/*
- * dir.c - Operations for sysfs directories.
+ * fs/sysfs/dir.c - sysfs core and dir operation implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007 Tejun Heo <teheo@suse.de>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Please see Documentation/filesystems/sysfs.txt for more information.
*/
#undef DEBUG
#include <linux/idr.h>
#include <linux/completion.h>
#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/security.h>
+#include <linux/hash.h>
#include "sysfs.h"
DEFINE_MUTEX(sysfs_mutex);
-DEFINE_MUTEX(sysfs_rename_mutex);
-spinlock_t sysfs_assoc_lock = SPIN_LOCK_UNLOCKED;
+DEFINE_SPINLOCK(sysfs_assoc_lock);
-static spinlock_t sysfs_ino_lock = SPIN_LOCK_UNLOCKED;
+#define to_sysfs_dirent(X) rb_entry((X), struct sysfs_dirent, s_rb);
+
+static DEFINE_SPINLOCK(sysfs_ino_lock);
static DEFINE_IDA(sysfs_ino_ida);
/**
- * sysfs_link_sibling - link sysfs_dirent into sibling list
- * @sd: sysfs_dirent of interest
+ * sysfs_name_hash
+ * @ns: Namespace tag to hash
+ * @name: Null terminated string to hash
*
- * Link @sd into its sibling list which starts from
- * sd->s_parent->s_children.
- *
- * Locking:
- * mutex_lock(sysfs_mutex)
+ * Returns 31 bit hash of ns + name (so it fits in an off_t )
*/
-static void sysfs_link_sibling(struct sysfs_dirent *sd)
+static unsigned int sysfs_name_hash(const void *ns, const char *name)
{
- struct sysfs_dirent *parent_sd = sd->s_parent;
- struct sysfs_dirent **pos;
+ unsigned long hash = init_name_hash();
+ unsigned int len = strlen(name);
+ while (len--)
+ hash = partial_name_hash(*name++, hash);
+ hash = ( end_name_hash(hash) ^ hash_ptr( (void *)ns, 31 ) );
+ hash &= 0x7fffffffU;
+ /* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */
+ if (hash < 1)
+ hash += 2;
+ if (hash >= INT_MAX)
+ hash = INT_MAX - 1;
+ return hash;
+}
- BUG_ON(sd->s_sibling);
+static int sysfs_name_compare(unsigned int hash, const void *ns,
+ const char *name, const struct sysfs_dirent *sd)
+{
+ if (hash != sd->s_hash)
+ return hash - sd->s_hash;
+ if (ns != sd->s_ns)
+ return ns - sd->s_ns;
+ return strcmp(name, sd->s_name);
+}
- /* Store directory entries in order by ino. This allows
- * readdir to properly restart without having to add a
- * cursor into the s_children list.
- */
- for (pos = &parent_sd->s_children; *pos; pos = &(*pos)->s_sibling) {
- if (sd->s_ino < (*pos)->s_ino)
- break;
- }
- sd->s_sibling = *pos;
- *pos = sd;
+static int sysfs_sd_compare(const struct sysfs_dirent *left,
+ const struct sysfs_dirent *right)
+{
+ return sysfs_name_compare(left->s_hash, left->s_ns, left->s_name,
+ right);
}
/**
- * sysfs_unlink_sibling - unlink sysfs_dirent from sibling list
+ * sysfs_link_subling - link sysfs_dirent into sibling rbtree
* @sd: sysfs_dirent of interest
*
- * Unlink @sd from its sibling list which starts from
- * sd->s_parent->s_children.
+ * Link @sd into its sibling rbtree which starts from
+ * sd->s_parent->s_dir.children.
*
* Locking:
* mutex_lock(sysfs_mutex)
+ *
+ * RETURNS:
+ * 0 on susccess -EEXIST on failure.
*/
-static void sysfs_unlink_sibling(struct sysfs_dirent *sd)
+static int sysfs_link_sibling(struct sysfs_dirent *sd)
{
- struct sysfs_dirent **pos;
+ struct rb_node **node = &sd->s_parent->s_dir.children.rb_node;
+ struct rb_node *parent = NULL;
- for (pos = &sd->s_parent->s_children; *pos; pos = &(*pos)->s_sibling) {
- if (*pos == sd) {
- *pos = sd->s_sibling;
- sd->s_sibling = NULL;
- break;
- }
+ if (sysfs_type(sd) == SYSFS_DIR)
+ sd->s_parent->s_dir.subdirs++;
+
+ while (*node) {
+ struct sysfs_dirent *pos;
+ int result;
+
+ pos = to_sysfs_dirent(*node);
+ parent = *node;
+ result = sysfs_sd_compare(sd, pos);
+ if (result < 0)
+ node = &pos->s_rb.rb_left;
+ else if (result > 0)
+ node = &pos->s_rb.rb_right;
+ else
+ return -EEXIST;
}
+ /* add new node and rebalance the tree */
+ rb_link_node(&sd->s_rb, parent, node);
+ rb_insert_color(&sd->s_rb, &sd->s_parent->s_dir.children);
+ return 0;
}
/**
- * sysfs_get_dentry - get dentry for the given sysfs_dirent
+ * sysfs_unlink_sibling - unlink sysfs_dirent from sibling rbtree
* @sd: sysfs_dirent of interest
*
- * Get dentry for @sd. Dentry is looked up if currently not
- * present. This function descends from the root looking up
- * dentry for each step.
+ * Unlink @sd from its sibling rbtree which starts from
+ * sd->s_parent->s_dir.children.
*
- * LOCKING:
- * mutex_lock(sysfs_rename_mutex)
- *
- * RETURNS:
- * Pointer to found dentry on success, ERR_PTR() value on error.
+ * Locking:
+ * mutex_lock(sysfs_mutex)
*/
-struct dentry *sysfs_get_dentry(struct sysfs_dirent *sd)
+static void sysfs_unlink_sibling(struct sysfs_dirent *sd)
{
- struct dentry *dentry = dget(sysfs_sb->s_root);
+ if (sysfs_type(sd) == SYSFS_DIR)
+ sd->s_parent->s_dir.subdirs--;
- while (dentry->d_fsdata != sd) {
- struct sysfs_dirent *cur;
- struct dentry *parent;
+ rb_erase(&sd->s_rb, &sd->s_parent->s_dir.children);
+}
- /* find the first ancestor which hasn't been looked up */
- cur = sd;
- while (cur->s_parent != dentry->d_fsdata)
- cur = cur->s_parent;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
- /* look it up */
- parent = dentry;
- mutex_lock(&parent->d_inode->i_mutex);
- dentry = lookup_one_len_kern(cur->s_name, parent,
- strlen(cur->s_name));
- mutex_unlock(&parent->d_inode->i_mutex);
- dput(parent);
+/* Test for attributes that want to ignore lockdep for read-locking */
+static bool ignore_lockdep(struct sysfs_dirent *sd)
+{
+ return sysfs_type(sd) == SYSFS_KOBJ_ATTR &&
+ sd->s_attr.attr->ignore_lockdep;
+}
- if (IS_ERR(dentry))
- break;
- }
- return dentry;
+#else
+
+static inline bool ignore_lockdep(struct sysfs_dirent *sd)
+{
+ return true;
}
+#endif
+
/**
* sysfs_get_active - get an active reference to sysfs_dirent
* @sd: sysfs_dirent to get an active reference to
t = atomic_cmpxchg(&sd->s_active, v, v + 1);
if (likely(t == v))
- return sd;
+ break;
if (t < 0)
return NULL;
cpu_relax();
}
+
+ if (likely(!ignore_lockdep(sd)))
+ rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_);
+ return sd;
}
/**
*/
void sysfs_put_active(struct sysfs_dirent *sd)
{
- struct completion *cmpl;
int v;
if (unlikely(!sd))
return;
+ if (likely(!ignore_lockdep(sd)))
+ rwsem_release(&sd->dep_map, 1, _RET_IP_);
v = atomic_dec_return(&sd->s_active);
if (likely(v != SD_DEACTIVATED_BIAS))
return;
/* atomic_dec_return() is a mb(), we'll always see the updated
- * sd->s_sibling.
+ * sd->u.completion.
*/
- cmpl = (void *)sd->s_sibling;
- complete(cmpl);
-}
-
-/**
- * sysfs_get_active_two - get active references to sysfs_dirent and parent
- * @sd: sysfs_dirent of interest
- *
- * Get active reference to @sd and its parent. Parent's active
- * reference is grabbed first. This function is noop if @sd is
- * NULL.
- *
- * RETURNS:
- * Pointer to @sd on success, NULL on failure.
- */
-struct sysfs_dirent *sysfs_get_active_two(struct sysfs_dirent *sd)
-{
- if (sd) {
- if (sd->s_parent && unlikely(!sysfs_get_active(sd->s_parent)))
- return NULL;
- if (unlikely(!sysfs_get_active(sd))) {
- sysfs_put_active(sd->s_parent);
- return NULL;
- }
- }
- return sd;
-}
-
-/**
- * sysfs_put_active_two - put active references to sysfs_dirent and parent
- * @sd: sysfs_dirent of interest
- *
- * Put active references to @sd and its parent. This function is
- * noop if @sd is NULL.
- */
-void sysfs_put_active_two(struct sysfs_dirent *sd)
-{
- if (sd) {
- sysfs_put_active(sd);
- sysfs_put_active(sd->s_parent);
- }
+ complete(sd->u.completion);
}
/**
DECLARE_COMPLETION_ONSTACK(wait);
int v;
- BUG_ON(sd->s_sibling || !(sd->s_flags & SYSFS_FLAG_REMOVED));
- sd->s_sibling = (void *)&wait;
+ BUG_ON(!(sd->s_flags & SYSFS_FLAG_REMOVED));
+
+ if (!(sysfs_type(sd) & SYSFS_ACTIVE_REF))
+ return;
+
+ sd->u.completion = (void *)&wait;
+ rwsem_acquire(&sd->dep_map, 0, 0, _RET_IP_);
/* atomic_add_return() is a mb(), put_active() will always see
- * the updated sd->s_sibling.
+ * the updated sd->u.completion.
*/
v = atomic_add_return(SD_DEACTIVATED_BIAS, &sd->s_active);
- if (v != SD_DEACTIVATED_BIAS)
+ if (v != SD_DEACTIVATED_BIAS) {
+ lock_contended(&sd->dep_map, _RET_IP_);
wait_for_completion(&wait);
+ }
- sd->s_sibling = NULL;
+ lock_acquired(&sd->dep_map, _RET_IP_);
+ rwsem_release(&sd->dep_map, 1, _RET_IP_);
}
-static int sysfs_alloc_ino(ino_t *pino)
+static int sysfs_alloc_ino(unsigned int *pino)
{
int ino, rc;
return rc;
}
-static void sysfs_free_ino(ino_t ino)
+static void sysfs_free_ino(unsigned int ino)
{
spin_lock(&sysfs_ino_lock);
ida_remove(&sysfs_ino_ida, ino);
sysfs_put(sd->s_symlink.target_sd);
if (sysfs_type(sd) & SYSFS_COPY_NAME)
kfree(sd->s_name);
+ if (sd->s_iattr && sd->s_iattr->ia_secdata)
+ security_release_secctx(sd->s_iattr->ia_secdata,
+ sd->s_iattr->ia_secdata_len);
kfree(sd->s_iattr);
sysfs_free_ino(sd->s_ino);
kmem_cache_free(sysfs_dir_cachep, sd);
goto repeat;
}
-static void sysfs_d_iput(struct dentry * dentry, struct inode * inode)
+static int sysfs_dentry_delete(const struct dentry *dentry)
+{
+ struct sysfs_dirent *sd = dentry->d_fsdata;
+ return !(sd && !(sd->s_flags & SYSFS_FLAG_REMOVED));
+}
+
+static int sysfs_dentry_revalidate(struct dentry *dentry, unsigned int flags)
{
- struct sysfs_dirent * sd = dentry->d_fsdata;
+ struct sysfs_dirent *sd;
+ int is_dir;
+ int type;
+
+ if (flags & LOOKUP_RCU)
+ return -ECHILD;
+
+ sd = dentry->d_fsdata;
+ mutex_lock(&sysfs_mutex);
+
+ /* The sysfs dirent has been deleted */
+ if (sd->s_flags & SYSFS_FLAG_REMOVED)
+ goto out_bad;
+
+ /* The sysfs dirent has been moved? */
+ if (dentry->d_parent->d_fsdata != sd->s_parent)
+ goto out_bad;
+
+ /* The sysfs dirent has been renamed */
+ if (strcmp(dentry->d_name.name, sd->s_name) != 0)
+ goto out_bad;
+
+ /* The sysfs dirent has been moved to a different namespace */
+ type = KOBJ_NS_TYPE_NONE;
+ if (sd->s_parent) {
+ type = sysfs_ns_type(sd->s_parent);
+ if (type != KOBJ_NS_TYPE_NONE &&
+ sysfs_info(dentry->d_sb)->ns[type] != sd->s_ns)
+ goto out_bad;
+ }
+
+ mutex_unlock(&sysfs_mutex);
+out_valid:
+ return 1;
+out_bad:
+ /* Remove the dentry from the dcache hashes.
+ * If this is a deleted dentry we use d_drop instead of d_delete
+ * so sysfs doesn't need to cope with negative dentries.
+ *
+ * If this is a dentry that has simply been renamed we
+ * use d_drop to remove it from the dcache lookup on its
+ * old parent. If this dentry persists later when a lookup
+ * is performed at its new name the dentry will be readded
+ * to the dcache hashes.
+ */
+ is_dir = (sysfs_type(sd) == SYSFS_DIR);
+ mutex_unlock(&sysfs_mutex);
+ if (is_dir) {
+ /* If we have submounts we must allow the vfs caches
+ * to lie about the state of the filesystem to prevent
+ * leaks and other nasty things.
+ */
+ if (have_submounts(dentry))
+ goto out_valid;
+ shrink_dcache_parent(dentry);
+ }
+ d_drop(dentry);
+ return 0;
+}
- sysfs_put(sd);
- iput(inode);
+static void sysfs_dentry_release(struct dentry *dentry)
+{
+ sysfs_put(dentry->d_fsdata);
}
-static struct dentry_operations sysfs_dentry_ops = {
- .d_iput = sysfs_d_iput,
+const struct dentry_operations sysfs_dentry_ops = {
+ .d_revalidate = sysfs_dentry_revalidate,
+ .d_delete = sysfs_dentry_delete,
+ .d_release = sysfs_dentry_release,
};
struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type)
atomic_set(&sd->s_count, 1);
atomic_set(&sd->s_active, 0);
- atomic_set(&sd->s_event, 1);
sd->s_name = name;
sd->s_mode = mode;
return NULL;
}
-static int sysfs_ilookup_test(struct inode *inode, void *arg)
-{
- struct sysfs_dirent *sd = arg;
- return inode->i_ino == sd->s_ino;
-}
-
/**
* sysfs_addrm_start - prepare for sysfs_dirent add/remove
* @acxt: pointer to sysfs_addrm_cxt to be used
*
* This function is called when the caller is about to add or
* remove sysfs_dirent under @parent_sd. This function acquires
- * sysfs_mutex, grabs inode for @parent_sd if available and lock
- * i_mutex of it. @acxt is used to keep and pass context to
+ * sysfs_mutex. @acxt is used to keep and pass context to
* other addrm functions.
*
* LOCKING:
* Kernel thread context (may sleep). sysfs_mutex is locked on
- * return. i_mutex of parent inode is locked on return if
- * available.
+ * return.
*/
void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
struct sysfs_dirent *parent_sd)
{
- struct inode *inode;
-
memset(acxt, 0, sizeof(*acxt));
acxt->parent_sd = parent_sd;
- /* Lookup parent inode. inode initialization and I_NEW
- * clearing are protected by sysfs_mutex. By grabbing it and
- * looking up with _nowait variant, inode state can be
- * determined reliably.
- */
mutex_lock(&sysfs_mutex);
-
- inode = ilookup5_nowait(sysfs_sb, parent_sd->s_ino, sysfs_ilookup_test,
- parent_sd);
-
- if (inode && !(inode->i_state & I_NEW)) {
- /* parent inode available */
- acxt->parent_inode = inode;
-
- /* sysfs_mutex is below i_mutex in lock hierarchy.
- * First, trylock i_mutex. If fails, unlock
- * sysfs_mutex and lock them in order.
- */
- if (!mutex_trylock(&inode->i_mutex)) {
- mutex_unlock(&sysfs_mutex);
- mutex_lock(&inode->i_mutex);
- mutex_lock(&sysfs_mutex);
- }
- } else
- iput(inode);
}
/**
- * sysfs_add_one - add sysfs_dirent to parent
+ * __sysfs_add_one - add sysfs_dirent to parent without warning
* @acxt: addrm context to use
* @sd: sysfs_dirent to be added
*
* 0 on success, -EEXIST if entry with the given name already
* exists.
*/
-int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
+int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
{
- if (sysfs_find_dirent(acxt->parent_sd, sd->s_name)) {
- printk(KERN_WARNING "sysfs: duplicate filename '%s' "
- "can not be created\n", sd->s_name);
- WARN_ON(1);
- return -EEXIST;
+ struct sysfs_inode_attrs *ps_iattr;
+ int ret;
+
+ if (!!sysfs_ns_type(acxt->parent_sd) != !!sd->s_ns) {
+ WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n",
+ sysfs_ns_type(acxt->parent_sd)? "required": "invalid",
+ acxt->parent_sd->s_name, sd->s_name);
+ return -EINVAL;
}
+ sd->s_hash = sysfs_name_hash(sd->s_ns, sd->s_name);
sd->s_parent = sysfs_get(acxt->parent_sd);
- if (sysfs_type(sd) == SYSFS_DIR && acxt->parent_inode)
- inc_nlink(acxt->parent_inode);
+ ret = sysfs_link_sibling(sd);
+ if (ret)
+ return ret;
- acxt->cnt++;
-
- sysfs_link_sibling(sd);
+ /* Update timestamps on the parent */
+ ps_iattr = acxt->parent_sd->s_iattr;
+ if (ps_iattr) {
+ struct iattr *ps_iattrs = &ps_iattr->ia_iattr;
+ ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
+ }
return 0;
}
/**
- * sysfs_remove_one - remove sysfs_dirent from parent
+ * sysfs_pathname - return full path to sysfs dirent
+ * @sd: sysfs_dirent whose path we want
+ * @path: caller allocated buffer of size PATH_MAX
+ *
+ * Gives the name "/" to the sysfs_root entry; any path returned
+ * is relative to wherever sysfs is mounted.
+ */
+static char *sysfs_pathname(struct sysfs_dirent *sd, char *path)
+{
+ if (sd->s_parent) {
+ sysfs_pathname(sd->s_parent, path);
+ strlcat(path, "/", PATH_MAX);
+ }
+ strlcat(path, sd->s_name, PATH_MAX);
+ return path;
+}
+
+/**
+ * sysfs_add_one - add sysfs_dirent to parent
* @acxt: addrm context to use
* @sd: sysfs_dirent to be added
*
- * Mark @sd removed and drop nlink of parent inode if @sd is a
- * directory. @sd is unlinked from the children list.
+ * Get @acxt->parent_sd and set sd->s_parent to it and increment
+ * nlink of parent inode if @sd is a directory and link into the
+ * children list of the parent.
*
* This function should be called between calls to
* sysfs_addrm_start() and sysfs_addrm_finish() and should be
*
* LOCKING:
* Determined by sysfs_addrm_start().
+ *
+ * RETURNS:
+ * 0 on success, -EEXIST if entry with the given name already
+ * exists.
*/
-void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
+int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
{
- BUG_ON(sd->s_flags & SYSFS_FLAG_REMOVED);
-
- sysfs_unlink_sibling(sd);
-
- sd->s_flags |= SYSFS_FLAG_REMOVED;
- sd->s_sibling = acxt->removed;
- acxt->removed = sd;
-
- if (sysfs_type(sd) == SYSFS_DIR && acxt->parent_inode)
- drop_nlink(acxt->parent_inode);
+ int ret;
+
+ ret = __sysfs_add_one(acxt, sd);
+ if (ret == -EEXIST) {
+ char *path = kzalloc(PATH_MAX, GFP_KERNEL);
+ WARN(1, KERN_WARNING
+ "sysfs: cannot create duplicate filename '%s'\n",
+ (path == NULL) ? sd->s_name
+ : (sysfs_pathname(acxt->parent_sd, path),
+ strlcat(path, "/", PATH_MAX),
+ strlcat(path, sd->s_name, PATH_MAX),
+ path));
+ kfree(path);
+ }
- acxt->cnt++;
+ return ret;
}
/**
- * sysfs_drop_dentry - drop dentry for the specified sysfs_dirent
- * @sd: target sysfs_dirent
+ * sysfs_remove_one - remove sysfs_dirent from parent
+ * @acxt: addrm context to use
+ * @sd: sysfs_dirent to be removed
+ *
+ * Mark @sd removed and drop nlink of parent inode if @sd is a
+ * directory. @sd is unlinked from the children list.
+ *
+ * This function should be called between calls to
+ * sysfs_addrm_start() and sysfs_addrm_finish() and should be
+ * passed the same @acxt as passed to sysfs_addrm_start().
*
- * Drop dentry for @sd. @sd must have been unlinked from its
- * parent on entry to this function such that it can't be looked
- * up anymore.
+ * LOCKING:
+ * Determined by sysfs_addrm_start().
*/
-static void sysfs_drop_dentry(struct sysfs_dirent *sd)
+void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
{
- struct inode *inode;
- struct dentry *dentry;
-
- inode = ilookup(sysfs_sb, sd->s_ino);
- if (!inode)
- return;
-
- /* Drop any existing dentries associated with sd.
- *
- * For the dentry to be properly freed we need to grab a
- * reference to the dentry under the dcache lock, unhash it,
- * and then put it. The playing with the dentry count allows
- * dput to immediately free the dentry if it is not in use.
- */
-repeat:
- spin_lock(&dcache_lock);
- list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
- if (d_unhashed(dentry))
- continue;
- dget_locked(dentry);
- spin_lock(&dentry->d_lock);
- __d_drop(dentry);
- spin_unlock(&dentry->d_lock);
- spin_unlock(&dcache_lock);
- dput(dentry);
- goto repeat;
- }
- spin_unlock(&dcache_lock);
+ struct sysfs_inode_attrs *ps_iattr;
- /* adjust nlink and update timestamp */
- mutex_lock(&inode->i_mutex);
+ BUG_ON(sd->s_flags & SYSFS_FLAG_REMOVED);
- inode->i_ctime = CURRENT_TIME;
- drop_nlink(inode);
- if (sysfs_type(sd) == SYSFS_DIR)
- drop_nlink(inode);
+ sysfs_unlink_sibling(sd);
- mutex_unlock(&inode->i_mutex);
+ /* Update timestamps on the parent */
+ ps_iattr = acxt->parent_sd->s_iattr;
+ if (ps_iattr) {
+ struct iattr *ps_iattrs = &ps_iattr->ia_iattr;
+ ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
+ }
- iput(inode);
+ sd->s_flags |= SYSFS_FLAG_REMOVED;
+ sd->u.removed_list = acxt->removed;
+ acxt->removed = sd;
}
/**
*
* Finish up sysfs_dirent add/remove. Resources acquired by
* sysfs_addrm_start() are released and removed sysfs_dirents are
- * cleaned up. Timestamps on the parent inode are updated.
+ * cleaned up.
*
* LOCKING:
- * All mutexes acquired by sysfs_addrm_start() are released.
+ * sysfs_mutex is released.
*/
void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt)
{
/* release resources acquired by sysfs_addrm_start() */
mutex_unlock(&sysfs_mutex);
- if (acxt->parent_inode) {
- struct inode *inode = acxt->parent_inode;
-
- /* if added/removed, update timestamps on the parent */
- if (acxt->cnt)
- inode->i_ctime = inode->i_mtime = CURRENT_TIME;
-
- mutex_unlock(&inode->i_mutex);
- iput(inode);
- }
/* kill removed sysfs_dirents */
while (acxt->removed) {
struct sysfs_dirent *sd = acxt->removed;
- acxt->removed = sd->s_sibling;
- sd->s_sibling = NULL;
+ acxt->removed = sd->u.removed_list;
- sysfs_drop_dentry(sd);
sysfs_deactivate(sd);
+ unmap_bin_file(sd);
sysfs_put(sd);
}
}
* Pointer to sysfs_dirent if found, NULL if not.
*/
struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
+ const void *ns,
const unsigned char *name)
{
- struct sysfs_dirent *sd;
+ struct rb_node *node = parent_sd->s_dir.children.rb_node;
+ unsigned int hash;
- for (sd = parent_sd->s_children; sd; sd = sd->s_sibling)
- if (!strcmp(sd->s_name, name))
+ if (!!sysfs_ns_type(parent_sd) != !!ns) {
+ WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n",
+ sysfs_ns_type(parent_sd)? "required": "invalid",
+ parent_sd->s_name, name);
+ return NULL;
+ }
+
+ hash = sysfs_name_hash(ns, name);
+ while (node) {
+ struct sysfs_dirent *sd;
+ int result;
+
+ sd = to_sysfs_dirent(node);
+ result = sysfs_name_compare(hash, ns, name, sd);
+ if (result < 0)
+ node = node->rb_left;
+ else if (result > 0)
+ node = node->rb_right;
+ else
return sd;
+ }
return NULL;
}
* Pointer to sysfs_dirent if found, NULL if not.
*/
struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
+ const void *ns,
const unsigned char *name)
{
struct sysfs_dirent *sd;
mutex_lock(&sysfs_mutex);
- sd = sysfs_find_dirent(parent_sd, name);
+ sd = sysfs_find_dirent(parent_sd, ns, name);
sysfs_get(sd);
mutex_unlock(&sysfs_mutex);
return sd;
}
+EXPORT_SYMBOL_GPL(sysfs_get_dirent);
static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd,
- const char *name, struct sysfs_dirent **p_sd)
+ enum kobj_ns_type type, const void *ns, const char *name,
+ struct sysfs_dirent **p_sd)
{
umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO;
struct sysfs_addrm_cxt acxt;
sd = sysfs_new_dirent(name, mode, SYSFS_DIR);
if (!sd)
return -ENOMEM;
+
+ sd->s_flags |= (type << SYSFS_NS_TYPE_SHIFT);
+ sd->s_ns = ns;
sd->s_dir.kobj = kobj;
/* link in */
int sysfs_create_subdir(struct kobject *kobj, const char *name,
struct sysfs_dirent **p_sd)
{
- return create_dir(kobj, kobj->sd, name, p_sd);
+ return create_dir(kobj, kobj->sd,
+ KOBJ_NS_TYPE_NONE, NULL, name, p_sd);
+}
+
+/**
+ * sysfs_read_ns_type: return associated ns_type
+ * @kobj: the kobject being queried
+ *
+ * Each kobject can be tagged with exactly one namespace type
+ * (i.e. network or user). Return the ns_type associated with
+ * this object if any
+ */
+static enum kobj_ns_type sysfs_read_ns_type(struct kobject *kobj)
+{
+ const struct kobj_ns_type_operations *ops;
+ enum kobj_ns_type type;
+
+ ops = kobj_child_ns_ops(kobj);
+ if (!ops)
+ return KOBJ_NS_TYPE_NONE;
+
+ type = ops->type;
+ BUG_ON(type <= KOBJ_NS_TYPE_NONE);
+ BUG_ON(type >= KOBJ_NS_TYPES);
+ BUG_ON(!kobj_ns_type_registered(type));
+
+ return type;
}
/**
*/
int sysfs_create_dir(struct kobject * kobj)
{
+ enum kobj_ns_type type;
struct sysfs_dirent *parent_sd, *sd;
+ const void *ns = NULL;
int error = 0;
BUG_ON(!kobj);
else
parent_sd = &sysfs_root;
- error = create_dir(kobj, parent_sd, kobject_name(kobj), &sd);
+ if (!parent_sd)
+ return -ENOENT;
+
+ if (sysfs_ns_type(parent_sd))
+ ns = kobj->ktype->namespace(kobj);
+ type = sysfs_read_ns_type(kobj);
+
+ error = create_dir(kobj, parent_sd, type, ns, kobject_name(kobj), &sd);
if (!error)
kobj->sd = sd;
return error;
}
static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct dentry *ret = NULL;
- struct sysfs_dirent *parent_sd = dentry->d_parent->d_fsdata;
+ struct dentry *parent = dentry->d_parent;
+ struct sysfs_dirent *parent_sd = parent->d_fsdata;
struct sysfs_dirent *sd;
struct inode *inode;
+ enum kobj_ns_type type;
+ const void *ns;
mutex_lock(&sysfs_mutex);
- sd = sysfs_find_dirent(parent_sd, dentry->d_name.name);
+ type = sysfs_ns_type(parent_sd);
+ ns = sysfs_info(dir->i_sb)->ns[type];
+
+ sd = sysfs_find_dirent(parent_sd, ns, dentry->d_name.name);
/* no such entry */
- if (!sd)
+ if (!sd) {
+ ret = ERR_PTR(-ENOENT);
goto out_unlock;
+ }
+ dentry->d_fsdata = sysfs_get(sd);
/* attach dentry and inode */
- inode = sysfs_get_inode(sd);
+ inode = sysfs_get_inode(dir->i_sb, sd);
if (!inode) {
ret = ERR_PTR(-ENOMEM);
goto out_unlock;
}
/* instantiate and hash dentry */
- dentry->d_op = &sysfs_dentry_ops;
- dentry->d_fsdata = sysfs_get(sd);
- d_instantiate(dentry, inode);
- d_rehash(dentry);
-
+ ret = d_materialise_unique(dentry, inode);
out_unlock:
mutex_unlock(&sysfs_mutex);
return ret;
const struct inode_operations sysfs_dir_inode_operations = {
.lookup = sysfs_lookup,
+ .permission = sysfs_permission,
.setattr = sysfs_setattr,
+ .getattr = sysfs_getattr,
+ .setxattr = sysfs_setxattr,
};
static void remove_dir(struct sysfs_dirent *sd)
static void __sysfs_remove_dir(struct sysfs_dirent *dir_sd)
{
struct sysfs_addrm_cxt acxt;
- struct sysfs_dirent **pos;
+ struct rb_node *pos;
if (!dir_sd)
return;
pr_debug("sysfs %s: removing dir\n", dir_sd->s_name);
sysfs_addrm_start(&acxt, dir_sd);
- pos = &dir_sd->s_children;
- while (*pos) {
- struct sysfs_dirent *sd = *pos;
-
+ pos = rb_first(&dir_sd->s_dir.children);
+ while (pos) {
+ struct sysfs_dirent *sd = to_sysfs_dirent(pos);
+ pos = rb_next(pos);
if (sysfs_type(sd) != SYSFS_DIR)
sysfs_remove_one(&acxt, sd);
- else
- pos = &(*pos)->s_sibling;
}
sysfs_addrm_finish(&acxt);
__sysfs_remove_dir(sd);
}
-int sysfs_rename_dir(struct kobject * kobj, const char *new_name)
+int sysfs_rename(struct sysfs_dirent *sd,
+ struct sysfs_dirent *new_parent_sd, const void *new_ns,
+ const char *new_name)
{
- struct sysfs_dirent *sd = kobj->sd;
- struct dentry *parent = NULL;
- struct dentry *old_dentry = NULL, *new_dentry = NULL;
- const char *dup_name = NULL;
int error;
- mutex_lock(&sysfs_rename_mutex);
+ mutex_lock(&sysfs_mutex);
error = 0;
- if (strcmp(sd->s_name, new_name) == 0)
+ if ((sd->s_parent == new_parent_sd) && (sd->s_ns == new_ns) &&
+ (strcmp(sd->s_name, new_name) == 0))
goto out; /* nothing to rename */
- /* get the original dentry */
- old_dentry = sysfs_get_dentry(sd);
- if (IS_ERR(old_dentry)) {
- error = PTR_ERR(old_dentry);
- goto out;
- }
-
- parent = old_dentry->d_parent;
-
- /* lock parent and get dentry for new name */
- mutex_lock(&parent->d_inode->i_mutex);
- mutex_lock(&sysfs_mutex);
-
error = -EEXIST;
- if (sysfs_find_dirent(sd->s_parent, new_name))
- goto out_unlock;
-
- error = -ENOMEM;
- new_dentry = d_alloc_name(parent, new_name);
- if (!new_dentry)
- goto out_unlock;
-
- /* rename kobject and sysfs_dirent */
- error = -ENOMEM;
- new_name = dup_name = kstrdup(new_name, GFP_KERNEL);
- if (!new_name)
- goto out_unlock;
+ if (sysfs_find_dirent(new_parent_sd, new_ns, new_name))
+ goto out;
- error = kobject_set_name(kobj, "%s", new_name);
- if (error)
- goto out_unlock;
+ /* rename sysfs_dirent */
+ if (strcmp(sd->s_name, new_name) != 0) {
+ error = -ENOMEM;
+ new_name = kstrdup(new_name, GFP_KERNEL);
+ if (!new_name)
+ goto out;
- dup_name = sd->s_name;
- sd->s_name = new_name;
+ kfree(sd->s_name);
+ sd->s_name = new_name;
+ }
- /* rename */
- d_add(new_dentry, NULL);
- d_move(old_dentry, new_dentry);
+ /* Move to the appropriate place in the appropriate directories rbtree. */
+ sysfs_unlink_sibling(sd);
+ sysfs_get(new_parent_sd);
+ sysfs_put(sd->s_parent);
+ sd->s_ns = new_ns;
+ sd->s_hash = sysfs_name_hash(sd->s_ns, sd->s_name);
+ sd->s_parent = new_parent_sd;
+ sysfs_link_sibling(sd);
error = 0;
- out_unlock:
- mutex_unlock(&sysfs_mutex);
- mutex_unlock(&parent->d_inode->i_mutex);
- kfree(dup_name);
- dput(old_dentry);
- dput(new_dentry);
out:
- mutex_unlock(&sysfs_rename_mutex);
+ mutex_unlock(&sysfs_mutex);
return error;
}
+int sysfs_rename_dir(struct kobject *kobj, const char *new_name)
+{
+ struct sysfs_dirent *parent_sd = kobj->sd->s_parent;
+ const void *new_ns = NULL;
+
+ if (sysfs_ns_type(parent_sd))
+ new_ns = kobj->ktype->namespace(kobj);
+
+ return sysfs_rename(kobj->sd, parent_sd, new_ns, new_name);
+}
+
int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent_kobj)
{
struct sysfs_dirent *sd = kobj->sd;
struct sysfs_dirent *new_parent_sd;
- struct dentry *old_parent, *new_parent = NULL;
- struct dentry *old_dentry = NULL, *new_dentry = NULL;
- int error;
+ const void *new_ns = NULL;
- mutex_lock(&sysfs_rename_mutex);
BUG_ON(!sd->s_parent);
- new_parent_sd = new_parent_kobj->sd ? new_parent_kobj->sd : &sysfs_root;
+ if (sysfs_ns_type(sd->s_parent))
+ new_ns = kobj->ktype->namespace(kobj);
+ new_parent_sd = new_parent_kobj && new_parent_kobj->sd ?
+ new_parent_kobj->sd : &sysfs_root;
- error = 0;
- if (sd->s_parent == new_parent_sd)
- goto out; /* nothing to move */
+ return sysfs_rename(sd, new_parent_sd, new_ns, sd->s_name);
+}
- /* get dentries */
- old_dentry = sysfs_get_dentry(sd);
- if (IS_ERR(old_dentry)) {
- error = PTR_ERR(old_dentry);
- goto out;
- }
- old_parent = old_dentry->d_parent;
+/* Relationship between s_mode and the DT_xxx types */
+static inline unsigned char dt_type(struct sysfs_dirent *sd)
+{
+ return (sd->s_mode >> 12) & 15;
+}
- new_parent = sysfs_get_dentry(new_parent_sd);
- if (IS_ERR(new_parent)) {
- error = PTR_ERR(new_parent);
- goto out;
- }
+static int sysfs_dir_release(struct inode *inode, struct file *filp)
+{
+ sysfs_put(filp->private_data);
+ return 0;
+}
-again:
- mutex_lock(&old_parent->d_inode->i_mutex);
- if (!mutex_trylock(&new_parent->d_inode->i_mutex)) {
- mutex_unlock(&old_parent->d_inode->i_mutex);
- goto again;
+static struct sysfs_dirent *sysfs_dir_pos(const void *ns,
+ struct sysfs_dirent *parent_sd, loff_t hash, struct sysfs_dirent *pos)
+{
+ if (pos) {
+ int valid = !(pos->s_flags & SYSFS_FLAG_REMOVED) &&
+ pos->s_parent == parent_sd &&
+ hash == pos->s_hash;
+ sysfs_put(pos);
+ if (!valid)
+ pos = NULL;
}
- mutex_lock(&sysfs_mutex);
-
- error = -EEXIST;
- if (sysfs_find_dirent(new_parent_sd, sd->s_name))
- goto out_unlock;
-
- error = -ENOMEM;
- new_dentry = d_alloc_name(new_parent, sd->s_name);
- if (!new_dentry)
- goto out_unlock;
-
- error = 0;
- d_add(new_dentry, NULL);
- d_move(old_dentry, new_dentry);
- dput(new_dentry);
-
- /* Remove from old parent's list and insert into new parent's list. */
- sysfs_unlink_sibling(sd);
- sysfs_get(new_parent_sd);
- sysfs_put(sd->s_parent);
- sd->s_parent = new_parent_sd;
- sysfs_link_sibling(sd);
-
- out_unlock:
- mutex_unlock(&sysfs_mutex);
- mutex_unlock(&new_parent->d_inode->i_mutex);
- mutex_unlock(&old_parent->d_inode->i_mutex);
- out:
- dput(new_parent);
- dput(old_dentry);
- dput(new_dentry);
- mutex_unlock(&sysfs_rename_mutex);
- return error;
+ if (!pos && (hash > 1) && (hash < INT_MAX)) {
+ struct rb_node *node = parent_sd->s_dir.children.rb_node;
+ while (node) {
+ pos = to_sysfs_dirent(node);
+
+ if (hash < pos->s_hash)
+ node = node->rb_left;
+ else if (hash > pos->s_hash)
+ node = node->rb_right;
+ else
+ break;
+ }
+ }
+ /* Skip over entries in the wrong namespace */
+ while (pos && pos->s_ns != ns) {
+ struct rb_node *node = rb_next(&pos->s_rb);
+ if (!node)
+ pos = NULL;
+ else
+ pos = to_sysfs_dirent(node);
+ }
+ return pos;
}
-/* Relationship between s_mode and the DT_xxx types */
-static inline unsigned char dt_type(struct sysfs_dirent *sd)
+static struct sysfs_dirent *sysfs_dir_next_pos(const void *ns,
+ struct sysfs_dirent *parent_sd, ino_t ino, struct sysfs_dirent *pos)
{
- return (sd->s_mode >> 12) & 15;
+ pos = sysfs_dir_pos(ns, parent_sd, ino, pos);
+ if (pos) do {
+ struct rb_node *node = rb_next(&pos->s_rb);
+ if (!node)
+ pos = NULL;
+ else
+ pos = to_sysfs_dirent(node);
+ } while (pos && pos->s_ns != ns);
+ return pos;
}
static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
struct dentry *dentry = filp->f_path.dentry;
struct sysfs_dirent * parent_sd = dentry->d_fsdata;
- struct sysfs_dirent *pos;
+ struct sysfs_dirent *pos = filp->private_data;
+ enum kobj_ns_type type;
+ const void *ns;
ino_t ino;
+ type = sysfs_ns_type(parent_sd);
+ ns = sysfs_info(dentry->d_sb)->ns[type];
+
if (filp->f_pos == 0) {
ino = parent_sd->s_ino;
if (filldir(dirent, ".", 1, filp->f_pos, ino, DT_DIR) == 0)
if (filldir(dirent, "..", 2, filp->f_pos, ino, DT_DIR) == 0)
filp->f_pos++;
}
- if ((filp->f_pos > 1) && (filp->f_pos < INT_MAX)) {
- mutex_lock(&sysfs_mutex);
-
- /* Skip the dentries we have already reported */
- pos = parent_sd->s_children;
- while (pos && (filp->f_pos > pos->s_ino))
- pos = pos->s_sibling;
-
- for ( ; pos; pos = pos->s_sibling) {
- const char * name;
- int len;
-
- name = pos->s_name;
- len = strlen(name);
- filp->f_pos = ino = pos->s_ino;
+ mutex_lock(&sysfs_mutex);
+ for (pos = sysfs_dir_pos(ns, parent_sd, filp->f_pos, pos);
+ pos;
+ pos = sysfs_dir_next_pos(ns, parent_sd, filp->f_pos, pos)) {
+ const char * name;
+ unsigned int type;
+ int len, ret;
+
+ name = pos->s_name;
+ len = strlen(name);
+ ino = pos->s_ino;
+ type = dt_type(pos);
+ filp->f_pos = pos->s_hash;
+ filp->private_data = sysfs_get(pos);
- if (filldir(dirent, name, len, filp->f_pos, ino,
- dt_type(pos)) < 0)
- break;
- }
- if (!pos)
- filp->f_pos = INT_MAX;
mutex_unlock(&sysfs_mutex);
+ ret = filldir(dirent, name, len, filp->f_pos, ino, type);
+ mutex_lock(&sysfs_mutex);
+ if (ret < 0)
+ break;
+ }
+ mutex_unlock(&sysfs_mutex);
+ if ((filp->f_pos > 1) && !pos) { /* EOF */
+ filp->f_pos = INT_MAX;
+ filp->private_data = NULL;
}
return 0;
}
+static loff_t sysfs_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+ struct inode *inode = file_inode(file);
+ loff_t ret;
+
+ mutex_lock(&inode->i_mutex);
+ ret = generic_file_llseek(file, offset, whence);
+ mutex_unlock(&inode->i_mutex);
+
+ return ret;
+}
const struct file_operations sysfs_dir_operations = {
.read = generic_read_dir,
.readdir = sysfs_readdir,
+ .release = sysfs_dir_release,
+ .llseek = sysfs_dir_llseek,
};