diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 3 | ||||
| -rw-r--r-- | mm/Makefile | 3 | ||||
| -rw-r--r-- | mm/backing-dev.c | 5 | ||||
| -rw-r--r-- | mm/compaction.c | 26 | ||||
| -rw-r--r-- | mm/debug-pagealloc.c | 56 | ||||
| -rw-r--r-- | mm/filemap.c | 3 | ||||
| -rw-r--r-- | mm/highmem.c | 2 | ||||
| -rw-r--r-- | mm/huge_memory.c | 54 | ||||
| -rw-r--r-- | mm/ksm.c | 3 | ||||
| -rw-r--r-- | mm/memblock.c | 11 | ||||
| -rw-r--r-- | mm/memcontrol.c | 3 | ||||
| -rw-r--r-- | mm/memory-failure.c | 12 | ||||
| -rw-r--r-- | mm/mempolicy.c | 2 | ||||
| -rw-r--r-- | mm/migrate.c | 83 | ||||
| -rw-r--r-- | mm/mlock.c | 13 | ||||
| -rw-r--r-- | mm/mmap.c | 9 | ||||
| -rw-r--r-- | mm/mremap.c | 42 | ||||
| -rw-r--r-- | mm/oom_kill.c | 53 | ||||
| -rw-r--r-- | mm/page-writeback.c | 4 | ||||
| -rw-r--r-- | mm/page_alloc.c | 17 | ||||
| -rw-r--r-- | mm/page_cgroup.c | 3 | ||||
| -rw-r--r-- | mm/process_vm_access.c | 496 | ||||
| -rw-r--r-- | mm/rmap.c | 2 | ||||
| -rw-r--r-- | mm/shmem.c | 10 | ||||
| -rw-r--r-- | mm/slab.c | 19 | ||||
| -rw-r--r-- | mm/slub.c | 605 | ||||
| -rw-r--r-- | mm/swapfile.c | 2 | ||||
| -rw-r--r-- | mm/thrash.c | 2 | ||||
| -rw-r--r-- | mm/vmalloc.c | 80 | ||||
| -rw-r--r-- | mm/vmscan.c | 327 | ||||
| -rw-r--r-- | mm/vmstat.c | 3 |
31 files changed, 1391 insertions, 562 deletions
@@ -131,6 +131,9 @@ config SPARSEMEM_VMEMMAP config HAVE_MEMBLOCK boolean +config NO_BOOTMEM + boolean + # eventually, we can have this option just 'select SPARSEMEM' config MEMORY_HOTPLUG bool "Allow for memory hot-add" diff --git a/mm/Makefile b/mm/Makefile index 836e416..50ec00e 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -5,7 +5,8 @@ mmu-y := nommu.o mmu-$(CONFIG_MMU) := fremap.o highmem.o madvise.o memory.o mincore.o \ mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \ - vmalloc.o pagewalk.o pgtable-generic.o + vmalloc.o pagewalk.o pgtable-generic.o \ + process_vm_access.o obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page_alloc.o page-writeback.o \ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index a87da52..7520ef0 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -404,9 +404,8 @@ static int bdi_forker_thread(void *ptr) /* * In the following loop we are going to check whether we have * some work to do without any synchronization with tasks - * waking us up to do work for them. So we have to set task - * state already here so that we don't miss wakeups coming - * after we verify some condition. + * waking us up to do work for them. Set the task state here + * so that we don't miss wakeups after verifying conditions. */ set_current_state(TASK_INTERRUPTIBLE); diff --git a/mm/compaction.c b/mm/compaction.c index 6cc604b..899d956 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -35,10 +35,6 @@ struct compact_control { unsigned long migrate_pfn; /* isolate_migratepages search base */ bool sync; /* Synchronous migration */ - /* Account for isolated anon and file pages */ - unsigned long nr_anon; - unsigned long nr_file; - unsigned int order; /* order a direct compactor needs */ int migratetype; /* MOVABLE, RECLAIMABLE etc */ struct zone *zone; @@ -223,17 +219,13 @@ static void isolate_freepages(struct zone *zone, static void acct_isolated(struct zone *zone, struct compact_control *cc) { struct page *page; - unsigned int count[NR_LRU_LISTS] = { 0, }; + unsigned int count[2] = { 0, }; - list_for_each_entry(page, &cc->migratepages, lru) { - int lru = page_lru_base_type(page); - count[lru]++; - } + list_for_each_entry(page, &cc->migratepages, lru) + count[!!page_is_file_cache(page)]++; - cc->nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON]; - cc->nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE]; - __mod_zone_page_state(zone, NR_ISOLATED_ANON, cc->nr_anon); - __mod_zone_page_state(zone, NR_ISOLATED_FILE, cc->nr_file); + __mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]); + __mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]); } /* Similar to reclaim, but different enough that they don't share logic */ @@ -269,6 +261,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, unsigned long last_pageblock_nr = 0, pageblock_nr; unsigned long nr_scanned = 0, nr_isolated = 0; struct list_head *migratelist = &cc->migratepages; + isolate_mode_t mode = ISOLATE_ACTIVE|ISOLATE_INACTIVE; /* Do not scan outside zone boundaries */ low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn); @@ -356,8 +349,11 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, continue; } + if (!cc->sync) + mode |= ISOLATE_CLEAN; + /* Try isolate the page */ - if (__isolate_lru_page(page, ISOLATE_BOTH, 0) != 0) + if (__isolate_lru_page(page, mode, 0) != 0) continue; VM_BUG_ON(PageTransCompound(page)); @@ -586,7 +582,7 @@ out: return ret; } -unsigned long compact_zone_order(struct zone *zone, +static unsigned long compact_zone_order(struct zone *zone, int order, gfp_t gfp_mask, bool sync) { diff --git a/mm/debug-pagealloc.c b/mm/debug-pagealloc.c index a1e3324..7cea557 100644 --- a/mm/debug-pagealloc.c +++ b/mm/debug-pagealloc.c @@ -1,7 +1,10 @@ #include <linux/kernel.h> +#include <linux/string.h> #include <linux/mm.h> +#include <linux/highmem.h> #include <linux/page-debug-flags.h> #include <linux/poison.h> +#include <linux/ratelimit.h> static inline void set_page_poison(struct page *page) { @@ -18,28 +21,13 @@ static inline bool page_poison(struct page *page) return test_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags); } -static void poison_highpage(struct page *page) -{ - /* - * Page poisoning for highmem pages is not implemented. - * - * This can be called from interrupt contexts. - * So we need to create a new kmap_atomic slot for this - * application and it will need interrupt protection. - */ -} - static void poison_page(struct page *page) { - void *addr; + void *addr = kmap_atomic(page); - if (PageHighMem(page)) { - poison_highpage(page); - return; - } set_page_poison(page); - addr = page_address(page); memset(addr, PAGE_POISON, PAGE_SIZE); + kunmap_atomic(addr); } static void poison_pages(struct page *page, int n) @@ -59,14 +47,12 @@ static bool single_bit_flip(unsigned char a, unsigned char b) static void check_poison_mem(unsigned char *mem, size_t bytes) { + static DEFINE_RATELIMIT_STATE(ratelimit, 5 * HZ, 10); unsigned char *start; unsigned char *end; - for (start = mem; start < mem + bytes; start++) { - if (*start != PAGE_POISON) - break; - } - if (start == mem + bytes) + start = memchr_inv(mem, PAGE_POISON, bytes); + if (!start) return; for (end = mem + bytes - 1; end > start; end--) { @@ -74,7 +60,7 @@ static void check_poison_mem(unsigned char *mem, size_t bytes) break; } - if (!printk_ratelimit()) + if (!__ratelimit(&ratelimit)) return; else if (start == end && single_bit_flip(*start, PAGE_POISON)) printk(KERN_ERR "pagealloc: single bit error\n"); @@ -86,27 +72,17 @@ static void check_poison_mem(unsigned char *mem, size_t bytes) dump_stack(); } -static void unpoison_highpage(struct page *page) -{ - /* - * See comment in poison_highpage(). - * Highmem pages should not be poisoned for now - */ - BUG_ON(page_poison(page)); -} - static void unpoison_page(struct page *page) { - if (PageHighMem(page)) { - unpoison_highpage(page); + void *addr; + + if (!page_poison(page)) return; - } - if (page_poison(page)) { - void *addr = page_address(page); - check_poison_mem(addr, PAGE_SIZE); - clear_page_poison(page); - } + addr = kmap_atomic(page); + check_poison_mem(addr, PAGE_SIZE); + clear_page_poison(page); + kunmap_atomic(addr); } static void unpoison_pages(struct page *page, int n) diff --git a/mm/filemap.c b/mm/filemap.c index 7771871..5cf820a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2115,6 +2115,7 @@ void iov_iter_advance(struct iov_iter *i, size_t bytes) } else { const struct iovec *iov = i->iov; size_t base = i->iov_offset; + unsigned long nr_segs = i->nr_segs; /* * The !iov->iov_len check ensures we skip over unlikely @@ -2130,11 +2131,13 @@ void iov_iter_advance(struct iov_iter *i, size_t bytes) base += copy; if (iov->iov_len == base) { iov++; + nr_segs--; base = 0; } } i->iov = iov; i->iov_offset = base; + i->nr_segs = nr_segs; } } EXPORT_SYMBOL(iov_iter_advance); diff --git a/mm/highmem.c b/mm/highmem.c index 5ef672c..e159a7b 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -250,7 +250,7 @@ void *kmap_high_get(struct page *page) #endif /** - * kunmap_high - map a highmem page into memory + * kunmap_high - unmap a highmem page into memory * @page: &struct page to unmap * * If ARCH_NEEDS_KMAP_HIGH_GET is not defined then this may be called diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e2d1587..860ec21 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -89,7 +89,8 @@ struct khugepaged_scan { struct list_head mm_head; struct mm_slot *mm_slot; unsigned long address; -} khugepaged_scan = { +}; +static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; @@ -829,7 +830,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, for (i = 0; i < HPAGE_PMD_NR; i++) { copy_user_highpage(pages[i], page + i, - haddr + PAGE_SHIFT*i, vma); + haddr + PAGE_SIZE * i, vma); __SetPageUptodate(pages[i]); cond_resched(); } @@ -1052,6 +1053,51 @@ int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, return ret; } +int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, + unsigned long old_addr, + unsigned long new_addr, unsigned long old_end, + pmd_t *old_pmd, pmd_t *new_pmd) +{ + int ret = 0; + pmd_t pmd; + + struct mm_struct *mm = vma->vm_mm; + + if ((old_addr & ~HPAGE_PMD_MASK) || + (new_addr & ~HPAGE_PMD_MASK) || + old_end - old_addr < HPAGE_PMD_SIZE || + (new_vma->vm_flags & VM_NOHUGEPAGE)) + goto out; + + /* + * The destination pmd shouldn't be established, free_pgtables() + * should have release it. + */ + if (WARN_ON(!pmd_none(*new_pmd))) { + VM_BUG_ON(pmd_trans_huge(*new_pmd)); + goto out; + } + + spin_lock(&mm->page_table_lock); + if (likely(pmd_trans_huge(*old_pmd))) { + if (pmd_trans_splitting(*old_pmd)) { + spin_unlock(&mm->page_table_lock); + wait_split_huge_page(vma->anon_vma, old_pmd); + ret = -1; + } else { + pmd = pmdp_get_and_clear(mm, old_addr, old_pmd); + VM_BUG_ON(!pmd_none(*new_pmd)); + set_pmd_at(mm, new_addr, new_pmd, pmd); + spin_unlock(&mm->page_table_lock); + ret = 1; + } + } else { + spin_unlock(&mm->page_table_lock); + } +out: + return ret; +} + int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot) { @@ -1906,7 +1952,7 @@ static void collapse_huge_page(struct mm_struct *mm, BUG_ON(!pmd_none(*pmd)); page_add_new_anon_rmap(new_page, vma, address); set_pmd_at(mm, address, pmd, _pmd); - update_mmu_cache(vma, address, entry); + update_mmu_cache(vma, address, _pmd); prepare_pmd_huge_pte(pgtable, mm); mm->nr_ptes--; spin_unlock(&mm->page_table_lock); @@ -2024,6 +2070,8 @@ static void collect_mm_slot(struct mm_slot *mm_slot) static unsigned int khugepaged_scan_mm_slot(unsigned int pages, struct page **hpage) + __releases(&khugepaged_mm_lock) + __acquires(&khugepaged_mm_lock) { struct mm_slot *mm_slot; struct mm_struct *mm; @@ -1905,7 +1905,8 @@ static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr, oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX); err = unmerge_and_remove_all_rmap_items(); - test_set_oom_score_adj(oom_score_adj); + compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, + oom_score_adj); if (err) { ksm_run = KSM_RUN_STOP; count = err; diff --git a/mm/memblock.c b/mm/memblock.c index ccbf973..84bec49 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -58,7 +58,8 @@ static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, p return ((base1 < (base2 + size2)) && (base2 < (base1 + size1))); } -long __init_memblock memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size) +static long __init_memblock memblock_overlaps_region(struct memblock_type *type, + phys_addr_t base, phys_addr_t size) { unsigned long i; @@ -267,7 +268,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type) return 0; } -extern int __init_memblock __weak memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1, +int __init_memblock __weak memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1, phys_addr_t addr2, phys_addr_t size2) { return 1; @@ -626,6 +627,12 @@ phys_addr_t __init memblock_phys_mem_size(void) return memblock.memory_size; } +/* lowest address */ +phys_addr_t __init_memblock memblock_start_of_DRAM(void) +{ + return memblock.memory.regions[0].base; +} + phys_addr_t __init_memblock memblock_end_of_DRAM(void) { int idx = memblock.memory.cnt - 1; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3508777..2d57555 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1185,7 +1185,8 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page) unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, struct list_head *dst, unsigned long *scanned, int order, - int mode, struct zone *z, + isolate_mode_t mode, + struct zone *z, struct mem_cgroup *mem_cont, int active, int file) { diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 2b43ba0..edc388d 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1310,7 +1310,7 @@ int unpoison_memory(unsigned long pfn) * to the end. */ if (PageHuge(page)) { - pr_debug("MCE: Memory failure is now running on free hugepage %#lx\n", pfn); + pr_info("MCE: Memory failure is now running on free hugepage %#lx\n", pfn); return 0; } if (TestClearPageHWPoison(p)) @@ -1419,7 +1419,7 @@ static int soft_offline_huge_page(struct page *page, int flags) if (PageHWPoison(hpage)) { put_page(hpage); - pr_debug("soft offline: %#lx hugepage already poisoned\n", pfn); + pr_info("soft offline: %#lx hugepage already poisoned\n", pfn); return -EBUSY; } @@ -1433,8 +1433,8 @@ static int soft_offline_huge_page(struct page *page, int flags) list_for_each_entry_safe(page1, page2, &pagelist, lru) put_page(page1); - pr_debug("soft offline: %#lx: migration failed %d, type %lx\n", - pfn, ret, page->flags); + pr_info("soft offline: %#lx: migration failed %d, type %lx\n", + pfn, ret, page->flags); if (ret > 0) ret = -EIO; return ret; @@ -1505,7 +1505,7 @@ int soft_offline_page(struct page *page, int flags) } if (!PageLRU(page)) { pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n", - pfn, page->flags); + pfn, page->flags); return -EIO; } @@ -1566,7 +1566,7 @@ int soft_offline_page(struct page *page, int flags) } } else { pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n", - pfn, ret, page_count(page), page->flags); + pfn, ret, page_count(page), page->flags); } if (ret) return ret; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 9c51f9f..cd237f4 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -111,7 +111,7 @@ enum zone_type policy_zone = 0; /* * run-time system-wide default policy => local allocation */ -struct mempolicy default_policy = { +static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ .mode = MPOL_PREFERRED, .flags = MPOL_F_LOCAL, diff --git a/mm/migrate.c b/mm/migrate.c index 666e4e6..33358f8 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -120,10 +120,10 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, ptep = pte_offset_map(pmd, addr); - if (!is_swap_pte(*ptep)) { - pte_unmap(ptep); - goto out; - } + /* + * Peek to check is_swap_pte() before taking ptlock? No, we + * can race mremap's move_ptes(), which skips anon_vma lock. + */ ptl = pte_lockptr(mm, pmd); } @@ -621,38 +621,18 @@ static int move_to_new_page(struct page *newpage, struct page *page, return rc; } -/* - * Obtain the lock on page, remove all ptes and migrate the page - * to the newly allocated page in newpage. - */ -static int unmap_and_move(new_page_t get_new_page, unsigned long private, - struct page *page, int force, bool offlining, bool sync) +static int __unmap_and_move(struct page *page, struct page *newpage, + int force, bool offlining, bool sync) { - int rc = 0; - int *result = NULL; - struct page *newpage = get_new_page(page, private, &result); + int rc = -EAGAIN; int remap_swapcache = 1; int charge = 0; struct mem_cgroup *mem; struct anon_vma *anon_vma = NULL; - if (!newpage) - return -ENOMEM; - - if (page_count(page) == 1) { - /* page was freed from under us. So we are done. */ - goto move_newpage; - } - if (unlikely(PageTransHuge(page))) - if (unlikely(split_huge_page(page))) - goto move_newpage; - - /* prepare cgroup just returns 0 or -ENOMEM */ - rc = -EAGAIN; - if (!trylock_page(page)) { if (!force || !sync) - goto move_newpage; + goto out; /* * It's not safe for direct compaction to call lock_page. @@ -668,7 +648,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, * altogether. */ if (current->flags & PF_MEMALLOC) - goto move_newpage; + goto out; lock_page(page); } @@ -785,27 +765,52 @@ uncharge: mem_cgroup_end_migration(mem, page, newpage, rc == 0); unlock: unlock_page(page); +out: + return rc; +} -move_newpage: +/* + * Obtain the lock on page, remove all ptes and migrate the page + * to the newly allocated page in newpage. + */ +static int unmap_and_move(new_page_t get_new_page, unsigned long private, + struct page *page, int force, bool offlining, bool sync) +{ + int rc = 0; + int *result = NULL; + struct page *newpage = get_new_page(page, private, &result); + + if (!newpage) + return -ENOMEM; + + if (page_count(page) == 1) { + /* page was freed from under us. So we are done. */ + goto out; + } + + if (unlikely(PageTransHuge(page))) + if (unlikely(split_huge_page(page))) + goto out; + + rc = __unmap_and_move(page, newpage, force, offlining, sync); +out: if (rc != -EAGAIN) { - /* - * A page that has been migrated has all references - * removed and will be freed. A page that has not been - * migrated will have kepts its references and be - * restored. - */ - list_del(&page->lru); + /* + * A page that has been migrated has all references + * removed and will be freed. A page that has not been + * migrated will have kepts its references and be + * restored. + */ + list_del(&page->lru); dec_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); putback_lru_page(page); } - /* * Move the new page to the LRU. If migration was not successful * then this will free the page. */ putback_lru_page(newpage); - if (result) { if (rc) *result = rc; @@ -110,7 +110,15 @@ void munlock_vma_page(struct page *page) if (TestClearPageMlocked(page)) { dec_zone_page_state(page, NR_MLOCK); if (!isolate_lru_page(page)) { - int ret = try_to_munlock(page); + int ret = SWAP_AGAIN; + + /* + * Optimization: if the page was mapped just once, + * that's our mapping and we don't need to check all the + * other vmas. + */ + if (page_mapcount(page) > 1) + ret = try_to_munlock(page); /* * did try_to_unlock() succeed or punt? */ @@ -549,7 +557,8 @@ SYSCALL_DEFINE1(mlockall, int, flags) if (!can_do_mlock()) goto out; - lru_add_drain_all(); /* flush pagevec */ + if (flags & MCL_CURRENT) + lru_add_drain_all(); /* flush pagevec */ down_write(¤t->mm->mmap_sem); @@ -2558,7 +2558,6 @@ int mm_take_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; - int ret = -EINTR; BUG_ON(down_read_trylock(&mm->mmap_sem)); @@ -2579,13 +2578,11 @@ int mm_take_all_locks(struct mm_struct *mm) vm_lock_anon_vma(mm, avc->anon_vma); } - ret = 0; + return 0; out_unlock: - if (ret) - mm_drop_all_locks(mm); - - return ret; + mm_drop_all_locks(mm); + return -EINTR; } static void vm_unlock_anon_vma(struct anon_vma *anon_vma) diff --git a/mm/mremap.c b/mm/mremap.c index 506fa44..d6959cb 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -41,8 +41,7 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr) return NULL; pmd = pmd_offset(pud, addr); - split_huge_page_pmd(mm, pmd); - if (pmd_none_or_clear_bad(pmd)) + if (pmd_none(*pmd)) return NULL; return pmd; @@ -65,8 +64,6 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma, return NULL; VM_BUG_ON(pmd_trans_huge(*pmd)); - if (pmd_none(*pmd) && __pte_alloc(mm, vma, pmd, addr)) - return NULL; return pmd; } @@ -80,11 +77,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, struct mm_struct *mm = vma->vm_mm; pte_t *old_pte, *new_pte, pte; spinlock_t *old_ptl, *new_ptl; - unsigned long old_start; - old_start = old_addr; - mmu_notifier_invalidate_range_start(vma->vm_mm, - old_start, old_end); if (vma->vm_file) { /* * Subtle point from Rajesh Venkatasubramanian: before @@ -111,7 +104,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, new_pte++, new_addr += PAGE_SIZE) { if (pte_none(*old_pte)) continue; - pte = ptep_clear_flush(vma, old_addr, old_pte); + pte = ptep_get_and_clear(mm, old_addr, old_pte); pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr); set_pte_at(mm, new_addr, new_pte, pte); } @@ -123,7 +116,6 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, pte_unmap_unlock(old_pte - 1, old_ptl); if (mapping) mutex_unlock(&mapping->i_mmap_mutex); - mmu_notifier_invalidate_range_end(vma->vm_mm, old_start, old_end); } #define LATENCY_LIMIT (64 * PAGE_SIZE) @@ -134,22 +126,43 @@ unsigned long move_page_tables(struct vm_area_struct *vma, { unsigned long extent, next, old_end; pmd_t *old_pmd, *new_pmd; + bool need_flush = false; old_end = old_addr + len; flush_cache_range(vma, old_addr, old_end); + mmu_notifier_invalidate_range_start(vma->vm_mm, old_addr, old_end); + for (; old_addr < old_end; old_addr += extent, new_addr += extent) { cond_resched(); next = (old_addr + PMD_SIZE) & PMD_MASK; - if (next - 1 > old_end) - next = old_end; + /* even if next overflowed, extent below will be ok */ extent = next - old_addr; + if (extent > old_end - old_addr) + extent = old_end - old_addr; old_pmd = get_old_pmd(vma->vm_mm, old_addr); if (!old_pmd) continue; new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr); if (!new_pmd) break; + if (pmd_trans_huge(*old_pmd)) { + int err = 0; + if (extent == HPAGE_PMD_SIZE) + err = move_huge_pmd(vma, new_vma, old_addr, + new_addr, old_end, + old_pmd, new_pmd); + if (err > 0) { + need_flush = true; + continue; + } else if (!err) { + split_huge_page_pmd(vma->vm_mm, old_pmd); + } + VM_BUG_ON(pmd_trans_huge(*old_pmd)); + } + if (pmd_none(*new_pmd) && __pte_alloc(new_vma->vm_mm, new_vma, + new_pmd, new_addr)) + break; next = (new_addr + PMD_SIZE) & PMD_MASK; if (extent > next - new_addr) extent = next - new_addr; @@ -157,7 +170,12 @@ unsigned long move_page_tables(struct vm_area_struct *vma, extent = LATENCY_LIMIT; move_ptes(vma, old_pmd, old_addr, old_addr + extent, new_vma, new_pmd, new_addr); + need_flush = true; } + if (likely(need_flush)) + flush_tlb_range(vma, old_end-len, old_addr); + + mmu_notifier_invalidate_range_end(vma->vm_mm, old_end-len, old_end); return len + old_addr - old_end; /* how much done */ } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 626303b..e916168 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -32,12 +32,32 @@ #include <linux/mempolicy.h> #include <linux/security.h> #include <linux/ptrace.h> +#include <linux/freezer.h> int sysctl_panic_on_oom; int sysctl_oom_kill_allocating_task; int sysctl_oom_dump_tasks = 1; static DEFINE_SPINLOCK(zone_scan_lock); +/* + * compare_swap_oom_score_adj() - compare and swap current's oom_score_adj + * @old_val: old oom_score_adj for compare + * @new_val: new oom_score_adj for swap + * + * Sets the oom_score_adj value for current to @new_val iff its present value is + * @old_val. Usually used to reinstate a previous value to prevent racing with + * userspacing tuning the value in the interim. + */ +void compare_swap_oom_score_adj(int old_val, int new_val) +{ + struct sighand_struct *sighand = current->sighand; + + spin_lock_irq(&sighand->siglock); + if (current->signal->oom_score_adj == old_val) + current->signal->oom_score_adj = new_val; + spin_unlock_irq(&sighand->siglock); +} + /** * test_set_oom_score_adj() - set current's oom_score_adj and return old value * @new_val: new oom_score_adj value @@ -53,13 +73,7 @@ int test_set_oom_score_adj(int new_val) spin_lock_irq(&sighand->siglock); old_val = current->signal->oom_score_adj; - if (new_val != old_val) { - if (new_val == OOM_SCORE_ADJ_MIN) - atomic_inc(¤t->mm->oom_disable_count); - else if (old_val == OOM_SCORE_ADJ_MIN) - atomic_dec(¤t->mm->oom_disable_count); - current->signal->oom_score_adj = new_val; - } + current->signal->oom_score_adj = new_val; spin_unlock_irq(&sighand->siglock); return old_val; @@ -172,16 +186,6 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, return 0; /* - * Shortcut check for a thread sharing p->mm that is OOM_SCORE_ADJ_MIN - * so the entire heuristic doesn't need to be executed for something - * that cannot be killed. - */ - if (atomic_read(&p->mm->oom_disable_count)) { - task_unlock(p); - return 0; - } - - /* * The memory controller may have a limit of 0 bytes, so avoid a divide * by zero, if necessary. */ @@ -317,8 +321,11 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, * blocked waiting for another task which itself is waiting * for memory. Is there a better alternative? */ - if (test_tsk_thread_flag(p, TIF_MEMDIE)) + if (test_tsk_thread_flag(p, TIF_MEMDIE)) { + if (unlikely(frozen(p))) + thaw_process(p); return ERR_PTR(-1UL); + } if (!p->mm) continue; @@ -435,7 +442,7 @@ static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem) task_unlock(p); /* - * Kill all processes sharing p->mm in other thread groups, if any. + * Kill all user processes sharing p->mm in other thread groups, if any. * They don't get access to memory reserves or a higher scheduler * priority, though, to avoid depletion of all memory or task * starvation. This prevents mm->mmap_sem livelock when an oom killed @@ -445,7 +452,11 @@ static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem) * signal. */ for_each_process(q) - if (q->mm == mm && !same_thread_group(q, p)) { + if (q->mm == mm && !same_thread_group(q, p) && + !(q->flags & PF_KTHREAD)) { + if (q->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) + continue; + task_lock(q); /* Protect ->comm from prctl() */ pr_err("Kill process %d (%s) sharing same memory\n", task_pid_nr(q), q->comm); @@ -722,7 +733,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, read_lock(&tasklist_lock); if (sysctl_oom_kill_allocating_task && !oom_unkillable_task(current, NULL, nodemask) && - current->mm && !atomic_read(¤t->mm->oom_disable_count)) { + current->mm) { /* * oom_kill_process() needs tasklist_lock held. If it returns * non-zero, current could not be killed so we must fallback to diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0e309cd..793e987 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -305,7 +305,9 @@ static unsigned long task_min_dirty_limit(unsigned long bdi_dirty) } /* - * + * bdi_min_ratio keeps the sum of the minimum dirty shares of all + * registered backing devices, which, for obvious reasons, can not + * exceed 100%. */ static unsigned int bdi_min_ratio; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6e8ecb6..9dd443d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -318,6 +318,7 @@ static void bad_page(struct page *page) current->comm, page_to_pfn(page)); dump_page(page); + print_modules(); dump_stack(); out: /* Leave bad fields for debug, except PageBuddy could make trouble */ @@ -1753,7 +1754,6 @@ static DEFINE_RATELIMIT_STATE(nopage_rs, void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...) { - va_list args; unsigned int filter = SHOW_MEM_FILTER_NODES; if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs)) @@ -1772,14 +1772,21 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...) filter &= ~SHOW_MEM_FILTER_NODES; if (fmt) { - printk(KERN_WARNING); + struct va_format vaf; + va_list args; + va_start(args, fmt); - vprintk(fmt, args); + + vaf.fmt = fmt; + vaf.va = &args; + + pr_warn("%pV", &vaf); + va_end(args); } - pr_warning("%s: page allocation failure: order:%d, mode:0x%x\n", - current->comm, order, gfp_mask); + pr_warn("%s: page allocation failure: order:%d, mode:0x%x\n", + current->comm, order, gfp_mask); dump_stack(); if (!should_suppress_show_mem()) diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 39d216d..6bdc67d 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -513,11 +513,10 @@ int swap_cgroup_swapon(int type, unsigned long max_pages) length = DIV_ROUND_UP(max_pages, SC_PER_PAGE); array_size = length * sizeof(void *); - array = vmalloc(array_size); + array = vzalloc(array_size); if (!array) goto nomem; - memset(array, 0, array_size); ctrl = &swap_cgroup_ctrl[type]; mutex_lock(&swap_cgroup_mutex); ctrl->length = length; diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c new file mode 100644 index 0000000..e920aa3 --- /dev/null +++ b/mm/process_vm_access.c @@ -0,0 +1,496 @@ +/* + * linux/mm/process_vm_access.c + * + * Copyright (C) 2010-2011 Christopher Yeoh <cyeoh@au1.ibm.com>, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/mm.h> +#include <linux/uio.h> +#include <linux/sched.h> +#include <linux/highmem.h> +#include <linux/ptrace.h> +#include <linux/slab.h> +#include <linux/syscalls.h> + +#ifdef CONFIG_COMPAT +#include <linux/compat.h> +#endif + +/** + * process_vm_rw_pages - read/write pages from task specified + * @task: task to read/write from + * @mm: mm for task + * @process_pages: struct pages area that can store at least + * nr_pages_to_copy struct page pointers + * @pa: address of page in task to start copying from/to + * @start_offset: offset in page to start copying from/to + * @len: number of bytes to copy + * @lvec: iovec array specifying where to copy to/from + * @lvec_cnt: number of elements in iovec array + * @lvec_current: index in iovec array we are up to + * @lvec_offset: offset in bytes from current iovec iov_base we are up to + * @vm_write: 0 means copy from, 1 means copy to + * @nr_pages_to_copy: number of pages to copy + * @bytes_copied: returns number of bytes successfully copied + * Returns 0 on success, error code otherwise + */ +static int process_vm_rw_pages(struct task_struct *task, + struct mm_struct *mm, + struct page **process_pages, + unsigned long pa, + unsigned long start_offset, + unsigned long len, + const struct iovec *lvec, + unsigned long lvec_cnt, + unsigned long *lvec_current, + size_t *lvec_offset, + int vm_write, + unsigned int nr_pages_to_copy, + ssize_t *bytes_copied) +{ + int pages_pinned; + void *target_kaddr; + int pgs_copied = 0; + int j; + int ret; + ssize_t bytes_to_copy; + ssize_t rc = 0; + + *bytes_copied = 0; + + /* Get the pages we're interested in */ + down_read(&mm->mmap_sem); + pages_pinned = get_user_pages(task, mm, pa, + nr_pages_to_copy, + vm_write, 0, process_pages, NULL); + up_read(&mm->mmap_sem); + + if (pages_pinned != nr_pages_to_copy) { + rc = -EFAULT; + goto end; + } + + /* Do the copy for each page */ + for (pgs_copied = 0; + (pgs_copied < nr_pages_to_copy) && (*lvec_current < lvec_cnt); + pgs_copied++) { + /* Make sure we have a non zero length iovec */ + while (*lvec_current < lvec_cnt + && lvec[*lvec_current].iov_len == 0) + (*lvec_current)++; + if (*lvec_current == lvec_cnt) + break; + + /* + * Will copy smallest of: + * - bytes remaining in page + * - bytes remaining in destination iovec + */ + bytes_to_copy = min_t(ssize_t, PAGE_SIZE - start_offset, + len - *bytes_copied); + bytes_to_copy = min_t(ssize_t, bytes_to_copy, + lvec[*lvec_current].iov_len + - *lvec_offset); + + target_kaddr = kmap(process_pages[pgs_copied]) + start_offset; + + if (vm_write) + ret = copy_from_user(target_kaddr, + lvec[*lvec_current].iov_base + + *lvec_offset, + bytes_to_copy); + else + ret = copy_to_user(lvec[*lvec_current].iov_base + + *lvec_offset, + target_kaddr, bytes_to_copy); + kunmap(process_pages[pgs_copied]); + if (ret) { + *bytes_copied += bytes_to_copy - ret; + pgs_copied++; + rc = -EFAULT; + goto end; + } + *bytes_copied += bytes_to_copy; + *lvec_offset += bytes_to_copy; + if (*lvec_offset == lvec[*lvec_current].iov_len) { + /* + * Need to copy remaining part of page into the + * next iovec if there are any bytes left in page + */ + (*lvec_current)++; + *lvec_offset = 0; + start_offset = (start_offset + bytes_to_copy) + % PAGE_SIZE; + if (start_offset) + pgs_copied--; + } else { + start_offset = 0; + } + } + +end: + if (vm_write) { + for (j = 0; j < pages_pinned; j++) { + if (j < pgs_copied) + set_page_dirty_lock(process_pages[j]); + put_page(process_pages[j]); + } + } else { + for (j = 0; j < pages_pinned; j++) + put_page(process_pages[j]); + } + + return rc; +} + +/* Maximum number of pages kmalloc'd to hold struct page's during copy */ +#define PVM_MAX_KMALLOC_PAGES (PAGE_SIZE * 2) + +/** + * process_vm_rw_single_vec - read/write pages from task specified + * @addr: start memory address of target process + * @len: size of area to copy to/from + * @lvec: iovec array specifying where to copy to/from locally + * @lvec_cnt: number of elements in iovec array + * @lvec_current: index in iovec array we are up to + * @lvec_offset: offset in bytes from current iovec iov_base we are up to + * @process_pages: struct pages area that can store at least + * nr_pages_to_copy struct page pointers + * @mm: mm for task + * @task: task to read/write from + * @vm_write: 0 means copy from, 1 means copy to + * @bytes_copied: returns number of bytes successfully copied + * Returns 0 on success or on failure error code + */ +static int process_vm_rw_single_vec(unsigned long addr, + unsigned long len, + const struct iovec *lvec, + unsigned long lvec_cnt, + unsigned long *lvec_current, + size_t *lvec_offset, + struct page **process_pages, + struct mm_struct *mm, + struct task_struct *task, + int vm_write, + ssize_t *bytes_copied) +{ + unsigned long pa = addr & PAGE_MASK; + unsigned long start_offset = addr - pa; + unsigned long nr_pages; + ssize_t bytes_copied_loop; + ssize_t rc = 0; + unsigned long nr_pages_copied = 0; + unsigned long nr_pages_to_copy; + unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES + / sizeof(struct pages *); + + *bytes_copied = 0; + + /* Work out address and page range required */ + if (len == 0) + return 0; + nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1; + + while ((nr_pages_copied < nr_pages) && (*lvec_current < lvec_cnt)) { + nr_pages_to_copy = min(nr_pages - nr_pages_copied, + max_pages_per_loop); + + rc = process_vm_rw_pages(task, mm, process_pages, pa, + start_offset, len, + lvec, lvec_cnt, + lvec_current, lvec_offset, + vm_write, nr_pages_to_copy, + &bytes_copied_loop); + start_offset = 0; + *bytes_copied += bytes_copied_loop; + + if (rc < 0) { + return rc; + } else { + len -= bytes_copied_loop; + nr_pages_copied += nr_pages_to_copy; + pa += nr_pages_to_copy * PAGE_SIZE; + } + } + + return rc; +} + +/* Maximum number of entries for process pages array + which lives on stack */ +#define PVM_MAX_PP_ARRAY_COUNT 16 + +/** + * process_vm_rw_core - core of reading/writing pages from task specified + * @pid: PID of process to read/write from/to + * @lvec: iovec array specifying where to copy to/from locally + * @liovcnt: size of lvec array + * @rvec: iovec array specifying where to copy to/from in the other process + * @riovcnt: size of rvec array + * @flags: currently unused + * @vm_write: 0 if reading from other process, 1 if writing to other process + * Returns the number of bytes read/written or error code. May + * return less bytes than expected if an error occurs during the copying + * process. + */ +static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec, + unsigned long liovcnt, + const struct iovec *rvec, + unsigned long riovcnt, + unsigned long flags, int vm_write) +{ + struct task_struct *task; + struct page *pp_stack[PVM_MAX_PP_ARRAY_COUNT]; + struct page **process_pages = pp_stack; + struct mm_struct *mm; + unsigned long i; + ssize_t rc = 0; + ssize_t bytes_copied_loop; + ssize_t bytes_copied = 0; + unsigned long nr_pages = 0; + unsigned long nr_pages_iov; + unsigned long iov_l_curr_idx = 0; + size_t iov_l_curr_offset = 0; + ssize_t iov_len; + + /* + * Work out how many pages of struct pages we're going to need + * when eventually calling get_user_pages + */ + for (i = 0; i < riovcnt; i++) { + iov_len = rvec[i].iov_len; + if (iov_len > 0) { + nr_pages_iov = ((unsigned long)rvec[i].iov_base + + iov_len) + / PAGE_SIZE - (unsigned long)rvec[i].iov_base + / PAGE_SIZE + 1; + nr_pages = max(nr_pages, nr_pages_iov); + } + } + + if (nr_pages == 0) + return 0; + + if (nr_pages > PVM_MAX_PP_ARRAY_COUNT) { + /* For reliability don't try to kmalloc more than + 2 pages worth */ + process_pages = kmalloc(min_t(size_t, PVM_MAX_KMALLOC_PAGES, + sizeof(struct pages *)*nr_pages), + GFP_KERNEL); + + if (!process_pages) + return -ENOMEM; + } + + /* Get process information */ + rcu_read_lock(); + task = find_task_by_vpid(pid); + if (task) + get_task_struct(task); + rcu_read_unlock(); + if (!task) { + rc = -ESRCH; + goto free_proc_pages; + } + + task_lock(task); + if (__ptrace_may_access(task, PTRACE_MODE_ATTACH)) { + task_unlock(task); + rc = -EPERM; + goto put_task_struct; + } + mm = task->mm; + + if (!mm || (task->flags & PF_KTHREAD)) { + task_unlock(task); + rc = -EINVAL; + goto put_task_struct; + } + + atomic_inc(&mm->mm_users); + task_unlock(task); + + for (i = 0; i < riovcnt && iov_l_curr_idx < liovcnt; i++) { + rc = process_vm_rw_single_vec( + (unsigned long)rvec[i].iov_base, rvec[i].iov_len, + lvec, liovcnt, &iov_l_curr_idx, &iov_l_curr_offset, + process_pages, mm, task, vm_write, &bytes_copied_loop); + bytes_copied += bytes_copied_loop; + if (rc != 0) { + /* If we have managed to copy any data at all then + we return the number of bytes copied. Otherwise + we return the error code */ + if (bytes_copied) + rc = bytes_copied; + goto put_mm; + } + } + + rc = bytes_copied; +put_mm: + mmput(mm); + +put_task_struct: + put_task_struct(task); + +free_proc_pages: + if (process_pages != pp_stack) + kfree(process_pages); + return rc; +} + +/** + * process_vm_rw - check iovecs before calling core routine + * @pid: PID of process to read/write from/to + * @lvec: iovec array specifying where to copy to/from locally + * @liovcnt: size of lvec array + * @rvec: iovec array specifying where to copy to/from in the other process + * @riovcnt: size of rvec array + * @flags: currently unused + * @vm_write: 0 if reading from other process, 1 if writing to other process + * Returns the number of bytes read/written or error code. May + * return less bytes than expected if an error occurs during the copying + * process. + */ +static ssize_t process_vm_rw(pid_t pid, + const struct iovec __user *lvec, + unsigned long liovcnt, + const struct iovec __user *rvec, + unsigned long riovcnt, + unsigned long flags, int vm_write) +{ + struct iovec iovstack_l[UIO_FASTIOV]; + struct iovec iovstack_r[UIO_FASTIOV]; + struct iovec *iov_l = iovstack_l; + struct iovec *iov_r = iovstack_r; + ssize_t rc; + + if (flags != 0) + return -EINVAL; + + /* Check iovecs */ + if (vm_write) + rc = rw_copy_check_uvector(WRITE, lvec, liovcnt, UIO_FASTIOV, + iovstack_l, &iov_l, 1); + else + rc = rw_copy_check_uvector(READ, lvec, liovcnt, UIO_FASTIOV, + iovstack_l, &iov_l, 1); + if (rc <= 0) + goto free_iovecs; + + rc = rw_copy_check_uvector(READ, rvec, riovcnt, UIO_FASTIOV, + iovstack_r, &iov_r, 0); + if (rc <= 0) + goto free_iovecs; + + rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags, + vm_write); + +free_iovecs: + if (iov_r != iovstack_r) + kfree(iov_r); + if (iov_l != iovstack_l) + kfree(iov_l); + + return rc; +} + +SYSCALL_DEFINE6(process_vm_readv, pid_t, pid, const struct iovec __user *, lvec, + unsigned long, liovcnt, const struct iovec __user *, rvec, + unsigned long, riovcnt, unsigned long, flags) +{ + return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 0); +} + +SYSCALL_DEFINE6(process_vm_writev, pid_t, pid, + const struct iovec __user *, lvec, + unsigned long, liovcnt, const struct iovec __user *, rvec, + unsigned long, riovcnt, unsigned long, flags) +{ + return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 1); +} + +#ifdef CONFIG_COMPAT + +asmlinkage ssize_t +compat_process_vm_rw(compat_pid_t pid, + const struct compat_iovec __user *lvec, + unsigned long liovcnt, + const struct compat_iovec __user *rvec, + unsigned long riovcnt, + unsigned long flags, int vm_write) +{ + struct iovec iovstack_l[UIO_FASTIOV]; + struct iovec iovstack_r[UIO_FASTIOV]; + struct iovec *iov_l = iovstack_l; + struct iovec *iov_r = iovstack_r; + ssize_t rc = -EFAULT; + + if (flags != 0) + return -EINVAL; + + if (!access_ok(VERIFY_READ, lvec, liovcnt * sizeof(*lvec))) + goto out; + + if (!access_ok(VERIFY_READ, rvec, riovcnt * sizeof(*rvec))) + goto out; + + if (vm_write) + rc = compat_rw_copy_check_uvector(WRITE, lvec, liovcnt, + UIO_FASTIOV, iovstack_l, + &iov_l, 1); + else + rc = compat_rw_copy_check_uvector(READ, lvec, liovcnt, + UIO_FASTIOV, iovstack_l, + &iov_l, 1); + if (rc <= 0) + goto free_iovecs; + rc = compat_rw_copy_check_uvector(READ, rvec, riovcnt, + UIO_FASTIOV, iovstack_r, + &iov_r, 0); + if (rc <= 0) + goto free_iovecs; + + rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags, + vm_write); + +free_iovecs: + if (iov_r != iovstack_r) + kfree(iov_r); + if (iov_l != iovstack_l) + kfree(iov_l); + +out: + return rc; +} + +asmlinkage ssize_t +compat_sys_process_vm_readv(compat_pid_t pid, + const struct compat_iovec __user *lvec, + unsigned long liovcnt, + const struct compat_iovec __user *rvec, + unsigned long riovcnt, + unsigned long flags) +{ + return compat_process_vm_rw(pid, lvec, liovcnt, rvec, + riovcnt, flags, 0); +} + +asmlinkage ssize_t +compat_sys_process_vm_writev(compat_pid_t pid, + const struct compat_iovec __user *lvec, + unsigned long liovcnt, + const struct compat_iovec __user *rvec, + unsigned long riovcnt, + unsigned long flags) +{ + return compat_process_vm_rw(pid, lvec, liovcnt, rvec, + riovcnt, flags, 1); +} + +#endif @@ -1164,7 +1164,7 @@ void page_remove_rmap(struct page *page) /* * Subfunctions of try_to_unmap: try_to_unmap_one called - * repeatedly from either try_to_unmap_anon or try_to_unmap_file. + * repeatedly from try_to_unmap_ksm, try_to_unmap_anon or try_to_unmap_file. */ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, unsigned long address, enum ttu_flags flags) @@ -1068,6 +1068,12 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) user_shm_unlock(inode->i_size, user); info->flags &= ~VM_LOCKED; mapping_clear_unevictable(file->f_mapping); + /* + * Ensure that a racing putback_lru_page() can see + * the pages of this mapping are evictable when we + * skip them due to !PageLRU during the scan. + */ + smp_mb__after_clear_bit(); scan_mapping_unevictable_pages(file->f_mapping); } retval = 0; @@ -1458,7 +1464,7 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE); if (inode) { error = security_inode_init_security(inode, dir, - &dentry->d_name, NULL, + &dentry->d_name, NULL, NULL); if (error) { if (error != -EOPNOTSUPP) { @@ -1598,7 +1604,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s if (!inode) return -ENOSPC; - error = security_inode_init_security(inode, dir, &dentry->d_name, NULL, + error = security_inode_init_security(inode, dir, &dentry->d_name, NULL, NULL); if (error) { if (error != -EOPNOTSUPP) { @@ -1851,15 +1851,15 @@ static void dump_line(char *data, int offset, int limit) unsigned char error = 0; int bad_count = 0; - printk(KERN_ERR "%03x:", offset); + printk(KERN_ERR "%03x: ", offset); for (i = 0; i < limit; i++) { if (data[offset + i] != POISON_FREE) { error = data[offset + i]; bad_count++; } - printk(" %02x", (unsigned char)data[offset + i]); } - printk("\n"); + print_hex_dump(KERN_CONT, "", 0, 16, 1, + &data[offset], limit, 1); if (bad_count == 1) { error ^= POISON_FREE; @@ -3039,14 +3039,9 @@ bad: printk(KERN_ERR "slab: Internal list corruption detected in " "cache '%s'(%d), slabp %p(%d). Hexdump:\n", cachep->name, cachep->num, slabp, slabp->inuse); - for (i = 0; - i < sizeof(*slabp) + cachep->num * sizeof(kmem_bufctl_t); - i++) { - if (i % 16 == 0) - printk("\n%03x:", i); - printk(" %02x", ((unsigned char *)slabp)[i]); - } - printk("\n"); + print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, slabp, + sizeof(*slabp) + cachep->num * sizeof(kmem_bufctl_t), + 1); BUG(); } } @@ -4584,7 +4579,7 @@ static const struct file_operations proc_slabstats_operations = { static int __init slab_proc_init(void) { - proc_create("slabinfo",S_IWUSR|S_IRUGO,NULL,&proc_slabinfo_operations); + proc_create("slabinfo",S_IWUSR|S_IRUSR,NULL,&proc_slabinfo_operations); #ifdef CONFIG_DEBUG_SLAB_LEAK proc_create("slab_allocators", 0, NULL, &proc_slabstats_operations); #endif @@ -467,34 +467,8 @@ static int disable_higher_order_debug; */ static void print_section(char *text, u8 *addr, unsigned int length) { - int i, offset; - int newline = 1; - char ascii[17]; - - ascii[16] = 0; - - for (i = 0; i < length; i++) { - if (newline) { - printk(KERN_ERR "%8s 0x%p: ", text, addr + i); - newline = 0; - } - printk(KERN_CONT " %02x", addr[i]); - offset = i % 16; - ascii[offset] = isgraph(addr[i]) ? addr[i] : '.'; - if (offset == 15) { - printk(KERN_CONT " %s\n", ascii); - newline = 1; - } - } - if (!newline) { - i %= 16; - while (i < 16) { - printk(KERN_CONT " "); - ascii[i] = ' '; - i++; - } - printk(KERN_CONT " %s\n", ascii); - } + print_hex_dump(KERN_ERR, text, DUMP_PREFIX_ADDRESS, 16, 1, addr, + length, 1); } static struct track *get_track(struct kmem_cache *s, void *object, @@ -625,12 +599,12 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) p, p - addr, get_freepointer(s, p)); if (p > addr + 16) - print_section("Bytes b4", p - 16, 16); - - print_section("Object", p, min_t(unsigned long, s->objsize, PAGE_SIZE)); + print_section("Bytes b4 ", p - 16, 16); + print_section("Object ", p, min_t(unsigned long, s->objsize, + PAGE_SIZE)); if (s->flags & SLAB_RED_ZONE) - print_section("Redzone", p + s->objsize, + print_section("Redzone ", p + s->objsize, s->inuse - s->objsize); if (s->offset) @@ -643,7 +617,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) if (off != s->size) /* Beginning of the filler is the free pointer */ - print_section("Padding", p + off, s->size - off); + print_section("Padding ", p + off, s->size - off); dump_stack(); } @@ -681,49 +655,6 @@ static void init_object(struct kmem_cache *s, void *object, u8 val) memset(p + s->objsize, val, s->inuse - s->objsize); } -static u8 *check_bytes8(u8 *start, u8 value, unsigned int bytes) -{ - while (bytes) { - if (*start != value) - return start; - start++; - bytes--; - } - return NULL; -} - -static u8 *check_bytes(u8 *start, u8 value, unsigned int bytes) -{ - u64 value64; - unsigned int words, prefix; - - if (bytes <= 16) - return check_bytes8(start, value, bytes); - - value64 = value | value << 8 | value << 16 | value << 24; - value64 = (value64 & 0xffffffff) | value64 << 32; - prefix = 8 - ((unsigned long)start) % 8; - - if (prefix) { - u8 *r = check_bytes8(start, value, prefix); - if (r) - return r; - start += prefix; - bytes -= prefix; - } - - words = bytes / 8; - - while (words) { - if (*(u64 *)start != value64) - return check_bytes8(start, value, 8); - start += 8; - words--; - } - - return check_bytes8(start, value, bytes % 8); -} - static void restore_bytes(struct kmem_cache *s, char *message, u8 data, void *from, void *to) { @@ -738,7 +669,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, u8 *fault; u8 *end; - fault = check_bytes(start, value, bytes); + fault = memchr_inv(start, value, bytes); if (!fault) return 1; @@ -831,14 +762,14 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page) if (!remainder) return 1; - fault = check_bytes(end - remainder, POISON_INUSE, remainder); + fault = memchr_inv(end - remainder, POISON_INUSE, remainder); if (!fault) return 1; while (end > fault && end[-1] == POISON_INUSE) end--; slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1); - print_section("Padding", end - remainder, remainder); + print_section("Padding ", end - remainder, remainder); restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, end); return 0; @@ -987,7 +918,7 @@ static void trace(struct kmem_cache *s, struct page *page, void *object, page->freelist); if (!alloc) - print_section("Object", (void *)object, s->objsize); + print_section("Object ", (void *)object, s->objsize); dump_stack(); } @@ -1447,7 +1378,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) set_freepointer(s, last, NULL); page->freelist = start; - page->inuse = 0; + page->inuse = page->objects; page->frozen = 1; out: return page; @@ -1534,7 +1465,7 @@ static inline void add_partial(struct kmem_cache_node *n, struct page *page, int tail) { n->nr_partial++; - if (tail) + if (tail == DEACTIVATE_TO_TAIL) list_add_tail(&page->lru, &n->partial); else list_add(&page->lru, &n->partial); @@ -1554,10 +1485,13 @@ static inline void remove_partial(struct kmem_cache_node *n, * Lock slab, remove from the partial list and put the object into the * per cpu freelist. * + * Returns a list of objects or NULL if it fails. + * * Must hold list_lock. */ -static inline int acquire_slab(struct kmem_cache *s, - struct kmem_cache_node *n, struct page *page) +static inline void *acquire_slab(struct kmem_cache *s, + struct kmem_cache_node *n, struct page *page, + int mode) { void *freelist; unsigned long counters; @@ -1572,7 +1506,8 @@ static inline int acquire_slab(struct kmem_cache *s, freelist = page->freelist; counters = page->counters; new.counters = counters; - new.inuse = page->objects; + if (mode) + new.inuse = page->objects; VM_BUG_ON(new.frozen); new.frozen = 1; @@ -1583,32 +1518,19 @@ static inline int acquire_slab(struct kmem_cache *s, "lock and freeze")); remove_partial(n, page); - - if (freelist) { - /* Populate the per cpu freelist */ - this_cpu_write(s->cpu_slab->freelist, freelist); - this_cpu_write(s->cpu_slab->page, page); - this_cpu_write(s->cpu_slab->node, page_to_nid(page)); - return 1; - } else { - /* - * Slab page came from the wrong list. No object to allocate - * from. Put it onto the correct list and continue partial - * scan. - */ - printk(KERN_ERR "SLUB: %s : Page without available objects on" - " partial list\n", s->name); - return 0; - } + return freelist; } +static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain); + /* * Try to allocate a partial slab from a specific node. */ -static struct page *get_partial_node(struct kmem_cache *s, - struct kmem_cache_node *n) +static void *get_partial_node(struct kmem_cache *s, + struct kmem_cache_node *n, struct kmem_cache_cpu *c) { - struct page *page; + struct page *page, *page2; + void *object = NULL; /* * Racy check. If we mistakenly see no partial slabs then we @@ -1620,26 +1542,43 @@ static struct page *get_partial_node(struct kmem_cache *s, return NULL; spin_lock(&n->list_lock); - list_for_each_entry(page, &n->partial, lru) - if (acquire_slab(s, n, page)) - goto out; - page = NULL; -out: + list_for_each_entry_safe(page, page2, &n->partial, lru) { + void *t = acquire_slab(s, n, page, object == NULL); + int available; + + if (!t) + break; + + if (!object) { + c->page = page; + c->node = page_to_nid(page); + stat(s, ALLOC_FROM_PARTIAL); + object = t; + available = page->objects - page->inuse; + } else { + page->freelist = t; + available = put_cpu_partial(s, page, 0); + } + if (kmem_cache_debug(s) || available > s->cpu_partial / 2) + break; + + } spin_unlock(&n->list_lock); - return page; + return object; } /* * Get a page from somewhere. Search in increasing NUMA distances. */ -static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags) +static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags, + struct kmem_cache_cpu *c) { #ifdef CONFIG_NUMA struct zonelist *zonelist; struct zoneref *z; struct zone *zone; enum zone_type high_zoneidx = gfp_zone(flags); - struct page *page; + void *object; /* * The defrag ratio allows a configuration of the tradeoffs between @@ -1672,10 +1611,10 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags) if (n && cpuset_zone_allowed_hardwall(zone, flags) && n->nr_partial > s->min_partial) { - page = get_partial_node(s, n); - if (page) { + object = get_partial_node(s, n, c); + if (object) { put_mems_allowed(); - return page; + return object; } } } @@ -1687,16 +1626,17 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags) /* * Get a partial page, lock it and return it. */ -static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node) +static void *get_partial(struct kmem_cache *s, gfp_t flags, int node, + struct kmem_cache_cpu *c) { - struct page *page; + void *object; int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node; - page = get_partial_node(s, get_node(s, searchnode)); - if (page || node != NUMA_NO_NODE) - return page; + object = get_partial_node(s, get_node(s, searchnode), c); + if (object || node != NUMA_NO_NODE) + return object; - return get_any_partial(s, flags); + return get_any_partial(s, flags, c); } #ifdef CONFIG_PREEMPT @@ -1765,9 +1705,6 @@ void init_kmem_cache_cpus(struct kmem_cache *s) for_each_possible_cpu(cpu) per_cpu_ptr(s->cpu_slab, cpu)->tid = init_tid(cpu); } -/* - * Remove the cpu slab - */ /* * Remove the cpu slab @@ -1781,13 +1718,13 @@ static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) enum slab_modes l = M_NONE, m = M_NONE; void *freelist; void *nextfree; - int tail = 0; + int tail = DEACTIVATE_TO_HEAD; struct page new; struct page old; if (page->freelist) { stat(s, DEACTIVATE_REMOTE_FREES); - tail = 1; + tail = DEACTIVATE_TO_TAIL; } c->tid = next_tid(c->tid); @@ -1893,7 +1830,7 @@ redo: if (m == M_PARTIAL) { add_partial(n, page, tail); - stat(s, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD); + stat(s, tail); } else if (m == M_FULL) { @@ -1920,6 +1857,123 @@ redo: } } +/* Unfreeze all the cpu partial slabs */ +static void unfreeze_partials(struct kmem_cache *s) +{ + struct kmem_cache_node *n = NULL; + struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab); + struct page *page; + + while ((page = c->partial)) { + enum slab_modes { M_PARTIAL, M_FREE }; + enum slab_modes l, m; + struct page new; + struct page old; + + c->partial = page->next; + l = M_FREE; + + do { + + old.freelist = page->freelist; + old.counters = page->counters; + VM_BUG_ON(!old.frozen); + + new.counters = old.counters; + new.freelist = old.freelist; + + new.frozen = 0; + + if (!new.inuse && (!n || n->nr_partial > s->min_partial)) + m = M_FREE; + else { + struct kmem_cache_node *n2 = get_node(s, + page_to_nid(page)); + + m = M_PARTIAL; + if (n != n2) { + if (n) + spin_unlock(&n->list_lock); + + n = n2; + spin_lock(&n->list_lock); + } + } + + if (l != m) { + if (l == M_PARTIAL) + remove_partial(n, page); + else + add_partial(n, page, 1); + + l = m; + } + + } while (!cmpxchg_double_slab(s, page, + old.freelist, old.counters, + new.freelist, new.counters, + "unfreezing slab")); + + if (m == M_FREE) { + stat(s, DEACTIVATE_EMPTY); + discard_slab(s, page); + stat(s, FREE_SLAB); + } + } + + if (n) + spin_unlock(&n->list_lock); +} + +/* + * Put a page that was just frozen (in __slab_free) into a partial page + * slot if available. This is done without interrupts disabled and without + * preemption disabled. The cmpxchg is racy and may put the partial page + * onto a random cpus partial slot. + * + * If we did not find a slot then simply move all the partials to the + * per node partial list. + */ +int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) +{ + struct page *oldpage; + int pages; + int pobjects; + + do { + pages = 0; + pobjects = 0; + oldpage = this_cpu_read(s->cpu_slab->partial); + + if (oldpage) { + pobjects = oldpage->pobjects; + pages = oldpage->pages; + if (drain && pobjects > s->cpu_partial) { + unsigned long flags; + /* + * partial array is full. Move the existing + * set to the per node partial list. + */ + local_irq_save(flags); + unfreeze_partials(s); + local_irq_restore(flags); + pobjects = 0; + pages = 0; + } + } + + pages++; + pobjects += page->objects - page->inuse; + + page->pages = pages; + page->pobjects = pobjects; + page->next = oldpage; + + } while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage); + stat(s, CPU_PARTIAL_FREE); + return pobjects; +} + static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) { stat(s, CPUSLAB_FLUSH); @@ -1935,8 +1989,12 @@ static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu) { struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu); - if (likely(c && c->page)) - flush_slab(s, c); + if (likely(c)) { + if (c->page) + flush_slab(s, c); + + unfreeze_partials(s); + } } static void flush_cpu_slab(void *d) @@ -2027,12 +2085,39 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) } } +static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags, + int node, struct kmem_cache_cpu **pc) +{ + void *object; + struct kmem_cache_cpu *c; + struct page *page = new_slab(s, flags, node); + + if (page) { + c = __this_cpu_ptr(s->cpu_slab); + if (c->page) + flush_slab(s, c); + + /* + * No other reference to the page yet so we can + * muck around with it freely without cmpxchg + */ + object = page->freelist; + page->freelist = NULL; + + stat(s, ALLOC_SLAB); + c->node = page_to_nid(page); + c->page = page; + *pc = c; + } else + object = NULL; + + return object; +} + /* * Slow path. The lockless freelist is empty or we need to perform * debugging duties. * - * Interrupts are disabled. - * * Processing is still very fast if new objects have been freed to the * regular freelist. In that case we simply take over the regular freelist * as the lockless freelist and zap the regular freelist. @@ -2049,7 +2134,6 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, unsigned long addr, struct kmem_cache_cpu *c) { void **object; - struct page *page; unsigned long flags; struct page new; unsigned long counters; @@ -2064,13 +2148,9 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, c = this_cpu_ptr(s->cpu_slab); #endif - /* We handle __GFP_ZERO in the caller */ - gfpflags &= ~__GFP_ZERO; - - page = c->page; - if (!page) + if (!c->page) goto new_slab; - +redo: if (unlikely(!node_match(c, node))) { stat(s, ALLOC_NODE_MISMATCH); deactivate_slab(s, c); @@ -2080,8 +2160,8 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, stat(s, ALLOC_SLOWPATH); do { - object = page->freelist; - counters = page->counters; + object = c->page->freelist; + counters = c->page->counters; new.counters = counters; VM_BUG_ON(!new.frozen); @@ -2093,17 +2173,17 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, * * If there are objects left then we retrieve them * and use them to refill the per cpu queue. - */ + */ - new.inuse = page->objects; + new.inuse = c->page->objects; new.frozen = object != NULL; - } while (!__cmpxchg_double_slab(s, page, + } while (!__cmpxchg_double_slab(s, c->page, object, counters, NULL, new.counters, "__slab_alloc")); - if (unlikely(!object)) { + if (!object) { c->page = NULL; stat(s, DEACTIVATE_BYPASS); goto new_slab; @@ -2112,58 +2192,47 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, stat(s, ALLOC_REFILL); load_freelist: - VM_BUG_ON(!page->frozen); c->freelist = get_freepointer(s, object); c->tid = next_tid(c->tid); local_irq_restore(flags); return object; new_slab: - page = get_partial(s, gfpflags, node); - if (page) { - stat(s, ALLOC_FROM_PARTIAL); - object = c->freelist; - if (kmem_cache_debug(s)) - goto debug; - goto load_freelist; + if (c->partial) { + c->page = c->partial; + c->partial = c->page->next; + c->node = page_to_nid(c->page); + stat(s, CPU_PARTIAL_ALLOC); + c->freelist = NULL; + goto redo; } - page = new_slab(s, gfpflags, node); + /* Then do expensive stuff like retrieving pages from the partial lists */ + object = get_partial(s, gfpflags, node, c); - if (page) { - c = __this_cpu_ptr(s->cpu_slab); - if (c->page) - flush_slab(s, c); + if (unlikely(!object)) { - /* - * No other reference to the page yet so we can - * muck around with it freely without cmpxchg - */ - object = page->freelist; - page->freelist = NULL; - page->inuse = page->objects; + object = new_slab_objects(s, gfpflags, node, &c); - stat(s, ALLOC_SLAB); - c->node = page_to_nid(page); - c->page = page; + if (unlikely(!object)) { + if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit()) + slab_out_of_memory(s, gfpflags, node); - if (kmem_cache_debug(s)) - goto debug; - goto load_freelist; + local_irq_restore(flags); + return NULL; + } } - if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit()) - slab_out_of_memory(s, gfpflags, node); - local_irq_restore(flags); - return NULL; -debug: - if (!object || !alloc_debug_processing(s, page, object, addr)) - goto new_slab; + if (likely(!kmem_cache_debug(s))) + goto load_freelist; + + /* Only entered in the debug case */ + if (!alloc_debug_processing(s, c->page, object, addr)) + goto new_slab; /* Slab failed checks. Next slab needed */ c->freelist = get_freepointer(s, object); deactivate_slab(s, c); - c->page = NULL; c->node = NUMA_NO_NODE; local_irq_restore(flags); return object; @@ -2333,16 +2402,29 @@ static void __slab_free(struct kmem_cache *s, struct page *page, was_frozen = new.frozen; new.inuse--; if ((!new.inuse || !prior) && !was_frozen && !n) { - n = get_node(s, page_to_nid(page)); - /* - * Speculatively acquire the list_lock. - * If the cmpxchg does not succeed then we may - * drop the list_lock without any processing. - * - * Otherwise the list_lock will synchronize with - * other processors updating the list of slabs. - */ - spin_lock_irqsave(&n->list_lock, flags); + + if (!kmem_cache_debug(s) && !prior) + + /* + * Slab was on no list before and will be partially empty + * We can defer the list move and instead freeze it. + */ + new.frozen = 1; + + else { /* Needs to be taken off a list */ + + n = get_node(s, page_to_nid(page)); + /* + * Speculatively acquire the list_lock. + * If the cmpxchg does not succeed then we may + * drop the list_lock without any processing. + * + * Otherwise the list_lock will synchronize with + * other processors updating the list of slabs. + */ + spin_lock_irqsave(&n->list_lock, flags); + + } } inuse = new.inuse; @@ -2352,7 +2434,15 @@ static void __slab_free(struct kmem_cache *s, struct page *page, "__slab_free")); if (likely(!n)) { - /* + + /* + * If we just froze the page then put it onto the + * per cpu partial list. + */ + if (new.frozen && !was_frozen) + put_cpu_partial(s, page, 1); + + /* * The list lock was not taken therefore no list * activity can be necessary. */ @@ -2377,7 +2467,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, */ if (unlikely(!prior)) { remove_full(s, page); - add_partial(n, page, 1); + add_partial(n, page, DEACTIVATE_TO_TAIL); stat(s, FREE_ADD_PARTIAL); } } @@ -2421,7 +2511,6 @@ static __always_inline void slab_free(struct kmem_cache *s, slab_free_hook(s, x); redo: - /* * Determine the currently cpus per cpu slab. * The cpu may change afterward. However that does not matter since @@ -2685,7 +2774,7 @@ static void early_kmem_cache_node_alloc(int node) n = page->freelist; BUG_ON(!n); page->freelist = get_freepointer(kmem_cache_node, n); - page->inuse++; + page->inuse = 1; page->frozen = 0; kmem_cache_node->node[node] = n; #ifdef CONFIG_SLUB_DEBUG @@ -2695,7 +2784,7 @@ static void early_kmem_cache_node_alloc(int node) init_kmem_cache_node(n, kmem_cache_node); inc_slabs_node(kmem_cache_node, node, page->objects); - add_partial(n, page, 0); + add_partial(n, page, DEACTIVATE_TO_HEAD); } static void free_kmem_cache_nodes(struct kmem_cache *s) @@ -2911,7 +3000,34 @@ static int kmem_cache_open(struct kmem_cache *s, * The larger the object size is, the more pages we want on the partial * list to avoid pounding the page allocator excessively. */ - set_min_partial(s, ilog2(s->size)); + set_min_partial(s, ilog2(s->size) / 2); + + /* + * cpu_partial determined the maximum number of objects kept in the + * per cpu partial lists of a processor. + * + * Per cpu partial lists mainly contain slabs that just have one + * object freed. If they are used for allocation then they can be + * filled up again with minimal effort. The slab will never hit the + * per node partial lists and therefore no locking will be required. + * + * This setting also determines + * + * A) The number of objects from per cpu partial slabs dumped to the + * per node list when we reach the limit. + * B) The number of objects in cpu partial slabs to extract from the + * per node list when we run out of per cpu objects. We only fetch 50% + * to keep some capacity around for frees. + */ + if (s->size >= PAGE_SIZE) + s->cpu_partial = 2; + else if (s->size >= 1024) + s->cpu_partial = 6; + else if (s->size >= 256) + s->cpu_partial = 13; + else + s->cpu_partial = 30; + s->refcount = 1; #ifdef CONFIG_NUMA s->remote_node_defrag_ratio = 1000; @@ -2970,13 +3086,13 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, /* * Attempt to free all partial slabs on a node. + * This is called from kmem_cache_close(). We must be the last thread + * using the cache and therefore we do not need to lock anymore. */ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) { - unsigned long flags; struct page *page, *h; - spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry_safe(page, h, &n->partial, lru) { if (!page->inuse) { remove_partial(n, page); @@ -2986,7 +3102,6 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) "Objects remaining on kmem_cache_close()"); } } - spin_unlock_irqrestore(&n->list_lock, flags); } /* @@ -3020,6 +3135,7 @@ void kmem_cache_destroy(struct kmem_cache *s) s->refcount--; if (!s->refcount) { list_del(&s->list); + up_write(&slub_lock); if (kmem_cache_close(s)) { printk(KERN_ERR "SLUB %s: %s called for cache that " "still has objects.\n", s->name, __func__); @@ -3028,8 +3144,8 @@ void kmem_cache_destroy(struct kmem_cache *s) if (s->flags & SLAB_DESTROY_BY_RCU) rcu_barrier(); sysfs_slab_remove(s); - } - up_write(&slub_lock); + } else + up_write(&slub_lock); } EXPORT_SYMBOL(kmem_cache_destroy); @@ -3347,23 +3463,23 @@ int kmem_cache_shrink(struct kmem_cache *s) * list_lock. page->inuse here is the upper limit. */ list_for_each_entry_safe(page, t, &n->partial, lru) { - if (!page->inuse) { - remove_partial(n, page); - discard_slab(s, page); - } else { - list_move(&page->lru, - slabs_by_inuse + page->inuse); - } + list_move(&page->lru, slabs_by_inuse + page->inuse); + if (!page->inuse) + n->nr_partial--; } /* * Rebuild the partial list with the slabs filled up most * first and the least used slabs at the end. */ - for (i = objects - 1; i >= 0; i--) + for (i = objects - 1; i > 0; i--) list_splice(slabs_by_inuse + i, n->partial.prev); spin_unlock_irqrestore(&n->list_lock, flags); + + /* Release empty slabs */ + list_for_each_entry_safe(page, t, slabs_by_inuse, lru) + discard_slab(s, page); } kfree(slabs_by_inuse); @@ -4319,6 +4435,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s, for_each_possible_cpu(cpu) { struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu); + struct page *page; if (!c || c->node < 0) continue; @@ -4334,6 +4451,13 @@ static ssize_t show_slab_objects(struct kmem_cache *s, total += x; nodes[c->node] += x; } + page = c->partial; + + if (page) { + x = page->pobjects; + total += x; + nodes[c->node] += x; + } per_cpu[c->node]++; } } @@ -4412,11 +4536,12 @@ struct slab_attribute { }; #define SLAB_ATTR_RO(_name) \ - static struct slab_attribute _name##_attr = __ATTR_RO(_name) + static struct slab_attribute _name##_attr = \ + __ATTR(_name, 0400, _name##_show, NULL) #define SLAB_ATTR(_name) \ static struct slab_attribute _name##_attr = \ - __ATTR(_name, 0644, _name##_show, _name##_store) + __ATTR(_name, 0600, _name##_show, _name##_store) static ssize_t slab_size_show(struct kmem_cache *s, char *buf) { @@ -4485,6 +4610,27 @@ static ssize_t min_partial_store(struct kmem_cache *s, const char *buf, } SLAB_ATTR(min_partial); +static ssize_t cpu_partial_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%u\n", s->cpu_partial); +} + +static ssize_t cpu_partial_store(struct kmem_cache *s, const char *buf, + size_t length) +{ + unsigned long objects; + int err; + + err = strict_strtoul(buf, 10, &objects); + if (err) + return err; + + s->cpu_partial = objects; + flush_all(s); + return length; +} +SLAB_ATTR(cpu_partial); + static ssize_t ctor_show(struct kmem_cache *s, char *buf) { if (!s->ctor) @@ -4523,6 +4669,37 @@ static ssize_t objects_partial_show(struct kmem_cache *s, char *buf) } SLAB_ATTR_RO(objects_partial); +static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf) +{ + int objects = 0; + int pages = 0; + int cpu; + int len; + + for_each_online_cpu(cpu) { + struct page *page = per_cpu_ptr(s->cpu_slab, cpu)->partial; + + if (page) { + pages += page->pages; + objects += page->pobjects; + } + } + + len = sprintf(buf, "%d(%d)", objects, pages); + +#ifdef CONFIG_SMP + for_each_online_cpu(cpu) { + struct page *page = per_cpu_ptr(s->cpu_slab, cpu) ->partial; + + if (page && len < PAGE_SIZE - 20) + len += sprintf(buf + len, " C%d=%d(%d)", cpu, + page->pobjects, page->pages); + } +#endif + return len + sprintf(buf + len, "\n"); +} +SLAB_ATTR_RO(slabs_cpu_partial); + static ssize_t reclaim_account_show(struct kmem_cache *s, char *buf) { return sprintf(buf, "%d\n", !!(s->flags & SLAB_RECLAIM_ACCOUNT)); @@ -4845,6 +5022,8 @@ STAT_ATTR(DEACTIVATE_BYPASS, deactivate_bypass); STAT_ATTR(ORDER_FALLBACK, order_fallback); STAT_ATTR(CMPXCHG_DOUBLE_CPU_FAIL, cmpxchg_double_cpu_fail); STAT_ATTR(CMPXCHG_DOUBLE_FAIL, cmpxchg_double_fail); +STAT_ATTR(CPU_PARTIAL_ALLOC, cpu_partial_alloc); +STAT_ATTR(CPU_PARTIAL_FREE, cpu_partial_free); #endif static struct attribute *slab_attrs[] = { @@ -4853,6 +5032,7 @@ static struct attribute *slab_attrs[] = { &objs_per_slab_attr.attr, &order_attr.attr, &min_partial_attr.attr, + &cpu_partial_attr.attr, &objects_attr.attr, &objects_partial_attr.attr, &partial_attr.attr, @@ -4865,6 +5045,7 @@ static struct attribute *slab_attrs[] = { &destroy_by_rcu_attr.attr, &shrink_attr.attr, &reserved_attr.attr, + &slabs_cpu_partial_attr.attr, #ifdef CONFIG_SLUB_DEBUG &total_objects_attr.attr, &slabs_attr.attr, @@ -4906,6 +5087,8 @@ static struct attribute *slab_attrs[] = { &order_fallback_attr.attr, &cmpxchg_double_fail_attr.attr, &cmpxchg_double_cpu_fail_attr.attr, + &cpu_partial_alloc_attr.attr, + &cpu_partial_free_attr.attr, #endif #ifdef CONFIG_FAILSLAB &failslab_attr.attr, @@ -5257,7 +5440,7 @@ static const struct file_operations proc_slabinfo_operations = { static int __init slab_proc_init(void) { - proc_create("slabinfo", S_IRUGO, NULL, &proc_slabinfo_operations); + proc_create("slabinfo", S_IRUSR, NULL, &proc_slabinfo_operations); return 0; } module_init(slab_proc_init); diff --git a/mm/swapfile.c b/mm/swapfile.c index 17bc224..c9d6540 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1617,7 +1617,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX); err = try_to_unuse(type); - test_set_oom_score_adj(oom_score_adj); + compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, oom_score_adj); if (err) { /* diff --git a/mm/thrash.c b/mm/thrash.c index e53f7d0..57ad495 100644 --- a/mm/thrash.c +++ b/mm/thrash.c @@ -29,7 +29,7 @@ static DEFINE_SPINLOCK(swap_token_lock); struct mm_struct *swap_token_mm; -struct mem_cgroup *swap_token_memcg; +static struct mem_cgroup *swap_token_memcg; #ifdef CONFIG_CGROUP_MEM_RES_CTLR static struct mem_cgroup *swap_token_memcg_from_mm(struct mm_struct *mm) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 5016f19..b669aa6 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1253,18 +1253,22 @@ EXPORT_SYMBOL_GPL(map_vm_area); DEFINE_RWLOCK(vmlist_lock); struct vm_struct *vmlist; -static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, +static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, unsigned long flags, void *caller) { - struct vm_struct *tmp, **p; - vm->flags = flags; vm->addr = (void *)va->va_start; vm->size = va->va_end - va->va_start; vm->caller = caller; va->private = vm; va->flags |= VM_VM_AREA; +} +static void insert_vmalloc_vmlist(struct vm_struct *vm) +{ + struct vm_struct *tmp, **p; + + vm->flags &= ~VM_UNLIST; write_lock(&vmlist_lock); for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) { if (tmp->addr >= vm->addr) @@ -1275,6 +1279,13 @@ static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, write_unlock(&vmlist_lock); } +static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, + unsigned long flags, void *caller) +{ + setup_vmalloc_vm(vm, va, flags, caller); + insert_vmalloc_vmlist(vm); +} + static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, void *caller) @@ -1313,7 +1324,18 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, return NULL; } - insert_vmalloc_vm(area, va, flags, caller); + /* + * When this function is called from __vmalloc_node_range, + * we do not add vm_struct to vmlist here to avoid + * accessing uninitialized members of vm_struct such as + * pages and nr_pages fields. They will be set later. + * To distinguish it from others, we use a VM_UNLIST flag. + */ + if (flags & VM_UNLIST) + setup_vmalloc_vm(area, va, flags, caller); + else + insert_vmalloc_vm(area, va, flags, caller); + return area; } @@ -1381,17 +1403,20 @@ struct vm_struct *remove_vm_area(const void *addr) va = find_vmap_area((unsigned long)addr); if (va && va->flags & VM_VM_AREA) { struct vm_struct *vm = va->private; - struct vm_struct *tmp, **p; - /* - * remove from list and disallow access to this vm_struct - * before unmap. (address range confliction is maintained by - * vmap.) - */ - write_lock(&vmlist_lock); - for (p = &vmlist; (tmp = *p) != vm; p = &tmp->next) - ; - *p = tmp->next; - write_unlock(&vmlist_lock); + + if (!(vm->flags & VM_UNLIST)) { + struct vm_struct *tmp, **p; + /* + * remove from list and disallow access to + * this vm_struct before unmap. (address range + * confliction is maintained by vmap.) + */ + write_lock(&vmlist_lock); + for (p = &vmlist; (tmp = *p) != vm; p = &tmp->next) + ; + *p = tmp->next; + write_unlock(&vmlist_lock); + } vmap_debug_free_range(va->va_start, va->va_end); free_unmap_vmap_area(va); @@ -1568,8 +1593,8 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, return area->addr; fail: - warn_alloc_failed(gfp_mask, order, "vmalloc: allocation failure, " - "allocated %ld of %ld bytes\n", + warn_alloc_failed(gfp_mask, order, + "vmalloc: allocation failure, allocated %ld of %ld bytes\n", (area->nr_pages*PAGE_SIZE), area->size); vfree(area->addr); return NULL; @@ -1600,17 +1625,22 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, size = PAGE_ALIGN(size); if (!size || (size >> PAGE_SHIFT) > totalram_pages) - return NULL; - - area = __get_vm_area_node(size, align, VM_ALLOC, start, end, node, - gfp_mask, caller); + goto fail; + area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNLIST, + start, end, node, gfp_mask, caller); if (!area) - return NULL; + goto fail; addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller); /* + * In this function, newly allocated vm_struct is not added + * to vmlist at __get_vm_area_node(). so, it is added here. + */ + insert_vmalloc_vmlist(area); + + /* * A ref_count = 3 is needed because the vm_struct and vmap_area * structures allocated in the __get_vm_area_node() function contain * references to the virtual address of the vmalloc'ed block. @@ -1618,6 +1648,12 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, kmemleak_alloc(addr, real_size, 3, gfp_mask); return addr; + +fail: + warn_alloc_failed(gfp_mask, 0, + "vmalloc: allocation failure: %lu bytes\n", + real_size); + return NULL; } /** diff --git a/mm/vmscan.c b/mm/vmscan.c index b55699c..a90c603 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -495,15 +495,6 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, return PAGE_ACTIVATE; } - /* - * Wait on writeback if requested to. This happens when - * direct reclaiming a large contiguous area and the - * first attempt to free a range of pages fails. - */ - if (PageWriteback(page) && - (sc->reclaim_mode & RECLAIM_MODE_SYNC)) - wait_on_page_writeback(page); - if (!PageWriteback(page)) { /* synchronous write or broken a_ops? */ ClearPageReclaim(page); @@ -642,13 +633,14 @@ redo: lru = LRU_UNEVICTABLE; add_page_to_unevictable_list(page); /* - * When racing with an mlock clearing (page is - * unlocked), make sure that if the other thread does - * not observe our setting of PG_lru and fails - * isolation, we see PG_mlocked cleared below and move + * When racing with an mlock or AS_UNEVICTABLE clearing + * (page is unlocked) make sure that if the other thread + * does not observe our setting of PG_lru and fails + * isolation/check_move_unevictable_page, + * we see PG_mlocked/AS_UNEVICTABLE cleared below and move * the page back to the evictable list. * - * The other side is TestClearPageMlocked(). + * The other side is TestClearPageMlocked() or shmem_lock(). */ smp_mb(); } @@ -759,7 +751,10 @@ static noinline_for_stack void free_page_list(struct list_head *free_pages) */ static unsigned long shrink_page_list(struct list_head *page_list, struct zone *zone, - struct scan_control *sc) + struct scan_control *sc, + int priority, + unsigned long *ret_nr_dirty, + unsigned long *ret_nr_writeback) { LIST_HEAD(ret_pages); LIST_HEAD(free_pages); @@ -767,6 +762,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, unsigned long nr_dirty = 0; unsigned long nr_congested = 0; unsigned long nr_reclaimed = 0; + unsigned long nr_writeback = 0; cond_resched(); @@ -803,13 +799,12 @@ static unsigned long shrink_page_list(struct list_head *page_list, (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO)); if (PageWriteback(page)) { + nr_writeback++; /* - * Synchronous reclaim is performed in two passes, - * first an asynchronous pass over the list to - * start parallel writeback, and a second synchronous - * pass to wait for the IO to complete. Wait here - * for any page for which writeback has already - * started. + * Synchronous reclaim cannot queue pages for + * writeback due to the possibility of stack overflow + * but if it encounters a page under writeback, wait + * for the IO to complete. */ if ((sc->reclaim_mode & RECLAIM_MODE_SYNC) && may_enter_fs) @@ -865,6 +860,25 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (PageDirty(page)) { nr_dirty++; + /* + * Only kswapd can writeback filesystem pages to + * avoid risk of stack overflow but do not writeback + * unless under significant pressure. + */ + if (page_is_file_cache(page) && + (!current_is_kswapd() || priority >= DEF_PRIORITY - 2)) { + /* + * Immediately reclaim when written back. + * Similar in principal to deactivate_page() + * except we already have the page isolated + * and know it's dirty + */ + inc_zone_page_state(page, NR_VMSCAN_IMMEDIATE); + SetPageReclaim(page); + + goto keep_locked; + } + if (references == PAGEREF_RECLAIM_CLEAN) goto keep_locked; if (!may_enter_fs) @@ -999,6 +1013,8 @@ keep_lumpy: list_splice(&ret_pages, page_list); count_vm_events(PGACTIVATE, pgactivate); + *ret_nr_dirty += nr_dirty; + *ret_nr_writeback += nr_writeback; return nr_reclaimed; } @@ -1012,23 +1028,27 @@ keep_lumpy: * * returns 0 on success, -ve errno on failure. */ -int __isolate_lru_page(struct page *page, int mode, int file) +int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file) { + bool all_lru_mode; int ret = -EINVAL; /* Only take pages on the LRU. */ if (!PageLRU(page)) return ret; + all_lru_mode = (mode & (ISOLATE_ACTIVE|ISOLATE_INACTIVE)) == + (ISOLATE_ACTIVE|ISOLATE_INACTIVE); + /* * When checking the active state, we need to be sure we are * dealing with comparible boolean values. Take the logical not * of each. */ - if (mode != ISOLATE_BOTH && (!PageActive(page) != !mode)) + if (!all_lru_mode && !PageActive(page) != !(mode & ISOLATE_ACTIVE)) return ret; - if (mode != ISOLATE_BOTH && page_is_file_cache(page) != file) + if (!all_lru_mode && !!page_is_file_cache(page) != file) return ret; /* @@ -1041,6 +1061,12 @@ int __isolate_lru_page(struct page *page, int mode, int file) ret = -EBUSY; + if ((mode & ISOLATE_CLEAN) && (PageDirty(page) || PageWriteback(page))) + return ret; + + if ((mode & ISOLATE_UNMAPPED) && page_mapped(page)) + return ret; + if (likely(get_page_unless_zero(page))) { /* * Be careful not to clear PageLRU until after we're @@ -1076,7 +1102,8 @@ int __isolate_lru_page(struct page *page, int mode, int file) */ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, struct list_head *src, struct list_head *dst, - unsigned long *scanned, int order, int mode, int file) + unsigned long *scanned, int order, isolate_mode_t mode, + int file) { unsigned long nr_taken = 0; unsigned long nr_lumpy_taken = 0; @@ -1201,8 +1228,8 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, static unsigned long isolate_pages_global(unsigned long nr, struct list_head *dst, unsigned long *scanned, int order, - int mode, struct zone *z, - int active, int file) + isolate_mode_t mode, + struct zone *z, int active, int file) { int lru = LRU_BASE; if (active) @@ -1394,7 +1421,7 @@ static noinline_for_stack void update_isolated_counts(struct zone *zone, } /* - * Returns true if the caller should wait to clean dirty/writeback pages. + * Returns true if a direct reclaim should wait on pages under writeback. * * If we are direct reclaiming for contiguous pages and we do not reclaim * everything in the list, try again and wait for writeback IO to complete. @@ -1416,7 +1443,7 @@ static inline bool should_reclaim_stall(unsigned long nr_taken, if (sc->reclaim_mode & RECLAIM_MODE_SINGLE) return false; - /* If we have relaimed everything on the isolated list, no stall */ + /* If we have reclaimed everything on the isolated list, no stall */ if (nr_freed == nr_taken) return false; @@ -1448,6 +1475,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, unsigned long nr_taken; unsigned long nr_anon; unsigned long nr_file; + unsigned long nr_dirty = 0; + unsigned long nr_writeback = 0; + isolate_mode_t reclaim_mode = ISOLATE_INACTIVE; while (unlikely(too_many_isolated(zone, file, sc))) { congestion_wait(BLK_RW_ASYNC, HZ/10); @@ -1458,15 +1488,21 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, } set_reclaim_mode(priority, sc, false); + if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM) + reclaim_mode |= ISOLATE_ACTIVE; + lru_add_drain(); + + if (!sc->may_unmap) + reclaim_mode |= ISOLATE_UNMAPPED; + if (!sc->may_writepage) + reclaim_mode |= ISOLATE_CLEAN; + spin_lock_irq(&zone->lru_lock); if (scanning_global_lru(sc)) { - nr_taken = isolate_pages_global(nr_to_scan, - &page_list, &nr_scanned, sc->order, - sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ? - ISOLATE_BOTH : ISOLATE_INACTIVE, - zone, 0, file); + nr_taken = isolate_pages_global(nr_to_scan, &page_list, + &nr_scanned, sc->order, reclaim_mode, zone, 0, file); zone->pages_scanned += nr_scanned; if (current_is_kswapd()) __count_zone_vm_events(PGSCAN_KSWAPD, zone, @@ -1475,12 +1511,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, __count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scanned); } else { - nr_taken = mem_cgroup_isolate_pages(nr_to_scan, - &page_list, &nr_scanned, sc->order, - sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ? - ISOLATE_BOTH : ISOLATE_INACTIVE, - zone, sc->mem_cgroup, - 0, file); + nr_taken = mem_cgroup_isolate_pages(nr_to_scan, &page_list, + &nr_scanned, sc->order, reclaim_mode, zone, + sc->mem_cgroup, 0, file); /* * mem_cgroup_isolate_pages() keeps track of * scanned pages on its own. @@ -1496,12 +1529,14 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, spin_unlock_irq(&zone->lru_lock); - nr_reclaimed = shrink_page_list(&page_list, zone, sc); + nr_reclaimed = shrink_page_list(&page_list, zone, sc, priority, + &nr_dirty, &nr_writeback); /* Check if we should syncronously wait for writeback */ if (should_reclaim_stall(nr_taken, nr_reclaimed, priority, sc)) { set_reclaim_mode(priority, sc, true); - nr_reclaimed += shrink_page_list(&page_list, zone, sc); + nr_reclaimed += shrink_page_list(&page_list, zone, sc, + priority, &nr_dirty, &nr_writeback); } local_irq_disable(); @@ -1511,6 +1546,32 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, putback_lru_pages(zone, sc, nr_anon, nr_file, &page_list); + /* + * If reclaim is isolating dirty pages under writeback, it implies + * that the long-lived page allocation rate is exceeding the page + * laundering rate. Either the global limits are not being effective + * at throttling processes due to the page distribution throughout + * zones or there is heavy usage of a slow backing device. The + * only option is to throttle from reclaim context which is not ideal + * as there is no guarantee the dirtying process is throttled in the + * same way balance_dirty_pages() manages. + * + * This scales the number of dirty pages that must be under writeback + * before throttling depending on priority. It is a simple backoff + * function that has the most effect in the range DEF_PRIORITY to + * DEF_PRIORITY-2 which is the priority reclaim is considered to be + * in trouble and reclaim is considered to be in trouble. + * + * DEF_PRIORITY 100% isolated pages must be PageWriteback to throttle + * DEF_PRIORITY-1 50% must be PageWriteback + * DEF_PRIORITY-2 25% must be PageWriteback, kswapd in trouble + * ... + * DEF_PRIORITY-6 For SWAP_CLUSTER_MAX isolated pages, throttle if any + * isolated page is PageWriteback + */ + if (nr_writeback && nr_writeback >= (nr_taken >> (DEF_PRIORITY-priority))) + wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10); + trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id, zone_idx(zone), nr_scanned, nr_reclaimed, @@ -1582,19 +1643,26 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, struct page *page; struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc); unsigned long nr_rotated = 0; + isolate_mode_t reclaim_mode = ISOLATE_ACTIVE; lru_add_drain(); + + if (!sc->may_unmap) + reclaim_mode |= ISOLATE_UNMAPPED; + if (!sc->may_writepage) + reclaim_mode |= ISOLATE_CLEAN; + spin_lock_irq(&zone->lru_lock); if (scanning_global_lru(sc)) { nr_taken = isolate_pages_global(nr_pages, &l_hold, &pgscanned, sc->order, - ISOLATE_ACTIVE, zone, + reclaim_mode, zone, 1, file); zone->pages_scanned += pgscanned; } else { nr_taken = mem_cgroup_isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order, - ISOLATE_ACTIVE, zone, + reclaim_mode, zone, sc->mem_cgroup, 1, file); /* * mem_cgroup_isolate_pages() keeps track of @@ -1795,12 +1863,19 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc, enum lru_list l; int noswap = 0; bool force_scan = false; - unsigned long nr_force_scan[2]; - /* kswapd does zone balancing and needs to scan this zone */ + /* + * If the zone or memcg is small, nr[l] can be 0. This + * results in no scanning on this priority and a potential + * priority drop. Global direct reclaim can go to the next + * zone and tends to have no problems. Global kswapd is for + * zone balancing and it needs to scan a minimum amount. When + * reclaiming for a memcg, a priority drop can cause high + * latencies, so it's better to scan a minimum amount there as + * well. + */ if (scanning_global_lru(sc) && current_is_kswapd()) force_scan = true; - /* memcg may have small limit and need to avoid priority drop */ if (!scanning_global_lru(sc)) force_scan = true; @@ -1810,8 +1885,6 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc, fraction[0] = 0; fraction[1] = 1; denominator = 1; - nr_force_scan[0] = 0; - nr_force_scan[1] = SWAP_CLUSTER_MAX; goto out; } @@ -1828,8 +1901,6 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc, fraction[0] = 1; fraction[1] = 0; denominator = 1; - nr_force_scan[0] = SWAP_CLUSTER_MAX; - nr_force_scan[1] = 0; goto out; } } @@ -1878,11 +1949,6 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc, fraction[0] = ap; fraction[1] = fp; denominator = ap + fp + 1; - if (force_scan) { - unsigned long scan = SWAP_CLUSTER_MAX; - nr_force_scan[0] = div64_u64(scan * ap, denominator); - nr_force_scan[1] = div64_u64(scan * fp, denominator); - } out: for_each_evictable_lru(l) { int file = is_file_lru(l); @@ -1891,20 +1957,10 @@ out: scan = zone_nr_lru_pages(zone, sc, l); if (priority || noswap) { scan >>= priority; + if (!scan && force_scan) + scan = SWAP_CLUSTER_MAX; scan = div64_u64(scan * fraction[file], denominator); } - - /* - * If zone is small or memcg is small, nr[l] can be 0. - * This results no-scan on this priority and priority drop down. - * For global direct reclaim, it can visit next zone and tend - * not to have problems. For global kswapd, it's for zone - * balancing and it need to scan a small amounts. When using - * memcg, priority drop can cause big latency. So, it's better - * to scan small amount. See may_noscan above. - */ - if (!scan && force_scan) - scan = nr_force_scan[file]; nr[l] = scan; } } @@ -1983,12 +2039,14 @@ static void shrink_zone(int priority, struct zone *zone, enum lru_list l; unsigned long nr_reclaimed, nr_scanned; unsigned long nr_to_reclaim = sc->nr_to_reclaim; + struct blk_plug plug; restart: nr_reclaimed = 0; nr_scanned = sc->nr_scanned; get_scan_count(zone, sc, nr, priority); + blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { for_each_evictable_lru(l) { @@ -2012,6 +2070,7 @@ restart: if (nr_reclaimed >= nr_to_reclaim && priority < DEF_PRIORITY) break; } + blk_finish_plug(&plug); sc->nr_reclaimed += nr_reclaimed; /* @@ -2044,14 +2103,19 @@ restart: * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. + * + * This function returns true if a zone is being reclaimed for a costly + * high-order allocation and compaction is either ready to begin or deferred. + * This indicates to the caller that it should retry the allocation or fail. */ -static void shrink_zones(int priority, struct zonelist *zonelist, +static bool shrink_zones(int priority, struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; + bool should_abort_reclaim = false; for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(sc->gfp_mask), sc->nodemask) { @@ -2066,6 +2130,23 @@ static void shrink_zones(int priority, struct zonelist *zonelist, continue; if (zone->all_unreclaimable && priority != DEF_PRIORITY) continue; /* Let kswapd poll it */ + if (COMPACTION_BUILD) { + /* + * If we already have plenty of memory free for + * compaction in this zone, don't free any more. + * Even though compaction is invoked for any + * non-zero order, only frequent costly order + * reclamation is disruptive enough to become a + * noticable problem, like transparent huge page + * allocations. + */ + if (sc->order > PAGE_ALLOC_COSTLY_ORDER && + (compaction_suitable(zone, sc->order) || + compaction_deferred(zone))) { + should_abort_reclaim = true; + continue; + } + } /* * This steals pages from memory cgroups over softlimit * and returns the number of reclaimed pages and @@ -2083,6 +2164,8 @@ static void shrink_zones(int priority, struct zonelist *zonelist, shrink_zone(priority, zone, sc); } + + return should_abort_reclaim; } static bool zone_reclaimable(struct zone *zone) @@ -2147,7 +2230,9 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, sc->nr_scanned = 0; if (!priority) disable_swap_token(sc->mem_cgroup); - shrink_zones(priority, zonelist, sc); + if (shrink_zones(priority, zonelist, sc)) + break; + /* * Don't shrink slabs when reclaiming memory from * over limit cgroups @@ -2690,6 +2775,8 @@ out: /* If balanced, clear the congested flag */ zone_clear_flag(zone, ZONE_CONGESTED); + if (i <= *classzone_idx) + balanced += zone->present_pages; } } @@ -2763,7 +2850,9 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) static int kswapd(void *p) { unsigned long order, new_order; + unsigned balanced_order; int classzone_idx, new_classzone_idx; + int balanced_classzone_idx; pg_data_t *pgdat = (pg_data_t*)p; struct task_struct *tsk = current; @@ -2794,7 +2883,9 @@ static int kswapd(void *p) set_freezable(); order = new_order = 0; + balanced_order = 0; classzone_idx = new_classzone_idx = pgdat->nr_zones - 1; + balanced_classzone_idx = classzone_idx; for ( ; ; ) { int ret; @@ -2803,7 +2894,8 @@ static int kswapd(void *p) * new request of a similar or harder type will succeed soon * so consider going to sleep on the basis we reclaimed at */ - if (classzone_idx >= new_classzone_idx && order == new_order) { + if (balanced_classzone_idx >= new_classzone_idx && + balanced_order == new_order) { new_order = pgdat->kswapd_max_order; new_classzone_idx = pgdat->classzone_idx; pgdat->kswapd_max_order = 0; @@ -2818,9 +2910,12 @@ static int kswapd(void *p) order = new_order; classzone_idx = new_classzone_idx; } else { - kswapd_try_to_sleep(pgdat, order, classzone_idx); + kswapd_try_to_sleep(pgdat, balanced_order, + balanced_classzone_idx); order = pgdat->kswapd_max_order; classzone_idx = pgdat->classzone_idx; + new_order = order; + new_classzone_idx = classzone_idx; pgdat->kswapd_max_order = 0; pgdat->classzone_idx = pgdat->nr_zones - 1; } @@ -2835,7 +2930,9 @@ static int kswapd(void *p) */ if (!ret) { trace_mm_vmscan_kswapd_wake(pgdat->node_id, order); - order = balance_pgdat(pgdat, order, &classzone_idx); + balanced_classzone_idx = classzone_idx; + balanced_order = balance_pgdat(pgdat, order, + &balanced_classzone_idx); } } return 0; @@ -3347,66 +3444,12 @@ void scan_mapping_unevictable_pages(struct address_space *mapping) } -/** - * scan_zone_unevictable_pages - check unevictable list for evictable pages - * @zone - zone of which to scan the unevictable list - * - * Scan @zone's unevictable LRU lists to check for pages that have become - * evictable. Move those that have to @zone's inactive list where they - * become candidates for reclaim, unless shrink_inactive_zone() decides - * to reactivate them. Pages that are still unevictable are rotated - * back onto @zone's unevictable list. - */ -#define SCAN_UNEVICTABLE_BATCH_SIZE 16UL /* arbitrary lock hold batch size */ -static void scan_zone_unevictable_pages(struct zone *zone) +static void warn_scan_unevictable_pages(void) { - struct list_head *l_unevictable = &zone->lru[LRU_UNEVICTABLE].list; - unsigned long scan; - unsigned long nr_to_scan = zone_page_state(zone, NR_UNEVICTABLE); - - while (nr_to_scan > 0) { - unsigned long batch_size = min(nr_to_scan, - SCAN_UNEVICTABLE_BATCH_SIZE); - - spin_lock_irq(&zone->lru_lock); - for (scan = 0; scan < batch_size; scan++) { - struct page *page = lru_to_page(l_unevictable); - - if (!trylock_page(page)) - continue; - - prefetchw_prev_lru_page(page, l_unevictable, flags); - - if (likely(PageLRU(page) && PageUnevictable(page))) - check_move_unevictable_page(page, zone); - - unlock_page(page); - } - spin_unlock_irq(&zone->lru_lock); - - nr_to_scan -= batch_size; - } -} - - -/** - * scan_all_zones_unevictable_pages - scan all unevictable lists for evictable pages - * - * A really big hammer: scan all zones' unevictable LRU lists to check for - * pages that have become evictable. Move those back to the zones' - * inactive list where they become candidates for reclaim. - * This occurs when, e.g., we have unswappable pages on the unevictable lists, - * and we add swap to the system. As such, it runs in the context of a task - * that has possibly/probably made some previously unevictable pages - * evictable. - */ -static void scan_all_zones_unevictable_pages(void) -{ - struct zone *zone; - - for_each_zone(zone) { - scan_zone_unevictable_pages(zone); - } + printk_once(KERN_WARNING + "The scan_unevictable_pages sysctl/node-interface has been " + "disabled for lack of a legitimate use case. If you have " + "one, please send an email to linux-mm@kvack.org.\n"); } /* @@ -3419,11 +3462,8 @@ int scan_unevictable_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { + warn_scan_unevictable_pages(); proc_doulongvec_minmax(table, write, buffer, length, ppos); - - if (write && *(unsigned long *)table->data) - scan_all_zones_unevictable_pages(); - scan_unevictable_pages = 0; return 0; } @@ -3438,6 +3478,7 @@ static ssize_t read_scan_unevictable_node(struct sys_device *dev, struct sysdev_attribute *attr, char *buf) { + warn_scan_unevictable_pages(); return sprintf(buf, "0\n"); /* always zero; should fit... */ } @@ -3445,19 +3486,7 @@ static ssize_t write_scan_unevictable_node(struct sys_device *dev, struct sysdev_attribute *attr, const char *buf, size_t count) { - struct zone *node_zones = NODE_DATA(dev->id)->node_zones; - struct zone *zone; - unsigned long res; - unsigned long req = strict_strtoul(buf, 10, &res); - - if (!req) - return 1; /* zero is no-op */ - - for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { - if (!populated_zone(zone)) - continue; - scan_zone_unevictable_pages(zone); - } + warn_scan_unevictable_pages(); return 1; } diff --git a/mm/vmstat.c b/mm/vmstat.c index d52b13d..8fd603b 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -78,7 +78,7 @@ void vm_events_fold_cpu(int cpu) * * vm_stat contains the global counters */ -atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; +atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp; EXPORT_SYMBOL(vm_stat); #ifdef CONFIG_SMP @@ -702,6 +702,7 @@ const char * const vmstat_text[] = { "nr_unstable", "nr_bounce", "nr_vmscan_write", + "nr_vmscan_immediate_reclaim", "nr_writeback_temp", "nr_isolated_anon", "nr_isolated_file", |