[XFS] Convert l_flushsema to a sv_t

The l_flushsema doesn't exactly have completion semantics, nor mutex
semantics. It's used as a list of tasks which are waiting to be notified
that a flush has completed. It was also being used in a way that was
potentially racy, depending on the semaphore implementation.

By using a sv_t instead of a semaphore we avoid the need for a separate
counter, since we know we just need to wake everything on the queue.

Original waitqueue implementation from Matthew Wilcox. Cleanup and
conversion to sv_t by Christoph Hellwig.

SGI-PV: 981507
SGI-Modid: xfs-linux-melb:xfs-kern:31059a

Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: David Chinner <dgc@sgi.com>
Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>

2 files changed, 15 insertions, 20 deletions

diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 6195cc880101..91b00a5686cd 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1232,7 +1232,7 @@ xlog_alloc_log(xfs_mount_t	*mp,
 
 	spin_lock_init(&log->l_icloglock);
 	spin_lock_init(&log->l_grant_lock);
-	initnsema(&log->l_flushsema, 0, "ic-flush");
+	sv_init(&log->l_flush_wait, 0, "flush_wait");
 
 	/* log record size must be multiple of BBSIZE; see xlog_rec_header_t */
 	ASSERT((XFS_BUF_SIZE(bp) & BBMASK) == 0);
@@ -1577,7 +1577,6 @@ xlog_dealloc_log(xlog_t *log)
 		kmem_free(iclog);
 		iclog = next_iclog;
 	}
-	freesema(&log->l_flushsema);
 	spinlock_destroy(&log->l_icloglock);
 	spinlock_destroy(&log->l_grant_lock);
 
@@ -2101,6 +2100,7 @@ xlog_state_do_callback(
 	int		   funcdidcallbacks; /* flag: function did callbacks */
 	int		   repeats;	/* for issuing console warnings if
 					 * looping too many times */
+	int		   wake = 0;
 
 	spin_lock(&log->l_icloglock);
 	first_iclog = iclog = log->l_iclog;
@@ -2282,15 +2282,13 @@ xlog_state_do_callback(
 	}
 #endif
 
-	flushcnt = 0;
-	if (log->l_iclog->ic_state & (XLOG_STATE_ACTIVE|XLOG_STATE_IOERROR)) {
-		flushcnt = log->l_flushcnt;
-		log->l_flushcnt = 0;
-	}
+	if (log->l_iclog->ic_state & (XLOG_STATE_ACTIVE|XLOG_STATE_IOERROR))
+		wake = 1;
 	spin_unlock(&log->l_icloglock);
-	while (flushcnt--)
-		vsema(&log->l_flushsema);
-}	/* xlog_state_do_callback */
+
+	if (wake)
+		sv_broadcast(&log->l_flush_wait);
+}
 
 
 /*
@@ -2388,16 +2386,15 @@ restart:
 	}
 
 	iclog = log->l_iclog;
-	if (! (iclog->ic_state == XLOG_STATE_ACTIVE)) {
-		log->l_flushcnt++;
-		spin_unlock(&log->l_icloglock);
+	if (iclog->ic_state != XLOG_STATE_ACTIVE) {
 		xlog_trace_iclog(iclog, XLOG_TRACE_SLEEP_FLUSH);
 		XFS_STATS_INC(xs_log_noiclogs);
-		/* Ensure that log writes happen */
-		psema(&log->l_flushsema, PINOD);
+
+		/* Wait for log writes to have flushed */
+		sv_wait(&log->l_flush_wait, 0, &log->l_icloglock, 0);
 		goto restart;
 	}
-	ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE);
+
 	head = &iclog->ic_header;
 
 	atomic_inc(&iclog->ic_refcnt);	/* prevents sync */
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 8952a392b5f3..6245913196b4 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -423,10 +423,8 @@ typedef struct log {
 	int			l_logBBsize;    /* size of log in BB chunks */
 
 	/* The following block of fields are changed while holding icloglock */
-	sema_t			l_flushsema ____cacheline_aligned_in_smp;
-						/* iclog flushing semaphore */
-	int			l_flushcnt;	/* # of procs waiting on this
-						 * sema */
+	sv_t			l_flush_wait ____cacheline_aligned_in_smp;
+						/* waiting for iclog flush */
 	int			l_covered_state;/* state of "covering disk
 						 * log entries" */
 	xlog_in_core_t		*l_iclog;       /* head log queue	*/