4.0.9-stable review

@@ -1093,3 +1093,99 @@ simple_nosetlease(struct file *filp, lon
 	return -EINVAL;
 }
 EXPORT_SYMBOL(simple_nosetlease);
+
+
+/*
+ * Operations for a permanently empty directory.
+ */
+static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
+	return ERR_PTR(-ENOENT);
+}
+
+static int empty_dir_getattr(struct vfsmount *mnt, struct dentry *dentry,
+				 struct kstat *stat)
+{
+	struct inode *inode = d_inode(dentry);
+	generic_fillattr(inode, stat);
+	return 0;
+}
+
+static int empty_dir_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	return -EPERM;
+}
+
+static int empty_dir_setxattr(struct dentry *dentry, const char *name,
+			      const void *value, size_t size, int flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static ssize_t empty_dir_getxattr(struct dentry *dentry, const char *name,
+				  void *value, size_t size)
+{
+	return -EOPNOTSUPP;
+}
+
+static int empty_dir_removexattr(struct dentry *dentry, const char *name)
+{
+	return -EOPNOTSUPP;
+}
+
+static ssize_t empty_dir_listxattr(struct dentry *dentry, char *list, size_t size)
+{
+	return -EOPNOTSUPP;
+}
+
+static const struct inode_operations empty_dir_inode_operations = {
+	.lookup		= empty_dir_lookup,
+	.permission	= generic_permission,
+	.setattr	= empty_dir_setattr,
+	.getattr	= empty_dir_getattr,
+	.setxattr	= empty_dir_setxattr,
+	.getxattr	= empty_dir_getxattr,
+	.removexattr	= empty_dir_removexattr,
+	.listxattr	= empty_dir_listxattr,
+};
+
+static loff_t empty_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+	/* An empty directory has two entries . and .. at offsets 0 and 1 */
+	return generic_file_llseek_size(file, offset, whence, 2, 2);
+}
+
+static int empty_dir_readdir(struct file *file, struct dir_context *ctx)
+{
+	dir_emit_dots(file, ctx);
+	return 0;
+}
+
+static const struct file_operations empty_dir_operations = {
+	.llseek		= empty_dir_llseek,
+	.read		= generic_read_dir,
+	.iterate	= empty_dir_readdir,
+	.fsync		= noop_fsync,
+};
+
+
+void make_empty_dir_inode(struct inode *inode)
+{
+	set_nlink(inode, 2);
+	inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	inode->i_uid = GLOBAL_ROOT_UID;
+	inode->i_gid = GLOBAL_ROOT_GID;
+	inode->i_rdev = 0;
+	inode->i_size = 2;
+	inode->i_blkbits = PAGE_SHIFT;
+	inode->i_blocks = 0;
+
+	inode->i_op = &empty_dir_inode_operations;
+	inode->i_fop = &empty_dir_operations;
+}
+
+bool is_empty_dir_inode(struct inode *inode)
+{
+	return (inode->i_fop == &empty_dir_operations) &&
+		(inode->i_op == &empty_dir_inode_operations);
+}

@@ -2721,6 +2721,8 @@ extern struct dentry *simple_lookup(stru
 extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
 extern const struct file_operations simple_dir_operations;
 extern const struct inode_operations simple_dir_inode_operations;
+extern void make_empty_dir_inode(struct inode *inode);
+extern bool is_empty_dir_inode(struct inode *inode);
 struct tree_descr { char *name; const struct file_operations *ops; int mode; };
 struct dentry *d_alloc_name(struct dentry *, const char *);
 extern int simple_fill_super(struct super_block *, unsigned long, struct tree_descr *);

@@ -19,6 +19,28 @@ static const struct inode_operations pro
 static const struct file_operations proc_sys_dir_file_operations;
 static const struct inode_operations proc_sys_dir_operations;
 
+/* Support for permanently empty directories */
+
+struct ctl_table sysctl_mount_point[] = {
+	{ }
+};
+
+static bool is_empty_dir(struct ctl_table_header *head)
+{
+	return head->ctl_table[0].child == sysctl_mount_point;
+}
+
+static void set_empty_dir(struct ctl_dir *dir)
+{
+	dir->header.ctl_table[0].child = sysctl_mount_point;
+}
+
+static void clear_empty_dir(struct ctl_dir *dir)
+
+{
+	dir->header.ctl_table[0].child = NULL;
+}
+
 void proc_sys_poll_notify(struct ctl_table_poll *poll)
 {
 	if (!poll)

@@ -187,6 +209,17 @@ static int insert_header(struct ctl_dir
 	struct ctl_table *entry;
 	int err;
 
+	/* Is this a permanently empty directory? */
+	if (is_empty_dir(&dir->header))
+		return -EROFS;
+
+	/* Am I creating a permanently empty directory? */
+	if (header->ctl_table == sysctl_mount_point) {
+		if (!RB_EMPTY_ROOT(&dir->root))
+			return -EINVAL;
+		set_empty_dir(dir);
+	}
+
 	dir->header.nreg++;
 	header->parent = dir;
 	err = insert_links(header);

@@ -202,6 +235,8 @@ fail:
 	erase_header(header);
 	put_links(header);
 fail_links:
+	if (header->ctl_table == sysctl_mount_point)
+		clear_empty_dir(dir);
 	header->parent = NULL;
 	drop_sysctl_table(&dir->header);
 	return err;

@@ -419,6 +454,8 @@ static struct inode *proc_sys_make_inode
 		inode->i_mode |= S_IFDIR;
 		inode->i_op = &proc_sys_dir_operations;
 		inode->i_fop = &proc_sys_dir_file_operations;
+		if (is_empty_dir(head))
+			make_empty_dir_inode(inode);
 	}
 out:
 	return inode;

@@ -188,6 +188,9 @@ struct ctl_table_header *register_sysctl
 void unregister_sysctl_table(struct ctl_table_header * table);
 
 extern int sysctl_init(void);
+
+extern struct ctl_table sysctl_mount_point[];
+
 #else /* CONFIG_SYSCTL */
 static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table)
 {

@@ -1510,12 +1510,6 @@ static struct ctl_table vm_table[] = {
 	{ }
 };
 
-#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
-static struct ctl_table binfmt_misc_table[] = {
-	{ }
-};
-#endif
-
 static struct ctl_table fs_table[] = {
 	{
 		.procname	= "inode-nr",

@@ -1669,7 +1663,7 @@ static struct ctl_table fs_table[] = {
 	{
 		.procname	= "binfmt_misc",
 		.mode		= 0555,
-		.child		= binfmt_misc_table,
+		.child		= sysctl_mount_point,
 	},
 #endif
 	{

@@ -373,6 +373,10 @@ static struct proc_dir_entry *__proc_cre
 		WARN(1, "create '/proc/%s' by hand\n", qstr.name);
 		return NULL;
 	}
+	if (is_empty_pde(*parent)) {
+		WARN(1, "attempt to add to permanently empty directory");
+		return NULL;
+	}
 
 	ent = kzalloc(sizeof(struct proc_dir_entry) + qstr.len + 1, GFP_KERNEL);
 	if (!ent)

@@ -455,6 +459,25 @@ struct proc_dir_entry *proc_mkdir(const
 }
 EXPORT_SYMBOL(proc_mkdir);
 
+struct proc_dir_entry *proc_create_mount_point(const char *name)
+{
+	umode_t mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	struct proc_dir_entry *ent, *parent = NULL;
+
+	ent = __proc_create(&parent, name, mode, 2);
+	if (ent) {
+		ent->data = NULL;
+		ent->proc_fops = NULL;
+		ent->proc_iops = NULL;
+		if (proc_register(parent, ent) < 0) {
+			kfree(ent);
+			parent->nlink--;
+			ent = NULL;
+		}
+	}
+	return ent;
+}
+
 struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
 					struct proc_dir_entry *parent,
 					const struct file_operations *proc_fops,

@@ -423,6 +423,10 @@ struct inode *proc_get_inode(struct supe
 		inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 		PROC_I(inode)->pde = de;
 
+		if (is_empty_pde(de)) {
+			make_empty_dir_inode(inode);
+			return inode;
+		}
 		if (de->mode) {
 			inode->i_mode = de->mode;
 			inode->i_uid = de->uid;

@@ -191,6 +191,12 @@ static inline struct proc_dir_entry *pde
 }
 extern void pde_put(struct proc_dir_entry *);
 
+static inline bool is_empty_pde(const struct proc_dir_entry *pde)
+{
+	return S_ISDIR(pde->mode) && !pde->proc_iops;
+}
+struct proc_dir_entry *proc_create_mount_point(const char *name);
+
 /*
  * inode.c
  */

@@ -182,10 +182,10 @@ void __init proc_root_init(void)
 #endif
 	proc_mkdir("fs", NULL);
 	proc_mkdir("driver", NULL);
-	proc_mkdir("fs/nfsd", NULL); /* somewhere for the nfsd filesystem to be mounted */
+	proc_create_mount_point("fs/nfsd"); /* somewhere for the nfsd filesystem to be mounted */
 #if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
 	/* just give it a mountpoint */
-	proc_mkdir("openprom", NULL);
+	proc_create_mount_point("openprom");
 #endif
 	proc_tty_init();
 	proc_mkdir("bus", NULL);

@@ -592,6 +592,9 @@ int kernfs_add_one(struct kernfs_node *k
 		goto out_unlock;
 
 	ret = -ENOENT;
+	if (parent->flags & KERNFS_EMPTY_DIR)
+		goto out_unlock;
+
 	if ((parent->flags & KERNFS_ACTIVATED) && !kernfs_active(parent))
 		goto out_unlock;
 

@@ -783,6 +786,38 @@ struct kernfs_node *kernfs_create_dir_ns
 	return ERR_PTR(rc);
 }
 
+/**
+ * kernfs_create_empty_dir - create an always empty directory
+ * @parent: parent in which to create a new directory
+ * @name: name of the new directory
+ *
+ * Returns the created node on success, ERR_PTR() value on failure.
+ */
+struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent,
+					    const char *name)
+{
+	struct kernfs_node *kn;
+	int rc;
+
+	/* allocate */
+	kn = kernfs_new_node(parent, name, S_IRUGO|S_IXUGO|S_IFDIR, KERNFS_DIR);
+	if (!kn)
+		return ERR_PTR(-ENOMEM);
+
+	kn->flags |= KERNFS_EMPTY_DIR;
+	kn->dir.root = parent->dir.root;
+	kn->ns = NULL;
+	kn->priv = NULL;
+
+	/* link in */
+	rc = kernfs_add_one(kn);
+	if (!rc)
+		return kn;
+
+	kernfs_put(kn);
+	return ERR_PTR(rc);
+}
+
 static struct dentry *kernfs_iop_lookup(struct inode *dir,
 					struct dentry *dentry,
 					unsigned int flags)

@@ -1254,7 +1289,8 @@ int kernfs_rename_ns(struct kernfs_node
 	mutex_lock(&kernfs_mutex);
 
 	error = -ENOENT;
-	if (!kernfs_active(kn) || !kernfs_active(new_parent))
+	if (!kernfs_active(kn) || !kernfs_active(new_parent) ||
+	    (new_parent->flags & KERNFS_EMPTY_DIR))
 		goto out;
 
 	error = 0;

@@ -296,6 +296,8 @@ static void kernfs_init_inode(struct ker
 	case KERNFS_DIR:
 		inode->i_op = &kernfs_dir_iops;
 		inode->i_fop = &kernfs_dir_fops;
+		if (kn->flags & KERNFS_EMPTY_DIR)
+			make_empty_dir_inode(inode);
 		break;
 	case KERNFS_FILE:
 		inode->i_size = kn->attr.size;

@@ -45,6 +45,7 @@ enum kernfs_node_flag {
 	KERNFS_LOCKDEP		= 0x0100,
 	KERNFS_SUICIDAL		= 0x0400,
 	KERNFS_SUICIDED		= 0x0800,
+	KERNFS_EMPTY_DIR	= 0x1000,
 };
 
 /* @flags for kernfs_create_root() */

@@ -285,6 +286,8 @@ void kernfs_destroy_root(struct kernfs_r
 struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
 					 const char *name, umode_t mode,
 					 void *priv, const void *ns);
+struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent,
+					    const char *name);
 struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 					 const char *name,
 					 umode_t mode, loff_t size,

@@ -121,3 +121,37 @@ int sysfs_move_dir_ns(struct kobject *ko
 
 	return kernfs_rename_ns(kn, new_parent, kn->name, new_ns);
 }
+
+/**
+ * sysfs_create_mount_point - create an always empty directory
+ * @parent_kobj:  kobject that will contain this always empty directory
+ * @name: The name of the always empty directory to add
+ */
+int sysfs_create_mount_point(struct kobject *parent_kobj, const char *name)
+{
+	struct kernfs_node *kn, *parent = parent_kobj->sd;
+
+	kn = kernfs_create_empty_dir(parent, name);
+	if (IS_ERR(kn)) {
+		if (PTR_ERR(kn) == -EEXIST)
+			sysfs_warn_dup(parent, name);
+		return PTR_ERR(kn);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(sysfs_create_mount_point);
+
+/**
+ *	sysfs_remove_mount_point - remove an always empty directory.
+ *	@parent_kobj: kobject that will contain this always empty directory
+ *	@name: The name of the always empty directory to remove
+ *
+ */
+void sysfs_remove_mount_point(struct kobject *parent_kobj, const char *name)
+{
+	struct kernfs_node *parent = parent_kobj->sd;
+
+	kernfs_remove_by_name_ns(parent, name, NULL);
+}
+EXPORT_SYMBOL_GPL(sysfs_remove_mount_point);

@@ -195,6 +195,10 @@ int __must_check sysfs_rename_dir_ns(str
 int __must_check sysfs_move_dir_ns(struct kobject *kobj,
 				   struct kobject *new_parent_kobj,
 				   const void *new_ns);
+int __must_check sysfs_create_mount_point(struct kobject *parent_kobj,
+					  const char *name);
+void sysfs_remove_mount_point(struct kobject *parent_kobj,
+			      const char *name);
 
 int __must_check sysfs_create_file_ns(struct kobject *kobj,
 				      const struct attribute *attr,

@@ -283,6 +287,17 @@ static inline int sysfs_move_dir_ns(stru
 	return 0;
 }
 
+static inline int sysfs_create_mount_point(struct kobject *parent_kobj,
+					   const char *name)
+{
+	return 0;
+}
+
+static inline void sysfs_remove_mount_point(struct kobject *parent_kobj,
+					    const char *name)
+{
+}
+
 static inline int sysfs_create_file_ns(struct kobject *kobj,
 				       const struct attribute *attr,
 				       const void *ns)

@@ -3196,9 +3196,8 @@ bool fs_fully_visible(struct file_system
 			/* Only worry about locked mounts */
 			if (!(mnt->mnt.mnt_flags & MNT_LOCKED))
 				continue;
-			if (!S_ISDIR(inode->i_mode))
-				goto next;
-			if (inode->i_nlink > 2)
+			/* Is the directory permanetly empty? */
+			if (!is_empty_dir_inode(inode))
 				goto next;
 		}
 		visible = true;

@@ -2334,6 +2334,8 @@ unlock:
 	return err;
 }
 
+static bool fs_fully_visible(struct file_system_type *fs_type);
+
 /*
  * create a new mount for userspace and request it to be added into the
  * namespace's tree

@@ -2365,6 +2367,10 @@ static int do_new_mount(struct path *pat
 			flags |= MS_NODEV;
 			mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
 		}
+		if (type->fs_flags & FS_USERNS_VISIBLE) {
+			if (!fs_fully_visible(type))
+				return -EPERM;
+		}
 	}
 
 	mnt = vfs_kern_mount(type, flags, name, data);

@@ -3166,7 +3172,7 @@ bool current_chrooted(void)
 	return chrooted;
 }
 
-bool fs_fully_visible(struct file_system_type *type)
+static bool fs_fully_visible(struct file_system_type *type)
 {
 	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
 	struct mount *mnt;

@@ -112,9 +112,6 @@ static struct dentry *proc_mount(struct
 		ns = task_active_pid_ns(current);
 		options = data;
 
-		if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
-			return ERR_PTR(-EPERM);
-
 		/* Does the mounter have privilege over the pid namespace? */
 		if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
 			return ERR_PTR(-EPERM);

@@ -159,7 +156,7 @@ static struct file_system_type proc_fs_t
 	.name		= "proc",
 	.mount		= proc_mount,
 	.kill_sb	= proc_kill_sb,
-	.fs_flags	= FS_USERNS_MOUNT,
+	.fs_flags	= FS_USERNS_VISIBLE | FS_USERNS_MOUNT,
 };
 
 void __init proc_root_init(void)

@@ -31,9 +31,6 @@ static struct dentry *sysfs_mount(struct
 	bool new_sb;
 
 	if (!(flags & MS_KERNMOUNT)) {
-		if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
-			return ERR_PTR(-EPERM);
-
 		if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET))
 			return ERR_PTR(-EPERM);
 	}

@@ -58,7 +55,7 @@ static struct file_system_type sysfs_fs_
 	.name		= "sysfs",
 	.mount		= sysfs_mount,
 	.kill_sb	= sysfs_kill_sb,
-	.fs_flags	= FS_USERNS_MOUNT,
+	.fs_flags	= FS_USERNS_VISIBLE | FS_USERNS_MOUNT,
 };
 
 int __init sysfs_init(void)

@@ -1863,6 +1863,7 @@ struct file_system_type {
 #define FS_HAS_SUBTYPE		4
 #define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
 #define FS_USERNS_DEV_MOUNT	16 /* A userns mount does not imply MNT_NODEV */
+#define FS_USERNS_VISIBLE	32	/* FS must already be visible */
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
 	struct dentry *(*mount) (struct file_system_type *, int,
 		       const char *, void *);

@@ -1950,7 +1951,6 @@ extern int vfs_ustat(dev_t, struct kstat
 extern int freeze_super(struct super_block *super);
 extern int thaw_super(struct super_block *super);
 extern bool our_mnt(struct vfsmount *mnt);
-extern bool fs_fully_visible(struct file_system_type *);
 
 extern int current_umask(void);
 

@@ -2334,7 +2334,7 @@ unlock:
 	return err;
 }
 
-static bool fs_fully_visible(struct file_system_type *fs_type);
+static bool fs_fully_visible(struct file_system_type *fs_type, int *new_mnt_flags);
 
 /*
  * create a new mount for userspace and request it to be added into the

@@ -2368,7 +2368,7 @@ static int do_new_mount(struct path *pat
 			mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
 		}
 		if (type->fs_flags & FS_USERNS_VISIBLE) {
-			if (!fs_fully_visible(type))
+			if (!fs_fully_visible(type, &mnt_flags))
 				return -EPERM;
 		}
 	}

@@ -3172,9 +3172,10 @@ bool current_chrooted(void)
 	return chrooted;
 }
 
-static bool fs_fully_visible(struct file_system_type *type)
+static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags)
 {
 	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
+	int new_flags = *new_mnt_flags;
 	struct mount *mnt;
 	bool visible = false;
 

@@ -3193,6 +3194,19 @@ static bool fs_fully_visible(struct file
 		if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root)
 			continue;
 
+		/* Verify the mount flags are equal to or more permissive
+		 * than the proposed new mount.
+		 */
+		if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) &&
+		    !(new_flags & MNT_READONLY))
+			continue;
+		if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) &&
+		    !(new_flags & MNT_NODEV))
+			continue;
+		if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) &&
+		    ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK)))
+			continue;
+
 		/* This mount is not fully visible if there are any
 		 * locked child mounts that cover anything except for
 		 * empty directories.

@@ -3206,6 +3220,10 @@ static bool fs_fully_visible(struct file
 			if (!is_empty_dir_inode(inode))
 				goto next;
 		}
+		/* Preserve the locked attributes */
+		*new_mnt_flags |= mnt->mnt.mnt_flags & (MNT_LOCK_READONLY | \
+							MNT_LOCK_NODEV    | \
+							MNT_LOCK_ATIME);
 		visible = true;
 		goto found;
 	next:	;

@@ -458,8 +458,6 @@ static const struct super_operations hyp
 	.show_options	= hypfs_show_options,
 };
 
-static struct kobject *s390_kobj;
-
 static int __init hypfs_init(void)
 {
 	int rc;

@@ -483,18 +481,16 @@ static int __init hypfs_init(void)
 		rc = -ENODATA;
 		goto fail_hypfs_sprp_exit;
 	}
-	s390_kobj = kobject_create_and_add("s390", hypervisor_kobj);
-	if (!s390_kobj) {
-		rc = -ENOMEM;
+	rc = sysfs_create_mount_point(hypervisor_kobj, "s390");
+	if (rc)
 		goto fail_hypfs_diag0c_exit;
-	}
 	rc = register_filesystem(&hypfs_type);
 	if (rc)
 		goto fail_filesystem;
 	return 0;
 
 fail_filesystem:
-	kobject_put(s390_kobj);
+	sysfs_remove_mount_point(hypervisor_kobj, "s390");
 fail_hypfs_diag0c_exit:
 	hypfs_diag0c_exit();
 fail_hypfs_sprp_exit:

@@ -512,7 +508,7 @@ fail_dbfs_exit:
 static void __exit hypfs_exit(void)
 {
 	unregister_filesystem(&hypfs_type);
-	kobject_put(s390_kobj);
+	sysfs_remove_mount_point(hypervisor_kobj, "s390");
 	hypfs_diag0c_exit();
 	hypfs_sprp_exit();
 	hypfs_vm_exit();

@@ -65,7 +65,6 @@ static int __init parse_efi_cmdline(char
 early_param("efi", parse_efi_cmdline);
 
 static struct kobject *efi_kobj;
-static struct kobject *efivars_kobj;
 
 /*
  * Let's not leave out systab information that snuck into

@@ -212,10 +211,9 @@ static int __init efisubsys_init(void)
 		goto err_remove_group;
 
 	/* and the standard mountpoint for efivarfs */
-	efivars_kobj = kobject_create_and_add("efivars", efi_kobj);
-	if (!efivars_kobj) {
+	error = sysfs_create_mount_point(efi_kobj, "efivars");
+	if (error) {
 		pr_err("efivars: Subsystem registration failed.\n");
-		error = -ENOMEM;
 		goto err_remove_group;
 	}
 

@@ -129,8 +129,6 @@ void configfs_release_fs(void)
 }
 
 
-static struct kobject *config_kobj;
-
 static int __init configfs_init(void)
 {
 	int err = -ENOMEM;

@@ -141,8 +139,8 @@ static int __init configfs_init(void)
 	if (!configfs_dir_cachep)
 		goto out;
 
-	config_kobj = kobject_create_and_add("config", kernel_kobj);
-	if (!config_kobj)
+	err = sysfs_create_mount_point(kernel_kobj, "config");
+	if (err)
 		goto out2;
 
 	err = register_filesystem(&configfs_fs_type);

@@ -152,7 +150,7 @@ static int __init configfs_init(void)
 	return 0;
 out3:
 	pr_err("Unable to register filesystem!\n");
-	kobject_put(config_kobj);
+	sysfs_remove_mount_point(kernel_kobj, "config");
 out2:
 	kmem_cache_destroy(configfs_dir_cachep);
 	configfs_dir_cachep = NULL;

@@ -163,7 +161,7 @@ out:
 static void __exit configfs_exit(void)
 {
 	unregister_filesystem(&configfs_fs_type);
-	kobject_put(config_kobj);
+	sysfs_remove_mount_point(kernel_kobj, "config");
 	kmem_cache_destroy(configfs_dir_cachep);
 	configfs_dir_cachep = NULL;
 }

@@ -713,20 +713,17 @@ bool debugfs_initialized(void)
 }
 EXPORT_SYMBOL_GPL(debugfs_initialized);
 
-
-static struct kobject *debug_kobj;
-
 static int __init debugfs_init(void)
 {
 	int retval;
 
-	debug_kobj = kobject_create_and_add("debug", kernel_kobj);
-	if (!debug_kobj)
-		return -EINVAL;
+	retval = sysfs_create_mount_point(kernel_kobj, "debug");
+	if (retval)
+		return retval;
 
 	retval = register_filesystem(&debug_fs_type);
 	if (retval)
-		kobject_put(debug_kobj);
+		sysfs_remove_mount_point(kernel_kobj, "debug");
 	else
 		debugfs_registered = true;
 

@@ -1238,7 +1238,6 @@ static void fuse_fs_cleanup(void)
 }
 
 static struct kobject *fuse_kobj;
-static struct kobject *connections_kobj;
 
 static int fuse_sysfs_init(void)
 {

@@ -1250,11 +1249,9 @@ static int fuse_sysfs_init(void)
 		goto out_err;
 	}
 
-	connections_kobj = kobject_create_and_add("connections", fuse_kobj);
-	if (!connections_kobj) {
-		err = -ENOMEM;
+	err = sysfs_create_mount_point(fuse_kobj, "connections");
+	if (err)
 		goto out_fuse_unregister;
-	}
 
 	return 0;
 

@@ -1266,7 +1263,7 @@ static int fuse_sysfs_init(void)
 
 static void fuse_sysfs_cleanup(void)
 {
-	kobject_put(connections_kobj);
+	sysfs_remove_mount_point(fuse_kobj, "connections");
 	kobject_put(fuse_kobj);
 }
 

@@ -458,22 +458,18 @@ static struct file_system_type pstore_fs
 	.kill_sb	= pstore_kill_sb,
 };
 
-static struct kobject *pstore_kobj;
-
 static int __init init_pstore_fs(void)
 {
-	int err = 0;
+	int err;
 
 	/* Create a convenient mount point for people to access pstore */
-	pstore_kobj = kobject_create_and_add("pstore", fs_kobj);
-	if (!pstore_kobj) {
-		err = -ENOMEM;
+	err = sysfs_create_mount_point(fs_kobj, "pstore");
+	if (err)
 		goto out;
-	}
 
 	err = register_filesystem(&pstore_fs_type);
 	if (err < 0)
-		kobject_put(pstore_kobj);
+		sysfs_remove_mount_point(fs_kobj, "pstore");
 
 out:
 	return err;

@@ -1924,8 +1924,6 @@ static struct file_system_type cgroup_fs
 	.kill_sb = cgroup_kill_sb,
 };
 
-static struct kobject *cgroup_kobj;
-
 /**
  * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
  * @task: target task

@@ -5042,13 +5040,13 @@ int __init cgroup_init(void)
 		}
 	}
 
-	cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);
-	if (!cgroup_kobj)
-		return -ENOMEM;
+	err = sysfs_create_mount_point(fs_kobj, "cgroup");
+	if (err)
+		return err;
 
 	err = register_filesystem(&cgroup_fs_type);
 	if (err < 0) {
-		kobject_put(cgroup_kobj);
+		sysfs_remove_mount_point(fs_kobj, "cgroup");
 		return err;
 	}
 

@@ -215,19 +215,17 @@ void securityfs_remove(struct dentry *de
 }
 EXPORT_SYMBOL_GPL(securityfs_remove);
 
-static struct kobject *security_kobj;
-
 static int __init securityfs_init(void)
 {
 	int retval;
 
-	security_kobj = kobject_create_and_add("security", kernel_kobj);
-	if (!security_kobj)
-		return -EINVAL;
+	retval = sysfs_create_mount_point(kernel_kobj, "security");
+	if (retval)
+		return retval;
 
 	retval = register_filesystem(&fs_type);
 	if (retval)
-		kobject_put(security_kobj);
+		sysfs_remove_mount_point(kernel_kobj, "security");
 	return retval;
 }
 

@@ -1853,7 +1853,6 @@ static struct file_system_type sel_fs_ty
 };
 
 struct vfsmount *selinuxfs_mount;
-static struct kobject *selinuxfs_kobj;
 
 static int __init init_sel_fs(void)
 {

@@ -1862,13 +1861,13 @@ static int __init init_sel_fs(void)
 	if (!selinux_enabled)
 		return 0;
 
-	selinuxfs_kobj = kobject_create_and_add("selinux", fs_kobj);
-	if (!selinuxfs_kobj)
-		return -ENOMEM;
+	err = sysfs_create_mount_point(fs_kobj, "selinux");
+	if (err)
+		return err;
 
 	err = register_filesystem(&sel_fs_type);
 	if (err) {
-		kobject_put(selinuxfs_kobj);
+		sysfs_remove_mount_point(fs_kobj, "selinux");
 		return err;
 	}
 

@@ -1887,7 +1886,7 @@ __initcall(init_sel_fs);
 #ifdef CONFIG_SECURITY_SELINUX_DISABLE
 void exit_sel_fs(void)
 {
-	kobject_put(selinuxfs_kobj);
+	sysfs_remove_mount_point(fs_kobj, "selinux");
 	kern_unmount(selinuxfs_mount);
 	unregister_filesystem(&sel_fs_type);
 }

@@ -2150,16 +2150,16 @@ static const struct file_operations smk_
 	.llseek		= generic_file_llseek,
 };
 
-static struct kset *smackfs_kset;
 /**
  * smk_init_sysfs - initialize /sys/fs/smackfs
  *
  */
 static int smk_init_sysfs(void)
 {
-	smackfs_kset = kset_create_and_add("smackfs", NULL, fs_kobj);
-	if (!smackfs_kset)
-		return -ENOMEM;
+	int err;
+	err = sysfs_create_mount_point(fs_kobj, "smackfs");
+	if (err)
+		return err;
 	return 0;
 }
 

@@ -250,6 +250,7 @@ static struct irq_chip crystalcove_irqch
 	.irq_set_type		= crystalcove_irq_type,
 	.irq_bus_lock		= crystalcove_bus_lock,
 	.irq_bus_sync_unlock	= crystalcove_bus_sync_unlock,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
 static irqreturn_t crystalcove_gpio_irq_handler(int irq, void *data)

@@ -182,6 +182,11 @@ static void __rcu_process_callbacks(stru
 
 	/* Move the ready-to-invoke callbacks to a local list. */
 	local_irq_save(flags);
+	if (rcp->donetail == &rcp->rcucblist) {
+		/* No callbacks ready, so just leave. */
+		local_irq_restore(flags);
+		return;
+	}
 	RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1));
 	list = rcp->rcucblist;
 	rcp->rcucblist = *rcp->donetail;

@@ -268,7 +268,7 @@
 #define IPR_RUNTIME_RESET				0x40000000
 
 #define IPR_IPL_INIT_MIN_STAGE_TIME			5
-#define IPR_IPL_INIT_DEFAULT_STAGE_TIME                 15
+#define IPR_IPL_INIT_DEFAULT_STAGE_TIME                 30
 #define IPR_IPL_INIT_STAGE_UNKNOWN			0x0
 #define IPR_IPL_INIT_STAGE_TRANSOP			0xB0000000
 #define IPR_IPL_INIT_STAGE_MASK				0xff000000

@@ -104,6 +104,9 @@
 #define TOPIC_EXCA_IF_CONTROL		0x3e	/* 8 bit */
 #define TOPIC_EXCA_IFC_33V_ENA		0x01
 
+#define TOPIC_PCI_CFG_PPBCN		0x3e	/* 16-bit */
+#define TOPIC_PCI_CFG_PPBCN_WBEN	0x0400
+
 static void topic97_zoom_video(struct pcmcia_socket *sock, int onoff)
 {
 	struct yenta_socket *socket = container_of(sock, struct yenta_socket, socket);

@@ -138,6 +141,7 @@ static int topic97_override(struct yenta
 static int topic95_override(struct yenta_socket *socket)
 {
 	u8 fctrl;
+	u16 ppbcn;
 
 	/* enable 3.3V support for 16bit cards */
 	fctrl = exca_readb(socket, TOPIC_EXCA_IF_CONTROL);

@@ -146,6 +150,18 @@ static int topic95_override(struct yenta
 	/* tell yenta to use exca registers to power 16bit cards */
 	socket->flags |= YENTA_16BIT_POWER_EXCA | YENTA_16BIT_POWER_DF;
 
+	/* Disable write buffers to prevent lockups under load with numerous
+	   Cardbus cards, observed on Tecra 500CDT and reported elsewhere on the
+	   net.  This is not a power-on default according to the datasheet
+	   but some BIOSes seem to set it. */
+	if (pci_read_config_word(socket->dev, TOPIC_PCI_CFG_PPBCN, &ppbcn) == 0
+	    && socket->dev->revision <= 7
+	    && (ppbcn & TOPIC_PCI_CFG_PPBCN_WBEN)) {
+		ppbcn &= ~TOPIC_PCI_CFG_PPBCN_WBEN;
+		pci_write_config_word(socket->dev, TOPIC_PCI_CFG_PPBCN, ppbcn);
+		dev_info(&socket->dev->dev, "Disabled ToPIC95 Cardbus write buffers.\n");
+	}
+
 	return 0;
 }
 

@@ -1044,7 +1044,8 @@ void snd_pcm_detach_substream(struct snd
 static ssize_t show_pcm_class(struct device *dev,
 			      struct device_attribute *attr, char *buf)
 {
-	struct snd_pcm *pcm;
+	struct snd_pcm_str *pstr = container_of(dev, struct snd_pcm_str, dev);
+	struct snd_pcm *pcm = pstr->pcm;
 	const char *str;
 	static const char *strs[SNDRV_PCM_CLASS_LAST + 1] = {
 		[SNDRV_PCM_CLASS_GENERIC] = "generic",

@@ -1053,8 +1054,7 @@ static ssize_t show_pcm_class(struct dev
 		[SNDRV_PCM_CLASS_DIGITIZER] = "digitizer",
 	};
 
-	if (! (pcm = dev_get_drvdata(dev)) ||
-	    pcm->dev_class > SNDRV_PCM_CLASS_LAST)
+	if (pcm->dev_class > SNDRV_PCM_CLASS_LAST)
 		str = "none";
 	else
 		str = strs[pcm->dev_class];

@@ -4421,6 +4421,7 @@ enum {
 	ALC255_FIXUP_HEADSET_MODE_NO_HP_MIC,
 	ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
 	ALC292_FIXUP_TPT440_DOCK,
+	ALC292_FIXUP_TPT440_DOCK2,
 	ALC283_FIXUP_BXBT2807_MIC,
 	ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED,
 	ALC282_FIXUP_ASPIRE_V5_PINS,

@@ -4864,6 +4865,12 @@ static const struct hda_fixup alc269_fix
 		.chain_id = ALC269_FIXUP_HEADSET_MODE
 	},
 	[ALC292_FIXUP_TPT440_DOCK] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc269_fixup_pincfg_no_hp_to_lineout,
+		.chained = true,
+		.chain_id = ALC292_FIXUP_TPT440_DOCK2
+	},
+	[ALC292_FIXUP_TPT440_DOCK2] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
 			{ 0x16, 0x21211010 }, /* dock headphone */

@@ -2056,6 +2056,8 @@ static const struct pci_device_id azx_id
 	{ PCI_DEVICE(0x1022, 0x780d),
 	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_SB },
 	/* ATI HDMI */
+	{ PCI_DEVICE(0x1002, 0x1308),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0x793b),
 	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
 	{ PCI_DEVICE(0x1002, 0x7919),

@@ -2064,6 +2066,8 @@ static const struct pci_device_id azx_id
 	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
 	{ PCI_DEVICE(0x1002, 0x970f),
 	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
+	{ PCI_DEVICE(0x1002, 0x9840),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0xaa00),
 	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
 	{ PCI_DEVICE(0x1002, 0xaa08),

@@ -4394,6 +4394,7 @@ enum {
 	ALC269_FIXUP_DELL3_MIC_NO_PRESENCE,
 	ALC269_FIXUP_HEADSET_MODE,
 	ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC,
+	ALC269_FIXUP_ASPIRE_HEADSET_MIC,
 	ALC269_FIXUP_ASUS_X101_FUNC,
 	ALC269_FIXUP_ASUS_X101_VERB,
 	ALC269_FIXUP_ASUS_X101,

@@ -4663,6 +4664,15 @@ static const struct hda_fixup alc269_fix
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_headset_mode_no_hp_mic,
 	},
+	[ALC269_FIXUP_ASPIRE_HEADSET_MIC] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x01a1913c }, /* headset mic w/o jack detect */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MODE,
+	},
 	[ALC286_FIXUP_SONY_MIC_NO_PRESENCE] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {

@@ -4937,6 +4947,8 @@ static const struct snd_pci_quirk alc269
 	SND_PCI_QUIRK(0x1025, 0x029b, "Acer 1810TZ", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x0349, "Acer AOD260", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x047c, "Acer AC700", ALC269_FIXUP_ACER_AC700),
+	SND_PCI_QUIRK(0x1025, 0x072d, "Acer Aspire V5-571G", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x0740, "Acer AO725", ALC271_FIXUP_HP_GATE_MIC_JACK),
 	SND_PCI_QUIRK(0x1025, 0x0742, "Acer AO756", ALC271_FIXUP_HP_GATE_MIC_JACK),
 	SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),

@@ -4374,6 +4374,7 @@ enum {
 	ALC269_FIXUP_LIFEBOOK,
 	ALC269_FIXUP_LIFEBOOK_EXTMIC,
 	ALC269_FIXUP_LIFEBOOK_HP_PIN,
+	ALC269_FIXUP_LIFEBOOK_NO_HP_TO_LINEOUT,
 	ALC269_FIXUP_AMIC,
 	ALC269_FIXUP_DMIC,
 	ALC269VB_FIXUP_AMIC,

@@ -4536,6 +4537,10 @@ static const struct hda_fixup alc269_fix
 			{ }
 		},
 	},
+	[ALC269_FIXUP_LIFEBOOK_NO_HP_TO_LINEOUT] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc269_fixup_pincfg_no_hp_to_lineout,
+	},
 	[ALC269_FIXUP_AMIC] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {

@@ -5046,6 +5051,7 @@ static const struct snd_pci_quirk alc269
 	SND_PCI_QUIRK(0x104d, 0x9084, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ),
 	SND_PCI_QUIRK(0x104d, 0x9099, "Sony VAIO S13", ALC275_FIXUP_SONY_DISABLE_AAMIX),
 	SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK),
+	SND_PCI_QUIRK(0x10cf, 0x159f, "Lifebook E780", ALC269_FIXUP_LIFEBOOK_NO_HP_TO_LINEOUT),
 	SND_PCI_QUIRK(0x10cf, 0x15dc, "Lifebook T731", ALC269_FIXUP_LIFEBOOK_HP_PIN),
 	SND_PCI_QUIRK(0x10cf, 0x1757, "Lifebook E752", ALC269_FIXUP_LIFEBOOK_HP_PIN),
 	SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),

@@ -467,6 +467,16 @@ static int __init acpi_bus_init_irq(void
 	return 0;
 }
 
+/**
+ * acpi_early_init - Initialize ACPICA and populate the ACPI namespace.
+ *
+ * The ACPI tables are accessible after this, but the handling of events has not
+ * been initialized and the global lock is not available yet, so AML should not
+ * be executed at this point.
+ *
+ * Doing this before switching the EFI runtime services to virtual mode allows
+ * the EfiBootServices memory to be freed slightly earlier on boot.
+ */
 void __init acpi_early_init(void)
 {
 	acpi_status status;

@@ -530,26 +540,42 @@ void __init acpi_early_init(void)
 		acpi_gbl_FADT.sci_interrupt = acpi_sci_override_gsi;
 	}
 #endif
+	return;
+
+ error0:
+	disable_acpi();
+}
+
+/**
+ * acpi_subsystem_init - Finalize the early initialization of ACPI.
+ *
+ * Switch over the platform to the ACPI mode (if possible), initialize the
+ * handling of ACPI events, install the interrupt and global lock handlers.
+ *
+ * Doing this too early is generally unsafe, but at the same time it needs to be
+ * done before all things that really depend on ACPI.  The right spot appears to
+ * be before finalizing the EFI initialization.
+ */
+void __init acpi_subsystem_init(void)
+{
+	acpi_status status;
+
+	if (acpi_disabled)
+		return;
 
 	status = acpi_enable_subsystem(~ACPI_NO_ACPI_ENABLE);
 	if (ACPI_FAILURE(status)) {
 		printk(KERN_ERR PREFIX "Unable to enable ACPI\n");
-		goto error0;
+		disable_acpi();
+	} else {
+		/*
+		 * If the system is using ACPI then we can be reasonably
+		 * confident that any regulators are managed by the firmware
+		 * so tell the regulator core it has everything it needs to
+		 * know.
+		 */
+		regulator_has_full_constraints();
 	}
-
-	/*
-	 * If the system is using ACPI then we can be reasonably
-	 * confident that any regulators are managed by the firmware
-	 * so tell the regulator core it has everything it needs to
-	 * know.
-	 */
-	regulator_has_full_constraints();
-
-	return;
-
-      error0:
-	disable_acpi();
-	return;
 }
 
 static int __init acpi_bus_init(void)

@@ -428,6 +428,7 @@ extern acpi_status acpi_pci_osc_control_
 #define ACPI_OST_SC_INSERT_NOT_SUPPORTED	0x82
 
 extern void acpi_early_init(void);
+extern void acpi_subsystem_init(void);
 
 extern int acpi_nvs_register(__u64 start, __u64 size);
 

@@ -477,6 +478,7 @@ static inline const char *acpi_dev_name(
 }
 
 static inline void acpi_early_init(void) { }
+static inline void acpi_subsystem_init(void) { }
 
 static inline int early_acpi_boot_init(void)
 {

@@ -661,6 +661,7 @@ asmlinkage __visible void __init start_k
 
 	check_bugs();
 
+	acpi_subsystem_init();
 	sfi_init_late();
 
 	if (efi_enabled(EFI_RUNTIME_SERVICES)) {

@@ -953,6 +953,7 @@ EXPORT_SYMBOL_GPL(acpi_subsys_prepare);
  */
 void acpi_subsys_complete(struct device *dev)
 {
+	pm_generic_complete(dev);
 	/*
 	 * If the device had been runtime-suspended before the system went into
 	 * the sleep state it is going out of and it has never been resumed till

@@ -1422,6 +1422,7 @@ static const struct dev_pm_ops kxcjk1013
 static const struct acpi_device_id kx_acpi_match[] = {
 	{"KXCJ1013", KXCJK1013},
 	{"KXCJ1008", KXCJ91008},
+	{"KXCJ9000", KXCJ91008},
 	{"KXTJ1009", KXTJ21009},
 	{"SMO8500",  KXCJ91008},
 	{ },

@@ -43,6 +43,12 @@ static inline int atomic_##op##_return(i
 {									\
 	unsigned int temp;						\
 									\
+	/*								\
+	 * Explicit full memory barrier needed before/after as		\
+	 * LLOCK/SCOND thmeselves don't provide any such semantics	\
+	 */								\
+	smp_mb();							\
+									\
 	__asm__ __volatile__(						\
 	"1:	llock   %0, [%1]	\n"				\
 	"	" #asm_op " %0, %0, %2	\n"				\

@@ -52,6 +58,8 @@ static inline int atomic_##op##_return(i
 	: "r"(&v->counter), "ir"(i)					\
 	: "cc");							\
 									\
+	smp_mb();							\
+									\
 	return temp;							\
 }
 

@@ -105,6 +113,9 @@ static inline int atomic_##op##_return(i
 	unsigned long flags;						\
 	unsigned long temp;						\
 									\
+	/*								\
+	 * spin lock/unlock provides the needed smp_mb() before/after	\
+	 */								\
 	atomic_ops_lock(flags);						\
 	temp = v->counter;						\
 	temp c_op i;							\

@@ -142,9 +153,19 @@ ATOMIC_OP(and, &=, and)
 #define __atomic_add_unless(v, a, u)					\
 ({									\
 	int c, old;							\
+									\
+	/*								\
+	 * Explicit full memory barrier needed before/after as		\
+	 * LLOCK/SCOND thmeselves don't provide any such semantics	\
+	 */								\
+	smp_mb();							\
+									\
 	c = atomic_read(v);						\
 	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c)\
 		c = old;						\
+									\
+	smp_mb();							\
+									\
 	c;								\
 })
 

@@ -103,6 +103,12 @@ static inline int test_and_set_bit(unsig
 	if (__builtin_constant_p(nr))
 		nr &= 0x1f;
 
+	/*
+	 * Explicit full memory barrier needed before/after as
+	 * LLOCK/SCOND themselves don't provide any such semantics
+	 */
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	llock   %0, [%2]	\n"
 	"	bset    %1, %0, %3	\n"

@@ -112,6 +118,8 @@ static inline int test_and_set_bit(unsig
 	: "r"(m), "ir"(nr)
 	: "cc");
 
+	smp_mb();
+
 	return (old & (1 << nr)) != 0;
 }
 

@@ -125,6 +133,8 @@ test_and_clear_bit(unsigned long nr, vol
 	if (__builtin_constant_p(nr))
 		nr &= 0x1f;
 
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	llock   %0, [%2]	\n"
 	"	bclr    %1, %0, %3	\n"

@@ -134,6 +144,8 @@ test_and_clear_bit(unsigned long nr, vol
 	: "r"(m), "ir"(nr)
 	: "cc");
 
+	smp_mb();
+
 	return (old & (1 << nr)) != 0;
 }
 

@@ -147,6 +159,8 @@ test_and_change_bit(unsigned long nr, vo
 	if (__builtin_constant_p(nr))
 		nr &= 0x1f;
 
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	llock   %0, [%2]	\n"
 	"	bxor    %1, %0, %3	\n"

@@ -156,6 +170,8 @@ test_and_change_bit(unsigned long nr, vo
 	: "r"(m), "ir"(nr)
 	: "cc");
 
+	smp_mb();
+
 	return (old & (1 << nr)) != 0;
 }
 

@@ -235,6 +251,9 @@ static inline int test_and_set_bit(unsig
 	if (__builtin_constant_p(nr))
 		nr &= 0x1f;
 
+	/*
+	 * spin lock/unlock provide the needed smp_mb() before/after
+	 */
 	bitops_lock(flags);
 
 	old = *m;

@@ -10,6 +10,8 @@
 #define __ASM_ARC_CMPXCHG_H
 
 #include <linux/types.h>
+
+#include <asm/barrier.h>
 #include <asm/smp.h>
 
 #ifdef CONFIG_ARC_HAS_LLSC

@@ -19,6 +21,12 @@ __cmpxchg(volatile void *ptr, unsigned l
 {
 	unsigned long prev;
 
+	/*
+	 * Explicit full memory barrier needed before/after as
+	 * LLOCK/SCOND thmeselves don't provide any such semantics
+	 */
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	llock   %0, [%1]	\n"
 	"	brne    %0, %2, 2f	\n"

@@ -30,6 +38,8 @@ __cmpxchg(volatile void *ptr, unsigned l
 	  "r"(new) /* can't be "ir". scond can't take limm for "b" */
 	: "cc");
 
+	smp_mb();
+
 	return prev;
 }
 

@@ -42,6 +52,9 @@ __cmpxchg(volatile void *ptr, unsigned l
 	int prev;
 	volatile unsigned long *p = ptr;
 
+	/*
+	 * spin lock/unlock provide the needed smp_mb() before/after
+	 */
 	atomic_ops_lock(flags);
 	prev = *p;
 	if (prev == expected)

@@ -77,12 +90,16 @@ static inline unsigned long __xchg(unsig
 
 	switch (size) {
 	case 4:
+		smp_mb();
+
 		__asm__ __volatile__(
 		"	ex  %0, [%1]	\n"
 		: "+r"(val)
 		: "r"(ptr)
 		: "memory");
 
+		smp_mb();
+
 		return val;
 	}
 	return __xchg_bad_pointer();

@@ -22,24 +22,46 @@ static inline void arch_spin_lock(arch_s
 {
 	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
 
+	/*
+	 * This smp_mb() is technically superfluous, we only need the one
+	 * after the lock for providing the ACQUIRE semantics.
+	 * However doing the "right" thing was regressing hackbench
+	 * so keeping this, pending further investigation
+	 */
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
 	"	breq  %0, %2, 1b	\n"
 	: "+&r" (tmp)
 	: "r"(&(lock->slock)), "ir"(__ARCH_SPIN_LOCK_LOCKED__)
 	: "memory");
+
+	/*
+	 * ACQUIRE barrier to ensure load/store after taking the lock
+	 * don't "bleed-up" out of the critical section (leak-in is allowed)
+	 * http://www.spinics.net/lists/kernel/msg2010409.html
+	 *
+	 * ARCv2 only has load-load, store-store and all-all barrier
+	 * thus need the full all-all barrier
+	 */
+	smp_mb();
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
 
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
 	: "+r" (tmp)
 	: "r"(&(lock->slock))
 	: "memory");
 
+	smp_mb();
+
 	return (tmp == __ARCH_SPIN_LOCK_UNLOCKED__);
 }
 

@@ -47,12 +69,22 @@ static inline void arch_spin_unlock(arch
 {
 	unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__;
 
+	/*
+	 * RELEASE barrier: given the instructions avail on ARCv2, full barrier
+	 * is the only option
+	 */
+	smp_mb();
+
 	__asm__ __volatile__(
 	"	ex  %0, [%1]		\n"
 	: "+r" (tmp)
 	: "r"(&(lock->slock))
 	: "memory");
 
+	/*
+	 * superfluous, but keeping for now - see pairing version in
+	 * arch_spin_lock above
+	 */
 	smp_mb();
 }
 

@@ -33,10 +33,11 @@ __cmpxchg(volatile void *ptr, unsigned l
 	"	scond   %3, [%1]	\n"
 	"	bnz     1b		\n"
 	"2:				\n"
-	: "=&r"(prev)
-	: "r"(ptr), "ir"(expected),
-	  "r"(new) /* can't be "ir". scond can't take limm for "b" */
-	: "cc");
+	: "=&r"(prev)	/* Early clobber, to prevent reg reuse */
+	: "r"(ptr),	/* Not "m": llock only supports reg direct addr mode */
+	  "ir"(expected),
+	  "r"(new)	/* can't be "ir". scond can't take LIMM for "b" */
+	: "cc", "memory"); /* so that gcc knows memory is being written here */
 
 	smp_mb();
 

@@ -573,7 +573,7 @@ void mei_host_client_init(struct work_st
 bool mei_hbuf_acquire(struct mei_device *dev)
 {
 	if (mei_pg_state(dev) == MEI_PG_ON ||
-	    dev->pg_event == MEI_PG_EVENT_WAIT) {
+	    mei_pg_in_transition(dev)) {
 		dev_dbg(dev->dev, "device is in pg\n");
 		return false;
 	}

99 lines not on this page · raw message

@@ -302,6 +302,18 @@ int mei_txe_aliveness_set_sync(struct me
 }
 
 /**
+ * mei_txe_pg_in_transition - is device now in pg transition
+ *
+ * @dev: the device structure
+ *
+ * Return: true if in pg transition, false otherwise
+ */
+static bool mei_txe_pg_in_transition(struct mei_device *dev)
+{
+	return dev->pg_event == MEI_PG_EVENT_WAIT;
+}
+
+/**
  * mei_txe_pg_is_enabled - detect if PG is supported by HW
  *
  * @dev: the device structure

@@ -1138,6 +1150,7 @@ static const struct mei_hw_ops mei_txe_h
 	.hw_config = mei_txe_hw_config,
 	.hw_start = mei_txe_hw_start,
 
+	.pg_in_transition = mei_txe_pg_in_transition,
 	.pg_is_enabled = mei_txe_pg_is_enabled,
 
 	.intr_clear = mei_txe_intr_clear,

@@ -269,6 +269,7 @@ struct mei_cl {
 
  * @fw_status        : get fw status registers
  * @pg_state         : power gating state of the device
+ * @pg_in_transition : is device now in pg transition
  * @pg_is_enabled    : is power gating enabled
 
  * @intr_clear       : clear pending interrupts

@@ -298,6 +299,7 @@ struct mei_hw_ops {
 
 	int (*fw_status)(struct mei_device *dev, struct mei_fw_status *fw_sts);
 	enum mei_pg_state (*pg_state)(struct mei_device *dev);
+	bool (*pg_in_transition)(struct mei_device *dev);
 	bool (*pg_is_enabled)(struct mei_device *dev);
 
 	void (*intr_clear)(struct mei_device *dev);

@@ -396,11 +398,15 @@ struct mei_cl_device {
  * @MEI_PG_EVENT_IDLE: the driver is not in power gating transition
  * @MEI_PG_EVENT_WAIT: the driver is waiting for a pg event to complete
  * @MEI_PG_EVENT_RECEIVED: the driver received pg event
+ * @MEI_PG_EVENT_INTR_WAIT: the driver is waiting for a pg event interrupt
+ * @MEI_PG_EVENT_INTR_RECEIVED: the driver received pg event interrupt
  */
 enum mei_pg_event {
 	MEI_PG_EVENT_IDLE,
 	MEI_PG_EVENT_WAIT,
 	MEI_PG_EVENT_RECEIVED,
+	MEI_PG_EVENT_INTR_WAIT,
+	MEI_PG_EVENT_INTR_RECEIVED,
 };
 
 /**

@@ -727,6 +733,11 @@ static inline enum mei_pg_state mei_pg_s
 	return dev->ops->pg_state(dev);
 }
 
+static inline bool mei_pg_in_transition(struct mei_device *dev)
+{
+	return dev->ops->pg_in_transition(dev);
+}
+
 static inline bool mei_pg_is_enabled(struct mei_device *dev)
 {
 	return dev->ops->pg_is_enabled(dev);

@@ -16,6 +16,7 @@
 
 #include <linux/pci.h>
 #include <linux/jiffies.h>
+#include <linux/ktime.h>
 #include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/irqreturn.h>

@@ -218,26 +219,25 @@ static u32 mei_txe_aliveness_get(struct
  *
  * Polls for HICR_HOST_ALIVENESS_RESP.ALIVENESS_RESP to be set
  *
- * Return: > 0 if the expected value was received, -ETIME otherwise
+ * Return: 0 if the expected value was received, -ETIME otherwise
  */
 static int mei_txe_aliveness_poll(struct mei_device *dev, u32 expected)
 {
 	struct mei_txe_hw *hw = to_txe_hw(dev);
-	int t = 0;
+	ktime_t stop, start;
 
+	start = ktime_get();
+	stop = ktime_add(start, ms_to_ktime(SEC_ALIVENESS_WAIT_TIMEOUT));
 	do {
 		hw->aliveness = mei_txe_aliveness_get(dev);
 		if (hw->aliveness == expected) {
 			dev->pg_event = MEI_PG_EVENT_IDLE;
-			dev_dbg(dev->dev,
-				"aliveness settled after %d msecs\n", t);
-			return t;
+			dev_dbg(dev->dev, "aliveness settled after %lld usecs\n",
+				ktime_to_us(ktime_sub(ktime_get(), start)));
+			return 0;
 		}
-		mutex_unlock(&dev->device_lock);
-		msleep(MSEC_PER_SEC / 5);
-		mutex_lock(&dev->device_lock);
-		t += MSEC_PER_SEC / 5;
-	} while (t < SEC_ALIVENESS_WAIT_TIMEOUT);
+		usleep_range(20, 50);
+	} while (ktime_before(ktime_get(), stop));
 
 	dev->pg_event = MEI_PG_EVENT_IDLE;
 	dev_err(dev->dev, "aliveness timed out\n");

@@ -92,6 +92,14 @@ static void reset_context(void *info)
 	unsigned int cpu = smp_processor_id();
 	struct mm_struct *mm = current->active_mm;
 
+	/*
+	 * current->active_mm could be init_mm for the idle thread immediately
+	 * after secondary CPU boot or hotplug. TTBR0_EL1 is already set to
+	 * the reserved value, so no need to reset any context.
+	 */
+	if (mm == &init_mm)
+		return;
+
 	smp_rmb();
 	asid = cpu_last_asid + cpu;
 

@@ -260,7 +260,7 @@ static void __init free_unused_memmap(vo
 		 * memmap entries are valid from the bank end aligned to
 		 * MAX_ORDER_NR_PAGES.
 		 */
-		prev_end = ALIGN(start + __phys_to_pfn(reg->size),
+		prev_end = ALIGN(__phys_to_pfn(reg->base + reg->size),
 				 MAX_ORDER_NR_PAGES);
 	}
 

@@ -195,6 +195,8 @@ static struct kmem_cache *scan_area_cach
 
 /* set if tracing memory operations is enabled */
 static int kmemleak_enabled;
+/* same as above but only for the kmemleak_free() callback */
+static int kmemleak_free_enabled;
 /* set in the late_initcall if there were no errors */
 static int kmemleak_initialized;
 /* enables or disables early logging of the memory operations */

@@ -942,7 +944,7 @@ void __ref kmemleak_free(const void *ptr
 {
 	pr_debug("%s(0x%p)\n", __func__, ptr);
 
-	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
+	if (kmemleak_free_enabled && ptr && !IS_ERR(ptr))
 		delete_object_full((unsigned long)ptr);
 	else if (kmemleak_early_log)
 		log_early(KMEMLEAK_FREE, ptr, 0, 0);

@@ -982,7 +984,7 @@ void __ref kmemleak_free_percpu(const vo
 
 	pr_debug("%s(0x%p)\n", __func__, ptr);
 
-	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
+	if (kmemleak_free_enabled && ptr && !IS_ERR(ptr))
 		for_each_possible_cpu(cpu)
 			delete_object_full((unsigned long)per_cpu_ptr(ptr,
 								      cpu));

@@ -1750,6 +1752,13 @@ static void kmemleak_do_cleanup(struct w
 	mutex_lock(&scan_mutex);
 	stop_scan_thread();
 
+	/*
+	 * Once the scan thread has stopped, it is safe to no longer track
+	 * object freeing. Ordering of the scan thread stopping and the memory
+	 * accesses below is guaranteed by the kthread_stop() function.
+	 */
+	kmemleak_free_enabled = 0;
+
 	if (!kmemleak_found_leaks)
 		__kmemleak_do_cleanup();
 	else

@@ -1776,6 +1785,8 @@ static void kmemleak_disable(void)
 	/* check whether it is too early for a kernel thread */
 	if (kmemleak_initialized)
 		schedule_work(&cleanup_work);
+	else
+		kmemleak_free_enabled = 0;
 
 	pr_info("Kernel memory leak detector disabled\n");
 }

@@ -1840,8 +1851,10 @@ void __init kmemleak_init(void)
 	if (kmemleak_error) {
 		local_irq_restore(flags);
 		return;
-	} else
+	} else {
 		kmemleak_enabled = 1;
+		kmemleak_free_enabled = 1;
+	}
 	local_irq_restore(flags);
 
 	/*

@@ -28,7 +28,8 @@
 extern void kmemleak_init(void) __ref;
 extern void kmemleak_alloc(const void *ptr, size_t size, int min_count,
 			   gfp_t gfp) __ref;
-extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size) __ref;
+extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
+				  gfp_t gfp) __ref;
 extern void kmemleak_free(const void *ptr) __ref;
 extern void kmemleak_free_part(const void *ptr, size_t size) __ref;
 extern void kmemleak_free_percpu(const void __percpu *ptr) __ref;

@@ -71,7 +72,8 @@ static inline void kmemleak_alloc_recurs
 					    gfp_t gfp)
 {
 }
-static inline void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size)
+static inline void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
+					 gfp_t gfp)
 {
 }
 static inline void kmemleak_free(const void *ptr)

@@ -909,12 +909,13 @@ EXPORT_SYMBOL_GPL(kmemleak_alloc);
  * kmemleak_alloc_percpu - register a newly allocated __percpu object
  * @ptr:	__percpu pointer to beginning of the object
  * @size:	size of the object
+ * @gfp:	flags used for kmemleak internal memory allocations
  *
  * This function is called from the kernel percpu allocator when a new object
- * (memory block) is allocated (alloc_percpu). It assumes GFP_KERNEL
- * allocation.
+ * (memory block) is allocated (alloc_percpu).
  */
-void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size)
+void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
+				 gfp_t gfp)
 {
 	unsigned int cpu;
 

@@ -927,7 +928,7 @@ void __ref kmemleak_alloc_percpu(const v
 	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
 		for_each_possible_cpu(cpu)
 			create_object((unsigned long)per_cpu_ptr(ptr, cpu),
-				      size, 0, GFP_KERNEL);
+				      size, 0, gfp);
 	else if (kmemleak_early_log)
 		log_early(KMEMLEAK_ALLOC_PERCPU, ptr, size, 0);
 }

@@ -1030,7 +1030,7 @@ area_found:
 		memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
 
 	ptr = __addr_to_pcpu_ptr(chunk->base_addr + off);
-	kmemleak_alloc_percpu(ptr, size);
+	kmemleak_alloc_percpu(ptr, size, gfp);
 	return ptr;
 
 fail_unlock:

@@ -1971,35 +1971,41 @@ retry_cpuset:
 	pol = get_vma_policy(vma, addr);
 	cpuset_mems_cookie = read_mems_allowed_begin();
 
-	if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage &&
-					pol->mode != MPOL_INTERLEAVE)) {
+	if (pol->mode == MPOL_INTERLEAVE) {
+		unsigned nid;
+
+		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
+		mpol_cond_put(pol);
+		page = alloc_page_interleave(gfp, order, nid);
+		goto out;
+	}
+
+	if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) {
+		int hpage_node = node;
+
 		/*
 		 * For hugepage allocation and non-interleave policy which
-		 * allows the current node, we only try to allocate from the
-		 * current node and don't fall back to other nodes, as the
-		 * cost of remote accesses would likely offset THP benefits.
+		 * allows the current node (or other explicitly preferred
+		 * node) we only try to allocate from the current/preferred
+		 * node and don't fall back to other nodes, as the cost of
+		 * remote accesses would likely offset THP benefits.
 		 *
 		 * If the policy is interleave, or does not allow the current
 		 * node in its nodemask, we allocate the standard way.
 		 */
+		if (pol->mode == MPOL_PREFERRED &&
+						!(pol->flags & MPOL_F_LOCAL))
+			hpage_node = pol->v.preferred_node;
+
 		nmask = policy_nodemask(gfp, pol);
-		if (!nmask || node_isset(node, *nmask)) {
+		if (!nmask || node_isset(hpage_node, *nmask)) {
 			mpol_cond_put(pol);
-			page = alloc_pages_exact_node(node,
+			page = alloc_pages_exact_node(hpage_node,
 						gfp | __GFP_THISNODE, order);
 			goto out;
 		}
 	}
 
-	if (pol->mode == MPOL_INTERLEAVE) {
-		unsigned nid;
-
-		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
-		mpol_cond_put(pol);
-		page = alloc_page_interleave(gfp, order, nid);
-		goto out;
-	}
-
 	nmask = policy_nodemask(gfp, pol);
 	zl = policy_zonelist(gfp, pol, node);
 	mpol_cond_put(pol);

@@ -65,6 +65,8 @@ static int
 isert_rdma_accept(struct isert_conn *isert_conn);
 struct rdma_cm_id *isert_setup_id(struct isert_np *isert_np);
 
+static void isert_release_work(struct work_struct *work);
+
 static inline bool
 isert_prot_cmd(struct isert_conn *conn, struct se_cmd *cmd)
 {

@@ -604,6 +606,7 @@ isert_connect_request(struct rdma_cm_id
 	mutex_init(&isert_conn->conn_mutex);
 	spin_lock_init(&isert_conn->conn_lock);
 	INIT_LIST_HEAD(&isert_conn->conn_fr_pool);
+	INIT_WORK(&isert_conn->release_work, isert_release_work);
 
 	isert_conn->conn_cm_id = cma_id;
 

@@ -863,6 +866,7 @@ isert_disconnected_handler(struct rdma_c
 {
 	struct isert_np *isert_np = cma_id->context;
 	struct isert_conn *isert_conn;
+	bool terminating = false;
 
 	if (isert_np->np_cm_id == cma_id)
 		return isert_np_cma_handler(cma_id->context, event);

@@ -870,12 +874,25 @@ isert_disconnected_handler(struct rdma_c
 	isert_conn = cma_id->qp->qp_context;
 
 	mutex_lock(&isert_conn->conn_mutex);
+	terminating = (isert_conn->state == ISER_CONN_TERMINATING);
 	isert_conn_terminate(isert_conn);
 	mutex_unlock(&isert_conn->conn_mutex);
 
 	isert_info("conn %p completing conn_wait\n", isert_conn);
 	complete(&isert_conn->conn_wait);
 
+	if (terminating)
+		goto out;
+
+	mutex_lock(&isert_np->np_accept_mutex);
+	if (!list_empty(&isert_conn->conn_accept_node)) {
+		list_del_init(&isert_conn->conn_accept_node);
+		isert_put_conn(isert_conn);
+		queue_work(isert_release_wq, &isert_conn->release_work);
+	}
+	mutex_unlock(&isert_np->np_accept_mutex);
+
+out:
 	return 0;
 }
 

@@ -3305,7 +3322,6 @@ static void isert_wait_conn(struct iscsi
 	isert_wait4flush(isert_conn);
 	isert_wait4logout(isert_conn);
 
-	INIT_WORK(&isert_conn->release_work, isert_release_work);
 	queue_work(isert_release_wq, &isert_conn->release_work);
 }
 

@@ -2318,7 +2318,7 @@ int regmap_bulk_read(struct regmap *map,
 					  &ival);
 			if (ret != 0)
 				return ret;
-			memcpy(val + (i * val_bytes), &ival, val_bytes);
+			map->format.format_val(val + (i * val_bytes), ival, 0);
 		}
 	}
 

@@ -945,11 +945,10 @@ EXPORT_SYMBOL_GPL(devm_regmap_init);
 static void regmap_field_init(struct regmap_field *rm_field,
 	struct regmap *regmap, struct reg_field reg_field)
 {
-	int field_bits = reg_field.msb - reg_field.lsb + 1;
 	rm_field->regmap = regmap;
 	rm_field->reg = reg_field.reg;
 	rm_field->shift = reg_field.lsb;
-	rm_field->mask = ((BIT(field_bits) - 1) << reg_field.lsb);
+	rm_field->mask = GENMASK(reg_field.msb, reg_field.lsb);
 	rm_field->id_size = reg_field.id_size;
 	rm_field->id_offset = reg_field.id_offset;
 }

@@ -88,7 +88,7 @@ enum max77686_ramp_rate {
 };
 
 struct max77686_data {
-	u64 gpio_enabled:MAX77686_REGULATORS;
+	DECLARE_BITMAP(gpio_enabled, MAX77686_REGULATORS);
 
 	/* Array indexed by regulator id */
 	unsigned int opmode[MAX77686_REGULATORS];

@@ -121,7 +121,7 @@ static unsigned int max77686_map_normal_
 	case MAX77686_BUCK8:
 	case MAX77686_BUCK9:
 	case MAX77686_LDO20 ... MAX77686_LDO22:
-		if (max77686->gpio_enabled & (1 << id))
+		if (test_bit(id, max77686->gpio_enabled))
 			return MAX77686_GPIO_CONTROL;
 	}
 

@@ -277,7 +277,7 @@ static int max77686_of_parse_cb(struct d
 	}
 
 	if (gpio_is_valid(config->ena_gpio)) {
-		max77686->gpio_enabled |= (1 << desc->id);
+		set_bit(desc->id, max77686->gpio_enabled);
 
 		return regmap_update_bits(config->regmap, desc->enable_reg,
 					  desc->enable_mask,

@@ -770,7 +770,7 @@ static int suspend_prepare(struct regula
 static void print_constraints(struct regulator_dev *rdev)
 {
 	struct regulation_constraints *constraints = rdev->constraints;
-	char buf[80] = "";
+	char buf[160] = "";
 	int count = 0;
 	int ret;
 

@@ -179,7 +179,9 @@ static int klp_find_object_symbol(const
 		.count = 0
 	};
 
+	mutex_lock(&module_mutex);
 	kallsyms_on_each_symbol(klp_find_callback, &args);
+	mutex_unlock(&module_mutex);
 
 	if (args.count == 0)
 		pr_err("symbol '%s' not found in symbol table\n", name);

@@ -219,13 +221,19 @@ static int klp_verify_vmlinux_symbol(con
 		.name = name,
 		.addr = addr,
 	};
+	int ret;
 
-	if (kallsyms_on_each_symbol(klp_verify_callback, &args))
-		return 0;
+	mutex_lock(&module_mutex);
+	ret = kallsyms_on_each_symbol(klp_verify_callback, &args);
+	mutex_unlock(&module_mutex);
+
+	if (!ret) {
+		pr_err("symbol '%s' not found at specified address 0x%016lx, kernel mismatch?\n",
+			name, addr);
+		return -EINVAL;
+	}
 
-	pr_err("symbol '%s' not found at specified address 0x%016lx, kernel mismatch?\n",
-		name, addr);
-	return -EINVAL;
+	return 0;
 }
 
 static int klp_find_verify_func_addr(struct klp_object *obj,

@@ -61,6 +61,12 @@ enum orion_spi_type {
 
 struct orion_spi_dev {
 	enum orion_spi_type	typ;
+	/*
+	 * min_divisor and max_hz should be exclusive, the only we can
+	 * have both is for managing the armada-370-spi case with old
+	 * device tree
+	 */
+	unsigned long		max_hz;
 	unsigned int		min_divisor;
 	unsigned int		max_divisor;
 	u32			prescale_mask;

@@ -387,8 +393,9 @@ static const struct orion_spi_dev orion_
 
 static const struct orion_spi_dev armada_spi_dev_data = {
 	.typ = ARMADA_SPI,
-	.min_divisor = 1,
+	.min_divisor = 4,
 	.max_divisor = 1920,
+	.max_hz = 50000000,
 	.prescale_mask = ARMADA_SPI_CLK_PRESCALE_MASK,
 };
 

@@ -454,7 +461,21 @@ static int orion_spi_probe(struct platfo
 		goto out;
 
 	tclk_hz = clk_get_rate(spi->clk);
-	master->max_speed_hz = DIV_ROUND_UP(tclk_hz, devdata->min_divisor);
+
+	/*
+	 * With old device tree, armada-370-spi could be used with
+	 * Armada XP, however for this SoC the maximum frequency is
+	 * 50MHz instead of tclk/4. On Armada 370, tclk cannot be
+	 * higher than 200MHz. So, in order to be able to handle both
+	 * SoCs, we can take the minimum of 50MHz and tclk/4.
+	 */
+	if (of_device_is_compatible(pdev->dev.of_node,
+					"marvell,armada-370-spi"))
+		master->max_speed_hz = min(devdata->max_hz,
+				DIV_ROUND_UP(tclk_hz, devdata->min_divisor));
+	else
+		master->max_speed_hz =
+			DIV_ROUND_UP(tclk_hz, devdata->min_divisor);
 	master->min_speed_hz = DIV_ROUND_UP(tclk_hz, devdata->max_divisor);
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);

@@ -396,6 +396,36 @@ static void srp_reconnect_work(struct wo
 	}
 }
 
+/**
+ * scsi_request_fn_active() - number of kernel threads inside scsi_request_fn()
+ * @shost: SCSI host for which to count the number of scsi_request_fn() callers.
+ *
+ * To do: add support for scsi-mq in this function.
+ */
+static int scsi_request_fn_active(struct Scsi_Host *shost)
+{
+	struct scsi_device *sdev;
+	struct request_queue *q;
+	int request_fn_active = 0;
+
+	shost_for_each_device(sdev, shost) {
+		q = sdev->request_queue;
+
+		spin_lock_irq(q->queue_lock);
+		request_fn_active += q->request_fn_active;
+		spin_unlock_irq(q->queue_lock);
+	}
+
+	return request_fn_active;
+}
+
+/* Wait until ongoing shost->hostt->queuecommand() calls have finished. */
+static void srp_wait_for_queuecommand(struct Scsi_Host *shost)
+{
+	while (scsi_request_fn_active(shost))
+		msleep(20);
+}
+
 static void __rport_fail_io_fast(struct srp_rport *rport)
 {
 	struct Scsi_Host *shost = rport_to_shost(rport);

@@ -504,27 +534,6 @@ void srp_start_tl_fail_timers(struct srp
 EXPORT_SYMBOL(srp_start_tl_fail_timers);
 
 /**
- * scsi_request_fn_active() - number of kernel threads inside scsi_request_fn()
- * @shost: SCSI host for which to count the number of scsi_request_fn() callers.
- */
-static int scsi_request_fn_active(struct Scsi_Host *shost)
-{
-	struct scsi_device *sdev;
-	struct request_queue *q;
-	int request_fn_active = 0;
-
-	shost_for_each_device(sdev, shost) {
-		q = sdev->request_queue;
-
-		spin_lock_irq(q->queue_lock);
-		request_fn_active += q->request_fn_active;
-		spin_unlock_irq(q->queue_lock);
-	}
-
-	return request_fn_active;
-}
-
-/**
  * srp_reconnect_rport() - reconnect to an SRP target port
  * @rport: SRP target port.
  *

@@ -559,8 +568,7 @@ int srp_reconnect_rport(struct srp_rport
 	if (res)
 		goto out;
 	scsi_target_block(&shost->shost_gendev);
-	while (scsi_request_fn_active(shost))
-		msleep(20);
+	srp_wait_for_queuecommand(shost);
 	res = rport->state != SRP_RPORT_LOST ? i->f->reconnect(rport) : -ENODEV;
 	pr_debug("%s (state %d): transport.reconnect() returned %d\n",
 		 dev_name(&shost->shost_gendev), rport->state, res);

@@ -439,8 +439,10 @@ static void __rport_fail_io_fast(struct
 
 	/* Involve the LLD if possible to terminate all I/O on the rport. */
 	i = to_srp_internal(shost->transportt);
-	if (i->f->terminate_rport_io)
+	if (i->f->terminate_rport_io) {
+		srp_wait_for_queuecommand(shost);
 		i->f->terminate_rport_io(rport);
+	}
 }
 
 /**

@@ -3171,11 +3171,11 @@ static ssize_t srp_create_target(struct
 
 	ret = srp_parse_options(buf, target);
 	if (ret)
-		goto err;
+		goto out;
 
 	ret = scsi_init_shared_tag_map(target_host, target_host->can_queue);
 	if (ret)
-		goto err;
+		goto out;
 
 	target->req_ring_size = target->queue_size - SRP_TSK_MGMT_SQ_SIZE;
 

@@ -3186,7 +3186,7 @@ static ssize_t srp_create_target(struct
 			     be64_to_cpu(target->ioc_guid),
 			     be64_to_cpu(target->initiator_ext));
 		ret = -EEXIST;
-		goto err;
+		goto out;
 	}
 
 	if (!srp_dev->has_fmr && !srp_dev->has_fr && !target->allow_ext_sg &&

@@ -3207,7 +3207,7 @@ static ssize_t srp_create_target(struct
 	spin_lock_init(&target->lock);
 	ret = ib_query_gid(ibdev, host->port, 0, &target->sgid);
 	if (ret)
-		goto err;
+		goto out;
 
 	ret = -ENOMEM;
 	target->ch_count = max_t(unsigned, num_online_nodes(),

@@ -3218,7 +3218,7 @@ static ssize_t srp_create_target(struct
 	target->ch = kcalloc(target->ch_count, sizeof(*target->ch),
 			     GFP_KERNEL);
 	if (!target->ch)
-		goto err;
+		goto out;
 
 	node_idx = 0;
 	for_each_online_node(node) {

@@ -3314,9 +3314,6 @@ err_disconnect:
 	}
 
 	kfree(target->ch);
-
-err:
-	scsi_host_put(target_host);
 	goto out;
 }
 

@@ -992,8 +992,6 @@ static int srp_connect_ch(struct srp_rdm
 
 	WARN_ON_ONCE(!multich && target->connected);
 
-	target->qp_in_error = false;
-
 	ret = srp_lookup_path(ch);
 	if (ret)
 		return ret;

@@ -1242,6 +1240,9 @@ static int srp_rport_reconnect(struct sr
 		for (j = 0; j < target->queue_size; ++j)
 			list_add(&ch->tx_ring[j]->list, &ch->free_tx);
 	}
+
+	target->qp_in_error = false;
+
 	for (i = 0; i < target->ch_count; i++) {
 		ch = &target->ch[i];
 		if (ret || !ch->target) {

@@ -464,14 +464,13 @@ static struct srp_fr_pool *srp_alloc_fr_
  */
 static void srp_destroy_qp(struct srp_rdma_ch *ch)
 {
-	struct srp_target_port *target = ch->target;
 	static struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR };
 	static struct ib_recv_wr wr = { .wr_id = SRP_LAST_WR_ID };
 	struct ib_recv_wr *bad_wr;
 	int ret;
 
 	/* Destroying a QP and reusing ch->done is only safe if not connected */
-	WARN_ON_ONCE(target->connected);
+	WARN_ON_ONCE(ch->connected);
 
 	ret = ib_modify_qp(ch->qp, &attr, IB_QP_STATE);
 	WARN_ONCE(ret, "ib_cm_init_qp_attr() returned %d\n", ret);

@@ -810,35 +809,19 @@ static bool srp_queue_remove_work(struct
 	return changed;
 }
 
-static bool srp_change_conn_state(struct srp_target_port *target,
-				  bool connected)
-{
-	bool changed = false;
-
-	spin_lock_irq(&target->lock);
-	if (target->connected != connected) {
-		target->connected = connected;
-		changed = true;
-	}
-	spin_unlock_irq(&target->lock);
-
-	return changed;
-}
-
 static void srp_disconnect_target(struct srp_target_port *target)
 {
 	struct srp_rdma_ch *ch;
 	int i;
 
-	if (srp_change_conn_state(target, false)) {
-		/* XXX should send SRP_I_LOGOUT request */
+	/* XXX should send SRP_I_LOGOUT request */
 
-		for (i = 0; i < target->ch_count; i++) {
-			ch = &target->ch[i];
-			if (ch->cm_id && ib_send_cm_dreq(ch->cm_id, NULL, 0)) {
-				shost_printk(KERN_DEBUG, target->scsi_host,
-					     PFX "Sending CM DREQ failed\n");
-			}
+	for (i = 0; i < target->ch_count; i++) {
+		ch = &target->ch[i];
+		ch->connected = false;
+		if (ch->cm_id && ib_send_cm_dreq(ch->cm_id, NULL, 0)) {
+			shost_printk(KERN_DEBUG, target->scsi_host,
+				     PFX "Sending CM DREQ failed\n");
 		}
 	}
 }

@@ -985,12 +968,26 @@ static void srp_rport_delete(struct srp_
 	srp_queue_remove_work(target);
 }
 
+/**
+ * srp_connected_ch() - number of connected channels
+ * @target: SRP target port.
+ */
+static int srp_connected_ch(struct srp_target_port *target)
+{
+	int i, c = 0;
+
+	for (i = 0; i < target->ch_count; i++)
+		c += target->ch[i].connected;
+
+	return c;
+}
+
 static int srp_connect_ch(struct srp_rdma_ch *ch, bool multich)
 {
 	struct srp_target_port *target = ch->target;
 	int ret;
 
-	WARN_ON_ONCE(!multich && target->connected);
+	WARN_ON_ONCE(!multich && srp_connected_ch(target) > 0);
 
 	ret = srp_lookup_path(ch);
 	if (ret)

@@ -1013,7 +1010,7 @@ static int srp_connect_ch(struct srp_rdm
 		 */
 		switch (ch->status) {
 		case 0:
-			srp_change_conn_state(target, true);
+			ch->connected = true;
 			return 0;
 
 		case SRP_PORT_REDIRECT:

@@ -1929,7 +1926,7 @@ static void srp_handle_qp_err(u64 wr_id,
 		return;
 	}
 
-	if (target->connected && !target->qp_in_error) {
+	if (ch->connected && !target->qp_in_error) {
 		if (wr_id & LOCAL_INV_WR_ID_MASK) {
 			shost_printk(KERN_ERR, target->scsi_host, PFX
 				     "LOCAL_INV failed with status %d\n",

@@ -2367,7 +2364,7 @@ static int srp_cm_handler(struct ib_cm_i
 	case IB_CM_DREQ_RECEIVED:
 		shost_printk(KERN_WARNING, target->scsi_host,
 			     PFX "DREQ received - connection closed\n");
-		srp_change_conn_state(target, false);
+		ch->connected = false;
 		if (ib_send_cm_drep(cm_id, NULL, 0))
 			shost_printk(KERN_ERR, target->scsi_host,
 				     PFX "Sending CM DREP failed\n");