ufs.patch

Index: sys/ufs/ffs/ffs_softdep.c
===================================================================
--- sys/ufs/ffs/ffs_softdep.c	(revision 282245)
+++ sys/ufs/ffs/ffs_softdep.c	(working copy)
@@ -735,9 +735,10 @@ static struct malloc_type *memtype[] = {
 static	void check_clear_deps(struct mount *);
 static	void softdep_error(char *, int);
 static	int softdep_process_worklist(struct mount *, int);
-static	int softdep_waitidle(struct mount *);
+static	int softdep_waitidle(struct mount *, int);
 static	void drain_output(struct vnode *);
 static	struct buf *getdirtybuf(struct buf *, struct rwlock *, int);
+static	int check_inodedep_free(struct inodedep *);
 static	void clear_remove(struct mount *);
 static	void clear_inodedeps(struct mount *);
 static	void unlinked_inodedep(struct mount *, struct inodedep *);
@@ -1377,6 +1378,10 @@ softdep_flush(addr)
 	mp = (struct mount *)addr;
 	ump = VFSTOUFS(mp);
 	atomic_add_int(&stat_flush_threads, 1);
+	ACQUIRE_LOCK(ump);
+	ump->softdep_flags &= ~FLUSH_STARTING;
+	wakeup(&ump->softdep_flushtd);
+	FREE_LOCK(ump);
 	if (print_threads) {
 		if (stat_flush_threads == 1)
 			printf("Running %s at pid %d\n", bufdaemonproc->p_comm,
@@ -1389,7 +1394,7 @@ softdep_flush(addr)
 		    VFSTOUFS(mp)->softdep_jblocks->jb_suspended))
 			kthread_suspend_check();
 		ACQUIRE_LOCK(ump);
-		if ((ump->softdep_flags & FLUSH_CLEANUP) == 0)
+		if ((ump->softdep_flags & (FLUSH_CLEANUP | FLUSH_EXIT)) == 0)
 			msleep(&ump->softdep_flushtd, LOCK_PTR(ump), PVM,
 			    "sdflush", hz / 2);
 		ump->softdep_flags &= ~FLUSH_CLEANUP;
@@ -1419,11 +1424,9 @@ worklist_speedup(mp)
 
 	ump = VFSTOUFS(mp);
 	LOCK_OWNED(ump);
-	if ((ump->softdep_flags & (FLUSH_CLEANUP | FLUSH_EXIT)) == 0) {
+	if ((ump->softdep_flags & (FLUSH_CLEANUP | FLUSH_EXIT)) == 0)
 		ump->softdep_flags |= FLUSH_CLEANUP;
-		if (ump->softdep_flushtd->td_wchan == &ump->softdep_flushtd)
-			wakeup(&ump->softdep_flushtd);
-	}
+	wakeup(&ump->softdep_flushtd);
 }
 
 static int
@@ -1468,14 +1471,10 @@ softdep_speedup(ump)
 			TAILQ_INSERT_TAIL(&softdepmounts, sdp, sd_next);
 			FREE_GBLLOCK(&lk);
 			if ((altump->softdep_flags &
-			    (FLUSH_CLEANUP | FLUSH_EXIT)) == 0) {
+			    (FLUSH_CLEANUP | FLUSH_EXIT)) == 0)
 				altump->softdep_flags |= FLUSH_CLEANUP;
-				altump->um_softdep->sd_cleanups++;
-				if (altump->softdep_flushtd->td_wchan ==
-				    &altump->softdep_flushtd) {
-					wakeup(&altump->softdep_flushtd);
-				}
-			}
+			altump->um_softdep->sd_cleanups++;
+			wakeup(&altump->softdep_flushtd);
 			FREE_LOCK(altump);
 		}
 	}
@@ -1887,8 +1886,8 @@ softdep_flushworklist(oldmnt, countp, td
 	struct thread *td;
 {
 	struct vnode *devvp;
-	int count, error = 0;
 	struct ufsmount *ump;
+	int count, error;
 
 	/*
 	 * Alternately flush the block device associated with the mount
@@ -1897,6 +1896,7 @@ softdep_flushworklist(oldmnt, countp, td
 	 * are found.
 	 */
 	*countp = 0;
+	error = 0;
 	ump = VFSTOUFS(oldmnt);
 	devvp = ump->um_devvp;
 	while ((count = softdep_process_worklist(oldmnt, 1)) > 0) {
@@ -1904,36 +1904,47 @@ softdep_flushworklist(oldmnt, countp, td
 		vn_lock(devvp, LK_EXCLUSIVE | LK_RETRY);
 		error = VOP_FSYNC(devvp, MNT_WAIT, td);
 		VOP_UNLOCK(devvp, 0);
-		if (error)
+		if (error != 0)
 			break;
 	}
 	return (error);
 }
 
+#define	SU_WAITIDLE_RETRIES	20
 static int
-softdep_waitidle(struct mount *mp)
+softdep_waitidle(struct mount *mp, int flags __unused)
 {
 	struct ufsmount *ump;
-	int error;
-	int i;
+	struct vnode *devvp;
+	struct thread *td;
+	int error, i;
 
 	ump = VFSTOUFS(mp);
+	devvp = ump->um_devvp;
+	td = curthread;
+	error = 0;
 	ACQUIRE_LOCK(ump);
-	for (i = 0; i < 10 && ump->softdep_deps; i++) {
+	for (i = 0; i < SU_WAITIDLE_RETRIES && ump->softdep_deps != 0; i++) {
 		ump->softdep_req = 1;
-		if (ump->softdep_on_worklist)
-			panic("softdep_waitidle: work added after flush.");
-		msleep(&ump->softdep_deps, LOCK_PTR(ump), PVM, "softdeps", 1);
+		KASSERT((flags & FORCECLOSE) == 0 ||
+		    ump->softdep_on_worklist == 0,
+		    ("softdep_waitidle: work added after flush"));
+		msleep(&ump->softdep_deps, LOCK_PTR(ump), PVM | PDROP,
+		    "softdeps", 10 * hz);
+		vn_lock(devvp, LK_EXCLUSIVE | LK_RETRY);
+		error = VOP_FSYNC(devvp, MNT_WAIT, td);
+		VOP_UNLOCK(devvp, 0);
+		if (error != 0)
+			break;
+		ACQUIRE_LOCK(ump);
 	}
 	ump->softdep_req = 0;
-	FREE_LOCK(ump);
-	error = 0;
-	if (i == 10) {
+	if (i == SU_WAITIDLE_RETRIES && error == 0 && ump->softdep_deps != 0) {
 		error = EBUSY;
 		printf("softdep_waitidle: Failed to flush worklist for %p\n",
 		    mp);
 	}
-
+	FREE_LOCK(ump);
 	return (error);
 }
 
@@ -1990,7 +2001,7 @@ retry_flush:
 		error = EBUSY;
 	}
 	if (!error)
-		error = softdep_waitidle(oldmnt);
+		error = softdep_waitidle(oldmnt, flags);
 	if (!error) {
 		if (oldmnt->mnt_kern_flag & MNTK_UNMOUNT) {
 			retry = 0;
@@ -2490,9 +2501,18 @@ softdep_mount(devvp, mp, fs, cred)
 	/*
 	 * Start our flushing thread in the bufdaemon process.
 	 */
+	ACQUIRE_LOCK(ump);
+	ump->softdep_flags |= FLUSH_STARTING;
+	FREE_LOCK(ump);
 	kproc_kthread_add(&softdep_flush, mp, &bufdaemonproc,
 	    &ump->softdep_flushtd, 0, 0, "softdepflush", "%s worker",
 	    mp->mnt_stat.f_mntonname);
+	ACQUIRE_LOCK(ump);
+	while ((ump->softdep_flags & FLUSH_STARTING) != 0) {
+		msleep(&ump->softdep_flushtd, LOCK_PTR(ump), PVM, "sdstart",
+		    hz / 2);
+	}
+	FREE_LOCK(ump);
 	/*
 	 * When doing soft updates, the counters in the
 	 * superblock may have gotten out of sync. Recomputation
@@ -7629,17 +7649,13 @@ check_inode_unwritten(inodedep)
 	return (1);
 }
 
-/*
- * Try to free an inodedep structure. Return 1 if it could be freed.
- */
 static int
-free_inodedep(inodedep)
+check_inodedep_free(inodedep)
 	struct inodedep *inodedep;
 {
 
 	LOCK_OWNED(VFSTOUFS(inodedep->id_list.wk_mp));
-	if ((inodedep->id_state & (ONWORKLIST | UNLINKED)) != 0 ||
-	    (inodedep->id_state & ALLCOMPLETE) != ALLCOMPLETE ||
+	if ((inodedep->id_state & ALLCOMPLETE) != ALLCOMPLETE ||
 	    !LIST_EMPTY(&inodedep->id_dirremhd) ||
 	    !LIST_EMPTY(&inodedep->id_pendinghd) ||
 	    !LIST_EMPTY(&inodedep->id_bufwait) ||
@@ -7654,6 +7670,21 @@ free_inodedep(inodedep)
 	    inodedep->id_nlinkdelta != 0 ||
 	    inodedep->id_savedino1 != NULL)
 		return (0);
+	return (1);
+}
+
+/*
+ * Try to free an inodedep structure. Return 1 if it could be freed.
+ */
+static int
+free_inodedep(inodedep)
+	struct inodedep *inodedep;
+{
+
+	LOCK_OWNED(VFSTOUFS(inodedep->id_list.wk_mp));
+	if ((inodedep->id_state & (ONWORKLIST | UNLINKED)) != 0 ||
+	    !check_inodedep_free(inodedep))
+		return (0);
 	if (inodedep->id_state & ONDEPLIST)
 		LIST_REMOVE(inodedep, id_deps);
 	LIST_REMOVE(inodedep, id_hash);
@@ -13838,7 +13869,8 @@ softdep_check_suspend(struct mount *mp,
 {
 	struct bufobj *bo;
 	struct ufsmount *ump;
-	int error;
+	struct inodedep *inodedep;
+	int error, unlinked;
 
 	bo = &devvp->v_bufobj;
 	ASSERT_BO_WLOCKED(bo);
@@ -13899,6 +13931,20 @@ softdep_check_suspend(struct mount *mp,
 		break;
 	}
 
+	unlinked = 0;
+	if (MOUNTEDSUJ(mp)) {
+		for (inodedep = TAILQ_FIRST(&ump->softdep_unlinked);
+		    inodedep != NULL;
+		    inodedep = TAILQ_NEXT(inodedep, id_unlinked)) {
+			if ((inodedep->id_state & (UNLINKED | UNLINKLINKS |
+			    UNLINKONLIST)) != (UNLINKED | UNLINKLINKS |
+			    UNLINKONLIST) ||
+			    !check_inodedep_free(inodedep))
+				continue;
+			unlinked++;
+		}
+	}
+
 	/*
 	 * Reasons for needing more work before suspend:
 	 * - Dirty buffers on devvp.
@@ -13908,8 +13954,8 @@ softdep_check_suspend(struct mount *mp,
 	error = 0;
 	if (bo->bo_numoutput > 0 ||
 	    bo->bo_dirty.bv_cnt > 0 ||
-	    softdep_depcnt != 0 ||
-	    ump->softdep_deps != 0 ||
+	    softdep_depcnt != unlinked ||
+	    ump->softdep_deps != unlinked ||
 	    softdep_accdepcnt != ump->softdep_accdeps ||
 	    secondary_writes != 0 ||
 	    mp->mnt_secondary_writes != 0 ||
Index: sys/ufs/ffs/ffs_vfsops.c
===================================================================
--- sys/ufs/ffs/ffs_vfsops.c	(revision 282245)
+++ sys/ufs/ffs/ffs_vfsops.c	(working copy)
@@ -1502,8 +1502,11 @@ ffs_sync(mp, waitfor)
 	if (fs->fs_fmod != 0 && fs->fs_ronly != 0 && ump->um_fsckpid == 0)
 		panic("%s: ffs_sync: modification on read-only filesystem",
 		    fs->fs_fsmnt);
-	if (waitfor == MNT_LAZY)
-		return (ffs_sync_lazy(mp));
+	if (waitfor == MNT_LAZY) {
+		if (!rebooting)
+			return (ffs_sync_lazy(mp));
+		waitfor = MNT_NOWAIT;
+	}
 
 	/*
 	 * Write back each (modified) inode.
@@ -1560,7 +1563,7 @@ loop:
 	/*
 	 * Force stale filesystem control information to be flushed.
 	 */
-	if (waitfor == MNT_WAIT) {
+	if (waitfor == MNT_WAIT || rebooting) {
 		if ((error = softdep_flushworklist(ump->um_mountp, &count, td)))
 			allerror = error;
 		/* Flushed work items may create new vnodes to clean */
@@ -1577,9 +1580,12 @@ loop:
 	if (bo->bo_numoutput > 0 || bo->bo_dirty.bv_cnt > 0) {
 		BO_UNLOCK(bo);
 		vn_lock(devvp, LK_EXCLUSIVE | LK_RETRY);
-		if ((error = VOP_FSYNC(devvp, waitfor, td)) != 0)
-			allerror = error;
+		error = VOP_FSYNC(devvp, waitfor, td);
 		VOP_UNLOCK(devvp, 0);
+		if (MOUNTEDSOFTDEP(mp) && (error == 0 || error == EAGAIN))
+			error = ffs_sbupdate(ump, waitfor, 0);
+		if (error != 0)
+			allerror = error;
 		if (allerror == 0 && waitfor == MNT_WAIT)
 			goto loop;
 	} else if (suspend != 0) {
Index: sys/ufs/ffs/softdep.h
===================================================================
--- sys/ufs/ffs/softdep.h	(revision 282245)
+++ sys/ufs/ffs/softdep.h	(working copy)
@@ -1063,6 +1063,8 @@ struct mount_softdeps {
  */
 #define FLUSH_EXIT	0x0001	/* time to exit */
 #define FLUSH_CLEANUP	0x0002	/* need to clear out softdep structures */
+#define	FLUSH_STARTING	0x0004	/* flush thread not yet started */
+
 /*
  * Keep the old names from when these were in the ufsmount structure.
  */