Merge branch 'for-linus' of git://oss.sgi.com/xfs/xfs

* 'for-linus' of git://oss.sgi.com/xfs/xfs:
  xfs: obey minleft values during extent allocation correctly
  xfs: reset buffer pointers before freeing them
  xfs: avoid getting stuck during async inode flushes
  xfs: fix xfs_itruncate_start tracing
  xfs: fix duplicate workqueue initialisation
  xfs: kill off xfs_printk()
  xfs: fix race condition in AIL push trigger
  xfs: make AIL target updates and compares 32bit safe.
  xfs: always push the AIL to the target
  xfs: exit AIL push work correctly when AIL is empty
  xfs: ensure reclaim cursor is reset correctly at end of AG
  xfs: add an x86 compat handler for XFS_IOC_ZERO_RANGE
  xfs: fix compiler warning in xfs_trace.h
  xfs: cleanup duplicate initializations
  xfs: reduce the number of pagb_lock roundtrips in xfs_alloc_clear_busy
  xfs: exact busy extent tracking
  xfs: do not immediately reuse busy extent ranges
  xfs: optimize AGFL refills

25 files changed, 721 insertions, 417 deletions

diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 9ef9ed2cfe2e..52b2b5da566e 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -33,7 +33,6 @@
 #include <linux/migrate.h>
 #include <linux/backing-dev.h>
 #include <linux/freezer.h>
-#include <linux/list_sort.h>
 
 #include "xfs_sb.h"
 #include "xfs_inum.h"
@@ -709,6 +708,27 @@ xfs_buf_get_empty(
 	return bp;
 }
 
+/*
+ * Return a buffer allocated as an empty buffer and associated to external
+ * memory via xfs_buf_associate_memory() back to it's empty state.
+ */
+void
+xfs_buf_set_empty(
+	struct xfs_buf		*bp,
+	size_t			len)
+{
+	if (bp->b_pages)
+		_xfs_buf_free_pages(bp);
+
+	bp->b_pages = NULL;
+	bp->b_page_count = 0;
+	bp->b_addr = NULL;
+	bp->b_file_offset = 0;
+	bp->b_buffer_length = bp->b_count_desired = len;
+	bp->b_bn = XFS_BUF_DADDR_NULL;
+	bp->b_flags &= ~XBF_MAPPED;
+}
+
 static inline struct page *
 mem_to_page(
 	void			*addr)
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index a9a1c4512645..50a7d5fb3b73 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -178,6 +178,7 @@ extern xfs_buf_t *xfs_buf_read(xfs_buftarg_t *, xfs_off_t, size_t,
 				xfs_buf_flags_t);
 
 extern xfs_buf_t *xfs_buf_get_empty(size_t, xfs_buftarg_t *);
+extern void xfs_buf_set_empty(struct xfs_buf *bp, size_t len);
 extern xfs_buf_t *xfs_buf_get_uncached(struct xfs_buftarg *, size_t, int);
 extern int xfs_buf_associate_memory(xfs_buf_t *, void *, size_t);
 extern void xfs_buf_hold(xfs_buf_t *);
diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.c b/fs/xfs/linux-2.6/xfs_ioctl32.c
index b3486dfa5520..54e623bfbb85 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl32.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl32.c
@@ -586,7 +586,8 @@ xfs_file_compat_ioctl(
 	case XFS_IOC_RESVSP_32:
 	case XFS_IOC_UNRESVSP_32:
 	case XFS_IOC_RESVSP64_32:
-	case XFS_IOC_UNRESVSP64_32: {
+	case XFS_IOC_UNRESVSP64_32:
+	case XFS_IOC_ZERO_RANGE_32: {
 		struct xfs_flock64	bf;
 
 		if (xfs_compat_flock64_copyin(&bf, arg))
diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.h b/fs/xfs/linux-2.6/xfs_ioctl32.h
index 08b605792a99..80f4060e8970 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl32.h
+++ b/fs/xfs/linux-2.6/xfs_ioctl32.h
@@ -184,6 +184,7 @@ typedef struct compat_xfs_flock64 {
 #define XFS_IOC_UNRESVSP_32	_IOW('X', 41, struct compat_xfs_flock64)
 #define XFS_IOC_RESVSP64_32	_IOW('X', 42, struct compat_xfs_flock64)
 #define XFS_IOC_UNRESVSP64_32	_IOW('X', 43, struct compat_xfs_flock64)
+#define XFS_IOC_ZERO_RANGE_32	_IOW('X', 57, struct compat_xfs_flock64)
 
 typedef struct compat_xfs_fsop_geom_v1 {
 	__u32		blocksize;	/* filesystem (data) block size */
diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h
index 244be9cbfe78..8633521b3b2e 100644
--- a/fs/xfs/linux-2.6/xfs_linux.h
+++ b/fs/xfs/linux-2.6/xfs_linux.h
@@ -70,6 +70,7 @@
 #include <linux/ctype.h>
 #include <linux/writeback.h>
 #include <linux/capability.h>
+#include <linux/list_sort.h>
 
 #include <asm/page.h>
 #include <asm/div64.h>
diff --git a/fs/xfs/linux-2.6/xfs_message.c b/fs/xfs/linux-2.6/xfs_message.c
index 9f76cceb678d..bd672def95ac 100644
--- a/fs/xfs/linux-2.6/xfs_message.c
+++ b/fs/xfs/linux-2.6/xfs_message.c
@@ -41,23 +41,6 @@ __xfs_printk(
 	printk("%sXFS: %pV\n", level, vaf);
 }
 
-void xfs_printk(
-	const char		*level,
-	const struct xfs_mount	*mp,
-	const char		*fmt, ...)
-{
-	struct va_format	vaf;
-	va_list			args;
-
-	va_start(args, fmt);
-
-	vaf.fmt = fmt;
-	vaf.va = &args;
-
-	__xfs_printk(level, mp, &vaf);
-	va_end(args);
-}
-
 #define define_xfs_printk_level(func, kern_level)		\
 void func(const struct xfs_mount *mp, const char *fmt, ...)	\
 {								\
@@ -95,8 +78,7 @@ xfs_alert_tag(
 	int			do_panic = 0;
 
 	if (xfs_panic_mask && (xfs_panic_mask & panic_tag)) {
-		xfs_printk(KERN_ALERT, mp,
-			"XFS: Transforming an alert into a BUG.");
+		xfs_alert(mp, "Transforming an alert into a BUG.");
 		do_panic = 1;
 	}
 
diff --git a/fs/xfs/linux-2.6/xfs_message.h b/fs/xfs/linux-2.6/xfs_message.h
index f1b3fc1b6c4e..7fb7ea007672 100644
--- a/fs/xfs/linux-2.6/xfs_message.h
+++ b/fs/xfs/linux-2.6/xfs_message.h
@@ -3,9 +3,6 @@
 
 struct xfs_mount;
 
-extern void xfs_printk(const char *level, const struct xfs_mount *mp,
-                      const char *fmt, ...)
-        __attribute__ ((format (printf, 3, 4)));
 extern void xfs_emerg(const struct xfs_mount *mp, const char *fmt, ...)
         __attribute__ ((format (printf, 2, 3)));
 extern void xfs_alert(const struct xfs_mount *mp, const char *fmt, ...)
@@ -28,7 +25,9 @@ extern void xfs_info(const struct xfs_mount *mp, const char *fmt, ...)
 extern void xfs_debug(const struct xfs_mount *mp, const char *fmt, ...)
         __attribute__ ((format (printf, 2, 3)));
 #else
-static inline void xfs_debug(const struct xfs_mount *mp, const char *fmt, ...)
+static inline void
+__attribute__ ((format (printf, 2, 3)))
+xfs_debug(const struct xfs_mount *mp, const char *fmt, ...)
 {
 }
 #endif
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index b38e58d02299..b0aa59e51fd0 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -1787,10 +1787,6 @@ init_xfs_fs(void)
 	if (error)
 		goto out_cleanup_procfs;
 
-	error = xfs_init_workqueues();
-	if (error)
-		goto out_sysctl_unregister;
-
 	vfs_initquota();
 
 	error = register_filesystem(&xfs_fs_type);
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 3e898a48122d..cb1bb2080e44 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -267,6 +267,16 @@ xfs_sync_inode_attr(
 
 	error = xfs_iflush(ip, flags);
 
+	/*
+	 * We don't want to try again on non-blocking flushes that can't run
+	 * again immediately. If an inode really must be written, then that's
+	 * what the SYNC_WAIT flag is for.
+	 */
+	if (error == EAGAIN) {
+		ASSERT(!(flags & SYNC_WAIT));
+		error = 0;
+	}
+
  out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 	return error;
diff --git a/fs/xfs/linux-2.6/xfs_trace.h b/fs/xfs/linux-2.6/xfs_trace.h
index 2d0bcb479075..d48b7a579ae1 100644
--- a/fs/xfs/linux-2.6/xfs_trace.h
+++ b/fs/xfs/linux-2.6/xfs_trace.h
@@ -1151,44 +1151,7 @@ TRACE_EVENT(xfs_bunmap,
 
 );
 
-#define XFS_BUSY_SYNC \
-	{ 0,	"async" }, \
-	{ 1,	"sync" }
-
-TRACE_EVENT(xfs_alloc_busy,
-	TP_PROTO(struct xfs_trans *trans, xfs_agnumber_t agno,
-		 xfs_agblock_t agbno, xfs_extlen_t len, int sync),
-	TP_ARGS(trans, agno, agbno, len, sync),
-	TP_STRUCT__entry(
-		__field(dev_t, dev)
-		__field(struct xfs_trans *, tp)
-		__field(int, tid)
-		__field(xfs_agnumber_t, agno)
-		__field(xfs_agblock_t, agbno)
-		__field(xfs_extlen_t, len)
-		__field(int, sync)
-	),
-	TP_fast_assign(
-		__entry->dev = trans->t_mountp->m_super->s_dev;
-		__entry->tp = trans;
-		__entry->tid = trans->t_ticket->t_tid;
-		__entry->agno = agno;
-		__entry->agbno = agbno;
-		__entry->len = len;
-		__entry->sync = sync;
-	),
-	TP_printk("dev %d:%d trans 0x%p tid 0x%x agno %u agbno %u len %u %s",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->tp,
-		  __entry->tid,
-		  __entry->agno,
-		  __entry->agbno,
-		  __entry->len,
-		  __print_symbolic(__entry->sync, XFS_BUSY_SYNC))
-
-);
-
-TRACE_EVENT(xfs_alloc_unbusy,
+DECLARE_EVENT_CLASS(xfs_busy_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agblock_t agbno, xfs_extlen_t len),
 	TP_ARGS(mp, agno, agbno, len),
@@ -1210,35 +1173,45 @@ TRACE_EVENT(xfs_alloc_unbusy,
 		  __entry->agbno,
 		  __entry->len)
 );
+#define DEFINE_BUSY_EVENT(name) \
+DEFINE_EVENT(xfs_busy_class, name, \
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
+		 xfs_agblock_t agbno, xfs_extlen_t len), \
+	TP_ARGS(mp, agno, agbno, len))
+DEFINE_BUSY_EVENT(xfs_alloc_busy);
+DEFINE_BUSY_EVENT(xfs_alloc_busy_enomem);
+DEFINE_BUSY_EVENT(xfs_alloc_busy_force);
+DEFINE_BUSY_EVENT(xfs_alloc_busy_reuse);
+DEFINE_BUSY_EVENT(xfs_alloc_busy_clear);
 
-#define XFS_BUSY_STATES \
-	{ 0,	"missing" }, \
-	{ 1,	"found" }
-
-TRACE_EVENT(xfs_alloc_busysearch,
+TRACE_EVENT(xfs_alloc_busy_trim,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 xfs_agblock_t agbno, xfs_extlen_t len, int found),
-	TP_ARGS(mp, agno, agbno, len, found),
+		 xfs_agblock_t agbno, xfs_extlen_t len,
+		 xfs_agblock_t tbno, xfs_extlen_t tlen),
+	TP_ARGS(mp, agno, agbno, len, tbno, tlen),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
 		__field(xfs_agblock_t, agbno)
 		__field(xfs_extlen_t, len)
-		__field(int, found)
+		__field(xfs_agblock_t, tbno)
+		__field(xfs_extlen_t, tlen)
 	),
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
 		__entry->agno = agno;
 		__entry->agbno = agbno;
 		__entry->len = len;
-		__entry->found = found;
+		__entry->tbno = tbno;
+		__entry->tlen = tlen;
 	),
-	TP_printk("dev %d:%d agno %u agbno %u len %u %s",
+	TP_printk("dev %d:%d agno %u agbno %u len %u tbno %u tlen %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
 		  __entry->agbno,
 		  __entry->len,
-		  __print_symbolic(__entry->found, XFS_BUSY_STATES))
+		  __entry->tbno,
+		  __entry->tlen)
 );
 
 TRACE_EVENT(xfs_trans_commit_lsn,
@@ -1418,7 +1391,7 @@ DECLARE_EVENT_CLASS(xfs_alloc_class,
 		  __entry->wasfromfl,
 		  __entry->isfl,
 		  __entry->userdata,
-		  __entry->firstblock)
+		  (unsigned long long)__entry->firstblock)
 )
 
 #define DEFINE_ALLOC_EVENT(name) \
@@ -1433,11 +1406,14 @@ DEFINE_ALLOC_EVENT(xfs_alloc_near_first);
 DEFINE_ALLOC_EVENT(xfs_alloc_near_greater);
 DEFINE_ALLOC_EVENT(xfs_alloc_near_lesser);
 DEFINE_ALLOC_EVENT(xfs_alloc_near_error);
+DEFINE_ALLOC_EVENT(xfs_alloc_near_noentry);
+DEFINE_ALLOC_EVENT(xfs_alloc_near_busy);
 DEFINE_ALLOC_EVENT(xfs_alloc_size_neither);
 DEFINE_ALLOC_EVENT(xfs_alloc_size_noentry);
 DEFINE_ALLOC_EVENT(xfs_alloc_size_nominleft);
 DEFINE_ALLOC_EVENT(xfs_alloc_size_done);
 DEFINE_ALLOC_EVENT(xfs_alloc_size_error);
+DEFINE_ALLOC_EVENT(xfs_alloc_size_busy);
 DEFINE_ALLOC_EVENT(xfs_alloc_small_freelist);
 DEFINE_ALLOC_EVENT(xfs_alloc_small_notenough);
 DEFINE_ALLOC_EVENT(xfs_alloc_small_done);
diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h
index 58632cc17f2d..da0a561ffba2 100644
--- a/fs/xfs/xfs_ag.h
+++ b/fs/xfs/xfs_ag.h
@@ -187,7 +187,6 @@ struct xfs_busy_extent {
 	xfs_agnumber_t	agno;
 	xfs_agblock_t	bno;
 	xfs_extlen_t	length;
-	xlog_tid_t	tid;		/* transaction that created this */
 };
 
 /*
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index 27d64d752eab..acdced86413c 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -41,19 +41,13 @@
 #define	XFSA_FIXUP_BNO_OK	1
 #define	XFSA_FIXUP_CNT_OK	2
 
-/*
- * Prototypes for per-ag allocation routines
- */
-
 STATIC int xfs_alloc_ag_vextent_exact(xfs_alloc_arg_t *);
 STATIC int xfs_alloc_ag_vextent_near(xfs_alloc_arg_t *);
 STATIC int xfs_alloc_ag_vextent_size(xfs_alloc_arg_t *);
 STATIC int xfs_alloc_ag_vextent_small(xfs_alloc_arg_t *,
-	xfs_btree_cur_t *, xfs_agblock_t *, xfs_extlen_t *, int *);
-
-/*
- * Internal functions.
- */
+		xfs_btree_cur_t *, xfs_agblock_t *, xfs_extlen_t *, int *);
+STATIC void xfs_alloc_busy_trim(struct xfs_alloc_arg *,
+		xfs_agblock_t, xfs_extlen_t, xfs_agblock_t *, xfs_extlen_t *);
 
 /*
  * Lookup the record equal to [bno, len] in the btree given by cur.
@@ -154,19 +148,21 @@ xfs_alloc_compute_aligned(
 	xfs_extlen_t	*reslen)	/* result length */
 {
 	xfs_agblock_t	bno;
-	xfs_extlen_t	diff;
 	xfs_extlen_t	len;
 
-	if (args->alignment > 1 && foundlen >= args->minlen) {
-		bno = roundup(foundbno, args->alignment);
-		diff = bno - foundbno;
-		len = diff >= foundlen ? 0 : foundlen - diff;
+	/* Trim busy sections out of found extent */
+	xfs_alloc_busy_trim(args, foundbno, foundlen, &bno, &len);
+
+	if (args->alignment > 1 && len >= args->minlen) {
+		xfs_agblock_t	aligned_bno = roundup(bno, args->alignment);
+		xfs_extlen_t	diff = aligned_bno - bno;
+
+		*resbno = aligned_bno;
+		*reslen = diff >= len ? 0 : len - diff;
 	} else {
-		bno = foundbno;
-		len = foundlen;
+		*resbno = bno;
+		*reslen = len;
 	}
-	*resbno = bno;
-	*reslen = len;
 }
 
 /*
@@ -280,7 +276,6 @@ xfs_alloc_fix_minleft(
 		return 1;
 	agf = XFS_BUF_TO_AGF(args->agbp);
 	diff = be32_to_cpu(agf->agf_freeblks)
-		+ be32_to_cpu(agf->agf_flcount)
 		- args->len - args->minleft;
 	if (diff >= 0)
 		return 1;
@@ -541,16 +536,8 @@ xfs_alloc_ag_vextent(
 		if (error)
 			return error;
 
-		/*
-		 * Search the busylist for these blocks and mark the
-		 * transaction as synchronous if blocks are found. This
-		 * avoids the need to block due to a synchronous log
-		 * force to ensure correct ordering as the synchronous
-		 * transaction will guarantee that for us.
-		 */
-		if (xfs_alloc_busy_search(args->mp, args->agno,
-					args->agbno, args->len))
-			xfs_trans_set_sync(args->tp);
+		ASSERT(!xfs_alloc_busy_search(args->mp, args->agno,
+					      args->agbno, args->len));
 	}
 
 	if (!args->isfl) {
@@ -577,14 +564,14 @@ xfs_alloc_ag_vextent_exact(
 {
 	xfs_btree_cur_t	*bno_cur;/* by block-number btree cursor */
 	xfs_btree_cur_t	*cnt_cur;/* by count btree cursor */
-	xfs_agblock_t	end;	/* end of allocated extent */
 	int		error;
 	xfs_agblock_t	fbno;	/* start block of found extent */
-	xfs_agblock_t	fend;	/* end block of found extent */
 	xfs_extlen_t	flen;	/* length of found extent */
+	xfs_agblock_t	tbno;	/* start block of trimmed extent */
+	xfs_extlen_t	tlen;	/* length of trimmed extent */
+	xfs_agblock_t	tend;	/* end block of trimmed extent */
+	xfs_agblock_t	end;	/* end of allocated extent */
 	int		i;	/* success/failure of operation */
-	xfs_agblock_t	maxend;	/* end of maximal extent */
-	xfs_agblock_t	minend;	/* end of minimal extent */
 	xfs_extlen_t	rlen;	/* length of returned extent */
 
 	ASSERT(args->alignment == 1);
@@ -614,14 +601,22 @@ xfs_alloc_ag_vextent_exact(
 		goto error0;
 	XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
 	ASSERT(fbno <= args->agbno);
-	minend = args->agbno + args->minlen;
-	maxend = args->agbno + args->maxlen;
-	fend = fbno + flen;
 
 	/*
-	 * Give up if the freespace isn't long enough for the minimum request.
+	 * Check for overlapping busy extents.
+	 */
+	xfs_alloc_busy_trim(args, fbno, flen, &tbno, &tlen);
+
+	/*
+	 * Give up if the start of the extent is busy, or the freespace isn't
+	 * long enough for the minimum request.
 	 */
-	if (fend < minend)
+	if (tbno > args->agbno)
+		goto not_found;
+	if (tlen < args->minlen)
+		goto not_found;
+	tend = tbno + tlen;
+	if (tend < args->agbno + args->minlen)
 		goto not_found;
 
 	/*
@@ -630,14 +625,14 @@ xfs_alloc_ag_vextent_exact(
 	 *
 	 * Fix the length according to mod and prod if given.
 	 */
-	end = XFS_AGBLOCK_MIN(fend, maxend);
+	end = XFS_AGBLOCK_MIN(tend, args->agbno + args->maxlen);
 	args->len = end - args->agbno;
 	xfs_alloc_fix_len(args);
 	if (!xfs_alloc_fix_minleft(args))
 		goto not_found;
 
 	rlen = args->len;
-	ASSERT(args->agbno + rlen <= fend);
+	ASSERT(args->agbno + rlen <= tend);
 	end = args->agbno + rlen;
 
 	/*
@@ -686,11 +681,11 @@ xfs_alloc_find_best_extent(
 	struct xfs_btree_cur	**scur,	/* searching cursor */
 	xfs_agblock_t		gdiff,	/* difference for search comparison */
 	xfs_agblock_t		*sbno,	/* extent found by search */
-	xfs_extlen_t		*slen,
-	xfs_extlen_t		*slena,	/* aligned length */
+	xfs_extlen_t		*slen,	/* extent length */
+	xfs_agblock_t		*sbnoa,	/* aligned extent found by search */
+	xfs_extlen_t		*slena,	/* aligned extent length */
 	int			dir)	/* 0 = search right, 1 = search left */
 {
-	xfs_agblock_t		bno;
 	xfs_agblock_t		new;
 	xfs_agblock_t		sdiff;
 	int			error;
@@ -708,16 +703,16 @@ xfs_alloc_find_best_extent(
 		if (error)
 			goto error0;
 		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		xfs_alloc_compute_aligned(args, *sbno, *slen, &bno, slena);
+		xfs_alloc_compute_aligned(args, *sbno, *slen, sbnoa, slena);
 
 		/*
 		 * The good extent is closer than this one.
 		 */
 		if (!dir) {
-			if (bno >= args->agbno + gdiff)
+			if (*sbnoa >= args->agbno + gdiff)
 				goto out_use_good;
 		} else {
-			if (bno <= args->agbno - gdiff)
+			if (*sbnoa <= args->agbno - gdiff)
 				goto out_use_good;
 		}
 
@@ -729,8 +724,8 @@ xfs_alloc_find_best_extent(
 			xfs_alloc_fix_len(args);
 
 			sdiff = xfs_alloc_compute_diff(args->agbno, args->len,
-						       args->alignment, *sbno,
-						       *slen, &new);
+						       args->alignment, *sbnoa,
+						       *slena, &new);
 
 			/*
 			 * Choose closer size and invalidate other cursor.
@@ -780,7 +775,7 @@ xfs_alloc_ag_vextent_near(
 	xfs_agblock_t	gtbnoa;		/* aligned ... */
 	xfs_extlen_t	gtdiff;		/* difference to right side entry */
 	xfs_extlen_t	gtlen;		/* length of right side entry */
-	xfs_extlen_t	gtlena = 0;	/* aligned ... */
+	xfs_extlen_t	gtlena;		/* aligned ... */
 	xfs_agblock_t	gtnew;		/* useful start bno of right side */
 	int		error;		/* error code */
 	int		i;		/* result code, temporary */
@@ -789,9 +784,10 @@ xfs_alloc_ag_vextent_near(
 	xfs_agblock_t	ltbnoa;		/* aligned ... */
 	xfs_extlen_t	ltdiff;		/* difference to left side entry */
 	xfs_extlen_t	ltlen;		/* length of left side entry */
-	xfs_extlen_t	ltlena = 0;	/* aligned ... */
+	xfs_extlen_t	ltlena;		/* aligned ... */
 	xfs_agblock_t	ltnew;		/* useful start bno of left side */
 	xfs_extlen_t	rlen;		/* length of returned extent */
+	int		forced = 0;
 #if defined(DEBUG) && defined(__KERNEL__)
 	/*
 	 * Randomly don't execute the first algorithm.
@@ -800,13 +796,20 @@ xfs_alloc_ag_vextent_near(
 
 	dofirst = random32() & 1;
 #endif
+
+restart:
+	bno_cur_lt = NULL;
+	bno_cur_gt = NULL;
+	ltlen = 0;
+	gtlena = 0;
+	ltlena = 0;
+
 	/*
 	 * Get a cursor for the by-size btree.
 	 */
 	cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
 		args->agno, XFS_BTNUM_CNT);
-	ltlen = 0;
-	bno_cur_lt = bno_cur_gt = NULL;
+
 	/*
 	 * See if there are any free extents as big as maxlen.
 	 */
@@ -822,11 +825,13 @@ xfs_alloc_ag_vextent_near(
 			goto error0;
 		if (i == 0 || ltlen == 0) {
 			xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
+			trace_xfs_alloc_near_noentry(args);
 			return 0;
 		}
 		ASSERT(i == 1);
 	}
 	args->wasfromfl = 0;
+
 	/*
 	 * First algorithm.
 	 * If the requested extent is large wrt the freespaces available
@@ -890,7 +895,7 @@ xfs_alloc_ag_vextent_near(
 			if (args->len < blen)
 				continue;
 			ltdiff = xfs_alloc_compute_diff(args->agbno, args->len,
-				args->alignment, ltbno, ltlen, &ltnew);
+				args->alignment, ltbnoa, ltlena, &ltnew);
 			if (ltnew != NULLAGBLOCK &&
 			    (args->len > blen || ltdiff < bdiff)) {
 				bdiff = ltdiff;
@@ -1042,11 +1047,12 @@ xfs_alloc_ag_vextent_near(
 			args->len = XFS_EXTLEN_MIN(ltlena, args->maxlen);
 			xfs_alloc_fix_len(args);
 			ltdiff = xfs_alloc_compute_diff(args->agbno, args->len,
-				args->alignment, ltbno, ltlen, &ltnew);
+				args->alignment, ltbnoa, ltlena, &ltnew);
 
 			error = xfs_alloc_find_best_extent(args,
 						&bno_cur_lt, &bno_cur_gt,
-						ltdiff, &gtbno, &gtlen, &gtlena,
+						ltdiff, &gtbno, &gtlen,
+						&gtbnoa, &gtlena,
 						0 /* search right */);
 		} else {
 			ASSERT(gtlena >= args->minlen);
@@ -1057,11 +1063,12 @@ xfs_alloc_ag_vextent_near(
 			args->len = XFS_EXTLEN_MIN(gtlena, args->maxlen);
 			xfs_alloc_fix_len(args);
 			gtdiff = xfs_alloc_compute_diff(args->agbno, args->len,
-				args->alignment, gtbno, gtlen, &gtnew);
+				args->alignment, gtbnoa, gtlena, &gtnew);
 
 			error = xfs_alloc_find_best_extent(args,
 						&bno_cur_gt, &bno_cur_lt,
-						gtdiff, &ltbno, &ltlen, &ltlena,
+						gtdiff, &ltbno, &ltlen,
+						&ltbnoa, &ltlena,
 						1 /* search left */);
 		}
 
@@ -1073,6 +1080,12 @@ xfs_alloc_ag_vextent_near(
 	 * If we couldn't get anything, give up.
 	 */
 	if (bno_cur_lt == NULL && bno_cur_gt == NULL) {
+		if (!forced++) {
+			trace_xfs_alloc_near_busy(args);
+			xfs_log_force(args->mp, XFS_LOG_SYNC);
+			goto restart;
+		}
+
 		trace_xfs_alloc_size_neither(args);
 		args->agbno = NULLAGBLOCK;
 		return 0;
@@ -1107,12 +1120,13 @@ xfs_alloc_ag_vextent_near(
 		return 0;
 	}
 	rlen = args->len;
-	(void)xfs_alloc_compute_diff(args->agbno, rlen, args->alignment, ltbno,
-		ltlen, &ltnew);
+	(void)xfs_alloc_compute_diff(args->agbno, rlen, args->alignment,
+				     ltbnoa, ltlena, &ltnew);
 	ASSERT(ltnew >= ltbno);
-	ASSERT(ltnew + rlen <= ltbno + ltlen);
+	ASSERT(ltnew + rlen <= ltbnoa + ltlena);
 	ASSERT(ltnew + rlen <= be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_length));
 	args->agbno = ltnew;
+
 	if ((error = xfs_alloc_fixup_trees(cnt_cur, bno_cur_lt, ltbno, ltlen,
 			ltnew, rlen, XFSA_FIXUP_BNO_OK)))
 		goto error0;
@@ -1155,26 +1169,35 @@ xfs_alloc_ag_vextent_size(
 	int		i;		/* temp status variable */
 	xfs_agblock_t	rbno;		/* returned block number */
 	xfs_extlen_t	rlen;		/* length of returned extent */
+	int		forced = 0;
 
+restart:
 	/*
 	 * Allocate and initialize a cursor for the by-size btree.
 	 */
 	cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
 		args->agno, XFS_BTNUM_CNT);
 	bno_cur = NULL;
+
 	/*
 	 * Look for an entry >= maxlen+alignment-1 blocks.
 	 */
 	if ((error = xfs_alloc_lookup_ge(cnt_cur, 0,
 			args->maxlen + args->alignment - 1, &i)))
 		goto error0;
+
 	/*
-	 * If none, then pick up the last entry in the tree unless the
-	 * tree is empty.
+	 * If none or we have busy extents that we cannot allocate from, then
+	 * we have to settle for a smaller extent. In the case that there are
+	 * no large extents, this will return the last entry in the tree unless
+	 * the tree is empty. In the case that there are only busy large
+	 * extents, this will return the largest small extent unless there
+	 * are no smaller extents available.
 	 */
-	if (!i) {
-		if ((error = xfs_alloc_ag_vextent_small(args, cnt_cur, &fbno,
-				&flen, &i)))
+	if (!i || forced > 1) {
+		error = xfs_alloc_ag_vextent_small(args, cnt_cur,
+						   &fbno, &flen, &i);
+		if (error)
 			goto error0;
 		if (i == 0 || flen == 0) {
 			xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
@@ -1182,22 +1205,56 @@ xfs_alloc_ag_vextent_size(
 			return 0;
 		}
 		ASSERT(i == 1);
+		xfs_alloc_compute_aligned(args, fbno, flen, &rbno, &rlen);
+	} else {
+		/*
+		 * Search for a non-busy extent that is large enough.
+		 * If we are at low space, don't check, or if we fall of
+		 * the end of the btree, turn off the busy check and
+		 * restart.
+		 */
+		for (;;) {
+			error = xfs_alloc_get_rec(cnt_cur, &fbno, &flen, &i);
+			if (error)
+				goto error0;
+			XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
+
+			xfs_alloc_compute_aligned(args, fbno, flen,
+						  &rbno, &rlen);
+
+			if (rlen >= args->maxlen)
+				break;
+
+			error = xfs_btree_increment(cnt_cur, 0, &i);
+			if (error)
+				goto error0;
+			if (i == 0) {
+				/*
+				 * Our only valid extents must have been busy.
+				 * Make it unbusy by forcing the log out and
+				 * retrying. If we've been here before, forcing
+				 * the log isn't making the extents available,
+				 * which means they have probably been freed in
+				 * this transaction.  In that case, we have to
+				 * give up on them and we'll attempt a minlen
+				 * allocation the next time around.
+				 */
+				xfs_btree_del_cursor(cnt_cur,
+						     XFS_BTREE_NOERROR);
+				trace_xfs_alloc_size_busy(args);
+				if (!forced++)
+					xfs_log_force(args->mp, XFS_LOG_SYNC);
+				goto restart;
+			}
+		}
 	}
-	/*
-	 * There's a freespace as big as maxlen+alignment-1, get it.
-	 */
-	else {
-		if ((error = xfs_alloc_get_rec(cnt_cur, &fbno, &flen, &i)))
-			goto error0;
-		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-	}
+
 	/*
 	 * In the first case above, we got the last entry in the
 	 * by-size btree.  Now we check to see if the space hits maxlen
 	 * once aligned; if not, we search left for something better.
 	 * This can't happen in the second case above.
 	 */
-	xfs_alloc_compute_aligned(args, fbno, flen, &rbno, &rlen);
 	rlen = XFS_EXTLEN_MIN(args->maxlen, rlen);
 	XFS_WANT_CORRUPTED_GOTO(rlen == 0 ||
 			(rlen <= flen && rbno + rlen <= fbno + flen), error0);
@@ -1251,13 +1308,19 @@ xfs_alloc_ag_vextent_size(
 	 * Fix up the length.
 	 */
 	args->len = rlen;
-	xfs_alloc_fix_len(args);
-	if (rlen < args->minlen || !xfs_alloc_fix_minleft(args)) {
-		xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
-		trace_xfs_alloc_size_nominleft(args);
-		args->agbno = NULLAGBLOCK;
-		return 0;
+	if (rlen < args->minlen) {
+		if (!forced++) {
+			xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
+			trace_xfs_alloc_size_busy(args);
+			xfs_log_force(args->mp, XFS_LOG_SYNC);
+			goto restart;
+		}
+		goto out_nominleft;
 	}
+	xfs_alloc_fix_len(args);
+
+	if (!xfs_alloc_fix_minleft(args))
+		goto out_nominleft;
 	rlen = args->len;
 	XFS_WANT_CORRUPTED_GOTO(rlen <= flen, error0);
 	/*
@@ -1287,6 +1350,12 @@ error0:
 	if (bno_cur)
 		xfs_btree_del_cursor(bno_cur, XFS_BTREE_ERROR);
 	return error;
+
+out_nominleft:
+	xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
+	trace_xfs_alloc_size_nominleft(args);
+	args->agbno = NULLAGBLOCK;
+	return 0;
 }
 
 /*
@@ -1326,6 +1395,9 @@ xfs_alloc_ag_vextent_small(
 		if (error)
 			goto error0;
 		if (fbno != NULLAGBLOCK) {
+			xfs_alloc_busy_reuse(args->mp, args->agno, fbno, 1,
+					     args->userdata);
+
 			if (args->userdata) {
 				xfs_buf_t	*bp;
 
@@ -1617,18 +1689,6 @@ xfs_free_ag_extent(
 
 	trace_xfs_free_extent(mp, agno, bno, len, isfl, haveleft, haveright);
 
-	/*
-	 * Since blocks move to the free list without the coordination
-	 * used in xfs_bmap_finish, we can't allow block to be available
-	 * for reallocation and non-transaction writing (user data)
-	 * until we know that the transaction that moved it to the free
-	 * list is permanently on disk.  We track the blocks by declaring
-	 * these blocks as "busy"; the busy list is maintained on a per-ag
-	 * basis and each transaction records which entries should be removed
-	 * when the iclog commits to disk.  If a busy block is allocated,
-	 * the iclog is pushed up to the LSN that freed the block.
-	 */
-	xfs_alloc_busy_insert(tp, agno, bno, len);
 	return 0;
 
  error0:
@@ -1923,21 +1983,6 @@ xfs_alloc_get_freelist(
 	xfs_alloc_log_agf(tp, agbp, logflags);
 	*bnop = bno;
 
-	/*
-	 * As blocks are freed, they are added to the per-ag busy list and
-	 * remain there until the freeing transaction is committed to disk.
-	 * Now that we have allocated blocks, this list must be searched to see
-	 * if a block is being reused.  If one is, then the freeing transaction
-	 * must be pushed to disk before this transaction.
-	 *
-	 * We do this by setting the current transaction to a sync transaction
-	 * which guarantees that the freeing transaction is on disk before this
-	 * transaction. This is done instead of a synchronous log force here so
-	 * that we don't sit and wait with the AGF locked in the transaction
-	 * during the log force.
-	 */
-	if (xfs_alloc_busy_search(mp, be32_to_cpu(agf->agf_seqno), bno, 1))
-		xfs_trans_set_sync(tp);
 	return 0;
 }
 
@@ -2423,105 +2468,13 @@ xfs_free_extent(
 	}
 
 	error = xfs_free_ag_extent(tp, args.agbp, args.agno, args.agbno, len, 0);
+	if (!error)
+		xfs_alloc_busy_insert(tp, args.agno, args.agbno, len);
 error0:
 	xfs_perag_put(args.pag);
 	return error;
 }
 
-
-/*
- * AG Busy list management