#include <linux/init.h>
#include <linux/hash.h>
#include <linux/cache.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/mount.h>
#include <linux/file.h>
#include <asm/uaccess.h>
#include <linux/bit_spinlock.h>
#include <linux/rculist_bl.h>
#include <linux/prefetch.h>
+#include <linux/ratelimit.h>
#include "internal.h"
+#include "mount.h"
/*
* Usage:
* dcache->d_inode->i_lock protects:
- * - i_dentry, d_alias, d_inode of aliases
+ * - i_dentry, d_u.d_alias, d_inode of aliases
* dcache_hash_bucket lock protects:
* - the dcache hash table
* s_anon bl list spinlock protects:
* - d_unhashed()
* - d_parent and d_subdirs
* - childrens' d_child and d_parent
- * - d_alias, d_inode
+ * - d_u.d_alias, d_inode
*
* Ordering:
* dentry->d_inode->i_lock
* This hash-function tries to avoid losing too many bits of hash
* information, yet avoid using a prime hash-size or similar.
*/
-#define D_HASHBITS d_hash_shift
-#define D_HASHMASK d_hash_mask
static unsigned int d_hash_mask __read_mostly;
static unsigned int d_hash_shift __read_mostly;
static struct hlist_bl_head *dentry_hashtable __read_mostly;
-static inline struct hlist_bl_head *d_hash(struct dentry *parent,
- unsigned long hash)
+static inline struct hlist_bl_head *d_hash(const struct dentry *parent,
+ unsigned int hash)
{
- hash += ((unsigned long) parent ^ GOLDEN_RATIO_PRIME) / L1_CACHE_BYTES;
- hash = hash ^ ((hash ^ GOLDEN_RATIO_PRIME) >> D_HASHBITS);
- return dentry_hashtable + (hash & D_HASHMASK);
+ hash += (unsigned long) parent / L1_CACHE_BYTES;
+ return dentry_hashtable + hash_32(hash, d_hash_shift);
}
/* Statistics gathering. */
}
#endif
+/*
+ * Compare 2 name strings, return 0 if they match, otherwise non-zero.
+ * The strings are both count bytes long, and count is non-zero.
+ */
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+
+#include <asm/word-at-a-time.h>
+/*
+ * NOTE! 'cs' and 'scount' come from a dentry, so it has a
+ * aligned allocation for this particular component. We don't
+ * strictly need the load_unaligned_zeropad() safety, but it
+ * doesn't hurt either.
+ *
+ * In contrast, 'ct' and 'tcount' can be from a pathname, and do
+ * need the careful unaligned handling.
+ */
+static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount)
+{
+ unsigned long a,b,mask;
+
+ for (;;) {
+ a = *(unsigned long *)cs;
+ b = load_unaligned_zeropad(ct);
+ if (tcount < sizeof(unsigned long))
+ break;
+ if (unlikely(a != b))
+ return 1;
+ cs += sizeof(unsigned long);
+ ct += sizeof(unsigned long);
+ tcount -= sizeof(unsigned long);
+ if (!tcount)
+ return 0;
+ }
+ mask = ~(~0ul << tcount*8);
+ return unlikely(!!((a ^ b) & mask));
+}
+
+#else
+
+static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount)
+{
+ do {
+ if (*cs != *ct)
+ return 1;
+ cs++;
+ ct++;
+ tcount--;
+ } while (tcount);
+ return 0;
+}
+
+#endif
+
+static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount)
+{
+ const unsigned char *cs;
+ /*
+ * Be careful about RCU walk racing with rename:
+ * use ACCESS_ONCE to fetch the name pointer.
+ *
+ * NOTE! Even if a rename will mean that the length
+ * was not loaded atomically, we don't care. The
+ * RCU walk will check the sequence count eventually,
+ * and catch it. And we won't overrun the buffer,
+ * because we're reading the name pointer atomically,
+ * and a dentry name is guaranteed to be properly
+ * terminated with a NUL byte.
+ *
+ * End result: even if 'len' is wrong, we'll exit
+ * early because the data cannot match (there can
+ * be no NUL in the ct/tcount data)
+ */
+ cs = ACCESS_ONCE(dentry->d_name.name);
+ smp_read_barrier_depends();
+ return dentry_string_cmp(cs, ct, tcount);
+}
+
static void __d_free(struct rcu_head *head)
{
struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
- WARN_ON(!list_empty(&dentry->d_alias));
if (dname_external(dentry))
kfree(dentry->d_name.name);
kmem_cache_free(dentry_cache, dentry);
*/
static void d_free(struct dentry *dentry)
{
+ WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias));
BUG_ON(dentry->d_count);
this_cpu_dec(nr_dentry);
if (dentry->d_op && dentry->d_op->d_release)
struct inode *inode = dentry->d_inode;
if (inode) {
dentry->d_inode = NULL;
- list_del_init(&dentry->d_alias);
+ hlist_del_init(&dentry->d_u.d_alias);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
if (!inode->i_nlink)
{
struct inode *inode = dentry->d_inode;
dentry->d_inode = NULL;
- list_del_init(&dentry->d_alias);
+ hlist_del_init(&dentry->d_u.d_alias);
dentry_rcuwalk_barrier(dentry);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
}
/*
- * dentry_lru_(add|del|move_tail) must be called with d_lock held.
+ * dentry_lru_(add|del|prune|move_tail) must be called with d_lock held.
*/
static void dentry_lru_add(struct dentry *dentry)
{
static void __dentry_lru_del(struct dentry *dentry)
{
list_del_init(&dentry->d_lru);
+ dentry->d_flags &= ~DCACHE_SHRINK_LIST;
dentry->d_sb->s_nr_dentry_unused--;
dentry_stat.nr_unused--;
}
+/*
+ * Remove a dentry with references from the LRU.
+ */
static void dentry_lru_del(struct dentry *dentry)
{
if (!list_empty(&dentry->d_lru)) {
}
}
-static void dentry_lru_move_tail(struct dentry *dentry)
+static void dentry_lru_move_list(struct dentry *dentry, struct list_head *list)
{
spin_lock(&dcache_lru_lock);
if (list_empty(&dentry->d_lru)) {
- list_add_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
+ list_add_tail(&dentry->d_lru, list);
dentry->d_sb->s_nr_dentry_unused++;
dentry_stat.nr_unused++;
} else {
- list_move_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
+ list_move_tail(&dentry->d_lru, list);
}
spin_unlock(&dcache_lru_lock);
}
__releases(parent->d_lock)
__releases(dentry->d_inode->i_lock)
{
- list_del(&dentry->d_u.d_child);
+ __list_del_entry(&dentry->d_child);
/*
- * Inform try_to_ascend() that we are no longer attached to the
+ * Inform ascending readers that we are no longer attached to the
* dentry tree
*/
- dentry->d_flags |= DCACHE_DISCONNECTED;
+ dentry->d_flags |= DCACHE_DENTRY_KILLED;
if (parent)
spin_unlock(&parent->d_lock);
dentry_iput(dentry);
}
EXPORT_SYMBOL(d_drop);
-/*
- * d_clear_need_lookup - drop a dentry from cache and clear the need lookup flag
- * @dentry: dentry to drop
- *
- * This is called when we do a lookup on a placeholder dentry that needed to be
- * looked up. The dentry should have been hashed in order for it to be found by
- * the lookup code, but now needs to be unhashed while we do the actual lookup
- * and clear the DCACHE_NEED_LOOKUP flag.
- */
-void d_clear_need_lookup(struct dentry *dentry)
-{
- spin_lock(&dentry->d_lock);
- __d_drop(dentry);
- dentry->d_flags &= ~DCACHE_NEED_LOOKUP;
- spin_unlock(&dentry->d_lock);
-}
-EXPORT_SYMBOL(d_clear_need_lookup);
-
/*
* Finish off a dentry we've decided to kill.
* dentry->d_lock must be held, returns with it unlocked.
if (ref)
dentry->d_count--;
- /* if dentry was on the d_lru list delete it from there */
+ /*
+ * inform the fs via d_prune that this dentry is about to be
+ * unhashed and destroyed.
+ */
+ if (dentry->d_flags & DCACHE_OP_PRUNE)
+ dentry->d_op->d_prune(dentry);
+
dentry_lru_del(dentry);
/* if it was on the hash then remove it */
__d_drop(dentry);
return;
}
+ if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED))
+ goto kill_it;
+
if (dentry->d_flags & DCACHE_OP_DELETE) {
if (dentry->d_op->d_delete(dentry))
goto kill_it;
if (d_unhashed(dentry))
goto kill_it;
- /*
- * If this dentry needs lookup, don't set the referenced flag so that it
- * is more likely to be cleaned up by the dcache shrinker in case of
- * memory pressure.
- */
- if (!d_need_lookup(dentry))
- dentry->d_flags |= DCACHE_REFERENCED;
+ dentry->d_flags |= DCACHE_REFERENCED;
dentry_lru_add(dentry);
dentry->d_count--;
* would make it unreachable from the root,
* we might still populate it if it was a
* working directory or similar).
+ * We also need to leave mountpoints alone,
+ * directory or not.
*/
- if (dentry->d_count > 1) {
- if (dentry->d_inode && S_ISDIR(dentry->d_inode->i_mode)) {
+ if (dentry->d_count > 1 && dentry->d_inode) {
+ if (S_ISDIR(dentry->d_inode->i_mode) || d_mountpoint(dentry)) {
spin_unlock(&dentry->d_lock);
return -EBUSY;
}
again:
discon_alias = NULL;
- list_for_each_entry(alias, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
spin_lock(&alias->d_lock);
if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
if (IS_ROOT(alias) &&
{
struct dentry *de = NULL;
- if (!list_empty(&inode->i_dentry)) {
+ if (!hlist_empty(&inode->i_dentry)) {
spin_lock(&inode->i_lock);
de = __d_find_alias(inode, 0);
spin_unlock(&inode->i_lock);
struct dentry *dentry;
restart:
spin_lock(&inode->i_lock);
- list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
spin_lock(&dentry->d_lock);
if (!dentry->d_count) {
__dget_dlock(dentry);
}
/**
- * __shrink_dcache_sb - shrink the dentry LRU on a given superblock
- * @sb: superblock to shrink dentry LRU.
- * @count: number of entries to prune
- * @flags: flags to control the dentry processing
+ * prune_dcache_sb - shrink the dcache
+ * @sb: superblock
+ * @count: number of entries to try to free
+ *
+ * Attempt to shrink the superblock dcache LRU by @count entries. This is
+ * done when we need more memory an called from the superblock shrinker
+ * function.
*
- * If flags contains DCACHE_REFERENCED reference dentries will not be pruned.
+ * This function may fail to free any resources if all the dentries are in
+ * use.
*/
-static void __shrink_dcache_sb(struct super_block *sb, int count, int flags)
+void prune_dcache_sb(struct super_block *sb, int count)
{
struct dentry *dentry;
LIST_HEAD(referenced);
goto relock;
}
- /*
- * If we are honouring the DCACHE_REFERENCED flag and the
- * dentry has this flag set, don't free it. Clear the flag
- * and put it back on the LRU.
- */
- if (flags & DCACHE_REFERENCED &&
- dentry->d_flags & DCACHE_REFERENCED) {
+ if (dentry->d_flags & DCACHE_REFERENCED) {
dentry->d_flags &= ~DCACHE_REFERENCED;
list_move(&dentry->d_lru, &referenced);
spin_unlock(&dentry->d_lock);
} else {
list_move_tail(&dentry->d_lru, &tmp);
+ dentry->d_flags |= DCACHE_SHRINK_LIST;
spin_unlock(&dentry->d_lock);
if (!--count)
break;
shrink_dentry_list(&tmp);
}
-/**
- * prune_dcache_sb - shrink the dcache
- * @nr_to_scan: number of entries to try to free
- *
- * Attempt to shrink the superblock dcache LRU by @nr_to_scan entries. This is
- * done when we need more memory an called from the superblock shrinker
- * function.
- *
- * This function may fail to free any resources if all the dentries are in
- * use.
- */
-void prune_dcache_sb(struct super_block *sb, int nr_to_scan)
-{
- __shrink_dcache_sb(sb, nr_to_scan, DCACHE_REFERENCED);
-}
-
/**
* shrink_dcache_sb - shrink dcache for a superblock
* @sb: superblock
BUG_ON(!IS_ROOT(dentry));
- /* detach this root from the system */
- dentry_lru_del(dentry);
- __d_shrink(dentry);
-
for (;;) {
/* descend to the first leaf in the current subtree */
- while (!list_empty(&dentry->d_subdirs)) {
- struct dentry *loop;
-
- /* this is a branch with children - detach all of them
- * from the system in one go */
- list_for_each_entry(loop, &dentry->d_subdirs,
- d_u.d_child) {
- dentry_lru_del(loop);
- __d_shrink(loop);
- }
-
- /* move to the first child */
+ while (!list_empty(&dentry->d_subdirs))
dentry = list_entry(dentry->d_subdirs.next,
- struct dentry, d_u.d_child);
- }
+ struct dentry, d_child);
/* consume the dentries from this leaf up through its parents
* until we find one with children or run out altogether */
do {
struct inode *inode;
+ /*
+ * inform the fs that this dentry is about to be
+ * unhashed and destroyed.
+ */
+ if (dentry->d_flags & DCACHE_OP_PRUNE)
+ dentry->d_op->d_prune(dentry);
+
+ dentry_lru_del(dentry);
+ __d_shrink(dentry);
+
if (dentry->d_count != 0) {
printk(KERN_ERR
"BUG: Dentry %p{i=%lx,n=%s}"
if (IS_ROOT(dentry)) {
parent = NULL;
- list_del(&dentry->d_u.d_child);
+ list_del(&dentry->d_child);
} else {
parent = dentry->d_parent;
parent->d_count--;
- list_del(&dentry->d_u.d_child);
+ list_del(&dentry->d_child);
}
inode = dentry->d_inode;
if (inode) {
dentry->d_inode = NULL;
- list_del_init(&dentry->d_alias);
+ hlist_del_init(&dentry->d_u.d_alias);
if (dentry->d_op && dentry->d_op->d_iput)
dentry->d_op->d_iput(dentry, inode);
else
} while (list_empty(&dentry->d_subdirs));
dentry = list_entry(dentry->d_subdirs.next,
- struct dentry, d_u.d_child);
+ struct dentry, d_child);
}
}
}
}
-/*
- * This tries to ascend one level of parenthood, but
- * we can race with renaming, so we need to re-check
- * the parenthood after dropping the lock and check
- * that the sequence number still matches.
- */
-static struct dentry *try_to_ascend(struct dentry *old, int locked, unsigned seq)
-{
- struct dentry *new = old->d_parent;
-
- rcu_read_lock();
- spin_unlock(&old->d_lock);
- spin_lock(&new->d_lock);
-
- /*
- * might go back up the wrong parent if we have had a rename
- * or deletion
- */
- if (new != old->d_parent ||
- (old->d_flags & DCACHE_DISCONNECTED) ||
- (!locked && read_seqretry(&rename_lock, seq))) {
- spin_unlock(&new->d_lock);
- new = NULL;
- }
- rcu_read_unlock();
- return new;
-}
-
-
/*
* Search for at least 1 mount point in the dentry's subdirs.
* We descend to the next level whenever the d_subdirs
resume:
while (next != &this_parent->d_subdirs) {
struct list_head *tmp = next;
- struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
+ struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
next = tmp->next;
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
/*
* All done at this level ... ascend and resume the search.
*/
+ rcu_read_lock();
+ascend:
if (this_parent != parent) {
struct dentry *child = this_parent;
- this_parent = try_to_ascend(this_parent, locked, seq);
- if (!this_parent)
+ this_parent = child->d_parent;
+
+ spin_unlock(&child->d_lock);
+ spin_lock(&this_parent->d_lock);
+
+ /* might go back up the wrong parent if we have had a rename. */
+ if (!locked && read_seqretry(&rename_lock, seq))
goto rename_retry;
- next = child->d_u.d_child.next;
+ /* go into the first sibling still alive */
+ do {
+ next = child->d_child.next;
+ if (next == &this_parent->d_subdirs)
+ goto ascend;
+ child = list_entry(next, struct dentry, d_child);
+ } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
+ rcu_read_unlock();
goto resume;
}
- spin_unlock(&this_parent->d_lock);
if (!locked && read_seqretry(&rename_lock, seq))
goto rename_retry;
+ spin_unlock(&this_parent->d_lock);
+ rcu_read_unlock();
if (locked)
write_sequnlock(&rename_lock);
return 0; /* No mount points found in tree */
positive:
if (!locked && read_seqretry(&rename_lock, seq))
- goto rename_retry;
+ goto rename_retry_unlocked;
if (locked)
write_sequnlock(&rename_lock);
return 1;
rename_retry:
+ spin_unlock(&this_parent->d_lock);
+ rcu_read_unlock();
+ if (locked)
+ goto again;
+rename_retry_unlocked:
locked = 1;
write_seqlock(&rename_lock);
goto again;
EXPORT_SYMBOL(have_submounts);
/*
- * Search the dentry child list for the specified parent,
+ * Search the dentry child list of the specified parent,
* and move any unused dentries to the end of the unused
* list for prune_dcache(). We descend to the next level
* whenever the d_subdirs list is non-empty and continue
* drop the lock and return early due to latency
* constraints.
*/
-static int select_parent(struct dentry * parent)
+static int select_parent(struct dentry *parent, struct list_head *dispose)
{
struct dentry *this_parent;
struct list_head *next;
resume:
while (next != &this_parent->d_subdirs) {
struct list_head *tmp = next;
- struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
+ struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
next = tmp->next;
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
- /*
- * move only zero ref count dentries to the end
- * of the unused list for prune_dcache
+ /*
+ * move only zero ref count dentries to the dispose list.
+ *
+ * Those which are presently on the shrink list, being processed
+ * by shrink_dentry_list(), shouldn't be moved. Otherwise the
+ * loop in shrink_dcache_parent() might not make any progress
+ * and loop forever.
*/
- if (!dentry->d_count) {
- dentry_lru_move_tail(dentry);
- found++;
- } else {
+ if (dentry->d_count) {
dentry_lru_del(dentry);
+ } else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
+ dentry_lru_move_list(dentry, dispose);
+ dentry->d_flags |= DCACHE_SHRINK_LIST;
+ found++;
}
-
/*
* We can return to the caller if we have found some (this
* ensures forward progress). We'll be coming back to find
*/
if (found && need_resched()) {
spin_unlock(&dentry->d_lock);
+ rcu_read_lock();
goto out;
}
/*
* All done at this level ... ascend and resume the search.
*/
+ rcu_read_lock();
+ascend:
if (this_parent != parent) {
struct dentry *child = this_parent;
- this_parent = try_to_ascend(this_parent, locked, seq);
- if (!this_parent)
+ this_parent = child->d_parent;
+
+ spin_unlock(&child->d_lock);
+ spin_lock(&this_parent->d_lock);
+
+ /* might go back up the wrong parent if we have had a rename. */
+ if (!locked && read_seqretry(&rename_lock, seq))
goto rename_retry;
- next = child->d_u.d_child.next;
+ /* go into the first sibling still alive */
+ do {
+ next = child->d_child.next;
+ if (next == &this_parent->d_subdirs)
+ goto ascend;
+ child = list_entry(next, struct dentry, d_child);
+ } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
+ rcu_read_unlock();
goto resume;
}
out:
- spin_unlock(&this_parent->d_lock);
if (!locked && read_seqretry(&rename_lock, seq))
goto rename_retry;
+ spin_unlock(&this_parent->d_lock);
+ rcu_read_unlock();
if (locked)
write_sequnlock(&rename_lock);
return found;
rename_retry:
+ spin_unlock(&this_parent->d_lock);
+ rcu_read_unlock();
if (found)
return found;
+ if (locked)
+ goto again;
locked = 1;
write_seqlock(&rename_lock);
goto again;
*
* Prune the dcache to remove unused children of the parent dentry.
*/
-
void shrink_dcache_parent(struct dentry * parent)
{
- struct super_block *sb = parent->d_sb;
+ LIST_HEAD(dispose);
int found;
- while ((found = select_parent(parent)) != 0)
- __shrink_dcache_sb(sb, found, 0);
+ while ((found = select_parent(parent, &dispose)) != 0) {
+ shrink_dentry_list(&dispose);
+ cond_resched();
+ }
}
EXPORT_SYMBOL(shrink_dcache_parent);
if (!dentry)
return NULL;
+ /*
+ * We guarantee that the inline name is always NUL-terminated.
+ * This way the memcpy() done by the name switching in rename
+ * 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;
if (name->len > DNAME_INLINE_LEN-1) {
dname = kmalloc(name->len + 1, GFP_KERNEL);
if (!dname) {
} else {
dname = dentry->d_iname;
}
- dentry->d_name.name = dname;
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_wmb();
+ dentry->d_name.name = dname;
+
dentry->d_count = 1;
dentry->d_flags = 0;
spin_lock_init(&dentry->d_lock);
INIT_HLIST_BL_NODE(&dentry->d_hash);
INIT_LIST_HEAD(&dentry->d_lru);
INIT_LIST_HEAD(&dentry->d_subdirs);
- INIT_LIST_HEAD(&dentry->d_alias);
- INIT_LIST_HEAD(&dentry->d_u.d_child);
+ INIT_HLIST_NODE(&dentry->d_u.d_alias);
+ INIT_LIST_HEAD(&dentry->d_child);
d_set_d_op(dentry, dentry->d_sb->s_d_op);
this_cpu_inc(nr_dentry);
*/
__dget_dlock(parent);
dentry->d_parent = parent;
- list_add(&dentry->d_u.d_child, &parent->d_subdirs);
+ list_add(&dentry->d_child, &parent->d_subdirs);
spin_unlock(&parent->d_lock);
return dentry;
WARN_ON_ONCE(dentry->d_flags & (DCACHE_OP_HASH |
DCACHE_OP_COMPARE |
DCACHE_OP_REVALIDATE |
+ DCACHE_OP_WEAK_REVALIDATE |
DCACHE_OP_DELETE ));
dentry->d_op = op;
if (!op)
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;
}
EXPORT_SYMBOL(d_set_d_op);
if (inode) {
if (unlikely(IS_AUTOMOUNT(inode)))
dentry->d_flags |= DCACHE_NEED_AUTOMOUNT;
- list_add(&dentry->d_alias, &inode->i_dentry);
+ hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
}
dentry->d_inode = inode;
dentry_rcuwalk_barrier(dentry);
void d_instantiate(struct dentry *entry, struct inode * inode)
{
- BUG_ON(!list_empty(&entry->d_alias));
+ BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
if (inode)
spin_lock(&inode->i_lock);
__d_instantiate(entry, inode);
return NULL;
}
- list_for_each_entry(alias, &inode->i_dentry, d_alias) {
- struct qstr *qstr = &alias->d_name;
-
+ 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 (qstr->hash != hash)
+ if (alias->d_name.hash != hash)
continue;
if (alias->d_parent != entry->d_parent)
continue;
- if (dentry_cmp(qstr->name, qstr->len, name, len))
+ if (alias->d_name.len != len)
+ continue;
+ if (dentry_cmp(alias, name, len))
continue;
__dget(alias);
return alias;
{
struct dentry *result;
- BUG_ON(!list_empty(&entry->d_alias));
+ BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
if (inode)
spin_lock(&inode->i_lock);
EXPORT_SYMBOL(d_instantiate_unique);
-/**
- * d_alloc_root - allocate root dentry
- * @root_inode: inode to allocate the root for
- *
- * Allocate a root ("/") dentry for the inode given. The inode is
- * instantiated and returned. %NULL is returned if there is insufficient
- * memory or the inode passed is %NULL.
- */
-
-struct dentry * d_alloc_root(struct inode * root_inode)
+struct dentry *d_make_root(struct inode *root_inode)
{
struct dentry *res = NULL;
if (root_inode) {
- static const struct qstr name = { .name = "/", .len = 1 };
+ static const struct qstr name = QSTR_INIT("/", 1);
res = __d_alloc(root_inode->i_sb, &name);
if (res)
d_instantiate(res, root_inode);
+ else
+ iput(root_inode);
}
return res;
}
-EXPORT_SYMBOL(d_alloc_root);
+EXPORT_SYMBOL(d_make_root);
static struct dentry * __d_find_any_alias(struct inode *inode)
{
struct dentry *alias;
- if (list_empty(&inode->i_dentry))
+ if (hlist_empty(&inode->i_dentry))
return NULL;
- alias = list_first_entry(&inode->i_dentry, struct dentry, d_alias);
+ alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
__dget(alias);
return alias;
}
-static struct dentry * d_find_any_alias(struct inode *inode)
+/**
+ * d_find_any_alias - find any alias for a given inode
+ * @inode: inode to find an alias for
+ *
+ * If any aliases exist for the given inode, take and return a
+ * reference for one of them. If no aliases exist, return %NULL.
+ */
+struct dentry *d_find_any_alias(struct inode *inode)
{
struct dentry *de;
spin_unlock(&inode->i_lock);
return de;
}
-
+EXPORT_SYMBOL(d_find_any_alias);
/**
* d_obtain_alias - find or allocate a dentry for a given inode
*/
struct dentry *d_obtain_alias(struct inode *inode)
{
- static const struct qstr anonstring = { .name = "" };
+ static const struct qstr anonstring = QSTR_INIT("/", 1);
struct dentry *tmp;
struct dentry *res;
spin_lock(&tmp->d_lock);
tmp->d_inode = inode;
tmp->d_flags |= DCACHE_DISCONNECTED;
- list_add(&tmp->d_alias, &inode->i_dentry);
+ hlist_add_head(&tmp->d_u.d_alias, &inode->i_dentry);
hlist_bl_lock(&tmp->d_sb->s_anon);
hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon);
hlist_bl_unlock(&tmp->d_sb->s_anon);
struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
struct qstr *name)
{
- int error;
struct dentry *found;
struct dentry *new;
* if not go ahead and create it now.
*/
found = d_hash_and_lookup(dentry->d_parent, name);
+ if (unlikely(IS_ERR(found)))
+ goto err_out;
if (!found) {
new = d_alloc(dentry->d_parent, name);
if (!new) {
- error = -ENOMEM;
+ found = ERR_PTR(-ENOMEM);
goto err_out;
}
return found;
}
- /*
- * We are going to instantiate this dentry, unhash it and clear the
- * lookup flag so we can do that.
- */
- if (unlikely(d_need_lookup(found)))
- d_clear_need_lookup(found);
-
/*
* Negative dentry: instantiate it unless the inode is a directory and
* already has a dentry.
err_out:
iput(inode);
- return ERR_PTR(error);
+ return found;
}
EXPORT_SYMBOL(d_add_ci);
+/*
+ * Do the slow-case of the dentry name compare.
+ *
+ * Unlike the dentry_cmp() function, we need to atomically
+ * load the name, length and inode information, so that the
+ * filesystem can rely on them, and can use the 'name' and
+ * 'len' information without worrying about walking off the
+ * end of memory etc.
+ *
+ * Thus the read_seqcount_retry() and the "duplicate" info
+ * in arguments (the low-level filesystem should not look
+ * at the dentry inode or name contents directly, since
+ * rename can change them while we're in RCU mode).
+ */
+enum slow_d_compare {
+ D_COMP_OK,
+ D_COMP_NOMATCH,
+ D_COMP_SEQRETRY,
+};
+
+static noinline enum slow_d_compare slow_dentry_cmp(
+ const struct dentry *parent,
+ struct inode *inode,
+ struct dentry *dentry,
+ unsigned int seq,
+ const struct qstr *name)
+{
+ int tlen = dentry->d_name.len;
+ const char *tname = dentry->d_name.name;
+ struct inode *i = dentry->d_inode;
+
+ if (read_seqcount_retry(&dentry->d_seq, seq)) {
+ cpu_relax();
+ return D_COMP_SEQRETRY;
+ }
+ if (parent->d_op->d_compare(parent, inode,
+ dentry, i,
+ tlen, tname, name))
+ return D_COMP_NOMATCH;
+ return D_COMP_OK;
+}
+
/**
* __d_lookup_rcu - search for a dentry (racy, store-free)
* @parent: parent dentry
* @name: qstr of name we wish to find
- * @seq: returns d_seq value at the point where the dentry was found
+ * @seqp: returns d_seq value at the point where the dentry was found
* @inode: returns dentry->d_inode when the inode was found valid.
* Returns: dentry, or NULL
*
* 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
* is formed, giving integrity down the path walk.
+ *
+ * NOTE! The caller *has* to check the resulting dentry against the sequence
+ * number we've returned before using any of the resulting dentry state!
*/
-struct dentry *__d_lookup_rcu(struct dentry *parent, struct qstr *name,
- unsigned *seq, struct inode **inode)
+struct dentry *__d_lookup_rcu(const struct dentry *parent,
+ const struct qstr *name,
+ unsigned *seqp, struct inode *inode)
{
- unsigned int len = name->len;
- unsigned int hash = name->hash;
+ u64 hashlen = name->hash_len;
const unsigned char *str = name->name;
- struct hlist_bl_head *b = d_hash(parent, hash);
+ struct hlist_bl_head *b = d_hash(parent, hashlen_hash(hashlen));
struct hlist_bl_node *node;
struct dentry *dentry;
* See Documentation/filesystems/path-lookup.txt for more details.
*/
hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
- struct inode *i;
- const char *tname;
- int tlen;
-
- if (dentry->d_name.hash != hash)
- continue;
+ unsigned seq;
seqretry:
- *seq = read_seqcount_begin(&dentry->d_seq);
+ /*
+ * The dentry sequence count protects us from concurrent
+ * renames, and thus protects inode, parent and name fields.
+ *
+ * The caller must perform a seqcount check in order
+ * to do anything useful with the returned dentry,
+ * including using the 'd_inode' pointer.
+ *
+ * NOTE! We do a "raw" seqcount_begin here. That means that
+ * we don't wait for the sequence count to stabilize if it
+ * is in the middle of a sequence change. If we do the slow
+ * dentry compare, we will do seqretries until it is stable,
+ * and if we end up with a successful lookup, we actually
+ * want to exit RCU lookup anyway.
+ */
+ seq = raw_seqcount_begin(&dentry->d_seq);
if (dentry->d_parent != parent)
continue;
if (d_unhashed(dentry))
continue;
- tlen = dentry->d_name.len;
- tname = dentry->d_name.name;
- i = dentry->d_inode;
- prefetch(tname);
- /*
- * This seqcount check is required to ensure name and
- * len are loaded atomically, so as not to walk off the
- * edge of memory when walking. If we could load this
- * atomically some other way, we could drop this check.
- */
- if (read_seqcount_retry(&dentry->d_seq, *seq))
- goto seqretry;
- if (parent->d_flags & DCACHE_OP_COMPARE) {
- if (parent->d_op->d_compare(parent, *inode,
- dentry, i,
- tlen, tname, name))
+ *seqp = seq;
+
+ if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) {
+ if (dentry->d_name.hash != hashlen_hash(hashlen))
continue;
- } else {
- if (dentry_cmp(tname, tlen, str, len))
+ switch (slow_dentry_cmp(parent, inode, dentry, seq, name)) {
+ case D_COMP_OK:
+ return dentry;
+ case D_COMP_NOMATCH:
continue;
+ default:
+ goto seqretry;
+ }
}
- /*
- * No extra seqcount check is required after the name
- * compare. The caller must perform a seqcount check in
- * order to do anything useful with the returned dentry
- * anyway.
- */
- *inode = i;
- return dentry;
+
+ if (dentry->d_name.hash_len != hashlen)
+ continue;
+ if (!dentry_cmp(dentry, str, hashlen_len(hashlen)))
+ return dentry;
}
return NULL;
}
* dentry is returned. The caller must use dput to free the entry when it has
* finished using it. %NULL is returned if the dentry does not exist.
*/
-struct dentry *d_lookup(struct dentry *parent, struct qstr *name)
+struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name)
{
struct dentry *dentry;
unsigned seq;
*
* __d_lookup callers must be commented.
*/
-struct dentry *__d_lookup(struct dentry *parent, struct qstr *name)
+struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name)
{
unsigned int len = name->len;
unsigned int hash = name->hash;
rcu_read_lock();
hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
- const char *tname;
- int tlen;
if (dentry->d_name.hash != hash)
continue;
* It is safe to compare names since d_move() cannot
* change the qstr (protected by d_lock).
*/
- tlen = dentry->d_name.len;
- tname = dentry->d_name.name;
if (parent->d_flags & DCACHE_OP_COMPARE) {
+ int tlen = dentry->d_name.len;
+ const char *tname = dentry->d_name.name;
if (parent->d_op->d_compare(parent, parent->d_inode,
dentry, dentry->d_inode,
tlen, tname, name))
goto next;
} else {
- if (dentry_cmp(tname, tlen, str, len))
+ if (dentry->d_name.len != len)
+ goto next;
+ if (dentry_cmp(dentry, str, len))
goto next;
}
* @dir: Directory to search in
* @name: qstr of name we wish to find
*
- * On hash failure or on lookup failure NULL is returned.
+ * On lookup failure NULL is returned; on bad name - ERR_PTR(-error)
*/
struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name)
{
- struct dentry *dentry = NULL;
-
/*
* Check for a fs-specific hash function. Note that we must
* calculate the standard hash first, as the d_op->d_hash()
*/
name->hash = full_name_hash(name->name, name->len);
if (dir->d_flags & DCACHE_OP_HASH) {
- if (dir->d_op->d_hash(dir, dir->d_inode, name) < 0)
- goto out;
+ int err = dir->d_op->d_hash(dir, dir->d_inode, name);
+ if (unlikely(err < 0))
+ return ERR_PTR(err);
}
- dentry = d_lookup(dir, name);
-out:
- return dentry;
+ return d_lookup(dir, name);
}
+EXPORT_SYMBOL(d_hash_and_lookup);
/**
* d_validate - verify dentry provided from insecure source (deprecated)
struct dentry *child;
spin_lock(&dparent->d_lock);
- list_for_each_entry(child, &dparent->d_subdirs, d_u.d_child) {
+ list_for_each_entry(child, &dparent->d_subdirs, d_child) {
if (dentry == child) {
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
__dget_dlock(dentry);
inode = dentry->d_inode;
isdir = S_ISDIR(inode->i_mode);
if (dentry->d_count == 1) {
- if (inode && !spin_trylock(&inode->i_lock)) {
+ if (!spin_trylock(&inode->i_lock)) {
spin_unlock(&dentry->d_lock);
cpu_relax();
goto again;
/* Unhash the target: dput() will then get rid of it */
__d_drop(target);
- list_del(&dentry->d_u.d_child);
- list_del(&target->d_u.d_child);
+ list_del(&dentry->d_child);
+ list_del(&target->d_child);
/* Switch the names.. */
switch_names(dentry, target);
if (IS_ROOT(dentry)) {
dentry->d_parent = target->d_parent;
target->d_parent = target;
- INIT_LIST_HEAD(&target->d_u.d_child);
+ INIT_LIST_HEAD(&target->d_child);
} else {
swap(dentry->d_parent, target->d_parent);
/* And add them back to the (new) parent lists */
- list_add(&target->d_u.d_child, &target->d_parent->d_subdirs);
+ list_add(&target->d_child, &target->d_parent->d_subdirs);
}
- list_add(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
+ list_add(&dentry->d_child, &dentry->d_parent->d_subdirs);
write_seqcount_end(&target->d_seq);
write_seqcount_end(&dentry->d_seq);
struct dentry *dentry, struct dentry *alias)
{
struct mutex *m1 = NULL, *m2 = NULL;
- struct dentry *ret;
+ struct dentry *ret = ERR_PTR(-EBUSY);
/* If alias and dentry share a parent, then no extra locks required */
if (alias->d_parent == dentry->d_parent)
goto out_unalias;
/* See lock_rename() */
- ret = ERR_PTR(-EBUSY);
if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex))
goto out_err;
m1 = &dentry->d_sb->s_vfs_rename_mutex;
goto out_err;
m2 = &alias->d_parent->d_inode->i_mutex;
out_unalias:
- __d_move(alias, dentry);
- ret = alias;
+ if (likely(!d_mountpoint(alias))) {
+ __d_move(alias, dentry);
+ ret = alias;
+ }
out_err:
spin_unlock(&inode->i_lock);
if (m2)
*/
static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
{
- struct dentry *dparent, *aparent;
+ struct dentry *dparent;
dentry_lock_for_move(anon, dentry);
write_seqcount_begin(&anon->d_seq);
dparent = dentry->d_parent;
- aparent = anon->d_parent;
switch_names(dentry, anon);
swap(dentry->d_name.hash, anon->d_name.hash);
- dentry->d_parent = (aparent == anon) ? dentry : aparent;
- list_del(&dentry->d_u.d_child);
- if (!IS_ROOT(dentry))
- list_add(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
- else
- INIT_LIST_HEAD(&dentry->d_u.d_child);
-
- anon->d_parent = (dparent == dentry) ? anon : dparent;
- list_del(&anon->d_u.d_child);
- if (!IS_ROOT(anon))
- list_add(&anon->d_u.d_child, &anon->d_parent->d_subdirs);
- else
- INIT_LIST_HEAD(&anon->d_u.d_child);
+ dentry->d_parent = dentry;
+ list_del_init(&dentry->d_child);
+ anon->d_parent = dparent;
+ list_move(&anon->d_child, &dparent->d_subdirs);
write_seqcount_end(&dentry->d_seq);
write_seqcount_end(&anon->d_seq);
if (d_ancestor(alias, dentry)) {
/* Check for loops */
actual = ERR_PTR(-ELOOP);
+ spin_unlock(&inode->i_lock);
} else if (IS_ROOT(alias)) {
/* Is this an anonymous mountpoint that we
* could splice into our tree? */
goto found;
} else {
/* Nope, but we must(!) avoid directory
- * aliasing */
+ * aliasing. This drops inode->i_lock */
actual = __d_unalias(inode, dentry, alias);
}
write_sequnlock(&rename_lock);
- if (IS_ERR(actual))
+ if (IS_ERR(actual)) {
+ if (PTR_ERR(actual) == -ELOOP)
+ pr_warn_ratelimited(
+ "VFS: Lookup of '%s' in %s %s"
+ " would have caused loop\n",
+ dentry->d_name.name,
+ inode->i_sb->s_type->name,
+ inode->i_sb->s_id);
dput(alias);
+ }
goto out_nolock;
}
}
/**
* prepend_path - Prepend path string to a buffer
* @path: the dentry/vfsmount to report
- * @root: root vfsmnt/dentry (may be modified by this function)
+ * @root: root vfsmnt/dentry
* @buffer: pointer to the end of the buffer
* @buflen: pointer to buffer length
*
* Caller holds the rename_lock.
- *
- * If path is not reachable from the supplied root, then the value of
- * root is changed (without modifying refcounts).
*/
-static int prepend_path(const struct path *path, struct path *root,
+static int prepend_path(const struct path *path,
+ const struct path *root,
char **buffer, int *buflen)
{
struct dentry *dentry = path->dentry;
struct vfsmount *vfsmnt = path->mnt;
+ struct mount *mnt = real_mount(vfsmnt);
+ char *orig_buffer = *buffer;
+ int orig_len = *buflen;
bool slash = false;
int error = 0;
- br_read_lock(vfsmount_lock);
while (dentry != root->dentry || vfsmnt != root->mnt) {
struct dentry * parent;
if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) {
- /* Global root? */
- if (vfsmnt->mnt_parent == vfsmnt) {
+ /* Escaped? */
+ if (dentry != vfsmnt->mnt_root) {
+ *buffer = orig_buffer;
+ *buflen = orig_len;
+ slash = false;
+ error = 3;
goto global_root;
}
- dentry = vfsmnt->mnt_mountpoint;
- vfsmnt = vfsmnt->mnt_parent;
+ /* Global root? */
+ if (!mnt_has_parent(mnt))
+ goto global_root;
+ dentry = mnt->mnt_mountpoint;
+ mnt = mnt->mnt_parent;
+ vfsmnt = &mnt->mnt;
continue;
}
parent = dentry->d_parent;
dentry = parent;
}
-out:
if (!error && !slash)
error = prepend(buffer, buflen, "/", 1);
- br_read_unlock(vfsmount_lock);
return error;
global_root:
- /*
- * Filesystems needing to implement special "root names"
- * should do so with ->d_dname()
- */
- if (IS_ROOT(dentry) &&
- (dentry->d_name.len != 1 || dentry->d_name.name[0] != '/')) {
- WARN(1, "Root dentry has weird name <%.*s>\n",
- (int) dentry->d_name.len, dentry->d_name.name);
- }
- root->mnt = vfsmnt;
- root->dentry = dentry;
- goto out;
+ if (!slash)
+ error = prepend(buffer, buflen, "/", 1);
+ if (!error)
+ error = is_mounted(vfsmnt) ? 1 : 2;
+ return error;
}
/**
* __d_path - return the path of a dentry
* @path: the dentry/vfsmount to report
- * @root: root vfsmnt/dentry (may be modified by this function)
+ * @root: root vfsmnt/dentry
* @buf: buffer to return value in
* @buflen: buffer length
*
*
* "buflen" should be positive.
*
- * If path is not reachable from the supplied root, then the value of
- * root is changed (without modifying refcounts).
+ * If the path is not reachable from the supplied root, return %NULL.
*/
-char *__d_path(const struct path *path, struct path *root,
+char *__d_path(const struct path *path,
+ const struct path *root,
char *buf, int buflen)
{
char *res = buf + buflen;
int error;
prepend(&res, &buflen, "\0", 1);
+ br_read_lock(&vfsmount_lock);
write_seqlock(&rename_lock);
error = prepend_path(path, root, &res, &buflen);
write_sequnlock(&rename_lock);
+ br_read_unlock(&vfsmount_lock);
- if (error)
+ if (error < 0)
+ return ERR_PTR(error);
+ if (error > 0)
+ return NULL;
+ return res;
+}
+
+char *d_absolute_path(const struct path *path,
+ char *buf, int buflen)
+{
+ struct path root = {};
+ char *res = buf + buflen;
+ int error;
+
+ prepend(&res, &buflen, "\0", 1);
+ br_read_lock(&vfsmount_lock);
+ write_seqlock(&rename_lock);
+ error = prepend_path(path, &root, &res, &buflen);
+ write_sequnlock(&rename_lock);
+ br_read_unlock(&vfsmount_lock);
+
+ if (error > 1)
+ error = -EINVAL;
+ if (error < 0)
return ERR_PTR(error);
return res;
}
/*
* same as __d_path but appends "(deleted)" for unlinked files.
*/
-static int path_with_deleted(const struct path *path, struct path *root,
- char **buf, int *buflen)
+static int path_with_deleted(const struct path *path,
+ const struct path *root,
+ char **buf, int *buflen)
{
prepend(buf, buflen, "\0", 1);
if (d_unlinked(path->dentry)) {
{
char *res = buf + buflen;
struct path root;
- struct path tmp;
int error;
/*
* thus don't need to be hashed. They also don't need a name until a
* user wants to identify the object in /proc/pid/fd/. The little hack
* below allows us to generate a name for these objects on demand:
+ *
+ * Some pseudo inodes are mountable. When they are mounted
+ * path->dentry == path->mnt->mnt_root. In that case don't call d_dname
+ * and instead have d_path return the mounted path.
*/
- if (path->dentry->d_op && path->dentry->d_op->d_dname)
+ if (path->dentry->d_op && path->dentry->d_op->d_dname &&
+ (!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root))
return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
get_fs_root(current->fs, &root);
+ br_read_lock(&vfsmount_lock);
write_seqlock(&rename_lock);
- tmp = root;
- error = path_with_deleted(path, &tmp, &res, &buflen);
- if (error)
- res = ERR_PTR(error);
+ error = path_with_deleted(path, &root, &res, &buflen);
write_sequnlock(&rename_lock);
+ br_read_unlock(&vfsmount_lock);
+ if (error < 0)
+ res = ERR_PTR(error);
path_put(&root);
return res;
}
EXPORT_SYMBOL(d_path);
-/**
- * d_path_with_unreachable - return the path of a dentry
- * @path: path to report
- * @buf: buffer to return value in
- * @buflen: buffer length
- *
- * The difference from d_path() is that this prepends "(unreachable)"
- * to paths which are unreachable from the current process' root.
- */
-char *d_path_with_unreachable(const struct path *path, char *buf, int buflen)
-{
- char *res = buf + buflen;
- struct path root;
- struct path tmp;
- int error;
-
- if (path->dentry->d_op && path->dentry->d_op->d_dname)
- return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
-
- get_fs_root(current->fs, &root);
- write_seqlock(&rename_lock);
- tmp = root;
- error = path_with_deleted(path, &tmp, &res, &buflen);
- if (!error && !path_equal(&tmp, &root))
- error = prepend_unreachable(&res, &buflen);
- write_sequnlock(&rename_lock);
- path_put(&root);
- if (error)
- res = ERR_PTR(error);
-
- return res;
-}
-
/*
* Helper function for dentry_operations.d_dname() members
*/
return memcpy(buffer, temp, sz);
}
+char *simple_dname(struct dentry *dentry, char *buffer, int buflen)
+{
+ char *end = buffer + buflen;
+ /* these dentries are never renamed, so d_lock is not needed */
+ if (prepend(&end, &buflen, " (deleted)", 11) ||
+ prepend_name(&end, &buflen, &dentry->d_name) ||
+ prepend(&end, &buflen, "/", 1))
+ end = ERR_PTR(-ENAMETOOLONG);
+ return end;
+}
+
/*
* Write full pathname from the root of the filesystem into the buffer.
*/
get_fs_root_and_pwd(current->fs, &root, &pwd);
error = -ENOENT;
+ br_read_lock(&vfsmount_lock);
write_seqlock(&rename_lock);
if (!d_unlinked(pwd.dentry)) {
unsigned long len;
- struct path tmp = root;
char *cwd = page + PAGE_SIZE;
int buflen = PAGE_SIZE;
prepend(&cwd, &buflen, "\0", 1);
- error = prepend_path(&pwd, &tmp, &cwd, &buflen);
+ error = prepend_path(&pwd, &root, &cwd, &buflen);
write_sequnlock(&rename_lock);
+ br_read_unlock(&vfsmount_lock);
- if (error)
+ if (error < 0)
goto out;
/* Unreachable from current root */
- if (!path_equal(&tmp, &root)) {
+ if (error > 0) {
error = prepend_unreachable(&cwd, &buflen);
if (error)
goto out;
}
} else {
write_sequnlock(&rename_lock);
+ br_read_unlock(&vfsmount_lock);
}
out:
return result;
}
-int path_is_under(struct path *path1, struct path *path2)
-{
- struct vfsmount *mnt = path1->mnt;
- struct dentry *dentry = path1->dentry;
- int res;
-
- br_read_lock(vfsmount_lock);
- if (mnt != path2->mnt) {
- for (;;) {
- if (mnt->mnt_parent == mnt) {
- br_read_unlock(vfsmount_lock);
- return 0;
- }
- if (mnt->mnt_parent == path2->mnt)
- break;
- mnt = mnt->mnt_parent;
- }
- dentry = mnt->mnt_mountpoint;
- }
- res = is_subdir(dentry, path2->dentry);
- br_read_unlock(vfsmount_lock);
- return res;
-}
-EXPORT_SYMBOL(path_is_under);
-
void d_genocide(struct dentry *root)
{
struct dentry *this_parent;
resume:
while (next != &this_parent->d_subdirs) {
struct list_head *tmp = next;
- struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
+ struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
next = tmp->next;
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
}
spin_unlock(&dentry->d_lock);
}
+ rcu_read_lock();
+ascend:
if (this_parent != root) {
struct dentry *child = this_parent;
if (!(this_parent->d_flags & DCACHE_GENOCIDE)) {
this_parent->d_flags |= DCACHE_GENOCIDE;
this_parent->d_count--;
}
- this_parent = try_to_ascend(this_parent, locked, seq);
- if (!this_parent)
+ this_parent = child->d_parent;
+
+ spin_unlock(&child->d_lock);
+ spin_lock(&this_parent->d_lock);
+
+ /* might go back up the wrong parent if we have had a rename. */
+ if (!locked && read_seqretry(&rename_lock, seq))
goto rename_retry;
- next = child->d_u.d_child.next;
+ /* go into the first sibling still alive */
+ do {
+ next = child->d_child.next;
+ if (next == &this_parent->d_subdirs)
+ goto ascend;
+ child = list_entry(next, struct dentry, d_child);
+ } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
+ rcu_read_unlock();
goto resume;
}
- spin_unlock(&this_parent->d_lock);
if (!locked && read_seqretry(&rename_lock, seq))
goto rename_retry;
+ spin_unlock(&this_parent->d_lock);
+ rcu_read_unlock();
if (locked)
write_sequnlock(&rename_lock);
return;
rename_retry:
+ spin_unlock(&this_parent->d_lock);
+ rcu_read_unlock();
+ if (locked)
+ goto again;
locked = 1;
write_seqlock(&rename_lock);
goto again;
ino_t ino = 0;
dentry = d_hash_and_lookup(dir, name);
- if (dentry) {
+ if (!IS_ERR_OR_NULL(dentry)) {
if (dentry->d_inode)
ino = dentry->d_inode->i_ino;
dput(dentry);
static void __init dcache_init_early(void)
{
- int loop;
+ unsigned int loop;
/* If hashes are distributed across NUMA nodes, defer
* hash allocation until vmalloc space is available.
HASH_EARLY,
&d_hash_shift,
&d_hash_mask,
+ 0,
0);
- for (loop = 0; loop < (1 << d_hash_shift); loop++)
+ for (loop = 0; loop < (1U << d_hash_shift); loop++)
INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
}
static void __init dcache_init(void)
{
- int loop;
+ unsigned int loop;
/*
* A constructor could be added for stable state like the lists,
0,
&d_hash_shift,
&d_hash_mask,
+ 0,
0);
- for (loop = 0; loop < (1 << d_hash_shift); loop++)
+ for (loop = 0; loop < (1U << d_hash_shift); loop++)
INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
}