aufs: pin or lock the parent dir and the child on a branch

To create/delete/rename files including copy-up, aufs acquires several
locks on the branch fs internally. These lock/unlock operations are
consolidated into struct au_pin in this commit.
au_pin handles
- LOCKDEP class
- re-validate/verify
- suspend/resume HNOTIFY

See also lookup.txt in later commit.
Signed-off-by: J. R. Okajima <hooanon05g@gmail.com>

fs/aufs/Makefile

@@ -13,8 +13,8 @@ obj-$(CONFIG_AUFS_FS) += aufs.o
 aufs-y := module.o sbinfo.o super.o branch.o xino.o sysaufs.o opts.o \
 	wkq.o vfsub.o dcsub.o \
 	cpup.o whout.o \
-	dinfo.o \
-	iinfo.o inode.o
+	dinfo.o dentry.o \
+	iinfo.o inode.o i_op.o
 
 # all are boolean
 aufs-$(CONFIG_PROC_FS) += procfs.o plink.o

fs/aufs/debug.h

@@ -80,6 +80,9 @@ AuStubInt0(au_debug_test, void)
 		AuDbg("err %ld\n", PTR_ERR(p)); \
 } while (0)
 
+/* dirty macros for debug print, use with "%.*s" and caution */
+#define AuLNPair(qstr)		(qstr)->len, (qstr)->name
+
 /* ---------------------------------------------------------------------- */
 
 struct dentry;

fs/aufs/dentry.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2019 Junjiro R. Okajima
+ */
+
+/*
+ * lookup and dentry operations
+ */
+
+#include <linux/iversion.h>
+#include <linux/namei.h>
+#include "aufs.h"
+
+/* subset of struct inode */
+struct au_iattr {
+	unsigned long		i_ino;
+	/* unsigned int		i_nlink; */
+	kuid_t			i_uid;
+	kgid_t			i_gid;
+	u64			i_version;
+/*
+	loff_t			i_size;
+	blkcnt_t		i_blocks;
+*/
+	umode_t			i_mode;
+};
+
+static void au_iattr_save(struct au_iattr *ia, struct inode *h_inode)
+{
+	ia->i_ino = h_inode->i_ino;
+	/* ia->i_nlink = h_inode->i_nlink; */
+	ia->i_uid = h_inode->i_uid;
+	ia->i_gid = h_inode->i_gid;
+	ia->i_version = inode_query_iversion(h_inode);
+/*
+	ia->i_size = h_inode->i_size;
+	ia->i_blocks = h_inode->i_blocks;
+*/
+	ia->i_mode = (h_inode->i_mode & S_IFMT);
+}
+
+static int au_iattr_test(struct au_iattr *ia, struct inode *h_inode)
+{
+	return ia->i_ino != h_inode->i_ino
+		/* || ia->i_nlink != h_inode->i_nlink */
+		|| !uid_eq(ia->i_uid, h_inode->i_uid)
+		|| !gid_eq(ia->i_gid, h_inode->i_gid)
+		|| !inode_eq_iversion(h_inode, ia->i_version)
+/*
+		|| ia->i_size != h_inode->i_size
+		|| ia->i_blocks != h_inode->i_blocks
+*/
+		|| ia->i_mode != (h_inode->i_mode & S_IFMT);
+}
+
+static int au_h_verify_dentry(struct dentry *h_dentry, struct dentry *h_parent,
+			      struct au_branch *br)
+{
+	int err;
+	struct au_iattr ia;
+	struct inode *h_inode;
+	struct dentry *h_d;
+	struct super_block *h_sb;
+
+	err = 0;
+	memset(&ia, -1, sizeof(ia));
+	h_sb = h_dentry->d_sb;
+	h_inode = NULL;
+	if (d_is_positive(h_dentry)) {
+		h_inode = d_inode(h_dentry);
+		au_iattr_save(&ia, h_inode);
+	} else if (au_test_nfs(h_sb))
+		/* nfs d_revalidate may return 0 for negative dentry */
+		goto out;
+
+	/* main purpose is namei.c:cached_lookup() and d_revalidate */
+	h_d = vfsub_lkup_one(&h_dentry->d_name, h_parent);
+	err = PTR_ERR(h_d);
+	if (IS_ERR(h_d))
+		goto out;
+
+	err = 0;
+	if (unlikely(h_d != h_dentry
+		     || d_inode(h_d) != h_inode
+		     || (h_inode && au_iattr_test(&ia, h_inode))))
+		err = -EBUSY;
+	dput(h_d);
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+int au_h_verify(struct dentry *h_dentry, struct inode *h_dir,
+		struct dentry *h_parent, struct au_branch *br)
+{
+	int err;
+
+	err = 0;
+	if (!au_test_fs_remote(h_dentry->d_sb)) {
+		IMustLock(h_dir);
+		err = (d_inode(h_dentry->d_parent) != h_dir);
+	} else
+		err = au_h_verify_dentry(h_dentry, h_parent, br);
+
+	return err;
+}

fs/aufs/dentry.h

@@ -31,6 +31,11 @@ struct au_dinfo {
 
 /* ---------------------------------------------------------------------- */
 
+/* dentry.c */
+struct au_branch;
+int au_h_verify(struct dentry *h_dentry, struct inode *h_dir,
+		struct dentry *h_parent, struct au_branch *br);
+
 /* dinfo.c */
 void au_di_init_once(void *_di);
 struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc);

fs/aufs/i_op.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2019 Junjiro R. Okajima
+ */
+
+/*
+ * inode operations (except add/del/rename)
+ */
+
+#include "aufs.h"
+
+void au_pin_hdir_unlock(struct au_pin *p)
+{
+	if (p->hdir)
+		inode_unlock(p->hdir->hi_inode);
+}
+
+int au_pin_hdir_lock(struct au_pin *p)
+{
+	int err;
+
+	err = 0;
+	if (!p->hdir)
+		goto out;
+
+	/* even if an error happens later, keep this lock */
+	inode_lock_nested(p->hdir->hi_inode, p->lsc_hi);
+
+	err = -EBUSY;
+	if (unlikely(p->hdir->hi_inode != d_inode(p->h_parent)))
+		goto out;
+
+	err = 0;
+	if (p->h_dentry)
+		err = au_h_verify(p->h_dentry, p->hdir->hi_inode, p->h_parent,
+				  p->br);
+
+out:
+	return err;
+}
+
+int au_pin_hdir_relock(struct au_pin *p)
+{
+	int err, i;
+	struct inode *h_i;
+	struct dentry *h_d[] = {
+		p->h_dentry,
+		p->h_parent
+	};
+
+	err = au_pin_hdir_lock(p);
+	if (unlikely(err))
+		goto out;
+
+	for (i = 0; !err && i < sizeof(h_d)/sizeof(*h_d); i++) {
+		if (!h_d[i])
+			continue;
+		if (d_is_positive(h_d[i])) {
+			h_i = d_inode(h_d[i]);
+			err = !h_i->i_nlink;
+		}
+	}
+
+out:
+	return err;
+}
+
+static void au_pin_hdir_set_owner(struct au_pin *p, struct task_struct *task)
+{
+#if !defined(CONFIG_RWSEM_GENERIC_SPINLOCK) && defined(CONFIG_RWSEM_SPIN_ON_OWNER)
+	p->hdir->hi_inode->i_rwsem.owner = task;
+#endif
+}
+
+void au_pin_hdir_acquire_nest(struct au_pin *p)
+{
+	if (p->hdir) {
+		rwsem_acquire_nest(&p->hdir->hi_inode->i_rwsem.dep_map,
+				   p->lsc_hi, 0, NULL, _RET_IP_);
+		au_pin_hdir_set_owner(p, current);
+	}
+}
+
+void au_pin_hdir_release(struct au_pin *p)
+{
+	if (p->hdir) {
+		au_pin_hdir_set_owner(p, p->task);
+		rwsem_release(&p->hdir->hi_inode->i_rwsem.dep_map, 1, _RET_IP_);
+	}
+}
+
+struct dentry *au_pinned_h_parent(struct au_pin *pin)
+{
+	if (pin && pin->parent)
+		return au_h_dptr(pin->parent, pin->bindex);
+	return NULL;
+}
+
+void au_unpin(struct au_pin *p)
+{
+	if (p->hdir)
+		au_pin_hdir_unlock(p);
+	if (p->h_mnt && au_ftest_pin(p->flags, MNT_WRITE))
+		vfsub_mnt_drop_write(p->h_mnt);
+	if (!p->hdir)
+		return;
+
+	if (!au_ftest_pin(p->flags, DI_LOCKED))
+		di_read_unlock(p->parent, AuLock_IR);
+	iput(p->hdir->hi_inode);
+	dput(p->parent);
+	p->parent = NULL;
+	p->hdir = NULL;
+	p->h_mnt = NULL;
+	/* do not clear p->task */
+}
+
+int au_do_pin(struct au_pin *p)
+{
+	int err;
+	struct super_block *sb;
+	struct inode *h_dir;
+
+	err = 0;
+	sb = p->dentry->d_sb;
+	p->br = au_sbr(sb, p->bindex);
+	if (IS_ROOT(p->dentry)) {
+		if (au_ftest_pin(p->flags, MNT_WRITE)) {
+			p->h_mnt = au_br_mnt(p->br);
+			err = vfsub_mnt_want_write(p->h_mnt);
+			if (unlikely(err)) {
+				au_fclr_pin(p->flags, MNT_WRITE);
+				goto out_err;
+			}
+		}
+		goto out;
+	}
+
+	p->h_dentry = NULL;
+	if (p->bindex <= au_dbbot(p->dentry))
+		p->h_dentry = au_h_dptr(p->dentry, p->bindex);
+
+	p->parent = dget_parent(p->dentry);
+	if (!au_ftest_pin(p->flags, DI_LOCKED))
+		di_read_lock(p->parent, AuLock_IR, p->lsc_di);
+
+	h_dir = NULL;
+	p->h_parent = au_h_dptr(p->parent, p->bindex);
+	p->hdir = au_hi(d_inode(p->parent), p->bindex);
+	if (p->hdir)
+		h_dir = p->hdir->hi_inode;
+
+	/*
+	 * udba case, or
+	 * if DI_LOCKED is not set, then p->parent may be different
+	 * and h_parent can be NULL.
+	 */
+	if (unlikely(!p->hdir || !h_dir || !p->h_parent)) {
+		err = -EBUSY;
+		if (!au_ftest_pin(p->flags, DI_LOCKED))
+			di_read_unlock(p->parent, AuLock_IR);
+		dput(p->parent);
+		p->parent = NULL;
+		goto out_err;
+	}
+
+	if (au_ftest_pin(p->flags, MNT_WRITE)) {
+		p->h_mnt = au_br_mnt(p->br);
+		err = vfsub_mnt_want_write(p->h_mnt);
+		if (unlikely(err)) {
+			au_fclr_pin(p->flags, MNT_WRITE);
+			if (!au_ftest_pin(p->flags, DI_LOCKED))
+				di_read_unlock(p->parent, AuLock_IR);
+			dput(p->parent);
+			p->parent = NULL;
+			goto out_err;
+		}
+	}
+
+	au_igrab(h_dir);
+	err = au_pin_hdir_lock(p);
+	if (!err)
+		goto out; /* success */
+
+	au_unpin(p);
+
+out_err:
+	pr_err("err %d\n", err);
+	err = -EBUSY;
+out:
+	return err;
+}
+
+void au_pin_init(struct au_pin *p, struct dentry *dentry,
+		 aufs_bindex_t bindex, int lsc_di, int lsc_hi,
+		 unsigned char flags)
+{
+	p->dentry = dentry;
+	p->lsc_di = lsc_di;
+	p->lsc_hi = lsc_hi;
+	p->flags = flags;
+	p->bindex = bindex;
+
+	p->parent = NULL;
+	p->hdir = NULL;
+	p->h_mnt = NULL;
+
+	p->h_dentry = NULL;
+	p->h_parent = NULL;
+	p->br = NULL;
+	p->task = current;
+}
+
+int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex,
+	   unsigned char flags)
+{
+	au_pin_init(pin, dentry, bindex, AuLsc_DI_PARENT, AuLsc_I_PARENT2,
+		    flags);
+	return au_do_pin(pin);
+}

fs/aufs/inode.h

@@ -15,6 +15,8 @@
 #include <linux/fs.h>
 #include "rwsem.h"
 
+struct vfsmount;
+
 struct au_hinode {
 	struct inode		*hi_inode;
 	aufs_bindex_t		hi_id;
@@ -42,6 +44,38 @@ struct au_icntnr {
 	struct rcu_head		rcu;
 } ____cacheline_aligned_in_smp;
 
+/* au_pin flags */
+#define AuPin_DI_LOCKED		1
+#define AuPin_MNT_WRITE		(1 << 1)
+#define au_ftest_pin(flags, name)	((flags) & AuPin_##name)
+#define au_fset_pin(flags, name) \
+	do { (flags) |= AuPin_##name; } while (0)
+#define au_fclr_pin(flags, name) \
+	do { (flags) &= ~AuPin_##name; } while (0)
+
+struct au_pin {
+	/* input */
+	struct dentry *dentry;
+	unsigned char lsc_di, lsc_hi, flags;
+	aufs_bindex_t bindex;
+
+	/* output */
+	struct dentry *parent;
+	struct au_hinode *hdir;
+	struct vfsmount *h_mnt;
+
+	/* temporary unlock/relock for copyup */
+	struct dentry *h_dentry, *h_parent;
+	struct au_branch *br;
+	struct task_struct *task;
+};
+
+void au_pin_hdir_unlock(struct au_pin *p);
+int au_pin_hdir_lock(struct au_pin *p);
+int au_pin_hdir_relock(struct au_pin *p);
+void au_pin_hdir_acquire_nest(struct au_pin *p);
+void au_pin_hdir_release(struct au_pin *p);
+
 /* ---------------------------------------------------------------------- */
 
 static inline struct au_iinfo *au_ii(struct inode *inode)
@@ -57,6 +91,16 @@ struct inode *au_igrab(struct inode *inode);
 int au_test_h_perm(struct inode *h_inode, int mask);
 int au_test_h_perm_sio(struct inode *h_inode, int mask);
 
+/* i_op.c */
+struct dentry *au_pinned_h_parent(struct au_pin *pin);
+void au_pin_init(struct au_pin *pin, struct dentry *dentry,
+		 aufs_bindex_t bindex, int lsc_di, int lsc_hi,
+		 unsigned char flags);
+int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex,
+	   unsigned char flags) __must_check;
+int au_do_pin(struct au_pin *pin) __must_check;
+void au_unpin(struct au_pin *pin);
+
 /* iinfo.c */
 struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex);
 void au_hiput(struct au_hinode *hinode);
@@ -279,5 +323,55 @@ static inline struct au_hinode *au_hi(struct inode *inode, aufs_bindex_t bindex)
 	return au_hinode(au_ii(inode), bindex);
 }
 
+/* ---------------------------------------------------------------------- */
+
+static inline struct dentry *au_pinned_parent(struct au_pin *pin)
+{
+	if (pin)
+		return pin->parent;
+	return NULL;
+}
+
+static inline struct inode *au_pinned_h_dir(struct au_pin *pin)
+{
+	if (pin && pin->hdir)
+		return pin->hdir->hi_inode;
+	return NULL;
+}
+
+static inline struct au_hinode *au_pinned_hdir(struct au_pin *pin)
+{
+	if (pin)
+		return pin->hdir;
+	return NULL;
+}
+
+static inline void au_pin_set_dentry(struct au_pin *pin, struct dentry *dentry)
+{
+	if (pin)
+		pin->dentry = dentry;
+}
+
+static inline void au_pin_set_parent_lflag(struct au_pin *pin,
+					   unsigned char lflag)
+{
+	if (pin) {
+		if (lflag)
+			au_fset_pin(pin->flags, DI_LOCKED);
+		else
+			au_fclr_pin(pin->flags, DI_LOCKED);
+	}
+}
+
+#if 0 /* reserved */
+static inline void au_pin_set_parent(struct au_pin *pin, struct dentry *parent)
+{
+	if (pin) {
+		dput(pin->parent);
+		pin->parent = dget(parent);
+	}
+}
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* __AUFS_INODE_H__ */

fs/aufs/vfsub.c

@@ -66,6 +66,12 @@ out:
 	return path.dentry;
 }
 
+void vfsub_call_lkup_one(void *args)
+{
+	struct vfsub_lkup_one_args *a = args;
+	*a->errp = vfsub_lkup_one(a->name, a->parent);
+}
+
 /* ---------------------------------------------------------------------- */
 
 int vfsub_create(struct inode *dir, struct path *path, int mode, bool want_excl)

fs/aufs/vfsub.h

@@ -44,12 +44,20 @@ int vfsub_kern_path(const char *name, unsigned int flags, struct path *path);
 struct dentry *vfsub_lookup_one_len(const char *name, struct dentry *parent,
 				    int len);
 
+struct vfsub_lkup_one_args {
+	struct dentry **errp;
+	struct qstr *name;
+	struct dentry *parent;
+};
+
 static inline struct dentry *vfsub_lkup_one(struct qstr *name,
 					    struct dentry *parent)
 {
 	return vfsub_lookup_one_len(name->name, parent, name->len);
 }
 
+void vfsub_call_lkup_one(void *args);
+
 /* ---------------------------------------------------------------------- */
 
 static inline int vfsub_mnt_want_write(struct vfsmount *mnt)

fs/aufs/whout.c

@@ -446,9 +446,7 @@ static void reinit_br_wh(void *arg)
 
 	inode_lock_nested(hdir->hi_inode, AuLsc_I_PARENT);
 	wbr_wh_write_lock(wbr);
-	/* re-commit later */
-	/* err = au_h_verify(wbr->wbr_whbase, hdir->hi_inode, h_root, a->br); */
-	err = 0;
+	err = au_h_verify(wbr->wbr_whbase, hdir->hi_inode, h_root, a->br);
 	if (!err) {
 		h_path.dentry = wbr->wbr_whbase;
 		h_path.mnt = au_br_mnt(a->br);