diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 4 | ||||
| -rw-r--r-- | mm/filemap.c | 20 | ||||
| -rw-r--r-- | mm/migrate.c | 24 | ||||
| -rw-r--r-- | mm/mmap.c | 34 | ||||
| -rw-r--r-- | mm/oom_kill.c | 3 | ||||
| -rw-r--r-- | mm/page_alloc.c | 14 | ||||
| -rw-r--r-- | mm/slub.c | 71 | ||||
| -rw-r--r-- | mm/swapfile.c | 6 | ||||
| -rw-r--r-- | mm/vmstat.c | 1 |
9 files changed, 120 insertions, 57 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 86187221e78f..e24d348083c3 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -116,11 +116,11 @@ config SPARSEMEM_EXTREME config MEMORY_HOTPLUG bool "Allow for memory hot-add" depends on SPARSEMEM || X86_64_ACPI_NUMA - depends on HOTPLUG && !SOFTWARE_SUSPEND && ARCH_ENABLE_MEMORY_HOTPLUG + depends on HOTPLUG && !HIBERNATION && ARCH_ENABLE_MEMORY_HOTPLUG depends on (IA64 || X86 || PPC64 || SUPERH) comment "Memory hotplug is currently incompatible with Software Suspend" - depends on SPARSEMEM && HOTPLUG && SOFTWARE_SUSPEND + depends on SPARSEMEM && HOTPLUG && HIBERNATION config MEMORY_HOTPLUG_SPARSE def_bool y diff --git a/mm/filemap.c b/mm/filemap.c index 49a6fe375d01..90b657b50f81 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1218,26 +1218,6 @@ out: } EXPORT_SYMBOL(generic_file_aio_read); -int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size) -{ - ssize_t written; - unsigned long count = desc->count; - struct file *file = desc->arg.data; - - if (size > count) - size = count; - - written = file->f_op->sendpage(file, page, offset, - size, &file->f_pos, size<count); - if (written < 0) { - desc->error = written; - written = 0; - } - desc->count = count - written; - desc->written += written; - return written; -} - static ssize_t do_readahead(struct address_space *mapping, struct file *filp, unsigned long index, unsigned long nr) diff --git a/mm/migrate.c b/mm/migrate.c index 34d8ada053e4..37c73b902008 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -49,9 +49,8 @@ int isolate_lru_page(struct page *page, struct list_head *pagelist) struct zone *zone = page_zone(page); spin_lock_irq(&zone->lru_lock); - if (PageLRU(page)) { + if (PageLRU(page) && get_page_unless_zero(page)) { ret = 0; - get_page(page); ClearPageLRU(page); if (PageActive(page)) del_page_from_active_list(zone, page); @@ -632,18 +631,35 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, goto unlock; wait_on_page_writeback(page); } - /* - * Establish migration ptes or remove ptes + * By try_to_unmap(), page->mapcount goes down to 0 here. In this case, + * we cannot notice that anon_vma is freed while we migrates a page. + * This rcu_read_lock() delays freeing anon_vma pointer until the end + * of migration. File cache pages are no problem because of page_lock() + */ + rcu_read_lock(); + /* + * This is a corner case handling. + * When a new swap-cache is read into, it is linked to LRU + * and treated as swapcache but has no rmap yet. + * Calling try_to_unmap() against a page->mapping==NULL page is + * BUG. So handle it here. */ + if (!page->mapping) + goto rcu_unlock; + /* Establish migration ptes or remove ptes */ try_to_unmap(page, 1); + if (!page_mapped(page)) rc = move_to_new_page(newpage, page); if (rc) remove_migration_ptes(page, page); +rcu_unlock: + rcu_read_unlock(); unlock: + unlock_page(page); if (rc != -EAGAIN) { diff --git a/mm/mmap.c b/mm/mmap.c index 7afc7a7cec6f..b6537211b9cc 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1029,6 +1029,40 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr, } EXPORT_SYMBOL(do_mmap_pgoff); +/* + * Some shared mappigns will want the pages marked read-only + * to track write events. If so, we'll downgrade vm_page_prot + * to the private version (using protection_map[] without the + * VM_SHARED bit). + */ +int vma_wants_writenotify(struct vm_area_struct *vma) +{ + unsigned int vm_flags = vma->vm_flags; + + /* If it was private or non-writable, the write bit is already clear */ + if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED))) + return 0; + + /* The backer wishes to know when pages are first written to? */ + if (vma->vm_ops && vma->vm_ops->page_mkwrite) + return 1; + + /* The open routine did something to the protections already? */ + if (pgprot_val(vma->vm_page_prot) != + pgprot_val(protection_map[vm_flags & + (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)])) + return 0; + + /* Specialty mapping? */ + if (vm_flags & (VM_PFNMAP|VM_INSERTPAGE)) + return 0; + + /* Can the mapping track the dirty pages? */ + return vma->vm_file && vma->vm_file->f_mapping && + mapping_cap_account_dirty(vma->vm_file->f_mapping); +} + + unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, unsigned long flags, unsigned int vm_flags, unsigned long pgoff, diff --git a/mm/oom_kill.c b/mm/oom_kill.c index a7001410ab15..f9b82ad5047f 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -17,6 +17,7 @@ #include <linux/oom.h> #include <linux/mm.h> +#include <linux/err.h> #include <linux/sched.h> #include <linux/swap.h> #include <linux/timex.h> @@ -156,7 +157,7 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) } #ifdef DEBUG - printk(KERN_DEBUG "OOMkill: task %d (%s) got %d points\n", + printk(KERN_DEBUG "OOMkill: task %d (%s) got %lu points\n", p->pid, p->comm, points); #endif return points; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 40954fb81598..3da85b81dabb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -726,7 +726,7 @@ static void __drain_pages(unsigned int cpu) } } -#ifdef CONFIG_PM +#ifdef CONFIG_HIBERNATION void mark_free_pages(struct zone *zone) { @@ -772,7 +772,7 @@ void drain_local_pages(void) __drain_pages(smp_processor_id()); local_irq_restore(flags); } -#endif /* CONFIG_PM */ +#endif /* CONFIG_HIBERNATION */ /* * Free a 0-order page @@ -1350,6 +1350,10 @@ nofail_alloc: if (page) goto got_pg; + /* The OOM killer will not help higher order allocs so fail */ + if (order > PAGE_ALLOC_COSTLY_ORDER) + goto nopage; + out_of_memory(zonelist, gfp_mask, order); goto restart; } @@ -2775,11 +2779,11 @@ unsigned long __meminit __absent_pages_in_range(int nid, if (i == -1) return 0; + prev_end_pfn = min(early_node_map[i].start_pfn, range_end_pfn); + /* Account for ranges before physical memory on this node */ if (early_node_map[i].start_pfn > range_start_pfn) - hole_pages = early_node_map[i].start_pfn - range_start_pfn; - - prev_end_pfn = early_node_map[i].start_pfn; + hole_pages = prev_end_pfn - range_start_pfn; /* Find all holes for the zone within the node */ for (; i != -1; i = next_active_region_index_in_nid(i, nid)) { diff --git a/mm/slub.c b/mm/slub.c index 9b2d6178d06c..69d02e3e439e 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -211,7 +211,8 @@ static inline void ClearSlabDebug(struct page *page) #define MAX_OBJECTS_PER_SLAB 65535 /* Internal SLUB flags */ -#define __OBJECT_POISON 0x80000000 /* Poison object */ +#define __OBJECT_POISON 0x80000000 /* Poison object */ +#define __SYSFS_ADD_DEFERRED 0x40000000 /* Not yet visible via sysfs */ /* Not all arches define cache_line_size */ #ifndef cache_line_size @@ -1131,6 +1132,7 @@ static void __free_slab(struct kmem_cache *s, struct page *page) slab_pad_check(s, page); for_each_object(p, s, page_address(page)) check_object(s, page, p, 0); + ClearSlabDebug(page); } mod_zone_page_state(page_zone(page), @@ -1169,7 +1171,6 @@ static void discard_slab(struct kmem_cache *s, struct page *page) atomic_long_dec(&n->nr_slabs); reset_page_mapcount(page); - ClearSlabDebug(page); __ClearPageSlab(page); free_slab(s, page); } @@ -1656,6 +1657,7 @@ static void __always_inline slab_free(struct kmem_cache *s, unsigned long flags; local_irq_save(flags); + debug_check_no_locks_freed(object, s->objsize); if (likely(page == s->cpu_slab[smp_processor_id()] && !SlabDebug(page))) { object[page->offset] = page->lockless_freelist; @@ -2276,10 +2278,26 @@ panic: } #ifdef CONFIG_ZONE_DMA + +static void sysfs_add_func(struct work_struct *w) +{ + struct kmem_cache *s; + + down_write(&slub_lock); + list_for_each_entry(s, &slab_caches, list) { + if (s->flags & __SYSFS_ADD_DEFERRED) { + s->flags &= ~__SYSFS_ADD_DEFERRED; + sysfs_slab_add(s); + } + } + up_write(&slub_lock); +} + +static DECLARE_WORK(sysfs_add_work, sysfs_add_func); + static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags) { struct kmem_cache *s; - struct kmem_cache *x; char *text; size_t realsize; @@ -2288,22 +2306,36 @@ static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags) return s; /* Dynamically create dma cache */ - x = kmalloc(kmem_size, flags & ~SLUB_DMA); - if (!x) - panic("Unable to allocate memory for dma cache\n"); + if (flags & __GFP_WAIT) + down_write(&slub_lock); + else { + if (!down_write_trylock(&slub_lock)) + goto out; + } + + if (kmalloc_caches_dma[index]) + goto unlock_out; realsize = kmalloc_caches[index].objsize; - text = kasprintf(flags & ~SLUB_DMA, "kmalloc_dma-%d", - (unsigned int)realsize); - s = create_kmalloc_cache(x, text, realsize, flags); - down_write(&slub_lock); - if (!kmalloc_caches_dma[index]) { - kmalloc_caches_dma[index] = s; - up_write(&slub_lock); - return s; + text = kasprintf(flags & ~SLUB_DMA, "kmalloc_dma-%d", (unsigned int)realsize), + s = kmalloc(kmem_size, flags & ~SLUB_DMA); + + if (!s || !text || !kmem_cache_open(s, flags, text, + realsize, ARCH_KMALLOC_MINALIGN, + SLAB_CACHE_DMA|__SYSFS_ADD_DEFERRED, NULL)) { + kfree(s); + kfree(text); + goto unlock_out; } + + list_add(&s->list, &slab_caches); + kmalloc_caches_dma[index] = s; + + schedule_work(&sysfs_add_work); + +unlock_out: up_write(&slub_lock); - kmem_cache_destroy(s); +out: return kmalloc_caches_dma[index]; } #endif @@ -2499,15 +2531,11 @@ int kmem_cache_shrink(struct kmem_cache *s) slab_unlock(page); discard_slab(s, page); } else { - if (n->nr_partial > MAX_PARTIAL) - list_move(&page->lru, - slabs_by_inuse + page->inuse); + list_move(&page->lru, + slabs_by_inuse + page->inuse); } } - if (n->nr_partial <= MAX_PARTIAL) - goto out; - /* * Rebuild the partial list with the slabs filled up most * first and the least used slabs at the end. @@ -2515,7 +2543,6 @@ int kmem_cache_shrink(struct kmem_cache *s) for (i = s->objects - 1; i >= 0; i--) list_splice(slabs_by_inuse + i, n->partial.prev); - out: spin_unlock_irqrestore(&n->list_lock, flags); } diff --git a/mm/swapfile.c b/mm/swapfile.c index 7ff0a81c7b01..f071648e1360 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -425,7 +425,7 @@ void free_swap_and_cache(swp_entry_t entry) } } -#ifdef CONFIG_SOFTWARE_SUSPEND +#ifdef CONFIG_HIBERNATION /* * Find the swap type that corresponds to given device (if any). * @@ -951,7 +951,7 @@ sector_t map_swap_page(struct swap_info_struct *sis, pgoff_t offset) } } -#ifdef CONFIG_SOFTWARE_SUSPEND +#ifdef CONFIG_HIBERNATION /* * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev * corresponding to given index in swap_info (swap type). @@ -966,7 +966,7 @@ sector_t swapdev_block(int swap_type, pgoff_t offset) sis = swap_info + swap_type; return (sis->flags & SWP_WRITEOK) ? map_swap_page(sis, offset) : 0; } -#endif /* CONFIG_SOFTWARE_SUSPEND */ +#endif /* CONFIG_HIBERNATION */ /* * Free all of a swapdev's extent information diff --git a/mm/vmstat.c b/mm/vmstat.c index fadf791cd7e6..c64d169537bf 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -10,6 +10,7 @@ */ #include <linux/mm.h> +#include <linux/err.h> #include <linux/module.h> #include <linux/cpu.h> #include <linux/sched.h> |