Message-ID: <YsN1kfBsfMdH+eiU@ZenIV>
Date:   Tue, 5 Jul 2022 00:19:45 +0100
From:   Al Viro <viro@...iv.linux.org.uk>
To:     Linus Torvalds <torvalds@...ux-foundation.org>
Cc:     Alexander Potapenko <glider@...gle.com>,
        Alexei Starovoitov <ast@...nel.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Andrey Konovalov <andreyknvl@...gle.com>,
        Andy Lutomirski <luto@...nel.org>,
        Arnd Bergmann <arnd@...db.de>, Borislav Petkov <bp@...en8.de>,
        Christoph Hellwig <hch@....de>,
        Christoph Lameter <cl@...ux.com>,
        David Rientjes <rientjes@...gle.com>,
        Dmitry Vyukov <dvyukov@...gle.com>,
        Eric Dumazet <edumazet@...gle.com>,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        Herbert Xu <herbert@...dor.apana.org.au>,
        Ilya Leoshkevich <iii@...ux.ibm.com>,
        Ingo Molnar <mingo@...hat.com>, Jens Axboe <axboe@...nel.dk>,
        Joonsoo Kim <iamjoonsoo.kim@....com>,
        Kees Cook <keescook@...omium.org>,
        Marco Elver <elver@...gle.com>,
        Mark Rutland <mark.rutland@....com>,
        Matthew Wilcox <willy@...radead.org>,
        "Michael S. Tsirkin" <mst@...hat.com>,
        Pekka Enberg <penberg@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Petr Mladek <pmladek@...e.com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        Vasily Gorbik <gor@...ux.ibm.com>,
        Vegard Nossum <vegard.nossum@...cle.com>,
        Vlastimil Babka <vbabka@...e.cz>,
        kasan-dev <kasan-dev@...glegroups.com>,
        Linux-MM <linux-mm@...ck.org>,
        linux-arch <linux-arch@...r.kernel.org>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        Evgenii Stepanov <eugenis@...gle.com>,
        Nathan Chancellor <nathan@...nel.org>,
        Nick Desaulniers <ndesaulniers@...gle.com>,
        Segher Boessenkool <segher@...nel.crashing.org>,
        Vitaly Buka <vitalybuka@...gle.com>,
        linux-toolchains <linux-toolchains@...r.kernel.org>
Subject: Re: [PATCH 1/7] __follow_mount_rcu(): verify that mount_lock remains
 unchanged

	Just in case - this series is RFC only; it's very lightly
tested.  Might be carved into too many steps, at that.  Cumulative
delta follows; might or might not be more convenient for review.

diff --git a/fs/namei.c b/fs/namei.c
index 1f28d3f463c3..f2c99e75b578 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -567,7 +567,7 @@ struct nameidata {
 	struct path	root;
 	struct inode	*inode; /* path.dentry.d_inode */
 	unsigned int	flags, state;
-	unsigned	seq, m_seq, r_seq;
+	unsigned	seq, next_seq, m_seq, r_seq;
 	int		last_type;
 	unsigned	depth;
 	int		total_link_count;
@@ -772,6 +772,7 @@ static bool try_to_unlazy(struct nameidata *nd)
 		goto out;
 	if (unlikely(!legitimize_root(nd)))
 		goto out;
+	nd->seq = nd->next_seq = 0;
 	rcu_read_unlock();
 	BUG_ON(nd->inode != parent->d_inode);
 	return true;
@@ -780,6 +781,7 @@ static bool try_to_unlazy(struct nameidata *nd)
 	nd->path.mnt = NULL;
 	nd->path.dentry = NULL;
 out:
+	nd->seq = nd->next_seq = 0;
 	rcu_read_unlock();
 	return false;
 }
@@ -788,7 +790,6 @@ static bool try_to_unlazy(struct nameidata *nd)
  * try_to_unlazy_next - try to switch to ref-walk mode.
  * @nd: nameidata pathwalk data
  * @dentry: next dentry to step into
- * @seq: seq number to check @dentry against
  * Returns: true on success, false on failure
  *
  * Similar to try_to_unlazy(), but here we have the next dentry already
@@ -797,7 +798,7 @@ static bool try_to_unlazy(struct nameidata *nd)
  * Nothing should touch nameidata between try_to_unlazy_next() failure and
  * terminate_walk().
  */
-static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry, unsigned seq)
+static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry)
 {
 	BUG_ON(!(nd->flags & LOOKUP_RCU));
 
@@ -818,7 +819,7 @@ static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry, unsi
 	 */
 	if (unlikely(!lockref_get_not_dead(&dentry->d_lockref)))
 		goto out;
-	if (unlikely(read_seqcount_retry(&dentry->d_seq, seq)))
+	if (unlikely(read_seqcount_retry(&dentry->d_seq, nd->next_seq)))
 		goto out_dput;
 	/*
 	 * Sequence counts matched. Now make sure that the root is
@@ -826,6 +827,7 @@ static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry, unsi
 	 */
 	if (unlikely(!legitimize_root(nd)))
 		goto out_dput;
+	nd->seq = nd->next_seq = 0;
 	rcu_read_unlock();
 	return true;
 
@@ -834,9 +836,11 @@ static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry, unsi
 out1:
 	nd->path.dentry = NULL;
 out:
+	nd->seq = nd->next_seq = 0;
 	rcu_read_unlock();
 	return false;
 out_dput:
+	nd->seq = nd->next_seq = 0;
 	rcu_read_unlock();
 	dput(dentry);
 	return false;
@@ -1466,8 +1470,7 @@ EXPORT_SYMBOL(follow_down);
  * Try to skip to top of mountpoint pile in rcuwalk mode.  Fail if
  * we meet a managed dentry that would need blocking.
  */
-static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
-			       struct inode **inode, unsigned *seqp)
+static bool __follow_mount_rcu(struct nameidata *nd, struct path *path)
 {
 	struct dentry *dentry = path->dentry;
 	unsigned int flags = dentry->d_flags;
@@ -1496,15 +1499,12 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 				path->mnt = &mounted->mnt;
 				dentry = path->dentry = mounted->mnt.mnt_root;
 				nd->state |= ND_JUMPED;
-				*seqp = read_seqcount_begin(&dentry->d_seq);
-				*inode = dentry->d_inode;
-				/*
-				 * We don't need to re-check ->d_seq after this
-				 * ->d_inode read - there will be an RCU delay
-				 * between mount hash removal and ->mnt_root
-				 * becoming unpinned.
-				 */
+				nd->next_seq = read_seqcount_begin(&dentry->d_seq);
 				flags = dentry->d_flags;
+				// makes sure that non-RCU pathwalk could reach
+				// this state.
+				if (read_seqretry(&mount_lock, nd->m_seq))
+					return false;
 				continue;
 			}
 			if (read_seqretry(&mount_lock, nd->m_seq))
@@ -1515,8 +1515,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 }
 
 static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry,
-			  struct path *path, struct inode **inode,
-			  unsigned int *seqp)
+			  struct path *path)
 {
 	bool jumped;
 	int ret;
@@ -1524,16 +1523,15 @@ static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry,
 	path->mnt = nd->path.mnt;
 	path->dentry = dentry;
 	if (nd->flags & LOOKUP_RCU) {
-		unsigned int seq = *seqp;
-		if (unlikely(!*inode))
-			return -ENOENT;
-		if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
+		unsigned int seq = nd->next_seq;
+		if (likely(__follow_mount_rcu(nd, path)))
 			return 0;
-		if (!try_to_unlazy_next(nd, dentry, seq))
-			return -ECHILD;
-		// *path might've been clobbered by __follow_mount_rcu()
+		// *path and nd->next_seq might've been clobbered
 		path->mnt = nd->path.mnt;
 		path->dentry = dentry;
+		nd->next_seq = seq;
+		if (!try_to_unlazy_next(nd, dentry))
+			return -ECHILD;
 	}
 	ret = traverse_mounts(path, &jumped, &nd->total_link_count, nd->flags);
 	if (jumped) {
@@ -1546,9 +1544,6 @@ static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry,
 		dput(path->dentry);
 		if (path->mnt != nd->path.mnt)
 			mntput(path->mnt);
-	} else {
-		*inode = d_backing_inode(path->dentry);
-		*seqp = 0; /* out of RCU mode, so the value doesn't matter */
 	}
 	return ret;
 }
@@ -1607,9 +1602,7 @@ static struct dentry *__lookup_hash(const struct qstr *name,
 	return dentry;
 }
 
-static struct dentry *lookup_fast(struct nameidata *nd,
-				  struct inode **inode,
-			          unsigned *seqp)
+static struct dentry *lookup_fast(struct nameidata *nd)
 {
 	struct dentry *dentry, *parent = nd->path.dentry;
 	int status = 1;
@@ -1620,37 +1613,24 @@ static struct dentry *lookup_fast(struct nameidata *nd,
 	 * going to fall back to non-racy lookup.
 	 */
 	if (nd->flags & LOOKUP_RCU) {
-		unsigned seq;
-		dentry = __d_lookup_rcu(parent, &nd->last, &seq);
+		dentry = __d_lookup_rcu(parent, &nd->last, &nd->next_seq);
 		if (unlikely(!dentry)) {
 			if (!try_to_unlazy(nd))
 				return ERR_PTR(-ECHILD);
 			return NULL;
 		}
 
-		/*
-		 * This sequence count validates that the inode matches
-		 * the dentry name information from lookup.
-		 */
-		*inode = d_backing_inode(dentry);
-		if (unlikely(read_seqcount_retry(&dentry->d_seq, seq)))
-			return ERR_PTR(-ECHILD);
-
-		/*
+	        /*
 		 * This sequence count validates that the parent had no
 		 * changes while we did the lookup of the dentry above.
-		 *
-		 * The memory barrier in read_seqcount_begin of child is
-		 *  enough, we can use __read_seqcount_retry here.
 		 */
-		if (unlikely(__read_seqcount_retry(&parent->d_seq, nd->seq)))
+		if (unlikely(read_seqcount_retry(&parent->d_seq, nd->seq)))
 			return ERR_PTR(-ECHILD);
 
-		*seqp = seq;
 		status = d_revalidate(dentry, nd->flags);
 		if (likely(status > 0))
 			return dentry;
-		if (!try_to_unlazy_next(nd, dentry, seq))
+		if (!try_to_unlazy_next(nd, dentry))
 			return ERR_PTR(-ECHILD);
 		if (status == -ECHILD)
 			/* we'd been told to redo it in non-rcu mode */
@@ -1731,7 +1711,7 @@ static inline int may_lookup(struct user_namespace *mnt_userns,
 	return inode_permission(mnt_userns, nd->inode, MAY_EXEC);
 }
 
-static int reserve_stack(struct nameidata *nd, struct path *link, unsigned seq)
+static int reserve_stack(struct nameidata *nd, struct path *link)
 {
 	if (unlikely(nd->total_link_count++ >= MAXSYMLINKS))
 		return -ELOOP;
@@ -1746,7 +1726,7 @@ static int reserve_stack(struct nameidata *nd, struct path *link, unsigned seq)
 	if (nd->flags & LOOKUP_RCU) {
 		// we need to grab link before we do unlazy.  And we can't skip
 		// unlazy even if we fail to grab the link - cleanup needs it
-		bool grabbed_link = legitimize_path(nd, link, seq);
+		bool grabbed_link = legitimize_path(nd, link, nd->next_seq);
 
 		if (!try_to_unlazy(nd) || !grabbed_link)
 			return -ECHILD;
@@ -1760,11 +1740,11 @@ static int reserve_stack(struct nameidata *nd, struct path *link, unsigned seq)
 enum {WALK_TRAILING = 1, WALK_MORE = 2, WALK_NOFOLLOW = 4};
 
 static const char *pick_link(struct nameidata *nd, struct path *link,
-		     struct inode *inode, unsigned seq, int flags)
+		     struct inode *inode, int flags)
 {
 	struct saved *last;
 	const char *res;
-	int error = reserve_stack(nd, link, seq);
+	int error = reserve_stack(nd, link);
 
 	if (unlikely(error)) {
 		if (!(nd->flags & LOOKUP_RCU))
@@ -1774,7 +1754,7 @@ static const char *pick_link(struct nameidata *nd, struct path *link,
 	last = nd->stack + nd->depth++;
 	last->link = *link;
 	clear_delayed_call(&last->done);
-	last->seq = seq;
+	last->seq = nd->next_seq;
 
 	if (flags & WALK_TRAILING) {
 		error = may_follow_link(nd, inode);
@@ -1836,43 +1816,50 @@ static const char *pick_link(struct nameidata *nd, struct path *link,
  * to do this check without having to look at inode->i_op,
  * so we keep a cache of "no, this doesn't need follow_link"
  * for the common case.
+ *
+ * NOTE: dentry must be what nd->next_seq had been sampled from.
  */
 static const char *step_into(struct nameidata *nd, int flags,
-		     struct dentry *dentry, struct inode *inode, unsigned seq)
+		     struct dentry *dentry)
 {
 	struct path path;
-	int err = handle_mounts(nd, dentry, &path, &inode, &seq);
+	struct inode *inode;
+	int err = handle_mounts(nd, dentry, &path);
 
 	if (err < 0)
 		return ERR_PTR(err);
+	inode = path.dentry->d_inode;
 	if (likely(!d_is_symlink(path.dentry)) ||
 	   ((flags & WALK_TRAILING) && !(nd->flags & LOOKUP_FOLLOW)) ||
 	   (flags & WALK_NOFOLLOW)) {
 		/* not a symlink or should not follow */
-		if (!(nd->flags & LOOKUP_RCU)) {
+		if (nd->flags & LOOKUP_RCU) {
+			if (read_seqcount_retry(&path.dentry->d_seq, nd->next_seq))
+				return ERR_PTR(-ECHILD);
+			if (unlikely(!inode))
+				return ERR_PTR(-ENOENT);
+		} else {
 			dput(nd->path.dentry);
 			if (nd->path.mnt != path.mnt)
 				mntput(nd->path.mnt);
 		}
 		nd->path = path;
 		nd->inode = inode;
-		nd->seq = seq;
+		nd->seq = nd->next_seq;
 		return NULL;
 	}
 	if (nd->flags & LOOKUP_RCU) {
 		/* make sure that d_is_symlink above matches inode */
-		if (read_seqcount_retry(&path.dentry->d_seq, seq))
+		if (read_seqcount_retry(&path.dentry->d_seq, nd->next_seq))
 			return ERR_PTR(-ECHILD);
 	} else {
 		if (path.mnt == nd->path.mnt)
 			mntget(path.mnt);
 	}
-	return pick_link(nd, &path, inode, seq, flags);
+	return pick_link(nd, &path, inode, flags);
 }
 
-static struct dentry *follow_dotdot_rcu(struct nameidata *nd,
-					struct inode **inodep,
-					unsigned *seqp)
+static struct dentry *follow_dotdot_rcu(struct nameidata *nd)
 {
 	struct dentry *parent, *old;
 
@@ -1889,14 +1876,15 @@ static struct dentry *follow_dotdot_rcu(struct nameidata *nd,
 		nd->path = path;
 		nd->inode = path.dentry->d_inode;
 		nd->seq = seq;
+		// makes sure that non-RCU pathwalk could reach this state
 		if (unlikely(read_seqretry(&mount_lock, nd->m_seq)))
 			return ERR_PTR(-ECHILD);
 		/* we know that mountpoint was pinned */
 	}
 	old = nd->path.dentry;
 	parent = old->d_parent;
-	*inodep = parent->d_inode;
-	*seqp = read_seqcount_begin(&parent->d_seq);
+	nd->next_seq = read_seqcount_begin(&parent->d_seq);
+	// makes sure that non-RCU pathwalk could reach this state
 	if (unlikely(read_seqcount_retry(&old->d_seq, nd->seq)))
 		return ERR_PTR(-ECHILD);
 	if (unlikely(!path_connected(nd->path.mnt, parent)))
@@ -1907,12 +1895,11 @@ static struct dentry *follow_dotdot_rcu(struct nameidata *nd,
 		return ERR_PTR(-ECHILD);
 	if (unlikely(nd->flags & LOOKUP_BENEATH))
 		return ERR_PTR(-ECHILD);
-	return NULL;
+	nd->next_seq = nd->seq;
+	return nd->path.dentry;
 }
 
-static struct dentry *follow_dotdot(struct nameidata *nd,
-				 struct inode **inodep,
-				 unsigned *seqp)
+static struct dentry *follow_dotdot(struct nameidata *nd)
 {
 	struct dentry *parent;
 
@@ -1936,15 +1923,12 @@ static struct dentry *follow_dotdot(struct nameidata *nd,
 		dput(parent);
 		return ERR_PTR(-ENOENT);
 	}
-	*seqp = 0;
-	*inodep = parent->d_inode;
 	return parent;
 
 in_root:
 	if (unlikely(nd->flags & LOOKUP_BENEATH))
 		return ERR_PTR(-EXDEV);
-	dget(nd->path.dentry);
-	return NULL;
+	return dget(nd->path.dentry);
 }
 
 static const char *handle_dots(struct nameidata *nd, int type)
@@ -1952,8 +1936,6 @@ static const char *handle_dots(struct nameidata *nd, int type)
 	if (type == LAST_DOTDOT) {
 		const char *error = NULL;
 		struct dentry *parent;
-		struct inode *inode;
-		unsigned seq;
 
 		if (!nd->root.mnt) {
 			error = ERR_PTR(set_root(nd));
@@ -1961,17 +1943,12 @@ static const char *handle_dots(struct nameidata *nd, int type)
 				return error;
 		}
 		if (nd->flags & LOOKUP_RCU)
-			parent = follow_dotdot_rcu(nd, &inode, &seq);
+			parent = follow_dotdot_rcu(nd);
 		else
-			parent = follow_dotdot(nd, &inode, &seq);
+			parent = follow_dotdot(nd);
 		if (IS_ERR(parent))
 			return ERR_CAST(parent);
-		if (unlikely(!parent))
-			error = step_into(nd, WALK_NOFOLLOW,
-					 nd->path.dentry, nd->inode, nd->seq);
-		else
-			error = step_into(nd, WALK_NOFOLLOW,
-					 parent, inode, seq);
+		error = step_into(nd, WALK_NOFOLLOW, parent);
 		if (unlikely(error))
 			return error;
 
@@ -1995,8 +1972,6 @@ static const char *handle_dots(struct nameidata *nd, int type)
 static const char *walk_component(struct nameidata *nd, int flags)
 {
 	struct dentry *dentry;
-	struct inode *inode;
-	unsigned seq;
 	/*
 	 * "." and ".." are special - ".." especially so because it has
 	 * to be able to know about the current root directory and
@@ -2007,7 +1982,7 @@ static const char *walk_component(struct nameidata *nd, int flags)
 			put_link(nd);
 		return handle_dots(nd, nd->last_type);
 	}
-	dentry = lookup_fast(nd, &inode, &seq);
+	dentry = lookup_fast(nd);
 	if (IS_ERR(dentry))
 		return ERR_CAST(dentry);
 	if (unlikely(!dentry)) {
@@ -2017,7 +1992,7 @@ static const char *walk_component(struct nameidata *nd, int flags)
 	}
 	if (!(flags & WALK_MORE) && nd->depth)
 		put_link(nd);
-	return step_into(nd, flags, dentry, inode, seq);
+	return step_into(nd, flags, dentry);
 }
 
 /*
@@ -2372,6 +2347,8 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 		flags &= ~LOOKUP_RCU;
 	if (flags & LOOKUP_RCU)
 		rcu_read_lock();
+	else
+		nd->seq = nd->next_seq = 0;
 
 	nd->flags = flags;
 	nd->state |= ND_JUMPED;
@@ -2473,8 +2450,8 @@ static int handle_lookup_down(struct nameidata *nd)
 {
 	if (!(nd->flags & LOOKUP_RCU))
 		dget(nd->path.dentry);
-	return PTR_ERR(step_into(nd, WALK_NOFOLLOW,
-			nd->path.dentry, nd->inode, nd->seq));
+	nd->next_seq = nd->seq;
+	return PTR_ERR(step_into(nd, WALK_NOFOLLOW, nd->path.dentry));
 }
 
 /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
@@ -3393,8 +3370,6 @@ static const char *open_last_lookups(struct nameidata *nd,
 	struct dentry *dir = nd->path.dentry;
 	int open_flag = op->open_flag;
 	bool got_write = false;
-	unsigned seq;
-	struct inode *inode;
 	struct dentry *dentry;
 	const char *res;
 
@@ -3410,7 +3385,7 @@ static const char *open_last_lookups(struct nameidata *nd,
 		if (nd->last.name[nd->last.len])
 			nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
 		/* we _can_ be in RCU mode here */
-		dentry = lookup_fast(nd, &inode, &seq);
+		dentry = lookup_fast(nd);
 		if (IS_ERR(dentry))
 			return ERR_CAST(dentry);
 		if (likely(dentry))
@@ -3464,7 +3439,7 @@ static const char *open_last_lookups(struct nameidata *nd,
 finish_lookup:
 	if (nd->depth)
 		put_link(nd);
-	res = step_into(nd, WALK_TRAILING, dentry, inode, seq);
+	res = step_into(nd, WALK_TRAILING, dentry);
 	if (unlikely(res))
 		nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
 	return res;

Powered by blists - more mailing lists