v2.4.7.7 -> v2.4.7.8

  - Jeff Hartmann: serverworks AGP gart unload memory leak fix
  - Marcelo Tosatti: make zone_inactive_shortage() return how big the shortage is.
  - Hugh Dickins: tidy up age_page_down()
  - Al Viro: super block handling cleanups

Documentation/DocBook/parportbook.tmpl

@@ -771,6 +771,7 @@ struct parport_driver {
    <funcprototype>
     <funcdef>struct pardevice *<function>parport_open</function></funcdef>
     <paramdef>int <parameter>devnum</parameter></paramdef>
+    <paramdef>const char *<parameter>name</parameter></paramdef>
     <paramdef>int <parameter>(*pf)</parameter>
      <funcparams>void *</funcparams></paramdef>
     <paramdef>int <parameter>(*kf)</parameter>

Makefile

 VERSION = 2
 PATCHLEVEL = 4
 SUBLEVEL = 8
-EXTRAVERSION =-pre7
+EXTRAVERSION =-pre8
 
 KERNELRELEASE=$(VERSION).$(PATCHLEVEL).$(SUBLEVEL)$(EXTRAVERSION)
 

arch/parisc/hpux/sys_hpux.c

@@ -109,9 +109,11 @@ static int hpux_ustat(dev_t dev, struct hpux_ustat *ubuf)
 
 	lock_kernel();
 	s = get_super(to_kdev_t(dev));
+	unlock_kernel();
 	if (s == NULL)
 		goto out;
 	err = vfs_statfs(s, &sbuf);
+	drop_super(s);
 	if (err)
 		goto out;
 
@@ -124,7 +126,6 @@ static int hpux_ustat(dev_t dev, struct hpux_ustat *ubuf)
 	/* Changed to hpux_ustat:  */
 	err = copy_to_user(ubuf,&tmp,sizeof(struct hpux_ustat)) ? -EFAULT : 0;
 out:
-	unlock_kernel();
 	return err;
 }
 

drivers/char/agp/agpgart_be.c

@@ -2375,6 +2375,7 @@ static int serverworks_free_gatt_table(void)
 
 	serverworks_free_gatt_pages();
 	serverworks_free_page_map(&page_dir);
+	serverworks_free_page_map(&serverworks_private.scratch_dir);
 	return 0;
 }
 

drivers/char/drm/Makefile

@@ -3,9 +3,7 @@
 # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher.
 
 O_TARGET	:= drm.o
-export-objs	:= gamma_drv.o tdfx_drv.o r128_drv.o mga_drv.o i810_drv.o \
-		   ffb_drv.o
-list-multi	:= gamma.o tdfx.o r128.o mga.o i810.o ffb.o
+list-multi	:= gamma.o tdfx.o r128.o mga.o i810.o radeon.o ffb.o
 
 gamma-objs  := gamma_drv.o gamma_dma.o
 tdfx-objs   := tdfx_drv.o

fs/block_dev.c

@@ -678,8 +678,10 @@ int blkdev_put(struct block_device *bdev, int kind)
 	down(&bdev->bd_sem);
 	/* syncing will go here */
 	lock_kernel();
-	if (kind == BDEV_FILE || kind == BDEV_FS)
+	if (kind == BDEV_FILE)
 		fsync_dev(rdev);
+	else if (kind == BDEV_FS)
+		fsync_no_super(rdev);
 	if (atomic_dec_and_test(&bdev->bd_openers)) {
 		/* invalidating buffers will go here */
 		invalidate_buffers(rdev);

fs/buffer.c

@@ -346,6 +346,12 @@ int fsync_super(struct super_block *sb)
 	return sync_buffers(dev, 1);
 }
 
+int fsync_no_super(kdev_t dev)
+{
+	sync_buffers(dev, 0);
+	return sync_buffers(dev, 1);
+}
+
 int fsync_dev(kdev_t dev)
 {
 	sync_buffers(dev, 0);

fs/dquot.c

@@ -1597,6 +1597,8 @@ asmlinkage long sys_quotactl(int cmd, const char *special, int id, caddr_t addr)
 	if (sb && sb_has_quota_enabled(sb, type))
 		ret = set_dqblk(sb, id, type, flags, (struct dqblk *) addr);
 out:
+	if (sb)
+		drop_super(sb);
 	unlock_kernel();
 	return ret;
 }

fs/inode.c

@@ -258,23 +258,6 @@ static inline void sync_list(struct list_head *head)
 		__sync_one(list_entry(tmp, struct inode, i_list), 0);
 }
 
-static inline int wait_on_dirty(struct list_head *head)
-{
-	struct list_head * tmp;
-	list_for_each(tmp, head) {
-		struct inode *inode = list_entry(tmp, struct inode, i_list);
-		if (!inode->i_state & I_DIRTY)
-			continue;
-		__iget(inode);
-		spin_unlock(&inode_lock);
-		__wait_on_inode(inode);
-		iput(inode);
-		spin_lock(&inode_lock);
-		return 1;
-	}
-	return 0;
-}
-
 static inline void wait_on_locked(struct list_head *head)
 {
 	struct list_head * tmp;
@@ -319,61 +302,96 @@ static inline int try_to_sync_unused_list(struct list_head *head)
 	return 1;
 }
 
-/**
- *	sync_inodes
- *	@dev: device to sync the inodes from.
- *
- *	sync_inodes goes through the super block's dirty list, 
- *	writes them out, and puts them back on the normal list.
- */
-
-/*
- * caller holds exclusive lock on sb->s_umount
- */
- 
 void sync_inodes_sb(struct super_block *sb)
 {
 	spin_lock(&inode_lock);
-	sync_list(&sb->s_dirty);
-	wait_on_locked(&sb->s_locked_inodes);
+	while (!list_empty(&sb->s_dirty)||!list_empty(&sb->s_locked_inodes)) {
+		sync_list(&sb->s_dirty);
+		wait_on_locked(&sb->s_locked_inodes);
+	}
 	spin_unlock(&inode_lock);
 }
 
+/*
+ * Note:
+ * We don't need to grab a reference to superblock here. If it has non-empty
+ * ->s_dirty it's hadn't been killed yet and kill_super() won't proceed
+ * past sync_inodes_sb() until both ->s_dirty and ->s_locked_inodes are
+ * empty. Since __sync_one() regains inode_lock before it finally moves
+ * inode from superblock lists we are OK.
+ */
+
 void sync_unlocked_inodes(void)
 {
-	struct super_block * sb = sb_entry(super_blocks.next);
+	struct super_block * sb;
+	spin_lock(&inode_lock);
+	spin_lock(&sb_lock);
+	sb = sb_entry(super_blocks.next);
 	for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.next)) {
 		if (!list_empty(&sb->s_dirty)) {
-			spin_lock(&inode_lock);
+			spin_unlock(&sb_lock);
 			sync_list(&sb->s_dirty);
-			spin_unlock(&inode_lock);
+			spin_lock(&sb_lock);
+		}
+	}
+	spin_unlock(&sb_lock);
+	spin_unlock(&inode_lock);
+}
+
+/*
+ * Find a superblock with inodes that need to be synced
+ */
+
+static struct super_block *get_super_to_sync(void)
+{
+	struct list_head *p;
+restart:
+	spin_lock(&inode_lock);
+	spin_lock(&sb_lock);
+	list_for_each(p, &super_blocks) {
+		struct super_block *s = list_entry(p,struct super_block,s_list);
+		if (list_empty(&s->s_dirty) && list_empty(&s->s_locked_inodes))
+			continue;
+		s->s_count++;
+		spin_unlock(&sb_lock);
+		spin_unlock(&inode_lock);
+		down_read(&s->s_umount);
+		if (!s->s_root) {
+			drop_super(s);
+			goto restart;
 		}
+		return s;
 	}
+	spin_unlock(&sb_lock);
+	spin_unlock(&inode_lock);
+	return NULL;
 }
 
+/**
+ *	sync_inodes
+ *	@dev: device to sync the inodes from.
+ *
+ *	sync_inodes goes through the super block's dirty list, 
+ *	writes them out, and puts them back on the normal list.
+ */
+
 void sync_inodes(kdev_t dev)
 {
-	struct super_block * sb = sb_entry(super_blocks.next);
+	struct super_block * s;
 
 	/*
 	 * Search the super_blocks array for the device(s) to sync.
 	 */
-	for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.next)) {
-		if (!sb->s_dev)
-			continue;
-		if (dev && sb->s_dev != dev)
-			continue;
-		down_read(&sb->s_umount);
-		if (sb->s_dev && (sb->s_dev == dev || !dev)) {
-			spin_lock(&inode_lock);
-			do {
-				sync_list(&sb->s_dirty);
-			} while (wait_on_dirty(&sb->s_locked_inodes));
-			spin_unlock(&inode_lock);
+	if (dev) {
+		if ((s = get_super(dev)) != NULL) {
+			sync_inodes_sb(s);
+			drop_super(s);
+		}
+	} else {
+		while ((s = get_super_to_sync()) != NULL) {
+			sync_inodes_sb(s);
+			drop_super(s);
 		}
-		up_read(&sb->s_umount);
-		if (dev)
-			break;
 	}
 }
 
@@ -382,13 +400,19 @@ void sync_inodes(kdev_t dev)
  */
 static void try_to_sync_unused_inodes(void)
 {
-	struct super_block * sb = sb_entry(super_blocks.next);
+	struct super_block * sb;
+
+	spin_lock(&sb_lock);
+	sb = sb_entry(super_blocks.next);
 	for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.next)) {
 		if (!sb->s_dev)
 			continue;
+		spin_unlock(&sb_lock);
 		if (!try_to_sync_unused_list(&sb->s_dirty))
-			break;
+			return;
+		spin_lock(&sb_lock);
 	}
+	spin_unlock(&sb_lock);
 }
 
 /**
@@ -598,15 +622,18 @@ int invalidate_inodes(struct super_block * sb)
  
 int invalidate_device(kdev_t dev, int do_sync)
 {
-	struct super_block *sb = get_super(dev);
+	struct super_block *sb;
 	int res;
 
 	if (do_sync)
 		fsync_dev(dev);
 
 	res = 0;
-	if (sb)
+	sb = get_super(dev);
+	if (sb) {
 		res = invalidate_inodes(sb);
+		drop_super(sb);
+	}
 	invalidate_buffers(dev);
 	return res;
 }

fs/super.c

@@ -59,9 +59,8 @@ static int do_remount_sb(struct super_block *sb, int flags, char * data);
 /* this is initialized in init/main.c */
 kdev_t ROOT_DEV;
 
-int nr_super_blocks;
-int max_super_blocks = NR_SUPER;
 LIST_HEAD(super_blocks);
+spinlock_t sb_lock = SPIN_LOCK_UNLOCKED;
 
 /*
  * Handling of filesystem drivers list.
@@ -386,7 +385,6 @@ static struct vfsmount *add_vfsmnt(struct dentry *root, const char *dev_name)
 	mnt->mnt_parent = mnt;
 
 	spin_lock(&dcache_lock);
-	list_add(&mnt->mnt_instances, &sb->s_mounts);
 	list_add(&mnt->mnt_list, vfsmntlist.prev);
 	spin_unlock(&dcache_lock);
 	if (sb->s_type->fs_flags & FS_SINGLE)
@@ -395,10 +393,11 @@ static struct vfsmount *add_vfsmnt(struct dentry *root, const char *dev_name)
 	return mnt;
 }
 
-static struct vfsmount *clone_mnt(struct vfsmount *old_mnt, struct dentry *root)
+static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root)
 {
-	char *name = old_mnt->mnt_devname;
+	char *name = old->mnt_devname;
 	struct vfsmount *mnt = alloc_vfsmnt();
+	struct super_block *sb = old->mnt_sb;
 
 	if (!mnt)
 		goto out;
@@ -408,14 +407,12 @@ static struct vfsmount *clone_mnt(struct vfsmount *old_mnt, struct dentry *root)
 		if (mnt->mnt_devname)
 			strcpy(mnt->mnt_devname, name);
 	}
-	mnt->mnt_sb = old_mnt->mnt_sb;
+	mnt->mnt_sb = sb;
 	mnt->mnt_root = dget(root);
 	mnt->mnt_mountpoint = mnt->mnt_root;
 	mnt->mnt_parent = mnt;
 
-	spin_lock(&dcache_lock);
-	list_add(&mnt->mnt_instances, &old_mnt->mnt_instances);
-	spin_unlock(&dcache_lock);
+	atomic_inc(&sb->s_active);
 out:
 	return mnt;
 }
@@ -487,16 +484,12 @@ void __mntput(struct vfsmount *mnt)
 	struct super_block *sb = mnt->mnt_sb;
 
 	dput(mnt->mnt_root);
-	spin_lock(&dcache_lock);
-	list_del(&mnt->mnt_instances);
-	spin_unlock(&dcache_lock);
 	if (mnt->mnt_devname)
 		kfree(mnt->mnt_devname);
 	kmem_cache_free(mnt_cache, mnt);
 	kill_super(sb);
 }
 
-
 /* Use octal escapes, like mount does, for embedded spaces etc. */
 static unsigned char need_escaping[] = { ' ', '\t', '\n', '\\' };
 
@@ -645,6 +638,49 @@ int get_filesystem_info( char *buf )
 #undef MANGLE
 #undef FREEROOM
 }
+
+static inline void __put_super(struct super_block *sb)
+{
+	spin_lock(&sb_lock);
+	if (!--sb->s_count)
+		kfree(sb);
+	spin_unlock(&sb_lock);
+}
+
+static inline struct super_block * find_super(kdev_t dev)
+{
+	struct list_head *p;
+
+	list_for_each(p, &super_blocks) {
+		struct super_block * s = sb_entry(p);
+		if (s->s_dev == dev) {
+			s->s_count++;
+			return s;
+		}
+	}
+	return NULL;
+}
+
+void drop_super(struct super_block *sb)
+{
+	up_read(&sb->s_umount);
+	__put_super(sb);
+}
+
+static void put_super(struct super_block *sb)
+{
+	up_write(&sb->s_umount);
+	__put_super(sb);
+}
+
+static inline void write_super(struct super_block *sb)
+{
+	lock_super(sb);
+	if (sb->s_root && sb->s_dirt)
+		if (sb->s_op && sb->s_op->write_super)
+			sb->s_op->write_super(sb);
+	unlock_super(sb);
+}
  
 /*
  * Note: check the dirty flag before waiting, so we don't
@@ -655,21 +691,29 @@ void sync_supers(kdev_t dev)
 {
 	struct super_block * sb;
 
-	for (sb = sb_entry(super_blocks.next);
-	     sb != sb_entry(&super_blocks); 
-	     sb = sb_entry(sb->s_list.next)) {
-		if (!sb->s_dev)
-			continue;
-		if (dev && sb->s_dev != dev)
-			continue;
-		if (!sb->s_dirt)
-			continue;
-		lock_super(sb);
-		if (sb->s_dev && sb->s_dirt && (!dev || dev == sb->s_dev))
-			if (sb->s_op && sb->s_op->write_super)
-				sb->s_op->write_super(sb);
-		unlock_super(sb);
+	if (dev) {
+		sb = get_super(dev);
+		if (sb) {
+			if (sb->s_dirt)
+				write_super(sb);
+			drop_super(sb);
+		}
+		return;
 	}
+restart:
+	spin_lock(&sb_lock);
+	sb = sb_entry(super_blocks.next);
+	while (sb != sb_entry(&super_blocks))
+		if (sb->s_dirt) {
+			sb->s_count++;
+			spin_unlock(&sb_lock);
+			down_read(&sb->s_umount);
+			write_super(sb);
+			drop_super(sb);
+			goto restart;
+		} else
+			sb = sb_entry(sb->s_list.next);
+	spin_unlock(&sb_lock);
 }
 
 /**
@@ -687,17 +731,21 @@ struct super_block * get_super(kdev_t dev)
 	if (!dev)
 		return NULL;
 restart:
-	s = sb_entry(super_blocks.next);
-	while (s != sb_entry(&super_blocks))
-		if (s->s_dev == dev) {
-			/* Yes, it sucks. As soon as we get refcounting... */
-			lock_super(s);
-			unlock_super(s);
-			if (s->s_dev == dev)
-				return s;
-			goto restart;
-		} else
-			s = sb_entry(s->s_list.next);
+	spin_lock(&sb_lock);
+	s = find_super(dev);
+	if (s) {
+		spin_unlock(&sb_lock);
+		/* Yes, it sucks. As soon as we get refcounting... */
+		/* Almost there - next two lines will go away RSN */
+		lock_super(s);
+		unlock_super(s);
+		down_read(&s->s_umount);
+		if (s->s_root)
+			return s;
+		drop_super(s);
+		goto restart;
+	}
+	spin_unlock(&sb_lock);
 	return NULL;
 }
 
@@ -714,6 +762,7 @@ asmlinkage long sys_ustat(dev_t dev, struct ustat * ubuf)
         if (s == NULL)
                 goto out;
 	err = vfs_statfs(s, &sbuf);
+	drop_super(s);
 	if (err)
 		goto out;
 
@@ -735,35 +784,23 @@ asmlinkage long sys_ustat(dev_t dev, struct ustat * ubuf)
  *	the request.
  */
  
-static struct super_block *get_empty_super(void)
+static struct super_block *alloc_super(void)
 {
-	struct super_block *s;
-
-	for (s  = sb_entry(super_blocks.next);
-	     s != sb_entry(&super_blocks); 
-	     s  = sb_entry(s->s_list.next)) {
-		if (s->s_dev)
-			continue;
-		return s;
-	}
-	/* Need a new one... */
-	if (nr_super_blocks >= max_super_blocks)
-		return NULL;
-	s = kmalloc(sizeof(struct super_block),  GFP_USER);
+	struct super_block *s = kmalloc(sizeof(struct super_block),  GFP_USER);
 	if (s) {
-		nr_super_blocks++;
 		memset(s, 0, sizeof(struct super_block));
 		INIT_LIST_HEAD(&s->s_dirty);
 		INIT_LIST_HEAD(&s->s_locked_inodes);
-		list_add (&s->s_list, super_blocks.prev);
 		INIT_LIST_HEAD(&s->s_files);
-		INIT_LIST_HEAD(&s->s_mounts);
 		init_rwsem(&s->s_umount);
 		sema_init(&s->s_lock, 1);
+		s->s_count = 1;
+		atomic_set(&s->s_active, 1);
 		sema_init(&s->s_vfs_rename_sem,1);
 		sema_init(&s->s_nfsd_free_path_sem,1);
 		sema_init(&s->s_dquot.dqio_sem, 1);
 		sema_init(&s->s_dquot.dqoff_sem, 1);
+		s->s_maxbytes = MAX_NON_LFS;
 	}
 	return s;
 }
@@ -773,16 +810,16 @@ static struct super_block * read_super(kdev_t dev, struct block_device *bdev,
 				       void *data, int silent)
 {
 	struct super_block * s;
-	s = get_empty_super();
+	s = alloc_super();
 	if (!s)
 		goto out;
 	s->s_dev = dev;
 	s->s_bdev = bdev;
 	s->s_flags = flags;
-	s->s_dirt = 0;
 	s->s_type = type;
-	s->s_dquot.flags = 0;
-	s->s_maxbytes = MAX_NON_LFS;
+	spin_lock(&sb_lock);
+	list_add (&s->s_list, super_blocks.prev);
+	spin_unlock(&sb_lock);
 	lock_super(s);
 	if (!type->read_super(s, data, silent))
 		goto out_fail;
@@ -798,6 +835,11 @@ static struct super_block * read_super(kdev_t dev, struct block_device *bdev,
 	s->s_bdev = 0;
 	s->s_type = NULL;
 	unlock_super(s);
+	atomic_dec(&s->s_active);
+	spin_lock(&sb_lock);
+	list_del(&s->s_list);
+	spin_unlock(&sb_lock);
+	__put_super(s);
 	return NULL;
 }
 
@@ -863,9 +905,25 @@ static struct super_block *get_sb_bdev(struct file_system_type *fs_type,
 	if (sb) {
 		if (fs_type == sb->s_type &&
 		    ((flags ^ sb->s_flags) & MS_RDONLY) == 0) {
+/*
+ * We are heavily relying on mount_sem here. We _will_ get rid of that
+ * ugliness RSN (and then atomicity of ->s_active will play), but first
+ * we need to get rid of "reuse" branch of get_empty_super() and that
+ * requires reference counters. Chicken and egg problem, but fortunately
+ * we can use the fact that right now all accesses to ->s_active are
+ * under mount_sem.
+ */
+			if (atomic_read(&sb->s_active)) {
+				spin_lock(&sb_lock);
+				sb->s_count--;
+				spin_unlock(&sb_lock);
+			}
+			atomic_inc(&sb->s_active);
+			up_read(&sb->s_umount);
 			path_release(&nd);
 			return sb;
 		}
+		drop_super(sb);
 	} else {
 		mode_t mode = FMODE_READ; /* we always need it ;-) */
 		if (!(flags & MS_RDONLY))
@@ -926,6 +984,7 @@ static struct super_block *get_sb_single(struct file_system_type *fs_type,
 	sb = fs_type->kern_mnt->mnt_sb;
 	if (!sb)
 		BUG();
+	atomic_inc(&sb->s_active);
 	do_remount_sb(sb, flags, data);
 	return sb;
 }
@@ -938,12 +997,8 @@ static void kill_super(struct super_block *sb)
 	struct file_system_type *fs = sb->s_type;
 	struct super_operations *sop = sb->s_op;
 
-	spin_lock(&dcache_lock);
-	if (!list_empty(&sb->s_mounts)) {
-		spin_unlock(&dcache_lock);
+	if (!atomic_dec_and_test(&sb->s_active))
 		return;
-	}
-	spin_unlock(&dcache_lock);
 	down_write(&sb->s_umount);
 	lock_kernel();
 	sb->s_root = NULL;
@@ -975,12 +1030,15 @@ static void kill_super(struct super_block *sb)
 	sb->s_type = NULL;
 	unlock_super(sb);
 	unlock_kernel();
-	up_write(&sb->s_umount);
 	if (bdev) {
 		blkdev_put(bdev, BDEV_FS);
 		bdput(bdev);
 	} else
 		put_unnamed_dev(dev);
+	spin_lock(&sb_lock);
+	list_del(&sb->s_list);
+	spin_unlock(&sb_lock);
+	put_super(sb);
 }
 
 /*
@@ -1045,9 +1103,6 @@ struct vfsmount *kern_mount(struct file_system_type *type)
 	mnt->mnt_root = dget(sb->s_root);
 	mnt->mnt_mountpoint = mnt->mnt_root;
 	mnt->mnt_parent = mnt;
-	spin_lock(&dcache_lock);
-	list_add(&mnt->mnt_instances, &sb->s_mounts);
-	spin_unlock(&dcache_lock);
 	type->kern_mnt = mnt;
 	return mnt;
 }
@@ -1092,7 +1147,7 @@ static int do_umount(struct vfsmount *mnt, int flags)
 
 	spin_lock(&dcache_lock);
 
-	if (mnt->mnt_instances.next != mnt->mnt_instances.prev) {
+	if (atomic_read(&sb->s_active) > 1) {
 		if (atomic_read(&mnt->mnt_count) > 2) {
 			spin_unlock(&dcache_lock);
 			return -EBUSY;
@@ -1324,9 +1379,6 @@ static int do_add_mount(struct nameidata *nd, char *type, int flags,
 	mnt->mnt_root = dget(sb->s_root);
 	mnt->mnt_mountpoint = mnt->mnt_root;
 	mnt->mnt_parent = mnt;
-	spin_lock(&dcache_lock);
-	list_add(&mnt->mnt_instances, &sb->s_mounts);
-	spin_unlock(&dcache_lock);
 
 	/* Something was mounted here while we slept */
 	while(d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry))
@@ -1583,7 +1635,10 @@ void __init mount_root(void)
 	check_disk_change(ROOT_DEV);
 	sb = get_super(ROOT_DEV);
 	if (sb) {
+		/* FIXME */
 		fs_type = sb->s_type;
+		atomic_inc(&sb->s_active);
+		up_read(&sb->s_umount);
 		goto mount_it;
 	}
 

include/asm-ppc/processor.h

@@ -631,7 +631,7 @@ struct thread_struct {
 #define INIT_THREAD  { \
 	INIT_SP, /* ksp */ \
 	0, /* wchan */ \
-	(struct pt_regs *)INIT_SP - 1, /* regs */ \
+	0, /* regs */ \
 	KERNEL_DS, /*fs*/ \
 	swapper_pg_dir, /* pgdir */ \
 	0, /* last_syscall */ \
@@ -659,8 +659,8 @@ static inline unsigned long thread_saved_pc(struct thread_struct *t)
 
 unsigned long get_wchan(struct task_struct *p);
 
-#define KSTK_EIP(tsk)  ((tsk)->thread.regs->nip)
-#define KSTK_ESP(tsk)  ((tsk)->thread.regs->gpr[1])
+#define KSTK_EIP(tsk)  ((tsk)->thread.regs? (tsk)->thread.regs->nip: 0)
+#define KSTK_ESP(tsk)  ((tsk)->thread.regs? (tsk)->thread.regs->gpr[1]: 0)
 
 /*
  * NOTE! The task struct and the stack go together

include/linux/fs.h

@@ -61,7 +61,6 @@ struct inodes_stat_t {
 };
 extern struct inodes_stat_t inodes_stat;
 
-extern int max_super_blocks, nr_super_blocks;
 extern int leases_enable, dir_notify_enable, lease_break_time;
 
 #define NR_FILE  8192	/* this can well be larger on a larger system */
@@ -663,6 +662,7 @@ struct quota_mount_options
 #include <linux/cramfs_fs_sb.h>
 
 extern struct list_head super_blocks;
+extern spinlock_t sb_lock;
 
 #define sb_entry(list)	list_entry((list), struct super_block, s_list)
 struct super_block {
@@ -680,13 +680,14 @@ struct super_block {
 	struct dentry		*s_root;
 	struct rw_semaphore	s_umount;
 	struct semaphore	s_lock;
+	int			s_count;
+	atomic_t		s_active;
 
 	struct list_head	s_dirty;	/* dirty inodes */
 	struct list_head	s_locked_inodes;/* inodes being synced */
 	struct list_head	s_files;
 
 	struct block_device	*s_bdev;
-	struct list_head	s_mounts;	/* vfsmount(s) of this one */
 	struct quota_mount_options s_dquot;	/* Diskquota specific options */
 
 	union {
@@ -1161,6 +1162,7 @@ extern void write_inode_now(struct inode *, int);
 extern void sync_dev(kdev_t);
 extern int fsync_dev(kdev_t);
 extern int fsync_super(struct super_block *);
+extern int fsync_no_super(kdev_t);
 extern void sync_inodes_sb(struct super_block *);
 extern int fsync_inode_buffers(struct inode *);
 extern int osync_inode_buffers(struct inode *);
@@ -1358,11 +1360,12 @@ extern int dcache_readdir(struct file *, void *, filldir_t);
 
 extern struct file_system_type *get_fs_type(const char *name);
 extern struct super_block *get_super(kdev_t);
+extern void drop_super(struct super_block *sb);
 static inline int is_mounted(kdev_t dev)
 {
 	struct super_block *sb = get_super(dev);
 	if (sb) {
-		/* drop_super(sb); will go here */
+		drop_super(sb);
 		return 1;
 	}
 	return 0;

include/linux/mount.h

@@ -18,7 +18,6 @@ struct vfsmount
 	struct vfsmount *mnt_parent;	/* fs we are mounted on */
 	struct dentry *mnt_mountpoint;	/* dentry of mountpoint */
 	struct dentry *mnt_root;	/* root of the mounted tree */
-	struct list_head mnt_instances;	/* other vfsmounts of the same fs */
 	struct super_block *mnt_sb;	/* pointer to superblock */
 	struct list_head mnt_mounts;	/* list of children, anchored here */
 	struct list_head mnt_child;	/* and going through their mnt_child */

include/linux/pagemap.h

@@ -72,7 +72,9 @@ static inline unsigned long _page_hashfn(struct address_space * mapping, unsigne
 #define page_hash(mapping,index) (page_hash_table+_page_hashfn(mapping,index))
 
 extern struct page * __find_get_page(struct address_space *mapping,
-				     unsigned long offset, struct page **hash);
+				unsigned long index, struct page **hash);
+#define find_get_page(mapping, index) \
+	__find_get_page(mapping, index, page_hash(mapping, index))
 extern struct page * __find_lock_page (struct address_space * mapping,
 				unsigned long index, struct page **hash);
 extern void lock_page(struct page *page);

include/linux/swap.h

@@ -100,9 +100,6 @@ struct zone_t;
 
 /* linux/mm/swap.c */
 extern int memory_pressure;
-extern void age_page_down(struct page *);
-extern void age_page_down_nolock(struct page *);
-extern void age_page_down_ageonly(struct page *);
 extern void deactivate_page(struct page *);
 extern void deactivate_page_nolock(struct page *);
 extern void activate_page(struct page *);

kernel/ksyms.c

@@ -128,6 +128,7 @@ EXPORT_SYMBOL(def_blk_fops);
 EXPORT_SYMBOL(update_atime);
 EXPORT_SYMBOL(get_fs_type);
 EXPORT_SYMBOL(get_super);
+EXPORT_SYMBOL(drop_super);
 EXPORT_SYMBOL(getname);
 EXPORT_SYMBOL(names_cachep);
 EXPORT_SYMBOL(fput);
@@ -244,6 +245,7 @@ EXPORT_SYMBOL(generic_read_dir);
 EXPORT_SYMBOL(__pollwait);
 EXPORT_SYMBOL(poll_freewait);
 EXPORT_SYMBOL(ROOT_DEV);
+EXPORT_SYMBOL(__find_get_page);
 EXPORT_SYMBOL(__find_lock_page);
 EXPORT_SYMBOL(grab_cache_page);
 EXPORT_SYMBOL(read_cache_page);

kernel/sysctl.c

@@ -286,10 +286,6 @@ static ctl_table fs_table[] = {
 	 0444, NULL, &proc_dointvec},
 	{FS_MAXFILE, "file-max", &files_stat.max_files, sizeof(int),
 	 0644, NULL, &proc_dointvec},
-	{FS_NRSUPER, "super-nr", &nr_super_blocks, sizeof(int),
-	 0444, NULL, &proc_dointvec},
-	{FS_MAXSUPER, "super-max", &max_super_blocks, sizeof(int),
-	 0644, NULL, &proc_dointvec},
 	{FS_NRDQUOT, "dquot-nr", &nr_dquots, 2*sizeof(int),
 	 0444, NULL, &proc_dointvec},
 	{FS_MAXDQUOT, "dquot-max", &max_dquots, sizeof(int),

mm/shmem.c

@@ -402,7 +402,7 @@ static int shmem_getpage(struct inode * inode, unsigned long idx, struct page **
 	int error;
 
 	down (&inode->i_sem);
-	if (inode->i_size < (loff_t) idx * PAGE_CACHE_SIZE)
+	if (inode->i_size <= (loff_t) idx * PAGE_CACHE_SIZE)
 		goto sigbus;
 	*ptr = shmem_getpage_locked(inode, idx);
 	if (IS_ERR (*ptr))

mm/swap.c

@@ -74,42 +74,6 @@ pager_daemon_t pager_daemon = {
 	8,	/* do swap I/O in clusters of this size */
 };
 
-/*
- * We use this (minimal) function in the case where we
- * know we can't deactivate the page (yet).
- */
-void age_page_down_ageonly(struct page * page)
-{
-	page->age /= 2;
-}
-
-void age_page_down_nolock(struct page * page)
-{
-	/* The actual page aging bit */
-	page->age /= 2;
-
-	/*
-	 * The page is now an old page. Move to the inactive
-	 * list (if possible ... see below).
-	 */
-	if (!page->age)
-	       deactivate_page_nolock(page);
-}
-
-void age_page_down(struct page * page)
-{
-	/* The actual page aging bit */
-	page->age /= 2;
-
-	/*
-	 * The page is now an old page. Move to the inactive
-	 * list (if possible ... see below).
-	 */
-	if (!page->age)
-	       deactivate_page(page);
-}
-
-
 /**
  * (de)activate_page - move pages from/to active and inactive lists
  * @page: the page we want to move

mm/vmscan.c

@@ -26,6 +26,19 @@
 
 #define MAX(a,b) ((a) > (b) ? (a) : (b))
 
+static inline void age_page_up(struct page *page)
+{
+	unsigned age = page->age + PAGE_AGE_ADV;
+	if (age > PAGE_AGE_MAX)
+		age = PAGE_AGE_MAX;
+	page->age = age;
+}
+
+static inline void age_page_down(struct page * page)
+{
+	page->age /= 2;
+}
+
 /*
  * The swap-out function returns 1 if it successfully
  * scanned all the pages it was asked to (`count').
@@ -54,16 +67,19 @@ static unsigned int zone_inactive_plenty(zone_t *zone)
 
 static unsigned int zone_inactive_shortage(zone_t *zone) 
 {
-	unsigned int inactive;
+	unsigned int sum;
 
 	if (!zone->size)
 		return 0;
 
-	inactive = zone->inactive_dirty_pages;
-	inactive += zone->inactive_clean_pages;
-	inactive += zone->free_pages;
-
-	return inactive < zone->pages_high;
+	sum = zone->pages_high;
+	sum -= zone->inactive_dirty_pages;
+	sum -= zone->inactive_clean_pages;
+	sum -= zone->free_pages;
+	
+	if (sum > 0)
+		return sum;
+	return 0;
 }
 
 static unsigned int zone_free_plenty(zone_t *zone)
@@ -103,9 +119,7 @@ static void try_to_swap_out(struct mm_struct * mm, struct vm_area_struct* vma, u
 
 	/* Don't look at this pte if it's been accessed recently. */
 	if (ptep_test_and_clear_young(page_table)) {
-		page->age += PAGE_AGE_ADV;
-		if (page->age > PAGE_AGE_MAX)
-			page->age = PAGE_AGE_MAX;
+		age_page_up(page);
 		return;
 	}
 
@@ -700,15 +714,6 @@ int page_launder(int gfp_mask, int sync)
 	return cleaned_pages;
 }
 
-static inline void age_page_up(struct page *page)
-{
-	unsigned age = page->age + PAGE_AGE_ADV;
-	if (age > PAGE_AGE_MAX)
-		age = PAGE_AGE_MAX;
-	page->age = age;
-}
-
-
 /**
  * refill_inactive_scan - scan the active list and find pages to deactivate
  * @priority: the priority at which to scan
@@ -760,7 +765,7 @@ int refill_inactive_scan(zone_t *zone, unsigned int priority, int target)
 			age_page_up(page);
 			page_active = 1;
 		} else {
-			age_page_down_ageonly(page);
+			age_page_down(page);
 			/*
 			 * Since we don't hold a reference on the page
 			 * ourselves, we have to do our test a bit more