diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Kconfig | 6 | ||||
-rw-r--r-- | mm/Makefile | 2 | ||||
-rw-r--r-- | mm/backing-dev.c | 381 | ||||
-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.c | 336 | ||||
-rw-r--r-- | mm/mmap.c | 3 | ||||
-rw-r--r-- | mm/nommu.c | 10 | ||||
-rw-r--r-- | mm/oom_kill.c | 64 | ||||
-rw-r--r-- | mm/page-writeback.c | 182 | ||||
-rw-r--r-- | mm/page_alloc.c | 10 | ||||
-rw-r--r-- | mm/pdflush.c | 269 | ||||
-rw-r--r-- | mm/percpu.c | 50 | ||||
-rw-r--r-- | mm/rmap.c | 1 | ||||
-rw-r--r-- | mm/shmem.c | 6 | ||||
-rw-r--r-- | mm/shmem_acl.c | 11 | ||||
-rw-r--r-- | mm/slob.c | 5 | ||||
-rw-r--r-- | mm/slub.c | 86 | ||||
-rw-r--r-- | mm/swap_state.c | 1 | ||||
-rw-r--r-- | mm/swapfile.c | 6 | ||||
-rw-r--r-- | mm/vmscan.c | 11 |
22 files changed, 886 insertions, 731 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index fe221c7df75..3aa519f52e1 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -225,9 +225,9 @@ config DEFAULT_MMAP_MIN_ADDR For most ia64, ppc64 and x86 users with lots of address space a value of 65536 is reasonable and should cause no problems. On arm and other archs it should not be higher than 32768. - Programs which use vm86 functionality would either need additional - permissions from either the LSM or the capabilities module or have - this protection disabled. + Programs which use vm86 functionality or have some need to map + this low address space will need CAP_SYS_RAWIO or disable this + protection by setting the value to 0. This value can be changed after boot using the /proc/sys/vm/mmap_min_addr tunable. diff --git a/mm/Makefile b/mm/Makefile index 5e0bd642669..147a7a7873c 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) diff --git a/mm/backing-dev.c b/mm/backing-dev.c index c86edd24429..d3ca0dac111 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, @@ -22,6 +26,18 @@ struct backing_dev_info default_backing_dev_info = { EXPORT_SYMBOL_GPL(default_backing_dev_info); static struct class *bdi_class; +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> @@ -37,9 +53,29 @@ 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 +85,22 @@ 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 +231,13 @@ 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 +246,248 @@ 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(&bdi_lock); + list_add(&bdi->bdi_list, &bdi_list); + spin_unlock(&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(&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(&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(&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(&bdi_lock); + list_add_tail(&bdi->bdi_list, &bdi_pending_list); + spin_unlock(&bdi_lock); + + bdi_flush_io(bdi); + } + } + + return 0; +} + +/* + * 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_move_tail(&bdi->bdi_list, &bdi_pending_list); + + /* + * 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); + } +} + int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...) { @@ -211,9 +506,35 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, goto exit; } + spin_lock(&bdi_lock); + list_add_tail(&bdi->bdi_list, &bdi_list); + spin_unlock(&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; + + spin_lock(&bdi_lock); + list_del(&bdi->bdi_list); + spin_unlock(&bdi_lock); + goto exit; + } + } + + bdi_debug_register(bdi, dev_name(dev)); + set_bit(BDI_registered, &bdi->state); exit: return ret; } @@ -225,9 +546,42 @@ 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 + */ + spin_lock(&bdi_lock); + list_del(&bdi->bdi_list); + spin_unlock(&bdi_lock); + + /* + * 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 +591,25 @@ 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_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 +634,8 @@ void bdi_destroy(struct backing_dev_info *bdi) { int i; + WARN_ON(bdi_has_dirty_io(bdi)); + bdi_unregister(bdi); for (i = 0; i < NR_BDI_STAT_ITEMS; i++) diff --git a/mm/bootmem.c b/mm/bootmem.c index 701740c9e81..555d5d2731c 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 ccea3b665c1..dd51c68e2b8 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 cafdcee154e..b16d6363477 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.c b/mm/kmemleak.c index 487267310a8..4ea4510e299 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/mmap.c b/mm/mmap.c index 34579b23ebd..8101de490c7 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -88,9 +88,6 @@ int sysctl_overcommit_ratio = 50; /* default is 50% */ int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; struct percpu_counter vm_committed_as; -/* amount of vm to protect from userspace access */ -unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR; - /* * Check that a process has enough memory to allocate a new virtual * mapping. 0 means there is enough memory for the allocation to diff --git a/mm/nommu.c b/mm/nommu.c index 53cab10fece..66e81e7e9fe 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -69,9 +69,6 @@ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT; int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS; int heap_stack_gap = 0; -/* amount of vm to protect from userspace access */ -unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR; - atomic_long_t mmap_pages_allocated; EXPORT_SYMBOL(mem_map); @@ -922,6 +919,10 @@ static int validate_mmap_request(struct file *file, if (!file->f_op->read) capabilities &= ~BDI_CAP_MAP_COPY; + /* The file shall have been opened with read permission. */ + if (!(file->f_mode & FMODE_READ)) + return -EACCES; + if (flags & MAP_SHARED) { /* do checks for writing, appending and locking */ if ((prot & PROT_WRITE) && @@ -1351,6 +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) @@ -1360,8 +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/oom_kill.c b/mm/oom_kill.c index 175a67a78a9..a7b2460e922 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -58,7 +58,6 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) unsigned long points, cpu_time, run_time; struct mm_struct *mm; struct task_struct *child; - int oom_adj; task_lock(p); mm = p->mm; @@ -66,11 +65,6 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) task_unlock(p); return 0; } - oom_adj = mm->oom_adj; - if (oom_adj == OOM_DISABLE) { - task_unlock(p); - return 0; - } /* * The memory size of the process is the basis for the badness. @@ -154,15 +148,15 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) points /= 8; /* - * Adjust the score by oom_adj. + * Adjust the score by oomkilladj. */ - if (oom_adj) { - if (oom_adj > 0) { + if (p->oomkilladj) { + if (p->oomkilladj > 0) { if (!points) points = 1; - points <<= oom_adj; + points <<= p->oomkilladj; } else - points >>= -(oom_adj); + points >>= -(p->oomkilladj); } #ifdef DEBUG @@ -257,8 +251,11 @@ static struct task_struct *select_bad_process(unsigned long *ppoints, *ppoints = ULONG_MAX; } + if (p->oomkilladj == OOM_DISABLE) + continue; + points = badness(p, uptime.tv_sec); - if (points > *ppoints) { + if (points > *ppoints || !chosen) { chosen = p; *ppoints = points; } @@ -307,7 +304,8 @@ static void dump_tasks(const struct mem_cgroup *mem) } printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d %3d %s\n", p->pid, __task_cred(p)->uid, p->tgid, mm->total_vm, - get_mm_rss(mm), (int)task_cpu(p), mm->oom_adj, p->comm); + get_mm_rss(mm), (int)task_cpu(p), p->oomkilladj, + p->comm); task_unlock(p); } while_each_thread(g, p); } @@ -325,8 +323,11 @@ static void __oom_kill_task(struct task_struct *p, int verbose) return; } - if (!p->mm) + if (!p->mm) { + WARN_ON(1); + printk(KERN_WARNING "tried to kill an mm-less task!\n"); return; + } if (verbose) printk(KERN_ERR "Killed process %d (%s)\n", @@ -348,13 +349,28 @@ static int oom_kill_task(struct task_struct *p) struct mm_struct *mm; struct task_struct *g, *q; - task_lock(p); mm = p->mm; - if (!mm || mm->oom_adj == OOM_DISABLE) { - task_unlock(p); + + /* WARNING: mm may not be dereferenced since we did not obtain its + * value from get_task_mm(p). This is OK since all we need to do is + * compare mm to q->mm below. + * + * Furthermore, even if mm contains a non-NULL value, p->mm may + * change to NULL at any time since we do not hold task_lock(p). + * However, this is of no concern to us. + */ + + if (mm == NULL) return 1; - } - task_unlock(p); + + /* + * Don't kill the process if any threads are set to OOM_DISABLE + */ + do_each_thread(g, q) { + if (q->mm == mm && q->oomkilladj == OOM_DISABLE) + return 1; + } while_each_thread(g, q); + __oom_kill_task(p, 1); /* @@ -377,11 +393,10 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, struct task_struct *c; if (printk_ratelimit()) { - task_lock(current); printk(KERN_WARNING "%s invoked oom-killer: " - "gfp_mask=0x%x, order=%d, oom_adj=%d\n", - current->comm, gfp_mask, order, - current->mm ? current->mm->oom_adj : OOM_DISABLE); + "gfp_mask=0x%x, order=%d, oomkilladj=%d\n", + current->comm, gfp_mask, order, current->oomkilladj); + task_lock(current); cpuset_print_task_mems_allowed(current); task_unlock(current); dump_stack(); @@ -394,9 +409,8 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, /* * If the task is already exiting, don't alarm the sysadmin or kill * its children or threads, just set TIF_MEMDIE so it can die quickly - * if its mm is still attached. */ - if (p->mm && (p->flags & PF_EXITING)) { + if (p->flags & PF_EXITING) { __oom_kill_task(p, 0); return 0; } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 81627ebcd31..25e7770309b 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(&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(&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(&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(&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 +580,18 @@ 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) - > background_thresh))) - pdflush_operation(background_writeout, 0); + (!laptop_mode && ((nr_writeback = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS)) + > background_thresh))) { + struct writeback_control wbc = { + .bdi = bdi, + .sync_mode = WB_SYNC_NONE, + .nr_to_write = nr_writeback, + }; + + + bdi_start_writeback(&wbc); + } } void set_page_dirty_balance(struct page *page, int page_mkwrite) @@ -681,153 +675,35 @@ 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) -{ - if (pdflush_operation(wb_kupdate, 0) < 0) - mod_timer(&wb_timer, jiffies + HZ); /* delay 1 second */ -} - -static void laptop_flush(unsigned long unused) +static void do_laptop_sync(struct work_struct *work) { - 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 +786,6 @@ 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); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d052abbe306..a0de15f4698 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); @@ -2544,7 +2546,6 @@ static void build_zonelists(pg_data_t *pgdat) prev_node = local_node; nodes_clear(used_mask); - memset(node_load, 0, sizeof(node_load)); memset(node_order, 0, sizeof(node_order)); j = 0; @@ -2653,6 +2654,9 @@ static int __build_all_zonelists(void *dummy) { int nid; +#ifdef CONFIG_NUMA + memset(node_load, 0, sizeof(node_load)); +#endif for_each_online_node(nid) { pg_data_t *pgdat = NODE_DATA(nid); diff --git a/mm/pdflush.c b/mm/pdflush.c deleted file mode 100644 index 235ac440c44..00000000000 --- 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 b70f2acd885..3311c8919f3 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -8,12 +8,12 @@ * * 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 num_possible_cpus() 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 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 * * c0 c1 c2 * ------------------- ------------------- ------------ @@ -197,7 +197,12 @@ static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, static bool pcpu_chunk_page_occupied(struct pcpu_chunk *chunk, int page_idx) { - return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL; + /* + * Any possible cpu id can be used here, so there's no need to + * worry about preemption or cpu hotplug. + */ + return *pcpu_chunk_pagep(chunk, raw_smp_processor_id(), + page_idx) != NULL; } /* set the pointer to a chunk in a page struct */ @@ -297,6 +302,14 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) 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 += raw_smp_processor_id() * pcpu_unit_size; return pcpu_get_page_chunk(vmalloc_to_page(addr)); } @@ -558,7 +571,7 @@ static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme) static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end, bool flush_tlb) { - unsigned int last = num_possible_cpus() - 1; + unsigned int last = nr_cpu_ids - 1; unsigned int cpu; /* unmap must not be done on immutable chunk */ @@ -643,7 +656,7 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size, */ static int pcpu_map(struct pcpu_chunk *chunk, int page_start, int page_end) { - unsigned int last = num_possible_cpus() - 1; + unsigned int last = nr_cpu_ids - 1; unsigned int cpu; int err; @@ -749,7 +762,7 @@ static struct pcpu_chunk *alloc_pcpu_chunk(void) chunk->map[chunk->map_used++] = pcpu_unit_size; chunk->page = chunk->page_ar; - chunk->vm = get_vm_area(pcpu_chunk_size, GFP_KERNEL); + chunk->vm = get_vm_area(pcpu_chunk_size, VM_ALLOC); if (!chunk->vm) { free_pcpu_chunk(chunk); return NULL; @@ -1067,9 +1080,9 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, PFN_UP(size_sum)); pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; - pcpu_chunk_size = num_possible_cpus() * pcpu_unit_size; + pcpu_chunk_size = nr_cpu_ids * pcpu_unit_size; pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) - + num_possible_cpus() * pcpu_unit_pages * sizeof(struct page *); + + nr_cpu_ids * pcpu_unit_pages * sizeof(struct page *); if (dyn_size < 0) dyn_size = pcpu_unit_size - static_size - reserved_size; @@ -1248,7 +1261,7 @@ ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size, } else pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE); - chunk_size = pcpue_unit_size * num_possible_cpus(); + chunk_size = pcpue_unit_size * nr_cpu_ids; pcpue_ptr = __alloc_bootmem_nopanic(chunk_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); @@ -1259,12 +1272,15 @@ ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size, } /* return the leftover and copy */ - for_each_possible_cpu(cpu) { + for (cpu = 0; cpu < nr_cpu_ids; cpu++) { void *ptr = pcpue_ptr + cpu * pcpue_unit_size; - free_bootmem(__pa(ptr + pcpue_size), - pcpue_unit_size - pcpue_size); - memcpy(ptr, __per_cpu_load, static_size); + 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); } /* we're ready, commit */ diff --git a/mm/rmap.c b/mm/rmap.c index 836c6c63e1f..0895b5c7cbf 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -358,6 +358,7 @@ static int page_referenced_one(struct page *page, */ if (vma->vm_flags & VM_LOCKED) { *mapcount = 1; /* break early from loop */ + *vm_flags |= VM_LOCKED; goto out_unmap; } diff --git a/mm/shmem.c b/mm/shmem.c index d713239ce2c..5a0b3d4055f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2446,7 +2446,7 @@ 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 +2469,7 @@ 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 +2480,7 @@ 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 }; diff --git a/mm/shmem_acl.c b/mm/shmem_acl.c index 606a8e757a4..df2c87fdae5 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 9641da3d5e5..837ebd64cc3 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 b9f1491a58a..417ed843b25 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; } @@ -1109,8 +1126,7 @@ 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 +1576,10 @@ 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 +2021,7 @@ static inline int calculate_order(int size) return order; fraction /= 2; } - min_objects --; + min_objects--; } /* @@ -2400,6 +2420,7 @@ 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 +2473,18 @@ 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 +2627,6 @@ 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 +2637,8 @@ 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 +2823,11 @@ 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 +2836,7 @@ 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 +3194,12 @@ 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 +3226,28 @@ 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 +4594,11 @@ 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 +4780,7 @@ 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 42cd38eba79..5ae6b8b78c8 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 8ffdc0d23c5..74f1102e874 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/vmscan.c b/mm/vmscan.c index dea7abd3109..ba8228e0a80 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -630,9 +630,14 @@ static unsigned long shrink_page_list(struct list_head *page_list, referenced = page_referenced(page, 1, sc->mem_cgroup, &vm_flags); - /* In active use or really unfreeable? Activate it. */ + /* + * In active use or really unfreeable? Activate it. + * If page which have PG_mlocked lost isoltation race, + * try_to_unmap moves it to unevictable list + */ if (sc->order <= PAGE_ALLOC_COSTLY_ORDER && - referenced && page_mapping_inuse(page)) + referenced && page_mapping_inuse(page) + && !(vm_flags & VM_LOCKED)) goto activate_locked; /* @@ -1715,7 +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; } |