diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/backing-dev.c | 52 | ||||
| -rw-r--r-- | mm/compaction.c | 156 | ||||
| -rw-r--r-- | mm/filemap.c | 7 | ||||
| -rw-r--r-- | mm/huge_memory.c | 1 | ||||
| -rw-r--r-- | mm/internal.h | 1 | ||||
| -rw-r--r-- | mm/memblock.c | 2 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 16 | ||||
| -rw-r--r-- | mm/mempolicy.c | 2 | ||||
| -rw-r--r-- | mm/mmap.c | 7 | ||||
| -rw-r--r-- | mm/page-writeback.c | 1 | ||||
| -rw-r--r-- | mm/page_alloc.c | 40 | ||||
| -rw-r--r-- | mm/slab.c | 95 | ||||
| -rw-r--r-- | mm/slob.c | 31 | ||||
| -rw-r--r-- | mm/slub.c | 45 | ||||
| -rw-r--r-- | mm/vmscan.c | 1 |
15 files changed, 247 insertions, 210 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 6b4718e2ee34..b41823cc05e6 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -39,12 +39,6 @@ DEFINE_SPINLOCK(bdi_lock); LIST_HEAD(bdi_list); LIST_HEAD(bdi_pending_list); -static struct task_struct *sync_supers_tsk; -static struct timer_list sync_supers_timer; - -static int bdi_sync_supers(void *); -static void sync_supers_timer_fn(unsigned long); - void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2) { if (wb1 < wb2) { @@ -250,12 +244,6 @@ static int __init default_bdi_init(void) { int err; - sync_supers_tsk = kthread_run(bdi_sync_supers, NULL, "sync_supers"); - BUG_ON(IS_ERR(sync_supers_tsk)); - - setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0); - bdi_arm_supers_timer(); - err = bdi_init(&default_backing_dev_info); if (!err) bdi_register(&default_backing_dev_info, NULL, "default"); @@ -270,46 +258,6 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi) return wb_has_dirty_io(&bdi->wb); } -/* - * kupdated() used to do this. We cannot do it from the bdi_forker_thread() - * or we risk deadlocking on ->s_umount. The longer term solution would be - * to implement sync_supers_bdi() or similar and simply do it from the - * bdi writeback thread individually. - */ -static int bdi_sync_supers(void *unused) -{ - set_user_nice(current, 0); - - while (!kthread_should_stop()) { - set_current_state(TASK_INTERRUPTIBLE); - schedule(); - - /* - * Do this periodically, like kupdated() did before. - */ - sync_supers(); - } - - return 0; -} - -void bdi_arm_supers_timer(void) -{ - unsigned long next; - - if (!dirty_writeback_interval) - return; - - next = msecs_to_jiffies(dirty_writeback_interval * 10) + jiffies; - mod_timer(&sync_supers_timer, round_jiffies_up(next)); -} - -static void sync_supers_timer_fn(unsigned long unused) -{ - wake_up_process(sync_supers_tsk); - bdi_arm_supers_timer(); -} - static void wakeup_timer_fn(unsigned long data) { struct backing_dev_info *bdi = (struct backing_dev_info *)data; diff --git a/mm/compaction.c b/mm/compaction.c index e78cb9688421..7fcd3a52e68d 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -51,6 +51,47 @@ static inline bool migrate_async_suitable(int migratetype) } /* + * Compaction requires the taking of some coarse locks that are potentially + * very heavily contended. Check if the process needs to be scheduled or + * if the lock is contended. For async compaction, back out in the event + * if contention is severe. For sync compaction, schedule. + * + * Returns true if the lock is held. + * Returns false if the lock is released and compaction should abort + */ +static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags, + bool locked, struct compact_control *cc) +{ + if (need_resched() || spin_is_contended(lock)) { + if (locked) { + spin_unlock_irqrestore(lock, *flags); + locked = false; + } + + /* async aborts if taking too long or contended */ + if (!cc->sync) { + if (cc->contended) + *cc->contended = true; + return false; + } + + cond_resched(); + if (fatal_signal_pending(current)) + return false; + } + + if (!locked) + spin_lock_irqsave(lock, *flags); + return true; +} + +static inline bool compact_trylock_irqsave(spinlock_t *lock, + unsigned long *flags, struct compact_control *cc) +{ + return compact_checklock_irqsave(lock, flags, false, cc); +} + +/* * Isolate free pages onto a private freelist. Caller must hold zone->lock. * If @strict is true, will abort returning 0 on any invalid PFNs or non-free * pages inside of the pageblock (even though it may still end up isolating @@ -173,7 +214,7 @@ isolate_freepages_range(unsigned long start_pfn, unsigned long end_pfn) } /* Update the number of anon and file isolated pages in the zone */ -static void acct_isolated(struct zone *zone, struct compact_control *cc) +static void acct_isolated(struct zone *zone, bool locked, struct compact_control *cc) { struct page *page; unsigned int count[2] = { 0, }; @@ -181,8 +222,14 @@ static void acct_isolated(struct zone *zone, struct compact_control *cc) list_for_each_entry(page, &cc->migratepages, lru) count[!!page_is_file_cache(page)]++; - __mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]); - __mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]); + /* If locked we can use the interrupt unsafe versions */ + if (locked) { + __mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]); + __mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]); + } else { + 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 */ @@ -228,6 +275,8 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, struct list_head *migratelist = &cc->migratepages; isolate_mode_t mode = 0; struct lruvec *lruvec; + unsigned long flags; + bool locked; /* * Ensure that there are not too many pages isolated from the LRU @@ -247,25 +296,22 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, /* Time to isolate some pages for migration */ cond_resched(); - spin_lock_irq(&zone->lru_lock); + spin_lock_irqsave(&zone->lru_lock, flags); + locked = true; for (; low_pfn < end_pfn; low_pfn++) { struct page *page; - bool locked = true; /* give a chance to irqs before checking need_resched() */ if (!((low_pfn+1) % SWAP_CLUSTER_MAX)) { - spin_unlock_irq(&zone->lru_lock); + spin_unlock_irqrestore(&zone->lru_lock, flags); locked = false; } - if (need_resched() || spin_is_contended(&zone->lru_lock)) { - if (locked) - spin_unlock_irq(&zone->lru_lock); - cond_resched(); - spin_lock_irq(&zone->lru_lock); - if (fatal_signal_pending(current)) - break; - } else if (!locked) - spin_lock_irq(&zone->lru_lock); + + /* Check if it is ok to still hold the lock */ + locked = compact_checklock_irqsave(&zone->lru_lock, &flags, + locked, cc); + if (!locked) + break; /* * migrate_pfn does not necessarily start aligned to a @@ -349,9 +395,10 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, } } - acct_isolated(zone, cc); + acct_isolated(zone, locked, cc); - spin_unlock_irq(&zone->lru_lock); + if (locked) + spin_unlock_irqrestore(&zone->lru_lock, flags); trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); @@ -384,6 +431,20 @@ static bool suitable_migration_target(struct page *page) } /* + * Returns the start pfn of the last page block in a zone. This is the starting + * point for full compaction of a zone. Compaction searches for free pages from + * the end of each zone, while isolate_freepages_block scans forward inside each + * page block. + */ +static unsigned long start_free_pfn(struct zone *zone) +{ + unsigned long free_pfn; + free_pfn = zone->zone_start_pfn + zone->spanned_pages; + free_pfn &= ~(pageblock_nr_pages-1); + return free_pfn; +} + +/* * Based on information in the current compact_control, find blocks * suitable for isolating free pages from and then isolate them. */ @@ -422,17 +483,6 @@ static void isolate_freepages(struct zone *zone, pfn -= pageblock_nr_pages) { unsigned long isolated; - /* - * Skip ahead if another thread is compacting in the area - * simultaneously. If we wrapped around, we can only skip - * ahead if zone->compact_cached_free_pfn also wrapped to - * above our starting point. - */ - if (cc->order > 0 && (!cc->wrapped || - zone->compact_cached_free_pfn > - cc->start_free_pfn)) - pfn = min(pfn, zone->compact_cached_free_pfn); - if (!pfn_valid(pfn)) continue; @@ -458,7 +508,16 @@ static void isolate_freepages(struct zone *zone, * are disabled */ isolated = 0; - spin_lock_irqsave(&zone->lock, flags); + + /* + * The zone lock must be held to isolate freepages. This + * unfortunately this is a very coarse lock and can be + * heavily contended if there are parallel allocations + * or parallel compactions. For async compaction do not + * spin on the lock + */ + if (!compact_trylock_irqsave(&zone->lock, &flags, cc)) + break; if (suitable_migration_target(page)) { end_pfn = min(pfn + pageblock_nr_pages, zone_end_pfn); isolated = isolate_freepages_block(pfn, end_pfn, @@ -474,7 +533,15 @@ static void isolate_freepages(struct zone *zone, */ if (isolated) { high_pfn = max(high_pfn, pfn); - if (cc->order > 0) + + /* + * If the free scanner has wrapped, update + * compact_cached_free_pfn to point to the highest + * pageblock with free pages. This reduces excessive + * scanning of full pageblocks near the end of the + * zone + */ + if (cc->order > 0 && cc->wrapped) zone->compact_cached_free_pfn = high_pfn; } } @@ -484,6 +551,11 @@ static void isolate_freepages(struct zone *zone, cc->free_pfn = high_pfn; cc->nr_freepages = nr_freepages; + + /* If compact_cached_free_pfn is reset then set it now */ + if (cc->order > 0 && !cc->wrapped && + zone->compact_cached_free_pfn == start_free_pfn(zone)) + zone->compact_cached_free_pfn = high_pfn; } /* @@ -570,20 +642,6 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, return ISOLATE_SUCCESS; } -/* - * Returns the start pfn of the last page block in a zone. This is the starting - * point for full compaction of a zone. Compaction searches for free pages from - * the end of each zone, while isolate_freepages_block scans forward inside each - * page block. - */ -static unsigned long start_free_pfn(struct zone *zone) -{ - unsigned long free_pfn; - free_pfn = zone->zone_start_pfn + zone->spanned_pages; - free_pfn &= ~(pageblock_nr_pages-1); - return free_pfn; -} - static int compact_finished(struct zone *zone, struct compact_control *cc) { @@ -771,7 +829,7 @@ out: static unsigned long compact_zone_order(struct zone *zone, int order, gfp_t gfp_mask, - bool sync) + bool sync, bool *contended) { struct compact_control cc = { .nr_freepages = 0, @@ -780,6 +838,7 @@ static unsigned long compact_zone_order(struct zone *zone, .migratetype = allocflags_to_migratetype(gfp_mask), .zone = zone, .sync = sync, + .contended = contended, }; INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); @@ -801,7 +860,7 @@ int sysctl_extfrag_threshold = 500; */ unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask, - bool sync) + bool sync, bool *contended) { enum zone_type high_zoneidx = gfp_zone(gfp_mask); int may_enter_fs = gfp_mask & __GFP_FS; @@ -825,7 +884,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, nodemask) { int status; - status = compact_zone_order(zone, order, gfp_mask, sync); + status = compact_zone_order(zone, order, gfp_mask, sync, + contended); rc = max(status, rc); /* If a normal allocation would succeed, stop compacting */ @@ -861,7 +921,7 @@ static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) if (cc->order > 0) { int ok = zone_watermark_ok(zone, cc->order, low_wmark_pages(zone), 0, 0); - if (ok && cc->order > zone->compact_order_failed) + if (ok && cc->order >= zone->compact_order_failed) zone->compact_order_failed = cc->order + 1; /* Currently async compaction is never deferred. */ else if (!ok && cc->sync) diff --git a/mm/filemap.c b/mm/filemap.c index fa5ca304148e..384344575c37 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1412,12 +1412,8 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, retval = filemap_write_and_wait_range(mapping, pos, pos + iov_length(iov, nr_segs) - 1); if (!retval) { - struct blk_plug plug; - - blk_start_plug(&plug); retval = mapping->a_ops->direct_IO(READ, iocb, iov, pos, nr_segs); - blk_finish_plug(&plug); } if (retval > 0) { *ppos = pos + retval; @@ -2527,14 +2523,12 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; - struct blk_plug plug; ssize_t ret; BUG_ON(iocb->ki_pos != pos); sb_start_write(inode->i_sb); mutex_lock(&inode->i_mutex); - blk_start_plug(&plug); ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); mutex_unlock(&inode->i_mutex); @@ -2545,7 +2539,6 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (err < 0 && ret > 0) ret = err; } - blk_finish_plug(&plug); sb_end_write(inode->i_sb); return ret; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 57c4b9309015..141dbb695097 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1811,7 +1811,6 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, src_page = pte_page(pteval); copy_user_highpage(page, src_page, address, vma); VM_BUG_ON(page_mapcount(src_page) != 1); - VM_BUG_ON(page_count(src_page) != 2); release_pte_page(src_page); /* * ptl mostly unnecessary, but preempt has to diff --git a/mm/internal.h b/mm/internal.h index 3314f79d775a..b8c91b342e24 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -130,6 +130,7 @@ struct compact_control { int order; /* order a direct compactor needs */ int migratetype; /* MOVABLE, RECLAIMABLE etc */ struct zone *zone; + bool *contended; /* True if a lock was contended */ }; unsigned long diff --git a/mm/memblock.c b/mm/memblock.c index 4d9393c7edc9..82aa349d2f7a 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -246,7 +246,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, min(new_area_start, memblock.current_limit), new_alloc_size, PAGE_SIZE); - new_array = addr ? __va(addr) : 0; + new_array = addr ? __va(addr) : NULL; } if (!addr) { pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n", diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 3ad25f9d1fc1..6a5b90d0cfd7 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -126,9 +126,6 @@ static void register_page_bootmem_info_section(unsigned long start_pfn) struct mem_section *ms; struct page *page, *memmap; - if (!pfn_valid(start_pfn)) - return; - section_nr = pfn_to_section_nr(start_pfn); ms = __nr_to_section(section_nr); @@ -187,9 +184,16 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat) end_pfn = pfn + pgdat->node_spanned_pages; /* register_section info */ - for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) - register_page_bootmem_info_section(pfn); - + for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { + /* + * Some platforms can assign the same pfn to multiple nodes - on + * node0 as well as nodeN. To avoid registering a pfn against + * multiple nodes we check that this pfn does not already + * reside in some other node. + */ + if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node)) + register_page_bootmem_info_section(pfn); + } } #endif /* !CONFIG_SPARSEMEM_VMEMMAP */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index bd92431d4c49..4ada3be6e252 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2562,7 +2562,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context) break; default: - BUG(); + return -EINVAL; } l = strlen(policy_modes[mode]); diff --git a/mm/mmap.c b/mm/mmap.c index e3e86914f11a..ae18a48e7e4e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1356,9 +1356,8 @@ out: } else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK)) make_pages_present(addr, addr + len); - if (file && uprobe_mmap(vma)) - /* matching probes but cannot insert */ - goto unmap_and_free_vma; + if (file) + uprobe_mmap(vma); return addr; @@ -2309,7 +2308,7 @@ void exit_mmap(struct mm_struct *mm) } vm_unacct_memory(nr_accounted); - BUG_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT); + WARN_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT); } /* Insert vm structure into process list sorted by address diff --git a/mm/page-writeback.c b/mm/page-writeback.c index e5363f34e025..5ad5ce23c1e0 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1532,7 +1532,6 @@ int dirty_writeback_centisecs_handler(ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { proc_dointvec(table, write, buffer, length, ppos); - bdi_arm_supers_timer(); return 0; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 009ac285fea7..c13ea7538891 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -584,7 +584,7 @@ static inline void __free_one_page(struct page *page, combined_idx = buddy_idx & page_idx; higher_page = page + (combined_idx - page_idx); buddy_idx = __find_buddy_index(combined_idx, order + 1); - higher_buddy = page + (buddy_idx - combined_idx); + higher_buddy = higher_page + (buddy_idx - combined_idx); if (page_is_buddy(higher_page, higher_buddy, order + 1)) { list_add_tail(&page->lru, &zone->free_area[order].free_list[migratetype]); @@ -1928,6 +1928,17 @@ this_zone_full: zlc_active = 0; goto zonelist_scan; } + + if (page) + /* + * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was + * necessary to allocate the page. The expectation is + * that the caller is taking steps that will free more + * memory. The caller should avoid the page being used + * for !PFMEMALLOC purposes. + */ + page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS); + return page; } @@ -2091,7 +2102,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, int migratetype, bool sync_migration, - bool *deferred_compaction, + bool *contended_compaction, bool *deferred_compaction, unsigned long *did_some_progress) { struct page *page; @@ -2106,7 +2117,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, current->flags |= PF_MEMALLOC; *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask, - nodemask, sync_migration); + nodemask, sync_migration, + contended_compaction); current->flags &= ~PF_MEMALLOC; if (*did_some_progress != COMPACT_SKIPPED) { @@ -2152,7 +2164,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, int migratetype, bool sync_migration, - bool *deferred_compaction, + bool *contended_compaction, bool *deferred_compaction, unsigned long *did_some_progress) { return NULL; @@ -2325,6 +2337,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, unsigned long did_some_progress; bool sync_migration = false; bool deferred_compaction = false; + bool contended_compaction = false; /* * In the slowpath, we sanity check order to avoid ever trying to @@ -2389,14 +2402,6 @@ rebalance: zonelist, high_zoneidx, nodemask, preferred_zone, migratetype); if (page) { - /* - * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was - * necessary to allocate the page. The expectation is - * that the caller is taking steps that will free more - * memory. The caller should avoid the page being used - * for !PFMEMALLOC purposes. - */ - page->pfmemalloc = true; goto got_pg; } } @@ -2422,6 +2427,7 @@ rebalance: nodemask, alloc_flags, preferred_zone, migratetype, sync_migration, + &contended_compaction, &deferred_compaction, &did_some_progress); if (page) @@ -2431,10 +2437,11 @@ rebalance: /* * If compaction is deferred for high-order allocations, it is because * sync compaction recently failed. In this is the case and the caller - * has requested the system not be heavily disrupted, fail the - * allocation now instead of entering direct reclaim + * requested a movable allocation that does not heavily disrupt the + * system then fail the allocation instead of entering direct reclaim. */ - if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD)) + if ((deferred_compaction || contended_compaction) && + (gfp_mask & __GFP_NO_KSWAPD)) goto nopage; /* Try direct reclaim and then allocating */ @@ -2505,6 +2512,7 @@ rebalance: nodemask, alloc_flags, preferred_zone, migratetype, sync_migration, + &contended_compaction, &deferred_compaction, &did_some_progress); if (page) @@ -2569,8 +2577,6 @@ retry_cpuset: page = __alloc_pages_slowpath(gfp_mask, order, zonelist, high_zoneidx, nodemask, preferred_zone, migratetype); - else - page->pfmemalloc = false; trace_mm_page_alloc(page, order, gfp_mask, migratetype); diff --git a/mm/slab.c b/mm/slab.c index 8524923966b5..a99f71a39baf 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -498,14 +498,6 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp) #endif -#ifdef CONFIG_TRACING -size_t slab_buffer_size(struct kmem_cache *cachep) -{ - return cachep->size; -} -EXPORT_SYMBOL(slab_buffer_size); -#endif - /* * Do not go above this order unless 0 objects fit into the slab or * overridden on the command line. @@ -812,6 +804,7 @@ static void __slab_error(const char *function, struct kmem_cache *cachep, printk(KERN_ERR "slab error in %s(): cache `%s': %s\n", function, cachep->name, msg); dump_stack(); + add_taint(TAINT_BAD_PAGE); } #endif @@ -978,7 +971,7 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac, } /* The caller cannot use PFMEMALLOC objects, find another one */ - for (i = 1; i < ac->avail; i++) { + for (i = 0; i < ac->avail; i++) { /* If a !PFMEMALLOC object is found, swap them */ if (!is_obj_pfmemalloc(ac->entry[i])) { objp = ac->entry[i]; @@ -995,7 +988,7 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac, l3 = cachep->nodelists[numa_mem_id()]; if (!list_empty(&l3->slabs_free) && force_refill) { struct slab *slabp = virt_to_slab(objp); - ClearPageSlabPfmemalloc(virt_to_page(slabp->s_mem)); + ClearPageSlabPfmemalloc(virt_to_head_page(slabp->s_mem)); clear_obj_pfmemalloc(&objp); recheck_pfmemalloc_active(cachep, ac); return objp; @@ -1027,7 +1020,7 @@ static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac, { if (unlikely(pfmemalloc_active)) { /* Some pfmemalloc slabs exist, check if this is one */ - struct page *page = virt_to_page(objp); + struct page *page = virt_to_head_page(objp); if (PageSlabPfmemalloc(page)) set_obj_pfmemalloc(&objp); } @@ -1784,9 +1777,6 @@ void __init kmem_cache_init_late(void) slab_state = UP; - /* Annotate slab for lockdep -- annotate the malloc caches */ - init_lock_keys(); - /* 6) resize the head arrays to their final sizes */ mutex_lock(&slab_mutex); list_for_each_entry(cachep, &slab_caches, list) @@ -1794,6 +1784,9 @@ void __init kmem_cache_init_late(void) BUG(); mutex_unlock(&slab_mutex); + /* Annotate slab for lockdep -- annotate the malloc caches */ + init_lock_keys(); + /* Done! */ slab_state = FULL; @@ -2478,8 +2471,9 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) } #if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC) if (size >= malloc_sizes[INDEX_L3 + 1].cs_size - && cachep->object_size > cache_line_size() && ALIGN(size, align) < PAGE_SIZE) { - cachep->obj_offset += PAGE_SIZE - ALIGN(size, align); + && cachep->object_size > cache_line_size() + && ALIGN(size, cachep->align) < PAGE_SIZE) { + cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align); size = PAGE_SIZE; } #endif @@ -3044,7 +3038,7 @@ static inline void verify_redzone_free(struct kmem_cache *cache, void *obj) } static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, - void *caller) + unsigned long caller) { struct page *page; unsigned int objnr; @@ -3064,7 +3058,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, *dbg_redzone2(cachep, objp) = RED_INACTIVE; } if (cachep->flags & SLAB_STORE_USER) - *dbg_userword(cachep, objp) = caller; + *dbg_userword(cachep, objp) = (void *)caller; objnr = obj_to_index(cachep, slabp, objp); @@ -3077,7 +3071,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, if (cachep->flags & SLAB_POISON) { #ifdef CONFIG_DEBUG_PAGEALLOC if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) { - store_stackinfo(cachep, objp, (unsigned long)caller); + store_stackinfo(cachep, objp, caller); kernel_map_pages(virt_to_page(objp), cachep->size / PAGE_SIZE, 0); } else { @@ -3206,6 +3200,7 @@ force_grow: /* cache_grow can reenable interrupts, then ac could change. */ ac = cpu_cache_get(cachep); + node = numa_mem_id(); /* no objects in sight? abort */ if (!x && (ac->avail == 0 || force_refill)) @@ -3230,7 +3225,7 @@ static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep, #if DEBUG static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, - gfp_t flags, void *objp, void *caller) + gfp_t flags, void *objp, unsigned long caller) { if (!objp) return objp; @@ -3247,7 +3242,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, poison_obj(cachep, objp, POISON_INUSE); } if (cachep->flags & SLAB_STORE_USER) - *dbg_userword(cachep, objp) = caller; + *dbg_userword(cachep, objp) = (void *)caller; if (cachep->flags & SLAB_RED_ZONE) { if (*dbg_redzone1(cachep, objp) != RED_INACTIVE || @@ -3521,8 +3516,8 @@ done: * Fallback to other node is possible if __GFP_THISNODE is not set. */ static __always_inline void * -__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, - void *caller) +slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, + unsigned long caller) { unsigned long save_flags; void *ptr; @@ -3608,7 +3603,7 @@ __do_cache_alloc(struct kmem_cache *cachep, gfp_t flags) #endif /* CONFIG_NUMA */ static __always_inline void * -__cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller) +slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller) { unsigned long save_flags; void *objp; @@ -3744,7 +3739,7 @@ free_done: * be in this state _before_ it is released. Called with disabled ints. */ static inline void __cache_free(struct kmem_cache *cachep, void *objp, - void *caller) + unsigned long caller) { struct array_cache *ac = cpu_cache_get(cachep); @@ -3784,7 +3779,7 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp, */ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) { - void *ret = __cache_alloc(cachep, flags, __builtin_return_address(0)); + void *ret = slab_alloc(cachep, flags, _RET_IP_); trace_kmem_cache_alloc(_RET_IP_, ret, cachep->object_size, cachep->size, flags); @@ -3795,14 +3790,14 @@ EXPORT_SYMBOL(kmem_cache_alloc); #ifdef CONFIG_TRACING void * -kmem_cache_alloc_trace(size_t size, struct kmem_cache *cachep, gfp_t flags) +kmem_cache_alloc_trace(struct kmem_cache *cachep, gfp_t flags, size_t size) { void *ret; - ret = __cache_alloc(cachep, flags, __builtin_return_address(0)); + ret = slab_alloc(cachep, flags, _RET_IP_); trace_kmalloc(_RET_IP_, ret, - size, slab_buffer_size(cachep), flags); + size, cachep->size, flags); return ret; } EXPORT_SYMBOL(kmem_cache_alloc_trace); @@ -3811,8 +3806,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_trace); #ifdef CONFIG_NUMA void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) { - void *ret = __cache_alloc_node(cachep, flags, nodeid, - __builtin_return_address(0)); + void *ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_); trace_kmem_cache_alloc_node(_RET_IP_, ret, cachep->object_size, cachep->size, @@ -3823,17 +3817,17 @@ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) EXPORT_SYMBOL(kmem_cache_alloc_node); #ifdef CONFIG_TRACING -void *kmem_cache_alloc_node_trace(size_t size, - struct kmem_cache *cachep, +void *kmem_cache_alloc_node_trace(struct kmem_cache *cachep, gfp_t flags, - int nodeid) + int nodeid, + size_t size) { void *ret; - ret = __cache_alloc_node(cachep, flags, nodeid, - __builtin_return_address(0)); + ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP); + trace_kmalloc_node(_RET_IP_, ret, - size, slab_buffer_size(cachep), + size, cachep->size, flags, nodeid); return ret; } @@ -3841,34 +3835,33 @@ EXPORT_SYMBOL(kmem_cache_alloc_node_trace); #endif static __always_inline void * -__do_kmalloc_node(size_t size, gfp_t flags, int node, void *caller) +__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller) { struct kmem_cache *cachep; cachep = kmem_find_general_cachep(size, flags); if (unlikely(ZERO_OR_NULL_PTR(cachep))) return cachep; - return kmem_cache_alloc_node_trace(size, cachep, flags, node); + return kmem_cache_alloc_node_trace(cachep, flags, node, size); } #if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_TRACING) void *__kmalloc_node(size_t size, gfp_t flags, int node) { - return __do_kmalloc_node(size, flags, node, - __builtin_return_address(0)); + return __do_kmalloc_node(size, flags, node, _RET_IP_); } EXPORT_SYMBOL(__kmalloc_node); void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, unsigned long caller) { - return __do_kmalloc_node(size, flags, node, (void *)caller); + return __do_kmalloc_node(size, flags, node, caller); } EXPORT_SYMBOL(__kmalloc_node_track_caller); #else void *__kmalloc_node(size_t size, gfp_t flags, int node) { - return __do_kmalloc_node(size, flags, node, NULL); + return __do_kmalloc_node(size, flags, node, 0); } EXPORT_SYMBOL(__kmalloc_node); #endif /* CONFIG_DEBUG_SLAB || CONFIG_TRACING */ @@ -3881,7 +3874,7 @@ EXPORT_SYMBOL(__kmalloc_node); * @caller: function caller for debug tracking of the caller */ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, - void *caller) + unsigned long caller) { struct kmem_cache *cachep; void *ret; @@ -3894,9 +3887,9 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, cachep = __find_general_cachep(size, flags); if (unlikely(ZERO_OR_NULL_PTR(cachep))) return cachep; - ret = __cache_alloc(cachep, flags, caller); + ret = slab_alloc(cachep, flags, caller); - trace_kmalloc((unsigned long) caller, ret, + trace_kmalloc(caller, ret, size, cachep->size, flags); return ret; @@ -3906,20 +3899,20 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, #if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_TRACING) void *__kmalloc(size_t size, gfp_t flags) { - return __do_kmalloc(size, flags, __builtin_return_address(0)); + return __do_kmalloc(size, flags, _RET_IP_); } EXPORT_SYMBOL(__kmalloc); void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller) { - return __do_kmalloc(size, flags, (void *)caller); + return __do_kmalloc(size, flags, caller); } EXPORT_SYMBOL(__kmalloc_track_caller); #else void *__kmalloc(size_t size, gfp_t flags) { - return __do_kmalloc(size, flags, NULL); + return __do_kmalloc(size, flags, 0); } EXPORT_SYMBOL(__kmalloc); #endif @@ -3940,7 +3933,7 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) debug_check_no_locks_freed(objp, cachep->object_size); if (!(cachep->flags & SLAB_DEBUG_OBJECTS)) debug_check_no_obj_freed(objp, cachep->object_size); - __cache_free(cachep, objp, __builtin_return_address(0)); + __cache_free(cachep, objp, _RET_IP_); local_irq_restore(flags); trace_kmem_cache_free(_RET_IP_, objp); @@ -3971,7 +3964,7 @@ void kfree(const void *objp) debug_check_no_locks_freed(objp, c->object_size); debug_check_no_obj_freed(objp, c->object_size); - __cache_free(c, (void *)objp, __builtin_return_address(0)); + __cache_free(c, (void *)objp, _RET_IP_); local_irq_restore(flags); } EXPORT_SYMBOL(kfree); diff --git a/mm/slob.c b/mm/slob.c index 3edfeaac3208..f3a5ced392d7 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -194,7 +194,7 @@ static void *slob_new_pages(gfp_t gfp, int order, int node) void *page; #ifdef CONFIG_NUMA - if (node != -1) + if (node != NUMA_NO_NODE) page = alloc_pages_exact_node(node, gfp, order); else #endif @@ -290,7 +290,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) * If there's a node specification, search for a partial * page with a matching node id in the freelist. */ - if (node != -1 && page_to_nid(sp) != node) + if (node != NUMA_NO_NODE && page_to_nid(sp) != node) continue; #endif /* Enough room on this page? */ @@ -425,7 +425,8 @@ out: * End of slob allocator proper. Begin kmem_cache_alloc and kmalloc frontend. */ -void *__kmalloc_node(size_t size, gfp_t gfp, int node) +static __always_inline void * +__do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller) { unsigned int *m; int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); @@ -446,7 +447,7 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node) *m = size; ret = (void *)m + align; - trace_kmalloc_node(_RET_IP_, ret, + trace_kmalloc_node(caller, ret, size, size + align, gfp, node); } else { unsigned int order = get_order(size); @@ -460,15 +461,35 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node) page->private = size; } - trace_kmalloc_node(_RET_IP_, ret, + trace_kmalloc_node(caller, ret, size, PAGE_SIZE << order, gfp, node); } kmemleak_alloc(ret, size, 1, gfp); return ret; } + +void *__kmalloc_node(size_t size, gfp_t gfp, int node) +{ + return __do_kmalloc_node(size, gfp, node, _RET_IP_); +} EXPORT_SYMBOL(__kmalloc_node); +#ifdef CONFIG_TRACING +void *__kmalloc_track_caller(size_t size, gfp_t gfp, unsigned long caller) +{ + return __do_kmalloc_node(size, gfp, NUMA_NO_NODE, caller); +} + +#ifdef CONFIG_NUMA +void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, + int node, unsigned long caller) +{ + return __do_kmalloc_node(size, gfp, node, caller); +} +#endif +#endif + void kfree(const void *block) { struct page *sp; diff --git a/mm/slub.c b/mm/slub.c index 2258ed82880a..a0d698467f70 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -564,6 +564,8 @@ static void slab_bug(struct kmem_cache *s, char *fmt, ...) printk(KERN_ERR "BUG %s (%s): %s\n", s->name, print_tainted(), buf); printk(KERN_ERR "----------------------------------------" "-------------------------------------\n\n"); + + add_taint(TAINT_BAD_PAGE); } static void slab_fix(struct kmem_cache *s, char *fmt, ...) @@ -1525,12 +1527,13 @@ static inline void *acquire_slab(struct kmem_cache *s, } static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain); +static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags); /* * Try to allocate a partial slab from a specific node. */ -static void *get_partial_node(struct kmem_cache *s, - struct kmem_cache_node *n, struct kmem_cache_cpu *c) +static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, + struct kmem_cache_cpu *c, gfp_t flags) { struct page *page, *page2; void *object = NULL; @@ -1546,9 +1549,13 @@ static void *get_partial_node(struct kmem_cache *s, spin_lock(&n->list_lock); list_for_each_entry_safe(page, page2, &n->partial, lru) { - void *t = acquire_slab(s, n, page, object == NULL); + void *t; int available; + if (!pfmemalloc_match(page, flags)) + continue; + + t = acquire_slab(s, n, page, object == NULL); if (!t) break; @@ -1615,7 +1622,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, if (n && cpuset_zone_allowed_hardwall(zone, flags) && n->nr_partial > s->min_partial) { - object = get_partial_node(s, n, c); + object = get_partial_node(s, n, c, flags); if (object) { /* * Return the object even if @@ -1644,7 +1651,7 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node, void *object; int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node; - object = get_partial_node(s, get_node(s, searchnode), c); + object = get_partial_node(s, get_node(s, searchnode), c, flags); if (object || node != NUMA_NO_NODE) return object; @@ -1710,7 +1717,7 @@ static inline void note_cmpxchg_failure(const char *n, stat(s, CMPXCHG_DOUBLE_CPU_FAIL); } -void init_kmem_cache_cpus(struct kmem_cache *s) +static void init_kmem_cache_cpus(struct kmem_cache *s) { int cpu; @@ -1935,7 +1942,7 @@ static void unfreeze_partials(struct kmem_cache *s) * 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) +static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) { struct page *oldpage; int pages; @@ -2307,7 +2314,7 @@ new_slab: * * Otherwise we can simply pick the next object from the lockless free list. */ -static __always_inline void *slab_alloc(struct kmem_cache *s, +static __always_inline void *slab_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node, unsigned long addr) { void **object; @@ -2377,9 +2384,15 @@ redo: return object; } +static __always_inline void *slab_alloc(struct kmem_cache *s, + gfp_t gfpflags, unsigned long addr) +{ + return slab_alloc_node(s, gfpflags, NUMA_NO_NODE, addr); +} + void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) { - void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_); + void *ret = slab_alloc(s, gfpflags, _RET_IP_); trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size, s->size, gfpflags); @@ -2390,7 +2403,7 @@ EXPORT_SYMBOL(kmem_cache_alloc); #ifdef CONFIG_TRACING void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) { - void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_); + void *ret = slab_alloc(s, gfpflags, _RET_IP_); trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags); return ret; } @@ -2408,7 +2421,7 @@ EXPORT_SYMBOL(kmalloc_order_trace); #ifdef CONFIG_NUMA void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node) { - void *ret = slab_alloc(s, gfpflags, node, _RET_IP_); + void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_); trace_kmem_cache_alloc_node(_RET_IP_, ret, s->object_size, s->size, gfpflags, node); @@ -2422,7 +2435,7 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) { - void *ret = slab_alloc(s, gfpflags, node, _RET_IP_); + void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_); trace_kmalloc_node(_RET_IP_, ret, size, s->size, gfpflags, node); @@ -3345,7 +3358,7 @@ void *__kmalloc(size_t size, gfp_t flags) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc(s, flags, NUMA_NO_NODE, _RET_IP_); + ret = slab_alloc(s, flags, _RET_IP_); trace_kmalloc(_RET_IP_, ret, size, s->size, flags); @@ -3388,7 +3401,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc(s, flags, node, _RET_IP_); + ret = slab_alloc_node(s, flags, node, _RET_IP_); trace_kmalloc_node(_RET_IP_, ret, size, s->size, flags, node); @@ -4011,7 +4024,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, caller); + ret = slab_alloc(s, gfpflags, caller); /* Honor the call site pointer we received. */ trace_kmalloc(caller, ret, size, s->size, gfpflags); @@ -4041,7 +4054,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc(s, gfpflags, node, caller); + ret = slab_alloc_node(s, gfpflags, node, caller); /* Honor the call site pointer we received. */ trace_kmalloc_node(caller, ret, size, s->size, gfpflags, node); diff --git a/mm/vmscan.c b/mm/vmscan.c index 8d01243d9560..99b434b674c0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3102,6 +3102,7 @@ int kswapd_run(int nid) /* failure at boot is fatal */ BUG_ON(system_state == SYSTEM_BOOTING); printk("Failed to start kswapd on node %d\n",nid); + pgdat->kswapd = NULL; ret = -1; } return ret; |