1 files changed, 370 insertions, 242 deletions

diff --git a/fs/dcache.c b/fs/dcache.c
index 4c144519aa70..dc2fff4811d1 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -35,6 +35,8 @@
 #include "internal.h"
 #include "mount.h"
 
+#include <asm/runtime-const.h>
+
 /*
  * Usage:
  * dcache->d_inode->i_lock protects:
@@ -71,14 +73,21 @@
  * If no ancestor relationship:
  * arbitrary, since it's serialized on rename_lock
  */
-int sysctl_vfs_cache_pressure __read_mostly = 100;
-EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);
+static int sysctl_vfs_cache_pressure __read_mostly = 100;
+static int sysctl_vfs_cache_pressure_denom __read_mostly = 100;
+
+unsigned long vfs_pressure_ratio(unsigned long val)
+{
+	return mult_frac(val, sysctl_vfs_cache_pressure, sysctl_vfs_cache_pressure_denom);
+}
+EXPORT_SYMBOL_GPL(vfs_pressure_ratio);
 
 __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
 
 EXPORT_SYMBOL(rename_lock);
 
-static struct kmem_cache *dentry_cache __ro_after_init;
+static struct kmem_cache *__dentry_cache __ro_after_init;
+#define dentry_cache runtime_const_ptr(__dentry_cache)
 
 const struct qstr empty_name = QSTR_INIT("", 0);
 EXPORT_SYMBOL(empty_name);
@@ -94,15 +103,21 @@ EXPORT_SYMBOL(dotdot_name);
  *
  * This hash-function tries to avoid losing too many bits of hash
  * information, yet avoid using a prime hash-size or similar.
+ *
+ * Marking the variables "used" ensures that the compiler doesn't
+ * optimize them away completely on architectures with runtime
+ * constant infrastructure, this allows debuggers to see their
+ * values. But updating these values has no effect on those arches.
  */
 
-static unsigned int d_hash_shift __ro_after_init;
+static unsigned int d_hash_shift __ro_after_init __used;
 
-static struct hlist_bl_head *dentry_hashtable __ro_after_init;
+static struct hlist_bl_head *dentry_hashtable __ro_after_init __used;
 
-static inline struct hlist_bl_head *d_hash(unsigned int hash)
+static inline struct hlist_bl_head *d_hash(unsigned long hashlen)
 {
-	return dentry_hashtable + (hash >> d_hash_shift);
+	return runtime_const_ptr(dentry_hashtable) +
+		runtime_const_shift_right_32(hashlen, d_hash_shift);
 }
 
 #define IN_LOOKUP_SHIFT 10
@@ -127,6 +142,7 @@ struct dentry_stat_t {
 static DEFINE_PER_CPU(long, nr_dentry);
 static DEFINE_PER_CPU(long, nr_dentry_unused);
 static DEFINE_PER_CPU(long, nr_dentry_negative);
+static int dentry_negative_policy;
 
 #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
 /* Statistics gathering. */
@@ -174,7 +190,7 @@ static long get_nr_dentry_negative(void)
 	return sum < 0 ? 0 : sum;
 }
 
-static int proc_nr_dentry(struct ctl_table *table, int write, void *buffer,
+static int proc_nr_dentry(const struct ctl_table *table, int write, void *buffer,
 			  size_t *lenp, loff_t *ppos)
 {
 	dentry_stat.nr_dentry = get_nr_dentry();
@@ -183,7 +199,7 @@ static int proc_nr_dentry(struct ctl_table *table, int write, void *buffer,
 	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table fs_dcache_sysctls[] = {
+static const struct ctl_table fs_dcache_sysctls[] = {
 	{
 		.procname	= "dentry-state",
 		.data		= &dentry_stat,
@@ -191,10 +207,39 @@ static struct ctl_table fs_dcache_sysctls[] = {
 		.mode		= 0444,
 		.proc_handler	= proc_nr_dentry,
 	},
+	{
+		.procname	= "dentry-negative",
+		.data		= &dentry_negative_policy,
+		.maxlen		= sizeof(dentry_negative_policy),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+};
+
+static const struct ctl_table vm_dcache_sysctls[] = {
+	{
+		.procname	= "vfs_cache_pressure",
+		.data		= &sysctl_vfs_cache_pressure,
+		.maxlen		= sizeof(sysctl_vfs_cache_pressure),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+	},
+	{
+		.procname	= "vfs_cache_pressure_denom",
+		.data		= &sysctl_vfs_cache_pressure_denom,
+		.maxlen		= sizeof(sysctl_vfs_cache_pressure_denom),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE_HUNDRED,
+	},
 };
 
 static int __init init_fs_dcache_sysctls(void)
 {
+	register_sysctl_init("vm", vm_dcache_sysctls);
 	register_sysctl_init("fs", fs_dcache_sysctls);
 	return 0;
 }
@@ -277,12 +322,16 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c
 	return dentry_string_cmp(cs, ct, tcount);
 }
 
+/*
+ * long names are allocated separately from dentry and never modified.
+ * Refcounted, freeing is RCU-delayed.  See take_dentry_name_snapshot()
+ * for the reason why ->count and ->head can't be combined into a union.
+ * dentry_string_cmp() relies upon ->name[] being word-aligned.
+ */
 struct external_name {
-	union {
-		atomic_t count;
-		struct rcu_head head;
-	} u;
-	unsigned char name[];
+	atomic_t count;
+	struct rcu_head head;
+	unsigned char name[] __aligned(sizeof(unsigned long));
 };
 
 static inline struct external_name *external_name(struct dentry *dentry)
@@ -306,31 +355,45 @@ static void __d_free_external(struct rcu_head *head)
 
 static inline int dname_external(const struct dentry *dentry)
 {
-	return dentry->d_name.name != dentry->d_iname;
+	return dentry->d_name.name != dentry->d_shortname.string;
 }
 
 void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry)
 {
-	spin_lock(&dentry->d_lock);
-	name->name = dentry->d_name;
-	if (unlikely(dname_external(dentry))) {
-		atomic_inc(&external_name(dentry)->u.count);
+	unsigned seq;
+	const unsigned char *s;
+
+	rcu_read_lock();
+retry:
+	seq = read_seqcount_begin(&dentry->d_seq);
+	s = READ_ONCE(dentry->d_name.name);
+	name->name.hash_len = dentry->d_name.hash_len;
+	name->name.name = name->inline_name.string;
+	if (likely(s == dentry->d_shortname.string)) {
+		name->inline_name = dentry->d_shortname;
 	} else {
-		memcpy(name->inline_name, dentry->d_iname,
-		       dentry->d_name.len + 1);
-		name->name.name = name->inline_name;
+		struct external_name *p;
+		p = container_of(s, struct external_name, name[0]);
+		// get a valid reference
+		if (unlikely(!atomic_inc_not_zero(&p->count)))
+			goto retry;
+		name->name.name = s;
 	}
-	spin_unlock(&dentry->d_lock);
+	if (read_seqcount_retry(&dentry->d_seq, seq)) {
+		release_dentry_name_snapshot(name);
+		goto retry;
+	}
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL(take_dentry_name_snapshot);
 
 void release_dentry_name_snapshot(struct name_snapshot *name)
 {
-	if (unlikely(name->name.name != name->inline_name)) {
+	if (unlikely(name->name.name != name->inline_name.string)) {
 		struct external_name *p;
 		p = container_of(name->name.name, struct external_name, name[0]);
-		if (unlikely(atomic_dec_and_test(&p->u.count)))
-			kfree_rcu(p, u.head);
+		if (unlikely(atomic_dec_and_test(&p->count)))
+			kfree_rcu(p, head);
 	}
 }
 EXPORT_SYMBOL(release_dentry_name_snapshot);
@@ -368,7 +431,7 @@ static void dentry_free(struct dentry *dentry)
 	WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias));
 	if (unlikely(dname_external(dentry))) {
 		struct external_name *p = external_name(dentry);
-		if (likely(atomic_dec_and_test(&p->u.count))) {
+		if (likely(atomic_dec_and_test(&p->count))) {
 			call_rcu(&dentry->d_u.d_rcu, __d_free_external);
 			return;
 		}
@@ -732,7 +795,7 @@ void d_mark_dontcache(struct inode *inode)
 		de->d_flags |= DCACHE_DONTCACHE;
 		spin_unlock(&de->d_lock);
 	}
-	inode->i_state |= I_DONTCACHE;
+	inode_state_set(inode, I_DONTCACHE);
 	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL(d_mark_dontcache);
@@ -807,6 +870,24 @@ locked:
 	return false;
 }
 
+static void finish_dput(struct dentry *dentry)
+	__releases(dentry->d_lock)
+	__releases(RCU)
+{
+	while (lock_for_kill(dentry)) {
+		rcu_read_unlock();
+		dentry = __dentry_kill(dentry);
+		if (!dentry)
+			return;
+		if (retain_dentry(dentry, true)) {
+			spin_unlock(&dentry->d_lock);
+			return;
+		}
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
+	spin_unlock(&dentry->d_lock);
+}
 
 /* 
  * This is dput
@@ -844,22 +925,21 @@ void dput(struct dentry *dentry)
 		rcu_read_unlock();
 		return;
 	}
-	while (lock_for_kill(dentry)) {
-		rcu_read_unlock();
-		dentry = __dentry_kill(dentry);
-		if (!dentry)
-			return;
-		if (retain_dentry(dentry, true)) {
-			spin_unlock(&dentry->d_lock);
-			return;
-		}
-		rcu_read_lock();
-	}
-	rcu_read_unlock();
-	spin_unlock(&dentry->d_lock);
+	finish_dput(dentry);
 }
 EXPORT_SYMBOL(dput);
 
+void d_make_discardable(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	WARN_ON(!(dentry->d_flags & DCACHE_PERSISTENT));
+	dentry->d_flags &= ~DCACHE_PERSISTENT;
+	dentry->d_lockref.count--;
+	rcu_read_lock();
+	finish_dput(dentry);
+}
+EXPORT_SYMBOL(d_make_discardable);
+
 static void to_shrink_list(struct dentry *dentry, struct list_head *list)
 __must_hold(&dentry->d_lock)
 {
@@ -1011,7 +1091,7 @@ struct dentry *d_find_alias_rcu(struct inode *inode)
 	spin_lock(&inode->i_lock);
 	// ->i_dentry and ->i_rcu are colocated, but the latter won't be
 	// used without having I_FREEING set, which means no aliases left
-	if (likely(!(inode->i_state & I_FREEING) && !hlist_empty(l))) {
+	if (likely(!(inode_state_read(inode) & I_FREEING) && !hlist_empty(l))) {
 		if (S_ISDIR(inode->i_mode)) {
 			de = hlist_entry(l->first, struct dentry, d_u.d_alias);
 		} else {
@@ -1024,6 +1104,15 @@ struct dentry *d_find_alias_rcu(struct inode *inode)
 	return de;
 }
 
+void d_dispose_if_unused(struct dentry *dentry, struct list_head *dispose)
+{
+	spin_lock(&dentry->d_lock);
+	if (!dentry->d_lockref.count)
+		to_shrink_list(dentry, dispose);
+	spin_unlock(&dentry->d_lock);
+}
+EXPORT_SYMBOL(d_dispose_if_unused);
+
 /*
  *	Try to kill dentries associated with this inode.
  * WARNING: you must own a reference to inode.
@@ -1034,12 +1123,8 @@ void d_prune_aliases(struct inode *inode)
 	struct dentry *dentry;
 
 	spin_lock(&inode->i_lock);
-	hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
-		spin_lock(&dentry->d_lock);
-		if (!dentry->d_lockref.count)
-			to_shrink_list(dentry, &dispose);
-		spin_unlock(&dentry->d_lock);
-	}
+	hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias)
+		d_dispose_if_unused(dentry, &dispose);
 	spin_unlock(&inode->i_lock);
 	shrink_dentry_list(&dispose);
 }
@@ -1079,9 +1164,10 @@ void shrink_dentry_list(struct list_head *list)
 		shrink_kill(dentry);
 	}
 }
+EXPORT_SYMBOL(shrink_dentry_list);
 
 static enum lru_status dentry_lru_isolate(struct list_head *item,
-		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
+		struct list_lru_one *lru, void *arg)
 {
 	struct list_head *freeable = arg;
 	struct dentry	*dentry = container_of(item, struct dentry, d_lru);
@@ -1162,7 +1248,7 @@ long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc)
 }
 
 static enum lru_status dentry_lru_isolate_shrink(struct list_head *item,
-		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
+		struct list_lru_one *lru, void *arg)
 {
 	struct list_head *freeable = arg;
 	struct dentry	*dentry = container_of(item, struct dentry, d_lru);
@@ -1328,6 +1414,7 @@ struct check_mount {
 	unsigned int mounted;
 };
 
+/* locks: mount_locked_reader && dentry->d_lock */
 static enum d_walk_ret path_check_mount(void *data, struct dentry *dentry)
 {
 	struct check_mount *info = data;
@@ -1354,9 +1441,8 @@ int path_has_submounts(const struct path *parent)
 {
 	struct check_mount data = { .mnt = parent->mnt, .mounted = 0 };
 
-	read_seqlock_excl(&mount_lock);
+	guard(mount_locked_reader)();
 	d_walk(parent->dentry, &data, path_check_mount);
-	read_sequnlock_excl(&mount_lock);
 
 	return data.mounted;
 }
@@ -1374,7 +1460,7 @@ int d_set_mounted(struct dentry *dentry)
 {
 	struct dentry *p;
 	int ret = -ENOENT;
-	write_seqlock(&rename_lock);
+	read_seqlock_excl(&rename_lock);
 	for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) {
 		/* Need exclusion wrt. d_invalidate() */
 		spin_lock(&p->d_lock);
@@ -1394,7 +1480,7 @@ int d_set_mounted(struct dentry *dentry)
 	}
  	spin_unlock(&dentry->d_lock);
 out:
-	write_sequnlock(&rename_lock);
+	read_sequnlock_excl(&rename_lock);
 	return ret;
 }
 
@@ -1449,6 +1535,15 @@ out:
 	return ret;
 }
 
+static enum d_walk_ret select_collect_umount(void *_data, struct dentry *dentry)
+{
+	if (dentry->d_flags & DCACHE_PERSISTENT) {
+		dentry->d_flags &= ~DCACHE_PERSISTENT;
+		dentry->d_lockref.count--;
+	}
+	return select_collect(_data, dentry);
+}
+
 static enum d_walk_ret select_collect2(void *_data, struct dentry *dentry)
 {
 	struct select_data *data = _data;
@@ -1477,18 +1572,20 @@ out:
 }
 
 /**
- * shrink_dcache_parent - prune dcache
+ * shrink_dcache_tree - prune dcache
  * @parent: parent of entries to prune
+ * @for_umount: true if we want to unpin the persistent ones
  *
  * Prune the dcache to remove unused children of the parent dentry.
  */
-void shrink_dcache_parent(struct dentry *parent)
+static void shrink_dcache_tree(struct dentry *parent, bool for_umount)
 {
 	for (;;) {
 		struct select_data data = {.start = parent};
 
 		INIT_LIST_HEAD(&data.dispose);
-		d_walk(parent, &data, select_collect);
+		d_walk(parent, &data,
+			for_umount ? select_collect_umount : select_collect);
 
 		if (!list_empty(&data.dispose)) {
 			shrink_dentry_list(&data.dispose);
@@ -1513,6 +1610,11 @@ void shrink_dcache_parent(struct dentry *parent)
 			shrink_dentry_list(&data.dispose);
 	}
 }
+
+void shrink_dcache_parent(struct dentry *parent)
+{
+	shrink_dcache_tree(parent, false);
+}
 EXPORT_SYMBOL(shrink_dcache_parent);
 
 static enum d_walk_ret umount_check(void *_data, struct dentry *dentry)
@@ -1539,7 +1641,7 @@ static enum d_walk_ret umount_check(void *_data, struct dentry *dentry)
 
 static void do_one_tree(struct dentry *dentry)
 {
-	shrink_dcache_parent(dentry);
+	shrink_dcache_tree(dentry, true);
 	d_walk(dentry, dentry, umount_check);
 	d_drop(dentry);
 	dput(dentry);
@@ -1552,7 +1654,7 @@ void shrink_dcache_for_umount(struct super_block *sb)
 {
 	struct dentry *dentry;
 
-	WARN(down_read_trylock(&sb->s_umount), "s_umount should've been locked");
+	rwsem_assert_held_write(&sb->s_umount);
 
 	dentry = sb->s_root;
 	sb->s_root = NULL;
@@ -1636,10 +1738,10 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	 * will still always have a NUL at the end, even if we might
 	 * be overwriting an internal NUL character
 	 */
-	dentry->d_iname[DNAME_INLINE_LEN-1] = 0;
+	dentry->d_shortname.string[DNAME_INLINE_LEN-1] = 0;
 	if (unlikely(!name)) {
 		name = &slash_name;
-		dname = dentry->d_iname;
+		dname = dentry->d_shortname.string;
 	} else if (name->len > DNAME_INLINE_LEN-1) {
 		size_t size = offsetof(struct external_name, name[1]);
 		struct external_name *p = kmalloc(size + name->len,
@@ -1649,35 +1751,34 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 			kmem_cache_free(dentry_cache, dentry); 
 			return NULL;
 		}
-		atomic_set(&p->u.count, 1);
+		atomic_set(&p->count, 1);
 		dname = p->name;
 	} else  {
-		dname = dentry->d_iname;
+		dname = dentry->d_shortname.string;
 	}	
 
-	dentry->d_name.len = name->len;
-	dentry->d_name.hash = name->hash;
+	dentry->__d_name.len = name->len;
+	dentry->__d_name.hash = name->hash;
 	memcpy(dname, name->name, name->len);
 	dname[name->len] = 0;
 
 	/* Make sure we always see the terminating NUL character */
-	smp_store_release(&dentry->d_name.name, dname); /* ^^^ */
+	smp_store_release(&dentry->__d_name.name, dname); /* ^^^ */
 
-	dentry->d_lockref.count = 1;
 	dentry->d_flags = 0;
-	spin_lock_init(&dentry->d_lock);
+	lockref_init(&dentry->d_lockref);
 	seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock);
 	dentry->d_inode = NULL;
 	dentry->d_parent = dentry;
 	dentry->d_sb = sb;
-	dentry->d_op = NULL;
+	dentry->d_op = sb->__s_d_op;
+	dentry->d_flags = sb->s_d_flags;
 	dentry->d_fsdata = NULL;
 	INIT_HLIST_BL_NODE(&dentry->d_hash);
 	INIT_LIST_HEAD(&dentry->d_lru);
 	INIT_HLIST_HEAD(&dentry->d_children);
 	INIT_HLIST_NODE(&dentry->d_u.d_alias);
 	INIT_HLIST_NODE(&dentry->d_sib);
-	d_set_d_op(dentry, dentry->d_sb->s_d_op);
 
 	if (dentry->d_op && dentry->d_op->d_init) {
 		err = dentry->d_op->d_init(dentry);
@@ -1760,8 +1861,9 @@ struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name)
 	struct dentry *dentry = __d_alloc(sb, name);
 	if (likely(dentry)) {
 		dentry->d_flags |= DCACHE_NORCU;
-		if (!sb->s_d_op)
-			d_set_d_op(dentry, &anon_ops);
+		/* d_op_flags(&anon_ops) is 0 */
+		if (!dentry->d_op)
+			dentry->d_op = &anon_ops;
 	}
 	return dentry;
 }
@@ -1776,35 +1878,50 @@ struct dentry *d_alloc_name(struct dentry *parent, const char *name)
 }
 EXPORT_SYMBOL(d_alloc_name);
 
-void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
+#define DCACHE_OP_FLAGS \
+	(DCACHE_OP_HASH | DCACHE_OP_COMPARE | DCACHE_OP_REVALIDATE | \
+	 DCACHE_OP_WEAK_REVALIDATE | DCACHE_OP_DELETE | DCACHE_OP_PRUNE | \
+	 DCACHE_OP_REAL)
+
+static unsigned int d_op_flags(const struct dentry_operations *op)
 {
+	unsigned int flags = 0;
+	if (op) {
+		if (op->d_hash)
+			flags |= DCACHE_OP_HASH;
+		if (op->d_compare)
+			flags |= DCACHE_OP_COMPARE;
+		if (op->d_revalidate)
+			flags |= DCACHE_OP_REVALIDATE;
+		if (op->d_weak_revalidate)
+			flags |= DCACHE_OP_WEAK_REVALIDATE;
+		if (op->d_delete)
+			flags |= DCACHE_OP_DELETE;
+		if (op->d_prune)
+			flags |= DCACHE_OP_PRUNE;
+		if (op->d_real)
+			flags |= DCACHE_OP_REAL;
+	}
+	return flags;
+}
+
+static void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
+{
+	unsigned int flags = d_op_flags(op);
 	WARN_ON_ONCE(dentry->d_op);
-	WARN_ON_ONCE(dentry->d_flags & (DCACHE_OP_HASH	|
-				DCACHE_OP_COMPARE	|
-				DCACHE_OP_REVALIDATE	|
-				DCACHE_OP_WEAK_REVALIDATE	|
-				DCACHE_OP_DELETE	|
-				DCACHE_OP_REAL));
+	WARN_ON_ONCE(dentry->d_flags & DCACHE_OP_FLAGS);
 	dentry->d_op = op;
-	if (!op)
-		return;
-	if (op->d_hash)
-		dentry->d_flags |= DCACHE_OP_HASH;
-	if (op->d_compare)
-		dentry->d_flags |= DCACHE_OP_COMPARE;
-	if (op->d_revalidate)
-		dentry->d_flags |= DCACHE_OP_REVALIDATE;
-	if (op->d_weak_revalidate)
-		dentry->d_flags |= DCACHE_OP_WEAK_REVALIDATE;
-	if (op->d_delete)
-		dentry->d_flags |= DCACHE_OP_DELETE;
-	if (op->d_prune)
-		dentry->d_flags |= DCACHE_OP_PRUNE;
-	if (op->d_real)
-		dentry->d_flags |= DCACHE_OP_REAL;
-
-}
-EXPORT_SYMBOL(d_set_d_op);
+	if (flags)
+		dentry->d_flags |= flags;
+}
+
+void set_default_d_op(struct super_block *s, const struct dentry_operations *ops)
+{
+	unsigned int flags = d_op_flags(ops);
+	s->__s_d_op = ops;
+	s->s_d_flags = (s->s_d_flags & ~DCACHE_OP_FLAGS) | flags;
+}
+EXPORT_SYMBOL(set_default_d_op);
 
 static unsigned d_flags_for_inode(struct inode *inode)
 {
@@ -1846,7 +1963,6 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 	unsigned add_flags = d_flags_for_inode(inode);
 	WARN_ON(d_in_lookup(dentry));
 
-	spin_lock(&dentry->d_lock);
 	/*
 	 * The negative counter only tracks dentries on the LRU. Don't dec if
 	 * d_lru is on another list.
@@ -1859,7 +1975,6 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 	__d_set_inode_and_type(dentry, inode, add_flags);
 	raw_write_seqcount_end(&dentry->d_seq);
 	fsnotify_update_flags(dentry);
-	spin_unlock(&dentry->d_lock);
 }
 
 /**
@@ -1883,7 +1998,9 @@ void d_instantiate(struct dentry *entry, struct inode * inode)
 	if (inode) {
 		security_d_instantiate(entry, inode);
 		spin_lock(&inode->i_lock);
+		spin_lock(&entry->d_lock);
 		__d_instantiate(entry, inode);
+		spin_unlock(&entry->d_lock);
 		spin_unlock(&inode->i_lock);
 	}
 }
@@ -1902,11 +2019,12 @@ void d_instantiate_new(struct dentry *entry, struct inode *inode)
 	lockdep_annotate_inode_mutex_key(inode);
 	security_d_instantiate(entry, inode);
 	spin_lock(&inode->i_lock);
+	spin_lock(&entry->d_lock);
 	__d_instantiate(entry, inode);
-	WARN_ON(!(inode->i_state & I_NEW));
-	inode->i_state &= ~I_NEW & ~I_CREATING;
-	smp_mb();
-	wake_up_bit(&inode->i_state, __I_NEW);
+	spin_unlock(&entry->d_lock);
+	WARN_ON(!(inode_state_read(inode) & I_NEW));
+	inode_state_clear(inode, I_NEW | I_CREATING);
+	inode_wake_up_bit(inode, __I_NEW);
 	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL(d_instantiate_new);
@@ -2026,8 +2144,8 @@ EXPORT_SYMBOL(d_obtain_root);
 
 /**
  * d_add_ci - lookup or allocate new dentry with case-exact name
- * @inode:  the inode case-insensitive lookup has found
  * @dentry: the negative dentry that was passed to the parent's lookup func
+ * @inode:  the inode case-insensitive lookup has found
  * @name:   the case-exact name to be associated with the returned dentry
  *
  * This is to avoid filling the dcache with case-insensitive names to the
@@ -2080,8 +2198,8 @@ EXPORT_SYMBOL(d_add_ci);
 
 /**
  * d_same_name - compare dentry name with case-exact name
- * @parent: parent dentry
  * @dentry: the negative dentry that was passed to the parent's lookup func
+ * @parent: parent dentry
  * @name:   the case-exact name to be associated with the returned dentry
  *
  * Return: true if names are same, or false
@@ -2110,7 +2228,7 @@ static noinline struct dentry *__d_lookup_rcu_op_compare(
 	unsigned *seqp)
 {
 	u64 hashlen = name->hash_len;
-	struct hlist_bl_head *b = d_hash(hashlen_hash(hashlen));
+	struct hlist_bl_head *b = d_hash(hashlen);
 	struct hlist_bl_node *node;
 	struct dentry *dentry;
 
@@ -2160,9 +2278,6 @@ seqretry:
  * without taking d_lock and checking d_seq sequence count against @seq
  * returned here.
  *
- * A refcount may be taken on the found dentry with the d_rcu_to_refcount
- * function.
- *
  * Alternatively, __d_lookup_rcu may be called again to look up the child of
  * the returned dentry, so long as its parent's seqlock is checked after the
  * child is looked up. Thus, an interlocking stepping of sequence lock checks
@@ -2177,7 +2292,7 @@ struct dentry *__d_lookup_rcu(const struct dentry *parent,
 {
 	u64 hashlen = name->hash_len;
 	const unsigned char *str = name->name;
-	struct hlist_bl_head *b = d_hash(hashlen_hash(hashlen));
+	struct hlist_bl_head *b = d_hash(hashlen);
 	struct hlist_bl_node *node;
 	struct dentry *dentry;
 
@@ -2227,11 +2342,20 @@ struct dentry *__d_lookup_rcu(const struct dentry *parent,
 		seq = raw_seqcount_begin(&dentry->d_seq);
 		if (dentry->d_parent != parent)
 			continue;
-		if (d_unhashed(dentry))
-			continue;
 		if (dentry->d_name.hash_len != hashlen)
 			continue;
-		if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0)
+		if (unlikely(dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0))
+			continue;
+		/*
+		 * Check for the dentry being unhashed.
+		 *
+		 * As tempting as it is, we *can't* skip it because of a race window
+		 * between us finding the dentry before it gets unhashed and loading
+		 * the sequence counter after unhashing is finished.
+		 *
+		 * We can at least predict on it.
+		 */
+		if (unlikely(d_unhashed(dentry)))
 			continue;
 		*seqp = seq;
 		return dentry;
@@ -2358,7 +2482,6 @@ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name)
 	}
 	return d_lookup(dir, name);
 }
-EXPORT_SYMBOL(d_hash_and_lookup);
 
 /*
  * When a file is deleted, we have two options:
@@ -2391,6 +2514,8 @@ void d_delete(struct dentry * dentry)
 	 * Are we the only user?
 	 */
 	if (dentry->d_lockref.count == 1) {
+		if (dentry_negative_policy)
+			__d_drop(dentry);
 		dentry->d_flags &= ~DCACHE_CANT_MOUNT;
 		dentry_unlink_inode(dentry);
 	} else {
@@ -2429,8 +2554,8 @@ static inline unsigned start_dir_add(struct inode *dir)
 {
 	preempt_disable_nested();
 	for (;;) {
-		unsigned n = dir->i_dir_seq;
-		if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n)
+		unsigned n = READ_ONCE(dir->i_dir_seq);
+		if (!(n & 1) && try_cmpxchg(&dir->i_dir_seq, &n, n + 1))
 			return n;
 		cpu_relax();
 	}
@@ -2441,7 +2566,8 @@ static inline void end_dir_add(struct inode *dir, unsigned int n,
 {
 	smp_store_release(&dir->i_dir_seq, n + 2);
 	preempt_enable_nested();
-	wake_up_all(d_wait);
+	if (wq_has_sleeper(d_wait))
+		wake_up_all(d_wait);
 }
 
 static void d_wait_lookup(struct dentry *dentry)
@@ -2465,13 +2591,21 @@ struct dentry *d_alloc_parallel(struct dentry *parent,
 	unsigned int hash = name->hash;
 	struct hlist_bl_head *b = in_lookup_hash(parent, hash);
 	struct hlist_bl_node *node;
-	struct dentry *new = d_alloc(parent, name);
+	struct dentry *new = __d_alloc(parent->d_sb, name);
 	struct dentry *dentry;
 	unsigned seq, r_seq, d_seq;
 
 	if (unlikely(!new))
 		return ERR_PTR(-ENOMEM);
 
+	new->d_flags |= DCACHE_PAR_LOOKUP;
+	spin_lock(&parent->d_lock);
+	new->d_parent = dget_dlock(parent);
+	hlist_add_head(&new->d_sib, &parent->d_children);
+	if (parent->d_flags & DCACHE_DISCONNECTED)
+		new->d_flags |= DCACHE_DISCONNECTED;
+	spin_unlock(&parent->d_lock);
+
 retry:
 	rcu_read_lock();
 	seq = smp_load_acquire(&parent->d_inode->i_dir_seq);
@@ -2555,8 +2689,6 @@ retry:
 		return dentry;
 	}
 	rcu_read_unlock();
-	/* we can't take ->d_lock here; it's OK, though. */
-	new->d_flags |= DCACHE_PAR_LOOKUP;
 	new->d_wait = wq;
 	hlist_bl_add_head(&new->d_u.d_in_lookup_hash, b);
 	hlist_bl_unlock(b);
@@ -2602,7 +2734,8 @@ EXPORT_SYMBOL(__d_lookup_unhash_wake);
 
 /* inode->i_lock held if inode is non-NULL */
 
-static inline void __d_add(struct dentry *dentry, struct inode *inode)
+static inline void __d_add(struct dentry *dentry, struct inode *inode,
+			   const struct dentry_operations *ops)
 {
 	wait_queue_head_t *d_wait;
 	struct inode *dir = NULL;
@@ -2613,6 +2746,8 @@ static inline void __d_add(struct dentry *dentry, struct inode *inode)
 		n = start_dir_add(dir);
 		d_wait = __d_lookup_unhash(dentry);
 	}
+	if (unlikely(ops))
+		d_set_d_op(dentry, ops);
 	if (inode) {
 		unsigned add_flags = d_flags_for_inode(inode);
 		hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
@@ -2644,55 +2779,27 @@ void d_add(struct dentry *entry, struct inode *inode)
 		security_d_instantiate(entry, inode);
 		spin_lock(&inode->i_lock);
 	}
-	__d_add(entry, inode);
+	__d_add(entry, inode, NULL);
 }
 EXPORT_SYMBOL(d_add);
 
-/**
- * d_exact_alias - find and hash an exact unhashed alias
- * @entry: dentry to add
- * @inode: The inode to go with this dentry
- *
- * If an unhashed dentry with the same name/parent and desired
- * inode already exists, hash and return it.  Otherwise, return
- * NULL.
- *
- * Parent directory should be locked.
- */
-struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode)
+struct dentry *d_make_persistent(struct dentry *dentry, struct inode *inode)
 {
-	struct dentry *alias;
-	unsigned int hash = entry->d_name.hash;
-
+	WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias));
+	WARN_ON(!inode);
+	security_d_instantiate(dentry, inode);
 	spin_lock(&inode->i_lock);
-	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
-		/*
-		 * Don't need alias->d_lock here, because aliases with
-		 * d_parent == entry->d_parent are not subject to name or
-		 * parent changes, because the parent inode i_mutex is held.
-		 */
-		if (alias->d_name.hash != hash)
-			continue;
-		if (alias->d_parent != entry->d_parent)
-			continue;
-		if (!d_same_name(alias, entry->d_parent, &entry->d_name))
-			continue;
-		spin_lock(&alias->d_lock);
-		if (!d_unhashed(alias)) {
-			spin_unlock(&alias->d_lock);
-			alias = NULL;
-		} else {
-			dget_dlock(alias);
-			__d_rehash(alias);
-			spin_unlock(&alias->d_lock);
-		}
-		spin_unlock(&inode->i_lock);
-		return alias;
-	}
+	spin_lock(&dentry->d_lock);
+	__d_instantiate(dentry, inode);
+	dentry->d_flags |= DCACHE_PERSISTENT;
+	dget_dlock(dentry);
+	if (d_unhashed(dentry))
+		__d_rehash(dentry);
+	spin_unlock(&dentry->d_lock);
 	spin_unlock(&inode->i_lock);
-	return NULL;
+	return dentry;
 }
-EXPORT_SYMBOL(d_exact_alias);
+EXPORT_SYMBOL(d_make_persistent);
 
 static void swap_names(struct dentry *dentry, struct dentry *target)
 {
@@ -2701,16 +2808,15 @@ static void swap_names(struct dentry *dentry, struct dentry *target)
 			/*
 			 * Both external: swap the pointers
 			 */
-			swap(target->d_name.name, dentry->d_name.name);
+			swap(target->__d_name.name, dentry->__d_name.name);
 		} else {
 			/*
 			 * dentry:internal, target:external.  Steal target's
 			 * storage and make target internal.
 			 */
-			memcpy(target->d_iname, dentry->d_name.name,
-					dentry->d_name.len + 1);
-			dentry->d_name.name = target->d_name.name;
-			target->d_name.name = target->d_iname;
+			dentry->__d_name.name = target->__d_name.name;
+			target->d_shortname = dentry->d_shortname;
+			target->__d_name.name = target->d_shortname.string;
 		}
 	} else {
 		if (unlikely(dname_external(dentry))) {
@@ -2718,23 +2824,19 @@ static void swap_names(struct dentry *dentry, struct dentry *target)
 			 * dentry:external, target:internal.  Give dentry's
 			 * storage to target and make dentry internal
 			 */
-			memcpy(dentry->d_iname, target->d_name.name,
-					target->d_name.len + 1);
-			target->d_name.name = dentry->d_name.name;
-			dentry->d_name.name = dentry->d_iname;
+			target->__d_name.name = dentry->__d_name.name;
+			dentry->d_shortname = target->d_shortname;
+			dentry->__d_name.name = dentry->d_shortname.string;
 		} else {
 			/*
 			 * Both are internal.
 			 */
-			unsigned int i;
-			BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long)));
-			for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) {
-				swap(((long *) &dentry->d_iname)[i],
-				     ((long *) &target->d_iname)[i]);
-			}
+			for (int i = 0; i < DNAME_INLINE_WORDS; i++)
+				swap(dentry->d_shortname.words[i],
+				     target->d_shortname.words[i]);
 		}
 	}
-	swap(dentry->d_name.hash_len, target->d_name.hash_len);
+	swap(dentry->__d_name.hash_len, target->__d_name.hash_len);
 }
 
 static void copy_name(struct dentry *dentry, struct dentry *target)
@@ -2743,16 +2845,15 @@ static void copy_name(struct dentry *dentry, struct dentry *target)
 	if (unlikely(dname_external(dentry)))
 		old_name = external_name(dentry);
 	if (unlikely(dname_external(target))) {
-		atomic_inc(&external_name(target)->u.count);
-		dentry->d_name = target->d_name;
+		atomic_inc(&external_name(target)->count);
+		dentry->__d_name = target->__d_name;
 	} else {
-		memcpy(dentry->d_iname, target->d_name.name,
-				target->d_name.len + 1);
-		dentry->d_name.name = dentry->d_iname;
-		dentry->d_name.hash_len = target->d_name.hash_len;
+		dentry->d_shortname = target->d_shortname;
+		dentry->__d_name.name = dentry->d_shortname.string;
+		dentry->__d_name.hash_len = target->__d_name.hash_len;
 	}
-	if (old_name && likely(atomic_dec_and_test(&old_name->u.count)))
-		kfree_rcu(old_name, u.head);
+	if (old_name && likely(atomic_dec_and_test(&old_name->count)))
+		kfree_rcu(old_name, head);
 }
 
 /*
@@ -2761,10 +2862,10 @@ static void copy_name(struct dentry *dentry, struct dentry *target)
  * @target: new dentry
  * @exchange: exchange the two dentries
  *
- * Update the dcache to reflect the move of a file name. Negative
- * dcache entries should not be moved in this way. Caller must hold
- * rename_lock, the i_mutex of the source and target directories,
- * and the sb->s_vfs_rename_mutex if they differ. See lock_rename().
+ * Update the dcache to reflect the move of a file name. Negative dcache
+ * entries should not be moved in this way. Caller must hold rename_lock, the
+ * i_rwsem of the source and target directories (exclusively), and the sb->
+ * s_vfs_rename_mutex if they differ. See lock_rename().
  */
 static void __d_move(struct dentry *dentry, struct dentry *target,
 		     bool exchange)
@@ -2886,6 +2987,7 @@ void d_exchange(struct dentry *dentry1, struct dentry *dentry2)
 
 	write_sequnlock(&rename_lock);
 }
+EXPORT_SYMBOL(d_exchange);
 
 /**
  * d_ancestor - search for an ancestor
@@ -2910,7 +3012,7 @@ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2)
  * This helper attempts to cope with remotely renamed directories
  *
  * It assumes that the caller is already holding
- * dentry->d_parent->d_inode->i_mutex, and rename_lock
+ * dentry->d_parent->d_inode->i_rwsem, and rename_lock
  *
  * Note: If ever the locking in lock_rename() changes, then please
  * remember to update this too...
@@ -2933,7 +3035,12 @@ static int __d_unalias(struct dentry *dentry, struct dentry *alias)
 		goto out_err;
 	m2 = &alias->d_parent->d_inode->i_rwsem;
 out_unalias:
+	if (alias->d_op && alias->d_op->d_unalias_trylock &&
+	    !alias->d_op->d_unalias_trylock(alias))
+		goto out_err;
 	__d_move(alias, dentry, false);
+	if (alias->d_op && alias->d_op->d_unalias_unlock)
+		alias->d_op->d_unalias_unlock(alias);
 	ret = 0;
 out_err:
 	if (m2)
@@ -2943,30 +3050,8 @@ out_err:
 	return ret;
 }
 
-/**
- * d_splice_alias - splice a disconnected dentry into the tree if one exists
- * @inode:  the inode which may have a disconnected dentry
- * @dentry: a negative dentry which we want to point to the inode.
- *
- * If inode is a directory and has an IS_ROOT alias, then d_move that in
- * place of the given dentry and return it, else simply d_add the inode
- * to the dentry and return NULL.
- *
- * If a non-IS_ROOT directory is found, the filesystem is corrupt, and
- * we should error out: directories can't have multiple aliases.
- *
- * This is needed in the lookup routine of any filesystem that is exportable
- * (via knfsd) so that we can build dcache paths to directories effectively.
- *
- * If a dentry was found and moved, then it is returned.  Otherwise NULL
- * is returned.  This matches the expected return value of ->lookup.
- *
- * Cluster filesystems may call this function with a negative, hashed dentry.
- * In that case, we know that the inode will be a regular file, and also this
- * will only occur during atomic_open. So we need to check for the dentry
- * being already hashed only in the final case.
- */
-struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
+struct dentry *d_splice_alias_ops(struct inode *inode, struct dentry *dentry,
+				  const struct dentry_operations *ops)
 {
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
@@ -3012,9 +3097,37 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
 		}
 	}
 out:
-	__d_add(dentry, inode);
+	__d_add(dentry, inode, ops);
 	return NULL;
 }
+
+/**
+ * d_splice_alias - splice a disconnected dentry into the tree if one exists
+ * @inode:  the inode which may have a disconnected dentry
+ * @dentry: a negative dentry which we want to point to the inode.
+ *
+ * If inode is a directory and has an IS_ROOT alias, then d_move that in
+ * place of the given dentry and return it, else simply d_add the inode
+ * to the dentry and return NULL.
+ *
+ * If a non-IS_ROOT directory is found, the filesystem is corrupt, and
+ * we should error out: directories can't have multiple aliases.
+ *
+ * This is needed in the lookup routine of any filesystem that is exportable
+ * (via knfsd) so that we can build dcache paths to directories effectively.
+ *
+ * If a dentry was found and moved, then it is returned.  Otherwise NULL
+ * is returned.  This matches the expected return value of ->lookup.
+ *
+ * Cluster filesystems may call this function with a negative, hashed dentry.
+ * In that case, we know that the inode will be a regular file, and also this
+ * will only occur during atomic_open. So we need to check for the dentry
+ * being already hashed only in the final case.
+ */
+struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
+{
+	return d_splice_alias_ops(inode, dentry, NULL);
+}
 EXPORT_SYMBOL(d_splice_alias);
 
 /*
@@ -3057,36 +3170,16 @@ bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry)
 }
 EXPORT_SYMBOL(is_subdir);
 
-static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry)
-{
-	struct dentry *root = data;
-	if (dentry != root) {
-		if (d_unhashed(dentry) || !dentry->d_inode)
-			return D_WALK_SKIP;
-
-		if (!(dentry->d_flags & DCACHE_GENOCIDE)) {
-			dentry->d_flags |= DCACHE_GENOCIDE;
-			dentry->d_lockref.count--;
-		}
-	}
-	return D_WALK_CONTINUE;
-}
-
-void d_genocide(struct dentry *parent)
-{
-	d_walk(parent, parent, d_genocide_kill);
-}
-
 void d_mark_tmpfile(struct file *file, struct inode *inode)
 {
 	struct dentry *dentry = file->f_path.dentry;
 
-	BUG_ON(dentry->d_name.name != dentry->d_iname ||
+	BUG_ON(dname_external(dentry) ||
 		!hlist_unhashed(&dentry->d_u.d_alias) ||
 		!d_unlinked(dentry));
 	spin_lock(&dentry->d_parent->d_lock);
 	spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
-	dentry->d_name.len = sprintf(dentry->d_iname, "#%llu",
+	dentry->__d_name.len = sprintf(dentry->d_shortname.string, "#%llu",
 				(unsigned long long)inode->i_ino);
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&dentry->d_parent->d_lock);
@@ -3103,6 +3196,34 @@ void d_tmpfile(struct file *file, struct inode *inode)
 }
 EXPORT_SYMBOL(d_tmpfile);
 
+/*
+ * Obtain inode number of the parent dentry.
+ */
+ino_t d_parent_ino(struct dentry *dentry)
+{
+	struct dentry *parent;
+	struct inode *iparent;
+	unsigned seq;
+	ino_t ret;
+
+	scoped_guard(rcu) {
+		seq = raw_seqcount_begin(&dentry->d_seq);
+		parent = READ_ONCE(dentry->d_parent);
+		iparent = d_inode_rcu(parent);
+		if (likely(iparent)) {
+			ret = iparent->i_ino;
+			if (!read_seqcount_retry(&dentry->d_seq, seq))
+				return ret;
+		}
+	}
+
+	spin_lock(&dentry->d_lock);
+	ret = dentry->d_parent->d_inode->i_ino;
+	spin_unlock(&dentry->d_lock);
+	return ret;
+}
+EXPORT_SYMBOL(d_parent_ino);
+
 static __initdata unsigned long dhash_entries;
 static int __init set_dhash_entries(char *str)
 {
@@ -3132,6 +3253,9 @@ static void __init dcache_init_early(void)
 					0,
 					0);
 	d_hash_shift = 32 - d_hash_shift;
+
+	runtime_const_init(shift, d_hash_shift);
+	runtime_const_init(ptr, dentry_hashtable);
 }
 
 static void __init dcache_init(void)
@@ -3141,9 +3265,10 @@ static void __init dcache_init(void)
 	 * but it is probably not worth it because of the cache nature
 	 * of the dcache.
 	 */
-	dentry_cache = KMEM_CACHE_USERCOPY(dentry,
+	__dentry_cache = KMEM_CACHE_USERCOPY(dentry,
 		SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT,
-		d_iname);
+		d_shortname.string);
+	runtime_const_init(ptr, __dentry_cache);
 
 	/* Hash may have been set up in dcache_init_early */
 	if (!hashdist)
@@ -3160,6 +3285,9 @@ static void __init dcache_init(void)
 					0,
 					0);
 	d_hash_shift = 32 - d_hash_shift;
+
+	runtime_const_init(shift, d_hash_shift);
+	runtime_const_init(ptr, dentry_hashtable);
 }
 
 /* SLAB cache for __getname() consumers */