#include <linux/rculist_bl.h>
#include <linux/prefetch.h>
#include <linux/ratelimit.h>
+#include <linux/list_lru.h>
#include "internal.h"
#include "mount.h"
* - the dcache hash table
* s_anon bl list spinlock protects:
* - the s_anon list (see __d_drop)
- * dcache_lru_lock protects:
+ * dentry->d_sb->s_dentry_lru_lock protects:
* - the dcache lru lists and counters
* d_lock protects:
* - d_flags
* Ordering:
* dentry->d_inode->i_lock
* dentry->d_lock
- * dcache_lru_lock
+ * dentry->d_sb->s_dentry_lru_lock
* dcache_hash_bucket lock
* s_anon lock
*
int sysctl_vfs_cache_pressure __read_mostly = 100;
EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);
-static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lru_lock);
__cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
EXPORT_SYMBOL(rename_lock);
.age_limit = 45,
};
-static DEFINE_PER_CPU(unsigned int, nr_dentry);
+static DEFINE_PER_CPU(long, nr_dentry);
+static DEFINE_PER_CPU(long, nr_dentry_unused);
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
-static int get_nr_dentry(void)
+
+/*
+ * Here we resort to our own counters instead of using generic per-cpu counters
+ * for consistency with what the vfs inode code does. We are expected to harvest
+ * better code and performance by having our own specialized counters.
+ *
+ * Please note that the loop is done over all possible CPUs, not over all online
+ * CPUs. The reason for this is that we don't want to play games with CPUs going
+ * on and off. If one of them goes off, we will just keep their counters.
+ *
+ * glommer: See cffbc8a for details, and if you ever intend to change this,
+ * please update all vfs counters to match.
+ */
+static long get_nr_dentry(void)
{
int i;
- int sum = 0;
+ long sum = 0;
for_each_possible_cpu(i)
sum += per_cpu(nr_dentry, i);
return sum < 0 ? 0 : sum;
}
+static long get_nr_dentry_unused(void)
+{
+ int i;
+ long sum = 0;
+ for_each_possible_cpu(i)
+ sum += per_cpu(nr_dentry_unused, i);
+ return sum < 0 ? 0 : sum;
+}
+
int proc_nr_dentry(ctl_table *table, int write, void __user *buffer,
size_t *lenp, loff_t *ppos)
{
dentry_stat.nr_dentry = get_nr_dentry();
- return proc_dointvec(table, write, buffer, lenp, ppos);
+ dentry_stat.nr_unused = get_nr_dentry_unused();
+ return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
#endif
}
/*
- * dentry_lru_(add|del|prune|move_tail) must be called with d_lock held.
+ * The DCACHE_LRU_LIST bit is set whenever the 'd_lru' entry
+ * is in use - which includes both the "real" per-superblock
+ * LRU list _and_ the DCACHE_SHRINK_LIST use.
+ *
+ * The DCACHE_SHRINK_LIST bit is set whenever the dentry is
+ * on the shrink list (ie not on the superblock LRU list).
+ *
+ * The per-cpu "nr_dentry_unused" counters are updated with
+ * the DCACHE_LRU_LIST bit.
+ *
+ * These helper functions make sure we always follow the
+ * rules. d_lock must be held by the caller.
*/
-static void dentry_lru_add(struct dentry *dentry)
+#define D_FLAG_VERIFY(dentry,x) WARN_ON_ONCE(((dentry)->d_flags & (DCACHE_LRU_LIST | DCACHE_SHRINK_LIST)) != (x))
+static void d_lru_add(struct dentry *dentry)
{
- if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST))) {
- spin_lock(&dcache_lru_lock);
- dentry->d_flags |= DCACHE_LRU_LIST;
- list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
- dentry->d_sb->s_nr_dentry_unused++;
- dentry_stat.nr_unused++;
- spin_unlock(&dcache_lru_lock);
- }
+ D_FLAG_VERIFY(dentry, 0);
+ dentry->d_flags |= DCACHE_LRU_LIST;
+ this_cpu_inc(nr_dentry_unused);
+ WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
}
-static void __dentry_lru_del(struct dentry *dentry)
+static void d_lru_del(struct dentry *dentry)
{
+ D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
+ dentry->d_flags &= ~DCACHE_LRU_LIST;
+ this_cpu_dec(nr_dentry_unused);
+ WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
+}
+
+static void d_shrink_del(struct dentry *dentry)
+{
+ D_FLAG_VERIFY(dentry, DCACHE_SHRINK_LIST | DCACHE_LRU_LIST);
list_del_init(&dentry->d_lru);
dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST);
- dentry->d_sb->s_nr_dentry_unused--;
- dentry_stat.nr_unused--;
+ this_cpu_dec(nr_dentry_unused);
+}
+
+static void d_shrink_add(struct dentry *dentry, struct list_head *list)
+{
+ D_FLAG_VERIFY(dentry, 0);
+ list_add(&dentry->d_lru, list);
+ dentry->d_flags |= DCACHE_SHRINK_LIST | DCACHE_LRU_LIST;
+ this_cpu_inc(nr_dentry_unused);
}
/*
- * Remove a dentry with references from the LRU.
+ * These can only be called under the global LRU lock, ie during the
+ * callback for freeing the LRU list. "isolate" removes it from the
+ * LRU lists entirely, while shrink_move moves it to the indicated
+ * private list.
*/
-static void dentry_lru_del(struct dentry *dentry)
+static void d_lru_isolate(struct dentry *dentry)
{
- if (!list_empty(&dentry->d_lru)) {
- spin_lock(&dcache_lru_lock);
- __dentry_lru_del(dentry);
- spin_unlock(&dcache_lru_lock);
- }
+ D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
+ dentry->d_flags &= ~DCACHE_LRU_LIST;
+ this_cpu_dec(nr_dentry_unused);
+ list_del_init(&dentry->d_lru);
}
-static void dentry_lru_move_list(struct dentry *dentry, struct list_head *list)
+static void d_lru_shrink_move(struct dentry *dentry, struct list_head *list)
{
- spin_lock(&dcache_lru_lock);
- if (list_empty(&dentry->d_lru)) {
- dentry->d_flags |= DCACHE_LRU_LIST;
- 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, list);
+ D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
+ dentry->d_flags |= DCACHE_SHRINK_LIST;
+ list_move_tail(&dentry->d_lru, list);
+}
+
+/*
+ * dentry_lru_(add|del)_list) must be called with d_lock held.
+ */
+static void dentry_lru_add(struct dentry *dentry)
+{
+ if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST)))
+ d_lru_add(dentry);
+}
+
+/*
+ * Remove a dentry with references from the LRU.
+ *
+ * If we are on the shrink list, then we can get to try_prune_one_dentry() and
+ * lose our last reference through the parent walk. In this case, we need to
+ * remove ourselves from the shrink list, not the LRU.
+ */
+static void dentry_lru_del(struct dentry *dentry)
+{
+ if (dentry->d_flags & DCACHE_LRU_LIST) {
+ if (dentry->d_flags & DCACHE_SHRINK_LIST)
+ return d_shrink_del(dentry);
+ d_lru_del(dentry);
}
- spin_unlock(&dcache_lru_lock);
}
/**
* If ref is non-zero, then decrement the refcount too.
* Returns dentry requiring refcount drop, or NULL if we're done.
*/
-static inline struct dentry *dentry_kill(struct dentry *dentry)
+static inline struct dentry *
+dentry_kill(struct dentry *dentry, int unlock_on_failure)
__releases(dentry->d_lock)
{
struct inode *inode;
inode = dentry->d_inode;
if (inode && !spin_trylock(&inode->i_lock)) {
relock:
- spin_unlock(&dentry->d_lock);
- cpu_relax();
+ if (unlock_on_failure) {
+ spin_unlock(&dentry->d_lock);
+ cpu_relax();
+ }
return dentry; /* try again with same dentry */
}
if (IS_ROOT(dentry))
return;
kill_it:
- dentry = dentry_kill(dentry);
+ dentry = dentry_kill(dentry, 1);
if (dentry)
goto repeat;
}
*
* This may fail if locks cannot be acquired no problem, just try again.
*/
-static void try_prune_one_dentry(struct dentry *dentry)
+static struct dentry * try_prune_one_dentry(struct dentry *dentry)
__releases(dentry->d_lock)
{
struct dentry *parent;
- parent = dentry_kill(dentry);
+ parent = dentry_kill(dentry, 0);
/*
* If dentry_kill returns NULL, we have nothing more to do.
* if it returns the same dentry, trylocks failed. In either
* fragmentation.
*/
if (!parent)
- return;
+ return NULL;
if (parent == dentry)
- return;
+ return dentry;
/* Prune ancestors. */
dentry = parent;
while (dentry) {
if (lockref_put_or_lock(&dentry->d_lockref))
- return;
- dentry = dentry_kill(dentry);
+ return NULL;
+ dentry = dentry_kill(dentry, 1);
}
+ return NULL;
}
static void shrink_dentry_list(struct list_head *list)
dentry = list_entry_rcu(list->prev, struct dentry, d_lru);
if (&dentry->d_lru == list)
break; /* empty */
+
+ /*
+ * Get the dentry lock, and re-verify that the dentry is
+ * this on the shrinking list. If it is, we know that
+ * DCACHE_SHRINK_LIST and DCACHE_LRU_LIST are set.
+ */
spin_lock(&dentry->d_lock);
if (dentry != list_entry(list->prev, struct dentry, d_lru)) {
spin_unlock(&dentry->d_lock);
}
/*
+ * The dispose list is isolated and dentries are not accounted
+ * to the LRU here, so we can simply remove it from the list
+ * here regardless of whether it is referenced or not.
+ */
+ d_shrink_del(dentry);
+
+ /*
* We found an inuse dentry which was not removed from
- * the LRU because of laziness during lookup. Do not free
- * it - just keep it off the LRU list.
+ * the LRU because of laziness during lookup. Do not free it.
*/
if (dentry->d_lockref.count) {
- dentry_lru_del(dentry);
spin_unlock(&dentry->d_lock);
continue;
}
-
rcu_read_unlock();
- try_prune_one_dentry(dentry);
+ /*
+ * If 'try_to_prune()' returns a dentry, it will
+ * be the same one we passed in, and d_lock will
+ * have been held the whole time, so it will not
+ * have been added to any other lists. We failed
+ * to get the inode lock.
+ *
+ * We just add it back to the shrink list.
+ */
+ dentry = try_prune_one_dentry(dentry);
rcu_read_lock();
+ if (dentry) {
+ d_shrink_add(dentry, list);
+ spin_unlock(&dentry->d_lock);
+ }
}
rcu_read_unlock();
}
+static enum lru_status
+dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
+{
+ struct list_head *freeable = arg;
+ struct dentry *dentry = container_of(item, struct dentry, d_lru);
+
+
+ /*
+ * we are inverting the lru lock/dentry->d_lock here,
+ * so use a trylock. If we fail to get the lock, just skip
+ * it
+ */
+ if (!spin_trylock(&dentry->d_lock))
+ return LRU_SKIP;
+
+ /*
+ * Referenced dentries are still in use. If they have active
+ * counts, just remove them from the LRU. Otherwise give them
+ * another pass through the LRU.
+ */
+ if (dentry->d_lockref.count) {
+ d_lru_isolate(dentry);
+ spin_unlock(&dentry->d_lock);
+ return LRU_REMOVED;
+ }
+
+ if (dentry->d_flags & DCACHE_REFERENCED) {
+ dentry->d_flags &= ~DCACHE_REFERENCED;
+ spin_unlock(&dentry->d_lock);
+
+ /*
+ * The list move itself will be made by the common LRU code. At
+ * this point, we've dropped the dentry->d_lock but keep the
+ * lru lock. This is safe to do, since every list movement is
+ * protected by the lru lock even if both locks are held.
+ *
+ * This is guaranteed by the fact that all LRU management
+ * functions are intermediated by the LRU API calls like
+ * list_lru_add and list_lru_del. List movement in this file
+ * only ever occur through this functions or through callbacks
+ * like this one, that are called from the LRU API.
+ *
+ * The only exceptions to this are functions like
+ * shrink_dentry_list, and code that first checks for the
+ * DCACHE_SHRINK_LIST flag. Those are guaranteed to be
+ * operating only with stack provided lists after they are
+ * properly isolated from the main list. It is thus, always a
+ * local access.
+ */
+ return LRU_ROTATE;
+ }
+
+ d_lru_shrink_move(dentry, freeable);
+ spin_unlock(&dentry->d_lock);
+
+ return LRU_REMOVED;
+}
+
/**
* prune_dcache_sb - shrink the dcache
* @sb: superblock
- * @count: number of entries to try to free
+ * @nr_to_scan : number of entries to try to free
+ * @nid: which node to scan for freeable entities
*
- * Attempt to shrink the superblock dcache LRU by @count entries. This is
+ * 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 count)
+long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan,
+ int nid)
{
- struct dentry *dentry;
- LIST_HEAD(referenced);
- LIST_HEAD(tmp);
+ LIST_HEAD(dispose);
+ long freed;
-relock:
- spin_lock(&dcache_lru_lock);
- while (!list_empty(&sb->s_dentry_lru)) {
- dentry = list_entry(sb->s_dentry_lru.prev,
- struct dentry, d_lru);
- BUG_ON(dentry->d_sb != sb);
-
- if (!spin_trylock(&dentry->d_lock)) {
- spin_unlock(&dcache_lru_lock);
- cpu_relax();
- goto relock;
- }
+ freed = list_lru_walk_node(&sb->s_dentry_lru, nid, dentry_lru_isolate,
+ &dispose, &nr_to_scan);
+ shrink_dentry_list(&dispose);
+ return freed;
+}
- 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;
- }
- cond_resched_lock(&dcache_lru_lock);
- }
- if (!list_empty(&referenced))
- list_splice(&referenced, &sb->s_dentry_lru);
- spin_unlock(&dcache_lru_lock);
+static enum lru_status dentry_lru_isolate_shrink(struct list_head *item,
+ spinlock_t *lru_lock, void *arg)
+{
+ struct list_head *freeable = arg;
+ struct dentry *dentry = container_of(item, struct dentry, d_lru);
+
+ /*
+ * we are inverting the lru lock/dentry->d_lock here,
+ * so use a trylock. If we fail to get the lock, just skip
+ * it
+ */
+ if (!spin_trylock(&dentry->d_lock))
+ return LRU_SKIP;
+
+ d_lru_shrink_move(dentry, freeable);
+ spin_unlock(&dentry->d_lock);
- shrink_dentry_list(&tmp);
+ return LRU_REMOVED;
}
+
/**
* shrink_dcache_sb - shrink dcache for a superblock
* @sb: superblock
*/
void shrink_dcache_sb(struct super_block *sb)
{
- LIST_HEAD(tmp);
+ long freed;
- spin_lock(&dcache_lru_lock);
- while (!list_empty(&sb->s_dentry_lru)) {
- list_splice_init(&sb->s_dentry_lru, &tmp);
- spin_unlock(&dcache_lru_lock);
- shrink_dentry_list(&tmp);
- spin_lock(&dcache_lru_lock);
- }
- spin_unlock(&dcache_lru_lock);
+ do {
+ LIST_HEAD(dispose);
+
+ freed = list_lru_walk(&sb->s_dentry_lru,
+ dentry_lru_isolate_shrink, &dispose, UINT_MAX);
+
+ this_cpu_sub(nr_dentry_unused, freed);
+ shrink_dentry_list(&dispose);
+ } while (freed > 0);
}
EXPORT_SYMBOL(shrink_dcache_sb);
if (dentry->d_lockref.count) {
dentry_lru_del(dentry);
} else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
- dentry_lru_move_list(dentry, &data->dispose);
- dentry->d_flags |= DCACHE_SHRINK_LIST;
+ /*
+ * We can't use d_lru_shrink_move() because we
+ * need to get the global LRU lock and do the
+ * LRU accounting.
+ */
+ d_lru_del(dentry);
+ d_shrink_add(dentry, &data->dispose);
data->found++;
ret = D_WALK_NORETRY;
}
return prepend(buffer, buflen, "(unreachable)", 13);
}
+static void get_fs_root_rcu(struct fs_struct *fs, struct path *root)
+{
+ unsigned seq;
+
+ do {
+ seq = read_seqcount_begin(&fs->seq);
+ *root = fs->root;
+ } while (read_seqcount_retry(&fs->seq, seq));
+}
+
/**
* d_path - return the path of a dentry
* @path: path to report
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);
+ rcu_read_lock();
+ get_fs_root_rcu(current->fs, &root);
br_read_lock(&vfsmount_lock);
error = path_with_deleted(path, &root, &res, &buflen);
br_read_unlock(&vfsmount_lock);
+ rcu_read_unlock();
+
if (error < 0)
res = ERR_PTR(error);
- path_put(&root);
return res;
}
EXPORT_SYMBOL(d_path);
return ERR_PTR(-ENAMETOOLONG);
}
-static inline void get_fs_root_and_pwd(struct fs_struct *fs, struct path *root,
- struct path *pwd)
+static void get_fs_root_and_pwd_rcu(struct fs_struct *fs, struct path *root,
+ struct path *pwd)
{
- spin_lock(&fs->lock);
- *root = fs->root;
- path_get(root);
- *pwd = fs->pwd;
- path_get(pwd);
- spin_unlock(&fs->lock);
+ unsigned seq;
+
+ do {
+ seq = read_seqcount_begin(&fs->seq);
+ *root = fs->root;
+ *pwd = fs->pwd;
+ } while (read_seqcount_retry(&fs->seq, seq));
}
/*
{
int error;
struct path pwd, root;
- char *page = (char *) __get_free_page(GFP_USER);
+ char *page = __getname();
if (!page)
return -ENOMEM;
- get_fs_root_and_pwd(current->fs, &root, &pwd);
+ rcu_read_lock();
+ get_fs_root_and_pwd_rcu(current->fs, &root, &pwd);
error = -ENOENT;
br_read_lock(&vfsmount_lock);
if (!d_unlinked(pwd.dentry)) {
unsigned long len;
- char *cwd = page + PAGE_SIZE;
- int buflen = PAGE_SIZE;
+ char *cwd = page + PATH_MAX;
+ int buflen = PATH_MAX;
prepend(&cwd, &buflen, "\0", 1);
error = prepend_path(&pwd, &root, &cwd, &buflen);
br_read_unlock(&vfsmount_lock);
+ rcu_read_unlock();
if (error < 0)
goto out;
}
error = -ERANGE;
- len = PAGE_SIZE + page - cwd;
+ len = PATH_MAX + page - cwd;
if (len <= size) {
error = len;
if (copy_to_user(buf, cwd, len))
}
} else {
br_read_unlock(&vfsmount_lock);
+ rcu_read_unlock();
}
out:
- path_put(&pwd);
- path_put(&root);
- free_page((unsigned long) page);
+ __putname(page);
return error;
}