diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 2 | ||||
| -rw-r--r-- | mm/Makefile | 4 | ||||
| -rw-r--r-- | mm/allocpercpu.c | 28 | ||||
| -rw-r--r-- | mm/backing-dev.c | 427 | ||||
| -rw-r--r-- | mm/bootmem.c | 6 | ||||
| -rw-r--r-- | mm/filemap.c | 170 | ||||
| -rw-r--r-- | mm/hugetlb.c | 1 | ||||
| -rw-r--r-- | mm/kmemleak-test.c | 6 | ||||
| -rw-r--r-- | mm/kmemleak.c | 336 | ||||
| -rw-r--r-- | mm/memory.c | 1 | ||||
| -rw-r--r-- | mm/mmap.c | 2 | ||||
| -rw-r--r-- | mm/nommu.c | 3 | ||||
| -rw-r--r-- | mm/page-writeback.c | 179 | ||||
| -rw-r--r-- | mm/page_alloc.c | 6 | ||||
| -rw-r--r-- | mm/pdflush.c | 269 | ||||
| -rw-r--r-- | mm/percpu.c | 1421 | ||||
| -rw-r--r-- | mm/quicklist.c | 2 | ||||
| -rw-r--r-- | mm/shmem.c | 15 | ||||
| -rw-r--r-- | mm/shmem_acl.c | 11 | ||||
| -rw-r--r-- | mm/slob.c | 5 | ||||
| -rw-r--r-- | mm/slub.c | 92 | ||||
| -rw-r--r-- | mm/swap_state.c | 1 | ||||
| -rw-r--r-- | mm/swapfile.c | 6 | ||||
| -rw-r--r-- | mm/vmalloc.c | 338 | ||||
| -rw-r--r-- | mm/vmscan.c | 2 |
25 files changed, 2274 insertions, 1059 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index fe5f674d7a7d..3aa519f52e18 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -153,7 +153,7 @@ config MEMORY_HOTREMOVE # config PAGEFLAGS_EXTENDED def_bool y - depends on 64BIT || SPARSEMEM_VMEMMAP || !NUMA || !SPARSEMEM + depends on 64BIT || SPARSEMEM_VMEMMAP || !SPARSEMEM # Heavily threaded applications may benefit from splitting the mm-wide # page_table_lock, so that faults on different parts of the user address diff --git a/mm/Makefile b/mm/Makefile index 5e0bd6426693..ea4b18bd3960 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -8,7 +8,7 @@ mmu-$(CONFIG_MMU) := fremap.o highmem.o madvise.o memory.o mincore.o \ vmalloc.o obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \ - maccess.o page_alloc.o page-writeback.o pdflush.o \ + maccess.o page_alloc.o page-writeback.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \ page_isolation.o mm_init.o $(mmu-y) @@ -33,7 +33,7 @@ obj-$(CONFIG_FAILSLAB) += failslab.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o -ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA +ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA obj-$(CONFIG_SMP) += percpu.o else obj-$(CONFIG_SMP) += allocpercpu.o diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c index dfdee6a47359..df34ceae0c67 100644 --- a/mm/allocpercpu.c +++ b/mm/allocpercpu.c @@ -5,6 +5,8 @@ */ #include <linux/mm.h> #include <linux/module.h> +#include <linux/bootmem.h> +#include <asm/sections.h> #ifndef cache_line_size #define cache_line_size() L1_CACHE_BYTES @@ -147,3 +149,29 @@ void free_percpu(void *__pdata) kfree(__percpu_disguise(__pdata)); } EXPORT_SYMBOL_GPL(free_percpu); + +/* + * Generic percpu area setup. + */ +#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA +unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; + +EXPORT_SYMBOL(__per_cpu_offset); + +void __init setup_per_cpu_areas(void) +{ + unsigned long size, i; + char *ptr; + unsigned long nr_possible_cpus = num_possible_cpus(); + + /* Copy section for each CPU (we discard the original) */ + size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE); + ptr = alloc_bootmem_pages(size * nr_possible_cpus); + + for_each_possible_cpu(i) { + __per_cpu_offset[i] = ptr - __per_cpu_start; + memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start); + ptr += size; + } +} +#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index c86edd244294..3d3accb1f800 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -1,8 +1,11 @@ #include <linux/wait.h> #include <linux/backing-dev.h> +#include <linux/kthread.h> +#include <linux/freezer.h> #include <linux/fs.h> #include <linux/pagemap.h> +#include <linux/mm.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/writeback.h> @@ -14,6 +17,7 @@ void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page) EXPORT_SYMBOL(default_unplug_io_fn); struct backing_dev_info default_backing_dev_info = { + .name = "default", .ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE, .state = 0, .capabilities = BDI_CAP_MAP_COPY, @@ -23,6 +27,24 @@ EXPORT_SYMBOL_GPL(default_backing_dev_info); static struct class *bdi_class; +/* + * bdi_lock protects updates to bdi_list and bdi_pending_list, as well as + * reader side protection for bdi_pending_list. bdi_list has RCU reader side + * locking. + */ +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); +static void arm_supers_timer(void); + +static void bdi_add_default_flusher_task(struct backing_dev_info *bdi); + #ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> #include <linux/seq_file.h> @@ -37,9 +59,29 @@ static void bdi_debug_init(void) static int bdi_debug_stats_show(struct seq_file *m, void *v) { struct backing_dev_info *bdi = m->private; + struct bdi_writeback *wb; unsigned long background_thresh; unsigned long dirty_thresh; unsigned long bdi_thresh; + unsigned long nr_dirty, nr_io, nr_more_io, nr_wb; + struct inode *inode; + + /* + * inode lock is enough here, the bdi->wb_list is protected by + * RCU on the reader side + */ + nr_wb = nr_dirty = nr_io = nr_more_io = 0; + spin_lock(&inode_lock); + list_for_each_entry(wb, &bdi->wb_list, list) { + nr_wb++; + list_for_each_entry(inode, &wb->b_dirty, i_list) + nr_dirty++; + list_for_each_entry(inode, &wb->b_io, i_list) + nr_io++; + list_for_each_entry(inode, &wb->b_more_io, i_list) + nr_more_io++; + } + spin_unlock(&inode_lock); get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi); @@ -49,12 +91,22 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) "BdiReclaimable: %8lu kB\n" "BdiDirtyThresh: %8lu kB\n" "DirtyThresh: %8lu kB\n" - "BackgroundThresh: %8lu kB\n", + "BackgroundThresh: %8lu kB\n" + "WriteBack threads:%8lu\n" + "b_dirty: %8lu\n" + "b_io: %8lu\n" + "b_more_io: %8lu\n" + "bdi_list: %8u\n" + "state: %8lx\n" + "wb_mask: %8lx\n" + "wb_list: %8u\n" + "wb_cnt: %8u\n", (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)), (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)), - K(bdi_thresh), - K(dirty_thresh), - K(background_thresh)); + K(bdi_thresh), K(dirty_thresh), + K(background_thresh), nr_wb, nr_dirty, nr_io, nr_more_io, + !list_empty(&bdi->bdi_list), bdi->state, bdi->wb_mask, + !list_empty(&bdi->wb_list), bdi->wb_cnt); #undef K return 0; @@ -185,6 +237,13 @@ 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)); + + init_timer(&sync_supers_timer); + setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0); + arm_supers_timer(); + err = bdi_init(&default_backing_dev_info); if (!err) bdi_register(&default_backing_dev_info, NULL, "default"); @@ -193,6 +252,279 @@ static int __init default_bdi_init(void) } subsys_initcall(default_bdi_init); +static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi) +{ + memset(wb, 0, sizeof(*wb)); + + wb->bdi = bdi; + wb->last_old_flush = jiffies; + INIT_LIST_HEAD(&wb->b_dirty); + INIT_LIST_HEAD(&wb->b_io); + INIT_LIST_HEAD(&wb->b_more_io); +} + +static void bdi_task_init(struct backing_dev_info *bdi, + struct bdi_writeback *wb) +{ + struct task_struct *tsk = current; + + spin_lock(&bdi->wb_lock); + list_add_tail_rcu(&wb->list, &bdi->wb_list); + spin_unlock(&bdi->wb_lock); + + tsk->flags |= PF_FLUSHER | PF_SWAPWRITE; + set_freezable(); + + /* + * Our parent may run at a different priority, just set us to normal + */ + set_user_nice(tsk, 0); +} + +static int bdi_start_fn(void *ptr) +{ + struct bdi_writeback *wb = ptr; + struct backing_dev_info *bdi = wb->bdi; + int ret; + + /* + * Add us to the active bdi_list + */ + spin_lock_bh(&bdi_lock); + list_add_rcu(&bdi->bdi_list, &bdi_list); + spin_unlock_bh(&bdi_lock); + + bdi_task_init(bdi, wb); + + /* + * Clear pending bit and wakeup anybody waiting to tear us down + */ + clear_bit(BDI_pending, &bdi->state); + smp_mb__after_clear_bit(); + wake_up_bit(&bdi->state, BDI_pending); + + ret = bdi_writeback_task(wb); + + /* + * Remove us from the list + */ + spin_lock(&bdi->wb_lock); + list_del_rcu(&wb->list); + spin_unlock(&bdi->wb_lock); + + /* + * Flush any work that raced with us exiting. No new work + * will be added, since this bdi isn't discoverable anymore. + */ + if (!list_empty(&bdi->work_list)) + wb_do_writeback(wb, 1); + + wb->task = NULL; + return ret; +} + +int bdi_has_dirty_io(struct backing_dev_info *bdi) +{ + return wb_has_dirty_io(&bdi->wb); +} + +static void bdi_flush_io(struct backing_dev_info *bdi) +{ + struct writeback_control wbc = { + .bdi = bdi, + .sync_mode = WB_SYNC_NONE, + .older_than_this = NULL, + .range_cyclic = 1, + .nr_to_write = 1024, + }; + + writeback_inodes_wbc(&wbc); +} + +/* + * kupdated() used to do this. We cannot do it from the bdi_forker_task() + * 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 tasks 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; +} + +static void arm_supers_timer(void) +{ + unsigned long next; + + 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); + arm_supers_timer(); +} + +static int bdi_forker_task(void *ptr) +{ + struct bdi_writeback *me = ptr; + + bdi_task_init(me->bdi, me); + + for (;;) { + struct backing_dev_info *bdi, *tmp; + struct bdi_writeback *wb; + + /* + * Temporary measure, we want to make sure we don't see + * dirty data on the default backing_dev_info + */ + if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list)) + wb_do_writeback(me, 0); + + spin_lock_bh(&bdi_lock); + + /* + * Check if any existing bdi's have dirty data without + * a thread registered. If so, set that up. + */ + list_for_each_entry_safe(bdi, tmp, &bdi_list, bdi_list) { + if (bdi->wb.task) + continue; + if (list_empty(&bdi->work_list) && + !bdi_has_dirty_io(bdi)) + continue; + + bdi_add_default_flusher_task(bdi); + } + + set_current_state(TASK_INTERRUPTIBLE); + + if (list_empty(&bdi_pending_list)) { + unsigned long wait; + + spin_unlock_bh(&bdi_lock); + wait = msecs_to_jiffies(dirty_writeback_interval * 10); + schedule_timeout(wait); + try_to_freeze(); + continue; + } + + __set_current_state(TASK_RUNNING); + + /* + * This is our real job - check for pending entries in + * bdi_pending_list, and create the tasks that got added + */ + bdi = list_entry(bdi_pending_list.next, struct backing_dev_info, + bdi_list); + list_del_init(&bdi->bdi_list); + spin_unlock_bh(&bdi_lock); + + wb = &bdi->wb; + wb->task = kthread_run(bdi_start_fn, wb, "flush-%s", + dev_name(bdi->dev)); + /* + * If task creation fails, then readd the bdi to + * the pending list and force writeout of the bdi + * from this forker thread. That will free some memory + * and we can try again. + */ + if (IS_ERR(wb->task)) { + wb->task = NULL; + + /* + * Add this 'bdi' to the back, so we get + * a chance to flush other bdi's to free + * memory. + */ + spin_lock_bh(&bdi_lock); + list_add_tail(&bdi->bdi_list, &bdi_pending_list); + spin_unlock_bh(&bdi_lock); + + bdi_flush_io(bdi); + } + } + + return 0; +} + +static void bdi_add_to_pending(struct rcu_head *head) +{ + struct backing_dev_info *bdi; + + bdi = container_of(head, struct backing_dev_info, rcu_head); + INIT_LIST_HEAD(&bdi->bdi_list); + + spin_lock(&bdi_lock); + list_add_tail(&bdi->bdi_list, &bdi_pending_list); + spin_unlock(&bdi_lock); + + /* + * We are now on the pending list, wake up bdi_forker_task() + * to finish the job and add us back to the active bdi_list + */ + wake_up_process(default_backing_dev_info.wb.task); +} + +/* + * Add the default flusher task that gets created for any bdi + * that has dirty data pending writeout + */ +void static bdi_add_default_flusher_task(struct backing_dev_info *bdi) +{ + if (!bdi_cap_writeback_dirty(bdi)) + return; + + if (WARN_ON(!test_bit(BDI_registered, &bdi->state))) { + printk(KERN_ERR "bdi %p/%s is not registered!\n", + bdi, bdi->name); + return; + } + + /* + * Check with the helper whether to proceed adding a task. Will only + * abort if we two or more simultanous calls to + * bdi_add_default_flusher_task() occured, further additions will block + * waiting for previous additions to finish. + */ + if (!test_and_set_bit(BDI_pending, &bdi->state)) { + list_del_rcu(&bdi->bdi_list); + + /* + * We must wait for the current RCU period to end before + * moving to the pending list. So schedule that operation + * from an RCU callback. + */ + call_rcu(&bdi->rcu_head, bdi_add_to_pending); + } +} + +/* + * Remove bdi from bdi_list, and ensure that it is no longer visible + */ +static void bdi_remove_from_list(struct backing_dev_info *bdi) +{ + spin_lock_bh(&bdi_lock); + list_del_rcu(&bdi->bdi_list); + spin_unlock_bh(&bdi_lock); + + synchronize_rcu(); +} + int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...) { @@ -211,9 +543,33 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, goto exit; } + spin_lock_bh(&bdi_lock); + list_add_tail_rcu(&bdi->bdi_list, &bdi_list); + spin_unlock_bh(&bdi_lock); + bdi->dev = dev; - bdi_debug_register(bdi, dev_name(dev)); + /* + * Just start the forker thread for our default backing_dev_info, + * and add other bdi's to the list. They will get a thread created + * on-demand when they need it. + */ + if (bdi_cap_flush_forker(bdi)) { + struct bdi_writeback *wb = &bdi->wb; + + wb->task = kthread_run(bdi_forker_task, wb, "bdi-%s", + dev_name(dev)); + if (IS_ERR(wb->task)) { + wb->task = NULL; + ret = -ENOMEM; + + bdi_remove_from_list(bdi); + goto exit; + } + } + + bdi_debug_register(bdi, dev_name(dev)); + set_bit(BDI_registered, &bdi->state); exit: return ret; } @@ -225,9 +581,40 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev) } EXPORT_SYMBOL(bdi_register_dev); +/* + * Remove bdi from the global list and shutdown any threads we have running + */ +static void bdi_wb_shutdown(struct backing_dev_info *bdi) +{ + struct bdi_writeback *wb; + + if (!bdi_cap_writeback_dirty(bdi)) + return; + + /* + * If setup is pending, wait for that to complete first + */ + wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait, + TASK_UNINTERRUPTIBLE); + + /* + * Make sure nobody finds us on the bdi_list anymore + */ + bdi_remove_from_list(bdi); + + /* + * Finally, kill the kernel threads. We don't need to be RCU + * safe anymore, since the bdi is gone from visibility. + */ + list_for_each_entry(wb, &bdi->wb_list, list) + kthread_stop(wb->task); +} + void bdi_unregister(struct backing_dev_info *bdi) { if (bdi->dev) { + if (!bdi_cap_flush_forker(bdi)) + bdi_wb_shutdown(bdi); bdi_debug_unregister(bdi); device_unregister(bdi->dev); bdi->dev = NULL; @@ -237,14 +624,26 @@ EXPORT_SYMBOL(bdi_unregister); int bdi_init(struct backing_dev_info *bdi) { - int i; - int err; + int i, err; bdi->dev = NULL; bdi->min_ratio = 0; bdi->max_ratio = 100; bdi->max_prop_frac = PROP_FRAC_BASE; + spin_lock_init(&bdi->wb_lock); + INIT_RCU_HEAD(&bdi->rcu_head); + INIT_LIST_HEAD(&bdi->bdi_list); + INIT_LIST_HEAD(&bdi->wb_list); + INIT_LIST_HEAD(&bdi->work_list); + + bdi_wb_init(&bdi->wb, bdi); + + /* + * Just one thread support for now, hard code mask and count + */ + bdi->wb_mask = 1; + bdi->wb_cnt = 1; for (i = 0; i < NR_BDI_STAT_ITEMS; i++) { err = percpu_counter_init(&bdi->bdi_stat[i], 0); @@ -269,6 +668,20 @@ void bdi_destroy(struct backing_dev_info *bdi) { int i; + /* + * Splice our entries to the default_backing_dev_info, if this + * bdi disappears + */ + if (bdi_has_dirty_io(bdi)) { + struct bdi_writeback *dst = &default_backing_dev_info.wb; + + spin_lock(&inode_lock); + list_splice(&bdi->wb.b_dirty, &dst->b_dirty); + list_splice(&bdi->wb.b_io, &dst->b_io); + list_splice(&bdi->wb.b_more_io, &dst->b_more_io); + spin_unlock(&inode_lock); + } + bdi_unregister(bdi); for (i = 0; i < NR_BDI_STAT_ITEMS; i++) diff --git a/mm/bootmem.c b/mm/bootmem.c index 701740c9e81b..555d5d2731c6 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -521,7 +521,11 @@ find_block: region = phys_to_virt(PFN_PHYS(bdata->node_min_pfn) + start_off); memset(region, 0, size); - kmemleak_alloc(region, size, 1, 0); + /* + * The min_count is set to 0 so that bootmem allocated blocks + * are never reported as leaks. + */ + kmemleak_alloc(region, size, 0, 0); return region; } diff --git a/mm/filemap.c b/mm/filemap.c index ccea3b665c12..dd51c68e2b86 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -39,11 +39,10 @@ /* * FIXME: remove all knowledge of the buffer layer from the core VM */ -#include <linux/buffer_head.h> /* for generic_osync_inode */ +#include <linux/buffer_head.h> /* for try_to_free_buffers */ #include <asm/mman.h> - /* * Shared mappings implemented 30.11.1994. It's not fully working yet, * though. @@ -307,68 +306,24 @@ int wait_on_page_writeback_range(struct address_space *mapping, } /** - * sync_page_range - write and wait on all pages in the passed range - * @inode: target inode - * @mapping: target address_space - * @pos: beginning offset in pages to write - * @count: number of bytes to write - * - * Write and wait upon all the pages in the passed range. This is a "data - * integrity" operation. It waits upon in-flight writeout before starting and - * waiting upon new writeout. If there was an IO error, return it. + * 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) * - * We need to re-take i_mutex during the generic_osync_inode list walk because - * it is otherwise livelockable. - */ -int sync_page_range(struct inode *inode, struct address_space *mapping, - loff_t pos, loff_t count) -{ - pgoff_t start = pos >> PAGE_CACHE_SHIFT; - pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT; - int ret; - - if (!mapping_cap_writeback_dirty(mapping) || !count) - return 0; - ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1); - if (ret == 0) { - mutex_lock(&inode->i_mutex); - ret = generic_osync_inode(inode, mapping, OSYNC_METADATA); - mutex_unlock(&inode->i_mutex); - } - if (ret == 0) - ret = wait_on_page_writeback_range(mapping, start, end); - return ret; -} -EXPORT_SYMBOL(sync_page_range); - -/** - * sync_page_range_nolock - write & wait on all pages in the passed range without locking - * @inode: target inode - * @mapping: target address_space - * @pos: beginning offset in pages to write - * @count: number of bytes to write + * Walk the list of under-writeback pages of the given address space + * in the given range and wait for all of them. * - * Note: Holding i_mutex across sync_page_range_nolock() is not a good idea - * as it forces O_SYNC writers to different parts of the same file - * to be serialised right until io completion. + * This is just a simple wrapper so that callers don't have to convert offsets + * to page indexes themselves */ -int sync_page_range_nolock(struct inode *inode, struct address_space *mapping, - loff_t pos, loff_t count) +int filemap_fdatawait_range(struct address_space *mapping, loff_t start, + loff_t end) { - pgoff_t start = pos >> PAGE_CACHE_SHIFT; - pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT; - int ret; - - if (!mapping_cap_writeback_dirty(mapping) || !count) - return 0; - ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1); - if (ret == 0) - ret = generic_osync_inode(inode, mapping, OSYNC_METADATA); - if (ret == 0) - ret = wait_on_page_writeback_range(mapping, start, end); - return ret; + return wait_on_page_writeback_range(mapping, start >> PAGE_CACHE_SHIFT, + end >> PAGE_CACHE_SHIFT); } -EXPORT_SYMBOL(sync_page_range_nolock); +EXPORT_SYMBOL(filemap_fdatawait_range); /** * filemap_fdatawait - wait for all under-writeback pages to complete @@ -2167,20 +2122,7 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, } *ppos = end; } - - /* - * Sync the fs metadata but not the minor inode changes and - * of course not the data as we did direct DMA for the IO. - * i_mutex is held, which protects generic_osync_inode() from - * livelocking. AIO O_DIRECT ops attempt to sync metadata here. - */ out: - if ((written >= 0 || written == -EIOCBQUEUED) && - ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - int err = generic_osync_inode(inode, mapping, OSYNC_METADATA); - if (err < 0) - written = err; - } return written; } EXPORT_SYMBOL(generic_file_direct_write); @@ -2312,8 +2254,6 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; - const struct address_space_operations *a_ops = mapping->a_ops; - struct inode *inode = mapping->host; ssize_t status; struct iov_iter i; @@ -2323,16 +2263,6 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, if (likely(status >= 0)) { written += status; *ppos = pos + status; - - /* - * For now, when the user asks for O_SYNC, we'll actually give - * O_DSYNC - */ - if (unlikely((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - if (!a_ops->writepage || !is_sync_kiocb(iocb)) - status = generic_osync_inode(inode, mapping, - OSYNC_METADATA|OSYNC_DATA); - } } /* @@ -2348,9 +2278,27 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, } EXPORT_SYMBOL(generic_file_buffered_write); -static ssize_t -__generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) +/** + * __generic_file_aio_write - write data to a file + * @iocb: IO state structure (file, offset, etc.) + * @iov: vector with data to write + * @nr_segs: number of segments in the vector + * @ppos: position where to write + * + * This function does all the work needed for actually writing data to a + * file. It does all basic checks, removes SUID from the file, updates + * modification times and calls proper subroutines depending on whether we + * do direct IO or a standard buffered write. + * + * It expects i_mutex to be grabbed unless we work on a block device or similar + * object which does not need locking at all. + * + * This function does *not* take care of syncing data in case of O_SYNC write. + * A caller has to handle it. This is mainly due to the fact that we want to + * avoid syncing under i_mutex. + */ +ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t *ppos) { struct file *file = iocb->ki_filp; struct address_space * mapping = file->f_mapping; @@ -2447,51 +2395,37 @@ out: current->backing_dev_info = NULL; return written ? written : err; } +EXPORT_SYMBOL(__generic_file_aio_write); -ssize_t generic_file_aio_write_nolock(struct kiocb *iocb, - const struct iovec *iov, unsigned long nr_segs, loff_t pos) -{ - struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - ssize_t ret; - - BUG_ON(iocb->ki_pos != pos); - - ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, - &iocb->ki_pos); - - if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - ssize_t err; - - err = sync_page_range_nolock(inode, mapping, pos, ret); - if (err < 0) - ret = err; - } - return ret; -} -EXPORT_SYMBOL(generic_file_aio_write_nolock); - +/** + * generic_file_aio_write - write data to a file + * @iocb: IO state structure + * @iov: vector with data to write + * @nr_segs: number of segments in the vector + * @pos: position in file where to write + * + * This is a wrapper around __generic_file_aio_write() to be used by most + * filesystems. It takes care of syncing the file in case of O_SYNC file + * and acquires i_mutex as needed. + */ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; + struct inode *inode = file->f_mapping->host; ssize_t ret; BUG_ON(iocb->ki_pos != pos); mutex_lock(&inode->i_mutex); - ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, - &iocb->ki_pos); + ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); mutex_unlock(&inode->i_mutex); - if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { + if (ret > 0 || ret == -EIOCBQUEUED) { ssize_t err; - err = sync_page_range(inode, mapping, pos, ret); - if (err < 0) + err = generic_write_sync(file, pos, ret); + if (err < 0 && ret > 0) ret = err; } return ret; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index cafdcee154e8..b16d63634777 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -234,6 +234,7 @@ unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) return 1UL << (hstate->order + PAGE_SHIFT); } +EXPORT_SYMBOL_GPL(vma_kernel_pagesize); /* * Return the page size being used by the MMU to back a VMA. In the majority diff --git a/mm/kmemleak-test.c b/mm/kmemleak-test.c index d5292fc6f523..177a5169bbde 100644 --- a/mm/kmemleak-test.c +++ b/mm/kmemleak-test.c @@ -36,7 +36,7 @@ struct test_node { }; static LIST_HEAD(test_list); -static DEFINE_PER_CPU(void *, test_pointer); +static DEFINE_PER_CPU(void *, kmemleak_test_pointer); /* * Some very simple testing. This function needs to be extended for @@ -86,9 +86,9 @@ static int __init kmemleak_test_init(void) } for_each_possible_cpu(i) { - per_cpu(test_pointer, i) = kmalloc(129, GFP_KERNEL); + per_cpu(kmemleak_test_pointer, i) = kmalloc(129, GFP_KERNEL); pr_info("kmemleak: kmalloc(129) = %p\n", - per_cpu(test_pointer, i)); + per_cpu(kmemleak_test_pointer, i)); } return 0; diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 487267310a84..4ea4510e2996 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -92,11 +92,13 @@ #include <linux/string.h> #include <linux/nodemask.h> #include <linux/mm.h> +#include <linux/workqueue.h> #include <asm/sections.h> #include <asm/processor.h> #include <asm/atomic.h> +#include <linux/kmemcheck.h> #include <linux/kmemleak.h> /* @@ -107,6 +109,7 @@ #define SECS_FIRST_SCAN 60 /* delay before the first scan */ #define SECS_SCAN_WAIT 600 /* subsequent auto scanning delay */ #define GRAY_LIST_PASSES 25 /* maximum number of gray list scans */ +#define MAX_SCAN_SIZE 4096 /* maximum size of a scanned block */ #define BYTES_PER_POINTER sizeof(void *) @@ -120,6 +123,9 @@ struct kmemleak_scan_area { size_t length; }; +#define KMEMLEAK_GREY 0 +#define KMEMLEAK_BLACK -1 + /* * Structure holding the metadata for each allocated memory block. * Modifications to such objects should be made while holding the @@ -161,6 +167,15 @@ struct kmemleak_object { /* flag set on newly allocated objects */ #define OBJECT_NEW (1 << 3) +/* number of bytes to print per line; must be 16 or 32 */ +#define HEX_ROW_SIZE 16 +/* number of bytes to print at a time (1, 2, 4, 8) */ +#define HEX_GROUP_SIZE 1 +/* include ASCII after the hex output */ +#define HEX_ASCII 1 +/* max number of lines to be printed */ +#define HEX_MAX_LINES 2 + /* the list of all allocated objects */ static LIST_HEAD(object_list); /* the list of gray-colored objects (see color_gray comment below) */ @@ -228,11 +243,14 @@ struct early_log { int min_count; /* minimum reference count */ unsigned long offset; /* scan area offset */ size_t length; /* scan area length */ + unsigned long trace[MAX_TRACE]; /* stack trace */ + unsigned int trace_len; /* stack trace length */ }; /* early logging buffer and current position */ -static struct early_log early_log[CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE]; -static int crt_early_log; +static struct early_log + early_log[CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE] __initdata; +static int crt_early_log __initdata; static void kmemleak_disable(void); @@ -255,6 +273,35 @@ static void kmemleak_disable(void); } while (0) /* + * Printing of the objects hex dump to the seq file. The number of lines to be + * printed is limited to HEX_MAX_LINES to prevent seq file spamming. The + * actual number of printed bytes depends on HEX_ROW_SIZE. It must be called + * with the object->lock held. + */ +static void hex_dump_object(struct seq_file *seq, + struct kmemleak_object *object) +{ + const u8 *ptr = (const u8 *)object->pointer; + int i, len, remaining; + unsigned char linebuf[HEX_ROW_SIZE * 5]; + + /* limit the number of lines to HEX_MAX_LINES */ + remaining = len = + min(object->size, (size_t)(HEX_MAX_LINES * HEX_ROW_SIZE)); + + seq_printf(seq, " hex dump (first %d bytes):\n", len); + for (i = 0; i < len; i += HEX_ROW_SIZE) { + int linelen = min(remaining, HEX_ROW_SIZE); + + remaining -= HEX_ROW_SIZE; + hex_dump_to_buffer(ptr + i, linelen, HEX_ROW_SIZE, + HEX_GROUP_SIZE, linebuf, sizeof(linebuf), + HEX_ASCII); + seq_printf(seq, " %s\n", linebuf); + } +} + +/* * Object colors, encoded with count and min_count: * - white - orphan object, not enough references to it (count < min_count) * - gray - not orphan, not marked as false positive (min_count == 0) or @@ -264,19 +311,21 @@ static void kmemleak_disable(void); * Newly created objects don't have any color assigned (object->count == -1) * before the next memory scan when they become white. */ -static int color_white(const struct kmemleak_object *object) +static bool color_white(const struct kmemleak_object *object) { - return object->count != -1 && object->count < object->min_count; + return object->count != KMEMLEAK_BLACK && + object->count < object->min_count; } -static int color_gray(const struct kmemleak_object *object) +static bool color_gray(const struct kmemleak_object *object) { - return object->min_count != -1 && object->count >= object->min_count; + return object->min_count != KMEMLEAK_BLACK && + object->count >= object->min_count; } -static int color_black(const struct kmemleak_object *object) +static bool color_black(const struct kmemleak_object *object) { - return object->min_count == -1; + return object->min_count == KMEMLEAK_BLACK; } /* @@ -284,7 +333,7 @@ static int color_black(const struct kmemleak_object *object) * not be deleted and have a minimum age to avoid false positives caused by * pointers temporarily stored in CPU registers. */ -static int unreferenced_object(struct kmemleak_object *object) +static bool unreferenced_object(struct kmemleak_object *object) { return (object->flags & OBJECT_ALLOCATED) && color_white(object) && time_before_eq(object->jiffies + jiffies_min_age, @@ -304,6 +353,7 @@ static void print_unreferenced(struct seq_file *seq, object->pointer, object->size); seq_printf(seq, " comm \"%s\", pid %d, jiffies %lu\n", object->comm, object->pid, object->jiffies); + hex_dump_object(seq, object); seq_printf(seq, " backtrace:\n"); for (i = 0; i < object->trace_len; i++) { @@ -330,6 +380,7 @@ static void dump_object_info(struct kmemleak_object *object) object->comm, object->pid, object->jiffies); pr_notice(" min_count = %d\n", object->min_count); pr_notice(" count = %d\n", object->count); + pr_notice(" flags = 0x%lx\n", object->flags); pr_notice(" backtrace:\n"); print_stack_trace(&trace, 4); } @@ -434,21 +485,36 @@ static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias) } /* + * Save stack trace to the given array of MAX_TRACE size. + */ +static int __save_stack_trace(unsigned long *trace) +{ + struct stack_trace stack_trace; + + stack_trace.max_entries = MAX_TRACE; + stack_trace.nr_entries = 0; + stack_trace.entries = trace; + stack_trace.skip = 2; + save_stack_trace(&stack_trace); + + return stack_trace.nr_entries; +} + +/* * Create the metadata (struct kmemleak_object) corresponding to an allocated * memory block and add it to the object_list and object_tree_root. */ -static void create_object(unsigned long ptr, size_t size, int min_count, - gfp_t gfp) +static struct kmemleak_object *create_object(unsigned long ptr, size_t size, + int min_count, gfp_t gfp) { unsigned long flags; struct kmemleak_object *object; struct prio_tree_node *node; - struct stack_trace trace; object = kmem_cache_alloc(object_cache, gfp & GFP_KMEMLEAK_MASK); if (!object) { kmemleak_stop("Cannot allocate a kmemleak_object structure\n"); - return; + return NULL; } INIT_LIST_HEAD(&object->object_list); @@ -482,18 +548,14 @@ static void create_object(unsigned long ptr, size_t size, int min_count, } /* kernel backtrace */ - trace.max_entries = MAX_TRACE; - trace.nr_entries = 0; - trace.entries = object->trace; - trace.skip = 1; - save_stack_trace(&trace); - object->trace_len = trace.nr_entries; + object->trace_len = __save_stack_trace(object->trace); INIT_PRIO_TREE_NODE(&object->tree_node); object->tree_node.start = ptr; object->tree_node.last = ptr + size - 1; write_lock_irqsave(&kmemleak_lock, flags); + min_addr = min(min_addr, ptr); max_addr = max(max_addr, ptr + size); node = prio_tree_insert(&object_tree_root, &object->tree_node); @@ -504,20 +566,19 @@ static void create_object(unsigned long ptr, size_t size, int min_count, * random memory blocks. */ if (node != &object->tree_node) { - unsigned long flags; - kmemleak_stop("Cannot insert 0x%lx into the object search tree " "(already existing)\n", ptr); object = lookup_object(ptr, 1); - spin_lock_irqsave(&object->lock, flags); + spin_lock(&object->lock); dump_object_info(object); - spin_unlock_irqrestore(&object->lock, flags); + spin_unlock(&object->lock); goto out; } list_add_tail_rcu(&object->object_list, &object_list); out: write_unlock_irqrestore(&kmemleak_lock, flags); + return object; } /* @@ -604,46 +665,55 @@ static void delete_object_part(unsigned long ptr, size_t size) put_object(object); } -/* - * Make a object permanently as gray-colored so that it can no longer be - * reported as a leak. This is used in general to mark a false positive. - */ -static void make_gray_object(unsigned long ptr) + +static void __paint_it(struct kmemleak_object *object, int color) +{ + object->min_count = color; + if (color == KMEMLEAK_BLACK) + object->flags |= OBJECT_NO_SCAN; +} + +static void paint_it(struct kmemleak_object *object, int color) { unsigned long flags; + + spin_lock_irqsave(&object->lock, flags); + __paint_it(object, color); + spin_unlock_irqrestore(&object->lock, flags); +} + +static void paint_ptr(unsigned long ptr, int color) +{ struct kmemleak_object *object; object = find_and_get_object(ptr, 0); if (!object) { - kmemleak_warn("Graying unknown object at 0x%08lx\n", ptr); + kmemleak_warn("Trying to color unknown object " + "at 0x%08lx as %s\n", ptr, + (color == KMEMLEAK_GREY) ? "Grey" : + (color == KMEMLEAK_BLACK) ? "Black" : "Unknown"); return; } - - spin_lock_irqsave(&object->lock, flags); - object->min_count = 0; - spin_unlock_irqrestore(&object->lock, flags); + paint_it(object, color); put_object(object); } /* + * Make a object permanently as gray-colored so that it can no longer be + * reported as a leak. This is used in general to mark a false positive. + */ +static void make_gray_object(unsigned long ptr) +{ + paint_ptr(ptr, KMEMLEAK_GREY); +} + +/* * Mark the object as black-colored so that it is ignored from scans and * reporting. */ static void make_black_object(unsigned long ptr) { - unsigned long flags; - struct kmemleak_object *object; - - object = find_and_get_object(ptr, 0); - if (!object) { - kmemleak_warn("Blacking unknown object at 0x%08lx\n", ptr); - return; - } - - spin_lock_irqsave(&object->lock, flags); - object->min_count = -1; - spin_unlock_irqrestore(&object->lock, flags); - put_object(object); + paint_ptr(ptr, KMEMLEAK_BLACK); } /* @@ -715,14 +785,15 @@ static void object_no_scan(unsigned long ptr) * Log an early kmemleak_* call to the early_log buffer. These calls will be * processed later once kmemleak is fully initialized. */ -static void log_early(int op_type, const void *ptr, size_t size, - int min_count, unsigned long offset, size_t length) +static void __init log_early(int op_type, const void *ptr, size_t size, + int min_count, unsigned long offset, size_t length) { unsigned long flags; struct early_log *log; if (crt_early_log >= ARRAY_SIZE(early_log)) { - pr_warning("Early log buffer exceeded\n"); + pr_warning("Early log buffer exceeded, " + "please increase DEBUG_KMEMLEAK_EARLY_LOG_SIZE\n"); kmemleak_disable(); return; } @@ -739,16 +810,45 @@ static void log_early(int op_type, const void *ptr, size_t size, log->min_count = min_count; log->offset = offset; log->length = length; + if (op_type == KMEMLEAK_ALLOC) + log->trace_len = __save_stack_trace(log->trace); crt_early_log++; local_irq_restore(flags); } /* + * Log an early allocated block and populate the stack trace. + */ +static void early_alloc(struct early_log *log) +{ + struct kmemleak_object *object; + unsigned long flags; + int i; + + if (!atomic_read(&kmemleak_enabled) || !log->ptr || IS_ERR(log->ptr)) + return; + + /* + * RCU locking needed to ensure object is not freed via put_object(). + */ + rcu_read_lock(); + object = create_object((unsigned long)log->ptr, log->size, + log->min_count, GFP_KERNEL); + 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); + rcu_read_unlock(); +} + +/* * Memory allocation function callback. This function is called from the * kernel allocators when a new block is allocated (kmem_cache_alloc, kmalloc, * vmalloc etc.). */ -void kmemleak_alloc(const void *ptr, size_t size, int min_count, gfp_t gfp) +void __ref kmemleak_alloc(const void *ptr, size_t size, int min_count, + gfp_t gfp) { pr_debug("%s(0x%p, %zu, %d)\n", __func__, ptr, size, min_count); @@ -763,7 +863,7 @@ EXPORT_SYMBOL_GPL(kmemleak_alloc); * Memory freeing function callback. This function is called from the kernel * allocators when a block is freed (kmem_cache_free, kfree, vfree etc.). */ -void kmemleak_free(const void *ptr) +void __ref kmemleak_free(const void *ptr) { pr_debug("%s(0x%p)\n", __func__, ptr); @@ -778,7 +878,7 @@ EXPORT_SYMBOL_GPL(kmemleak_free); * Partial memory freeing function callback. This function is usually called * from bootmem allocator when (part of) a memory block is freed. */ -void kmemleak_free_part(const void *ptr, size_t size) +void __ref kmemleak_free_part(const void *ptr, size_t size) { pr_debug("%s(0x%p)\n", __func__, ptr); @@ -793,7 +893,7 @@ EXPORT_SYMBOL_GPL(kmemleak_free_part); * Mark an already allocated memory block as a false positive. This will cause * the block to no longer be reported as leak and always be scanned. */ -void kmemleak_not_leak(const void *ptr) +void __ref kmemleak_not_leak(const void *ptr) { pr_debug("%s(0x%p)\n", __func__, ptr); @@ -809,7 +909,7 @@ EXPORT_SYMBOL(kmemleak_not_leak); * corresponding block is not a leak and does not contain any references to * other allocated memory blocks. */ -void kmemleak_ignore(const void *ptr) +void __ref kmemleak_ignore(const void *ptr) { pr_debug("%s(0x%p)\n", __func__, ptr); @@ -823,8 +923,8 @@ EXPORT_SYMBOL(kmemleak_ignore); /* * Limit the range to be scanned in an allocated memory block. */ -void kmemleak_scan_area(const void *ptr, unsigned long offset, size_t length, - gfp_t gfp) +void __ref kmemleak_scan_area(const void *ptr, unsigned long offset, + size_t length, gfp_t gfp) { pr_debug("%s(0x%p)\n", __func__, ptr); @@ -838,7 +938,7 @@ EXPORT_SYMBOL(kmemleak_scan_area); /* * Inform kmemleak not to scan the given memory block. */ -void kmemleak_no_scan(const void *ptr) +void __ref kmemleak_no_scan(const void *ptr) { pr_debug("%s(0x%p)\n", __func__, ptr); @@ -882,15 +982,22 @@ static void scan_block(void *_start, void *_end, unsigned long *end = _end - (BYTES_PER_POINTER - 1); for (ptr = start; ptr < end; ptr++) { - unsigned long flags; - unsigned long pointer = *ptr; struct kmemleak_object *object; + unsigned long flags; + unsigned long pointer; if (allow_resched) cond_resched(); if (scan_should_stop()) break; + /* don't scan uninitialized memory */ + if (!kmemcheck_is_obj_initialized((unsigned long)ptr, + BYTES_PER_POINTER)) + continue; + + pointer = *ptr; + object = find_and_get_object(pointer, 1); if (!object) continue; @@ -949,10 +1056,21 @@ static void scan_object(struct kmemleak_object *object) if (!(object->flags & OBJECT_ALLOCATED)) /* already freed object */ goto out; - if (hlist_empty(&object->area_list)) - scan_block((void *)object->pointer, - (void *)(object->pointer + object->size), object, 0); - else + if (hlist_empty(&object->area_list)) { + void *start = (void *)object->pointer; + void *end = (void *)(object->pointer + object->size); + + while (start < end && (object->flags & OBJECT_ALLOCATED) && + !(object->flags & OBJECT_NO_SCAN)) { + scan_block(start, min(start + MAX_SCAN_SIZE, end), + object, 0); + start += MAX_SCAN_SIZE; + + spin_unlock_irqrestore(&object->lock, flags); + cond_resched(); + spin_lock_irqsave(&object->lock, flags); + } + } else hlist_for_each_entry(area, elem, &object->area_list, node) scan_block((void *)(object->pointer + area->offset), (void *)(object->pointer + area->offset @@ -970,7 +1088,6 @@ static void kmemleak_scan(void) { unsigned long flags; struct kmemleak_object *object, *tmp; - struct task_struct *task; int i; int new_leaks = 0; int gray_list_pass = 0; @@ -1037,15 +1154,16 @@ static void kmemleak_scan(void) } /* - * Scanning the task stacks may introduce false negatives and it is - * not enabled by default. + * Scanning the task stacks (may introduce false negatives). */ if (kmemleak_stack_scan) { + struct task_struct *p, *g; + read_lock(&tasklist_lock); - for_each_process(task) - scan_block(task_stack_page(task), - task_stack_page(task) + THREAD_SIZE, - NULL, 0); + do_each_thread(g, p) { + scan_block(task_stack_page(p), task_stack_page(p) + + THREAD_SIZE, NULL, 0); + } while_each_thread(g, p); read_unlock(&tasklist_lock); } @@ -1170,7 +1288,7 @@ static int kmemleak_scan_thread(void *arg) * Start the automatic memory scanning thread. This function must be called * with the scan_mutex held. */ -void start_scan_thread(void) +static void start_scan_thread(void) { if (scan_thread) return; @@ -1185,7 +1303,7 @@ void start_scan_thread(void) * Stop the automatic memory scanning thread. This function must be called * with the scan_mutex held. */ -void stop_scan_thread(void) +static void stop_scan_thread(void) { if (scan_thread) { kthread_stop(scan_thread); @@ -1294,6 +1412,49 @@ static int kmemleak_release(struct inode *inode, struct file *file) return seq_release(inode, file); } +static int dump_str_object_info(const char *str) +{ + unsigned long flags; + struct kmemleak_object *object; + unsigned long addr; + + addr= simple_strtoul(str, NULL, 0); + object = find_and_get_object(addr, 0); + if (!object) { + pr_info("Unknown object at 0x%08lx\n", addr); + return -EINVAL; + } + + spin_lock_irqsave(&object->lock, flags); + dump_object_info(object); + spin_unlock_irqrestore(&object->lock, flags); + + put_object(object); + return 0; +} + +/* + * We use grey instead of black to ensure we can do future scans on the same + * objects. If we did not do future scans these black objects could + * potentially contain references to newly allocated objects in the future and + * we'd end up with false positives. + */ +static void kmemleak_clear(void) +{ + struct kmemleak_object *object; + unsigned long flags; + + rcu_read_lock(); + list_for_each_entry_rcu(object, &object_list, object_list) { + spin_lock_irqsave(&object->lock, flags); + if ((object->flags & OBJECT_REPORTED) && + unreferenced_object(object)) + __paint_it(object, KMEMLEAK_GREY); + spin_unlock_irqrestore(&object->lock, flags); + } + rcu_read_unlock(); +} + /* * File write operation to configure kmemleak at run-time. The following * commands can be written to the /sys/kernel/debug/kmemleak file: @@ -1305,6 +1466,9 @@ static int kmemleak_release(struct inode *inode, struct file *file) * scan=... - set the automatic memory scanning period in seconds (0 to * disable it) * scan - trigger a memory scan + * clear - mark all current reported unreferenced kmemleak objects as + * grey to ignore printing them + * dump=... - dump information about the object found at the given address */ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, size_t size, loff_t *ppos) @@ -1345,6 +1509,10 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, } } else if (strncmp(buf, "scan", 4) == 0) kmemleak_scan(); + else if (strncmp(buf, "clear", 5) == 0) + kmemleak_clear(); + else if (strncmp(buf, "dump=", 5) == 0) + ret = dump_str_object_info(buf + 5); else ret = -EINVAL; @@ -1371,7 +1539,7 @@ static const struct file_operations kmemleak_fops = { * Perform the freeing of the kmemleak internal objects after waiting for any * current memory scan to complete. */ -static int kmemleak_cleanup_thread(void *arg) +static void kmemleak_do_cleanup(struct work_struct *work) { struct kmemleak_object *object; @@ -1383,22 +1551,9 @@ static int kmemleak_cleanup_thread(void *arg) delete_object_full(object->pointer); rcu_read_unlock(); mutex_unlock(&scan_mutex); - - return 0; } -/* - * Start the clean-up thread. - */ -static void kmemleak_cleanup(void) -{ - struct task_struct *cleanup_thread; - - cleanup_thread = kthread_run(kmemleak_cleanup_thread, NULL, - "kmemleak-clean"); - if (IS_ERR(cleanup_thread)) - pr_warning("Failed to create the clean-up thread\n"); -} +static DECLARE_WORK(cleanup_work, kmemleak_do_cleanup); /* * Disable kmemleak. No memory allocation/freeing will be traced once this @@ -1416,7 +1571,7 @@ static void kmemleak_disable(void) /* check whether it is too early for a kernel thread */ if (atomic_read(&kmemleak_initialized)) - kmemleak_cleanup(); + schedule_work(&cleanup_work); pr_info("Kernel memory leak detector disabled\n"); } @@ -1469,8 +1624,7 @@ void __init kmemleak_init(void) switch (log->op_type) { case KMEMLEAK_ALLOC: - kmemleak_alloc(log->ptr, log->size, log->min_count, - GFP_KERNEL); + early_alloc(log); break; case KMEMLEAK_FREE: kmemleak_free(log->ptr); @@ -1513,7 +1667,7 @@ static int __init kmemleak_late_init(void) * after setting kmemleak_initialized and we may end up with * two clean-up threads but serialized by scan_mutex. */ - kmemleak_cleanup(); + schedule_work(&cleanup_work); return -ENOMEM; } diff --git a/mm/memory.c b/mm/memory.c index aede2ce3aba4..e8f63d9961ea 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -56,6 +56,7 @@ #include <linux/swapops.h> #include <linux/elf.h> +#include <asm/io.h> #include <asm/pgalloc.h> #include <asm/uaccess.h> #include <asm/tlb.h> diff --git a/mm/mmap.c b/mm/mmap.c index 8101de490c73..26892e346d8f 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -905,7 +905,7 @@ void vm_stat_account(struct mm_struct *mm, unsigned long flags, #endif /* CONFIG_PROC_FS */ /* - * The caller must hold down_write(current->mm->mmap_sem). + * The caller must hold down_write(¤t->mm->mmap_sem). */ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, diff --git a/mm/nommu.c b/mm/nommu.c index 4bde489ec431..66e81e7e9fe9 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1352,6 +1352,7 @@ unsigned long do_mmap_pgoff(struct file *file, } vma->vm_region = region; + add_nommu_region(region); /* set up the mapping */ if (file && vma->vm_flags & VM_SHARED) @@ -1361,8 +1362,6 @@ unsigned long do_mmap_pgoff(struct file *file, if (ret < 0) goto error_put_region; - add_nommu_region(region); - /* okay... we have a mapping; now we have to register it */ result = vma->vm_start; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 81627ebcd313..1eea4fa0d410 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -36,15 +36,6 @@ #include <linux/pagevec.h> /* - * The maximum number of pages to writeout in a single bdflush/kupdate - * operation. We do this so we don't hold I_SYNC against an inode for - * enormous amounts of time, which would block a userspace task which has - * been forced to throttle against that inode. Also, the code reevaluates - * the dirty each time it has written this many pages. - */ -#define MAX_WRITEBACK_PAGES 1024 - -/* * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited * will look to see if it needs to force writeback or throttling. */ @@ -117,8 +108,6 @@ EXPORT_SYMBOL(laptop_mode); /* End of sysctl-exported parameters */ -static void background_writeout(unsigned long _min_pages); - /* * Scale the writeback cache size proportional to the relative writeout speeds. * @@ -320,15 +309,13 @@ static void task_dirty_limit(struct task_struct *tsk, unsigned long *pdirty) /* * */ -static DEFINE_SPINLOCK(bdi_lock); static unsigned int bdi_min_ratio; int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { int ret = 0; - unsigned long flags; - spin_lock_irqsave(&bdi_lock, flags); + spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { @@ -340,27 +327,26 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) ret = -EINVAL; } } - spin_unlock_irqrestore(&bdi_lock, flags); + spin_unlock_bh(&bdi_lock); return ret; } int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio) { - unsigned long flags; int ret = 0; if (max_ratio > 100) return -EINVAL; - spin_lock_irqsave(&bdi_lock, flags); + spin_lock_bh(&bdi_lock); if (bdi->min_ratio > max_ratio) { ret = -EINVAL; } else { bdi->max_ratio = max_ratio; bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100; } - spin_unlock_irqrestore(&bdi_lock, flags); + spin_unlock_bh(&bdi_lock); return ret; } @@ -546,7 +532,7 @@ static void balance_dirty_pages(struct address_space *mapping) * up. */ if (bdi_nr_reclaimable > bdi_thresh) { - writeback_inodes(&wbc); + writeback_inodes_wbc(&wbc); pages_written += write_chunk - wbc.nr_to_write; get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi); @@ -575,7 +561,7 @@ static void balance_dirty_pages(struct address_space *mapping) if (pages_written >= write_chunk) break; /* We've done our duty */ - congestion_wait(BLK_RW_ASYNC, HZ/10); + schedule_timeout(1); } if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh && @@ -594,10 +580,10 @@ static void balance_dirty_pages(struct address_space *mapping) * background_thresh, to keep the amount of dirty memory low. */ if ((laptop_mode && pages_written) || - (!laptop_mode && (global_page_state(NR_FILE_DIRTY) - + global_page_state(NR_UNSTABLE_NFS) + (!laptop_mode && ((nr_writeback = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS)) > background_thresh))) - pdflush_operation(background_writeout, 0); + bdi_start_writeback(bdi, nr_writeback); } void set_page_dirty_balance(struct page *page, int page_mkwrite) @@ -610,6 +596,8 @@ void set_page_dirty_balance(struct page *page, int page_mkwrite) } } +static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0; + /** * balance_dirty_pages_ratelimited_nr - balance dirty memory state * @mapping: address_space which was dirtied @@ -627,7 +615,6 @@ void set_page_dirty_balance(struct page *page, int page_mkwrite) void balance_dirty_pages_ratelimited_nr(struct address_space *mapping, unsigned long nr_pages_dirtied) { - static DEFINE_PER_CPU(unsigned long, ratelimits) = 0; unsigned long ratelimit; unsigned long *p; @@ -640,7 +627,7 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping, * tasks in balance_dirty_pages(). Period. */ preempt_disable(); - p = &__get_cpu_var(ratelimits); + p = &__get_cpu_var(bdp_ratelimits); *p += nr_pages_dirtied; if (unlikely(*p >= ratelimit)) { *p = 0; @@ -681,153 +668,35 @@ void throttle_vm_writeout(gfp_t gfp_mask) } } -/* - * writeback at least _min_pages, and keep writing until the amount of dirty - * memory is less than the background threshold, or until we're all clean. - */ -static void background_writeout(unsigned long _min_pages) -{ - long min_pages = _min_pages; - struct writeback_control wbc = { - .bdi = NULL, - .sync_mode = WB_SYNC_NONE, - .older_than_this = NULL, - .nr_to_write = 0, - .nonblocking = 1, - .range_cyclic = 1, - }; - - for ( ; ; ) { - unsigned long background_thresh; - unsigned long dirty_thresh; - - get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL); - if (global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS) < background_thresh - && min_pages <= 0) - break; - wbc.more_io = 0; - wbc.encountered_congestion = 0; - wbc.nr_to_write = MAX_WRITEBACK_PAGES; - wbc.pages_skipped = 0; - writeback_inodes(&wbc); - min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; - if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) { - /* Wrote less than expected */ - if (wbc.encountered_congestion || wbc.more_io) - congestion_wait(BLK_RW_ASYNC, HZ/10); - else - break; - } - } -} - -/* - * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back - * the whole world. Returns 0 if a pdflush thread was dispatched. Returns - * -1 if all pdflush threads were busy. - */ -int wakeup_pdflush(long nr_pages) -{ - if (nr_pages == 0) - nr_pages = global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS); - return pdflush_operation(background_writeout, nr_pages); -} - -static void wb_timer_fn(unsigned long unused); static void laptop_timer_fn(unsigned long unused); -static DEFINE_TIMER(wb_timer, wb_timer_fn, 0, 0); static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0); /* - * Periodic writeback of "old" data. - * - * Define "old": the first time one of an inode's pages is dirtied, we mark the - * dirtying-time in the inode's address_space. So this periodic writeback code - * just walks the superblock inode list, writing back any inodes which are - * older than a specific point in time. - * - * Try to run once per dirty_writeback_interval. But if a writeback event - * takes longer than a dirty_writeback_interval interval, then leave a - * one-second gap. - * - * older_than_this takes precedence over nr_to_write. So we'll only write back - * all dirty pages if they are all attached to "old" mappings. - */ -static void wb_kupdate(unsigned long arg) -{ - unsigned long oldest_jif; - unsigned long start_jif; - unsigned long next_jif; - long nr_to_write; - struct writeback_control wbc = { - .bdi = NULL, - .sync_mode = WB_SYNC_NONE, - .older_than_this = &oldest_jif, - .nr_to_write = 0, - .nonblocking = 1, - .for_kupdate = 1, - .range_cyclic = 1, - }; - - sync_supers(); - - oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); - start_jif = jiffies; - next_jif = start_jif + msecs_to_jiffies(dirty_writeback_interval * 10); - nr_to_write = global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS) + - (inodes_stat.nr_inodes - inodes_stat.nr_unused); - while (nr_to_write > 0) { - wbc.more_io = 0; - wbc.encountered_congestion = 0; - wbc.nr_to_write = MAX_WRITEBACK_PAGES; - writeback_inodes(&wbc); - if (wbc.nr_to_write > 0) { - if (wbc.encountered_congestion || wbc.more_io) - congestion_wait(BLK_RW_ASYNC, HZ/10); - else - break; /* All the old data is written */ - } - nr_to_write -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; - } - if (time_before(next_jif, jiffies + HZ)) - next_jif = jiffies + HZ; - if (dirty_writeback_interval) - mod_timer(&wb_timer, next_jif); -} - -/* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ int dirty_writeback_centisecs_handler(ctl_table *table, int write, struct file *file, void __user *buffer, size_t *length, loff_t *ppos) { proc_dointvec(table, write, file, buffer, length, ppos); - if (dirty_writeback_interval) - mod_timer(&wb_timer, jiffies + - msecs_to_jiffies(dirty_writeback_interval * 10)); - else - del_timer(&wb_timer); return 0; } -static void wb_timer_fn(unsigned long unused) +static void do_laptop_sync(struct work_struct *work) { - if (pdflush_operation(wb_kupdate, 0) < 0) - mod_timer(&wb_timer, jiffies + HZ); /* delay 1 second */ -} - -static void laptop_flush(unsigned long unused) -{ - sys_sync(); + wakeup_flusher_threads(0); + kfree(work); } static void laptop_timer_fn(unsigned long unused) { - pdflush_operation(laptop_flush, 0); + struct work_struct *work; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); + if (work) { + INIT_WORK(work, do_laptop_sync); + schedule_work(work); + } } /* @@ -910,8 +779,6 @@ void __init page_writeback_init(void) { int shift; - mod_timer(&wb_timer, - jiffies + msecs_to_jiffies(dirty_writeback_interval * 10)); writeback_set_ratelimit(); register_cpu_notifier(&ratelimit_nb); @@ -1145,12 +1012,10 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc) if (wbc->nr_to_write <= 0) return 0; - wbc->for_writepages = 1; if (mapping->a_ops->writepages) ret = mapping->a_ops->writepages(mapping, wbc); else ret = generic_writepages(mapping, wbc); - wbc->for_writepages = 0; return ret; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5cc986eb9f6f..a0de15f46987 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -817,13 +817,15 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) * agressive about taking ownership of free pages */ if (unlikely(current_order >= (pageblock_order >> 1)) || - start_migratetype == MIGRATE_RECLAIMABLE) { + start_migratetype == MIGRATE_RECLAIMABLE || + page_group_by_mobility_disabled) { unsigned long pages; pages = move_freepages_block(zone, page, start_migratetype); /* Claim the whole block if over half of it is free */ - if (pages >= (1 << (pageblock_order-1))) + if (pages >= (1 << (pageblock_order-1)) || + page_group_by_mobility_disabled) set_pageblock_migratetype(page, start_migratetype); diff --git a/mm/pdflush.c b/mm/pdflush.c deleted file mode 100644 index 235ac440c44e..000000000000 --- a/mm/pdflush.c +++ /dev/null @@ -1,269 +0,0 @@ -/* - * mm/pdflush.c - worker threads for writing back filesystem data - * - * Copyright (C) 2002, Linus Torvalds. - * - * 09Apr2002 Andrew Morton - * Initial version - * 29Feb2004 kaos@sgi.com - * Move worker thread creation to kthread to avoid chewing - * up stack space with nested calls to kernel_thread. - */ - -#include <linux/sched.h> -#include <linux/list.h> -#include <linux/signal.h> -#include <linux/spinlock.h> -#include <linux/gfp.h> -#include <linux/init.h> -#include <linux/module.h> -#include <linux/fs.h> /* Needed by writeback.h */ -#include <linux/writeback.h> /* Prototypes pdflush_operation() */ -#include <linux/kthread.h> -#include <linux/cpuset.h> -#include <linux/freezer.h> - - -/* - * Minimum and maximum number of pdflush instances - */ -#define MIN_PDFLUSH_THREADS 2 -#define MAX_PDFLUSH_THREADS 8 - -static void start_one_pdflush_thread(void); - - -/* - * The pdflush threads are worker threads for writing back dirty data. - * Ideally, we'd like one thread per active disk spindle. But the disk - * topology is very hard to divine at this level. Instead, we take - * care in various places to prevent more than one pdflush thread from - * performing writeback against a single filesystem. pdflush threads - * have the PF_FLUSHER flag set in current->flags to aid in this. - */ - -/* - * All the pdflush threads. Protected by pdflush_lock - */ -static LIST_HEAD(pdflush_list); -static DEFINE_SPINLOCK(pdflush_lock); - -/* - * The count of currently-running pdflush threads. Protected - * by pdflush_lock. - * - * Readable by sysctl, but not writable. Published to userspace at - * /proc/sys/vm/nr_pdflush_threads. - */ -int nr_pdflush_threads = 0; - -/* - * The time at which the pdflush thread pool last went empty - */ -static unsigned long last_empty_jifs; - -/* - * The pdflush thread. - * - * Thread pool management algorithm: - * - * - The minimum and maximum number of pdflush instances are bound - * by MIN_PDFLUSH_THREADS and MAX_PDFLUSH_THREADS. - * - * - If there have been no idle pdflush instances for 1 second, create - * a new one. - * - * - If the least-recently-went-to-sleep pdflush thread has been asleep - * for more than one second, terminate a thread. - */ - -/* - * A structure for passing work to a pdflush thread. Also for passing - * state information between pdflush threads. Protected by pdflush_lock. - */ -struct pdflush_work { - struct task_struct *who; /* The thread */ - void (*fn)(unsigned long); /* A callback function */ - unsigned long arg0; /* An argument to the callback */ - struct list_head list; /* On pdflush_list, when idle */ - unsigned long when_i_went_to_sleep; -}; - -static int __pdflush(struct pdflush_work *my_work) -{ - current->flags |= PF_FLUSHER | PF_SWAPWRITE; - set_freezable(); - my_work->fn = NULL; - my_work->who = current; - INIT_LIST_HEAD(&my_work->list); - - spin_lock_irq(&pdflush_lock); - for ( ; ; ) { - struct pdflush_work *pdf; - - set_current_state(TASK_INTERRUPTIBLE); - list_move(&my_work->list, &pdflush_list); - my_work->when_i_went_to_sleep = jiffies; - spin_unlock_irq(&pdflush_lock); - schedule(); - try_to_freeze(); - spin_lock_irq(&pdflush_lock); - if (!list_empty(&my_work->list)) { - /* - * Someone woke us up, but without removing our control - * structure from the global list. swsusp will do this - * in try_to_freeze()->refrigerator(). Handle it. - */ - my_work->fn = NULL; - continue; - } - if (my_work->fn == NULL) { - printk("pdflush: bogus wakeup\n"); - continue; - } - spin_unlock_irq(&pdflush_lock); - - (*my_work->fn)(my_work->arg0); - - spin_lock_irq(&pdflush_lock); - - /* - * Thread creation: For how long have there been zero - * available threads? - * - * To throttle creation, we reset last_empty_jifs. - */ - if (time_after(jiffies, last_empty_jifs + 1 * HZ)) { - if (list_empty(&pdflush_list)) { - if (nr_pdflush_threads < MAX_PDFLUSH_THREADS) { - last_empty_jifs = jiffies; - nr_pdflush_threads++; - spin_unlock_irq(&pdflush_lock); - start_one_pdflush_thread(); - spin_lock_irq(&pdflush_lock); - } - } - } - - my_work->fn = NULL; - - /* - * Thread destruction: For how long has the sleepiest - * thread slept? - */ - if (list_empty(&pdflush_list)) - continue; - if (nr_pdflush_threads <= MIN_PDFLUSH_THREADS) - continue; - pdf = list_entry(pdflush_list.prev, struct pdflush_work, list); - if (time_after(jiffies, pdf->when_i_went_to_sleep + 1 * HZ)) { - /* Limit exit rate */ - pdf->when_i_went_to_sleep = jiffies; - break; /* exeunt */ - } - } - nr_pdflush_threads--; - spin_unlock_irq(&pdflush_lock); - return 0; -} - -/* - * Of course, my_work wants to be just a local in __pdflush(). It is - * separated out in this manner to hopefully prevent the compiler from - * performing unfortunate optimisations against the auto variables. Because - * these are visible to other tasks and CPUs. (No problem has actually - * been observed. This is just paranoia). - */ -static int pdflush(void *dummy) -{ - struct pdflush_work my_work; - cpumask_var_t cpus_allowed; - - /* - * Since the caller doesn't even check kthread_run() worked, let's not - * freak out too much if this fails. - */ - if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { - printk(KERN_WARNING "pdflush failed to allocate cpumask\n"); - return 0; - } - - /* - * pdflush can spend a lot of time doing encryption via dm-crypt. We - * don't want to do that at keventd's priority. - */ - set_user_nice(current, 0); - - /* - * Some configs put our parent kthread in a limited cpuset, - * which kthread() overrides, forcing cpus_allowed == cpu_all_mask. - * Our needs are more modest - cut back to our cpusets cpus_allowed. - * This is needed as pdflush's are dynamically created and destroyed. - * The boottime pdflush's are easily placed w/o these 2 lines. - */ - cpuset_cpus_allowed(current, cpus_allowed); - set_cpus_allowed_ptr(current, cpus_allowed); - free_cpumask_var(cpus_allowed); - - return __pdflush(&my_work); -} - -/* - * Attempt to wake up a pdflush thread, and get it to do some work for you. - * Returns zero if it indeed managed to find a worker thread, and passed your - * payload to it. - */ -int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0) -{ - unsigned long flags; - int ret = 0; - - BUG_ON(fn == NULL); /* Hard to diagnose if it's deferred */ - - spin_lock_irqsave(&pdflush_lock, flags); - if (list_empty(&pdflush_list)) { - ret = -1; - } else { - struct pdflush_work *pdf; - - pdf = list_entry(pdflush_list.next, struct pdflush_work, list); - list_del_init(&pdf->list); - if (list_empty(&pdflush_list)) - last_empty_jifs = jiffies; - pdf->fn = fn; - pdf->arg0 = arg0; - wake_up_process(pdf->who); - } - spin_unlock_irqrestore(&pdflush_lock, flags); - - return ret; -} - -static void start_one_pdflush_thread(void) -{ - struct task_struct *k; - - k = kthread_run(pdflush, NULL, "pdflush"); - if (unlikely(IS_ERR(k))) { - spin_lock_irq(&pdflush_lock); - nr_pdflush_threads--; - spin_unlock_irq(&pdflush_lock); - } -} - -static int __init pdflush_init(void) -{ - int i; - - /* - * Pre-set nr_pdflush_threads... If we fail to create, - * the count will be decremented. - */ - nr_pdflush_threads = MIN_PDFLUSH_THREADS; - - for (i = 0; i < MIN_PDFLUSH_THREADS; i++) - start_one_pdflush_thread(); - return 0; -} - -module_init(pdflush_init); diff --git a/mm/percpu.c b/mm/percpu.c index 5fe37842e0ea..43d8cacfdaa5 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -8,12 +8,13 @@ * * This is percpu allocator which can handle both static and dynamic * areas. Percpu areas are allocated in chunks in vmalloc area. Each - * chunk is consisted of nr_cpu_ids units and the first chunk is used - * for static percpu variables in the kernel image (special boot time - * alloc/init handling necessary as these areas need to be brought up - * before allocation services are running). Unit grows as necessary - * and all units grow or shrink in unison. When a chunk is filled up, - * another chunk is allocated. ie. in vmalloc area + * chunk is consisted of boot-time determined number of units and the + * first chunk is used for static percpu variables in the kernel image + * (special boot time alloc/init handling necessary as these areas + * need to be brought up before allocation services are running). + * Unit grows as necessary and all units grow or shrink in unison. + * When a chunk is filled up, another chunk is allocated. ie. in + * vmalloc area * * c0 c1 c2 * ------------------- ------------------- ------------ @@ -22,11 +23,13 @@ * * Allocation is done in offset-size areas of single unit space. Ie, * an area of 512 bytes at 6k in c1 occupies 512 bytes at 6k of c1:u0, - * c1:u1, c1:u2 and c1:u3. Percpu access can be done by configuring - * percpu base registers pcpu_unit_size apart. + * c1:u1, c1:u2 and c1:u3. On UMA, units corresponds directly to + * cpus. On NUMA, the mapping can be non-linear and even sparse. + * Percpu access can be done by configuring percpu base registers + * according to cpu to unit mapping and pcpu_unit_size. * - * There are usually many small percpu allocations many of them as - * small as 4 bytes. The allocator organizes chunks into lists + * There are usually many small percpu allocations many of them being + * as small as 4 bytes. The allocator organizes chunks into lists * according to free size and tries to allocate from the fullest one. * Each chunk keeps the maximum contiguous area size hint which is * guaranteed to be eqaul to or larger than the maximum contiguous @@ -43,7 +46,7 @@ * * To use this allocator, arch code should do the followings. * - * - define CONFIG_HAVE_DYNAMIC_PER_CPU_AREA + * - drop CONFIG_HAVE_LEGACY_PER_CPU_AREA * * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate * regular address to percpu pointer and back if they need to be @@ -55,7 +58,9 @@ #include <linux/bitmap.h> #include <linux/bootmem.h> +#include <linux/err.h> #include <linux/list.h> +#include <linux/log2.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/mutex.h> @@ -89,25 +94,38 @@ struct pcpu_chunk { struct list_head list; /* linked to pcpu_slot lists */ int free_size; /* free bytes in the chunk */ int contig_hint; /* max contiguous size hint */ - struct vm_struct *vm; /* mapped vmalloc region */ + void *base_addr; /* base address of this chunk */ int map_used; /* # of map entries used */ int map_alloc; /* # of map entries allocated */ int *map; /* allocation map */ + struct vm_struct **vms; /* mapped vmalloc regions */ bool immutable; /* no [de]population allowed */ - struct page **page; /* points to page array */ - struct page *page_ar[]; /* #cpus * UNIT_PAGES */ + unsigned long populated[]; /* populated bitmap */ }; static int pcpu_unit_pages __read_mostly; static int pcpu_unit_size __read_mostly; -static int pcpu_chunk_size __read_mostly; +static int pcpu_nr_units __read_mostly; +static int pcpu_atom_size __read_mostly; static int pcpu_nr_slots __read_mostly; static size_t pcpu_chunk_struct_size __read_mostly; +/* cpus with the lowest and highest unit numbers */ +static unsigned int pcpu_first_unit_cpu __read_mostly; +static unsigned int pcpu_last_unit_cpu __read_mostly; + /* the address of the first chunk which starts with the kernel static area */ void *pcpu_base_addr __read_mostly; EXPORT_SYMBOL_GPL(pcpu_base_addr); +static const int *pcpu_unit_map __read_mostly; /* cpu -> unit */ +const unsigned long *pcpu_unit_offsets __read_mostly; /* cpu -> unit offset */ + +/* group information, used for vm allocation */ +static int pcpu_nr_groups __read_mostly; +static const unsigned long *pcpu_group_offsets __read_mostly; +static const size_t *pcpu_group_sizes __read_mostly; + /* * The first chunk which always exists. Note that unlike other * chunks, this one can be allocated and mapped in several different @@ -129,9 +147,9 @@ static int pcpu_reserved_chunk_limit; * Synchronization rules. * * There are two locks - pcpu_alloc_mutex and pcpu_lock. The former - * protects allocation/reclaim paths, chunks and chunk->page arrays. - * The latter is a spinlock and protects the index data structures - - * chunk slots, chunks and area maps in chunks. + * protects allocation/reclaim paths, chunks, populated bitmap and + * vmalloc mapping. The latter is a spinlock and protects the index + * data structures - chunk slots, chunks and area maps in chunks. * * During allocation, pcpu_alloc_mutex is kept locked all the time and * pcpu_lock is grabbed and released as necessary. All actual memory @@ -178,26 +196,23 @@ static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) static int pcpu_page_idx(unsigned int cpu, int page_idx) { - return cpu * pcpu_unit_pages + page_idx; -} - -static struct page **pcpu_chunk_pagep(struct pcpu_chunk *chunk, - unsigned int cpu, int page_idx) -{ - return &chunk->page[pcpu_page_idx(cpu, page_idx)]; + return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx; } static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx) { - return (unsigned long)chunk->vm->addr + - (pcpu_page_idx(cpu, page_idx) << PAGE_SHIFT); + return (unsigned long)chunk->base_addr + pcpu_unit_offsets[cpu] + + (page_idx << PAGE_SHIFT); } -static bool pcpu_chunk_page_occupied(struct pcpu_chunk *chunk, - int page_idx) +static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) { - return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL; + /* must not be used on pre-mapped chunk */ + WARN_ON(chunk->immutable); + + return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx)); } /* set the pointer to a chunk in a page struct */ @@ -212,6 +227,34 @@ static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) return (struct pcpu_chunk *)page->index; } +static void pcpu_next_unpop(struct pcpu_chunk *chunk, int *rs, int *re, int end) +{ + *rs = find_next_zero_bit(chunk->populated, end, *rs); + *re = find_next_bit(chunk->populated, end, *rs + 1); +} + +static void pcpu_next_pop(struct pcpu_chunk *chunk, int *rs, int *re, int end) +{ + *rs = find_next_bit(chunk->populated, end, *rs); + *re = find_next_zero_bit(chunk->populated, end, *rs + 1); +} + +/* + * (Un)populated page region iterators. Iterate over (un)populated + * page regions betwen @start and @end in @chunk. @rs and @re should + * be integer variables and will be set to start and end page index of + * the current region. + */ +#define pcpu_for_each_unpop_region(chunk, rs, re, start, end) \ + for ((rs) = (start), pcpu_next_unpop((chunk), &(rs), &(re), (end)); \ + (rs) < (re); \ + (rs) = (re) + 1, pcpu_next_unpop((chunk), &(rs), &(re), (end))) + +#define pcpu_for_each_pop_region(chunk, rs, re, start, end) \ + for ((rs) = (start), pcpu_next_pop((chunk), &(rs), &(re), (end)); \ + (rs) < (re); \ + (rs) = (re) + 1, pcpu_next_pop((chunk), &(rs), &(re), (end))) + /** * pcpu_mem_alloc - allocate memory * @size: bytes to allocate @@ -287,16 +330,24 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) */ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) { - void *first_start = pcpu_first_chunk->vm->addr; + void *first_start = pcpu_first_chunk->base_addr; /* is it in the first chunk? */ - if (addr >= first_start && addr < first_start + pcpu_chunk_size) { + if (addr >= first_start && addr < first_start + pcpu_unit_size) { /* is it in the reserved area? */ if (addr < first_start + pcpu_reserved_chunk_limit) return pcpu_reserved_chunk; return pcpu_first_chunk; } + /* + * The address is relative to unit0 which might be unused and + * thus unmapped. Offset the address to the unit space of the + * current processor before looking it up in the vmalloc + * space. Note that any possible cpu id can be used here, so + * there's no need to worry about preemption or cpu hotplug. + */ + addr += pcpu_unit_offsets[raw_smp_processor_id()]; return pcpu_get_page_chunk(vmalloc_to_page(addr)); } @@ -545,125 +596,327 @@ static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme) } /** - * pcpu_unmap - unmap pages out of a pcpu_chunk + * pcpu_get_pages_and_bitmap - get temp pages array and bitmap * @chunk: chunk of interest - * @page_start: page index of the first page to unmap - * @page_end: page index of the last page to unmap + 1 - * @flush_tlb: whether to flush tlb or not + * @bitmapp: output parameter for bitmap + * @may_alloc: may allocate the array * - * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. - * If @flush is true, vcache is flushed before unmapping and tlb - * after. + * Returns pointer to array of pointers to struct page and bitmap, + * both of which can be indexed with pcpu_page_idx(). The returned + * array is cleared to zero and *@bitmapp is copied from + * @chunk->populated. Note that there is only one array and bitmap + * and access exclusion is the caller's responsibility. + * + * CONTEXT: + * pcpu_alloc_mutex and does GFP_KERNEL allocation if @may_alloc. + * Otherwise, don't care. + * + * RETURNS: + * Pointer to temp pages array on success, NULL on failure. */ -static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end, - bool flush_tlb) +static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk, + unsigned long **bitmapp, + bool may_alloc) { - unsigned int last = nr_cpu_ids - 1; - unsigned int cpu; + static struct page **pages; + static unsigned long *bitmap; + size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]); + size_t bitmap_size = BITS_TO_LONGS(pcpu_unit_pages) * + sizeof(unsigned long); + + if (!pages || !bitmap) { + if (may_alloc && !pages) + pages = pcpu_mem_alloc(pages_size); + if (may_alloc && !bitmap) + bitmap = pcpu_mem_alloc(bitmap_size); + if (!pages || !bitmap) + return NULL; + } - /* unmap must not be done on immutable chunk */ - WARN_ON(chunk->immutable); + memset(pages, 0, pages_size); + bitmap_copy(bitmap, chunk->populated, pcpu_unit_pages); - /* - * Each flushing trial can be very expensive, issue flush on - * the whole region at once rather than doing it for each cpu. - * This could be an overkill but is more scalable. - */ - flush_cache_vunmap(pcpu_chunk_addr(chunk, 0, page_start), - pcpu_chunk_addr(chunk, last, page_end)); + *bitmapp = bitmap; + return pages; +} - for_each_possible_cpu(cpu) - unmap_kernel_range_noflush( - pcpu_chunk_addr(chunk, cpu, page_start), - (page_end - page_start) << PAGE_SHIFT); - - /* ditto as flush_cache_vunmap() */ - if (flush_tlb) - flush_tlb_kernel_range(pcpu_chunk_addr(chunk, 0, page_start), - pcpu_chunk_addr(chunk, last, page_end)); +/** + * pcpu_free_pages - free pages which were allocated for @chunk + * @chunk: chunk pages were allocated for + * @pages: array of pages to be freed, indexed by pcpu_page_idx() + * @populated: populated bitmap + * @page_start: page index of the first page to be freed + * @page_end: page index of the last page to be freed + 1 + * + * Free pages [@page_start and @page_end) in @pages for all units. + * The pages were allocated for @chunk. + */ +static void pcpu_free_pages(struct pcpu_chunk *chunk, + struct page **pages, unsigned long *populated, + int page_start, int page_end) +{ + unsigned int cpu; + int i; + + for_each_possible_cpu(cpu) { + for (i = page_start; i < page_end; i++) { + struct page *page = pages[pcpu_page_idx(cpu, i)]; + + if (page) + __free_page(page); + } + } } /** - * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk - * @chunk: chunk to depopulate - * @off: offset to the area to depopulate - * @size: size of the area to depopulate in bytes - * @flush: whether to flush cache and tlb or not - * - * For each cpu, depopulate and unmap pages [@page_start,@page_end) - * from @chunk. If @flush is true, vcache is flushed before unmapping - * and tlb after. - * - * CONTEXT: - * pcpu_alloc_mutex. + * pcpu_alloc_pages - allocates pages for @chunk + * @chunk: target chunk + * @pages: array to put the allocated pages into, indexed by pcpu_page_idx() + * @populated: populated bitmap + * @page_start: page index of the first page to be allocated + * @page_end: page index of the last page to be allocated + 1 + * + * Allocate pages [@page_start,@page_end) into @pages for all units. + * The allocation is for @chunk. Percpu core doesn't care about the + * content of @pages and will pass it verbatim to pcpu_map_pages(). */ -static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size, - bool flush) +static int pcpu_alloc_pages(struct pcpu_chunk *chunk, + struct page **pages, unsigned long *populated, + int page_start, int page_end) { - int page_start = PFN_DOWN(off); - int page_end = PFN_UP(off + size); - int unmap_start = -1; - int uninitialized_var(unmap_end); + const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD; unsigned int cpu; int i; - for (i = page_start; i < page_end; i++) { - for_each_possible_cpu(cpu) { - struct page **pagep = pcpu_chunk_pagep(chunk, cpu, i); + for_each_possible_cpu(cpu) { + for (i = page_start; i < page_end; i++) { + struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; + + *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0); + if (!*pagep) { + pcpu_free_pages(chunk, pages, populated, + page_start, page_end); + return -ENOMEM; + } + } + } + return 0; +} - if (!*pagep) - continue; +/** + * pcpu_pre_unmap_flush - flush cache prior to unmapping + * @chunk: chunk the regions to be flushed belongs to + * @page_start: page index of the first page to be flushed + * @page_end: page index of the last page to be flushed + 1 + * + * Pages in [@page_start,@page_end) of @chunk are about to be + * unmapped. Flush cache. As each flushing trial can be very + * expensive, issue flush on the whole region at once rather than + * doing it for each cpu. This could be an overkill but is more + * scalable. + */ +static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk, + int page_start, int page_end) +{ + flush_cache_vunmap( + pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start), + pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end)); +} + +static void __pcpu_unmap_pages(unsigned long addr, int nr_pages) +{ + unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT); +} - __free_page(*pagep); +/** + * pcpu_unmap_pages - unmap pages out of a pcpu_chunk + * @chunk: chunk of interest + * @pages: pages array which can be used to pass information to free + * @populated: populated bitmap + * @page_start: page index of the first page to unmap + * @page_end: page index of the last page to unmap + 1 + * + * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. + * Corresponding elements in @pages were cleared by the caller and can + * be used to carry information to pcpu_free_pages() which will be + * called after all unmaps are finished. The caller should call + * proper pre/post flush functions. + */ +static void pcpu_unmap_pages(struct pcpu_chunk *chunk, + struct page **pages, unsigned long *populated, + int page_start, int page_end) +{ + unsigned int cpu; + int i; - /* - * If it's partial depopulation, it might get - * populated or depopulated again. Mark the - * page gone. - */ - *pagep = NULL; + for_each_possible_cpu(cpu) { + for (i = page_start; i < page_end; i++) { + struct page *page; - unmap_start = unmap_start < 0 ? i : unmap_start; - unmap_end = i + 1; + page = pcpu_chunk_page(chunk, cpu, i); + WARN_ON(!page); + pages[pcpu_page_idx(cpu, i)] = page; } + __pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start), + page_end - page_start); } - if (unmap_start >= 0) - pcpu_unmap(chunk, unmap_start, unmap_end, flush); + for (i = page_start; i < page_end; i++) + __clear_bit(i, populated); +} + +/** + * pcpu_post_unmap_tlb_flush - flush TLB after unmapping + * @chunk: pcpu_chunk the regions to be flushed belong to + * @page_start: page index of the first page to be flushed + * @page_end: page index of the last page to be flushed + 1 + * + * Pages [@page_start,@page_end) of @chunk have been unmapped. Flush + * TLB for the regions. This can be skipped if the area is to be + * returned to vmalloc as vmalloc will handle TLB flushing lazily. + * + * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once + * for the whole region. + */ +static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, + int page_start, int page_end) +{ + flush_tlb_kernel_range( + pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start), + pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end)); +} + +static int __pcpu_map_pages(unsigned long addr, struct page **pages, + int nr_pages) +{ + return map_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT, + PAGE_KERNEL, pages); } /** - * pcpu_map - map pages into a pcpu_chunk + * pcpu_map_pages - map pages into a pcpu_chunk * @chunk: chunk of interest + * @pages: pages array containing pages to be mapped + * @populated: populated bitmap * @page_start: page index of the first page to map * @page_end: page index of the last page to map + 1 * - * For each cpu, map pages [@page_start,@page_end) into @chunk. - * vcache is flushed afterwards. + * For each cpu, map pages [@page_start,@page_end) into @chunk. The + * caller is responsible for calling pcpu_post_map_flush() after all + * mappings are complete. + * + * This function is responsible for setting corresponding bits in + * @chunk->populated bitmap and whatever is necessary for reverse + * lookup (addr -> chunk). */ -static int pcpu_map(struct pcpu_chunk *chunk, int page_start, int page_end) +static int pcpu_map_pages(struct pcpu_chunk *chunk, + struct page **pages, unsigned long *populated, + int page_start, int page_end) { - unsigned int last = nr_cpu_ids - 1; - unsigned int cpu; - int err; - - /* map must not be done on immutable chunk */ - WARN_ON(chunk->immutable); + unsigned int cpu, tcpu; + int i, err; for_each_possible_cpu(cpu) { - err = map_kernel_range_noflush( - pcpu_chunk_addr(chunk, cpu, page_start), - (page_end - page_start) << PAGE_SHIFT, - PAGE_KERNEL, - pcpu_chunk_pagep(chunk, cpu, page_start)); + err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start), + &pages[pcpu_page_idx(cpu, page_start)], + page_end - page_start); if (err < 0) - return err; + goto err; + } + + /* mapping successful, link chunk and mark populated */ + for (i = page_start; i < page_end; i++) { + for_each_possible_cpu(cpu) + pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)], + chunk); + __set_bit(i, populated); } - /* flush at once, please read comments in pcpu_unmap() */ - flush_cache_vmap(pcpu_chunk_addr(chunk, 0, page_start), - pcpu_chunk_addr(chunk, last, page_end)); return 0; + +err: + for_each_possible_cpu(tcpu) { + if (tcpu == cpu) + break; + __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), + page_end - page_start); + } + return err; +} + +/** + * pcpu_post_map_flush - flush cache after mapping + * @chunk: pcpu_chunk the regions to be flushed belong to + * @page_start: page index of the first page to be flushed + * @page_end: page index of the last page to be flushed + 1 + * + * Pages [@page_start,@page_end) of @chunk have been mapped. Flush + * cache. + * + * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once + * for the whole region. + */ +static void pcpu_post_map_flush(struct pcpu_chunk *chunk, + int page_start, int page_end) +{ + flush_cache_vmap( + pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start), + pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end)); +} + +/** + * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk + * @chunk: chunk to depopulate + * @off: offset to the area to depopulate + * @size: size of the area to depopulate in bytes + * @flush: whether to flush cache and tlb or not + * + * For each cpu, depopulate and unmap pages [@page_start,@page_end) + * from @chunk. If @flush is true, vcache is flushed before unmapping + * and tlb after. + * + * CONTEXT: + * pcpu_alloc_mutex. + */ +static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size) +{ + int page_start = PFN_DOWN(off); + int page_end = PFN_UP(off + size); + struct page **pages; + unsigned long *populated; + int rs, re; + + /* quick path, check whether it's empty already */ + pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) { + if (rs == page_start && re == page_end) + return; + break; + } + + /* immutable chunks can't be depopulated */ + WARN_ON(chunk->immutable); + + /* + * If control reaches here, there must have been at least one + * successful population attempt so the temp pages array must + * be available now. + */ + pages = pcpu_get_pages_and_bitmap(chunk, &populated, false); + BUG_ON(!pages); + + /* unmap and free */ + pcpu_pre_unmap_flush(chunk, page_start, page_end); + + pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end) + pcpu_unmap_pages(chunk, pages, populated, rs, re); + + /* no need to flush tlb, vmalloc will handle it lazily */ + + pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end) + pcpu_free_pages(chunk, pages, populated, rs, re); + + /* commit new bitmap */ + bitmap_copy(chunk->populated, populated, pcpu_unit_pages); } /** @@ -680,58 +933,68 @@ static int pcpu_map(struct pcpu_chunk *chunk, int page_start, int page_end) */ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size) { - const gfp_t alloc_mask = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD; int page_start = PFN_DOWN(off); int page_end = PFN_UP(off + size); - int map_start = -1; - int uninitialized_var(map_end); + int free_end = page_start, unmap_end = page_start; + struct page **pages; + unsigned long *populated; unsigned int cpu; - int i; + int rs, re, rc; - for (i = page_start; i < page_end; i++) { - if (pcpu_chunk_page_occupied(chunk, i)) { - if (map_start >= 0) { - if (pcpu_map(chunk, map_start, map_end)) - goto err; - map_start = -1; - } - continue; - } + /* quick path, check whether all pages are already there */ + pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end) { + if (rs == page_start && re == page_end) + goto clear; + break; + } - map_start = map_start < 0 ? i : map_start; - map_end = i + 1; + /* need to allocate and map pages, this chunk can't be immutable */ + WARN_ON(chunk->immutable); - for_each_possible_cpu(cpu) { - struct page **pagep = pcpu_chunk_pagep(chunk, cpu, i); + pages = pcpu_get_pages_and_bitmap(chunk, &populated, true); + if (!pages) + return -ENOMEM; - *pagep = alloc_pages_node(cpu_to_node(cpu), - alloc_mask, 0); - if (!*pagep) - goto err; - pcpu_set_page_chunk(*pagep, chunk); - } + /* alloc and map */ + pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) { + rc = pcpu_alloc_pages(chunk, pages, populated, rs, re); + if (rc) + goto err_free; + free_end = re; } - if (map_start >= 0 && pcpu_map(chunk, map_start, map_end)) - goto err; + pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) { + rc = pcpu_map_pages(chunk, pages, populated, rs, re); + if (rc) + goto err_unmap; + unmap_end = re; + } + pcpu_post_map_flush(chunk, page_start, page_end); + /* commit new bitmap */ + bitmap_copy(chunk->populated, populated, pcpu_unit_pages); +clear: for_each_possible_cpu(cpu) - memset(chunk->vm->addr + cpu * pcpu_unit_size + off, 0, - size); - + memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size); return 0; -err: - /* likely under heavy memory pressure, give memory back */ - pcpu_depopulate_chunk(chunk, off, size, true); - return -ENOMEM; + +err_unmap: + pcpu_pre_unmap_flush(chunk, page_start, unmap_end); + pcpu_for_each_unpop_region(chunk, rs, re, page_start, unmap_end) + pcpu_unmap_pages(chunk, pages, populated, rs, re); + pcpu_post_unmap_tlb_flush(chunk, page_start, unmap_end); +err_free: + pcpu_for_each_unpop_region(chunk, rs, re, page_start, free_end) + pcpu_free_pages(chunk, pages, populated, rs, re); + return rc; } static void free_pcpu_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; - if (chunk->vm) - free_vm_area(chunk->vm); + if (chunk->vms) + pcpu_free_vm_areas(chunk->vms, pcpu_nr_groups); pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0])); kfree(chunk); } @@ -747,10 +1010,11 @@ static struct pcpu_chunk *alloc_pcpu_chunk(void) chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0])); chunk->map_alloc = PCPU_DFL_MAP_ALLOC; chunk->map[chunk->map_used++] = pcpu_unit_size; - chunk->page = chunk->page_ar; - chunk->vm = get_vm_area(pcpu_chunk_size, VM_ALLOC); - if (!chunk->vm) { + chunk->vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes, + pcpu_nr_groups, pcpu_atom_size, + GFP_KERNEL); + if (!chunk->vms) { free_pcpu_chunk(chunk); return NULL; } @@ -758,6 +1022,7 @@ static struct pcpu_chunk *alloc_pcpu_chunk(void) INIT_LIST_HEAD(&chunk->list); chunk->free_size = pcpu_unit_size; chunk->contig_hint = pcpu_unit_size; + chunk->base_addr = chunk->vms[0]->addr - pcpu_group_offsets[0]; return chunk; } @@ -847,7 +1112,8 @@ area_found: mutex_unlock(&pcpu_alloc_mutex); - return __addr_to_pcpu_ptr(chunk->vm->addr + off); + /* return address relative to base address */ + return __addr_to_pcpu_ptr(chunk->base_addr + off); fail_unlock: spin_unlock_irq(&pcpu_lock); @@ -925,12 +1191,13 @@ static void pcpu_reclaim(struct work_struct *work) } spin_unlock_irq(&pcpu_lock); - mutex_unlock(&pcpu_alloc_mutex); list_for_each_entry_safe(chunk, next, &todo, list) { - pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size, false); + pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size); free_pcpu_chunk(chunk); } + + mutex_unlock(&pcpu_alloc_mutex); } /** @@ -955,7 +1222,7 @@ void free_percpu(void *ptr) spin_lock_irqsave(&pcpu_lock, flags); chunk = pcpu_chunk_addr_search(addr); - off = addr - chunk->vm->addr; + off = addr - chunk->base_addr; pcpu_free_area(chunk, off); @@ -974,30 +1241,295 @@ void free_percpu(void *ptr) } EXPORT_SYMBOL_GPL(free_percpu); +static inline size_t pcpu_calc_fc_sizes(size_t static_size, + size_t reserved_size, + ssize_t *dyn_sizep) +{ + size_t size_sum; + + size_sum = PFN_ALIGN(static_size + reserved_size + + (*dyn_sizep >= 0 ? *dyn_sizep : 0)); + if (*dyn_sizep != 0) + *dyn_sizep = size_sum - static_size - reserved_size; + + return size_sum; +} + /** - * pcpu_setup_first_chunk - initialize the first percpu chunk - * @get_page_fn: callback to fetch page pointer - * @static_size: the size of static percpu area in bytes + * pcpu_alloc_alloc_info - allocate percpu allocation info + * @nr_groups: the number of groups + * @nr_units: the number of units + * + * Allocate ai which is large enough for @nr_groups groups containing + * @nr_units units. The returned ai's groups[0].cpu_map points to the + * cpu_map array which is long enough for @nr_units and filled with + * NR_CPUS. It's the caller's responsibility to initialize cpu_map + * pointer of other groups. + * + * RETURNS: + * Pointer to the allocated pcpu_alloc_info on success, NULL on + * failure. + */ +struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, + int nr_units) +{ + struct pcpu_alloc_info *ai; + size_t base_size, ai_size; + void *ptr; + int unit; + + base_size = ALIGN(sizeof(*ai) + nr_groups * sizeof(ai->groups[0]), + __alignof__(ai->groups[0].cpu_map[0])); + ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]); + + ptr = alloc_bootmem_nopanic(PFN_ALIGN(ai_size)); + if (!ptr) + return NULL; + ai = ptr; + ptr += base_size; + + ai->groups[0].cpu_map = ptr; + + for (unit = 0; unit < nr_units; unit++) + ai->groups[0].cpu_map[unit] = NR_CPUS; + + ai->nr_groups = nr_groups; + ai->__ai_size = PFN_ALIGN(ai_size); + + return ai; +} + +/** + * pcpu_free_alloc_info - free percpu allocation info + * @ai: pcpu_alloc_info to free + * + * Free @ai which was allocated by pcpu_alloc_alloc_info(). + */ +void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) +{ + free_bootmem(__pa(ai), ai->__ai_size); +} + +/** + * pcpu_build_alloc_info - build alloc_info considering distances between CPUs * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: free size for dynamic allocation in bytes, -1 for auto - * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto - * @base_addr: mapped address, NULL for auto - * @populate_pte_fn: callback to allocate pagetable, NULL if unnecessary + * @atom_size: allocation atom size + * @cpu_distance_fn: callback to determine distance between cpus, optional + * + * This function determines grouping of units, their mappings to cpus + * and other parameters considering needed percpu size, allocation + * atom size and distances between CPUs. + * + * Groups are always mutliples of atom size and CPUs which are of + * LOCAL_DISTANCE both ways are grouped together and share space for + * units in the same group. The returned configuration is guaranteed + * to have CPUs on different nodes on different groups and >=75% usage + * of allocated virtual address space. + * + * RETURNS: + * On success, pointer to the new allocation_info is returned. On + * failure, ERR_PTR value is returned. + */ +struct pcpu_alloc_info * __init pcpu_build_alloc_info( + size_t reserved_size, ssize_t dyn_size, + size_t atom_size, + pcpu_fc_cpu_distance_fn_t cpu_distance_fn) +{ + static int group_map[NR_CPUS] __initdata; + static int group_cnt[NR_CPUS] __initdata; + const size_t static_size = __per_cpu_end - __per_cpu_start; + int group_cnt_max = 0, nr_groups = 1, nr_units = 0; + size_t size_sum, min_unit_size, alloc_size; + int upa, max_upa, uninitialized_var(best_upa); /* units_per_alloc */ + int last_allocs, group, unit; + unsigned int cpu, tcpu; + struct pcpu_alloc_info *ai; + unsigned int *cpu_map; + + /* + * Determine min_unit_size, alloc_size and max_upa such that + * alloc_size is multiple of atom_size and is the smallest + * which can accomodate 4k aligned segments which are equal to + * or larger than min_unit_size. + */ + size_sum = pcpu_calc_fc_sizes(static_size, reserved_size, &dyn_size); + min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE); + + alloc_size = roundup(min_unit_size, atom_size); + upa = alloc_size / min_unit_size; + while (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK)) + upa--; + max_upa = upa; + + /* group cpus according to their proximity */ + for_each_possible_cpu(cpu) { + group = 0; + next_group: + for_each_possible_cpu(tcpu) { + if (cpu == tcpu) + break; + if (group_map[tcpu] == group && cpu_distance_fn && + (cpu_distance_fn(cpu, tcpu) > LOCAL_DISTANCE || + cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) { + group++; + nr_groups = max(nr_groups, group + 1); + goto next_group; + } + } + group_map[cpu] = group; + group_cnt[group]++; + group_cnt_max = max(group_cnt_max, group_cnt[group]); + } + + /* + * Expand unit size until address space usage goes over 75% + * and then as much as possible without using more address + * space. + */ + last_allocs = INT_MAX; + for (upa = max_upa; upa; upa--) { + int allocs = 0, wasted = 0; + + if (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK)) + continue; + + for (group = 0; group < nr_groups; group++) { + int this_allocs = DIV_ROUND_UP(group_cnt[group], upa); + allocs += this_allocs; + wasted += this_allocs * upa - group_cnt[group]; + } + + /* + * Don't accept if wastage is over 25%. The + * greater-than comparison ensures upa==1 always + * passes the following check. + */ + if (wasted > num_possible_cpus() / 3) + continue; + + /* and then don't consume more memory */ + if (allocs > last_allocs) + break; + last_allocs = allocs; + best_upa = upa; + } + upa = best_upa; + + /* allocate and fill alloc_info */ + for (group = 0; group < nr_groups; group++) + nr_units += roundup(group_cnt[group], upa); + + ai = pcpu_alloc_alloc_info(nr_groups, nr_units); + if (!ai) + return ERR_PTR(-ENOMEM); + cpu_map = ai->groups[0].cpu_map; + + for (group = 0; group < nr_groups; group++) { + ai->groups[group].cpu_map = cpu_map; + cpu_map += roundup(group_cnt[group], upa); + } + + ai->static_size = static_size; + ai->reserved_size = reserved_size; + ai->dyn_size = dyn_size; + ai->unit_size = alloc_size / upa; + ai->atom_size = atom_size; + ai->alloc_size = alloc_size; + + for (group = 0, unit = 0; group_cnt[group]; group++) { + struct pcpu_group_info *gi = &ai->groups[group]; + + /* + * Initialize base_offset as if all groups are located + * back-to-back. The caller should update this to + * reflect actual allocation. + */ + gi->base_offset = unit * ai->unit_size; + + for_each_possible_cpu(cpu) + if (group_map[cpu] == group) + gi->cpu_map[gi->nr_units++] = cpu; + gi->nr_units = roundup(gi->nr_units, upa); + unit += gi->nr_units; + } + BUG_ON(unit != nr_units); + + return ai; +} + +/** + * pcpu_dump_alloc_info - print out information about pcpu_alloc_info + * @lvl: loglevel + * @ai: allocation info to dump + * + * Print out information about @ai using loglevel @lvl. + */ +static void pcpu_dump_alloc_info(const char *lvl, + const struct pcpu_alloc_info *ai) +{ + int group_width = 1, cpu_width = 1, width; + char empty_str[] = "--------"; + int alloc = 0, alloc_end = 0; + int group, v; + int upa, apl; /* units per alloc, allocs per line */ + + v = ai->nr_groups; + while (v /= 10) + group_width++; + + v = num_possible_cpus(); + while (v /= 10) + cpu_width++; + empty_str[min_t(int, cpu_width, sizeof(empty_str) - 1)] = '\0'; + + upa = ai->alloc_size / ai->unit_size; + width = upa * (cpu_width + 1) + group_width + 3; + apl = rounddown_pow_of_two(max(60 / width, 1)); + + printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu", + lvl, ai->static_size, ai->reserved_size, ai->dyn_size, + ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size); + + for (group = 0; group < ai->nr_groups; group++) { + const struct pcpu_group_info *gi = &ai->groups[group]; + int unit = 0, unit_end = 0; + + BUG_ON(gi->nr_units % upa); + for (alloc_end += gi->nr_units / upa; + alloc < alloc_end; alloc++) { + if (!(alloc % apl)) { + printk("\n"); + printk("%spcpu-alloc: ", lvl); + } + printk("[%0*d] ", group_width, group); + + for (unit_end += upa; unit < unit_end; unit++) + if (gi->cpu_map[unit] != NR_CPUS) + printk("%0*d ", cpu_width, + gi->cpu_map[unit]); + else + printk("%s ", empty_str); + } + } + printk("\n"); +} + +/** + * pcpu_setup_first_chunk - initialize the first percpu chunk + * @ai: pcpu_alloc_info describing how to percpu area is shaped + * @base_addr: mapped address * * Initialize the first percpu chunk which contains the kernel static * perpcu area. This function is to be called from arch percpu area - * setup path. The first two parameters are mandatory. The rest are - * optional. - * - * @get_page_fn() should return pointer to percpu page given cpu - * number and page number. It should at least return enough pages to - * cover the static area. The returned pages for static area should - * have been initialized with valid data. If @unit_size is specified, - * it can also return pages after the static area. NULL return - * indicates end of pages for the cpu. Note that @get_page_fn() must - * return the same number of pages for all cpus. - * - * @reserved_size, if non-zero, specifies the amount of bytes to + * setup path. + * + * @ai contains all information necessary to initialize the first + * chunk and prime the dynamic percpu allocator. + * + * @ai->static_size is the size of static percpu area. + * + * @ai->reserved_size, if non-zero, specifies the amount of bytes to * reserve after the static area in the first chunk. This reserves * the first chunk such that it's available only through reserved * percpu allocation. This is primarily used to serve module percpu @@ -1005,22 +1537,29 @@ EXPORT_SYMBOL_GPL(free_percpu); * limited offset range for symbol relocations to guarantee module * percpu symbols fall inside the relocatable range. * - * @dyn_size, if non-negative, determines the number of bytes - * available for dynamic allocation in the first chunk. Specifying - * non-negative value makes percpu leave alone the area beyond - * @static_size + @reserved_size + @dyn_size. + * @ai->dyn_size determines the number of bytes available for dynamic + * allocation in the first chunk. The area between @ai->static_size + + * @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused. * - * @unit_size, if non-negative, specifies unit size and must be - * aligned to PAGE_SIZE and equal to or larger than @static_size + - * @reserved_size + if non-negative, @dyn_size. + * @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE + * and equal to or larger than @ai->static_size + @ai->reserved_size + + * @ai->dyn_size. * - * Non-null @base_addr means that the caller already allocated virtual - * region for the first chunk and mapped it. percpu must not mess - * with the chunk. Note that @base_addr with 0 @unit_size or non-NULL - * @populate_pte_fn doesn't make any sense. + * @ai->atom_size is the allocation atom size and used as alignment + * for vm areas. * - * @populate_pte_fn is used to populate the pagetable. NULL means the - * caller already populated the pagetable. + * @ai->alloc_size is the allocation size and always multiple of + * @ai->atom_size. This is larger than @ai->atom_size if + * @ai->unit_size is larger than @ai->atom_size. + * + * @ai->nr_groups and @ai->groups describe virtual memory layout of + * percpu areas. Units which should be colocated are put into the + * same group. Dynamic VM areas will be allocated according to these + * groupings. If @ai->nr_groups is zero, a single group containing + * all units is assumed. + * + * The caller should have mapped the first chunk at @base_addr and + * copied static data to each unit. * * If the first chunk ends up with both reserved and dynamic areas, it * is served by two chunks - one to serve the core static and reserved @@ -1030,49 +1569,83 @@ EXPORT_SYMBOL_GPL(free_percpu); * and available for dynamic allocation like any other chunks. * * RETURNS: - * The determined pcpu_unit_size which can be used to initialize - * percpu access. + * 0 on success, -errno on failure. */ -size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, - size_t static_size, size_t reserved_size, - ssize_t dyn_size, ssize_t unit_size, - void *base_addr, - pcpu_populate_pte_fn_t populate_pte_fn) +int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, + void *base_addr) { - static struct vm_struct first_vm; static int smap[2], dmap[2]; - size_t size_sum = static_size + reserved_size + - (dyn_size >= 0 ? dyn_size : 0); + size_t dyn_size = ai->dyn_size; + size_t size_sum = ai->static_size + ai->reserved_size + dyn_size; struct pcpu_chunk *schunk, *dchunk = NULL; + unsigned long *group_offsets; + size_t *group_sizes; + unsigned long *unit_off; unsigned int cpu; - int nr_pages; - int err, i; + int *unit_map; + int group, unit, i; - /* santiy checks */ + /* sanity checks */ BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC || ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC); - BUG_ON(!static_size); - if (unit_size >= 0) { - BUG_ON(unit_size < size_sum); - BUG_ON(unit_size & ~PAGE_MASK); - BUG_ON(unit_size < PCPU_MIN_UNIT_SIZE); - } else - BUG_ON(base_addr); - BUG_ON(base_addr && populate_pte_fn); - - if (unit_size >= 0) - pcpu_unit_pages = unit_size >> PAGE_SHIFT; - else - pcpu_unit_pages = max_t(int, PCPU_MIN_UNIT_SIZE >> PAGE_SHIFT, - PFN_UP(size_sum)); + BUG_ON(ai->nr_groups <= 0); + BUG_ON(!ai->static_size); + BUG_ON(!base_addr); + BUG_ON(ai->unit_size < size_sum); + BUG_ON(ai->unit_size & ~PAGE_MASK); + BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE); + + pcpu_dump_alloc_info(KERN_DEBUG, ai); + + /* process group information and build config tables accordingly */ + group_offsets = alloc_bootmem(ai->nr_groups * sizeof(group_offsets[0])); + group_sizes = alloc_bootmem(ai->nr_groups * sizeof(group_sizes[0])); + unit_map = alloc_bootmem(nr_cpu_ids * sizeof(unit_map[0])); + unit_off = alloc_bootmem(nr_cpu_ids * sizeof(unit_off[0])); + + for (cpu = 0; cpu < nr_cpu_ids; cpu++) + unit_map[cpu] = NR_CPUS; + pcpu_first_unit_cpu = NR_CPUS; + + for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) { + const struct pcpu_group_info *gi = &ai->groups[group]; + + group_offsets[group] = gi->base_offset; + group_sizes[group] = gi->nr_units * ai->unit_size; + + for (i = 0; i < gi->nr_units; i++) { + cpu = gi->cpu_map[i]; + if (cpu == NR_CPUS) + continue; - pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; - pcpu_chunk_size = nr_cpu_ids * pcpu_unit_size; - pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) - + nr_cpu_ids * pcpu_unit_pages * sizeof(struct page *); + BUG_ON(cpu > nr_cpu_ids || !cpu_possible(cpu)); + BUG_ON(unit_map[cpu] != NR_CPUS); - if (dyn_size < 0) - dyn_size = pcpu_unit_size - static_size - reserved_size; + unit_map[cpu] = unit + i; + unit_off[cpu] = gi->base_offset + i * ai->unit_size; + + if (pcpu_first_unit_cpu == NR_CPUS) + pcpu_first_unit_cpu = cpu; + } + } + pcpu_last_unit_cpu = cpu; + pcpu_nr_units = unit; + + for_each_possible_cpu(cpu) + BUG_ON(unit_map[cpu] == NR_CPUS); + + pcpu_nr_groups = ai->nr_groups; + pcpu_group_offsets = group_offsets; + pcpu_group_sizes = group_sizes; + pcpu_unit_map = unit_map; + pcpu_unit_offsets = unit_off; + + /* determine basic parameters */ + pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT; + pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; + pcpu_atom_size = ai->atom_size; + pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) + + BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long); /* * Allocate chunk slots. The additional last slot is for @@ -1092,189 +1665,351 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, */ schunk = alloc_bootmem(pcpu_chunk_struct_size); INIT_LIST_HEAD(&schunk->list); - schunk->vm = &first_vm; + schunk->base_addr = base_addr; schunk->map = smap; schunk->map_alloc = ARRAY_SIZE(smap); - schunk->page = schunk->page_ar; + schunk->immutable = true; + bitmap_fill(schunk->populated, pcpu_unit_pages); - if (reserved_size) { - schunk->free_size = reserved_size; + if (ai->reserved_size) { + schunk->free_size = ai->reserved_size; pcpu_reserved_chunk = schunk; - pcpu_reserved_chunk_limit = static_size + reserved_size; + pcpu_reserved_chunk_limit = ai->static_size + ai->reserved_size; } else { schunk->free_size = dyn_size; dyn_size = 0; /* dynamic area covered */ } schunk->contig_hint = schunk->free_size; - schunk->map[schunk->map_used++] = -static_size; + schunk->map[schunk->map_used++] = -ai->static_size; if (schunk->free_size) schunk->map[schunk->map_used++] = schunk->free_size; /* init dynamic chunk if necessary */ if (dyn_size) { - dchunk = alloc_bootmem(sizeof(struct pcpu_chunk)); + dchunk = alloc_bootmem(pcpu_chunk_struct_size); INIT_LIST_HEAD(&dchunk->list); - dchunk->vm = &first_vm; + dchunk->base_addr = base_addr; dchunk->map = dmap; dchunk->map_alloc = ARRAY_SIZE(dmap); - dchunk->page = schunk->page_ar; /* share page map with schunk */ + dchunk->immutable = true; + bitmap_fill(dchunk->populated, pcpu_unit_pages); dchunk->contig_hint = dchunk->free_size = dyn_size; dchunk->map[dchunk->map_used++] = -pcpu_reserved_chunk_limit; dchunk->map[dchunk->map_used++] = dchunk->free_size; } - /* allocate vm address */ - first_vm.flags = VM_ALLOC; - first_vm.size = pcpu_chunk_size; - - if (!base_addr) - vm_area_register_early(&first_vm, PAGE_SIZE); - else { - /* - * Pages already mapped. No need to remap into - * vmalloc area. In this case the first chunks can't - * be mapped or unmapped by percpu and are marked - * immutable. - */ - first_vm.addr = base_addr; - schunk->immutable = true; - if (dchunk) - dchunk->immutable = true; - } - - /* assign pages */ - nr_pages = -1; - for_each_possible_cpu(cpu) { - for (i = 0; i < pcpu_unit_pages; i++) { - struct page *page = get_page_fn(cpu, i); - - if (!page) - break; - *pcpu_chunk_pagep(schunk, cpu, i) = page; - } - - BUG_ON(i < PFN_UP(static_size)); - - if (nr_pages < 0) - nr_pages = i; - else - BUG_ON(nr_pages != i); - } - - /* map them */ - if (populate_pte_fn) { - for_each_possible_cpu(cpu) - for (i = 0; i < nr_pages; i++) - populate_pte_fn(pcpu_chunk_addr(schunk, - cpu, i)); - - err = pcpu_map(schunk, 0, nr_pages); - if (err) - panic("failed to setup static percpu area, err=%d\n", - err); - } - /* link the first chunk in */ pcpu_first_chunk = dchunk ?: schunk; pcpu_chunk_relocate(pcpu_first_chunk, -1); /* we're done */ - pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0); - return pcpu_unit_size; + pcpu_base_addr = base_addr; + return 0; } -/* - * Embedding first chunk setup helper. - */ -static void *pcpue_ptr __initdata; -static size_t pcpue_size __initdata; -static size_t pcpue_unit_size __initdata; +const char *pcpu_fc_names[PCPU_FC_NR] __initdata = { + [PCPU_FC_AUTO] = "auto", + [PCPU_FC_EMBED] = "embed", + [PCPU_FC_PAGE] = "page", +}; -static struct page * __init pcpue_get_page(unsigned int cpu, int pageno) -{ - size_t off = (size_t)pageno << PAGE_SHIFT; +enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO; - if (off >= pcpue_size) - return NULL; +static int __init percpu_alloc_setup(char *str) +{ + if (0) + /* nada */; +#ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK + else if (!strcmp(str, "embed")) + pcpu_chosen_fc = PCPU_FC_EMBED; +#endif +#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK + else if (!strcmp(str, "page")) + pcpu_chosen_fc = PCPU_FC_PAGE; +#endif + else + pr_warning("PERCPU: unknown allocator %s specified\n", str); - return virt_to_page(pcpue_ptr + cpu * pcpue_unit_size + off); + return 0; } +early_param("percpu_alloc", percpu_alloc_setup); +#if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \ + !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) /** * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem - * @static_size: the size of static percpu area in bytes * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: free size for dynamic allocation in bytes, -1 for auto - * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto + * @atom_size: allocation atom size + * @cpu_distance_fn: callback to determine distance between cpus, optional + * @alloc_fn: function to allocate percpu page + * @free_fn: funtion to free percpu page * * This is a helper to ease setting up embedded first percpu chunk and * can be called where pcpu_setup_first_chunk() is expected. * * If this function is used to setup the first chunk, it is allocated - * as a contiguous area using bootmem allocator and used as-is without - * being mapped into vmalloc area. This enables the first chunk to - * piggy back on the linear physical mapping which often uses larger - * page size. + * by calling @alloc_fn and used as-is without being mapped into + * vmalloc area. Allocations are always whole multiples of @atom_size + * aligned to @atom_size. + * + * This enables the first chunk to piggy back on the linear physical + * mapping which often uses larger page size. Please note that this + * can result in very sparse cpu->unit mapping on NUMA machines thus + * requiring large vmalloc address space. Don't use this allocator if + * vmalloc space is not orders of magnitude larger than distances + * between node memory addresses (ie. 32bit NUMA machines). * * When @dyn_size is positive, dynamic area might be larger than - * specified to fill page alignment. Also, when @dyn_size is auto, - * @dyn_size does not fill the whole first chunk but only what's - * necessary for page alignment after static and reserved areas. + * specified to fill page alignment. When @dyn_size is auto, + * @dyn_size is just big enough to fill page alignment after static + * and reserved areas. * * If the needed size is smaller than the minimum or specified unit - * size, the leftover is returned to the bootmem allocator. + * size, the leftover is returned using @free_fn. * * RETURNS: - * The determined pcpu_unit_size which can be used to initialize - * percpu access on success, -errno on failure. + * 0 on success, -errno on failure. */ -ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size, - ssize_t dyn_size, ssize_t unit_size) +int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size, + size_t atom_size, + pcpu_fc_cpu_distance_fn_t cpu_distance_fn, + pcpu_fc_alloc_fn_t alloc_fn, + pcpu_fc_free_fn_t free_fn) { - size_t chunk_size; - unsigned int cpu; + void *base = (void *)ULONG_MAX; + void **areas = NULL; + struct pcpu_alloc_info *ai; + size_t size_sum, areas_size; + int group, i, rc; + + ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size, + cpu_distance_fn); + if (IS_ERR(ai)) + return PTR_ERR(ai); + + size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; + areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *)); + + areas = alloc_bootmem_nopanic(areas_size); + if (!areas) { + rc = -ENOMEM; + goto out_free; + } - /* determine parameters and allocate */ - pcpue_size = PFN_ALIGN(static_size + reserved_size + - (dyn_size >= 0 ? dyn_size : 0)); - if (dyn_size != 0) - dyn_size = pcpue_size - static_size - reserved_size; - - if (unit_size >= 0) { - BUG_ON(unit_size < pcpue_size); - pcpue_unit_size = unit_size; - } else - pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE); - - chunk_size = pcpue_unit_size * nr_cpu_ids; - - pcpue_ptr = __alloc_bootmem_nopanic(chunk_size, PAGE_SIZE, - __pa(MAX_DMA_ADDRESS)); - if (!pcpue_ptr) { - pr_warning("PERCPU: failed to allocate %zu bytes for " - "embedding\n", chunk_size); - return -ENOMEM; + /* allocate, copy and determine base address */ + for (group = 0; group < ai->nr_groups; group++) { + struct pcpu_group_info *gi = &ai->groups[group]; + unsigned int cpu = NR_CPUS; + void *ptr; + + for (i = 0; i < gi->nr_units && cpu == NR_CPUS; i++) + cpu = gi->cpu_map[i]; + BUG_ON(cpu == NR_CPUS); + + /* allocate space for the whole group */ + ptr = alloc_fn(cpu, gi->nr_units * ai->unit_size, atom_size); + if (!ptr) { + rc = -ENOMEM; + goto out_free_areas; + } + areas[group] = ptr; + + base = min(ptr, base); + + for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) { + if (gi->cpu_map[i] == NR_CPUS) { + /* unused unit, free whole */ + free_fn(ptr, ai->unit_size); + continue; + } + /* copy and return the unused part */ + memcpy(ptr, __per_cpu_load, ai->static_size); + free_fn(ptr + size_sum, ai->unit_size - size_sum); + } } - /* return the leftover and copy */ - for (cpu = 0; cpu < nr_cpu_ids; cpu++) { - void *ptr = pcpue_ptr + cpu * pcpue_unit_size; + /* base address is now known, determine group base offsets */ + for (group = 0; group < ai->nr_groups; group++) + ai->groups[group].base_offset = areas[group] - base; + + pr_info("PERCPU: Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n", + PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size, + ai->dyn_size, ai->unit_size); + + rc = pcpu_setup_first_chunk(ai, base); + goto out_free; + +out_free_areas: + for (group = 0; group < ai->nr_groups; group++) + free_fn(areas[group], + ai->groups[group].nr_units * ai->unit_size); +out_free: + pcpu_free_alloc_info(ai); + if (areas) + free_bootmem(__pa(areas), areas_size); + return rc; +} +#endif /* CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK || + !CONFIG_HAVE_SETUP_PER_CPU_AREA */ + +#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK +/** + * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages + * @reserved_size: the size of reserved percpu area in bytes + * @alloc_fn: function to allocate percpu page, always called with PAGE_SIZE + * @free_fn: funtion to free percpu page, always called with PAGE_SIZE + * @populate_pte_fn: function to populate pte + * + * This is a helper to ease setting up page-remapped first percpu + * chunk and can be called where pcpu_setup_first_chunk() is expected. + * + * This is the basic allocator. Static percpu area is allocated + * page-by-page into vmalloc area. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int __init pcpu_page_first_chunk(size_t reserved_size, + pcpu_fc_alloc_fn_t alloc_fn, + pcpu_fc_free_fn_t free_fn, + pcpu_fc_populate_pte_fn_t populate_pte_fn) +{ + static struct vm_struct vm; + struct pcpu_alloc_info *ai; + char psize_str[16]; + int unit_pages; + size_t pages_size; + struct page **pages; + int unit, i, j, rc; + + snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10); + + ai = pcpu_build_alloc_info(reserved_size, -1, PAGE_SIZE, NULL); + if (IS_ERR(ai)) + return PTR_ERR(ai); + BUG_ON(ai->nr_groups != 1); + BUG_ON(ai->groups[0].nr_units != num_possible_cpus()); + + unit_pages = ai->unit_size >> PAGE_SHIFT; + + /* unaligned allocations can't be freed, round up to page size */ + pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * + sizeof(pages[0])); + pages = alloc_bootmem(pages_size); + + /* allocate pages */ + j = 0; + for (unit = 0; unit < num_possible_cpus(); unit++) + for (i = 0; i < unit_pages; i++) { + unsigned int cpu = ai->groups[0].cpu_map[unit]; + void *ptr; + + ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE); + if (!ptr) { + pr_warning("PERCPU: failed to allocate %s page " + "for cpu%u\n", psize_str, cpu); + goto enomem; + } + pages[j++] = virt_to_page(ptr); + } + + /* allocate vm area, map the pages and copy static data */ + vm.flags = VM_ALLOC; + vm.size = num_possible_cpus() * ai->unit_size; + vm_area_register_early(&vm, PAGE_SIZE); + + for (unit = 0; unit < num_possible_cpus(); unit++) { + unsigned long unit_addr = + (unsigned long)vm.addr + unit * ai->unit_size; + + for (i = 0; i < unit_pages; i++) + populate_pte_fn(unit_addr + (i << PAGE_SHIFT)); + + /* pte already populated, the following shouldn't fail */ + rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages], + unit_pages); + if (rc < 0) + panic("failed to map percpu area, err=%d\n", rc); - if (cpu_possible(cpu)) { - free_bootmem(__pa(ptr + pcpue_size), - pcpue_unit_size - pcpue_size); - memcpy(ptr, __per_cpu_load, static_size); - } else - free_bootmem(__pa(ptr), pcpue_unit_size); + /* + * FIXME: Archs with virtual cache should flush local + * cache for the linear mapping here - something + * equivalent to flush_cache_vmap() on the local cpu. + * flush_cache_vmap() can't be used as most supporting + * data structures are not set up yet. + */ + + /* copy static data */ + memcpy((void *)unit_addr, __per_cpu_load, ai->static_size); } /* we're ready, commit */ - pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n", - pcpue_size >> PAGE_SHIFT, pcpue_ptr, static_size); + pr_info("PERCPU: %d %s pages/cpu @%p s%zu r%zu d%zu\n", + unit_pages, psize_str, vm.addr, ai->static_size, + ai->reserved_size, ai->dyn_size); + + rc = pcpu_setup_first_chunk(ai, vm.addr); + goto out_free_ar; + +enomem: + while (--j >= 0) + free_fn(page_address(pages[j]), PAGE_SIZE); + rc = -ENOMEM; +out_free_ar: + free_bootmem(__pa(pages), pages_size); + pcpu_free_alloc_info(ai); + return rc; +} +#endif /* CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK */ + +/* + * Generic percpu area setup. + * + * The embedding helper is used because its behavior closely resembles + * the original non-dynamic generic percpu area setup. This is + * important because many archs have addressing restrictions and might + * fail if the percpu area is located far away from the previous + * location. As an added bonus, in non-NUMA cases, embedding is + * generally a good idea TLB-wise because percpu area can piggy back + * on the physical linear memory mapping which uses large page + * mappings on applicable archs. + */ +#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA +unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; +EXPORT_SYMBOL(__per_cpu_offset); + +static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, + size_t align) +{ + return __alloc_bootmem_nopanic(size, align, __pa(MAX_DMA_ADDRESS)); +} - return pcpu_setup_first_chunk(pcpue_get_page, static_size, - reserved_size, dyn_size, - pcpue_unit_size, pcpue_ptr, NULL); +static void __init pcpu_dfl_fc_free(void *ptr, size_t size) +{ + free_bootmem(__pa(ptr), size); +} + +void __init setup_per_cpu_areas(void) +{ + unsigned long delta; + unsigned int cpu; + int rc; + + /* + * Always reserve area for module percpu variables. That's + * what the legacy allocator did. + */ + rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, + PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL, + pcpu_dfl_fc_alloc, pcpu_dfl_fc_free); + if (rc < 0) + panic("Failed to initialized percpu areas."); + + delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; + for_each_possible_cpu(cpu) + __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; } +#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */ diff --git a/mm/quicklist.c b/mm/quicklist.c index e66d07d1b4ff..6eedf7e473d1 100644 --- a/mm/quicklist.c +++ b/mm/quicklist.c @@ -19,7 +19,7 @@ #include <linux/module.h> #include <linux/quicklist.h> -DEFINE_PER_CPU(struct quicklist, quicklist)[CONFIG_NR_QUICK]; +DEFINE_PER_CPU(struct quicklist [CONFIG_NR_QUICK], quicklist); #define FRACTION_OF_NODE_MEM 16 diff --git a/mm/shmem.c b/mm/shmem.c index d713239ce2ce..bd20f8bb02aa 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2298,8 +2298,7 @@ static void shmem_put_super(struct super_block *sb) sb->s_fs_info = NULL; } -static int shmem_fill_super(struct super_block *sb, - void *data, int silent) +int shmem_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; struct dentry *root; @@ -2446,7 +2445,7 @@ static const struct inode_operations shmem_inode_operations = { .getxattr = generic_getxattr, .listxattr = generic_listxattr, .removexattr = generic_removexattr, - .permission = shmem_permission, + .check_acl = shmem_check_acl, #endif }; @@ -2469,7 +2468,7 @@ static const struct inode_operations shmem_dir_inode_operations = { .getxattr = generic_getxattr, .listxattr = generic_listxattr, .removexattr = generic_removexattr, - .permission = shmem_permission, + .check_acl = shmem_check_acl, #endif }; @@ -2480,7 +2479,7 @@ static const struct inode_operations shmem_special_inode_operations = { .getxattr = generic_getxattr, .listxattr = generic_listxattr, .removexattr = generic_removexattr, - .permission = shmem_permission, + .check_acl = shmem_check_acl, #endif }; @@ -2519,7 +2518,7 @@ static struct file_system_type tmpfs_fs_type = { .kill_sb = kill_litter_super, }; -static int __init init_tmpfs(void) +int __init init_tmpfs(void) { int error; @@ -2576,7 +2575,7 @@ static struct file_system_type tmpfs_fs_type = { .kill_sb = kill_litter_super, }; -static int __init init_tmpfs(void) +int __init init_tmpfs(void) { BUG_ON(register_filesystem(&tmpfs_fs_type) != 0); @@ -2687,5 +2686,3 @@ int shmem_zero_setup(struct vm_area_struct *vma) vma->vm_ops = &shmem_vm_ops; return 0; } - -module_init(init_tmpfs) diff --git a/mm/shmem_acl.c b/mm/shmem_acl.c index 606a8e757a42..df2c87fdae50 100644 --- a/mm/shmem_acl.c +++ b/mm/shmem_acl.c @@ -157,7 +157,7 @@ shmem_acl_init(struct inode *inode, struct inode *dir) /** * shmem_check_acl - check_acl() callback for generic_permission() */ -static int +int shmem_check_acl(struct inode *inode, int mask) { struct posix_acl *acl = shmem_get_acl(inode, ACL_TYPE_ACCESS); @@ -169,12 +169,3 @@ shmem_check_acl(struct inode *inode, int mask) } return -EAGAIN; } - -/** - * shmem_permission - permission() inode operation - */ -int -shmem_permission(struct inode *inode, int mask) -{ - return generic_permission(inode, mask, shmem_check_acl); -} diff --git a/mm/slob.c b/mm/slob.c index 9641da3d5e58..837ebd64cc34 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -692,3 +692,8 @@ void __init kmem_cache_init(void) { slob_ready = 1; } + +void __init kmem_cache_init_late(void) +{ + /* Nothing to do */ +} diff --git a/mm/slub.c b/mm/slub.c index b9f1491a58a1..0a216aae227e 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -141,6 +141,13 @@ SLAB_POISON | SLAB_STORE_USER) /* + * Debugging flags that require metadata to be stored in the slab. These get + * disabled when slub_debug=O is used and a cache's min order increases with + * metadata. + */ +#define DEBUG_METADATA_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER) + +/* * Set of flags that will prevent slab merging */ #define SLUB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \ @@ -325,6 +332,7 @@ static int slub_debug; #endif static char *slub_debug_slabs; +static int disable_higher_order_debug; /* * Object debugging @@ -646,7 +654,7 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page) slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1); print_section("Padding", end - remainder, remainder); - restore_bytes(s, "slab padding", POISON_INUSE, start, end); + restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, end); return 0; } @@ -976,6 +984,15 @@ static int __init setup_slub_debug(char *str) */ goto check_slabs; + if (tolower(*str) == 'o') { + /* + * Avoid enabling debugging on caches if its minimum order + * would increase as a result. + */ + disable_higher_order_debug = 1; + goto out; + } + slub_debug = 0; if (*str == '-') /* @@ -1026,8 +1043,8 @@ static unsigned long kmem_cache_flags(unsigned long objsize, * Enable debugging if selected on the kernel commandline. */ if (slub_debug && (!slub_debug_slabs || - strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs)) == 0)) - flags |= slub_debug; + !strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs)))) + flags |= slub_debug; return flags; } @@ -1054,6 +1071,8 @@ static inline unsigned long kmem_cache_flags(unsigned long objsize, } #define slub_debug 0 +#define disable_higher_order_debug 0 + static inline unsigned long slabs_node(struct kmem_cache *s, int node) { return 0; } static inline unsigned long node_nr_slabs(struct kmem_cache_node *n) @@ -1109,8 +1128,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) } if (kmemcheck_enabled - && !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) - { + && !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) { int pages = 1 << oo_order(oo); kmemcheck_alloc_shadow(page, oo_order(oo), flags, node); @@ -1560,6 +1578,10 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) "default order: %d, min order: %d\n", s->name, s->objsize, s->size, oo_order(s->oo), oo_order(s->min)); + if (oo_order(s->min) > get_order(s->objsize)) + printk(KERN_WARNING " %s debugging increased min order, use " + "slub_debug=O to disable.\n", s->name); + for_each_online_node(node) { struct kmem_cache_node *n = get_node(s, node); unsigned long nr_slabs; @@ -2001,7 +2023,7 @@ static inline int calculate_order(int size) return order; fraction /= 2; } - min_objects --; + min_objects--; } /* @@ -2091,8 +2113,8 @@ init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s) */ #define NR_KMEM_CACHE_CPU 100 -static DEFINE_PER_CPU(struct kmem_cache_cpu, - kmem_cache_cpu)[NR_KMEM_CACHE_CPU]; +static DEFINE_PER_CPU(struct kmem_cache_cpu [NR_KMEM_CACHE_CPU], + kmem_cache_cpu); static DEFINE_PER_CPU(struct kmem_cache_cpu *, kmem_cache_cpu_free); static DECLARE_BITMAP(kmem_cach_cpu_free_init_once, CONFIG_NR_CPUS); @@ -2400,6 +2422,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * on bootup. */ align = calculate_alignment(flags, align, s->objsize); + s->align = align; /* * SLUB stores one object immediately after another beginning from @@ -2452,6 +2475,18 @@ static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags, if (!calculate_sizes(s, -1)) goto error; + if (disable_higher_order_debug) { + /* + * Disable debugging flags that store metadata if the min slab + * order increased. + */ + if (get_order(s->size) > get_order(s->objsize)) { + s->flags &= ~DEBUG_METADATA_FLAGS; + s->offset = 0; + if (!calculate_sizes(s, -1)) + goto error; + } + } /* * The larger the object size is, the more pages we want on the partial @@ -2594,8 +2629,6 @@ static inline int kmem_cache_close(struct kmem_cache *s) */ void kmem_cache_destroy(struct kmem_cache *s) { - if (s->flags & SLAB_DESTROY_BY_RCU) - rcu_barrier(); down_write(&slub_lock); s->refcount--; if (!s->refcount) { @@ -2606,6 +2639,8 @@ void kmem_cache_destroy(struct kmem_cache *s) "still has objects.\n", s->name, __func__); dump_stack(); } + if (s->flags & SLAB_DESTROY_BY_RCU) + rcu_barrier(); sysfs_slab_remove(s); } else up_write(&slub_lock); @@ -2790,6 +2825,11 @@ static s8 size_index[24] = { 2 /* 192 */ }; +static inline int size_index_elem(size_t bytes) +{ + return (bytes - 1) / 8; +} + static struct kmem_cache *get_slab(size_t size, gfp_t flags) { int index; @@ -2798,7 +2838,7 @@ static struct kmem_cache *get_slab(size_t size, gfp_t flags) if (!size) return ZERO_SIZE_PTR; - index = size_index[(size - 1) / 8]; + index = size_index[size_index_elem(size)]; } else index = fls(size - 1); @@ -3156,10 +3196,12 @@ void __init kmem_cache_init(void) slab_state = PARTIAL; /* Caches that are not of the two-to-the-power-of size */ - if (KMALLOC_MIN_SIZE <= 64) { + if (KMALLOC_MIN_SIZE <= 32) { create_kmalloc_cache(&kmalloc_caches[1], "kmalloc-96", 96, GFP_NOWAIT); caches++; + } + if (KMALLOC_MIN_SIZE <= 64) { create_kmalloc_cache(&kmalloc_caches[2], "kmalloc-192", 192, GFP_NOWAIT); caches++; @@ -3186,17 +3228,28 @@ void __init kmem_cache_init(void) BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 || (KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1))); - for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) - size_index[(i - 1) / 8] = KMALLOC_SHIFT_LOW; + for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) { + int elem = size_index_elem(i); + if (elem >= ARRAY_SIZE(size_index)) + break; + size_index[elem] = KMALLOC_SHIFT_LOW; + } - if (KMALLOC_MIN_SIZE == 128) { + if (KMALLOC_MIN_SIZE == 64) { + /* + * The 96 byte size cache is not used if the alignment + * is 64 byte. + */ + for (i = 64 + 8; i <= 96; i += 8) + size_index[size_index_elem(i)] = 7; + } else if (KMALLOC_MIN_SIZE == 128) { /* * The 192 byte sized cache is not used if the alignment * is 128 byte. Redirect kmalloc to use the 256 byte cache * instead. */ for (i = 128 + 8; i <= 192; i += 8) - size_index[(i - 1) / 8] = 8; + size_index[size_index_elem(i)] = 8; } slab_state = UP; @@ -4543,8 +4596,11 @@ static int sysfs_slab_add(struct kmem_cache *s) } err = sysfs_create_group(&s->kobj, &slab_attr_group); - if (err) + if (err) { + kobject_del(&s->kobj); + kobject_put(&s->kobj); return err; + } kobject_uevent(&s->kobj, KOBJ_ADD); if (!unmergeable) { /* Setup first alias */ @@ -4726,7 +4782,7 @@ static const struct file_operations proc_slabinfo_operations = { static int __init slab_proc_init(void) { - proc_create("slabinfo",S_IWUSR|S_IRUGO,NULL,&proc_slabinfo_operations); + proc_create("slabinfo", S_IRUGO, NULL, &proc_slabinfo_operations); return 0; } module_init(slab_proc_init); diff --git a/mm/swap_state.c b/mm/swap_state.c index 42cd38eba79f..5ae6b8b78c80 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -34,6 +34,7 @@ static const struct address_space_operations swap_aops = { }; static struct backing_dev_info swap_backing_dev_info = { + .name = "swap", .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED, .unplug_io_fn = swap_unplug_io_fn, }; diff --git a/mm/swapfile.c b/mm/swapfile.c index 8ffdc0d23c53..74f1102e8749 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -161,7 +161,8 @@ static int discard_swap(struct swap_info_struct *si) } err = blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_KERNEL); + nr_blocks, GFP_KERNEL, + DISCARD_FL_BARRIER); if (err) break; @@ -200,7 +201,8 @@ static void discard_swap_cluster(struct swap_info_struct *si, start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_NOIO)) + nr_blocks, GFP_NOIO, + DISCARD_FL_BARRIER)) break; } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index f8189a4b3e13..204b8243d8ab 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -265,6 +265,7 @@ struct vmap_area { static DEFINE_SPINLOCK(vmap_area_lock); static struct rb_root vmap_area_root = RB_ROOT; static LIST_HEAD(vmap_area_list); +static unsigned long vmap_area_pcpu_hole; static struct vmap_area *__find_vmap_area(unsigned long addr) { @@ -431,6 +432,15 @@ static void __free_vmap_area(struct vmap_area *va) RB_CLEAR_NODE(&va->rb_node); list_del_rcu(&va->list); + /* + * Track the highest possible candidate for pcpu area + * allocation. Areas outside of vmalloc area can be returned + * here too, consider only end addresses which fall inside + * vmalloc area proper. + */ + if (va->va_end > VMALLOC_START && va->va_end <= VMALLOC_END) + vmap_area_pcpu_hole = max(vmap_area_pcpu_hole, va->va_end); + call_rcu(&va->rcu_head, rcu_free_va); } @@ -1038,6 +1048,9 @@ void __init vmalloc_init(void) va->va_end = va->va_start + tmp->size; __insert_vmap_area(va); } + + vmap_area_pcpu_hole = VMALLOC_END; + vmap_initialized = true; } @@ -1122,13 +1135,34 @@ EXPORT_SYMBOL_GPL(map_vm_area); DEFINE_RWLOCK(vmlist_lock); struct vm_struct *vmlist; +static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, + unsigned long flags, void *caller) +{ + struct vm_struct *tmp, **p; + + vm->flags = flags; + vm->addr = (void *)va->va_start; + vm->size = va->va_end - va->va_start; + vm->caller = caller; + va->private = vm; + va->flags |= VM_VM_AREA; + + write_lock(&vmlist_lock); + for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) { + if (tmp->addr >= vm->addr) + break; + } + vm->next = *p; + *p = vm; + write_unlock(&vmlist_lock); +} + 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) { static struct vmap_area *va; struct vm_struct *area; - struct vm_struct *tmp, **p; unsigned long align = 1; BUG_ON(in_interrupt()); @@ -1147,7 +1181,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, if (unlikely(!size)) return NULL; - area = kmalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node); + area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!area)) return NULL; @@ -1162,25 +1196,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, return NULL; } - area->flags = flags; - area->addr = (void *)va->va_start; - area->size = size; - area->pages = NULL; - area->nr_pages = 0; - area->phys_addr = 0; - area->caller = caller; - va->private = area; - va->flags |= VM_VM_AREA; - - write_lock(&vmlist_lock); - for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) { - if (tmp->addr >= area->addr) - break; - } - area->next = *p; - *p = area; - write_unlock(&vmlist_lock); - + insert_vmalloc_vm(area, va, flags, caller); return area; } @@ -1818,6 +1834,286 @@ void free_vm_area(struct vm_struct *area) } EXPORT_SYMBOL_GPL(free_vm_area); +static struct vmap_area *node_to_va(struct rb_node *n) +{ + return n ? rb_entry(n, struct vmap_area, rb_node) : NULL; +} + +/** + * pvm_find_next_prev - find the next and prev vmap_area surrounding @end + * @end: target address + * @pnext: out arg for the next vmap_area + * @pprev: out arg for the previous vmap_area + * + * Returns: %true if either or both of next and prev are found, + * %false if no vmap_area exists + * + * Find vmap_areas end addresses of which enclose @end. ie. if not + * NULL, *pnext->va_end > @end and *pprev->va_end <= @end. + */ +static bool pvm_find_next_prev(unsigned long end, + struct vmap_area **pnext, + struct vmap_area **pprev) +{ + struct rb_node *n = vmap_area_root.rb_node; + struct vmap_area *va = NULL; + + while (n) { + va = rb_entry(n, struct vmap_area, rb_node); + if (end < va->va_end) + n = n->rb_left; + else if (end > va->va_end) + n = n->rb_right; + else + break; + } + + if (!va) + return false; + + if (va->va_end > end) { + *pnext = va; + *pprev = node_to_va(rb_prev(&(*pnext)->rb_node)); + } else { + *pprev = va; + *pnext = node_to_va(rb_next(&(*pprev)->rb_node)); + } + return true; +} + +/** + * pvm_determine_end - find the highest aligned address between two vmap_areas + * @pnext: in/out arg for the next vmap_area + * @pprev: in/out arg for the previous vmap_area + * @align: alignment + * + * Returns: determined end address + * + * Find the highest aligned address between *@pnext and *@pprev below + * VMALLOC_END. *@pnext and *@pprev are adjusted so that the aligned + * down address is between the end addresses of the two vmap_areas. + * + * Please note that the address returned by this function may fall + * inside *@pnext vmap_area. The caller is responsible for checking + * that. + */ +static unsigned long pvm_determine_end(struct vmap_area **pnext, + struct vmap_area **pprev, + unsigned long align) +{ + const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1); + unsigned long addr; + + if (*pnext) + addr = min((*pnext)->va_start & ~(align - 1), vmalloc_end); + else + addr = vmalloc_end; + + while (*pprev && (*pprev)->va_end > addr) { + *pnext = *pprev; + *pprev = node_to_va(rb_prev(&(*pnext)->rb_node)); + } + + return addr; +} + +/** + * pcpu_get_vm_areas - allocate vmalloc areas for percpu allocator + * @offsets: array containing offset of each area + * @sizes: array containing size of each area + * @nr_vms: the number of areas to allocate + * @align: alignment, all entries in @offsets and @sizes must be aligned to this + * @gfp_mask: allocation mask + * + * Returns: kmalloc'd vm_struct pointer array pointing to allocated + * vm_structs on success, %NULL on failure + * + * Percpu allocator wants to use congruent vm areas so that it can + * maintain the offsets among percpu areas. This function allocates + * congruent vmalloc areas for it. These areas tend to be scattered + * pretty far, distance between two areas easily going up to + * gigabytes. To avoid interacting with regular vmallocs, these areas + * are allocated from top. + * + * Despite its complicated look, this allocator is rather simple. It + * does everything top-down and scans areas from the end looking for + * matching slot. While scanning, if any of the areas overlaps with + * existing vmap_area, the base address is pulled down to fit the + * area. Scanning is repeated till all the areas fit and then all + * necessary data structres are inserted and the result is returned. + */ +struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, + const size_t *sizes, int nr_vms, + size_t align, gfp_t gfp_mask) +{ + const unsigned long vmalloc_start = ALIGN(VMALLOC_START, align); + const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1); + struct vmap_area **vas, *prev, *next; + struct vm_struct **vms; + int area, area2, last_area, term_area; + unsigned long base, start, end, last_end; + bool purged = false; + + gfp_mask &= GFP_RECLAIM_MASK; + + /* verify parameters and allocate data structures */ + BUG_ON(align & ~PAGE_MASK || !is_power_of_2(align)); + for (last_area = 0, area = 0; area < nr_vms; area++) { + start = offsets[area]; + end = start + sizes[area]; + + /* is everything aligned properly? */ + BUG_ON(!IS_ALIGNED(offsets[area], align)); + BUG_ON(!IS_ALIGNED(sizes[area], align)); + + /* detect the area with the highest address */ + if (start > offsets[last_area]) + last_area = area; + + for (area2 = 0; area2 < nr_vms; area2++) { + unsigned long start2 = offsets[area2]; + unsigned long end2 = start2 + sizes[area2]; + + if (area2 == area) + continue; + + BUG_ON(start2 >= start && start2 < end); + BUG_ON(end2 <= end && end2 > start); + } + } + last_end = offsets[last_area] + sizes[last_area]; + + if (vmalloc_end - vmalloc_start < last_end) { + WARN_ON(true); + return NULL; + } + + vms = kzalloc(sizeof(vms[0]) * nr_vms, gfp_mask); + vas = kzalloc(sizeof(vas[0]) * nr_vms, gfp_mask); + if (!vas || !vms) + goto err_free; + + for (area = 0; area < nr_vms; area++) { + vas[area] = kzalloc(sizeof(struct vmap_area), gfp_mask); + vms[area] = kzalloc(sizeof(struct vm_struct), gfp_mask); + if (!vas[area] || !vms[area]) + goto err_free; + } +retry: + spin_lock(&vmap_area_lock); + + /* start scanning - we scan from the top, begin with the last area */ + area = term_area = last_area; + start = offsets[area]; + end = start + sizes[area]; + + if (!pvm_find_next_prev(vmap_area_pcpu_hole, &next, &prev)) { + base = vmalloc_end - last_end; + goto found; + } + base = pvm_determine_end(&next, &prev, align) - end; + + while (true) { + BUG_ON(next && next->va_end <= base + end); + BUG_ON(prev && prev->va_end > base + end); + + /* + * base might have underflowed, add last_end before + * comparing. + */ + if (base + last_end < vmalloc_start + last_end) { + spin_unlock(&vmap_area_lock); + if (!purged) { + purge_vmap_area_lazy(); + purged = true; + goto retry; + } + goto err_free; + } + + /* + * If next overlaps, move base downwards so that it's + * right below next and then recheck. + */ + if (next && next->va_start < base + end) { + base = pvm_determine_end(&next, &prev, align) - end; + term_area = area; + continue; + } + + /* + * If prev overlaps, shift down next and prev and move + * base so that it's right below new next and then + * recheck. + */ + if (prev && prev->va_end > base + start) { + next = prev; + prev = node_to_va(rb_prev(&next->rb_node)); + base = pvm_determine_end(&next, &prev, align) - end; + term_area = area; + continue; + } + + /* + * This area fits, move on to the previous one. If + * the previous one is the terminal one, we're done. + */ + area = (area + nr_vms - 1) % nr_vms; + if (area == term_area) + break; + start = offsets[area]; + end = start + sizes[area]; + pvm_find_next_prev(base + end, &next, &prev); + } +found: + /* we've found a fitting base, insert all va's */ + for (area = 0; area < nr_vms; area++) { + struct vmap_area *va = vas[area]; + + va->va_start = base + offsets[area]; + va->va_end = va->va_start + sizes[area]; + __insert_vmap_area(va); + } + + vmap_area_pcpu_hole = base + offsets[last_area]; + + spin_unlock(&vmap_area_lock); + + /* insert all vm's */ + for (area = 0; area < nr_vms; area++) + insert_vmalloc_vm(vms[area], vas[area], VM_ALLOC, + pcpu_get_vm_areas); + + kfree(vas); + return vms; + +err_free: + for (area = 0; area < nr_vms; area++) { + if (vas) + kfree(vas[area]); + if (vms) + kfree(vms[area]); + } + kfree(vas); + kfree(vms); + return NULL; +} + +/** + * pcpu_free_vm_areas - free vmalloc areas for percpu allocator + * @vms: vm_struct pointer array returned by pcpu_get_vm_areas() + * @nr_vms: the number of allocated areas + * + * Free vm_structs and the array allocated by pcpu_get_vm_areas(). + */ +void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) +{ + int i; + + for (i = 0; i < nr_vms; i++) + free_vm_area(vms[i]); + kfree(vms); +} #ifdef CONFIG_PROC_FS static void *s_start(struct seq_file *m, loff_t *pos) diff --git a/mm/vmscan.c b/mm/vmscan.c index 94e86dd6954c..ba8228e0a806 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1720,7 +1720,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, */ if (total_scanned > sc->swap_cluster_max + sc->swap_cluster_max / 2) { - wakeup_pdflush(laptop_mode ? 0 : total_scanned); + wakeup_flusher_threads(laptop_mode ? 0 : total_scanned); sc->may_writepage = 1; } |
