* A check for whether or not the parent directory has changed.
* In the case it has, we assume that the dentries are untrustworthy
* and may need to be looked up again.
+ * If rcu_walk prevents us from performing a full check, return 0.
*/
-static int nfs_check_verifier(struct inode *dir, struct dentry *dentry)
+static int nfs_check_verifier(struct inode *dir, struct dentry *dentry,
+ int rcu_walk)
{
+ int ret;
+
if (IS_ROOT(dentry))
return 1;
if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONE)
if (!nfs_verify_change_attribute(dir, dentry->d_time))
return 0;
/* Revalidate nfsi->cache_change_attribute before we declare a match */
- if (nfs_revalidate_inode(NFS_SERVER(dir), dir) < 0)
+ if (rcu_walk)
+ ret = nfs_revalidate_inode_rcu(NFS_SERVER(dir), dir);
+ else
+ ret = nfs_revalidate_inode(NFS_SERVER(dir), dir);
+ if (ret < 0)
return 0;
if (!nfs_verify_change_attribute(dir, dentry->d_time))
return 0;
out:
return (inode->i_nlink == 0) ? -ENOENT : 0;
out_force:
+ if (flags & LOOKUP_RCU)
+ return -ECHILD;
ret = __nfs_revalidate_inode(server, inode);
if (ret != 0)
return ret;
*
* If parent mtime has changed, we revalidate, else we wait for a
* period corresponding to the parent's attribute cache timeout value.
+ *
+ * If LOOKUP_RCU prevents us from performing a full check, return 1
+ * suggesting a reval is needed.
*/
static inline
int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry,
return 0;
if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG)
return 1;
- return !nfs_check_verifier(dir, dentry);
+ return !nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU);
}
/*
struct nfs4_label *label = NULL;
int error;
- if (flags & LOOKUP_RCU)
- return -ECHILD;
-
- parent = dget_parent(dentry);
- dir = parent->d_inode;
+ if (flags & LOOKUP_RCU) {
+ parent = ACCESS_ONCE(dentry->d_parent);
+ dir = ACCESS_ONCE(parent->d_inode);
+ if (!dir)
+ return -ECHILD;
+ } else {
+ parent = dget_parent(dentry);
+ dir = parent->d_inode;
+ }
nfs_inc_stats(dir, NFSIOS_DENTRYREVALIDATE);
inode = dentry->d_inode;
if (!inode) {
- if (nfs_neg_need_reval(dir, dentry, flags))
+ if (nfs_neg_need_reval(dir, dentry, flags)) {
+ if (flags & LOOKUP_RCU)
+ return -ECHILD;
goto out_bad;
+ }
goto out_valid_noent;
}
if (is_bad_inode(inode)) {
+ if (flags & LOOKUP_RCU)
+ return -ECHILD;
dfprintk(LOOKUPCACHE, "%s: %pd2 has dud inode\n",
__func__, dentry);
goto out_bad;
goto out_set_verifier;
/* Force a full look up iff the parent directory has changed */
- if (!nfs_is_exclusive_create(dir, flags) && nfs_check_verifier(dir, dentry)) {
- if (nfs_lookup_verify_inode(inode, flags))
+ if (!nfs_is_exclusive_create(dir, flags) &&
+ nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) {
+
+ if (nfs_lookup_verify_inode(inode, flags)) {
+ if (flags & LOOKUP_RCU)
+ return -ECHILD;
goto out_zap_parent;
+ }
goto out_valid;
}
+ if (flags & LOOKUP_RCU)
+ return -ECHILD;
+
if (NFS_STALE(inode))
goto out_bad;
/* Success: notify readdir to use READDIRPLUS */
nfs_advise_use_readdirplus(dir);
out_valid_noent:
- dput(parent);
+ if (flags & LOOKUP_RCU) {
+ if (parent != ACCESS_ONCE(dentry->d_parent))
+ return -ECHILD;
+ } else
+ dput(parent);
dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is valid\n",
__func__, dentry);
return 1;
out_zap_parent:
nfs_zap_caches(dir);
out_bad:
+ WARN_ON(flags & LOOKUP_RCU);
nfs_free_fattr(fattr);
nfs_free_fhandle(fhandle);
nfs4_label_free(label);
__func__, dentry);
return 0;
out_error:
+ WARN_ON(flags & LOOKUP_RCU);
nfs_free_fattr(fattr);
nfs_free_fhandle(fhandle);
nfs4_label_free(label);
static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags)
{
- struct dentry *parent = NULL;
struct inode *inode;
- struct inode *dir;
int ret = 0;
- if (flags & LOOKUP_RCU)
- return -ECHILD;
-
if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY))
goto no_open;
if (d_mountpoint(dentry))
goto no_open;
inode = dentry->d_inode;
- parent = dget_parent(dentry);
- dir = parent->d_inode;
/* We can't create new files in nfs_open_revalidate(), so we
* optimize away revalidation of negative dentries.
*/
if (inode == NULL) {
+ struct dentry *parent;
+ struct inode *dir;
+
+ if (flags & LOOKUP_RCU) {
+ parent = ACCESS_ONCE(dentry->d_parent);
+ dir = ACCESS_ONCE(parent->d_inode);
+ if (!dir)
+ return -ECHILD;
+ } else {
+ parent = dget_parent(dentry);
+ dir = parent->d_inode;
+ }
if (!nfs_neg_need_reval(dir, dentry, flags))
ret = 1;
+ else if (flags & LOOKUP_RCU)
+ ret = -ECHILD;
+ if (!(flags & LOOKUP_RCU))
+ dput(parent);
+ else if (parent != ACCESS_ONCE(dentry->d_parent))
+ return -ECHILD;
goto out;
}
/* NFS only supports OPEN on regular files */
if (!S_ISREG(inode->i_mode))
- goto no_open_dput;
+ goto no_open;
/* We cannot do exclusive creation on a positive dentry */
if (flags & LOOKUP_EXCL)
- goto no_open_dput;
+ goto no_open;
/* Let f_op->open() actually open (and revalidate) the file */
ret = 1;
out:
- dput(parent);
return ret;
-no_open_dput:
- dput(parent);
no_open:
return nfs_lookup_revalidate(dentry, flags);
}
static LIST_HEAD(nfs_access_lru_list);
static atomic_long_t nfs_access_nr_entries;
+static unsigned long nfs_access_max_cachesize = ULONG_MAX;
+module_param(nfs_access_max_cachesize, ulong, 0644);
+MODULE_PARM_DESC(nfs_access_max_cachesize, "NFS access maximum total cache length");
+
static void nfs_access_free_entry(struct nfs_access_entry *entry)
{
put_rpccred(entry->cred);
- kfree(entry);
+ kfree_rcu(entry, rcu_head);
smp_mb__before_atomic();
atomic_long_dec(&nfs_access_nr_entries);
smp_mb__after_atomic();
}
}
-unsigned long
-nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
+static unsigned long
+nfs_do_access_cache_scan(unsigned int nr_to_scan)
{
LIST_HEAD(head);
struct nfs_inode *nfsi, *next;
struct nfs_access_entry *cache;
- int nr_to_scan = sc->nr_to_scan;
- gfp_t gfp_mask = sc->gfp_mask;
long freed = 0;
- if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL)
- return SHRINK_STOP;
-
spin_lock(&nfs_access_lru_lock);
list_for_each_entry_safe(nfsi, next, &nfs_access_lru_list, access_cache_inode_lru) {
struct inode *inode;
return freed;
}
+unsigned long
+nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+ int nr_to_scan = sc->nr_to_scan;
+ gfp_t gfp_mask = sc->gfp_mask;
+
+ if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL)
+ return SHRINK_STOP;
+ return nfs_do_access_cache_scan(nr_to_scan);
+}
+
+
unsigned long
nfs_access_cache_count(struct shrinker *shrink, struct shrink_control *sc)
{
return vfs_pressure_ratio(atomic_long_read(&nfs_access_nr_entries));
}
+static void
+nfs_access_cache_enforce_limit(void)
+{
+ long nr_entries = atomic_long_read(&nfs_access_nr_entries);
+ unsigned long diff;
+ unsigned int nr_to_scan;
+
+ if (nr_entries < 0 || nr_entries <= nfs_access_max_cachesize)
+ return;
+ nr_to_scan = 100;
+ diff = nr_entries - nfs_access_max_cachesize;
+ if (diff < nr_to_scan)
+ nr_to_scan = diff;
+ nfs_do_access_cache_scan(nr_to_scan);
+}
+
static void __nfs_access_zap_cache(struct nfs_inode *nfsi, struct list_head *head)
{
struct rb_root *root_node = &nfsi->access_cache;
return -ENOENT;
}
+static int nfs_access_get_cached_rcu(struct inode *inode, struct rpc_cred *cred, struct nfs_access_entry *res)
+{
+ /* Only check the most recently returned cache entry,
+ * but do it without locking.
+ */
+ struct nfs_inode *nfsi = NFS_I(inode);
+ struct nfs_access_entry *cache;
+ int err = -ECHILD;
+ struct list_head *lh;
+
+ rcu_read_lock();
+ if (nfsi->cache_validity & NFS_INO_INVALID_ACCESS)
+ goto out;
+ lh = rcu_dereference(nfsi->access_cache_entry_lru.prev);
+ cache = list_entry(lh, struct nfs_access_entry, lru);
+ if (lh == &nfsi->access_cache_entry_lru ||
+ cred != cache->cred)
+ cache = NULL;
+ if (cache == NULL)
+ goto out;
+ if (!nfs_have_delegated_attributes(inode) &&
+ !time_in_range_open(jiffies, cache->jiffies, cache->jiffies + nfsi->attrtimeo))
+ goto out;
+ res->jiffies = cache->jiffies;
+ res->cred = cache->cred;
+ res->mask = cache->mask;
+ err = 0;
+out:
+ rcu_read_unlock();
+ return err;
+}
+
static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry *set)
{
struct nfs_inode *nfsi = NFS_I(inode);
cache->cred = get_rpccred(set->cred);
cache->mask = set->mask;
+ /* The above field assignments must be visible
+ * before this item appears on the lru. We cannot easily
+ * use rcu_assign_pointer, so just force the memory barrier.
+ */
+ smp_wmb();
nfs_access_add_rbtree(inode, cache);
/* Update accounting */
&nfs_access_lru_list);
spin_unlock(&nfs_access_lru_lock);
}
+ nfs_access_cache_enforce_limit();
}
EXPORT_SYMBOL_GPL(nfs_access_add_cache);
trace_nfs_access_enter(inode);
- status = nfs_access_get_cached(inode, cred, &cache);
+ status = nfs_access_get_cached_rcu(inode, cred, &cache);
+ if (status != 0)
+ status = nfs_access_get_cached(inode, cred, &cache);
if (status == 0)
goto out_cached;
+ status = -ECHILD;
+ if (mask & MAY_NOT_BLOCK)
+ goto out;
+
/* Be clever: ask server to check for all possible rights */
cache.mask = MAY_EXEC | MAY_WRITE | MAY_READ;
cache.cred = cred;
struct rpc_cred *cred;
int res = 0;
- if (mask & MAY_NOT_BLOCK)
- return -ECHILD;
-
nfs_inc_stats(inode, NFSIOS_VFSACCESS);
if ((mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0)
if (!NFS_PROTO(inode)->access)
goto out_notsup;
- cred = rpc_lookup_cred();
- if (!IS_ERR(cred)) {
- res = nfs_do_access(inode, cred, mask);
- put_rpccred(cred);
- } else
+ /* Always try fast lookups first */
+ rcu_read_lock();
+ cred = rpc_lookup_cred_nonblock();
+ if (!IS_ERR(cred))
+ res = nfs_do_access(inode, cred, mask|MAY_NOT_BLOCK);
+ else
res = PTR_ERR(cred);
+ rcu_read_unlock();
+ if (res == -ECHILD && !(mask & MAY_NOT_BLOCK)) {
+ /* Fast lookup failed, try the slow way */
+ cred = rpc_lookup_cred();
+ if (!IS_ERR(cred)) {
+ res = nfs_do_access(inode, cred, mask);
+ put_rpccred(cred);
+ } else
+ res = PTR_ERR(cred);
+ }
out:
if (!res && (mask & MAY_EXEC) && !execute_ok(inode))
res = -EACCES;
inode->i_sb->s_id, inode->i_ino, mask, res);
return res;
out_notsup:
+ if (mask & MAY_NOT_BLOCK)
+ return -ECHILD;
+
res = nfs_revalidate_inode(NFS_SERVER(inode), inode);
if (res == 0)
res = generic_permission(inode, mask);
projects / karo-tx-linux.git / blobdiff