From 018e0446890661504783f92388ecce7138c1566d Mon Sep 17 00:00:00 2001
From: Jens Axboe <jens.axboe@oracle.com>
Date: Fri, 26 Jun 2009 16:27:10 +0200
Subject: block: get rid of queue-private command filter

The initial patches to support this through sysfs export were broken
and have been if 0'ed out in any release. So lets just kill the code
and reclaim some space in struct request_queue, if anyone would later
like to fixup the sysfs bits, the git history can easily restore
the removed bits.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 include/linux/blkdev.h | 15 +--------------
 1 file changed, 1 insertion(+), 14 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8963d9149b5f..49ae07951d55 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -301,12 +301,6 @@ struct blk_queue_tag {
 #define BLK_SCSI_MAX_CMDS	(256)
 #define BLK_SCSI_CMD_PER_LONG	(BLK_SCSI_MAX_CMDS / (sizeof(long) * 8))
 
-struct blk_cmd_filter {
-	unsigned long read_ok[BLK_SCSI_CMD_PER_LONG];
-	unsigned long write_ok[BLK_SCSI_CMD_PER_LONG];
-	struct kobject kobj;
-};
-
 struct queue_limits {
 	unsigned long		bounce_pfn;
 	unsigned long		seg_boundary_mask;
@@ -445,7 +439,6 @@ struct request_queue
 #if defined(CONFIG_BLK_DEV_BSG)
 	struct bsg_class_device bsg_dev;
 #endif
-	struct blk_cmd_filter cmd_filter;
 };
 
 #define QUEUE_FLAG_CLUSTER	0	/* cluster several segments into 1 */
@@ -998,13 +991,7 @@ static inline int sb_issue_discard(struct super_block *sb,
 	return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL);
 }
 
-/*
-* command filter functions
-*/
-extern int blk_verify_command(struct blk_cmd_filter *filter,
-			      unsigned char *cmd, fmode_t has_write_perm);
-extern void blk_unregister_filter(struct gendisk *disk);
-extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter);
+extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
 
 #define MAX_PHYS_SEGMENTS 128
 #define MAX_HW_SEGMENTS 128
-- 
cgit v1.3-8-gc7d7


From 8aa7e847d834ed937a9ad37a0f2ad5b8584c1ab0 Mon Sep 17 00:00:00 2001
From: Jens Axboe <jens.axboe@oracle.com>
Date: Thu, 9 Jul 2009 14:52:32 +0200
Subject: Fix congestion_wait() sync/async vs read/write confusion

Commit 1faa16d22877f4839bd433547d770c676d1d964c accidentally broke
the bdi congestion wait queue logic, causing us to wait on congestion
for WRITE (== 1) when we really wanted BLK_RW_ASYNC (== 0) instead.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 arch/x86/lib/usercopy_32.c  |  2 +-
 drivers/block/pktcdvd.c     | 10 ++++++----
 drivers/md/dm-crypt.c       |  2 +-
 fs/fat/file.c               |  2 +-
 fs/fuse/dev.c               |  8 ++++----
 fs/nfs/write.c              |  8 +++++---
 fs/reiserfs/journal.c       |  2 +-
 fs/xfs/linux-2.6/kmem.c     |  4 ++--
 fs/xfs/linux-2.6/xfs_buf.c  |  2 +-
 include/linux/backing-dev.h |  6 +++---
 include/linux/blkdev.h      |  8 ++++----
 mm/backing-dev.c            |  7 +++----
 mm/memcontrol.c             |  2 +-
 mm/page-writeback.c         |  8 ++++----
 mm/page_alloc.c             |  4 ++--
 mm/vmscan.c                 |  8 ++++----
 16 files changed, 43 insertions(+), 40 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 7c8ca91bb9ec..1f118d462acc 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 83650e00632d..99a506f619b7 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -1372,8 +1372,10 @@ try_next_bio:
 	wakeup = (pd->write_congestion_on > 0
 	 		&& pd->bio_queue_size <= pd->write_congestion_off);
 	spin_unlock(&pd->lock);
-	if (wakeup)
-		clear_bdi_congested(&pd->disk->queue->backing_dev_info, WRITE);
+	if (wakeup) {
+		clear_bdi_congested(&pd->disk->queue->backing_dev_info,
+					BLK_RW_ASYNC);
+	}
 
 	pkt->sleep_time = max(PACKET_WAIT_TIME, 1);
 	pkt_set_state(pkt, PACKET_WAITING_STATE);
@@ -2592,10 +2594,10 @@ static int pkt_make_request(struct request_queue *q, struct bio *bio)
 	spin_lock(&pd->lock);
 	if (pd->write_congestion_on > 0
 	    && pd->bio_queue_size >= pd->write_congestion_on) {
-		set_bdi_congested(&q->backing_dev_info, WRITE);
+		set_bdi_congested(&q->backing_dev_info, BLK_RW_ASYNC);
 		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 9933eb861c71..529e2ba505c3 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 b28ea646ff60..f042b965c95c 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/fuse/dev.c b/fs/fuse/dev.c
index f58ecbc416c8..6484eb75acd6 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -286,8 +286,8 @@ __releases(&fc->lock)
 		}
 		if (fc->num_background == FUSE_CONGESTION_THRESHOLD &&
 		    fc->connected && fc->bdi_initialized) {
-			clear_bdi_congested(&fc->bdi, READ);
-			clear_bdi_congested(&fc->bdi, WRITE);
+			clear_bdi_congested(&fc->bdi, BLK_RW_SYNC);
+			clear_bdi_congested(&fc->bdi, BLK_RW_ASYNC);
 		}
 		fc->num_background--;
 		fc->active_background--;
@@ -414,8 +414,8 @@ static void fuse_request_send_nowait_locked(struct fuse_conn *fc,
 		fc->blocked = 1;
 	if (fc->num_background == FUSE_CONGESTION_THRESHOLD &&
 	    fc->bdi_initialized) {
-		set_bdi_congested(&fc->bdi, READ);
-		set_bdi_congested(&fc->bdi, WRITE);
+		set_bdi_congested(&fc->bdi, BLK_RW_SYNC);
+		set_bdi_congested(&fc->bdi, BLK_RW_ASYNC);
 	}
 	list_add_tail(&req->list, &fc->bg_queue);
 	flush_bg_queue(fc);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index ce728829f79a..0a0a2ff767c3 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -202,8 +202,10 @@ static int nfs_set_page_writeback(struct page *page)
 		struct nfs_server *nfss = NFS_SERVER(inode);
 
 		if (atomic_long_inc_return(&nfss->writeback) >
-				NFS_CONGESTION_ON_THRESH)
-			set_bdi_congested(&nfss->backing_dev_info, WRITE);
+				NFS_CONGESTION_ON_THRESH) {
+			set_bdi_congested(&nfss->backing_dev_info,
+						BLK_RW_ASYNC);
+		}
 	}
 	return ret;
 }
@@ -215,7 +217,7 @@ static void nfs_end_page_writeback(struct page *page)
 
 	end_page_writeback(page);
 	if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
-		clear_bdi_congested(&nfss->backing_dev_info, WRITE);
+		clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
 }
 
 /*
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 77f5bb746bf0..90622200b39c 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 1cd3b55ee3d2..2d3f90afe5f1 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 1418b916fc27..0c93c7ef3d18 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/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 0ec2c594868e..3a52a63c1351 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -229,9 +229,9 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi)
 				  (1 << BDI_async_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 clear_bdi_congested(struct backing_dev_info *bdi, int sync);
+void set_bdi_congested(struct backing_dev_info *bdi, int sync);
+long congestion_wait(int sync, long timeout);
 
 
 static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 49ae07951d55..bb3d39978701 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -779,18 +779,18 @@ extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
  * congested queues, and wake up anyone who was waiting for requests to be
  * put back.
  */
-static inline void blk_clear_queue_congested(struct request_queue *q, int rw)
+static inline void blk_clear_queue_congested(struct request_queue *q, int sync)
 {
-	clear_bdi_congested(&q->backing_dev_info, rw);
+	clear_bdi_congested(&q->backing_dev_info, sync);
 }
 
 /*
  * 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(struct request_queue *q, int rw)
+static inline void blk_set_queue_congested(struct request_queue *q, int sync)
 {
-	set_bdi_congested(&q->backing_dev_info, rw);
+	set_bdi_congested(&q->backing_dev_info, sync);
 }
 
 extern void blk_start_queue(struct request_queue *q);
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 493b468a5035..c86edd244294 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 e2fa20dadf40..e717964cb5a0 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 7687879253b9..81627ebcd313 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 ad7cd1c56b07..a35eeab2724c 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 54155268dfca..dea7abd31098 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);
 		}
 	}
 
-- 
cgit v1.3-8-gc7d7


From ecb554a846f8e9d2a58f6d6c118168a63ac065aa Mon Sep 17 00:00:00 2001
From: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Date: Thu, 9 Jul 2009 14:46:53 +0200
Subject: block: fix sg SG_DXFER_TO_FROM_DEV regression

I overlooked SG_DXFER_TO_FROM_DEV support when I converted sg to use
the block layer mapping API (2.6.28).

Douglas Gilbert explained SG_DXFER_TO_FROM_DEV:

http://www.spinics.net/lists/linux-scsi/msg37135.html

=
The semantics of SG_DXFER_TO_FROM_DEV were:
   - copy user space buffer to kernel (LLD) buffer
   - do SCSI command which is assumed to be of the DATA_IN
     (data from device) variety. This would overwrite
     some or all of the kernel buffer
   - copy kernel (LLD) buffer back to the user space.

The idea was to detect short reads by filling the original
user space buffer with some marker bytes ("0xec" it would
seem in this report). The "resid" value is a better way
of detecting short reads but that was only added this century
and requires co-operation from the LLD.
=

This patch changes the block layer mapping API to support this
semantics. This simply adds another field to struct rq_map_data and
enables __bio_copy_iov() to copy data from user space even with READ
requests.

It's better to add the flags field and kills null_mapped and the new
from_user fields in struct rq_map_data but that approach makes it
difficult to send this patch to stable trees because st and osst
drivers use struct rq_map_data (they were converted to use the block
layer in 2.6.29 and 2.6.30). Well, I should clean up the block layer
mapping API.

zhou sf reported this regiression and tested this patch:

http://www.spinics.net/lists/linux-scsi/msg37128.html
http://www.spinics.net/lists/linux-scsi/msg37168.html

Reported-by: zhou sf <sxzzsf@gmail.com>
Tested-by: zhou sf <sxzzsf@gmail.com>
Cc: stable@kernel.org
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 drivers/scsi/sg.c      |  4 ++++
 fs/bio.c               | 22 ++++++++++++----------
 include/linux/blkdev.h |  1 +
 3 files changed, 17 insertions(+), 10 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 4d6f2fe1cfe9..9230402c45af 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1656,6 +1656,10 @@ static int sg_start_req(Sg_request *srp, unsigned char *cmd)
 		md->nr_entries = req_schp->k_use_sg;
 		md->offset = 0;
 		md->null_mapped = hp->dxferp ? 0 : 1;
+		if (dxfer_dir == SG_DXFER_TO_FROM_DEV)
+			md->from_user = 1;
+		else
+			md->from_user = 0;
 	}
 
 	if (iov_count) {
diff --git a/fs/bio.c b/fs/bio.c
index 1486b19fc431..76738005c8e8 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -705,14 +705,13 @@ static struct bio_map_data *bio_alloc_map_data(int nr_segs, int iov_count,
 }
 
 static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
-			  struct sg_iovec *iov, int iov_count, int uncopy,
-			  int do_free_page)
+			  struct sg_iovec *iov, int iov_count,
+			  int to_user, int from_user, int do_free_page)
 {
 	int ret = 0, i;
 	struct bio_vec *bvec;
 	int iov_idx = 0;
 	unsigned int iov_off = 0;
-	int read = bio_data_dir(bio) == READ;
 
 	__bio_for_each_segment(bvec, bio, i, 0) {
 		char *bv_addr = page_address(bvec->bv_page);
@@ -727,13 +726,14 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
 			iov_addr = iov[iov_idx].iov_base + iov_off;
 
 			if (!ret) {
-				if (!read && !uncopy)
-					ret = copy_from_user(bv_addr, iov_addr,
-							     bytes);
-				if (read && uncopy)
+				if (to_user)
 					ret = copy_to_user(iov_addr, bv_addr,
 							   bytes);
 
+				if (from_user)
+					ret = copy_from_user(bv_addr, iov_addr,
+							     bytes);
+
 				if (ret)
 					ret = -EFAULT;
 			}
@@ -770,7 +770,8 @@ int bio_uncopy_user(struct bio *bio)
 
 	if (!bio_flagged(bio, BIO_NULL_MAPPED))
 		ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs,
-				     bmd->nr_sgvecs, 1, bmd->is_our_pages);
+				     bmd->nr_sgvecs, bio_data_dir(bio) == READ,
+				     0, bmd->is_our_pages);
 	bio_free_map_data(bmd);
 	bio_put(bio);
 	return ret;
@@ -875,8 +876,9 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 	/*
 	 * success
 	 */
-	if (!write_to_vm && (!map_data || !map_data->null_mapped)) {
-		ret = __bio_copy_iov(bio, bio->bi_io_vec, iov, iov_count, 0, 0);
+	if ((!write_to_vm && (!map_data || !map_data->null_mapped)) ||
+	    (map_data && map_data->from_user)) {
+		ret = __bio_copy_iov(bio, bio->bi_io_vec, iov, iov_count, 0, 1, 0);
 		if (ret)
 			goto cleanup;
 	}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index bb3d39978701..0146e0fecf1a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -723,6 +723,7 @@ struct rq_map_data {
 	int nr_entries;
 	unsigned long offset;
 	int null_mapped;
+	int from_user;
 };
 
 struct req_iterator {
-- 
cgit v1.3-8-gc7d7


From 373c0a7ed3ea3b34efedb7c83ffb521adff7c894 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Sat, 11 Jul 2009 10:06:54 -0400
Subject: Fix compile error due to congestion_wait() changes

Move the definition of BLK_RW_ASYNC/BLK_RW_SYNC into linux/backing-dev.h
so that it is available to all callers of set/clear_bdi_congested().

This replaces commit 097041e576ee3a50d92dd643ee8ca65bf6a62e21 ("fuse:
Fix build error"), which will be reverted.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Acked-by: Larry Finger <Larry.Finger@lwfinger.net>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/backing-dev.h | 5 +++++
 include/linux/blkdev.h      | 5 -----
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 3a52a63c1351..1d52425a6118 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -229,6 +229,11 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi)
 				  (1 << BDI_async_congested));
 }
 
+enum {
+	BLK_RW_ASYNC	= 0,
+	BLK_RW_SYNC	= 1,
+};
+
 void clear_bdi_congested(struct backing_dev_info *bdi, int sync);
 void set_bdi_congested(struct backing_dev_info *bdi, int sync);
 long congestion_wait(int sync, long timeout);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0146e0fecf1a..e7cb5dbf6c26 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -70,11 +70,6 @@ enum rq_cmd_type_bits {
 	REQ_TYPE_ATA_PC,
 };
 
-enum {
-	BLK_RW_ASYNC	= 0,
-	BLK_RW_SYNC	= 1,
-};
-
 /*
  * For request of type REQ_TYPE_LINUX_BLOCK, rq->cmd[0] is the opcode being
  * sent down (similar to how REQ_TYPE_BLOCK_PC means that ->cmd[] holds a
-- 
cgit v1.3-8-gc7d7


From 7c958e32649e0c35801762878fb0b6da8c55a515 Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 31 Jul 2009 11:49:11 -0400
Subject: block: Add a wrapper for setting minimum request size without a queue

Introduce blk_limits_io_min() and make blk_queue_io_min() call it.

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-settings.c   | 31 ++++++++++++++++++++++++-------
 include/linux/blkdev.h |  1 +
 2 files changed, 25 insertions(+), 7 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 8e86e2d2b147..1f7197434166 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -383,6 +383,29 @@ void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset)
 }
 EXPORT_SYMBOL(blk_queue_alignment_offset);
 
+/**
+ * blk_limits_io_min - set minimum request size for a device
+ * @limits: the queue limits
+ * @min:  smallest I/O size in bytes
+ *
+ * Description:
+ *   Some devices have an internal block size bigger than the reported
+ *   hardware sector size.  This function can be used to signal the
+ *   smallest I/O the device can perform without incurring a performance
+ *   penalty.
+ */
+void blk_limits_io_min(struct queue_limits *limits, unsigned int min)
+{
+	limits->io_min = min;
+
+	if (limits->io_min < limits->logical_block_size)
+		limits->io_min = limits->logical_block_size;
+
+	if (limits->io_min < limits->physical_block_size)
+		limits->io_min = limits->physical_block_size;
+}
+EXPORT_SYMBOL(blk_limits_io_min);
+
 /**
  * blk_queue_io_min - set minimum request size for the queue
  * @q:	the request queue for the device
@@ -396,13 +419,7 @@ EXPORT_SYMBOL(blk_queue_alignment_offset);
  */
 void blk_queue_io_min(struct request_queue *q, unsigned int min)
 {
-	q->limits.io_min = min;
-
-	if (q->limits.io_min < q->limits.logical_block_size)
-		q->limits.io_min = q->limits.logical_block_size;
-
-	if (q->limits.io_min < q->limits.physical_block_size)
-		q->limits.io_min = q->limits.physical_block_size;
+	blk_limits_io_min(&q->limits, min);
 }
 EXPORT_SYMBOL(blk_queue_io_min);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index e7cb5dbf6c26..69103e053c92 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -913,6 +913,7 @@ extern void blk_queue_logical_block_size(struct request_queue *, unsigned short)
 extern void blk_queue_physical_block_size(struct request_queue *, unsigned short);
 extern void blk_queue_alignment_offset(struct request_queue *q,
 				       unsigned int alignment);
+extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
 extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
 extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
 extern void blk_set_default_limits(struct queue_limits *lim);
-- 
cgit v1.3-8-gc7d7


From a82afdfcb8c0df09776b6458af6b68fc58b2e87b Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 3 Jul 2009 17:48:16 +0900
Subject: block: use the same failfast bits for bio and request

bio and request use the same set of failfast bits.  This patch makes
the following changes to simplify things.

* enumify BIO_RW* bits and reorder bits such that BIOS_RW_FAILFAST_*
  bits coincide with __REQ_FAILFAST_* bits.

* The above pushes BIO_RW_AHEAD out of sync with __REQ_FAILFAST_DEV
  but the matching is useless anyway.  init_request_from_bio() is
  responsible for setting FAILFAST bits on FS requests and non-FS
  requests never use BIO_RW_AHEAD.  Drop the code and comment from
  blk_rq_bio_prep().

* Define REQ_FAILFAST_MASK which is OR of all FAILFAST bits and
  simplify FAILFAST flags handling in init_request_from_bio().

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-core.c       | 19 +++++++------------
 include/linux/bio.h    | 43 +++++++++++++++++++++++--------------------
 include/linux/blkdev.h |  4 ++++
 3 files changed, 34 insertions(+), 32 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-core.c b/block/blk-core.c
index e3299a77a0d8..4daae1ee2b23 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1111,17 +1111,13 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	req->cmd_type = REQ_TYPE_FS;
 
 	/*
-	 * inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST)
+	 * Inherit FAILFAST from bio (for read-ahead, and explicit
+	 * FAILFAST).  FAILFAST flags are identical for req and bio.
 	 */
 	if (bio_rw_ahead(bio))
-		req->cmd_flags |= (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
-				   REQ_FAILFAST_DRIVER);
-	if (bio_failfast_dev(bio))
-		req->cmd_flags |= REQ_FAILFAST_DEV;
-	if (bio_failfast_transport(bio))
-		req->cmd_flags |= REQ_FAILFAST_TRANSPORT;
-	if (bio_failfast_driver(bio))
-		req->cmd_flags |= REQ_FAILFAST_DRIVER;
+		req->cmd_flags |= REQ_FAILFAST_MASK;
+	else
+		req->cmd_flags |= bio->bi_rw & REQ_FAILFAST_MASK;
 
 	if (unlikely(bio_discard(bio))) {
 		req->cmd_flags |= REQ_DISCARD;
@@ -2239,9 +2235,8 @@ EXPORT_SYMBOL(__blk_end_request_cur);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		     struct bio *bio)
 {
-	/* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw, and
-	   we want BIO_RW_AHEAD (bit 1) to imply REQ_FAILFAST (bit 1). */
-	rq->cmd_flags |= (bio->bi_rw & 3);
+	/* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */
+	rq->cmd_flags |= bio->bi_rw & REQ_RW;
 
 	if (bio_has_data(bio)) {
 		rq->nr_phys_segments = bio_phys_segments(q, bio);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 2892b710771c..a299ed38fcd7 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -142,37 +142,40 @@ struct bio {
  *
  * bit 0 -- data direction
  *	If not set, bio is a read from device. If set, it's a write to device.
- * bit 1 -- rw-ahead when set
- * bit 2 -- barrier
+ * bit 1 -- fail fast device errors
+ * bit 2 -- fail fast transport errors
+ * bit 3 -- fail fast driver errors
+ * bit 4 -- rw-ahead when set
+ * bit 5 -- barrier
  *	Insert a serialization point in the IO queue, forcing previously
  *	submitted IO to be completed before this one is issued.
- * bit 3 -- synchronous I/O hint.
- * bit 4 -- Unplug the device immediately after submitting this bio.
- * bit 5 -- metadata request
+ * bit 6 -- synchronous I/O hint.
+ * bit 7 -- Unplug the device immediately after submitting this bio.
+ * bit 8 -- metadata request
  *	Used for tracing to differentiate metadata and data IO. May also
  *	get some preferential treatment in the IO scheduler
- * bit 6 -- discard sectors
+ * bit 9 -- discard sectors
  *	Informs the lower level device that this range of sectors is no longer
  *	used by the file system and may thus be freed by the device. Used
  *	for flash based storage.
- * bit 7 -- fail fast device errors
- * bit 8 -- fail fast transport errors
- * bit 9 -- fail fast driver errors
  *	Don't want driver retries for any fast fail whatever the reason.
  * bit 10 -- Tell the IO scheduler not to wait for more requests after this
 	one has been submitted, even if it is a SYNC request.
  */
-#define BIO_RW		0	/* Must match RW in req flags (blkdev.h) */
-#define BIO_RW_AHEAD	1	/* Must match FAILFAST in req flags */
-#define BIO_RW_BARRIER	2
-#define BIO_RW_SYNCIO	3
-#define BIO_RW_UNPLUG	4
-#define BIO_RW_META	5
-#define BIO_RW_DISCARD	6
-#define BIO_RW_FAILFAST_DEV		7
-#define BIO_RW_FAILFAST_TRANSPORT	8
-#define BIO_RW_FAILFAST_DRIVER		9
-#define BIO_RW_NOIDLE	10
+enum bio_rw_flags {
+	BIO_RW,
+	BIO_RW_FAILFAST_DEV,
+	BIO_RW_FAILFAST_TRANSPORT,
+	BIO_RW_FAILFAST_DRIVER,
+	/* above flags must match REQ_* */
+	BIO_RW_AHEAD,
+	BIO_RW_BARRIER,
+	BIO_RW_SYNCIO,
+	BIO_RW_UNPLUG,
+	BIO_RW_META,
+	BIO_RW_DISCARD,
+	BIO_RW_NOIDLE,
+};
 
 #define bio_rw_flagged(bio, flag)	((bio)->bi_rw & (1 << (flag)))
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 69103e053c92..c3015736d814 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -93,6 +93,7 @@ enum rq_flag_bits {
 	__REQ_FAILFAST_DEV,	/* no driver retries of device errors */
 	__REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
 	__REQ_FAILFAST_DRIVER,	/* no driver retries of driver errors */
+	/* above flags must match BIO_RW_* */
 	__REQ_DISCARD,		/* request to discard sectors */
 	__REQ_SORTED,		/* elevator knows about this request */
 	__REQ_SOFTBARRIER,	/* may not be passed by ioscheduler */
@@ -143,6 +144,9 @@ enum rq_flag_bits {
 #define REQ_NOIDLE	(1 << __REQ_NOIDLE)
 #define REQ_IO_STAT	(1 << __REQ_IO_STAT)
 
+#define REQ_FAILFAST_MASK	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | \
+				 REQ_FAILFAST_DRIVER)
+
 #define BLK_MAX_CDB	16
 
 /*
-- 
cgit v1.3-8-gc7d7


From 80a761fd33cf812f771e212139157bf8f58d4b3f Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 3 Jul 2009 17:48:17 +0900
Subject: block: implement mixed merge of different failfast requests

Failfast has characteristics from other attributes.  When issuing,
executing and successuflly completing requests, failfast doesn't make
any difference.  It only affects how a request is handled on failure.
Allowing requests with different failfast settings to be merged cause
normal IOs to fail prematurely while not allowing has performance
penalties as failfast is used for read aheads which are likely to be
located near in-flight or to-be-issued normal IOs.

This patch introduces the concept of 'mixed merge'.  A request is a
mixed merge if it is merge of segments which require different
handling on failure.  Currently the only mixable attributes are
failfast ones (or lack thereof).

When a bio with different failfast settings is added to an existing
request or requests of different failfast settings are merged, the
merged request is marked mixed.  Each bio carries failfast settings
and the request always tracks failfast state of the first bio.  When
the request fails, blk_rq_err_bytes() can be used to determine how
many bytes can be safely failed without crossing into an area which
requires further retrials.

This allows request merging regardless of failfast settings while
keeping the failure handling correct.

This patch only implements mixed merge but doesn't enable it.  The
next one will update SCSI to make use of mixed merge.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Niel Lambrechts <niel.lambrechts@gmail.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-core.c       | 99 ++++++++++++++++++++++++++++++++++++++++++++++++++
 block/blk-merge.c      | 43 ++++++++++++++++++++++
 block/blk.h            |  1 +
 include/linux/blkdev.h | 23 +++++++++---
 4 files changed, 161 insertions(+), 5 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-core.c b/block/blk-core.c
index 4daae1ee2b23..c822239bcc9d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1157,6 +1157,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	const unsigned short prio = bio_prio(bio);
 	const int sync = bio_sync(bio);
 	const int unplug = bio_unplug(bio);
+	const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK;
 	int rw_flags;
 
 	if (bio_barrier(bio) && bio_has_data(bio) &&
@@ -1186,6 +1187,9 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 		trace_block_bio_backmerge(q, bio);
 
+		if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
+			blk_rq_set_mixed_merge(req);
+
 		req->biotail->bi_next = bio;
 		req->biotail = bio;
 		req->__data_len += bytes;
@@ -1205,6 +1209,12 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 		trace_block_bio_frontmerge(q, bio);
 
+		if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) {
+			blk_rq_set_mixed_merge(req);
+			req->cmd_flags &= ~REQ_FAILFAST_MASK;
+			req->cmd_flags |= ff;
+		}
+
 		bio->bi_next = req->bio;
 		req->bio = bio;
 
@@ -1649,6 +1659,50 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 }
 EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
 
+/**
+ * blk_rq_err_bytes - determine number of bytes till the next failure boundary
+ * @rq: request to examine
+ *
+ * Description:
+ *     A request could be merge of IOs which require different failure
+ *     handling.  This function determines the number of bytes which
+ *     can be failed from the beginning of the request without
+ *     crossing into area which need to be retried further.
+ *
+ * Return:
+ *     The number of bytes to fail.
+ *
+ * Context:
+ *     queue_lock must be held.
+ */
+unsigned int blk_rq_err_bytes(const struct request *rq)
+{
+	unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
+	unsigned int bytes = 0;
+	struct bio *bio;
+
+	if (!(rq->cmd_flags & REQ_MIXED_MERGE))
+		return blk_rq_bytes(rq);
+
+	/*
+	 * Currently the only 'mixing' which can happen is between
+	 * different fastfail types.  We can safely fail portions
+	 * which have all the failfast bits that the first one has -
+	 * the ones which are at least as eager to fail as the first
+	 * one.
+	 */
+	for (bio = rq->bio; bio; bio = bio->bi_next) {
+		if ((bio->bi_rw & ff) != ff)
+			break;
+		bytes += bio->bi_size;
+	}
+
+	/* this could lead to infinite loop */
+	BUG_ON(blk_rq_bytes(rq) && !bytes);
+	return bytes;
+}
+EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
+
 static void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
 	if (blk_do_io_stat(req)) {
@@ -1995,6 +2049,12 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	if (blk_fs_request(req) || blk_discard_rq(req))
 		req->__sector += total_bytes >> 9;
 
+	/* mixed attributes always follow the first bio */
+	if (req->cmd_flags & REQ_MIXED_MERGE) {
+		req->cmd_flags &= ~REQ_FAILFAST_MASK;
+		req->cmd_flags |= req->bio->bi_rw & REQ_FAILFAST_MASK;
+	}
+
 	/*
 	 * If total number of sectors is less than the first segment
 	 * size, something has gone terribly wrong.
@@ -2173,6 +2233,25 @@ bool blk_end_request_cur(struct request *rq, int error)
 }
 EXPORT_SYMBOL(blk_end_request_cur);
 
+/**
+ * blk_end_request_err - Finish a request till the next failure boundary.
+ * @rq: the request to finish till the next failure boundary for
+ * @error: must be negative errno
+ *
+ * Description:
+ *     Complete @rq till the next failure boundary.
+ *
+ * Return:
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
+ */
+bool blk_end_request_err(struct request *rq, int error)
+{
+	WARN_ON(error >= 0);
+	return blk_end_request(rq, error, blk_rq_err_bytes(rq));
+}
+EXPORT_SYMBOL_GPL(blk_end_request_err);
+
 /**
  * __blk_end_request - Helper function for drivers to complete the request.
  * @rq:       the request being processed
@@ -2232,6 +2311,26 @@ bool __blk_end_request_cur(struct request *rq, int error)
 }
 EXPORT_SYMBOL(__blk_end_request_cur);
 
+/**
+ * __blk_end_request_err - Finish a request till the next failure boundary.
+ * @rq: the request to finish till the next failure boundary for
+ * @error: must be negative errno
+ *
+ * Description:
+ *     Complete @rq till the next failure boundary.  Must be called
+ *     with queue lock held.
+ *
+ * Return:
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
+ */
+bool __blk_end_request_err(struct request *rq, int error)
+{
+	WARN_ON(error >= 0);
+	return __blk_end_request(rq, error, blk_rq_err_bytes(rq));
+}
+EXPORT_SYMBOL_GPL(__blk_end_request_err);
+
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		     struct bio *bio)
 {
diff --git a/block/blk-merge.c b/block/blk-merge.c
index e1999679a4d5..7c9ca01baa45 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -311,6 +311,36 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	return 1;
 }
 
+/**
+ * blk_rq_set_mixed_merge - mark a request as mixed merge
+ * @rq: request to mark as mixed merge
+ *
+ * Description:
+ *     @rq is about to be mixed merged.  Make sure the attributes
+ *     which can be mixed are set in each bio and mark @rq as mixed
+ *     merged.
+ */
+void blk_rq_set_mixed_merge(struct request *rq)
+{
+	unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
+	struct bio *bio;
+
+	if (rq->cmd_flags & REQ_MIXED_MERGE)
+		return;
+
+	/*
+	 * @rq will no longer represent mixable attributes for all the
+	 * contained bios.  It will just track those of the first one.
+	 * Distributes the attributs to each bio.
+	 */
+	for (bio = rq->bio; bio; bio = bio->bi_next) {
+		WARN_ON_ONCE((bio->bi_rw & REQ_FAILFAST_MASK) &&
+			     (bio->bi_rw & REQ_FAILFAST_MASK) != ff);
+		bio->bi_rw |= ff;
+	}
+	rq->cmd_flags |= REQ_MIXED_MERGE;
+}
+
 static void blk_account_io_merge(struct request *req)
 {
 	if (blk_do_io_stat(req)) {
@@ -365,6 +395,19 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	if (!ll_merge_requests_fn(q, req, next))
 		return 0;
 
+	/*
+	 * If failfast settings disagree or any of the two is already
+	 * a mixed merge, mark both as mixed before proceeding.  This
+	 * makes sure that all involved bios have mixable attributes
+	 * set properly.
+	 */
+	if ((req->cmd_flags | next->cmd_flags) & REQ_MIXED_MERGE ||
+	    (req->cmd_flags & REQ_FAILFAST_MASK) !=
+	    (next->cmd_flags & REQ_FAILFAST_MASK)) {
+		blk_rq_set_mixed_merge(req);
+		blk_rq_set_mixed_merge(next);
+	}
+
 	/*
 	 * At this point we have either done a back merge
 	 * or front merge. We need the smaller start_time of
diff --git a/block/blk.h b/block/blk.h
index 3fae6add5430..5ee3d7e72feb 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -104,6 +104,7 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 int attempt_back_merge(struct request_queue *q, struct request *rq);
 int attempt_front_merge(struct request_queue *q, struct request *rq);
 void blk_recalc_rq_segments(struct request *rq);
+void blk_rq_set_mixed_merge(struct request *rq);
 
 void blk_queue_congestion_threshold(struct request_queue *q);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c3015736d814..650b6a9cb679 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -115,6 +115,7 @@ enum rq_flag_bits {
 	__REQ_INTEGRITY,	/* integrity metadata has been remapped */
 	__REQ_NOIDLE,		/* Don't anticipate more IO after this one */
 	__REQ_IO_STAT,		/* account I/O stat */
+	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -143,6 +144,7 @@ enum rq_flag_bits {
 #define REQ_INTEGRITY	(1 << __REQ_INTEGRITY)
 #define REQ_NOIDLE	(1 << __REQ_NOIDLE)
 #define REQ_IO_STAT	(1 << __REQ_IO_STAT)
+#define REQ_MIXED_MERGE	(1 << __REQ_MIXED_MERGE)
 
 #define REQ_FAILFAST_MASK	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | \
 				 REQ_FAILFAST_DRIVER)
@@ -832,11 +834,13 @@ static inline void blk_run_address_space(struct address_space *mapping)
 }
 
 /*
- * blk_rq_pos()		: the current sector
- * blk_rq_bytes()	: bytes left in the entire request
- * blk_rq_cur_bytes()	: bytes left in the current segment
- * blk_rq_sectors()	: sectors left in the entire request
- * blk_rq_cur_sectors()	: sectors left in the current segment
+ * blk_rq_pos()			: the current sector
+ * blk_rq_bytes()		: bytes left in the entire request
+ * blk_rq_cur_bytes()		: bytes left in the current segment
+ * blk_rq_err_bytes()		: bytes left till the next error boundary
+ * blk_rq_sectors()		: sectors left in the entire request
+ * blk_rq_cur_sectors()		: sectors left in the current segment
+ * blk_rq_err_sectors()		: sectors left till the next error boundary
  */
 static inline sector_t blk_rq_pos(const struct request *rq)
 {
@@ -853,6 +857,8 @@ static inline int blk_rq_cur_bytes(const struct request *rq)
 	return rq->bio ? bio_cur_bytes(rq->bio) : 0;
 }
 
+extern unsigned int blk_rq_err_bytes(const struct request *rq);
+
 static inline unsigned int blk_rq_sectors(const struct request *rq)
 {
 	return blk_rq_bytes(rq) >> 9;
@@ -863,6 +869,11 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 	return blk_rq_cur_bytes(rq) >> 9;
 }
 
+static inline unsigned int blk_rq_err_sectors(const struct request *rq)
+{
+	return blk_rq_err_bytes(rq) >> 9;
+}
+
 /*
  * Request issue related functions.
  */
@@ -889,10 +900,12 @@ extern bool blk_end_request(struct request *rq, int error,
 			    unsigned int nr_bytes);
 extern void blk_end_request_all(struct request *rq, int error);
 extern bool blk_end_request_cur(struct request *rq, int error);
+extern bool blk_end_request_err(struct request *rq, int error);
 extern bool __blk_end_request(struct request *rq, int error,
 			      unsigned int nr_bytes);
 extern void __blk_end_request_all(struct request *rq, int error);
 extern bool __blk_end_request_cur(struct request *rq, int error);
+extern bool __blk_end_request_err(struct request *rq, int error);
 
 extern void blk_complete_request(struct request *);
 extern void __blk_complete_request(struct request *);
-- 
cgit v1.3-8-gc7d7


From 1f98a13f623e0ef666690a18c1250335fc6d7ef1 Mon Sep 17 00:00:00 2001
From: Jens Axboe <jens.axboe@oracle.com>
Date: Fri, 11 Sep 2009 14:32:04 +0200
Subject: bio: first step in sanitizing the bio->bi_rw flag testing

Get rid of any functions that test for these bits and make callers
use bio_rw_flagged() directly. Then it is at least directly apparent
what variable and flag they check.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-core.c            | 25 +++++++++++++------------
 block/cfq-iosched.c         |  2 +-
 block/elevator.c            |  3 ++-
 drivers/block/loop.c        |  2 +-
 drivers/md/dm-raid1.c       |  2 +-
 drivers/md/dm-stripe.c      |  2 +-
 drivers/md/dm.c             | 12 ++++++------
 drivers/md/linear.c         |  2 +-
 drivers/md/multipath.c      |  4 ++--
 drivers/md/raid0.c          |  2 +-
 drivers/md/raid1.c          | 14 ++++++++------
 drivers/md/raid10.c         |  6 +++---
 drivers/md/raid5.c          |  2 +-
 drivers/staging/dst/dcore.c |  5 +++--
 fs/btrfs/volumes.c          |  4 ++--
 include/linux/bio.h         | 25 +++++++------------------
 include/linux/blkdev.h      |  2 +-
 17 files changed, 54 insertions(+), 60 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-core.c b/block/blk-core.c
index c822239bcc9d..52559715cb90 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1114,24 +1114,24 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	 * Inherit FAILFAST from bio (for read-ahead, and explicit
 	 * FAILFAST).  FAILFAST flags are identical for req and bio.
 	 */
-	if (bio_rw_ahead(bio))
+	if (bio_rw_flagged(bio, BIO_RW_AHEAD))
 		req->cmd_flags |= REQ_FAILFAST_MASK;
 	else
 		req->cmd_flags |= bio->bi_rw & REQ_FAILFAST_MASK;
 
-	if (unlikely(bio_discard(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_DISCARD))) {
 		req->cmd_flags |= REQ_DISCARD;
-		if (bio_barrier(bio))
+		if (bio_rw_flagged(bio, BIO_RW_BARRIER))
 			req->cmd_flags |= REQ_SOFTBARRIER;
 		req->q->prepare_discard_fn(req->q, req);
-	} else if (unlikely(bio_barrier(bio)))
+	} else if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)))
 		req->cmd_flags |= REQ_HARDBARRIER;
 
-	if (bio_sync(bio))
+	if (bio_rw_flagged(bio, BIO_RW_SYNCIO))
 		req->cmd_flags |= REQ_RW_SYNC;
-	if (bio_rw_meta(bio))
+	if (bio_rw_flagged(bio, BIO_RW_META))
 		req->cmd_flags |= REQ_RW_META;
-	if (bio_noidle(bio))
+	if (bio_rw_flagged(bio, BIO_RW_NOIDLE))
 		req->cmd_flags |= REQ_NOIDLE;
 
 	req->errors = 0;
@@ -1155,12 +1155,12 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	int el_ret;
 	unsigned int bytes = bio->bi_size;
 	const unsigned short prio = bio_prio(bio);
-	const int sync = bio_sync(bio);
-	const int unplug = bio_unplug(bio);
+	const bool sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
+	const bool unplug = bio_rw_flagged(bio, BIO_RW_UNPLUG);
 	const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK;
 	int rw_flags;
 
-	if (bio_barrier(bio) && bio_has_data(bio) &&
+	if (bio_rw_flagged(bio, BIO_RW_BARRIER) && bio_has_data(bio) &&
 	    (q->next_ordered == QUEUE_ORDERED_NONE)) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
@@ -1174,7 +1174,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 	spin_lock_irq(q->queue_lock);
 
-	if (unlikely(bio_barrier(bio)) || elv_queue_empty(q))
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)) || elv_queue_empty(q))
 		goto get_rq;
 
 	el_ret = elv_merge(q, &req, bio);
@@ -1470,7 +1470,8 @@ static inline void __generic_make_request(struct bio *bio)
 		if (bio_check_eod(bio, nr_sectors))
 			goto end_io;
 
-		if (bio_discard(bio) && !q->prepare_discard_fn) {
+		if (bio_rw_flagged(bio, BIO_RW_DISCARD) &&
+		    !q->prepare_discard_fn) {
 			err = -EOPNOTSUPP;
 			goto end_io;
 		}
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index ca0d7e71324b..9e6d0af6c990 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -257,7 +257,7 @@ static inline void cic_set_cfqq(struct cfq_io_context *cic,
  */
 static inline int cfq_bio_sync(struct bio *bio)
 {
-	if (bio_data_dir(bio) == READ || bio_sync(bio))
+	if (bio_data_dir(bio) == READ || bio_rw_flagged(bio, BIO_RW_SYNCIO))
 		return 1;
 
 	return 0;
diff --git a/block/elevator.c b/block/elevator.c
index ca861927ba41..1975b619c86d 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -79,7 +79,8 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio)
 	/*
 	 * Don't merge file system requests and discard requests
 	 */
-	if (bio_discard(bio) != bio_discard(rq->bio))
+	if (bio_rw_flagged(bio, BIO_RW_DISCARD) !=
+	    bio_rw_flagged(rq->bio, BIO_RW_DISCARD))
 		return 0;
 
 	/*
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 5757188cd1fb..bbb79441d895 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -475,7 +475,7 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
 	pos = ((loff_t) bio->bi_sector << 9) + lo->lo_offset;
 
 	if (bio_rw(bio) == WRITE) {
-		int barrier = bio_barrier(bio);
+		bool barrier = bio_rw_flagged(bio, BIO_RW_BARRIER);
 		struct file *file = lo->lo_backing_file;
 
 		if (barrier) {
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 33f179e66bf5..cc9dc79b0784 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1129,7 +1129,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio,
 	if (error == -EOPNOTSUPP)
 		goto out;
 
-	if ((error == -EWOULDBLOCK) && bio_rw_ahead(bio))
+	if ((error == -EWOULDBLOCK) && bio_rw_flagged(bio, BIO_RW_AHEAD))
 		goto out;
 
 	if (unlikely(error)) {
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 3e563d251733..fde658ccbcec 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -285,7 +285,7 @@ static int stripe_end_io(struct dm_target *ti, struct bio *bio,
 	if (!error)
 		return 0; /* I/O complete */
 
-	if ((error == -EWOULDBLOCK) && bio_rw_ahead(bio))
+	if ((error == -EWOULDBLOCK) && bio_rw_flagged(bio, BIO_RW_AHEAD))
 		return error;
 
 	if (error == -EOPNOTSUPP)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index b4845b14740d..ec012f030240 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -586,7 +586,7 @@ static void dec_pending(struct dm_io *io, int error)
 			 */
 			spin_lock_irqsave(&md->deferred_lock, flags);
 			if (__noflush_suspending(md)) {
-				if (!bio_barrier(io->bio))
+				if (!bio_rw_flagged(io->bio, BIO_RW_BARRIER))
 					bio_list_add_head(&md->deferred,
 							  io->bio);
 			} else
@@ -598,7 +598,7 @@ static void dec_pending(struct dm_io *io, int error)
 		io_error = io->error;
 		bio = io->bio;
 
-		if (bio_barrier(bio)) {
+		if (bio_rw_flagged(bio, BIO_RW_BARRIER)) {
 			/*
 			 * There can be just one barrier request so we use
 			 * a per-device variable for error reporting.
@@ -1209,7 +1209,7 @@ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio)
 
 	ci.map = dm_get_table(md);
 	if (unlikely(!ci.map)) {
-		if (!bio_barrier(bio))
+		if (!bio_rw_flagged(bio, BIO_RW_BARRIER))
 			bio_io_error(bio);
 		else
 			if (!md->barrier_error)
@@ -1321,7 +1321,7 @@ static int _dm_request(struct request_queue *q, struct bio *bio)
 	 * we have to queue this io for later.
 	 */
 	if (unlikely(test_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags)) ||
-	    unlikely(bio_barrier(bio))) {
+	    unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		up_read(&md->io_lock);
 
 		if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) &&
@@ -1344,7 +1344,7 @@ static int dm_make_request(struct request_queue *q, struct bio *bio)
 {
 	struct mapped_device *md = q->queuedata;
 
-	if (unlikely(bio_barrier(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
@@ -2164,7 +2164,7 @@ static void dm_wq_work(struct work_struct *work)
 		if (dm_request_based(md))
 			generic_make_request(c);
 		else {
-			if (bio_barrier(c))
+			if (bio_rw_flagged(c, BIO_RW_BARRIER))
 				process_barrier(md, c);
 			else
 				__split_and_process_bio(md, c);
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 5fe39c2a3d2b..ea4842905444 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -288,7 +288,7 @@ static int linear_make_request (struct request_queue *q, struct bio *bio)
 	sector_t start_sector;
 	int cpu;
 
-	if (unlikely(bio_barrier(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 7140909f6662..89e76819f61f 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -90,7 +90,7 @@ static void multipath_end_request(struct bio *bio, int error)
 
 	if (uptodate)
 		multipath_end_bh_io(mp_bh, 0);
-	else if (!bio_rw_ahead(bio)) {
+	else if (!bio_rw_flagged(bio, BIO_RW_AHEAD)) {
 		/*
 		 * oops, IO error:
 		 */
@@ -144,7 +144,7 @@ static int multipath_make_request (struct request_queue *q, struct bio * bio)
 	const int rw = bio_data_dir(bio);
 	int cpu;
 
-	if (unlikely(bio_barrier(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 898e2bdfee47..f845ed98fec9 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -448,7 +448,7 @@ static int raid0_make_request(struct request_queue *q, struct bio *bio)
 	const int rw = bio_data_dir(bio);
 	int cpu;
 
-	if (unlikely(bio_barrier(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 8726fd7ebce5..ff7ed3335995 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -782,8 +782,9 @@ static int make_request(struct request_queue *q, struct bio * bio)
 	struct bio_list bl;
 	struct page **behind_pages = NULL;
 	const int rw = bio_data_dir(bio);
-	const int do_sync = bio_sync(bio);
-	int cpu, do_barriers;
+	const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
+	int cpu;
+	bool do_barriers;
 	mdk_rdev_t *blocked_rdev;
 
 	/*
@@ -797,7 +798,8 @@ static int make_request(struct request_queue *q, struct bio * bio)
 
 	md_write_start(mddev, bio); /* wait on superblock update early */
 
-	if (unlikely(!mddev->barriers_work && bio_barrier(bio))) {
+	if (unlikely(!mddev->barriers_work &&
+		     bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		if (rw == WRITE)
 			md_write_end(mddev);
 		bio_endio(bio, -EOPNOTSUPP);
@@ -925,7 +927,7 @@ static int make_request(struct request_queue *q, struct bio * bio)
 	atomic_set(&r1_bio->remaining, 0);
 	atomic_set(&r1_bio->behind_remaining, 0);
 
-	do_barriers = bio_barrier(bio);
+	do_barriers = bio_rw_flagged(bio, BIO_RW_BARRIER);
 	if (do_barriers)
 		set_bit(R1BIO_Barrier, &r1_bio->state);
 
@@ -1600,7 +1602,7 @@ static void raid1d(mddev_t *mddev)
 			 * We already have a nr_pending reference on these rdevs.
 			 */
 			int i;
-			const int do_sync = bio_sync(r1_bio->master_bio);
+			const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO);
 			clear_bit(R1BIO_BarrierRetry, &r1_bio->state);
 			clear_bit(R1BIO_Barrier, &r1_bio->state);
 			for (i=0; i < conf->raid_disks; i++)
@@ -1654,7 +1656,7 @@ static void raid1d(mddev_t *mddev)
 				       (unsigned long long)r1_bio->sector);
 				raid_end_bio_io(r1_bio);
 			} else {
-				const int do_sync = bio_sync(r1_bio->master_bio);
+				const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO);
 				r1_bio->bios[r1_bio->read_disk] =
 					mddev->ro ? IO_BLOCKED : NULL;
 				r1_bio->read_disk = disk;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 3d9020cf6f6e..d0a2152e064f 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -796,12 +796,12 @@ static int make_request(struct request_queue *q, struct bio * bio)
 	int i;
 	int chunk_sects = conf->chunk_mask + 1;
 	const int rw = bio_data_dir(bio);
-	const int do_sync = bio_sync(bio);
+	const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
 	struct bio_list bl;
 	unsigned long flags;
 	mdk_rdev_t *blocked_rdev;
 
-	if (unlikely(bio_barrier(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
@@ -1610,7 +1610,7 @@ static void raid10d(mddev_t *mddev)
 				raid_end_bio_io(r10_bio);
 				bio_put(bio);
 			} else {
-				const int do_sync = bio_sync(r10_bio->master_bio);
+				const bool do_sync = bio_rw_flagged(r10_bio->master_bio, BIO_RW_SYNCIO);
 				bio_put(bio);
 				rdev = conf->mirrors[mirror].rdev;
 				if (printk_ratelimit())
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index b8a2c5dc67ba..826eb3467357 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3606,7 +3606,7 @@ static int make_request(struct request_queue *q, struct bio * bi)
 	const int rw = bio_data_dir(bi);
 	int cpu, remaining;
 
-	if (unlikely(bio_barrier(bi))) {
+	if (unlikely(bio_rw_flagged(bi, BIO_RW_BARRIER))) {
 		bio_endio(bi, -EOPNOTSUPP);
 		return 0;
 	}
diff --git a/drivers/staging/dst/dcore.c b/drivers/staging/dst/dcore.c
index fad25b753042..b1c258ca2102 100644
--- a/drivers/staging/dst/dcore.c
+++ b/drivers/staging/dst/dcore.c
@@ -112,8 +112,9 @@ static int dst_request(struct request_queue *q, struct bio *bio)
 		 * I worked with.
 		 *
 		 * Empty barriers are not allowed anyway, see 51fd77bd9f512
-		 * for example, although later it was changed to bio_discard()
-		 * only, which does not work in this case.
+		 * for example, although later it was changed to
+		 * bio_rw_flagged(bio, BIO_RW_DISCARD) only, which does not
+		 * work in this case.
 		 */
 		//err = -EOPNOTSUPP;
 		err = 0;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 5dbefd11b4af..5cf405b0828d 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -260,7 +260,7 @@ loop_lock:
 		num_run++;
 		batch_run++;
 
-		if (bio_sync(cur))
+		if (bio_rw_flagged(cur, BIO_RW_SYNCIO))
 			num_sync_run++;
 
 		if (need_resched()) {
@@ -2903,7 +2903,7 @@ static noinline int schedule_bio(struct btrfs_root *root,
 	bio->bi_rw |= rw;
 
 	spin_lock(&device->io_lock);
-	if (bio_sync(bio))
+	if (bio_rw_flagged(bio, BIO_RW_SYNCIO))
 		pending_bios = &device->pending_sync_bios;
 	else
 		pending_bios = &device->pending_bios;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 4f8fd0221cd2..5be93f18d842 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -177,28 +177,17 @@ enum bio_rw_flags {
 	BIO_RW_NOIDLE,
 };
 
+/*
+ * First four bits must match between bio->bi_rw and rq->cmd_flags, make
+ * that explicit here.
+ */
+#define BIO_RW_RQ_MASK		0xf
+
 static inline bool bio_rw_flagged(struct bio *bio, enum bio_rw_flags flag)
 {
 	return (bio->bi_rw & (1 << flag)) != 0;
 }
 
-/*
- * Old defines, these should eventually be replaced by direct usage of
- * bio_rw_flagged()
- */
-#define bio_barrier(bio)	bio_rw_flagged(bio, BIO_RW_BARRIER)
-#define bio_sync(bio)		bio_rw_flagged(bio, BIO_RW_SYNCIO)
-#define bio_unplug(bio)		bio_rw_flagged(bio, BIO_RW_UNPLUG)
-#define bio_failfast_dev(bio)	bio_rw_flagged(bio, BIO_RW_FAILFAST_DEV)
-#define bio_failfast_transport(bio)	\
-		bio_rw_flagged(bio, BIO_RW_FAILFAST_TRANSPORT)
-#define bio_failfast_driver(bio) 	\
-		bio_rw_flagged(bio, BIO_RW_FAILFAST_DRIVER)
-#define bio_rw_ahead(bio)	bio_rw_flagged(bio, BIO_RW_AHEAD)
-#define bio_rw_meta(bio)	bio_rw_flagged(bio, BIO_RW_META)
-#define bio_discard(bio)	bio_rw_flagged(bio, BIO_RW_DISCARD)
-#define bio_noidle(bio)		bio_rw_flagged(bio, BIO_RW_NOIDLE)
-
 /*
  * upper 16 bits of bi_rw define the io priority of this bio
  */
@@ -222,7 +211,7 @@ static inline bool bio_rw_flagged(struct bio *bio, enum bio_rw_flags flag)
 #define bio_offset(bio)		bio_iovec((bio))->bv_offset
 #define bio_segments(bio)	((bio)->bi_vcnt - (bio)->bi_idx)
 #define bio_sectors(bio)	((bio)->bi_size >> 9)
-#define bio_empty_barrier(bio)	(bio_barrier(bio) && !bio_has_data(bio) && !bio_discard(bio))
+#define bio_empty_barrier(bio)	(bio_rw_flagged(bio, BIO_RW_BARRIER) && !bio_has_data(bio) && !bio_rw_flagged(bio, BIO_RW_DISCARD))
 
 static inline unsigned int bio_cur_bytes(struct bio *bio)
 {
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 650b6a9cb679..88edb62def82 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -86,7 +86,7 @@ enum {
 };
 
 /*
- * request type modified bits. first two bits match BIO_RW* bits, important
+ * request type modified bits. first four bits match BIO_RW* bits, important
  */
 enum rq_flag_bits {
 	__REQ_RW,		/* not set, read. set, write */
-- 
cgit v1.3-8-gc7d7


From fb1e75389bd06fd5987e9cda1b4e0305c782f854 Mon Sep 17 00:00:00 2001
From: Jens Axboe <jens.axboe@oracle.com>
Date: Thu, 30 Jul 2009 08:18:24 +0200
Subject: block: improve queue_should_plug() by looking at IO depths

Instead of just checking whether this device uses block layer
tagging, we can improve the detection by looking at the maximum
queue depth it has reached. If that crosses 4, then deem it a
queuing device.

This is important on high IOPS devices, since plugging hurts
the performance there (it can be as much as 10-15% of the sys
time).

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-core.c       | 11 +++++++++--
 include/linux/blkdev.h |  2 ++
 2 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-core.c b/block/blk-core.c
index 52559715cb90..93051d151635 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1146,7 +1146,7 @@ void init_request_from_bio(struct request *req, struct bio *bio)
  */
 static inline bool queue_should_plug(struct request_queue *q)
 {
-	return !(blk_queue_nonrot(q) && blk_queue_tagged(q));
+	return !(blk_queue_nonrot(q) && blk_queue_queuing(q));
 }
 
 static int __make_request(struct request_queue *q, struct bio *bio)
@@ -1857,8 +1857,15 @@ void blk_dequeue_request(struct request *rq)
 	 * and to it is freed is accounted as io that is in progress at
 	 * the driver side.
 	 */
-	if (blk_account_rq(rq))
+	if (blk_account_rq(rq)) {
 		q->in_flight[rq_is_sync(rq)]++;
+		/*
+		 * Mark this device as supporting hardware queuing, if
+		 * we have more IOs in flight than 4.
+		 */
+		if (!blk_queue_queuing(q) && queue_in_flight(q) > 4)
+			set_bit(QUEUE_FLAG_CQ, &q->queue_flags);
+	}
 }
 
 /**
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 88edb62def82..98b45633a27e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -459,6 +459,7 @@ struct request_queue
 #define QUEUE_FLAG_NONROT      14	/* non-rotational device (SSD) */
 #define QUEUE_FLAG_VIRT        QUEUE_FLAG_NONROT /* paravirt device */
 #define QUEUE_FLAG_IO_STAT     15	/* do IO stats */
+#define QUEUE_FLAG_CQ	       16	/* hardware does queuing */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_CLUSTER) |		\
@@ -581,6 +582,7 @@ enum {
 
 #define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
+#define blk_queue_queuing(q)	test_bit(QUEUE_FLAG_CQ, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
-- 
cgit v1.3-8-gc7d7


From 01e97f6b897bf06ec83375d691f2f4d57f5b3a09 Mon Sep 17 00:00:00 2001
From: Jens Axboe <jens.axboe@oracle.com>
Date: Thu, 3 Sep 2009 20:06:47 +0200
Subject: block: enable rq CPU completion affinity by default

Test results here look good, and on big OLTP runs it has also shown
to significantly increase cycles attributed to the database and
cause a performance boost.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 include/linux/blkdev.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux/blkdev.h')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 98b45633a27e..8bf1a10e4d88 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -463,7 +463,8 @@ struct request_queue
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_CLUSTER) |		\
-				 (1 << QUEUE_FLAG_STACKABLE))
+				 (1 << QUEUE_FLAG_STACKABLE)	|	\
+				 (1 << QUEUE_FLAG_SAME_COMP))
 
 static inline int queue_is_locked(struct request_queue *q)
 {
-- 
cgit v1.3-8-gc7d7


From 3c5820c743479285ce2678fd3c12b1fd39fe998f Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 11 Sep 2009 21:54:52 +0200
Subject: block: Optimal I/O limit wrapper

Implement blk_limits_io_opt() and make blk_queue_io_opt() a wrapper
around it. DM needs this to avoid poking at the queue_limits directly.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-settings.c   | 21 ++++++++++++++++++++-
 drivers/md/dm-stripe.c |  2 +-
 include/linux/blkdev.h |  1 +
 3 files changed, 22 insertions(+), 2 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 476d87065073..83413ff83739 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -427,6 +427,25 @@ void blk_queue_io_min(struct request_queue *q, unsigned int min)
 }
 EXPORT_SYMBOL(blk_queue_io_min);
 
+/**
+ * blk_limits_io_opt - set optimal request size for a device
+ * @limits: the queue limits
+ * @opt:  smallest I/O size in bytes
+ *
+ * Description:
+ *   Storage devices may report an optimal I/O size, which is the
+ *   device's preferred unit for sustained I/O.  This is rarely reported
+ *   for disk drives.  For RAID arrays it is usually the stripe width or
+ *   the internal track size.  A properly aligned multiple of
+ *   optimal_io_size is the preferred request size for workloads where
+ *   sustained throughput is desired.
+ */
+void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt)
+{
+	limits->io_opt = opt;
+}
+EXPORT_SYMBOL(blk_limits_io_opt);
+
 /**
  * blk_queue_io_opt - set optimal request size for the queue
  * @q:	the request queue for the device
@@ -442,7 +461,7 @@ EXPORT_SYMBOL(blk_queue_io_min);
  */
 void blk_queue_io_opt(struct request_queue *q, unsigned int opt)
 {
-	q->limits.io_opt = opt;
+	blk_limits_io_opt(&q->limits, opt);
 }
 EXPORT_SYMBOL(blk_queue_io_opt);
 
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index fde658ccbcec..e0efc1adcaff 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -336,7 +336,7 @@ static void stripe_io_hints(struct dm_target *ti,
 	unsigned chunk_size = (sc->chunk_mask + 1) << 9;
 
 	blk_limits_io_min(limits, chunk_size);
-	limits->io_opt = chunk_size * sc->stripes;
+	blk_limits_io_opt(limits, chunk_size * sc->stripes);
 }
 
 static struct target_type stripe_target = {
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8bf1a10e4d88..86c2bdff3b89 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -935,6 +935,7 @@ extern void blk_queue_alignment_offset(struct request_queue *q,
 				       unsigned int alignment);
 extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
 extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
+extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);
 extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
 extern void blk_set_default_limits(struct queue_limits *lim);
 extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
-- 
cgit v1.3-8-gc7d7


From 746cd1e7e4a555ddaee53b19a46e05c9c61eaf09 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Sat, 12 Sep 2009 07:35:43 +0200
Subject: block: use blkdev_issue_discard in blk_ioctl_discard

blk_ioctl_discard duplicates large amounts of code from blkdev_issue_discard,
the only difference between the two is that blkdev_issue_discard needs to
send a barrier discard request and blk_ioctl_discard a non-barrier one,
and blk_ioctl_discard needs to wait on the request.  To facilitates this
add a flags argument to blkdev_issue_discard to control both aspects of the
behaviour.  This will be very useful later on for using the waiting
funcitonality for other callers.

Based on an earlier patch from Matthew Wilcox <matthew@wil.cx>.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-barrier.c    | 31 +++++++++++++++++++------------
 block/ioctl.c          | 49 ++-----------------------------------------------
 fs/btrfs/extent-tree.c |  3 ++-
 fs/gfs2/rgrp.c         |  6 ++++--
 include/linux/blkdev.h |  9 ++++++---
 mm/swapfile.c          |  6 ++++--
 6 files changed, 37 insertions(+), 67 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index 30022b4e2f63..6593ab39cfe9 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -348,6 +348,9 @@ static void blkdev_discard_end_io(struct bio *bio, int err)
 		clear_bit(BIO_UPTODATE, &bio->bi_flags);
 	}
 
+	if (bio->bi_private)
+		complete(bio->bi_private);
+
 	bio_put(bio);
 }
 
@@ -357,21 +360,20 @@ static void blkdev_discard_end_io(struct bio *bio, int err)
  * @sector:	start sector
  * @nr_sects:	number of sectors to discard
  * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @flags:	DISCARD_FL_* flags to control behaviour
  *
  * Description:
- *    Issue a discard request for the sectors in question. Does not wait.
+ *    Issue a discard request for the sectors in question.
  */
-int blkdev_issue_discard(struct block_device *bdev,
-			 sector_t sector, sector_t nr_sects, gfp_t gfp_mask)
+int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, int flags)
 {
-	struct request_queue *q;
-	struct bio *bio;
+	DECLARE_COMPLETION_ONSTACK(wait);
+	struct request_queue *q = bdev_get_queue(bdev);
+	int type = flags & DISCARD_FL_BARRIER ?
+		DISCARD_BARRIER : DISCARD_NOBARRIER;
 	int ret = 0;
 
-	if (bdev->bd_disk == NULL)
-		return -ENXIO;
-
-	q = bdev_get_queue(bdev);
 	if (!q)
 		return -ENXIO;
 
@@ -379,12 +381,14 @@ int blkdev_issue_discard(struct block_device *bdev,
 		return -EOPNOTSUPP;
 
 	while (nr_sects && !ret) {
-		bio = bio_alloc(gfp_mask, 0);
+		struct bio *bio = bio_alloc(gfp_mask, 0);
 		if (!bio)
 			return -ENOMEM;
 
 		bio->bi_end_io = blkdev_discard_end_io;
 		bio->bi_bdev = bdev;
+		if (flags & DISCARD_FL_WAIT)
+			bio->bi_private = &wait;
 
 		bio->bi_sector = sector;
 
@@ -396,10 +400,13 @@ int blkdev_issue_discard(struct block_device *bdev,
 			bio->bi_size = nr_sects << 9;
 			nr_sects = 0;
 		}
+
 		bio_get(bio);
-		submit_bio(DISCARD_BARRIER, bio);
+		submit_bio(type, bio);
+
+		if (flags & DISCARD_FL_WAIT)
+			wait_for_completion(&wait);
 
-		/* Check if it failed immediately */
 		if (bio_flagged(bio, BIO_EOPNOTSUPP))
 			ret = -EOPNOTSUPP;
 		else if (!bio_flagged(bio, BIO_UPTODATE))
diff --git a/block/ioctl.c b/block/ioctl.c
index 500e4c73cc52..d3e6b5827a34 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -112,22 +112,9 @@ static int blkdev_reread_part(struct block_device *bdev)
 	return res;
 }
 
-static void blk_ioc_discard_endio(struct bio *bio, int err)
-{
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	}
-	complete(bio->bi_private);
-}
-
 static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 			     uint64_t len)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
-	int ret = 0;
-
 	if (start & 511)
 		return -EINVAL;
 	if (len & 511)
@@ -137,40 +124,8 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 
 	if (start + len > (bdev->bd_inode->i_size >> 9))
 		return -EINVAL;
-
-	if (!q->prepare_discard_fn)
-		return -EOPNOTSUPP;
-
-	while (len && !ret) {
-		DECLARE_COMPLETION_ONSTACK(wait);
-		struct bio *bio;
-
-		bio = bio_alloc(GFP_KERNEL, 0);
-
-		bio->bi_end_io = blk_ioc_discard_endio;
-		bio->bi_bdev = bdev;
-		bio->bi_private = &wait;
-		bio->bi_sector = start;
-
-		if (len > queue_max_hw_sectors(q)) {
-			bio->bi_size = queue_max_hw_sectors(q) << 9;
-			len -= queue_max_hw_sectors(q);
-			start += queue_max_hw_sectors(q);
-		} else {
-			bio->bi_size = len << 9;
-			len = 0;
-		}
-		submit_bio(DISCARD_NOBARRIER, bio);
-
-		wait_for_completion(&wait);
-
-		if (bio_flagged(bio, BIO_EOPNOTSUPP))
-			ret = -EOPNOTSUPP;
-		else if (!bio_flagged(bio, BIO_UPTODATE))
-			ret = -EIO;
-		bio_put(bio);
-	}
-	return ret;
+	return blkdev_issue_discard(bdev, start, len, GFP_KERNEL,
+				    DISCARD_FL_WAIT);
 }
 
 static int put_ushort(unsigned long arg, unsigned short val)
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 72a2b9c28e9f..535f85ba104f 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1511,7 +1511,8 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans,
 static void btrfs_issue_discard(struct block_device *bdev,
 				u64 start, u64 len)
 {
-	blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL);
+	blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL,
+			     DISCARD_FL_BARRIER);
 }
 #endif
 
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index fba795798d3a..fbc43241f2ef 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -857,7 +857,8 @@ static void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
 					goto start_new_extent;
 				if ((start + nr_sects) != blk) {
 					rv = blkdev_issue_discard(bdev, start,
-							    nr_sects, GFP_NOFS);
+							    nr_sects, GFP_NOFS,
+							    DISCARD_FL_BARRIER);
 					if (rv)
 						goto fail;
 					nr_sects = 0;
@@ -871,7 +872,8 @@ start_new_extent:
 		}
 	}
 	if (nr_sects) {
-		rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS);
+		rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS,
+					 DISCARD_FL_BARRIER);
 		if (rv)
 			goto fail;
 	}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 86c2bdff3b89..e23a86cae5ac 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -998,15 +998,18 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
 }
 
 extern int blkdev_issue_flush(struct block_device *, sector_t *);
-extern int blkdev_issue_discard(struct block_device *,
-				sector_t sector, sector_t nr_sects, gfp_t);
+#define DISCARD_FL_WAIT		0x01	/* wait for completion */
+#define DISCARD_FL_BARRIER	0x02	/* issue DISCARD_BARRIER request */
+extern int blkdev_issue_discard(struct block_device *, sector_t sector,
+		sector_t nr_sects, gfp_t, int flags);
 
 static inline int sb_issue_discard(struct super_block *sb,
 				   sector_t block, sector_t nr_blocks)
 {
 	block <<= (sb->s_blocksize_bits - 9);
 	nr_blocks <<= (sb->s_blocksize_bits - 9);
-	return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL);
+	return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL,
+				    DISCARD_FL_BARRIER);
 }
 
 extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 8ffdc0d23c53..74f1102e8749 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -161,7 +161,8 @@ static int discard_swap(struct swap_info_struct *si)
 		}
 
 		err = blkdev_issue_discard(si->bdev, start_block,
-						nr_blocks, GFP_KERNEL);
+						nr_blocks, GFP_KERNEL,
+						DISCARD_FL_BARRIER);
 		if (err)
 			break;
 
@@ -200,7 +201,8 @@ static void discard_swap_cluster(struct swap_info_struct *si,
 			start_block <<= PAGE_SHIFT - 9;
 			nr_blocks <<= PAGE_SHIFT - 9;
 			if (blkdev_issue_discard(si->bdev, start_block,
-							nr_blocks, GFP_NOIO))
+							nr_blocks, GFP_NOIO,
+							DISCARD_FL_BARRIER))
 				break;
 		}
 
-- 
cgit v1.3-8-gc7d7