diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Kconfig | 13 | ||||
-rw-r--r-- | mm/backing-dev.c | 27 | ||||
-rw-r--r-- | mm/bootmem.c | 24 | ||||
-rw-r--r-- | mm/filemap.c | 51 | ||||
-rw-r--r-- | mm/highmem.c | 17 | ||||
-rw-r--r-- | mm/kmemleak.c | 9 | ||||
-rw-r--r-- | mm/ksm.c | 11 | ||||
-rw-r--r-- | mm/memcontrol.c | 6 | ||||
-rw-r--r-- | mm/memory-failure.c | 61 | ||||
-rw-r--r-- | mm/memory.c | 14 | ||||
-rw-r--r-- | mm/memory_hotplug.c | 24 | ||||
-rw-r--r-- | mm/mempolicy.c | 13 | ||||
-rw-r--r-- | mm/migrate.c | 2 | ||||
-rw-r--r-- | mm/mmap.c | 46 | ||||
-rw-r--r-- | mm/mremap.c | 241 | ||||
-rw-r--r-- | mm/nommu.c | 6 | ||||
-rw-r--r-- | mm/page-writeback.c | 15 | ||||
-rw-r--r-- | mm/page_alloc.c | 7 | ||||
-rw-r--r-- | mm/percpu.c | 144 | ||||
-rw-r--r-- | mm/slab.c | 118 | ||||
-rw-r--r-- | mm/slub.c | 2 | ||||
-rw-r--r-- | mm/swapfile.c | 3 | ||||
-rw-r--r-- | mm/truncate.c | 2 | ||||
-rw-r--r-- | mm/util.c | 44 | ||||
-rw-r--r-- | mm/vmalloc.c | 50 | ||||
-rw-r--r-- | mm/vmscan.c | 14 |
26 files changed, 589 insertions, 375 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index edd300aca17..44cf6f0a3a6 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -67,7 +67,7 @@ config DISCONTIGMEM config SPARSEMEM def_bool y - depends on SPARSEMEM_MANUAL + depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL config FLATMEM def_bool y @@ -128,11 +128,8 @@ config SPARSEMEM_VMEMMAP config MEMORY_HOTPLUG bool "Allow for memory hot-add" depends on SPARSEMEM || X86_64_ACPI_NUMA - depends on HOTPLUG && !(HIBERNATION && !S390) && ARCH_ENABLE_MEMORY_HOTPLUG - depends on (IA64 || X86 || PPC64 || SUPERH || S390) - -comment "Memory hotplug is currently incompatible with Software Suspend" - depends on SPARSEMEM && HOTPLUG && HIBERNATION && !S390 + depends on HOTPLUG && ARCH_ENABLE_MEMORY_HOTPLUG + depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390) config MEMORY_HOTPLUG_SPARSE def_bool y @@ -224,7 +221,9 @@ config KSM the many instances by a single resident page with that content, so saving memory until one or another app needs to modify the content. Recommended for use with KVM, or with other duplicative applications. - See Documentation/vm/ksm.txt for more information. + See Documentation/vm/ksm.txt for more information: KSM is inactive + until a program has madvised that an area is MADV_MERGEABLE, and + root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set). config DEFAULT_MMAP_MIN_ADDR int "Low address space to protect from user allocation" diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 3d3accb1f80..0e8ca034770 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -92,7 +92,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) "BdiDirtyThresh: %8lu kB\n" "DirtyThresh: %8lu kB\n" "BackgroundThresh: %8lu kB\n" - "WriteBack threads:%8lu\n" + "WritebackThreads: %8lu\n" "b_dirty: %8lu\n" "b_io: %8lu\n" "b_more_io: %8lu\n" @@ -604,15 +604,36 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) /* * Finally, kill the kernel threads. We don't need to be RCU - * safe anymore, since the bdi is gone from visibility. + * safe anymore, since the bdi is gone from visibility. Force + * unfreeze of the thread before calling kthread_stop(), otherwise + * it would never exet if it is currently stuck in the refrigerator. */ - list_for_each_entry(wb, &bdi->wb_list, list) + list_for_each_entry(wb, &bdi->wb_list, list) { + thaw_process(wb->task); kthread_stop(wb->task); + } +} + +/* + * This bdi is going away now, make sure that no super_blocks point to it + */ +static void bdi_prune_sb(struct backing_dev_info *bdi) +{ + struct super_block *sb; + + spin_lock(&sb_lock); + list_for_each_entry(sb, &super_blocks, s_list) { + if (sb->s_bdi == bdi) + sb->s_bdi = NULL; + } + spin_unlock(&sb_lock); } void bdi_unregister(struct backing_dev_info *bdi) { if (bdi->dev) { + bdi_prune_sb(bdi); + if (!bdi_cap_flush_forker(bdi)) bdi_wb_shutdown(bdi); bdi_debug_unregister(bdi); diff --git a/mm/bootmem.c b/mm/bootmem.c index 555d5d2731c..d1dc23cc7f1 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -143,6 +143,30 @@ unsigned long __init init_bootmem(unsigned long start, unsigned long pages) return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages); } +/* + * free_bootmem_late - free bootmem pages directly to page allocator + * @addr: starting address of the range + * @size: size of the range in bytes + * + * This is only useful when the bootmem allocator has already been torn + * down, but we are still initializing the system. Pages are given directly + * to the page allocator, no bootmem metadata is updated because it is gone. + */ +void __init free_bootmem_late(unsigned long addr, unsigned long size) +{ + unsigned long cursor, end; + + kmemleak_free_part(__va(addr), size); + + cursor = PFN_UP(addr); + end = PFN_DOWN(addr + size); + + for (; cursor < end; cursor++) { + __free_pages_bootmem(pfn_to_page(cursor), 0); + totalram_pages++; + } +} + static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) { int aligned; diff --git a/mm/filemap.c b/mm/filemap.c index ef169f37156..8b4d88f9249 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -260,27 +260,27 @@ int filemap_flush(struct address_space *mapping) EXPORT_SYMBOL(filemap_flush); /** - * wait_on_page_writeback_range - wait for writeback to complete - * @mapping: target address_space - * @start: beginning page index - * @end: ending page index + * filemap_fdatawait_range - wait for writeback to complete + * @mapping: address space structure to wait for + * @start_byte: offset in bytes where the range starts + * @end_byte: offset in bytes where the range ends (inclusive) * - * Wait for writeback to complete against pages indexed by start->end - * inclusive + * Walk the list of under-writeback pages of the given address space + * in the given range and wait for all of them. */ -int wait_on_page_writeback_range(struct address_space *mapping, - pgoff_t start, pgoff_t end) +int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, + loff_t end_byte) { + pgoff_t index = start_byte >> PAGE_CACHE_SHIFT; + pgoff_t end = end_byte >> PAGE_CACHE_SHIFT; struct pagevec pvec; int nr_pages; int ret = 0; - pgoff_t index; - if (end < start) + if (end_byte < start_byte) return 0; pagevec_init(&pvec, 0); - index = start; while ((index <= end) && (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_WRITEBACK, @@ -310,25 +310,6 @@ int wait_on_page_writeback_range(struct address_space *mapping, return ret; } - -/** - * filemap_fdatawait_range - wait for all under-writeback pages to complete in a given range - * @mapping: address space structure to wait for - * @start: offset in bytes where the range starts - * @end: offset in bytes where the range ends (inclusive) - * - * Walk the list of under-writeback pages of the given address space - * in the given range and wait for all of them. - * - * This is just a simple wrapper so that callers don't have to convert offsets - * to page indexes themselves - */ -int filemap_fdatawait_range(struct address_space *mapping, loff_t start, - loff_t end) -{ - return wait_on_page_writeback_range(mapping, start >> PAGE_CACHE_SHIFT, - end >> PAGE_CACHE_SHIFT); -} EXPORT_SYMBOL(filemap_fdatawait_range); /** @@ -345,8 +326,7 @@ int filemap_fdatawait(struct address_space *mapping) if (i_size == 0) return 0; - return wait_on_page_writeback_range(mapping, 0, - (i_size - 1) >> PAGE_CACHE_SHIFT); + return filemap_fdatawait_range(mapping, 0, i_size - 1); } EXPORT_SYMBOL(filemap_fdatawait); @@ -393,9 +373,8 @@ int filemap_write_and_wait_range(struct address_space *mapping, WB_SYNC_ALL); /* See comment of filemap_write_and_wait() */ if (err != -EIO) { - int err2 = wait_on_page_writeback_range(mapping, - lstart >> PAGE_CACHE_SHIFT, - lend >> PAGE_CACHE_SHIFT); + int err2 = filemap_fdatawait_range(mapping, + lstart, lend); if (!err) err = err2; } @@ -1844,7 +1823,7 @@ static size_t __iovec_copy_from_user_inatomic(char *vaddr, /* * Copy as much as we can into the page and return the number of bytes which - * were sucessfully copied. If a fault is encountered then return the number of + * were successfully copied. If a fault is encountered then return the number of * bytes which were copied. */ size_t iov_iter_copy_from_user_atomic(struct page *page, diff --git a/mm/highmem.c b/mm/highmem.c index 25878cc49da..9c1e627f282 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -426,16 +426,21 @@ void __init page_address_init(void) void debug_kmap_atomic(enum km_type type) { - static unsigned warn_count = 10; + static int warn_count = 10; - if (unlikely(warn_count == 0)) + if (unlikely(warn_count < 0)) return; if (unlikely(in_interrupt())) { - if (in_irq()) { + if (in_nmi()) { + if (type != KM_NMI && type != KM_NMI_PTE) { + WARN_ON(1); + warn_count--; + } + } else if (in_irq()) { if (type != KM_IRQ0 && type != KM_IRQ1 && type != KM_BIO_SRC_IRQ && type != KM_BIO_DST_IRQ && - type != KM_BOUNCE_READ) { + type != KM_BOUNCE_READ && type != KM_IRQ_PTE) { WARN_ON(1); warn_count--; } @@ -452,7 +457,9 @@ void debug_kmap_atomic(enum km_type type) } if (type == KM_IRQ0 || type == KM_IRQ1 || type == KM_BOUNCE_READ || - type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ) { + type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ || + type == KM_IRQ_PTE || type == KM_NMI || + type == KM_NMI_PTE ) { if (!irqs_disabled()) { WARN_ON(1); warn_count--; diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 4ea4510e299..13f33b3081e 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -833,12 +833,15 @@ static void early_alloc(struct early_log *log) */ rcu_read_lock(); object = create_object((unsigned long)log->ptr, log->size, - log->min_count, GFP_KERNEL); + log->min_count, GFP_ATOMIC); + if (!object) + goto out; spin_lock_irqsave(&object->lock, flags); for (i = 0; i < log->trace_len; i++) object->trace[i] = log->trace[i]; object->trace_len = log->trace_len; spin_unlock_irqrestore(&object->lock, flags); +out: rcu_read_unlock(); } @@ -1047,8 +1050,8 @@ static void scan_object(struct kmemleak_object *object) unsigned long flags; /* - * Once the object->lock is aquired, the corresponding memory block - * cannot be freed (the same lock is aquired in delete_object). + * Once the object->lock is acquired, the corresponding memory block + * cannot be freed (the same lock is acquired in delete_object). */ spin_lock_irqsave(&object->lock, flags); if (object->flags & OBJECT_NO_SCAN) @@ -184,11 +184,6 @@ static DEFINE_SPINLOCK(ksm_mmlist_lock); sizeof(struct __struct), __alignof__(struct __struct),\ (__flags), NULL) -static void __init ksm_init_max_kernel_pages(void) -{ - ksm_max_kernel_pages = nr_free_buffer_pages() / 4; -} - static int __init ksm_slab_init(void) { rmap_item_cache = KSM_KMEM_CACHE(rmap_item, 0); @@ -1017,6 +1012,7 @@ static struct rmap_item *unstable_tree_search_insert(struct page *page, struct rmap_item *tree_rmap_item; int ret; + cond_resched(); tree_rmap_item = rb_entry(*new, struct rmap_item, node); page2[0] = get_mergeable_page(tree_rmap_item); if (!page2[0]) @@ -1673,7 +1669,7 @@ static int __init ksm_init(void) struct task_struct *ksm_thread; int err; - ksm_init_max_kernel_pages(); + ksm_max_kernel_pages = totalram_pages / 4; err = ksm_slab_init(); if (err) @@ -1697,6 +1693,9 @@ static int __init ksm_init(void) kthread_stop(ksm_thread); goto out_free2; } +#else + ksm_run = KSM_RUN_MERGE; /* no way for user to start it */ + #endif /* CONFIG_SYSFS */ return 0; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f99f5991d6b..c31a310aa14 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -209,7 +209,7 @@ struct mem_cgroup { int prev_priority; /* for recording reclaim priority */ /* - * While reclaiming in a hiearchy, we cache the last child we + * While reclaiming in a hierarchy, we cache the last child we * reclaimed from. */ int last_scanned_child; @@ -1720,7 +1720,7 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, /* * While swap-in, try_charge -> commit or cancel, the page is locked. * And when try_charge() successfully returns, one refcnt to memcg without - * struct page_cgroup is aquired. This refcnt will be cumsumed by + * struct page_cgroup is acquired. This refcnt will be consumed by * "commit()" or removed by "cancel()" */ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, @@ -2466,7 +2466,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, cgroup_lock(); /* - * If parent's use_hiearchy is set, we can't make any modifications + * If parent's use_hierarchy is set, we can't make any modifications * in the child subtrees. If it is unset, then the change can * occur, provided the current cgroup has no children. * diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 729d4b15b64..1ac49fef95a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -35,6 +35,7 @@ #include <linux/mm.h> #include <linux/page-flags.h> #include <linux/sched.h> +#include <linux/ksm.h> #include <linux/rmap.h> #include <linux/pagemap.h> #include <linux/swap.h> @@ -173,7 +174,7 @@ static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno, list_for_each_entry_safe (tk, next, to_kill, nd) { if (doit) { /* - * In case something went wrong with munmaping + * In case something went wrong with munmapping * make sure the process doesn't catch the * signal and then access the memory. Just kill it. * the signal handlers @@ -370,9 +371,6 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) int ret = FAILED; struct address_space *mapping; - if (!isolate_lru_page(p)) - page_cache_release(p); - /* * For anonymous pages we're done the only reference left * should be the one m_f() holds. @@ -498,30 +496,18 @@ static int me_pagecache_dirty(struct page *p, unsigned long pfn) */ static int me_swapcache_dirty(struct page *p, unsigned long pfn) { - int ret = FAILED; - ClearPageDirty(p); /* Trigger EIO in shmem: */ ClearPageUptodate(p); - if (!isolate_lru_page(p)) { - page_cache_release(p); - ret = DELAYED; - } - - return ret; + return DELAYED; } static int me_swapcache_clean(struct page *p, unsigned long pfn) { - int ret = FAILED; - - if (!isolate_lru_page(p)) { - page_cache_release(p); - ret = RECOVERED; - } delete_from_swap_cache(p); - return ret; + + return RECOVERED; } /* @@ -611,8 +597,6 @@ static struct page_state { { 0, 0, "unknown page state", me_unknown }, }; -#undef lru - static void action_result(unsigned long pfn, char *msg, int result) { struct page *page = NULL; @@ -629,13 +613,16 @@ static int page_action(struct page_state *ps, struct page *p, unsigned long pfn, int ref) { int result; + int count; result = ps->action(p, pfn); action_result(pfn, ps->msg, result); - if (page_count(p) != 1 + ref) + + count = page_count(p) - 1 - ref; + if (count != 0) printk(KERN_ERR "MCE %#lx: %s page still referenced by %d users\n", - pfn, ps->msg, page_count(p) - 1); + pfn, ps->msg, count); /* Could do more checks here if page looks ok */ /* @@ -661,12 +648,9 @@ static void hwpoison_user_mappings(struct page *p, unsigned long pfn, int i; int kill = 1; - if (PageReserved(p) || PageCompound(p) || PageSlab(p)) + if (PageReserved(p) || PageCompound(p) || PageSlab(p) || PageKsm(p)) return; - if (!PageLRU(p)) - lru_add_drain_all(); - /* * This check implies we don't kill processes if their pages * are in the swap cache early. Those are always late kills. @@ -738,6 +722,7 @@ static void hwpoison_user_mappings(struct page *p, unsigned long pfn, int __memory_failure(unsigned long pfn, int trapno, int ref) { + unsigned long lru_flag; struct page_state *ps; struct page *p; int res; @@ -775,6 +760,24 @@ int __memory_failure(unsigned long pfn, int trapno, int ref) } /* + * We ignore non-LRU pages for good reasons. + * - PG_locked is only well defined for LRU pages and a few others + * - to avoid races with __set_page_locked() + * - to avoid races with __SetPageSlab*() (and more non-atomic ops) + * The check (unnecessarily) ignores LRU pages being isolated and + * walked by the page reclaim code, however that's not a big loss. + */ + if (!PageLRU(p)) + lru_add_drain_all(); + lru_flag = p->flags & lru; + if (isolate_lru_page(p)) { + action_result(pfn, "non LRU", IGNORED); + put_page(p); + return -EBUSY; + } + page_cache_release(p); + + /* * Lock the page and wait for writeback to finish. * It's very difficult to mess with pages currently under IO * and in many cases impossible, so we just avoid it here. @@ -790,7 +793,7 @@ int __memory_failure(unsigned long pfn, int trapno, int ref) /* * Torn down by someone else? */ - if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) { + if ((lru_flag & lru) && !PageSwapCache(p) && p->mapping == NULL) { action_result(pfn, "already truncated LRU", IGNORED); res = 0; goto out; @@ -798,7 +801,7 @@ int __memory_failure(unsigned long pfn, int trapno, int ref) res = -EBUSY; for (ps = error_states;; ps++) { - if ((p->flags & ps->mask) == ps->res) { + if (((p->flags | lru_flag)& ps->mask) == ps->res) { res = page_action(ps, p, pfn, ref); break; } diff --git a/mm/memory.c b/mm/memory.c index 7e91b5f9f69..6ab19dd4a19 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -641,6 +641,7 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { + pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; spinlock_t *src_ptl, *dst_ptl; int progress = 0; @@ -654,6 +655,8 @@ again: src_pte = pte_offset_map_nested(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + orig_src_pte = src_pte; + orig_dst_pte = dst_pte; arch_enter_lazy_mmu_mode(); do { @@ -677,9 +680,9 @@ again: arch_leave_lazy_mmu_mode(); spin_unlock(src_ptl); - pte_unmap_nested(src_pte - 1); + pte_unmap_nested(orig_src_pte); add_mm_rss(dst_mm, rss[0], rss[1]); - pte_unmap_unlock(dst_pte - 1, dst_ptl); + pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); if (addr != end) goto again; @@ -1820,10 +1823,10 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, token = pmd_pgtable(*pmd); do { - err = fn(pte, token, addr, data); + err = fn(pte++, token, addr, data); if (err) break; - } while (pte++, addr += PAGE_SIZE, addr != end); + } while (addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); @@ -2539,7 +2542,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, } else if (PageHWPoison(page)) { ret = VM_FAULT_HWPOISON; delayacct_clear_flag(DELAYACCT_PF_SWAPIN); - goto out; + goto out_release; } lock_page(page); @@ -2611,6 +2614,7 @@ out_nomap: pte_unmap_unlock(page_table, ptl); out_page: unlock_page(page); +out_release: page_cache_release(page); return ret; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 821dee59637..2047465cd27 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -26,6 +26,7 @@ #include <linux/migrate.h> #include <linux/page-isolation.h> #include <linux/pfn.h> +#include <linux/suspend.h> #include <asm/tlbflush.h> @@ -447,7 +448,8 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) } #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ -static pg_data_t *hotadd_new_pgdat(int nid, u64 start) +/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ +static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) { struct pglist_data *pgdat; unsigned long zones_size[MAX_NR_ZONES] = {0}; @@ -484,14 +486,18 @@ int __ref add_memory(int nid, u64 start, u64 size) struct resource *res; int ret; + lock_system_sleep(); + res = register_memory_resource(start, size); + ret = -EEXIST; if (!res) - return -EEXIST; + goto out; if (!node_online(nid)) { pgdat = hotadd_new_pgdat(nid, start); + ret = -ENOMEM; if (!pgdat) - return -ENOMEM; + goto out; new_pgdat = 1; } @@ -514,7 +520,8 @@ int __ref add_memory(int nid, u64 start, u64 size) BUG_ON(ret); } - return ret; + goto out; + error: /* rollback pgdat allocation and others */ if (new_pgdat) @@ -522,6 +529,8 @@ error: if (res) release_memory_resource(res); +out: + unlock_system_sleep(); return ret; } EXPORT_SYMBOL_GPL(add_memory); @@ -758,6 +767,8 @@ int offline_pages(unsigned long start_pfn, if (!test_pages_in_a_zone(start_pfn, end_pfn)) return -EINVAL; + lock_system_sleep(); + zone = page_zone(pfn_to_page(start_pfn)); node = zone_to_nid(zone); nr_pages = end_pfn - start_pfn; @@ -765,7 +776,7 @@ int offline_pages(unsigned long start_pfn, /* set above range as isolated */ ret = start_isolate_page_range(start_pfn, end_pfn); if (ret) - return ret; + goto out; arg.start_pfn = start_pfn; arg.nr_pages = nr_pages; @@ -843,6 +854,7 @@ repeat: writeback_set_ratelimit(); memory_notify(MEM_OFFLINE, &arg); + unlock_system_sleep(); return 0; failed_removal: @@ -852,6 +864,8 @@ failed_removal: /* pushback to free area */ undo_isolate_page_range(start_pfn, end_pfn); +out: + unlock_system_sleep(); return ret; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 7dd9d9f8069..4545d594424 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1024,7 +1024,7 @@ static long do_mbind(unsigned long start, unsigned long len, err = migrate_prep(); if (err) - return err; + goto mpol_out; } { NODEMASK_SCRATCH(scratch); @@ -1039,10 +1039,9 @@ static long do_mbind(unsigned long start, unsigned long len, err = -ENOMEM; NODEMASK_SCRATCH_FREE(scratch); } - if (err) { - mpol_put(new); - return err; - } + if (err) + goto mpol_out; + vma = check_range(mm, start, end, nmask, flags | MPOL_MF_INVERT, &pagelist); @@ -1058,9 +1057,11 @@ static long do_mbind(unsigned long start, unsigned long len, if (!err && nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; - } + } else + putback_lru_pages(&pagelist); up_write(&mm->mmap_sem); + mpol_out: mpol_put(new); return err; } diff --git a/mm/migrate.c b/mm/migrate.c index 1a4bf481378..7dbcb22316d 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -602,7 +602,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, struct page *newpage = get_new_page(page, private, &result); int rcu_locked = 0; int charge = 0; - struct mem_cgroup *mem; + struct mem_cgroup *mem = NULL; if (!newpage) return -ENOMEM; diff --git a/mm/mmap.c b/mm/mmap.c index 73f5e4b6401..ed70a68e882 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -20,7 +20,6 @@ #include <linux/fs.h> #include <linux/personality.h> #include <linux/security.h> -#include <linux/ima.h> #include <linux/hugetlb.h> #include <linux/profile.h> #include <linux/module.h> @@ -932,13 +931,9 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); - error = arch_mmap_check(addr, len, flags); - if (error) - return error; - /* Careful about overflows.. */ len = PAGE_ALIGN(len); - if (!len || len > TASK_SIZE) + if (!len) return -ENOMEM; /* offset overflow? */ @@ -949,24 +944,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, if (mm->map_count > sysctl_max_map_count) return -ENOMEM; - if (flags & MAP_HUGETLB) { - struct user_struct *user = NULL; - if (file) - return -EINVAL; - - /* - * VM_NORESERVE is used because the reservations will be - * taken when vm_ops->mmap() is called - * A dummy user value is used because we are not locking - * memory so no accounting is necessary - */ - len = ALIGN(len, huge_page_size(&default_hstate)); - file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, - &user, HUGETLB_ANONHUGE_INODE); - if (IS_ERR(file)) - return PTR_ERR(file); - } - /* Obtain the address to map to. we verify (or select) it and ensure * that it represents a valid section of the address space. */ @@ -1061,9 +1038,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, error = security_file_mmap(file, reqprot, prot, flags, addr, 0); if (error) return error; - error = ima_file_mmap(file, prot); - if (error) - return error; return mmap_region(file, addr, len, flags, vm_flags, pgoff); } @@ -1459,6 +1433,14 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); + unsigned long error = arch_mmap_check(addr, len, flags); + if (error) + return error; + + /* Careful about overflows.. */ + if (len > TASK_SIZE) + return -ENOMEM; + get_area = current->mm->get_unmapped_area; if (file && file->f_op && file->f_op->get_unmapped_area) get_area = file->f_op->get_unmapped_area; @@ -2003,20 +1985,14 @@ unsigned long do_brk(unsigned long addr, unsigned long len) if (!len) return addr; - if ((addr + len) > TASK_SIZE || (addr + len) < addr) - return -EINVAL; - - if (is_hugepage_only_range(mm, addr, len)) - return -EINVAL; - error = security_file_mmap(NULL, 0, 0, 0, addr, 1); if (error) return error; flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; - error = arch_mmap_check(addr, len, flags); - if (error) + error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); + if (error & ~PAGE_MASK) return error; /* diff --git a/mm/mremap.c b/mm/mremap.c index 97bff254771..845190898d5 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -261,6 +261,137 @@ static unsigned long move_vma(struct vm_area_struct *vma, return new_addr; } +static struct vm_area_struct *vma_to_resize(unsigned long addr, + unsigned long old_len, unsigned long new_len, unsigned long *p) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma = find_vma(mm, addr); + + if (!vma || vma->vm_start > addr) + goto Efault; + + if (is_vm_hugetlb_page(vma)) + goto Einval; + + /* We can't remap across vm area boundaries */ + if (old_len > vma->vm_end - addr) + goto Efault; + + if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) { + if (new_len > old_len) + goto Efault; + } + + if (vma->vm_flags & VM_LOCKED) { + unsigned long locked, lock_limit; + locked = mm->locked_vm << PAGE_SHIFT; + lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur; + locked += new_len - old_len; + if (locked > lock_limit && !capable(CAP_IPC_LOCK)) + goto Eagain; + } + + if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT)) + goto Enomem; + + if (vma->vm_flags & VM_ACCOUNT) { + unsigned long charged = (new_len - old_len) >> PAGE_SHIFT; + if (security_vm_enough_memory(charged)) + goto Efault; + *p = charged; + } + + return vma; + +Efault: /* very odd choice for most of the cases, but... */ + return ERR_PTR(-EFAULT); +Einval: + return ERR_PTR(-EINVAL); +Enomem: + return ERR_PTR(-ENOMEM); +Eagain: + return ERR_PTR(-EAGAIN); +} + +static unsigned long mremap_to(unsigned long addr, + unsigned long old_len, unsigned long new_addr, + unsigned long new_len) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long ret = -EINVAL; + unsigned long charged = 0; + unsigned long map_flags; + + if (new_addr & ~PAGE_MASK) + goto out; + + if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len) + goto out; + + /* Check if the location we're moving into overlaps the + * old location at all, and fail if it does. + */ + if ((new_addr <= addr) && (new_addr+new_len) > addr) + goto out; + + if ((addr <= new_addr) && (addr+old_len) > new_addr) + goto out; + + ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1); + if (ret) + goto out; + + ret = do_munmap(mm, new_addr, new_len); + if (ret) + goto out; + + if (old_len >= new_len) { + ret = do_munmap(mm, addr+new_len, old_len - new_len); + if (ret && old_len != new_len) + goto out; + old_len = new_len; + } + + vma = vma_to_resize(addr, old_len, new_len, &charged); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto out; + } + + map_flags = MAP_FIXED; + if (vma->vm_flags & VM_MAYSHARE) + map_flags |= MAP_SHARED; + + ret = get_unmapped_area(vma->vm_file, new_addr, new_len, vma->vm_pgoff + + ((addr - vma->vm_start) >> PAGE_SHIFT), + map_flags); + if (ret & ~PAGE_MASK) + goto out1; + + ret = move_vma(vma, addr, old_len, new_len, new_addr); + if (!(ret & ~PAGE_MASK)) + goto out; +out1: + vm_unacct_memory(charged); + +out: + return ret; +} + +static int vma_expandable(struct vm_area_struct *vma, unsigned long delta) +{ + unsigned long end = vma->vm_end + delta; + if (end < vma->vm_end) /* overflow */ + return 0; + if (vma->vm_next && vma->vm_next->vm_start < end) /* intersection */ + return 0; + if (get_unmapped_area(NULL, vma->vm_start, end - vma->vm_start, + 0, MAP_FIXED) & ~PAGE_MASK) + return 0; + return 1; +} + /* * Expand (or shrink) an existing mapping, potentially moving it at the * same time (controlled by the MREMAP_MAYMOVE flag and available VM space) @@ -294,32 +425,10 @@ unsigned long do_mremap(unsigned long addr, if (!new_len) goto out; - /* new_addr is only valid if MREMAP_FIXED is specified */ if (flags & MREMAP_FIXED) { - if (new_addr & ~PAGE_MASK) - goto out; - if (!(flags & MREMAP_MAYMOVE)) - goto out; - - if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len) - goto out; - - /* Check if the location we're moving into overlaps the - * old location at all, and fail if it does. - */ - if ((new_addr <= addr) && (new_addr+new_len) > addr) - goto out; - - if ((addr <= new_addr) && (addr+old_len) > new_addr) - goto out; - - ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1); - if (ret) - goto out; - - ret = do_munmap(mm, new_addr, new_len); - if (ret) - goto out; + if (flags & MREMAP_MAYMOVE) + ret = mremap_to(addr, old_len, new_addr, new_len); + goto out; } /* @@ -332,60 +441,23 @@ unsigned long do_mremap(unsigned long addr, if (ret && old_len != new_len) goto out; ret = addr; - if (!(flags & MREMAP_FIXED) || (new_addr == addr)) - goto out; - old_len = new_len; + goto out; } /* - * Ok, we need to grow.. or relocate. + * Ok, we need to grow.. */ - ret = -EFAULT; - vma = find_vma(mm, addr); - if (!vma || vma->vm_start > addr) - goto out; - if (is_vm_hugetlb_page(vma)) { - ret = -EINVAL; - goto out; - } - /* We can't remap across vm area boundaries */ - if (old_len > vma->vm_end - addr) - goto out; - if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) { - if (new_len > old_len) - goto out; - } - if (vma->vm_flags & VM_LOCKED) { - unsigned long locked, lock_limit; - locked = mm->locked_vm << PAGE_SHIFT; - lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur; - locked += new_len - old_len; - ret = -EAGAIN; - if (locked > lock_limit && !capable(CAP_IPC_LOCK)) - goto out; - } - if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT)) { - ret = -ENOMEM; + vma = vma_to_resize(addr, old_len, new_len, &charged); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); goto out; } - if (vma->vm_flags & VM_ACCOUNT) { - charged = (new_len - old_len) >> PAGE_SHIFT; - if (security_vm_enough_memory(charged)) - goto out_nc; - } - /* old_len exactly to the end of the area.. - * And we're not relocating the area. */ - if (old_len == vma->vm_end - addr && - !((flags & MREMAP_FIXED) && (addr != new_addr)) && - (old_len != new_len || !(flags & MREMAP_MAYMOVE))) { - unsigned long max_addr = TASK_SIZE; - if (vma->vm_next) - max_addr = vma->vm_next->vm_start; + if (old_len == vma->vm_end - addr) { /* can we just expand the current mapping? */ - if (max_addr - addr >= new_len) { + if (vma_expandable(vma, new_len - old_len)) { int pages = (new_len - old_len) >> PAGE_SHIFT; vma_adjust(vma, vma->vm_start, @@ -409,28 +481,27 @@ unsigned long do_mremap(unsigned long addr, */ ret = -ENOMEM; if (flags & MREMAP_MAYMOVE) { - if (!(flags & MREMAP_FIXED)) { - unsigned long map_flags = 0; - if (vma->vm_flags & VM_MAYSHARE) - map_flags |= MAP_SHARED; - - new_addr = get_unmapped_area(vma->vm_file, 0, new_len, - vma->vm_pgoff, map_flags); - if (new_addr & ~PAGE_MASK) { - ret = new_addr; - goto out; - } - - ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1); - if (ret) - goto out; + unsigned long map_flags = 0; + if (vma->vm_flags & VM_MAYSHARE) + map_flags |= MAP_SHARED; + + new_addr = get_unmapped_area(vma->vm_file, 0, new_len, + vma->vm_pgoff + + ((addr - vma->vm_start) >> PAGE_SHIFT), + map_flags); + if (new_addr & ~PAGE_MASK) { + ret = new_addr; + goto out; } + + ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1); + if (ret) + goto out; ret = move_vma(vma, addr, old_len, new_len, new_addr); } out: if (ret & ~PAGE_MASK) vm_unacct_memory(charged); -out_nc: return ret; } diff --git a/mm/nommu.c b/mm/nommu.c index 5189b5aed8c..9876fa0c3ad 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1362,9 +1362,11 @@ share: error_just_free: up_write(&nommu_region_sem); error: - fput(region->vm_file); + if (region->vm_file) + fput(region->vm_file); kmem_cache_free(vm_region_jar, region); - fput(vma->vm_file); + if (vma->vm_file) + fput(vma->vm_file); if (vma->vm_flags & VM_EXECUTABLE) removed_exe_file_vma(vma->vm_mm); kmem_cache_free(vm_area_cachep, vma); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index a3b14090b1f..0b19943ecf8 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -566,7 +566,8 @@ static void balance_dirty_pages(struct address_space *mapping, if (pages_written >= write_chunk) break; /* We've done our duty */ - schedule_timeout_interruptible(pause); + __set_current_state(TASK_INTERRUPTIBLE); + io_schedule_timeout(pause); /* * Increase the delay for each loop, up to our previous @@ -820,7 +821,6 @@ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data) { - struct backing_dev_info *bdi = mapping->backing_dev_info; int ret = 0; int done = 0; struct pagevec pvec; @@ -833,11 +833,6 @@ int write_cache_pages(struct address_space *mapping, int range_whole = 0; long nr_to_write = wbc->nr_to_write; - if (wbc->nonblocking && bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; - return 0; - } - pagevec_init(&pvec, 0); if (wbc->range_cyclic) { writeback_index = mapping->writeback_index; /* prev offset */ @@ -956,12 +951,6 @@ continue_unlock: break; } } - - if (wbc->nonblocking && bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; - done = 1; - break; - } } pagevec_release(&pvec); cond_resched(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index bf720550b44..2bc2ac63f41 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1769,7 +1769,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask) * See also cpuset_zone_allowed() comment in kernel/cpuset.c. */ alloc_flags &= ~ALLOC_CPUSET; - } else if (unlikely(rt_task(p))) + } else if (unlikely(rt_task(p)) && !in_interrupt()) alloc_flags |= ALLOC_HARDER; if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) { @@ -1817,9 +1817,9 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE) goto nopage; +restart: wake_all_kswapd(order, zonelist, high_zoneidx); -restart: /* * OK, we're below the kswapd watermark and have kicked background * reclaim. Now things get more complex, so set up alloc_flags according @@ -2183,7 +2183,7 @@ void show_free_areas(void) printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n" " active_file:%lu inactive_file:%lu isolated_file:%lu\n" " unevictable:%lu" - " dirty:%lu writeback:%lu unstable:%lu buffer:%lu\n" + " dirty:%lu writeback:%lu unstable:%lu\n" " free:%lu slab_reclaimable:%lu slab_unreclaimable:%lu\n" " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n", global_page_state(NR_ACTIVE_ANON), @@ -2196,7 +2196,6 @@ void show_free_areas(void) global_page_state(NR_FILE_DIRTY), global_page_state(NR_WRITEBACK), global_page_state(NR_UNSTABLE_NFS), - nr_blockdev_pages(), global_page_state(NR_FREE_PAGES), global_page_state(NR_SLAB_RECLAIMABLE), global_page_state(NR_SLAB_UNRECLAIMABLE), diff --git a/mm/percpu.c b/mm/percpu.c index 4a048abad04..5adfc268b40 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -153,7 +153,10 @@ static int pcpu_reserved_chunk_limit; * * During allocation, pcpu_alloc_mutex is kept locked all the time and * pcpu_lock is grabbed and released as necessary. All actual memory - * allocations are done using GFP_KERNEL with pcpu_lock released. + * allocations are done using GFP_KERNEL with pcpu_lock released. In + * general, percpu memory can't be allocated with irq off but + * irqsave/restore are still used in alloc path so that it can be used + * from early init path - sched_init() specifically. * * Free path accesses and alters only the index data structures, so it * can be safely called from atomic context. When memory needs to be @@ -352,62 +355,86 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) } /** - * pcpu_extend_area_map - extend area map for allocation - * @chunk: target chunk + * pcpu_need_to_extend - determine whether chunk area map needs to be extended + * @chunk: chunk of interest * - * Extend area map of @chunk so that it can accomodate an allocation. - * A single allocation can split an area into three areas, so this - * function makes sure that @chunk->map has at least two extra slots. + * Determine whether area map of @chunk needs to be extended to + * accomodate a new allocation. * * CONTEXT: - * pcpu_alloc_mutex, pcpu_lock. pcpu_lock is released and reacquired - * if area map is extended. + * pcpu_lock. * * RETURNS: - * 0 if noop, 1 if successfully extended, -errno on failure. + * New target map allocation length if extension is necessary, 0 + * otherwise. */ -static int pcpu_extend_area_map(struct pcpu_chunk *chunk) +static int pcpu_need_to_extend(struct pcpu_chunk *chunk) { int new_alloc; - int *new; - size_t size; - /* has enough? */ if (chunk->map_alloc >= chunk->map_used + 2) return 0; - spin_unlock_irq(&pcpu_lock); - new_alloc = PCPU_DFL_MAP_ALLOC; while (new_alloc < chunk->map_used + 2) new_alloc *= 2; - new = pcpu_mem_alloc(new_alloc * sizeof(new[0])); - if (!new) { - spin_lock_irq(&pcpu_lock); + return new_alloc; +} + +/** + * pcpu_extend_area_map - extend area map of a chunk + * @chunk: chunk of interest + * @new_alloc: new target allocation length of the area map + * + * Extend area map of @chunk to have @new_alloc entries. + * + * CONTEXT: + * Does GFP_KERNEL allocation. Grabs and releases pcpu_lock. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc) +{ + int *old = NULL, *new = NULL; + size_t old_size = 0, new_size = new_alloc * sizeof(new[0]); + unsigned long flags; + + new = pcpu_mem_alloc(new_size); + if (!new) return -ENOMEM; - } - /* - * Acquire pcpu_lock and switch to new area map. Only free - * could have happened inbetween, so map_used couldn't have - * grown. - */ - spin_lock_irq(&pcpu_lock); - BUG_ON(new_alloc < chunk->map_used + 2); + /* acquire pcpu_lock and switch to new area map */ + spin_lock_irqsave(&pcpu_lock, flags); + + if (new_alloc <= chunk->map_alloc) + goto out_unlock; - size = chunk->map_alloc * sizeof(chunk->map[0]); - memcpy(new, chunk->map, size); + old_size = chunk->map_alloc * sizeof(chunk->map[0]); + memcpy(new, chunk->map, old_size); /* * map_alloc < PCPU_DFL_MAP_ALLOC indicates that the chunk is * one of the first chunks and still using static map. */ if (chunk->map_alloc >= PCPU_DFL_MAP_ALLOC) - pcpu_mem_free(chunk->map, size); + old = chunk->map; chunk->map_alloc = new_alloc; chunk->map = new; + new = NULL; + +out_unlock: + spin_unlock_irqrestore(&pcpu_lock, flags); + + /* + * pcpu_mem_free() might end up calling vfree() which uses + * IRQ-unsafe lock and thus can't be called under pcpu_lock. + */ + pcpu_mem_free(old, old_size); + pcpu_mem_free(new, new_size); + return 0; } @@ -1046,7 +1073,8 @@ static void *pcpu_alloc(size_t size, size_t align, bool reserved) static int warn_limit = 10; struct pcpu_chunk *chunk; const char *err; - int slot, off; + int slot, off, new_alloc; + unsigned long flags; if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) { WARN(true, "illegal size (%zu) or align (%zu) for " @@ -1055,19 +1083,30 @@ static void *pcpu_alloc(size_t size, size_t align, bool reserved) } mutex_lock(&pcpu_alloc_mutex); - spin_lock_irq(&pcpu_lock); + spin_lock_irqsave(&pcpu_lock, flags); /* serve reserved allocations from the reserved chunk if available */ if (reserved && pcpu_reserved_chunk) { chunk = pcpu_reserved_chunk; - if (size > chunk->contig_hint || - pcpu_extend_area_map(chunk) < 0) { - err = "failed to extend area map of reserved chunk"; + + if (size > chunk->contig_hint) { + err = "alloc from reserved chunk failed"; goto fail_unlock; } + + while ((new_alloc = pcpu_need_to_extend(chunk))) { + spin_unlock_irqrestore(&pcpu_lock, flags); + if (pcpu_extend_area_map(chunk, new_alloc) < 0) { + err = "failed to extend area map of reserved chunk"; + goto fail_unlock_mutex; + } + spin_lock_irqsave(&pcpu_lock, flags); + } + off = pcpu_alloc_area(chunk, size, align); if (off >= 0) goto area_found; + err = "alloc from reserved chunk failed"; goto fail_unlock; } @@ -1079,14 +1118,20 @@ restart: if (size > chunk->contig_hint) continue; - switch (pcpu_extend_area_map(chunk)) { - case 0: - break; - case 1: - goto restart; /* pcpu_lock dropped, restart */ - default: - err = "failed to extend area map"; - goto fail_unlock; + new_alloc = pcpu_need_to_extend(chunk); + if (new_alloc) { + spin_unlock_irqrestore(&pcpu_lock, flags); + if (pcpu_extend_area_map(chunk, + new_alloc) < 0) { + err = "failed to extend area map"; + goto fail_unlock_mutex; + } + spin_lock_irqsave(&pcpu_lock, flags); + /* + * pcpu_lock has been dropped, need to + * restart cpu_slot list walking. + */ + goto restart; } off = pcpu_alloc_area(chunk, size, align); @@ -1096,7 +1141,7 @@ restart: } /* hmmm... no space left, create a new chunk */ - spin_unlock_irq(&pcpu_lock); + spin_unlock_irqrestore(&pcpu_lock, flags); chunk = alloc_pcpu_chunk(); if (!chunk) { @@ -1104,16 +1149,16 @@ restart: goto fail_unlock_mutex; } - spin_lock_irq(&pcpu_lock); + spin_lock_irqsave(&pcpu_lock, flags); pcpu_chunk_relocate(chunk, -1); goto restart; area_found: - spin_unlock_irq(&pcpu_lock); + spin_unlock_irqrestore(&pcpu_lock, flags); /* populate, map and clear the area */ if (pcpu_populate_chunk(chunk, off, size)) { - spin_lock_irq(&pcpu_lock); + spin_lock_irqsave(&pcpu_lock, flags); pcpu_free_area(chunk, off); err = "failed to populate"; goto fail_unlock; @@ -1125,7 +1170,7 @@ area_found: return __addr_to_pcpu_ptr(chunk->base_addr + off); fail_unlock: - spin_unlock_irq(&pcpu_lock); + spin_unlock_irqrestore(&pcpu_lock, flags); fail_unlock_mutex: mutex_unlock(&pcpu_alloc_mutex); if (warn_limit) { @@ -1870,13 +1915,14 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size, max_distance = 0; for (group = 0; group < ai->nr_groups; group++) { ai->groups[group].base_offset = areas[group] - base; - max_distance = max(max_distance, ai->groups[group].base_offset); + max_distance = max_t(size_t, max_distance, + ai->groups[group].base_offset); } max_distance += ai->unit_size; /* warn if maximum distance is further than 75% of vmalloc space */ if (max_distance > (VMALLOC_END - VMALLOC_START) * 3 / 4) { - pr_warning("PERCPU: max_distance=0x%lx too large for vmalloc " + pr_warning("PERCPU: max_distance=0x%zx too large for vmalloc " "space 0x%lx\n", max_distance, VMALLOC_END - VMALLOC_START); #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK diff --git a/mm/slab.c b/mm/slab.c index 7dfa481c96b..a6c9166996a 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -604,6 +604,26 @@ static struct kmem_cache cache_cache = { #define BAD_ALIEN_MAGIC 0x01020304ul +/* + * chicken and egg problem: delay the per-cpu array allocation + * until the general caches are up. + */ +static enum { + NONE, + PARTIAL_AC, + PARTIAL_L3, + EARLY, + FULL +} g_cpucache_up; + +/* + * used by boot code to determine if it can use slab based allocator + */ +int slab_is_available(void) +{ + return g_cpucache_up >= EARLY; +} + #ifdef CONFIG_LOCKDEP /* @@ -620,40 +640,52 @@ static struct kmem_cache cache_cache = { static struct lock_class_key on_slab_l3_key; static struct lock_class_key on_slab_alc_key; -static inline void init_lock_keys(void) - +static void init_node_lock_keys(int q) { - int q; struct cache_sizes *s = malloc_sizes; - while (s->cs_size != ULONG_MAX) { - for_each_node(q) { - struct array_cache **alc; - int r; - struct kmem_list3 *l3 = s->cs_cachep->nodelists[q]; - if (!l3 || OFF_SLAB(s->cs_cachep)) - continue; - lockdep_set_class(&l3->list_lock, &on_slab_l3_key); - alc = l3->alien; - /* - * FIXME: This check for BAD_ALIEN_MAGIC - * should go away when common slab code is taught to - * work even without alien caches. - * Currently, non NUMA code returns BAD_ALIEN_MAGIC - * for alloc_alien_cache, - */ - if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC) - continue; - for_each_node(r) { - if (alc[r]) - lockdep_set_class(&alc[r]->lock, - &on_slab_alc_key); - } + if (g_cpucache_up != FULL) + return; + + for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) { + struct array_cache **alc; + struct kmem_list3 *l3; + int r; + + l3 = s->cs_cachep->nodelists[q]; + if (!l3 || OFF_SLAB(s->cs_cachep)) + return; + lockdep_set_class(&l3->list_lock, &on_slab_l3_key); + alc = l3->alien; + /* + * FIXME: This check for BAD_ALIEN_MAGIC + * should go away when common slab code is taught to + * work even without alien caches. + * Currently, non NUMA code returns BAD_ALIEN_MAGIC + * for alloc_alien_cache, + */ + if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC) + return; + for_each_node(r) { + if (alc[r]) + lockdep_set_class(&alc[r]->lock, + &on_slab_alc_key); } - s++; } } + +static inline void init_lock_keys(void) +{ + int node; + + for_each_node(node) + init_node_lock_keys(node); +} #else +static void init_node_lock_keys(int q) +{ +} + static inline void init_lock_keys(void) { } @@ -665,26 +697,6 @@ static inline void init_lock_keys(void) static DEFINE_MUTEX(cache_chain_mutex); static struct list_head cache_chain; -/* - * chicken and egg problem: delay the per-cpu array allocation - * until the general caches are up. - */ -static enum { - NONE, - PARTIAL_AC, - PARTIAL_L3, - EARLY, - FULL -} g_cpucache_up; - -/* - * used by boot code to determine if it can use slab based allocator - */ -int slab_is_available(void) -{ - return g_cpucache_up >= EARLY; -} - static DEFINE_PER_CPU(struct delayed_work, reap_work); static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep) @@ -1254,6 +1266,8 @@ static int __cpuinit cpuup_prepare(long cpu) kfree(shared); free_alien_cache(alien); } + init_node_lock_keys(node); + return 0; bad: cpuup_canceled(cpu); @@ -3103,13 +3117,19 @@ static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags) } else { STATS_INC_ALLOCMISS(cachep); objp = cache_alloc_refill(cachep, flags); + /* + * the 'ac' may be updated by cache_alloc_refill(), + * and kmemleak_erase() requires its correct value. + */ + ac = cpu_cache_get(cachep); } /* * To avoid a false negative, if an object that is in one of the * per-CPU caches is leaked, we need to make sure kmemleak doesn't * treat the array pointers as a reference to the object. */ - kmemleak_erase(&ac->entry[ac->avail]); + if (objp) + kmemleak_erase(&ac->entry[ac->avail]); return objp; } @@ -3306,7 +3326,7 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, cache_alloc_debugcheck_before(cachep, flags); local_irq_save(save_flags); - if (unlikely(nodeid == -1)) + if (nodeid == -1) nodeid = numa_node_id(); if (unlikely(!cachep->nodelists[nodeid])) { diff --git a/mm/slub.c b/mm/slub.c index ac0ca4c0d05..da0ce55965d 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1735,7 +1735,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s, } local_irq_restore(flags); - if (unlikely((gfpflags & __GFP_ZERO) && object)) + if (unlikely(gfpflags & __GFP_ZERO) && object) memset(object, 0, objsize); kmemcheck_slab_alloc(s, gfpflags, object, c->objsize); diff --git a/mm/swapfile.c b/mm/swapfile.c index a1bc6b9af9a..9c590eef791 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1151,8 +1151,7 @@ static int try_to_unuse(unsigned int type) } else retval = unuse_mm(mm, entry, page); - if (set_start_mm && - swap_count(*swap_map) < swcount) { + if (set_start_mm && *swap_map < swcount) { mmput(new_start_mm); atomic_inc(&mm->mm_users); new_start_mm = mm; diff --git a/mm/truncate.c b/mm/truncate.c index 450cebdabfc..2c147a7e5f2 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -490,7 +490,7 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range); * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * - * Returns -EIO if any pages could not be invalidated. + * Returns -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2(struct address_space *mapping) { diff --git a/mm/util.c b/mm/util.c index 7c35ad95f92..b377ce43080 100644 --- a/mm/util.c +++ b/mm/util.c @@ -4,6 +4,10 @@ #include <linux/module.h> #include <linux/err.h> #include <linux/sched.h> +#include <linux/hugetlb.h> +#include <linux/syscalls.h> +#include <linux/mman.h> +#include <linux/file.h> #include <asm/uaccess.h> #define CREATE_TRACE_POINTS @@ -268,6 +272,46 @@ int __attribute__((weak)) get_user_pages_fast(unsigned long start, } EXPORT_SYMBOL_GPL(get_user_pages_fast); +SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, + unsigned long, prot, unsigned long, flags, + unsigned long, fd, unsigned long, pgoff) +{ + struct file * file = NULL; + unsigned long retval = -EBADF; + + if (!(flags & MAP_ANONYMOUS)) { + if (unlikely(flags & MAP_HUGETLB)) + return -EINVAL; + file = fget(fd); + if (!file) + goto out; + } else if (flags & MAP_HUGETLB) { + struct user_struct *user = NULL; + /* + * VM_NORESERVE is used because the reservations will be + * taken when vm_ops->mmap() is called + * A dummy user value is used because we are not locking + * memory so no accounting is necessary + */ + len = ALIGN(len, huge_page_size(&default_hstate)); + file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, + &user, HUGETLB_ANONHUGE_INODE); + if (IS_ERR(file)) + return PTR_ERR(file); + } + + flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); + + down_write(¤t->mm->mmap_sem); + retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff); + up_write(¤t->mm->mmap_sem); + + if (file) + fput(file); +out: + return retval; +} + /* Tracepoints definitions. */ EXPORT_TRACEPOINT_SYMBOL(kmalloc); EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 69511e66323..0f551a4a44c 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -12,6 +12,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/highmem.h> +#include <linux/sched.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/interrupt.h> @@ -25,10 +26,10 @@ #include <linux/rcupdate.h> #include <linux/pfn.h> #include <linux/kmemleak.h> -#include <linux/highmem.h> #include <asm/atomic.h> #include <asm/uaccess.h> #include <asm/tlbflush.h> +#include <asm/shmparam.h> /*** Page table manipulation functions ***/ @@ -1156,12 +1157,11 @@ static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, } static struct vm_struct *__get_vm_area_node(unsigned long size, - unsigned long flags, unsigned long start, unsigned long end, - int node, gfp_t gfp_mask, void *caller) + unsigned long align, unsigned long flags, unsigned long start, + unsigned long end, int node, gfp_t gfp_mask, void *caller) { static struct vmap_area *va; struct vm_struct *area; - unsigned long align = 1; BUG_ON(in_interrupt()); if (flags & VM_IOREMAP) { @@ -1201,7 +1201,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, unsigned long start, unsigned long end) { - return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL, + return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL, __builtin_return_address(0)); } EXPORT_SYMBOL_GPL(__get_vm_area); @@ -1210,7 +1210,7 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, void *caller) { - return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL, + return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL, caller); } @@ -1225,22 +1225,22 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, */ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) { - return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, + return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, -1, GFP_KERNEL, __builtin_return_address(0)); } struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, void *caller) { - return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, + return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, -1, GFP_KERNEL, caller); } struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags, int node, gfp_t gfp_mask) { - return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node, - gfp_mask, __builtin_return_address(0)); + return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, + node, gfp_mask, __builtin_return_address(0)); } static struct vm_struct *find_vm_area(const void *addr) @@ -1403,7 +1403,8 @@ void *vmap(struct page **pages, unsigned int count, } EXPORT_SYMBOL(vmap); -static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot, +static void *__vmalloc_node(unsigned long size, unsigned long align, + gfp_t gfp_mask, pgprot_t prot, int node, void *caller); static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot, int node, void *caller) @@ -1417,7 +1418,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, area->nr_pages = nr_pages; /* Please note that the recursion is strictly bounded. */ if (array_size > PAGE_SIZE) { - pages = __vmalloc_node(array_size, gfp_mask | __GFP_ZERO, + pages = __vmalloc_node(array_size, 1, gfp_mask | __GFP_ZERO, PAGE_KERNEL, node, caller); area->flags |= VM_VPAGES; } else { @@ -1476,6 +1477,7 @@ void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot) /** * __vmalloc_node - allocate virtually contiguous memory * @size: allocation size + * @align: desired alignment * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages * @node: node to use for allocation or -1 @@ -1485,8 +1487,9 @@ void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot) * allocator with @gfp_mask flags. Map them into contiguous * kernel virtual space, using a pagetable protection of @prot. */ -static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot, - int node, void *caller) +static void *__vmalloc_node(unsigned long size, unsigned long align, + gfp_t gfp_mask, pgprot_t prot, + int node, void *caller) { struct vm_struct *area; void *addr; @@ -1496,8 +1499,8 @@ static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot, if (!size || (size >> PAGE_SHIFT) > totalram_pages) return NULL; - area = __get_vm_area_node(size, VM_ALLOC, VMALLOC_START, VMALLOC_END, - node, gfp_mask, caller); + area = __get_vm_area_node(size, align, VM_ALLOC, VMALLOC_START, + VMALLOC_END, node, gfp_mask, caller); if (!area) return NULL; @@ -1516,7 +1519,7 @@ static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot, void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot) { - return __vmalloc_node(size, gfp_mask, prot, -1, + return __vmalloc_node(size, 1, gfp_mask, prot, -1, __builtin_return_address(0)); } EXPORT_SYMBOL(__vmalloc); @@ -1532,7 +1535,7 @@ EXPORT_SYMBOL(__vmalloc); */ void *vmalloc(unsigned long size) { - return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, + return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, -1, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc); @@ -1549,7 +1552,8 @@ void *vmalloc_user(unsigned long size) struct vm_struct *area; void *ret; - ret = __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, + ret = __vmalloc_node(size, SHMLBA, + GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL, -1, __builtin_return_address(0)); if (ret) { area = find_vm_area(ret); @@ -1572,7 +1576,7 @@ EXPORT_SYMBOL(vmalloc_user); */ void *vmalloc_node(unsigned long size, int node) { - return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, + return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, node, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_node); @@ -1595,7 +1599,7 @@ EXPORT_SYMBOL(vmalloc_node); void *vmalloc_exec(unsigned long size) { - return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC, + return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC, -1, __builtin_return_address(0)); } @@ -1616,7 +1620,7 @@ void *vmalloc_exec(unsigned long size) */ void *vmalloc_32(unsigned long size) { - return __vmalloc_node(size, GFP_VMALLOC32, PAGE_KERNEL, + return __vmalloc_node(size, 1, GFP_VMALLOC32, PAGE_KERNEL, -1, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_32); @@ -1633,7 +1637,7 @@ void *vmalloc_32_user(unsigned long size) struct vm_struct *area; void *ret; - ret = __vmalloc_node(size, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL, + ret = __vmalloc_node(size, 1, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL, -1, __builtin_return_address(0)); if (ret) { area = find_vm_area(ret); diff --git a/mm/vmscan.c b/mm/vmscan.c index 64e43889883..777af57fd8c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -544,6 +544,16 @@ 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 + * the page back to the evictable list. + * + * The other side is TestClearPageMlocked(). + */ + smp_mb(); } /* @@ -1088,7 +1098,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan, int lumpy_reclaim = 0; while (unlikely(too_many_isolated(zone, file, sc))) { - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) @@ -1356,7 +1366,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, * IO, plus JVM can create lots of anon VM_EXEC pages, * so we ignore them here. */ - if ((vm_flags & VM_EXEC) && !PageAnon(page)) { + if ((vm_flags & VM_EXEC) && page_is_file_cache(page)) { list_add(&page->lru, &l_active); continue; } |