#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>#include <linux/device.h>#include <trace/events/writeback.h> static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); 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,};EXPORT_SYMBOL_GPL(default_backing_dev_info); struct backing_dev_info noop_backing_dev_info = {	.name		= "noop",	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,};EXPORT_SYMBOL_GPL(noop_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); void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2){	if (wb1 < wb2) {		spin_lock(&wb1->list_lock);		spin_lock_nested(&wb2->list_lock, 1);	} else {		spin_lock(&wb2->list_lock);		spin_lock_nested(&wb1->list_lock, 1);	}} #ifdef CONFIG_DEBUG_FS#include <linux/debugfs.h>#include <linux/seq_file.h> static struct dentry *bdi_debug_root; static void bdi_debug_init(void){	bdi_debug_root = debugfs_create_dir("bdi", NULL);} static int bdi_debug_stats_show(struct seq_file *m, void *v){	struct backing_dev_info *bdi = m->private;	struct bdi_writeback *wb = &bdi->wb;	unsigned long background_thresh;	unsigned long dirty_thresh;	unsigned long bdi_thresh;	unsigned long nr_dirty, nr_io, nr_more_io;	struct inode *inode; 	nr_dirty = nr_io = nr_more_io = 0;	spin_lock(&wb->list_lock);	list_for_each_entry(inode, &wb->b_dirty, i_wb_list)		nr_dirty++;	list_for_each_entry(inode, &wb->b_io, i_wb_list)		nr_io++;	list_for_each_entry(inode, &wb->b_more_io, i_wb_list)		nr_more_io++;	spin_unlock(&wb->list_lock); 	global_dirty_limits(&background_thresh, &dirty_thresh);	bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); #define K(x) ((x) << (PAGE_SHIFT - 10))	seq_printf(m,		   "BdiWriteback:       %10lu kB\n"		   "BdiReclaimable:     %10lu kB\n"		   "BdiDirtyThresh:     %10lu kB\n"		   "DirtyThresh:        %10lu kB\n"		   "BackgroundThresh:   %10lu kB\n"		   "BdiDirtied:         %10lu kB\n"		   "BdiWritten:         %10lu kB\n"		   "BdiWriteBandwidth:  %10lu kBps\n"		   "b_dirty:            %10lu\n"		   "b_io:               %10lu\n"		   "b_more_io:          %10lu\n"		   "bdi_list:           %10u\n"		   "state:              %10lx\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),		   (unsigned long) K(bdi_stat(bdi, BDI_DIRTIED)),		   (unsigned long) K(bdi_stat(bdi, BDI_WRITTEN)),		   (unsigned long) K(bdi->write_bandwidth),		   nr_dirty,		   nr_io,		   nr_more_io,		   !list_empty(&bdi->bdi_list), bdi->state);#undef K 	return 0;} static int bdi_debug_stats_open(struct inode *inode, struct file *file){	return single_open(file, bdi_debug_stats_show, inode->i_private);} static const struct file_operations bdi_debug_stats_fops = {	.open		= bdi_debug_stats_open,	.read		= seq_read,	.llseek		= seq_lseek,	.release	= single_release,}; static void bdi_debug_register(struct backing_dev_info *bdi, const char *name){	bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root);	bdi->debug_stats = debugfs_create_file("stats", 0444, bdi->debug_dir,					       bdi, &bdi_debug_stats_fops);} static void bdi_debug_unregister(struct backing_dev_info *bdi){	debugfs_remove(bdi->debug_stats);	debugfs_remove(bdi->debug_dir);}#elsestatic inline void bdi_debug_init(void){}static inline void bdi_debug_register(struct backing_dev_info *bdi,				      const char *name){}static inline void bdi_debug_unregister(struct backing_dev_info *bdi){}#endif static ssize_t read_ahead_kb_store(struct device *dev,				  struct device_attribute *attr,				  const char *buf, size_t count){	struct backing_dev_info *bdi = dev_get_drvdata(dev);	char *end;	unsigned long read_ahead_kb;	ssize_t ret = -EINVAL; 	read_ahead_kb = simple_strtoul(buf, &end, 10);	if (*buf && (end[0] == '\0' || (end[0] == '\n' && end[1] == '\0'))) {		bdi->ra_pages = read_ahead_kb >> (PAGE_SHIFT - 10);		ret = count;	}	return ret;} #define K(pages) ((pages) << (PAGE_SHIFT - 10)) #define BDI_SHOW(name, expr)						\static ssize_t name##_show(struct device *dev,				\			   struct device_attribute *attr, char *page)	\{									\	struct backing_dev_info *bdi = dev_get_drvdata(dev);		\									\	return snprintf(page, PAGE_SIZE-1, "%lld\n", (long long)expr);	\} BDI_SHOW(read_ahead_kb, K(bdi->ra_pages)) static ssize_t min_ratio_store(struct device *dev,		struct device_attribute *attr, const char *buf, size_t count){	struct backing_dev_info *bdi = dev_get_drvdata(dev);	char *end;	unsigned int ratio;	ssize_t ret = -EINVAL; 	ratio = simple_strtoul(buf, &end, 10);	if (*buf && (end[0] == '\0' || (end[0] == '\n' && end[1] == '\0'))) {		ret = bdi_set_min_ratio(bdi, ratio);		if (!ret)			ret = count;	}	return ret;}BDI_SHOW(min_ratio, bdi->min_ratio) static ssize_t max_ratio_store(struct device *dev,		struct device_attribute *attr, const char *buf, size_t count){	struct backing_dev_info *bdi = dev_get_drvdata(dev);	char *end;	unsigned int ratio;	ssize_t ret = -EINVAL; 	ratio = simple_strtoul(buf, &end, 10);	if (*buf && (end[0] == '\0' || (end[0] == '\n' && end[1] == '\0'))) {		ret = bdi_set_max_ratio(bdi, ratio);		if (!ret)			ret = count;	}	return ret;}BDI_SHOW(max_ratio, bdi->max_ratio) #define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store) static struct device_attribute bdi_dev_attrs[] = {	__ATTR_RW(read_ahead_kb),	__ATTR_RW(min_ratio),	__ATTR_RW(max_ratio),	__ATTR_NULL,}; static __init int bdi_class_init(void){	bdi_class = class_create(THIS_MODULE, "bdi");	if (IS_ERR(bdi_class))		return PTR_ERR(bdi_class); 	bdi_class->dev_attrs = bdi_dev_attrs;	bdi_debug_init();	return 0;}postcore_initcall(bdi_class_init); static int __init default_bdi_init(void){	int err; 	err = bdi_init(&default_backing_dev_info);	if (!err)		bdi_register(&default_backing_dev_info, NULL, "default");	err = bdi_init(&noop_backing_dev_info); 	return err;}subsys_initcall(default_bdi_init); int bdi_has_dirty_io(struct backing_dev_info *bdi){	return wb_has_dirty_io(&bdi->wb);} static void wakeup_timer_fn(unsigned long data){	struct backing_dev_info *bdi = (struct backing_dev_info *)data; 	spin_lock_bh(&bdi->wb_lock);	if (bdi->wb.task) {		trace_writeback_wake_thread(bdi);		wake_up_process(bdi->wb.task);	} else if (bdi->dev) {		/*		 * When bdi tasks are inactive for long time, they are killed.		 * In this case we have to wake-up the forker thread which		 * should create and run the bdi thread.		 */		trace_writeback_wake_forker_thread(bdi);		wake_up_process(default_backing_dev_info.wb.task);	}	spin_unlock_bh(&bdi->wb_lock);} /* * This function is used when the first inode for this bdi is marked dirty. It * wakes-up the corresponding bdi thread which should then take care of the * periodic background write-out of dirty inodes. Since the write-out would * starts only 'dirty_writeback_interval' centisecs from now anyway, we just * set up a timer which wakes the bdi thread up later. * * Note, we wouldn't bother setting up the timer, but this function is on the * fast-path (used by '__mark_inode_dirty()'), so we save few context switches * by delaying the wake-up. */void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi){	unsigned long timeout; 	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);	mod_timer(&bdi->wb.wakeup_timer, jiffies + timeout);} /* * Calculate the longest interval (jiffies) bdi threads are allowed to be * inactive. */static unsigned long bdi_longest_inactive(void){	unsigned long interval; 	interval = msecs_to_jiffies(dirty_writeback_interval * 10);	return max(5UL * 60 * HZ, interval);} /* * Clear pending bit and wakeup anybody waiting for flusher thread creation or * shutdown */static void bdi_clear_pending(struct backing_dev_info *bdi){	clear_bit(BDI_pending, &bdi->state);	smp_mb__after_clear_bit();	wake_up_bit(&bdi->state, BDI_pending);} static int bdi_forker_thread(void *ptr){	struct bdi_writeback *me = ptr; 	current->flags |= PF_SWAPWRITE;	set_freezable(); 	/*	 * Our parent may run at a different priority, just set us to normal	 */	set_user_nice(current, 0); 	for (;;) {		struct task_struct *task = NULL;		struct backing_dev_info *bdi;		enum {			NO_ACTION,   /* Nothing to do */			FORK_THREAD, /* Fork bdi thread */			KILL_THREAD, /* Kill inactive bdi thread */		} action = NO_ACTION; 		/*		 * 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)) {			del_timer(&me->wakeup_timer);			wb_do_writeback(me, 0);		} 		spin_lock_bh(&bdi_lock);		/*		 * In the following loop we are going to check whether we have		 * some work to do without any synchronization with tasks		 * waking us up to do work for them. Set the task state here		 * so that we don't miss wakeups after verifying conditions.		 */		set_current_state(TASK_INTERRUPTIBLE); 		list_for_each_entry(bdi, &bdi_list, bdi_list) {			bool have_dirty_io; 			if (!bdi_cap_writeback_dirty(bdi) ||			     bdi_cap_flush_forker(bdi))				continue; 			WARN(!test_bit(BDI_registered, &bdi->state),			     "bdi %p/%s is not registered!\n", bdi, bdi->name); 			have_dirty_io = !list_empty(&bdi->work_list) ||					wb_has_dirty_io(&bdi->wb); 			/*			 * If the bdi has work to do, but the thread does not			 * exist - create it.			 */			if (!bdi->wb.task && have_dirty_io) {				/*				 * Set the pending bit - if someone will try to				 * unregister this bdi - it'll wait on this bit.				 */				set_bit(BDI_pending, &bdi->state);				action = FORK_THREAD;				break;			} 			spin_lock(&bdi->wb_lock); 			/*			 * If there is no work to do and the bdi thread was			 * inactive long enough - kill it. The wb_lock is taken			 * to make sure no-one adds more work to this bdi and			 * wakes the bdi thread up.			 */			if (bdi->wb.task && !have_dirty_io &&			    time_after(jiffies, bdi->wb.last_active +						bdi_longest_inactive())) {				task = bdi->wb.task;				bdi->wb.task = NULL;				spin_unlock(&bdi->wb_lock);				set_bit(BDI_pending, &bdi->state);				action = KILL_THREAD;				break;			}			spin_unlock(&bdi->wb_lock);		}		spin_unlock_bh(&bdi_lock); 		/* Keep working if default bdi still has things to do */		if (!list_empty(&me->bdi->work_list))			__set_current_state(TASK_RUNNING); 		switch (action) {		case FORK_THREAD:			__set_current_state(TASK_RUNNING);			task = kthread_create(bdi_writeback_thread, &bdi->wb,					      "flush-%s", dev_name(bdi->dev));			if (IS_ERR(task)) {				/*				 * If thread creation fails, force writeout of				 * the bdi from the thread. Hopefully 1024 is				 * large enough for efficient IO.				 */				writeback_inodes_wb(&bdi->wb, 1024,						    WB_REASON_FORKER_THREAD);			} else {				/*				 * The spinlock makes sure we do not lose				 * wake-ups when racing with 'bdi_queue_work()'.				 * And as soon as the bdi thread is visible, we				 * can start it.				 */				spin_lock_bh(&bdi->wb_lock);				bdi->wb.task = task;				spin_unlock_bh(&bdi->wb_lock);				wake_up_process(task);			}			bdi_clear_pending(bdi);			break; 		case KILL_THREAD:			__set_current_state(TASK_RUNNING);			kthread_stop(task);			bdi_clear_pending(bdi);			break; 		case NO_ACTION:			if (!wb_has_dirty_io(me) || !dirty_writeback_interval)				/*				 * There are no dirty data. The only thing we				 * should now care about is checking for				 * inactive bdi threads and killing them. Thus,				 * let's sleep for longer time, save energy and				 * be friendly for battery-driven devices.				 */				schedule_timeout(bdi_longest_inactive());			else				schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));			try_to_freeze();			break;		}	} 	return 0;} /* * 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_expedited();} int bdi_register(struct backing_dev_info *bdi, struct device *parent,		const char *fmt, ...){	va_list args;	struct device *dev; 	if (bdi->dev)	/* The driver needs to use separate queues per device */		return 0; 	va_start(args, fmt);	dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args);	va_end(args);	if (IS_ERR(dev))		return PTR_ERR(dev); 	bdi->dev = 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

Lines 1–500 of 856. Load more