aufs: ioctl, rdu (readdir in userspace)

For a directory which has millions of files, aufs VDIR consumes
much memory. In this case, RDU (readdir(3) in user-space) is definitely
better.
If you enable CONFIG_AUFS_RDU at compiling aufs, install libau.so from
aufs-util.git, and set some environment variables, then you can use this
feature. When readdir(3) in libau.so receives an aufs dir, it issues
ioctl(2) instead of regular readdir(3).
All merging and whiteout handling are done in userspace.
Signed-off-by: J. R. Okajima <hooanon05g@gmail.com>

fs/aufs/Kconfig

@@ -96,6 +96,18 @@ config AUFS_XATTR
 	branch attributes for EA.
 	See detail in aufs.5.
 
+config AUFS_RDU
+	bool "Readdir in userspace"
+	help
+	Aufs has two methods to provide a merged view for a directory,
+	by a user-space library and by kernel-space natively. The latter
+	is always enabled but sometimes large and slow.
+	If you enable this option, install the library in aufs2-util
+	package, and set some environment variables for your readdir(3),
+	then the work will be handled in user-space which generally
+	shows better performance in most cases.
+	See detail in aufs.5.
+
 config AUFS_DIRREN
 	bool "Workaround for rename(2)-ing a directory"
 	help

fs/aufs/Makefile

@@ -30,5 +30,6 @@ aufs-$(CONFIG_AUFS_EXPORT) += export.o
 aufs-$(CONFIG_AUFS_XATTR) += xattr.o
 aufs-$(CONFIG_FS_POSIX_ACL) += posix_acl.o
 aufs-$(CONFIG_AUFS_DIRREN) += dirren.o
+aufs-$(CONFIG_AUFS_RDU) += rdu.o
 aufs-$(CONFIG_AUFS_DEBUG) += debug.o
 aufs-$(CONFIG_AUFS_MAGIC_SYSRQ) += sysrq.o

fs/aufs/dir.h

@@ -101,5 +101,21 @@ int au_vdir_fill_de(struct file *file, struct dir_context *ctx);
 /* ioctl.c */
 long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg);
 
+#ifdef CONFIG_AUFS_RDU
+/* rdu.c */
+long au_rdu_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+#ifdef CONFIG_COMPAT
+long au_rdu_compat_ioctl(struct file *file, unsigned int cmd,
+			 unsigned long arg);
+#endif
+#else
+AuStub(long, au_rdu_ioctl, return -EINVAL, struct file *file,
+       unsigned int cmd, unsigned long arg)
+#ifdef CONFIG_COMPAT
+AuStub(long, au_rdu_compat_ioctl, return -EINVAL, struct file *file,
+       unsigned int cmd, unsigned long arg)
+#endif
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* __AUFS_DIR_H__ */

fs/aufs/ioctl.c

@@ -111,6 +111,11 @@ long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg)
 	long err;
 
 	switch (cmd) {
+	case AUFS_CTL_RDU:
+	case AUFS_CTL_RDU_INO:
+		err = au_rdu_ioctl(file, cmd, arg);
+		break;
+
 	case AUFS_CTL_WBR_FD:
 		err = au_wbr_fd(&file->f_path, (void __user *)arg);
 		break;
@@ -155,6 +160,11 @@ long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd,
 	long err;
 
 	switch (cmd) {
+	case AUFS_CTL_RDU:
+	case AUFS_CTL_RDU_INO:
+		err = au_rdu_compat_ioctl(file, cmd, arg);
+		break;
+
 	case AUFS_CTL_BRINFO:
 		err = au_brinfo_compat_ioctl(file, arg);
 		break;

fs/aufs/rdu.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2019 Junjiro R. Okajima
+ */
+
+/*
+ * readdir in userspace.
+ */
+
+#include <linux/compat.h>
+#include <linux/fs_stack.h>
+#include <linux/security.h>
+#include "aufs.h"
+
+/* bits for struct aufs_rdu.flags */
+#define	AuRdu_CALLED	1
+#define	AuRdu_CONT	(1 << 1)
+#define	AuRdu_FULL	(1 << 2)
+#define au_ftest_rdu(flags, name)	((flags) & AuRdu_##name)
+#define au_fset_rdu(flags, name) \
+	do { (flags) |= AuRdu_##name; } while (0)
+#define au_fclr_rdu(flags, name) \
+	do { (flags) &= ~AuRdu_##name; } while (0)
+
+struct au_rdu_arg {
+	struct dir_context		ctx;
+	struct aufs_rdu			*rdu;
+	union au_rdu_ent_ul		ent;
+	unsigned long			end;
+
+	struct super_block		*sb;
+	int				err;
+};
+
+static int au_rdu_fill(struct dir_context *ctx, const char *name, int nlen,
+		       loff_t offset, u64 h_ino, unsigned int d_type)
+{
+	int err, len;
+	struct au_rdu_arg *arg = container_of(ctx, struct au_rdu_arg, ctx);
+	struct aufs_rdu *rdu = arg->rdu;
+	struct au_rdu_ent ent;
+
+	err = 0;
+	arg->err = 0;
+	au_fset_rdu(rdu->cookie.flags, CALLED);
+	len = au_rdu_len(nlen);
+	if (arg->ent.ul + len  < arg->end) {
+		ent.ino = h_ino;
+		ent.bindex = rdu->cookie.bindex;
+		ent.type = d_type;
+		ent.nlen = nlen;
+		if (unlikely(nlen > AUFS_MAX_NAMELEN))
+			ent.type = DT_UNKNOWN;
+
+		/* unnecessary to support mmap_sem since this is a dir */
+		err = -EFAULT;
+		if (copy_to_user(arg->ent.e, &ent, sizeof(ent)))
+			goto out;
+		if (copy_to_user(arg->ent.e->name, name, nlen))
+			goto out;
+		/* the terminating NULL */
+		if (__put_user(0, arg->ent.e->name + nlen))
+			goto out;
+		err = 0;
+		/* AuDbg("%p, %.*s\n", arg->ent.p, nlen, name); */
+		arg->ent.ul += len;
+		rdu->rent++;
+	} else {
+		err = -EFAULT;
+		au_fset_rdu(rdu->cookie.flags, FULL);
+		rdu->full = 1;
+		rdu->tail = arg->ent;
+	}
+
+out:
+	/* AuTraceErr(err); */
+	return err;
+}
+
+static int au_rdu_do(struct file *h_file, struct au_rdu_arg *arg)
+{
+	int err;
+	loff_t offset;
+	struct au_rdu_cookie *cookie = &arg->rdu->cookie;
+
+	/* we don't have to care (FMODE_32BITHASH | FMODE_64BITHASH) for ext4 */
+	offset = vfsub_llseek(h_file, cookie->h_pos, SEEK_SET);
+	err = offset;
+	if (unlikely(offset != cookie->h_pos))
+		goto out;
+
+	err = 0;
+	do {
+		arg->err = 0;
+		au_fclr_rdu(cookie->flags, CALLED);
+		/* smp_mb(); */
+		err = vfsub_iterate_dir(h_file, &arg->ctx);
+		if (err >= 0)
+			err = arg->err;
+	} while (!err
+		 && au_ftest_rdu(cookie->flags, CALLED)
+		 && !au_ftest_rdu(cookie->flags, FULL));
+	cookie->h_pos = h_file->f_pos;
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+static int au_rdu(struct file *file, struct aufs_rdu *rdu)
+{
+	int err;
+	aufs_bindex_t bbot;
+	struct au_rdu_arg arg = {
+		.ctx = {
+			.actor = au_rdu_fill
+		}
+	};
+	struct dentry *dentry;
+	struct inode *inode;
+	struct file *h_file;
+	struct au_rdu_cookie *cookie = &rdu->cookie;
+
+	/* VERIFY_WRITE */
+	err = !access_ok(rdu->ent.e, rdu->sz);
+	if (unlikely(err)) {
+		err = -EFAULT;
+		AuTraceErr(err);
+		goto out;
+	}
+	rdu->rent = 0;
+	rdu->tail = rdu->ent;
+	rdu->full = 0;
+	arg.rdu = rdu;
+	arg.ent = rdu->ent;
+	arg.end = arg.ent.ul;
+	arg.end += rdu->sz;
+
+	err = -ENOTDIR;
+	if (unlikely(!file->f_op->iterate && !file->f_op->iterate_shared))
+		goto out;
+
+	err = security_file_permission(file, MAY_READ);
+	AuTraceErr(err);
+	if (unlikely(err))
+		goto out;
+
+	dentry = file->f_path.dentry;
+	inode = d_inode(dentry);
+	inode_lock_shared(inode);
+
+	arg.sb = inode->i_sb;
+	err = si_read_lock(arg.sb, AuLock_FLUSH | AuLock_NOPLM);
+	if (unlikely(err))
+		goto out_mtx;
+	err = au_alive_dir(dentry);
+	if (unlikely(err))
+		goto out_si;
+	/* todo: reval? */
+	fi_read_lock(file);
+
+	err = -EAGAIN;
+	if (unlikely(au_ftest_rdu(cookie->flags, CONT)
+		     && cookie->generation != au_figen(file)))
+		goto out_unlock;
+
+	err = 0;
+	if (!rdu->blk) {
+		rdu->blk = au_sbi(arg.sb)->si_rdblk;
+		if (!rdu->blk)
+			rdu->blk = au_dir_size(file, /*dentry*/NULL);
+	}
+	bbot = au_fbtop(file);
+	if (cookie->bindex < bbot)
+		cookie->bindex = bbot;
+	bbot = au_fbbot_dir(file);
+	/* AuDbg("b%d, b%d\n", cookie->bindex, bbot); */
+	for (; !err && cookie->bindex <= bbot;
+	     cookie->bindex++, cookie->h_pos = 0) {
+		h_file = au_hf_dir(file, cookie->bindex);
+		if (!h_file)
+			continue;
+
+		au_fclr_rdu(cookie->flags, FULL);
+		err = au_rdu_do(h_file, &arg);
+		AuTraceErr(err);
+		if (unlikely(au_ftest_rdu(cookie->flags, FULL) || err))
+			break;
+	}
+	AuDbg("rent %llu\n", rdu->rent);
+
+	if (!err && !au_ftest_rdu(cookie->flags, CONT)) {
+		rdu->shwh = !!au_opt_test(au_sbi(arg.sb)->si_mntflags, SHWH);
+		au_fset_rdu(cookie->flags, CONT);
+		cookie->generation = au_figen(file);
+	}
+
+	ii_read_lock_child(inode);
+	fsstack_copy_attr_atime(inode, au_h_iptr(inode, au_ibtop(inode)));
+	ii_read_unlock(inode);
+
+out_unlock:
+	fi_read_unlock(file);
+out_si:
+	si_read_unlock(arg.sb);
+out_mtx:
+	inode_unlock_shared(inode);
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+static int au_rdu_ino(struct file *file, struct aufs_rdu *rdu)
+{
+	int err;
+	ino_t ino;
+	unsigned long long nent;
+	union au_rdu_ent_ul *u;
+	struct au_rdu_ent ent;
+	struct super_block *sb;
+
+	err = 0;
+	nent = rdu->nent;
+	u = &rdu->ent;
+	sb = file->f_path.dentry->d_sb;
+	si_read_lock(sb, AuLock_FLUSH);
+	while (nent-- > 0) {
+		/* unnecessary to support mmap_sem since this is a dir */
+		err = copy_from_user(&ent, u->e, sizeof(ent));
+		if (!err)
+			/* VERIFY_WRITE */
+			err = !access_ok(&u->e->ino, sizeof(ino));
+		if (unlikely(err)) {
+			err = -EFAULT;
+			AuTraceErr(err);
+			break;
+		}
+
+		/* AuDbg("b%d, i%llu\n", ent.bindex, ent.ino); */
+		if (!ent.wh)
+			err = au_ino(sb, ent.bindex, ent.ino, ent.type, &ino);
+		else
+			err = au_wh_ino(sb, ent.bindex, ent.ino, ent.type,
+					&ino);
+		if (unlikely(err)) {
+			AuTraceErr(err);
+			break;
+		}
+
+		err = __put_user(ino, &u->e->ino);
+		if (unlikely(err)) {
+			err = -EFAULT;
+			AuTraceErr(err);
+			break;
+		}
+		u->ul += au_rdu_len(ent.nlen);
+	}
+	si_read_unlock(sb);
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_rdu_verify(struct aufs_rdu *rdu)
+{
+	AuDbg("rdu{%llu, %p, %u | %u | %llu, %u, %u | "
+	      "%llu, b%d, 0x%x, g%u}\n",
+	      rdu->sz, rdu->ent.e, rdu->verify[AufsCtlRduV_SZ],
+	      rdu->blk,
+	      rdu->rent, rdu->shwh, rdu->full,
+	      rdu->cookie.h_pos, rdu->cookie.bindex, rdu->cookie.flags,
+	      rdu->cookie.generation);
+
+	if (rdu->verify[AufsCtlRduV_SZ] == sizeof(*rdu))
+		return 0;
+
+	AuDbg("%u:%u\n",
+	      rdu->verify[AufsCtlRduV_SZ], (unsigned int)sizeof(*rdu));
+	return -EINVAL;
+}
+
+long au_rdu_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	long err, e;
+	struct aufs_rdu rdu;
+	void __user *p = (void __user *)arg;
+
+	err = copy_from_user(&rdu, p, sizeof(rdu));
+	if (unlikely(err)) {
+		err = -EFAULT;
+		AuTraceErr(err);
+		goto out;
+	}
+	err = au_rdu_verify(&rdu);
+	if (unlikely(err))
+		goto out;
+
+	switch (cmd) {
+	case AUFS_CTL_RDU:
+		err = au_rdu(file, &rdu);
+		if (unlikely(err))
+			break;
+
+		e = copy_to_user(p, &rdu, sizeof(rdu));
+		if (unlikely(e)) {
+			err = -EFAULT;
+			AuTraceErr(err);
+		}
+		break;
+	case AUFS_CTL_RDU_INO:
+		err = au_rdu_ino(file, &rdu);
+		break;
+
+	default:
+		/* err = -ENOTTY; */
+		err = -EINVAL;
+	}
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+#ifdef CONFIG_COMPAT
+long au_rdu_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	long err, e;
+	struct aufs_rdu rdu;
+	void __user *p = compat_ptr(arg);
+
+	/* todo: get_user()? */
+	err = copy_from_user(&rdu, p, sizeof(rdu));
+	if (unlikely(err)) {
+		err = -EFAULT;
+		AuTraceErr(err);
+		goto out;
+	}
+	rdu.ent.e = compat_ptr(rdu.ent.ul);
+	err = au_rdu_verify(&rdu);
+	if (unlikely(err))
+		goto out;
+
+	switch (cmd) {
+	case AUFS_CTL_RDU:
+		err = au_rdu(file, &rdu);
+		if (unlikely(err))
+			break;
+
+		rdu.ent.ul = ptr_to_compat(rdu.ent.e);
+		rdu.tail.ul = ptr_to_compat(rdu.tail.e);
+		e = copy_to_user(p, &rdu, sizeof(rdu));
+		if (unlikely(e)) {
+			err = -EFAULT;
+			AuTraceErr(err);
+		}
+		break;
+	case AUFS_CTL_RDU_INO:
+		err = au_rdu_ino(file, &rdu);
+		break;
+
+	default:
+		/* err = -ENOTTY; */
+		err = -EINVAL;
+	}
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+#endif

include/uapi/linux/aufs_type.h

@@ -193,6 +193,10 @@ static inline int au_br_wh_linkable(int brperm)
 
 /* ioctl */
 enum {
+	/* readdir in userspace */
+	AuCtl_RDU,
+	AuCtl_RDU_INO,
+
 	AuCtl_WBR_FD,	/* pathconf wrapper */
 	AuCtl_BR	/* info about branches */
 };
@@ -214,6 +218,62 @@ enum {
 #endif
 #endif
 
+struct au_rdu_cookie {
+	uint64_t	h_pos;
+	int16_t		bindex;
+	uint8_t		flags;
+	uint8_t		pad;
+	uint32_t	generation;
+} __aligned(8);
+
+struct au_rdu_ent {
+	uint64_t	ino;
+	int16_t		bindex;
+	uint8_t		type;
+	uint8_t		nlen;
+	uint8_t		wh;
+	char		name[0];
+} __aligned(8);
+
+static inline int au_rdu_len(int nlen)
+{
+	/* include the terminating NULL */
+	return ALIGN(sizeof(struct au_rdu_ent) + nlen + 1,
+		     sizeof(uint64_t));
+}
+
+union au_rdu_ent_ul {
+	struct au_rdu_ent __user	*e;
+	uint64_t			ul;
+};
+
+enum {
+	AufsCtlRduV_SZ,
+	AufsCtlRduV_End
+};
+
+struct aufs_rdu {
+	/* input */
+	union {
+		uint64_t	sz;	/* AuCtl_RDU */
+		uint64_t	nent;	/* AuCtl_RDU_INO */
+	};
+	union au_rdu_ent_ul	ent;
+	uint16_t		verify[AufsCtlRduV_End];
+
+	/* input/output */
+	uint32_t		blk;
+
+	/* output */
+	union au_rdu_ent_ul	tail;
+	/* number of entries which were added in a single call */
+	uint64_t		rent;
+	uint8_t			full;
+	uint8_t			shwh;
+
+	struct au_rdu_cookie	cookie;
+} __aligned(8);
+
 /* ---------------------------------------------------------------------- */
 
 /* dirren. the branch is identified by the filename who contains this */
@@ -257,6 +317,8 @@ union aufs_brinfo {
 /* ---------------------------------------------------------------------- */
 
 #define AuCtlType		'A'
+#define AUFS_CTL_RDU		_IOWR(AuCtlType, AuCtl_RDU, struct aufs_rdu)
+#define AUFS_CTL_RDU_INO	_IOWR(AuCtlType, AuCtl_RDU_INO, struct aufs_rdu)
 #define AUFS_CTL_WBR_FD		_IOW(AuCtlType, AuCtl_WBR_FD, \
 				     struct aufs_wbr_fd)
 #define AUFS_CTL_BRINFO		_IOW(AuCtlType, AuCtl_BR, union aufs_brinfo)