[PATCH 6/7] procfs: drop parent lock for d_alloc_parallel() in iterate_shared()

[NeilBrown <neilb@ownmail.net>]

From: NeilBrown <neil@brown.name>

When procfs finds a name in iterate_shared() that isn't in the dcache it
*must* add it so that it can have a stable inode number to report
(inodes are only accessible from the dcache in procfs).

It uses d_alloc_parallel().  A planned change to locking will make it
unsafe to call d_alloc_parallel() while holding the directory lock.

Other filesystems which prime the dcache in iterate_shared() use
d_alloc_trylock() which is safe but can fail if it races with ->lookup.
As procfs cannot handle failure we need something better.

procfs doesn't *need* the parent to be locked.  There are no shared data
structures accessed that don't have their own locking.  So it is safe to
drop and re-take the parent lock.  We could do this around the whole
iteration, but as failure of d_alloc_trylock() is rare it is more
efficient to drop and retake it just around a call of d_alloc_parallel()
when d_alloc_trylock does fail.

Other code that drops and retakes the lock in iterate_shared needs to
be careful to check S_DEAD which could be set while the lock is
dropped.  This is not needed in procfs as the flag is never set.

As d_alloc_trylock() calls try_lookup_noperm(), we can skip that call
and simplify the code.

Signed-off-by: NeilBrown <neil@brown.name>
---
 fs/proc/base.c        | 36 ++++++++++++++++++-------------
 fs/proc/proc_sysctl.c | 49 ++++++++++++++++++++++++-------------------
 2 files changed, 49 insertions(+), 36 deletions(-)

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 6a39de424f62..49939527763d 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2106,24 +2106,32 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx,
 	unsigned type = DT_UNKNOWN;
 	ino_t ino = 1;
 
-	child = try_lookup_noperm(&qname, dir);
+	child = d_alloc_trylock(dir, &qname);
 	if (IS_ERR(child))
 		goto end_instantiate;
 
-	if (!child) {
+	if (child == ERR_PTR(-EWOULDBLOCK)) {
+		/*
+		 * Need to drop directory lock, which isn't really
+		 * needed here anyway.  As rmdir never happens in procfs
+		 * we don't need to be concerned about S_DEAD being set
+		 * while unlocked.
+		 */
+		inode_unlock_shared(dir->d_inode);
 		child = d_alloc_parallel(dir, &qname);
-		if (IS_ERR(child))
-			goto end_instantiate;
-		if (d_in_lookup(child)) {
-			struct dentry *res;
-			res = instantiate(child, task, ptr);
-			d_lookup_done(child);
-			if (unlikely(res)) {
-				dput(child);
-				child = res;
-				if (IS_ERR(child))
-					goto end_instantiate;
-			}
+		inode_lock_shared(dir->d_inode);
+	}
+	if (IS_ERR(child))
+		goto end_instantiate;
+	if (d_in_lookup(child)) {
+		struct dentry *res;
+		res = instantiate(child, task, ptr);
+		d_lookup_done(child);
+		if (unlikely(res)) {
+			dput(child);
+			child = res;
+			if (IS_ERR(child))
+				goto end_instantiate;
 		}
 	}
 	inode = d_inode(child);
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 04a382178c65..de96a08a1e64 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -686,29 +686,34 @@ static bool proc_sys_fill_cache(struct file *file,
 	ino_t ino = 0;
 	unsigned type = DT_UNKNOWN;
 
-	qname.name = table->procname;
-	qname.len  = strlen(table->procname);
-	qname.hash = full_name_hash(dir, qname.name, qname.len);
-
-	child = d_lookup(dir, &qname);
-	if (!child) {
+	qname = QSTR(table->procname);
+	child = d_alloc_trylock(dir, &qname);
+	if (child == ERR_PTR(-EWOULDBLOCK)) {
+		/*
+		 * Need to drop directory lock, which isn't really
+		 * needed here anyway.  As rmdir never happens in procfs
+		 * we don't need to be concerned about S_DEAD being set
+		 * while unlocked.
+		 */
+		inode_unlock_shared(dir->d_inode);
 		child = d_alloc_parallel(dir, &qname);
-		if (IS_ERR(child))
-			return false;
-		if (d_in_lookup(child)) {
-			struct dentry *res;
-			inode = proc_sys_make_inode(dir->d_sb, head, table);
-			res = d_splice_alias_ops(inode, child,
-						 &proc_sys_dentry_operations);
-			d_lookup_done(child);
-			if (unlikely(res)) {
-				dput(child);
-
-				if (IS_ERR(res))
-					return false;
-
-				child = res;
-			}
+		inode_lock_shared(dir->d_inode);
+	}
+	if (IS_ERR(child))
+		return false;
+	if (d_in_lookup(child)) {
+		struct dentry *res;
+		inode = proc_sys_make_inode(dir->d_sb, head, table);
+		res = d_splice_alias_ops(inode, child,
+					 &proc_sys_dentry_operations);
+		d_lookup_done(child);
+		if (unlikely(res)) {
+			dput(child);
+
+			if (IS_ERR(res))
+				return false;
+
+			child = res;
 		}
 	}
 	inode = d_inode(child);
-- 
2.50.0.107.gf914562f5916.dirty