Merge branch 'superblock-scaling' of... (061f98e9) · Commits · 方亚芬 / raspberrypi_linux

fs/block_dev.c

+6 −6

Original line number	Diff line number	Diff line
		@@ -1769,7 +1769,7 @@ void iterate_bdevs(void (func)(struct block_device , void ), void arg)
		{
		struct inode inode, old_inode = NULL;

		spin_lock(&inode_sb_list_lock);
		spin_lock(&blockdev_superblock->s_inode_list_lock);
		list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) {
		struct address_space *mapping = inode->i_mapping;

		@@ -1781,13 +1781,13 @@ void iterate_bdevs(void (func)(struct block_device , void ), void arg)
		}
		__iget(inode);
		spin_unlock(&inode->i_lock);
		spin_unlock(&inode_sb_list_lock);
		spin_unlock(&blockdev_superblock->s_inode_list_lock);
		/*
		* We hold a reference to 'inode' so it couldn't have been
		* removed from s_inodes list while we dropped the
		* inode_sb_list_lock. We cannot iput the inode now as we can
		* s_inode_list_lock We cannot iput the inode now as we can
		* be holding the last reference and we cannot iput it under
		* inode_sb_list_lock. So we keep the reference and iput it
		* s_inode_list_lock. So we keep the reference and iput it
		* later.
		*/
		iput(old_inode);
		@@ -1795,8 +1795,8 @@ void iterate_bdevs(void (func)(struct block_device , void ), void arg)

		func(I_BDEV(inode), arg);

		spin_lock(&inode_sb_list_lock);
		spin_lock(&blockdev_superblock->s_inode_list_lock);
		}
		spin_unlock(&inode_sb_list_lock);
		spin_unlock(&blockdev_superblock->s_inode_list_lock);
		iput(old_inode);
		}

fs/drop_caches.c

+6 −4

Original line number	Diff line number	Diff line
		@@ -17,7 +17,7 @@ static void drop_pagecache_sb(struct super_block sb, void unused)
		{
		struct inode inode, toput_inode = NULL;

		spin_lock(&inode_sb_list_lock);
		spin_lock(&sb->s_inode_list_lock);
		list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
		spin_lock(&inode->i_lock);
		if ((inode->i_state & (I_FREEING\|I_WILL_FREE\|I_NEW)) \|\|
		@@ -27,13 +27,15 @@ static void drop_pagecache_sb(struct super_block sb, void unused)
		}
		__iget(inode);
		spin_unlock(&inode->i_lock);
		spin_unlock(&inode_sb_list_lock);
		spin_unlock(&sb->s_inode_list_lock);

		invalidate_mapping_pages(inode->i_mapping, 0, -1);
		iput(toput_inode);
		toput_inode = inode;
		spin_lock(&inode_sb_list_lock);

		spin_lock(&sb->s_inode_list_lock);
		}
		spin_unlock(&inode_sb_list_lock);
		spin_unlock(&sb->s_inode_list_lock);
		iput(toput_inode);
		}

fs/fs-writeback.c

+43 −29

Original line number	Diff line number	Diff line
		@@ -88,7 +88,7 @@ unsigned int dirtytime_expire_interval = 12 * 60 * 60;

		static inline struct inode wb_inode(struct list_head head)
		{
		return list_entry(head, struct inode, i_wb_list);
		return list_entry(head, struct inode, i_io_list);
		}

		/*
		@@ -125,22 +125,22 @@ static void wb_io_lists_depopulated(struct bdi_writeback *wb)
		}

		/**
		* inode_wb_list_move_locked - move an inode onto a bdi_writeback IO list
		* inode_io_list_move_locked - move an inode onto a bdi_writeback IO list
		* @inode: inode to be moved
		* @wb: target bdi_writeback
		* @head: one of @wb->b_{dirty\|io\|more_io}
		*
		* Move @inode->i_wb_list to @list of @wb and set %WB_has_dirty_io.
		* Move @inode->i_io_list to @list of @wb and set %WB_has_dirty_io.
		* Returns %true if @inode is the first occupant of the !dirty_time IO
		* lists; otherwise, %false.
		*/
		static bool inode_wb_list_move_locked(struct inode *inode,
		static bool inode_io_list_move_locked(struct inode *inode,
		struct bdi_writeback *wb,
		struct list_head *head)
		{
		assert_spin_locked(&wb->list_lock);

		list_move(&inode->i_wb_list, head);
		list_move(&inode->i_io_list, head);

		/* dirty_time doesn't count as dirty_io until expiration */
		if (head != &wb->b_dirty_time)
		@@ -151,19 +151,19 @@ static bool inode_wb_list_move_locked(struct inode *inode,
		}

		/**
		* inode_wb_list_del_locked - remove an inode from its bdi_writeback IO list
		* inode_io_list_del_locked - remove an inode from its bdi_writeback IO list
		* @inode: inode to be removed
		* @wb: bdi_writeback @inode is being removed from
		*
		* Remove @inode which may be on one of @wb->b_{dirty\|io\|more_io} lists and
		* clear %WB_has_dirty_io if all are empty afterwards.
		*/
		static void inode_wb_list_del_locked(struct inode *inode,
		static void inode_io_list_del_locked(struct inode *inode,
		struct bdi_writeback *wb)
		{
		assert_spin_locked(&wb->list_lock);

		list_del_init(&inode->i_wb_list);
		list_del_init(&inode->i_io_list);
		wb_io_lists_depopulated(wb);
		}

		@@ -351,7 +351,7 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)

		/*
		* Once I_FREEING is visible under i_lock, the eviction path owns
		* the inode and we shouldn't modify ->i_wb_list.
		* the inode and we shouldn't modify ->i_io_list.
		*/
		if (unlikely(inode->i_state & I_FREEING))
		goto skip_switch;
		@@ -390,16 +390,16 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
		* is always correct including from ->b_dirty_time. The transfer
		* preserves @inode->dirtied_when ordering.
		*/
		if (!list_empty(&inode->i_wb_list)) {
		if (!list_empty(&inode->i_io_list)) {
		struct inode *pos;

		inode_wb_list_del_locked(inode, old_wb);
		inode_io_list_del_locked(inode, old_wb);
		inode->i_wb = new_wb;
		list_for_each_entry(pos, &new_wb->b_dirty, i_wb_list)
		list_for_each_entry(pos, &new_wb->b_dirty, i_io_list)
		if (time_after_eq(inode->dirtied_when,
		pos->dirtied_when))
		break;
		inode_wb_list_move_locked(inode, new_wb, pos->i_wb_list.prev);
		inode_io_list_move_locked(inode, new_wb, pos->i_io_list.prev);
		} else {
		inode->i_wb = new_wb;
		}
		@@ -961,12 +961,12 @@ void wb_start_background_writeback(struct bdi_writeback *wb)
		/*
		* Remove the inode from the writeback list it is on.
		*/
		void inode_wb_list_del(struct inode *inode)
		void inode_io_list_del(struct inode *inode)
		{
		struct bdi_writeback *wb;

		wb = inode_to_wb_and_lock_list(inode);
		inode_wb_list_del_locked(inode, wb);
		inode_io_list_del_locked(inode, wb);
		spin_unlock(&wb->list_lock);
		}

		@@ -988,7 +988,7 @@ static void redirty_tail(struct inode inode, struct bdi_writeback wb)
		if (time_before(inode->dirtied_when, tail->dirtied_when))
		inode->dirtied_when = jiffies;
		}
		inode_wb_list_move_locked(inode, wb, &wb->b_dirty);
		inode_io_list_move_locked(inode, wb, &wb->b_dirty);
		}

		/*
		@@ -996,7 +996,7 @@ static void redirty_tail(struct inode inode, struct bdi_writeback wb)
		*/
		static void requeue_io(struct inode inode, struct bdi_writeback wb)
		{
		inode_wb_list_move_locked(inode, wb, &wb->b_more_io);
		inode_io_list_move_locked(inode, wb, &wb->b_more_io);
		}

		static void inode_sync_complete(struct inode *inode)
		@@ -1055,7 +1055,7 @@ static int move_expired_inodes(struct list_head *delaying_queue,
		if (older_than_this &&
		inode_dirtied_after(inode, *older_than_this))
		break;
		list_move(&inode->i_wb_list, &tmp);
		list_move(&inode->i_io_list, &tmp);
		moved++;
		if (flags & EXPIRE_DIRTY_ATIME)
		set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state);
		@@ -1078,7 +1078,7 @@ static int move_expired_inodes(struct list_head *delaying_queue,
		list_for_each_prev_safe(pos, node, &tmp) {
		inode = wb_inode(pos);
		if (inode->i_sb == sb)
		list_move(&inode->i_wb_list, dispatch_queue);
		list_move(&inode->i_io_list, dispatch_queue);
		}
		}
		out:
		@@ -1232,10 +1232,10 @@ static void requeue_inode(struct inode inode, struct bdi_writeback wb,
		redirty_tail(inode, wb);
		} else if (inode->i_state & I_DIRTY_TIME) {
		inode->dirtied_when = jiffies;
		inode_wb_list_move_locked(inode, wb, &wb->b_dirty_time);
		inode_io_list_move_locked(inode, wb, &wb->b_dirty_time);
		} else {
		/* The inode is clean. Remove from writeback lists. */
		inode_wb_list_del_locked(inode, wb);
		inode_io_list_del_locked(inode, wb);
		}
		}

		@@ -1378,7 +1378,7 @@ writeback_single_inode(struct inode inode, struct bdi_writeback wb,
		* touch it. See comment above for explanation.
		*/
		if (!(inode->i_state & I_DIRTY_ALL))
		inode_wb_list_del_locked(inode, wb);
		inode_io_list_del_locked(inode, wb);
		spin_unlock(&wb->list_lock);
		inode_sync_complete(inode);
		out:
		@@ -1439,7 +1439,9 @@ static long writeback_sb_inodes(struct super_block *sb,
		unsigned long start_time = jiffies;
		long write_chunk;
		long wrote = 0; /* count both pages and inodes */
		struct blk_plug plug;

		blk_start_plug(&plug);
		while (!list_empty(&wb->b_io)) {
		struct inode *inode = wb_inode(wb->b_io.prev);

		@@ -1537,6 +1539,7 @@ static long writeback_sb_inodes(struct super_block *sb,
		break;
		}
		}
		blk_finish_plug(&plug);
		return wrote;
		}

		@@ -2088,7 +2091,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
		else
		dirty_list = &wb->b_dirty_time;

		wakeup_bdi = inode_wb_list_move_locked(inode, wb,
		wakeup_bdi = inode_io_list_move_locked(inode, wb,
		dirty_list);

		spin_unlock(&wb->list_lock);
		@@ -2111,6 +2114,15 @@ out_unlock_inode:
		}
		EXPORT_SYMBOL(__mark_inode_dirty);

		/*
		* The @s_sync_lock is used to serialise concurrent sync operations
		* to avoid lock contention problems with concurrent wait_sb_inodes() calls.
		* Concurrent callers will block on the s_sync_lock rather than doing contending
		* walks. The queueing maintains sync(2) required behaviour as all the IO that
		* has been issued up to the time this function is enter is guaranteed to be
		* completed by the time we have gained the lock and waited for all IO that is
		* in progress regardless of the order callers are granted the lock.
		*/
		static void wait_sb_inodes(struct super_block *sb)
		{
		struct inode inode, old_inode = NULL;
		@@ -2121,7 +2133,8 @@ static void wait_sb_inodes(struct super_block *sb)
		*/
		WARN_ON(!rwsem_is_locked(&sb->s_umount));

		spin_lock(&inode_sb_list_lock);
		mutex_lock(&sb->s_sync_lock);
		spin_lock(&sb->s_inode_list_lock);

		/*
		* Data integrity sync. Must wait for all pages under writeback,
		@@ -2141,14 +2154,14 @@ static void wait_sb_inodes(struct super_block *sb)
		}
		__iget(inode);
		spin_unlock(&inode->i_lock);
		spin_unlock(&inode_sb_list_lock);
		spin_unlock(&sb->s_inode_list_lock);

		/*
		* We hold a reference to 'inode' so it couldn't have been
		* removed from s_inodes list while we dropped the
		* inode_sb_list_lock. We cannot iput the inode now as we can
		* s_inode_list_lock. We cannot iput the inode now as we can
		* be holding the last reference and we cannot iput it under
		* inode_sb_list_lock. So we keep the reference and iput it
		* s_inode_list_lock. So we keep the reference and iput it
		* later.
		*/
		iput(old_inode);
		@@ -2158,10 +2171,11 @@ static void wait_sb_inodes(struct super_block *sb)

		cond_resched();

		spin_lock(&inode_sb_list_lock);
		spin_lock(&sb->s_inode_list_lock);
		}
		spin_unlock(&inode_sb_list_lock);
		spin_unlock(&sb->s_inode_list_lock);
		iput(old_inode);
		mutex_unlock(&sb->s_sync_lock);
		}

		static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr,

fs/inode.c

+31 −19

Original line number	Diff line number	Diff line
		@@ -28,16 +28,16 @@
		* inode->i_state, inode->i_hash, __iget()
		* Inode LRU list locks protect:
		* inode->i_sb->s_inode_lru, inode->i_lru
		* inode_sb_list_lock protects:
		* sb->s_inodes, inode->i_sb_list
		* inode->i_sb->s_inode_list_lock protects:
		* inode->i_sb->s_inodes, inode->i_sb_list
		* bdi->wb.list_lock protects:
		* bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_wb_list
		* bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_io_list
		* inode_hash_lock protects:
		* inode_hashtable, inode->i_hash
		*
		* Lock ordering:
		*
		* inode_sb_list_lock
		* inode->i_sb->s_inode_list_lock
		* inode->i_lock
		* Inode LRU list locks
		*
		@@ -45,7 +45,7 @@
		* inode->i_lock
		*
		* inode_hash_lock
		* inode_sb_list_lock
		* inode->i_sb->s_inode_list_lock
		* inode->i_lock
		*
		* iunique_lock
		@@ -57,8 +57,6 @@ static unsigned int i_hash_shift __read_mostly;
		static struct hlist_head *inode_hashtable __read_mostly;
		static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);

		__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock);

		/*
		* Empty aops. Can be used for the cases where the user does not
		* define any of the address_space operations.
		@@ -359,7 +357,7 @@ void inode_init_once(struct inode *inode)
		memset(inode, 0, sizeof(*inode));
		INIT_HLIST_NODE(&inode->i_hash);
		INIT_LIST_HEAD(&inode->i_devices);
		INIT_LIST_HEAD(&inode->i_wb_list);
		INIT_LIST_HEAD(&inode->i_io_list);
		INIT_LIST_HEAD(&inode->i_lru);
		address_space_init_once(&inode->i_data);
		i_size_ordered_init(inode);
		@@ -426,18 +424,18 @@ static void inode_lru_list_del(struct inode *inode)
		*/
		void inode_sb_list_add(struct inode *inode)
		{
		spin_lock(&inode_sb_list_lock);
		spin_lock(&inode->i_sb->s_inode_list_lock);
		list_add(&inode->i_sb_list, &inode->i_sb->s_inodes);
		spin_unlock(&inode_sb_list_lock);
		spin_unlock(&inode->i_sb->s_inode_list_lock);
		}
		EXPORT_SYMBOL_GPL(inode_sb_list_add);

		static inline void inode_sb_list_del(struct inode *inode)
		{
		if (!list_empty(&inode->i_sb_list)) {
		spin_lock(&inode_sb_list_lock);
		spin_lock(&inode->i_sb->s_inode_list_lock);
		list_del_init(&inode->i_sb_list);
		spin_unlock(&inode_sb_list_lock);
		spin_unlock(&inode->i_sb->s_inode_list_lock);
		}
		}

		@@ -527,8 +525,8 @@ static void evict(struct inode *inode)
		BUG_ON(!(inode->i_state & I_FREEING));
		BUG_ON(!list_empty(&inode->i_lru));

		if (!list_empty(&inode->i_wb_list))
		inode_wb_list_del(inode);
		if (!list_empty(&inode->i_io_list))
		inode_io_list_del(inode);

		inode_sb_list_del(inode);

		@@ -577,6 +575,7 @@ static void dispose_list(struct list_head *head)
		list_del_init(&inode->i_lru);

		evict(inode);
		cond_resched();
		}
		}

		@@ -594,7 +593,8 @@ void evict_inodes(struct super_block *sb)
		struct inode inode, next;
		LIST_HEAD(dispose);

		spin_lock(&inode_sb_list_lock);
		again:
		spin_lock(&sb->s_inode_list_lock);
		list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
		if (atomic_read(&inode->i_count))
		continue;
		@@ -609,8 +609,20 @@ void evict_inodes(struct super_block *sb)
		inode_lru_list_del(inode);
		spin_unlock(&inode->i_lock);
		list_add(&inode->i_lru, &dispose);

		/*
		* We can have a ton of inodes to evict at unmount time given
		* enough memory, check to see if we need to go to sleep for a
		* bit so we don't livelock.
		*/
		if (need_resched()) {
		spin_unlock(&sb->s_inode_list_lock);
		cond_resched();
		dispose_list(&dispose);
		goto again;
		}
		}
		spin_unlock(&inode_sb_list_lock);
		spin_unlock(&sb->s_inode_list_lock);

		dispose_list(&dispose);
		}
		@@ -631,7 +643,7 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
		struct inode inode, next;
		LIST_HEAD(dispose);

		spin_lock(&inode_sb_list_lock);
		spin_lock(&sb->s_inode_list_lock);
		list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
		spin_lock(&inode->i_lock);
		if (inode->i_state & (I_NEW \| I_FREEING \| I_WILL_FREE)) {
		@@ -654,7 +666,7 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
		spin_unlock(&inode->i_lock);
		list_add(&inode->i_lru, &dispose);
		}
		spin_unlock(&inode_sb_list_lock);
		spin_unlock(&sb->s_inode_list_lock);

		dispose_list(&dispose);

		@@ -890,7 +902,7 @@ struct inode new_inode(struct super_block sb)
		{
		struct inode *inode;

		spin_lock_prefetch(&inode_sb_list_lock);
		spin_lock_prefetch(&sb->s_inode_list_lock);

		inode = new_inode_pseudo(sb);
		if (inode)

fs/internal.h

+1 −2

Original line number	Diff line number	Diff line
		@@ -112,14 +112,13 @@ extern int vfs_open(const struct path , struct file , const struct cred *);
		/*
		* inode.c
		*/
		extern spinlock_t inode_sb_list_lock;
		extern long prune_icache_sb(struct super_block sb, struct shrink_control sc);
		extern void inode_add_lru(struct inode *inode);

		/*
		* fs-writeback.c
		*/
		extern void inode_wb_list_del(struct inode *inode);
		extern void inode_io_list_del(struct inode *inode);

		extern long get_nr_dirty_inodes(void);
		extern void evict_inodes(struct super_block *);