writeback: cgroup writeback support

index d726058..1456278 100644
@@ -55,9 +55,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
 	if (PagePrivate(page))
 		page->mapping->a_ops->invalidatepage(page, 0, PAGE_CACHE_SIZE);
 
-	if (TestClearPageDirty(page))
-		account_page_cleaned(page, mapping);
-
+	cancel_dirty_page(page);
 	ClearPageMappedToDisk(page);
 	ll_delete_from_page_cache(page);
 }

index efd85e0..e776bec 100644
@@ -3233,8 +3233,8 @@ int try_to_free_buffers(struct page *page)
 	 * to synchronise against __set_page_dirty_buffers and prevent the
 	 * dirty bit from being lost.
 	 */
-	if (ret && TestClearPageDirty(page))
-		account_page_cleaned(page, mapping);
+	if (ret)
+		cancel_dirty_page(page);
 	spin_unlock(&mapping->private_lock);
 out:
 	if (buffers_to_free) {

index 0755b9f..a83cf3a 100644
@@ -1215,6 +1215,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping);
 void account_page_cleaned(struct page *page, struct address_space *mapping);
 int set_page_dirty(struct page *page);
 int set_page_dirty_lock(struct page *page);
+void cancel_dirty_page(struct page *page);
 int clear_page_dirty_for_io(struct page *page);
 
 int get_cmdline(struct task_struct *task, char *buffer, int buflen);

index 5daf556..227b867 100644
@@ -2112,12 +2112,6 @@ EXPORT_SYMBOL(account_page_dirtied);
 
 /*
  * Helper function for deaccounting dirty page without writeback.
- *
- * Doing this should *normally* only ever be done when a page
- * is truncated, and is not actually mapped anywhere at all. However,
- * fs/buffer.c does this when it notices that somebody has cleaned
- * out all the buffers on a page without actually doing it through
- * the VM. Can you say "ext3 is horribly ugly"? Thought you could.
  */
 void account_page_cleaned(struct page *page, struct address_space *mapping)
 {

@@ -2127,7 +2121,6 @@ void account_page_cleaned(struct page *page, struct address_space *mapping)
 		task_io_account_cancelled_write(PAGE_CACHE_SIZE);
 	}
 }
-EXPORT_SYMBOL(account_page_cleaned);
 
 /*
  * For address_spaces which do not use buffers.  Just tag the page as dirty in

@@ -2266,6 +2259,26 @@ int set_page_dirty_lock(struct page *page)
 EXPORT_SYMBOL(set_page_dirty_lock);
 
 /*
+ * This cancels just the dirty bit on the kernel page itself, it does NOT
+ * actually remove dirty bits on any mmap's that may be around. It also
+ * leaves the page tagged dirty, so any sync activity will still find it on
+ * the dirty lists, and in particular, clear_page_dirty_for_io() will still
+ * look at the dirty bits in the VM.
+ *
+ * Doing this should *normally* only ever be done when a page is truncated,
+ * and is not actually mapped anywhere at all. However, fs/buffer.c does
+ * this when it notices that somebody has cleaned out all the buffers on a
+ * page without actually doing it through the VM. Can you say "ext3 is
+ * horribly ugly"? Thought you could.
+ */
+void cancel_dirty_page(struct page *page)
+{
+	if (TestClearPageDirty(page))
+		account_page_cleaned(page, page_mapping(page));
+}
+EXPORT_SYMBOL(cancel_dirty_page);
+
+/*
  * Clear a page's dirty flag, while caring for dirty memory accounting.
  * Returns true if the page was previously dirty.
  *

index 66af903..0c36025 100644
@@ -116,9 +116,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
 	 * the VM has canceled the dirty bit (eg ext3 journaling).
 	 * Hence dirty accounting check is placed after invalidation.
 	 */
-	if (TestClearPageDirty(page))
-		account_page_cleaned(page, mapping);
-
+	cancel_dirty_page(page);
 	ClearPageMappedToDisk(page);
 	delete_from_page_cache(page);
 	return 0;

index e776bec..c8aecf5 100644
@@ -623,21 +623,22 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
  *
  * If warn is true, then emit a warning if the page is not uptodate and has
  * not been truncated.
+ *
+ * The caller must hold mem_cgroup_begin_page_stat() lock.
  */
-static void __set_page_dirty(struct page *page,
-		struct address_space *mapping, int warn)
+static void __set_page_dirty(struct page *page, struct address_space *mapping,
+			     struct mem_cgroup *memcg, int warn)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&mapping->tree_lock, flags);
 	if (page->mapping) {	/* Race with truncate? */
 		WARN_ON_ONCE(warn && !PageUptodate(page));
-		account_page_dirtied(page, mapping);
+		account_page_dirtied(page, mapping, memcg);
 		radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 	}
 	spin_unlock_irqrestore(&mapping->tree_lock, flags);
-	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 }
 
 /*

@@ -668,6 +669,7 @@ static void __set_page_dirty(struct page *page,
 int __set_page_dirty_buffers(struct page *page)
 {
 	int newly_dirty;
+	struct mem_cgroup *memcg;
 	struct address_space *mapping = page_mapping(page);
 
 	if (unlikely(!mapping))

@@ -683,11 +685,22 @@ int __set_page_dirty_buffers(struct page *page)
 			bh = bh->b_this_page;
 		} while (bh != head);
 	}
+	/*
+	 * Use mem_group_begin_page_stat() to keep PageDirty synchronized with
+	 * per-memcg dirty page counters.
+	 */
+	memcg = mem_cgroup_begin_page_stat(page);
 	newly_dirty = !TestSetPageDirty(page);
 	spin_unlock(&mapping->private_lock);
 
 	if (newly_dirty)
-		__set_page_dirty(page, mapping, 1);
+		__set_page_dirty(page, mapping, memcg, 1);
+
+	mem_cgroup_end_page_stat(memcg);
+
+	if (newly_dirty)
+		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+
 	return newly_dirty;
 }
 EXPORT_SYMBOL(__set_page_dirty_buffers);

@@ -1158,11 +1171,18 @@ void mark_buffer_dirty(struct buffer_head *bh)
 
 	if (!test_set_buffer_dirty(bh)) {
 		struct page *page = bh->b_page;
+		struct address_space *mapping = NULL;
+		struct mem_cgroup *memcg;
+
+		memcg = mem_cgroup_begin_page_stat(page);
 		if (!TestSetPageDirty(page)) {
-			struct address_space *mapping = page_mapping(page);
+			mapping = page_mapping(page);
 			if (mapping)
-				__set_page_dirty(page, mapping, 0);
+				__set_page_dirty(page, mapping, memcg, 0);
 		}
+		mem_cgroup_end_page_stat(memcg);
+		if (mapping)
+			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 	}
 }
 EXPORT_SYMBOL(mark_buffer_dirty);

index 095f94c..e5099f2 100644
@@ -1873,6 +1873,7 @@ xfs_vm_set_page_dirty(
 	loff_t			end_offset;
 	loff_t			offset;
 	int			newly_dirty;
+	struct mem_cgroup	*memcg;
 
 	if (unlikely(!mapping))
 		return !TestSetPageDirty(page);

@@ -1892,6 +1893,11 @@ xfs_vm_set_page_dirty(
 			offset += 1 << inode->i_blkbits;
 		} while (bh != head);
 	}
+	/*
+	 * Use mem_group_begin_page_stat() to keep PageDirty synchronized with
+	 * per-memcg dirty page counters.
+	 */
+	memcg = mem_cgroup_begin_page_stat(page);
 	newly_dirty = !TestSetPageDirty(page);
 	spin_unlock(&mapping->private_lock);
 

@@ -1902,13 +1908,15 @@ xfs_vm_set_page_dirty(
 		spin_lock_irqsave(&mapping->tree_lock, flags);
 		if (page->mapping) {	/* Race with truncate? */
 			WARN_ON_ONCE(!PageUptodate(page));
-			account_page_dirtied(page, mapping);
+			account_page_dirtied(page, mapping, memcg);
 			radix_tree_tag_set(&mapping->page_tree,
 					page_index(page), PAGECACHE_TAG_DIRTY);
 		}
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
-		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 	}
+	mem_cgroup_end_page_stat(memcg);
+	if (newly_dirty)
+		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 	return newly_dirty;
 }
 

index 72dff5f..5fe6411 100644
@@ -41,6 +41,7 @@ enum mem_cgroup_stat_index {
 	MEM_CGROUP_STAT_RSS,		/* # of pages charged as anon rss */
 	MEM_CGROUP_STAT_RSS_HUGE,	/* # of pages charged as anon huge */
 	MEM_CGROUP_STAT_FILE_MAPPED,	/* # of pages charged as file rss */
+	MEM_CGROUP_STAT_DIRTY,          /* # of dirty pages in page cache */
 	MEM_CGROUP_STAT_WRITEBACK,	/* # of pages under writeback */
 	MEM_CGROUP_STAT_SWAP,		/* # of pages, swapped out */
 	MEM_CGROUP_STAT_NSTATS,

index a83cf3a..f48d979 100644
@@ -1211,8 +1211,10 @@ int __set_page_dirty_nobuffers(struct page *page);
 int __set_page_dirty_no_writeback(struct page *page);
 int redirty_page_for_writepage(struct writeback_control *wbc,
 				struct page *page);
-void account_page_dirtied(struct page *page, struct address_space *mapping);
-void account_page_cleaned(struct page *page, struct address_space *mapping);
+void account_page_dirtied(struct page *page, struct address_space *mapping,
+			  struct mem_cgroup *memcg);
+void account_page_cleaned(struct page *page, struct address_space *mapping,
+			  struct mem_cgroup *memcg);
 int set_page_dirty(struct page *page);
 int set_page_dirty_lock(struct page *page);
 void cancel_dirty_page(struct page *page);

index 4b3736f..fb0814c 100644
@@ -651,7 +651,8 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 				pgoff_t index, gfp_t gfp_mask);
 extern void delete_from_page_cache(struct page *page);
-extern void __delete_from_page_cache(struct page *page, void *shadow);
+extern void __delete_from_page_cache(struct page *page, void *shadow,
+				     struct mem_cgroup *memcg);
 int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
 
 /*

index 6bf5e42..7b1443d 100644
@@ -100,6 +100,7 @@
  *    ->tree_lock		(page_remove_rmap->set_page_dirty)
  *    bdi.wb->list_lock		(page_remove_rmap->set_page_dirty)
  *    ->inode->i_lock		(page_remove_rmap->set_page_dirty)
+ *    ->memcg->move_lock	(page_remove_rmap->mem_cgroup_begin_page_stat)
  *    bdi.wb->list_lock		(zap_pte_range->set_page_dirty)
  *    ->inode->i_lock		(zap_pte_range->set_page_dirty)
  *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)

@@ -174,9 +175,11 @@ static void page_cache_tree_delete(struct address_space *mapping,
 /*
  * Delete a page from the page cache and free it. Caller has to make
  * sure the page is locked and that nobody else uses it - or that usage
- * is safe.  The caller must hold the mapping's tree_lock.
+ * is safe.  The caller must hold the mapping's tree_lock and
+ * mem_cgroup_begin_page_stat().
  */
-void __delete_from_page_cache(struct page *page, void *shadow)
+void __delete_from_page_cache(struct page *page, void *shadow,
+			      struct mem_cgroup *memcg)
 {
 	struct address_space *mapping = page->mapping;
 

@@ -210,7 +213,7 @@ void __delete_from_page_cache(struct page *page, void *shadow)
 	 * anyway will be cleared before returning page into buddy allocator.
 	 */
 	if (WARN_ON_ONCE(PageDirty(page)))
-		account_page_cleaned(page, mapping);
+		account_page_cleaned(page, mapping, memcg);
 }
 
 /**

@@ -224,14 +227,20 @@ void __delete_from_page_cache(struct page *page, void *shadow)
 void delete_from_page_cache(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
+	struct mem_cgroup *memcg;
+	unsigned long flags;
+
 	void (*freepage)(struct page *);
 
 	BUG_ON(!PageLocked(page));
 
 	freepage = mapping->a_ops->freepage;
-	spin_lock_irq(&mapping->tree_lock);
-	__delete_from_page_cache(page, NULL);
-	spin_unlock_irq(&mapping->tree_lock);
+
+	memcg = mem_cgroup_begin_page_stat(page);
+	spin_lock_irqsave(&mapping->tree_lock, flags);
+	__delete_from_page_cache(page, NULL, memcg);
+	spin_unlock_irqrestore(&mapping->tree_lock, flags);
+	mem_cgroup_end_page_stat(memcg);
 
 	if (freepage)
 		freepage(page);

@@ -470,6 +479,8 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 	if (!error) {
 		struct address_space *mapping = old->mapping;
 		void (*freepage)(struct page *);
+		struct mem_cgroup *memcg;
+		unsigned long flags;
 
 		pgoff_t offset = old->index;
 		freepage = mapping->a_ops->freepage;

@@ -478,15 +489,17 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 		new->mapping = mapping;
 		new->index = offset;
 
-		spin_lock_irq(&mapping->tree_lock);
-		__delete_from_page_cache(old, NULL);
+		memcg = mem_cgroup_begin_page_stat(old);
+		spin_lock_irqsave(&mapping->tree_lock, flags);
+		__delete_from_page_cache(old, NULL, memcg);
 		error = radix_tree_insert(&mapping->page_tree, offset, new);
 		BUG_ON(error);
 		mapping->nrpages++;
 		__inc_zone_page_state(new, NR_FILE_PAGES);
 		if (PageSwapBacked(new))
 			__inc_zone_page_state(new, NR_SHMEM);
-		spin_unlock_irq(&mapping->tree_lock);
+		spin_unlock_irqrestore(&mapping->tree_lock, flags);
+		mem_cgroup_end_page_stat(memcg);
 		mem_cgroup_migrate(old, new, true);
 		radix_tree_preload_end();
 		if (freepage)

index 14c2f20..c23c1a3 100644
@@ -90,6 +90,7 @@ static const char * const mem_cgroup_stat_names[] = {
 	"rss",
 	"rss_huge",
 	"mapped_file",
+	"dirty",
 	"writeback",
 	"swap",
 };

@@ -2011,6 +2012,7 @@ struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page)
 
 	return memcg;
 }
+EXPORT_SYMBOL(mem_cgroup_begin_page_stat);
 
 /**
  * mem_cgroup_end_page_stat - finish a page state statistics transaction

@@ -2029,6 +2031,7 @@ void mem_cgroup_end_page_stat(struct mem_cgroup *memcg)
 
 	rcu_read_unlock();
 }
+EXPORT_SYMBOL(mem_cgroup_end_page_stat);
 
 /**
  * mem_cgroup_update_page_stat - update page state statistics

@@ -4746,6 +4749,7 @@ static int mem_cgroup_move_account(struct page *page,
 {
 	unsigned long flags;
 	int ret;
+	bool anon;
 
 	VM_BUG_ON(from == to);
 	VM_BUG_ON_PAGE(PageLRU(page), page);

@@ -4771,15 +4775,33 @@ static int mem_cgroup_move_account(struct page *page,
 	if (page->mem_cgroup != from)
 		goto out_unlock;
 
+	anon = PageAnon(page);
+
 	spin_lock_irqsave(&from->move_lock, flags);
 
-	if (!PageAnon(page) && page_mapped(page)) {
+	if (!anon && page_mapped(page)) {
 		__this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED],
 			       nr_pages);
 		__this_cpu_add(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED],
 			       nr_pages);
 	}
 
+	/*
+	 * move_lock grabbed above and caller set from->moving_account, so
+	 * mem_cgroup_update_page_stat() will serialize updates to PageDirty.
+	 * So mapping should be stable for dirty pages.
+	 */
+	if (!anon && PageDirty(page)) {
+		struct address_space *mapping = page_mapping(page);
+
+		if (mapping_cap_account_dirty(mapping)) {
+			__this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_DIRTY],
+				       nr_pages);
+			__this_cpu_add(to->stat->count[MEM_CGROUP_STAT_DIRTY],
+				       nr_pages);
+		}
+	}
+
 	if (PageWriteback(page)) {
 		__this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_WRITEBACK],
 			       nr_pages);

120 lines not on this page · raw message

index 24dd3f9..8fc556c 100644
@@ -30,6 +30,8 @@
  *             swap_lock (in swap_duplicate, swap_info_get)
  *               mmlist_lock (in mmput, drain_mmlist and others)
  *               mapping->private_lock (in __set_page_dirty_buffers)
+ *                 mem_cgroup_{begin,end}_page_stat (memcg->move_lock)
+ *                   mapping->tree_lock (widely used)
  *               inode->i_lock (in set_page_dirty's __mark_inode_dirty)
  *               bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
  *                 sb_lock (within inode_lock in fs/fs-writeback.c)

index 0c36025..76e35ad 100644
@@ -510,19 +510,24 @@ EXPORT_SYMBOL(invalidate_mapping_pages);
 static int
 invalidate_complete_page2(struct address_space *mapping, struct page *page)
 {
+	struct mem_cgroup *memcg;
+	unsigned long flags;
+
 	if (page->mapping != mapping)
 		return 0;
 
 	if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
 		return 0;
 
-	spin_lock_irq(&mapping->tree_lock);
+	memcg = mem_cgroup_begin_page_stat(page);
+	spin_lock_irqsave(&mapping->tree_lock, flags);
 	if (PageDirty(page))
 		goto failed;
 
 	BUG_ON(page_has_private(page));
-	__delete_from_page_cache(page, NULL);
-	spin_unlock_irq(&mapping->tree_lock);
+	__delete_from_page_cache(page, NULL, memcg);
+	spin_unlock_irqrestore(&mapping->tree_lock, flags);
+	mem_cgroup_end_page_stat(memcg);
 
 	if (mapping->a_ops->freepage)
 		mapping->a_ops->freepage(page);

@@ -530,7 +535,8 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 	page_cache_release(page);	/* pagecache ref */
 	return 1;
 failed:
-	spin_unlock_irq(&mapping->tree_lock);
+	spin_unlock_irqrestore(&mapping->tree_lock, flags);
+	mem_cgroup_end_page_stat(memcg);
 	return 0;
 }
 

index 5e8eadd..7582f9f 100644
@@ -579,10 +579,14 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 static int __remove_mapping(struct address_space *mapping, struct page *page,
 			    bool reclaimed)
 {
+	unsigned long flags;
+	struct mem_cgroup *memcg;
+
 	BUG_ON(!PageLocked(page));
 	BUG_ON(mapping != page_mapping(page));
 
-	spin_lock_irq(&mapping->tree_lock);
+	memcg = mem_cgroup_begin_page_stat(page);
+	spin_lock_irqsave(&mapping->tree_lock, flags);
 	/*
 	 * The non racy check for a busy page.
 	 *

@@ -620,7 +624,8 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		swp_entry_t swap = { .val = page_private(page) };
 		mem_cgroup_swapout(page, swap);
 		__delete_from_swap_cache(page);
-		spin_unlock_irq(&mapping->tree_lock);
+		spin_unlock_irqrestore(&mapping->tree_lock, flags);
+		mem_cgroup_end_page_stat(memcg);
 		swapcache_free(swap);
 	} else {
 		void (*freepage)(struct page *);

@@ -640,8 +645,9 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		if (reclaimed && page_is_file_cache(page) &&
 		    !mapping_exiting(mapping))
 			shadow = workingset_eviction(mapping, page);
-		__delete_from_page_cache(page, shadow);
-		spin_unlock_irq(&mapping->tree_lock);
+		__delete_from_page_cache(page, shadow, memcg);
+		spin_unlock_irqrestore(&mapping->tree_lock, flags);
+		mem_cgroup_end_page_stat(memcg);
 
 		if (freepage != NULL)
 			freepage(page);

@@ -650,7 +656,8 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 	return 1;
 
 cannot_free:
-	spin_unlock_irq(&mapping->tree_lock);
+	spin_unlock_irqrestore(&mapping->tree_lock, flags);
+	mem_cgroup_end_page_stat(memcg);
 	return 0;
 }
 

index 0ac817b..c3226ce 100644
@@ -19,7 +19,7 @@
 #include <linux/genhd.h>
 #include <linux/delay.h>
 #include <linux/atomic.h>
-#include "blk-cgroup.h"
+#include <linux/blk-cgroup.h>
 #include "blk.h"
 
 #define MAX_KEY_LEN 100

603 lines not on this page · raw message

index de474b5d..ed2427f 100644
@@ -32,12 +32,12 @@
 #include <linux/delay.h>
 #include <linux/ratelimit.h>
 #include <linux/pm_runtime.h>
+#include <linux/blk-cgroup.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/block.h>
 
 #include "blk.h"
-#include "blk-cgroup.h"
 #include "blk-mq.h"
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);

index faaf36a..5677eb7 100644
@@ -8,9 +8,9 @@
 #include <linux/blkdev.h>
 #include <linux/blktrace_api.h>
 #include <linux/blk-mq.h>
+#include <linux/blk-cgroup.h>
 
 #include "blk.h"
-#include "blk-cgroup.h"
 #include "blk-mq.h"
 
 struct queue_sysfs_entry {

index 5b9c6d5..b231935 100644
@@ -9,7 +9,7 @@
 #include <linux/blkdev.h>
 #include <linux/bio.h>
 #include <linux/blktrace_api.h>
-#include "blk-cgroup.h"
+#include <linux/blk-cgroup.h>
 #include "blk.h"
 
 /* Max dispatch from a group in 1 round */

index 5da8e6e..bc8f429 100644
@@ -14,8 +14,8 @@
 #include <linux/rbtree.h>
 #include <linux/ioprio.h>
 #include <linux/blktrace_api.h>
+#include <linux/blk-cgroup.h>
 #include "blk.h"
-#include "blk-cgroup.h"
 
 /*
  * tunables

index 59794d0..3bbb48f 100644
@@ -35,11 +35,11 @@
 #include <linux/hash.h>
 #include <linux/uaccess.h>
 #include <linux/pm_runtime.h>
+#include <linux/blk-cgroup.h>
 
 #include <trace/events/block.h>
 
 #include "blk.h"
-#include "blk-cgroup.h"
 
 static DEFINE_SPINLOCK(elv_list_lock);
 static LIST_HEAD(elv_list);

603 lines not on this page · raw message

index c567865..51f95b3 100644
@@ -558,8 +558,8 @@ static inline void blkg_rwstat_merge(struct blkg_rwstat *to,
 
 #else	/* CONFIG_BLK_CGROUP */
 
-struct cgroup;
-struct blkcg;
+struct blkcg {
+};
 
 struct blkg_policy_data {
 };

@@ -570,6 +570,8 @@ struct blkcg_gq {
 struct blkcg_policy {
 };
 
+#ifdef CONFIG_BLOCK
+
 static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
 static inline int blkcg_init_queue(struct request_queue *q) { return 0; }
 static inline void blkcg_drain_queue(struct request_queue *q) { }

@@ -599,5 +601,6 @@ static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q
 #define blk_queue_for_each_rl(rl, q)	\
 	for ((rl) = &(q)->root_rl; (rl); (rl) = NULL)
 
+#endif	/* CONFIG_BLOCK */
 #endif	/* CONFIG_BLK_CGROUP */
 #endif	/* _BLK_CGROUP_H */

index c3226ce..2a4f77f 100644
@@ -235,13 +235,8 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 	blkg->online = true;
 	spin_unlock(&blkcg->lock);
 
-	if (!ret) {
-		if (blkcg == &blkcg_root) {
-			q->root_blkg = blkg;
-			q->root_rl.blkg = blkg;
-		}
+	if (!ret)
 		return blkg;
-	}
 
 	/* @blkg failed fully initialized, use the usual release path */
 	blkg_put(blkg);

@@ -340,15 +335,6 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 		rcu_assign_pointer(blkcg->blkg_hint, NULL);
 
 	/*
-	 * If root blkg is destroyed.  Just clear the pointer since root_rl
-	 * does not take reference on root blkg.
-	 */
-	if (blkcg == &blkcg_root) {
-		blkg->q->root_blkg = NULL;
-		blkg->q->root_rl.blkg = NULL;
-	}
-
-	/*
 	 * Put the reference taken at the time of creation so that when all
 	 * queues are gone, group can be destroyed.
 	 */

@@ -855,9 +841,45 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
  */
 int blkcg_init_queue(struct request_queue *q)
 {
-	might_sleep();
+	struct blkcg_gq *new_blkg, *blkg;
+	bool preloaded;
+	int ret;
+
+	new_blkg = blkg_alloc(&blkcg_root, q, GFP_KERNEL);
+	if (!new_blkg)
+		return -ENOMEM;
+
+	preloaded = !radix_tree_preload(GFP_KERNEL);
 
-	return blk_throtl_init(q);
+	/*
+	 * Make sure the root blkg exists and count the existing blkgs.  As
+	 * @q is bypassing at this point, blkg_lookup_create() can't be
+	 * used.  Open code insertion.
+	 */
+	rcu_read_lock();
+	spin_lock_irq(q->queue_lock);
+	blkg = blkg_create(&blkcg_root, q, new_blkg);
+	spin_unlock_irq(q->queue_lock);
+	rcu_read_unlock();
+
+	if (preloaded)
+		radix_tree_preload_end();
+
+	if (IS_ERR(blkg)) {
+		kfree(new_blkg);
+		return PTR_ERR(blkg);
+	}
+
+	q->root_blkg = blkg;
+	q->root_rl.blkg = blkg;
+
+	ret = blk_throtl_init(q);
+	if (ret) {
+		spin_lock_irq(q->queue_lock);
+		blkg_destroy_all(q);
+		spin_unlock_irq(q->queue_lock);
+	}
+	return ret;
 }
 
 /**

@@ -958,52 +980,20 @@ int blkcg_activate_policy(struct request_queue *q,
 			  const struct blkcg_policy *pol)
 {
 	LIST_HEAD(pds);
-	struct blkcg_gq *blkg, *new_blkg;
+	struct blkcg_gq *blkg;
 	struct blkg_policy_data *pd, *n;
 	int cnt = 0, ret;
-	bool preloaded;
 
 	if (blkcg_policy_enabled(q, pol))
 		return 0;
 
-	/* preallocations for root blkg */
-	new_blkg = blkg_alloc(&blkcg_root, q, GFP_KERNEL);
-	if (!new_blkg)
-		return -ENOMEM;
-
+	/* count and allocate policy_data for all existing blkgs */
 	blk_queue_bypass_start(q);
-
-	preloaded = !radix_tree_preload(GFP_KERNEL);
-
-	/*
-	 * Make sure the root blkg exists and count the existing blkgs.  As
-	 * @q is bypassing at this point, blkg_lookup_create() can't be
-	 * used.  Open code it.
-	 */
 	spin_lock_irq(q->queue_lock);
-
-	rcu_read_lock();
-	blkg = __blkg_lookup(&blkcg_root, q, false);
-	if (blkg)
-		blkg_free(new_blkg);
-	else
-		blkg = blkg_create(&blkcg_root, q, new_blkg);
-	rcu_read_unlock();
-
-	if (preloaded)
-		radix_tree_preload_end();
-
-	if (IS_ERR(blkg)) {
-		ret = PTR_ERR(blkg);
-		goto out_unlock;
-	}
-
 	list_for_each_entry(blkg, &q->blkg_list, q_node)
 		cnt++;
-
 	spin_unlock_irq(q->queue_lock);
 
-	/* allocate policy_data for all existing blkgs */
 	while (cnt--) {
 		pd = kzalloc_node(pol->pd_size, GFP_KERNEL, q->node);
 		if (!pd) {

@@ -1072,10 +1062,6 @@ void blkcg_deactivate_policy(struct request_queue *q,
 
 	__clear_bit(pol->plid, q->blkcg_pols);
 
-	/* if no policy is left, no need for blkgs - shoot them down */
-	if (bitmap_empty(q->blkcg_pols, BLKCG_MAX_POLS))
-		blkg_destroy_all(q);
-
 	list_for_each_entry(blkg, &q->blkg_list, q_node) {
 		/* grab blkcg lock too while removing @pd from @blkg */
 		spin_lock(&blkg->blkcg->lock);

index 5fe6411..294498f 100644
@@ -68,6 +68,8 @@ enum mem_cgroup_events_index {
 };
 
 #ifdef CONFIG_MEMCG
+extern struct cgroup_subsys_state *mem_cgroup_root_css;
+
 void mem_cgroup_events(struct mem_cgroup *memcg,
 		       enum mem_cgroup_events_index idx,
 		       unsigned int nr);

@@ -196,6 +198,8 @@ void mem_cgroup_split_huge_fixup(struct page *head);
 #else /* CONFIG_MEMCG */
 struct mem_cgroup;
 
+#define mem_cgroup_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL))
+
 static inline void mem_cgroup_events(struct mem_cgroup *memcg,
 				     enum mem_cgroup_events_index idx,
 				     unsigned int nr)

index c23c1a3..b22a92b 100644
@@ -77,6 +77,7 @@ EXPORT_SYMBOL(memory_cgrp_subsys);
 
 #define MEM_CGROUP_RECLAIM_RETRIES	5
 static struct mem_cgroup *root_mem_cgroup __read_mostly;
+struct cgroup_subsys_state *mem_cgroup_root_css __read_mostly;
 
 /* Whether the swap controller is active */
 #ifdef CONFIG_MEMCG_SWAP

@@ -4441,6 +4442,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	/* root ? */
 	if (parent_css == NULL) {
 		root_mem_cgroup = memcg;
+		mem_cgroup_root_css = &memcg->css;
 		page_counter_init(&memcg->memory, NULL);
 		memcg->high = PAGE_COUNTER_MAX;
 		memcg->soft_limit = PAGE_COUNTER_MAX;

index 2a4f77f..54ec172 100644
@@ -30,6 +30,8 @@ struct blkcg blkcg_root = { .cfq_weight = 2 * CFQ_WEIGHT_DEFAULT,
 			    .cfq_leaf_weight = 2 * CFQ_WEIGHT_DEFAULT, };
 EXPORT_SYMBOL_GPL(blkcg_root);
 
+struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css;
+
 static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
 
 static bool blkcg_policy_enabled(struct request_queue *q,

index 51f95b3..65f0c17 100644
@@ -134,6 +134,7 @@ struct blkcg_policy {
 };
 
 extern struct blkcg blkcg_root;
+extern struct cgroup_subsys_state * const blkcg_root_css;
 
 struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q);
 struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,

@@ -570,6 +571,8 @@ struct blkcg_gq {
 struct blkcg_policy {
 };
 
+#define blkcg_root_css	((struct cgroup_subsys_state *)ERR_PTR(-EINVAL))
+
 #ifdef CONFIG_BLOCK
 
 static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }

index c2ff8a8..cb7faac 100644
@@ -2011,7 +2011,6 @@ EXPORT_SYMBOL(bioset_create_nobvec);
 int bio_associate_current(struct bio *bio)
 {
 	struct io_context *ioc;
-	struct cgroup_subsys_state *css;
 
 	if (bio->bi_ioc)
 		return -EBUSY;

@@ -2020,17 +2019,9 @@ int bio_associate_current(struct bio *bio)
 	if (!ioc)
 		return -ENOENT;
 
-	/* acquire active ref on @ioc and associate */
 	get_io_context_active(ioc);
 	bio->bi_ioc = ioc;
-
-	/* associate blkcg if exists */
-	rcu_read_lock();
-	css = task_css(current, blkio_cgrp_id);
-	if (css && css_tryget_online(css))
-		bio->bi_css = css;
-	rcu_read_unlock();
-
+	bio->bi_css = task_get_css(current, blkio_cgrp_id);
 	return 0;
 }
 

index b9cb94c..e7da0aa 100644
@@ -774,6 +774,31 @@ static inline struct cgroup_subsys_state *task_css(struct task_struct *task,
 }
 
 /**
+ * task_get_css - find and get the css for (task, subsys)
+ * @task: the target task
+ * @subsys_id: the target subsystem ID
+ *
+ * Find the css for the (@task, @subsys_id) combination, increment a
+ * reference on and return it.  This function is guaranteed to return a
+ * valid css.
+ */
+static inline struct cgroup_subsys_state *
+task_get_css(struct task_struct *task, int subsys_id)
+{
+	struct cgroup_subsys_state *css;
+
+	rcu_read_lock();
+	while (true) {
+		css = task_css(task, subsys_id);
+		if (likely(css_tryget_online(css)))
+			break;
+		cpu_relax();
+	}
+	rcu_read_unlock();
+	return css;
+}
+
+/**
  * task_css_is_root - test whether a task belongs to the root css
  * @task: the target task
  * @subsys_id: the target subsystem ID

index 65f0c17..4dc643f 100644
@@ -195,6 +195,12 @@ static inline struct blkcg *bio_blkcg(struct bio *bio)
 	return task_blkcg(current);
 }
 
+static inline struct cgroup_subsys_state *
+task_get_blkcg_css(struct task_struct *task)
+{
+	return task_get_css(task, blkio_cgrp_id);
+}
+
 /**
  * blkcg_parent - get the parent of a blkcg
  * @blkcg: blkcg of interest

@@ -573,6 +579,12 @@ struct blkcg_policy {
 
 #define blkcg_root_css	((struct cgroup_subsys_state *)ERR_PTR(-EINVAL))
 
+static inline struct cgroup_subsys_state *
+task_get_blkcg_css(struct task_struct *task)
+{
+	return NULL;
+}
+
 #ifdef CONFIG_BLOCK
 
 static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }

index cb7faac..494ffdb 100644
@@ -1995,6 +1995,28 @@ struct bio_set *bioset_create_nobvec(unsigned int pool_size, unsigned int front_
 EXPORT_SYMBOL(bioset_create_nobvec);
 
 #ifdef CONFIG_BLK_CGROUP
+
+/**
+ * bio_associate_blkcg - associate a bio with the specified blkcg
+ * @bio: target bio
+ * @blkcg_css: css of the blkcg to associate
+ *
+ * Associate @bio with the blkcg specified by @blkcg_css.  Block layer will
+ * treat @bio as if it were issued by a task which belongs to the blkcg.
+ *
+ * This function takes an extra reference of @blkcg_css which will be put
+ * when @bio is released.  The caller must own @bio and is responsible for
+ * synchronizing calls to this function.
+ */
+int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css)
+{
+	if (unlikely(bio->bi_css))
+		return -EBUSY;
+	css_get(blkcg_css);
+	bio->bi_css = blkcg_css;
+	return 0;
+}
+
 /**
  * bio_associate_current - associate a bio with %current
  * @bio: target bio

@@ -2012,7 +2034,7 @@ int bio_associate_current(struct bio *bio)
 {
 	struct io_context *ioc;
 
-	if (bio->bi_ioc)
+	if (bio->bi_css)
 		return -EBUSY;
 
 	ioc = current->io_context;

index 7486ea1..14260d1 100644
@@ -483,9 +483,12 @@ extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int);
 extern unsigned int bvec_nr_vecs(unsigned short idx);
 
 #ifdef CONFIG_BLK_CGROUP
+int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css);
 int bio_associate_current(struct bio *bio);
 void bio_disassociate_task(struct bio *bio);
 #else	/* CONFIG_BLK_CGROUP */
+static inline int bio_associate_blkcg(struct bio *bio,
+			struct cgroup_subsys_state *blkcg_css) { return 0; }
 static inline int bio_associate_current(struct bio *bio) { return -ENOENT; }
 static inline void bio_disassociate_task(struct bio *bio) { }
 #endif	/* CONFIG_BLK_CGROUP */

index 294498f..637ef62 100644
@@ -115,6 +115,7 @@ static inline bool mm_match_cgroup(struct mm_struct *mm,
 }
 
 extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
+extern struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
 
 struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
 				   struct mem_cgroup *,

index b22a92b..763f8f3 100644
@@ -598,6 +598,20 @@ struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg)
 	return &memcg->css;
 }
 
+/**
+ * mem_cgroup_css_from_page - css of the memcg associated with a page
+ * @page: page of interest
+ *
+ * This function is guaranteed to return a valid cgroup_subsys_state and
+ * the returned css remains accessible until @page is released.
+ */
+struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
+{
+	if (page->mem_cgroup)
+		return &page->mem_cgroup->css;
+	return &root_mem_cgroup->css;
+}
+
 static struct mem_cgroup_per_zone *
 mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page)
 {

index 294498f..637ef62 100644
@@ -115,6 +115,7 @@ static inline bool mm_match_cgroup(struct mm_struct *mm,
 }
 
 extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
+extern struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
 
 struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
 				   struct mem_cgroup *,

index b22a92b..c76b85c 100644
@@ -598,6 +598,37 @@ struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg)
 	return &memcg->css;
 }
 
+/**
+ * mem_cgroup_css_from_page - css of the memcg associated with a page
+ * @page: page of interest
+ *
+ * This function is guaranteed to return a valid cgroup_subsys_state and
+ * the returned css remains associated with @page until it is released.
+ *
+ * This can only be used on the default hierarchy as @page's memcg
+ * association may change on the traditional hierarchies.  Use
+ * try_get_mem_cgroup_from_page() instead on the traditional hierarchies.
+ *
+ * XXX: The above comment isn't true yet as mem_cgroup_migrate() can modify
+ *      the association before @page is released even on the default
+ *      hierarchy; however, the current and planned usages don't mix the
+ *      the two functions and mem_cgroup_migrate() will soon be updated to
+ *      make the invariant actually true.
+ */
+struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
+{
+	struct cgroup_subsys_state *css;
+
+	if (page->mem_cgroup)
+		css = &page->mem_cgroup->css;
+	else
+		css = &root_mem_cgroup->css;
+
+	WARN_ON_ONCE(!cgroup_on_dfl(css->cgroup));
+
+	return css;
+}
+
 static struct mem_cgroup_per_zone *
 mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page)
 {

index 294498f..637ef62 100644
@@ -115,6 +115,7 @@ static inline bool mm_match_cgroup(struct mm_struct *mm,
 }
 
 extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
+extern struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
 
 struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
 				   struct mem_cgroup *,

index b22a92b..c856cec 100644
@@ -598,6 +598,37 @@ struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg)
 	return &memcg->css;
 }
 
+/**
+ * mem_cgroup_css_from_page - css of the memcg associated with a page
+ * @page: page of interest
+ *
+ * This function is guaranteed to return a valid cgroup_subsys_state and
+ * the returned css remains associated with @page until it is released.
+ *
+ * This can only be used on the default hierarchy as @page's memcg
+ * association may change on the traditional hierarchies.  Use
+ * try_get_mem_cgroup_from_page() instead on the traditional hierarchies.
+ *
+ * XXX: The above comment isn't true yet as replace_page_cache_page() can
+ *      modify the association before @page is released even on the default
+ *      hierarchy; however, the current and planned usages don't mix the
+ *      the two functions and replace_page_cache_page() will soon be
+ *      updated to make the invariant actually true.
+ */
+struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
+{
+	struct cgroup_subsys_state *css;
+
+	if (page->mem_cgroup)
+		css = &page->mem_cgroup->css;
+	else
+		css = &root_mem_cgroup->css;
+
+	WARN_ON_ONCE(!cgroup_on_dfl(css->cgroup));
+
+	return css;
+}
+
 static struct mem_cgroup_per_zone *
 mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page)
 {

index 294498f..637ef62 100644
@@ -115,6 +115,7 @@ static inline bool mm_match_cgroup(struct mm_struct *mm,
 }
 
 extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
+extern struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
 
 struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
 				   struct mem_cgroup *,

index b22a92b..5c270a0 100644
@@ -598,6 +598,39 @@ struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg)
 	return &memcg->css;
 }
 
+/**
+ * mem_cgroup_css_from_page - css of the memcg associated with a page
+ * @page: page of interest
+ *
+ * If memcg is bound to the default hierarchy, css of the memcg associated
+ * with @page is returned.  The returned css remains associated with @page
+ * until it is released.
+ *
+ * If memcg is bound to a traditional hierarchy, the css of root_mem_cgroup
+ * is returned.
+ *
+ * XXX: The above description of behavior on the default hierarchy isn't
+ * strictly true yet as replace_page_cache_page() can modify the
+ * association before @page is released even on the default hierarchy;
+ * however, the current and planned usages don't mix the the two functions
+ * and replace_page_cache_page() will soon be updated to make the invariant
+ * actually true.
+ */
+struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
+{
+	struct mem_cgroup *memcg;
+
+	rcu_read_lock();
+
+	memcg = page->mem_cgroup;
+
+	if (!memcg || !cgroup_on_dfl(memcg->css.cgroup))
+		memcg = root_mem_cgroup;
+
+	rcu_read_unlock();
+	return &memcg->css;
+}
+
 static struct mem_cgroup_per_zone *
 mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page)
 {

index ed2427f..f46688f 100644
@@ -620,7 +620,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 	q->backing_dev_info.ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
-	q->backing_dev_info.state = 0;
 	q->backing_dev_info.capabilities = 0;
 	q->backing_dev_info.name = "block";
 	q->node = node_id;

index 81fde9e..a151853 100644
@@ -2359,7 +2359,7 @@ static void drbd_cleanup(void)
  * @congested_data:	User data
  * @bdi_bits:		Bits the BDI flusher thread is currently interested in
  *
- * Returns 1<<BDI_async_congested and/or 1<<BDI_sync_congested if we are congested.
+ * Returns 1<<WB_async_congested and/or 1<<WB_sync_congested if we are congested.
  */
 static int drbd_congested(void *congested_data, int bdi_bits)
 {

@@ -2376,14 +2376,14 @@ static int drbd_congested(void *congested_data, int bdi_bits)
 	}
 
 	if (test_bit(CALLBACK_PENDING, &first_peer_device(device)->connection->flags)) {
-		r |= (1 << BDI_async_congested);
+		r |= (1 << WB_async_congested);
 		/* Without good local data, we would need to read from remote,
 		 * and that would need the worker thread as well, which is
 		 * currently blocked waiting for that usermode helper to
 		 * finish.
 		 */
 		if (!get_ldev_if_state(device, D_UP_TO_DATE))
-			r |= (1 << BDI_sync_congested);
+			r |= (1 << WB_sync_congested);
 		else
 			put_ldev(device);
 		r &= bdi_bits;

@@ -2399,9 +2399,9 @@ static int drbd_congested(void *congested_data, int bdi_bits)
 			reason = 'b';
 	}
 
-	if (bdi_bits & (1 << BDI_async_congested) &&
+	if (bdi_bits & (1 << WB_async_congested) &&
 	    test_bit(NET_CONGESTED, &first_peer_device(device)->connection->flags)) {
-		r |= (1 << BDI_async_congested);
+		r |= (1 << WB_async_congested);
 		reason = reason == 'b' ? 'a' : 'n';
 	}
 

index a930b72..081fb1e 100644
@@ -2162,7 +2162,7 @@ static int dm_any_congested(void *congested_data, int bdi_bits)
 			 * the query about congestion status of request_queue
 			 */
 			if (dm_request_based(md))
-				r = md->queue->backing_dev_info.state &
+				r = md->queue->backing_dev_info.wb.state &
 				    bdi_bits;
 			else
 				r = dm_table_any_congested(map, bdi_bits);

index 9157a29..f80f1af 100644
@@ -745,7 +745,7 @@ static int raid1_congested(struct mddev *mddev, int bits)
 	struct r1conf *conf = mddev->private;
 	int i, ret = 0;
 
-	if ((bits & (1 << BDI_async_congested)) &&
+	if ((bits & (1 << WB_async_congested)) &&
 	    conf->pending_count >= max_queued_requests)
 		return 1;
 

@@ -760,7 +760,7 @@ static int raid1_congested(struct mddev *mddev, int bits)
 			/* Note the '|| 1' - when read_balance prefers
 			 * non-congested targets, it can be removed
 			 */
-			if ((bits & (1<<BDI_async_congested)) || 1)
+			if ((bits & (1 << WB_async_congested)) || 1)
 				ret |= bdi_congested(&q->backing_dev_info, bits);
 			else
 				ret &= bdi_congested(&q->backing_dev_info, bits);

index e793ab6..fca8257 100644
@@ -914,7 +914,7 @@ static int raid10_congested(struct mddev *mddev, int bits)
 	struct r10conf *conf = mddev->private;
 	int i, ret = 0;
 
-	if ((bits & (1 << BDI_async_congested)) &&
+	if ((bits & (1 << WB_async_congested)) &&
 	    conf->pending_count >= max_queued_requests)
 		return 1;
 

index 32a8bbd..983312c 100644
@@ -74,7 +74,7 @@ unsigned int dirtytime_expire_interval = 12 * 60 * 60;
  */
 int writeback_in_progress(struct backing_dev_info *bdi)
 {
-	return test_bit(BDI_writeback_running, &bdi->state);
+	return test_bit(WB_writeback_running, &bdi->wb.state);
 }
 EXPORT_SYMBOL(writeback_in_progress);
 

@@ -112,7 +112,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage);
 static void bdi_wakeup_thread(struct backing_dev_info *bdi)
 {
 	spin_lock_bh(&bdi->wb_lock);
-	if (test_bit(BDI_registered, &bdi->state))
+	if (test_bit(WB_registered, &bdi->wb.state))
 		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
 	spin_unlock_bh(&bdi->wb_lock);
 }

@@ -123,7 +123,7 @@ static void bdi_queue_work(struct backing_dev_info *bdi,
 	trace_writeback_queue(bdi, work);
 
 	spin_lock_bh(&bdi->wb_lock);
-	if (!test_bit(BDI_registered, &bdi->state)) {
+	if (!test_bit(WB_registered, &bdi->wb.state)) {
 		if (work->done)
 			complete(work->done);
 		goto out_unlock;

@@ -1057,7 +1057,7 @@ static long wb_do_writeback(struct bdi_writeback *wb)
 	struct wb_writeback_work *work;
 	long wrote = 0;
 
-	set_bit(BDI_writeback_running, &wb->bdi->state);
+	set_bit(WB_writeback_running, &wb->state);
 	while ((work = get_next_work_item(bdi)) != NULL) {
 
 		trace_writeback_exec(bdi, work);

@@ -1079,7 +1079,7 @@ static long wb_do_writeback(struct bdi_writeback *wb)
 	 */
 	wrote += wb_check_old_data_flush(wb);
 	wrote += wb_check_background_flush(wb);
-	clear_bit(BDI_writeback_running, &wb->bdi->state);
+	clear_bit(WB_writeback_running, &wb->state);
 
 	return wrote;
 }

@@ -1099,7 +1099,7 @@ void bdi_writeback_workfn(struct work_struct *work)
 	current->flags |= PF_SWAPWRITE;
 
 	if (likely(!current_is_workqueue_rescuer() ||
-		   !test_bit(BDI_registered, &bdi->state))) {
+		   !test_bit(WB_registered, &wb->state))) {
 		/*
 		 * The normal path.  Keep writing back @bdi until its
 		 * work_list is empty.  Note that this path is also taken

@@ -1323,7 +1323,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			spin_unlock(&inode->i_lock);
 			spin_lock(&bdi->wb.list_lock);
 			if (bdi_cap_writeback_dirty(bdi)) {
-				WARN(!test_bit(BDI_registered, &bdi->state),
+				WARN(!test_bit(WB_registered, &bdi->wb.state),
 				     "bdi-%s not registered\n", bdi->name);
 
 				/*

index aff923a..eb14f98 100644
@@ -25,13 +25,13 @@ struct device;
 struct dentry;
 
 /*
- * Bits in backing_dev_info.state
+ * Bits in bdi_writeback.state
  */
-enum bdi_state {
-	BDI_async_congested,	/* The async (write) queue is getting full */
-	BDI_sync_congested,	/* The sync queue is getting full */
-	BDI_registered,		/* bdi_register() was done */
-	BDI_writeback_running,	/* Writeback is in progress */
+enum wb_state {
+	WB_async_congested,	/* The async (write) queue is getting full */
+	WB_sync_congested,	/* The sync queue is getting full */
+	WB_registered,		/* bdi_register() was done */
+	WB_writeback_running,	/* Writeback is in progress */
 };
 
 typedef int (congested_fn)(void *, int);

@@ -49,6 +49,7 @@ enum bdi_stat_item {
 struct bdi_writeback {
 	struct backing_dev_info *bdi;	/* our parent bdi */
 
+	unsigned long state;		/* Always use atomic bitops on this */
 	unsigned long last_old_flush;	/* last old data flush */
 
 	struct delayed_work dwork;	/* work item used for writeback */

@@ -62,7 +63,6 @@ struct bdi_writeback {
 struct backing_dev_info {
 	struct list_head bdi_list;
 	unsigned long ra_pages;	/* max readahead in PAGE_CACHE_SIZE units */
-	unsigned long state;	/* Always use atomic bitops on this */
 	unsigned int capabilities; /* Device capabilities */
 	congested_fn *congested_fn; /* Function pointer if device is md/dm */
 	void *congested_data;	/* Pointer to aux data for congested func */

@@ -250,23 +250,23 @@ static inline int bdi_congested(struct backing_dev_info *bdi, int bdi_bits)
 {
 	if (bdi->congested_fn)
 		return bdi->congested_fn(bdi->congested_data, bdi_bits);
-	return (bdi->state & bdi_bits);
+	return (bdi->wb.state & bdi_bits);
 }
 
 static inline int bdi_read_congested(struct backing_dev_info *bdi)
 {
-	return bdi_congested(bdi, 1 << BDI_sync_congested);
+	return bdi_congested(bdi, 1 << WB_sync_congested);
 }
 
 static inline int bdi_write_congested(struct backing_dev_info *bdi)
 {
-	return bdi_congested(bdi, 1 << BDI_async_congested);
+	return bdi_congested(bdi, 1 << WB_async_congested);
 }
 
 static inline int bdi_rw_congested(struct backing_dev_info *bdi)
 {
-	return bdi_congested(bdi, (1 << BDI_sync_congested) |
-				  (1 << BDI_async_congested));
+	return bdi_congested(bdi, (1 << WB_sync_congested) |
+				  (1 << WB_async_congested));
 }
 
 enum {

index 6dc4580..b23cf0e 100644
@@ -96,7 +96,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 		   nr_io,
 		   nr_more_io,
 		   nr_dirty_time,
-		   !list_empty(&bdi->bdi_list), bdi->state);
+		   !list_empty(&bdi->bdi_list), bdi->wb.state);
 #undef K
 
 	return 0;

@@ -280,7 +280,7 @@ void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
 
 	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
 	spin_lock_bh(&bdi->wb_lock);
-	if (test_bit(BDI_registered, &bdi->state))
+	if (test_bit(WB_registered, &bdi->wb.state))
 		queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
 	spin_unlock_bh(&bdi->wb_lock);
 }

@@ -315,7 +315,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 	bdi->dev = dev;
 
 	bdi_debug_register(bdi, dev_name(dev));
-	set_bit(BDI_registered, &bdi->state);
+	set_bit(WB_registered, &bdi->wb.state);
 
 	spin_lock_bh(&bdi_lock);
 	list_add_tail_rcu(&bdi->bdi_list, &bdi_list);

@@ -339,7 +339,7 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 {
 	/* Make sure nobody queues further work */
 	spin_lock_bh(&bdi->wb_lock);
-	if (!test_and_clear_bit(BDI_registered, &bdi->state)) {
+	if (!test_and_clear_bit(WB_registered, &bdi->wb.state)) {
 		spin_unlock_bh(&bdi->wb_lock);
 		return;
 	}

@@ -492,11 +492,11 @@ static atomic_t nr_bdi_congested[2];
 
 void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
-	enum bdi_state bit;
+	enum wb_state bit;
 	wait_queue_head_t *wqh = &congestion_wqh[sync];
 
-	bit = sync ? BDI_sync_congested : BDI_async_congested;
-	if (test_and_clear_bit(bit, &bdi->state))
+	bit = sync ? WB_sync_congested : WB_async_congested;
+	if (test_and_clear_bit(bit, &bdi->wb.state))
 		atomic_dec(&nr_bdi_congested[sync]);
 	smp_mb__after_atomic();
 	if (waitqueue_active(wqh))

@@ -506,10 +506,10 @@ EXPORT_SYMBOL(clear_bdi_congested);
 
 void set_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
-	enum bdi_state bit;
+	enum wb_state bit;
 
-	bit = sync ? BDI_sync_congested : BDI_async_congested;
-	if (!test_and_set_bit(bit, &bdi->state))
+	bit = sync ? WB_sync_congested : WB_async_congested;
+	if (!test_and_set_bit(bit, &bdi->wb.state))
 		atomic_inc(&nr_bdi_congested[sync]);
 }
 EXPORT_SYMBOL(set_bdi_congested);

index 983312c..8873ecd 100644
@@ -840,7 +840,7 @@ static bool over_bground_thresh(struct backing_dev_info *bdi)
 	    global_page_state(NR_UNSTABLE_NFS) > background_thresh)
 		return true;
 
-	if (bdi_stat(bdi, BDI_RECLAIMABLE) >
+	if (wb_stat(&bdi->wb, WB_RECLAIMABLE) >
 				bdi_dirty_limit(bdi, background_thresh))
 		return true;
 

index 5ef05b5..8c5e2fa 100644
@@ -1445,9 +1445,9 @@ static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req)
 
 	list_del(&req->writepages_entry);
 	for (i = 0; i < req->num_pages; i++) {
-		dec_bdi_stat(bdi, BDI_WRITEBACK);
+		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
 		dec_zone_page_state(req->pages[i], NR_WRITEBACK_TEMP);
-		bdi_writeout_inc(bdi);
+		wb_writeout_inc(&bdi->wb);
 	}
 	wake_up(&fi->page_waitq);
 }

@@ -1634,7 +1634,7 @@ static int fuse_writepage_locked(struct page *page)
 	req->end = fuse_writepage_end;
 	req->inode = inode;
 
-	inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK);
+	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
 	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	spin_lock(&fc->lock);

@@ -1749,9 +1749,9 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req,
 		copy_highpage(old_req->pages[0], page);
 		spin_unlock(&fc->lock);
 
-		dec_bdi_stat(bdi, BDI_WRITEBACK);
+		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
 		dec_zone_page_state(page, NR_WRITEBACK_TEMP);
-		bdi_writeout_inc(bdi);
+		wb_writeout_inc(&bdi->wb);
 		fuse_writepage_free(fc, new_req);
 		fuse_request_free(new_req);
 		goto out;

@@ -1848,7 +1848,7 @@ static int fuse_writepages_fill(struct page *page,
 	req->page_descs[req->num_pages].offset = 0;
 	req->page_descs[req->num_pages].length = PAGE_SIZE;
 
-	inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK);
+	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
 	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	err = 0;

index 9e6475b..7e3c460 100644
@@ -607,7 +607,7 @@ void nfs_mark_page_unstable(struct page *page)
 	struct inode *inode = page_file_mapping(page)->host;
 
 	inc_zone_page_state(page, NR_UNSTABLE_NFS);
-	inc_bdi_stat(inode_to_bdi(inode), BDI_RECLAIMABLE);
+	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_RECLAIMABLE);
 	 __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
 }
 

index d12a4be..94c7ce0 100644
@@ -853,7 +853,8 @@ static void
 nfs_clear_page_commit(struct page *page)
 {
 	dec_zone_page_state(page, NR_UNSTABLE_NFS);
-	dec_bdi_stat(inode_to_bdi(page_file_mapping(page)->host), BDI_RECLAIMABLE);
+	dec_wb_stat(&inode_to_bdi(page_file_mapping(page)->host)->wb,
+		    WB_RECLAIMABLE);
 }
 
 /* Called holding inode (/cinfo) lock */

139 lines not on this page · raw message

117 lines not on this page · raw message

136 lines not on this page · raw message

index 8ab0cf1..d211602 100644
@@ -53,7 +53,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 							PAGE_CACHE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
 	} else if (type == DIRTY_DENTS) {
-		if (sbi->sb->s_bdi->dirty_exceeded)
+		if (sbi->sb->s_bdi->wb.dirty_exceeded)
 			return false;
 		mem_size = get_pages(sbi, F2FS_DIRTY_DENTS);
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);

@@ -70,7 +70,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 				sizeof(struct extent_node)) >> PAGE_CACHE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
 	} else {
-		if (sbi->sb->s_bdi->dirty_exceeded)
+		if (sbi->sb->s_bdi->wb.dirty_exceeded)
 			return false;
 	}
 	return res;

index 85d7fa7..6408989 100644
@@ -713,7 +713,7 @@ static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi)
  */
 static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
 {
-	if (sbi->sb->s_bdi->dirty_exceeded)
+	if (sbi->sb->s_bdi->wb.dirty_exceeded)
 		return 0;
 
 	if (type == DATA)

index 8873ecd..1945cb9 100644
@@ -624,7 +624,7 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	return ret;
 }
 
-static long writeback_chunk_size(struct backing_dev_info *bdi,
+static long writeback_chunk_size(struct bdi_writeback *wb,
 				 struct wb_writeback_work *work)
 {
 	long pages;

@@ -645,7 +645,7 @@ static long writeback_chunk_size(struct backing_dev_info *bdi,
 	if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages)
 		pages = LONG_MAX;
 	else {
-		pages = min(bdi->avg_write_bandwidth / 2,
+		pages = min(wb->avg_write_bandwidth / 2,
 			    global_dirty_limit / DIRTY_SCOPE);
 		pages = min(pages, work->nr_pages);
 		pages = round_down(pages + MIN_WRITEBACK_PAGES,

@@ -743,7 +743,7 @@ static long writeback_sb_inodes(struct super_block *sb,
 		inode->i_state |= I_SYNC;
 		spin_unlock(&inode->i_lock);
 
-		write_chunk = writeback_chunk_size(wb->bdi, work);
+		write_chunk = writeback_chunk_size(wb, work);
 		wbc.nr_to_write = write_chunk;
 		wbc.pages_skipped = 0;
 

@@ -830,7 +830,7 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
 	return nr_pages - work.nr_pages;
 }
 
-static bool over_bground_thresh(struct backing_dev_info *bdi)
+static bool over_bground_thresh(struct bdi_writeback *wb)
 {
 	unsigned long background_thresh, dirty_thresh;
 

@@ -840,8 +840,7 @@ static bool over_bground_thresh(struct backing_dev_info *bdi)
 	    global_page_state(NR_UNSTABLE_NFS) > background_thresh)
 		return true;
 
-	if (wb_stat(&bdi->wb, WB_RECLAIMABLE) >
-				bdi_dirty_limit(bdi, background_thresh))
+	if (wb_stat(wb, WB_RECLAIMABLE) > wb_dirty_limit(wb, background_thresh))
 		return true;
 
 	return false;

@@ -854,7 +853,7 @@ static bool over_bground_thresh(struct backing_dev_info *bdi)
 static void wb_update_bandwidth(struct bdi_writeback *wb,
 				unsigned long start_time)
 {
-	__bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, 0, start_time);
+	__wb_update_bandwidth(wb, 0, 0, 0, 0, 0, start_time);
 }
 
 /*

@@ -906,7 +905,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 * For background writeout, stop when we are below the
 		 * background dirty threshold
 		 */
-		if (work->for_background && !over_bground_thresh(wb->bdi))
+		if (work->for_background && !over_bground_thresh(wb))
 			break;
 
 		/*

@@ -998,7 +997,7 @@ static unsigned long get_nr_dirty_pages(void)
 
 static long wb_check_background_flush(struct bdi_writeback *wb)
 {
-	if (over_bground_thresh(wb->bdi)) {
+	if (over_bground_thresh(wb)) {
 
 		struct wb_writeback_work work = {
 			.nr_pages	= LONG_MAX,

index 859c6ed..2982445 100644
@@ -748,7 +748,7 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
 
 	if (wbc->sync_mode == WB_SYNC_ALL)
 		gfs2_log_flush(GFS2_SB(inode), ip->i_gl, NORMAL_FLUSH);
-	if (bdi->dirty_exceeded)
+	if (bdi->wb.dirty_exceeded)
 		gfs2_ail1_flush(sdp, wbc);
 	else
 		filemap_fdatawrite(metamapping);

index fe7a907..2ab0604 100644
@@ -60,16 +60,6 @@ struct bdi_writeback {
 	spinlock_t list_lock;		/* protects the b_* lists */
 
 	struct percpu_counter stat[NR_WB_STAT_ITEMS];
-};
-
-struct backing_dev_info {
-	struct list_head bdi_list;
-	unsigned long ra_pages;	/* max readahead in PAGE_CACHE_SIZE units */
-	unsigned int capabilities; /* Device capabilities */
-	congested_fn *congested_fn; /* Function pointer if device is md/dm */
-	void *congested_data;	/* Pointer to aux data for congested func */
-
-	char *name;
 
 	unsigned long bw_time_stamp;	/* last time write bw is updated */
 	unsigned long dirtied_stamp;

@@ -88,6 +78,16 @@ struct backing_dev_info {
 
 	struct fprop_local_percpu completions;
 	int dirty_exceeded;
+};
+
+struct backing_dev_info {
+	struct list_head bdi_list;
+	unsigned long ra_pages;	/* max readahead in PAGE_CACHE_SIZE units */
+	unsigned int capabilities; /* Device capabilities */
+	congested_fn *congested_fn; /* Function pointer if device is md/dm */
+	void *congested_data;	/* Pointer to aux data for congested func */
+
+	char *name;
 
 	unsigned int min_ratio;
 	unsigned int max_ratio, max_prop_frac;

index b2dd371e..a6b9db7 100644
@@ -155,16 +155,15 @@ int dirty_writeback_centisecs_handler(struct ctl_table *, int,
 				      void __user *, size_t *, loff_t *);
 
 void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
-unsigned long bdi_dirty_limit(struct backing_dev_info *bdi,
-			       unsigned long dirty);
-
-void __bdi_update_bandwidth(struct backing_dev_info *bdi,
-			    unsigned long thresh,
-			    unsigned long bg_thresh,
-			    unsigned long dirty,
-			    unsigned long bdi_thresh,
-			    unsigned long bdi_dirty,
-			    unsigned long start_time);
+unsigned long wb_dirty_limit(struct bdi_writeback *wb, unsigned long dirty);
+
+void __wb_update_bandwidth(struct bdi_writeback *wb,
+			   unsigned long thresh,
+			   unsigned long bg_thresh,
+			   unsigned long dirty,
+			   unsigned long bdi_thresh,
+			   unsigned long bdi_dirty,
+			   unsigned long start_time);
 
 void page_writeback_init(void);
 void balance_dirty_pages_ratelimited(struct address_space *mapping);

index 880dd74..9b876f6 100644
@@ -400,13 +400,13 @@ TRACE_EVENT(bdi_dirty_ratelimit,
 
 	TP_fast_assign(
 		strlcpy(__entry->bdi, dev_name(bdi->dev), 32);
-		__entry->write_bw	= KBps(bdi->write_bandwidth);
-		__entry->avg_write_bw	= KBps(bdi->avg_write_bandwidth);
+		__entry->write_bw	= KBps(bdi->wb.write_bandwidth);
+		__entry->avg_write_bw	= KBps(bdi->wb.avg_write_bandwidth);
 		__entry->dirty_rate	= KBps(dirty_rate);
-		__entry->dirty_ratelimit = KBps(bdi->dirty_ratelimit);
+		__entry->dirty_ratelimit = KBps(bdi->wb.dirty_ratelimit);
 		__entry->task_ratelimit	= KBps(task_ratelimit);
 		__entry->balanced_dirty_ratelimit =
-					  KBps(bdi->balanced_dirty_ratelimit);
+					KBps(bdi->wb.balanced_dirty_ratelimit);
 	),
 
 	TP_printk("bdi %s: "

93 lines not on this page · raw message

507 lines not on this page · raw message

index cd39ee9..78ef551 100644
@@ -595,7 +595,7 @@ static long long pos_ratio_polynom(unsigned long setpoint,
  *
  * (o) global/bdi setpoints
  *
- * We want the dirty pages be balanced around the global/bdi setpoints.
+ * We want the dirty pages be balanced around the global/wb setpoints.
  * When the number of dirty pages is higher/lower than the setpoint, the
  * dirty position control ratio (and hence task dirty ratelimit) will be
  * decreased/increased to bring the dirty pages back to the setpoint.

@@ -605,8 +605,8 @@ static long long pos_ratio_polynom(unsigned long setpoint,
  *     if (dirty < setpoint) scale up   pos_ratio
  *     if (dirty > setpoint) scale down pos_ratio
  *
- *     if (bdi_dirty < bdi_setpoint) scale up   pos_ratio
- *     if (bdi_dirty > bdi_setpoint) scale down pos_ratio
+ *     if (wb_dirty < wb_setpoint) scale up   pos_ratio
+ *     if (wb_dirty > wb_setpoint) scale down pos_ratio
  *
  *     task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT
  *

@@ -631,7 +631,7 @@ static long long pos_ratio_polynom(unsigned long setpoint,
  *   0 +------------.------------------.----------------------*------------->
  *           freerun^          setpoint^                 limit^   dirty pages
  *
- * (o) bdi control line
+ * (o) wb control line
  *
  *     ^ pos_ratio
  *     |

@@ -657,27 +657,27 @@ static long long pos_ratio_polynom(unsigned long setpoint,
  *     |                      .                           .
  *     |                      .                             .
  *   0 +----------------------.-------------------------------.------------->
- *                bdi_setpoint^                    x_intercept^
+ *                wb_setpoint^                    x_intercept^
  *
- * The bdi control line won't drop below pos_ratio=1/4, so that bdi_dirty can
+ * The wb control line won't drop below pos_ratio=1/4, so that wb_dirty can
  * be smoothly throttled down to normal if it starts high in situations like
  * - start writing to a slow SD card and a fast disk at the same time. The SD
- *   card's bdi_dirty may rush to many times higher than bdi_setpoint.
- * - the bdi dirty thresh drops quickly due to change of JBOD workload
+ *   card's wb_dirty may rush to many times higher than wb_setpoint.
+ * - the wb dirty thresh drops quickly due to change of JBOD workload
  */
 static unsigned long wb_position_ratio(struct bdi_writeback *wb,
 				       unsigned long thresh,
 				       unsigned long bg_thresh,
 				       unsigned long dirty,
-				       unsigned long bdi_thresh,
-				       unsigned long bdi_dirty)
+				       unsigned long wb_thresh,
+				       unsigned long wb_dirty)
 {
 	unsigned long write_bw = wb->avg_write_bandwidth;
 	unsigned long freerun = dirty_freerun_ceiling(thresh, bg_thresh);
 	unsigned long limit = hard_dirty_limit(thresh);
 	unsigned long x_intercept;
 	unsigned long setpoint;		/* dirty pages' target balance point */
-	unsigned long bdi_setpoint;
+	unsigned long wb_setpoint;
 	unsigned long span;
 	long long pos_ratio;		/* for scaling up/down the rate limit */
 	long x;

@@ -696,146 +696,145 @@ static unsigned long wb_position_ratio(struct bdi_writeback *wb,
 	/*
 	 * The strictlimit feature is a tool preventing mistrusted filesystems
 	 * from growing a large number of dirty pages before throttling. For
-	 * such filesystems balance_dirty_pages always checks bdi counters
-	 * against bdi limits. Even if global "nr_dirty" is under "freerun".
+	 * such filesystems balance_dirty_pages always checks wb counters
+	 * against wb limits. Even if global "nr_dirty" is under "freerun".
 	 * This is especially important for fuse which sets bdi->max_ratio to
 	 * 1% by default. Without strictlimit feature, fuse writeback may
 	 * consume arbitrary amount of RAM because it is accounted in
 	 * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty".
 	 *
 	 * Here, in wb_position_ratio(), we calculate pos_ratio based on
-	 * two values: bdi_dirty and bdi_thresh. Let's consider an example:
+	 * two values: wb_dirty and wb_thresh. Let's consider an example:
 	 * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global
 	 * limits are set by default to 10% and 20% (background and throttle).
-	 * Then bdi_thresh is 1% of 20% of 16GB. This amounts to ~8K pages.
-	 * wb_dirty_limit(wb, bg_thresh) is about ~4K pages. bdi_setpoint is
-	 * about ~6K pages (as the average of background and throttle bdi
+	 * Then wb_thresh is 1% of 20% of 16GB. This amounts to ~8K pages.
+	 * wb_dirty_limit(wb, bg_thresh) is about ~4K pages. wb_setpoint is
+	 * about ~6K pages (as the average of background and throttle wb
 	 * limits). The 3rd order polynomial will provide positive feedback if
-	 * bdi_dirty is under bdi_setpoint and vice versa.
+	 * wb_dirty is under wb_setpoint and vice versa.
 	 *
 	 * Note, that we cannot use global counters in these calculations
-	 * because we want to throttle process writing to a strictlimit BDI
+	 * because we want to throttle process writing to a strictlimit wb
 	 * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB
 	 * in the example above).
 	 */
 	if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
-		long long bdi_pos_ratio;
-		unsigned long bdi_bg_thresh;
+		long long wb_pos_ratio;
+		unsigned long wb_bg_thresh;
 
-		if (bdi_dirty < 8)
+		if (wb_dirty < 8)
 			return min_t(long long, pos_ratio * 2,
 				     2 << RATELIMIT_CALC_SHIFT);
 
-		if (bdi_dirty >= bdi_thresh)
+		if (wb_dirty >= wb_thresh)
 			return 0;
 
-		bdi_bg_thresh = div_u64((u64)bdi_thresh * bg_thresh, thresh);
-		bdi_setpoint = dirty_freerun_ceiling(bdi_thresh,
-						     bdi_bg_thresh);
+		wb_bg_thresh = div_u64((u64)wb_thresh * bg_thresh, thresh);
+		wb_setpoint = dirty_freerun_ceiling(wb_thresh, wb_bg_thresh);
 
-		if (bdi_setpoint == 0 || bdi_setpoint == bdi_thresh)
+		if (wb_setpoint == 0 || wb_setpoint == wb_thresh)
 			return 0;
 
-		bdi_pos_ratio = pos_ratio_polynom(bdi_setpoint, bdi_dirty,
-						  bdi_thresh);
+		wb_pos_ratio = pos_ratio_polynom(wb_setpoint, wb_dirty,
+						 wb_thresh);
 
 		/*
-		 * Typically, for strictlimit case, bdi_setpoint << setpoint
-		 * and pos_ratio >> bdi_pos_ratio. In the other words global
+		 * Typically, for strictlimit case, wb_setpoint << setpoint
+		 * and pos_ratio >> wb_pos_ratio. In the other words global
 		 * state ("dirty") is not limiting factor and we have to
-		 * make decision based on bdi counters. But there is an
+		 * make decision based on wb counters. But there is an
 		 * important case when global pos_ratio should get precedence:
 		 * global limits are exceeded (e.g. due to activities on other
-		 * BDIs) while given strictlimit BDI is below limit.
+		 * wb's) while given strictlimit wb is below limit.
 		 *
-		 * "pos_ratio * bdi_pos_ratio" would work for the case above,
+		 * "pos_ratio * wb_pos_ratio" would work for the case above,
 		 * but it would look too non-natural for the case of all
-		 * activity in the system coming from a single strictlimit BDI
+		 * activity in the system coming from a single strictlimit wb
 		 * with bdi->max_ratio == 100%.
 		 *
 		 * Note that min() below somewhat changes the dynamics of the
 		 * control system. Normally, pos_ratio value can be well over 3
-		 * (when globally we are at freerun and bdi is well below bdi
+		 * (when globally we are at freerun and wb is well below wb
 		 * setpoint). Now the maximum pos_ratio in the same situation
 		 * is 2. We might want to tweak this if we observe the control
 		 * system is too slow to adapt.
 		 */
-		return min(pos_ratio, bdi_pos_ratio);
+		return min(pos_ratio, wb_pos_ratio);
 	}
 
 	/*
 	 * We have computed basic pos_ratio above based on global situation. If
-	 * the bdi is over/under its share of dirty pages, we want to scale
+	 * the wb is over/under its share of dirty pages, we want to scale
 	 * pos_ratio further down/up. That is done by the following mechanism.
 	 */
 
 	/*
-	 * bdi setpoint
+	 * wb setpoint
 	 *
-	 *        f(bdi_dirty) := 1.0 + k * (bdi_dirty - bdi_setpoint)
+	 *        f(wb_dirty) := 1.0 + k * (wb_dirty - wb_setpoint)
 	 *
-	 *                        x_intercept - bdi_dirty
+	 *                        x_intercept - wb_dirty
 	 *                     := --------------------------
-	 *                        x_intercept - bdi_setpoint
+	 *                        x_intercept - wb_setpoint
 	 *
-	 * The main bdi control line is a linear function that subjects to
+	 * The main wb control line is a linear function that subjects to
 	 *
-	 * (1) f(bdi_setpoint) = 1.0
-	 * (2) k = - 1 / (8 * write_bw)  (in single bdi case)
-	 *     or equally: x_intercept = bdi_setpoint + 8 * write_bw
+	 * (1) f(wb_setpoint) = 1.0
+	 * (2) k = - 1 / (8 * write_bw)  (in single wb case)
+	 *     or equally: x_intercept = wb_setpoint + 8 * write_bw
 	 *
-	 * For single bdi case, the dirty pages are observed to fluctuate
+	 * For single wb case, the dirty pages are observed to fluctuate
 	 * regularly within range
-	 *        [bdi_setpoint - write_bw/2, bdi_setpoint + write_bw/2]
+	 *        [wb_setpoint - write_bw/2, wb_setpoint + write_bw/2]
 	 * for various filesystems, where (2) can yield in a reasonable 12.5%
 	 * fluctuation range for pos_ratio.
 	 *
-	 * For JBOD case, bdi_thresh (not bdi_dirty!) could fluctuate up to its
+	 * For JBOD case, wb_thresh (not wb_dirty!) could fluctuate up to its
 	 * own size, so move the slope over accordingly and choose a slope that
-	 * yields 100% pos_ratio fluctuation on suddenly doubled bdi_thresh.
+	 * yields 100% pos_ratio fluctuation on suddenly doubled wb_thresh.
 	 */
-	if (unlikely(bdi_thresh > thresh))
-		bdi_thresh = thresh;
+	if (unlikely(wb_thresh > thresh))
+		wb_thresh = thresh;
 	/*
-	 * It's very possible that bdi_thresh is close to 0 not because the
+	 * It's very possible that wb_thresh is close to 0 not because the
 	 * device is slow, but that it has remained inactive for long time.
 	 * Honour such devices a reasonable good (hopefully IO efficient)
 	 * threshold, so that the occasional writes won't be blocked and active
 	 * writes can rampup the threshold quickly.
 	 */
-	bdi_thresh = max(bdi_thresh, (limit - dirty) / 8);
+	wb_thresh = max(wb_thresh, (limit - dirty) / 8);
 	/*
-	 * scale global setpoint to bdi's:
-	 *	bdi_setpoint = setpoint * bdi_thresh / thresh
+	 * scale global setpoint to wb's:
+	 *	wb_setpoint = setpoint * wb_thresh / thresh
 	 */
-	x = div_u64((u64)bdi_thresh << 16, thresh + 1);
-	bdi_setpoint = setpoint * (u64)x >> 16;
+	x = div_u64((u64)wb_thresh << 16, thresh + 1);
+	wb_setpoint = setpoint * (u64)x >> 16;
 	/*
-	 * Use span=(8*write_bw) in single bdi case as indicated by
-	 * (thresh - bdi_thresh ~= 0) and transit to bdi_thresh in JBOD case.
+	 * Use span=(8*write_bw) in single wb case as indicated by
+	 * (thresh - wb_thresh ~= 0) and transit to wb_thresh in JBOD case.
 	 *
-	 *        bdi_thresh                    thresh - bdi_thresh
-	 * span = ---------- * (8 * write_bw) + ------------------- * bdi_thresh
-	 *          thresh                            thresh
+	 *        wb_thresh                    thresh - wb_thresh
+	 * span = --------- * (8 * write_bw) + ------------------ * wb_thresh
+	 *         thresh                           thresh
 	 */
-	span = (thresh - bdi_thresh + 8 * write_bw) * (u64)x >> 16;
-	x_intercept = bdi_setpoint + span;
+	span = (thresh - wb_thresh + 8 * write_bw) * (u64)x >> 16;
+	x_intercept = wb_setpoint + span;
 
-	if (bdi_dirty < x_intercept - span / 4) {
-		pos_ratio = div64_u64(pos_ratio * (x_intercept - bdi_dirty),
-				    x_intercept - bdi_setpoint + 1);
+	if (wb_dirty < x_intercept - span / 4) {
+		pos_ratio = div64_u64(pos_ratio * (x_intercept - wb_dirty),
+				    x_intercept - wb_setpoint + 1);
 	} else
 		pos_ratio /= 4;
 
 	/*
-	 * bdi reserve area, safeguard against dirty pool underrun and disk idle
+	 * wb reserve area, safeguard against dirty pool underrun and disk idle
 	 * It may push the desired control point of global dirty pages higher
 	 * than setpoint.
 	 */
-	x_intercept = bdi_thresh / 2;
-	if (bdi_dirty < x_intercept) {
-		if (bdi_dirty > x_intercept / 8)
-			pos_ratio = div_u64(pos_ratio * x_intercept, bdi_dirty);
+	x_intercept = wb_thresh / 2;
+	if (wb_dirty < x_intercept) {
+		if (wb_dirty > x_intercept / 8)
+			pos_ratio = div_u64(pos_ratio * x_intercept, wb_dirty);
 		else
 			pos_ratio *= 8;
 	}

@@ -943,17 +942,17 @@ static void global_update_bandwidth(unsigned long thresh,
 }
 
 /*
- * Maintain bdi->dirty_ratelimit, the base dirty throttle rate.
+ * Maintain wb->dirty_ratelimit, the base dirty throttle rate.
  *
- * Normal bdi tasks will be curbed at or below it in long term.
+ * Normal wb tasks will be curbed at or below it in long term.
  * Obviously it should be around (write_bw / N) when there are N dd tasks.
  */
 static void wb_update_dirty_ratelimit(struct bdi_writeback *wb,
 				      unsigned long thresh,
 				      unsigned long bg_thresh,
 				      unsigned long dirty,
-				      unsigned long bdi_thresh,
-				      unsigned long bdi_dirty,
+				      unsigned long wb_thresh,
+				      unsigned long wb_dirty,
 				      unsigned long dirtied,
 				      unsigned long elapsed)
 {

@@ -976,7 +975,7 @@ static void wb_update_dirty_ratelimit(struct bdi_writeback *wb,
 	dirty_rate = (dirtied - wb->dirtied_stamp) * HZ / elapsed;
 
 	pos_ratio = wb_position_ratio(wb, thresh, bg_thresh, dirty,
-				      bdi_thresh, bdi_dirty);
+				      wb_thresh, wb_dirty);
 	/*
 	 * task_ratelimit reflects each dd's dirty rate for the past 200ms.
 	 */

@@ -986,7 +985,7 @@ static void wb_update_dirty_ratelimit(struct bdi_writeback *wb,
 
 	/*
 	 * A linear estimation of the "balanced" throttle rate. The theory is,
-	 * if there are N dd tasks, each throttled at task_ratelimit, the bdi's
+	 * if there are N dd tasks, each throttled at task_ratelimit, the wb's
 	 * dirty_rate will be measured to be (N * task_ratelimit). So the below
 	 * formula will yield the balanced rate limit (write_bw / N).
 	 *

@@ -1025,7 +1024,7 @@ static void wb_update_dirty_ratelimit(struct bdi_writeback *wb,
 	/*
 	 * We could safely do this and return immediately:
 	 *
-	 *	bdi->dirty_ratelimit = balanced_dirty_ratelimit;
+	 *	wb->dirty_ratelimit = balanced_dirty_ratelimit;
 	 *
 	 * However to get a more stable dirty_ratelimit, the below elaborated
 	 * code makes use of task_ratelimit to filter out singular points and

@@ -1059,22 +1058,22 @@ static void wb_update_dirty_ratelimit(struct bdi_writeback *wb,
 	step = 0;
 
 	/*
-	 * For strictlimit case, calculations above were based on bdi counters
+	 * For strictlimit case, calculations above were based on wb counters
 	 * and limits (starting from pos_ratio = wb_position_ratio() and up to
 	 * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate).
-	 * Hence, to calculate "step" properly, we have to use bdi_dirty as
-	 * "dirty" and bdi_setpoint as "setpoint".
+	 * Hence, to calculate "step" properly, we have to use wb_dirty as
+	 * "dirty" and wb_setpoint as "setpoint".
 	 *
-	 * We rampup dirty_ratelimit forcibly if bdi_dirty is low because
-	 * it's possible that bdi_thresh is close to zero due to inactivity
+	 * We rampup dirty_ratelimit forcibly if wb_dirty is low because
+	 * it's possible that wb_thresh is close to zero due to inactivity
 	 * of backing device (see the implementation of wb_dirty_limit()).
 	 */
 	if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
-		dirty = bdi_dirty;
-		if (bdi_dirty < 8)
-			setpoint = bdi_dirty + 1;
+		dirty = wb_dirty;
+		if (wb_dirty < 8)
+			setpoint = wb_dirty + 1;
 		else
-			setpoint = (bdi_thresh +
+			setpoint = (wb_thresh +
 				    wb_dirty_limit(wb, bg_thresh)) / 2;
 	}
 

@@ -1116,8 +1115,8 @@ void __wb_update_bandwidth(struct bdi_writeback *wb,
 			   unsigned long thresh,
 			   unsigned long bg_thresh,
 			   unsigned long dirty,
-			   unsigned long bdi_thresh,
-			   unsigned long bdi_dirty,
+			   unsigned long wb_thresh,
+			   unsigned long wb_dirty,
 			   unsigned long start_time)
 {
 	unsigned long now = jiffies;

@@ -1144,7 +1143,7 @@ void __wb_update_bandwidth(struct bdi_writeback *wb,
 	if (thresh) {
 		global_update_bandwidth(thresh, dirty, now);
 		wb_update_dirty_ratelimit(wb, thresh, bg_thresh, dirty,
-					  bdi_thresh, bdi_dirty,
+					  wb_thresh, wb_dirty,
 					  dirtied, elapsed);
 	}
 	wb_update_write_bandwidth(wb, elapsed, written);

@@ -1159,15 +1158,15 @@ static void wb_update_bandwidth(struct bdi_writeback *wb,
 				unsigned long thresh,
 				unsigned long bg_thresh,
 				unsigned long dirty,
-				unsigned long bdi_thresh,
-				unsigned long bdi_dirty,
+				unsigned long wb_thresh,
+				unsigned long wb_dirty,
 				unsigned long start_time)
 {
 	if (time_is_after_eq_jiffies(wb->bw_time_stamp + BANDWIDTH_INTERVAL))
 		return;
 	spin_lock(&wb->list_lock);
 	__wb_update_bandwidth(wb, thresh, bg_thresh, dirty,
-			      bdi_thresh, bdi_dirty, start_time);
+			      wb_thresh, wb_dirty, start_time);
 	spin_unlock(&wb->list_lock);
 }
 

@@ -1189,7 +1188,7 @@ static unsigned long dirty_poll_interval(unsigned long dirty,
 }
 
 static unsigned long wb_max_pause(struct bdi_writeback *wb,
-				      unsigned long bdi_dirty)
+				  unsigned long wb_dirty)
 {
 	unsigned long bw = wb->avg_write_bandwidth;
 	unsigned long t;

@@ -1201,7 +1200,7 @@ static unsigned long wb_max_pause(struct bdi_writeback *wb,
 	 *
 	 * 8 serves as the safety ratio.
 	 */
-	t = bdi_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8));
+	t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8));
 	t++;
 
 	return min_t(unsigned long, t, MAX_PAUSE);

@@ -1285,31 +1284,31 @@ static long wb_min_pause(struct bdi_writeback *wb,
 static inline void wb_dirty_limits(struct bdi_writeback *wb,
 				   unsigned long dirty_thresh,
 				   unsigned long background_thresh,
-				   unsigned long *bdi_dirty,
-				   unsigned long *bdi_thresh,
-				   unsigned long *bdi_bg_thresh)
+				   unsigned long *wb_dirty,
+				   unsigned long *wb_thresh,
+				   unsigned long *wb_bg_thresh)
 {
 	unsigned long wb_reclaimable;
 
 	/*
-	 * bdi_thresh is not treated as some limiting factor as
+	 * wb_thresh is not treated as some limiting factor as
 	 * dirty_thresh, due to reasons
-	 * - in JBOD setup, bdi_thresh can fluctuate a lot
+	 * - in JBOD setup, wb_thresh can fluctuate a lot
 	 * - in a system with HDD and USB key, the USB key may somehow
-	 *   go into state (bdi_dirty >> bdi_thresh) either because
-	 *   bdi_dirty starts high, or because bdi_thresh drops low.
+	 *   go into state (wb_dirty >> wb_thresh) either because
+	 *   wb_dirty starts high, or because wb_thresh drops low.
 	 *   In this case we don't want to hard throttle the USB key
-	 *   dirtiers for 100 seconds until bdi_dirty drops under
-	 *   bdi_thresh. Instead the auxiliary bdi control line in
+	 *   dirtiers for 100 seconds until wb_dirty drops under
+	 *   wb_thresh. Instead the auxiliary wb control line in
 	 *   wb_position_ratio() will let the dirtier task progress
-	 *   at some rate <= (write_bw / 2) for bringing down bdi_dirty.
+	 *   at some rate <= (write_bw / 2) for bringing down wb_dirty.
 	 */
-	*bdi_thresh = wb_dirty_limit(wb, dirty_thresh);
+	*wb_thresh = wb_dirty_limit(wb, dirty_thresh);
 
-	if (bdi_bg_thresh)
-		*bdi_bg_thresh = dirty_thresh ? div_u64((u64)*bdi_thresh *
-							background_thresh,
-							dirty_thresh) : 0;
+	if (wb_bg_thresh)
+		*wb_bg_thresh = dirty_thresh ? div_u64((u64)*wb_thresh *
+						       background_thresh,
+						       dirty_thresh) : 0;
 
 	/*
 	 * In order to avoid the stacked BDI deadlock we need

@@ -1321,12 +1320,12 @@ static inline void wb_dirty_limits(struct bdi_writeback *wb,
 	 * actually dirty; with m+n sitting in the percpu
 	 * deltas.
 	 */
-	if (*bdi_thresh < 2 * wb_stat_error(wb)) {
+	if (*wb_thresh < 2 * wb_stat_error(wb)) {
 		wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE);
-		*bdi_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK);
+		*wb_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK);
 	} else {
 		wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE);
-		*bdi_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK);
+		*wb_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK);
 	}
 }
 

@@ -1360,9 +1359,9 @@ static void balance_dirty_pages(struct address_space *mapping,
 
 	for (;;) {
 		unsigned long now = jiffies;
-		unsigned long uninitialized_var(bdi_thresh);
+		unsigned long uninitialized_var(wb_thresh);
 		unsigned long thresh;
-		unsigned long uninitialized_var(bdi_dirty);
+		unsigned long uninitialized_var(wb_dirty);
 		unsigned long dirty;
 		unsigned long bg_thresh;
 

@@ -1380,10 +1379,10 @@ static void balance_dirty_pages(struct address_space *mapping,
 
 		if (unlikely(strictlimit)) {
 			wb_dirty_limits(wb, dirty_thresh, background_thresh,
-					&bdi_dirty, &bdi_thresh, &bg_thresh);
+					&wb_dirty, &wb_thresh, &bg_thresh);
 
-			dirty = bdi_dirty;
-			thresh = bdi_thresh;
+			dirty = wb_dirty;
+			thresh = wb_thresh;
 		} else {
 			dirty = nr_dirty;
 			thresh = dirty_thresh;

@@ -1393,10 +1392,10 @@ static void balance_dirty_pages(struct address_space *mapping,
 		/*
 		 * Throttle it only when the background writeback cannot
 		 * catch-up. This avoids (excessively) small writeouts
-		 * when the bdi limits are ramping up in case of !strictlimit.
+		 * when the wb limits are ramping up in case of !strictlimit.
 		 *
-		 * In strictlimit case make decision based on the bdi counters
-		 * and limits. Small writeouts when the bdi limits are ramping
+		 * In strictlimit case make decision based on the wb counters
+		 * and limits. Small writeouts when the wb limits are ramping
 		 * up are the price we consciously pay for strictlimit-ing.
 		 */
 		if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh)) {

@@ -1412,24 +1411,23 @@ static void balance_dirty_pages(struct address_space *mapping,
 
 		if (!strictlimit)
 			wb_dirty_limits(wb, dirty_thresh, background_thresh,
-					&bdi_dirty, &bdi_thresh, NULL);
+					&wb_dirty, &wb_thresh, NULL);
 
-		dirty_exceeded = (bdi_dirty > bdi_thresh) &&
+		dirty_exceeded = (wb_dirty > wb_thresh) &&
 				 ((nr_dirty > dirty_thresh) || strictlimit);
 		if (dirty_exceeded && !wb->dirty_exceeded)
 			wb->dirty_exceeded = 1;
 
 		wb_update_bandwidth(wb, dirty_thresh, background_thresh,
-				    nr_dirty, bdi_thresh, bdi_dirty,
-				    start_time);
+				    nr_dirty, wb_thresh, wb_dirty, start_time);
 
 		dirty_ratelimit = wb->dirty_ratelimit;
 		pos_ratio = wb_position_ratio(wb, dirty_thresh,
 					      background_thresh, nr_dirty,
-					      bdi_thresh, bdi_dirty);
+					      wb_thresh, wb_dirty);
 		task_ratelimit = ((u64)dirty_ratelimit * pos_ratio) >>
 							RATELIMIT_CALC_SHIFT;
-		max_pause = wb_max_pause(wb, bdi_dirty);
+		max_pause = wb_max_pause(wb, wb_dirty);
 		min_pause = wb_min_pause(wb, max_pause,
 					 task_ratelimit, dirty_ratelimit,
 					 &nr_dirtied_pause);

@@ -1455,8 +1453,8 @@ static void balance_dirty_pages(struct address_space *mapping,
 						  dirty_thresh,
 						  background_thresh,
 						  nr_dirty,
-						  bdi_thresh,
-						  bdi_dirty,
+						  wb_thresh,
+						  wb_dirty,
 						  dirty_ratelimit,
 						  task_ratelimit,
 						  pages_dirtied,

@@ -1484,8 +1482,8 @@ static void balance_dirty_pages(struct address_space *mapping,
 					  dirty_thresh,
 					  background_thresh,
 					  nr_dirty,
-					  bdi_thresh,
-					  bdi_dirty,
+					  wb_thresh,
+					  wb_dirty,
 					  dirty_ratelimit,
 					  task_ratelimit,
 					  pages_dirtied,

@@ -1508,15 +1506,15 @@ static void balance_dirty_pages(struct address_space *mapping,
 
 		/*
 		 * In the case of an unresponding NFS server and the NFS dirty
-		 * pages exceeds dirty_thresh, give the other good bdi's a pipe
+		 * pages exceeds dirty_thresh, give the other good wb's a pipe
 		 * to go through, so that tasks on them still remain responsive.
 		 *
 		 * In theory 1 page is enough to keep the comsumer-producer
 		 * pipe going: the flusher cleans 1 page => the task dirties 1
-		 * more page. However bdi_dirty has accounting errors.  So use
+		 * more page. However wb_dirty has accounting errors.  So use
 		 * the larger and more IO friendly wb_stat_error.
 		 */
-		if (bdi_dirty <= wb_stat_error(wb))
+		if (wb_dirty <= wb_stat_error(wb))
 			break;
 
 		if (fatal_signal_pending(current))

index 1945cb9..a69d2e1 100644
@@ -109,34 +109,33 @@ static inline struct inode *wb_inode(struct list_head *head)
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage);
 
-static void bdi_wakeup_thread(struct backing_dev_info *bdi)
+static void wb_wakeup(struct bdi_writeback *wb)
 {
-	spin_lock_bh(&bdi->wb_lock);
-	if (test_bit(WB_registered, &bdi->wb.state))
-		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
-	spin_unlock_bh(&bdi->wb_lock);
+	spin_lock_bh(&wb->work_lock);
+	if (test_bit(WB_registered, &wb->state))
+		mod_delayed_work(bdi_wq, &wb->dwork, 0);
+	spin_unlock_bh(&wb->work_lock);
 }
 
-static void bdi_queue_work(struct backing_dev_info *bdi,
-			   struct wb_writeback_work *work)
+static void wb_queue_work(struct bdi_writeback *wb,
+			  struct wb_writeback_work *work)
 {
-	trace_writeback_queue(bdi, work);
+	trace_writeback_queue(wb->bdi, work);
 
-	spin_lock_bh(&bdi->wb_lock);
-	if (!test_bit(WB_registered, &bdi->wb.state)) {
+	spin_lock_bh(&wb->work_lock);
+	if (!test_bit(WB_registered, &wb->state)) {
 		if (work->done)
 			complete(work->done);
 		goto out_unlock;
 	}
-	list_add_tail(&work->list, &bdi->work_list);
-	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+	list_add_tail(&work->list, &wb->work_list);
+	mod_delayed_work(bdi_wq, &wb->dwork, 0);
 out_unlock:
-	spin_unlock_bh(&bdi->wb_lock);
+	spin_unlock_bh(&wb->work_lock);
 }
 
-static void
-__bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
-		      bool range_cyclic, enum wb_reason reason)
+static void __wb_start_writeback(struct bdi_writeback *wb, long nr_pages,
+				 bool range_cyclic, enum wb_reason reason)
 {
 	struct wb_writeback_work *work;
 

@@ -146,8 +145,8 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 	 */
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work) {
-		trace_writeback_nowork(bdi);
-		bdi_wakeup_thread(bdi);
+		trace_writeback_nowork(wb->bdi);
+		wb_wakeup(wb);
 		return;
 	}
 

@@ -156,7 +155,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 	work->range_cyclic = range_cyclic;
 	work->reason	= reason;
 
-	bdi_queue_work(bdi, work);
+	wb_queue_work(wb, work);
 }
 
 /**

@@ -174,7 +173,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 			enum wb_reason reason)
 {
-	__bdi_start_writeback(bdi, nr_pages, true, reason);
+	__wb_start_writeback(&bdi->wb, nr_pages, true, reason);
 }
 
 /**

@@ -194,7 +193,7 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi)
 	 * writeback as soon as there is no other work to do.
 	 */
 	trace_writeback_wake_background(bdi);
-	bdi_wakeup_thread(bdi);
+	wb_wakeup(&bdi->wb);
 }
 
 /*

@@ -898,7 +897,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 * after the other works are all done.
 		 */
 		if ((work->for_background || work->for_kupdate) &&
-		    !list_empty(&wb->bdi->work_list))
+		    !list_empty(&wb->work_list))
 			break;
 
 		/*

@@ -969,18 +968,17 @@ static long wb_writeback(struct bdi_writeback *wb,
 /*
  * Return the next wb_writeback_work struct that hasn't been processed yet.
  */
-static struct wb_writeback_work *
-get_next_work_item(struct backing_dev_info *bdi)
+static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb)
 {
 	struct wb_writeback_work *work = NULL;
 
-	spin_lock_bh(&bdi->wb_lock);
-	if (!list_empty(&bdi->work_list)) {
-		work = list_entry(bdi->work_list.next,
+	spin_lock_bh(&wb->work_lock);
+	if (!list_empty(&wb->work_list)) {
+		work = list_entry(wb->work_list.next,
 				  struct wb_writeback_work, list);
 		list_del_init(&work->list);
 	}
-	spin_unlock_bh(&bdi->wb_lock);
+	spin_unlock_bh(&wb->work_lock);
 	return work;
 }
 

@@ -1052,14 +1050,13 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb)
  */
 static long wb_do_writeback(struct bdi_writeback *wb)
 {
-	struct backing_dev_info *bdi = wb->bdi;
 	struct wb_writeback_work *work;
 	long wrote = 0;
 
 	set_bit(WB_writeback_running, &wb->state);
-	while ((work = get_next_work_item(bdi)) != NULL) {
+	while ((work = get_next_work_item(wb)) != NULL) {
 
-		trace_writeback_exec(bdi, work);
+		trace_writeback_exec(wb->bdi, work);
 
 		wrote += wb_writeback(wb, work);
 

@@ -1087,43 +1084,42 @@ static long wb_do_writeback(struct bdi_writeback *wb)
  * Handle writeback of dirty data for the device backed by this bdi. Also
  * reschedules periodically and does kupdated style flushing.
  */
-void bdi_writeback_workfn(struct work_struct *work)
+void wb_workfn(struct work_struct *work)
 {
 	struct bdi_writeback *wb = container_of(to_delayed_work(work),
 						struct bdi_writeback, dwork);
-	struct backing_dev_info *bdi = wb->bdi;
 	long pages_written;
 
-	set_worker_desc("flush-%s", dev_name(bdi->dev));
+	set_worker_desc("flush-%s", dev_name(wb->bdi->dev));
 	current->flags |= PF_SWAPWRITE;
 
 	if (likely(!current_is_workqueue_rescuer() ||
 		   !test_bit(WB_registered, &wb->state))) {
 		/*
-		 * The normal path.  Keep writing back @bdi until its
+		 * The normal path.  Keep writing back @wb until its
 		 * work_list is empty.  Note that this path is also taken
-		 * if @bdi is shutting down even when we're running off the
+		 * if @wb is shutting down even when we're running off the
 		 * rescuer as work_list needs to be drained.
 		 */
 		do {
 			pages_written = wb_do_writeback(wb);
 			trace_writeback_pages_written(pages_written);
-		} while (!list_empty(&bdi->work_list));
+		} while (!list_empty(&wb->work_list));
 	} else {
 		/*
 		 * bdi_wq can't get enough workers and we're running off
 		 * the emergency worker.  Don't hog it.  Hopefully, 1024 is
 		 * enough for efficient IO.
 		 */
-		pages_written = writeback_inodes_wb(&bdi->wb, 1024,
+		pages_written = writeback_inodes_wb(wb, 1024,
 						    WB_REASON_FORKER_THREAD);
 		trace_writeback_pages_written(pages_written);
 	}
 
-	if (!list_empty(&bdi->work_list))
+	if (!list_empty(&wb->work_list))
 		mod_delayed_work(bdi_wq, &wb->dwork, 0);
 	else if (wb_has_dirty_io(wb) && dirty_writeback_interval)
-		bdi_wakeup_thread_delayed(bdi);
+		wb_wakeup_delayed(wb);
 
 	current->flags &= ~PF_SWAPWRITE;
 }

@@ -1143,7 +1139,7 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason)
 	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
 		if (!bdi_has_dirty_io(bdi))
 			continue;
-		__bdi_start_writeback(bdi, nr_pages, false, reason);
+		__wb_start_writeback(&bdi->wb, nr_pages, false, reason);
 	}
 	rcu_read_unlock();
 }

@@ -1174,7 +1170,7 @@ static void wakeup_dirtytime_writeback(struct work_struct *w)
 	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
 		if (list_empty(&bdi->wb.b_dirty_time))
 			continue;
-		bdi_wakeup_thread(bdi);
+		wb_wakeup(&bdi->wb);
 	}
 	rcu_read_unlock();
 	schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ);

@@ -1347,7 +1343,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			trace_writeback_dirty_inode_enqueue(inode);
 
 			if (wakeup_bdi)
-				bdi_wakeup_thread_delayed(bdi);
+				wb_wakeup_delayed(&bdi->wb);
 			return;
 		}
 	}

@@ -1437,7 +1433,7 @@ void writeback_inodes_sb_nr(struct super_block *sb,
 	if (sb->s_bdi == &noop_backing_dev_info)
 		return;
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
-	bdi_queue_work(sb->s_bdi, &work);
+	wb_queue_work(&sb->s_bdi->wb, &work);
 	wait_for_completion(&done);
 }
 EXPORT_SYMBOL(writeback_inodes_sb_nr);

@@ -1521,7 +1517,7 @@ void sync_inodes_sb(struct super_block *sb)
 		return;
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
-	bdi_queue_work(sb->s_bdi, &work);
+	wb_queue_work(&sb->s_bdi->wb, &work);
 	wait_for_completion(&done);
 
 	wait_sb_inodes(sb);

index 2ab0604..d796f49 100644
@@ -52,7 +52,6 @@ struct bdi_writeback {
 	unsigned long state;		/* Always use atomic bitops on this */
 	unsigned long last_old_flush;	/* last old data flush */
 
-	struct delayed_work dwork;	/* work item used for writeback */
 	struct list_head b_dirty;	/* dirty inodes */
 	struct list_head b_io;		/* parked for writeback */
 	struct list_head b_more_io;	/* parked for more writeback */

@@ -78,6 +77,10 @@ struct bdi_writeback {
 
 	struct fprop_local_percpu completions;
 	int dirty_exceeded;
+
+	spinlock_t work_lock;		/* protects work_list & dwork scheduling */
+	struct list_head work_list;
+	struct delayed_work dwork;	/* work item used for writeback */
 };
 
 struct backing_dev_info {

@@ -93,9 +96,6 @@ struct backing_dev_info {
 	unsigned int max_ratio, max_prop_frac;
 
 	struct bdi_writeback wb;  /* default writeback info for this bdi */
-	spinlock_t wb_lock;	  /* protects work_list & wb.dwork scheduling */
-
-	struct list_head work_list;
 
 	struct device *dev;
 

@@ -121,9 +121,9 @@ int __must_check bdi_setup_and_register(struct backing_dev_info *, char *);
 void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 			enum wb_reason reason);
 void bdi_start_background_writeback(struct backing_dev_info *bdi);
-void bdi_writeback_workfn(struct work_struct *work);
+void wb_workfn(struct work_struct *work);
 int bdi_has_dirty_io(struct backing_dev_info *bdi);
-void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi);
+void wb_wakeup_delayed(struct bdi_writeback *wb);
 
 extern spinlock_t bdi_lock;
 extern struct list_head bdi_list;

132 lines not on this page · raw message

index 620d934..8aa56bb 100644
@@ -320,31 +320,21 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 		  const char *dev_name, char *data)
 {
-	int retval = -EINVAL;
 	struct p9_fid *fid;
-	int rc;
+	int rc = -ENOMEM;
 
 	v9ses->uname = kstrdup(V9FS_DEFUSER, GFP_KERNEL);
 	if (!v9ses->uname)
-		return ERR_PTR(-ENOMEM);
+		goto err_names;
 
 	v9ses->aname = kstrdup(V9FS_DEFANAME, GFP_KERNEL);
-	if (!v9ses->aname) {
-		kfree(v9ses->uname);
-		return ERR_PTR(-ENOMEM);
-	}
+	if (!v9ses->aname)
+		goto err_names;
 	init_rwsem(&v9ses->rename_sem);
 
 	rc = bdi_setup_and_register(&v9ses->bdi, "9p");
-	if (rc) {
-		kfree(v9ses->aname);
-		kfree(v9ses->uname);
-		return ERR_PTR(rc);
-	}
-
-	spin_lock(&v9fs_sessionlist_lock);
-	list_add(&v9ses->slist, &v9fs_sessionlist);
-	spin_unlock(&v9fs_sessionlist_lock);
+	if (rc)
+		goto err_names;
 
 	v9ses->uid = INVALID_UID;
 	v9ses->dfltuid = V9FS_DEFUID;