisoning_enabled = true; +} + +struct page_ext_operations page_poisoning_ops = { + .need = need_page_poisoning, + .init = init_page_poisoning, +}; + static inline void set_page_poison(struct page *page) { - __set_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags); + struct page_ext *page_ext; + + page_ext = lookup_page_ext(page); + __set_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags); } static inline void clear_page_poison(struct page *page) { - __clear_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags); + struct page_ext *page_ext; + + page_ext = lookup_page_ext(page); + __clear_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags); } static inline bool page_poison(struct page *page) { - return test_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags); + struct page_ext *page_ext; + + page_ext = lookup_page_ext(page); + return test_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags); } static void poison_page(struct page *page) @@ -93,8 +125,11 @@ static void unpoison_pages(struct page *page, int n) unpoison_page(page + i); } -void kernel_map_pages(struct page *page, int numpages, int enable) +void __kernel_map_pages(struct page *page, int numpages, int enable) { + if (!page_poisoning_enabled) + return; + if (enable) unpoison_pages(page, numpages); else diff --git a/mm/fadvise.c b/mm/fadvise.c index 3bcfd81d..2ad7adf 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -117,7 +117,11 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) __filemap_fdatawrite_range(mapping, offset, endbyte, WB_SYNC_NONE); - /* First and last FULL page! */ + /* + * First and last FULL page! Partial pages are deliberately + * preserved on the expectation that it is better to preserve + * needed memory than to discard unneeded memory. + */ start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT; end_index = (endbyte >> PAGE_CACHE_SHIFT); diff --git a/mm/filemap.c b/mm/filemap.c index 14b4642..e8905bc 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -62,16 +62,16 @@ /* * Lock ordering: * - * ->i_mmap_mutex (truncate_pagecache) + * ->i_mmap_rwsem (truncate_pagecache) * ->private_lock (__free_pte->__set_page_dirty_buffers) * ->swap_lock (exclusive_swap_page, others) * ->mapping->tree_lock * * ->i_mutex - * ->i_mmap_mutex (truncate->unmap_mapping_range) + * ->i_mmap_rwsem (truncate->unmap_mapping_range) * * ->mmap_sem - * ->i_mmap_mutex + * ->i_mmap_rwsem * ->page_table_lock or pte_lock (various, mainly in memory.c) * ->mapping->tree_lock (arch-dependent flush_dcache_mmap_lock) * @@ -85,7 +85,7 @@ * sb_lock (fs/fs-writeback.c) * ->mapping->tree_lock (__sync_single_inode) * - * ->i_mmap_mutex + * ->i_mmap_rwsem * ->anon_vma.lock (vma_adjust) * * ->anon_vma.lock @@ -105,7 +105,7 @@ * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->__set_page_dirty_buffers) * - * ->i_mmap_mutex + * ->i_mmap_rwsem * ->tasklist_lock (memory_failure, collect_procs_ao) */ diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index d8d9fe3..0d105ae 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -155,22 +155,14 @@ xip_file_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) EXPORT_SYMBOL_GPL(xip_file_read); /* - * __xip_unmap is invoked from xip_unmap and - * xip_write + * __xip_unmap is invoked from xip_unmap and xip_write * * This function walks all vmas of the address_space and unmaps the * __xip_sparse_page when found at pgoff. */ -static void -__xip_unmap (struct address_space * mapping, - unsigned long pgoff) +static void __xip_unmap(struct address_space * mapping, unsigned long pgoff) { struct vm_area_struct *vma; - struct mm_struct *mm; - unsigned long address; - pte_t *pte; - pte_t pteval; - spinlock_t *ptl; struct page *page; unsigned count; int locked = 0; @@ -182,11 +174,14 @@ __xip_unmap (struct address_space * mapping, return; retry: - mutex_lock(&mapping->i_mmap_mutex); + i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { - mm = vma->vm_mm; - address = vma->vm_start + + pte_t *pte, pteval; + spinlock_t *ptl; + struct mm_struct *mm = vma->vm_mm; + unsigned long address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + BUG_ON(address < vma->vm_start || address >= vma->vm_end); pte = page_check_address(page, mm, address, &ptl, 1); if (pte) { @@ -202,7 +197,7 @@ retry: page_cache_release(page); } } - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_read(mapping); if (locked) { mutex_unlock(&xip_sparse_mutex); diff --git a/mm/fremap.c b/mm/fremap.c index 72b8fa3..11ef7ec 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -238,13 +238,13 @@ get_write_lock: } goto out_freed; } - mutex_lock(&mapping->i_mmap_mutex); + i_mmap_lock_write(mapping); flush_dcache_mmap_lock(mapping); vma->vm_flags |= VM_NONLINEAR; vma_interval_tree_remove(vma, &mapping->i_mmap); vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear); flush_dcache_mmap_unlock(mapping); - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_write(mapping); } if (vma->vm_flags & VM_LOCKED) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 919b86a..47f6070 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1457,7 +1457,7 @@ int __weak alloc_bootmem_huge_page(struct hstate *h) return 0; found: - BUG_ON((unsigned long)virt_to_phys(m) & (huge_page_size(h) - 1)); + BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h))); /* Put them into a private list first because mem_map is not up yet */ list_add(&m->list, &huge_boot_pages); m->hstate = h; @@ -2083,7 +2083,7 @@ static void hugetlb_register_node(struct node *node) * devices of nodes that have memory. All on-line nodes should have * registered their associated device by this time. */ -static void hugetlb_register_all_nodes(void) +static void __init hugetlb_register_all_nodes(void) { int nid; @@ -2726,9 +2726,9 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb, * on its way out. We're lucky that the flag has such an appropriate * name, and can in fact be safely cleared here. We could clear it * before the __unmap_hugepage_range above, but all that's necessary - * is to clear it before releasing the i_mmap_mutex. This works + * is to clear it before releasing the i_mmap_rwsem. This works * because in the context this is called, the VMA is about to be - * destroyed and the i_mmap_mutex is held. + * destroyed and the i_mmap_rwsem is held. */ vma->vm_flags &= ~VM_MAYSHARE; } @@ -2774,7 +2774,7 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, * this mapping should be shared between all the VMAs, * __unmap_hugepage_range() is called as the lock is already held */ - mutex_lock(&mapping->i_mmap_mutex); + i_mmap_lock_write(mapping); vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) { /* Do not unmap the current VMA */ if (iter_vma == vma) @@ -2791,7 +2791,7 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, unmap_hugepage_range(iter_vma, address, address + huge_page_size(h), page); } - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_write(mapping); } /* @@ -3348,7 +3348,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, flush_cache_range(vma, address, end); mmu_notifier_invalidate_range_start(mm, start, end); - mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex); + i_mmap_lock_write(vma->vm_file->f_mapping); for (; address < end; address += huge_page_size(h)) { spinlock_t *ptl; ptep = huge_pte_offset(mm, address); @@ -3370,13 +3370,13 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, spin_unlock(ptl); } /* - * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare + * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare * may have cleared our pud entry and done put_page on the page table: - * once we release i_mmap_mutex, another task can do the final put_page + * once we release i_mmap_rwsem, another task can do the final put_page * and that page table be reused and filled with junk. */ flush_tlb_range(vma, start, end); - mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); + i_mmap_unlock_write(vma->vm_file->f_mapping); mmu_notifier_invalidate_range_end(mm, start, end); return pages << h->order; @@ -3525,7 +3525,7 @@ static int vma_shareable(struct vm_area_struct *vma, unsigned long addr) * and returns the corresponding pte. While this is not necessary for the * !shared pmd case because we can allocate the pmd later as well, it makes the * code much cleaner. pmd allocation is essential for the shared case because - * pud has to be populated inside the same i_mmap_mutex section - otherwise + * pud has to be populated inside the same i_mmap_rwsem section - otherwise * racing tasks could either miss the sharing (see huge_pte_offset) or select a * bad pmd for sharing. */ @@ -3544,7 +3544,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) if (!vma_shareable(vma, addr)) return (pte_t *)pmd_alloc(mm, pud, addr); - mutex_lock(&mapping->i_mmap_mutex); + i_mmap_lock_write(mapping); vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { if (svma == vma) continue; @@ -3572,7 +3572,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) spin_unlock(ptl); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_write(mapping); return pte; } diff --git a/mm/memblock.c b/mm/memblock.c index 6ecb0d9..252b77b 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -715,16 +715,13 @@ int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) } /** - * memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG. - * @base: the base phys addr of the region - * @size: the size of the region * - * This function isolates region [@base, @base + @size), and mark it with flag - * MEMBLOCK_HOTPLUG. + * This function isolates region [@base, @base + @size), and sets/clears flag * * Return 0 on succees, -errno on failure. */ -int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) +static int __init_memblock memblock_setclr_flag(phys_addr_t base, + phys_addr_t size, int set, int flag) { struct memblock_type *type = &memblock.memory; int i, ret, start_rgn, end_rgn; @@ -734,37 +731,37 @@ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) return ret; for (i = start_rgn; i < end_rgn; i++) - memblock_set_region_flags(&type->regions[i], MEMBLOCK_HOTPLUG); + if (set) + memblock_set_region_flags(&type->regions[i], flag); + else + memblock_clear_region_flags(&type->regions[i], flag); memblock_merge_regions(type); return 0; } /** - * memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region. + * memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG. * @base: the base phys addr of the region * @size: the size of the region * - * This function isolates region [@base, @base + @size), and clear flag - * MEMBLOCK_HOTPLUG for the isolated regions. + * Return 0 on succees, -errno on failure. + */ +int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) +{ + return memblock_setclr_flag(base, size, 1, MEMBLOCK_HOTPLUG); +} + +/** + * memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region. + * @base: the base phys addr of the region + * @size: the size of the region * * Return 0 on succees, -errno on failure. */ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) { - struct memblock_type *type = &memblock.memory; - int i, ret, start_rgn, end_rgn; - - ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); - if (ret) - return ret; - - for (i = start_rgn; i < end_rgn; i++) - memblock_clear_region_flags(&type->regions[i], - MEMBLOCK_HOTPLUG); - - memblock_merge_regions(type); - return 0; + return memblock_setclr_flag(base, size, 0, MEMBLOCK_HOTPLUG); } /** diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 85df503..ef91e85 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -296,7 +296,6 @@ struct mem_cgroup { * Should the accounting and control be hierarchical, per subtree? */ bool use_hierarchy; - unsigned long kmem_account_flags; /* See KMEM_ACCOUNTED_*, below */ bool oom_lock; atomic_t under_oom; @@ -366,22 +365,11 @@ struct mem_cgroup { /* WARNING: nodeinfo must be the last member here */ }; -/* internal only representation about the status of kmem accounting. */ -enum { - KMEM_ACCOUNTED_ACTIVE, /* accounted by this cgroup itself */ -}; - #ifdef CONFIG_MEMCG_KMEM -static inline void memcg_kmem_set_active(struct mem_cgroup *memcg) -{ - set_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags); -} - static bool memcg_kmem_is_active(struct mem_cgroup *memcg) { - return test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags); + return memcg->kmemcg_id >= 0; } - #endif /* Stuffs for move charges at task migration. */ @@ -1571,7 +1559,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, * select it. The goal is to allow it to allocate so that it may * quickly exit and free its memory. */ - if (fatal_signal_pending(current) || current->flags & PF_EXITING) { + if (fatal_signal_pending(current) || task_will_free_mem(current)) { set_thread_flag(TIF_MEMDIE); return; } @@ -1628,6 +1616,8 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, NULL, "Memory cgroup out of memory"); } +#if MAX_NUMNODES > 1 + /** * test_mem_cgroup_node_reclaimable * @memcg: the target memcg @@ -1650,7 +1640,6 @@ static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *memcg, return false; } -#if MAX_NUMNODES > 1 /* * Always updating the nodemask is not very good - even if we have an empty @@ -2646,7 +2635,6 @@ static void memcg_register_cache(struct mem_cgroup *memcg, if (!cachep) return; - css_get(&memcg->css); list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches); /* @@ -2680,40 +2668,6 @@ static void memcg_unregister_cache(struct kmem_cache *cachep) list_del(&cachep->memcg_params->list); kmem_cache_destroy(cachep); - - /* drop the reference taken in memcg_register_cache */ - css_put(&memcg->css); -} - -/* - * During the creation a new cache, we need to disable our accounting mechanism - * altogether. This is true even if we are not creating, but rather just - * enqueing new caches to be created. - * - * This is because that process will trigger allocations; some visible, like - * explicit kmallocs to auxiliary data structures, name strings and internal - * cache structures; some well concealed, like INIT_WORK() that can allocate - * objects during debug. - * - * If any allocation happens during memcg_kmem_get_cache, we will recurse back - * to it. This may not be a bounded recursion: since the first cache creation - * failed to complete (waiting on the allocation), we'll just try to create the - * cache again, failing at the same point. - * - * memcg_kmem_get_cache is prepared to abort after seeing a positive count of - * memcg_kmem_skip_account. So we enclose anything that might allocate memory - * inside the following two functions. - */ -static inline void memcg_stop_kmem_account(void) -{ - VM_BUG_ON(!current->mm); - current->memcg_kmem_skip_account++; -} - -static inline void memcg_resume_kmem_account(void) -{ - VM_BUG_ON(!current->mm); - current->memcg_kmem_skip_account--; } int __memcg_cleanup_cache_params(struct kmem_cache *s) @@ -2747,9 +2701,7 @@ static void memcg_unregister_all_caches(struct mem_cgroup *memcg) mutex_lock(&memcg_slab_mutex); list_for_each_entry_safe(params, tmp, &memcg->memcg_slab_caches, list) { cachep = memcg_params_to_cache(params); - kmem_cache_shrink(cachep); - if (atomic_read(&cachep->memcg_params->nr_pages) == 0) - memcg_unregister_cache(cachep); + memcg_unregister_cache(cachep); } mutex_unlock(&memcg_slab_mutex); } @@ -2784,10 +2736,10 @@ static void __memcg_schedule_register_cache(struct mem_cgroup *memcg, struct memcg_register_cache_work *cw; cw = kmalloc(sizeof(*cw), GFP_NOWAIT); - if (cw == NULL) { - css_put(&memcg->css); + if (!cw) return; - } + + css_get(&memcg->css); cw->memcg = memcg; cw->cachep = cachep; @@ -2810,20 +2762,16 @@ static void memcg_schedule_register_cache(struct mem_cgroup *memcg, * this point we can't allow ourselves back into memcg_kmem_get_cache, * the safest choice is to do it like this, wrapping the whole function. */ - memcg_stop_kmem_account(); + current->memcg_kmem_skip_account = 1; __memcg_schedule_register_cache(memcg, cachep); - memcg_resume_kmem_account(); + current->memcg_kmem_skip_account = 0; } int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order) { unsigned int nr_pages = 1 << order; - int res; - res = memcg_charge_kmem(cachep->memcg_params->memcg, gfp, nr_pages); - if (!res) - atomic_add(nr_pages, &cachep->memcg_params->nr_pages); - return res; + return memcg_charge_kmem(cachep->memcg_params->memcg, gfp, nr_pages); } void __memcg_uncharge_slab(struct kmem_cache *cachep, int order) @@ -2831,7 +2779,6 @@ void __memcg_uncharge_slab(struct kmem_cache *cachep, int order) unsigned int nr_pages = 1 << order; memcg_uncharge_kmem(cachep->memcg_params->memcg, nr_pages); - atomic_sub(nr_pages, &cachep->memcg_params->nr_pages); } /* @@ -2847,8 +2794,7 @@ void __memcg_uncharge_slab(struct kmem_cache *cachep, int order) * Can't be called in interrupt context or from kernel threads. * This function needs to be called with rcu_read_lock() held. */ -struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, - gfp_t gfp) +struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep) { struct mem_cgroup *memcg; struct kmem_cache *memcg_cachep; @@ -2856,25 +2802,16 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, VM_BUG_ON(!cachep->memcg_params); VM_BUG_ON(!cachep->memcg_params->is_root_cache); - if (!current->mm || current->memcg_kmem_skip_account) + if (current->memcg_kmem_skip_account) return cachep; - rcu_read_lock(); - memcg = mem_cgroup_from_task(rcu_dereference(current->mm->owner)); - + memcg = get_mem_cgroup_from_mm(current->mm); if (!memcg_kmem_is_active(memcg)) goto out; memcg_cachep = cache_from_memcg_idx(cachep, memcg_cache_id(memcg)); - if (likely(memcg_cachep)) { - cachep = memcg_cachep; - goto out; - } - - /* The corresponding put will be done in the workqueue. */ - if (!css_tryget_online(&memcg->css)) - goto out; - rcu_read_unlock(); + if (likely(memcg_cachep)) + return memcg_cachep; /* * If we are in a safe context (can wait, and not in interrupt @@ -2889,12 +2826,17 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, * defer everything. */ memcg_schedule_register_cache(memcg, cachep); - return cachep; out: - rcu_read_unlock(); + css_put(&memcg->css); return cachep; } +void __memcg_kmem_put_cache(struct kmem_cache *cachep) +{ + if (!is_root_cache(cachep)) + css_put(&cachep->memcg_params->memcg->css); +} + /* * We need to verify if the allocation against current->mm->owner's memcg is * possible for the given order. But the page is not allocated yet, so we'll @@ -2917,34 +2859,6 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order) *_memcg = NULL; - /* - * Disabling accounting is only relevant for some specific memcg - * internal allocations. Therefore we would initially not have such - * check here, since direct calls to the page allocator that are - * accounted to kmemcg (alloc_kmem_pages and friends) only happen - * outside memcg core. We are mostly concerned with cache allocations, - * and by having this test at memcg_kmem_get_cache, we are already able - * to relay the allocation to the root cache and bypass the memcg cache - * altogether. - * - * There is one exception, though: the SLUB allocator does not create - * large order caches, but rather service large kmallocs directly from - * the page allocator. Therefore, the following sequence when backed by - * the SLUB allocator: - * - * memcg_stop_kmem_account(); - * kmalloc(<large_number>) - * memcg_resume_kmem_account(); - * - * would effectively ignore the fact that we should skip accounting, - * since it will drive us directly to this function without passing - * through the cache selector memcg_kmem_get_cache. Such large - * allocations are extremely rare but can happen, for instance, for the - * cache arrays. We bring this test here. - */ - if (!current->mm || current->memcg_kmem_skip_account) - return true; - memcg = get_mem_cgroup_from_mm(current->mm); if (!memcg_kmem_is_active(memcg)) { @@ -2985,10 +2899,6 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order) memcg_uncharge_kmem(memcg, 1 << order); page->mem_cgroup = NULL; } -#else -static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg) -{ -} #endif /* CONFIG_MEMCG_KMEM */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -3539,12 +3449,6 @@ static int memcg_activate_kmem(struct mem_cgroup *memcg, return 0; /* - * We are going to allocate memory for data shared by all memory - * cgroups so let's stop accounting here. - */ - memcg_stop_kmem_account(); - - /* * For simplicity, we won't allow this to be disabled. It also can't * be changed if the cgroup has children already, or if tasks had * already joined. @@ -3570,25 +3474,22 @@ static int memcg_activate_kmem(struct mem_cgroup *memcg, goto out; } - memcg->kmemcg_id = memcg_id; - INIT_LIST_HEAD(&memcg->memcg_slab_caches); - /* - * We couldn't have accounted to this cgroup, because it hasn't got the - * active bit set yet, so this should succeed. + * We couldn't have accounted to this cgroup, because it hasn't got + * activated yet, so this should succeed. */ err = page_counter_limit(&memcg->kmem, nr_pages); VM_BUG_ON(err); static_key_slow_inc(&memcg_kmem_enabled_key); /* - * Setting the active bit after enabling static branching will + * A memory cgroup is considered kmem-active as soon as it gets + * kmemcg_id. Setting the id after enabling static branching will * guarantee no one starts accounting before all call sites are * patched. */ - memcg_kmem_set_active(memcg); + memcg->kmemcg_id = memcg_id; out: - memcg_resume_kmem_account(); return err; } @@ -3791,11 +3692,6 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v) } #endif /* CONFIG_NUMA */ -static inline void mem_cgroup_lru_names_not_uptodate(void) -{ - BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS); -} - static int memcg_stat_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); @@ -3803,6 +3699,8 @@ static int memcg_stat_show(struct seq_file *m, void *v) struct mem_cgroup *mi; unsigned int i; + BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS); + for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account) continue; @@ -4259,7 +4157,6 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { int ret; - memcg->kmemcg_id = -1; ret = memcg_propagate_kmem(memcg); if (ret) return ret; @@ -4269,6 +4166,7 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) static void memcg_destroy_kmem(struct mem_cgroup *memcg) { + memcg_unregister_all_caches(memcg); mem_cgroup_sockets_destroy(memcg); } #else @@ -4724,17 +4622,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) free_percpu(memcg->stat); - /* - * We need to make sure that (at least for now), the jump label - * destruction code runs outside of the cgroup lock. This is because - * get_online_cpus(), which is called from the static_branch update, - * can't be called inside the cgroup_lock. cpusets are the ones - * enforcing this dependency, so if they ever change, we might as well. - * - * schedule_work() will guarantee this happens. Be careful if you need - * to move this code around, and make sure it is outside - * the cgroup_lock. - */ disarm_static_keys(memcg); kfree(memcg); } @@ -4804,6 +4691,10 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) vmpressure_init(&memcg->vmpressure); INIT_LIST_HEAD(&memcg->event_list); spin_lock_init(&memcg->event_list_lock); +#ifdef CONFIG_MEMCG_KMEM + memcg->kmemcg_id = -1; + INIT_LIST_HEAD(&memcg->memcg_slab_caches); +#endif return &memcg->css; @@ -4885,7 +4776,6 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) } spin_unlock(&memcg->event_list_lock); - memcg_unregister_all_caches(memcg); vmpressure_cleanup(&memcg->vmpressure); } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index e5ee0ca..feb803b 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -239,19 +239,14 @@ void shake_page(struct page *p, int access) } /* - * Only call shrink_slab here (which would also shrink other caches) if - * access is not potentially fatal. + * Only call shrink_node_slabs here (which would also shrink + * other caches) if access is not potentially fatal. */ if (access) { int nr; int nid = page_to_nid(p); do { - struct shrink_control shrink = { - .gfp_mask = GFP_KERNEL, - }; - node_set(nid, shrink.nodes_to_scan); - - nr = shrink_slab(&shrink, 1000, 1000); + nr = shrink_node_slabs(GFP_KERNEL, nid, 1000, 1000); if (page_count(p) == 1) break; } while (nr > 10); @@ -466,7 +461,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, struct task_struct *tsk; struct address_space *mapping = page->mapping; - mutex_lock(&mapping->i_mmap_mutex); + i_mmap_lock_read(mapping); read_lock(&tasklist_lock); for_each_process(tsk) { pgoff_t pgoff = page_to_pgoff(page); @@ -488,7 +483,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, } } read_unlock(&tasklist_lock); - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_read(mapping); } /* diff --git a/mm/memory.c b/mm/memory.c index 4b5a282..fbf7411 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1326,9 +1326,9 @@ static void unmap_single_vma(struct mmu_gather *tlb, * safe to do nothing in this case. */ if (vma->vm_file) { - mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex); + i_mmap_lock_write(vma->vm_file->f_mapping); __unmap_hugepage_range_final(tlb, vma, start, end, NULL); - mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); + i_mmap_unlock_write(vma->vm_file->f_mapping); } } else unmap_page_range(tlb, vma, start, end, details); @@ -2377,12 +2377,12 @@ void unmap_mapping_range(struct address_space *mapping, details.last_index = ULONG_MAX; - mutex_lock(&mapping->i_mmap_mutex); + i_mmap_lock_read(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap))) unmap_mapping_range_tree(&mapping->i_mmap, &details); if (unlikely(!list_empty(&mapping->i_mmap_nonlinear))) unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details); - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_read(mapping); } EXPORT_SYMBOL(unmap_mapping_range); @@ -3365,6 +3365,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, return ret; } +EXPORT_SYMBOL_GPL(handle_mm_fault); #ifndef __PAGETABLE_PUD_FOLDED /* diff --git a/mm/migrate.c b/mm/migrate.c index 0143995..253474c 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -746,7 +746,7 @@ static int fallback_migrate_page(struct address_space *mapping, * MIGRATEPAGE_SUCCESS - success */ static int move_to_new_page(struct page *newpage, struct page *page, - int remap_swapcache, enum migrate_mode mode) + int page_was_mapped, enum migrate_mode mode) { struct address_space *mapping; int rc; @@ -784,7 +784,7 @@ static int move_to_new_page(struct page *newpage, struct page *page, newpage->mapping = NULL; } else { mem_cgroup_migrate(page, newpage, false); - if (remap_swapcache) + if (page_was_mapped) remove_migration_ptes(page, newpage); page->mapping = NULL; } @@ -798,7 +798,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, int force, enum migrate_mode mode) { int rc = -EAGAIN; - int remap_swapcache = 1; + int page_was_mapped = 0; struct anon_vma *anon_vma = NULL; if (!trylock_page(page)) { @@ -870,7 +870,6 @@ static int __unmap_and_move(struct page *page, struct page *newpage, * migrated but are not remapped when migration * completes */ - remap_swapcache = 0; } else { goto out_unlock; } @@ -910,13 +909,17 @@ static int __unmap_and_move(struct page *page, struct page *newpage, } /* Establish migration ptes or remove ptes */ - try_to_unmap(page, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS); + if (page_mapped(page)) { + try_to_unmap(page, + TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS); + page_was_mapped = 1; + } skip_unmap: if (!page_mapped(page)) - rc = move_to_new_page(newpage, page, remap_swapcache, mode); + rc = move_to_new_page(newpage, page, page_was_mapped, mode); - if (rc && remap_swapcache) + if (rc && page_was_mapped) remove_migration_ptes(page, page); /* Drop an anon_vma reference if we took one */ @@ -1017,6 +1020,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, { int rc = 0; int *result = NULL; + int page_was_mapped = 0; struct page *new_hpage; struct anon_vma *anon_vma = NULL; @@ -1047,12 +1051,16 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (PageAnon(hpage)) anon_vma = page_get_anon_vma(hpage); - try_to_unmap(hpage, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS); + if (page_mapped(hpage)) { + try_to_unmap(hpage, + TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS); + page_was_mapped = 1; + } if (!page_mapped(hpage)) - rc = move_to_new_page(new_hpage, hpage, 1, mode); + rc = move_to_new_page(new_hpage, hpage, page_was_mapped, mode); - if (rc != MIGRATEPAGE_SUCCESS) + if (rc != MIGRATEPAGE_SUCCESS && page_was_mapped) remove_migration_ptes(hpage, hpage); if (anon_vma) diff --git a/mm/mincore.c b/mm/mincore.c index 725c809..c8c528b 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -137,8 +137,11 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } else { /* pte is a swap entry */ swp_entry_t entry = pte_to_swp_entry(pte); - if (is_migration_entry(entry)) { - /* migration entries are always uptodate */ + if (non_swap_entry(entry)) { + /* + * migration or hwpoison entries are always + * uptodate + */ *vec = 1; } else { #ifdef CONFIG_SWAP @@ -232,7 +232,7 @@ error: } /* - * Requires inode->i_mapping->i_mmap_mutex + * Requires inode->i_mapping->i_mmap_rwsem */ static void __remove_shared_vm_struct(struct vm_area_struct *vma, struct file *file, struct address_space *mapping) @@ -260,9 +260,9 @@ void unlink_file_vma(struct vm_area_struct *vma) if (file) { struct address_space *mapping = file->f_mapping; - mutex_lock(&mapping->i_mmap_mutex); + i_mmap_lock_write(mapping); __remove_shared_vm_struct(vma, file, mapping); - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_write(mapping); } } @@ -674,14 +674,14 @@ static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma, if (vma->vm_file) { mapping = vma->vm_file->f_mapping; - mutex_lock(&mapping->i_mmap_mutex); + i_mmap_lock_write(mapping); } __vma_link(mm, vma, prev, rb_link, rb_parent); __vma_link_file(vma); if (mapping) - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_write(mapping); mm->map_count++; validate_mm(mm); @@ -796,7 +796,7 @@ again: remove_next = 1 + (end > next->vm_end); next->vm_end); } - mutex_lock(&mapping->i_mmap_mutex); + i_mmap_lock_write(mapping); if (insert) { /* * Put into interval tree now, so instantiated pages @@ -883,7 +883,7 @@ again: remove_next = 1 + (end > next->vm_end); anon_vma_unlock_write(anon_vma); } if (mapping) - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_write(mapping); if (root) { uprobe_mmap(vma); @@ -2362,6 +2362,8 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) } #endif +EXPORT_SYMBOL_GPL(find_extend_vma); + /* * Ok - we have the memory areas we should free on the vma list, * so release them, and do the vma updates. @@ -2791,7 +2793,7 @@ void exit_mmap(struct mm_struct *mm) /* Insert vm structure into process list sorted by address * and into the inode's i_mmap tree. If vm_file is non-NULL - * then i_mmap_mutex is taken here. + * then i_mmap_rwsem is taken here. */ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) { @@ -3086,7 +3088,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) */ if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); - mutex_lock_nest_lock(&mapping->i_mmap_mutex, &mm->mmap_sem); + down_write_nest_lock(&mapping->i_mmap_rwsem, &mm->mmap_sem); } } @@ -3113,7 +3115,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) * vma in this mm is backed by the same anon_vma or address_space. * * We can take all the locks in random order because the VM code - * taking i_mmap_mutex or anon_vma->rwsem outside the mmap_sem never + * taking i_mmap_rwsem or anon_vma->rwsem outside the mmap_sem never * takes more than one of them in a row. Secondly we're protected * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex. * @@ -3182,7 +3184,7 @@ static void vm_unlock_mapping(struct address_space *mapping) * AS_MM_ALL_LOCKS can't change to 0 from under us * because we hold the mm_all_locks_mutex. */ - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_write(mapping); if (!test_and_clear_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); diff --git a/mm/mremap.c b/mm/mremap.c index b147f66..84aa36f 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -99,7 +99,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, spinlock_t *old_ptl, *new_ptl; /* - * When need_rmap_locks is true, we take the i_mmap_mutex and anon_vma + * When need_rmap_locks is true, we take the i_mmap_rwsem and anon_vma * locks to ensure that rmap will always observe either the old or the * new ptes. This is the easiest way to avoid races with * truncate_pagecache(), page migration, etc... @@ -119,7 +119,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, if (need_rmap_locks) { if (vma->vm_file) { mapping = vma->vm_file->f_mapping; - mutex_lock(&mapping->i_mmap_mutex); + i_mmap_lock_write(mapping); } if (vma->anon_vma) { anon_vma = vma->anon_vma; @@ -156,7 +156,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, if (anon_vma) anon_vma_unlock_write(anon_vma); if (mapping) - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_write(mapping); } #define LATENCY_LIMIT (64 * PAGE_SIZE) @@ -722,11 +722,11 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) if (vma->vm_file) { mapping = vma->vm_file->f_mapping; - mutex_lock(&mapping->i_mmap_mutex); + i_mmap_lock_write(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_write(mapping); } /* add the VMA to the tree */ @@ -795,11 +795,11 @@ static void delete_vma_from_mm(struct vm_area_struct *vma) if (vma->vm_file) { mapping = vma->vm_file->f_mapping; - mutex_lock(&mapping->i_mmap_mutex); + i_mmap_lock_write(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_write(mapping); } /* remove from the MM's tree and list */ @@ -1149,8 +1149,7 @@ static int do_mmap_private(struct vm_area_struct *vma, unsigned long len, unsigned long capabilities) { - struct page *pages; - unsigned long total, point, n; + unsigned long total, point; void *base; int ret, order; @@ -1182,33 +1181,23 @@ static int do_mmap_private(struct vm_area_struct *vma, order = get_order(len); kdebug("alloc order %d for %lx", order, len); - pages = alloc_pages(GFP_KERNEL, order); - if (!pages) - goto enomem; - total = 1 << order; - atomic_long_add(total, &mmap_pages_allocated); - point = len >> PAGE_SHIFT; - /* we allocated a power-of-2 sized page set, so we may want to trim off - * the excess */ + /* we don't want to allocate a power-of-2 sized page set */ if (sysctl_nr_trim_pages && total - point >= sysctl_nr_trim_pages) { - while (total > point) { - order = ilog2(total - point); - n = 1 << order; - kdebug("shave %lu/%lu @%lu", n, total - point, total); - atomic_long_sub(n, &mmap_pages_allocated); - total -= n; - set_page_refcounted(pages + total); - __free_pages(pages + total, order); - } + total = point; + kdebug("try to alloc exact %lu pages", total); + base = alloc_pages_exact(len, GFP_KERNEL); + } else { + base = (void *)__get_free_pages(GFP_KERNEL, order); } - for (point = 1; point < total; point++) - set_page_refcounted(&pages[point]); + if (!base) + goto enomem; + + atomic_long_add(total, &mmap_pages_allocated); - base = page_address(pages); region->vm_flags = vma->vm_flags |= VM_MAPPED_COPY; region->vm_start = (unsigned long) base; region->vm_end = region->vm_start + len; @@ -2094,14 +2083,14 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size, high = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; down_write(&nommu_region_sem); - mutex_lock(&inode->i_mapping->i_mmap_mutex); + i_mmap_lock_read(inode->i_mapping); /* search for VMAs that fall within the dead zone */ vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap, low, high) { /* found one - only interested if it's shared out of the page * cache */ if (vma->vm_flags & VM_SHARED) { - mutex_unlock(&inode->i_mapping->i_mmap_mutex); + i_mmap_unlock_read(inode->i_mapping); up_write(&nommu_region_sem); return -ETXTBSY; /* not quite true, but near enough */ } @@ -2113,8 +2102,7 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size, * we don't check for any regions that start beyond the EOF as there * shouldn't be any */ - vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap, - 0, ULONG_MAX) { + vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap, 0, ULONG_MAX) { if (!(vma->vm_flags & VM_SHARED)) continue; @@ -2129,7 +2117,7 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size, } } - mutex_unlock(&inode->i_mapping->i_mmap_mutex); + i_mmap_unlock_read(inode->i_mapping); up_write(&nommu_region_sem); return 0; } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 864bba9..d503e9c 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -281,14 +281,9 @@ enum oom_scan_t oom_scan_process_thread(struct task_struct *task, if (oom_task_origin(task)) return OOM_SCAN_SELECT; - if (task->flags & PF_EXITING && !force_kill) { - /* - * If this task is not being ptraced on exit, then wait for it - * to finish before killing some other task unnecessarily. - */ - if (!(task->group_leader->ptrace & PT_TRACE_EXIT)) - return OOM_SCAN_ABORT; - } + if (task_will_free_mem(task) && !force_kill) + return OOM_SCAN_ABORT; + return OOM_SCAN_OK; } @@ -443,7 +438,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, * If the task is already exiting, don't alarm the sysadmin or kill * its children or threads, just set TIF_MEMDIE so it can die quickly */ - if (p->flags & PF_EXITING) { + if (task_will_free_mem(p)) { set_tsk_thread_flag(p, TIF_MEMDIE); put_task_struct(p); return; @@ -649,7 +644,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, * select it. The goal is to allow it to allocate so that it may * quickly exit and free its memory. */ - if (fatal_signal_pending(current) || current->flags & PF_EXITING) { + if (fatal_signal_pending(current) || task_will_free_mem(current)) { set_thread_flag(TIF_MEMDIE); return; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index df542fe..fa974d87 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -48,6 +48,7 @@ #include <linux/backing-dev.h> #include <linux/fault-inject.h> #include <linux/page-isolation.h> +#include <linux/page_ext.h> #include <linux/debugobjects.h> #include <linux/kmemleak.h> #include <linux/compaction.h> @@ -55,9 +56,10 @@ #include <linux/prefetch.h> #include <linux/mm_inline.h> #include <linux/migrate.h> -#include <linux/page-debug-flags.h> +#include <linux/page_ext.h> #include <linux/hugetlb.h> #include <linux/sched/rt.h> +#include <linux/page_owner.h> #include <asm/sections.h> #include <asm/tlbflush.h> @@ -424,6 +426,42 @@ static inline void prep_zero_page(struct page *page, unsigned int order, #ifdef CONFIG_DEBUG_PAGEALLOC unsigned int _debug_guardpage_minorder; +bool _debug_pagealloc_enabled __read_mostly; +bool _debug_guardpage_enabled __read_mostly; + +static int __init early_debug_pagealloc(char *buf) +{ + if (!buf) + return -EINVAL; + + if (strcmp(buf, "on") == 0) + _debug_pagealloc_enabled = true; + + return 0; +} +early_param("debug_pagealloc", early_debug_pagealloc); + +static bool need_debug_guardpage(void) +{ + /* If we don't use debug_pagealloc, we don't need guard page */ + if (!debug_pagealloc_enabled()) + return false; + + return true; +} + +static void init_debug_guardpage(void) +{ + if (!debug_pagealloc_enabled()) + return; + + _debug_guardpage_enabled = true; +} + +struct page_ext_operations debug_guardpage_ops = { + .need = need_debug_guardpage, + .init = init_debug_guardpage, +}; static int __init debug_guardpage_minorder_setup(char *buf) { @@ -439,18 +477,44 @@ static int __init debug_guardpage_minorder_setup(char *buf) } __setup("debug_guardpage_minorder=", debug_guardpage_minorder_setup); -static inline void set_page_guard_flag(struct page *page) +static inline void set_page_guard(struct zone *zone, struct page *page, + unsigned int order, int migratetype) { - __set_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags); + struct page_ext *page_ext; + + if (!debug_guardpage_enabled()) + return; + + page_ext = lookup_page_ext(page); + __set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags); + + INIT_LIST_HEAD(&page->lru); + set_page_private(page, order); + /* Guard pages are not available for any usage */ + __mod_zone_freepage_state(zone, -(1 << order), migratetype); } -static inline void clear_page_guard_flag(struct page *page) +static inline void clear_page_guard(struct zone *zone, struct page *page, + unsigned int order, int migratetype) { - __clear_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags); + struct page_ext *page_ext; + + if (!debug_guardpage_enabled()) + return; + + page_ext = lookup_page_ext(page); + __clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags); + + set_page_private(page, 0); + if (!is_migrate_isolate(migratetype)) + __mod_zone_freepage_state(zone, (1 << order), migratetype); } #else -static inline void set_page_guard_flag(struct page *page) { } -static inline void clear_page_guard_flag(struct page *page) { } +struct page_ext_operations debug_guardpage_ops = { NULL, }; +static inline void set_page_guard(struct zone *zone, struct page *page, + unsigned int order, int migratetype) {} +static inline void clear_page_guard(struct zone *zone, struct page *page, + unsigned int order, int migratetype) {} #endif static inline void set_page_order(struct page *page, unsigned int order) @@ -581,12 +645,7 @@ static inline void __free_one_page(struct page *page, * merge with it and move up one order. */ if (page_is_guard(buddy)) { - clear_page_guard_flag(buddy); - set_page_private(buddy, 0); - if (!is_migrate_isolate(migratetype)) { - __mod_zone_freepage_state(zone, 1 << order, - migratetype); - } + clear_page_guard(zone, buddy, order, migratetype); } else { list_del(&buddy->lru); zone->free_area[order].nr_free--; @@ -755,6 +814,8 @@ static bool free_pages_prepare(struct page *page, unsigned int order) if (bad) return false; + reset_page_owner(page, order); + if (!PageHighMem(page)) { debug_check_no_locks_freed(page_address(page), PAGE_SIZE << order); @@ -861,23 +922,18 @@ static inline void expand(struct zone *zone, struct page *page, size >>= 1; VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]); -#ifdef CONFIG_DEBUG_PAGEALLOC - if (high < debug_guardpage_minorder()) { + if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && + debug_guardpage_enabled() && + high < debug_guardpage_minorder()) { /* * Mark as guard pages (or page), that will allow to * merge back to allocator when buddy will be freed. * Corresponding page table entries will not be touched, * pages will stay not present in virtual address space */ - INIT_LIST_HEAD(&page[size].lru); - set_page_guard_flag(&page[size]); - set_page_private(&page[size], high); - /* Guard pages are not available for any usage */ - __mod_zone_freepage_state(zone, -(1 << high), - migratetype); + set_page_guard(zone, &page[size], high, migratetype); continue; } -#endif list_add(&page[size].lru, &area->free_list[migratetype]); area->nr_free++; set_page_order(&page[size], high); @@ -935,6 +991,8 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags) if (order && (gfp_flags & __GFP_COMP)) prep_compound_page(page, order); + set_page_owner(page, order, gfp_flags); + return 0; } @@ -1507,8 +1565,11 @@ void split_page(struct page *page, unsigned int order) split_page(virt_to_page(page[0].shadow), order); #endif - for (i = 1; i < (1 << order); i++) + set_page_owner(page, 0, 0); + for (i = 1; i < (1 << order); i++) { set_page_refcounted(page + i); + set_page_owner(page + i, 0, 0); + } } EXPORT_SYMBOL_GPL(split_page); @@ -1548,6 +1609,7 @@ int __isolate_free_page(struct page *page, unsigned int order) } } + set_page_owner(page, order, 0); return 1UL << order; } @@ -4856,6 +4918,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, #endif init_waitqueue_head(&pgdat->kswapd_wait); init_waitqueue_head(&pgdat->pfmemalloc_wait); + pgdat_page_ext_init(pgdat); for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; @@ -4874,16 +4937,18 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, * and per-cpu initialisations */ memmap_pages = calc_memmap_size(size, realsize); - 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); - } else - printk(KERN_WARNING - " %s zone: %lu pages exceeds freesize %lu\n", - zone_names[j], memmap_pages, freesize); + if (!is_highmem_idx(j)) { + 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); + } else + printk(KERN_WARNING + " %s zone: %lu pages exceeds freesize %lu\n", + zone_names[j], memmap_pages, freesize); + } /* Account for reserved pages */ if (j == 0 && freesize > dma_reserve) { @@ -6221,9 +6286,9 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, if (!PageLRU(page)) found++; /* - * If there are RECLAIMABLE pages, we need to check it. - * But now, memory offline itself doesn't call shrink_slab() - * and it still to be fixed. + * If there are RECLAIMABLE pages, we need to check + * it. But now, memory offline itself doesn't call + * shrink_node_slabs() and it still to be fixed. */ /* * If the page is not RAM, page_count()should be 0. diff --git a/mm/page_ext.c b/mm/page_ext.c new file mode 100644 index 0000000..d86fd2f --- /dev/null +++ b/mm/page_ext.c @@ -0,0 +1,403 @@ +#include <linux/mm.h> +#include <linux/mmzone.h> +#include <linux/bootmem.h> +#include <linux/page_ext.h> +#include <linux/memory.h> +#include <linux/vmalloc.h> +#include <linux/kmemleak.h> +#include <linux/page_owner.h> + +/* + * struct page extension + * + * This is the feature to manage memory for extended data per page. + * + * Until now, we must modify struct page itself to store extra data per page. + * This requires rebuilding the kernel and it is really time consuming process. + * And, sometimes, rebuild is impossible due to third party module dependency. + * At last, enlarging struct page could cause un-wanted system behaviour change. + * + * This feature is intended to overcome above mentioned problems. This feature + * allocates memory for extended data per page in certain place rather than + * the struct page itself. This memory can be accessed by the accessor + * functions provided by this code. During the boot process, it checks whether + * allocation of huge chunk of memory is needed or not. If not, it avoids + * allocating memory at all. With this advantage, we can include this feature + * into the kernel in default and can avoid rebuild and solve related problems. + * + * To help these things to work well, there are two callbacks for clients. One + * is the need callback which is mandatory if user wants to avoid useless + * memory allocation at boot-time. The other is optional, init callback, which + * is used to do proper initialization after memory is allocated. + * + * The need callback is used to decide whether extended memory allocation is + * needed or not. Sometimes users want to deactivate some features in this + * boot and extra memory would be unneccessary. In this case, to avoid + * allocating huge chunk of memory, each clients represent their need of + * extra memory through the need callback. If one of the need callbacks + * returns true, it means that someone needs extra memory so that + * page extension core should allocates memory for page extension. If + * none of need callbacks return true, memory isn't needed at all in this boot + * and page extension core can skip to allocate memory. As result, + * none of memory is wasted. + * + * The init callback is used to do proper initialization after page extension + * is completely initialized. In sparse memory system, extra memory is + * allocated some time later than memmap is allocated. In other words, lifetime + * of memory for page extension isn't same with memmap for struct page. + * Therefore, clients can't store extra data until page extension is + * initialized, even if pages are allocated and used freely. This could + * cause inadequate state of extra data per page, so, to prevent it, client + * can utilize this callback to initialize the state of it correctly. + */ + +static struct page_ext_operations *page_ext_ops[] = { + &debug_guardpage_ops, +#ifdef CONFIG_PAGE_POISONING + &page_poisoning_ops, +#endif +#ifdef CONFIG_PAGE_OWNER + &page_owner_ops, +#endif +}; + +static unsigned long total_usage; + +static bool __init invoke_need_callbacks(void) +{ + int i; + int entries = ARRAY_SIZE(page_ext_ops); + + for (i = 0; i < entries; i++) { + if (page_ext_ops[i]->need && page_ext_ops[i]->need()) + return true; + } + + return false; +} + +static void __init invoke_init_callbacks(void) +{ + int i; + int entries = ARRAY_SIZE(page_ext_ops); + + for (i = 0; i < entries; i++) { + if (page_ext_ops[i]->init) + page_ext_ops[i]->init(); + } +} + +#if !defined(CONFIG_SPARSEMEM) + + +void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) +{ + pgdat->node_page_ext = NULL; +} + +struct page_ext *lookup_page_ext(struct page *page) +{ + unsigned long pfn = page_to_pfn(page); + unsigned long offset; + struct page_ext *base; + + base = NODE_DATA(page_to_nid(page))->node_page_ext; +#ifdef CONFIG_DEBUG_VM + /* + * The sanity checks the page allocator does upon freeing a + * page can reach here before the page_ext arrays are + * allocated when feeding a range of pages to the allocator + * for the first time during bootup or memory hotplug. + */ + if (unlikely(!base)) + return NULL; +#endif + offset = pfn - round_down(node_start_pfn(page_to_nid(page)), + MAX_ORDER_NR_PAGES); + return base + offset; +} + +static int __init alloc_node_page_ext(int nid) +{ + struct page_ext *base; + unsigned long table_size; + unsigned long nr_pages; + + nr_pages = NODE_DATA(nid)->node_spanned_pages; + if (!nr_pages) + return 0; + + /* + * Need extra space if node range is not aligned with + * MAX_ORDER_NR_PAGES. When page allocator's buddy algorithm + * checks buddy's status, range could be out of exact node range. + */ + if (!IS_ALIGNED(node_start_pfn(nid), MAX_ORDER_NR_PAGES) || + !IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES)) + nr_pages += MAX_ORDER_NR_PAGES; + + table_size = sizeof(struct page_ext) * nr_pages; + + base = memblock_virt_alloc_try_nid_nopanic( + table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), + BOOTMEM_ALLOC_ACCESSIBLE, nid); + if (!base) + return -ENOMEM; + NODE_DATA(nid)->node_page_ext = base; + total_usage += table_size; + return 0; +} + +void __init page_ext_init_flatmem(void) +{ + + int nid, fail; + + if (!invoke_need_callbacks()) + return; + + for_each_online_node(nid) { + fail = alloc_node_page_ext(nid); + if (fail) + goto fail; + } + pr_info("allocated %ld bytes of page_ext\n", total_usage); + invoke_init_callbacks(); + return; + +fail: + pr_crit("allocation of page_ext failed.\n"); + panic("Out of memory"); +} + +#else /* CONFIG_FLAT_NODE_MEM_MAP */ + +struct page_ext *lookup_page_ext(struct page *page) +{ + unsigned long pfn = page_to_pfn(page); + struct mem_section *section = __pfn_to_section(pfn); +#ifdef CONFIG_DEBUG_VM + /* + * The sanity checks the page allocator does upon freeing a + * page can reach here before the page_ext arrays are + * allocated when feeding a range of pages to the allocator + * for the first time during bootup or memory hotplug. + */ + if (!section->page_ext) + return NULL; +#endif + return section->page_ext + pfn; +} + +static void *__meminit alloc_page_ext(size_t size, int nid) +{ + gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN; + void *addr = NULL; + + addr = alloc_pages_exact_nid(nid, size, flags); + if (addr) { + kmemleak_alloc(addr, size, 1, flags); + return addr; + } + + if (node_state(nid, N_HIGH_MEMORY)) + addr = vzalloc_node(size, nid); + else + addr = vzalloc(size); + + return addr; +} + +static int __meminit init_section_page_ext(unsigned long pfn, int nid) +{ + struct mem_section *section; + struct page_ext *base; + unsigned long table_size; + + section = __pfn_to_section(pfn); + + if (section->page_ext) + return 0; + + table_size = sizeof(struct page_ext) * PAGES_PER_SECTION; + base = alloc_page_ext(table_size, nid); + + /* + * The value stored in section->page_ext is (base - pfn) + * and it does not point to the memory block allocated above, + * causing kmemleak false positives. + */ + kmemleak_not_leak(base); + + if (!base) { + pr_err("page ext allocation failure\n"); + return -ENOMEM; + } + + /* + * The passed "pfn" may not be aligned to SECTION. For the calculation + * we need to apply a mask. + */ + pfn &= PAGE_SECTION_MASK; + section->page_ext = base - pfn; + total_usage += table_size; + return 0; +} +#ifdef CONFIG_MEMORY_HOTPLUG +static void free_page_ext(void *addr) +{ + if (is_vmalloc_addr(addr)) { + vfree(addr); + } else { + struct page *page = virt_to_page(addr); + size_t table_size; + + table_size = sizeof(struct page_ext) * PAGES_PER_SECTION; + + BUG_ON(PageReserved(page)); + free_pages_exact(addr, table_size); + } +} + +static void __free_page_ext(unsigned long pfn) +{ + struct mem_section *ms; + struct page_ext *base; + + ms = __pfn_to_section(pfn); + if (!ms || !ms->page_ext) + return; + base = ms->page_ext + pfn; + free_page_ext(base); + ms->page_ext = NULL; +} + +static int __meminit online_page_ext(unsigned long start_pfn, + unsigned long nr_pages, + int nid) +{ + unsigned long start, end, pfn; + int fail = 0; + + start = SECTION_ALIGN_DOWN(start_pfn); + end = SECTION_ALIGN_UP(start_pfn + nr_pages); + + if (nid == -1) { + /* + * In this case, "nid" already exists and contains valid memory. + * "start_pfn" passed to us is a pfn which is an arg for + * online__pages(), and start_pfn should exist. + */ + nid = pfn_to_nid(start_pfn); + VM_BUG_ON(!node_state(nid, N_ONLINE)); + } + + for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) { + if (!pfn_present(pfn)) + continue; + fail = init_section_page_ext(pfn, nid); + } + if (!fail) + return 0; + + /* rollback */ + for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) + __free_page_ext(pfn); + + return -ENOMEM; +} + +static int __meminit offline_page_ext(unsigned long start_pfn, + unsigned long nr_pages, int nid) +{ + unsigned long start, end, pfn; + + start = SECTION_ALIGN_DOWN(start_pfn); + end = SECTION_ALIGN_UP(start_pfn + nr_pages); + + for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) + __free_page_ext(pfn); + return 0; + +} + +static int __meminit page_ext_callback(struct notifier_block *self, + unsigned long action, void *arg) +{ + struct memory_notify *mn = arg; + int ret = 0; + + switch (action) { + case MEM_GOING_ONLINE: + ret = online_page_ext(mn->start_pfn, + mn->nr_pages, mn->status_change_nid); + break; + case MEM_OFFLINE: + offline_page_ext(mn->start_pfn, + mn->nr_pages, mn->status_change_nid); + break; + case MEM_CANCEL_ONLINE: + offline_page_ext(mn->start_pfn, + mn->nr_pages, mn->status_change_nid); + break; + case MEM_GOING_OFFLINE: + break; + case MEM_ONLINE: + case MEM_CANCEL_OFFLINE: + break; + } + + return notifier_from_errno(ret); +} + +#endif + +void __init page_ext_init(void) +{ + unsigned long pfn; + int nid; + + if (!invoke_need_callbacks()) + return; + + for_each_node_state(nid, N_MEMORY) { + unsigned long start_pfn, end_pfn; + + start_pfn = node_start_pfn(nid); + end_pfn = node_end_pfn(nid); + /* + * start_pfn and end_pfn may not be aligned to SECTION and the + * page->flags of out of node pages are not initialized. So we + * scan [start_pfn, the biggest section's pfn < end_pfn) here. + */ + for (pfn = start_pfn; pfn < end_pfn; + pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) { + + if (!pfn_valid(pfn)) + continue; + /* + * Nodes's pfns can be overlapping. + * We know some arch can have a nodes layout such as + * -------------pfn--------------> + * N0 | N1 | N2 | N0 | N1 | N2|.... + */ + if (pfn_to_nid(pfn) != nid) + continue; + if (init_section_page_ext(pfn, nid)) + goto oom; + } + } + hotplug_memory_notifier(page_ext_callback, 0); + pr_info("allocated %ld bytes of page_ext\n", total_usage); + invoke_init_callbacks(); + return; + +oom: + panic("Out of memory"); +} + +void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) +{ +} + +#endif diff --git a/mm/page_owner.c b/mm/page_owner.c new file mode 100644 index 0000000..9ab4a9b --- /dev/null +++ b/mm/page_owner.c @@ -0,0 +1,311 @@ +#include <linux/debugfs.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/bootmem.h> +#include <linux/stacktrace.h> +#include <linux/page_owner.h> +#include "internal.h" + +static bool page_owner_disabled = true; +bool page_owner_inited __read_mostly; + +static void init_early_allocated_pages(void); + +static int early_page_owner_param(char *buf) +{ + if (!buf) + return -EINVAL; + + if (strcmp(buf, "on") == 0) + page_owner_disabled = false; + + return 0; +} +early_param("page_owner", early_page_owner_param); + +static bool need_page_owner(void) +{ + if (page_owner_disabled) + return false; + + return true; +} + +static void init_page_owner(void) +{ + if (page_owner_disabled) + return; + + page_owner_inited = true; + init_early_allocated_pages(); +} + +struct page_ext_operations page_owner_ops = { + .need = need_page_owner, + .init = init_page_owner, +}; + +void __reset_page_owner(struct page *page, unsigned int order) +{ + int i; + struct page_ext *page_ext; + + for (i = 0; i < (1 << order); i++) { + page_ext = lookup_page_ext(page + i); + __clear_bit(PAGE_EXT_OWNER, &page_ext->flags); + } +} + +void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) +{ + struct page_ext *page_ext; + struct stack_trace *trace; + + page_ext = lookup_page_ext(page); + + trace = &page_ext->trace; + trace->nr_entries = 0; + trace->max_entries = ARRAY_SIZE(page_ext->trace_entries); + trace->entries = &page_ext->trace_entries[0]; + trace->skip = 3; + save_stack_trace(&page_ext->trace); + + page_ext->order = order; + page_ext->gfp_mask = gfp_mask; + + __set_bit(PAGE_EXT_OWNER, &page_ext->flags); +} + +static ssize_t +print_page_owner(char __user *buf, size_t count, unsigned long pfn, + struct page *page, struct page_ext *page_ext) +{ + int ret; + int pageblock_mt, page_mt; + char *kbuf; + + kbuf = kmalloc(count, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; + + ret = snprintf(kbuf, count, + "Page allocated via order %u, mask 0x%x\n", + page_ext->order, page_ext->gfp_mask); + + if (ret >= count) + goto err; + + /* Print information relevant to grouping pages by mobility */ + pageblock_mt = get_pfnblock_migratetype(page, pfn); + page_mt = gfpflags_to_migratetype(page_ext->gfp_mask); + ret += snprintf(kbuf + ret, count - ret, + "PFN %lu Block %lu type %d %s Flags %s%s%s%s%s%s%s%s%s%s%s%s\n", + pfn, + pfn >> pageblock_order, + pageblock_mt, + pageblock_mt != page_mt ? "Fallback" : " ", + PageLocked(page) ? "K" : " ", + PageError(page) ? "E" : " ", + PageReferenced(page) ? "R" : " ", + PageUptodate(page) ? "U" : " ", + PageDirty(page) ? "D" : " ", + PageLRU(page) ? "L" : " ", + PageActive(page) ? "A" : " ", + PageSlab(page) ? "S" : " ", + PageWriteback(page) ? "W" : " ", + PageCompound(page) ? "C" : " ", + PageSwapCache(page) ? "B" : " ", + PageMappedToDisk(page) ? "M" : " "); + + if (ret >= count) + goto err; + + ret += snprint_stack_trace(kbuf + ret, count - ret, + &page_ext->trace, 0); + if (ret >= count) + goto err; + + ret += snprintf(kbuf + ret, count - ret, "\n"); + if (ret >= count) + goto err; + + if (copy_to_user(buf, kbuf, ret)) + ret = -EFAULT; + + kfree(kbuf); + return ret; + +err: + kfree(kbuf); + return -ENOMEM; +} + +static ssize_t +read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + unsigned long pfn; + struct page *page; + struct page_ext *page_ext; + + if (!page_owner_inited) + return -EINVAL; + + page = NULL; + pfn = min_low_pfn + *ppos; + + /* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */ + while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) + pfn++; + + drain_all_pages(NULL); + + /* Find an allocated page */ + for (; pfn < max_pfn; pfn++) { + /* + * If the new page is in a new MAX_ORDER_NR_PAGES area, + * validate the area as existing, skip it if not + */ + if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0 && !pfn_valid(pfn)) { + pfn += MAX_ORDER_NR_PAGES - 1; + continue; + } + + /* Check for holes within a MAX_ORDER area */ + if (!pfn_valid_within(pfn)) + continue; + + page = pfn_to_page(pfn); + if (PageBuddy(page)) { + unsigned long freepage_order = page_order_unsafe(page); + + if (freepage_order < MAX_ORDER) + pfn += (1UL << freepage_order) - 1; + continue; + } + + page_ext = lookup_page_ext(page); + + /* + * Some pages could be missed by concurrent allocation or free, + * because we don't hold the zone lock. + */ + if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) + continue; + + /* Record the next PFN to read in the file offset */ + *ppos = (pfn - min_low_pfn) + 1; + + return print_page_owner(buf, count, pfn, page, page_ext); + } + + return 0; +} + +static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) +{ + struct page *page; + struct page_ext *page_ext; + unsigned long pfn = zone->zone_start_pfn, block_end_pfn; + unsigned long end_pfn = pfn + zone->spanned_pages; + unsigned long count = 0; + + /* Scan block by block. First and last block may be incomplete */ + pfn = zone->zone_start_pfn; + + /* + * Walk the zone in pageblock_nr_pages steps. If a page block spans + * a zone boundary, it will be double counted between zones. This does + * not matter as the mixed block count will still be correct + */ + for (; pfn < end_pfn; ) { + if (!pfn_valid(pfn)) { + pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); + continue; + } + + block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); + block_end_pfn = min(block_end_pfn, end_pfn); + + page = pfn_to_page(pfn); + + for (; pfn < block_end_pfn; pfn++) { + if (!pfn_valid_within(pfn)) + continue; + + page = pfn_to_page(pfn); + + /* + * We are safe to check buddy flag and order, because + * this is init stage and only single thread runs. + */ + if (PageBuddy(page)) { + pfn += (1UL << page_order(page)) - 1; + continue; + } + + if (PageReserved(page)) + continue; + + page_ext = lookup_page_ext(page); + + /* Maybe overraping zone */ + if (test_bit(PAGE_EXT_OWNER, &page_ext->flags)) + continue; + + /* Found early allocated page */ + set_page_owner(page, 0, 0); + count++; + } + } + + pr_info("Node %d, zone %8s: page owner found early allocated %lu pages\n", + pgdat->node_id, zone->name, count); +} + +static void init_zones_in_node(pg_data_t *pgdat) +{ + struct zone *zone; + struct zone *node_zones = pgdat->node_zones; + unsigned long flags; + + for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { + if (!populated_zone(zone)) + continue; + + spin_lock_irqsave(&zone->lock, flags); + init_pages_in_zone(pgdat, zone); + spin_unlock_irqrestore(&zone->lock, flags); + } +} + +static void init_early_allocated_pages(void) +{ + pg_data_t *pgdat; + + drain_all_pages(NULL); + for_each_online_pgdat(pgdat) + init_zones_in_node(pgdat); +} + +static const struct file_operations proc_page_owner_operations = { + .read = read_page_owner, +}; + +static int __init pageowner_init(void) +{ + struct dentry *dentry; + + if (!page_owner_inited) { + pr_info("page_owner is disabled\n"); + return 0; + } + + dentry = debugfs_create_file("page_owner", S_IRUSR, NULL, + NULL, &proc_page_owner_operations); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + + return 0; +} +module_init(pageowner_init) @@ -23,7 +23,7 @@ * inode->i_mutex (while writing or truncating, not reading or faulting) * mm->mmap_sem * page->flags PG_locked (lock_page) - * mapping->i_mmap_mutex + * mapping->i_mmap_rwsem * anon_vma->rwsem * mm->page_table_lock or pte_lock * zone->lru_lock (in mark_page_accessed, isolate_lru_page) @@ -1260,7 +1260,7 @@ out_mlock: /* * We need mmap_sem locking, Otherwise VM_LOCKED check makes * unstable result and race. Plus, We can't wait here because - * we now hold anon_vma->rwsem or mapping->i_mmap_mutex. + * we now hold anon_vma->rwsem or mapping->i_mmap_rwsem. * if trylock failed, the page remain in evictable lru and later * vmscan could retry to move the page to unevictable lru if the * page is actually mlocked. @@ -1635,7 +1635,7 @@ static struct anon_vma *rmap_walk_anon_lock(struct page *page, static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; - pgoff_t pgoff = page_to_pgoff(page); + pgoff_t pgoff; struct anon_vma_chain *avc; int ret = SWAP_AGAIN; @@ -1643,6 +1643,7 @@ static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc) if (!anon_vma) return ret; + pgoff = page_to_pgoff(page); anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); @@ -1676,7 +1677,7 @@ static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc) static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc) { struct address_space *mapping = page->mapping; - pgoff_t pgoff = page_to_pgoff(page); + pgoff_t pgoff; struct vm_area_struct *vma; int ret = SWAP_AGAIN; @@ -1684,13 +1685,15 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc) * The page lock not only makes sure that page->mapping cannot * suddenly be NULLified by truncation, it makes sure that the * structure at mapping cannot be freed and reused yet, - * so we can safely take mapping->i_mmap_mutex. + * so we can safely take mapping->i_mmap_rwsem. */ VM_BUG_ON_PAGE(!PageLocked(page), page); if (!mapping) return ret; - mutex_lock(&mapping->i_mmap_mutex); + + pgoff = page_to_pgoff(page); + i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { unsigned long address = vma_address(page, vma); @@ -1711,9 +1714,8 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc) goto done; ret = rwc->file_nonlinear(page, mapping, rwc->arg); - done: - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_read(mapping); return ret; } @@ -3015,7 +3015,7 @@ retry: for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { nid = zone_to_nid(zone); - if (cpuset_zone_allowed(zone, flags | __GFP_HARDWALL) && + if (cpuset_zone_allowed(zone, flags) && get_node(cache, nid) && get_node(cache, nid)->free_objects) { obj = ____cache_alloc_node(cache, @@ -3182,6 +3182,7 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, memset(ptr, 0, cachep->object_size); } + memcg_kmem_put_cache(cachep); return ptr; } @@ -3247,6 +3248,7 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller) memset(objp, 0, cachep->object_size); } + memcg_kmem_put_cache(cachep); return objp; } @@ -1233,13 +1233,17 @@ static inline void kfree_hook(const void *x) kmemleak_free(x); } -static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags) +static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, + gfp_t flags) { flags &= gfp_allowed_mask; lockdep_trace_alloc(flags); might_sleep_if(flags & __GFP_WAIT); - return should_failslab(s->object_size, flags, s->flags); + if (should_failslab(s->object_size, flags, s->flags)) + return NULL; + + return memcg_kmem_get_cache(s, flags); } static inline void slab_post_alloc_hook(struct kmem_cache *s, @@ -1248,6 +1252,7 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, flags &= gfp_allowed_mask; kmemcheck_slab_alloc(s, flags, object, slab_ksize(s)); kmemleak_alloc_recursive(object, s->object_size, 1, s->flags, flags); + memcg_kmem_put_cache(s); } static inline void slab_free_hook(struct kmem_cache *s, void *x) @@ -1665,8 +1670,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, n = get_node(s, zone_to_nid(zone)); - if (n && cpuset_zone_allowed(zone, - flags | __GFP_HARDWALL) && + if (n && cpuset_zone_allowed(zone, flags) && n->nr_partial > s->min_partial) { object = get_partial_node(s, n, c, flags); if (object) { @@ -2384,10 +2388,9 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s, struct page *page; unsigned long tid; - if (slab_pre_alloc_hook(s, gfpflags)) + s = slab_pre_alloc_hook(s, gfpflags); + if (!s) return NULL; - - s = memcg_kmem_get_cache(s, gfpflags); redo: /* * Must read kmem_cache cpu data via this cpu ptr. Preemption is diff --git a/mm/vmacache.c b/mm/vmacache.c index 9f25af8..b6e3662 100644 --- a/mm/vmacache.c +++ b/mm/vmacache.c @@ -17,6 +17,8 @@ void vmacache_flush_all(struct mm_struct *mm) { struct task_struct *g, *p; + count_vm_vmacache_event(VMACACHE_FULL_FLUSHES); + /* * Single threaded tasks need not iterate the entire * list of process. We can avoid the flushing as well diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 8a18196..39c3388 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2574,10 +2574,10 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v) if (!counters) return; - /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ - smp_rmb(); if (v->flags & VM_UNINITIALIZED) return; + /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ + smp_rmb(); memset(counters, 0, nr_node_ids * sizeof(unsigned int)); diff --git a/mm/vmscan.c b/mm/vmscan.c index a384339..bd9a72b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -229,9 +229,10 @@ EXPORT_SYMBOL(unregister_shrinker); #define SHRINK_BATCH 128 -static unsigned long -shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, - unsigned long nr_pages_scanned, unsigned long lru_pages) +static unsigned long shrink_slabs(struct shrink_control *shrinkctl, + struct shrinker *shrinker, + unsigned long nr_scanned, + unsigned long nr_eligible) { unsigned long freed = 0; unsigned long long delta; @@ -255,9 +256,9 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0); total_scan = nr; - delta = (4 * nr_pages_scanned) / shrinker->seeks; + delta = (4 * nr_scanned) / shrinker->seeks; delta *= freeable; - do_div(delta, lru_pages + 1); + do_div(delta, nr_eligible + 1); total_scan += delta; if (total_scan < 0) { pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n", @@ -289,8 +290,8 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, total_scan = freeable * 2; trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, - nr_pages_scanned, lru_pages, - freeable, delta, total_scan); + nr_scanned, nr_eligible, + freeable, delta, total_scan); /* * Normally, we should not scan less than batch_size objects in one @@ -339,34 +340,37 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, return freed; } -/* - * Call the shrink functions to age shrinkable caches - * - * Here we assume it costs one seek to replace a lru page and that it also - * takes a seek to recreate a cache object. With this in mind we age equal - * percentages of the lru and ageable caches. This should balance the seeks - * generated by these structures. +/** + * shrink_node_slabs - shrink slab caches of a given node + * @gfp_mask: allocation context + * @nid: node whose slab caches to target + * @nr_scanned: pressure numerator + * @nr_eligible: pressure denominator * - * If the vm encountered mapped pages on the LRU it increase the pressure on - * slab to avoid swapping. + * Call the shrink functions to age shrinkable caches. * - * We do weird things to avoid (scanned*seeks*entries) overflowing 32 bits. + * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, + * unaware shrinkers will receive a node id of 0 instead. * - * `lru_pages' represents the number of on-LRU pages in all the zones which - * are eligible for the caller's allocation attempt. It is used for balancing - * slab reclaim versus page reclaim. + * @nr_scanned and @nr_eligible form a ratio that indicate how much of + * the available objects should be scanned. Page reclaim for example + * passes the number of pages scanned and the number of pages on the + * LRU lists that it considered on @nid, plus a bias in @nr_scanned + * when it encountered mapped pages. The ratio is further biased by + * the ->seeks setting of the shrink function, which indicates the + * cost to recreate an object relative to that of an LRU page. * - * Returns the number of slab objects which we shrunk. + * Returns the number of reclaimed slab objects. */ -unsigned long shrink_slab(struct shrink_control *shrinkctl, - unsigned long nr_pages_scanned, - unsigned long lru_pages) +unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid, + unsigned long nr_scanned, + unsigned long nr_eligible) { struct shrinker *shrinker; unsigned long freed = 0; - if (nr_pages_scanned == 0) - nr_pages_scanned = SWAP_CLUSTER_MAX; + if (nr_scanned == 0) + nr_scanned = SWAP_CLUSTER_MAX; if (!down_read_trylock(&shrinker_rwsem)) { /* @@ -380,20 +384,17 @@ unsigned long shrink_slab(struct shrink_control *shrinkctl, } list_for_each_entry(shrinker, &shrinker_list, list) { - if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) { - shrinkctl->nid = 0; - freed += shrink_slab_node(shrinkctl, shrinker, - nr_pages_scanned, lru_pages); - continue; - } + struct shrink_control sc = { + .gfp_mask = gfp_mask, + .nid = nid, + }; - for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) { - if (node_online(shrinkctl->nid)) - freed += shrink_slab_node(shrinkctl, shrinker, - nr_pages_scanned, lru_pages); + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) + sc.nid = 0; - } + freed += shrink_slabs(&sc, shrinker, nr_scanned, nr_eligible); } + up_read(&shrinker_rwsem); out: cond_resched(); @@ -1876,7 +1877,8 @@ enum scan_balance { * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan */ static void get_scan_count(struct lruvec *lruvec, int swappiness, - struct scan_control *sc, unsigned long *nr) + struct scan_control *sc, unsigned long *nr, + unsigned long *lru_pages) { struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; u64 fraction[2]; @@ -2022,6 +2024,7 @@ out: some_scanned = false; /* Only use force_scan on second pass. */ for (pass = 0; !some_scanned && pass < 2; pass++) { + *lru_pages = 0; for_each_evictable_lru(lru) { int file = is_file_lru(lru); unsigned long size; @@ -2048,14 +2051,19 @@ out: case SCAN_FILE: case SCAN_ANON: /* Scan one type exclusively */ - if ((scan_balance == SCAN_FILE) != file) + if ((scan_balance == SCAN_FILE) != file) { + size = 0; scan = 0; + } break; default: /* Look ma, no brain */ BUG(); } + + *lru_pages += size; nr[lru] = scan; + /* * Skip the second pass and don't force_scan, * if we found something to scan. @@ -2069,7 +2077,7 @@ out: * This is a basic per-zone page freer. Used by both kswapd and direct reclaim. */ static void shrink_lruvec(struct lruvec *lruvec, int swappiness, - struct scan_control *sc) + struct scan_control *sc, unsigned long *lru_pages) { unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; @@ -2080,7 +2088,7 @@ static void shrink_lruvec(struct lruvec *lruvec, int swappiness, struct blk_plug plug; bool scan_adjusted; - get_scan_count(lruvec, swappiness, sc, nr); + get_scan_count(lruvec, swappiness, sc, nr, lru_pages); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); @@ -2258,7 +2266,8 @@ static inline bool should_continue_reclaim(struct zone *zone, } } -static bool shrink_zone(struct zone *zone, struct scan_control *sc) +static bool shrink_zone(struct zone *zone, struct scan_control *sc, + bool is_classzone) { unsigned long nr_reclaimed, nr_scanned; bool reclaimable = false; @@ -2269,6 +2278,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc) .zone = zone, .priority = sc->priority, }; + unsigned long zone_lru_pages = 0; struct mem_cgroup *memcg; nr_reclaimed = sc->nr_reclaimed; @@ -2276,13 +2286,15 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc) memcg = mem_cgroup_iter(root, NULL, &reclaim); do { + unsigned long lru_pages; struct lruvec *lruvec; int swappiness; lruvec = mem_cgroup_zone_lruvec(zone, memcg); swappiness = mem_cgroup_swappiness(memcg); - shrink_lruvec(lruvec, swappiness, sc); + shrink_lruvec(lruvec, swappiness, sc, &lru_pages); + zone_lru_pages += lru_pages; /* * Direct reclaim and kswapd have to scan all memory @@ -2302,6 +2314,25 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc) memcg = mem_cgroup_iter(root, memcg, &reclaim); } while (memcg); + /* + * Shrink the slab caches in the same proportion that + * the eligible LRU pages were scanned. + */ + if (global_reclaim(sc) && is_classzone) { + struct reclaim_state *reclaim_state; + + shrink_node_slabs(sc->gfp_mask, zone_to_nid(zone), + sc->nr_scanned - nr_scanned, + zone_lru_pages); + + reclaim_state = current->reclaim_state; + if (reclaim_state) { + sc->nr_reclaimed += + reclaim_state->reclaimed_slab; + reclaim_state->reclaimed_slab = 0; + } + } + vmpressure(sc->gfp_mask, sc->target_mem_cgroup, sc->nr_scanned - nr_scanned, sc->nr_reclaimed - nr_reclaimed); @@ -2376,12 +2407,7 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; - unsigned long lru_pages = 0; - struct reclaim_state *reclaim_state = current->reclaim_state; gfp_t orig_mask; - struct shrink_control shrink = { - .gfp_mask = sc->gfp_mask, - }; enum zone_type requested_highidx = gfp_zone(sc->gfp_mask); bool reclaimable = false; @@ -2394,12 +2420,18 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) if (buffer_heads_over_limit) sc->gfp_mask |= __GFP_HIGHMEM; - nodes_clear(shrink.nodes_to_scan); - for_each_zone_zonelist_nodemask(zone, z, zonelist, - gfp_zone(sc->gfp_mask), sc->nodemask) { + requested_highidx, sc->nodemask) { + enum zone_type classzone_idx; + if (!populated_zone(zone)) continue; + + classzone_idx = requested_highidx; + while (!populated_zone(zone->zone_pgdat->node_zones + + classzone_idx)) + classzone_idx--; + /* * Take care memory controller reclaiming has small influence * to global LRU. @@ -2409,9 +2441,6 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) GFP_KERNEL | __GFP_HARDWALL)) continue; - lru_pages += zone_reclaimable_pages(zone); - node_set(zone_to_nid(zone), shrink.nodes_to_scan); - if (sc->priority != DEF_PRIORITY && !zone_reclaimable(zone)) continue; /* Let kswapd poll it */ @@ -2450,7 +2479,7 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) /* need some check for avoid more shrink_zone() */ } - if (shrink_zone(zone, sc)) + if (shrink_zone(zone, sc, zone_idx(zone) == classzone_idx)) reclaimable = true; if (global_reclaim(sc) && @@ -2459,20 +2488,6 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) } /* - * Don't shrink slabs when reclaiming memory from over limit cgroups - * but do shrink slab at least once when aborting reclaim for - * compaction to avoid unevenly scanning file/anon LRU pages over slab - * pages. - */ - if (global_reclaim(sc)) { - shrink_slab(&shrink, sc->nr_scanned, lru_pages); - if (reclaim_state) { - sc->nr_reclaimed += reclaim_state->reclaimed_slab; - reclaim_state->reclaimed_slab = 0; - } - } - - /* * Restore to original mask to avoid the impact on the caller if we * promoted it to __GFP_HIGHMEM. */ @@ -2736,6 +2751,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, }; struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg); int swappiness = mem_cgroup_swappiness(memcg); + unsigned long lru_pages; sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); @@ -2751,7 +2767,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, * will pick up pages from other mem cgroup's as well. We hack * the priority and make it zero. */ - shrink_lruvec(lruvec, swappiness, &sc); + shrink_lruvec(lruvec, swappiness, &sc, &lru_pages); trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); @@ -2932,15 +2948,10 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, static bool kswapd_shrink_zone(struct zone *zone, int classzone_idx, struct scan_control *sc, - unsigned long lru_pages, unsigned long *nr_attempted) { int testorder = sc->order; unsigned long balance_gap; - struct reclaim_state *reclaim_state = current->reclaim_state; - struct shrink_control shrink = { - .gfp_mask = sc->gfp_mask, - }; bool lowmem_pressure; /* Reclaim above the high watermark. */ @@ -2975,13 +2986,7 @@ static bool kswapd_shrink_zone(struct zone *zone, balance_gap, classzone_idx)) return true; - shrink_zone(zone, sc); - nodes_clear(shrink.nodes_to_scan); - node_set(zone_to_nid(zone), shrink.nodes_to_scan); - - reclaim_state->reclaimed_slab = 0; - shrink_slab(&shrink, sc->nr_scanned, lru_pages); - sc->nr_reclaimed += reclaim_state->reclaimed_slab; + shrink_zone(zone, sc, zone_idx(zone) == classzone_idx); /* Account for the number of pages attempted to reclaim */ *nr_attempted += sc->nr_to_reclaim; @@ -3042,7 +3047,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, count_vm_event(PAGEOUTRUN); do { - unsigned long lru_pages = 0; unsigned long nr_attempted = 0; bool raise_priority = true; bool pgdat_needs_compaction = (order > 0); @@ -3102,8 +3106,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, if (!populated_zone(zone)) continue; - lru_pages += zone_reclaimable_pages(zone); - /* * If any zone is currently balanced then kswapd will * not call compaction as it is expected that the @@ -3159,8 +3161,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, * that that high watermark would be met at 100% * efficiency. */ - if (kswapd_shrink_zone(zone, end_zone, &sc, - lru_pages, &nr_attempted)) + if (kswapd_shrink_zone(zone, end_zone, + &sc, &nr_attempted)) raise_priority = false; } @@ -3612,10 +3614,6 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) .may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP), .may_swap = 1, }; - struct shrink_control shrink = { - .gfp_mask = sc.gfp_mask, - }; - unsigned long nr_slab_pages0, nr_slab_pages1; cond_resched(); /* @@ -3634,44 +3632,10 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) * priorities until we have enough memory freed. */ do { - shrink_zone(zone, &sc); + shrink_zone(zone, &sc, true); } while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0); } - nr_slab_pages0 = zone_page_state(zone, NR_SLAB_RECLAIMABLE); - if (nr_slab_pages0 > zone->min_slab_pages) { - /* - * shrink_slab() does not currently allow us to determine how - * many pages were freed in this zone. So we take the current - * number of slab pages and shake the slab until it is reduced - * by the same nr_pages that we used for reclaiming unmapped - * pages. - */ - nodes_clear(shrink.nodes_to_scan); - node_set(zone_to_nid(zone), shrink.nodes_to_scan); - for (;;) { - unsigned long lru_pages = zone_reclaimable_pages(zone); - - /* No reclaimable slab or very low memory pressure */ - if (!shrink_slab(&shrink, sc.nr_scanned, lru_pages)) - break; - - /* Freed enough memory */ - nr_slab_pages1 = zone_page_state(zone, - NR_SLAB_RECLAIMABLE); - if (nr_slab_pages1 + nr_pages <= nr_slab_pages0) - break; - } - - /* - * Update nr_reclaimed by the number of slab pages we - * reclaimed from this zone. - */ - nr_slab_pages1 = zone_page_state(zone, NR_SLAB_RECLAIMABLE); - if (nr_slab_pages1 < nr_slab_pages0) - sc.nr_reclaimed += nr_slab_pages0 - nr_slab_pages1; - } - p->reclaim_state = NULL; current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE); lockdep_clear_current_reclaim_state(); diff --git a/mm/vmstat.c b/mm/vmstat.c index 1b12d39..1284f89 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -22,6 +22,8 @@ #include <linux/writeback.h> #include <linux/compaction.h> #include <linux/mm_inline.h> +#include <linux/page_ext.h> +#include <linux/page_owner.h> #include "internal.h" @@ -898,6 +900,7 @@ const char * const vmstat_text[] = { #ifdef CONFIG_DEBUG_VM_VMACACHE "vmacache_find_calls", "vmacache_find_hits", + "vmacache_full_flushes", #endif #endif /* CONFIG_VM_EVENTS_COUNTERS */ }; @@ -1017,6 +1020,104 @@ static int pagetypeinfo_showblockcount(struct seq_file *m, void *arg) return 0; } +#ifdef CONFIG_PAGE_OWNER +static void pagetypeinfo_showmixedcount_print(struct seq_file *m, + pg_data_t *pgdat, + struct zone *zone) +{ + struct page *page; + struct page_ext *page_ext; + unsigned long pfn = zone->zone_start_pfn, block_end_pfn; + unsigned long end_pfn = pfn + zone->spanned_pages; + unsigned long count[MIGRATE_TYPES] = { 0, }; + int pageblock_mt, page_mt; + int i; + + /* Scan block by block. First and last block may be incomplete */ + pfn = zone->zone_start_pfn; + + /* + * Walk the zone in pageblock_nr_pages steps. If a page block spans + * a zone boundary, it will be double counted between zones. This does + * not matter as the mixed block count will still be correct + */ + for (; pfn < end_pfn; ) { + if (!pfn_valid(pfn)) { + pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); + continue; + } + + block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); + block_end_pfn = min(block_end_pfn, end_pfn); + + page = pfn_to_page(pfn); + pageblock_mt = get_pfnblock_migratetype(page, pfn); + + for (; pfn < block_end_pfn; pfn++) { + if (!pfn_valid_within(pfn)) + continue; + + page = pfn_to_page(pfn); + if (PageBuddy(page)) { + pfn += (1UL << page_order(page)) - 1; + continue; + } + + if (PageReserved(page)) + continue; + + page_ext = lookup_page_ext(page); + + if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) + continue; + + page_mt = gfpflags_to_migratetype(page_ext->gfp_mask); + if (pageblock_mt != page_mt) { + if (is_migrate_cma(pageblock_mt)) + count[MIGRATE_MOVABLE]++; + else + count[pageblock_mt]++; + + pfn = block_end_pfn; + break; + } + pfn += (1UL << page_ext->order) - 1; + } + } + + /* Print counts */ + seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); + for (i = 0; i < MIGRATE_TYPES; i++) + seq_printf(m, "%12lu ", count[i]); + seq_putc(m, '\n'); +} +#endif /* CONFIG_PAGE_OWNER */ + +/* + * Print out the number of pageblocks for each migratetype that contain pages + * of other types. This gives an indication of how well fallbacks are being + * contained by rmqueue_fallback(). It requires information from PAGE_OWNER + * to determine what is going on + */ +static void pagetypeinfo_showmixedcount(struct seq_file *m, pg_data_t *pgdat) +{ +#ifdef CONFIG_PAGE_OWNER + int mtype; + + if (!page_owner_inited) + return; + + drain_all_pages(NULL); + + seq_printf(m, "\n%-23s", "Number of mixed blocks "); + for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) + seq_printf(m, "%12s ", migratetype_names[mtype]); + seq_putc(m, '\n'); + + walk_zones_in_node(m, pgdat, pagetypeinfo_showmixedcount_print); +#endif /* CONFIG_PAGE_OWNER */ +} + /* * This prints out statistics in relation to grouping pages by mobility. * It is expensive to collect so do not constantly read the file. @@ -1034,6 +1135,7 @@ static int pagetypeinfo_show(struct seq_file *m, void *arg) seq_putc(m, '\n'); pagetypeinfo_showfree(m, pgdat); pagetypeinfo_showblockcount(m, pgdat); + pagetypeinfo_showmixedcount(m, pgdat); return 0; } @@ -132,7 +132,7 @@ static struct zbud_ops zbud_zpool_ops = { static void *zbud_zpool_create(gfp_t gfp, struct zpool_ops *zpool_ops) { - return zbud_create_pool(gfp, &zbud_zpool_ops); + return zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL); } static void zbud_zpool_destroy(void *pool) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 839a48c..4d0a063 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -155,8 +155,6 @@ * (reason above) */ #define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> 8) -#define ZS_SIZE_CLASSES ((ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) / \ - ZS_SIZE_CLASS_DELTA + 1) /* * We do not maintain any list for completely empty or full pages @@ -171,6 +169,11 @@ enum fullness_group { }; /* + * number of size_classes + */ +static int zs_size_classes; + +/* * We assign a page to ZS_ALMOST_EMPTY fullness group when: * n <= N / f, where * n = number of allocated objects @@ -214,7 +217,7 @@ struct link_free { }; struct zs_pool { - struct size_class size_class[ZS_SIZE_CLASSES]; + struct size_class **size_class; gfp_t flags; /* allocation flags used when growing pool */ atomic_long_t pages_allocated; @@ -468,7 +471,7 @@ static enum fullness_group fix_fullness_group(struct zs_pool *pool, if (newfg == currfg) goto out; - class = &pool->size_class[class_idx]; + class = pool->size_class[class_idx]; remove_zspage(page, class, currfg); insert_zspage(page, class, newfg); set_zspage_mapping(page, class_idx, newfg); @@ -629,6 +632,7 @@ static void init_zspage(struct page *first_page, struct size_class *class) struct page *next_page; struct link_free *link; unsigned int i = 1; + void *vaddr; /* * page->index stores offset of first object starting @@ -639,8 +643,8 @@ static void init_zspage(struct page *first_page, struct size_class *class) if (page != first_page) page->index = off; - link = (struct link_free *)kmap_atomic(page) + - off / sizeof(*link); + vaddr = kmap_atomic(page); + link = (struct link_free *)vaddr + off / sizeof(*link); while ((off += class->size) < PAGE_SIZE) { link->next = obj_location_to_handle(page, i++); @@ -654,7 +658,7 @@ static void init_zspage(struct page *first_page, struct size_class *class) */ next_page = get_next_page(page); link->next = obj_location_to_handle(next_page, 0); - kunmap_atomic(link); + kunmap_atomic(vaddr); page = next_page; off %= PAGE_SIZE; } @@ -784,7 +788,7 @@ static inline int __zs_cpu_up(struct mapping_area *area) */ if (area->vm_buf) return 0; - area->vm_buf = (char *)__get_free_page(GFP_KERNEL); + area->vm_buf = kmalloc(ZS_MAX_ALLOC_SIZE, GFP_KERNEL); if (!area->vm_buf) return -ENOMEM; return 0; @@ -792,8 +796,7 @@ static inline int __zs_cpu_up(struct mapping_area *area) static inline void __zs_cpu_down(struct mapping_area *area) { - if (area->vm_buf) - free_page((unsigned long)area->vm_buf); + kfree(area->vm_buf); area->vm_buf = NULL; } @@ -881,14 +884,10 @@ static struct notifier_block zs_cpu_nb = { .notifier_call = zs_cpu_notifier }; -static void zs_exit(void) +static void zs_unregister_cpu_notifier(void) { int cpu; -#ifdef CONFIG_ZPOOL - zpool_unregister_driver(&zs_zpool_driver); -#endif - cpu_notifier_register_begin(); for_each_online_cpu(cpu) @@ -898,31 +897,74 @@ static void zs_exit(void) cpu_notifier_register_done(); } -static int zs_init(void) +static int zs_register_cpu_notifier(void) { - int cpu, ret; + int cpu, uninitialized_var(ret); cpu_notifier_register_begin(); __register_cpu_notifier(&zs_cpu_nb); for_each_online_cpu(cpu) { ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu); - if (notifier_to_errno(ret)) { - cpu_notifier_register_done(); - goto fail; - } + if (notifier_to_errno(ret)) + break; } cpu_notifier_register_done(); + return notifier_to_errno(ret); +} + +static void init_zs_size_classes(void) +{ + int nr; + nr = (ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) / ZS_SIZE_CLASS_DELTA + 1; + if ((ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) % ZS_SIZE_CLASS_DELTA) + nr += 1; + + zs_size_classes = nr; +} + +static void __exit zs_exit(void) +{ #ifdef CONFIG_ZPOOL - zpool_register_driver(&zs_zpool_driver); + zpool_unregister_driver(&zs_zpool_driver); #endif + zs_unregister_cpu_notifier(); +} +static int __init zs_init(void) +{ + int ret = zs_register_cpu_notifier(); + + if (ret) { + zs_unregister_cpu_notifier(); + return ret; + } + + init_zs_size_classes(); + +#ifdef CONFIG_ZPOOL + zpool_register_driver(&zs_zpool_driver); +#endif return 0; -fail: - zs_exit(); - return notifier_to_errno(ret); +} + +static unsigned int get_maxobj_per_zspage(int size, int pages_per_zspage) +{ + return pages_per_zspage * PAGE_SIZE / size; +} + +static bool can_merge(struct size_class *prev, int size, int pages_per_zspage) +{ + if (prev->pages_per_zspage != pages_per_zspage) + return false; + + if (get_maxobj_per_zspage(prev->size, prev->pages_per_zspage) + != get_maxobj_per_zspage(size, pages_per_zspage)) + return false; + + return true; } /** @@ -937,33 +979,71 @@ fail: */ struct zs_pool *zs_create_pool(gfp_t flags) { - int i, ovhd_size; + int i; struct zs_pool *pool; + struct size_class *prev_class = NULL; - ovhd_size = roundup(sizeof(*pool), PAGE_SIZE); - pool = kzalloc(ovhd_size, GFP_KERNEL); + pool = kzalloc(sizeof(*pool), GFP_KERNEL); if (!pool) return NULL; - for (i = 0; i < ZS_SIZE_CLASSES; i++) { + pool->size_class = kcalloc(zs_size_classes, sizeof(struct size_class *), + GFP_KERNEL); + if (!pool->size_class) { + kfree(pool); + return NULL; + } + + /* + * Iterate reversly, because, size of size_class that we want to use + * for merging should be larger or equal to current size. + */ + for (i = zs_size_classes - 1; i >= 0; i--) { int size; + int pages_per_zspage; struct size_class *class; size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA; if (size > ZS_MAX_ALLOC_SIZE) size = ZS_MAX_ALLOC_SIZE; + pages_per_zspage = get_pages_per_zspage(size); + + /* + * size_class is used for normal zsmalloc operation such + * as alloc/free for that size. Although it is natural that we + * have one size_class for each size, there is a chance that we + * can get more memory utilization if we use one size_class for + * many different sizes whose size_class have same + * characteristics. So, we makes size_class point to + * previous size_class if possible. + */ + if (prev_class) { + if (can_merge(prev_class, size, pages_per_zspage)) { + pool->size_class[i] = prev_class; + continue; + } + } + + class = kzalloc(sizeof(struct size_class), GFP_KERNEL); + if (!class) + goto err; - class = &pool->size_class[i]; class->size = size; class->index = i; + class->pages_per_zspage = pages_per_zspage; spin_lock_init(&class->lock); - class->pages_per_zspage = get_pages_per_zspage(size); + pool->size_class[i] = class; + prev_class = class; } pool->flags = flags; return pool; + +err: + zs_destroy_pool(pool); + return NULL; } EXPORT_SYMBOL_GPL(zs_create_pool); @@ -971,9 +1051,15 @@ void zs_destroy_pool(struct zs_pool *pool) { int i; - for (i = 0; i < ZS_SIZE_CLASSES; i++) { + for (i = 0; i < zs_size_classes; i++) { int fg; - struct size_class *class = &pool->size_class[i]; + struct size_class *class = pool->size_class[i]; + + if (!class) + continue; + + if (class->index != i) + continue; for (fg = 0; fg < _ZS_NR_FULLNESS_GROUPS; fg++) { if (class->fullness_list[fg]) { @@ -981,7 +1067,10 @@ void zs_destroy_pool(struct zs_pool *pool) class->size, fg); } } + kfree(class); } + + kfree(pool->size_class); kfree(pool); } EXPORT_SYMBOL_GPL(zs_destroy_pool); @@ -999,8 +1088,8 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size) { unsigned long obj; struct link_free *link; - int class_idx; struct size_class *class; + void *vaddr; struct page *first_page, *m_page; unsigned long m_objidx, m_offset; @@ -1008,9 +1097,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size) if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE)) return 0; - class_idx = get_size_class_index(size); - class = &pool->size_class[class_idx]; - BUG_ON(class_idx != class->index); + class = pool->size_class[get_size_class_index(size)]; spin_lock(&class->lock); first_page = find_get_zspage(class); @@ -1031,11 +1118,11 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size) obj_handle_to_location(obj, &m_page, &m_objidx); m_offset = obj_idx_to_offset(m_page, m_objidx, class->size); - link = (struct link_free *)kmap_atomic(m_page) + - m_offset / sizeof(*link); + vaddr = kmap_atomic(m_page); + link = (struct link_free *)vaddr + m_offset / sizeof(*link); first_page->freelist = link->next; memset(link, POISON_INUSE, sizeof(*link)); - kunmap_atomic(link); + kunmap_atomic(vaddr); first_page->inuse++; /* Now move the zspage to another fullness group, if required */ @@ -1051,6 +1138,7 @@ void zs_free(struct zs_pool *pool, unsigned long obj) struct link_free *link; struct page *first_page, *f_page; unsigned long f_objidx, f_offset; + void *vaddr; int class_idx; struct size_class *class; @@ -1063,16 +1151,16 @@ void zs_free(struct zs_pool *pool, unsigned long obj) first_page = get_first_page(f_page); get_zspage_mapping(first_page, &class_idx, &fullness); - class = &pool->size_class[class_idx]; + class = pool->size_class[class_idx]; f_offset = obj_idx_to_offset(f_page, f_objidx, class->size); spin_lock(&class->lock); /* Insert this object in containing zspage's freelist */ - link = (struct link_free *)((unsigned char *)kmap_atomic(f_page) - + f_offset); + vaddr = kmap_atomic(f_page); + link = (struct link_free *)(vaddr + f_offset); link->next = first_page->freelist; - kunmap_atomic(link); + kunmap_atomic(vaddr); first_page->freelist = (void *)obj; first_page->inuse--; @@ -1124,7 +1212,7 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, obj_handle_to_location(handle, &page, &obj_idx); get_zspage_mapping(get_first_page(page), &class_idx, &fg); - class = &pool->size_class[class_idx]; + class = pool->size_class[class_idx]; off = obj_idx_to_offset(page, obj_idx, class->size); area = &get_cpu_var(zs_map_area); @@ -1158,7 +1246,7 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) obj_handle_to_location(handle, &page, &obj_idx); get_zspage_mapping(get_first_page(page), &class_idx, &fg); - class = &pool->size_class[class_idx]; + class = pool->size_class[class_idx]; off = obj_idx_to_offset(page, obj_idx, class->size); area = this_cpu_ptr(&zs_map_area); @@ -149,11 +149,10 @@ static int __init zswap_comp_init(void) return 0; } -static void zswap_comp_exit(void) +static void __init zswap_comp_exit(void) { /* free percpu transforms */ - if (zswap_comp_pcpu_tfms) - free_percpu(zswap_comp_pcpu_tfms); + free_percpu(zswap_comp_pcpu_tfms); } /********************************* @@ -206,7 +205,7 @@ static struct zswap_tree *zswap_trees[MAX_SWAPFILES]; **********************************/ static struct kmem_cache *zswap_entry_cache; -static int zswap_entry_cache_create(void) +static int __init zswap_entry_cache_create(void) { zswap_entry_cache = KMEM_CACHE(zswap_entry, 0); return zswap_entry_cache == NULL; @@ -389,7 +388,7 @@ static struct notifier_block zswap_cpu_notifier_block = { .notifier_call = zswap_cpu_notifier }; -static int zswap_cpu_init(void) +static int __init zswap_cpu_init(void) { unsigned long cpu; |
