Re: [PATCH] Fix congestion_wait() sync/async vs read/write confusion

[Chris Mason <chris.mason@oracle.com>]

On Wed, Jul 08, 2009 at 08:47:03PM +0200, Jens Axboe wrote:
> Hi,
> 
> This one isn't great, we currently have broken congestion wait logic in
> the kernel. 2.6.30 is impacted as well, so this patch should go to
> stable too once it's in -git. I'll let this one simmer until tomorrow,
> then ask Linus to pull it. The offending commit breaking this is
> 1faa16d22877f4839bd433547d770c676d1d964c.
> 
> Meanwhile, it could potentially cause buffered writeout slowdowns in the
> kernel. Perhaps the 2.6.30 regression in that area is caused by this?
> Would be interesting if the submitter could test. I can't find the list,
> CC'ing Rafael.

Even if this does slow down some workloads, the bug is not in using the
correct flag ;) So, I'd ack this one.

Jan Kara was able to reproduce the tiobench 2.6.30 regression, so I've
cc'd him and kept the patch below.

-chris

diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 7c8ca91..1f118d4 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -751,7 +751,7 @@ survive:
 
 			if (retval == -ENOMEM && is_global_init(current)) {
 				up_read(&current->mm->mmap_sem);
-				congestion_wait(WRITE, HZ/50);
+				congestion_wait(BLK_RW_ASYNC, HZ/50);
 				goto survive;
 			}
 
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 83650e0..f7ebe74 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2595,7 +2595,7 @@ static int pkt_make_request(struct request_queue *q, struct bio *bio)
 		set_bdi_congested(&q->backing_dev_info, WRITE);
 		do {
 			spin_unlock(&pd->lock);
-			congestion_wait(WRITE, HZ);
+			congestion_wait(BLK_RW_ASYNC, HZ);
 			spin_lock(&pd->lock);
 		} while(pd->bio_queue_size > pd->write_congestion_off);
 	}
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 9933eb8..529e2ba 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -776,7 +776,7 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 		 * But don't wait if split was due to the io size restriction
 		 */
 		if (unlikely(out_of_pages))
-			congestion_wait(WRITE, HZ/100);
+			congestion_wait(BLK_RW_ASYNC, HZ/100);
 
 		/*
 		 * With async crypto it is unsafe to share the crypto context
diff --git a/fs/fat/file.c b/fs/fat/file.c
index b28ea64..f042b96 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -134,7 +134,7 @@ 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);
-		congestion_wait(WRITE, HZ/10);
+		congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 	return 0;
 }
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 77f5bb7..9062220 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -997,7 +997,7 @@ static 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))
-		congestion_wait(WRITE, HZ / 10);
+		congestion_wait(BLK_RW_ASYNC, HZ / 10);
 	return 0;
 }
 
diff --git a/fs/xfs/linux-2.6/kmem.c b/fs/xfs/linux-2.6/kmem.c
index 1cd3b55..2d3f90a 100644
--- a/fs/xfs/linux-2.6/kmem.c
+++ b/fs/xfs/linux-2.6/kmem.c
@@ -53,7 +53,7 @@ kmem_alloc(size_t size, unsigned int __nocast flags)
 			printk(KERN_ERR "XFS: possible memory allocation "
 					"deadlock in %s (mode:0x%x)\n",
 					__func__, lflags);
-		congestion_wait(WRITE, HZ/50);
+		congestion_wait(BLK_RW_ASYNC, HZ/50);
 	} while (1);
 }
 
@@ -130,7 +130,7 @@ 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",
 					__func__, lflags);
-		congestion_wait(WRITE, HZ/50);
+		congestion_wait(BLK_RW_ASYNC, 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 1418b91..0c93c7e 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -412,7 +412,7 @@ _xfs_buf_lookup_pages(
 
 			XFS_STATS_INC(xb_page_retries);
 			xfsbufd_wakeup(0, gfp_mask);
-			congestion_wait(WRITE, HZ/50);
+			congestion_wait(BLK_RW_ASYNC, HZ/50);
 			goto retry;
 		}
 
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 493b468..c86edd2 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -283,7 +283,6 @@ static wait_queue_head_t congestion_wqh[2] = {
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
 	};
 
-
 void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
 	enum bdi_state bit;
@@ -308,18 +307,18 @@ EXPORT_SYMBOL(set_bdi_congested);
 
 /**
  * congestion_wait - wait for a backing_dev to become uncongested
- * @rw: READ or WRITE
+ * @sync: SYNC or ASYNC IO
  * @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 congestion_wait(int sync, long timeout)
 {
 	long ret;
 	DEFINE_WAIT(wait);
-	wait_queue_head_t *wqh = &congestion_wqh[rw];
+	wait_queue_head_t *wqh = &congestion_wqh[sync];
 
 	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
 	ret = io_schedule_timeout(timeout);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e2fa20d..e717964 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1973,7 +1973,7 @@ try_to_free:
 		if (!progress) {
 			nr_retries--;
 			/* maybe some writeback is necessary */
-			congestion_wait(WRITE, HZ/10);
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
 		}
 
 	}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 7687879..81627eb 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -575,7 +575,7 @@ static void balance_dirty_pages(struct address_space *mapping)
 		if (pages_written >= write_chunk)
 			break;		/* We've done our duty */
 
-		congestion_wait(WRITE, HZ/10);
+		congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 
 	if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
@@ -669,7 +669,7 @@ void throttle_vm_writeout(gfp_t gfp_mask)
                 if (global_page_state(NR_UNSTABLE_NFS) +
 			global_page_state(NR_WRITEBACK) <= dirty_thresh)
                         	break;
-                congestion_wait(WRITE, HZ/10);
+                congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 		/*
 		 * The caller might hold locks which can prevent IO completion
@@ -715,7 +715,7 @@ static void background_writeout(unsigned long _min_pages)
 		if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
 			/* Wrote less than expected */
 			if (wbc.encountered_congestion || wbc.more_io)
-				congestion_wait(WRITE, HZ/10);
+				congestion_wait(BLK_RW_ASYNC, HZ/10);
 			else
 				break;
 		}
@@ -787,7 +787,7 @@ static void wb_kupdate(unsigned long arg)
 		writeback_inodes(&wbc);
 		if (wbc.nr_to_write > 0) {
 			if (wbc.encountered_congestion || wbc.more_io)
-				congestion_wait(WRITE, HZ/10);
+				congestion_wait(BLK_RW_ASYNC, HZ/10);
 			else
 				break;	/* All the old data is written */
 		}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e0f2cdf..2862bcf 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1666,7 +1666,7 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
 			preferred_zone, migratetype);
 
 		if (!page && gfp_mask & __GFP_NOFAIL)
-			congestion_wait(WRITE, HZ/50);
+			congestion_wait(BLK_RW_ASYNC, HZ/50);
 	} while (!page && (gfp_mask & __GFP_NOFAIL));
 
 	return page;
@@ -1831,7 +1831,7 @@ rebalance:
 	pages_reclaimed += did_some_progress;
 	if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) {
 		/* Wait for some write requests to complete then retry */
-		congestion_wait(WRITE, HZ/50);
+		congestion_wait(BLK_RW_ASYNC, HZ/50);
 		goto rebalance;
 	}
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5415526..dea7abd 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1104,7 +1104,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		 */
 		if (nr_freed < nr_taken && !current_is_kswapd() &&
 		    lumpy_reclaim) {
-			congestion_wait(WRITE, HZ/10);
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 			/*
 			 * The attempt at page out may have made some
@@ -1721,7 +1721,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 
 		/* Take a nap, wait for some writeback to complete */
 		if (sc->nr_scanned && priority < DEF_PRIORITY - 2)
-			congestion_wait(WRITE, HZ/10);
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 	/* top priority shrink_zones still had more to do? don't OOM, then */
 	if (!sc->all_unreclaimable && scanning_global_lru(sc))
@@ -1960,7 +1960,7 @@ loop_again:
 		 * another pass across the zones.
 		 */
 		if (total_scanned && priority < DEF_PRIORITY - 2)
-			congestion_wait(WRITE, HZ/10);
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 		/*
 		 * We do this so kswapd doesn't build up large priorities for
@@ -2233,7 +2233,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 				goto out;
 
 			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
-				congestion_wait(WRITE, HZ / 10);
+				congestion_wait(BLK_RW_ASYNC, HZ / 10);
 		}
 	}
 

-- 
Jens Axboe