[PATCH] separate bdi congestion functions from queue congestion functions

Separate out the concept of "queue congestion" from "backing-dev congestion".
Congestion is a backing-dev concept, not a queue concept.

The blk_* congestion functions are retained, as wrappers around the core
backing-dev congestion functions.

This proper layering is needed so that NFS can cleanly use the congestion
functions, and so that CONFIG_BLOCK=n actually links.

Cc: "Thomas Maier" <balagi@justmail.de>
Cc: "Jens Axboe" <jens.axboe@oracle.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: David Howells <dhowells@redhat.com>
Cc: Peter Osterlund <petero2@telia.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

17 files changed, 126 insertions, 104 deletions

diff --git a/arch/i386/lib/usercopy.c b/arch/i386/lib/usercopy.c
index 258df6b..d22cfc9 100644
--- a/arch/i386/lib/usercopy.c
+++ b/arch/i386/lib/usercopy.c
@@ -9,6 +9,7 @@
 #include <linux/highmem.h>
 #include <linux/blkdev.h>
 #include <linux/module.h>
+#include <linux/backing-dev.h>
 #include <asm/uaccess.h>
 #include <asm/mmx.h>
 
@@ -741,7 +742,7 @@ survive:
 
 			if (retval == -ENOMEM && is_init(current)) {
 				up_read(&current->mm->mmap_sem);
-				blk_congestion_wait(WRITE, HZ/50);
+				congestion_wait(WRITE, HZ/50);
 				goto survive;
 			}
 
diff --git a/block/ll_rw_blk.c b/block/ll_rw_blk.c
index 132a858..1360665 100644
--- a/block/ll_rw_blk.c
+++ b/block/ll_rw_blk.c
@@ -56,11 +56,6 @@ static kmem_cache_t *requestq_cachep;
  */
 static kmem_cache_t *iocontext_cachep;
 
-static wait_queue_head_t congestion_wqh[2] = {
-		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
-		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
-	};
-
 /*
  * Controlling structure to kblockd
  */
@@ -112,37 +107,6 @@ static void blk_queue_congestion_threshold(struct request_queue *q)
 	q->nr_congestion_off = nr;
 }
 
-/*
- * A queue has just exitted congestion.  Note this in the global counter of
- * congested queues, and wake up anyone who was waiting for requests to be
- * put back.
- */
-void blk_clear_queue_congested(request_queue_t *q, int rw)
-{
-	enum bdi_state bit;
-	wait_queue_head_t *wqh = &congestion_wqh[rw];
-
-	bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
-	clear_bit(bit, &q->backing_dev_info.state);
-	smp_mb__after_clear_bit();
-	if (waitqueue_active(wqh))
-		wake_up(wqh);
-}
-EXPORT_SYMBOL(blk_clear_queue_congested);
-
-/*
- * A queue has just entered congestion.  Flag that in the queue's VM-visible
- * state flags and increment the global gounter of congested queues.
- */
-void blk_set_queue_congested(request_queue_t *q, int rw)
-{
-	enum bdi_state bit;
-
-	bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
-	set_bit(bit, &q->backing_dev_info.state);
-}
-EXPORT_SYMBOL(blk_set_queue_congested);
-
 /**
  * blk_get_backing_dev_info - get the address of a queue's backing_dev_info
  * @bdev:	device
@@ -2755,41 +2719,6 @@ void blk_end_sync_rq(struct request *rq, int error)
 }
 EXPORT_SYMBOL(blk_end_sync_rq);
 
-/**
- * blk_congestion_wait - wait for a queue to become uncongested
- * @rw: READ or WRITE
- * @timeout: timeout in jiffies
- *
- * Waits for up to @timeout jiffies for a queue (any queue) to exit congestion.
- * If no queues are congested then just wait for the next request to be
- * returned.
- */
-long blk_congestion_wait(int rw, long timeout)
-{
-	long ret;
-	DEFINE_WAIT(wait);
-	wait_queue_head_t *wqh = &congestion_wqh[rw];
-
-	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
-	ret = io_schedule_timeout(timeout);
-	finish_wait(wqh, &wait);
-	return ret;
-}
-
-EXPORT_SYMBOL(blk_congestion_wait);
-
-/**
- * blk_congestion_end - wake up sleepers on a congestion queue
- * @rw: READ or WRITE
- */
-void blk_congestion_end(int rw)
-{
-	wait_queue_head_t *wqh = &congestion_wqh[rw];
-
-	if (waitqueue_active(wqh))
-		wake_up(wqh);
-}
-
 /*
  * Has to be called with the request spinlock acquired
  */
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 655d816..a625576 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/crypto.h>
 #include <linux/workqueue.h>
+#include <linux/backing-dev.h>
 #include <asm/atomic.h>
 #include <linux/scatterlist.h>
 #include <asm/page.h>
@@ -602,7 +603,7 @@ static void process_write(struct crypt_io *io)
 
 		/* out of memory -> run queues */
 		if (remaining)
-			blk_congestion_wait(bio_data_dir(clone), HZ/100);
+			congestion_wait(bio_data_dir(clone), HZ/100);
 	}
 }
 
diff --git a/fs/fat/file.c b/fs/fat/file.c
index f4b8f8b..8337451 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -13,6 +13,7 @@
 #include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include <linux/writeback.h>
+#include <linux/backing-dev.h>
 #include <linux/blkdev.h>
 
 int fat_generic_ioctl(struct inode *inode, struct file *filp,
@@ -118,7 +119,7 @@ static int fat_file_release(struct inode *inode, struct file *filp)
 	if ((filp->f_mode & FMODE_WRITE) &&
 	     MSDOS_SB(inode->i_sb)->options.flush) {
 		fat_flush_inodes(inode->i_sb, inode, NULL);
-		blk_congestion_wait(WRITE, HZ/10);
+		congestion_wait(WRITE, HZ/10);
 	}
 	return 0;
 }
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index f6675d2..ca92ac3 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -57,6 +57,8 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_mount.h>
 #include <linux/nfs_page.h>
+#include <linux/backing-dev.h>
+
 #include <asm/uaccess.h>
 #include <linux/smp_lock.h>
 
@@ -395,7 +397,7 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 out:
 	clear_bit(BDI_write_congested, &bdi->state);
 	wake_up_all(&nfs_write_congestion);
-	writeback_congestion_end();
+	congestion_end(WRITE);
 	return err;
 }
 
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index ad8cbc4..85ce232 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -53,6 +53,7 @@
 #include <linux/workqueue.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
+#include <linux/backing-dev.h>
 
 /* gets a struct reiserfs_journal_list * from a list head */
 #define JOURNAL_LIST_ENTRY(h) (list_entry((h), struct reiserfs_journal_list, \
@@ -970,7 +971,7 @@ int reiserfs_async_progress_wait(struct super_block *s)
 	DEFINE_WAIT(wait);
 	struct reiserfs_journal *j = SB_JOURNAL(s);
 	if (atomic_read(&j->j_async_throttle))
-		blk_congestion_wait(WRITE, HZ / 10);
+		congestion_wait(WRITE, HZ / 10);
 	return 0;
 }
 
diff --git a/fs/xfs/linux-2.6/kmem.c b/fs/xfs/linux-2.6/kmem.c
index d597375..004baf6 100644
--- a/fs/xfs/linux-2.6/kmem.c
+++ b/fs/xfs/linux-2.6/kmem.c
@@ -21,6 +21,7 @@
 #include <linux/highmem.h>
 #include <linux/swap.h>
 #include <linux/blkdev.h>
+#include <linux/backing-dev.h>
 #include "time.h"
 #include "kmem.h"
 
@@ -53,7 +54,7 @@ kmem_alloc(size_t size, unsigned int __nocast flags)
 			printk(KERN_ERR "XFS: possible memory allocation "
 					"deadlock in %s (mode:0x%x)\n",
 					__FUNCTION__, lflags);
-		blk_congestion_wait(WRITE, HZ/50);
+		congestion_wait(WRITE, HZ/50);
 	} while (1);
 }
 
@@ -131,7 +132,7 @@ kmem_zone_alloc(kmem_zone_t *zone, unsigned int __nocast flags)
 			printk(KERN_ERR "XFS: possible memory allocation "
 					"deadlock in %s (mode:0x%x)\n",
 					__FUNCTION__, lflags);
-		blk_congestion_wait(WRITE, HZ/50);
+		congestion_wait(WRITE, HZ/50);
 	} while (1);
 }
 
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 9bbadaf..db5f5a3 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -30,6 +30,7 @@
 #include <linux/hash.h>
 #include <linux/kthread.h>
 #include <linux/migrate.h>
+#include <linux/backing-dev.h>
 #include "xfs_linux.h"
 
 STATIC kmem_zone_t *xfs_buf_zone;
@@ -395,7 +396,7 @@ _xfs_buf_lookup_pages(
 
 			XFS_STATS_INC(xb_page_retries);
 			xfsbufd_wakeup(0, gfp_mask);
-			blk_congestion_wait(WRITE, HZ/50);
+			congestion_wait(WRITE, HZ/50);
 			goto retry;
 		}
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index f7a1390..7011d625 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -10,6 +10,8 @@
 
 #include <asm/atomic.h>
 
+struct page;
+
 /*
  * Bits in backing_dev_info.state
  */
@@ -88,6 +90,11 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi)
 				  (1 << BDI_write_congested));
 }
 
+void clear_bdi_congested(struct backing_dev_info *bdi, int rw);
+void set_bdi_congested(struct backing_dev_info *bdi, int rw);
+long congestion_wait(int rw, long timeout);
+void congestion_end(int rw);
+
 #define bdi_cap_writeback_dirty(bdi) \
 	(!((bdi)->capabilities & BDI_CAP_NO_WRITEBACK))
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 9575e3a..7bfcde2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -651,8 +651,26 @@ extern void blk_recount_segments(request_queue_t *, struct bio *);
 extern int scsi_cmd_ioctl(struct file *, struct gendisk *, unsigned int, void __user *);
 extern int sg_scsi_ioctl(struct file *, struct request_queue *,
 		struct gendisk *, struct scsi_ioctl_command __user *);
-extern void blk_clear_queue_congested(request_queue_t *q, int rw);
-extern void blk_set_queue_congested(request_queue_t *q, int rw);
+
+/*
+ * A queue has just exitted congestion.  Note this in the global counter of
+ * congested queues, and wake up anyone who was waiting for requests to be
+ * put back.
+ */
+static inline void blk_clear_queue_congested(request_queue_t *q, int rw)
+{
+	clear_bdi_congested(&q->backing_dev_info, rw);
+}
+
+/*
+ * A queue has just entered congestion.  Flag that in the queue's VM-visible
+ * state flags and increment the global gounter of congested queues.
+ */
+static inline void blk_set_queue_congested(request_queue_t *q, int rw)
+{
+	set_bdi_congested(&q->backing_dev_info, rw);
+}
+
 extern void blk_start_queue(request_queue_t *q);
 extern void blk_stop_queue(request_queue_t *q);
 extern void blk_sync_queue(struct request_queue *q);
@@ -767,10 +785,8 @@ extern int blk_queue_init_tags(request_queue_t *, int, struct blk_queue_tag *);
 extern void blk_queue_free_tags(request_queue_t *);
 extern int blk_queue_resize_tags(request_queue_t *, int);
 extern void blk_queue_invalidate_tags(request_queue_t *);
-extern long blk_congestion_wait(int rw, long timeout);
 extern struct blk_queue_tag *blk_init_tags(int);
 extern void blk_free_tags(struct blk_queue_tag *);
-extern void blk_congestion_end(int rw);
 
 static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
 						int tag)
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index a341c80..fc35e6b 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -85,7 +85,6 @@ int wakeup_pdflush(long nr_pages);
 void laptop_io_completion(void);
 void laptop_sync_completion(void);
 void throttle_vm_writeout(void);
-void writeback_congestion_end(void);
 
 /* These are exported to sysctl. */
 extern int dirty_background_ratio;
diff --git a/mm/Makefile b/mm/Makefile
index 12b3a4e..f3c077e 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -10,7 +10,8 @@ mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
 obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
 			   page_alloc.o page-writeback.o pdflush.o \
 			   readahead.o swap.o truncate.o vmscan.o \
-			   prio_tree.o util.o mmzone.o vmstat.o $(mmu-y)
+			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
+			   $(mmu-y)
 
 ifeq ($(CONFIG_MMU)$(CONFIG_BLOCK),yy)
 obj-y			+= bounce.o
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
new file mode 100644
index 0000000..f50a281
--- /dev/null
+++ b/mm/backing-dev.c
@@ -0,0 +1,69 @@
+
+#include <linux/wait.h>
+#include <linux/backing-dev.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+
+static wait_queue_head_t congestion_wqh[2] = {
+		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
+		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
+	};
+
+
+void clear_bdi_congested(struct backing_dev_info *bdi, int rw)
+{
+	enum bdi_state bit;
+	wait_queue_head_t *wqh = &congestion_wqh[rw];
+
+	bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
+	clear_bit(bit, &bdi->state);
+	smp_mb__after_clear_bit();
+	if (waitqueue_active(wqh))
+		wake_up(wqh);
+}
+EXPORT_SYMBOL(clear_bdi_congested);
+
+void set_bdi_congested(struct backing_dev_info *bdi, int rw)
+{
+	enum bdi_state bit;
+
+	bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
+	set_bit(bit, &bdi->state);
+}
+EXPORT_SYMBOL(set_bdi_congested);
+
+/**
+ * congestion_wait - wait for a backing_dev to become uncongested
+ * @rw: READ or WRITE
+ * @timeout: timeout in jiffies
+ *
+ * Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit
+ * write congestion.  If no backing_devs are congested then just wait for the
+ * next write to be completed.
+ */
+long congestion_wait(int rw, long timeout)
+{
+	long ret;
+	DEFINE_WAIT(wait);
+	wait_queue_head_t *wqh = &congestion_wqh[rw];
+
+	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
+	ret = io_schedule_timeout(timeout);
+	finish_wait(wqh, &wait);
+	return ret;
+}
+EXPORT_SYMBOL(congestion_wait);
+
+/**
+ * congestion_end - wake up sleepers on a congested backing_dev_info
+ * @rw: READ or WRITE
+ */
+void congestion_end(int rw)
+{
+	wait_queue_head_t *wqh = &congestion_wqh[rw];
+
+	if (waitqueue_active(wqh))
+		wake_up(wqh);
+}
+EXPORT_SYMBOL(congestion_end);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index a0f3390..8d9b19f 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -222,7 +222,7 @@ static void balance_dirty_pages(struct address_space *mapping)
 			if (pages_written >= write_chunk)
 				break;		/* We've done our duty */
 		}
-		blk_congestion_wait(WRITE, HZ/10);
+		congestion_wait(WRITE, HZ/10);
 	}
 
 	if (nr_reclaimable + global_page_state(NR_WRITEBACK)
@@ -314,7 +314,7 @@ void throttle_vm_writeout(void)
                 if (global_page_state(NR_UNSTABLE_NFS) +
 			global_page_state(NR_WRITEBACK) <= dirty_thresh)
                         	break;
-                blk_congestion_wait(WRITE, HZ/10);
+                congestion_wait(WRITE, HZ/10);
         }
 }
 
@@ -351,7 +351,7 @@ static void background_writeout(unsigned long _min_pages)
 		min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
 		if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
 			/* Wrote less than expected */
-			blk_congestion_wait(WRITE, HZ/10);
+			congestion_wait(WRITE, HZ/10);
 			if (!wbc.encountered_congestion)
 				break;
 		}
@@ -422,7 +422,7 @@ static void wb_kupdate(unsigned long arg)
 		writeback_inodes(&wbc);
 		if (wbc.nr_to_write > 0) {
 			if (wbc.encountered_congestion)
-				blk_congestion_wait(WRITE, HZ/10);
+				congestion_wait(WRITE, HZ/10);
 			else
 				break;	/* All the old data is written */
 		}
@@ -956,15 +956,6 @@ int test_set_page_writeback(struct page *page)
 EXPORT_SYMBOL(test_set_page_writeback);
 
 /*
- * Wakes up tasks that are being throttled due to writeback congestion
- */
-void writeback_congestion_end(void)
-{
-	blk_congestion_end(WRITE);
-}
-EXPORT_SYMBOL(writeback_congestion_end);
-
-/*
  * Return true if any of the pages in the mapping are marged with the
  * passed tag.
  */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 40db96a..afee38f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -39,6 +39,7 @@
 #include <linux/stop_machine.h>
 #include <linux/sort.h>
 #include <linux/pfn.h>
+#include <linux/backing-dev.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -1050,7 +1051,7 @@ nofail_alloc:
 			if (page)
 				goto got_pg;
 			if (gfp_mask & __GFP_NOFAIL) {
-				blk_congestion_wait(WRITE, HZ/50);
+				congestion_wait(WRITE, HZ/50);
 				goto nofail_alloc;
 			}
 		}
@@ -1113,7 +1114,7 @@ rebalance:
 			do_retry = 1;
 	}
 	if (do_retry) {
-		blk_congestion_wait(WRITE, HZ/50);
+		congestion_wait(WRITE, HZ/50);
 		goto rebalance;
 	}
 
diff --git a/mm/shmem.c b/mm/shmem.c
index b378f66..4959535 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -48,6 +48,7 @@
 #include <linux/ctype.h>
 #include <linux/migrate.h>
 #include <linux/highmem.h>
+#include <linux/backing-dev.h>
 
 #include <asm/uaccess.h>
 #include <asm/div64.h>
@@ -1131,7 +1132,7 @@ repeat:
 			page_cache_release(swappage);
 			if (error == -ENOMEM) {
 				/* let kswapd refresh zone for GFP_ATOMICs */
-				blk_congestion_wait(WRITE, HZ/50);
+				congestion_wait(WRITE, HZ/50);
 			}
 			goto repeat;
 		}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index af73c14..f05527b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1059,7 +1059,7 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 
 		/* Take a nap, wait for some writeback to complete */
 		if (sc.nr_scanned && priority < DEF_PRIORITY - 2)
-			blk_congestion_wait(WRITE, HZ/10);
+			congestion_wait(WRITE, HZ/10);
 	}
 	/* top priority shrink_caches still had more to do? don't OOM, then */
 	if (!sc.all_unreclaimable)
@@ -1214,7 +1214,7 @@ scan:
 		 * another pass across the zones.
 		 */
 		if (total_scanned && priority < DEF_PRIORITY - 2)
-			blk_congestion_wait(WRITE, HZ/10);
+			congestion_wait(WRITE, HZ/10);
 
 		/*
 		 * We do this so kswapd doesn't build up large priorities for
@@ -1458,7 +1458,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 				goto out;
 
 			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
-				blk_congestion_wait(WRITE, HZ / 10);
+				congestion_wait(WRITE, HZ / 10);
 		}
 
 		lru_pages = 0;